Insights
Use the endpoints described below to generate and interpret insights for specific models.
Data slices bulk deletion
Operation path: DELETE /api/v2/dataSlices/
Authentication requirements: BearerAuth
Data slices bulk deletion.
Body parameter
{
"properties": {
"ids": {
"description": "List of data slices to remove.",
"items": {
"type": "string"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
}
},
"required": [
"ids"
],
"type": "object"
}
Parameters
Responses
| Status |
Meaning |
Description |
Schema |
| 204 |
No Content |
The requested data slice(s) are deleted successfully. |
None |
Request
Operation path: POST /api/v2/dataSlices/
Authentication requirements: BearerAuth
Request to create a new data slice.
Body parameter
{
"properties": {
"filters": {
"description": "List of filters the data slice is composed of.",
"items": {
"properties": {
"operand": {
"description": "Feature to apply operation to.",
"type": "string"
},
"operator": {
"description": "Operator to apply to the named operand in the dataset. The operator 'eq' mean 'equals the single specified value'. The operator 'in' means 'is one of a list of allowed values.'",
"enum": [
"eq",
"in",
"<",
">",
"between",
"notBetween"
],
"type": "string"
},
"values": {
"description": "Values to filter the operand by with the given operator.",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
}
]
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"required": [
"operand",
"operator",
"values"
],
"type": "object"
},
"maxItems": 3,
"minItems": 1,
"type": "array"
},
"name": {
"description": "User provided name for the data slice.",
"maxLength": 500,
"minLength": 1,
"type": "string"
},
"projectId": {
"description": "The project ID.",
"type": "string"
}
},
"required": [
"filters",
"name",
"projectId"
],
"type": "object"
}
Parameters
Example responses
200 Response
{
"properties": {
"filters": {
"description": "List of filters the data slice is composed of.",
"items": {
"properties": {
"operand": {
"description": "Feature to apply operation to.",
"type": "string"
},
"operator": {
"description": "Operator to apply to the named operand in the dataset. The operator 'eq' mean 'equals the single specified value'. The operator 'in' means 'is one of a list of allowed values.'",
"enum": [
"eq",
"in",
"<",
">",
"between",
"notBetween"
],
"type": "string"
},
"values": {
"description": "Values to filter the operand by with the given operator.",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
}
]
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"required": [
"operand",
"operator",
"values"
],
"type": "object"
},
"maxItems": 3,
"minItems": 1,
"type": "array"
},
"id": {
"description": "ID of the data slice.",
"type": "string"
},
"name": {
"description": "User provided name for the data slice.",
"maxLength": 500,
"minLength": 1,
"type": "string"
},
"projectId": {
"description": "The project ID.",
"type": "string"
}
},
"required": [
"filters",
"id",
"name",
"projectId"
],
"type": "object"
}
Responses
Delete a data slice by data slice ID
Operation path: DELETE /api/v2/dataSlices/{dataSliceId}/
Authentication requirements: BearerAuth
Deletes the data slice specified by the data slice ID.
Parameters
| Name |
In |
Type |
Required |
Description |
| dataSliceId |
path |
string |
true |
ID of the data slice. |
Responses
| Status |
Meaning |
Description |
Schema |
| 204 |
No Content |
The specified data slice was deleted. |
None |
Retrieve a Data Slice by data slice ID
Operation path: GET /api/v2/dataSlices/{dataSliceId}/
Authentication requirements: BearerAuth
Returns details about the specified data slice ID.
Parameters
| Name |
In |
Type |
Required |
Description |
| dataSliceId |
path |
string |
true |
ID of the data slice. |
Example responses
200 Response
{
"properties": {
"filters": {
"description": "List of filters the data slice is composed of.",
"items": {
"properties": {
"operand": {
"description": "Feature to apply operation to.",
"type": "string"
},
"operator": {
"description": "Operator to apply to the named operand in the dataset. The operator 'eq' mean 'equals the single specified value'. The operator 'in' means 'is one of a list of allowed values.'",
"enum": [
"eq",
"in",
"<",
">",
"between",
"notBetween"
],
"type": "string"
},
"values": {
"description": "Values to filter the operand by with the given operator.",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
}
]
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"required": [
"operand",
"operator",
"values"
],
"type": "object"
},
"maxItems": 3,
"minItems": 1,
"type": "array"
},
"id": {
"description": "ID of the data slice.",
"type": "string"
},
"name": {
"description": "User provided name for the data slice.",
"maxLength": 500,
"minLength": 1,
"type": "string"
},
"projectId": {
"description": "The project ID.",
"type": "string"
}
},
"required": [
"filters",
"id",
"name",
"projectId"
],
"type": "object"
}
Responses
Returns the number of rows available after applying a data slice by data slice ID
Operation path: GET /api/v2/dataSlices/{dataSliceId}/sliceSizes/
Authentication requirements: BearerAuth
Returns the number of rows available after applying a data slice to the specified subset of the dataset.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
query |
string |
true |
The project ID. |
| source |
query |
string |
true |
The source of data to use to calculate the size. |
| externalDatasetId |
query |
string,null |
false |
The external dataset ID to use when calculating the size of a slice. Use this parameter only when the source is 'externalTestSet'. |
| modelId |
query |
string,null |
false |
The model ID whose training dataset should be sliced. Use this parameter only when the source is 'training'. |
| dataSliceId |
path |
string |
true |
ID of the data slice. |
Enumerated Values
| Parameter |
Value |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, crossValidation, externalTestSet, holdout, holdout_training, training, validation, vectorDatabase] |
Example responses
200 Response
{
"properties": {
"dataSliceId": {
"description": "ID of the data slice.",
"type": "string"
},
"externalDatasetId": {
"description": "The external dataset ID to use when calculating the size of a slice. Use this parameter only when the source is 'externalTestSet'.",
"type": [
"string",
"null"
]
},
"messages": {
"description": "List of user-relevant messages related to a Data Slice.",
"items": {
"properties": {
"additionalInfo": {
"description": "Additional details about this message.",
"type": "string"
},
"description": {
"description": "Short summary description about this message.",
"type": "string"
},
"level": {
"description": "Message level.",
"enum": [
"CRITICAL",
"INFORMATIONAL",
"WARNING"
],
"type": "string"
}
},
"required": [
"additionalInfo",
"description",
"level"
],
"type": "object"
},
"maxItems": 100,
"type": "array"
},
"modelId": {
"description": "The model ID whose training dataset should be sliced. Use this parameter only when the source is 'training'.",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"sliceSize": {
"description": "Number of rows in the slice for the given source.",
"minimum": 0,
"type": "integer"
},
"source": {
"description": "The source of data to use to calculate the size.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"crossValidation",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation",
"vectorDatabase"
],
"type": "string"
}
},
"required": [
"dataSliceId",
"messages",
"projectId",
"sliceSize",
"source"
],
"type": "object"
}
Responses
Compute the number of rows available after applying a data slice by data slice ID
Operation path: POST /api/v2/dataSlices/{dataSliceId}/sliceSizes/
Authentication requirements: BearerAuth
Compute the number of rows available after applying a data slice to the specified subset of the dataset.
Body parameter
{
"properties": {
"externalDatasetId": {
"description": "The external dataset ID to use when calculating the size of a slice. Use this parameter only when the source is 'externalTestSet'.",
"type": [
"string",
"null"
]
},
"modelId": {
"description": "The model ID whose training dataset should be sliced. Use this parameter only when the source is 'training'.",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"source": {
"description": "The source of data to use to calculate the size.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"crossValidation",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation",
"vectorDatabase"
],
"type": "string"
}
},
"required": [
"projectId",
"source"
],
"type": "object"
}
Parameters
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
The requested data slices have been successfully validated. |
None |
Request calculation of Feature Effects
Operation path: POST /api/v2/insights/featureEffects/
Authentication requirements: BearerAuth
Request calculation of Feature Effects with an optional data slice.
Body parameter
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"training",
"backtest_0",
"backtest_1",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20",
"holdout",
"backtest_0_training",
"backtest_1_training",
"backtest_2_training",
"backtest_3_training",
"backtest_4_training",
"backtest_5_training",
"backtest_6_training",
"backtest_7_training",
"backtest_8_training",
"backtest_9_training",
"backtest_10_training",
"backtest_11_training",
"backtest_12_training",
"backtest_13_training",
"backtest_14_training",
"backtest_15_training",
"backtest_16_training",
"backtest_17_training",
"backtest_18_training",
"backtest_19_training",
"backtest_20_training",
"holdout_training"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object"
}
Parameters
Example responses
202 Response
{
"properties": {
"qid": {
"description": "The queue ID of the job that computes the insights request.",
"type": [
"integer",
"null"
]
}
},
"required": [
"qid"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
List of paginated Feature Effects insights by entity ID
Operation path: GET /api/v2/insights/featureEffects/models/{entityId}/
Authentication requirements: BearerAuth
List of paginated Feature Effects insights.
Parameters
| Name |
In |
Type |
Required |
Description |
| limit |
query |
integer |
true |
The numbers of items to return. |
| offset |
query |
integer |
true |
The number of items to skip before starting to collect the result set. |
| dataSliceId |
query |
string,null |
false |
ID of the data slice. |
| source |
query |
string |
true |
The subset of data used to compute the insight. |
| unslicedOnly |
query |
string |
false |
Return only insights without a data_slice_id. |
| entityId |
path |
string |
true |
The ID of the model. |
Enumerated Values
| Parameter |
Value |
| source |
[validation, training, backtest_0, backtest_1, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20, holdout, backtest_0_training, backtest_1_training, backtest_2_training, backtest_3_training, backtest_4_training, backtest_5_training, backtest_6_training, backtest_7_training, backtest_8_training, backtest_9_training, backtest_10_training, backtest_11_training, backtest_12_training, backtest_13_training, backtest_14_training, backtest_15_training, backtest_16_training, backtest_17_training, backtest_18_training, backtest_19_training, backtest_20_training, holdout_training] |
| unslicedOnly |
[false, False, true, True] |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated feature effects insights.",
"items": {
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`.",
"type": [
"string",
"null"
]
},
"data": {
"description": "Feature effects data.",
"properties": {
"featureEffects": {
"description": "Feature Effects computational results for each feature.",
"items": {
"properties": {
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureEffects"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"training",
"backtest_0",
"backtest_1",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20",
"holdout",
"backtest_0_training",
"backtest_1_training",
"backtest_2_training",
"backtest_3_training",
"backtest_4_training",
"backtest_5_training",
"backtest_6_training",
"backtest_7_training",
"backtest_8_training",
"backtest_9_training",
"backtest_10_training",
"backtest_11_training",
"backtest_12_training",
"backtest_13_training",
"backtest_14_training",
"backtest_15_training",
"backtest_16_training",
"backtest_17_training",
"backtest_18_training",
"backtest_19_training",
"backtest_20_training",
"holdout_training"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieves a model's Feature Effects, either for the specified data_slice_id or, if not specified, for all slices in the original data partition. |
RetrieveFeatureEffectsPaginatedResponse |
| 404 |
Not Found |
Requested entity ID or data slice ID not found |
None |
| 422 |
Unprocessable Entity |
Unsupported project type, or unsupported insight for model |
None |
Request calculation of Feature Impact
Operation path: POST /api/v2/insights/featureImpact/
Authentication requirements: BearerAuth
Request calculation of insight with an optional data slice.
Body parameter
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"rowCount": {
"description": "The number of rows to use for calculating Feature Impact.",
"maximum": 100000,
"minimum": 10,
"type": "integer"
},
"source": {
"default": "training",
"description": "The subset of data used to compute the insight.",
"enum": [
"training",
"backtest_2_training",
"backtest_3_training",
"backtest_4_training",
"backtest_5_training",
"backtest_6_training",
"backtest_7_training",
"backtest_8_training",
"backtest_9_training",
"backtest_10_training",
"backtest_11_training",
"backtest_12_training",
"backtest_13_training",
"backtest_14_training",
"backtest_15_training",
"backtest_16_training",
"backtest_17_training",
"backtest_18_training",
"backtest_19_training",
"backtest_20_training",
"backtest_1_training",
"holdout_training"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"rowCount",
"source"
],
"type": "object"
}
Parameters
Example responses
202 Response
{
"properties": {
"qid": {
"description": "The queue ID of the job that computes the insights request.",
"type": [
"integer",
"null"
]
}
},
"required": [
"qid"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
List of paginated Feature Impact insights by entity ID
Operation path: GET /api/v2/insights/featureImpact/models/{entityId}/
Authentication requirements: BearerAuth
List of paginated Feature Impact insights.
Parameters
| Name |
In |
Type |
Required |
Description |
| limit |
query |
integer |
true |
The numbers of items to return. |
| offset |
query |
integer |
true |
The number of items to skip before starting to collect the result set. |
| dataSliceId |
query |
string,null |
false |
ID of the data slice. |
| source |
query |
string |
false |
The subset of data used to compute the insight. |
| unslicedOnly |
query |
string |
false |
Return only insights without a data_slice_id. |
| entityId |
path |
string |
true |
The ID of the model. |
| Accept |
header |
string |
false |
Requested MIME type for the returned data. |
Enumerated Values
| Parameter |
Value |
| source |
[training, backtest_2_training, backtest_3_training, backtest_4_training, backtest_5_training, backtest_6_training, backtest_7_training, backtest_8_training, backtest_9_training, backtest_10_training, backtest_11_training, backtest_12_training, backtest_13_training, backtest_14_training, backtest_15_training, backtest_16_training, backtest_17_training, backtest_18_training, backtest_19_training, backtest_20_training, backtest_1_training, holdout_training] |
| unslicedOnly |
[false, False, true, True] |
| Accept |
application/json |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated feature impact insights.",
"items": {
"properties": {
"data": {
"description": "Feature impact data.",
"properties": {
"featureImpacts": {
"description": "A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"parentFeatureName": {
"description": "The name of the parent feature.",
"type": [
"string",
"null"
]
},
"redundantWith": {
"description": "Name of feature that has the highest correlation with this feature.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized",
"redundantWith"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"ranRedundancyDetection": {
"description": "Indicates whether redundant feature identification was run while calculating this feature impact.",
"type": "boolean"
},
"rowCount": {
"description": "The number of rows that was used to calculate feature impact. For the feature impact calculated with the default logic, without specifying the ``rowCount``, we return ``null`` here.",
"type": [
"integer",
"null"
]
}
},
"required": [
"featureImpacts",
"ranRedundancyDetection",
"rowCount"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"training",
"backtest_2Training",
"backtest_3Training",
"backtest_4Training",
"backtest_5Training",
"backtest_6Training",
"backtest_7Training",
"backtest_8Training",
"backtest_9Training",
"backtest_10Training",
"backtest_11Training",
"backtest_12Training",
"backtest_13Training",
"backtest_14Training",
"backtest_15Training",
"backtest_16Training",
"backtest_17Training",
"backtest_18Training",
"backtest_19Training",
"backtest_20Training",
"backtest_1Training",
"holdoutTraining"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 2,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieves a model's Feature Impact, either for the specified data_slice_id or, if not specified, for all slices in the original data partition. |
RetrieveFeatureImpactPaginatedResponse |
| 404 |
Not Found |
Requested entity ID or data slice ID not found |
None |
| 422 |
Unprocessable Entity |
Unsupported project type, or unsupported insight for model |
None |
Request calculation of Lift chart
Operation path: POST /api/v2/insights/liftChart/
Authentication requirements: BearerAuth
Request calculation of insight with an optional data slice.
Body parameter
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object"
}
Parameters
Example responses
202 Response
{
"properties": {
"qid": {
"description": "The queue ID of the job that computes the insights request.",
"type": [
"integer",
"null"
]
}
},
"required": [
"qid"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
List of paginated Lift chart insights by entity ID
Operation path: GET /api/v2/insights/liftChart/models/{entityId}/
Authentication requirements: BearerAuth
List of paginated Lift chart insights.
Parameters
| Name |
In |
Type |
Required |
Description |
| limit |
query |
integer |
true |
The numbers of items to return. |
| offset |
query |
integer |
true |
The number of items to skip before starting to collect the result set. |
| dataSliceId |
query |
string,null |
false |
ID of the data slice. |
| source |
query |
string |
false |
The subset of data used to compute the insight. |
| unslicedOnly |
query |
string |
false |
Return only insights without a data_slice_id. |
| externalDatasetId |
query |
string,null |
false |
The ID of the external dataset. |
| entityId |
path |
string |
true |
The ID of the model. |
| Accept |
header |
string |
false |
Requested MIME type for the returned data. |
Enumerated Values
| Parameter |
Value |
| source |
[validation, crossValidation, holdout, externalTestSet, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
| unslicedOnly |
[false, False, true, True] |
| Accept |
application/json |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated lift chart insights.",
"items": {
"properties": {
"data": {
"description": "Lift chart data.",
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"bins"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieves a model's Lift chart, either for the specified data_slice_id or, if not specified, for all slices in the original data partition. |
RetrieveLiftChartPaginatedResponse |
| 404 |
Not Found |
Requested entity ID or data slice ID not found |
None |
| 422 |
Unprocessable Entity |
Unsupported project type, or unsupported insight for model |
None |
Request calculation of Residuals chart
Operation path: POST /api/v2/insights/residuals/
Authentication requirements: BearerAuth
Request calculation of insight with an optional data slice.
Body parameter
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object"
}
Parameters
Example responses
202 Response
{
"properties": {
"qid": {
"description": "The queue ID of the job that computes the insights request.",
"type": [
"integer",
"null"
]
}
},
"required": [
"qid"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
List of paginated Residuals insights by entity ID
Operation path: GET /api/v2/insights/residuals/models/{entityId}/
Authentication requirements: BearerAuth
List of paginated Residuals insights.
Parameters
| Name |
In |
Type |
Required |
Description |
| limit |
query |
integer |
true |
The numbers of items to return. |
| offset |
query |
integer |
true |
The number of items to skip before starting to collect the result set. |
| dataSliceId |
query |
string,null |
false |
ID of the data slice. |
| source |
query |
string |
false |
The subset of data used to compute the insight. |
| unslicedOnly |
query |
string |
false |
Return only insights without a data_slice_id. |
| externalDatasetId |
query |
string,null |
false |
The ID of the external dataset. |
| entityId |
path |
string |
true |
The ID of the model. |
| Accept |
header |
string |
false |
Requested MIME type for the returned data. |
Enumerated Values
| Parameter |
Value |
| source |
[validation, crossValidation, holdout, externalTestSet] |
| unslicedOnly |
[false, False, true, True] |
| Accept |
application/json |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated residuals insights.",
"items": {
"properties": {
"data": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieves a model's Residuals chart, either for the specified data_slice_id or, if not specified, for all slices in the original data partition. |
RetrieveResidualsPaginatedResponse |
| 404 |
Not Found |
Requested entity ID or data slice ID not found |
None |
| 422 |
Unprocessable Entity |
Unsupported project type, or unsupported insight for model |
None |
Request calculation of ROC curve
Operation path: POST /api/v2/insights/rocCurve/
Authentication requirements: BearerAuth
Request calculation of insight with an optional data slice.
Body parameter
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object"
}
Parameters
Example responses
202 Response
{
"properties": {
"qid": {
"description": "The queue ID of the job that computes the insights request.",
"type": [
"integer",
"null"
]
}
},
"required": [
"qid"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
List of paginated ROC curve insights by entity ID
Operation path: GET /api/v2/insights/rocCurve/models/{entityId}/
Authentication requirements: BearerAuth
List of paginated ROC curve insights.
Parameters
| Name |
In |
Type |
Required |
Description |
| limit |
query |
integer |
true |
The numbers of items to return. |
| offset |
query |
integer |
true |
The number of items to skip before starting to collect the result set. |
| dataSliceId |
query |
string,null |
false |
ID of the data slice. |
| source |
query |
string |
false |
The subset of data used to compute the insight. |
| unslicedOnly |
query |
string |
false |
Return only insights without a data_slice_id. |
| externalDatasetId |
query |
string,null |
false |
The ID of the external dataset. |
| entityId |
path |
string |
true |
The ID of the model. |
| Accept |
header |
string |
false |
Requested MIME type for the returned data. |
Enumerated Values
| Parameter |
Value |
| source |
[validation, crossValidation, holdout, externalTestSet, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
| unslicedOnly |
[false, False, true, True] |
| Accept |
application/json |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated roc curve insights.",
"items": {
"properties": {
"data": {
"description": "Roc curve data.",
"properties": {
"auc": {
"description": "AUC value",
"type": [
"number",
"null"
]
},
"kolmogorovSmirnovMetric": {
"description": "Kolmogorov-Smirnov metric value",
"type": [
"number",
"null"
]
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the positive class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "The ROC curve data for that source, as specified below.",
"items": {
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"auc",
"kolmogorovSmirnovMetric",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieves a model's ROC curve, either for the specified data_slice_id or, if not specified, for all slices in the original data partition. |
RetrieveRocCurvePaginatedResponse |
| 404 |
Not Found |
Requested entity ID or data slice ID not found |
None |
| 422 |
Unprocessable Entity |
Unsupported project type, or unsupported insight for model |
None |
Request calculation of SHAP Distributions
Operation path: POST /api/v2/insights/shapDistributions/
Authentication requirements: BearerAuth
Request calculation of insight with an optional data slice.
Body parameter
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"quickCompute": {
"default": true,
"description": "(Deprecated) Limits the number of rows used from the selected source by default. Cannot be set to False for this insight.",
"type": "boolean"
},
"rowCount": {
"description": "(Deprecated) The number of rows to use for calculating SHAP Impact.",
"type": "integer",
"x-versiondeprecated": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object",
"x-versionadded": "v2.38"
}
Parameters
Example responses
202 Response
{
"properties": {
"qid": {
"description": "The queue ID of the job that computes the insights request.",
"type": [
"integer",
"null"
]
}
},
"required": [
"qid"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
List of paginated SHAP Distributions insights by entity ID
Operation path: GET /api/v2/insights/shapDistributions/models/{entityId}/
Authentication requirements: BearerAuth
List of paginated SHAP Distributions insights.
Parameters
| Name |
In |
Type |
Required |
Description |
| limit |
query |
integer |
true |
The numbers of items to return. |
| offset |
query |
integer |
true |
The number of items to skip before starting to collect the result set. |
| dataSliceId |
query |
string,null |
false |
ID of the data slice. |
| source |
query |
string |
false |
The subset of data used to compute the insight. |
| unslicedOnly |
query |
string |
false |
Return only insights without a data_slice_id. |
| externalDatasetId |
query |
string,null |
false |
The ID of the external dataset. |
| predictionFilterRowCount |
query |
integer |
false |
The maximum number of distribution rows to return. |
| featureFilterCount |
query |
integer |
false |
The maximum number of features to return. |
| featureFilterName |
query |
string |
false |
The names of the features to return. |
| quickCompute |
query |
boolean |
false |
When enabled, the default, limits the rows used from the selected subset (training sample or slice). |
| seriesId |
query |
string |
false |
The series ID used to filter records (for multiseries projects). |
| forecastDistance |
query |
integer |
false |
The forecast distance used to retrieve insight data. |
| featuresOrderBy |
query |
string |
false |
Order SHAP distributions by the specified field value. |
| entityId |
path |
string |
true |
The ID of the model. |
| Accept |
header |
string |
false |
Requested MIME type for the returned data. |
Enumerated Values
| Parameter |
Value |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, externalTestSet, holdout, holdout_training, training, validation] |
| unslicedOnly |
[false, False, true, True] |
| featuresOrderBy |
[featureImpact, -featureImpact, featureName, -featureName] |
| Accept |
[application/json, text/csv] |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated SHAP distributions insights.",
"items": {
"properties": {
"data": {
"description": "SHAP distributions data.",
"properties": {
"features": {
"description": "List of SHAP distributions for each requested row.",
"items": {
"properties": {
"feature": {
"description": "The feature name in the dataset.",
"type": "string"
},
"featureType": {
"description": "Feature type.",
"enum": [
"T",
"X",
"B",
"C",
"CI",
"N",
"D",
"DD",
"FD",
"Q",
"CD",
"GEO",
"MC",
"INT",
"DOC"
],
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"shapValues": {
"description": "The SHAP distributions values for this row.",
"items": {
"properties": {
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer"
},
"featureValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The value of the feature for this row."
},
"predictionValue": {
"description": "The prediction value for this row.",
"type": "number"
},
"rowIndex": {
"description": "The index of this row.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number"
},
"weight": {
"description": "Weight of the row in the dataset.",
"type": [
"number",
"null"
],
"x-versionadded": "v2.37"
}
},
"required": [
"featureRank",
"featureValue",
"predictionValue",
"rowIndex",
"shapValue",
"weight"
],
"type": "object",
"x-versionadded": "v2.35"
},
"maxItems": 2500,
"type": "array"
}
},
"required": [
"feature",
"featureType",
"impactNormalized",
"impactUnnormalized",
"shapValues"
],
"type": "object",
"x-versionadded": "v2.35"
},
"maxItems": 100,
"type": "array"
},
"totalFeaturesCount": {
"description": "The total number of features.",
"type": "integer"
}
},
"required": [
"features",
"totalFeaturesCount"
],
"type": "object",
"x-versionadded": "v2.35"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object",
"x-versionadded": "v2.35"
},
"maxItems": 10,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object",
"x-versionadded": "v2.35"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieves a model's SHAP Distributions chart, either for the specified data_slice_id or, if not specified, for all slices in the original data partition. |
string |
| 404 |
Not Found |
Requested entity ID or data slice ID not found |
None |
| 422 |
Unprocessable Entity |
Unsupported project type, or unsupported insight for model |
None |
Request calculation of SHAP Impact
Operation path: POST /api/v2/insights/shapImpact/
Authentication requirements: BearerAuth
Request calculation of insight with an optional data slice.
Body parameter
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"quickCompute": {
"default": true,
"description": "When enabled, limits the number of rows used from the selected source by default. When disabled, all rows are used.",
"type": "boolean"
},
"rowCount": {
"description": "(Deprecated) The number of rows to use for calculating SHAP Impact.",
"type": "integer",
"x-versionadded": "v2.35",
"x-versiondeprecated": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object",
"x-versionadded": "v2.35"
}
Parameters
Example responses
202 Response
{
"properties": {
"qid": {
"description": "The queue ID of the job that computes the insights request.",
"type": [
"integer",
"null"
]
}
},
"required": [
"qid"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
List of paginated SHAP Impact insights by entity ID
Operation path: GET /api/v2/insights/shapImpact/models/{entityId}/
Authentication requirements: BearerAuth
List of paginated SHAP Impact insights.
Parameters
| Name |
In |
Type |
Required |
Description |
| limit |
query |
integer |
true |
The numbers of items to return. |
| offset |
query |
integer |
true |
The number of items to skip before starting to collect the result set. |
| dataSliceId |
query |
string,null |
false |
ID of the data slice. |
| source |
query |
string |
false |
Subset of data used to compute the insight. |
| unslicedOnly |
query |
string |
false |
Return only insights without a data_slice_id. |
| entityId |
path |
string |
true |
The ID of the model. |
| Accept |
header |
string |
false |
Requested MIME type for the returned data. |
Enumerated Values
| Parameter |
Value |
| source |
[backtest_0, backtest_0Training, backtest_1, backtest_10, backtest_10Training, backtest_11, backtest_11Training, backtest_12, backtest_12Training, backtest_13, backtest_13Training, backtest_14, backtest_14Training, backtest_15, backtest_15Training, backtest_16, backtest_16Training, backtest_17, backtest_17Training, backtest_18, backtest_18Training, backtest_19, backtest_19Training, backtest_1Training, backtest_2, backtest_20, backtest_20Training, backtest_2Training, backtest_3, backtest_3Training, backtest_4, backtest_4Training, backtest_5, backtest_5Training, backtest_6, backtest_6Training, backtest_7, backtest_7Training, backtest_8, backtest_8Training, backtest_9, backtest_9Training, externalTestSet, holdout, holdoutTraining, training, validation] |
| unslicedOnly |
[false, False, true, True] |
| Accept |
application/json |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer",
"x-versionadded": "v2.33"
},
"data": {
"description": "List of paginated SHAP impact insights.",
"items": {
"properties": {
"data": {
"description": "SHAP impact data.",
"properties": {
"baseValue": {
"description": "Mean of raw model predictions for the training data.",
"items": {
"type": "number"
},
"type": "array",
"x-versionadded": "v2.33"
},
"link": {
"description": "Link function used to connect the SHAP importance values to the model output.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"quickCompute": {
"default": true,
"description": "When enabled, limits the rows used from the selected source subset by default. When disabled, all rows are used.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"rowCount": {
"description": "(Deprecated) The number of rows used to calculate SHAP impact. If ``rowCount`` is not specified, the value returned is ``null``.",
"type": [
"integer",
"null"
],
"x-versionadded": "v2.33",
"x-versiondeprecated": "v2.35"
},
"shapImpacts": {
"description": "A list that contains SHAP impact scores.",
"items": {
"properties": {
"featureName": {
"description": "The feature name in the dataset.",
"type": "string"
},
"impactNormalized": {
"description": "The normalized impact score value.",
"type": [
"number",
"null"
]
},
"impactUnnormalized": {
"description": "The raw impact score value.",
"type": "number"
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
}
},
"required": [
"baseValue",
"link",
"rowCount",
"shapImpacts"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"entityId": {
"description": "ID of the model.",
"type": "string",
"x-versionadded": "v2.33"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"id": {
"description": "ID of the created insight.",
"type": "string",
"x-versionadded": "v2.33"
},
"projectId": {
"description": "ID of the project.",
"type": "string",
"x-versionadded": "v2.33"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "Subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array",
"x-versionadded": "v2.33"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieves a model's SHAP impact chart, either for the specified data_slice_id or, if not specified, for all slices in the original data partition. |
RetrieveShapImpactPaginatedResponse |
| 404 |
Not Found |
Requested entity ID or data slice ID not found |
None |
| 422 |
Unprocessable Entity |
Unsupported project type, or unsupported insight for model |
None |
Request calculation of SHAP Matrix
Operation path: POST /api/v2/insights/shapMatrix/
Authentication requirements: BearerAuth
Request calculation of insight with an optional data slice.
Body parameter
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"quickCompute": {
"default": true,
"description": "When enabled, limits the number of rows used from the selected source by default. When disabled, all rows are used.",
"type": "boolean"
},
"rowCount": {
"description": "(Deprecated) The number of rows to use for calculating SHAP Impact.",
"type": "integer",
"x-versionadded": "v2.35",
"x-versiondeprecated": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object",
"x-versionadded": "v2.35"
}
Parameters
Example responses
202 Response
{
"properties": {
"qid": {
"description": "The queue ID of the job that computes the insights request.",
"type": [
"integer",
"null"
]
}
},
"required": [
"qid"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
List of paginated SHAP Matrix insights by entity ID
Operation path: GET /api/v2/insights/shapMatrix/models/{entityId}/
Authentication requirements: BearerAuth
List of paginated SHAP Matrix insights.
Parameters
| Name |
In |
Type |
Required |
Description |
| limit |
query |
integer |
true |
The numbers of items to return. |
| offset |
query |
integer |
true |
The number of items to skip before starting to collect the result set. |
| dataSliceId |
query |
string,null |
false |
ID of the data slice. |
| source |
query |
string |
false |
The subset of data used to compute the insight. |
| unslicedOnly |
query |
string |
false |
Return only insights without a data_slice_id. |
| externalDatasetId |
query |
string,null |
false |
The ID of the external dataset. |
| quickCompute |
query |
boolean |
false |
When enabled, limits the rows used from the selected source subset by default. When disabled, all rows are used. |
| entityId |
path |
string |
true |
The ID of the model. |
| Accept |
header |
string |
false |
Requested MIME type for the returned data. |
Enumerated Values
| Parameter |
Value |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, externalTestSet, holdout, holdout_training, training, validation] |
| unslicedOnly |
[false, False, true, True] |
| Accept |
[application/json, text/csv] |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer",
"x-versionadded": "v2.33"
},
"data": {
"description": "List of paginated SHAP matrix insights.",
"items": {
"properties": {
"data": {
"description": "SHAP matrix data.",
"properties": {
"baseValue": {
"description": "The mean of the raw model predictions for the training data.",
"items": {
"type": "number"
},
"type": "array",
"x-versionadded": "v2.33"
},
"colnames": {
"description": "The names of each column in the SHAP matrix.",
"items": {
"type": "string"
},
"type": "array",
"x-versionadded": "v2.33"
},
"linkFunction": {
"description": "The link function used to connect the feature importance values to the model output.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"matrix": {
"description": "SHAP matrix values.",
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array",
"x-versionadded": "v2.33"
},
"rowIndex": {
"description": "The index of the data row used to compute the SHAP matrix. Not used in time-aware projects.",
"items": {
"type": "integer"
},
"type": "array",
"x-versionadded": "v2.33"
},
"timeSeriesRowIndex": {
"description": "An index composed of the timestamp, series id and forecast distance. Only used in time-aware projects.",
"items": {
"items": {
"oneOf": [
{
"type": "integer"
},
{
"type": "string"
}
]
},
"maxLength": 2,
"minLength": 2,
"type": "array"
},
"type": "array",
"x-versionadded": "v2.36"
}
},
"required": [
"baseValue",
"colnames",
"linkFunction",
"matrix",
"rowIndex"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"entityId": {
"description": "ID of the model.",
"type": "string",
"x-versionadded": "v2.33"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"id": {
"description": "ID of the created insight.",
"type": "string",
"x-versionadded": "v2.33"
},
"projectId": {
"description": "ID of the project.",
"type": "string",
"x-versionadded": "v2.33"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array",
"x-versionadded": "v2.33"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieves a model's SHAP Matrix chart, either for the specified data_slice_id or, if not specified, for all slices in the original data partition. |
string |
| 404 |
Not Found |
Requested entity ID or data slice ID not found |
None |
| 422 |
Unprocessable Entity |
Unsupported project type, or unsupported insight for model |
None |
Request calculation of SHAP Preview
Operation path: POST /api/v2/insights/shapPreview/
Authentication requirements: BearerAuth
Request calculation of insight with an optional data slice.
Body parameter
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"quickCompute": {
"default": true,
"description": "When enabled, limits the number of rows used from the selected source by default. When disabled, all rows are used.",
"type": "boolean"
},
"rowCount": {
"description": "(Deprecated) The number of rows to use for calculating SHAP Impact.",
"type": "integer",
"x-versionadded": "v2.35",
"x-versiondeprecated": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object",
"x-versionadded": "v2.35"
}
Parameters
Example responses
202 Response
{
"properties": {
"qid": {
"description": "The queue ID of the job that computes the insights request.",
"type": [
"integer",
"null"
]
}
},
"required": [
"qid"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
List of paginated SHAP Preview insights by entity ID
Operation path: GET /api/v2/insights/shapPreview/models/{entityId}/
Authentication requirements: BearerAuth
List of paginated SHAP Preview insights.
Parameters
| Name |
In |
Type |
Required |
Description |
| limit |
query |
integer |
true |
The numbers of items to return. |
| offset |
query |
integer |
true |
The number of items to skip before starting to collect the result set. |
| dataSliceId |
query |
string,null |
false |
ID of the data slice. |
| source |
query |
string |
false |
The subset of data used to compute the insight. |
| unslicedOnly |
query |
string |
false |
Return only insights without a data_slice_id. |
| externalDatasetId |
query |
string,null |
false |
The ID of the external dataset. |
| predictionFilterRowCount |
query |
integer |
false |
The maximum number of preview rows to return. |
| predictionFilterPercentiles |
query |
integer |
false |
The number of percentile intervals to select from the total number of rows. This field will supersede predictionFilterRowCount if both are present. |
| predictionFilterOperandFirst |
query |
number |
false |
The first operand to apply to filtered predictions. |
| predictionFilterOperandSecond |
query |
number |
false |
The second operand to apply to filtered predictions. |
| predictionFilterOperator |
query |
string |
false |
The operator to apply to filtered predictions. |
| featureFilterCount |
query |
integer |
false |
The maximum number of features to return for each preview. |
| featureFilterName |
query |
string |
false |
The names of specific features to return for each preview. |
| quickCompute |
query |
boolean |
false |
When enabled, limits the rows used from the selected source subset by default. When disabled, all rows are used. |
| seriesId |
query |
string |
false |
The series ID used to filter records (for multiseries projects). |
| forecastDistance |
query |
integer |
false |
The forecast distance used to retrieve insight data. |
| entityId |
path |
string |
true |
The ID of the model. |
| Accept |
header |
string |
false |
Requested MIME type for the returned data. |
Enumerated Values
| Parameter |
Value |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, externalTestSet, holdout, holdout_training, training, validation] |
| unslicedOnly |
[false, False, true, True] |
| predictionFilterOperator |
[eq, in, <, >, between, notBetween] |
| Accept |
[application/json, text/csv] |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer",
"x-versionadded": "v2.33"
},
"data": {
"description": "List of paginated SHAP preview insights.",
"items": {
"properties": {
"data": {
"description": "SHAP preview data.",
"properties": {
"previews": {
"description": "List of SHAP previews for each requested row.",
"items": {
"properties": {
"predictionValue": {
"description": "The prediction value for this row.",
"type": "number",
"x-versionadded": "v2.33"
},
"previewValues": {
"description": "The SHAP preview values for this row.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string",
"x-versionadded": "v2.33"
},
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer",
"x-versionadded": "v2.33"
},
"featureValue": {
"description": "The value of the feature for this row.",
"type": "string",
"x-versionadded": "v2.33"
},
"hasTextExplanations": {
"description": "Whether the feature has text explanations available for this row.",
"type": "boolean",
"x-versionadded": "v2.33"
},
"isImage": {
"description": "Whether the feature is an image or not.",
"type": "boolean",
"x-versionadded": "v2.34"
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number",
"x-versionadded": "v2.33"
},
"textExplanations": {
"description": "List of the text explanations for the feature for this row.",
"items": {
"type": "string"
},
"type": "array",
"x-versionadded": "v2.33"
}
},
"required": [
"featureName",
"featureRank",
"featureValue",
"hasTextExplanations",
"shapValue",
"textExplanations"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
},
"rowIndex": {
"description": "The index of this row.",
"minimum": 0,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.33"
},
"timeSeriesRowIndex": {
"description": "An index composed of the timestamp, series ID, and forecast distance. This index is used only in time-aware projects.",
"items": {
"oneOf": [
{
"type": "integer"
},
{
"type": "string"
}
]
},
"maxLength": 2,
"minLength": 2,
"type": [
"array",
"null"
],
"x-versionadded": "v2.36"
},
"totalPreviewFeatures": {
"description": "The total number of features available after name filters have been applied.",
"minimum": 0,
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"predictionValue",
"previewValues",
"rowIndex",
"totalPreviewFeatures"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
},
"previewsCount": {
"description": "The total number of previews.",
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"previews",
"previewsCount"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"entityId": {
"description": "ID of the model.",
"type": "string",
"x-versionadded": "v2.33"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"id": {
"description": "ID of the created insight.",
"type": "string",
"x-versionadded": "v2.33"
},
"projectId": {
"description": "ID of the project.",
"type": "string",
"x-versionadded": "v2.33"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array",
"x-versionadded": "v2.33"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieves a model's SHAP Preview chart, either for the specified data_slice_id or, if not specified, for all slices in the original data partition. |
string |
| 404 |
Not Found |
Requested entity ID or data slice ID not found |
None |
| 422 |
Unprocessable Entity |
Unsupported project type, or unsupported insight for model |
None |
Delete insights by insightname
Operation path: DELETE /api/v2/insights/{insightName}/models/{entityId}/
Authentication requirements: BearerAuth
Delete insights for a specific model.
Parameters
| Name |
In |
Type |
Required |
Description |
| insightName |
path |
string |
true |
The name of the insight to be deleted. |
| entityId |
path |
string |
true |
The ID of the model. |
Enumerated Values
| Parameter |
Value |
| insightName |
[clusteringBarycentersMetric, clusteringDTW, confusionMatrix, featureEffects, featureImpact, liftChart, residuals, rocCurve, segmentationPreview, shapDistributions, shapImpact, shapMatrix, shapPreview, silhouetteDTW, timeSeriesClusteringBarycenters, umap] |
Responses
| Status |
Meaning |
Description |
Schema |
| 204 |
No Content |
Model insight records deleted. |
None |
| 404 |
Not Found |
Data was not found. |
None |
Retrieve multicategorical feature histogram by multilabelinsightskey
Operation path: GET /api/v2/multilabelInsights/{multilabelInsightsKey}/histogram/
Authentication requirements: BearerAuth
Retrieve multicategorical feature histogram.
Parameters
| Name |
In |
Type |
Required |
Description |
| multilabelInsightsKey |
path |
string |
true |
Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename] |
Example responses
200 Response
{
"properties": {
"featureName": {
"description": "Feature name.",
"type": "string"
},
"histogram": {
"description": "Feature histogram.",
"items": {
"properties": {
"label": {
"description": "Label name.",
"type": "string"
},
"plot": {
"description": "Relevance histogram for label.",
"items": {
"properties": {
"labelRelevance": {
"description": "Label relevance value.",
"maximum": 1,
"minimum": 0,
"type": "integer"
},
"rowCount": {
"description": "Number of rows for which the label has the given relevance.",
"minimum": 0,
"type": "integer"
},
"rowPct": {
"description": "Percentage of rows for which the label has the given relevance.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"labelRelevance",
"rowCount",
"rowPct"
],
"type": "object"
},
"maxItems": 2,
"minItems": 2,
"type": "array"
}
},
"required": [
"label",
"plot"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"projectId": {
"description": "Project Id.",
"type": "string"
}
},
"required": [
"featureName",
"histogram",
"projectId"
],
"type": "object"
}
Responses
Get all label lists by multilabelinsightskey
Operation path: GET /api/v2/multilabelInsights/{multilabelInsightsKey}/pairwiseManualSelections/
Authentication requirements: BearerAuth
Get all label lists.
Parameters
| Name |
In |
Type |
Required |
Description |
| multilabelInsightsKey |
path |
string |
true |
Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename] |
Example responses
200 Response
{
"properties": {
"data": {
"description": "List of manually selected labels sets",
"items": {
"properties": {
"columnLabels": {
"description": "Manually selected column labels.",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
"id": {
"description": "Id of the manually selected labels set",
"type": "string"
},
"name": {
"description": "Name for the set of manually selected labels.",
"maxLength": 100,
"type": "string"
},
"rowLabels": {
"description": "Manually selected row labels.",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
}
},
"required": [
"columnLabels",
"id",
"name",
"rowLabels"
],
"type": "object"
},
"type": "array"
},
"featureName": {
"description": "Name of the feature the request is related to",
"type": [
"string",
"null"
]
},
"multilabelInsightsKey": {
"description": "Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename]",
"type": "string"
},
"projectId": {
"description": "ID of the project the request is related to.",
"type": [
"string",
"null"
]
}
},
"required": [
"data",
"featureName",
"multilabelInsightsKey",
"projectId"
],
"type": "object"
}
Responses
Save a list of manually selected labels by multilabelinsightskey
Operation path: POST /api/v2/multilabelInsights/{multilabelInsightsKey}/pairwiseManualSelections/
Authentication requirements: BearerAuth
Save a list of manually selected labels for Feature Statistics matrix.
Body parameter
{
"properties": {
"columnLabels": {
"description": "Manually selected column labels.",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
"featureName": {
"description": "Name of the feature the request is related to",
"type": [
"string",
"null"
]
},
"multilabelInsightsKey": {
"description": "Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename]",
"type": "string"
},
"name": {
"description": "Name for the set of manually selected labels.",
"maxLength": 100,
"type": "string"
},
"projectId": {
"description": "ID of the project the request is related to.",
"type": [
"string",
"null"
]
},
"rowLabels": {
"description": "Manually selected row labels.",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
}
},
"required": [
"columnLabels",
"featureName",
"multilabelInsightsKey",
"name",
"projectId",
"rowLabels"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| multilabelInsightsKey |
path |
string |
true |
Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename] |
| body |
body |
PairwiseManualSelectionCreatePayload |
false |
none |
Example responses
200 Response
{
"properties": {
"id": {
"description": "ID of the label set.",
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
}
Responses
Delete label list by multilabelinsightskey
Operation path: DELETE /api/v2/multilabelInsights/{multilabelInsightsKey}/pairwiseManualSelections/{manualSelectionListId}/
Authentication requirements: BearerAuth
Delete label list.
Parameters
| Name |
In |
Type |
Required |
Description |
| multilabelInsightsKey |
path |
string |
true |
Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename] |
| manualSelectionListId |
path |
string |
true |
ID of the label set. |
Example responses
200 Response
{
"properties": {
"manualSelectionId": {
"description": "ID of the deleted or updated label set.",
"type": "string"
}
},
"required": [
"manualSelectionId"
],
"type": "object"
}
Responses
Update label list's name by multilabelinsightskey
Operation path: PATCH /api/v2/multilabelInsights/{multilabelInsightsKey}/pairwiseManualSelections/{manualSelectionListId}/
Authentication requirements: BearerAuth
Update label list's name.
Body parameter
{
"properties": {
"name": {
"description": "Name for the set of manually selected labels.",
"maxLength": 100,
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| multilabelInsightsKey |
path |
string |
true |
Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename] |
| manualSelectionListId |
path |
string |
true |
ID of the label set. |
| body |
body |
PairwiseManualSelectionUpdateRequest |
false |
none |
Example responses
200 Response
{
"properties": {
"manualSelectionId": {
"description": "ID of the deleted or updated label set.",
"type": "string"
}
},
"required": [
"manualSelectionId"
],
"type": "object"
}
Responses
Retrieve pairwise statistics by multilabelinsightskey
Operation path: GET /api/v2/multilabelInsights/{multilabelInsightsKey}/pairwiseStatistics/
Authentication requirements: BearerAuth
Retrieve multilabel specific pairwise label statistics for the given multilabel insights key: correlation, joint probability and conditional probability.
Parameters
| Name |
In |
Type |
Required |
Description |
| statisticType |
query |
string |
true |
Type of pairwise statistic. |
| multilabelInsightsKey |
path |
string |
true |
Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename] |
Enumerated Values
| Parameter |
Value |
| statisticType |
[conditionalProbability, correlation, jointProbability] |
Example responses
200 Response
{
"properties": {
"data": {
"description": "Statistic values.",
"items": {
"properties": {
"labelConfiguration": {
"description": "Configuration of all labels.",
"items": {
"properties": {
"label": {
"description": "Label name.",
"type": "string"
},
"relevance": {
"description": "Relevance value of the label.",
"maximum": 1,
"minimum": 0,
"type": "integer"
}
},
"required": [
"label"
],
"type": "object"
},
"maxItems": 2,
"minItems": 2,
"type": "array"
},
"statisticValue": {
"description": "Statistic value for the given label configuration.",
"type": [
"number",
"null"
]
}
},
"required": [
"labelConfiguration",
"statisticValue"
],
"type": "object"
},
"type": "array"
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"projectId": {
"description": "Project Id.",
"maxLength": 24,
"minLength": 24,
"type": "string"
},
"statisticType": {
"description": "Pairwise statistic type.",
"enum": [
"conditionalProbability",
"correlation",
"jointProbability"
],
"type": "string"
}
},
"required": [
"data",
"featureName",
"projectId",
"statisticType"
],
"type": "object"
}
Responses
Retrieve anomaly assessment records by project ID
Operation path: GET /api/v2/projects/{projectId}/anomalyAssessmentRecords/
Authentication requirements: BearerAuth
Retrieve anomaly assessment records.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
false |
At most this many results are returned. The default may change without notice. |
| modelId |
query |
string |
false |
The model ID to filter records by. |
| backtest |
query |
any |
false |
The backtest to filter records by. |
| source |
query |
string |
false |
The source of the data to filter records by. |
| seriesId |
query |
string |
false |
Can be specified for multiseries projects. The series id to filter records by. |
| projectId |
path |
string |
true |
The project ID |
Enumerated Values
| Parameter |
Value |
| source |
[training, validation] |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items in current page.",
"type": "integer"
},
"data": {
"description": "Anomaly assessment record.",
"items": {
"properties": {
"backtest": {
"description": "The backtest of the record.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
]
},
"deleteLocation": {
"description": "URL to delete anomaly assessment record.",
"format": "uri",
"type": [
"string",
"null"
]
},
"endDate": {
"description": "ISO-formatted last timestamp in the subset. For example: ``2019-08-30T00:00:00.000000Z``.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"latestExplanationsLocation": {
"description": "URL to retrieve the latest predictions with the shap explanations.",
"format": "uri",
"type": [
"string",
"null"
]
},
"modelId": {
"description": "The model ID of the record.",
"type": "string"
},
"predictionThreshold": {
"description": "The threshold, all rows with anomaly scores greater or equal to it have Shapley explanations computed.",
"type": [
"number",
"null"
]
},
"previewLocation": {
"description": "URL to retrieve predictions preview for the record.",
"format": "uri",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID of the record.",
"type": "string"
},
"recordId": {
"description": "The ID of the anomaly assessment record.",
"type": "string"
},
"seriesId": {
"description": "The series id of the record. Applicable in multiseries projects",
"type": [
"string",
"null"
]
},
"source": {
"description": "The source of the record",
"enum": [
"training",
"validation"
],
"type": "string"
},
"startDate": {
"description": "ISO-formatted first timestamp in the subset. For example: ``2019-08-01T00:00:00.000000Z``.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"status": {
"description": "The status of the anomaly assessment record.",
"enum": [
"noData",
"notSupported",
"completed"
],
"type": "string"
},
"statusDetails": {
"description": "The status details.",
"type": "string"
}
},
"required": [
"backtest",
"deleteLocation",
"endDate",
"latestExplanationsLocation",
"modelId",
"predictionThreshold",
"previewLocation",
"projectId",
"recordId",
"seriesId",
"source",
"startDate",
"status",
"statusDetails"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page)",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page)",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"count",
"data",
"next",
"previous"
],
"type": "object"
}
Responses
Delete the anomaly assessment record by project ID
Operation path: DELETE /api/v2/projects/{projectId}/anomalyAssessmentRecords/{recordId}/
Authentication requirements: BearerAuth
Delete the anomaly assessment record.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| recordId |
path |
string |
true |
The anomaly assessment record ID |
Responses
| Status |
Meaning |
Description |
Schema |
| 204 |
No Content |
Anomaly assessment record deleted. |
None |
| 404 |
Not Found |
Data was not found. |
None |
Retrieve anomaly assessment record by project ID
Operation path: GET /api/v2/projects/{projectId}/anomalyAssessmentRecords/{recordId}/explanations/
Authentication requirements: BearerAuth
Retrieve anomaly assessment record.
Two out of three parameters: startDate, endDate or pointsCount must be specified.
Parameters
| Name |
In |
Type |
Required |
Description |
| startDate |
query |
string(date-time) |
false |
The start of the date range to return. Date should be in UTC format. For example: 2019-08-01T00:00:00.000000Z. |
| endDate |
query |
string(date-time) |
false |
The end of the date range to return, inclusive. Date should be in UTC format. For example: 2020-01-01T00:00:00.000000Z. |
| pointsCount |
query |
integer |
false |
Count of points to return. |
| projectId |
path |
string |
true |
The project ID |
| recordId |
path |
string |
true |
The anomaly assessment record ID |
Example responses
200 Response
{
"properties": {
"backtest": {
"description": "The backtest of the record.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
]
},
"count": {
"description": "The count of points.",
"type": "integer"
},
"data": {
"description": "Each is a `DataPoint` corresponding to a row in the specified range.",
"items": {
"properties": {
"prediction": {
"description": "The output of the model for this row.",
"type": "number"
},
"shapExplanation": {
"description": "Either ``null`` or an array of up to 10 `ShapleyFeatureContribution` objects. Only rows with the highest anomaly scores have Shapley explanations calculated.",
"items": {
"properties": {
"feature": {
"description": "Feature name",
"type": "string"
},
"featureValue": {
"description": "Feature value for this row. First 50 characters are returned.",
"type": "string"
},
"strength": {
"description": "Shapley value for this feature and row.",
"type": "number"
}
},
"required": [
"feature",
"featureValue",
"strength"
],
"type": "object"
},
"type": "array"
},
"timestamp": {
"description": "ISO-formatted timestamp for the row.",
"format": "date-time",
"type": "string"
}
},
"required": [
"prediction",
"shapExplanation",
"timestamp"
],
"type": "object"
},
"type": "array"
},
"endDate": {
"description": "ISO-formatted last timestamp in the response. For example: ``2019-08-30T00:00:00.000000Z``.",
"format": "date-time",
"type": "string"
},
"modelId": {
"description": "The model ID of the record.",
"type": "string"
},
"projectId": {
"description": "The project ID of the record.",
"type": "string"
},
"recordId": {
"description": "The ID of the anomaly assessment record.",
"type": "string"
},
"seriesId": {
"description": "The series id of the record. Applicable in multiseries projects",
"type": [
"string",
"null"
]
},
"shapBaseValue": {
"description": "shap base value",
"type": "number"
},
"source": {
"description": "The source of the record",
"enum": [
"training",
"validation"
],
"type": "string"
},
"startDate": {
"description": "ISO-formatted first timestamp in the response. For example: ``2019-08-01T00:00:00.000000Z``.",
"format": "date-time",
"type": "string"
}
},
"required": [
"backtest",
"count",
"data",
"endDate",
"modelId",
"projectId",
"recordId",
"seriesId",
"shapBaseValue",
"source",
"startDate"
],
"type": "object"
}
Responses
Retrieve predictions preview by project ID
Operation path: GET /api/v2/projects/{projectId}/anomalyAssessmentRecords/{recordId}/predictionsPreview/
Authentication requirements: BearerAuth
Retrieve predictions preview for the anomaly assessment record.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| recordId |
path |
string |
true |
The anomaly assessment record ID |
Example responses
200 Response
{
"properties": {
"backtest": {
"description": "The backtest of the record.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
]
},
"endDate": {
"description": "ISO-formatted last timestamp in the subset. For example: ``2019-08-30T00:00:00.000000Z``.",
"format": "date-time",
"type": "string"
},
"modelId": {
"description": "The model ID of the record.",
"type": "string"
},
"previewBins": {
"description": "Aggregated predictions for the subset. Bins boundaries may differ from actual start/end dates because this is an aggregation.",
"items": {
"properties": {
"avgPredicted": {
"description": "Average prediction of the model in the bin. Null if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "ISO-formatted datetime of the end of the bin (exclusive).",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "Number of the rows in the bin.",
"type": "integer"
},
"maxPredicted": {
"description": "Maximum prediction of the model in the bin. Null if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "ISO-formatted datetime of the start of the bin (inclusive).",
"format": "date-time",
"type": "string"
}
},
"required": [
"avgPredicted",
"endDate",
"frequency",
"maxPredicted",
"startDate"
],
"type": "object"
},
"type": "array"
},
"projectId": {
"description": "The project ID of the record.",
"type": "string"
},
"recordId": {
"description": "The ID of the anomaly assessment record.",
"type": "string"
},
"seriesId": {
"description": "The series id of the record. Applicable in multiseries projects",
"type": [
"string",
"null"
]
},
"source": {
"description": "The source of the record",
"enum": [
"training",
"validation"
],
"type": "string"
},
"startDate": {
"description": "ISO-formatted first timestamp in the subset. For example: ``2019-08-01T00:00:00.000000Z``.",
"format": "date-time",
"type": "string"
}
},
"required": [
"backtest",
"endDate",
"modelId",
"previewBins",
"projectId",
"recordId",
"seriesId",
"source",
"startDate"
],
"type": "object"
}
Responses
List Bias vs Accuracy insights by project ID
Operation path: GET /api/v2/projects/{projectId}/biasVsAccuracyInsights/
Authentication requirements: BearerAuth
Retrieve a list of Bias vs Accuracy insights for the model.
Parameters
| Name |
In |
Type |
Required |
Description |
| accuracyMetric |
query |
string |
false |
The metric to return model accuracy scores. Defaults to the optimization metric configured in project options. |
| protectedFeature |
query |
any |
false |
Name of the protected feature. |
| fairnessMetric |
query |
any |
false |
The fairness metric used to calculate the fairness scores. |
| projectId |
path |
string |
true |
The project ID |
Enumerated Values
| Parameter |
Value |
| accuracyMetric |
[AUC, Weighted AUC, Area Under PR Curve, Weighted Area Under PR Curve, Kolmogorov-Smirnov, Weighted Kolmogorov-Smirnov, FVE Binomial, Weighted FVE Binomial, Gini Norm, Weighted Gini Norm, LogLoss, Weighted LogLoss, Max MCC, Weighted Max MCC, Rate@Top5%, Weighted Rate@Top5%, Rate@Top10%, Weighted Rate@Top10%, Rate@TopTenth%, RMSE, Weighted RMSE] |
Example responses
200 Response
{
"properties": {
"data": {
"description": "An array of bias vs accuracy insights for the model.",
"items": {
"properties": {
"accuracyMetric": {
"description": "The metric to return model accuracy scores. Defaults to the optimization metric configured in project options.",
"enum": [
"AUC",
"Weighted AUC",
"Area Under PR Curve",
"Weighted Area Under PR Curve",
"Kolmogorov-Smirnov",
"Weighted Kolmogorov-Smirnov",
"FVE Binomial",
"Weighted FVE Binomial",
"Gini Norm",
"Weighted Gini Norm",
"LogLoss",
"Weighted LogLoss",
"Max MCC",
"Weighted Max MCC",
"Rate@Top5%",
"Weighted Rate@Top5%",
"Rate@Top10%",
"Weighted Rate@Top10%",
"Rate@TopTenth%",
"RMSE",
"Weighted RMSE"
],
"type": "string"
},
"fairnessMetric": {
"description": "The fairness metric used to calculate the fairness scores.",
"oneOf": [
{
"enum": [
"proportionalParity",
"equalParity",
"favorableClassBalance",
"unfavorableClassBalance",
"trueUnfavorableRateParity",
"trueFavorableRateParity",
"favorablePredictiveValueParity",
"unfavorablePredictiveValueParity"
],
"type": "string"
},
{
"items": {
"enum": [
"proportionalParity",
"equalParity",
"favorableClassBalance",
"unfavorableClassBalance",
"trueUnfavorableRateParity",
"trueFavorableRateParity",
"favorablePredictiveValueParity",
"unfavorablePredictiveValueParity"
],
"type": "string"
},
"type": "array"
}
]
},
"fairnessThreshold": {
"default": 0.8,
"description": "Value of the fairness threshold, defined in project options.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"models": {
"description": "An array of models of the insight.",
"items": {
"properties": {
"accuracyValue": {
"description": "The model's accuracy score.",
"minimum": 0,
"type": "number"
},
"bp": {
"description": "The blueprint number of the model from the leaderboard.",
"exclusiveMinimum": 0,
"type": "integer"
},
"dsName": {
"description": "The name of the feature list used for model training.",
"type": "string"
},
"fairnessValue": {
"description": "The model's relative fairness score for the class with the lowest fairness score. In other words, the fairness score of the least privileged class.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"modelId": {
"description": "ID of the model.",
"type": "string"
},
"modelNumber": {
"description": "The model number from the Leaderboard.",
"exclusiveMinimum": 0,
"type": "integer"
},
"modelType": {
"description": "The type/name of the model.",
"type": "string"
},
"prime": {
"description": "Flag to indicate whether the model is a prime model.",
"type": "boolean"
},
"samplepct": {
"description": "The sample size percentage of the feature list data the model was trained on.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"accuracyValue",
"bp",
"dsName",
"fairnessValue",
"modelId",
"modelNumber",
"modelType",
"prime",
"samplepct"
],
"type": "object"
},
"type": "array"
},
"protectedFeature": {
"description": "Name of the protected feature.",
"oneOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
}
]
}
},
"required": [
"fairnessThreshold",
"models"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data"
],
"type": "object"
}
Responses
List paginated Data Slices by project ID
Operation path: GET /api/v2/projects/{projectId}/dataSlices/
Authentication requirements: BearerAuth
Returns a paginated list of data slices for the given project ID.
Parameters
| Name |
In |
Type |
Required |
Description |
| limit |
query |
integer |
true |
The numbers of items to return. |
| offset |
query |
integer |
true |
The number of items to skip before starting to collect the result set. |
| searchQuery |
query |
string |
false |
Search query for data slices. |
| projectId |
path |
string |
true |
The project ID. |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated Data Slices.",
"items": {
"properties": {
"filters": {
"description": "List of filters the data slice is composed of.",
"items": {
"properties": {
"operand": {
"description": "Feature to apply operation to.",
"type": "string"
},
"operator": {
"description": "Operator to apply to the named operand in the dataset. The operator 'eq' mean 'equals the single specified value'. The operator 'in' means 'is one of a list of allowed values.'",
"enum": [
"eq",
"in",
"<",
">",
"between",
"notBetween"
],
"type": "string"
},
"values": {
"description": "Values to filter the operand by with the given operator.",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
}
]
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"required": [
"operand",
"operator",
"values"
],
"type": "object"
},
"maxItems": 3,
"minItems": 1,
"type": "array"
},
"id": {
"description": "ID of the data slice.",
"type": "string"
},
"name": {
"description": "User provided name for the data slice.",
"maxLength": 500,
"minLength": 1,
"type": "string"
},
"projectId": {
"description": "The project ID.",
"type": "string"
}
},
"required": [
"filters",
"id",
"name",
"projectId"
],
"type": "object"
},
"maxItems": 100,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
Retrieve the data by project ID
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/accuracyOverTimePlots/
Authentication requirements: BearerAuth
Retrieve the data for the Accuracy over Time plots.
Parameters
| Name |
In |
Type |
Required |
Description |
| seriesId |
query |
string |
false |
The name of the series to retrieve. Only available for time series multiseries projects. If not provided an average plot for the first 1000 series will be retrieved. |
| backtest |
query |
any |
false |
Retrieve plots for a specific backtest (use the backtest index starting from zero) or holdout. If not specified the first backtest (backtest index 0) will be used. |
| source |
query |
string |
false |
The source of the data for the backtest/holdout. |
| forecastDistance |
query |
integer |
false |
Forecast distance to retrieve the data for. If not specified, the first forecast distance for this project will be used. Forecast distance specifies the number of time steps between the predicted point and the origin point. Only available for time series supervised projects. |
| resolution |
query |
string |
false |
Specifying at which resolution the data should be binned. If not specified, optimal resolution will be used to build chart data with number of bins <= maxBinSize |
| maxBinSize |
query |
integer |
false |
Specifies the maximum number of bins for the retrieval. |
| startDate |
query |
string(date-time) |
false |
The start of the date range to return. If not specified, start date for requested plots will be used. |
| endDate |
query |
string(date-time) |
false |
The end of the date range to return. If not specified, end date for requested plots will be used. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| source |
[training, validation] |
| resolution |
[milliseconds, seconds, minutes, hours, days, weeks, months, quarters, years] |
Example responses
200 Response
{
"properties": {
"bins": {
"description": "An array of bins for the retrieved plots.",
"items": {
"properties": {
"actual": {
"description": "Average actual value of the target in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "Indicates number of values averaged in bin in case of a resolution change.",
"type": [
"integer",
"null"
]
},
"predicted": {
"description": "Average prediction of the model in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"frequency",
"predicted",
"startDate"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"calendarEvents": {
"description": "An array of calendar events for a retrieved plot.",
"items": {
"properties": {
"date": {
"description": "The date of the calendar event.",
"format": "date-time",
"type": "string"
},
"name": {
"description": "Name of the calendar event.",
"type": "string"
},
"seriesId": {
"description": "The series ID for the event. If this event does not specify a series ID, then this will be `null`, indicating that the event applies to all series.",
"type": [
"string",
"null"
]
}
},
"required": [
"date",
"name",
"seriesId"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). ",
"format": "date-time",
"type": "string"
},
"resolution": {
"description": "The resolution that is used for binning.",
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). ",
"format": "date-time",
"type": "string"
},
"statistics": {
"description": "Statistics calculated for the chart data.",
"properties": {
"durbinWatson": {
"description": "The Durbin-Watson statistic for the chart data. Value is between 0 and 4. Durbin-Watson statistic is a test statistic used to detect the presence of autocorrelation at lag 1 in the residuals (prediction errors) from a regression analysis. More info https://wikipedia.org/wiki/Durbin%E2%80%93Watson_statistic",
"maximum": 4,
"minimum": 0,
"type": [
"number",
"null"
]
}
},
"required": [
"durbinWatson"
],
"type": "object"
}
},
"required": [
"bins",
"calendarEvents",
"endDate",
"resolution",
"startDate",
"statistics"
],
"type": "object"
}
Responses
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/accuracyOverTimePlots/metadata/
Authentication requirements: BearerAuth
Retrieve the metadata for the Accuracy over Time insights.
| Name |
In |
Type |
Required |
Description |
| forecastDistance |
query |
integer |
false |
Forecast distance to retrieve the data for. If not specified, the first forecast distance for this project will be used. Forecast distance specifies the number of time steps between the predicted point and the origin point. Only available for time series supervised projects. |
| seriesId |
query |
string |
false |
The name of the series to retrieve. Only available for time series multiseries projects. If not provided a metadata of average plot for the first 1000 series will be retrieved. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| Accept |
header |
string |
false |
Requested MIME type for the returned data. |
Enumerated Values
| Parameter |
Value |
| Accept |
application/json |
Example responses
200 Response
{
"properties": {
"backtestMetadata": {
"description": "An array of metadata information for each backtest. The array index of metadata object is the backtest index.",
"items": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"backtestStatuses": {
"description": "An array of status information for each backtest. The array index of status object is the backtest index.",
"items": {
"description": "Status for accuracy over time plots.",
"properties": {
"training": {
"description": "The status for the training.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
},
"validation": {
"description": "The status for the validation.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"estimatedSeriesLimit": {
"description": "Estimated number of series that can be calculated in one request for 1 FD.",
"minimum": 1,
"type": "integer"
},
"forecastDistance": {
"description": "The forecast distance for which the data was retrieved. `null` for OTV projects.",
"maximum": 1000,
"minimum": 0,
"type": [
"integer",
"null"
]
},
"holdoutMetadata": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"holdoutStatuses": {
"description": "Status for accuracy over time plots.",
"properties": {
"training": {
"description": "The status for the training.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
},
"validation": {
"description": "The status for the validation.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"resolutions": {
"description": "An array of available time resolutions for which plots can be retrieved.",
"items": {
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"maxItems": 9,
"minItems": 1,
"type": "array"
}
},
"required": [
"backtestMetadata",
"backtestStatuses",
"forecastDistance",
"holdoutMetadata",
"holdoutStatuses",
"resolutions"
],
"type": "object"
}
Responses
Retrieve the preview by project ID
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/accuracyOverTimePlots/preview/
Authentication requirements: BearerAuth
Retrieve the preview for the Accuracy over Time plots.
Parameters
| Name |
In |
Type |
Required |
Description |
| seriesId |
query |
string |
false |
The name of the series to retrieve. Only available for time series multiseries projects. If not provided an average plot for the first 1000 series will be retrieved. |
| backtest |
query |
any |
false |
Retrieve plots for a specific backtest (use the backtest index starting from zero) or holdout. If not specified the first backtest (backtest index 0) will be used. |
| source |
query |
string |
false |
The source of the data for the backtest/holdout. |
| forecastDistance |
query |
integer |
false |
Forecast distance to retrieve the data for. If not specified, the first forecast distance for this project will be used. Forecast distance specifies the number of time steps between the predicted point and the origin point. Only available for time series supervised projects. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| source |
[training, validation] |
Example responses
200 Response
{
"properties": {
"bins": {
"description": "An array of bins for the retrieved plots.",
"items": {
"properties": {
"actual": {
"description": "Average actual value of the target in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"predicted": {
"description": "Average prediction of the model in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"predicted",
"startDate"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). ",
"format": "date-time",
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"bins",
"endDate",
"startDate"
],
"type": "object"
}
Responses
Retrieve anomaly over time plots by id
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/anomalyOverTimePlots/
Authentication requirements: BearerAuth
Retrieve the data for the Anomaly over Time plots.
Parameters
| Name |
In |
Type |
Required |
Description |
| seriesId |
query |
string |
false |
The name of the series to retrieve. Only available for time series multiseries projects. If not provided an average plot for the first 1000 series will be retrieved. |
| backtest |
query |
any |
false |
Retrieve plots for a specific backtest (use the backtest index starting from zero) or holdout. If not specified the first backtest (backtest index 0) will be used. |
| source |
query |
string |
false |
The source of the data for the backtest/holdout. |
| resolution |
query |
string |
false |
Specifying at which resolution the data should be binned. If not specified, optimal resolution will be used to build chart data with number of bins <= maxBinSize |
| maxBinSize |
query |
integer |
false |
Specifies the maximum number of bins for the retrieval. |
| startDate |
query |
string(date-time) |
false |
The start of the date range to return. If not specified, start date for requested plots will be used. |
| endDate |
query |
string(date-time) |
false |
The end of the date range to return. If not specified, end date for requested plots will be used. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| source |
[training, validation] |
| resolution |
[milliseconds, seconds, minutes, hours, days, weeks, months, quarters, years] |
Example responses
200 Response
{
"properties": {
"bins": {
"description": "An array of bins for the retrieved plots.",
"items": {
"properties": {
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "Indicates number of values averaged in bin in case of a resolution change.",
"type": [
"integer",
"null"
]
},
"predicted": {
"description": "Average prediction of the model in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"endDate",
"frequency",
"predicted",
"startDate"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"calendarEvents": {
"description": "An array of calendar events for a retrieved plot.",
"items": {
"properties": {
"date": {
"description": "The date of the calendar event.",
"format": "date-time",
"type": "string"
},
"name": {
"description": "Name of the calendar event.",
"type": "string"
},
"seriesId": {
"description": "The series ID for the event. If this event does not specify a series ID, then this will be `null`, indicating that the event applies to all series.",
"type": [
"string",
"null"
]
}
},
"required": [
"date",
"name",
"seriesId"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). ",
"format": "date-time",
"type": "string"
},
"resolution": {
"description": "The resolution that is used for binning.",
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"bins",
"calendarEvents",
"endDate",
"resolution",
"startDate"
],
"type": "object"
}
Responses
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/anomalyOverTimePlots/metadata/
Authentication requirements: BearerAuth
Retrieve the metadata for the Anomaly over Time insights.
| Name |
In |
Type |
Required |
Description |
| seriesId |
query |
string |
false |
The name of the series to retrieve. Only available for time series multiseries projects. If not provided a metadata of average plot for the first 1000 series will be retrieved. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| Accept |
header |
string |
false |
Requested MIME type for the returned data. |
Enumerated Values
| Parameter |
Value |
| Accept |
application/json |
Example responses
200 Response
{
"properties": {
"backtestMetadata": {
"description": "An array of metadata information for each backtest. The array index of metadata object is the backtest index.",
"items": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"backtestStatuses": {
"description": "An array of status information for each backtest. The array index of status object is the backtest index.",
"items": {
"description": "Status for accuracy over time plots.",
"properties": {
"training": {
"description": "The status for the training.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
},
"validation": {
"description": "The status for the validation.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"estimatedSeriesLimit": {
"description": "Estimated number of series that can be calculated in one request for 1 FD.",
"minimum": 1,
"type": "integer"
},
"holdoutMetadata": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"holdoutStatuses": {
"description": "Status for accuracy over time plots.",
"properties": {
"training": {
"description": "The status for the training.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
},
"validation": {
"description": "The status for the validation.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"resolutions": {
"description": "An array of available time resolutions for which plots can be retrieved.",
"items": {
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"maxItems": 9,
"minItems": 1,
"type": "array"
}
},
"required": [
"backtestMetadata",
"backtestStatuses",
"holdoutMetadata",
"holdoutStatuses",
"resolutions"
],
"type": "object"
}
Responses
Retrieve preview by id
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/anomalyOverTimePlots/preview/
Authentication requirements: BearerAuth
Retrieve the preview for the Anomaly over Time plots.
Parameters
| Name |
In |
Type |
Required |
Description |
| seriesId |
query |
string |
false |
The name of the series to retrieve. Only available for time series multiseries projects. If not provided an average plot for the first 1000 series will be retrieved. |
| backtest |
query |
any |
false |
Retrieve plots for a specific backtest (use the backtest index starting from zero) or holdout. If not specified the first backtest (backtest index 0) will be used. |
| source |
query |
string |
false |
The source of the data for the backtest/holdout. |
| predictionThreshold |
query |
number |
false |
Only bins with predictions exceeding this threshold will be returned in the response. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| source |
[training, validation] |
Example responses
200 Response
{
"properties": {
"bins": {
"description": "An array of bins for the retrieved plots.",
"items": {
"properties": {
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). ",
"format": "date-time",
"type": "string"
},
"predictionThreshold": {
"description": "Only bins with predictions exceeding this threshold are returned in the response.",
"exclusiveMinimum": 0,
"maximum": 1,
"type": "number"
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"bins",
"endDate",
"predictionThreshold",
"startDate"
],
"type": "object"
}
Responses
Retrieve a plot displaying the stability of the datetime model across by project ID
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/backtestStabilityPlot/
Authentication requirements: BearerAuth
Retrieve a plot displaying the stability of the datetime model across different backtests.
All durations and datetimes should be specified in accordance with the :ref:timestamp and duration formatting rules<time_format>.
Parameters
| Name |
In |
Type |
Required |
Description |
| metricName |
query |
string |
false |
The name of the metric to retrieve the scores for. If omitted, the default project metric will be used |
| forecastDistance |
query |
integer |
false |
The forecast distance to retrieve the plot for. If not specified, the scores for each partition are aggregated across all forecast distances. This parameter is only available for time series models. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"backtestPlotData": {
"description": "An array of objects containing the details of the scores for each partition defined for the project.",
"items": {
"properties": {
"backtestIndex": {
"description": "An integer representing the index of the backtest, starting from 0. For holdout, this field will be null.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"partition": {
"description": "Identifier of the partition. Can either identify a specific backtest (\"backtest0\", \"backtest1\", ...) or the holdout set (\"holdout\").",
"type": "string"
},
"score": {
"description": "Score for this partition. Can be null if the score is unavailable for this partition (e.g. holdout is locked or backtesting has not been run yet).",
"type": [
"number",
"null"
]
},
"scoringEndDate": {
"description": "End date of the subset used for scoring.",
"format": "date-time",
"type": "string"
},
"scoringStartDate": {
"description": "Start date of the subset used for scoring.",
"format": "date-time",
"type": "string"
}
},
"required": [
"backtestIndex",
"partition",
"score",
"scoringEndDate",
"scoringStartDate"
],
"type": "object"
},
"type": "array"
},
"endDate": {
"description": "End date of the project dataset.",
"format": "date-time",
"type": "string"
},
"metricName": {
"description": "Name of the metric used to compute the scores.",
"type": "string"
},
"startDate": {
"description": "Start date of the project dataset.",
"format": "date-time",
"type": "string"
}
},
"required": [
"backtestPlotData",
"endDate",
"metricName",
"startDate"
],
"type": "object"
}
Responses
Retrieve the Accuracy Over Time (AOT) chart data by project ID
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/datasetAccuracyOverTimePlots/{datasetId}/
Authentication requirements: BearerAuth
Retrieve the Accuracy Over Time (AOT) chart data for an external dataset for a project.
Datetimes are specified in accordance with :ref:timestamp and duration formatting rules <time_format>.
Parameters
| Name |
In |
Type |
Required |
Description |
| maxBinSize |
query |
integer |
false |
The limit of returned bins. |
| startDate |
query |
string(date-time) |
false |
The start of the date range to return (UTC string), for example: '2010-05-13T00:00:00.000000Z'. If not specified, the start date for this model and source of the data will be used instead. |
| endDate |
query |
string(date-time) |
false |
The end of the date range to return (UTC string), for example: '2010-05-13T00:00:00.000000Z'. If not specified, the end date for this model and source of the data will be used instead. |
| resolution |
query |
string |
false |
Specifies at which resolution the data should be binned. If not specified, optimal resolution will be used to build chart data such that bins <= maxBinSize. |
| projectId |
path |
string |
true |
The project id which was used to compute the AOT chart. |
| modelId |
path |
string |
true |
The model id which was used to compute the AOT chart. |
| datasetId |
path |
string |
true |
The dataset id which was used to compute the AOT chart. |
Enumerated Values
| Parameter |
Value |
| resolution |
[microseconds, milliseconds, seconds, minutes, hours, days, weeks, months, quarters, years] |
Example responses
200 Response
{
"properties": {
"bins": {
"description": "The datetime chart data for that source.",
"items": {
"properties": {
"actual": {
"description": "The average actual value of the target in the bin. ``null`` if there are no entries in the bin or if this is an anomaly detection project.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive).",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "As indicated by the frequencyType in the Metadata, used to determine what the averages mentioned above are taken over. ``null`` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"predicted": {
"description": "The average prediction of the model in the bin. ``null`` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive).",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"frequency",
"predicted",
"startDate"
],
"type": "object"
},
"type": "array"
},
"datasetId": {
"description": "The dataset id to which the chart data belongs.",
"type": "string"
},
"endDate": {
"description": "The requested `endDate`, or, if not specified, the end date for this dataset (exclusive). Example: '2010-05-13T00:00:00.000000Z'.",
"format": "date-time",
"type": "string"
},
"modelId": {
"description": "The model id to which the chart data belongs.",
"type": "string"
},
"projectId": {
"description": "The project id to which the chart data belongs.",
"type": "string"
},
"resolution": {
"description": "The resolution used for binning where a resolution is one of ['milliseconds', 'seconds', 'minutes', 'hours', 'days', 'weeks', 'months', 'years'].",
"enum": [
"microseconds",
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"startDate": {
"description": "The requested `startDate`, or, if not specified, the start date for this dataset. Example: '2010-05-13T00:00:00.000000Z'.",
"format": "date-time",
"type": "string"
},
"statistics": {
"description": "Statistics calculated on the chart data.",
"properties": {
"durbinWatson": {
"description": "The Durbin-Watson statistic for the chart data. Value is between 0 and 4. Returns -1 when the statistic is invalid for the data, e.g. if this is an anomaly detection project.",
"type": "number"
}
},
"required": [
"durbinWatson"
],
"type": "object"
}
},
"required": [
"bins",
"datasetId",
"modelId",
"projectId",
"resolution",
"statistics"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Accuracy Over Time (AOT) chart data for an external dataset for a project. |
AOTChartRetrieveResponse |
| 404 |
Not Found |
No insights found. |
None |
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/datasetAccuracyOverTimePlots/{datasetId}/metadata/
Authentication requirements: BearerAuth
Retrieve the metadata of the Accuracy Over Time (AOT) chart for an external dataset.
Datetimes are specified in accordance with :ref:timestamp and duration formatting rules <time_format>.
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project id which was used to compute the AOT chart. |
| modelId |
path |
string |
true |
The model id which was used to compute the AOT chart. |
| datasetId |
path |
string |
true |
The dataset id which was used to compute the AOT chart. |
Example responses
200 Response
{
"properties": {
"datasetId": {
"description": "The dataset id which was used to compute the AOT chart.",
"type": "string"
},
"datasetMetadata": {
"description": "The dataset metadata.",
"properties": {
"endDate": {
"description": "ISO-8601 formatted end date (max date) in the dataset.",
"format": "date-time",
"type": "string"
},
"startDate": {
"description": "ISO-8601 formatted start date (min date) in the dataset.",
"format": "date-time",
"type": "string"
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"frequencyType": {
"description": "How to interpret the frequency attribute of each datetimeTrendBin. One of ['rowCount', 'weightedRowCount', 'exposure', 'weightedExposure'].",
"enum": [
"rowCount",
"weightedRowCount",
"exposure",
"weightedExposure"
],
"type": "string"
},
"metricName": {
"description": "The metric used to score each bin and the calculate the metric attribute of each datetimeTrendBin.",
"type": "string"
},
"modelId": {
"description": "The model id which was used to compute the AOT chart.",
"type": "string"
},
"projectId": {
"description": "The project id which was used to compute the AOT chart.",
"type": "string"
},
"resolutions": {
"description": "Suggested time resolutions where a resolution is one of ['milliseconds', 'seconds', 'minutes', 'hours', 'days', 'weeks', 'months', 'years'].",
"items": {
"enum": [
"microseconds",
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"type": "array"
}
},
"required": [
"datasetId",
"datasetMetadata",
"frequencyType",
"metricName",
"modelId",
"projectId",
"resolutions"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Metadata of the Accuracy Over Time (AOT) chart for an external dataset. |
AOTChartMetadataResponse |
| 404 |
Not Found |
No insights found. |
None |
Retrieve a preview of the Accuracy Over Time (AOT) chart by project ID
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/datasetAccuracyOverTimePlots/{datasetId}/preview/
Authentication requirements: BearerAuth
Retrieve a preview of the Accuracy Over Time (AOT) chart for an external dataset.
Datetimes are specified in accordance with :ref:timestamp and duration formatting rules <time_format>.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project id which was used to compute the AOT chart. |
| modelId |
path |
string |
true |
The model id which was used to compute the AOT chart. |
| datasetId |
path |
string |
true |
The dataset id which was used to compute the AOT chart. |
Example responses
200 Response
{
"properties": {
"bins": {
"description": "The datetime chart data for that source.",
"items": {
"properties": {
"actual": {
"description": "The average actual value of the target in the bin. ``null`` if there are no entries in the bin or if this is an anomaly detection project.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive).",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "As indicated by the frequencyType in the Metadata, used to determine what the averages mentioned above are taken over. ``null`` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"predicted": {
"description": "The average prediction of the model in the bin. ``null`` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive).",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"frequency",
"predicted",
"startDate"
],
"type": "object"
},
"type": "array"
},
"datasetId": {
"description": "The dataset id which was used to compute the AOT chart.",
"type": "string"
},
"modelId": {
"description": "The model id which was used to compute the AOT chart.",
"type": "string"
},
"projectId": {
"description": "The project id which was used to compute the AOT chart.",
"type": "string"
}
},
"required": [
"bins",
"datasetId",
"modelId",
"projectId"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Preview of the Accuracy Over Time (AOT) chart for an external dataset. |
AOTChartPreviewResponse |
| 404 |
Not Found |
No insights found. |
None |
Computes Datetime Trend plots by project ID
Operation path: POST /api/v2/projects/{projectId}/datetimeModels/{modelId}/datetimeTrendPlots/
Authentication requirements: BearerAuth
Computes Datetime Trend plots for time series and OTV projects:
* For OTV projects, computes Accuracy over Time plots.
* For time series supervised projects, computes both Accuracy over Time plots and Forecast vs Actual plots.
.. minversion:: v2.25
* For unsupervised time series and OTV models, computes Anomaly Over Time plots.
.. note::
For the multiseries time series projects only first 1000 series in alphabetical order and an average plot for them will be computed.
.. note::
Maximum 100 forecast distances can be requested for calculation in time series supervised projects.
Body parameter
{
"properties": {
"backtest": {
"default": 0,
"description": "Compute plots for a specific backtest (use the backtest index starting from zero) or `holdout`. If not specified the first backtest (backtest index 0) will be used.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
]
},
"forecastDistanceEnd": {
"description": "The end of forecast distance range (forecast window) to compute. If not specified, the last forecast distance for this project will be used. Forecast distance specifies the number of time steps between the predicted point and the origin point. Only available for time series supervised projects.",
"minimum": 0,
"type": "integer"
},
"forecastDistanceStart": {
"description": "The start of forecast distance range (forecast window) to compute. If not specified, the first forecast distance for this project will be used. Forecast distance specifies the number of time steps between the predicted point and the origin point. Only available for time series supervised projects.",
"minimum": 0,
"type": "integer"
},
"fullAverage": {
"default": false,
"description": "Whether to compute an average plot for all series. Only available for time series multiseries projects.",
"type": "boolean",
"x-versionadded": "2.28"
},
"seriesIds": {
"description": "Only available for time series multiseries projects. Each element should be a name of a single series in a multiseries project. It is possible to compute a maximum of 1000 series per one request. If not specified the first 1000 series in alphabetical order will be computed. It is not possible to specify `fullAverage: true` while also setting `seriesIds`. This parameter can only be specified after first 1000 series in alphabetical order are computed.",
"items": {
"type": "string"
},
"maxItems": 1000,
"minItems": 1,
"type": "array",
"x-versionadded": "2.28"
},
"source": {
"default": "validation",
"description": "The source of the data for the backtest/holdout.",
"enum": [
"training",
"validation"
],
"type": "string"
}
},
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| body |
body |
DatetimeTrendPlotsCreate |
false |
none |
Example responses
202 Response
{
"properties": {
"message": {
"description": "Any extended message to include about the result. For example, if a job is submitted that is a duplicate of a job that has already been added to the queue, the message will mention that no new job can be created.",
"type": "string"
}
},
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Retrieve Feature Effects by project ID
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/featureEffects/
Authentication requirements: BearerAuth
Retrieve Feature Effects for a model backtest.
Feature Effects provides partial dependence and predicted vs actual values for the top 500 features, ordered by feature impact score.
The partial dependence shows marginal effect of a feature on the target variable after accounting for the average effects of all other predictive features. It indicates how, holding all other variables except the feature of interest as they were, the value of this feature affects your prediction.
If a Feature Effects job was previously submitted for a given backtest, this endpoint will return a response structured as {"message": , "jobId": } where jobId is the ID of the job. Retrieve the job with [GET /api/v2/projects/{projectId}/jobs/{jobId}/][get-apiv2projectsprojectidjobsjobid].
Parameters
| Name |
In |
Type |
Required |
Description |
| source |
query |
string |
false |
Models data source. |
| backtestIndex |
query |
string |
true |
The backtest index. For example: 0, 1, ..., 20, holdout, startstop. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| source |
[training, validation, holdout] |
Example responses
200 Response
{
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`, `startstop`.",
"type": "string"
},
"featureEffects": {
"description": "Feature Effects computational results for each feature.",
"items": {
"properties": {
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model ID",
"type": "string"
},
"projectId": {
"description": "The project ID",
"type": "string"
},
"source": {
"description": "Models data source.",
"type": "string"
}
},
"required": [
"backtestIndex",
"featureEffects",
"modelId",
"projectId",
"source"
],
"type": "object"
}
Responses
Add a request by project ID
Operation path: POST /api/v2/projects/{projectId}/datetimeModels/{modelId}/featureEffects/
Authentication requirements: BearerAuth
Add a request to the queue to calculate Feature Effects for a backtest.
If the job has been previously submitted, the request fails, returning the jobId of the previously submitted job. Use this jobId to check status of the previously submitted job.
Body parameter
{
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`, `startstop`.",
"type": "string"
},
"rowCount": {
"description": "The number of rows from dataset to use for Feature Impact calculation.",
"maximum": 100000,
"minimum": 10,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.21"
}
},
"required": [
"backtestIndex"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| body |
body |
FeatureEffectsCreateDatetime |
false |
none |
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
The Feature Effects request for a backtest has been successfully submitted. See Location header. |
None |
| 403 |
Forbidden |
User does not have permission to view or submit jobs for the project. |
None |
| 404 |
Not Found |
Provided project, model, or backtest index does not exist. |
None |
| 422 |
Unprocessable Entity |
Queue submission error. |
None |
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/featureEffectsMetadata/
Authentication requirements: BearerAuth
Retrieve Feature Effects metadata for each backtest. Response contains status and available sources for each backtest of the model.
One of the provided backtestIndex indexes used for submitting the compute request and retrieving Feature Effects.
* Start/stop models contain a single backtestIndex response value of startstop.
* Other models contain backtestIndex of 0, 1, ..., holdout.
One of the provided source parameters used for retrieving Feature Effects.
* Each backtest source can be, at a minimum, training or validation. If holdout is configured for the project, backtestIndex also includes holdout with sources training and holdout.
* Source value of training is always available. (versions prior to v2.17 support validation only)
* When a start/stop model is trained into validation or holdout without stacked predictions (i.e., no out-of-sample predictions in validation or holdout), validation and holdout sources are not available.
* Source holdout is not available when there is no holdout configured for the project.
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"data": {
"description": "List of objects with status and sources of each backtest.",
"items": {
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`, `startstop`.",
"type": "string"
},
"sources": {
"description": "List of sources available for the model.",
"items": {
"enum": [
"training",
"validation",
"holdout"
],
"type": "string"
},
"type": "array"
},
"status": {
"description": "Status of the job.",
"enum": [
"INPROGRESS",
"COMPLETED",
"NOT_COMPLETED"
],
"type": "string"
}
},
"required": [
"backtestIndex",
"sources",
"status"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data"
],
"type": "object"
}
Responses
Retrieve a plot displaying the stability of the time series model across by project ID
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/forecastDistanceStabilityPlot/
Authentication requirements: BearerAuth
Retrieve a plot displaying the stability of the time series model across different forecast distances.
.. note::
All durations and datetimes are specified in accordance with the :ref:timestamp and duration formatting rules <time_format>.
Parameters
| Name |
In |
Type |
Required |
Description |
| metricName |
query |
string |
false |
The name of the metric to retrieve the scores for. If omitted, the default project metric will be used. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"endDate": {
"description": "ISO-formatted start date of the project dataset.",
"format": "date-time",
"type": "string"
},
"forecastDistancePlotData": {
"description": "An array of objects containing the details of the scores for each forecast distance.",
"items": {
"properties": {
"backtestingScore": {
"description": "Backtesting score for this forecast distance. If backtesting has not been run for this model, this score will be `null`.",
"type": [
"number",
"null"
]
},
"forecastDistance": {
"description": "The number of time units the scored rows are away from the forecast point.",
"type": "integer"
},
"holdoutScore": {
"description": "Holdout set score for this forecast distance. If holdout is locked for the project, this score will be `null`.",
"type": [
"number",
"null"
]
},
"validationScore": {
"description": "Validation set score for this forecast distance.",
"type": "number"
}
},
"required": [
"backtestingScore",
"forecastDistance",
"holdoutScore",
"validationScore"
],
"type": "object"
},
"type": "array"
},
"metricName": {
"description": "Name of the metric used to compute the scores.",
"type": "string"
},
"startDate": {
"description": "ISO-formatted start date of the project dataset.",
"format": "date-time",
"type": "string"
}
},
"required": [
"endDate",
"forecastDistancePlotData",
"metricName",
"startDate"
],
"type": "object"
}
Responses
Retrieve forecast vs actual plots by id
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/forecastVsActualPlots/
Authentication requirements: BearerAuth
Retrieve the data for the Forecast vs Actual plots.
Parameters
| Name |
In |
Type |
Required |
Description |
| seriesId |
query |
string |
false |
The name of the series to retrieve. Only available for time series multiseries projects. If not provided an average plot for the first 1000 series will be retrieved. |
| backtest |
query |
any |
false |
Retrieve plots for a specific backtest (use the backtest index starting from zero) or holdout. If not specified the first backtest (backtest index 0) will be used. |
| source |
query |
string |
false |
The source of the data for the backtest/holdout. |
| resolution |
query |
string |
false |
Specifying at which resolution the data should be binned. If not specified, optimal resolution will be used to build chart data with number of bins <= maxBinSize |
| forecastDistanceStart |
query |
integer |
false |
The start of forecast distance range (forecast window) to retrieve. If not specified, the first forecast distance for this project will be used. Forecast distance specifies the number of time steps between the predicted point and the origin point. Only available for time series supervised projects. |
| forecastDistanceEnd |
query |
integer |
false |
The end of forecast distance range (forecast window) to retrieve. If not specified, the last forecast distance for this project will be used. Forecast distance specifies the number of time steps between the predicted point and the origin point. Only available for time series supervised projects. |
| maxBinSize |
query |
integer |
false |
Specifies the maximum number of bins for the retrieval. |
| startDate |
query |
string(date-time) |
false |
The start of the date range to return. If not specified, start date for requested plots will be used. |
| endDate |
query |
string(date-time) |
false |
The end of the date range to return. If not specified, end date for requested plots will be used. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| source |
[training, validation] |
| resolution |
[milliseconds, seconds, minutes, hours, days, weeks, months, quarters, years] |
Example responses
200 Response
{
"properties": {
"bins": {
"description": "An array of bins for the retrieved plots.",
"items": {
"properties": {
"actual": {
"description": "Average actual value of the target in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"error": {
"description": "Average absolute residual value of the bin. `null` if there are no entries in the bin.",
"minimum": 0,
"type": [
"number",
"null"
]
},
"forecasts": {
"description": "An array of average forecasts for the model for each forecast distance. Empty if there are no forecasts in the bin. Each index in the `forecasts` array maps to `forecastDistances` array index.",
"items": {
"type": "number"
},
"maxItems": 100,
"type": "array"
},
"frequency": {
"description": "Indicates number of values averaged in bin in case of a resolution change.",
"type": [
"integer",
"null"
]
},
"normalizedError": {
"description": "Normalized average absolute residual value of the bin. `null` if there are no entries in the bin.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"error",
"forecasts",
"frequency",
"normalizedError",
"startDate"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"calendarEvents": {
"description": "An array of calendar events for a retrieved plot.",
"items": {
"properties": {
"date": {
"description": "The date of the calendar event.",
"format": "date-time",
"type": "string"
},
"name": {
"description": "Name of the calendar event.",
"type": "string"
},
"seriesId": {
"description": "The series ID for the event. If this event does not specify a series ID, then this will be `null`, indicating that the event applies to all series.",
"type": [
"string",
"null"
]
}
},
"required": [
"date",
"name",
"seriesId"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). ",
"format": "date-time",
"type": "string"
},
"forecastDistances": {
"description": "An array of forecast distances. Forecast distance specifies the number of time steps between the predicted point and the origin point.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 100,
"minItems": 1,
"type": "array"
},
"resolution": {
"description": "The resolution that is used for binning.",
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"bins",
"calendarEvents",
"endDate",
"forecastDistances",
"resolution",
"startDate"
],
"type": "object"
}
Responses
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/forecastVsActualPlots/metadata/
Authentication requirements: BearerAuth
Retrieve the metadata for the Forecast vs Actual insights.
| Name |
In |
Type |
Required |
Description |
| seriesId |
query |
string |
false |
The name of the series to retrieve. Only available for time series multiseries projects. If not provided a metadata of average plot for the first 1000 series will be retrieved. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| Accept |
header |
string |
false |
Requested MIME type for the returned data. |
Enumerated Values
| Parameter |
Value |
| Accept |
application/json |
Example responses
200 Response
{
"properties": {
"backtestMetadata": {
"description": "An array of metadata information for each backtest. The array index of metadata object is the backtest index.",
"items": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"backtestStatuses": {
"description": "An array of status information for each backtest. The array index of status object is the backtest index.",
"items": {
"description": "Status for forecast vs actual plots.",
"properties": {
"training": {
"description": "Status for backtest/holdout training.",
"properties": {
"completed": {
"description": "An array of available forecast distances for the `completed` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"errored": {
"description": "An array of available forecast distances for the `errored` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"inProgress": {
"description": "An array of available forecast distances for the `inProgress` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"insufficientData": {
"description": "An array of available forecast distances for the `insufficientData` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"notCompleted": {
"description": "An array of available forecast distances for the `notCompleted` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"type": "object"
},
"validation": {
"description": "Status for backtest/holdout training.",
"properties": {
"completed": {
"description": "An array of available forecast distances for the `completed` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"errored": {
"description": "An array of available forecast distances for the `errored` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"inProgress": {
"description": "An array of available forecast distances for the `inProgress` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"insufficientData": {
"description": "An array of available forecast distances for the `insufficientData` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"notCompleted": {
"description": "An array of available forecast distances for the `notCompleted` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"estimatedSeriesLimit": {
"description": "Estimated number of series that can be calculated in one request for 1 FD.",
"minimum": 1,
"type": "integer"
},
"holdoutMetadata": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"holdoutStatuses": {
"description": "Status for forecast vs actual plots.",
"properties": {
"training": {
"description": "Status for backtest/holdout training.",
"properties": {
"completed": {
"description": "An array of available forecast distances for the `completed` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"errored": {
"description": "An array of available forecast distances for the `errored` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"inProgress": {
"description": "An array of available forecast distances for the `inProgress` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"insufficientData": {
"description": "An array of available forecast distances for the `insufficientData` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"notCompleted": {
"description": "An array of available forecast distances for the `notCompleted` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"type": "object"
},
"validation": {
"description": "Status for backtest/holdout training.",
"properties": {
"completed": {
"description": "An array of available forecast distances for the `completed` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"errored": {
"description": "An array of available forecast distances for the `errored` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"inProgress": {
"description": "An array of available forecast distances for the `inProgress` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"insufficientData": {
"description": "An array of available forecast distances for the `insufficientData` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"notCompleted": {
"description": "An array of available forecast distances for the `notCompleted` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"resolutions": {
"description": "An array of available time resolutions for which plots can be retrieved.",
"items": {
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"maxItems": 9,
"minItems": 1,
"type": "array"
}
},
"required": [
"backtestMetadata",
"backtestStatuses",
"holdoutMetadata",
"holdoutStatuses",
"resolutions"
],
"type": "object"
}
Responses
Retrieve preview by id
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/forecastVsActualPlots/preview/
Authentication requirements: BearerAuth
Retrieve the preview for the Forecast vs Actual plots.
Parameters
| Name |
In |
Type |
Required |
Description |
| seriesId |
query |
string |
false |
The name of the series to retrieve. Only available for time series multiseries projects. If not provided an average plot for the first 1000 series will be retrieved. |
| backtest |
query |
any |
false |
Retrieve plots for a specific backtest (use the backtest index starting from zero) or holdout. If not specified the first backtest (backtest index 0) will be used. |
| source |
query |
string |
false |
The source of the data for the backtest/holdout. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| source |
[training, validation] |
Example responses
200 Response
{
"properties": {
"bins": {
"description": "An array of bins for the retrieved plots.",
"items": {
"properties": {
"actual": {
"description": "Average actual value of the target in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"predicted": {
"description": "Average prediction of the model in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"predicted",
"startDate"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). ",
"format": "date-time",
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"bins",
"endDate",
"startDate"
],
"type": "object"
}
Responses
Retrieve feature effects by project ID
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/multiclassFeatureEffects/
Authentication requirements: BearerAuth
Retrieve feature effects for each class in a multiclass datetime model.
Parameters
| Name |
In |
Type |
Required |
Description |
| source |
query |
string |
false |
Models data source. |
| backtestIndex |
query |
string |
true |
The backtest index. For example: 0, 1, ..., 20, holdout, startstop. |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
false |
At most this many results are returned. The default may change without notice. |
| class |
query |
string,null |
false |
Target class label. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| source |
[training, validation, holdout] |
Example responses
200 Response
{
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`, `startstop`.",
"type": "string"
},
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "A list of feature effects scores for each class in multiclass project.",
"items": {
"properties": {
"class": {
"description": "Target class label.",
"type": "string"
},
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"class",
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model ID",
"type": "string"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID",
"type": "string"
},
"source": {
"description": "Models data source.",
"type": "string"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"backtestIndex",
"data",
"modelId",
"next",
"previous",
"projectId",
"source",
"totalCount"
],
"type": "object"
}
Responses
Compute feature effects by project ID
Operation path: POST /api/v2/projects/{projectId}/datetimeModels/{modelId}/multiclassFeatureEffects/
Authentication requirements: BearerAuth
Compute feature effects for a multiclass datetime model. If the job has been previously submitted, the request fails, returning the jobId of the previously submitted job. Use this jobId to check status of the previously submitted job.
NOTE: feature effects are computed for top 100 classes.
Body parameter
{
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`, `startstop`.",
"type": "string"
},
"features": {
"description": "The list of features to use to calculate feature effects.",
"items": {
"type": "string"
},
"maxItems": 20000,
"type": "array"
},
"rowCount": {
"description": "The number of rows from dataset to use for Feature Impact calculation.",
"maximum": 100000,
"minimum": 10,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.21"
},
"topNFeatures": {
"description": "Number of top features (ranked by feature impact) to use to calculate feature effects.",
"exclusiveMinimum": 0,
"maximum": 1000,
"type": [
"integer",
"null"
]
}
},
"required": [
"backtestIndex"
],
"type": "object"
}
Parameters
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
The Feature Effects request has been successfully submitted. See Location header. |
None |
| 403 |
Forbidden |
User does not have permission to view or submit jobs for the project. |
None |
| 404 |
Not Found |
Project, model, source or computation results do not exist. |
None |
| 422 |
Unprocessable Entity |
Queue submission error. If the rowCount exceeds the maximum or minimum value for this dataset. Minimum is 10 rows. Maximum is 100000 rows or the training sample size of the model, whichever is less. If invalid class names are provided in classes.If neither features nor topNFeatures is provided. If invalid backtestIndex is provided. |
None |
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Retrieve the histograms by project ID
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/multiseriesHistograms/
Authentication requirements: BearerAuth
Retrieve the histograms for series insights.
Histogram is computed only for first 1000 series (ordered by name).
Parameters
| Name |
In |
Type |
Required |
Description |
| attribute |
query |
string |
true |
The series attribute to build a histogram for. |
| metric |
query |
string |
false |
The name of the metric to retrieve the histogram for attributes "validationScore", "backtestingScore", and"holdoutScore". If omitted, the default project metric will be used. |
| bins |
query |
string |
true |
The number of bins in a histogram. Can be 10, 20 or 50. The default is 10. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| attribute |
[rowCount, duration, startDate, endDate, targetAverage, validationScore, backtestingScore, holdoutScore, rowPercent, clusterCount, clustering] |
| bins |
[10, 20, 50] |
Example responses
200 Response
{
"properties": {
"bins": {
"description": "List of bins representing histogram.",
"items": {
"properties": {
"count": {
"description": "The value count of the bin",
"type": "integer"
},
"left": {
"description": "The inclusive left boundary of the bin.",
"oneOf": [
{
"type": "number"
},
{
"type": "string"
}
]
},
"right": {
"description": "The exclusive right boundary of the bin. The last bin has an inclusive right boundary.",
"oneOf": [
{
"type": "number"
},
{
"type": "string"
}
]
}
},
"required": [
"count",
"left",
"right"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"bins"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieve the histograms for series insights in form of an array of histogram bins. |
MultiseriesHistogramsRetrieveResponse |
| 403 |
Forbidden |
User does not have permissions to manage models. |
None |
| 404 |
Not Found |
Model with specified modelId doesn't exist, or user does not have access to the project. |
None |
| 422 |
Unprocessable Entity |
Metric provided to query is not found. |
None |
List the scores per individual series by project ID
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/multiseriesScores/
Authentication requirements: BearerAuth
List the scores per individual series for the specified multiseries model.
Parameters
| Name |
In |
Type |
Required |
Description |
| multiseriesValue |
query |
string |
false |
Only the series containing the given value in one of the series ID columns will be returned if specified. |
| offset |
query |
integer |
true |
The number of results to skip. Defaults to 0 if not specified. |
| limit |
query |
integer |
true |
The maximum number of results to return. Defaults to 100 if not specified. |
| metric |
query |
string |
false |
The name of the metric to retrieve the scores for.If omitted, the default project metric will be used. |
| orderBy |
query |
string |
false |
Used for sorting the series. Supported attributes for ordering include: "multiseriesValue", "rowCount", "validationScore", "holdoutScore" and "backtestingScore", "startDate", "endDate", and "targetAverage".Prefix the attribute name with a dash to sort in descending order,e.g. orderBy=-rowCount. If multiple series with equal values of the ordering attributeexist, ties will be broken arbitrarily. |
| filterBy |
query |
string |
false |
Used to specify on which attribute values to filter the series.Supported attributes for filtering include: "rowCount", "startDate", "endDate", "targetAverage", "validationScore", "holdoutScore", and "backtestingScore".filterByBins and numberOfBins are required if this parameter is used. |
| numberOfBins |
query |
string |
false |
Used to specify the number of bins in the histogram on which to filter the series.Can be 10, 20 or 50.filterBy and filterByBins are required if this parameter is used. |
| filterByBins |
query |
string |
false |
Used to specify the multiseries histogram bins on which to filter the series.filterBy and numberOfBins are required if this parameter is used. |
| clusterNames |
query |
string |
false |
Used to specify the specific cluster on which to filter the series.filterBy is required if this parameter is used.Only valid for unsupervised clustering projects. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| orderBy |
[multiseriesValue, -multiseriesValue, rowCount, -rowCount, startDate, -startDate, endDate, -endDate, targetAverage, -targetAverage, validationScore, -validationScore, backtestingScore, -backtestingScore, holdoutScore, -holdoutScore, cluster, -cluster] |
| filterBy |
[rowCount, startDate, endDate, targetAverage, validationScore, backtestingScore, holdoutScore, cluster] |
| numberOfBins |
[10, 20, 50] |
Example responses
200 Response
{
"properties": {
"data": {
"description": "An array of available multiseries identifiers and column values.",
"items": {
"properties": {
"backtestingScore": {
"description": "The backtesting score for this series. If backtesting has not been run for this model, this score will be null.",
"type": [
"number",
"null"
]
},
"cluster": {
"description": "The cluster associated with this series. ",
"type": [
"string",
"null"
]
},
"duration": {
"description": "The duration of this series formatted as an ISO 8601 duration string.",
"format": "duration",
"type": "string"
},
"endDate": {
"description": "The ISO-formatted end date of this series.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"holdoutScore": {
"description": "The holdout set score for this series. If holdout is locked for the project, this score will be null.",
"type": [
"number",
"null"
]
},
"multiseriesId": {
"description": "A DataRobot-generated ID corresponding to a single series in a multiseries dataset.",
"type": "string"
},
"multiseriesValues": {
"description": "The actual values of series ID columns from the dataset.",
"items": {
"type": "string"
},
"type": "array"
},
"rowCount": {
"description": "The number of rows available for this series in the input dataset.",
"type": "integer"
},
"startDate": {
"description": "The ISO-formatted start date of this series.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"targetAverage": {
"description": "For regression projects, this is the average (mean) value of target values for this series.For classification projects, this is the ratio of the positive class in the target for this series.",
"oneOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "null"
}
]
},
"validationScore": {
"description": "The validation set score for this series",
"type": [
"number",
"null"
]
}
},
"required": [
"backtestingScore",
"duration",
"multiseriesId",
"multiseriesValues",
"rowCount",
"validationScore"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "A URL pointing to the next page (if null, there is no next page).",
"type": [
"string",
"null"
]
},
"previous": {
"description": "A URL pointing to the previous page (if null, there is no previous page).",
"type": [
"string",
"null"
]
},
"querySeriesCount": {
"description": "The total number of series after filtering is applied.",
"type": "integer"
},
"totalSeriesCount": {
"description": "The total number of series in the project dataset.",
"type": "integer"
}
},
"required": [
"data",
"querySeriesCount",
"totalSeriesCount"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieve the accuracy scores for each series for the specified multiseries model. |
SeriesAccuracyRetrieveResponse |
| 403 |
Forbidden |
User does not have permissions to manage models. |
None |
| 404 |
Not Found |
Model with specified modelId doesn't exist, or user does not have access to the project. |
None |
| 422 |
Unprocessable Entity |
Metric provided to query is not found. |
None |
Request the computation of per-series scores by project ID
Operation path: POST /api/v2/projects/{projectId}/datetimeModels/{modelId}/multiseriesScores/
Authentication requirements: BearerAuth
Request the computation of per-series scores for a multiseries model.
.. note::
Computation uses available partitions only. This endpoint will not compute backtesting scores if no backtesting scores exist prior to this request.
Body parameter
{
"properties": {
"computeAllSeries": {
"default": false,
"description": "Indicates whether to calculate accuracy for all series or only first 1000 (sorted by name).",
"type": "boolean",
"x-versionadded": "2.22"
}
},
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| body |
body |
SeriesAccuracyCompute |
false |
none |
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
Multiseries score computation has been successfully requested. |
None |
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Retrieve the CSV file by project ID
Operation path: GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/multiseriesScores/file/
Authentication requirements: BearerAuth
Retrieve the CSV file for the series accuracy.
Parameters
| Name |
In |
Type |
Required |
Description |
| multiseriesValue |
query |
string |
false |
If specified, only the series containing the given value in one of the series ID columns will be returned. |
| metric |
query |
string |
false |
The name of the metric to retrieve the scores for. If omitted, the default project metric will be used. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
The response will contain a file containing the series accuracy data in csv format. |
None |
| 403 |
Forbidden |
User does not have permissions to manage models. |
None |
| 404 |
Not Found |
Model with specified modelId doesn't exist, or user does not have access to the project. |
None |
| 422 |
Unprocessable Entity |
Metric provided to query is not found. |
None |
| Status |
Header |
Type |
Format |
Description |
| 200 |
Content-Disposition |
string |
|
Contains an auto generated filename for this download ("attachment;filename=Series accuracy (model:) ().csv"). |
| 200 |
Content-Type |
string |
|
MIME type of the returned data |
List of scores on prediction datasets by project ID
Operation path: GET /api/v2/projects/{projectId}/externalScores/
Authentication requirements: BearerAuth
List of scores on prediction datasets for a project with filtering option by dataset or model or both of them. Prediction dataset may have scores if it contained a column with actual values and predictions were computed on this dataset.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
false |
At most this many results are returned. The default may change without notice. |
| datasetId |
query |
string |
false |
If provided will return scores for dataset with matching datasetId. |
| modelId |
query |
string |
false |
If provided will return scores for model with matching modelId. |
| projectId |
path |
string |
true |
The project ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "The list of objects is containing following data.",
"items": {
"properties": {
"actualValueColumn": {
"description": "The name of the column with actuals that was used to calculate the scores.",
"type": "string"
},
"datasetId": {
"description": "The datasetId the data comes from.",
"type": "string"
},
"modelId": {
"description": "The modelId for the scores.",
"type": "string"
},
"projectId": {
"description": "The projectId for the scores.",
"type": "string"
},
"scores": {
"description": "A json array of the computed scores.",
"items": {
"properties": {
"label": {
"description": "The metric name, which was used to compute the score.",
"type": "string"
},
"value": {
"description": "The score value.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualValueColumn",
"datasetId",
"modelId",
"projectId",
"scores"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"type": [
"string",
"null"
]
}
},
"required": [
"count",
"data",
"next",
"previous"
],
"type": "object"
}
Responses
Compute model scores by project ID
Operation path: POST /api/v2/projects/{projectId}/externalScores/
Authentication requirements: BearerAuth
Compute model scores for external dataset, first upload your dataset to the project, and then using the corresponding datasetId, compute scores against that dataset. Computing external scores and insights depends on computed prediction, predictions will be computed if they are not available for this dataset. In order to compute scores and insights, uploaded dataset should contain actual value column. This api is not available in time series projects.
Body parameter
{
"properties": {
"actualValueColumn": {
"description": "Actual value column name that contains actual values to be used for computing scores and insights for unsupervised projects only. This value can be set once for a dataset and cannot be changed.",
"type": "string"
},
"datasetId": {
"description": "The dataset to compute predictions for - must have previously been uploaded.",
"type": "string"
},
"modelId": {
"description": "The model to use to make predictions.",
"type": "string"
}
},
"required": [
"datasetId",
"modelId"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| body |
body |
ExternalScoresCreate |
false |
none |
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
none |
None |
| 422 |
Unprocessable Entity |
The project type does not support or modeling is not finished yet. |
None |
List all featurelists with feature association matrix availability flags by project ID
Operation path: GET /api/v2/projects/{projectId}/featureAssociationFeaturelists/
Authentication requirements: BearerAuth
List all featurelists with feature association matrix availability flags for a project.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
Example responses
200 Response
{
"properties": {
"featurelists": {
"description": "List all featurelists with feature association matrix availability flags.",
"items": {
"properties": {
"featurelistId": {
"description": "The featurelist Id.",
"type": "string"
},
"hasFam": {
"description": "Whether Feature Association Matrix is calculated for featurelist.",
"type": "boolean"
},
"title": {
"description": "The name of featurelist.",
"type": "string"
}
},
"required": [
"featurelistId",
"hasFam",
"title"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featurelists"
],
"type": "object"
}
Responses
Retrieval by project ID
Operation path: GET /api/v2/projects/{projectId}/featureAssociationMatrix/
Authentication requirements: BearerAuth
Retrieval for pairwise feature association statistics.
Projects created prior to v2.17 are not supported by this feature.
Parameters
| Name |
In |
Type |
Required |
Description |
| type |
query |
string |
true |
the type of dependence for the data. Must be either association or correlation. Since v2.19 this is optional and defaults to association. |
| metric |
query |
string |
true |
the name of a metric to get pairwise data for. Must be one of mutualInfo, cramersV, spearman, pearson, or tau. Since v2.19 this is optional and defaults to mutualInfo. |
| featurelistId |
query |
string |
false |
the feature list to lookup FAM data for. By default, depending on the type of the project Informative Features or Timeseries Informative Features list will be used. |
| projectId |
path |
string |
true |
The project ID |
Enumerated Values
| Parameter |
Value |
| type |
[association, correlation] |
| metric |
[mutualInfo, cramersV, spearman, pearson, tau] |
Example responses
200 Response
{
"properties": {
"features": {
"description": "Metadata for each feature and where it goes in the matrix as structured below.",
"items": {
"properties": {
"alphabeticSortIndex": {
"description": "A number representing the alphabetical order of this feature compared to the other features in this dataset.",
"type": "integer"
},
"clusterId": {
"description": "ID of the cluster this feature belongs to.",
"type": [
"integer",
"null"
]
},
"clusterName": {
"description": "Name of feature cluster.",
"type": "string"
},
"clusterSortIndex": {
"description": "A number representing the ordering of the feature across all feature clusters. Features in the same cluster always have adjacent indices.",
"type": "integer"
},
"feature": {
"description": "Name of the feature.",
"type": "string"
},
"importanceSortIndex": {
"description": "A number ranking the importance of this feature compared to the other features in this dataset.",
"type": "integer"
},
"strengthSortIndex": {
"description": "A number ranking the strength of this feature compared to the other features in this dataset.",
"type": "integer"
}
},
"required": [
"alphabeticSortIndex",
"clusterId",
"clusterSortIndex",
"feature",
"importanceSortIndex",
"strengthSortIndex"
],
"type": "object"
},
"type": "array"
},
"strengths": {
"description": "Pairwise statistics for the available features as structured below.",
"items": {
"properties": {
"feature1": {
"description": "The name of the first feature.",
"type": "string"
},
"feature2": {
"description": "The name of the second feature.",
"type": "string"
},
"statistic": {
"description": "Feature association statistics for `feature1` and `feature2`. For features with no pairwise statistics available the value is `null`.",
"type": [
"number",
"null"
]
}
},
"required": [
"feature1",
"feature2",
"statistic"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"features",
"strengths"
],
"type": "object"
}
Responses
Compute feature association matrix by project ID
Operation path: POST /api/v2/projects/{projectId}/featureAssociationMatrix/
Authentication requirements: BearerAuth
Compute feature association matrix for given featurelist.
Body parameter
{
"properties": {
"featurelistId": {
"description": "A featurelist ID to calculate feature association matrix.",
"type": "string"
}
},
"required": [
"featurelistId"
],
"type": "object"
}
Parameters
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
none |
None |
| 404 |
Not Found |
A project with projectId or a featurelist with featurelistId was not found. |
None |
| 422 |
Unprocessable Entity |
The feature association matrix calculation is not supported for this project. |
None |
Retrieve feature association matrix details by id
Operation path: GET /api/v2/projects/{projectId}/featureAssociationMatrixDetails/
Authentication requirements: BearerAuth
Retrieval for feature association plotting between a pair of features.
Projects created prior to v2.17 are not supported by this feature.
Parameters
| Name |
In |
Type |
Required |
Description |
| feature1 |
query |
string |
true |
The name of a feature. |
| feature2 |
query |
string |
true |
the name of another feature. |
| featurelistId |
query |
string |
false |
the feature list to lookup FAM data for. By default, depending on the type of the project Informative Features or Timeseries Informative Features list will be used. |
| projectId |
path |
string |
true |
The project ID |
Example responses
200 Response
{
"properties": {
"chartType": {
"description": "Which type of plotting the pair of features gets in the UI, e.g. `SCATTER`",
"type": "string"
},
"features": {
"description": "The name of `feature1` and `feature2`.",
"items": {
"type": "string"
},
"type": "array"
},
"types": {
"description": "The type of `feature1` and `feature2`. Possible values: `CATEGORICAL`, `NUMERIC`.",
"items": {
"enum": [
"CATEGORICAL",
"NUMERIC"
],
"type": "string"
},
"type": "array"
},
"values": {
"description": "The data triplets for pairwise plotting.",
"items": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
}
]
},
"type": "array"
},
"type": "array"
}
},
"required": [
"chartType",
"features",
"types",
"values"
],
"type": "object"
}
Responses
Operation path: GET /api/v2/projects/{projectId}/features/{featureName}/frequentValues/
Authentication requirements: BearerAuth
Retrieve the frequent values information for a particular feature.
Only valid for numeric features.
This route returns information about the frequent values seen for a particular feature,
based on the EDA sample of the dataset. Up to 60 values will be returned,
and when more values are present, they will be bucketed into a level called "==All Other=="
at the end of the response.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
project id |
| featureName |
path |
string |
true |
name of the feature |
Example responses
200 Response
{
"properties": {
"frequentValues": {
"description": "List of frequent value and data quality information",
"items": {
"properties": {
"count": {
"description": "Count of specified frequent value in the sample, weighted by exposure or weights",
"type": "integer"
},
"dataQuality": {
"description": "Any data quality issue associated with this particularvalue of the feature. Possible data quality types include 'excess_zero', 'inlier', 'disguised_missing_value', and 'no_issues_found' and the relevant statistics.",
"type": "string"
},
"target": {
"description": "Average target value for the specified frequent value if the target is binary or numeric. With weights or exposure, this becomes a weighted average. If the target is not set, it returns None.",
"type": [
"number",
"null"
]
},
"value": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
}
],
"description": "Specified frequent value, either a float or a string, like `=All Others+`"
}
},
"required": [
"count",
"dataQuality",
"target",
"value"
],
"type": "object"
},
"type": "array"
},
"name": {
"description": "Name of the feature",
"type": "string"
},
"numRows": {
"description": "Number of rows in the sample used to determine frequent values",
"type": "integer"
},
"projectId": {
"description": "Project Id",
"type": "string"
}
},
"required": [
"frequentValues",
"name",
"numRows",
"projectId"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieve the frequent values information for a particular feature. |
FrequentValuesResponse |
| 404 |
Not Found |
If the feature doesn't exist, or no such projectId exists |
None |
| 422 |
Unprocessable Entity |
If the feature isn't numeric |
None |
Create a map of one location feature by project ID
Operation path: POST /api/v2/projects/{projectId}/geometryFeaturePlots/
Authentication requirements: BearerAuth
Create a map of one location feature.
Body parameter
{
"properties": {
"feature": {
"description": "Name of a location feature from the dataset to plot on map.",
"type": "string"
}
},
"required": [
"feature"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
Project Id. It is the project to select the location feature from. |
| body |
body |
GeometryFeaturePLotCreatePayload |
false |
none |
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Retrieve a map of one location feature by project ID
Operation path: GET /api/v2/projects/{projectId}/geometryFeaturePlots/{featureName}/
Authentication requirements: BearerAuth
Retrieve a map of one location feature.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
Project Id. It is the project to select the feature from. |
| featureName |
path |
string |
true |
Name of location feature to plot on map. Must be supplied in order to determine which plot to retrieve. |
Example responses
200 Response
{
"properties": {
"feature": {
"description": "Name of location feature to plot on map.",
"type": "string"
},
"plotData": {
"description": "Geo feature plot data",
"properties": {
"aggregation": {
"description": "Type of geo aggregation.",
"enum": [
"grid",
"unique"
],
"type": "string"
},
"bbox": {
"description": "Bounding box of feature map.",
"type": "object"
},
"features": {
"description": "Location features over map",
"items": {
"properties": {
"geometry": {
"description": "Geometry.",
"properties": {
"coordinates": {
"description": "Coordinate representative of a geometry.",
"items": {
"type": "object"
},
"type": "array"
},
"type": {
"description": "Type of geometry.",
"enum": [
"Point",
"LineString",
"Polygon"
],
"type": "string"
}
},
"required": [
"coordinates",
"type"
],
"type": "object"
},
"properties": {
"description": "Properties of location features.",
"properties": {
"count": {
"description": "Total num of samples located within this geometry.",
"type": "integer"
}
},
"required": [
"count"
],
"type": "object"
},
"type": {
"description": "With a fixed value of 'Feature'.",
"type": "string"
}
},
"required": [
"geometry",
"properties",
"type"
],
"type": "object"
},
"type": "array"
},
"summary": {
"description": "Summary of feature map.",
"properties": {
"maxCount": {
"description": "Max num of samples located within one geometry.",
"type": "integer"
},
"minCount": {
"description": "Min num of samples located within one geometry.",
"type": "integer"
},
"totalCount": {
"description": "Total num of samples across all geometry objects.",
"type": "integer"
}
},
"required": [
"maxCount",
"minCount",
"totalCount"
],
"type": "object"
},
"type": {
"description": "GeoJSON FeatureCollection.",
"type": "string"
},
"valueAggregation": {
"description": "Type of feature aggregation.",
"enum": [
"geometry"
],
"type": "string"
}
},
"required": [
"aggregation",
"bbox",
"features",
"summary",
"type",
"valueAggregation"
],
"type": "object"
},
"projectId": {
"description": "The project to select a location feature from.",
"type": "string"
}
},
"required": [
"feature",
"plotData",
"projectId"
],
"type": "object"
}
Responses
List all Image Activation Maps by project ID
Operation path: GET /api/v2/projects/{projectId}/imageActivationMaps/
Authentication requirements: BearerAuth
List all Image Activation Maps for the project.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
The number of items to skip over. |
| limit |
query |
integer |
false |
The number of items to return. |
| projectId |
path |
string |
true |
The project ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of Image Activation Maps",
"items": {
"properties": {
"featureName": {
"description": "Name of feature",
"type": "string"
},
"modelId": {
"description": "Model ID of the target model",
"type": "string"
}
},
"required": [
"featureName",
"modelId"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
Calculate the anomaly assessment insight by project ID
Operation path: POST /api/v2/projects/{projectId}/models/{modelId}/anomalyAssessmentInitialization/
Authentication requirements: BearerAuth
Initialize the anomaly assessment insight and calculate Shapley explanations for the most anomalous points in the subset. The insight is available for anomaly detection models in time series unsupervised projects which also support calculation of Shapley values.
Body parameter
{
"properties": {
"backtest": {
"description": "The backtest to compute insight for.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
]
},
"seriesId": {
"description": "Required for multiseries projects. The series id to compute insight for.",
"type": "string"
},
"source": {
"description": "The source to compute insight for.",
"enum": [
"training",
"validation"
],
"type": "string"
}
},
"required": [
"backtest",
"source"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| body |
body |
AnomalyAssessmentInitialize |
false |
none |
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
Job submitted. See Location header. |
None |
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Retrieve a CSV file of the raw data displayed by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/anomalyInsightsFile/
Authentication requirements: BearerAuth
Retrieve a CSV file of the raw data displayed with the anomaly score from the specific model. The number of rows included will be set by the expected outlier fraction but up to a maximum of 1000 rows. Only models built from anomaly detection blueprints have those insights.
Parameters
| Name |
In |
Type |
Required |
Description |
| filename |
query |
string |
false |
name of the file to generate and return |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieve a CSV file of the raw data displayed with the anomaly score from the model. |
None |
| 404 |
Not Found |
project Id / model Id does not exist or model doesn't have anomaly insights table. |
None |
Retrieve a table of the raw data displayed by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/anomalyInsightsTable/
Authentication requirements: BearerAuth
Retrieve a table of the raw data displayed with the anomaly score from the specific model. The number of rows displayed is limited to 100 rows by the ANOMALY_INSIGHT_SAMPLE_ROW_COUNT configuration setting. Additionally, feature column count and the size of data in text fields is also limited. Only models built from anomaly detection blueprints have those insights.
Parameters
| Name |
In |
Type |
Required |
Description |
| anomalyScoreRounding |
query |
integer |
false |
number of decimals each element anomalyScore column will be rounded to. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"modelId": {
"description": "given model identifier",
"type": "string"
},
"table": {
"description": "anomaly insights table",
"items": {
"properties": {
"columns": {
"description": "array of columns that contain columns from training dataset and `anomalyScore` column.",
"items": {
"type": "string"
},
"type": "array"
},
"data": {
"description": "array of arrays with actual data. Order in each array corresponds to order in columns array.",
"items": {
"type": "number"
},
"type": "array"
},
"rowId": {
"description": "index 0-based array. Each rowId corresponds to the actual row number of training data",
"items": {
"type": "integer"
},
"type": "array"
}
},
"required": [
"columns",
"data",
"rowId"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"modelId",
"table"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Retrieve a table of the raw data displayed with the anomaly score from the specific model. |
AnomalyInsightTableRetrieve |
| 404 |
Not Found |
The model doesn't have anomaly insights table. |
None |
Retrieve Cluster Insights by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/clusterInsights/
Authentication requirements: BearerAuth
Retrieve all computed Cluster Insights for a clustering project model.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
true |
At most this many results are returned. The default may change without notice. |
| orderBy |
query |
string |
false |
Order results by the specified field value. |
| searchFor |
query |
string |
false |
Search for a specific string in a feature name.This search is case insensitive. If not specified, all features will be returned. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| orderBy |
[featureImpact, -featureImpact, featureName, -featureName] |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "A list of features with clusters insights.",
"items": {
"anyOf": [
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"image"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for an image feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"images",
"percentageOfMissingImages"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"representativeImages"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"clusterName",
"images",
"percentageOfMissingImages"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"geospatialPoint"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a geospatial centroid or point feature.",
"items": {
"properties": {
"insightName": {
"description": "Insight name.",
"enum": [
"representativeLocations"
],
"type": "string"
},
"perCluster": {
"description": "Statistic for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"maxLength": 50,
"minLength": 1,
"type": "string"
},
"representativeLocations": {
"description": "A list of latitude and longitude location list",
"items": {
"description": "Latitude and longitude list.",
"items": {
"description": "Longitude or latitude, in degrees.",
"maximum": 180,
"minimum": -180,
"type": "number"
},
"type": "array"
},
"maxItems": 1000,
"type": "array"
}
},
"required": [
"clusterName",
"representativeLocations"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"text"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"importantNgrams"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"numeric"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistic value for all data.",
"type": [
"number",
"null"
]
},
"insightName": {
"description": "Insight name.",
"enum": [
"min",
"max",
"median",
"avg",
"firstQuartile",
"thirdQuartile",
"missingRowsPercent"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for for each cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"statistic": {
"description": "Statistic value for this cluster.",
"type": [
"number",
"null"
]
}
},
"required": [
"clusterName",
"statistic"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"categorical"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"categoryLevelFrequencyPercent"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"document"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"importantNgrams"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
}
]
},
"maxItems": 100,
"type": "array"
},
"isCurrentClusterInsightVersion": {
"description": "If retrieved insights are current version.",
"type": "boolean"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
},
"version": {
"description": "Current version of the computed insight.",
"minimum": 0,
"type": "integer"
}
},
"required": [
"data",
"isCurrentClusterInsightVersion",
"next",
"previous",
"totalCount",
"version"
],
"type": "object"
}
Responses
Compute Cluster Insights by project ID
Operation path: POST /api/v2/projects/{projectId}/models/{modelId}/clusterInsights/
Authentication requirements: BearerAuth
Compute Cluster Insights for a clustering project model.The number of features computed for cluster insights are capped at 100, starting with the features used to train the model sorted by feature impact (high to low), and then the remaining features in the dataset alphabetically.
Body parameter
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| body |
body |
Empty |
false |
none |
Example responses
202 Response
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
A URI of the newly submitted job in the "Location" header. |
Empty |
| 404 |
Not Found |
The project or the model was not found or insights have not been computed yet. |
None |
| 422 |
Unprocessable Entity |
Feature Impact is already in progress or Cluster Insighst is already in progress, but we were unable to find the previous job. |
None |
Download Cluster Insights result by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/clusterInsights/download/
Authentication requirements: BearerAuth
Download all computed Cluster Insights for a clustering project model.
Parameters
| Name |
In |
Type |
Required |
Description |
| format |
query |
string |
false |
A format to use. |
| featurelistId |
query |
string,null |
false |
The ID of the featurelist to download data for. If not specified all columns will be downloaded. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| format |
CSV |
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
A file with insights for a clustering project model. |
None |
| 404 |
Not Found |
The project or the model was not found or insights have not been computed yet. |
None |
| 422 |
Unprocessable Entity |
Feature Impact is required. Please, compute it first. |
None |
| Status |
Header |
Type |
Format |
Description |
| 200 |
Content-Disposition |
string |
|
Contains an auto generated filename for this download ("attachment;filename=cluster_insights__.csv"). |
Retrieve all available confusion charts by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/confusionCharts/
Authentication requirements: BearerAuth
Retrieve all available confusion charts for model. The response will
include a json array of all available confusion charts, in the same format as the response
from [GET /api/v2/projects/{projectId}/models/{modelId}/confusionCharts/{source}/][get-apiv2projectsprojectidmodelsmodelidconfusionchartssource].
.. note:: Available for multiclass projects only.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"charts": {
"description": "Chart data from all available sources.",
"items": {
"properties": {
"columns": {
"description": "[colStart, colEnd] column dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"data": {
"description": "confusion chart data with the format below.",
"properties": {
"classMetrics": {
"description": "per-class information including one vs all scores in a format specified below",
"items": {
"properties": {
"actualCount": {
"description": "number of times this class is seen in the validation data",
"type": "integer"
},
"className": {
"description": "name of the class",
"type": "string"
},
"confusionMatrixOneVsAll": {
"description": "2d array representing 2x2 one vs all matrix. This represents the True/False Negative/Positive rates as integer for each class. The data structure looks like: ``[ [ True Negative, False Positive ], [ False Negative, True Positive ] ]``",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"f1": {
"description": "F1 score",
"type": "number"
},
"precision": {
"description": "precision score",
"type": "number"
},
"predictedCount": {
"description": "number of times this class has been predicted for the validation data",
"type": "integer"
},
"recall": {
"description": "recall score",
"type": "number"
},
"wasActualPercentages": {
"description": "one vs all actual percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className`",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
},
"wasPredictedPercentages": {
"description": "one vs all predicted percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualCount",
"className",
"confusionMatrixOneVsAll",
"f1",
"precision",
"predictedCount",
"recall",
"wasActualPercentages",
"wasPredictedPercentages"
],
"type": "object"
},
"type": "array"
},
"classes": {
"description": "class labels from the dataset, union of row classes & column classes. This field is deprecated as of v2.13. The rows and columns may have different class labels when using query parameters to retrieve a slice of the matrix; please use 'rowClasses' and 'colClasses' instead.",
"items": {
"type": "string"
},
"type": "array"
},
"colClasses": {
"description": "class labels on columns of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
},
"confusionMatrix": {
"description": "2d array of ints representing confusion matrix, aligned with `rowClasses` and 'colClasses'array. For confusionMatrix[A][B] we can get an integer that represents the number of times 'if class with index A was correct we have class with index B predicted' (if the orientation is 'actual').",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"rowClasses": {
"description": "class labels on rows of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"classMetrics",
"classes",
"colClasses",
"confusionMatrix",
"rowClasses"
],
"type": "object"
},
"globalMetrics": {
"description": "average metrics across all classes",
"properties": {
"f1": {
"description": "Average F1 score",
"type": "number"
},
"precision": {
"description": "Average precision score",
"type": "number"
},
"recall": {
"description": "Avergae recall score",
"type": "number"
}
},
"required": [
"f1",
"precision",
"recall"
],
"type": "object"
},
"numberOfClasses": {
"description": "count of classes in full confusion matrix.",
"type": "integer"
},
"rows": {
"description": "[rowStart, rowEnd] row dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"source": {
"description": "source of the chart",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
},
"totalMatrixSum": {
"description": "sum of all values in full confusion matrix",
"type": "integer"
}
},
"required": [
"columns",
"data",
"globalMetrics",
"numberOfClasses",
"rows",
"source",
"totalMatrixSum"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"charts"
],
"type": "object"
}
Responses
Retrieve the confusion chart data by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/confusionCharts/{source}/
Authentication requirements: BearerAuth
Retrieve the confusion chart data from a single source. A confusion chart consists of the confusion matrix for all classes, classes frequencies and oneVsAll metrics for all classes. The confusion matrix can be requested in a particular sort order and orientated by rows or columns. A subset of the confusion matrix can also be requested in part by specifying slicing indices. Throughout the following specification, C refers to the total number of classes in the dataset. The full confusion matrix refers to the confusion matrix with C classes.
.. note:: Available for multiclass projects only.
An example on the meaning of wasActualPercentages and wasPredictedPercentages:
Let's say we have the following data:
.. code-block:: js
classMetrics.classA.wasActualPercentages[0].percentage = 0.56
classMetrics.classA.wasPredictedPercentages[0].percentage = 0.62
classA.wasActualPercentages[0].otherClassName = "classB"
classA.wasPredictedPercentages[0].otherClassName = "classB"
That means:
1) "Given that it was actually classA, it predicted classB 56% of the time".
2) "Given that classA was predicted, it was actually classB 62% of the time".
Parameters
| Name |
In |
Type |
Required |
Description |
| orderBy |
query |
string |
false |
Ordering the chart data by following attributes.Prefix the attribute name with a dash to sort in descending order, e.g. orderBy='-predictedCount' |
| orientation |
query |
string |
false |
Determines whether the values in the rows of the confusion matrix should correspond to the same actual class ('actual') or predicted class ('predicted'). |
| rowStart |
query |
integer |
false |
start index of row for slicing the confusion matrix. |
| rowEnd |
query |
integer |
false |
end index of row for slicing the confusion matrix. |
| colStart |
query |
integer |
false |
start index of column for slicing the confusion matrix. |
| colEnd |
query |
integer |
false |
end index of column for slicing the confusion matrix. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| source |
path |
string |
true |
Source of the data |
Enumerated Values
| Parameter |
Value |
| orderBy |
[className, -className, actualCount, -actualCount, predictedCount, -predictedCount, f1, -f1, precision, -precision, recall, -recall] |
| orientation |
[actual, -actual, predicted, -predicted] |
| source |
[validation, crossValidation, holdout, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
Example responses
200 Response
{
"properties": {
"columns": {
"description": "[colStart, colEnd] column dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"data": {
"description": "confusion chart data with the format below.",
"properties": {
"classMetrics": {
"description": "per-class information including one vs all scores in a format specified below",
"items": {
"properties": {
"actualCount": {
"description": "number of times this class is seen in the validation data",
"type": "integer"
},
"className": {
"description": "name of the class",
"type": "string"
},
"confusionMatrixOneVsAll": {
"description": "2d array representing 2x2 one vs all matrix. This represents the True/False Negative/Positive rates as integer for each class. The data structure looks like: ``[ [ True Negative, False Positive ], [ False Negative, True Positive ] ]``",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"f1": {
"description": "F1 score",
"type": "number"
},
"precision": {
"description": "precision score",
"type": "number"
},
"predictedCount": {
"description": "number of times this class has been predicted for the validation data",
"type": "integer"
},
"recall": {
"description": "recall score",
"type": "number"
},
"wasActualPercentages": {
"description": "one vs all actual percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className`",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
},
"wasPredictedPercentages": {
"description": "one vs all predicted percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualCount",
"className",
"confusionMatrixOneVsAll",
"f1",
"precision",
"predictedCount",
"recall",
"wasActualPercentages",
"wasPredictedPercentages"
],
"type": "object"
},
"type": "array"
},
"classes": {
"description": "class labels from the dataset, union of row classes & column classes. This field is deprecated as of v2.13. The rows and columns may have different class labels when using query parameters to retrieve a slice of the matrix; please use 'rowClasses' and 'colClasses' instead.",
"items": {
"type": "string"
},
"type": "array"
},
"colClasses": {
"description": "class labels on columns of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
},
"confusionMatrix": {
"description": "2d array of ints representing confusion matrix, aligned with `rowClasses` and 'colClasses'array. For confusionMatrix[A][B] we can get an integer that represents the number of times 'if class with index A was correct we have class with index B predicted' (if the orientation is 'actual').",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"rowClasses": {
"description": "class labels on rows of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"classMetrics",
"classes",
"colClasses",
"confusionMatrix",
"rowClasses"
],
"type": "object"
},
"globalMetrics": {
"description": "average metrics across all classes",
"properties": {
"f1": {
"description": "Average F1 score",
"type": "number"
},
"precision": {
"description": "Average precision score",
"type": "number"
},
"recall": {
"description": "Avergae recall score",
"type": "number"
}
},
"required": [
"f1",
"precision",
"recall"
],
"type": "object"
},
"numberOfClasses": {
"description": "count of classes in full confusion matrix.",
"type": "integer"
},
"rows": {
"description": "[rowStart, rowEnd] row dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"source": {
"description": "source of the chart",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
},
"totalMatrixSum": {
"description": "sum of all values in full confusion matrix",
"type": "integer"
}
},
"required": [
"columns",
"data",
"globalMetrics",
"numberOfClasses",
"rows",
"source",
"totalMatrixSum"
],
"type": "object"
}
Responses
Calculates and sends frequency of class in distributed among other classes by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/confusionCharts/{source}/classDetails/
Authentication requirements: BearerAuth
Calculates and sends frequency of class in distributed among other
classes for actual and predicted data. A confusion chart class details for given class gives
stats of misclassification done by model for given class for actual and predicted data.
.. note:: Available for multiclass projects only.
Parameters
| Name |
In |
Type |
Required |
Description |
| className |
query |
string |
true |
Name of a class for which distribution frequency is requested. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| source |
path |
string |
true |
Source of the data |
Enumerated Values
| Parameter |
Value |
| source |
[validation, crossValidation, holdout, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
Example responses
200 Response
{
"properties": {
"actualFrequency": {
"description": "One vs all actual percentage and count in a format specified below sorted by percentage in decreasing order",
"items": {
"properties": {
"otherClassName": {
"description": "The name of the class.",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className` (from 0 to 100).",
"maximum": 100,
"minimum": 0,
"type": "number"
},
"value": {
"description": "The count of the times this class was predicted when is was actually `classMetrics.className`.",
"minimum": 0,
"type": "integer"
}
},
"required": [
"otherClassName",
"percentage",
"value"
],
"type": "object"
},
"type": "array"
},
"className": {
"description": "Name of a class for which distribution frequency is requested.",
"type": "string"
},
"predictedFrequency": {
"description": "One vs all predicted percentage and count in a format specified below sorted by percentage in decreasing order",
"items": {
"properties": {
"otherClassName": {
"description": "The name of the class.",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted (from 0 to 100)",
"maximum": 100,
"minimum": 0,
"type": "number"
},
"value": {
"description": "The count of the times this class was actual `classMetrics.className` when it was predicted",
"minimum": 0,
"type": "integer"
}
},
"required": [
"otherClassName",
"percentage",
"value"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualFrequency",
"className",
"predictedFrequency"
],
"type": "object"
}
Responses
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/confusionCharts/{source}/metadata/
Authentication requirements: BearerAuth
Retrieve metadata for the confusion chart of a model.
.. note:: Available for multiclass projects only.
| Name |
In |
Type |
Required |
Description |
| orderBy |
query |
string |
false |
Ordering the chart data by following attributes.Prefix the attribute name with a dash to sort in descending order, e.g. orderBy='-predictedCount' |
| orientation |
query |
string |
false |
Determines whether the values in the rows of the confusion matrix should correspond to the same actual class ('actual') or predicted class ('predicted'). |
| thumbnailCellSize |
query |
integer |
false |
Number of classes in a single 'thumbnail' cell. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| source |
path |
string |
true |
Source of the data |
Enumerated Values
| Parameter |
Value |
| orderBy |
[className, -className, actualCount, -actualCount, predictedCount, -predictedCount, f1, -f1, precision, -precision, recall, -recall] |
| orientation |
[actual, -actual, predicted, -predicted] |
| source |
[validation, crossValidation, holdout, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
Example responses
200 Response
{
"properties": {
"classNames": {
"description": "List of all class names in the full confusion matrix, sorted by the `orderBy` parameter",
"items": {
"type": "string"
},
"type": "array"
},
"globalMetrics": {
"description": "average metrics across all classes",
"properties": {
"f1": {
"description": "Average F1 score",
"type": "number"
},
"precision": {
"description": "Average precision score",
"type": "number"
},
"recall": {
"description": "Avergae recall score",
"type": "number"
}
},
"required": [
"f1",
"precision",
"recall"
],
"type": "object"
},
"relevantClassesPositions": {
"description": "Matrix to highlight important cell blocks in the confusion chart. Intended to represent a thumbnail view, where the relevantClassesPositions array has a 1 in thumbnail cells that are of interest, and 0 otherwise. The dimensions of the implied thumbnail will not match those of the confusion matrix, e.g. a twenty-class confusion matrix may have a 2x2 thumbnail.",
"items": {
"items": {
"maximum": 1,
"minimum": 0,
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"source": {
"description": "Source of the chart.",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
},
"totalMatrixSum": {
"description": "Sum of all values in the full confusion matrix (equal to the number of points considered)",
"minimum": 0,
"type": "integer"
}
},
"required": [
"classNames",
"globalMetrics",
"relevantClassesPositions",
"source",
"totalMatrixSum"
],
"type": "object"
}
Responses
List Cross Class Accuracy scores by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/crossClassAccuracyScores/
Authentication requirements: BearerAuth
Retrieves a list of Cross Class Accuracy scores for the model.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of items to skip. Defaults to 0 if not provided. |
| limit |
query |
integer |
false |
Number of items to return, defaults to 100 if not provided. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "An array of cross-class accuracy scores for the model.",
"items": {
"properties": {
"feature": {
"description": "The name of the categorical feature.",
"type": "string"
},
"modelId": {
"description": "ID of the model for the cross-class accuracy scores.",
"type": "string"
},
"perClassAccuracyScores": {
"description": "An array of metric scores for each class of the feature.",
"items": {
"properties": {
"className": {
"description": "The name of the class value for the categorical feature.",
"type": "string"
},
"metrics": {
"description": "An array of metric scores.",
"items": {
"properties": {
"metric": {
"description": "The name of the metric.",
"enum": [
"AUC",
"Weighted AUC",
"Area Under PR Curve",
"Weighted Area Under PR Curve",
"Kolmogorov-Smirnov",
"Weighted Kolmogorov-Smirnov",
"FVE Binomial",
"Weighted FVE Binomial",
"Gini Norm",
"Weighted Gini Norm",
"LogLoss",
"Weighted LogLoss",
"Max MCC",
"Weighted Max MCC",
"Rate@Top5%",
"Weighted Rate@Top5%",
"Rate@Top10%",
"Weighted Rate@Top10%",
"Rate@TopTenth%",
"RMSE",
"Weighted RMSE",
"f1",
"accuracy"
],
"type": "string"
},
"value": {
"description": "The calculated score of the metric.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"metric",
"value"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"className",
"metrics"
],
"type": "object"
},
"type": "array"
},
"predictionThreshold": {
"description": "Value of the prediction threshold for the model.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"feature",
"modelId",
"perClassAccuracyScores",
"predictionThreshold"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
Start Cross Class Accuracy calculations by project ID
Operation path: POST /api/v2/projects/{projectId}/models/{modelId}/crossClassAccuracyScores/
Authentication requirements: BearerAuth
Submits a job to start Cross Class Accuracy scores calculations for the model.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
202 Response
{
"properties": {
"statusId": {
"description": "The ID of the status object.",
"type": "string"
}
},
"required": [
"statusId"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Get Cross Class Data Disparity results by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/dataDisparityInsights/
Authentication requirements: BearerAuth
Retrieve a list of Cross Class Data Disparity insights for the model.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of items to skip. Defaults to 0 if not provided. |
| limit |
query |
integer |
false |
Number of items to return, defaults to 100 if not provided. |
| feature |
query |
string |
true |
Feature for which insight is computed. |
| className1 |
query |
string |
true |
One of the compared classes. |
| className2 |
query |
string |
true |
Another compared class. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "Computed data disparity insights if available.",
"properties": {
"features": {
"description": "A mapping of the feature name to the corresponding values on the graph.",
"items": {
"properties": {
"detailsHistogram": {
"description": "Histogram details for the specified feature.",
"items": {
"properties": {
"bars": {
"description": "Class details for the histogram chart",
"items": {
"properties": {
"label": {
"description": "Name of the class.",
"type": "string"
},
"value": {
"description": "Ratio of occurrence of the class.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
},
"bin": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
],
"description": "Label for the bin grouping"
}
},
"required": [
"bars",
"bin"
],
"type": "object"
},
"type": "array"
},
"disparityScore": {
"description": "A number to describe disparity for the feature between the compared classes.",
"type": "number"
},
"featureImpact": {
"description": "A feature importance value.",
"type": "number"
},
"name": {
"description": "Name of the feature.",
"type": "string"
},
"status": {
"description": "A status of the feature.",
"enum": [
"Healthy",
"At Risk",
"Failing"
],
"type": "string"
}
},
"required": [
"detailsHistogram",
"disparityScore",
"featureImpact",
"name",
"status"
],
"type": "object"
},
"type": "array"
},
"metric": {
"description": "Metric used to calculate the impact of a feature on data disparity.",
"type": "string"
},
"protectedFeature": {
"description": "Feature for which insights were computed.",
"type": "string"
},
"values": {
"description": "Class count details for each class being compared.",
"items": {
"description": "Number of occurrences of each class being compared.",
"properties": {
"count": {
"description": "Number of times the class was encountered.",
"type": "integer"
},
"label": {
"description": "Name of the class.",
"type": "string"
}
},
"required": [
"count",
"label"
],
"type": "object"
},
"type": "array"
}
},
"type": "object"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
Start insight calculations by project ID
Operation path: POST /api/v2/projects/{projectId}/models/{modelId}/dataDisparityInsights/
Authentication requirements: BearerAuth
Submits a job to start Cross Class Data Disparity insight calculations.
Body parameter
{
"properties": {
"comparedClassNames": {
"description": "An array of classes to calculate data disparity for.",
"items": {
"type": "string"
},
"maxItems": 2,
"minItems": 2,
"type": "array"
},
"feature": {
"description": "Feature for which insight is computed.",
"type": "string"
}
},
"required": [
"comparedClassNames",
"feature"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| body |
body |
DataDisparityCreatePayload |
false |
none |
Example responses
202 Response
{
"properties": {
"statusId": {
"description": "The ID of the status object.",
"type": "string"
}
},
"required": [
"statusId"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
List of Confusion Charts objects on external datasets by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/datasetConfusionCharts/
Authentication requirements: BearerAuth
List of Confusion Charts objects on external datasets for a project with filtering option by dataset. Prediction dataset may have Confusion Chart for multiclass projects computed if it contained a target with actual values and insights were computed on this dataset. A confusion chart consists of the confusion matrix for all classes, classes frequencies and oneVsAll metrics for all classes. The confusion matrix can be requested in a particular sort order and orientated by rows or columns. Available for multiclass projects only.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
false |
At most this many results are returned. The default may change without notice. |
| orderBy |
query |
string |
false |
Ordering the chart data by following attributes.Prefix the attribute name with a dash to sort in descending order, e.g. orderBy='-predictedCount' |
| orientation |
query |
string |
false |
Determines whether the values in the rows of the confusion matrix should correspond to the same actual class ('actual') or predicted class ('predicted'). |
| rowStart |
query |
integer |
false |
start index of row for slicing the confusion matrix. |
| rowEnd |
query |
integer |
false |
end index of row for slicing the confusion matrix. |
| colStart |
query |
integer |
false |
start index of column for slicing the confusion matrix. |
| colEnd |
query |
integer |
false |
end index of column for slicing the confusion matrix. |
| datasetId |
query |
string |
false |
The datasetId to retrieve a Confusion chart from. |
| projectId |
path |
string |
true |
The project to retrieve a Confusion chart from. |
| modelId |
path |
string |
true |
The model to retrieve a Confusion chart from. |
Enumerated Values
| Parameter |
Value |
| orderBy |
[className, -className, actualCount, -actualCount, predictedCount, -predictedCount, f1, -f1, precision, -precision, recall, -recall] |
| orientation |
[actual, -actual, predicted, -predicted] |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of results returned on this page.",
"type": "integer"
},
"data": {
"description": "Confusion chart data with the in the same format as the response from [GET /api/v2/projects/{projectId}/models/{modelId}/confusionCharts/{source}/][get-apiv2projectsprojectidmodelsmodelidconfusionchartssource] with additional totalCount field.",
"items": {
"properties": {
"columns": {
"description": "[colStart, colEnd] column dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"data": {
"description": "confusion chart data with the format below.",
"properties": {
"classMetrics": {
"description": "per-class information including one vs all scores in a format specified below",
"items": {
"properties": {
"actualCount": {
"description": "number of times this class is seen in the validation data",
"type": "integer"
},
"className": {
"description": "name of the class",
"type": "string"
},
"confusionMatrixOneVsAll": {
"description": "2d array representing 2x2 one vs all matrix. This represents the True/False Negative/Positive rates as integer for each class. The data structure looks like: ``[ [ True Negative, False Positive ], [ False Negative, True Positive ] ]``",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"f1": {
"description": "F1 score",
"type": "number"
},
"precision": {
"description": "precision score",
"type": "number"
},
"predictedCount": {
"description": "number of times this class has been predicted for the validation data",
"type": "integer"
},
"recall": {
"description": "recall score",
"type": "number"
},
"wasActualPercentages": {
"description": "one vs all actual percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className`",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
},
"wasPredictedPercentages": {
"description": "one vs all predicted percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualCount",
"className",
"confusionMatrixOneVsAll",
"f1",
"precision",
"predictedCount",
"recall",
"wasActualPercentages",
"wasPredictedPercentages"
],
"type": "object"
},
"type": "array"
},
"classes": {
"description": "class labels from the dataset, union of row classes & column classes. This field is deprecated as of v2.13. The rows and columns may have different class labels when using query parameters to retrieve a slice of the matrix; please use 'rowClasses' and 'colClasses' instead.",
"items": {
"type": "string"
},
"type": "array"
},
"colClasses": {
"description": "class labels on columns of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
},
"confusionMatrix": {
"description": "2d array of ints representing confusion matrix, aligned with `rowClasses` and 'colClasses'array. For confusionMatrix[A][B] we can get an integer that represents the number of times 'if class with index A was correct we have class with index B predicted' (if the orientation is 'actual').",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"rowClasses": {
"description": "class labels on rows of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"classMetrics",
"classes",
"colClasses",
"confusionMatrix",
"rowClasses"
],
"type": "object"
},
"globalMetrics": {
"description": "average metrics across all classes",
"properties": {
"f1": {
"description": "Average F1 score",
"type": "number"
},
"precision": {
"description": "Average precision score",
"type": "number"
},
"recall": {
"description": "Avergae recall score",
"type": "number"
}
},
"required": [
"f1",
"precision",
"recall"
],
"type": "object"
},
"numberOfClasses": {
"description": "count of classes in full confusion matrix.",
"type": "integer"
},
"rows": {
"description": "[rowStart, rowEnd] row dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"source": {
"description": "source of the chart",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
},
"totalMatrixSum": {
"description": "sum of all values in full confusion matrix",
"type": "integer"
}
},
"required": [
"columns",
"data",
"globalMetrics",
"numberOfClasses",
"rows",
"source",
"totalMatrixSum"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "Total count of confusion charts for model.",
"type": "integer"
}
},
"required": [
"count",
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
Retrieve Confusion Chart objects on external datasets by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/datasetConfusionCharts/{datasetId}/
Authentication requirements: BearerAuth
Retrieve Confusion Chart objects on external datasets for a project. Prediction dataset may have Confusion Chart for multiclass projects computed if it contained a target with actual values and insights were computed on this dataset. A confusion chart consists of the confusion matrix for all classes, classes frequencies and oneVsAll metrics for all classes. The confusion matrix can be requested in a particular sort order and oriented by rows or columns (zero-indexed). Available for multiclass projects only.
Parameters
| Name |
In |
Type |
Required |
Description |
| orderBy |
query |
string |
false |
Ordering the chart data by following attributes.Prefix the attribute name with a dash to sort in descending order, e.g. orderBy='-predictedCount' |
| orientation |
query |
string |
false |
Determines whether the values in the rows of the confusion matrix should correspond to the same actual class ('actual') or predicted class ('predicted'). |
| rowStart |
query |
integer |
false |
start index of row for slicing the confusion matrix. |
| rowEnd |
query |
integer |
false |
end index of row for slicing the confusion matrix. |
| colStart |
query |
integer |
false |
start index of column for slicing the confusion matrix. |
| colEnd |
query |
integer |
false |
end index of column for slicing the confusion matrix. |
| projectId |
path |
string |
true |
The project to retrieve a Confusion chart from. |
| modelId |
path |
string |
true |
The model to retrieve a Confusion chart from. |
| datasetId |
path |
string |
true |
The dataset to retrieve a Confusion chart from. |
Enumerated Values
| Parameter |
Value |
| orderBy |
[className, -className, actualCount, -actualCount, predictedCount, -predictedCount, f1, -f1, precision, -precision, recall, -recall] |
| orientation |
[actual, -actual, predicted, -predicted] |
Example responses
200 Response
{
"properties": {
"columns": {
"description": "[colStart, colEnd] column dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"data": {
"description": "confusion chart data with the format below.",
"properties": {
"classMetrics": {
"description": "per-class information including one vs all scores in a format specified below",
"items": {
"properties": {
"actualCount": {
"description": "number of times this class is seen in the validation data",
"type": "integer"
},
"className": {
"description": "name of the class",
"type": "string"
},
"confusionMatrixOneVsAll": {
"description": "2d array representing 2x2 one vs all matrix. This represents the True/False Negative/Positive rates as integer for each class. The data structure looks like: ``[ [ True Negative, False Positive ], [ False Negative, True Positive ] ]``",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"f1": {
"description": "F1 score",
"type": "number"
},
"precision": {
"description": "precision score",
"type": "number"
},
"predictedCount": {
"description": "number of times this class has been predicted for the validation data",
"type": "integer"
},
"recall": {
"description": "recall score",
"type": "number"
},
"wasActualPercentages": {
"description": "one vs all actual percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className`",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
},
"wasPredictedPercentages": {
"description": "one vs all predicted percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualCount",
"className",
"confusionMatrixOneVsAll",
"f1",
"precision",
"predictedCount",
"recall",
"wasActualPercentages",
"wasPredictedPercentages"
],
"type": "object"
},
"type": "array"
},
"classes": {
"description": "class labels from the dataset, union of row classes & column classes. This field is deprecated as of v2.13. The rows and columns may have different class labels when using query parameters to retrieve a slice of the matrix; please use 'rowClasses' and 'colClasses' instead.",
"items": {
"type": "string"
},
"type": "array"
},
"colClasses": {
"description": "class labels on columns of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
},
"confusionMatrix": {
"description": "2d array of ints representing confusion matrix, aligned with `rowClasses` and 'colClasses'array. For confusionMatrix[A][B] we can get an integer that represents the number of times 'if class with index A was correct we have class with index B predicted' (if the orientation is 'actual').",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"rowClasses": {
"description": "class labels on rows of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"classMetrics",
"classes",
"colClasses",
"confusionMatrix",
"rowClasses"
],
"type": "object"
},
"datasetId": {
"description": "The datasetId to retrieve a Confusion chart from.",
"type": "string"
},
"numberOfClasses": {
"description": "count of classes in full confusion matrix.",
"type": "integer"
},
"rows": {
"description": "[rowStart, rowEnd] row dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"totalMatrixSum": {
"description": "sum of all values in full confusion matrix",
"type": "integer"
}
},
"required": [
"columns",
"data",
"datasetId",
"numberOfClasses",
"rows",
"totalMatrixSum"
],
"type": "object"
}
Responses
Calculate and sends frequency of class in distributed among other classes by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/datasetConfusionCharts/{datasetId}/classDetails/
Authentication requirements: BearerAuth
Calculate and sends frequency of class in distributed among other classes for actual and predicted data. A confusion chart class details for given class gives stats of misclassification done by model for given class for actual and predicted data. Available for multiclass projects only.
Parameters
| Name |
In |
Type |
Required |
Description |
| className |
query |
string |
true |
Name of a class for which distribution frequency is requested. |
| projectId |
path |
string |
true |
The project to retrieve a Confusion chart from. |
| modelId |
path |
string |
true |
The model to retrieve a Confusion chart from. |
| datasetId |
path |
string |
true |
The dataset to retrieve a Confusion chart from. |
Example responses
200 Response
{
"properties": {
"actualFrequency": {
"description": "One vs All actual percentage and count in a format specified below sorted by percentage in decreasing order",
"items": {
"properties": {
"otherClassName": {
"description": "The name of the class.",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className` (from 0 to 100).",
"maximum": 100,
"minimum": 0,
"type": "number"
},
"value": {
"description": "The count of the times this class was predicted when is was actually `classMetrics.className`.",
"minimum": 0,
"type": "integer"
}
},
"required": [
"otherClassName",
"percentage",
"value"
],
"type": "object"
},
"type": "array"
},
"className": {
"description": "Name of a class for which distribution frequency is requested",
"type": "string"
},
"datasetId": {
"description": "The dataset to retrieve a Confusion chart from.",
"type": "string"
},
"modelId": {
"description": "The model to retrieve a Confusion chart from.",
"type": "string"
},
"predictedFrequency": {
"description": "One vs All predicted percentage and count in a format specified below sorted by percentage in decreasing order",
"items": {
"properties": {
"otherClassName": {
"description": "The name of the class.",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted (from 0 to 100)",
"maximum": 100,
"minimum": 0,
"type": "number"
},
"value": {
"description": "The count of the times this class was actual `classMetrics.className` when it was predicted",
"minimum": 0,
"type": "integer"
}
},
"required": [
"otherClassName",
"percentage",
"value"
],
"type": "object"
},
"type": "array"
},
"projectId": {
"description": "The project to retrieve a Confusion chart from.",
"type": "string"
}
},
"required": [
"actualFrequency",
"className",
"datasetId",
"modelId",
"predictedFrequency",
"projectId"
],
"type": "object"
}
Responses
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/datasetConfusionCharts/{datasetId}/metadata/
Authentication requirements: BearerAuth
Retrieve metadata for the confusion chart of a model on external dataset for a project. Available for multiclass projects only.
| Name |
In |
Type |
Required |
Description |
| orderBy |
query |
string |
false |
Ordering the chart data by following attributes.Prefix the attribute name with a dash to sort in descending order, e.g. orderBy='-predictedCount' |
| orientation |
query |
string |
false |
Determines whether the values in the rows of the confusion matrix should correspond to the same actual class ('actual') or predicted class ('predicted'). |
| thumbnailCellSize |
query |
integer |
false |
Number of classes in a single 'thumbnail' cell. |
| projectId |
path |
string |
true |
The project to retrieve a Confusion chart from. |
| modelId |
path |
string |
true |
The model to retrieve a Confusion chart from. |
| datasetId |
path |
string |
true |
The dataset to retrieve a Confusion chart from. |
Enumerated Values
| Parameter |
Value |
| orderBy |
[className, -className, actualCount, -actualCount, predictedCount, -predictedCount, f1, -f1, precision, -precision, recall, -recall] |
| orientation |
[actual, -actual, predicted, -predicted] |
Example responses
200 Response
{
"properties": {
"classNames": {
"description": "list of all class names in the full confusion matrix, sorted by the `orderBy` parameter.",
"items": {
"type": "string"
},
"type": "array"
},
"datasetId": {
"description": "The dataset to retrieve a Confusion chart from.",
"type": "string"
},
"modelId": {
"description": "The model to retrieve a Confusion chart from.",
"type": "string"
},
"projectId": {
"description": "The project to retrieve a Confusion chart from.",
"type": "string"
},
"relevantClassesPositions": {
"description": "Matrix to highlight important cell blocks in the confusion chart. Intended to represent a thumbnail view, where the relevantClassesPositions array has a 1 in thumbnail cells that are of interest, and 0 otherwise. The dimensions of the implied thumbnail will not match those of the confusion matrix, e.g. a twenty-class confusion matrix may have a 2x2 thumbnail.",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"totalMatrixSum": {
"description": "Sum of all values in the full confusion matrix (equal to the number of points considered).",
"type": "integer"
}
},
"required": [
"classNames",
"datasetId",
"modelId",
"projectId",
"relevantClassesPositions",
"totalMatrixSum"
],
"type": "object"
}
Responses
Retrieve List of Lift chart data on prediction datasets by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/datasetLiftCharts/
Authentication requirements: BearerAuth
List of Lift chart objects on prediction datasets for a project with filtering option by dataset. Prediction dataset may have Lift chart computed if it contained a column with actual values and predictions were computed on this dataset. This controller is not supported for multiclass classification projects. For multiclass, instead use /projects//models//datasetMulticlassLiftCharts/.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
false |
At most this many results are returned. The default may change without notice. |
| datasetId |
query |
string |
false |
If provided will return Lift chart for dataset with matching datasetId. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of results returned on this page.",
"type": "integer"
},
"data": {
"description": "Array of lift chart data for dataset, as specified below",
"items": {
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"datasetId": {
"description": "The dataset id of dataset which was used to compute Lift chart.",
"type": "string"
}
},
"required": [
"bins",
"datasetId"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"count",
"data",
"next",
"previous"
],
"type": "object"
}
Responses
Retrieve List of Multiclass Lift chart data on prediction datasets by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/datasetMulticlassLiftCharts/
Authentication requirements: BearerAuth
List of Multiclass Lift chart objects on prediction datasets for a project with filtering option by dataset. Prediction dataset may have Multiclass Lift chart computed if it contained a column with actual values and predictions were computed on this dataset. Multiclass Lift charts are supported for multiclass classification projects only.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
false |
At most this many results are returned. The default may change without notice. |
| datasetId |
query |
string |
false |
If provided will return Lift chart for dataset with matching datasetId. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of results returned on this page.",
"type": "integer"
},
"data": {
"description": "Array of multiclass lift chart data for dataset, as specified below.",
"items": {
"properties": {
"classBins": {
"description": "List of lift chart data for each target class.",
"items": {
"properties": {
"bins": {
"description": "The lift chart data for that source and class, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"targetClass": {
"description": "The target class for the lift chart.",
"type": "string"
}
},
"required": [
"bins",
"targetClass"
],
"type": "object"
},
"type": "array"
},
"datasetId": {
"description": "The dataset id of dataset which was used to compute Lift chart.",
"type": "string"
}
},
"required": [
"classBins",
"datasetId"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model id to which the chart data belongs.",
"type": "string"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project id to which the chart data belongs.",
"type": "string"
},
"totalCount": {
"description": "Total count of multiclass lift charts matching to the query condition.",
"type": "integer"
}
},
"required": [
"count",
"data",
"modelId",
"next",
"previous",
"projectId",
"totalCount"
],
"type": "object"
}
Responses
List of residuals charts objects by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/datasetResidualsCharts/
Authentication requirements: BearerAuth
List of residuals charts objects on prediction datasets for a project with filtering option by dataset. Prediction dataset may have residuals chart computed if it contained a column with actual values and predictions were computed on this dataset.
Residuals charts are supported for regression projects only.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
false |
At most this many results are returned. The default may change without notice. |
| datasetId |
query |
string |
false |
If provided will return ROC curve for dataset with matching datasetId. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of residuals charts for dataset.",
"items": {
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input.",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be `null`.",
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"histogram": {
"description": "Data to plot a histogram of residual values. The object contains three keys, intervalStart, intervalEnd, and occurrences, the number of times the predicted value fits within that interval. For all but the last interval, the end value is exclusive.",
"items": {
"properties": {
"intervalEnd": {
"description": "The end of the interval.",
"type": "number"
},
"intervalStart": {
"description": "The start of the interval.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within that interval.",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset.",
"type": "number"
},
"standardDeviation": {
"description": "The Standard Deviation value measures variation in the dataset. A low value indicates that the data points tend to be close to the mean; a high value indicates that the data points are spread over a wider range of values.",
"type": "number"
}
},
"required": [
"coefficientOfDetermination",
"data",
"datasetId",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model ID.",
"type": "string"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"modelId",
"next",
"previous",
"projectId",
"totalCount"
],
"type": "object"
}
Responses
List of ROC curve objects on prediction datasets for a project with filtering option by DEPRECATED by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/datasetRocCurves/
Authentication requirements: BearerAuth
List of ROC curve objects on prediction datasets for a project with filtering option by dataset.
Prediction dataset may have ROC curve computed if it contained a column with actual values and predictions were computed on this dataset.
Each ROC curve object includes an array of points showing the performance of the model at different thresholds for classification, and arrays of sample predictions for both the positive and negative classes.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
false |
At most this many results are returned. The default may change without notice. |
| datasetId |
query |
string |
false |
If provided will return ROC curve for dataset with matching datasetId. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of ROC curve data for datasets.",
"items": {
"description": "ROC curve data for datasets.",
"properties": {
"datasetId": {
"description": "The ID of dataset which was used to compute ROC curve.",
"type": "string"
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
}
},
"required": [
"datasetId",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"data",
"next",
"previous"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Objects were returned successfully. No objects is a valid case. |
RocCurveForDatasetsList |
List calculated Per Class Bias insights by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/fairnessInsights/
Authentication requirements: BearerAuth
Retrieve a list of Per Class Bias insights for the model.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of items to skip. Defaults to 0 if not provided. |
| limit |
query |
integer |
false |
Number of items to return, defaults to 100 if not provided. |
| fairnessMetricsSet |
query |
string |
false |
Metric to use for calculating fairness. Can be one of proportionalParity, equalParity, predictionBalance, trueFavorableAndUnfavorableRateParity or FavorableAndUnfavorablePredictiveValueParity. Used and required only if Bias & Fairness in AutoML feature is enabled. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| fairnessMetricsSet |
[proportionalParity, equalParity, predictionBalance, trueFavorableAndUnfavorableRateParity, favorableAndUnfavorablePredictiveValueParity] |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "An array of fairness insights for the model.",
"items": {
"properties": {
"fairnessMetric": {
"description": "The fairness metric used to calculate the fairness scores.",
"enum": [
"proportionalParity",
"equalParity",
"favorableClassBalance",
"unfavorableClassBalance",
"trueUnfavorableRateParity",
"trueFavorableRateParity",
"favorablePredictiveValueParity",
"unfavorablePredictiveValueParity"
],
"type": "string"
},
"fairnessThreshold": {
"default": 0.8,
"description": "Value of the fairness threshold, defined in project options.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"modelId": {
"description": "ID of the model fairness was measured for.",
"type": "string"
},
"perClassFairness": {
"description": "An array of calculated fairness scores for each protected feature class.",
"items": {
"properties": {
"absoluteValue": {
"description": "Absolute fairness score for the class",
"minimum": 0,
"type": "number"
},
"className": {
"description": "Name of the protected class the score is calculated for.",
"type": "string"
},
"entriesCount": {
"description": "The number of entries of the class in the analysed data.",
"minimum": 0,
"type": "integer"
},
"isStatisticallySignificant": {
"description": "Flag to tell whether the score can be treated as statistically significant. In other words, whether we are confident enough with the score for this protected class.",
"type": "boolean"
},
"value": {
"description": "The relative fairness score for the class.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"absoluteValue",
"className",
"entriesCount",
"isStatisticallySignificant",
"value"
],
"type": "object"
},
"type": "array"
},
"predictionThreshold": {
"description": "Model's prediction threshold used when insight was calculated. ``null`` if prediction threshold is not required for the fairness metric calculations.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"protectedFeature": {
"description": "Name of the protected feature the fairness calculation is made for.",
"type": "string"
}
},
"required": [
"fairnessMetric",
"fairnessThreshold",
"modelId",
"perClassFairness",
"protectedFeature"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
Create fairness insights by id
Operation path: POST /api/v2/projects/{projectId}/models/{modelId}/fairnessInsights/
Authentication requirements: BearerAuth
Submits a job to start Per Class Bias insight calculations for the model.
Body parameter
{
"properties": {
"fairnessMetricsSet": {
"description": "Metric to use for calculating fairness. Can be one of ``proportionalParity``, ``equalParity``, ``predictionBalance``, ``trueFavorableAndUnfavorableRateParity`` or ``FavorableAndUnfavorablePredictiveValueParity``. Used and required only if *Bias & Fairness in AutoML* feature is enabled.",
"enum": [
"proportionalParity",
"equalParity",
"predictionBalance",
"trueFavorableAndUnfavorableRateParity",
"favorableAndUnfavorablePredictiveValueParity"
],
"type": "string",
"x-versionadded": "v2.24"
}
},
"type": "object"
}
Parameters
Example responses
202 Response
{
"properties": {
"statusId": {
"description": "The ID of the status object.",
"type": "string"
}
},
"required": [
"statusId"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Retrieve feature effects by id
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/featureEffects/
Authentication requirements: BearerAuth
Retrieve Feature Effects for the model.
Feature Effects provides partial dependence and predicted vs actual values for the top 500 features, ordered by feature impact score.
The partial dependence shows marginal effect of a feature on the target variable after accounting for the average effects of all other predictive features. It indicates how, holding all other variables except the feature of interest as they were, the value of this feature affects your prediction.
If a Feature Effects job was previously submitted, this endpoint will return a response structured as {"message": , "jobId": } where jobId is the ID of the job. Retrieve the job with [GET /api/v2/projects/{projectId}/jobs/{jobId}/][get-apiv2projectsprojectidjobsjobid].
Parameters
| Name |
In |
Type |
Required |
Description |
| source |
query |
string |
false |
Models data source. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| source |
[training, validation, holdout] |
Example responses
200 Response
{
"properties": {
"featureEffects": {
"description": "Feature Effects computational results for each feature.",
"items": {
"properties": {
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model ID",
"type": "string"
},
"projectId": {
"description": "The project ID",
"type": "string"
},
"source": {
"description": "Models data source.",
"type": "string"
}
},
"required": [
"featureEffects",
"modelId",
"projectId",
"source"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
none |
FeatureEffectsResponse |
| 403 |
Forbidden |
User does not have permission to view the project. |
None |
| 404 |
Not Found |
Project, model, source or computation results do not exist. |
None |
Create feature effects by id
Operation path: POST /api/v2/projects/{projectId}/models/{modelId}/featureEffects/
Authentication requirements: BearerAuth
Add a request to the queue to calculate Feature Effects.
If the job has been previously submitted, the request fails, returning the jobId of the previously submitted job. Use this jobId to check status of the previously submitted job.
Body parameter
{
"properties": {
"rowCount": {
"description": "The number of rows from dataset to use for Feature Impact calculation.",
"maximum": 100000,
"minimum": 10,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.21"
}
},
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| body |
body |
FeatureEffectCreate |
false |
none |
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
The Feature Effects request has been successfully submitted. See Location header. |
None |
| 403 |
Forbidden |
User does not have permission to view or submit jobs for the project. |
None |
| 404 |
Not Found |
Provided project or model does not exist. |
None |
| 422 |
Unprocessable Entity |
Queue submission error. |
|
.. minversion:: v2.21
If the rowCount exceeds the maximum or minimum value for this dataset. Minimum
is 10 rows. Maximum is 100000 rows or the training sample size of the model,
whichever is less.|None|
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/featureEffectsMetadata/
Authentication requirements: BearerAuth
Retrieve Feature Effects metadata. Response contains status and available sources.
One of the provided source parameters used for retrieving Feature Effects.
* Source can be, at a minimum, training or validation. If holdout is configured for the project, source also includes holdout.
* Source value of training is always available. (versions prior to v2.17 support validation only)
* When a model is trained into validation or holdout without stacked predictions (i.e., no out-of-sample predictions in validation or holdout), validation and holdout sources are not available.
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"sources": {
"description": "List of sources available for the model.",
"items": {
"enum": [
"training",
"validation",
"holdout"
],
"type": "string"
},
"type": "array"
},
"status": {
"description": "Status of the job.",
"enum": [
"INPROGRESS",
"COMPLETED",
"NOT_COMPLETED"
],
"type": "string"
}
},
"required": [
"sources",
"status"
],
"type": "object"
}
Responses
Retrieve feature impact scores by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/featureImpact/
Authentication requirements: BearerAuth
Retrieve feature impact scores for features in a model.
Feature Impact is computed for each column by creating new data with that column randomly permuted (but the others left unchanged), and seeing how the error metric score for the predictions is affected. Elsewhere this technique is sometimes called 'Permutation Importance'.
The impactUnnormalized is how much worse the error metric score is when making predictions on this modified data. The impactNormalized is normalized so that the largest value is 1. In both cases, larger values indicate more important features. If a feature is a redundant feature, i.e. once other features are considered it doesn't contribute much in addition, the redundantWith value is the name of feature that has the highest correlation with this feature.
Parameters
| Name |
In |
Type |
Required |
Description |
| backtest |
query |
any |
false |
The backtest value used for Feature Impact computation. Applicable for datetime aware models. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"backtest": {
"description": "The backtest model used to compute Feature Impact.Defined for datetime aware models.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
},
{
"type": "null"
}
],
"x-versionadded": "v2.29"
},
"count": {
"description": "Number of feature impact records in a given batch.",
"type": "integer"
},
"featureImpacts": {
"description": "A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"parentFeatureName": {
"description": "The name of the parent feature.",
"type": [
"string",
"null"
]
},
"redundantWith": {
"description": "Name of feature that has the highest correlation with this feature.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized",
"redundantWith"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"next": {
"description": "URL for the next page of results or `null`.",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL for the next page of results or `null`.",
"format": "uri",
"type": [
"string",
"null"
]
},
"ranRedundancyDetection": {
"description": "Indicates whether redundant feature identification was run while calculating this feature impact.",
"type": "boolean"
},
"rowCount": {
"description": "The number of rows that was used to calculate feature impact. For the feature impact calculated with the default logic, without specifying the ``rowCount``, we return ``null`` here.",
"type": [
"integer",
"null"
],
"x-versionadded": "v2.21"
},
"shapBased": {
"description": "Indicates whether feature impact was calculated using Shapley values. True for anomaly detection models when the project is unsupervised, as permutation approach is not applicable. Note that supervised projects must use an alternative route for SHAP impact: /api/v2/projects/(projectId)/models/(modelId)/shapImpact/",
"type": "boolean",
"x-versionadded": "v2.18"
}
},
"required": [
"backtest",
"count",
"featureImpacts",
"next",
"previous",
"ranRedundancyDetection",
"rowCount",
"shapBased"
],
"type": "object"
}
Responses
Create feature impact by id
Operation path: POST /api/v2/projects/{projectId}/models/{modelId}/featureImpact/
Authentication requirements: BearerAuth
Add a request to calculate feature impact to the queue.
If the job has been previously submitted, the request will fail and return the jobId of previously submitted job. This jobId can be used to check status of previously submitted job.
Body parameter
{
"properties": {
"backtest": {
"description": "The backtest value used for Feature Impact computation. Applicable for datetime aware models.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
],
"x-versionadded": "v2.28"
},
"rowCount": {
"description": "The sample size to use for Feature Impact computation. It is possible to re-compute Feature Impact with a different row count.",
"maximum": 100000,
"minimum": 10,
"type": "integer",
"x-versionadded": "v2.21"
}
},
"type": "object"
}
Parameters
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
The request was accepted and will be worked on. |
None |
| 404 |
Not Found |
If modelId does not exist in project leaderboard |
None |
| 422 |
Unprocessable Entity |
If feature impact has already run will return error including jobId property which is the jobId of the previously started feature impact job. |
|
.. minversion:: v2.21
If the rowCount exceeds the maximum or minimum value for this dataset. Minimum is 10 rows. Maximum is 100000 rows or the training sample size of the model, whichever is less.|None|
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Retrieve cluster insights by id
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/featureLists/{datasetId}/clusterInsights/
Authentication requirements: BearerAuth
Retrieve computed Cluster Insights for a clustering project model on a single featurelist.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
true |
At most this many results are returned. The default may change without notice. |
| orderBy |
query |
string |
false |
Order results by the specified field value. |
| searchFor |
query |
string |
false |
Search for a specific string in a feature name.This search is case insensitive. If not specified, all features will be returned. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| datasetId |
path |
string |
true |
The dataset ID |
Enumerated Values
| Parameter |
Value |
| orderBy |
[featureImpact, -featureImpact, featureName, -featureName] |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "A list of features with clusters insights.",
"items": {
"anyOf": [
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"image"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for an image feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"images",
"percentageOfMissingImages"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"representativeImages"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"clusterName",
"images",
"percentageOfMissingImages"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"geospatialPoint"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a geospatial centroid or point feature.",
"items": {
"properties": {
"insightName": {
"description": "Insight name.",
"enum": [
"representativeLocations"
],
"type": "string"
},
"perCluster": {
"description": "Statistic for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"maxLength": 50,
"minLength": 1,
"type": "string"
},
"representativeLocations": {
"description": "A list of latitude and longitude location list",
"items": {
"description": "Latitude and longitude list.",
"items": {
"description": "Longitude or latitude, in degrees.",
"maximum": 180,
"minimum": -180,
"type": "number"
},
"type": "array"
},
"maxItems": 1000,
"type": "array"
}
},
"required": [
"clusterName",
"representativeLocations"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"text"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"importantNgrams"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"numeric"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistic value for all data.",
"type": [
"number",
"null"
]
},
"insightName": {
"description": "Insight name.",
"enum": [
"min",
"max",
"median",
"avg",
"firstQuartile",
"thirdQuartile",
"missingRowsPercent"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for for each cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"statistic": {
"description": "Statistic value for this cluster.",
"type": [
"number",
"null"
]
}
},
"required": [
"clusterName",
"statistic"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"categorical"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"categoryLevelFrequencyPercent"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"document"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"importantNgrams"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
}
]
},
"maxItems": 100,
"type": "array"
},
"isCurrentClusterInsightVersion": {
"description": "If retrieved insights are current version.",
"type": "boolean"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
},
"version": {
"description": "Current version of the computed insight.",
"minimum": 0,
"type": "integer"
}
},
"required": [
"data",
"isCurrentClusterInsightVersion",
"next",
"previous",
"totalCount",
"version"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Insights for a clustering project model on a single featurelist. |
ClusterInsightsPaginatedResponse |
| 404 |
Not Found |
The project or the model was not found or insights have not been computed yet. |
None |
| 422 |
Unprocessable Entity |
Feature Impact is required. Please, compute it first. |
None |
Retrieve Image Activation Maps by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/imageActivationMaps/
Authentication requirements: BearerAuth
Retrieve Image Activation Maps for a feature of a model.
Image Activation maps are a technique to get the discriminative image regions used by a CNN to identify a specific class in the image. In other words, an image activation map lets us see which regions in the image were relevant to this class. The higher the value in the activation map the greater the effect the region had on the prediction.
Parameters
| Name |
In |
Type |
Required |
Description |
| featureName |
query |
string |
true |
Name of the feature to query |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"activationMapHeight": {
"description": "The height of each activation map (the number of rows in each activationValues matrix).",
"type": [
"integer",
"null"
]
},
"activationMapWidth": {
"description": "The width of each activation map (the number of items in each row of each activationValues matrix).",
"type": [
"integer",
"null"
]
},
"activationMaps": {
"description": "List of activation map objects",
"items": {
"properties": {
"activationValues": {
"description": "A 2D matrix of values (row-major) representing the activation strengths for particular image regions.",
"items": {
"items": {
"maximum": 255,
"minimum": 0,
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"actualTargetValue": {
"description": "Actual target value of the dataset row",
"oneOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
]
},
"featureName": {
"description": "The name of the column containing the image value the activation map is based upon.",
"type": "string"
},
"imageHeight": {
"description": "The height of the original image (in pixels) this activation map has been computed for.",
"type": "integer"
},
"imageId": {
"description": "ID of the original image this activation map has been computed for.",
"type": "string"
},
"imageWidth": {
"description": "The width of the original image (in pixels) this activation map has been computed for.",
"type": "integer"
},
"links": {
"description": "Download URLs.",
"properties": {
"downloadOriginalImage": {
"description": "URL of the original image",
"format": "uri",
"type": "string"
},
"downloadOverlayImage": {
"description": "URL of the original image overlaid by the activation heatmap",
"format": "uri",
"type": "string"
}
},
"required": [
"downloadOriginalImage",
"downloadOverlayImage"
],
"type": "object"
},
"overlayImageId": {
"description": "ID of the image containing the original image overlaid by the activation heatmap.",
"type": "string"
},
"predictedTargetValue": {
"description": "predicted target value of the dataset row containing this image.",
"oneOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"items": {
"type": "string"
},
"type": "array"
}
]
}
},
"required": [
"activationValues",
"actualTargetValue",
"featureName",
"imageHeight",
"imageId",
"imageWidth",
"links",
"overlayImageId",
"predictedTargetValue"
],
"type": "object"
},
"type": "array"
},
"targetBins": {
"description": "List of bin objects for regression or null",
"items": {
"properties": {
"targetBinEnd": {
"description": "End value for the target bin",
"type": "number"
},
"targetBinStart": {
"description": "Start value for the target bin",
"type": "number"
}
},
"required": [
"targetBinEnd",
"targetBinStart"
],
"type": "object"
},
"type": "array"
},
"targetValues": {
"description": "List of target values for classification or null",
"items": {
"description": "Target value",
"type": "string"
},
"type": "array"
}
},
"required": [
"activationMapHeight",
"activationMapWidth",
"activationMaps",
"targetBins",
"targetValues"
],
"type": "object"
}
Responses
Request the computation of image activation maps by project ID
Operation path: POST /api/v2/projects/{projectId}/models/{modelId}/imageActivationMaps/
Authentication requirements: BearerAuth
Request the computation of image activation maps for the specified model.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
202 Response
{
"properties": {
"id": {
"description": "The job ID.",
"type": "string"
},
"isBlocked": {
"description": "True if the job is waiting for its dependencies to be resolved first.",
"type": "boolean"
},
"jobType": {
"description": "the type of the job",
"enum": [
"compute_image_activation_maps"
],
"type": "string"
},
"message": {
"description": "Error message in case of failure.",
"type": "string"
},
"modelId": {
"description": "the model ID of the target model",
"type": "string"
},
"projectId": {
"description": "The project the job belongs to.",
"type": "string"
},
"status": {
"description": "The job status.",
"enum": [
"queue",
"inprogress",
"error",
"ABORTED",
"COMPLETED"
],
"type": "string"
},
"url": {
"description": "A URL that can be used to request details about the job.",
"type": "string"
}
},
"required": [
"id",
"isBlocked",
"jobType",
"message",
"modelId",
"projectId",
"status",
"url"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
Image activation map computation has been successfully requested |
ActivationMapsComputeResponse |
| 422 |
Unprocessable Entity |
Cannot compute image activation maps: if image activation maps were already computed for the model or there was another issue creating this job |
None |
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
url |
a url that can be polled to check the status of the job. |
Retrieve labelwise ROC curves by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/labelwiseRocCurves/{source}/
Authentication requirements: BearerAuth
Retrieve labelwise ROC curves for model and given source.
Parameters
| Name |
In |
Type |
Required |
Description |
| labels |
query |
string |
false |
Labels for which data is requested. |
| searchQuery |
query |
string |
false |
Search query for label. |
| sortBy |
query |
string |
false |
Property to sort labels in the response. |
| sortOrder |
query |
string |
false |
Sort order. |
| threshold |
query |
number |
false |
Threshold at which the metric should be sorted. |
| offset |
query |
integer |
false |
Number of labels to skip. |
| limit |
query |
integer |
false |
Number of labels to return. |
| includeModelAverage |
query |
boolean |
false |
Whether model average metrics should be included in the response. |
| projectId |
path |
string |
true |
Project Id. |
| modelId |
path |
string |
true |
Model Id. |
| source |
path |
string |
true |
Chart source. |
Enumerated Values
| Parameter |
Value |
| sortBy |
[accuracy, f1Score, falsePositiveRate, label, matthewsCorrelationCoefficient, negativePredictiveValue, positivePredictiveValue, trueNegativeRate, truePositiveRate] |
| sortOrder |
[ascending, descending] |
| source |
[validation, crossValidation, holdout] |
Example responses
200 Response
{
"properties": {
"averageModelMetrics": {
"description": "All average model metrics from one data source.",
"properties": {
"metrics": {
"description": "Average model metrics for the given thresholds.",
"items": {
"properties": {
"name": {
"description": "Metric name.",
"enum": [
"accuracy",
"f1Score",
"falsePositiveRate",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"trueNegativeRate",
"truePositiveRate"
],
"type": "string"
},
"numLabelsUsedInCalculation": {
"description": "Number of labels that were taken into account in the calculation of metric averages",
"type": "integer"
},
"values": {
"description": "Metric values at given thresholds.",
"items": {
"type": "number"
},
"maxItems": 100,
"minItems": 100,
"type": "array"
}
},
"required": [
"name",
"numLabelsUsedInCalculation",
"values"
],
"type": "object"
},
"maxItems": 8,
"minItems": 8,
"type": "array"
},
"source": {
"description": "Chart source.",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
},
"thresholds": {
"description": "Threshold values for which model metrics are available.",
"items": {
"maximum": 1,
"minimum": 0,
"type": "number"
},
"maxItems": 100,
"minItems": 100,
"type": "array"
}
},
"required": [
"metrics",
"source",
"thresholds"
],
"type": "object"
},
"charts": {
"description": "ROC data for all labels from one data source.",
"items": {
"properties": {
"auc": {
"description": "Area under the curve.",
"type": "number"
},
"kolmogorovSmirnovMetric": {
"description": "Kolmogorov-Smirnov metric.",
"type": "number"
},
"label": {
"description": "Label name.",
"type": "string"
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the positive class.",
"items": {
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "ROC characteristics for label.",
"items": {
"properties": {
"accuracy": {
"description": "Accuracy.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"falsePositiveRate": {
"description": "False positive rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"falsePositiveScore": {
"description": "False positive score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"fractionPredictedAsNegative": {
"description": "Fraction of negative predictions.",
"type": [
"number",
"null"
]
},
"fractionPredictedAsPositive": {
"description": "Fraction of positive predictions.",
"type": [
"number",
"null"
]
},
"liftNegative": {
"description": "Negative lift.",
"type": [
"number",
"null"
]
},
"liftPositive": {
"description": "Positive lift.",
"type": [
"number",
"null"
]
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"maximum": 1,
"minimum": -1,
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"threshold": {
"description": "Threshold.",
"maximum": 2,
"minimum": 0,
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"trueNegativeScore": {
"description": "True negative score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"truePositiveRate": {
"description": "True positive rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"truePositiveScore": {
"description": "True positive score.",
"minimum": 0,
"type": [
"integer",
"null"
]
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Data source of ROC characteristics.",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
}
},
"required": [
"auc",
"kolmogorovSmirnovMetric",
"label",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints",
"source"
],
"type": "object"
},
"type": "array"
},
"count": {
"description": "Number of labels returned on this page.",
"type": "integer"
},
"labels": {
"description": "All available target labels for this insight.",
"items": {
"description": "Label name.",
"type": "string"
},
"maxItems": 100,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"rocType": {
"description": "Type of ROC.",
"enum": [
"binary",
"labelwise"
],
"type": "string"
},
"totalCount": {
"description": "Total number of labels across all pages.",
"type": "integer"
}
},
"required": [
"averageModelMetrics",
"charts",
"labels",
"next",
"previous",
"rocType",
"totalCount"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Labelwise ROC curves for model and given source. |
LabelwiseROC |
Retrieve all available lift charts by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/liftChart/
Authentication requirements: BearerAuth
Retrieve all available lift charts for model. The response will include a json list of all available lift charts, in the same format as the response from [GET /api/v2/projects/{projectId}/models/{modelId}/liftChart/{source}/][get-apiv2projectsprojectidmodelsmodelidliftchartsource].
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"charts": {
"description": "List of lift chart data from all available sources.",
"items": {
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data.",
"enum": [
"validation",
"crossValidation",
"holdout",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string",
"x-enum-versionadded": [
{
"value": "backtest_2",
"x-versionadded": "v2.23"
},
{
"value": "backtest_3",
"x-versionadded": "v2.23"
},
{
"value": "backtest_4",
"x-versionadded": "v2.23"
},
{
"value": "backtest_5",
"x-versionadded": "v2.23"
},
{
"value": "backtest_6",
"x-versionadded": "v2.23"
},
{
"value": "backtest_7",
"x-versionadded": "v2.23"
},
{
"value": "backtest_8",
"x-versionadded": "v2.23"
},
{
"value": "backtest_9",
"x-versionadded": "v2.23"
},
{
"value": "backtest_10",
"x-versionadded": "v2.23"
},
{
"value": "backtest_11",
"x-versionadded": "v2.23"
},
{
"value": "backtest_12",
"x-versionadded": "v2.23"
},
{
"value": "backtest_13",
"x-versionadded": "v2.23"
},
{
"value": "backtest_14",
"x-versionadded": "v2.23"
},
{
"value": "backtest_15",
"x-versionadded": "v2.23"
},
{
"value": "backtest_16",
"x-versionadded": "v2.23"
},
{
"value": "backtest_17",
"x-versionadded": "v2.23"
},
{
"value": "backtest_18",
"x-versionadded": "v2.23"
},
{
"value": "backtest_19",
"x-versionadded": "v2.23"
},
{
"value": "backtest_20",
"x-versionadded": "v2.23"
}
]
}
},
"required": [
"bins",
"source"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"charts"
],
"type": "object"
}
Responses
Retrieve the lift chart data by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/liftChart/{source}/
Authentication requirements: BearerAuth
Retrieve the lift chart data from a single source.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| source |
path |
string |
true |
Source of the data |
Enumerated Values
| Parameter |
Value |
| source |
[validation, crossValidation, holdout, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
Example responses
200 Response
{
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data.",
"enum": [
"validation",
"crossValidation",
"holdout",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string",
"x-enum-versionadded": [
{
"value": "backtest_2",
"x-versionadded": "v2.23"
},
{
"value": "backtest_3",
"x-versionadded": "v2.23"
},
{
"value": "backtest_4",
"x-versionadded": "v2.23"
},
{
"value": "backtest_5",
"x-versionadded": "v2.23"
},
{
"value": "backtest_6",
"x-versionadded": "v2.23"
},
{
"value": "backtest_7",
"x-versionadded": "v2.23"
},
{
"value": "backtest_8",
"x-versionadded": "v2.23"
},
{
"value": "backtest_9",
"x-versionadded": "v2.23"
},
{
"value": "backtest_10",
"x-versionadded": "v2.23"
},
{
"value": "backtest_11",
"x-versionadded": "v2.23"
},
{
"value": "backtest_12",
"x-versionadded": "v2.23"
},
{
"value": "backtest_13",
"x-versionadded": "v2.23"
},
{
"value": "backtest_14",
"x-versionadded": "v2.23"
},
{
"value": "backtest_15",
"x-versionadded": "v2.23"
},
{
"value": "backtest_16",
"x-versionadded": "v2.23"
},
{
"value": "backtest_17",
"x-versionadded": "v2.23"
},
{
"value": "backtest_18",
"x-versionadded": "v2.23"
},
{
"value": "backtest_19",
"x-versionadded": "v2.23"
},
{
"value": "backtest_20",
"x-versionadded": "v2.23"
}
]
}
},
"required": [
"bins",
"source"
],
"type": "object"
}
Responses
Retrieve multiclass feature effects by id
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/multiclassFeatureEffects/
Authentication requirements: BearerAuth
Retrieve feature effects for each class in a multiclass model.
Parameters
| Name |
In |
Type |
Required |
Description |
| source |
query |
string |
false |
Models data source. |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
false |
At most this many results are returned. The default may change without notice. |
| class |
query |
string,null |
false |
Target class label. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| source |
[training, validation, holdout] |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "A list of feature effects scores for each class in multiclass project.",
"items": {
"properties": {
"class": {
"description": "Target class label.",
"type": "string"
},
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"class",
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model ID",
"type": "string"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID",
"type": "string"
},
"source": {
"description": "Models data source.",
"type": "string"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"modelId",
"next",
"previous",
"projectId",
"source",
"totalCount"
],
"type": "object"
}
Responses
Create multiclass feature effects by id
Operation path: POST /api/v2/projects/{projectId}/models/{modelId}/multiclassFeatureEffects/
Authentication requirements: BearerAuth
Compute feature effects for a multiclass model. If the job has been previously submitted, the request fails, returning the jobId of the previously submitted job. Use this jobId to check status of the previously submitted job.
NOTE: feature effects are computed for top 100 classes.
Body parameter
{
"properties": {
"features": {
"description": "The list of features to use to calculate feature effects.",
"items": {
"type": "string"
},
"maxItems": 20000,
"type": "array"
},
"rowCount": {
"description": "The number of rows from dataset to use for Feature Impact calculation.",
"maximum": 100000,
"minimum": 10,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.21"
},
"topNFeatures": {
"description": "Number of top features (ranked by feature impact) to use to calculate feature effects.",
"exclusiveMinimum": 0,
"maximum": 1000,
"type": [
"integer",
"null"
]
}
},
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| body |
body |
MulticlassFeatureEffectCreate |
false |
none |
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
The Feature Effects request has been successfully submitted. See Location header. |
None |
| 403 |
Forbidden |
User does not have permission to view or submit jobs for the project. |
None |
| 404 |
Not Found |
Project, model, source or computation results do not exist. |
None |
| 422 |
Unprocessable Entity |
Queue submission error. If the rowCount exceeds the maximum or minimum value for this dataset. Minimum is 10 rows. Maximum is 100000 rows or the training sample size of the model, whichever is less. If neither features nor topNFeatures is provided. |
None |
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Retrieve multiclass feature impact by id
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/multiclassFeatureImpact/
Authentication requirements: BearerAuth
Retrieve feature impact scores for each class in a multiclass model.
Feature Impact is computed for each column by creating new data with that column randomly permuted (but the others left unchanged), and seeing how the error metric score for the predictions is affected. Elsewhere this technique is sometimes called 'Permutation Importance'.
The impactUnnormalized is how much worse the error metric score is when making predictions on this modified data. The impactNormalized is normalized so that the largest value is 1. In both cases, larger values indicate more important features.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"classFeatureImpacts": {
"description": "A list of feature importance scores for each class in multiclass project.",
"items": {
"properties": {
"class": {
"description": "Target class label.",
"type": "string"
},
"featureImpacts": {
"description": "A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"parentFeatureName": {
"description": "The name of the parent feature.",
"type": [
"string",
"null"
]
},
"redundantWith": {
"description": "Name of feature that has the highest correlation with this feature.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized",
"redundantWith"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
}
},
"required": [
"class",
"featureImpacts"
],
"type": "object"
},
"type": "array"
},
"count": {
"description": "Number of feature impact records in a given batch.",
"type": "integer"
},
"next": {
"description": "URL for the next page of results or `null`.",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL for the next page of results or `null`.",
"format": "uri",
"type": [
"string",
"null"
]
},
"ranRedundancyDetection": {
"description": "Indicates whether redundant feature identification was run while calculating this feature impact. Currently always False, as redundant feature identification isn't supported for multiclass in DataRobot.",
"type": "boolean"
},
"shapBased": {
"description": "Indicates whether feature impact was calculated using Shapley values. Currently always `False`, as SHAP isn't supported for multiclass in DataRobot.",
"type": "boolean"
}
},
"required": [
"classFeatureImpacts",
"count",
"next",
"previous",
"ranRedundancyDetection",
"shapBased"
],
"type": "object"
}
Responses
Retrieve multiclass lift chart by id
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/multiclassLiftChart/
Authentication requirements: BearerAuth
Retrieve all available lift charts for multiclass model.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"charts": {
"description": "List of lift chart data from all available sources.",
"items": {
"properties": {
"classBins": {
"description": "List of lift chart data for each target class.",
"items": {
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"targetClass": {
"description": "Target class for the lift chart.",
"type": "string"
}
},
"required": [
"bins",
"targetClass"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
}
},
"required": [
"classBins",
"source"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"charts"
],
"type": "object"
}
Responses
Retrieve the multiclass lift chart data by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/multiclassLiftChart/{source}/
Authentication requirements: BearerAuth
Retrieve the multiclass lift chart data from a single source.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| source |
path |
string |
true |
Source of the data. |
Enumerated Values
| Parameter |
Value |
| source |
[validation, crossValidation, holdout] |
Example responses
200 Response
{
"properties": {
"classBins": {
"description": "List of lift chart data for each target class.",
"items": {
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"targetClass": {
"description": "Target class for the lift chart.",
"type": "string"
}
},
"required": [
"bins",
"targetClass"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
}
},
"required": [
"classBins",
"source"
],
"type": "object"
}
Responses
Retrieve labelwise lift charts by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/multilabelLiftCharts/{source}/
Authentication requirements: BearerAuth
Retrieve labelwise lift charts for model and given source.
Parameters
| Name |
In |
Type |
Required |
Description |
| labels |
query |
string |
false |
Labels for which data is requested. |
| projectId |
path |
string |
true |
Project Id. |
| modelId |
path |
string |
true |
Model Id. |
| source |
path |
string |
true |
Chart source. |
Enumerated Values
| Parameter |
Value |
| source |
[validation, crossValidation, holdout] |
Example responses
200 Response
{
"properties": {
"labelBins": {
"description": "Lift charts for the given data source.",
"items": {
"properties": {
"bins": {
"description": "Lift chart data for that label.",
"items": {
"properties": {
"actual": {
"description": "Average of actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "For projects with weights, it is the sum of the weights of all rows in the bins. Otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "Average of predicted target values for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"maxItems": 60,
"type": "array"
},
"label": {
"description": "Label name.",
"type": "string"
}
},
"required": [
"bins",
"label"
],
"type": "object"
},
"maxItems": 100,
"type": "array"
},
"labels": {
"description": "All available target labels for this insight.",
"items": {
"description": "Label name.",
"type": "string"
},
"maxItems": 100,
"type": "array"
},
"modelId": {
"description": "Model Id.",
"type": "string"
},
"projectId": {
"description": "Project Id.",
"type": "string"
},
"source": {
"description": "Data source of Lift charts.",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
}
},
"required": [
"labelBins",
"labels",
"modelId",
"projectId",
"source"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
Labelwise lift charts for model and given source. |
LabelwiseLiftChart |
Retrieve all residuals charts by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/residuals/
Authentication requirements: BearerAuth
Retrieve all residuals charts for a model.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"residuals": {
"description": "Residuals chart data from all available sources",
"properties": {
"crossValidation": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"holdout": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"validation": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
}
},
"type": "object"
}
},
"required": [
"residuals"
],
"type": "object"
}
Responses
Retrieve the residuals chart data by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/residuals/{source}/
Authentication requirements: BearerAuth
Retrieve the residuals chart data from a single source.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| source |
path |
string |
true |
Source of the data. |
Enumerated Values
| Parameter |
Value |
| source |
[validation, crossValidation, holdout] |
Example responses
200 Response
{
"properties": {
"residuals": {
"description": "Residuals chart data from all available sources",
"properties": {
"crossValidation": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"holdout": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"validation": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
}
},
"type": "object"
}
},
"required": [
"residuals"
],
"type": "object"
}
Responses
Retrieve all available ROC curves by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/rocCurve/
Authentication requirements: BearerAuth
Retrieve all available ROC curves for model. The response will include a json list of all available ROC curves, in the same format as the response from [GET /api/v2/projects/{projectId}/models/{modelId}/rocCurve/{source}/][get-apiv2projectsprojectidmodelsmodelidroccurvesource].
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"charts": {
"description": "List of ROC curve data from all available sources.",
"items": {
"properties": {
"auc": {
"description": "AUC value",
"type": [
"number",
"null"
]
},
"kolmogorovSmirnovMetric": {
"description": "Kolmogorov-Smirnov metric value",
"type": [
"number",
"null"
]
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the positive class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "The ROC curve data for that source, as specified below.",
"items": {
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data.",
"enum": [
"validation",
"crossValidation",
"holdout",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string",
"x-enum-versionadded": [
{
"value": "backtest_2",
"x-versionadded": "v2.23"
},
{
"value": "backtest_3",
"x-versionadded": "v2.23"
},
{
"value": "backtest_4",
"x-versionadded": "v2.23"
},
{
"value": "backtest_5",
"x-versionadded": "v2.23"
},
{
"value": "backtest_6",
"x-versionadded": "v2.23"
},
{
"value": "backtest_7",
"x-versionadded": "v2.23"
},
{
"value": "backtest_8",
"x-versionadded": "v2.23"
},
{
"value": "backtest_9",
"x-versionadded": "v2.23"
},
{
"value": "backtest_10",
"x-versionadded": "v2.23"
},
{
"value": "backtest_11",
"x-versionadded": "v2.23"
},
{
"value": "backtest_12",
"x-versionadded": "v2.23"
},
{
"value": "backtest_13",
"x-versionadded": "v2.23"
},
{
"value": "backtest_14",
"x-versionadded": "v2.23"
},
{
"value": "backtest_15",
"x-versionadded": "v2.23"
},
{
"value": "backtest_16",
"x-versionadded": "v2.23"
},
{
"value": "backtest_17",
"x-versionadded": "v2.23"
},
{
"value": "backtest_18",
"x-versionadded": "v2.23"
},
{
"value": "backtest_19",
"x-versionadded": "v2.23"
},
{
"value": "backtest_20",
"x-versionadded": "v2.23"
}
]
}
},
"required": [
"auc",
"kolmogorovSmirnovMetric",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints",
"source"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"charts"
],
"type": "object"
}
Responses
Retrieve the ROC curve data by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/rocCurve/{source}/
Authentication requirements: BearerAuth
Retrieve the ROC curve data from a single source. The response includes an array of pointsshowing the performance of the model at different thresholds for classification, and arrays of sample predictions for both the positive and negative classes.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| source |
path |
string |
true |
Source of the data |
Enumerated Values
| Parameter |
Value |
| source |
[validation, crossValidation, holdout, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
Example responses
200 Response
{
"properties": {
"auc": {
"description": "AUC value",
"type": [
"number",
"null"
]
},
"kolmogorovSmirnovMetric": {
"description": "Kolmogorov-Smirnov metric value",
"type": [
"number",
"null"
]
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the positive class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "The ROC curve data for that source, as specified below.",
"items": {
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data.",
"enum": [
"validation",
"crossValidation",
"holdout",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string",
"x-enum-versionadded": [
{
"value": "backtest_2",
"x-versionadded": "v2.23"
},
{
"value": "backtest_3",
"x-versionadded": "v2.23"
},
{
"value": "backtest_4",
"x-versionadded": "v2.23"
},
{
"value": "backtest_5",
"x-versionadded": "v2.23"
},
{
"value": "backtest_6",
"x-versionadded": "v2.23"
},
{
"value": "backtest_7",
"x-versionadded": "v2.23"
},
{
"value": "backtest_8",
"x-versionadded": "v2.23"
},
{
"value": "backtest_9",
"x-versionadded": "v2.23"
},
{
"value": "backtest_10",
"x-versionadded": "v2.23"
},
{
"value": "backtest_11",
"x-versionadded": "v2.23"
},
{
"value": "backtest_12",
"x-versionadded": "v2.23"
},
{
"value": "backtest_13",
"x-versionadded": "v2.23"
},
{
"value": "backtest_14",
"x-versionadded": "v2.23"
},
{
"value": "backtest_15",
"x-versionadded": "v2.23"
},
{
"value": "backtest_16",
"x-versionadded": "v2.23"
},
{
"value": "backtest_17",
"x-versionadded": "v2.23"
},
{
"value": "backtest_18",
"x-versionadded": "v2.23"
},
{
"value": "backtest_19",
"x-versionadded": "v2.23"
},
{
"value": "backtest_20",
"x-versionadded": "v2.23"
}
]
}
},
"required": [
"auc",
"kolmogorovSmirnovMetric",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints",
"source"
],
"type": "object"
}
Responses
Retrieve Feature Impact for a model by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/shapImpact/
Authentication requirements: BearerAuth
Retrieve Feature Impact for a model. SHAP impact is computed by calculating the shap values on a sample of training data and then taking the mean absolute value for each column. The larger the impact value, the more important the feature.
DEPRECATED: Use the componentized route instead: [GET /api/v2/insights/shapImpact/models/{entityId}/][get-apiv2insightsshapimpactmodelsentityid].
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "The number of shapImpact object returned",
"type": "integer"
},
"rowCount": {
"description": "The number of rows from dataset to use.",
"type": "integer"
},
"shapImpacts": {
"description": "A list which contains shap impact scores for top 1000 features used by a model",
"items": {
"properties": {
"featureName": {
"description": "The feature name in dataset",
"type": "string"
},
"impactNormalized": {
"description": "The normalized impact score value (largest value is 1)",
"type": "number"
},
"impactUnnormalized": {
"description": "The raw impact score value",
"type": "number"
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"required": [
"count",
"shapImpacts"
],
"type": "object"
}
Responses
Create SHAP-based Feature Impact by project ID
Operation path: POST /api/v2/projects/{projectId}/models/{modelId}/shapImpact/
Authentication requirements: BearerAuth
Create SHAP-based Feature Impact for the model.
DEPRECATED: Use the componentized route instead: [POST /api/v2/insights/shapImpact/][post-apiv2insightsshapimpact].
Body parameter
{
"properties": {
"rowCount": {
"description": "The sample size to use for Feature Impact computation. It is possible to re-compute Feature Impact with a different row count.",
"maximum": 100000,
"minimum": 10,
"type": "integer",
"x-versionadded": "v2.21"
}
},
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| body |
body |
FeatureImpactCreatePayload |
false |
none |
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
none |
None |
Retrieve word cloud data by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/wordCloud/
Authentication requirements: BearerAuth
Retrieve word cloud data for a model. Not all models will have word cloud data available, even when they use text features.
Parameters
| Name |
In |
Type |
Required |
Description |
| excludeStopWords |
query |
string |
false |
Set to true if you want stopwords excluded from the response. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Enumerated Values
| Parameter |
Value |
| excludeStopWords |
[false, False, true, True] |
Example responses
200 Response
{
"properties": {
"ngrams": {
"description": "A list of dictionaries containing information about the most important ngrams.",
"items": {
"properties": {
"class": {
"description": "For classification - values of the target class for corresponding word or ngram. For regression - null.",
"type": [
"string",
"null"
]
},
"coefficient": {
"description": "Describes effect of this ngram on the target. A large negative value means a strong effect toward the negative class in classification projects and a smaller predicted target value in regression projects. A large positive value means a strong effect toward the positive class and a larger predicted target value respectively.",
"maximum": 1,
"minimum": -1,
"type": "number"
},
"count": {
"description": "Number of rows in the training sample where this ngram appears.",
"type": "integer"
},
"frequency": {
"description": "Frequency of this ngram relative to the most common ngram.",
"exclusiveMinimum": 0,
"maximum": 1,
"type": "number"
},
"isStopword": {
"description": "True for ngrams that DataRobot evaluates as stopwords.",
"type": "boolean"
},
"ngram": {
"description": "Word or ngram value.",
"type": "string"
},
"variable": {
"description": "String representation of the ngram source - contains column name and, for some models, preprocessing details. E.g. NGRAM_OCCUR_L2_colname will be for ngram occurrences count using L2 normalization from the colname column.",
"type": "string",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficient",
"count",
"frequency",
"isStopword",
"ngram",
"variable"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"ngrams"
],
"type": "object"
}
Responses
Retrieve multicategorical data quality log by project ID
Operation path: GET /api/v2/projects/{projectId}/multicategoricalInvalidFormat/
Authentication requirements: BearerAuth
Retrieve multicategorical data quality log.
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The ID of the project this request is associated with. |
Example responses
200 Response
{
"properties": {
"data": {
"description": "Error data.",
"properties": {
"errors": {
"description": "Multicategorical format errors.",
"items": {
"properties": {
"error": {
"description": "Error type.",
"type": "string"
},
"feature": {
"description": "Feature name.",
"type": "string"
},
"rowData": {
"description": "Content of the row containing format error.",
"type": [
"string",
"null"
]
},
"rowIndex": {
"description": "Row index of the row containing format error.",
"type": [
"integer",
"null"
]
}
},
"required": [
"error",
"feature",
"rowData",
"rowIndex"
],
"type": "object"
},
"maxItems": 100,
"type": "array"
}
},
"required": [
"errors"
],
"type": "object"
},
"projectId": {
"description": "The ID of the project this request is associated with.",
"type": "string"
}
},
"required": [
"data",
"projectId"
],
"type": "object"
}
Responses
Get file by project ID
Operation path: GET /api/v2/projects/{projectId}/multicategoricalInvalidFormat/file/
Authentication requirements: BearerAuth
Get file with format errors of potential multicategorical features.
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The ID of the project this request is associated with. |
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
File with format errors of potential multicategorical features. |
None |
List of all payoff matrices by project ID
Operation path: GET /api/v2/projects/{projectId}/payoffMatrices/
Authentication requirements: BearerAuth
List of all payoff matrices for a project.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
true |
Number of payoff matrices to skip. |
| limit |
query |
integer |
true |
Number of payoff matrices to return. |
| projectId |
path |
string |
true |
The project ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items in current page.",
"type": "integer"
},
"data": {
"description": "Payoff matrices for a project.",
"items": {
"properties": {
"falseNegativeValue": {
"description": "Payoff value for false negatives used in profit curve calculation.",
"type": "number"
},
"falsePositiveValue": {
"description": "Payoff value for false positives used in profit curve calculation.",
"type": "number"
},
"id": {
"description": "ObjectId of the payoff matrix.",
"type": "string"
},
"name": {
"description": "Label for the payoff matrix.",
"type": "string"
},
"projectId": {
"description": "ID of the project associated with the payoff matrix.",
"type": "string"
},
"trueNegativeValue": {
"description": "Payoff value for true negatives used in profit curve calculation.",
"type": "number"
},
"truePositiveValue": {
"description": "Payoff value for true positives used in profit curve calculation.",
"type": "number"
}
},
"required": [
"falseNegativeValue",
"falsePositiveValue",
"id",
"name",
"projectId",
"trueNegativeValue",
"truePositiveValue"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page)",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page)",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "Total number of items.",
"type": "integer"
}
},
"required": [
"count",
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Responses
Create a payoff matrix by project ID
Operation path: POST /api/v2/projects/{projectId}/payoffMatrices/
Authentication requirements: BearerAuth
Create a payoff matrix associated with a project.
Body parameter
{
"properties": {
"falseNegativeValue": {
"description": "False negative value to use for profit curve calculation.",
"type": "number"
},
"falsePositiveValue": {
"description": "False positive value to use for profit curve calculation.",
"type": "number"
},
"name": {
"description": "Name of the payoff matrix to be created.",
"type": "string"
},
"trueNegativeValue": {
"description": "True negative value to use for profit curve calculation.",
"type": "number"
},
"truePositiveValue": {
"description": "True positive value to use for profit curve calculation.",
"type": "number"
}
},
"required": [
"falseNegativeValue",
"falsePositiveValue",
"name",
"trueNegativeValue",
"truePositiveValue"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| body |
body |
PayoffMatricesCreate |
false |
none |
Responses
| Status |
Meaning |
Description |
Schema |
| 201 |
Created |
none |
None |
| 409 |
Conflict |
Conflict occurred: [Error details from exception] |
None |
| 422 |
Unprocessable Entity |
- This route is only allowed for binary classification projects. |
|
| - Error occurred during processing: [Error details from exception] |
None |
|
|
Delete a payoff matrix by project ID
Operation path: DELETE /api/v2/projects/{projectId}/payoffMatrices/{payoffMatrixId}/
Authentication requirements: BearerAuth
Delete a payoff matrix in a project.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| payoffMatrixId |
path |
string |
true |
ObjectId of the payoff matrix. |
Responses
| Status |
Meaning |
Description |
Schema |
| 204 |
No Content |
Payoff matrix deleted successfully. |
None |
Update a payoff matrix by project ID
Operation path: PUT /api/v2/projects/{projectId}/payoffMatrices/{payoffMatrixId}/
Authentication requirements: BearerAuth
Update all fields in a payoff matrix, including values and label.
Body parameter
{
"properties": {
"falseNegativeValue": {
"description": "False negative value to use for profit curve calculation.",
"type": "number"
},
"falsePositiveValue": {
"description": "False positive value to use for profit curve calculation.",
"type": "number"
},
"name": {
"description": "Name of the payoff matrix to be created.",
"type": "string"
},
"trueNegativeValue": {
"description": "True negative value to use for profit curve calculation.",
"type": "number"
},
"truePositiveValue": {
"description": "True positive value to use for profit curve calculation.",
"type": "number"
}
},
"required": [
"falseNegativeValue",
"falsePositiveValue",
"name",
"trueNegativeValue",
"truePositiveValue"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| payoffMatrixId |
path |
string |
true |
ObjectId of the payoff matrix. |
| body |
body |
PayoffMatricesCreate |
false |
none |
Example responses
200 Response
{
"properties": {
"falseNegativeValue": {
"description": "Payoff value for false negatives used in profit curve calculation.",
"type": "number"
},
"falsePositiveValue": {
"description": "Payoff value for false positives used in profit curve calculation.",
"type": "number"
},
"id": {
"description": "ObjectId of the payoff matrix.",
"type": "string"
},
"name": {
"description": "Label for the payoff matrix.",
"type": "string"
},
"projectId": {
"description": "ID of the project associated with the payoff matrix.",
"type": "string"
},
"trueNegativeValue": {
"description": "Payoff value for true negatives used in profit curve calculation.",
"type": "number"
},
"truePositiveValue": {
"description": "Payoff value for true positives used in profit curve calculation.",
"type": "number"
}
},
"required": [
"falseNegativeValue",
"falsePositiveValue",
"id",
"name",
"projectId",
"trueNegativeValue",
"truePositiveValue"
],
"type": "object"
}
Responses
List Rating Table Models by project ID
Operation path: GET /api/v2/projects/{projectId}/ratingTableModels/
Authentication requirements: BearerAuth
Lists all the models from a project that have rating tables.
Parameters
| Name |
In |
Type |
Required |
Description |
| withMetric |
query |
string |
false |
If specified, the returned models will only have scores for this metric. If not, all metrics will be included. |
| showInSampleScores |
query |
boolean |
false |
If specified, will return metric scores for models trained into validation/holdout for projects that do not have stacked predictions. |
| name |
query |
string |
false |
If specified, filters for models with a model type matching name. |
| samplePct |
query |
number |
false |
If specified, filters for models with a matching sample percentage. |
| isStarred |
query |
string |
false |
If specified, filters for models marked as starred. |
| orderBy |
query |
string |
false |
A comma-separated list of metrics to sort by. If metric is prefixed with a '-', models are sorted by this metric in descending order, otherwise are sorted in ascending order. Valid sorting metrics are metric and samplePct. Use of metric sorts models by metric value selected for this project using the validation score. Use of the prefix accounts for the direction of the metric, so -metric will sort in order of decreasing 'goodness', which may be opposite to the natural numerical order. If not specified, -metric will be used. |
| projectId |
path |
string |
true |
the project to list models from |
Enumerated Values
| Parameter |
Value |
| isStarred |
[false, False, true, True] |
| orderBy |
[metric, -metric, samplePct, -samplePct] |
Example responses
200 Response
{
"items": {
"properties": {
"blenderModels": {
"description": "Models that are in the blender.",
"items": {
"type": "integer"
},
"maxItems": 100,
"type": "array",
"x-versionadded": "v2.36"
},
"blueprintId": {
"description": "The blueprint used to construct the model.",
"type": "string"
},
"dataSelectionMethod": {
"description": "Identifies which setting defines the training size of the model when making predictions and scoring. Only used by datetime models.",
"enum": [
"duration",
"rowCount",
"selectedDateRange",
"useProjectSettings"
],
"type": "string"
},
"externalPredictionModel": {
"description": "If the model is an external prediction model.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"featurelistId": {
"description": "The ID of the feature list used by the model.",
"type": [
"string",
"null"
]
},
"featurelistName": {
"description": "The name of the feature list used by the model. If null, themodel was trained on multiple feature lists.",
"type": [
"string",
"null"
]
},
"frozenPct": {
"description": "The training percent used to train the frozen model.",
"type": [
"number",
"null"
],
"x-versionadded": "v2.36"
},
"hasCodegen": {
"description": "If the model has a codegen JAR file.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"hasFinetuners": {
"description": "Whether a model has fine tuners.",
"type": "boolean"
},
"icons": {
"description": "The icons associated with the model.",
"type": [
"integer",
"null"
],
"x-versionadded": "v2.36"
},
"id": {
"description": "The ID of the model.",
"type": "string"
},
"isAugmented": {
"description": "Whether a model was trained using augmentation.",
"type": "boolean"
},
"isBlender": {
"description": "If the model is a blender.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"isCustom": {
"description": "If the model contains custom tasks.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"isFrozen": {
"description": "Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model.",
"type": "boolean"
},
"isNClustersDynamicallyDetermined": {
"description": "Whether number of clusters is dynamically determined. Only valid in unsupervised clustering projects.",
"type": "boolean"
},
"isStarred": {
"description": "Indicates whether the model has been starred.",
"type": "boolean"
},
"isTrainedIntoHoldout": {
"description": "Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size.",
"type": "boolean"
},
"isTrainedIntoValidation": {
"description": "Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size.",
"type": "boolean"
},
"isTrainedOnGpu": {
"description": "Whether the model was trained using GPU workers.",
"type": "boolean",
"x-versionadded": "v2.33"
},
"isTransparent": {
"description": "If the model is a transparent model with exposed coefficients.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"isUserModel": {
"description": "If the model was created with Composable ML.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"lifecycle": {
"description": "Object returning model lifecycle.",
"properties": {
"reason": {
"description": "Reason for lifecycle stage. None if model is active.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.30"
},
"stage": {
"description": "Model lifecycle stage.",
"enum": [
"active",
"deprecated",
"disabled"
],
"type": "string",
"x-versionadded": "v2.30"
}
},
"required": [
"reason",
"stage"
],
"type": "object"
},
"linkFunction": {
"description": "The link function the final modeler uses in the blueprint. If no link function exists, returns null.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"metrics": {
"description": "The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed.",
"type": "object"
},
"modelCategory": {
"description": "Indicates the type of model. Returns `prime` for DataRobot Prime models, `blend` for blender models, `combined` for combined models, and `model` for all other models.",
"enum": [
"model",
"prime",
"blend",
"combined",
"incrementalLearning"
],
"type": "string"
},
"modelFamily": {
"description": "the family model belongs to, e.g. SVM, GBM, etc.",
"type": "string",
"x-versionadded": "v2.21"
},
"modelFamilyFullName": {
"description": "The full name of the family that the model belongs to. For e.g., Support Vector Machine, Gradient Boosting Machine, etc.",
"type": "string",
"x-versionadded": "v2.31"
},
"modelNumber": {
"description": "The model number from the Leaderboard.",
"exclusiveMinimum": 0,
"type": [
"integer",
"null"
]
},
"modelType": {
"description": "Identifies the model (e.g.,`Nystroem Kernel SVM Regressor`).",
"type": "string"
},
"monotonicDecreasingFeaturelistId": {
"description": "the ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"monotonicIncreasingFeaturelistId": {
"description": "the ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"nClusters": {
"description": "The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.",
"type": [
"integer",
"null"
]
},
"parentModelId": {
"description": "The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise.",
"type": [
"string",
"null"
]
},
"predictionThreshold": {
"description": "threshold used for binary classification in predictions.",
"maximum": 1,
"minimum": 0,
"type": "number",
"x-versionadded": "v2.13"
},
"predictionThresholdReadOnly": {
"description": "indicates whether modification of a predictions threshold is forbidden. Since v2.22 threshold modification is allowed.",
"type": "boolean",
"x-versionadded": "v2.13"
},
"processes": {
"description": "The list of processes used by the model.",
"items": {
"type": "string"
},
"maxItems": 100,
"type": "array"
},
"projectId": {
"description": "The ID of the project to which the model belongs.",
"type": "string"
},
"ratingTableId": {
"description": "The rating table ID",
"type": "string"
},
"samplePct": {
"description": "The percentage of the dataset used in training the model.",
"exclusiveMinimum": 0,
"type": [
"number",
"null"
]
},
"samplingMethod": {
"description": "indicates sampling method used to select training data in datetime models. For row-based project this is the way how requested number of rows are selected.For other projects (duration-based, start/end, project settings) - how specified percent of rows (timeWindowSamplePct) is selected from specified time window.",
"enum": [
"random",
"latest"
],
"type": "string"
},
"supportsComposableMl": {
"description": "indicates whether this model is supported in Composable ML.",
"type": "boolean",
"x-versionadded": "2.26"
},
"supportsMonotonicConstraints": {
"description": "whether this model supports enforcing monotonic constraints",
"type": "boolean",
"x-versionadded": "v2.21"
},
"timeWindowSamplePct": {
"description": "An integer between 1 and 99, indicating the percentage of sampling within the time window. The points kept are determined by samplingMethod option. Will be null if no sampling was specified. Only used by datetime models.",
"exclusiveMaximum": 100,
"exclusiveMinimum": 0,
"type": [
"integer",
"null"
]
},
"trainingDuration": {
"description": "the duration spanned by the dates in the partition column for the data used to train the model",
"type": [
"string",
"null"
]
},
"trainingEndDate": {
"description": "the end date of the dates in the partition column for the data used to train the model",
"format": "date-time",
"type": [
"string",
"null"
]
},
"trainingRowCount": {
"description": "The number of rows used to train the model.",
"exclusiveMinimum": 0,
"type": [
"integer",
"null"
]
},
"trainingStartDate": {
"description": "the start date of the dates in the partition column for the data used to train the model",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"blenderModels",
"blueprintId",
"externalPredictionModel",
"featurelistId",
"featurelistName",
"frozenPct",
"hasCodegen",
"icons",
"id",
"isBlender",
"isCustom",
"isFrozen",
"isStarred",
"isTrainedIntoHoldout",
"isTrainedIntoValidation",
"isTrainedOnGpu",
"isTransparent",
"isUserModel",
"lifecycle",
"linkFunction",
"metrics",
"modelCategory",
"modelFamily",
"modelFamilyFullName",
"modelNumber",
"modelType",
"monotonicDecreasingFeaturelistId",
"monotonicIncreasingFeaturelistId",
"parentModelId",
"predictionThreshold",
"predictionThresholdReadOnly",
"processes",
"projectId",
"ratingTableId",
"samplePct",
"supportsComposableMl",
"supportsMonotonicConstraints",
"trainingDuration",
"trainingEndDate",
"trainingRowCount",
"trainingStartDate"
],
"type": "object"
},
"type": "array"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
The response will include a json list of models in the same format as |
|
| those from GET /api/v2/projects/(projectId)/ratingTableModels/(modelId)/. |
Inline |
|
|
Response Schema
Status Code 200
| Name |
Type |
Required |
Restrictions |
Description |
| anonymous |
[RatingTableModelDetailsResponse] |
false |
|
none |
| » blenderModels |
[integer] |
true |
maxItems: 100
|
Models that are in the blender. |
| » blueprintId |
string |
true |
|
The blueprint used to construct the model. |
| » dataSelectionMethod |
string |
false |
|
Identifies which setting defines the training size of the model when making predictions and scoring. Only used by datetime models. |
| » externalPredictionModel |
boolean |
true |
|
If the model is an external prediction model. |
| » featurelistId |
string,null |
true |
|
The ID of the feature list used by the model. |
| » featurelistName |
string,null |
true |
|
The name of the feature list used by the model. If null, themodel was trained on multiple feature lists. |
| » frozenPct |
number,null |
true |
|
The training percent used to train the frozen model. |
| » hasCodegen |
boolean |
true |
|
If the model has a codegen JAR file. |
| » hasFinetuners |
boolean |
false |
|
Whether a model has fine tuners. |
| » icons |
integer,null |
true |
|
The icons associated with the model. |
| » id |
string |
true |
|
The ID of the model. |
| » isAugmented |
boolean |
false |
|
Whether a model was trained using augmentation. |
| » isBlender |
boolean |
true |
|
If the model is a blender. |
| » isCustom |
boolean |
true |
|
If the model contains custom tasks. |
| » isFrozen |
boolean |
true |
|
Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model. |
| » isNClustersDynamicallyDetermined |
boolean |
false |
|
Whether number of clusters is dynamically determined. Only valid in unsupervised clustering projects. |
| » isStarred |
boolean |
true |
|
Indicates whether the model has been starred. |
| » isTrainedIntoHoldout |
boolean |
true |
|
Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size. |
| » isTrainedIntoValidation |
boolean |
true |
|
Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size. |
| » isTrainedOnGpu |
boolean |
true |
|
Whether the model was trained using GPU workers. |
| » isTransparent |
boolean |
true |
|
If the model is a transparent model with exposed coefficients. |
| » isUserModel |
boolean |
true |
|
If the model was created with Composable ML. |
| » lifecycle |
ModelLifecycle |
true |
|
Object returning model lifecycle. |
| »» reason |
string,null |
true |
|
Reason for lifecycle stage. None if model is active. |
| »» stage |
string |
true |
|
Model lifecycle stage. |
| » linkFunction |
string,null |
true |
|
The link function the final modeler uses in the blueprint. If no link function exists, returns null. |
| » metrics |
object |
true |
|
The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed. |
| » modelCategory |
string |
true |
|
Indicates the type of model. Returns prime for DataRobot Prime models, blend for blender models, combined for combined models, and model for all other models. |
| » modelFamily |
string |
true |
|
the family model belongs to, e.g. SVM, GBM, etc. |
| » modelFamilyFullName |
string |
true |
|
The full name of the family that the model belongs to. For e.g., Support Vector Machine, Gradient Boosting Machine, etc. |
| » modelNumber |
integer,null |
true |
|
The model number from the Leaderboard. |
| » modelType |
string |
true |
|
Identifies the model (e.g.,Nystroem Kernel SVM Regressor). |
| » monotonicDecreasingFeaturelistId |
string,null |
true |
|
the ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced. |
| » monotonicIncreasingFeaturelistId |
string,null |
true |
|
the ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced. |
| » nClusters |
integer,null |
false |
|
The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects. |
| » parentModelId |
string,null |
true |
|
The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise. |
| » predictionThreshold |
number |
true |
maximum: 1
minimum: 0
|
threshold used for binary classification in predictions. |
| » predictionThresholdReadOnly |
boolean |
true |
|
indicates whether modification of a predictions threshold is forbidden. Since v2.22 threshold modification is allowed. |
| » processes |
[string] |
true |
maxItems: 100
|
The list of processes used by the model. |
| » projectId |
string |
true |
|
The ID of the project to which the model belongs. |
| » ratingTableId |
string |
true |
|
The rating table ID |
| » samplePct |
number,null |
true |
|
The percentage of the dataset used in training the model. |
| » samplingMethod |
string |
false |
|
indicates sampling method used to select training data in datetime models. For row-based project this is the way how requested number of rows are selected.For other projects (duration-based, start/end, project settings) - how specified percent of rows (timeWindowSamplePct) is selected from specified time window. |
| » supportsComposableMl |
boolean |
true |
|
indicates whether this model is supported in Composable ML. |
| » supportsMonotonicConstraints |
boolean |
true |
|
whether this model supports enforcing monotonic constraints |
| » timeWindowSamplePct |
integer,null |
false |
|
An integer between 1 and 99, indicating the percentage of sampling within the time window. The points kept are determined by samplingMethod option. Will be null if no sampling was specified. Only used by datetime models. |
| » trainingDuration |
string,null |
true |
|
the duration spanned by the dates in the partition column for the data used to train the model |
| » trainingEndDate |
string,null(date-time) |
true |
|
the end date of the dates in the partition column for the data used to train the model |
| » trainingRowCount |
integer,null |
true |
|
The number of rows used to train the model. |
| » trainingStartDate |
string,null(date-time) |
true |
|
the start date of the dates in the partition column for the data used to train the model |
Enumerated Values
| Property |
Value |
| dataSelectionMethod |
[duration, rowCount, selectedDateRange, useProjectSettings] |
| stage |
[active, deprecated, disabled] |
| modelCategory |
[model, prime, blend, combined, incrementalLearning] |
| samplingMethod |
[random, latest] |
Create New Models by project ID
Operation path: POST /api/v2/projects/{projectId}/ratingTableModels/
Authentication requirements: BearerAuth
Create a new rating table model from a validated rating table record.
Body parameter
{
"properties": {
"ratingTableId": {
"description": "the rating table ID to use to create a new model",
"type": "string"
}
},
"required": [
"ratingTableId"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
the project that owns this data |
| body |
body |
CreateRatingTableModel |
false |
none |
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
the request was understood and accepted, and is now being worked on |
None |
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
url |
a url of an asynchronous operation status object that can be polled to check the status of the job validating the new rating table |
Retrieve Rating Table Model by project ID
Operation path: GET /api/v2/projects/{projectId}/ratingTableModels/{modelId}/
Authentication requirements: BearerAuth
Look up a particular rating table model.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
the project to retrieve the model from |
| modelId |
path |
string |
true |
the model to retrieve |
Example responses
200 Response
{
"properties": {
"blenderModels": {
"description": "Models that are in the blender.",
"items": {
"type": "integer"
},
"maxItems": 100,
"type": "array",
"x-versionadded": "v2.36"
},
"blueprintId": {
"description": "The blueprint used to construct the model.",
"type": "string"
},
"dataSelectionMethod": {
"description": "Identifies which setting defines the training size of the model when making predictions and scoring. Only used by datetime models.",
"enum": [
"duration",
"rowCount",
"selectedDateRange",
"useProjectSettings"
],
"type": "string"
},
"externalPredictionModel": {
"description": "If the model is an external prediction model.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"featurelistId": {
"description": "The ID of the feature list used by the model.",
"type": [
"string",
"null"
]
},
"featurelistName": {
"description": "The name of the feature list used by the model. If null, themodel was trained on multiple feature lists.",
"type": [
"string",
"null"
]
},
"frozenPct": {
"description": "The training percent used to train the frozen model.",
"type": [
"number",
"null"
],
"x-versionadded": "v2.36"
},
"hasCodegen": {
"description": "If the model has a codegen JAR file.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"hasFinetuners": {
"description": "Whether a model has fine tuners.",
"type": "boolean"
},
"icons": {
"description": "The icons associated with the model.",
"type": [
"integer",
"null"
],
"x-versionadded": "v2.36"
},
"id": {
"description": "The ID of the model.",
"type": "string"
},
"isAugmented": {
"description": "Whether a model was trained using augmentation.",
"type": "boolean"
},
"isBlender": {
"description": "If the model is a blender.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"isCustom": {
"description": "If the model contains custom tasks.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"isFrozen": {
"description": "Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model.",
"type": "boolean"
},
"isNClustersDynamicallyDetermined": {
"description": "Whether number of clusters is dynamically determined. Only valid in unsupervised clustering projects.",
"type": "boolean"
},
"isStarred": {
"description": "Indicates whether the model has been starred.",
"type": "boolean"
},
"isTrainedIntoHoldout": {
"description": "Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size.",
"type": "boolean"
},
"isTrainedIntoValidation": {
"description": "Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size.",
"type": "boolean"
},
"isTrainedOnGpu": {
"description": "Whether the model was trained using GPU workers.",
"type": "boolean",
"x-versionadded": "v2.33"
},
"isTransparent": {
"description": "If the model is a transparent model with exposed coefficients.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"isUserModel": {
"description": "If the model was created with Composable ML.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"lifecycle": {
"description": "Object returning model lifecycle.",
"properties": {
"reason": {
"description": "Reason for lifecycle stage. None if model is active.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.30"
},
"stage": {
"description": "Model lifecycle stage.",
"enum": [
"active",
"deprecated",
"disabled"
],
"type": "string",
"x-versionadded": "v2.30"
}
},
"required": [
"reason",
"stage"
],
"type": "object"
},
"linkFunction": {
"description": "The link function the final modeler uses in the blueprint. If no link function exists, returns null.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"metrics": {
"description": "The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed.",
"type": "object"
},
"modelCategory": {
"description": "Indicates the type of model. Returns `prime` for DataRobot Prime models, `blend` for blender models, `combined` for combined models, and `model` for all other models.",
"enum": [
"model",
"prime",
"blend",
"combined",
"incrementalLearning"
],
"type": "string"
},
"modelFamily": {
"description": "the family model belongs to, e.g. SVM, GBM, etc.",
"type": "string",
"x-versionadded": "v2.21"
},
"modelFamilyFullName": {
"description": "The full name of the family that the model belongs to. For e.g., Support Vector Machine, Gradient Boosting Machine, etc.",
"type": "string",
"x-versionadded": "v2.31"
},
"modelNumber": {
"description": "The model number from the Leaderboard.",
"exclusiveMinimum": 0,
"type": [
"integer",
"null"
]
},
"modelType": {
"description": "Identifies the model (e.g.,`Nystroem Kernel SVM Regressor`).",
"type": "string"
},
"monotonicDecreasingFeaturelistId": {
"description": "the ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"monotonicIncreasingFeaturelistId": {
"description": "the ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"nClusters": {
"description": "The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.",
"type": [
"integer",
"null"
]
},
"parentModelId": {
"description": "The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise.",
"type": [
"string",
"null"
]
},
"predictionThreshold": {
"description": "threshold used for binary classification in predictions.",
"maximum": 1,
"minimum": 0,
"type": "number",
"x-versionadded": "v2.13"
},
"predictionThresholdReadOnly": {
"description": "indicates whether modification of a predictions threshold is forbidden. Since v2.22 threshold modification is allowed.",
"type": "boolean",
"x-versionadded": "v2.13"
},
"processes": {
"description": "The list of processes used by the model.",
"items": {
"type": "string"
},
"maxItems": 100,
"type": "array"
},
"projectId": {
"description": "The ID of the project to which the model belongs.",
"type": "string"
},
"ratingTableId": {
"description": "The rating table ID",
"type": "string"
},
"samplePct": {
"description": "The percentage of the dataset used in training the model.",
"exclusiveMinimum": 0,
"type": [
"number",
"null"
]
},
"samplingMethod": {
"description": "indicates sampling method used to select training data in datetime models. For row-based project this is the way how requested number of rows are selected.For other projects (duration-based, start/end, project settings) - how specified percent of rows (timeWindowSamplePct) is selected from specified time window.",
"enum": [
"random",
"latest"
],
"type": "string"
},
"supportsComposableMl": {
"description": "indicates whether this model is supported in Composable ML.",
"type": "boolean",
"x-versionadded": "2.26"
},
"supportsMonotonicConstraints": {
"description": "whether this model supports enforcing monotonic constraints",
"type": "boolean",
"x-versionadded": "v2.21"
},
"timeWindowSamplePct": {
"description": "An integer between 1 and 99, indicating the percentage of sampling within the time window. The points kept are determined by samplingMethod option. Will be null if no sampling was specified. Only used by datetime models.",
"exclusiveMaximum": 100,
"exclusiveMinimum": 0,
"type": [
"integer",
"null"
]
},
"trainingDuration": {
"description": "the duration spanned by the dates in the partition column for the data used to train the model",
"type": [
"string",
"null"
]
},
"trainingEndDate": {
"description": "the end date of the dates in the partition column for the data used to train the model",
"format": "date-time",
"type": [
"string",
"null"
]
},
"trainingRowCount": {
"description": "The number of rows used to train the model.",
"exclusiveMinimum": 0,
"type": [
"integer",
"null"
]
},
"trainingStartDate": {
"description": "the start date of the dates in the partition column for the data used to train the model",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"blenderModels",
"blueprintId",
"externalPredictionModel",
"featurelistId",
"featurelistName",
"frozenPct",
"hasCodegen",
"icons",
"id",
"isBlender",
"isCustom",
"isFrozen",
"isStarred",
"isTrainedIntoHoldout",
"isTrainedIntoValidation",
"isTrainedOnGpu",
"isTransparent",
"isUserModel",
"lifecycle",
"linkFunction",
"metrics",
"modelCategory",
"modelFamily",
"modelFamilyFullName",
"modelNumber",
"modelType",
"monotonicDecreasingFeaturelistId",
"monotonicIncreasingFeaturelistId",
"parentModelId",
"predictionThreshold",
"predictionThresholdReadOnly",
"processes",
"projectId",
"ratingTableId",
"samplePct",
"supportsComposableMl",
"supportsMonotonicConstraints",
"trainingDuration",
"trainingEndDate",
"trainingRowCount",
"trainingStartDate"
],
"type": "object"
}
Responses
List Rating Tables by project ID
Operation path: GET /api/v2/projects/{projectId}/ratingTables/
Authentication requirements: BearerAuth
List RatingTable objects for a project.
These contain metadata about the rating table and the location at which the corresponding rating
table file can be retrieved.
Parameters
| Name |
In |
Type |
Required |
Description |
| parentModelId |
query |
string |
false |
optional. If specified, only rating tables with this parentModelId will be returned |
| modelId |
query |
string |
false |
optional. If specified, only rating tables with this modelId will be returned |
| offset |
query |
integer |
false |
optional (default: 0), this many results will be skipped |
| limit |
query |
integer |
false |
optional (default: no limit), at most this many results are returned. To specify no limit, use 0. The default may change and a maximum limit may be imposed without notice. |
| projectId |
path |
string |
true |
The project ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "the number of RatingTable objects returned",
"type": "integer"
},
"data": {
"description": "the actual records. Each element of the array has the same schema\n as if retrieving the table individually from\n GET /api/v2/projects/(projectId)/ratingTables/(ratingTableId)/",
"items": {
"properties": {
"created": {
"description": "ISO-8601 timestamp of when the rating table record was created.",
"type": "number"
},
"id": {
"description": "the ID of the rating table record",
"type": "string"
},
"modelId": {
"description": "the model ID of a model that was created from the rating table.\n May be null if a model has not been created from the rating table.",
"type": "string"
},
"modelJobId": {
"description": "the qid of the job to create a model from this rating table.\n Can be null if a model has not been created from the rating table.",
"type": "integer"
},
"originalFilename": {
"description": "the filename of the uploaded rating table file",
"type": "string"
},
"parentModelId": {
"description": "the model ID of the model the rating table was modified from",
"type": "string"
},
"projectId": {
"description": "the project ID of the rating table record",
"type": "string"
},
"ratingTableName": {
"description": "the name of the rating table",
"type": "string"
},
"validationError": {
"description": "rating table validation error messages. If the rating table\n was validated successfully, it will be an empty string.",
"type": "string"
},
"validationJobId": {
"description": "the qid of the created job to validate the rating table.\n Can be null if the rating table has not been validated.",
"type": "string"
},
"validationWarnings": {
"description": "rating table validation warning messages.",
"type": "string"
}
},
"required": [
"created",
"id",
"modelId",
"modelJobId",
"originalFilename",
"parentModelId",
"projectId",
"ratingTableName",
"validationError",
"validationJobId",
"validationWarnings"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page)",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page)",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"count",
"data",
"next",
"previous"
],
"type": "object"
}
Responses
Upload Modified Rating Table File by project ID
Operation path: POST /api/v2/projects/{projectId}/ratingTables/
Authentication requirements: BearerAuth
Create a new rating table from a rating table file
This will create a new rating table, regardless of whether the validation succeeds.
The rating table object will have a validationError which will be left blank in the case of successful validation.
Body parameter
properties:
parentModelId:
description: the parent model this rating table file was derived from
type: string
ratingTableFile:
description: rating table file to use for the new rating table. Accepts
`Content-Type:multipart/form-data`
format: binary
type: string
ratingTableName:
description: the name of the new rating table to create
type: string
required:
- parentModelId
- ratingTableFile
- ratingTableName
type: object
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
the project that owns this data |
| body |
body |
UploadRatingTable |
false |
none |
Example responses
202 Response
{
"properties": {
"ratingTableId": {
"description": "the ID of the newly created rating table",
"type": "string"
},
"ratingTableName": {
"description": "The name that was used for the rating table. May differ from the ratingTableName in the request, as names are trimmed and a suffix added to ensure all rating tables derived from the same model have unique names",
"type": "string"
}
},
"required": [
"ratingTableId",
"ratingTableName"
],
"type": "object"
}
Responses
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
url |
a url of an asynchronous operation status object that can be polled to check the status of the job validating the new rating table |
Operation path: GET /api/v2/projects/{projectId}/ratingTables/{ratingTableId}/
Authentication requirements: BearerAuth
Retrieves a rating table.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
the project that owns this data |
| ratingTableId |
path |
string |
true |
the rating table ID to retrieve the source file from |
Example responses
200 Response
{
"properties": {
"created": {
"description": "ISO-8601 timestamp of when the rating table record was created.",
"type": "number"
},
"id": {
"description": "the ID of the rating table record",
"type": "string"
},
"modelId": {
"description": "the model ID of a model that was created from the rating table.\n May be null if a model has not been created from the rating table.",
"type": "string"
},
"modelJobId": {
"description": "the qid of the job to create a model from this rating table.\n Can be null if a model has not been created from the rating table.",
"type": "integer"
},
"originalFilename": {
"description": "the filename of the uploaded rating table file",
"type": "string"
},
"parentModelId": {
"description": "the model ID of the model the rating table was modified from",
"type": "string"
},
"projectId": {
"description": "the project ID of the rating table record",
"type": "string"
},
"ratingTableName": {
"description": "the name of the rating table",
"type": "string"
},
"validationError": {
"description": "rating table validation error messages. If the rating table\n was validated successfully, it will be an empty string.",
"type": "string"
},
"validationJobId": {
"description": "the qid of the created job to validate the rating table.\n Can be null if the rating table has not been validated.",
"type": "string"
},
"validationWarnings": {
"description": "rating table validation warning messages.",
"type": "string"
}
},
"required": [
"created",
"id",
"modelId",
"modelJobId",
"originalFilename",
"parentModelId",
"projectId",
"ratingTableName",
"validationError",
"validationJobId",
"validationWarnings"
],
"type": "object"
}
Responses
Update an uploaded rating table by project ID
Operation path: PATCH /api/v2/projects/{projectId}/ratingTables/{ratingTableId}/
Authentication requirements: BearerAuth
Rating tables may only be updated if they have not yet been used to create a model.
Body parameter
{
"properties": {
"ratingTableName": {
"description": "the name of the new model",
"type": "string"
}
},
"required": [
"ratingTableName"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
the project that owns this data |
| ratingTableId |
path |
string |
true |
the rating table ID to retrieve the source file from |
| body |
body |
RatingTableUpdate |
false |
none |
Example responses
200 Response
{
"properties": {
"created": {
"description": "ISO-8601 timestamp of when the rating table record was created.",
"type": "number"
},
"id": {
"description": "the ID of the rating table record",
"type": "string"
},
"modelId": {
"description": "the model ID of a model that was created from the rating table.\n May be null if a model has not been created from the rating table.",
"type": "string"
},
"modelJobId": {
"description": "the qid of the job to create a model from this rating table.\n Can be null if a model has not been created from the rating table.",
"type": "integer"
},
"originalFilename": {
"description": "the filename of the uploaded rating table file",
"type": "string"
},
"parentModelId": {
"description": "the model ID of the model the rating table was modified from",
"type": "string"
},
"projectId": {
"description": "the project ID of the rating table record",
"type": "string"
},
"ratingTableName": {
"description": "the name of the rating table",
"type": "string"
},
"validationError": {
"description": "rating table validation error messages. If the rating table\n was validated successfully, it will be an empty string.",
"type": "string"
},
"validationJobId": {
"description": "the qid of the created job to validate the rating table.\n Can be null if the rating table has not been validated.",
"type": "string"
},
"validationWarnings": {
"description": "rating table validation warning messages.",
"type": "string"
}
},
"required": [
"created",
"id",
"modelId",
"modelJobId",
"originalFilename",
"parentModelId",
"projectId",
"ratingTableName",
"validationError",
"validationJobId",
"validationWarnings"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
On success, will return the modified rating table record in the same |
|
| format as GET /api/v2/projects/(projectId)/ratingTables/(ratingTableId)/ |
RatingTableRetrieveResponse |
|
|
Retrieve Rating Table File by project ID
Operation path: GET /api/v2/projects/{projectId}/ratingTables/{ratingTableId}/file/
Authentication requirements: BearerAuth
Retrieve the CSV file for the rating table.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
the project that owns this data |
| ratingTableId |
path |
string |
true |
the rating table ID to retrieve the source file from |
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
The response will contain a file containing the rating table in csv format |
None |
List SHAP matrix records by project ID
Operation path: GET /api/v2/projects/{projectId}/shapMatrices/
Authentication requirements: BearerAuth
Return a list of available SHAP matrix records.
DEPRECATED: Use the componentized route instead: [GET /api/v2/insights/shapMatrix/models/{entityId}/][get-apiv2insightsshapmatrixmodelsentityid].
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
Number of results to skip. |
| limit |
query |
integer |
false |
At most this many results are returned. The default may change without notice. |
| projectId |
path |
string |
true |
The project ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "Array of SHAP matrix scores records.",
"items": {
"properties": {
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"id": {
"description": "The ID of the SHAP matrix record.",
"type": "string"
},
"metadata": {
"description": "The metadata containing SHAP matrix calculation details.",
"properties": {
"maxNormalizedMismatch": {
"default": 0,
"description": "The maximal relative normalized mismatch value.",
"type": "number"
},
"mismatchRowCount": {
"default": 0,
"description": "The count of rows for which additivity check failed.",
"type": "integer"
}
},
"type": "object"
},
"modelId": {
"description": "The model ID.",
"type": "string"
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"url": {
"description": "The url at which you can retrieve the SHAP matrix.",
"format": "uri",
"type": "string"
}
},
"required": [
"datasetId",
"id",
"metadata",
"modelId",
"projectId",
"url"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"data",
"next",
"previous"
],
"type": "object"
}
Responses
Calculate a matrix with SHAP-based prediction explanations scores by project ID
Operation path: POST /api/v2/projects/{projectId}/shapMatrices/
Authentication requirements: BearerAuth
Submit a request to calculate a matrix with SHAP based prediction explanations scores.
DEPRECATED: Use the componentized route instead: [POST /api/v2/insights/shapMatrix/][post-apiv2insightsshapmatrix].
Body parameter
{
"properties": {
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"modelId": {
"description": "The model ID.",
"type": "string"
}
},
"required": [
"datasetId",
"modelId"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| body |
body |
CreateShapMatrixPayload |
false |
none |
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
Job submitted. See Location header. |
None |
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Return matrix with SHAP-based prediction explanations scores by project ID
Operation path: GET /api/v2/projects/{projectId}/shapMatrices/{shapMatrixId}/
Authentication requirements: BearerAuth
Return matrix with SHAP-based prediction explanations scores.
DEPRECATED: Use the componentized route instead: [GET /api/v2/insights/shapMatrix/models/{entityId}/][get-apiv2insightsshapmatrixmodelsentityid].
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID. |
| shapMatrixId |
path |
string |
true |
The SHAP matrix ID. |
Example responses
200 Response
{
"properties": {
"columnNames": {
"description": "The column names for corresponding dataset & their SHAP values.",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"columnNames"
],
"type": "object"
}
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
none |
string |
Delete an existing PredictionExplanationsInitialization by project ID
Operation path: DELETE /api/v2/projects/{projectId}/models/{modelId}/predictionExplanationsInitialization/
Authentication requirements: BearerAuth
Delete an existing PredictionExplanationsInitialization.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
Responses
| Status |
Meaning |
Description |
Schema |
| 204 |
No Content |
The deletion was successful. |
None |
Retrieve the current PredictionExplanationsInitialization by project ID
Operation path: GET /api/v2/projects/{projectId}/models/{modelId}/predictionExplanationsInitialization/
Authentication requirements: BearerAuth
Retrieve the current PredictionExplanationsInitialization.
A PredictionExplanationsInitialization is a pre-requisite for successfully computing prediction explanations using a particular model, and can be used to preview the prediction explanations that would be generated for a complete dataset.
Body parameter
{
"properties": {
"modelId": {
"description": "The model ID.",
"type": "string"
},
"predictionExplanationsSample": {
"description": "Each is a PredictionExplanationsRow. They represent a small sample of prediction explanations that could be generated for a particular dataset. They will have the same schema as the `data` array in the response from [GET /api/v2/projects/{projectId}/predictionExplanations/{predictionExplanationsId}/][get-apiv2projectsprojectidpredictionexplanationspredictionexplanationsid]. As of v2.21 only difference is that there is no forecastPoint in response for time series projects.",
"items": {
"properties": {
"adjustedPrediction": {
"description": "The exposure-adjusted output of the model for this row.",
"type": "number",
"x-versionadded": "v2.8"
},
"adjustedPredictionValues": {
"description": "The exposure-adjusted output of the model for this row.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.8"
},
"forecastDistance": {
"description": "Forecast distance for the row. For time series projects only.",
"type": "integer",
"x-versionadded": "v2.21"
},
"forecastPoint": {
"description": "Forecast point for the row. For time series projects only.",
"type": "string",
"x-versionadded": "v2.21"
},
"prediction": {
"description": "The output of the model for this row.",
"type": "number"
},
"predictionExplanations": {
"description": "A list of prediction explanations.",
"items": {
"properties": {
"feature": {
"description": "The name of the feature contributing to the prediction.",
"type": "string"
},
"featureValue": {
"description": "The value the feature took on for this row. For image features, this value is the URL of the input image (New in v2.21).",
"type": "string"
},
"imageExplanationUrl": {
"description": "For image features, the URL of the image containing the input image overlaid by the activation heatmap. For non-image features, this field is null.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"perNgramTextExplanations": {
"description": "For text features, an array of JSON object containing the per ngram based text prediction explanations.",
"items": {
"properties": {
"isUnknown": {
"description": "Whether the ngram is identifiable by the blueprint or not.",
"type": "boolean",
"x-versionadded": "v2.28"
},
"ngrams": {
"description": "List of JSON objects with the ngram starting index, ngram ending index and unknown ngram information.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"maxItems": 1000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly these ngrams's affected the prediction(e.g. '+++', '--', '+', '<+', '<-').",
"type": "string",
"x-versionadded": "v2.28"
},
"strength": {
"description": "The amount these ngrams's affected the prediction.",
"type": "number",
"x-versionadded": "v2.28"
}
},
"required": [
"isUnknown",
"ngrams",
"qualitativateStrength",
"strength"
],
"type": "object"
},
"maxItems": 10000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly the feature affected the prediction. A large positive effect is denoted '+++', medium '++', small '+', very small '<+'. A large negative effect is denoted '---', medium '--', small '-', very small '<-'.",
"type": "string"
},
"strength": {
"description": "The amount this feature's value affected the prediction.",
"type": "number"
}
},
"required": [
"feature",
"featureValue",
"imageExplanationUrl",
"label",
"qualitativateStrength",
"strength"
],
"type": "object"
},
"type": "array"
},
"predictionThreshold": {
"description": "The threshold value used for classification prediction.",
"type": [
"number",
"null"
]
},
"predictionValues": {
"description": "A list of prediction values.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
},
"rowId": {
"description": "Which row this PredictionExplanationsRow describes.",
"type": "integer"
},
"seriesId": {
"description": "The ID of the series value for the row in a multiseries project. For a single series project this will be null. For time series projects only.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"timestamp": {
"description": "Timestamp for the row. For time series projects only.",
"type": "string",
"x-versionadded": "v2.21"
}
},
"required": [
"adjustedPrediction",
"adjustedPredictionValues",
"forecastDistance",
"forecastPoint",
"prediction",
"predictionExplanations",
"predictionThreshold",
"predictionValues",
"rowId",
"seriesId",
"timestamp"
],
"type": "object"
},
"type": "array"
},
"projectId": {
"description": "The project ID.",
"type": "string"
}
},
"required": [
"modelId",
"predictionExplanationsSample",
"projectId"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| excludeAdjustedPredictions |
query |
string |
false |
Whether to include adjusted prediction in the PredictionExplanationsSample response. |
| projectId |
path |
string |
true |
The project ID |
| modelId |
path |
string |
true |
The model ID |
| body |
body |
PredictionExplanationsInitializationRetrieve |
false |
none |
Enumerated Values
| Parameter |
Value |
| excludeAdjustedPredictions |
[false, False, true, True] |
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
none |
None |
Create a new prediction explanations initialization by project ID
Operation path: POST /api/v2/projects/{projectId}/models/{modelId}/predictionExplanationsInitialization/
Authentication requirements: BearerAuth
Create a new prediction explanations initialization. This is a necessary prerequisite for generating prediction explanations.
Body parameter
{
"properties": {
"maxExplanations": {
"default": 3,
"description": "The maximum number of prediction explanations to supply per row of the dataset.",
"maximum": 10,
"minimum": 1,
"type": "integer"
},
"thresholdHigh": {
"default": null,
"description": "The high threshold, above which a prediction must score in order for prediction explanations to be computed. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows.",
"type": [
"number",
"null"
]
},
"thresholdLow": {
"default": null,
"description": "The lower threshold, below which a prediction must score in order for prediction explanations to be computed for a row in the dataset. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows.",
"type": [
"number",
"null"
]
}
},
"type": "object"
}
Parameters
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
The request was accepted and will be worked on. |
None |
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Create a new PredictionExplanations object ( by project ID
Operation path: POST /api/v2/projects/{projectId}/predictionExplanations/
Authentication requirements: BearerAuth
Create a new PredictionExplanations object (and its accompanying PredictionExplanationsRecord).
In order to successfully create PredictionExplanations for a particular model and dataset, you must first
- Compute feature impact for the model via [POST /api/v2/projects/{projectId}/models/{modelId}/featureImpact/][post-apiv2projectsprojectidmodelsmodelidfeatureimpact]
- Compute a PredictionExplanationsInitialization for the model via [POST /api/v2/projects/{projectId}/models/{modelId}/predictionExplanationsInitialization/][post-apiv2projectsprojectidmodelsmodelidpredictionexplanationsinitialization]
- Compute predictions for the model and dataset via [POST /api/v2/projects/{projectId}/predictions/][post-apiv2projectsprojectidpredictions]
thresholdHigh and thresholdLow are optional filters applied to speed up computation. When at least one is specified, only the selected outlier rows will have prediction explanations computed. Rows are considered to be outliers if their predicted value (in case of regression projects) or probability of being the positive class (in case of classification projects) isless than thresholdLow or greater than thresholdHigh. If neither is specified, prediction explanations will be computed for all rows.
Body parameter
{
"properties": {
"classNames": {
"description": "Sets a list of selected class names for which corresponding explanations are returned in each row. This setting is mutually exclusive with numTopClasses. If neither parameter is specified, the default setting is numTopClasses=1.",
"items": {
"type": "string"
},
"maxItems": 100,
"type": "array",
"x-versionadded": "v2.29"
},
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"maxExplanations": {
"default": 3,
"description": "The maximum number of prediction explanations to supply per row of the dataset.",
"maximum": 10,
"minimum": 0,
"type": "integer"
},
"modelId": {
"description": "The model ID.",
"type": "string"
},
"numTopClasses": {
"description": "Sets the number of most probable (top predicted) classes for which corresponding explanations are returned in each row. This setting is mutually exclusive with classNames. If neither parameter is specified, the default setting is numTopClasses=1.",
"maximum": 100,
"minimum": 1,
"type": "integer",
"x-versionadded": "v2.29"
},
"thresholdHigh": {
"default": null,
"description": "The high threshold, above which a prediction must score in order for prediction explanations to be computed. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows.",
"type": [
"number",
"null"
]
},
"thresholdLow": {
"default": null,
"description": "The lower threshold, below which a prediction must score in order for prediction explanations to be computed for a row in the dataset. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows.",
"type": [
"number",
"null"
]
}
},
"required": [
"datasetId",
"modelId"
],
"type": "object"
}
Parameters
Responses
| Status |
Meaning |
Description |
Schema |
| 202 |
Accepted |
The request was accepted and will be worked on. |
None |
| Status |
Header |
Type |
Format |
Description |
| 202 |
Location |
string |
|
A url that can be polled to check the status. |
Retrieve stored Prediction Explanations by project ID
Operation path: GET /api/v2/projects/{projectId}/predictionExplanations/{predictionExplanationsId}/
Authentication requirements: BearerAuth
Retrieve stored Prediction Explanations.
Each PredictionExplanationsRow retrieved corresponds to a row of the prediction dataset, although some rows may not have had prediction explanations computed depending on the thresholds selected.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
This many results will be skipped. |
| limit |
query |
integer |
true |
At most this many results are returned. The default may change and a new maximum limit may be imposed without notice. |
| excludeAdjustedPredictions |
query |
string |
false |
Whether to include adjusted prediction in PredictionExplanationsRow response. |
| projectId |
path |
string |
true |
The project ID |
| predictionExplanationsId |
path |
string |
true |
The ID of the PredictionExplanationsRecord to retrieve. |
Enumerated Values
| Parameter |
Value |
| excludeAdjustedPredictions |
[false, False, true, True] |
Example responses
200 Response
{
"properties": {
"adjustmentMethod": {
"description": "'exposureNormalized' (for regression projects with exposure) or 'N/A' (for classification projects) The value of 'exposureNormalized' indicates that prediction outputs are adjusted (or divided) by exposure. The value of 'N/A' indicates that no adjustments are applied to the adjusted predictions and they are identical to the unadjusted predictions.",
"type": "string",
"x-versionadded": "v2.8"
},
"count": {
"description": "How many rows of prediction explanations were returned.",
"type": "integer"
},
"data": {
"description": "Each is a PredictionExplanationsRow corresponding to one row of the prediction dataset.",
"items": {
"properties": {
"adjustedPrediction": {
"description": "The exposure-adjusted output of the model for this row.",
"type": "number",
"x-versionadded": "v2.8"
},
"adjustedPredictionValues": {
"description": "The exposure-adjusted output of the model for this row.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.8"
},
"forecastDistance": {
"description": "Forecast distance for the row. For time series projects only.",
"type": "integer",
"x-versionadded": "v2.21"
},
"forecastPoint": {
"description": "Forecast point for the row. For time series projects only.",
"type": "string",
"x-versionadded": "v2.21"
},
"prediction": {
"description": "The output of the model for this row.",
"type": "number"
},
"predictionExplanations": {
"description": "A list of prediction explanations.",
"items": {
"properties": {
"feature": {
"description": "The name of the feature contributing to the prediction.",
"type": "string"
},
"featureValue": {
"description": "The value the feature took on for this row. For image features, this value is the URL of the input image (New in v2.21).",
"type": "string"
},
"imageExplanationUrl": {
"description": "For image features, the URL of the image containing the input image overlaid by the activation heatmap. For non-image features, this field is null.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"perNgramTextExplanations": {
"description": "For text features, an array of JSON object containing the per ngram based text prediction explanations.",
"items": {
"properties": {
"isUnknown": {
"description": "Whether the ngram is identifiable by the blueprint or not.",
"type": "boolean",
"x-versionadded": "v2.28"
},
"ngrams": {
"description": "List of JSON objects with the ngram starting index, ngram ending index and unknown ngram information.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"maxItems": 1000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly these ngrams's affected the prediction(e.g. '+++', '--', '+', '<+', '<-').",
"type": "string",
"x-versionadded": "v2.28"
},
"strength": {
"description": "The amount these ngrams's affected the prediction.",
"type": "number",
"x-versionadded": "v2.28"
}
},
"required": [
"isUnknown",
"ngrams",
"qualitativateStrength",
"strength"
],
"type": "object"
},
"maxItems": 10000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly the feature affected the prediction. A large positive effect is denoted '+++', medium '++', small '+', very small '<+'. A large negative effect is denoted '---', medium '--', small '-', very small '<-'.",
"type": "string"
},
"strength": {
"description": "The amount this feature's value affected the prediction.",
"type": "number"
}
},
"required": [
"feature",
"featureValue",
"imageExplanationUrl",
"label",
"qualitativateStrength",
"strength"
],
"type": "object"
},
"type": "array"
},
"predictionThreshold": {
"description": "The threshold value used for classification prediction.",
"type": [
"number",
"null"
]
},
"predictionValues": {
"description": "A list of prediction values.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
},
"rowId": {
"description": "Which row this PredictionExplanationsRow describes.",
"type": "integer"
},
"seriesId": {
"description": "The ID of the series value for the row in a multiseries project. For a single series project this will be null. For time series projects only.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"timestamp": {
"description": "Timestamp for the row. For time series projects only.",
"type": "string",
"x-versionadded": "v2.21"
}
},
"required": [
"adjustedPrediction",
"adjustedPredictionValues",
"forecastDistance",
"forecastPoint",
"prediction",
"predictionExplanations",
"predictionThreshold",
"predictionValues",
"rowId",
"seriesId",
"timestamp"
],
"type": "object"
},
"type": "array"
},
"id": {
"description": "The ID of this group of prediction explanations.",
"type": "string"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"predictionExplanationsRecordLocation": {
"description": "The URL of the PredictionExplanationsRecord associated with these prediction explanations.",
"type": "string"
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"adjustmentMethod",
"count",
"data",
"id",
"next",
"predictionExplanationsRecordLocation",
"previous"
],
"type": "object"
}
Responses
List PredictionExplanationsRecord objects by project ID
Operation path: GET /api/v2/projects/{projectId}/predictionExplanationsRecords/
Authentication requirements: BearerAuth
List PredictionExplanationsRecord objects for a project.
These contain metadata about the computed prediction explanations and the location at which the PredictionExplanations can be retrieved.
Parameters
| Name |
In |
Type |
Required |
Description |
| offset |
query |
integer |
false |
This many results will be skipped. |
| limit |
query |
integer |
false |
At most this many results are returned. |
| modelId |
query |
string |
false |
If specified, only prediction explanations records computed for this model will be returned. |
| projectId |
path |
string |
true |
The project ID |
Example responses
200 Response
{
"properties": {
"count": {
"description": "The number of items returned on this page.",
"minimum": 0,
"type": "integer"
},
"data": {
"description": "Each has the same schema as if retrieving the prediction explanations individually from [GET /api/v2/projects/{projectId}/predictionExplanationsRecords/{predictionExplanationsId}/][get-apiv2projectsprojectidpredictionexplanationsrecordspredictionexplanationsid].",
"items": {
"properties": {
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"finishTime": {
"description": "Timestamp referencing when computation for these prediction explanations finished.",
"type": "number"
},
"id": {
"description": "The PredictionExplanationsRecord ID.",
"type": "string"
},
"maxExplanations": {
"description": "The maximum number of codes generated per prediction.",
"type": "integer"
},
"modelId": {
"description": "The model ID.",
"type": "string"
},
"numColumns": {
"description": "The number of columns prediction explanations were computed for.",
"type": "integer"
},
"predictionExplanationsLocation": {
"description": "Where to retrieve the prediction explanations.",
"type": "string"
},
"predictionThreshold": {
"description": "The threshold value used for binary classification prediction.",
"type": [
"number",
"null"
]
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"thresholdHigh": {
"description": "The prediction explanation high threshold. Predictions must be above this value (or below the thresholdLow value) to have PredictionExplanations computed.",
"type": [
"number",
"null"
]
},
"thresholdLow": {
"description": "The prediction explanation low threshold. Predictions must be below this value (or above the thresholdHigh value) to have PredictionExplanations computed.",
"type": [
"number",
"null"
]
}
},
"required": [
"datasetId",
"finishTime",
"id",
"maxExplanations",
"modelId",
"numColumns",
"predictionExplanationsLocation",
"predictionThreshold",
"projectId",
"thresholdHigh",
"thresholdLow"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "A URL pointing to the next page (if `null`, there is no next page).",
"type": [
"string",
"null"
]
},
"previous": {
"description": "A URL pointing to the previous page (if `null`, there is no previous page).",
"type": [
"string",
"null"
]
}
},
"required": [
"count",
"data",
"next",
"previous"
],
"type": "object"
}
Responses
Delete saved Prediction Explanations by project ID
Operation path: DELETE /api/v2/projects/{projectId}/predictionExplanationsRecords/{predictionExplanationsId}/
Authentication requirements: BearerAuth
Delete saved Prediction Explanations.
Deletes both the actual prediction explanations and the corresponding PredictionExplanationsRecord.
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| predictionExplanationsId |
path |
string |
true |
The ID of the PredictionExplanationsRecord to retrieve. |
Responses
| Status |
Meaning |
Description |
Schema |
| 204 |
No Content |
The object was deleted successfully. |
None |
Retrieve a PredictionExplanationsRecord object by project ID
Operation path: GET /api/v2/projects/{projectId}/predictionExplanationsRecords/{predictionExplanationsId}/
Authentication requirements: BearerAuth
Retrieve a PredictionExplanationsRecord object.
A PredictionExplanationsRecord contains metadata about the computed prediction explanations and the location at which the PredictionExplanations can be retrieved.
Body parameter
{
"properties": {
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"finishTime": {
"description": "Timestamp referencing when computation for these prediction explanations finished.",
"type": "number"
},
"id": {
"description": "The PredictionExplanationsRecord ID.",
"type": "string"
},
"maxExplanations": {
"description": "The maximum number of codes generated per prediction.",
"type": "integer"
},
"modelId": {
"description": "The model ID.",
"type": "string"
},
"numColumns": {
"description": "The number of columns prediction explanations were computed for.",
"type": "integer"
},
"predictionExplanationsLocation": {
"description": "Where to retrieve the prediction explanations.",
"type": "string"
},
"predictionThreshold": {
"description": "The threshold value used for binary classification prediction.",
"type": [
"number",
"null"
]
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"thresholdHigh": {
"description": "The prediction explanation high threshold. Predictions must be above this value (or below the thresholdLow value) to have PredictionExplanations computed.",
"type": [
"number",
"null"
]
},
"thresholdLow": {
"description": "The prediction explanation low threshold. Predictions must be below this value (or above the thresholdHigh value) to have PredictionExplanations computed.",
"type": [
"number",
"null"
]
}
},
"required": [
"datasetId",
"finishTime",
"id",
"maxExplanations",
"modelId",
"numColumns",
"predictionExplanationsLocation",
"predictionThreshold",
"projectId",
"thresholdHigh",
"thresholdLow"
],
"type": "object"
}
Parameters
| Name |
In |
Type |
Required |
Description |
| projectId |
path |
string |
true |
The project ID |
| predictionExplanationsId |
path |
string |
true |
The ID of the PredictionExplanationsRecord to retrieve. |
| body |
body |
PredictionExplanationsRecord |
false |
none |
Responses
| Status |
Meaning |
Description |
Schema |
| 200 |
OK |
The object was found and returned successfully. |
None |
Schemas
AOTChartBins
{
"properties": {
"actual": {
"description": "The average actual value of the target in the bin. ``null`` if there are no entries in the bin or if this is an anomaly detection project.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive).",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "As indicated by the frequencyType in the Metadata, used to determine what the averages mentioned above are taken over. ``null`` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"predicted": {
"description": "The average prediction of the model in the bin. ``null`` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive).",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"frequency",
"predicted",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actual |
number,null |
true |
|
The average actual value of the target in the bin. null if there are no entries in the bin or if this is an anomaly detection project. |
| endDate |
string(date-time) |
true |
|
The datetime of the end of the bin (exclusive). |
| frequency |
number,null |
true |
|
As indicated by the frequencyType in the Metadata, used to determine what the averages mentioned above are taken over. null if there are no entries in the bin. |
| predicted |
number,null |
true |
|
The average prediction of the model in the bin. null if there are no entries in the bin. |
| startDate |
string(date-time) |
true |
|
The datetime of the start of the bin (inclusive). |
{
"description": "The dataset metadata.",
"properties": {
"endDate": {
"description": "ISO-8601 formatted end date (max date) in the dataset.",
"format": "date-time",
"type": "string"
},
"startDate": {
"description": "ISO-8601 formatted start date (min date) in the dataset.",
"format": "date-time",
"type": "string"
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
The dataset metadata.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| endDate |
string(date-time) |
true |
|
ISO-8601 formatted end date (max date) in the dataset. |
| startDate |
string(date-time) |
true |
|
ISO-8601 formatted start date (min date) in the dataset. |
{
"properties": {
"datasetId": {
"description": "The dataset id which was used to compute the AOT chart.",
"type": "string"
},
"datasetMetadata": {
"description": "The dataset metadata.",
"properties": {
"endDate": {
"description": "ISO-8601 formatted end date (max date) in the dataset.",
"format": "date-time",
"type": "string"
},
"startDate": {
"description": "ISO-8601 formatted start date (min date) in the dataset.",
"format": "date-time",
"type": "string"
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"frequencyType": {
"description": "How to interpret the frequency attribute of each datetimeTrendBin. One of ['rowCount', 'weightedRowCount', 'exposure', 'weightedExposure'].",
"enum": [
"rowCount",
"weightedRowCount",
"exposure",
"weightedExposure"
],
"type": "string"
},
"metricName": {
"description": "The metric used to score each bin and the calculate the metric attribute of each datetimeTrendBin.",
"type": "string"
},
"modelId": {
"description": "The model id which was used to compute the AOT chart.",
"type": "string"
},
"projectId": {
"description": "The project id which was used to compute the AOT chart.",
"type": "string"
},
"resolutions": {
"description": "Suggested time resolutions where a resolution is one of ['milliseconds', 'seconds', 'minutes', 'hours', 'days', 'weeks', 'months', 'years'].",
"items": {
"enum": [
"microseconds",
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"type": "array"
}
},
"required": [
"datasetId",
"datasetMetadata",
"frequencyType",
"metricName",
"modelId",
"projectId",
"resolutions"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| datasetId |
string |
true |
|
The dataset id which was used to compute the AOT chart. |
| datasetMetadata |
AOTChartMetadataDatasetMetadata |
true |
|
The dataset metadata. |
| frequencyType |
string |
true |
|
How to interpret the frequency attribute of each datetimeTrendBin. One of ['rowCount', 'weightedRowCount', 'exposure', 'weightedExposure']. |
| metricName |
string |
true |
|
The metric used to score each bin and the calculate the metric attribute of each datetimeTrendBin. |
| modelId |
string |
true |
|
The model id which was used to compute the AOT chart. |
| projectId |
string |
true |
|
The project id which was used to compute the AOT chart. |
| resolutions |
[string] |
true |
|
Suggested time resolutions where a resolution is one of ['milliseconds', 'seconds', 'minutes', 'hours', 'days', 'weeks', 'months', 'years']. |
Enumerated Values
| Property |
Value |
| frequencyType |
[rowCount, weightedRowCount, exposure, weightedExposure] |
AOTChartPreviewResponse
{
"properties": {
"bins": {
"description": "The datetime chart data for that source.",
"items": {
"properties": {
"actual": {
"description": "The average actual value of the target in the bin. ``null`` if there are no entries in the bin or if this is an anomaly detection project.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive).",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "As indicated by the frequencyType in the Metadata, used to determine what the averages mentioned above are taken over. ``null`` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"predicted": {
"description": "The average prediction of the model in the bin. ``null`` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive).",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"frequency",
"predicted",
"startDate"
],
"type": "object"
},
"type": "array"
},
"datasetId": {
"description": "The dataset id which was used to compute the AOT chart.",
"type": "string"
},
"modelId": {
"description": "The model id which was used to compute the AOT chart.",
"type": "string"
},
"projectId": {
"description": "The project id which was used to compute the AOT chart.",
"type": "string"
}
},
"required": [
"bins",
"datasetId",
"modelId",
"projectId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[AOTChartBins] |
true |
|
The datetime chart data for that source. |
| datasetId |
string |
true |
|
The dataset id which was used to compute the AOT chart. |
| modelId |
string |
true |
|
The model id which was used to compute the AOT chart. |
| projectId |
string |
true |
|
The project id which was used to compute the AOT chart. |
AOTChartRetrieveResponse
{
"properties": {
"bins": {
"description": "The datetime chart data for that source.",
"items": {
"properties": {
"actual": {
"description": "The average actual value of the target in the bin. ``null`` if there are no entries in the bin or if this is an anomaly detection project.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive).",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "As indicated by the frequencyType in the Metadata, used to determine what the averages mentioned above are taken over. ``null`` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"predicted": {
"description": "The average prediction of the model in the bin. ``null`` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive).",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"frequency",
"predicted",
"startDate"
],
"type": "object"
},
"type": "array"
},
"datasetId": {
"description": "The dataset id to which the chart data belongs.",
"type": "string"
},
"endDate": {
"description": "The requested `endDate`, or, if not specified, the end date for this dataset (exclusive). Example: '2010-05-13T00:00:00.000000Z'.",
"format": "date-time",
"type": "string"
},
"modelId": {
"description": "The model id to which the chart data belongs.",
"type": "string"
},
"projectId": {
"description": "The project id to which the chart data belongs.",
"type": "string"
},
"resolution": {
"description": "The resolution used for binning where a resolution is one of ['milliseconds', 'seconds', 'minutes', 'hours', 'days', 'weeks', 'months', 'years'].",
"enum": [
"microseconds",
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"startDate": {
"description": "The requested `startDate`, or, if not specified, the start date for this dataset. Example: '2010-05-13T00:00:00.000000Z'.",
"format": "date-time",
"type": "string"
},
"statistics": {
"description": "Statistics calculated on the chart data.",
"properties": {
"durbinWatson": {
"description": "The Durbin-Watson statistic for the chart data. Value is between 0 and 4. Returns -1 when the statistic is invalid for the data, e.g. if this is an anomaly detection project.",
"type": "number"
}
},
"required": [
"durbinWatson"
],
"type": "object"
}
},
"required": [
"bins",
"datasetId",
"modelId",
"projectId",
"resolution",
"statistics"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[AOTChartBins] |
true |
|
The datetime chart data for that source. |
| datasetId |
string |
true |
|
The dataset id to which the chart data belongs. |
| endDate |
string(date-time) |
false |
|
The requested endDate, or, if not specified, the end date for this dataset (exclusive). Example: '2010-05-13T00:00:00.000000Z'. |
| modelId |
string |
true |
|
The model id to which the chart data belongs. |
| projectId |
string |
true |
|
The project id to which the chart data belongs. |
| resolution |
string |
true |
|
The resolution used for binning where a resolution is one of ['milliseconds', 'seconds', 'minutes', 'hours', 'days', 'weeks', 'months', 'years']. |
| startDate |
string(date-time) |
false |
|
The requested startDate, or, if not specified, the start date for this dataset. Example: '2010-05-13T00:00:00.000000Z'. |
| statistics |
AOTChartStatistics |
true |
|
Statistics calculated on the chart data. |
Enumerated Values
| Property |
Value |
| resolution |
[microseconds, milliseconds, seconds, minutes, hours, days, weeks, months, quarters, years] |
AOTChartStatistics
{
"description": "Statistics calculated on the chart data.",
"properties": {
"durbinWatson": {
"description": "The Durbin-Watson statistic for the chart data. Value is between 0 and 4. Returns -1 when the statistic is invalid for the data, e.g. if this is an anomaly detection project.",
"type": "number"
}
},
"required": [
"durbinWatson"
],
"type": "object"
}
Statistics calculated on the chart data.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| durbinWatson |
number |
true |
|
The Durbin-Watson statistic for the chart data. Value is between 0 and 4. Returns -1 when the statistic is invalid for the data, e.g. if this is an anomaly detection project. |
AccuracyMetrics
{
"properties": {
"metric": {
"description": "The name of the metric.",
"enum": [
"AUC",
"Weighted AUC",
"Area Under PR Curve",
"Weighted Area Under PR Curve",
"Kolmogorov-Smirnov",
"Weighted Kolmogorov-Smirnov",
"FVE Binomial",
"Weighted FVE Binomial",
"Gini Norm",
"Weighted Gini Norm",
"LogLoss",
"Weighted LogLoss",
"Max MCC",
"Weighted Max MCC",
"Rate@Top5%",
"Weighted Rate@Top5%",
"Rate@Top10%",
"Weighted Rate@Top10%",
"Rate@TopTenth%",
"RMSE",
"Weighted RMSE",
"f1",
"accuracy"
],
"type": "string"
},
"value": {
"description": "The calculated score of the metric.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"metric",
"value"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| metric |
string |
true |
|
The name of the metric. |
| value |
number |
true |
maximum: 1
minimum: 0
|
The calculated score of the metric. |
Enumerated Values
| Property |
Value |
| metric |
[AUC, Weighted AUC, Area Under PR Curve, Weighted Area Under PR Curve, Kolmogorov-Smirnov, Weighted Kolmogorov-Smirnov, FVE Binomial, Weighted FVE Binomial, Gini Norm, Weighted Gini Norm, LogLoss, Weighted LogLoss, Max MCC, Weighted Max MCC, Rate@Top5%, Weighted Rate@Top5%, Rate@Top10%, Weighted Rate@Top10%, Rate@TopTenth%, RMSE, Weighted RMSE, f1, accuracy] |
AccuracyOverTimePlotsBins
{
"properties": {
"actual": {
"description": "Average actual value of the target in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "Indicates number of values averaged in bin in case of a resolution change.",
"type": [
"integer",
"null"
]
},
"predicted": {
"description": "Average prediction of the model in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"frequency",
"predicted",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actual |
number,null |
true |
|
Average actual value of the target in the bin. null if there are no entries in the bin. |
| endDate |
string(date-time) |
true |
|
The datetime of the end of the bin (exclusive). |
| frequency |
integer,null |
true |
|
Indicates number of values averaged in bin in case of a resolution change. |
| predicted |
number,null |
true |
|
Average prediction of the model in the bin. null if there are no entries in the bin. |
| startDate |
string(date-time) |
true |
|
The datetime of the start of the bin (inclusive). |
AccuracyOverTimePlotsDataResponse
{
"properties": {
"bins": {
"description": "An array of bins for the retrieved plots.",
"items": {
"properties": {
"actual": {
"description": "Average actual value of the target in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "Indicates number of values averaged in bin in case of a resolution change.",
"type": [
"integer",
"null"
]
},
"predicted": {
"description": "Average prediction of the model in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"frequency",
"predicted",
"startDate"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"calendarEvents": {
"description": "An array of calendar events for a retrieved plot.",
"items": {
"properties": {
"date": {
"description": "The date of the calendar event.",
"format": "date-time",
"type": "string"
},
"name": {
"description": "Name of the calendar event.",
"type": "string"
},
"seriesId": {
"description": "The series ID for the event. If this event does not specify a series ID, then this will be `null`, indicating that the event applies to all series.",
"type": [
"string",
"null"
]
}
},
"required": [
"date",
"name",
"seriesId"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). ",
"format": "date-time",
"type": "string"
},
"resolution": {
"description": "The resolution that is used for binning.",
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). ",
"format": "date-time",
"type": "string"
},
"statistics": {
"description": "Statistics calculated for the chart data.",
"properties": {
"durbinWatson": {
"description": "The Durbin-Watson statistic for the chart data. Value is between 0 and 4. Durbin-Watson statistic is a test statistic used to detect the presence of autocorrelation at lag 1 in the residuals (prediction errors) from a regression analysis. More info https://wikipedia.org/wiki/Durbin%E2%80%93Watson_statistic",
"maximum": 4,
"minimum": 0,
"type": [
"number",
"null"
]
}
},
"required": [
"durbinWatson"
],
"type": "object"
}
},
"required": [
"bins",
"calendarEvents",
"endDate",
"resolution",
"startDate",
"statistics"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[AccuracyOverTimePlotsBins] |
true |
maxItems: 1000
minItems: 1
|
An array of bins for the retrieved plots. |
| calendarEvents |
[CalendarEvent] |
true |
maxItems: 1000
|
An array of calendar events for a retrieved plot. |
| endDate |
string(date-time) |
true |
|
The datetime of the end of the chart data (exclusive). |
| resolution |
string |
true |
|
The resolution that is used for binning. |
| startDate |
string(date-time) |
true |
|
The datetime of the start of the chart data (inclusive). |
| statistics |
AccuracyOverTimePlotsStatistics |
true |
|
Statistics calculated for the chart data. |
Enumerated Values
| Property |
Value |
| resolution |
[milliseconds, seconds, minutes, hours, days, weeks, months, quarters, years] |
{
"properties": {
"backtestMetadata": {
"description": "An array of metadata information for each backtest. The array index of metadata object is the backtest index.",
"items": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"backtestStatuses": {
"description": "An array of status information for each backtest. The array index of status object is the backtest index.",
"items": {
"description": "Status for accuracy over time plots.",
"properties": {
"training": {
"description": "The status for the training.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
},
"validation": {
"description": "The status for the validation.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"estimatedSeriesLimit": {
"description": "Estimated number of series that can be calculated in one request for 1 FD.",
"minimum": 1,
"type": "integer"
},
"forecastDistance": {
"description": "The forecast distance for which the data was retrieved. `null` for OTV projects.",
"maximum": 1000,
"minimum": 0,
"type": [
"integer",
"null"
]
},
"holdoutMetadata": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"holdoutStatuses": {
"description": "Status for accuracy over time plots.",
"properties": {
"training": {
"description": "The status for the training.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
},
"validation": {
"description": "The status for the validation.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"resolutions": {
"description": "An array of available time resolutions for which plots can be retrieved.",
"items": {
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"maxItems": 9,
"minItems": 1,
"type": "array"
}
},
"required": [
"backtestMetadata",
"backtestStatuses",
"forecastDistance",
"holdoutMetadata",
"holdoutStatuses",
"resolutions"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestMetadata |
[DatetimeTrendPlotsBacktestMetadata] |
true |
maxItems: 20
minItems: 1
|
An array of metadata information for each backtest. The array index of metadata object is the backtest index. |
| backtestStatuses |
[AccuracyOverTimePlotsStatus] |
true |
maxItems: 20
minItems: 1
|
An array of status information for each backtest. The array index of status object is the backtest index. |
| estimatedSeriesLimit |
integer |
false |
minimum: 1
|
Estimated number of series that can be calculated in one request for 1 FD. |
| forecastDistance |
integer,null |
true |
maximum: 1000
minimum: 0
|
The forecast distance for which the data was retrieved. null for OTV projects. |
| holdoutMetadata |
DatetimeTrendPlotsBacktestMetadata |
true |
|
Metadata for backtest/holdout. |
| holdoutStatuses |
AccuracyOverTimePlotsStatus |
true |
|
Status for accuracy over time plots. |
| resolutions |
[string] |
true |
maxItems: 9
minItems: 1
|
An array of available time resolutions for which plots can be retrieved. |
AccuracyOverTimePlotsStatistics
{
"description": "Statistics calculated for the chart data.",
"properties": {
"durbinWatson": {
"description": "The Durbin-Watson statistic for the chart data. Value is between 0 and 4. Durbin-Watson statistic is a test statistic used to detect the presence of autocorrelation at lag 1 in the residuals (prediction errors) from a regression analysis. More info https://wikipedia.org/wiki/Durbin%E2%80%93Watson_statistic",
"maximum": 4,
"minimum": 0,
"type": [
"number",
"null"
]
}
},
"required": [
"durbinWatson"
],
"type": "object"
}
Statistics calculated for the chart data.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| durbinWatson |
number,null |
true |
maximum: 4
minimum: 0
|
The Durbin-Watson statistic for the chart data. Value is between 0 and 4. Durbin-Watson statistic is a test statistic used to detect the presence of autocorrelation at lag 1 in the residuals (prediction errors) from a regression analysis. More info https://wikipedia.org/wiki/Durbin%E2%80%93Watson_statistic |
AccuracyOverTimePlotsStatus
{
"description": "Status for accuracy over time plots.",
"properties": {
"training": {
"description": "The status for the training.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
},
"validation": {
"description": "The status for the validation.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
}
},
"required": [
"training",
"validation"
],
"type": "object"
}
Status for accuracy over time plots.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| training |
string |
true |
|
The status for the training. |
| validation |
string |
true |
|
The status for the validation. |
Enumerated Values
| Property |
Value |
| training |
[completed, errored, inProgress, insufficientData, notCompleted, notSupported] |
| validation |
[completed, errored, inProgress, insufficientData, notCompleted, notSupported] |
ActivationMap
{
"properties": {
"activationValues": {
"description": "A 2D matrix of values (row-major) representing the activation strengths for particular image regions.",
"items": {
"items": {
"maximum": 255,
"minimum": 0,
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"actualTargetValue": {
"description": "Actual target value of the dataset row",
"oneOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
]
},
"featureName": {
"description": "The name of the column containing the image value the activation map is based upon.",
"type": "string"
},
"imageHeight": {
"description": "The height of the original image (in pixels) this activation map has been computed for.",
"type": "integer"
},
"imageId": {
"description": "ID of the original image this activation map has been computed for.",
"type": "string"
},
"imageWidth": {
"description": "The width of the original image (in pixels) this activation map has been computed for.",
"type": "integer"
},
"links": {
"description": "Download URLs.",
"properties": {
"downloadOriginalImage": {
"description": "URL of the original image",
"format": "uri",
"type": "string"
},
"downloadOverlayImage": {
"description": "URL of the original image overlaid by the activation heatmap",
"format": "uri",
"type": "string"
}
},
"required": [
"downloadOriginalImage",
"downloadOverlayImage"
],
"type": "object"
},
"overlayImageId": {
"description": "ID of the image containing the original image overlaid by the activation heatmap.",
"type": "string"
},
"predictedTargetValue": {
"description": "predicted target value of the dataset row containing this image.",
"oneOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"items": {
"type": "string"
},
"type": "array"
}
]
}
},
"required": [
"activationValues",
"actualTargetValue",
"featureName",
"imageHeight",
"imageId",
"imageWidth",
"links",
"overlayImageId",
"predictedTargetValue"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| activationValues |
[array] |
true |
|
A 2D matrix of values (row-major) representing the activation strengths for particular image regions. |
| actualTargetValue |
any |
true |
|
Actual target value of the dataset row |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
number |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
[string] |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
null |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| featureName |
string |
true |
|
The name of the column containing the image value the activation map is based upon. |
| imageHeight |
integer |
true |
|
The height of the original image (in pixels) this activation map has been computed for. |
| imageId |
string |
true |
|
ID of the original image this activation map has been computed for. |
| imageWidth |
integer |
true |
|
The width of the original image (in pixels) this activation map has been computed for. |
| links |
ActivationMapLinks |
true |
|
Download URLs. |
| overlayImageId |
string |
true |
|
ID of the image containing the original image overlaid by the activation heatmap. |
| predictedTargetValue |
any |
true |
|
predicted target value of the dataset row containing this image. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
number |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
[string] |
false |
|
none |
ActivationMapLinks
{
"description": "Download URLs.",
"properties": {
"downloadOriginalImage": {
"description": "URL of the original image",
"format": "uri",
"type": "string"
},
"downloadOverlayImage": {
"description": "URL of the original image overlaid by the activation heatmap",
"format": "uri",
"type": "string"
}
},
"required": [
"downloadOriginalImage",
"downloadOverlayImage"
],
"type": "object"
}
Download URLs.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| downloadOriginalImage |
string(uri) |
true |
|
URL of the original image |
| downloadOverlayImage |
string(uri) |
true |
|
URL of the original image overlaid by the activation heatmap |
ActivationMapsComputeResponse
{
"properties": {
"id": {
"description": "The job ID.",
"type": "string"
},
"isBlocked": {
"description": "True if the job is waiting for its dependencies to be resolved first.",
"type": "boolean"
},
"jobType": {
"description": "the type of the job",
"enum": [
"compute_image_activation_maps"
],
"type": "string"
},
"message": {
"description": "Error message in case of failure.",
"type": "string"
},
"modelId": {
"description": "the model ID of the target model",
"type": "string"
},
"projectId": {
"description": "The project the job belongs to.",
"type": "string"
},
"status": {
"description": "The job status.",
"enum": [
"queue",
"inprogress",
"error",
"ABORTED",
"COMPLETED"
],
"type": "string"
},
"url": {
"description": "A URL that can be used to request details about the job.",
"type": "string"
}
},
"required": [
"id",
"isBlocked",
"jobType",
"message",
"modelId",
"projectId",
"status",
"url"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| id |
string |
true |
|
The job ID. |
| isBlocked |
boolean |
true |
|
True if the job is waiting for its dependencies to be resolved first. |
| jobType |
string |
true |
|
the type of the job |
| message |
string |
true |
|
Error message in case of failure. |
| modelId |
string |
true |
|
the model ID of the target model |
| projectId |
string |
true |
|
The project the job belongs to. |
| status |
string |
true |
|
The job status. |
| url |
string |
true |
|
A URL that can be used to request details about the job. |
Enumerated Values
| Property |
Value |
| jobType |
compute_image_activation_maps |
| status |
[queue, inprogress, error, ABORTED, COMPLETED] |
ActivationMapsListResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of Image Activation Maps",
"items": {
"properties": {
"featureName": {
"description": "Name of feature",
"type": "string"
},
"modelId": {
"description": "Model ID of the target model",
"type": "string"
}
},
"required": [
"featureName",
"modelId"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[ImageInsightsMetadataElement] |
true |
|
List of Image Activation Maps |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
ActivationMapsRetrieveResponse
{
"properties": {
"activationMapHeight": {
"description": "The height of each activation map (the number of rows in each activationValues matrix).",
"type": [
"integer",
"null"
]
},
"activationMapWidth": {
"description": "The width of each activation map (the number of items in each row of each activationValues matrix).",
"type": [
"integer",
"null"
]
},
"activationMaps": {
"description": "List of activation map objects",
"items": {
"properties": {
"activationValues": {
"description": "A 2D matrix of values (row-major) representing the activation strengths for particular image regions.",
"items": {
"items": {
"maximum": 255,
"minimum": 0,
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"actualTargetValue": {
"description": "Actual target value of the dataset row",
"oneOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
]
},
"featureName": {
"description": "The name of the column containing the image value the activation map is based upon.",
"type": "string"
},
"imageHeight": {
"description": "The height of the original image (in pixels) this activation map has been computed for.",
"type": "integer"
},
"imageId": {
"description": "ID of the original image this activation map has been computed for.",
"type": "string"
},
"imageWidth": {
"description": "The width of the original image (in pixels) this activation map has been computed for.",
"type": "integer"
},
"links": {
"description": "Download URLs.",
"properties": {
"downloadOriginalImage": {
"description": "URL of the original image",
"format": "uri",
"type": "string"
},
"downloadOverlayImage": {
"description": "URL of the original image overlaid by the activation heatmap",
"format": "uri",
"type": "string"
}
},
"required": [
"downloadOriginalImage",
"downloadOverlayImage"
],
"type": "object"
},
"overlayImageId": {
"description": "ID of the image containing the original image overlaid by the activation heatmap.",
"type": "string"
},
"predictedTargetValue": {
"description": "predicted target value of the dataset row containing this image.",
"oneOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"items": {
"type": "string"
},
"type": "array"
}
]
}
},
"required": [
"activationValues",
"actualTargetValue",
"featureName",
"imageHeight",
"imageId",
"imageWidth",
"links",
"overlayImageId",
"predictedTargetValue"
],
"type": "object"
},
"type": "array"
},
"targetBins": {
"description": "List of bin objects for regression or null",
"items": {
"properties": {
"targetBinEnd": {
"description": "End value for the target bin",
"type": "number"
},
"targetBinStart": {
"description": "Start value for the target bin",
"type": "number"
}
},
"required": [
"targetBinEnd",
"targetBinStart"
],
"type": "object"
},
"type": "array"
},
"targetValues": {
"description": "List of target values for classification or null",
"items": {
"description": "Target value",
"type": "string"
},
"type": "array"
}
},
"required": [
"activationMapHeight",
"activationMapWidth",
"activationMaps",
"targetBins",
"targetValues"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| activationMapHeight |
integer,null |
true |
|
The height of each activation map (the number of rows in each activationValues matrix). |
| activationMapWidth |
integer,null |
true |
|
The width of each activation map (the number of items in each row of each activationValues matrix). |
| activationMaps |
[ActivationMap] |
true |
|
List of activation map objects |
| targetBins |
[TargetBin] |
true |
|
List of bin objects for regression or null |
| targetValues |
[string] |
true |
|
List of target values for classification or null |
ActualFrequency
{
"properties": {
"otherClassName": {
"description": "The name of the class.",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className` (from 0 to 100).",
"maximum": 100,
"minimum": 0,
"type": "number"
},
"value": {
"description": "The count of the times this class was predicted when is was actually `classMetrics.className`.",
"minimum": 0,
"type": "integer"
}
},
"required": [
"otherClassName",
"percentage",
"value"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| otherClassName |
string |
true |
|
The name of the class. |
| percentage |
number |
true |
maximum: 100
minimum: 0
|
The percentage of the times this class was predicted when is was actually classMetrics.className (from 0 to 100). |
| value |
integer |
true |
minimum: 0
|
The count of the times this class was predicted when is was actually classMetrics.className. |
ActualPercentages
{
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className`",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| otherClassName |
string |
true |
|
the name of the class |
| percentage |
number |
true |
|
The percentage of the times this class was predicted when is was actually classMetrics.className |
AllDataImage
{
"description": "Statistics for all data for different feature values.",
"properties": {
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"images",
"percentageOfMissingImages"
],
"type": "object"
}
Statistics for all data for different feature values.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| images |
[string] |
true |
maxItems: 10
minItems: 1
|
A list of b64 encoded images. |
| percentageOfMissingImages |
number |
true |
maximum: 100
minimum: 0
|
A percentage of image rows that have a missing value for this feature. |
AllDataText
{
"description": "Statistics for all data for different feature values.",
"properties": {
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
}
Statistics for all data for different feature values.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| missingRowsPercent |
number,null |
false |
maximum: 100
minimum: 0
|
A percentage of all rows that have a missing value for this feature. |
| perValueStatistics |
[PerValueStatisticTextListItem] |
true |
|
Statistic value for feature values in all data or a cluster. |
AllMulticlassModelLiftChartsResponse
{
"properties": {
"charts": {
"description": "List of lift chart data from all available sources.",
"items": {
"properties": {
"classBins": {
"description": "List of lift chart data for each target class.",
"items": {
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"targetClass": {
"description": "Target class for the lift chart.",
"type": "string"
}
},
"required": [
"bins",
"targetClass"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
}
},
"required": [
"classBins",
"source"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"charts"
],
"type": "object"
}
Properties
AnalyzedFeature
{
"properties": {
"detailsHistogram": {
"description": "Histogram details for the specified feature.",
"items": {
"properties": {
"bars": {
"description": "Class details for the histogram chart",
"items": {
"properties": {
"label": {
"description": "Name of the class.",
"type": "string"
},
"value": {
"description": "Ratio of occurrence of the class.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
},
"bin": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
],
"description": "Label for the bin grouping"
}
},
"required": [
"bars",
"bin"
],
"type": "object"
},
"type": "array"
},
"disparityScore": {
"description": "A number to describe disparity for the feature between the compared classes.",
"type": "number"
},
"featureImpact": {
"description": "A feature importance value.",
"type": "number"
},
"name": {
"description": "Name of the feature.",
"type": "string"
},
"status": {
"description": "A status of the feature.",
"enum": [
"Healthy",
"At Risk",
"Failing"
],
"type": "string"
}
},
"required": [
"detailsHistogram",
"disparityScore",
"featureImpact",
"name",
"status"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| detailsHistogram |
[HistogramDetails] |
true |
|
Histogram details for the specified feature. |
| disparityScore |
number |
true |
|
A number to describe disparity for the feature between the compared classes. |
| featureImpact |
number |
true |
|
A feature importance value. |
| name |
string |
true |
|
Name of the feature. |
| status |
string |
true |
|
A status of the feature. |
Enumerated Values
| Property |
Value |
| status |
[Healthy, At Risk, Failing] |
AnomalyAssessmentExplanationsResponse
{
"properties": {
"backtest": {
"description": "The backtest of the record.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
]
},
"count": {
"description": "The count of points.",
"type": "integer"
},
"data": {
"description": "Each is a `DataPoint` corresponding to a row in the specified range.",
"items": {
"properties": {
"prediction": {
"description": "The output of the model for this row.",
"type": "number"
},
"shapExplanation": {
"description": "Either ``null`` or an array of up to 10 `ShapleyFeatureContribution` objects. Only rows with the highest anomaly scores have Shapley explanations calculated.",
"items": {
"properties": {
"feature": {
"description": "Feature name",
"type": "string"
},
"featureValue": {
"description": "Feature value for this row. First 50 characters are returned.",
"type": "string"
},
"strength": {
"description": "Shapley value for this feature and row.",
"type": "number"
}
},
"required": [
"feature",
"featureValue",
"strength"
],
"type": "object"
},
"type": "array"
},
"timestamp": {
"description": "ISO-formatted timestamp for the row.",
"format": "date-time",
"type": "string"
}
},
"required": [
"prediction",
"shapExplanation",
"timestamp"
],
"type": "object"
},
"type": "array"
},
"endDate": {
"description": "ISO-formatted last timestamp in the response. For example: ``2019-08-30T00:00:00.000000Z``.",
"format": "date-time",
"type": "string"
},
"modelId": {
"description": "The model ID of the record.",
"type": "string"
},
"projectId": {
"description": "The project ID of the record.",
"type": "string"
},
"recordId": {
"description": "The ID of the anomaly assessment record.",
"type": "string"
},
"seriesId": {
"description": "The series id of the record. Applicable in multiseries projects",
"type": [
"string",
"null"
]
},
"shapBaseValue": {
"description": "shap base value",
"type": "number"
},
"source": {
"description": "The source of the record",
"enum": [
"training",
"validation"
],
"type": "string"
},
"startDate": {
"description": "ISO-formatted first timestamp in the response. For example: ``2019-08-01T00:00:00.000000Z``.",
"format": "date-time",
"type": "string"
}
},
"required": [
"backtest",
"count",
"data",
"endDate",
"modelId",
"projectId",
"recordId",
"seriesId",
"shapBaseValue",
"source",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtest |
any |
true |
|
The backtest of the record. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
maximum: 19
minimum: 0
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
The count of points. |
| data |
[DataPointResponse] |
true |
|
Each is a DataPoint corresponding to a row in the specified range. |
| endDate |
string(date-time) |
true |
|
ISO-formatted last timestamp in the response. For example: 2019-08-30T00:00:00.000000Z. |
| modelId |
string |
true |
|
The model ID of the record. |
| projectId |
string |
true |
|
The project ID of the record. |
| recordId |
string |
true |
|
The ID of the anomaly assessment record. |
| seriesId |
string,null |
true |
|
The series id of the record. Applicable in multiseries projects |
| shapBaseValue |
number |
true |
|
shap base value |
| source |
string |
true |
|
The source of the record |
| startDate |
string(date-time) |
true |
|
ISO-formatted first timestamp in the response. For example: 2019-08-01T00:00:00.000000Z. |
Enumerated Values
| Property |
Value |
| anonymous |
holdout |
| source |
[training, validation] |
AnomalyAssessmentInitialize
{
"properties": {
"backtest": {
"description": "The backtest to compute insight for.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
]
},
"seriesId": {
"description": "Required for multiseries projects. The series id to compute insight for.",
"type": "string"
},
"source": {
"description": "The source to compute insight for.",
"enum": [
"training",
"validation"
],
"type": "string"
}
},
"required": [
"backtest",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtest |
any |
true |
|
The backtest to compute insight for. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
maximum: 19
minimum: 0
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| seriesId |
string |
false |
|
Required for multiseries projects. The series id to compute insight for. |
| source |
string |
true |
|
The source to compute insight for. |
Enumerated Values
| Property |
Value |
| anonymous |
holdout |
| source |
[training, validation] |
AnomalyAssessmentPreviewResponse
{
"properties": {
"backtest": {
"description": "The backtest of the record.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
]
},
"endDate": {
"description": "ISO-formatted last timestamp in the subset. For example: ``2019-08-30T00:00:00.000000Z``.",
"format": "date-time",
"type": "string"
},
"modelId": {
"description": "The model ID of the record.",
"type": "string"
},
"previewBins": {
"description": "Aggregated predictions for the subset. Bins boundaries may differ from actual start/end dates because this is an aggregation.",
"items": {
"properties": {
"avgPredicted": {
"description": "Average prediction of the model in the bin. Null if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "ISO-formatted datetime of the end of the bin (exclusive).",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "Number of the rows in the bin.",
"type": "integer"
},
"maxPredicted": {
"description": "Maximum prediction of the model in the bin. Null if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "ISO-formatted datetime of the start of the bin (inclusive).",
"format": "date-time",
"type": "string"
}
},
"required": [
"avgPredicted",
"endDate",
"frequency",
"maxPredicted",
"startDate"
],
"type": "object"
},
"type": "array"
},
"projectId": {
"description": "The project ID of the record.",
"type": "string"
},
"recordId": {
"description": "The ID of the anomaly assessment record.",
"type": "string"
},
"seriesId": {
"description": "The series id of the record. Applicable in multiseries projects",
"type": [
"string",
"null"
]
},
"source": {
"description": "The source of the record",
"enum": [
"training",
"validation"
],
"type": "string"
},
"startDate": {
"description": "ISO-formatted first timestamp in the subset. For example: ``2019-08-01T00:00:00.000000Z``.",
"format": "date-time",
"type": "string"
}
},
"required": [
"backtest",
"endDate",
"modelId",
"previewBins",
"projectId",
"recordId",
"seriesId",
"source",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtest |
any |
true |
|
The backtest of the record. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
maximum: 19
minimum: 0
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| endDate |
string(date-time) |
true |
|
ISO-formatted last timestamp in the subset. For example: 2019-08-30T00:00:00.000000Z. |
| modelId |
string |
true |
|
The model ID of the record. |
| previewBins |
[BinResponse] |
true |
|
Aggregated predictions for the subset. Bins boundaries may differ from actual start/end dates because this is an aggregation. |
| projectId |
string |
true |
|
The project ID of the record. |
| recordId |
string |
true |
|
The ID of the anomaly assessment record. |
| seriesId |
string,null |
true |
|
The series id of the record. Applicable in multiseries projects |
| source |
string |
true |
|
The source of the record |
| startDate |
string(date-time) |
true |
|
ISO-formatted first timestamp in the subset. For example: 2019-08-01T00:00:00.000000Z. |
Enumerated Values
| Property |
Value |
| anonymous |
holdout |
| source |
[training, validation] |
AnomalyAssessmentRecordResponse
{
"properties": {
"backtest": {
"description": "The backtest of the record.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
]
},
"deleteLocation": {
"description": "URL to delete anomaly assessment record.",
"format": "uri",
"type": [
"string",
"null"
]
},
"endDate": {
"description": "ISO-formatted last timestamp in the subset. For example: ``2019-08-30T00:00:00.000000Z``.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"latestExplanationsLocation": {
"description": "URL to retrieve the latest predictions with the shap explanations.",
"format": "uri",
"type": [
"string",
"null"
]
},
"modelId": {
"description": "The model ID of the record.",
"type": "string"
},
"predictionThreshold": {
"description": "The threshold, all rows with anomaly scores greater or equal to it have Shapley explanations computed.",
"type": [
"number",
"null"
]
},
"previewLocation": {
"description": "URL to retrieve predictions preview for the record.",
"format": "uri",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID of the record.",
"type": "string"
},
"recordId": {
"description": "The ID of the anomaly assessment record.",
"type": "string"
},
"seriesId": {
"description": "The series id of the record. Applicable in multiseries projects",
"type": [
"string",
"null"
]
},
"source": {
"description": "The source of the record",
"enum": [
"training",
"validation"
],
"type": "string"
},
"startDate": {
"description": "ISO-formatted first timestamp in the subset. For example: ``2019-08-01T00:00:00.000000Z``.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"status": {
"description": "The status of the anomaly assessment record.",
"enum": [
"noData",
"notSupported",
"completed"
],
"type": "string"
},
"statusDetails": {
"description": "The status details.",
"type": "string"
}
},
"required": [
"backtest",
"deleteLocation",
"endDate",
"latestExplanationsLocation",
"modelId",
"predictionThreshold",
"previewLocation",
"projectId",
"recordId",
"seriesId",
"source",
"startDate",
"status",
"statusDetails"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtest |
any |
true |
|
The backtest of the record. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
maximum: 19
minimum: 0
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| deleteLocation |
string,null(uri) |
true |
|
URL to delete anomaly assessment record. |
| endDate |
string,null(date-time) |
true |
|
ISO-formatted last timestamp in the subset. For example: 2019-08-30T00:00:00.000000Z. |
| latestExplanationsLocation |
string,null(uri) |
true |
|
URL to retrieve the latest predictions with the shap explanations. |
| modelId |
string |
true |
|
The model ID of the record. |
| predictionThreshold |
number,null |
true |
|
The threshold, all rows with anomaly scores greater or equal to it have Shapley explanations computed. |
| previewLocation |
string,null(uri) |
true |
|
URL to retrieve predictions preview for the record. |
| projectId |
string |
true |
|
The project ID of the record. |
| recordId |
string |
true |
|
The ID of the anomaly assessment record. |
| seriesId |
string,null |
true |
|
The series id of the record. Applicable in multiseries projects |
| source |
string |
true |
|
The source of the record |
| startDate |
string,null(date-time) |
true |
|
ISO-formatted first timestamp in the subset. For example: 2019-08-01T00:00:00.000000Z. |
| status |
string |
true |
|
The status of the anomaly assessment record. |
| statusDetails |
string |
true |
|
The status details. |
Enumerated Values
| Property |
Value |
| anonymous |
holdout |
| source |
[training, validation] |
| status |
[noData, notSupported, completed] |
AnomalyAssessmentRecordsResponse
{
"properties": {
"count": {
"description": "Number of items in current page.",
"type": "integer"
},
"data": {
"description": "Anomaly assessment record.",
"items": {
"properties": {
"backtest": {
"description": "The backtest of the record.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
]
},
"deleteLocation": {
"description": "URL to delete anomaly assessment record.",
"format": "uri",
"type": [
"string",
"null"
]
},
"endDate": {
"description": "ISO-formatted last timestamp in the subset. For example: ``2019-08-30T00:00:00.000000Z``.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"latestExplanationsLocation": {
"description": "URL to retrieve the latest predictions with the shap explanations.",
"format": "uri",
"type": [
"string",
"null"
]
},
"modelId": {
"description": "The model ID of the record.",
"type": "string"
},
"predictionThreshold": {
"description": "The threshold, all rows with anomaly scores greater or equal to it have Shapley explanations computed.",
"type": [
"number",
"null"
]
},
"previewLocation": {
"description": "URL to retrieve predictions preview for the record.",
"format": "uri",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID of the record.",
"type": "string"
},
"recordId": {
"description": "The ID of the anomaly assessment record.",
"type": "string"
},
"seriesId": {
"description": "The series id of the record. Applicable in multiseries projects",
"type": [
"string",
"null"
]
},
"source": {
"description": "The source of the record",
"enum": [
"training",
"validation"
],
"type": "string"
},
"startDate": {
"description": "ISO-formatted first timestamp in the subset. For example: ``2019-08-01T00:00:00.000000Z``.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"status": {
"description": "The status of the anomaly assessment record.",
"enum": [
"noData",
"notSupported",
"completed"
],
"type": "string"
},
"statusDetails": {
"description": "The status details.",
"type": "string"
}
},
"required": [
"backtest",
"deleteLocation",
"endDate",
"latestExplanationsLocation",
"modelId",
"predictionThreshold",
"previewLocation",
"projectId",
"recordId",
"seriesId",
"source",
"startDate",
"status",
"statusDetails"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page)",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page)",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"count",
"data",
"next",
"previous"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
Number of items in current page. |
| data |
[AnomalyAssessmentRecordResponse] |
true |
|
Anomaly assessment record. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page) |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page) |
AnomalyInsightTableData
{
"properties": {
"columns": {
"description": "array of columns that contain columns from training dataset and `anomalyScore` column.",
"items": {
"type": "string"
},
"type": "array"
},
"data": {
"description": "array of arrays with actual data. Order in each array corresponds to order in columns array.",
"items": {
"type": "number"
},
"type": "array"
},
"rowId": {
"description": "index 0-based array. Each rowId corresponds to the actual row number of training data",
"items": {
"type": "integer"
},
"type": "array"
}
},
"required": [
"columns",
"data",
"rowId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| columns |
[string] |
true |
|
array of columns that contain columns from training dataset and anomalyScore column. |
| data |
[number] |
true |
|
array of arrays with actual data. Order in each array corresponds to order in columns array. |
| rowId |
[integer] |
true |
|
index 0-based array. Each rowId corresponds to the actual row number of training data |
AnomalyInsightTableRetrieve
{
"properties": {
"modelId": {
"description": "given model identifier",
"type": "string"
},
"table": {
"description": "anomaly insights table",
"items": {
"properties": {
"columns": {
"description": "array of columns that contain columns from training dataset and `anomalyScore` column.",
"items": {
"type": "string"
},
"type": "array"
},
"data": {
"description": "array of arrays with actual data. Order in each array corresponds to order in columns array.",
"items": {
"type": "number"
},
"type": "array"
},
"rowId": {
"description": "index 0-based array. Each rowId corresponds to the actual row number of training data",
"items": {
"type": "integer"
},
"type": "array"
}
},
"required": [
"columns",
"data",
"rowId"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"modelId",
"table"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| modelId |
string |
true |
|
given model identifier |
| table |
[AnomalyInsightTableData] |
true |
|
anomaly insights table |
AnomalyOverTimePlotsBins
{
"properties": {
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "Indicates number of values averaged in bin in case of a resolution change.",
"type": [
"integer",
"null"
]
},
"predicted": {
"description": "Average prediction of the model in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"endDate",
"frequency",
"predicted",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| endDate |
string(date-time) |
true |
|
The datetime of the end of the bin (exclusive). |
| frequency |
integer,null |
true |
|
Indicates number of values averaged in bin in case of a resolution change. |
| predicted |
number,null |
true |
|
Average prediction of the model in the bin. null if there are no entries in the bin. |
| startDate |
string(date-time) |
true |
|
The datetime of the start of the bin (inclusive). |
AnomalyOverTimePlotsDataResponse
{
"properties": {
"bins": {
"description": "An array of bins for the retrieved plots.",
"items": {
"properties": {
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "Indicates number of values averaged in bin in case of a resolution change.",
"type": [
"integer",
"null"
]
},
"predicted": {
"description": "Average prediction of the model in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"endDate",
"frequency",
"predicted",
"startDate"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"calendarEvents": {
"description": "An array of calendar events for a retrieved plot.",
"items": {
"properties": {
"date": {
"description": "The date of the calendar event.",
"format": "date-time",
"type": "string"
},
"name": {
"description": "Name of the calendar event.",
"type": "string"
},
"seriesId": {
"description": "The series ID for the event. If this event does not specify a series ID, then this will be `null`, indicating that the event applies to all series.",
"type": [
"string",
"null"
]
}
},
"required": [
"date",
"name",
"seriesId"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). ",
"format": "date-time",
"type": "string"
},
"resolution": {
"description": "The resolution that is used for binning.",
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"bins",
"calendarEvents",
"endDate",
"resolution",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[AnomalyOverTimePlotsBins] |
true |
maxItems: 1000
minItems: 1
|
An array of bins for the retrieved plots. |
| calendarEvents |
[CalendarEvent] |
true |
maxItems: 1000
|
An array of calendar events for a retrieved plot. |
| endDate |
string(date-time) |
true |
|
The datetime of the end of the chart data (exclusive). |
| resolution |
string |
true |
|
The resolution that is used for binning. |
| startDate |
string(date-time) |
true |
|
The datetime of the start of the chart data (inclusive). |
Enumerated Values
| Property |
Value |
| resolution |
[milliseconds, seconds, minutes, hours, days, weeks, months, quarters, years] |
{
"properties": {
"backtestMetadata": {
"description": "An array of metadata information for each backtest. The array index of metadata object is the backtest index.",
"items": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"backtestStatuses": {
"description": "An array of status information for each backtest. The array index of status object is the backtest index.",
"items": {
"description": "Status for accuracy over time plots.",
"properties": {
"training": {
"description": "The status for the training.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
},
"validation": {
"description": "The status for the validation.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"estimatedSeriesLimit": {
"description": "Estimated number of series that can be calculated in one request for 1 FD.",
"minimum": 1,
"type": "integer"
},
"holdoutMetadata": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"holdoutStatuses": {
"description": "Status for accuracy over time plots.",
"properties": {
"training": {
"description": "The status for the training.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
},
"validation": {
"description": "The status for the validation.",
"enum": [
"completed",
"errored",
"inProgress",
"insufficientData",
"notCompleted",
"notSupported"
],
"type": "string"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"resolutions": {
"description": "An array of available time resolutions for which plots can be retrieved.",
"items": {
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"maxItems": 9,
"minItems": 1,
"type": "array"
}
},
"required": [
"backtestMetadata",
"backtestStatuses",
"holdoutMetadata",
"holdoutStatuses",
"resolutions"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestMetadata |
[DatetimeTrendPlotsBacktestMetadata] |
true |
maxItems: 20
minItems: 1
|
An array of metadata information for each backtest. The array index of metadata object is the backtest index. |
| backtestStatuses |
[AccuracyOverTimePlotsStatus] |
true |
maxItems: 20
minItems: 1
|
An array of status information for each backtest. The array index of status object is the backtest index. |
| estimatedSeriesLimit |
integer |
false |
minimum: 1
|
Estimated number of series that can be calculated in one request for 1 FD. |
| holdoutMetadata |
DatetimeTrendPlotsBacktestMetadata |
true |
|
Metadata for backtest/holdout. |
| holdoutStatuses |
AccuracyOverTimePlotsStatus |
true |
|
Status for accuracy over time plots. |
| resolutions |
[string] |
true |
maxItems: 9
minItems: 1
|
An array of available time resolutions for which plots can be retrieved. |
AnomalyOverTimePlotsPreviewBins
{
"properties": {
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| endDate |
string(date-time) |
true |
|
The datetime of the end of the bin (exclusive). |
| startDate |
string(date-time) |
true |
|
The datetime of the start of the bin (inclusive). |
AnomalyOverTimePlotsPreviewResponse
{
"properties": {
"bins": {
"description": "An array of bins for the retrieved plots.",
"items": {
"properties": {
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). ",
"format": "date-time",
"type": "string"
},
"predictionThreshold": {
"description": "Only bins with predictions exceeding this threshold are returned in the response.",
"exclusiveMinimum": 0,
"maximum": 1,
"type": "number"
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"bins",
"endDate",
"predictionThreshold",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[AnomalyOverTimePlotsPreviewBins] |
true |
maxItems: 1000
|
An array of bins for the retrieved plots. |
| endDate |
string(date-time) |
true |
|
The datetime of the end of the chart data (exclusive). |
| predictionThreshold |
number |
true |
maximum: 1
|
Only bins with predictions exceeding this threshold are returned in the response. |
| startDate |
string(date-time) |
true |
|
The datetime of the start of the chart data (inclusive). |
AverageModelMetricsField
{
"description": "All average model metrics from one data source.",
"properties": {
"metrics": {
"description": "Average model metrics for the given thresholds.",
"items": {
"properties": {
"name": {
"description": "Metric name.",
"enum": [
"accuracy",
"f1Score",
"falsePositiveRate",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"trueNegativeRate",
"truePositiveRate"
],
"type": "string"
},
"numLabelsUsedInCalculation": {
"description": "Number of labels that were taken into account in the calculation of metric averages",
"type": "integer"
},
"values": {
"description": "Metric values at given thresholds.",
"items": {
"type": "number"
},
"maxItems": 100,
"minItems": 100,
"type": "array"
}
},
"required": [
"name",
"numLabelsUsedInCalculation",
"values"
],
"type": "object"
},
"maxItems": 8,
"minItems": 8,
"type": "array"
},
"source": {
"description": "Chart source.",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
},
"thresholds": {
"description": "Threshold values for which model metrics are available.",
"items": {
"maximum": 1,
"minimum": 0,
"type": "number"
},
"maxItems": 100,
"minItems": 100,
"type": "array"
}
},
"required": [
"metrics",
"source",
"thresholds"
],
"type": "object"
}
All average model metrics from one data source.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| metrics |
[AverageModelMetricsValues] |
true |
maxItems: 8
minItems: 8
|
Average model metrics for the given thresholds. |
| source |
string |
true |
|
Chart source. |
| thresholds |
[number] |
true |
maxItems: 100
minItems: 100
|
Threshold values for which model metrics are available. |
Enumerated Values
| Property |
Value |
| source |
[validation, crossValidation, holdout] |
AverageModelMetricsValues
{
"properties": {
"name": {
"description": "Metric name.",
"enum": [
"accuracy",
"f1Score",
"falsePositiveRate",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"trueNegativeRate",
"truePositiveRate"
],
"type": "string"
},
"numLabelsUsedInCalculation": {
"description": "Number of labels that were taken into account in the calculation of metric averages",
"type": "integer"
},
"values": {
"description": "Metric values at given thresholds.",
"items": {
"type": "number"
},
"maxItems": 100,
"minItems": 100,
"type": "array"
}
},
"required": [
"name",
"numLabelsUsedInCalculation",
"values"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| name |
string |
true |
|
Metric name. |
| numLabelsUsedInCalculation |
integer |
true |
|
Number of labels that were taken into account in the calculation of metric averages |
| values |
[number] |
true |
maxItems: 100
minItems: 100
|
Metric values at given thresholds. |
Enumerated Values
| Property |
Value |
| name |
[accuracy, f1Score, falsePositiveRate, matthewsCorrelationCoefficient, negativePredictiveValue, positivePredictiveValue, trueNegativeRate, truePositiveRate] |
BacktestStabilityPlotData
{
"properties": {
"backtestIndex": {
"description": "An integer representing the index of the backtest, starting from 0. For holdout, this field will be null.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"partition": {
"description": "Identifier of the partition. Can either identify a specific backtest (\"backtest0\", \"backtest1\", ...) or the holdout set (\"holdout\").",
"type": "string"
},
"score": {
"description": "Score for this partition. Can be null if the score is unavailable for this partition (e.g. holdout is locked or backtesting has not been run yet).",
"type": [
"number",
"null"
]
},
"scoringEndDate": {
"description": "End date of the subset used for scoring.",
"format": "date-time",
"type": "string"
},
"scoringStartDate": {
"description": "Start date of the subset used for scoring.",
"format": "date-time",
"type": "string"
}
},
"required": [
"backtestIndex",
"partition",
"score",
"scoringEndDate",
"scoringStartDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestIndex |
integer,null |
true |
minimum: 0
|
An integer representing the index of the backtest, starting from 0. For holdout, this field will be null. |
| partition |
string |
true |
|
Identifier of the partition. Can either identify a specific backtest ("backtest0", "backtest1", ...) or the holdout set ("holdout"). |
| score |
number,null |
true |
|
Score for this partition. Can be null if the score is unavailable for this partition (e.g. holdout is locked or backtesting has not been run yet). |
| scoringEndDate |
string(date-time) |
true |
|
End date of the subset used for scoring. |
| scoringStartDate |
string(date-time) |
true |
|
Start date of the subset used for scoring. |
BacktestStabilityPlotResponse
{
"properties": {
"backtestPlotData": {
"description": "An array of objects containing the details of the scores for each partition defined for the project.",
"items": {
"properties": {
"backtestIndex": {
"description": "An integer representing the index of the backtest, starting from 0. For holdout, this field will be null.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"partition": {
"description": "Identifier of the partition. Can either identify a specific backtest (\"backtest0\", \"backtest1\", ...) or the holdout set (\"holdout\").",
"type": "string"
},
"score": {
"description": "Score for this partition. Can be null if the score is unavailable for this partition (e.g. holdout is locked or backtesting has not been run yet).",
"type": [
"number",
"null"
]
},
"scoringEndDate": {
"description": "End date of the subset used for scoring.",
"format": "date-time",
"type": "string"
},
"scoringStartDate": {
"description": "Start date of the subset used for scoring.",
"format": "date-time",
"type": "string"
}
},
"required": [
"backtestIndex",
"partition",
"score",
"scoringEndDate",
"scoringStartDate"
],
"type": "object"
},
"type": "array"
},
"endDate": {
"description": "End date of the project dataset.",
"format": "date-time",
"type": "string"
},
"metricName": {
"description": "Name of the metric used to compute the scores.",
"type": "string"
},
"startDate": {
"description": "Start date of the project dataset.",
"format": "date-time",
"type": "string"
}
},
"required": [
"backtestPlotData",
"endDate",
"metricName",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestPlotData |
[BacktestStabilityPlotData] |
true |
|
An array of objects containing the details of the scores for each partition defined for the project. |
| endDate |
string(date-time) |
true |
|
End date of the project dataset. |
| metricName |
string |
true |
|
Name of the metric used to compute the scores. |
| startDate |
string(date-time) |
true |
|
Start date of the project dataset. |
BiasVsAccuracyInsight
{
"properties": {
"accuracyMetric": {
"description": "The metric to return model accuracy scores. Defaults to the optimization metric configured in project options.",
"enum": [
"AUC",
"Weighted AUC",
"Area Under PR Curve",
"Weighted Area Under PR Curve",
"Kolmogorov-Smirnov",
"Weighted Kolmogorov-Smirnov",
"FVE Binomial",
"Weighted FVE Binomial",
"Gini Norm",
"Weighted Gini Norm",
"LogLoss",
"Weighted LogLoss",
"Max MCC",
"Weighted Max MCC",
"Rate@Top5%",
"Weighted Rate@Top5%",
"Rate@Top10%",
"Weighted Rate@Top10%",
"Rate@TopTenth%",
"RMSE",
"Weighted RMSE"
],
"type": "string"
},
"fairnessMetric": {
"description": "The fairness metric used to calculate the fairness scores.",
"oneOf": [
{
"enum": [
"proportionalParity",
"equalParity",
"favorableClassBalance",
"unfavorableClassBalance",
"trueUnfavorableRateParity",
"trueFavorableRateParity",
"favorablePredictiveValueParity",
"unfavorablePredictiveValueParity"
],
"type": "string"
},
{
"items": {
"enum": [
"proportionalParity",
"equalParity",
"favorableClassBalance",
"unfavorableClassBalance",
"trueUnfavorableRateParity",
"trueFavorableRateParity",
"favorablePredictiveValueParity",
"unfavorablePredictiveValueParity"
],
"type": "string"
},
"type": "array"
}
]
},
"fairnessThreshold": {
"default": 0.8,
"description": "Value of the fairness threshold, defined in project options.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"models": {
"description": "An array of models of the insight.",
"items": {
"properties": {
"accuracyValue": {
"description": "The model's accuracy score.",
"minimum": 0,
"type": "number"
},
"bp": {
"description": "The blueprint number of the model from the leaderboard.",
"exclusiveMinimum": 0,
"type": "integer"
},
"dsName": {
"description": "The name of the feature list used for model training.",
"type": "string"
},
"fairnessValue": {
"description": "The model's relative fairness score for the class with the lowest fairness score. In other words, the fairness score of the least privileged class.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"modelId": {
"description": "ID of the model.",
"type": "string"
},
"modelNumber": {
"description": "The model number from the Leaderboard.",
"exclusiveMinimum": 0,
"type": "integer"
},
"modelType": {
"description": "The type/name of the model.",
"type": "string"
},
"prime": {
"description": "Flag to indicate whether the model is a prime model.",
"type": "boolean"
},
"samplepct": {
"description": "The sample size percentage of the feature list data the model was trained on.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"accuracyValue",
"bp",
"dsName",
"fairnessValue",
"modelId",
"modelNumber",
"modelType",
"prime",
"samplepct"
],
"type": "object"
},
"type": "array"
},
"protectedFeature": {
"description": "Name of the protected feature.",
"oneOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
}
]
}
},
"required": [
"fairnessThreshold",
"models"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| accuracyMetric |
string |
false |
|
The metric to return model accuracy scores. Defaults to the optimization metric configured in project options. |
| fairnessMetric |
any |
false |
|
The fairness metric used to calculate the fairness scores. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
[string] |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| fairnessThreshold |
number |
true |
maximum: 1
minimum: 0
|
Value of the fairness threshold, defined in project options. |
| models |
[BiasVsAccuracyModels] |
true |
|
An array of models of the insight. |
| protectedFeature |
any |
false |
|
Name of the protected feature. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
[string] |
false |
|
none |
Enumerated Values
| Property |
Value |
| accuracyMetric |
[AUC, Weighted AUC, Area Under PR Curve, Weighted Area Under PR Curve, Kolmogorov-Smirnov, Weighted Kolmogorov-Smirnov, FVE Binomial, Weighted FVE Binomial, Gini Norm, Weighted Gini Norm, LogLoss, Weighted LogLoss, Max MCC, Weighted Max MCC, Rate@Top5%, Weighted Rate@Top5%, Rate@Top10%, Weighted Rate@Top10%, Rate@TopTenth%, RMSE, Weighted RMSE] |
| anonymous |
[proportionalParity, equalParity, favorableClassBalance, unfavorableClassBalance, trueUnfavorableRateParity, trueFavorableRateParity, favorablePredictiveValueParity, unfavorablePredictiveValueParity] |
BiasVsAccuracyInsightRetrieve
{
"properties": {
"data": {
"description": "An array of bias vs accuracy insights for the model.",
"items": {
"properties": {
"accuracyMetric": {
"description": "The metric to return model accuracy scores. Defaults to the optimization metric configured in project options.",
"enum": [
"AUC",
"Weighted AUC",
"Area Under PR Curve",
"Weighted Area Under PR Curve",
"Kolmogorov-Smirnov",
"Weighted Kolmogorov-Smirnov",
"FVE Binomial",
"Weighted FVE Binomial",
"Gini Norm",
"Weighted Gini Norm",
"LogLoss",
"Weighted LogLoss",
"Max MCC",
"Weighted Max MCC",
"Rate@Top5%",
"Weighted Rate@Top5%",
"Rate@Top10%",
"Weighted Rate@Top10%",
"Rate@TopTenth%",
"RMSE",
"Weighted RMSE"
],
"type": "string"
},
"fairnessMetric": {
"description": "The fairness metric used to calculate the fairness scores.",
"oneOf": [
{
"enum": [
"proportionalParity",
"equalParity",
"favorableClassBalance",
"unfavorableClassBalance",
"trueUnfavorableRateParity",
"trueFavorableRateParity",
"favorablePredictiveValueParity",
"unfavorablePredictiveValueParity"
],
"type": "string"
},
{
"items": {
"enum": [
"proportionalParity",
"equalParity",
"favorableClassBalance",
"unfavorableClassBalance",
"trueUnfavorableRateParity",
"trueFavorableRateParity",
"favorablePredictiveValueParity",
"unfavorablePredictiveValueParity"
],
"type": "string"
},
"type": "array"
}
]
},
"fairnessThreshold": {
"default": 0.8,
"description": "Value of the fairness threshold, defined in project options.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"models": {
"description": "An array of models of the insight.",
"items": {
"properties": {
"accuracyValue": {
"description": "The model's accuracy score.",
"minimum": 0,
"type": "number"
},
"bp": {
"description": "The blueprint number of the model from the leaderboard.",
"exclusiveMinimum": 0,
"type": "integer"
},
"dsName": {
"description": "The name of the feature list used for model training.",
"type": "string"
},
"fairnessValue": {
"description": "The model's relative fairness score for the class with the lowest fairness score. In other words, the fairness score of the least privileged class.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"modelId": {
"description": "ID of the model.",
"type": "string"
},
"modelNumber": {
"description": "The model number from the Leaderboard.",
"exclusiveMinimum": 0,
"type": "integer"
},
"modelType": {
"description": "The type/name of the model.",
"type": "string"
},
"prime": {
"description": "Flag to indicate whether the model is a prime model.",
"type": "boolean"
},
"samplepct": {
"description": "The sample size percentage of the feature list data the model was trained on.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"accuracyValue",
"bp",
"dsName",
"fairnessValue",
"modelId",
"modelNumber",
"modelType",
"prime",
"samplepct"
],
"type": "object"
},
"type": "array"
},
"protectedFeature": {
"description": "Name of the protected feature.",
"oneOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
}
]
}
},
"required": [
"fairnessThreshold",
"models"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
[BiasVsAccuracyInsight] |
true |
|
An array of bias vs accuracy insights for the model. |
BiasVsAccuracyModels
{
"properties": {
"accuracyValue": {
"description": "The model's accuracy score.",
"minimum": 0,
"type": "number"
},
"bp": {
"description": "The blueprint number of the model from the leaderboard.",
"exclusiveMinimum": 0,
"type": "integer"
},
"dsName": {
"description": "The name of the feature list used for model training.",
"type": "string"
},
"fairnessValue": {
"description": "The model's relative fairness score for the class with the lowest fairness score. In other words, the fairness score of the least privileged class.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"modelId": {
"description": "ID of the model.",
"type": "string"
},
"modelNumber": {
"description": "The model number from the Leaderboard.",
"exclusiveMinimum": 0,
"type": "integer"
},
"modelType": {
"description": "The type/name of the model.",
"type": "string"
},
"prime": {
"description": "Flag to indicate whether the model is a prime model.",
"type": "boolean"
},
"samplepct": {
"description": "The sample size percentage of the feature list data the model was trained on.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"accuracyValue",
"bp",
"dsName",
"fairnessValue",
"modelId",
"modelNumber",
"modelType",
"prime",
"samplepct"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| accuracyValue |
number |
true |
minimum: 0
|
The model's accuracy score. |
| bp |
integer |
true |
|
The blueprint number of the model from the leaderboard. |
| dsName |
string |
true |
|
The name of the feature list used for model training. |
| fairnessValue |
number,null |
true |
maximum: 1
minimum: 0
|
The model's relative fairness score for the class with the lowest fairness score. In other words, the fairness score of the least privileged class. |
| modelId |
string |
true |
|
ID of the model. |
| modelNumber |
integer |
true |
|
The model number from the Leaderboard. |
| modelType |
string |
true |
|
The type/name of the model. |
| prime |
boolean |
true |
|
Flag to indicate whether the model is a prime model. |
| samplepct |
number |
true |
maximum: 100
minimum: 0
|
The sample size percentage of the feature list data the model was trained on. |
BinResponse
{
"properties": {
"avgPredicted": {
"description": "Average prediction of the model in the bin. Null if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "ISO-formatted datetime of the end of the bin (exclusive).",
"format": "date-time",
"type": "string"
},
"frequency": {
"description": "Number of the rows in the bin.",
"type": "integer"
},
"maxPredicted": {
"description": "Maximum prediction of the model in the bin. Null if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "ISO-formatted datetime of the start of the bin (inclusive).",
"format": "date-time",
"type": "string"
}
},
"required": [
"avgPredicted",
"endDate",
"frequency",
"maxPredicted",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| avgPredicted |
number,null |
true |
|
Average prediction of the model in the bin. Null if there are no entries in the bin. |
| endDate |
string(date-time) |
true |
|
ISO-formatted datetime of the end of the bin (exclusive). |
| frequency |
integer |
true |
|
Number of the rows in the bin. |
| maxPredicted |
number,null |
true |
|
Maximum prediction of the model in the bin. Null if there are no entries in the bin. |
| startDate |
string(date-time) |
true |
|
ISO-formatted datetime of the start of the bin (inclusive). |
CalendarEvent
{
"properties": {
"date": {
"description": "The date of the calendar event.",
"format": "date-time",
"type": "string"
},
"name": {
"description": "Name of the calendar event.",
"type": "string"
},
"seriesId": {
"description": "The series ID for the event. If this event does not specify a series ID, then this will be `null`, indicating that the event applies to all series.",
"type": [
"string",
"null"
]
}
},
"required": [
"date",
"name",
"seriesId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| date |
string(date-time) |
true |
|
The date of the calendar event. |
| name |
string |
true |
|
Name of the calendar event. |
| seriesId |
string,null |
true |
|
The series ID for the event. If this event does not specify a series ID, then this will be null, indicating that the event applies to all series. |
Categorical
{
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"categoryLevelFrequencyPercent"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| allData |
PerValueStatistics |
true |
|
Statistics for all data for different feature values. |
| insightName |
string |
true |
|
Insight name. |
| perCluster |
[PerClusterCategorical] |
true |
|
Statistic values for different feature values in this cluster. |
Enumerated Values
| Property |
Value |
| insightName |
categoryLevelFrequencyPercent |
CategoricalFeature
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"categorical"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"categoryLevelFrequencyPercent"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureImpact |
number,null |
false |
|
Feature Impact score. |
| featureName |
string |
true |
|
Feature name. |
| featureType |
string |
true |
|
Feature Type. |
| insights |
[Categorical] |
true |
|
A list of Cluster Insights for a feature. |
Enumerated Values
| Property |
Value |
| featureType |
categorical |
ClusterInsightsPaginatedResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "A list of features with clusters insights.",
"items": {
"anyOf": [
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"image"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for an image feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"images",
"percentageOfMissingImages"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"representativeImages"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"clusterName",
"images",
"percentageOfMissingImages"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"geospatialPoint"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a geospatial centroid or point feature.",
"items": {
"properties": {
"insightName": {
"description": "Insight name.",
"enum": [
"representativeLocations"
],
"type": "string"
},
"perCluster": {
"description": "Statistic for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"maxLength": 50,
"minLength": 1,
"type": "string"
},
"representativeLocations": {
"description": "A list of latitude and longitude location list",
"items": {
"description": "Latitude and longitude list.",
"items": {
"description": "Longitude or latitude, in degrees.",
"maximum": 180,
"minimum": -180,
"type": "number"
},
"type": "array"
},
"maxItems": 1000,
"type": "array"
}
},
"required": [
"clusterName",
"representativeLocations"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"text"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"importantNgrams"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"numeric"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistic value for all data.",
"type": [
"number",
"null"
]
},
"insightName": {
"description": "Insight name.",
"enum": [
"min",
"max",
"median",
"avg",
"firstQuartile",
"thirdQuartile",
"missingRowsPercent"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for for each cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"statistic": {
"description": "Statistic value for this cluster.",
"type": [
"number",
"null"
]
}
},
"required": [
"clusterName",
"statistic"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"categorical"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"categoryLevelFrequencyPercent"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
},
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"document"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"importantNgrams"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
}
]
},
"maxItems": 100,
"type": "array"
},
"isCurrentClusterInsightVersion": {
"description": "If retrieved insights are current version.",
"type": "boolean"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
},
"version": {
"description": "Current version of the computed insight.",
"minimum": 0,
"type": "integer"
}
},
"required": [
"data",
"isCurrentClusterInsightVersion",
"next",
"previous",
"totalCount",
"version"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[anyOf] |
true |
maxItems: 100
|
A list of features with clusters insights. |
anyOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
ImageFeature |
false |
|
none |
or
or
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
TextFeature |
false |
|
none |
or
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
NumericFeature |
false |
|
none |
or
or
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
DocumentFeature |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| isCurrentClusterInsightVersion |
boolean |
true |
|
If retrieved insights are current version. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
| version |
integer |
true |
minimum: 0
|
Current version of the computed insight. |
ComputeFeatureEffectsRequest
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"training",
"backtest_0",
"backtest_1",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20",
"holdout",
"backtest_0_training",
"backtest_1_training",
"backtest_2_training",
"backtest_3_training",
"backtest_4_training",
"backtest_5_training",
"backtest_6_training",
"backtest_7_training",
"backtest_8_training",
"backtest_9_training",
"backtest_10_training",
"backtest_11_training",
"backtest_12_training",
"backtest_13_training",
"backtest_14_training",
"backtest_15_training",
"backtest_16_training",
"backtest_17_training",
"backtest_18_training",
"backtest_19_training",
"backtest_20_training",
"holdout_training"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| dataSliceId |
string |
false |
|
The ID of the data slice. |
| entityId |
string |
true |
|
The ID of the entity. |
| entityType |
string |
true |
|
The type of entity for which insights will be calculated. |
| externalDatasetId |
string |
false |
|
The ID of the external dataset. |
| source |
string |
true |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| entityType |
[datarobotModel, customModel, vectorDatabase] |
| source |
[validation, training, backtest_0, backtest_1, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20, holdout, backtest_0_training, backtest_1_training, backtest_2_training, backtest_3_training, backtest_4_training, backtest_5_training, backtest_6_training, backtest_7_training, backtest_8_training, backtest_9_training, backtest_10_training, backtest_11_training, backtest_12_training, backtest_13_training, backtest_14_training, backtest_15_training, backtest_16_training, backtest_17_training, backtest_18_training, backtest_19_training, backtest_20_training, holdout_training] |
ComputeFeatureImpactRequest
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"rowCount": {
"description": "The number of rows to use for calculating Feature Impact.",
"maximum": 100000,
"minimum": 10,
"type": "integer"
},
"source": {
"default": "training",
"description": "The subset of data used to compute the insight.",
"enum": [
"training",
"backtest_2_training",
"backtest_3_training",
"backtest_4_training",
"backtest_5_training",
"backtest_6_training",
"backtest_7_training",
"backtest_8_training",
"backtest_9_training",
"backtest_10_training",
"backtest_11_training",
"backtest_12_training",
"backtest_13_training",
"backtest_14_training",
"backtest_15_training",
"backtest_16_training",
"backtest_17_training",
"backtest_18_training",
"backtest_19_training",
"backtest_20_training",
"backtest_1_training",
"holdout_training"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"rowCount",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| dataSliceId |
string |
false |
|
The ID of the data slice. |
| entityId |
string |
true |
|
The ID of the entity. |
| entityType |
string |
true |
|
The type of entity for which insights will be calculated. |
| externalDatasetId |
string |
false |
|
The ID of the external dataset. |
| rowCount |
integer |
true |
maximum: 100000
minimum: 10
|
The number of rows to use for calculating Feature Impact. |
| source |
string |
true |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| entityType |
[datarobotModel, customModel, vectorDatabase] |
| source |
[training, backtest_2_training, backtest_3_training, backtest_4_training, backtest_5_training, backtest_6_training, backtest_7_training, backtest_8_training, backtest_9_training, backtest_10_training, backtest_11_training, backtest_12_training, backtest_13_training, backtest_14_training, backtest_15_training, backtest_16_training, backtest_17_training, backtest_18_training, backtest_19_training, backtest_20_training, backtest_1_training, holdout_training] |
ComputeInsightsResponse
{
"properties": {
"qid": {
"description": "The queue ID of the job that computes the insights request.",
"type": [
"integer",
"null"
]
}
},
"required": [
"qid"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| qid |
integer,null |
true |
|
The queue ID of the job that computes the insights request. |
ComputeLiftChartRequest
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| dataSliceId |
string |
false |
|
The ID of the data slice. |
| entityId |
string |
true |
|
The ID of the entity. |
| entityType |
string |
true |
|
The type of entity for which insights will be calculated. |
| externalDatasetId |
string |
false |
|
The ID of the external dataset. |
| source |
string |
true |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| entityType |
[datarobotModel, customModel, vectorDatabase] |
| source |
[validation, crossValidation, holdout, externalTestSet, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
ComputeResidualsRequest
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| dataSliceId |
string |
false |
|
The ID of the data slice. |
| entityId |
string |
true |
|
The ID of the entity. |
| entityType |
string |
true |
|
The type of entity for which insights will be calculated. |
| externalDatasetId |
string |
false |
|
The ID of the external dataset. |
| source |
string |
true |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| entityType |
[datarobotModel, customModel, vectorDatabase] |
| source |
[validation, crossValidation, holdout, externalTestSet] |
ComputeRocCurveRequest
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| dataSliceId |
string |
false |
|
The ID of the data slice. |
| entityId |
string |
true |
|
The ID of the entity. |
| entityType |
string |
true |
|
The type of entity for which insights will be calculated. |
| externalDatasetId |
string |
false |
|
The ID of the external dataset. |
| source |
string |
true |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| entityType |
[datarobotModel, customModel, vectorDatabase] |
| source |
[validation, crossValidation, holdout, externalTestSet, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
ComputeShapDistributionsRequest
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"quickCompute": {
"default": true,
"description": "(Deprecated) Limits the number of rows used from the selected source by default. Cannot be set to False for this insight.",
"type": "boolean"
},
"rowCount": {
"description": "(Deprecated) The number of rows to use for calculating SHAP Impact.",
"type": "integer",
"x-versiondeprecated": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object",
"x-versionadded": "v2.38"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| dataSliceId |
string |
false |
|
The ID of the data slice. |
| entityId |
string |
true |
|
The ID of the entity. |
| entityType |
string |
true |
|
The type of entity for which insights will be calculated. |
| externalDatasetId |
string |
false |
|
The ID of the external dataset. |
| quickCompute |
boolean |
false |
|
(Deprecated) Limits the number of rows used from the selected source by default. Cannot be set to False for this insight. |
| rowCount |
integer |
false |
|
(Deprecated) The number of rows to use for calculating SHAP Impact. |
| source |
string |
true |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| entityType |
[datarobotModel, customModel, vectorDatabase] |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, externalTestSet, holdout, holdout_training, training, validation] |
ComputeShapInsightsRequest
{
"properties": {
"dataSliceId": {
"description": "The ID of the data slice.",
"type": "string"
},
"entityId": {
"description": "The ID of the entity.",
"type": "string"
},
"entityType": {
"default": "datarobotModel",
"description": "The type of entity for which insights will be calculated.",
"enum": [
"datarobotModel",
"customModel",
"vectorDatabase"
],
"type": "string",
"x-versionadded": "v2.34"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": "string"
},
"quickCompute": {
"default": true,
"description": "When enabled, limits the number of rows used from the selected source by default. When disabled, all rows are used.",
"type": "boolean"
},
"rowCount": {
"description": "(Deprecated) The number of rows to use for calculating SHAP Impact.",
"type": "integer",
"x-versionadded": "v2.35",
"x-versiondeprecated": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string"
}
},
"required": [
"entityId",
"entityType",
"source"
],
"type": "object",
"x-versionadded": "v2.35"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| dataSliceId |
string |
false |
|
The ID of the data slice. |
| entityId |
string |
true |
|
The ID of the entity. |
| entityType |
string |
true |
|
The type of entity for which insights will be calculated. |
| externalDatasetId |
string |
false |
|
The ID of the external dataset. |
| quickCompute |
boolean |
false |
|
When enabled, limits the number of rows used from the selected source by default. When disabled, all rows are used. |
| rowCount |
integer |
false |
|
(Deprecated) The number of rows to use for calculating SHAP Impact. |
| source |
string |
true |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| entityType |
[datarobotModel, customModel, vectorDatabase] |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, externalTestSet, holdout, holdout_training, training, validation] |
ConfusionChartClassMatrix
{
"properties": {
"actualCount": {
"description": "number of times this class is seen in the validation data",
"type": "integer"
},
"className": {
"description": "name of the class",
"type": "string"
},
"confusionMatrixOneVsAll": {
"description": "2d array representing 2x2 one vs all matrix. This represents the True/False Negative/Positive rates as integer for each class. The data structure looks like: ``[ [ True Negative, False Positive ], [ False Negative, True Positive ] ]``",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"f1": {
"description": "F1 score",
"type": "number"
},
"precision": {
"description": "precision score",
"type": "number"
},
"predictedCount": {
"description": "number of times this class has been predicted for the validation data",
"type": "integer"
},
"recall": {
"description": "recall score",
"type": "number"
},
"wasActualPercentages": {
"description": "one vs all actual percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className`",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
},
"wasPredictedPercentages": {
"description": "one vs all predicted percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualCount",
"className",
"confusionMatrixOneVsAll",
"f1",
"precision",
"predictedCount",
"recall",
"wasActualPercentages",
"wasPredictedPercentages"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actualCount |
integer |
true |
|
number of times this class is seen in the validation data |
| className |
string |
true |
|
name of the class |
| confusionMatrixOneVsAll |
[array] |
true |
|
2d array representing 2x2 one vs all matrix. This represents the True/False Negative/Positive rates as integer for each class. The data structure looks like: [ [ True Negative, False Positive ], [ False Negative, True Positive ] ] |
| f1 |
number |
true |
|
F1 score |
| precision |
number |
true |
|
precision score |
| predictedCount |
integer |
true |
|
number of times this class has been predicted for the validation data |
| recall |
number |
true |
|
recall score |
| wasActualPercentages |
[ActualPercentages] |
true |
|
one vs all actual percentages in a format specified below |
| wasPredictedPercentages |
[PredictedPercentages] |
true |
|
one vs all predicted percentages in a format specified below |
ConfusionChartData
{
"description": "confusion chart data with the format below.",
"properties": {
"classMetrics": {
"description": "per-class information including one vs all scores in a format specified below",
"items": {
"properties": {
"actualCount": {
"description": "number of times this class is seen in the validation data",
"type": "integer"
},
"className": {
"description": "name of the class",
"type": "string"
},
"confusionMatrixOneVsAll": {
"description": "2d array representing 2x2 one vs all matrix. This represents the True/False Negative/Positive rates as integer for each class. The data structure looks like: ``[ [ True Negative, False Positive ], [ False Negative, True Positive ] ]``",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"f1": {
"description": "F1 score",
"type": "number"
},
"precision": {
"description": "precision score",
"type": "number"
},
"predictedCount": {
"description": "number of times this class has been predicted for the validation data",
"type": "integer"
},
"recall": {
"description": "recall score",
"type": "number"
},
"wasActualPercentages": {
"description": "one vs all actual percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className`",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
},
"wasPredictedPercentages": {
"description": "one vs all predicted percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualCount",
"className",
"confusionMatrixOneVsAll",
"f1",
"precision",
"predictedCount",
"recall",
"wasActualPercentages",
"wasPredictedPercentages"
],
"type": "object"
},
"type": "array"
},
"classes": {
"description": "class labels from the dataset, union of row classes & column classes. This field is deprecated as of v2.13. The rows and columns may have different class labels when using query parameters to retrieve a slice of the matrix; please use 'rowClasses' and 'colClasses' instead.",
"items": {
"type": "string"
},
"type": "array"
},
"colClasses": {
"description": "class labels on columns of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
},
"confusionMatrix": {
"description": "2d array of ints representing confusion matrix, aligned with `rowClasses` and 'colClasses'array. For confusionMatrix[A][B] we can get an integer that represents the number of times 'if class with index A was correct we have class with index B predicted' (if the orientation is 'actual').",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"rowClasses": {
"description": "class labels on rows of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"classMetrics",
"classes",
"colClasses",
"confusionMatrix",
"rowClasses"
],
"type": "object"
}
confusion chart data with the format below.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| classMetrics |
[ConfusionChartClassMatrix] |
true |
|
per-class information including one vs all scores in a format specified below |
| classes |
[string] |
true |
|
class labels from the dataset, union of row classes & column classes. This field is deprecated as of v2.13. The rows and columns may have different class labels when using query parameters to retrieve a slice of the matrix; please use 'rowClasses' and 'colClasses' instead. |
| colClasses |
[string] |
true |
|
class labels on columns of confusion matrix |
| confusionMatrix |
[array] |
true |
|
2d array of ints representing confusion matrix, aligned with rowClasses and 'colClasses'array. For confusionMatrix[A][B] we can get an integer that represents the number of times 'if class with index A was correct we have class with index B predicted' (if the orientation is 'actual'). |
| rowClasses |
[string] |
true |
|
class labels on rows of confusion matrix |
ConfusionChartForDatasetsListResponse
{
"properties": {
"count": {
"description": "Number of results returned on this page.",
"type": "integer"
},
"data": {
"description": "Confusion chart data with the in the same format as the response from [GET /api/v2/projects/{projectId}/models/{modelId}/confusionCharts/{source}/][get-apiv2projectsprojectidmodelsmodelidconfusionchartssource] with additional totalCount field.",
"items": {
"properties": {
"columns": {
"description": "[colStart, colEnd] column dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"data": {
"description": "confusion chart data with the format below.",
"properties": {
"classMetrics": {
"description": "per-class information including one vs all scores in a format specified below",
"items": {
"properties": {
"actualCount": {
"description": "number of times this class is seen in the validation data",
"type": "integer"
},
"className": {
"description": "name of the class",
"type": "string"
},
"confusionMatrixOneVsAll": {
"description": "2d array representing 2x2 one vs all matrix. This represents the True/False Negative/Positive rates as integer for each class. The data structure looks like: ``[ [ True Negative, False Positive ], [ False Negative, True Positive ] ]``",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"f1": {
"description": "F1 score",
"type": "number"
},
"precision": {
"description": "precision score",
"type": "number"
},
"predictedCount": {
"description": "number of times this class has been predicted for the validation data",
"type": "integer"
},
"recall": {
"description": "recall score",
"type": "number"
},
"wasActualPercentages": {
"description": "one vs all actual percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className`",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
},
"wasPredictedPercentages": {
"description": "one vs all predicted percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualCount",
"className",
"confusionMatrixOneVsAll",
"f1",
"precision",
"predictedCount",
"recall",
"wasActualPercentages",
"wasPredictedPercentages"
],
"type": "object"
},
"type": "array"
},
"classes": {
"description": "class labels from the dataset, union of row classes & column classes. This field is deprecated as of v2.13. The rows and columns may have different class labels when using query parameters to retrieve a slice of the matrix; please use 'rowClasses' and 'colClasses' instead.",
"items": {
"type": "string"
},
"type": "array"
},
"colClasses": {
"description": "class labels on columns of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
},
"confusionMatrix": {
"description": "2d array of ints representing confusion matrix, aligned with `rowClasses` and 'colClasses'array. For confusionMatrix[A][B] we can get an integer that represents the number of times 'if class with index A was correct we have class with index B predicted' (if the orientation is 'actual').",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"rowClasses": {
"description": "class labels on rows of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"classMetrics",
"classes",
"colClasses",
"confusionMatrix",
"rowClasses"
],
"type": "object"
},
"globalMetrics": {
"description": "average metrics across all classes",
"properties": {
"f1": {
"description": "Average F1 score",
"type": "number"
},
"precision": {
"description": "Average precision score",
"type": "number"
},
"recall": {
"description": "Avergae recall score",
"type": "number"
}
},
"required": [
"f1",
"precision",
"recall"
],
"type": "object"
},
"numberOfClasses": {
"description": "count of classes in full confusion matrix.",
"type": "integer"
},
"rows": {
"description": "[rowStart, rowEnd] row dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"source": {
"description": "source of the chart",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
},
"totalMatrixSum": {
"description": "sum of all values in full confusion matrix",
"type": "integer"
}
},
"required": [
"columns",
"data",
"globalMetrics",
"numberOfClasses",
"rows",
"source",
"totalMatrixSum"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "Total count of confusion charts for model.",
"type": "integer"
}
},
"required": [
"count",
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
Number of results returned on this page. |
| data |
[ModelConfusionChartRetrieveResponse] |
true |
|
Confusion chart data with the in the same format as the response from [GET /api/v2/projects/{projectId}/models/{modelId}/confusionCharts/{source}/][get-apiv2projectsprojectidmodelsmodelidconfusionchartssource] with additional totalCount field. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
Total count of confusion charts for model. |
ConfusionChartRetrieveForDatasets
{
"properties": {
"columns": {
"description": "[colStart, colEnd] column dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"data": {
"description": "confusion chart data with the format below.",
"properties": {
"classMetrics": {
"description": "per-class information including one vs all scores in a format specified below",
"items": {
"properties": {
"actualCount": {
"description": "number of times this class is seen in the validation data",
"type": "integer"
},
"className": {
"description": "name of the class",
"type": "string"
},
"confusionMatrixOneVsAll": {
"description": "2d array representing 2x2 one vs all matrix. This represents the True/False Negative/Positive rates as integer for each class. The data structure looks like: ``[ [ True Negative, False Positive ], [ False Negative, True Positive ] ]``",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"f1": {
"description": "F1 score",
"type": "number"
},
"precision": {
"description": "precision score",
"type": "number"
},
"predictedCount": {
"description": "number of times this class has been predicted for the validation data",
"type": "integer"
},
"recall": {
"description": "recall score",
"type": "number"
},
"wasActualPercentages": {
"description": "one vs all actual percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className`",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
},
"wasPredictedPercentages": {
"description": "one vs all predicted percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualCount",
"className",
"confusionMatrixOneVsAll",
"f1",
"precision",
"predictedCount",
"recall",
"wasActualPercentages",
"wasPredictedPercentages"
],
"type": "object"
},
"type": "array"
},
"classes": {
"description": "class labels from the dataset, union of row classes & column classes. This field is deprecated as of v2.13. The rows and columns may have different class labels when using query parameters to retrieve a slice of the matrix; please use 'rowClasses' and 'colClasses' instead.",
"items": {
"type": "string"
},
"type": "array"
},
"colClasses": {
"description": "class labels on columns of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
},
"confusionMatrix": {
"description": "2d array of ints representing confusion matrix, aligned with `rowClasses` and 'colClasses'array. For confusionMatrix[A][B] we can get an integer that represents the number of times 'if class with index A was correct we have class with index B predicted' (if the orientation is 'actual').",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"rowClasses": {
"description": "class labels on rows of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"classMetrics",
"classes",
"colClasses",
"confusionMatrix",
"rowClasses"
],
"type": "object"
},
"datasetId": {
"description": "The datasetId to retrieve a Confusion chart from.",
"type": "string"
},
"numberOfClasses": {
"description": "count of classes in full confusion matrix.",
"type": "integer"
},
"rows": {
"description": "[rowStart, rowEnd] row dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"totalMatrixSum": {
"description": "sum of all values in full confusion matrix",
"type": "integer"
}
},
"required": [
"columns",
"data",
"datasetId",
"numberOfClasses",
"rows",
"totalMatrixSum"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| columns |
[integer] |
true |
|
[colStart, colEnd] column dimension of confusion matrix in response |
| data |
ConfusionChartData |
true |
|
confusion chart data with the format below. |
| datasetId |
string |
true |
|
The datasetId to retrieve a Confusion chart from. |
| numberOfClasses |
integer |
true |
|
count of classes in full confusion matrix. |
| rows |
[integer] |
true |
|
[rowStart, rowEnd] row dimension of confusion matrix in response |
| totalMatrixSum |
integer |
true |
|
sum of all values in full confusion matrix |
{
"properties": {
"classNames": {
"description": "list of all class names in the full confusion matrix, sorted by the `orderBy` parameter.",
"items": {
"type": "string"
},
"type": "array"
},
"datasetId": {
"description": "The dataset to retrieve a Confusion chart from.",
"type": "string"
},
"modelId": {
"description": "The model to retrieve a Confusion chart from.",
"type": "string"
},
"projectId": {
"description": "The project to retrieve a Confusion chart from.",
"type": "string"
},
"relevantClassesPositions": {
"description": "Matrix to highlight important cell blocks in the confusion chart. Intended to represent a thumbnail view, where the relevantClassesPositions array has a 1 in thumbnail cells that are of interest, and 0 otherwise. The dimensions of the implied thumbnail will not match those of the confusion matrix, e.g. a twenty-class confusion matrix may have a 2x2 thumbnail.",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"totalMatrixSum": {
"description": "Sum of all values in the full confusion matrix (equal to the number of points considered).",
"type": "integer"
}
},
"required": [
"classNames",
"datasetId",
"modelId",
"projectId",
"relevantClassesPositions",
"totalMatrixSum"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| classNames |
[string] |
true |
|
list of all class names in the full confusion matrix, sorted by the orderBy parameter. |
| datasetId |
string |
true |
|
The dataset to retrieve a Confusion chart from. |
| modelId |
string |
true |
|
The model to retrieve a Confusion chart from. |
| projectId |
string |
true |
|
The project to retrieve a Confusion chart from. |
| relevantClassesPositions |
[array] |
true |
|
Matrix to highlight important cell blocks in the confusion chart. Intended to represent a thumbnail view, where the relevantClassesPositions array has a 1 in thumbnail cells that are of interest, and 0 otherwise. The dimensions of the implied thumbnail will not match those of the confusion matrix, e.g. a twenty-class confusion matrix may have a 2x2 thumbnail. |
| totalMatrixSum |
integer |
true |
|
Sum of all values in the full confusion matrix (equal to the number of points considered). |
CreateRatingTableModel
{
"properties": {
"ratingTableId": {
"description": "the rating table ID to use to create a new model",
"type": "string"
}
},
"required": [
"ratingTableId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| ratingTableId |
string |
true |
|
the rating table ID to use to create a new model |
CreateShapMatrixPayload
{
"properties": {
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"modelId": {
"description": "The model ID.",
"type": "string"
}
},
"required": [
"datasetId",
"modelId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| datasetId |
string |
true |
|
The dataset ID. |
| modelId |
string |
true |
|
The model ID. |
CrossClassAccuracy
{
"properties": {
"feature": {
"description": "The name of the categorical feature.",
"type": "string"
},
"modelId": {
"description": "ID of the model for the cross-class accuracy scores.",
"type": "string"
},
"perClassAccuracyScores": {
"description": "An array of metric scores for each class of the feature.",
"items": {
"properties": {
"className": {
"description": "The name of the class value for the categorical feature.",
"type": "string"
},
"metrics": {
"description": "An array of metric scores.",
"items": {
"properties": {
"metric": {
"description": "The name of the metric.",
"enum": [
"AUC",
"Weighted AUC",
"Area Under PR Curve",
"Weighted Area Under PR Curve",
"Kolmogorov-Smirnov",
"Weighted Kolmogorov-Smirnov",
"FVE Binomial",
"Weighted FVE Binomial",
"Gini Norm",
"Weighted Gini Norm",
"LogLoss",
"Weighted LogLoss",
"Max MCC",
"Weighted Max MCC",
"Rate@Top5%",
"Weighted Rate@Top5%",
"Rate@Top10%",
"Weighted Rate@Top10%",
"Rate@TopTenth%",
"RMSE",
"Weighted RMSE",
"f1",
"accuracy"
],
"type": "string"
},
"value": {
"description": "The calculated score of the metric.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"metric",
"value"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"className",
"metrics"
],
"type": "object"
},
"type": "array"
},
"predictionThreshold": {
"description": "Value of the prediction threshold for the model.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"feature",
"modelId",
"perClassAccuracyScores",
"predictionThreshold"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| feature |
string |
true |
|
The name of the categorical feature. |
| modelId |
string |
true |
|
ID of the model for the cross-class accuracy scores. |
| perClassAccuracyScores |
[PerClassAccuracy] |
true |
|
An array of metric scores for each class of the feature. |
| predictionThreshold |
number |
true |
maximum: 1
minimum: 0
|
Value of the prediction threshold for the model. |
CrossClassAccuracyCreateResponse
{
"properties": {
"statusId": {
"description": "The ID of the status object.",
"type": "string"
}
},
"required": [
"statusId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| statusId |
string |
true |
|
The ID of the status object. |
CrossClassAccuracyList
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "An array of cross-class accuracy scores for the model.",
"items": {
"properties": {
"feature": {
"description": "The name of the categorical feature.",
"type": "string"
},
"modelId": {
"description": "ID of the model for the cross-class accuracy scores.",
"type": "string"
},
"perClassAccuracyScores": {
"description": "An array of metric scores for each class of the feature.",
"items": {
"properties": {
"className": {
"description": "The name of the class value for the categorical feature.",
"type": "string"
},
"metrics": {
"description": "An array of metric scores.",
"items": {
"properties": {
"metric": {
"description": "The name of the metric.",
"enum": [
"AUC",
"Weighted AUC",
"Area Under PR Curve",
"Weighted Area Under PR Curve",
"Kolmogorov-Smirnov",
"Weighted Kolmogorov-Smirnov",
"FVE Binomial",
"Weighted FVE Binomial",
"Gini Norm",
"Weighted Gini Norm",
"LogLoss",
"Weighted LogLoss",
"Max MCC",
"Weighted Max MCC",
"Rate@Top5%",
"Weighted Rate@Top5%",
"Rate@Top10%",
"Weighted Rate@Top10%",
"Rate@TopTenth%",
"RMSE",
"Weighted RMSE",
"f1",
"accuracy"
],
"type": "string"
},
"value": {
"description": "The calculated score of the metric.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"metric",
"value"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"className",
"metrics"
],
"type": "object"
},
"type": "array"
},
"predictionThreshold": {
"description": "Value of the prediction threshold for the model.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"feature",
"modelId",
"perClassAccuracyScores",
"predictionThreshold"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[CrossClassAccuracy] |
true |
|
An array of cross-class accuracy scores for the model. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
DataDisparityCreatePayload
{
"properties": {
"comparedClassNames": {
"description": "An array of classes to calculate data disparity for.",
"items": {
"type": "string"
},
"maxItems": 2,
"minItems": 2,
"type": "array"
},
"feature": {
"description": "Feature for which insight is computed.",
"type": "string"
}
},
"required": [
"comparedClassNames",
"feature"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| comparedClassNames |
[string] |
true |
maxItems: 2
minItems: 2
|
An array of classes to calculate data disparity for. |
| feature |
string |
true |
|
Feature for which insight is computed. |
DataDisparityCreateResponse
{
"properties": {
"statusId": {
"description": "The ID of the status object.",
"type": "string"
}
},
"required": [
"statusId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| statusId |
string |
true |
|
The ID of the status object. |
DataDisparityInsights
{
"description": "Computed data disparity insights if available.",
"properties": {
"features": {
"description": "A mapping of the feature name to the corresponding values on the graph.",
"items": {
"properties": {
"detailsHistogram": {
"description": "Histogram details for the specified feature.",
"items": {
"properties": {
"bars": {
"description": "Class details for the histogram chart",
"items": {
"properties": {
"label": {
"description": "Name of the class.",
"type": "string"
},
"value": {
"description": "Ratio of occurrence of the class.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
},
"bin": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
],
"description": "Label for the bin grouping"
}
},
"required": [
"bars",
"bin"
],
"type": "object"
},
"type": "array"
},
"disparityScore": {
"description": "A number to describe disparity for the feature between the compared classes.",
"type": "number"
},
"featureImpact": {
"description": "A feature importance value.",
"type": "number"
},
"name": {
"description": "Name of the feature.",
"type": "string"
},
"status": {
"description": "A status of the feature.",
"enum": [
"Healthy",
"At Risk",
"Failing"
],
"type": "string"
}
},
"required": [
"detailsHistogram",
"disparityScore",
"featureImpact",
"name",
"status"
],
"type": "object"
},
"type": "array"
},
"metric": {
"description": "Metric used to calculate the impact of a feature on data disparity.",
"type": "string"
},
"protectedFeature": {
"description": "Feature for which insights were computed.",
"type": "string"
},
"values": {
"description": "Class count details for each class being compared.",
"items": {
"description": "Number of occurrences of each class being compared.",
"properties": {
"count": {
"description": "Number of times the class was encountered.",
"type": "integer"
},
"label": {
"description": "Name of the class.",
"type": "string"
}
},
"required": [
"count",
"label"
],
"type": "object"
},
"type": "array"
}
},
"type": "object"
}
Computed data disparity insights if available.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| features |
[AnalyzedFeature] |
false |
|
A mapping of the feature name to the corresponding values on the graph. |
| metric |
string |
false |
|
Metric used to calculate the impact of a feature on data disparity. |
| protectedFeature |
string |
false |
|
Feature for which insights were computed. |
| values |
[FeatureCounts] |
false |
|
Class count details for each class being compared. |
DataDisparityRetrieveResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "Computed data disparity insights if available.",
"properties": {
"features": {
"description": "A mapping of the feature name to the corresponding values on the graph.",
"items": {
"properties": {
"detailsHistogram": {
"description": "Histogram details for the specified feature.",
"items": {
"properties": {
"bars": {
"description": "Class details for the histogram chart",
"items": {
"properties": {
"label": {
"description": "Name of the class.",
"type": "string"
},
"value": {
"description": "Ratio of occurrence of the class.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
},
"bin": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
],
"description": "Label for the bin grouping"
}
},
"required": [
"bars",
"bin"
],
"type": "object"
},
"type": "array"
},
"disparityScore": {
"description": "A number to describe disparity for the feature between the compared classes.",
"type": "number"
},
"featureImpact": {
"description": "A feature importance value.",
"type": "number"
},
"name": {
"description": "Name of the feature.",
"type": "string"
},
"status": {
"description": "A status of the feature.",
"enum": [
"Healthy",
"At Risk",
"Failing"
],
"type": "string"
}
},
"required": [
"detailsHistogram",
"disparityScore",
"featureImpact",
"name",
"status"
],
"type": "object"
},
"type": "array"
},
"metric": {
"description": "Metric used to calculate the impact of a feature on data disparity.",
"type": "string"
},
"protectedFeature": {
"description": "Feature for which insights were computed.",
"type": "string"
},
"values": {
"description": "Class count details for each class being compared.",
"items": {
"description": "Number of occurrences of each class being compared.",
"properties": {
"count": {
"description": "Number of times the class was encountered.",
"type": "integer"
},
"label": {
"description": "Name of the class.",
"type": "string"
}
},
"required": [
"count",
"label"
],
"type": "object"
},
"type": "array"
}
},
"type": "object"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
DataDisparityInsights |
true |
|
Computed data disparity insights if available. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
DataPointResponse
{
"properties": {
"prediction": {
"description": "The output of the model for this row.",
"type": "number"
},
"shapExplanation": {
"description": "Either ``null`` or an array of up to 10 `ShapleyFeatureContribution` objects. Only rows with the highest anomaly scores have Shapley explanations calculated.",
"items": {
"properties": {
"feature": {
"description": "Feature name",
"type": "string"
},
"featureValue": {
"description": "Feature value for this row. First 50 characters are returned.",
"type": "string"
},
"strength": {
"description": "Shapley value for this feature and row.",
"type": "number"
}
},
"required": [
"feature",
"featureValue",
"strength"
],
"type": "object"
},
"type": "array"
},
"timestamp": {
"description": "ISO-formatted timestamp for the row.",
"format": "date-time",
"type": "string"
}
},
"required": [
"prediction",
"shapExplanation",
"timestamp"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| prediction |
number |
true |
|
The output of the model for this row. |
| shapExplanation |
[ShapExplanationResponse] |
true |
|
Either null or an array of up to 10 ShapleyFeatureContribution objects. Only rows with the highest anomaly scores have Shapley explanations calculated. |
| timestamp |
string(date-time) |
true |
|
ISO-formatted timestamp for the row. |
DataSliceComputeSubsetSizeRequest
{
"properties": {
"externalDatasetId": {
"description": "The external dataset ID to use when calculating the size of a slice. Use this parameter only when the source is 'externalTestSet'.",
"type": [
"string",
"null"
]
},
"modelId": {
"description": "The model ID whose training dataset should be sliced. Use this parameter only when the source is 'training'.",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"source": {
"description": "The source of data to use to calculate the size.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"crossValidation",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation",
"vectorDatabase"
],
"type": "string"
}
},
"required": [
"projectId",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| externalDatasetId |
string,null |
false |
|
The external dataset ID to use when calculating the size of a slice. Use this parameter only when the source is 'externalTestSet'. |
| modelId |
string,null |
false |
|
The model ID whose training dataset should be sliced. Use this parameter only when the source is 'training'. |
| projectId |
string |
true |
|
The project ID. |
| source |
string |
true |
|
The source of data to use to calculate the size. |
Enumerated Values
| Property |
Value |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, crossValidation, externalTestSet, holdout, holdout_training, training, validation, vectorDatabase] |
DataSliceIndividualResponse
{
"properties": {
"filters": {
"description": "List of filters the data slice is composed of.",
"items": {
"properties": {
"operand": {
"description": "Feature to apply operation to.",
"type": "string"
},
"operator": {
"description": "Operator to apply to the named operand in the dataset. The operator 'eq' mean 'equals the single specified value'. The operator 'in' means 'is one of a list of allowed values.'",
"enum": [
"eq",
"in",
"<",
">",
"between",
"notBetween"
],
"type": "string"
},
"values": {
"description": "Values to filter the operand by with the given operator.",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
}
]
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"required": [
"operand",
"operator",
"values"
],
"type": "object"
},
"maxItems": 3,
"minItems": 1,
"type": "array"
},
"id": {
"description": "ID of the data slice.",
"type": "string"
},
"name": {
"description": "User provided name for the data slice.",
"maxLength": 500,
"minLength": 1,
"type": "string"
},
"projectId": {
"description": "The project ID.",
"type": "string"
}
},
"required": [
"filters",
"id",
"name",
"projectId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| filters |
[FilterDataSlices] |
true |
maxItems: 3
minItems: 1
|
List of filters the data slice is composed of. |
| id |
string |
true |
|
ID of the data slice. |
| name |
string |
true |
maxLength: 500
minLength: 1
minLength: 1
|
User provided name for the data slice. |
| projectId |
string |
true |
|
The project ID. |
DataSliceMessage
{
"properties": {
"additionalInfo": {
"description": "Additional details about this message.",
"type": "string"
},
"description": {
"description": "Short summary description about this message.",
"type": "string"
},
"level": {
"description": "Message level.",
"enum": [
"CRITICAL",
"INFORMATIONAL",
"WARNING"
],
"type": "string"
}
},
"required": [
"additionalInfo",
"description",
"level"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| additionalInfo |
string |
true |
|
Additional details about this message. |
| description |
string |
true |
|
Short summary description about this message. |
| level |
string |
true |
|
Message level. |
Enumerated Values
| Property |
Value |
| level |
[CRITICAL, INFORMATIONAL, WARNING] |
DataSliceRetrieveSubsetSizeResponse
{
"properties": {
"dataSliceId": {
"description": "ID of the data slice.",
"type": "string"
},
"externalDatasetId": {
"description": "The external dataset ID to use when calculating the size of a slice. Use this parameter only when the source is 'externalTestSet'.",
"type": [
"string",
"null"
]
},
"messages": {
"description": "List of user-relevant messages related to a Data Slice.",
"items": {
"properties": {
"additionalInfo": {
"description": "Additional details about this message.",
"type": "string"
},
"description": {
"description": "Short summary description about this message.",
"type": "string"
},
"level": {
"description": "Message level.",
"enum": [
"CRITICAL",
"INFORMATIONAL",
"WARNING"
],
"type": "string"
}
},
"required": [
"additionalInfo",
"description",
"level"
],
"type": "object"
},
"maxItems": 100,
"type": "array"
},
"modelId": {
"description": "The model ID whose training dataset should be sliced. Use this parameter only when the source is 'training'.",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"sliceSize": {
"description": "Number of rows in the slice for the given source.",
"minimum": 0,
"type": "integer"
},
"source": {
"description": "The source of data to use to calculate the size.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"crossValidation",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation",
"vectorDatabase"
],
"type": "string"
}
},
"required": [
"dataSliceId",
"messages",
"projectId",
"sliceSize",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| dataSliceId |
string |
true |
|
ID of the data slice. |
| externalDatasetId |
string,null |
false |
|
The external dataset ID to use when calculating the size of a slice. Use this parameter only when the source is 'externalTestSet'. |
| messages |
[DataSliceMessage] |
true |
maxItems: 100
|
List of user-relevant messages related to a Data Slice. |
| modelId |
string,null |
false |
|
The model ID whose training dataset should be sliced. Use this parameter only when the source is 'training'. |
| projectId |
string |
true |
|
The project ID. |
| sliceSize |
integer |
true |
minimum: 0
|
Number of rows in the slice for the given source. |
| source |
string |
true |
|
The source of data to use to calculate the size. |
Enumerated Values
| Property |
Value |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, crossValidation, externalTestSet, holdout, holdout_training, training, validation, vectorDatabase] |
DataSlicesBulkDeleteRequest
{
"properties": {
"ids": {
"description": "List of data slices to remove.",
"items": {
"type": "string"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
}
},
"required": [
"ids"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| ids |
[string] |
true |
maxItems: 20
minItems: 1
|
List of data slices to remove. |
DataSlicesCreationRequest
{
"properties": {
"filters": {
"description": "List of filters the data slice is composed of.",
"items": {
"properties": {
"operand": {
"description": "Feature to apply operation to.",
"type": "string"
},
"operator": {
"description": "Operator to apply to the named operand in the dataset. The operator 'eq' mean 'equals the single specified value'. The operator 'in' means 'is one of a list of allowed values.'",
"enum": [
"eq",
"in",
"<",
">",
"between",
"notBetween"
],
"type": "string"
},
"values": {
"description": "Values to filter the operand by with the given operator.",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
}
]
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"required": [
"operand",
"operator",
"values"
],
"type": "object"
},
"maxItems": 3,
"minItems": 1,
"type": "array"
},
"name": {
"description": "User provided name for the data slice.",
"maxLength": 500,
"minLength": 1,
"type": "string"
},
"projectId": {
"description": "The project ID.",
"type": "string"
}
},
"required": [
"filters",
"name",
"projectId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| filters |
[FilterDataSlices] |
true |
maxItems: 3
minItems: 1
|
List of filters the data slice is composed of. |
| name |
string |
true |
maxLength: 500
minLength: 1
minLength: 1
|
User provided name for the data slice. |
| projectId |
string |
true |
|
The project ID. |
DataSlicesListAllSlicesResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated Data Slices.",
"items": {
"properties": {
"filters": {
"description": "List of filters the data slice is composed of.",
"items": {
"properties": {
"operand": {
"description": "Feature to apply operation to.",
"type": "string"
},
"operator": {
"description": "Operator to apply to the named operand in the dataset. The operator 'eq' mean 'equals the single specified value'. The operator 'in' means 'is one of a list of allowed values.'",
"enum": [
"eq",
"in",
"<",
">",
"between",
"notBetween"
],
"type": "string"
},
"values": {
"description": "Values to filter the operand by with the given operator.",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
}
]
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"required": [
"operand",
"operator",
"values"
],
"type": "object"
},
"maxItems": 3,
"minItems": 1,
"type": "array"
},
"id": {
"description": "ID of the data slice.",
"type": "string"
},
"name": {
"description": "User provided name for the data slice.",
"maxLength": 500,
"minLength": 1,
"type": "string"
},
"projectId": {
"description": "The project ID.",
"type": "string"
}
},
"required": [
"filters",
"id",
"name",
"projectId"
],
"type": "object"
},
"maxItems": 100,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[DataSliceIndividualResponse] |
true |
maxItems: 100
|
List of paginated Data Slices. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
{
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
}
Metadata for backtest/holdout.
Properties
DatetimeTrendPlotsCreate
{
"properties": {
"backtest": {
"default": 0,
"description": "Compute plots for a specific backtest (use the backtest index starting from zero) or `holdout`. If not specified the first backtest (backtest index 0) will be used.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
]
},
"forecastDistanceEnd": {
"description": "The end of forecast distance range (forecast window) to compute. If not specified, the last forecast distance for this project will be used. Forecast distance specifies the number of time steps between the predicted point and the origin point. Only available for time series supervised projects.",
"minimum": 0,
"type": "integer"
},
"forecastDistanceStart": {
"description": "The start of forecast distance range (forecast window) to compute. If not specified, the first forecast distance for this project will be used. Forecast distance specifies the number of time steps between the predicted point and the origin point. Only available for time series supervised projects.",
"minimum": 0,
"type": "integer"
},
"fullAverage": {
"default": false,
"description": "Whether to compute an average plot for all series. Only available for time series multiseries projects.",
"type": "boolean",
"x-versionadded": "2.28"
},
"seriesIds": {
"description": "Only available for time series multiseries projects. Each element should be a name of a single series in a multiseries project. It is possible to compute a maximum of 1000 series per one request. If not specified the first 1000 series in alphabetical order will be computed. It is not possible to specify `fullAverage: true` while also setting `seriesIds`. This parameter can only be specified after first 1000 series in alphabetical order are computed.",
"items": {
"type": "string"
},
"maxItems": 1000,
"minItems": 1,
"type": "array",
"x-versionadded": "2.28"
},
"source": {
"default": "validation",
"description": "The source of the data for the backtest/holdout.",
"enum": [
"training",
"validation"
],
"type": "string"
}
},
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtest |
any |
false |
|
Compute plots for a specific backtest (use the backtest index starting from zero) or holdout. If not specified the first backtest (backtest index 0) will be used. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
maximum: 19
minimum: 0
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| forecastDistanceEnd |
integer |
false |
minimum: 0
|
The end of forecast distance range (forecast window) to compute. If not specified, the last forecast distance for this project will be used. Forecast distance specifies the number of time steps between the predicted point and the origin point. Only available for time series supervised projects. |
| forecastDistanceStart |
integer |
false |
minimum: 0
|
The start of forecast distance range (forecast window) to compute. If not specified, the first forecast distance for this project will be used. Forecast distance specifies the number of time steps between the predicted point and the origin point. Only available for time series supervised projects. |
| fullAverage |
boolean |
false |
|
Whether to compute an average plot for all series. Only available for time series multiseries projects. |
| seriesIds |
[string] |
false |
maxItems: 1000
minItems: 1
|
Only available for time series multiseries projects. Each element should be a name of a single series in a multiseries project. It is possible to compute a maximum of 1000 series per one request. If not specified the first 1000 series in alphabetical order will be computed. It is not possible to specify fullAverage: true while also setting seriesIds. This parameter can only be specified after first 1000 series in alphabetical order are computed. |
| source |
string |
false |
|
The source of the data for the backtest/holdout. |
Enumerated Values
| Property |
Value |
| anonymous |
holdout |
| source |
[training, validation] |
{
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
Start and end dates for the backtest/holdout training.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| endDate |
string,null(date-time) |
true |
|
The datetime of the end of the chart data (exclusive). Null if chart data is not computed. |
| startDate |
string,null(date-time) |
true |
|
The datetime of the start of the chart data (inclusive). Null if chart data is not computed. |
DatetimeTrendPlotsPreviewBins
{
"properties": {
"actual": {
"description": "Average actual value of the target in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"predicted": {
"description": "Average prediction of the model in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"predicted",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actual |
number,null |
true |
|
Average actual value of the target in the bin. null if there are no entries in the bin. |
| endDate |
string(date-time) |
true |
|
The datetime of the end of the bin (exclusive). |
| predicted |
number,null |
true |
|
Average prediction of the model in the bin. null if there are no entries in the bin. |
| startDate |
string(date-time) |
true |
|
The datetime of the start of the bin (inclusive). |
DatetimeTrendPlotsPreviewResponse
{
"properties": {
"bins": {
"description": "An array of bins for the retrieved plots.",
"items": {
"properties": {
"actual": {
"description": "Average actual value of the target in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"predicted": {
"description": "Average prediction of the model in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"predicted",
"startDate"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). ",
"format": "date-time",
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"bins",
"endDate",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[DatetimeTrendPlotsPreviewBins] |
true |
maxItems: 1000
minItems: 1
|
An array of bins for the retrieved plots. |
| endDate |
string(date-time) |
true |
|
The datetime of the end of the chart data (exclusive). |
| startDate |
string(date-time) |
true |
|
The datetime of the start of the chart data (inclusive). |
DatetimeTrendPlotsResponse
{
"properties": {
"message": {
"description": "Any extended message to include about the result. For example, if a job is submitted that is a duplicate of a job that has already been added to the queue, the message will mention that no new job can be created.",
"type": "string"
}
},
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| message |
string |
false |
|
Any extended message to include about the result. For example, if a job is submitted that is a duplicate of a job that has already been added to the queue, the message will mention that no new job can be created. |
DocumentFeature
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"document"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"importantNgrams"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureImpact |
number,null |
false |
|
Feature Impact score. |
| featureName |
string |
true |
|
Feature name. |
| featureType |
string |
true |
|
Feature Type. |
| insights |
[Text] |
true |
|
A list of Cluster Insights for a feature. |
Enumerated Values
| Property |
Value |
| featureType |
document |
Empty
Properties
None
ExternalScoresCreate
{
"properties": {
"actualValueColumn": {
"description": "Actual value column name that contains actual values to be used for computing scores and insights for unsupervised projects only. This value can be set once for a dataset and cannot be changed.",
"type": "string"
},
"datasetId": {
"description": "The dataset to compute predictions for - must have previously been uploaded.",
"type": "string"
},
"modelId": {
"description": "The model to use to make predictions.",
"type": "string"
}
},
"required": [
"datasetId",
"modelId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actualValueColumn |
string |
false |
|
Actual value column name that contains actual values to be used for computing scores and insights for unsupervised projects only. This value can be set once for a dataset and cannot be changed. |
| datasetId |
string |
true |
|
The dataset to compute predictions for - must have previously been uploaded. |
| modelId |
string |
true |
|
The model to use to make predictions. |
ExternalScoresListData
{
"properties": {
"actualValueColumn": {
"description": "The name of the column with actuals that was used to calculate the scores.",
"type": "string"
},
"datasetId": {
"description": "The datasetId the data comes from.",
"type": "string"
},
"modelId": {
"description": "The modelId for the scores.",
"type": "string"
},
"projectId": {
"description": "The projectId for the scores.",
"type": "string"
},
"scores": {
"description": "A json array of the computed scores.",
"items": {
"properties": {
"label": {
"description": "The metric name, which was used to compute the score.",
"type": "string"
},
"value": {
"description": "The score value.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualValueColumn",
"datasetId",
"modelId",
"projectId",
"scores"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actualValueColumn |
string |
true |
|
The name of the column with actuals that was used to calculate the scores. |
| datasetId |
string |
true |
|
The datasetId the data comes from. |
| modelId |
string |
true |
|
The modelId for the scores. |
| projectId |
string |
true |
|
The projectId for the scores. |
| scores |
[ExternalScoresListDataScore] |
true |
|
A json array of the computed scores. |
ExternalScoresListDataScore
{
"properties": {
"label": {
"description": "The metric name, which was used to compute the score.",
"type": "string"
},
"value": {
"description": "The score value.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| label |
string |
true |
|
The metric name, which was used to compute the score. |
| value |
number |
true |
|
The score value. |
ExternalScoresListResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "The list of objects is containing following data.",
"items": {
"properties": {
"actualValueColumn": {
"description": "The name of the column with actuals that was used to calculate the scores.",
"type": "string"
},
"datasetId": {
"description": "The datasetId the data comes from.",
"type": "string"
},
"modelId": {
"description": "The modelId for the scores.",
"type": "string"
},
"projectId": {
"description": "The projectId for the scores.",
"type": "string"
},
"scores": {
"description": "A json array of the computed scores.",
"items": {
"properties": {
"label": {
"description": "The metric name, which was used to compute the score.",
"type": "string"
},
"value": {
"description": "The score value.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualValueColumn",
"datasetId",
"modelId",
"projectId",
"scores"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"type": [
"string",
"null"
]
}
},
"required": [
"count",
"data",
"next",
"previous"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
Number of items returned on this page. |
| data |
[ExternalScoresListData] |
true |
|
The list of objects is containing following data. |
| next |
string,null |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
FairnessInsight
{
"properties": {
"fairnessMetric": {
"description": "The fairness metric used to calculate the fairness scores.",
"enum": [
"proportionalParity",
"equalParity",
"favorableClassBalance",
"unfavorableClassBalance",
"trueUnfavorableRateParity",
"trueFavorableRateParity",
"favorablePredictiveValueParity",
"unfavorablePredictiveValueParity"
],
"type": "string"
},
"fairnessThreshold": {
"default": 0.8,
"description": "Value of the fairness threshold, defined in project options.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"modelId": {
"description": "ID of the model fairness was measured for.",
"type": "string"
},
"perClassFairness": {
"description": "An array of calculated fairness scores for each protected feature class.",
"items": {
"properties": {
"absoluteValue": {
"description": "Absolute fairness score for the class",
"minimum": 0,
"type": "number"
},
"className": {
"description": "Name of the protected class the score is calculated for.",
"type": "string"
},
"entriesCount": {
"description": "The number of entries of the class in the analysed data.",
"minimum": 0,
"type": "integer"
},
"isStatisticallySignificant": {
"description": "Flag to tell whether the score can be treated as statistically significant. In other words, whether we are confident enough with the score for this protected class.",
"type": "boolean"
},
"value": {
"description": "The relative fairness score for the class.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"absoluteValue",
"className",
"entriesCount",
"isStatisticallySignificant",
"value"
],
"type": "object"
},
"type": "array"
},
"predictionThreshold": {
"description": "Model's prediction threshold used when insight was calculated. ``null`` if prediction threshold is not required for the fairness metric calculations.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"protectedFeature": {
"description": "Name of the protected feature the fairness calculation is made for.",
"type": "string"
}
},
"required": [
"fairnessMetric",
"fairnessThreshold",
"modelId",
"perClassFairness",
"protectedFeature"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| fairnessMetric |
string |
true |
|
The fairness metric used to calculate the fairness scores. |
| fairnessThreshold |
number |
true |
maximum: 1
minimum: 0
|
Value of the fairness threshold, defined in project options. |
| modelId |
string |
true |
|
ID of the model fairness was measured for. |
| perClassFairness |
[PerClassFairness] |
true |
|
An array of calculated fairness scores for each protected feature class. |
| predictionThreshold |
number |
false |
maximum: 1
minimum: 0
|
Model's prediction threshold used when insight was calculated. null if prediction threshold is not required for the fairness metric calculations. |
| protectedFeature |
string |
true |
|
Name of the protected feature the fairness calculation is made for. |
Enumerated Values
| Property |
Value |
| fairnessMetric |
[proportionalParity, equalParity, favorableClassBalance, unfavorableClassBalance, trueUnfavorableRateParity, trueFavorableRateParity, favorablePredictiveValueParity, unfavorablePredictiveValueParity] |
FairnessInsightsListResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "An array of fairness insights for the model.",
"items": {
"properties": {
"fairnessMetric": {
"description": "The fairness metric used to calculate the fairness scores.",
"enum": [
"proportionalParity",
"equalParity",
"favorableClassBalance",
"unfavorableClassBalance",
"trueUnfavorableRateParity",
"trueFavorableRateParity",
"favorablePredictiveValueParity",
"unfavorablePredictiveValueParity"
],
"type": "string"
},
"fairnessThreshold": {
"default": 0.8,
"description": "Value of the fairness threshold, defined in project options.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"modelId": {
"description": "ID of the model fairness was measured for.",
"type": "string"
},
"perClassFairness": {
"description": "An array of calculated fairness scores for each protected feature class.",
"items": {
"properties": {
"absoluteValue": {
"description": "Absolute fairness score for the class",
"minimum": 0,
"type": "number"
},
"className": {
"description": "Name of the protected class the score is calculated for.",
"type": "string"
},
"entriesCount": {
"description": "The number of entries of the class in the analysed data.",
"minimum": 0,
"type": "integer"
},
"isStatisticallySignificant": {
"description": "Flag to tell whether the score can be treated as statistically significant. In other words, whether we are confident enough with the score for this protected class.",
"type": "boolean"
},
"value": {
"description": "The relative fairness score for the class.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"absoluteValue",
"className",
"entriesCount",
"isStatisticallySignificant",
"value"
],
"type": "object"
},
"type": "array"
},
"predictionThreshold": {
"description": "Model's prediction threshold used when insight was calculated. ``null`` if prediction threshold is not required for the fairness metric calculations.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"protectedFeature": {
"description": "Name of the protected feature the fairness calculation is made for.",
"type": "string"
}
},
"required": [
"fairnessMetric",
"fairnessThreshold",
"modelId",
"perClassFairness",
"protectedFeature"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[FairnessInsight] |
true |
|
An array of fairness insights for the model. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
FairnessInsightsStartCalculationPayload
{
"properties": {
"fairnessMetricsSet": {
"description": "Metric to use for calculating fairness. Can be one of ``proportionalParity``, ``equalParity``, ``predictionBalance``, ``trueFavorableAndUnfavorableRateParity`` or ``FavorableAndUnfavorablePredictiveValueParity``. Used and required only if *Bias & Fairness in AutoML* feature is enabled.",
"enum": [
"proportionalParity",
"equalParity",
"predictionBalance",
"trueFavorableAndUnfavorableRateParity",
"favorableAndUnfavorablePredictiveValueParity"
],
"type": "string",
"x-versionadded": "v2.24"
}
},
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| fairnessMetricsSet |
string |
false |
|
Metric to use for calculating fairness. Can be one of proportionalParity, equalParity, predictionBalance, trueFavorableAndUnfavorableRateParity or FavorableAndUnfavorablePredictiveValueParity. Used and required only if Bias & Fairness in AutoML feature is enabled. |
Enumerated Values
| Property |
Value |
| fairnessMetricsSet |
[proportionalParity, equalParity, predictionBalance, trueFavorableAndUnfavorableRateParity, favorableAndUnfavorablePredictiveValueParity] |
FairnessInsightsStartCalculationResponse
{
"properties": {
"statusId": {
"description": "The ID of the status object.",
"type": "string"
}
},
"required": [
"statusId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| statusId |
string |
true |
|
The ID of the status object. |
FeatureAssociationCreatePayload
{
"properties": {
"featurelistId": {
"description": "A featurelist ID to calculate feature association matrix.",
"type": "string"
}
},
"required": [
"featurelistId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featurelistId |
string |
true |
|
A featurelist ID to calculate feature association matrix. |
FeatureAssociationDetailsRetrieveControllerResponse
{
"properties": {
"chartType": {
"description": "Which type of plotting the pair of features gets in the UI, e.g. `SCATTER`",
"type": "string"
},
"features": {
"description": "The name of `feature1` and `feature2`.",
"items": {
"type": "string"
},
"type": "array"
},
"types": {
"description": "The type of `feature1` and `feature2`. Possible values: `CATEGORICAL`, `NUMERIC`.",
"items": {
"enum": [
"CATEGORICAL",
"NUMERIC"
],
"type": "string"
},
"type": "array"
},
"values": {
"description": "The data triplets for pairwise plotting.",
"items": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
}
]
},
"type": "array"
},
"type": "array"
}
},
"required": [
"chartType",
"features",
"types",
"values"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| chartType |
string |
true |
|
Which type of plotting the pair of features gets in the UI, e.g. SCATTER |
| features |
[string] |
true |
|
The name of feature1 and feature2. |
| types |
[string] |
true |
|
The type of feature1 and feature2. Possible values: CATEGORICAL, NUMERIC. |
| values |
[array] |
true |
|
The data triplets for pairwise plotting. |
anyOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
or
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
number |
false |
|
none |
FeatureAssociationList
{
"properties": {
"featurelistId": {
"description": "The featurelist Id.",
"type": "string"
},
"hasFam": {
"description": "Whether Feature Association Matrix is calculated for featurelist.",
"type": "boolean"
},
"title": {
"description": "The name of featurelist.",
"type": "string"
}
},
"required": [
"featurelistId",
"hasFam",
"title"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featurelistId |
string |
true |
|
The featurelist Id. |
| hasFam |
boolean |
true |
|
Whether Feature Association Matrix is calculated for featurelist. |
| title |
string |
true |
|
The name of featurelist. |
FeatureAssociationListControllerResponse
{
"properties": {
"featurelists": {
"description": "List all featurelists with feature association matrix availability flags.",
"items": {
"properties": {
"featurelistId": {
"description": "The featurelist Id.",
"type": "string"
},
"hasFam": {
"description": "Whether Feature Association Matrix is calculated for featurelist.",
"type": "boolean"
},
"title": {
"description": "The name of featurelist.",
"type": "string"
}
},
"required": [
"featurelistId",
"hasFam",
"title"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featurelists"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featurelists |
[FeatureAssociationList] |
true |
|
List all featurelists with feature association matrix availability flags. |
FeatureAssociationRetrieveControllerResponse
{
"properties": {
"features": {
"description": "Metadata for each feature and where it goes in the matrix as structured below.",
"items": {
"properties": {
"alphabeticSortIndex": {
"description": "A number representing the alphabetical order of this feature compared to the other features in this dataset.",
"type": "integer"
},
"clusterId": {
"description": "ID of the cluster this feature belongs to.",
"type": [
"integer",
"null"
]
},
"clusterName": {
"description": "Name of feature cluster.",
"type": "string"
},
"clusterSortIndex": {
"description": "A number representing the ordering of the feature across all feature clusters. Features in the same cluster always have adjacent indices.",
"type": "integer"
},
"feature": {
"description": "Name of the feature.",
"type": "string"
},
"importanceSortIndex": {
"description": "A number ranking the importance of this feature compared to the other features in this dataset.",
"type": "integer"
},
"strengthSortIndex": {
"description": "A number ranking the strength of this feature compared to the other features in this dataset.",
"type": "integer"
}
},
"required": [
"alphabeticSortIndex",
"clusterId",
"clusterSortIndex",
"feature",
"importanceSortIndex",
"strengthSortIndex"
],
"type": "object"
},
"type": "array"
},
"strengths": {
"description": "Pairwise statistics for the available features as structured below.",
"items": {
"properties": {
"feature1": {
"description": "The name of the first feature.",
"type": "string"
},
"feature2": {
"description": "The name of the second feature.",
"type": "string"
},
"statistic": {
"description": "Feature association statistics for `feature1` and `feature2`. For features with no pairwise statistics available the value is `null`.",
"type": [
"number",
"null"
]
}
},
"required": [
"feature1",
"feature2",
"statistic"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"features",
"strengths"
],
"type": "object"
}
Properties
FeatureAssociationRetrieveFeatures
{
"properties": {
"alphabeticSortIndex": {
"description": "A number representing the alphabetical order of this feature compared to the other features in this dataset.",
"type": "integer"
},
"clusterId": {
"description": "ID of the cluster this feature belongs to.",
"type": [
"integer",
"null"
]
},
"clusterName": {
"description": "Name of feature cluster.",
"type": "string"
},
"clusterSortIndex": {
"description": "A number representing the ordering of the feature across all feature clusters. Features in the same cluster always have adjacent indices.",
"type": "integer"
},
"feature": {
"description": "Name of the feature.",
"type": "string"
},
"importanceSortIndex": {
"description": "A number ranking the importance of this feature compared to the other features in this dataset.",
"type": "integer"
},
"strengthSortIndex": {
"description": "A number ranking the strength of this feature compared to the other features in this dataset.",
"type": "integer"
}
},
"required": [
"alphabeticSortIndex",
"clusterId",
"clusterSortIndex",
"feature",
"importanceSortIndex",
"strengthSortIndex"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| alphabeticSortIndex |
integer |
true |
|
A number representing the alphabetical order of this feature compared to the other features in this dataset. |
| clusterId |
integer,null |
true |
|
ID of the cluster this feature belongs to. |
| clusterName |
string |
false |
|
Name of feature cluster. |
| clusterSortIndex |
integer |
true |
|
A number representing the ordering of the feature across all feature clusters. Features in the same cluster always have adjacent indices. |
| feature |
string |
true |
|
Name of the feature. |
| importanceSortIndex |
integer |
true |
|
A number ranking the importance of this feature compared to the other features in this dataset. |
| strengthSortIndex |
integer |
true |
|
A number ranking the strength of this feature compared to the other features in this dataset. |
FeatureAssociationRetrieveStrengths
{
"properties": {
"feature1": {
"description": "The name of the first feature.",
"type": "string"
},
"feature2": {
"description": "The name of the second feature.",
"type": "string"
},
"statistic": {
"description": "Feature association statistics for `feature1` and `feature2`. For features with no pairwise statistics available the value is `null`.",
"type": [
"number",
"null"
]
}
},
"required": [
"feature1",
"feature2",
"statistic"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| feature1 |
string |
true |
|
The name of the first feature. |
| feature2 |
string |
true |
|
The name of the second feature. |
| statistic |
number,null |
true |
|
Feature association statistics for feature1 and feature2. For features with no pairwise statistics available the value is null. |
FeatureCounts
{
"description": "Number of occurrences of each class being compared.",
"properties": {
"count": {
"description": "Number of times the class was encountered.",
"type": "integer"
},
"label": {
"description": "Name of the class.",
"type": "string"
}
},
"required": [
"count",
"label"
],
"type": "object"
}
Number of occurrences of each class being compared.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
Number of times the class was encountered. |
| label |
string |
true |
|
Name of the class. |
FeatureEffectCreate
{
"properties": {
"rowCount": {
"description": "The number of rows from dataset to use for Feature Impact calculation.",
"maximum": 100000,
"minimum": 10,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.21"
}
},
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| rowCount |
integer,null |
false |
maximum: 100000
minimum: 10
|
The number of rows from dataset to use for Feature Impact calculation. |
FeatureEffects
{
"properties": {
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureImpactScore |
number |
true |
|
Feature impact score. |
| featureName |
string |
true |
|
Name of the feature. |
| featureType |
string |
true |
|
Feature type, either numeric or categorical. |
| isBinnable |
boolean |
true |
|
Whether values can be grouped into bins. |
| isScalable |
boolean,null |
true |
|
Whether numeric feature values can be reported on a log scale. |
| partialDependence |
PartialDependence |
false |
|
Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight. |
| predictedVsActual |
PredictedVsActual |
false |
|
Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight. |
| weightLabel |
string,null |
true |
|
Weight label if weight was configured for the project. |
FeatureEffectsCreateDatetime
{
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`, `startstop`.",
"type": "string"
},
"rowCount": {
"description": "The number of rows from dataset to use for Feature Impact calculation.",
"maximum": 100000,
"minimum": 10,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.21"
}
},
"required": [
"backtestIndex"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestIndex |
string |
true |
|
The backtest index. For example: 0, 1, ..., 20, holdout, startstop. |
| rowCount |
integer,null |
false |
maximum: 100000
minimum: 10
|
The number of rows from dataset to use for Feature Impact calculation. |
FeatureEffectsDatetimeResponse
{
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`, `startstop`.",
"type": "string"
},
"featureEffects": {
"description": "Feature Effects computational results for each feature.",
"items": {
"properties": {
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model ID",
"type": "string"
},
"projectId": {
"description": "The project ID",
"type": "string"
},
"source": {
"description": "Models data source.",
"type": "string"
}
},
"required": [
"backtestIndex",
"featureEffects",
"modelId",
"projectId",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestIndex |
string |
true |
|
The backtest index. For example: 0, 1, ..., 20, holdout, startstop. |
| featureEffects |
[FeatureEffects] |
true |
|
Feature Effects computational results for each feature. |
| modelId |
string |
true |
|
The model ID |
| projectId |
string |
true |
|
The project ID |
| source |
string |
true |
|
Models data source. |
FeatureEffectsInsightResponse
{
"description": "Feature effects data.",
"properties": {
"featureEffects": {
"description": "Feature Effects computational results for each feature.",
"items": {
"properties": {
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureEffects"
],
"type": "object"
}
Feature effects data.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureEffects |
[FeatureEffects] |
true |
|
Feature Effects computational results for each feature. |
FeatureEffectsResponse
{
"properties": {
"featureEffects": {
"description": "Feature Effects computational results for each feature.",
"items": {
"properties": {
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model ID",
"type": "string"
},
"projectId": {
"description": "The project ID",
"type": "string"
},
"source": {
"description": "Models data source.",
"type": "string"
}
},
"required": [
"featureEffects",
"modelId",
"projectId",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureEffects |
[FeatureEffects] |
true |
|
Feature Effects computational results for each feature. |
| modelId |
string |
true |
|
The model ID |
| projectId |
string |
true |
|
The project ID |
| source |
string |
true |
|
Models data source. |
FeatureImpactCreatePayload
{
"properties": {
"rowCount": {
"description": "The sample size to use for Feature Impact computation. It is possible to re-compute Feature Impact with a different row count.",
"maximum": 100000,
"minimum": 10,
"type": "integer",
"x-versionadded": "v2.21"
}
},
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| rowCount |
integer |
false |
maximum: 100000
minimum: 10
|
The sample size to use for Feature Impact computation. It is possible to re-compute Feature Impact with a different row count. |
FeatureImpactInsightResponse
{
"description": "Feature impact data.",
"properties": {
"featureImpacts": {
"description": "A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"parentFeatureName": {
"description": "The name of the parent feature.",
"type": [
"string",
"null"
]
},
"redundantWith": {
"description": "Name of feature that has the highest correlation with this feature.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized",
"redundantWith"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"ranRedundancyDetection": {
"description": "Indicates whether redundant feature identification was run while calculating this feature impact.",
"type": "boolean"
},
"rowCount": {
"description": "The number of rows that was used to calculate feature impact. For the feature impact calculated with the default logic, without specifying the ``rowCount``, we return ``null`` here.",
"type": [
"integer",
"null"
]
}
},
"required": [
"featureImpacts",
"ranRedundancyDetection",
"rowCount"
],
"type": "object"
}
Feature impact data.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureImpacts |
[FeatureImpactItem] |
true |
maxItems: 1000
|
A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned. |
| ranRedundancyDetection |
boolean |
true |
|
Indicates whether redundant feature identification was run while calculating this feature impact. |
| rowCount |
integer,null |
true |
|
The number of rows that was used to calculate feature impact. For the feature impact calculated with the default logic, without specifying the rowCount, we return null here. |
FeatureImpactItem
{
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"parentFeatureName": {
"description": "The name of the parent feature.",
"type": [
"string",
"null"
]
},
"redundantWith": {
"description": "Name of feature that has the highest correlation with this feature.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized",
"redundantWith"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureName |
string |
true |
|
The name of the feature. |
| impactNormalized |
number |
true |
maximum: 1
|
The same as impactUnnormalized, but normalized such that the highest value is 1. |
| impactUnnormalized |
number |
true |
|
How much worse the error metric score is when making predictions on modified data. |
| parentFeatureName |
string,null |
false |
|
The name of the parent feature. |
| redundantWith |
string,null |
true |
|
Name of feature that has the highest correlation with this feature. |
FilterDataSlices
{
"properties": {
"operand": {
"description": "Feature to apply operation to.",
"type": "string"
},
"operator": {
"description": "Operator to apply to the named operand in the dataset. The operator 'eq' mean 'equals the single specified value'. The operator 'in' means 'is one of a list of allowed values.'",
"enum": [
"eq",
"in",
"<",
">",
"between",
"notBetween"
],
"type": "string"
},
"values": {
"description": "Values to filter the operand by with the given operator.",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
}
]
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"required": [
"operand",
"operator",
"values"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| operand |
string |
true |
|
Feature to apply operation to. |
| operator |
string |
true |
|
Operator to apply to the named operand in the dataset. The operator 'eq' mean 'equals the single specified value'. The operator 'in' means 'is one of a list of allowed values.' |
| values |
[anyOf] |
true |
maxItems: 1000
minItems: 1
|
Values to filter the operand by with the given operator. |
anyOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
or
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
|
none |
or
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
number |
false |
|
none |
Enumerated Values
| Property |
Value |
| operator |
[eq, in, <, >, between, notBetween] |
ForecastDistancePlotDataEntryResponse
{
"properties": {
"backtestingScore": {
"description": "Backtesting score for this forecast distance. If backtesting has not been run for this model, this score will be `null`.",
"type": [
"number",
"null"
]
},
"forecastDistance": {
"description": "The number of time units the scored rows are away from the forecast point.",
"type": "integer"
},
"holdoutScore": {
"description": "Holdout set score for this forecast distance. If holdout is locked for the project, this score will be `null`.",
"type": [
"number",
"null"
]
},
"validationScore": {
"description": "Validation set score for this forecast distance.",
"type": "number"
}
},
"required": [
"backtestingScore",
"forecastDistance",
"holdoutScore",
"validationScore"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestingScore |
number,null |
true |
|
Backtesting score for this forecast distance. If backtesting has not been run for this model, this score will be null. |
| forecastDistance |
integer |
true |
|
The number of time units the scored rows are away from the forecast point. |
| holdoutScore |
number,null |
true |
|
Holdout set score for this forecast distance. If holdout is locked for the project, this score will be null. |
| validationScore |
number |
true |
|
Validation set score for this forecast distance. |
ForecastDistanceStabilityPlotResponse
{
"properties": {
"endDate": {
"description": "ISO-formatted start date of the project dataset.",
"format": "date-time",
"type": "string"
},
"forecastDistancePlotData": {
"description": "An array of objects containing the details of the scores for each forecast distance.",
"items": {
"properties": {
"backtestingScore": {
"description": "Backtesting score for this forecast distance. If backtesting has not been run for this model, this score will be `null`.",
"type": [
"number",
"null"
]
},
"forecastDistance": {
"description": "The number of time units the scored rows are away from the forecast point.",
"type": "integer"
},
"holdoutScore": {
"description": "Holdout set score for this forecast distance. If holdout is locked for the project, this score will be `null`.",
"type": [
"number",
"null"
]
},
"validationScore": {
"description": "Validation set score for this forecast distance.",
"type": "number"
}
},
"required": [
"backtestingScore",
"forecastDistance",
"holdoutScore",
"validationScore"
],
"type": "object"
},
"type": "array"
},
"metricName": {
"description": "Name of the metric used to compute the scores.",
"type": "string"
},
"startDate": {
"description": "ISO-formatted start date of the project dataset.",
"format": "date-time",
"type": "string"
}
},
"required": [
"endDate",
"forecastDistancePlotData",
"metricName",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| endDate |
string(date-time) |
true |
|
ISO-formatted start date of the project dataset. |
| forecastDistancePlotData |
[ForecastDistancePlotDataEntryResponse] |
true |
|
An array of objects containing the details of the scores for each forecast distance. |
| metricName |
string |
true |
|
Name of the metric used to compute the scores. |
| startDate |
string(date-time) |
true |
|
ISO-formatted start date of the project dataset. |
ForecastVsActualPlotsBins
{
"properties": {
"actual": {
"description": "Average actual value of the target in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"error": {
"description": "Average absolute residual value of the bin. `null` if there are no entries in the bin.",
"minimum": 0,
"type": [
"number",
"null"
]
},
"forecasts": {
"description": "An array of average forecasts for the model for each forecast distance. Empty if there are no forecasts in the bin. Each index in the `forecasts` array maps to `forecastDistances` array index.",
"items": {
"type": "number"
},
"maxItems": 100,
"type": "array"
},
"frequency": {
"description": "Indicates number of values averaged in bin in case of a resolution change.",
"type": [
"integer",
"null"
]
},
"normalizedError": {
"description": "Normalized average absolute residual value of the bin. `null` if there are no entries in the bin.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"error",
"forecasts",
"frequency",
"normalizedError",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actual |
number,null |
true |
|
Average actual value of the target in the bin. null if there are no entries in the bin. |
| endDate |
string(date-time) |
true |
|
The datetime of the end of the bin (exclusive). |
| error |
number,null |
true |
minimum: 0
|
Average absolute residual value of the bin. null if there are no entries in the bin. |
| forecasts |
[number] |
true |
maxItems: 100
|
An array of average forecasts for the model for each forecast distance. Empty if there are no forecasts in the bin. Each index in the forecasts array maps to forecastDistances array index. |
| frequency |
integer,null |
true |
|
Indicates number of values averaged in bin in case of a resolution change. |
| normalizedError |
number,null |
true |
maximum: 1
minimum: 0
|
Normalized average absolute residual value of the bin. null if there are no entries in the bin. |
| startDate |
string(date-time) |
true |
|
The datetime of the start of the bin (inclusive). |
ForecastVsActualPlotsDataResponse
{
"properties": {
"bins": {
"description": "An array of bins for the retrieved plots.",
"items": {
"properties": {
"actual": {
"description": "Average actual value of the target in the bin. `null` if there are no entries in the bin.",
"type": [
"number",
"null"
]
},
"endDate": {
"description": "The datetime of the end of the bin (exclusive). ",
"format": "date-time",
"type": "string"
},
"error": {
"description": "Average absolute residual value of the bin. `null` if there are no entries in the bin.",
"minimum": 0,
"type": [
"number",
"null"
]
},
"forecasts": {
"description": "An array of average forecasts for the model for each forecast distance. Empty if there are no forecasts in the bin. Each index in the `forecasts` array maps to `forecastDistances` array index.",
"items": {
"type": "number"
},
"maxItems": 100,
"type": "array"
},
"frequency": {
"description": "Indicates number of values averaged in bin in case of a resolution change.",
"type": [
"integer",
"null"
]
},
"normalizedError": {
"description": "Normalized average absolute residual value of the bin. `null` if there are no entries in the bin.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the bin (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"actual",
"endDate",
"error",
"forecasts",
"frequency",
"normalizedError",
"startDate"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"calendarEvents": {
"description": "An array of calendar events for a retrieved plot.",
"items": {
"properties": {
"date": {
"description": "The date of the calendar event.",
"format": "date-time",
"type": "string"
},
"name": {
"description": "Name of the calendar event.",
"type": "string"
},
"seriesId": {
"description": "The series ID for the event. If this event does not specify a series ID, then this will be `null`, indicating that the event applies to all series.",
"type": [
"string",
"null"
]
}
},
"required": [
"date",
"name",
"seriesId"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). ",
"format": "date-time",
"type": "string"
},
"forecastDistances": {
"description": "An array of forecast distances. Forecast distance specifies the number of time steps between the predicted point and the origin point.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 100,
"minItems": 1,
"type": "array"
},
"resolution": {
"description": "The resolution that is used for binning.",
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). ",
"format": "date-time",
"type": "string"
}
},
"required": [
"bins",
"calendarEvents",
"endDate",
"forecastDistances",
"resolution",
"startDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[ForecastVsActualPlotsBins] |
true |
maxItems: 1000
minItems: 1
|
An array of bins for the retrieved plots. |
| calendarEvents |
[CalendarEvent] |
true |
maxItems: 1000
|
An array of calendar events for a retrieved plot. |
| endDate |
string(date-time) |
true |
|
The datetime of the end of the chart data (exclusive). |
| forecastDistances |
[integer] |
true |
maxItems: 100
minItems: 1
|
An array of forecast distances. Forecast distance specifies the number of time steps between the predicted point and the origin point. |
| resolution |
string |
true |
|
The resolution that is used for binning. |
| startDate |
string(date-time) |
true |
|
The datetime of the start of the chart data (inclusive). |
Enumerated Values
| Property |
Value |
| resolution |
[milliseconds, seconds, minutes, hours, days, weeks, months, quarters, years] |
ForecastVsActualPlotsForecastDistancesStatus
{
"description": "Status for backtest/holdout training.",
"properties": {
"completed": {
"description": "An array of available forecast distances for the `completed` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"errored": {
"description": "An array of available forecast distances for the `errored` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"inProgress": {
"description": "An array of available forecast distances for the `inProgress` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"insufficientData": {
"description": "An array of available forecast distances for the `insufficientData` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"notCompleted": {
"description": "An array of available forecast distances for the `notCompleted` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"type": "object"
}
Status for backtest/holdout training.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| completed |
[integer] |
false |
maxItems: 1000
minItems: 1
|
An array of available forecast distances for the completed status. If there are no forecast distances for this status, it will not appear in the response. |
| errored |
[integer] |
false |
maxItems: 1000
minItems: 1
|
An array of available forecast distances for the errored status. If there are no forecast distances for this status, it will not appear in the response. |
| inProgress |
[integer] |
false |
maxItems: 1000
minItems: 1
|
An array of available forecast distances for the inProgress status. If there are no forecast distances for this status, it will not appear in the response. |
| insufficientData |
[integer] |
false |
maxItems: 1000
minItems: 1
|
An array of available forecast distances for the insufficientData status. If there are no forecast distances for this status, it will not appear in the response. |
| notCompleted |
[integer] |
false |
maxItems: 1000
minItems: 1
|
An array of available forecast distances for the notCompleted status. If there are no forecast distances for this status, it will not appear in the response. |
{
"properties": {
"backtestMetadata": {
"description": "An array of metadata information for each backtest. The array index of metadata object is the backtest index.",
"items": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"backtestStatuses": {
"description": "An array of status information for each backtest. The array index of status object is the backtest index.",
"items": {
"description": "Status for forecast vs actual plots.",
"properties": {
"training": {
"description": "Status for backtest/holdout training.",
"properties": {
"completed": {
"description": "An array of available forecast distances for the `completed` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"errored": {
"description": "An array of available forecast distances for the `errored` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"inProgress": {
"description": "An array of available forecast distances for the `inProgress` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"insufficientData": {
"description": "An array of available forecast distances for the `insufficientData` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"notCompleted": {
"description": "An array of available forecast distances for the `notCompleted` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"type": "object"
},
"validation": {
"description": "Status for backtest/holdout training.",
"properties": {
"completed": {
"description": "An array of available forecast distances for the `completed` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"errored": {
"description": "An array of available forecast distances for the `errored` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"inProgress": {
"description": "An array of available forecast distances for the `inProgress` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"insufficientData": {
"description": "An array of available forecast distances for the `insufficientData` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"notCompleted": {
"description": "An array of available forecast distances for the `notCompleted` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"maxItems": 20,
"minItems": 1,
"type": "array"
},
"estimatedSeriesLimit": {
"description": "Estimated number of series that can be calculated in one request for 1 FD.",
"minimum": 1,
"type": "integer"
},
"holdoutMetadata": {
"description": "Metadata for backtest/holdout.",
"properties": {
"training": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
},
"validation": {
"description": "Start and end dates for the backtest/holdout training.",
"properties": {
"endDate": {
"description": "The datetime of the end of the chart data (exclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"startDate": {
"description": "The datetime of the start of the chart data (inclusive). Null if chart data is not computed.",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"endDate",
"startDate"
],
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"holdoutStatuses": {
"description": "Status for forecast vs actual plots.",
"properties": {
"training": {
"description": "Status for backtest/holdout training.",
"properties": {
"completed": {
"description": "An array of available forecast distances for the `completed` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"errored": {
"description": "An array of available forecast distances for the `errored` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"inProgress": {
"description": "An array of available forecast distances for the `inProgress` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"insufficientData": {
"description": "An array of available forecast distances for the `insufficientData` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"notCompleted": {
"description": "An array of available forecast distances for the `notCompleted` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"type": "object"
},
"validation": {
"description": "Status for backtest/holdout training.",
"properties": {
"completed": {
"description": "An array of available forecast distances for the `completed` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"errored": {
"description": "An array of available forecast distances for the `errored` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"inProgress": {
"description": "An array of available forecast distances for the `inProgress` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"insufficientData": {
"description": "An array of available forecast distances for the `insufficientData` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"notCompleted": {
"description": "An array of available forecast distances for the `notCompleted` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
},
"resolutions": {
"description": "An array of available time resolutions for which plots can be retrieved.",
"items": {
"enum": [
"milliseconds",
"seconds",
"minutes",
"hours",
"days",
"weeks",
"months",
"quarters",
"years"
],
"type": "string"
},
"maxItems": 9,
"minItems": 1,
"type": "array"
}
},
"required": [
"backtestMetadata",
"backtestStatuses",
"holdoutMetadata",
"holdoutStatuses",
"resolutions"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestMetadata |
[DatetimeTrendPlotsBacktestMetadata] |
true |
maxItems: 20
minItems: 1
|
An array of metadata information for each backtest. The array index of metadata object is the backtest index. |
| backtestStatuses |
[ForecastVsActualPlotsStatus] |
true |
maxItems: 20
minItems: 1
|
An array of status information for each backtest. The array index of status object is the backtest index. |
| estimatedSeriesLimit |
integer |
false |
minimum: 1
|
Estimated number of series that can be calculated in one request for 1 FD. |
| holdoutMetadata |
DatetimeTrendPlotsBacktestMetadata |
true |
|
Metadata for backtest/holdout. |
| holdoutStatuses |
ForecastVsActualPlotsStatus |
true |
|
Status for forecast vs actual plots. |
| resolutions |
[string] |
true |
maxItems: 9
minItems: 1
|
An array of available time resolutions for which plots can be retrieved. |
ForecastVsActualPlotsStatus
{
"description": "Status for forecast vs actual plots.",
"properties": {
"training": {
"description": "Status for backtest/holdout training.",
"properties": {
"completed": {
"description": "An array of available forecast distances for the `completed` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"errored": {
"description": "An array of available forecast distances for the `errored` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"inProgress": {
"description": "An array of available forecast distances for the `inProgress` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"insufficientData": {
"description": "An array of available forecast distances for the `insufficientData` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"notCompleted": {
"description": "An array of available forecast distances for the `notCompleted` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"type": "object"
},
"validation": {
"description": "Status for backtest/holdout training.",
"properties": {
"completed": {
"description": "An array of available forecast distances for the `completed` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"errored": {
"description": "An array of available forecast distances for the `errored` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"inProgress": {
"description": "An array of available forecast distances for the `inProgress` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"insufficientData": {
"description": "An array of available forecast distances for the `insufficientData` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"notCompleted": {
"description": "An array of available forecast distances for the `notCompleted` status. If there are no forecast distances for this status, it will not appear in the response.",
"items": {
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"type": "object"
}
},
"required": [
"training",
"validation"
],
"type": "object"
}
Status for forecast vs actual plots.
Properties
FrequentValueData
{
"properties": {
"count": {
"description": "Count of specified frequent value in the sample, weighted by exposure or weights",
"type": "integer"
},
"dataQuality": {
"description": "Any data quality issue associated with this particularvalue of the feature. Possible data quality types include 'excess_zero', 'inlier', 'disguised_missing_value', and 'no_issues_found' and the relevant statistics.",
"type": "string"
},
"target": {
"description": "Average target value for the specified frequent value if the target is binary or numeric. With weights or exposure, this becomes a weighted average. If the target is not set, it returns None.",
"type": [
"number",
"null"
]
},
"value": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
}
],
"description": "Specified frequent value, either a float or a string, like `=All Others+`"
}
},
"required": [
"count",
"dataQuality",
"target",
"value"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
Count of specified frequent value in the sample, weighted by exposure or weights |
| dataQuality |
string |
true |
|
Any data quality issue associated with this particularvalue of the feature. Possible data quality types include 'excess_zero', 'inlier', 'disguised_missing_value', and 'no_issues_found' and the relevant statistics. |
| target |
number,null |
true |
|
Average target value for the specified frequent value if the target is binary or numeric. With weights or exposure, this becomes a weighted average. If the target is not set, it returns None. |
| value |
any |
true |
|
Specified frequent value, either a float or a string, like =All Others+ |
anyOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
number |
false |
|
none |
or
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
FrequentValuesResponse
{
"properties": {
"frequentValues": {
"description": "List of frequent value and data quality information",
"items": {
"properties": {
"count": {
"description": "Count of specified frequent value in the sample, weighted by exposure or weights",
"type": "integer"
},
"dataQuality": {
"description": "Any data quality issue associated with this particularvalue of the feature. Possible data quality types include 'excess_zero', 'inlier', 'disguised_missing_value', and 'no_issues_found' and the relevant statistics.",
"type": "string"
},
"target": {
"description": "Average target value for the specified frequent value if the target is binary or numeric. With weights or exposure, this becomes a weighted average. If the target is not set, it returns None.",
"type": [
"number",
"null"
]
},
"value": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
}
],
"description": "Specified frequent value, either a float or a string, like `=All Others+`"
}
},
"required": [
"count",
"dataQuality",
"target",
"value"
],
"type": "object"
},
"type": "array"
},
"name": {
"description": "Name of the feature",
"type": "string"
},
"numRows": {
"description": "Number of rows in the sample used to determine frequent values",
"type": "integer"
},
"projectId": {
"description": "Project Id",
"type": "string"
}
},
"required": [
"frequentValues",
"name",
"numRows",
"projectId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| frequentValues |
[FrequentValueData] |
true |
|
List of frequent value and data quality information |
| name |
string |
true |
|
Name of the feature |
| numRows |
integer |
true |
|
Number of rows in the sample used to determine frequent values |
| projectId |
string |
true |
|
Project Id |
GeoFeaturePlotData
{
"description": "Geo feature plot data",
"properties": {
"aggregation": {
"description": "Type of geo aggregation.",
"enum": [
"grid",
"unique"
],
"type": "string"
},
"bbox": {
"description": "Bounding box of feature map.",
"type": "object"
},
"features": {
"description": "Location features over map",
"items": {
"properties": {
"geometry": {
"description": "Geometry.",
"properties": {
"coordinates": {
"description": "Coordinate representative of a geometry.",
"items": {
"type": "object"
},
"type": "array"
},
"type": {
"description": "Type of geometry.",
"enum": [
"Point",
"LineString",
"Polygon"
],
"type": "string"
}
},
"required": [
"coordinates",
"type"
],
"type": "object"
},
"properties": {
"description": "Properties of location features.",
"properties": {
"count": {
"description": "Total num of samples located within this geometry.",
"type": "integer"
}
},
"required": [
"count"
],
"type": "object"
},
"type": {
"description": "With a fixed value of 'Feature'.",
"type": "string"
}
},
"required": [
"geometry",
"properties",
"type"
],
"type": "object"
},
"type": "array"
},
"summary": {
"description": "Summary of feature map.",
"properties": {
"maxCount": {
"description": "Max num of samples located within one geometry.",
"type": "integer"
},
"minCount": {
"description": "Min num of samples located within one geometry.",
"type": "integer"
},
"totalCount": {
"description": "Total num of samples across all geometry objects.",
"type": "integer"
}
},
"required": [
"maxCount",
"minCount",
"totalCount"
],
"type": "object"
},
"type": {
"description": "GeoJSON FeatureCollection.",
"type": "string"
},
"valueAggregation": {
"description": "Type of feature aggregation.",
"enum": [
"geometry"
],
"type": "string"
}
},
"required": [
"aggregation",
"bbox",
"features",
"summary",
"type",
"valueAggregation"
],
"type": "object"
}
Geo feature plot data
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| aggregation |
string |
true |
|
Type of geo aggregation. |
| bbox |
object |
true |
|
Bounding box of feature map. |
| features |
[GeoFeaturePlotFeature] |
true |
|
Location features over map |
| summary |
GeoFeaturePlotSummary |
true |
|
Summary of feature map. |
| type |
string |
true |
|
GeoJSON FeatureCollection. |
| valueAggregation |
string |
true |
|
Type of feature aggregation. |
Enumerated Values
| Property |
Value |
| aggregation |
[grid, unique] |
| valueAggregation |
geometry |
GeoFeaturePlotFeature
{
"properties": {
"geometry": {
"description": "Geometry.",
"properties": {
"coordinates": {
"description": "Coordinate representative of a geometry.",
"items": {
"type": "object"
},
"type": "array"
},
"type": {
"description": "Type of geometry.",
"enum": [
"Point",
"LineString",
"Polygon"
],
"type": "string"
}
},
"required": [
"coordinates",
"type"
],
"type": "object"
},
"properties": {
"description": "Properties of location features.",
"properties": {
"count": {
"description": "Total num of samples located within this geometry.",
"type": "integer"
}
},
"required": [
"count"
],
"type": "object"
},
"type": {
"description": "With a fixed value of 'Feature'.",
"type": "string"
}
},
"required": [
"geometry",
"properties",
"type"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| geometry |
GeoJSON |
true |
|
Geometry. |
| properties |
GeoFeaturePlotFeatureProperties |
true |
|
Properties of location features. |
| type |
string |
true |
|
With a fixed value of 'Feature'. |
GeoFeaturePlotFeatureProperties
{
"description": "Properties of location features.",
"properties": {
"count": {
"description": "Total num of samples located within this geometry.",
"type": "integer"
}
},
"required": [
"count"
],
"type": "object"
}
Properties of location features.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
Total num of samples located within this geometry. |
GeoFeaturePlotSummary
{
"description": "Summary of feature map.",
"properties": {
"maxCount": {
"description": "Max num of samples located within one geometry.",
"type": "integer"
},
"minCount": {
"description": "Min num of samples located within one geometry.",
"type": "integer"
},
"totalCount": {
"description": "Total num of samples across all geometry objects.",
"type": "integer"
}
},
"required": [
"maxCount",
"minCount",
"totalCount"
],
"type": "object"
}
Summary of feature map.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| maxCount |
integer |
true |
|
Max num of samples located within one geometry. |
| minCount |
integer |
true |
|
Min num of samples located within one geometry. |
| totalCount |
integer |
true |
|
Total num of samples across all geometry objects. |
GeoJSON
{
"description": "Geometry.",
"properties": {
"coordinates": {
"description": "Coordinate representative of a geometry.",
"items": {
"type": "object"
},
"type": "array"
},
"type": {
"description": "Type of geometry.",
"enum": [
"Point",
"LineString",
"Polygon"
],
"type": "string"
}
},
"required": [
"coordinates",
"type"
],
"type": "object"
}
Geometry.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| coordinates |
[object] |
true |
|
Coordinate representative of a geometry. |
| type |
string |
true |
|
Type of geometry. |
Enumerated Values
| Property |
Value |
| type |
[Point, LineString, Polygon] |
GeometryFeaturePLotCreatePayload
{
"properties": {
"feature": {
"description": "Name of a location feature from the dataset to plot on map.",
"type": "string"
}
},
"required": [
"feature"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| feature |
string |
true |
|
Name of a location feature from the dataset to plot on map. |
GeometryFeaturePlotRetrieveResponse
{
"properties": {
"feature": {
"description": "Name of location feature to plot on map.",
"type": "string"
},
"plotData": {
"description": "Geo feature plot data",
"properties": {
"aggregation": {
"description": "Type of geo aggregation.",
"enum": [
"grid",
"unique"
],
"type": "string"
},
"bbox": {
"description": "Bounding box of feature map.",
"type": "object"
},
"features": {
"description": "Location features over map",
"items": {
"properties": {
"geometry": {
"description": "Geometry.",
"properties": {
"coordinates": {
"description": "Coordinate representative of a geometry.",
"items": {
"type": "object"
},
"type": "array"
},
"type": {
"description": "Type of geometry.",
"enum": [
"Point",
"LineString",
"Polygon"
],
"type": "string"
}
},
"required": [
"coordinates",
"type"
],
"type": "object"
},
"properties": {
"description": "Properties of location features.",
"properties": {
"count": {
"description": "Total num of samples located within this geometry.",
"type": "integer"
}
},
"required": [
"count"
],
"type": "object"
},
"type": {
"description": "With a fixed value of 'Feature'.",
"type": "string"
}
},
"required": [
"geometry",
"properties",
"type"
],
"type": "object"
},
"type": "array"
},
"summary": {
"description": "Summary of feature map.",
"properties": {
"maxCount": {
"description": "Max num of samples located within one geometry.",
"type": "integer"
},
"minCount": {
"description": "Min num of samples located within one geometry.",
"type": "integer"
},
"totalCount": {
"description": "Total num of samples across all geometry objects.",
"type": "integer"
}
},
"required": [
"maxCount",
"minCount",
"totalCount"
],
"type": "object"
},
"type": {
"description": "GeoJSON FeatureCollection.",
"type": "string"
},
"valueAggregation": {
"description": "Type of feature aggregation.",
"enum": [
"geometry"
],
"type": "string"
}
},
"required": [
"aggregation",
"bbox",
"features",
"summary",
"type",
"valueAggregation"
],
"type": "object"
},
"projectId": {
"description": "The project to select a location feature from.",
"type": "string"
}
},
"required": [
"feature",
"plotData",
"projectId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| feature |
string |
true |
|
Name of location feature to plot on map. |
| plotData |
GeoFeaturePlotData |
true |
|
Geo feature plot data |
| projectId |
string |
true |
|
The project to select a location feature from. |
GeospatialFeature
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"geospatialPoint"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a geospatial centroid or point feature.",
"items": {
"properties": {
"insightName": {
"description": "Insight name.",
"enum": [
"representativeLocations"
],
"type": "string"
},
"perCluster": {
"description": "Statistic for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"maxLength": 50,
"minLength": 1,
"type": "string"
},
"representativeLocations": {
"description": "A list of latitude and longitude location list",
"items": {
"description": "Latitude and longitude list.",
"items": {
"description": "Longitude or latitude, in degrees.",
"maximum": 180,
"minimum": -180,
"type": "number"
},
"type": "array"
},
"maxItems": 1000,
"type": "array"
}
},
"required": [
"clusterName",
"representativeLocations"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureImpact |
number,null |
false |
|
Feature Impact score. |
| featureName |
string |
true |
|
Feature name. |
| featureType |
string |
true |
|
Feature Type. |
| insights |
[GeospatialInsights] |
true |
|
A list of Cluster Insights for a geospatial centroid or point feature. |
Enumerated Values
| Property |
Value |
| featureType |
geospatialPoint |
GeospatialInsights
{
"properties": {
"insightName": {
"description": "Insight name.",
"enum": [
"representativeLocations"
],
"type": "string"
},
"perCluster": {
"description": "Statistic for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"maxLength": 50,
"minLength": 1,
"type": "string"
},
"representativeLocations": {
"description": "A list of latitude and longitude location list",
"items": {
"description": "Latitude and longitude list.",
"items": {
"description": "Longitude or latitude, in degrees.",
"maximum": 180,
"minimum": -180,
"type": "number"
},
"type": "array"
},
"maxItems": 1000,
"type": "array"
}
},
"required": [
"clusterName",
"representativeLocations"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"insightName",
"perCluster"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| insightName |
string |
true |
|
Insight name. |
| perCluster |
[PerClusterGeospatial] |
true |
|
Statistic for different feature values in this cluster. |
Enumerated Values
| Property |
Value |
| insightName |
representativeLocations |
GlobalMetrics
{
"description": "average metrics across all classes",
"properties": {
"f1": {
"description": "Average F1 score",
"type": "number"
},
"precision": {
"description": "Average precision score",
"type": "number"
},
"recall": {
"description": "Avergae recall score",
"type": "number"
}
},
"required": [
"f1",
"precision",
"recall"
],
"type": "object"
}
average metrics across all classes
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| f1 |
number |
true |
|
Average F1 score |
| precision |
number |
true |
|
Average precision score |
| recall |
number |
true |
|
Avergae recall score |
Histogram
{
"properties": {
"intervalEnd": {
"description": "The end of the interval.",
"type": "number"
},
"intervalStart": {
"description": "The start of the interval.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within that interval.",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| intervalEnd |
number |
true |
|
The end of the interval. |
| intervalStart |
number |
true |
|
The start of the interval. |
| occurrences |
integer |
true |
|
The number of times the predicted value fits within that interval. |
HistogramBarsDetails
{
"properties": {
"label": {
"description": "Name of the class.",
"type": "string"
},
"value": {
"description": "Ratio of occurrence of the class.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| label |
string |
true |
|
Name of the class. |
| value |
number |
true |
|
Ratio of occurrence of the class. |
HistogramDetails
{
"properties": {
"bars": {
"description": "Class details for the histogram chart",
"items": {
"properties": {
"label": {
"description": "Name of the class.",
"type": "string"
},
"value": {
"description": "Ratio of occurrence of the class.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
},
"bin": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
],
"description": "Label for the bin grouping"
}
},
"required": [
"bars",
"bin"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bars |
[HistogramBarsDetails] |
true |
|
Class details for the histogram chart |
| bin |
any |
true |
|
Label for the bin grouping |
anyOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
or
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
|
none |
ImageFeature
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"image"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for an image feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"images",
"percentageOfMissingImages"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"representativeImages"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"clusterName",
"images",
"percentageOfMissingImages"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureImpact |
number,null |
false |
|
Feature Impact score. |
| featureName |
string |
true |
|
Feature name. |
| featureType |
string |
true |
|
Feature Type. |
| insights |
[ImageInsights] |
true |
|
A list of Cluster Insights for an image feature. |
Enumerated Values
| Property |
Value |
| featureType |
image |
ImageInsights
{
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"images",
"percentageOfMissingImages"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"representativeImages"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"clusterName",
"images",
"percentageOfMissingImages"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"insightName",
"perCluster"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| allData |
AllDataImage |
false |
|
Statistics for all data for different feature values. |
| insightName |
string |
true |
|
Insight name. |
| perCluster |
[PerClusterImage] |
true |
|
Statistic values for different feature values in this cluster. |
Enumerated Values
| Property |
Value |
| insightName |
representativeImages |
{
"properties": {
"featureName": {
"description": "Name of feature",
"type": "string"
},
"modelId": {
"description": "Model ID of the target model",
"type": "string"
}
},
"required": [
"featureName",
"modelId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureName |
string |
true |
|
Name of feature |
| modelId |
string |
true |
|
Model ID of the target model |
LabelRelevancePlot
{
"properties": {
"labelRelevance": {
"description": "Label relevance value.",
"maximum": 1,
"minimum": 0,
"type": "integer"
},
"rowCount": {
"description": "Number of rows for which the label has the given relevance.",
"minimum": 0,
"type": "integer"
},
"rowPct": {
"description": "Percentage of rows for which the label has the given relevance.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"labelRelevance",
"rowCount",
"rowPct"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| labelRelevance |
integer |
true |
maximum: 1
minimum: 0
|
Label relevance value. |
| rowCount |
integer |
true |
minimum: 0
|
Number of rows for which the label has the given relevance. |
| rowPct |
number |
true |
maximum: 100
minimum: 0
|
Percentage of rows for which the label has the given relevance. |
LabelwiseLiftChart
{
"properties": {
"labelBins": {
"description": "Lift charts for the given data source.",
"items": {
"properties": {
"bins": {
"description": "Lift chart data for that label.",
"items": {
"properties": {
"actual": {
"description": "Average of actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "For projects with weights, it is the sum of the weights of all rows in the bins. Otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "Average of predicted target values for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"maxItems": 60,
"type": "array"
},
"label": {
"description": "Label name.",
"type": "string"
}
},
"required": [
"bins",
"label"
],
"type": "object"
},
"maxItems": 100,
"type": "array"
},
"labels": {
"description": "All available target labels for this insight.",
"items": {
"description": "Label name.",
"type": "string"
},
"maxItems": 100,
"type": "array"
},
"modelId": {
"description": "Model Id.",
"type": "string"
},
"projectId": {
"description": "Project Id.",
"type": "string"
},
"source": {
"description": "Data source of Lift charts.",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
}
},
"required": [
"labelBins",
"labels",
"modelId",
"projectId",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| labelBins |
[LabelwiseLiftChartItem] |
true |
maxItems: 100
|
Lift charts for the given data source. |
| labels |
[string] |
true |
maxItems: 100
|
All available target labels for this insight. |
| modelId |
string |
true |
|
Model Id. |
| projectId |
string |
true |
|
Project Id. |
| source |
string |
true |
|
Data source of Lift charts. |
Enumerated Values
| Property |
Value |
| source |
[validation, crossValidation, holdout] |
LabelwiseLiftChartBin
{
"properties": {
"actual": {
"description": "Average of actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "For projects with weights, it is the sum of the weights of all rows in the bins. Otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "Average of predicted target values for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actual |
number |
true |
|
Average of actual target values for the rows in the bin. |
| binWeight |
number |
true |
|
For projects with weights, it is the sum of the weights of all rows in the bins. Otherwise, it is the number of rows in the bin. |
| predicted |
number |
true |
|
Average of predicted target values for the rows in the bin. |
LabelwiseLiftChartItem
{
"properties": {
"bins": {
"description": "Lift chart data for that label.",
"items": {
"properties": {
"actual": {
"description": "Average of actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "For projects with weights, it is the sum of the weights of all rows in the bins. Otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "Average of predicted target values for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"maxItems": 60,
"type": "array"
},
"label": {
"description": "Label name.",
"type": "string"
}
},
"required": [
"bins",
"label"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[LabelwiseLiftChartBin] |
true |
maxItems: 60
|
Lift chart data for that label. |
| label |
string |
true |
|
Label name. |
LabelwiseROC
{
"properties": {
"averageModelMetrics": {
"description": "All average model metrics from one data source.",
"properties": {
"metrics": {
"description": "Average model metrics for the given thresholds.",
"items": {
"properties": {
"name": {
"description": "Metric name.",
"enum": [
"accuracy",
"f1Score",
"falsePositiveRate",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"trueNegativeRate",
"truePositiveRate"
],
"type": "string"
},
"numLabelsUsedInCalculation": {
"description": "Number of labels that were taken into account in the calculation of metric averages",
"type": "integer"
},
"values": {
"description": "Metric values at given thresholds.",
"items": {
"type": "number"
},
"maxItems": 100,
"minItems": 100,
"type": "array"
}
},
"required": [
"name",
"numLabelsUsedInCalculation",
"values"
],
"type": "object"
},
"maxItems": 8,
"minItems": 8,
"type": "array"
},
"source": {
"description": "Chart source.",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
},
"thresholds": {
"description": "Threshold values for which model metrics are available.",
"items": {
"maximum": 1,
"minimum": 0,
"type": "number"
},
"maxItems": 100,
"minItems": 100,
"type": "array"
}
},
"required": [
"metrics",
"source",
"thresholds"
],
"type": "object"
},
"charts": {
"description": "ROC data for all labels from one data source.",
"items": {
"properties": {
"auc": {
"description": "Area under the curve.",
"type": "number"
},
"kolmogorovSmirnovMetric": {
"description": "Kolmogorov-Smirnov metric.",
"type": "number"
},
"label": {
"description": "Label name.",
"type": "string"
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the positive class.",
"items": {
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "ROC characteristics for label.",
"items": {
"properties": {
"accuracy": {
"description": "Accuracy.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"falsePositiveRate": {
"description": "False positive rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"falsePositiveScore": {
"description": "False positive score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"fractionPredictedAsNegative": {
"description": "Fraction of negative predictions.",
"type": [
"number",
"null"
]
},
"fractionPredictedAsPositive": {
"description": "Fraction of positive predictions.",
"type": [
"number",
"null"
]
},
"liftNegative": {
"description": "Negative lift.",
"type": [
"number",
"null"
]
},
"liftPositive": {
"description": "Positive lift.",
"type": [
"number",
"null"
]
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"maximum": 1,
"minimum": -1,
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"threshold": {
"description": "Threshold.",
"maximum": 2,
"minimum": 0,
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"trueNegativeScore": {
"description": "True negative score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"truePositiveRate": {
"description": "True positive rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"truePositiveScore": {
"description": "True positive score.",
"minimum": 0,
"type": [
"integer",
"null"
]
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Data source of ROC characteristics.",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
}
},
"required": [
"auc",
"kolmogorovSmirnovMetric",
"label",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints",
"source"
],
"type": "object"
},
"type": "array"
},
"count": {
"description": "Number of labels returned on this page.",
"type": "integer"
},
"labels": {
"description": "All available target labels for this insight.",
"items": {
"description": "Label name.",
"type": "string"
},
"maxItems": 100,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"rocType": {
"description": "Type of ROC.",
"enum": [
"binary",
"labelwise"
],
"type": "string"
},
"totalCount": {
"description": "Total number of labels across all pages.",
"type": "integer"
}
},
"required": [
"averageModelMetrics",
"charts",
"labels",
"next",
"previous",
"rocType",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| averageModelMetrics |
AverageModelMetricsField |
true |
|
All average model metrics from one data source. |
| charts |
[LabelwiseROCItem] |
true |
|
ROC data for all labels from one data source. |
| count |
integer |
false |
|
Number of labels returned on this page. |
| labels |
[string] |
true |
maxItems: 100
|
All available target labels for this insight. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| rocType |
string |
true |
|
Type of ROC. |
| totalCount |
integer |
true |
|
Total number of labels across all pages. |
Enumerated Values
| Property |
Value |
| rocType |
[binary, labelwise] |
LabelwiseROCItem
{
"properties": {
"auc": {
"description": "Area under the curve.",
"type": "number"
},
"kolmogorovSmirnovMetric": {
"description": "Kolmogorov-Smirnov metric.",
"type": "number"
},
"label": {
"description": "Label name.",
"type": "string"
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the positive class.",
"items": {
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "ROC characteristics for label.",
"items": {
"properties": {
"accuracy": {
"description": "Accuracy.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"falsePositiveRate": {
"description": "False positive rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"falsePositiveScore": {
"description": "False positive score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"fractionPredictedAsNegative": {
"description": "Fraction of negative predictions.",
"type": [
"number",
"null"
]
},
"fractionPredictedAsPositive": {
"description": "Fraction of positive predictions.",
"type": [
"number",
"null"
]
},
"liftNegative": {
"description": "Negative lift.",
"type": [
"number",
"null"
]
},
"liftPositive": {
"description": "Positive lift.",
"type": [
"number",
"null"
]
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"maximum": 1,
"minimum": -1,
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"threshold": {
"description": "Threshold.",
"maximum": 2,
"minimum": 0,
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"trueNegativeScore": {
"description": "True negative score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"truePositiveRate": {
"description": "True positive rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"truePositiveScore": {
"description": "True positive score.",
"minimum": 0,
"type": [
"integer",
"null"
]
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Data source of ROC characteristics.",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
}
},
"required": [
"auc",
"kolmogorovSmirnovMetric",
"label",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| auc |
number |
true |
|
Area under the curve. |
| kolmogorovSmirnovMetric |
number |
true |
|
Kolmogorov-Smirnov metric. |
| label |
string |
true |
|
Label name. |
| negativeClassPredictions |
[number] |
true |
|
List of example predictions for the negative class. |
| positiveClassPredictions |
[number] |
true |
|
List of example predictions for the positive class. |
| rocPoints |
[LabelwiseROCPoint] |
true |
|
ROC characteristics for label. |
| source |
string |
true |
|
Data source of ROC characteristics. |
Enumerated Values
| Property |
Value |
| source |
[validation, crossValidation, holdout] |
LabelwiseROCPoint
{
"properties": {
"accuracy": {
"description": "Accuracy.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"falsePositiveRate": {
"description": "False positive rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"falsePositiveScore": {
"description": "False positive score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"fractionPredictedAsNegative": {
"description": "Fraction of negative predictions.",
"type": [
"number",
"null"
]
},
"fractionPredictedAsPositive": {
"description": "Fraction of positive predictions.",
"type": [
"number",
"null"
]
},
"liftNegative": {
"description": "Negative lift.",
"type": [
"number",
"null"
]
},
"liftPositive": {
"description": "Positive lift.",
"type": [
"number",
"null"
]
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"maximum": 1,
"minimum": -1,
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"threshold": {
"description": "Threshold.",
"maximum": 2,
"minimum": 0,
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"trueNegativeScore": {
"description": "True negative score.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"truePositiveRate": {
"description": "True positive rate.",
"maximum": 1,
"minimum": 0,
"type": [
"number",
"null"
]
},
"truePositiveScore": {
"description": "True positive score.",
"minimum": 0,
"type": [
"integer",
"null"
]
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| accuracy |
number |
true |
maximum: 1
minimum: 0
|
Accuracy. |
| f1Score |
number |
true |
maximum: 1
minimum: 0
|
F1 score. |
| falseNegativeScore |
integer,null |
true |
minimum: 0
|
False negative score. |
| falsePositiveRate |
number,null |
true |
maximum: 1
minimum: 0
|
False positive rate. |
| falsePositiveScore |
integer,null |
true |
minimum: 0
|
False positive score. |
| fractionPredictedAsNegative |
number,null |
true |
|
Fraction of negative predictions. |
| fractionPredictedAsPositive |
number,null |
true |
|
Fraction of positive predictions. |
| liftNegative |
number,null |
true |
|
Negative lift. |
| liftPositive |
number,null |
true |
|
Positive lift. |
| matthewsCorrelationCoefficient |
number |
true |
maximum: 1
minimum: -1
|
Matthews correlation coefficient. |
| negativePredictiveValue |
number |
true |
maximum: 1
minimum: 0
|
Negative predictive value. |
| positivePredictiveValue |
number |
true |
maximum: 1
minimum: 0
|
Positive predictive value. |
| threshold |
number |
true |
maximum: 2
minimum: 0
|
Threshold. |
| trueNegativeRate |
number,null |
true |
maximum: 1
minimum: 0
|
True negative rate. |
| trueNegativeScore |
integer,null |
true |
minimum: 0
|
True negative score. |
| truePositiveRate |
number,null |
true |
maximum: 1
minimum: 0
|
True positive rate. |
| truePositiveScore |
integer,null |
true |
minimum: 0
|
True positive score. |
LiftBinResponse
{
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actual |
number |
true |
|
The average of the actual target values for the rows in the bin. |
| binWeight |
number |
true |
|
How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin. |
| predicted |
number |
true |
|
The average of predicted values of the target for the rows in the bin. |
LiftChartForDatasetsList
{
"properties": {
"count": {
"description": "Number of results returned on this page.",
"type": "integer"
},
"data": {
"description": "Array of lift chart data for dataset, as specified below",
"items": {
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"datasetId": {
"description": "The dataset id of dataset which was used to compute Lift chart.",
"type": "string"
}
},
"required": [
"bins",
"datasetId"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"count",
"data",
"next",
"previous"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
Number of results returned on this page. |
| data |
[LiftData] |
true |
|
Array of lift chart data for dataset, as specified below |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
LiftChartResponse
{
"description": "Lift chart data.",
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"bins"
],
"type": "object"
}
Lift chart data.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[LiftBinResponse] |
true |
|
The lift chart data for that source, as specified below. |
LiftChartbins
{
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actual |
number |
true |
|
The average of the actual target values for the rows in the bin. |
| binWeight |
number |
true |
|
How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin. |
| predicted |
number |
true |
|
The average of predicted values of the target for the rows in the bin. |
LiftData
{
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"datasetId": {
"description": "The dataset id of dataset which was used to compute Lift chart.",
"type": "string"
}
},
"required": [
"bins",
"datasetId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[LiftChartbins] |
true |
|
The lift chart data for that source, as specified below. |
| datasetId |
string |
true |
|
The dataset id of dataset which was used to compute Lift chart. |
ModelConfusionChartClassDetailsForDatasetRetrieve
{
"properties": {
"actualFrequency": {
"description": "One vs All actual percentage and count in a format specified below sorted by percentage in decreasing order",
"items": {
"properties": {
"otherClassName": {
"description": "The name of the class.",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className` (from 0 to 100).",
"maximum": 100,
"minimum": 0,
"type": "number"
},
"value": {
"description": "The count of the times this class was predicted when is was actually `classMetrics.className`.",
"minimum": 0,
"type": "integer"
}
},
"required": [
"otherClassName",
"percentage",
"value"
],
"type": "object"
},
"type": "array"
},
"className": {
"description": "Name of a class for which distribution frequency is requested",
"type": "string"
},
"datasetId": {
"description": "The dataset to retrieve a Confusion chart from.",
"type": "string"
},
"modelId": {
"description": "The model to retrieve a Confusion chart from.",
"type": "string"
},
"predictedFrequency": {
"description": "One vs All predicted percentage and count in a format specified below sorted by percentage in decreasing order",
"items": {
"properties": {
"otherClassName": {
"description": "The name of the class.",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted (from 0 to 100)",
"maximum": 100,
"minimum": 0,
"type": "number"
},
"value": {
"description": "The count of the times this class was actual `classMetrics.className` when it was predicted",
"minimum": 0,
"type": "integer"
}
},
"required": [
"otherClassName",
"percentage",
"value"
],
"type": "object"
},
"type": "array"
},
"projectId": {
"description": "The project to retrieve a Confusion chart from.",
"type": "string"
}
},
"required": [
"actualFrequency",
"className",
"datasetId",
"modelId",
"predictedFrequency",
"projectId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actualFrequency |
[ActualFrequency] |
true |
|
One vs All actual percentage and count in a format specified below sorted by percentage in decreasing order |
| className |
string |
true |
|
Name of a class for which distribution frequency is requested |
| datasetId |
string |
true |
|
The dataset to retrieve a Confusion chart from. |
| modelId |
string |
true |
|
The model to retrieve a Confusion chart from. |
| predictedFrequency |
[PredictedFrequency] |
true |
|
One vs All predicted percentage and count in a format specified below sorted by percentage in decreasing order |
| projectId |
string |
true |
|
The project to retrieve a Confusion chart from. |
ModelConfusionChartClassDetailsRetrieveReponseController
{
"properties": {
"actualFrequency": {
"description": "One vs all actual percentage and count in a format specified below sorted by percentage in decreasing order",
"items": {
"properties": {
"otherClassName": {
"description": "The name of the class.",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className` (from 0 to 100).",
"maximum": 100,
"minimum": 0,
"type": "number"
},
"value": {
"description": "The count of the times this class was predicted when is was actually `classMetrics.className`.",
"minimum": 0,
"type": "integer"
}
},
"required": [
"otherClassName",
"percentage",
"value"
],
"type": "object"
},
"type": "array"
},
"className": {
"description": "Name of a class for which distribution frequency is requested.",
"type": "string"
},
"predictedFrequency": {
"description": "One vs all predicted percentage and count in a format specified below sorted by percentage in decreasing order",
"items": {
"properties": {
"otherClassName": {
"description": "The name of the class.",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted (from 0 to 100)",
"maximum": 100,
"minimum": 0,
"type": "number"
},
"value": {
"description": "The count of the times this class was actual `classMetrics.className` when it was predicted",
"minimum": 0,
"type": "integer"
}
},
"required": [
"otherClassName",
"percentage",
"value"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualFrequency",
"className",
"predictedFrequency"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actualFrequency |
[ActualFrequency] |
true |
|
One vs all actual percentage and count in a format specified below sorted by percentage in decreasing order |
| className |
string |
true |
|
Name of a class for which distribution frequency is requested. |
| predictedFrequency |
[PredictedFrequency] |
true |
|
One vs all predicted percentage and count in a format specified below sorted by percentage in decreasing order |
ModelConfusionChartListResponse
{
"properties": {
"charts": {
"description": "Chart data from all available sources.",
"items": {
"properties": {
"columns": {
"description": "[colStart, colEnd] column dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"data": {
"description": "confusion chart data with the format below.",
"properties": {
"classMetrics": {
"description": "per-class information including one vs all scores in a format specified below",
"items": {
"properties": {
"actualCount": {
"description": "number of times this class is seen in the validation data",
"type": "integer"
},
"className": {
"description": "name of the class",
"type": "string"
},
"confusionMatrixOneVsAll": {
"description": "2d array representing 2x2 one vs all matrix. This represents the True/False Negative/Positive rates as integer for each class. The data structure looks like: ``[ [ True Negative, False Positive ], [ False Negative, True Positive ] ]``",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"f1": {
"description": "F1 score",
"type": "number"
},
"precision": {
"description": "precision score",
"type": "number"
},
"predictedCount": {
"description": "number of times this class has been predicted for the validation data",
"type": "integer"
},
"recall": {
"description": "recall score",
"type": "number"
},
"wasActualPercentages": {
"description": "one vs all actual percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className`",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
},
"wasPredictedPercentages": {
"description": "one vs all predicted percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualCount",
"className",
"confusionMatrixOneVsAll",
"f1",
"precision",
"predictedCount",
"recall",
"wasActualPercentages",
"wasPredictedPercentages"
],
"type": "object"
},
"type": "array"
},
"classes": {
"description": "class labels from the dataset, union of row classes & column classes. This field is deprecated as of v2.13. The rows and columns may have different class labels when using query parameters to retrieve a slice of the matrix; please use 'rowClasses' and 'colClasses' instead.",
"items": {
"type": "string"
},
"type": "array"
},
"colClasses": {
"description": "class labels on columns of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
},
"confusionMatrix": {
"description": "2d array of ints representing confusion matrix, aligned with `rowClasses` and 'colClasses'array. For confusionMatrix[A][B] we can get an integer that represents the number of times 'if class with index A was correct we have class with index B predicted' (if the orientation is 'actual').",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"rowClasses": {
"description": "class labels on rows of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"classMetrics",
"classes",
"colClasses",
"confusionMatrix",
"rowClasses"
],
"type": "object"
},
"globalMetrics": {
"description": "average metrics across all classes",
"properties": {
"f1": {
"description": "Average F1 score",
"type": "number"
},
"precision": {
"description": "Average precision score",
"type": "number"
},
"recall": {
"description": "Avergae recall score",
"type": "number"
}
},
"required": [
"f1",
"precision",
"recall"
],
"type": "object"
},
"numberOfClasses": {
"description": "count of classes in full confusion matrix.",
"type": "integer"
},
"rows": {
"description": "[rowStart, rowEnd] row dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"source": {
"description": "source of the chart",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
},
"totalMatrixSum": {
"description": "sum of all values in full confusion matrix",
"type": "integer"
}
},
"required": [
"columns",
"data",
"globalMetrics",
"numberOfClasses",
"rows",
"source",
"totalMatrixSum"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"charts"
],
"type": "object"
}
Properties
{
"properties": {
"classNames": {
"description": "List of all class names in the full confusion matrix, sorted by the `orderBy` parameter",
"items": {
"type": "string"
},
"type": "array"
},
"globalMetrics": {
"description": "average metrics across all classes",
"properties": {
"f1": {
"description": "Average F1 score",
"type": "number"
},
"precision": {
"description": "Average precision score",
"type": "number"
},
"recall": {
"description": "Avergae recall score",
"type": "number"
}
},
"required": [
"f1",
"precision",
"recall"
],
"type": "object"
},
"relevantClassesPositions": {
"description": "Matrix to highlight important cell blocks in the confusion chart. Intended to represent a thumbnail view, where the relevantClassesPositions array has a 1 in thumbnail cells that are of interest, and 0 otherwise. The dimensions of the implied thumbnail will not match those of the confusion matrix, e.g. a twenty-class confusion matrix may have a 2x2 thumbnail.",
"items": {
"items": {
"maximum": 1,
"minimum": 0,
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"source": {
"description": "Source of the chart.",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
},
"totalMatrixSum": {
"description": "Sum of all values in the full confusion matrix (equal to the number of points considered)",
"minimum": 0,
"type": "integer"
}
},
"required": [
"classNames",
"globalMetrics",
"relevantClassesPositions",
"source",
"totalMatrixSum"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| classNames |
[string] |
true |
|
List of all class names in the full confusion matrix, sorted by the orderBy parameter |
| globalMetrics |
GlobalMetrics |
true |
|
average metrics across all classes |
| relevantClassesPositions |
[array] |
true |
|
Matrix to highlight important cell blocks in the confusion chart. Intended to represent a thumbnail view, where the relevantClassesPositions array has a 1 in thumbnail cells that are of interest, and 0 otherwise. The dimensions of the implied thumbnail will not match those of the confusion matrix, e.g. a twenty-class confusion matrix may have a 2x2 thumbnail. |
| source |
string |
true |
|
Source of the chart. |
| totalMatrixSum |
integer |
true |
minimum: 0
|
Sum of all values in the full confusion matrix (equal to the number of points considered) |
Enumerated Values
| Property |
Value |
| source |
[validation, crossValidation, holdout] |
ModelConfusionChartRetrieveResponse
{
"properties": {
"columns": {
"description": "[colStart, colEnd] column dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"data": {
"description": "confusion chart data with the format below.",
"properties": {
"classMetrics": {
"description": "per-class information including one vs all scores in a format specified below",
"items": {
"properties": {
"actualCount": {
"description": "number of times this class is seen in the validation data",
"type": "integer"
},
"className": {
"description": "name of the class",
"type": "string"
},
"confusionMatrixOneVsAll": {
"description": "2d array representing 2x2 one vs all matrix. This represents the True/False Negative/Positive rates as integer for each class. The data structure looks like: ``[ [ True Negative, False Positive ], [ False Negative, True Positive ] ]``",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"f1": {
"description": "F1 score",
"type": "number"
},
"precision": {
"description": "precision score",
"type": "number"
},
"predictedCount": {
"description": "number of times this class has been predicted for the validation data",
"type": "integer"
},
"recall": {
"description": "recall score",
"type": "number"
},
"wasActualPercentages": {
"description": "one vs all actual percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "The percentage of the times this class was predicted when is was actually `classMetrics.className`",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
},
"wasPredictedPercentages": {
"description": "one vs all predicted percentages in a format specified below",
"items": {
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"actualCount",
"className",
"confusionMatrixOneVsAll",
"f1",
"precision",
"predictedCount",
"recall",
"wasActualPercentages",
"wasPredictedPercentages"
],
"type": "object"
},
"type": "array"
},
"classes": {
"description": "class labels from the dataset, union of row classes & column classes. This field is deprecated as of v2.13. The rows and columns may have different class labels when using query parameters to retrieve a slice of the matrix; please use 'rowClasses' and 'colClasses' instead.",
"items": {
"type": "string"
},
"type": "array"
},
"colClasses": {
"description": "class labels on columns of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
},
"confusionMatrix": {
"description": "2d array of ints representing confusion matrix, aligned with `rowClasses` and 'colClasses'array. For confusionMatrix[A][B] we can get an integer that represents the number of times 'if class with index A was correct we have class with index B predicted' (if the orientation is 'actual').",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
},
"rowClasses": {
"description": "class labels on rows of confusion matrix",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"classMetrics",
"classes",
"colClasses",
"confusionMatrix",
"rowClasses"
],
"type": "object"
},
"globalMetrics": {
"description": "average metrics across all classes",
"properties": {
"f1": {
"description": "Average F1 score",
"type": "number"
},
"precision": {
"description": "Average precision score",
"type": "number"
},
"recall": {
"description": "Avergae recall score",
"type": "number"
}
},
"required": [
"f1",
"precision",
"recall"
],
"type": "object"
},
"numberOfClasses": {
"description": "count of classes in full confusion matrix.",
"type": "integer"
},
"rows": {
"description": "[rowStart, rowEnd] row dimension of confusion matrix in response",
"items": {
"type": "integer"
},
"type": "array"
},
"source": {
"description": "source of the chart",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
},
"totalMatrixSum": {
"description": "sum of all values in full confusion matrix",
"type": "integer"
}
},
"required": [
"columns",
"data",
"globalMetrics",
"numberOfClasses",
"rows",
"source",
"totalMatrixSum"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| columns |
[integer] |
true |
|
[colStart, colEnd] column dimension of confusion matrix in response |
| data |
ConfusionChartData |
true |
|
confusion chart data with the format below. |
| globalMetrics |
GlobalMetrics |
true |
|
average metrics across all classes |
| numberOfClasses |
integer |
true |
|
count of classes in full confusion matrix. |
| rows |
[integer] |
true |
|
[rowStart, rowEnd] row dimension of confusion matrix in response |
| source |
string |
true |
|
source of the chart |
| totalMatrixSum |
integer |
true |
|
sum of all values in full confusion matrix |
Enumerated Values
| Property |
Value |
| source |
[validation, crossValidation, holdout] |
ModelLifecycle
{
"description": "Object returning model lifecycle.",
"properties": {
"reason": {
"description": "Reason for lifecycle stage. None if model is active.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.30"
},
"stage": {
"description": "Model lifecycle stage.",
"enum": [
"active",
"deprecated",
"disabled"
],
"type": "string",
"x-versionadded": "v2.30"
}
},
"required": [
"reason",
"stage"
],
"type": "object"
}
Object returning model lifecycle.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| reason |
string,null |
true |
|
Reason for lifecycle stage. None if model is active. |
| stage |
string |
true |
|
Model lifecycle stage. |
Enumerated Values
| Property |
Value |
| stage |
[active, deprecated, disabled] |
ModelLiftChartListResponse
{
"properties": {
"charts": {
"description": "List of lift chart data from all available sources.",
"items": {
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data.",
"enum": [
"validation",
"crossValidation",
"holdout",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string",
"x-enum-versionadded": [
{
"value": "backtest_2",
"x-versionadded": "v2.23"
},
{
"value": "backtest_3",
"x-versionadded": "v2.23"
},
{
"value": "backtest_4",
"x-versionadded": "v2.23"
},
{
"value": "backtest_5",
"x-versionadded": "v2.23"
},
{
"value": "backtest_6",
"x-versionadded": "v2.23"
},
{
"value": "backtest_7",
"x-versionadded": "v2.23"
},
{
"value": "backtest_8",
"x-versionadded": "v2.23"
},
{
"value": "backtest_9",
"x-versionadded": "v2.23"
},
{
"value": "backtest_10",
"x-versionadded": "v2.23"
},
{
"value": "backtest_11",
"x-versionadded": "v2.23"
},
{
"value": "backtest_12",
"x-versionadded": "v2.23"
},
{
"value": "backtest_13",
"x-versionadded": "v2.23"
},
{
"value": "backtest_14",
"x-versionadded": "v2.23"
},
{
"value": "backtest_15",
"x-versionadded": "v2.23"
},
{
"value": "backtest_16",
"x-versionadded": "v2.23"
},
{
"value": "backtest_17",
"x-versionadded": "v2.23"
},
{
"value": "backtest_18",
"x-versionadded": "v2.23"
},
{
"value": "backtest_19",
"x-versionadded": "v2.23"
},
{
"value": "backtest_20",
"x-versionadded": "v2.23"
}
]
}
},
"required": [
"bins",
"source"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"charts"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| charts |
[ModelLiftChartResponse] |
true |
|
List of lift chart data from all available sources. |
ModelLiftChartResponse
{
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data.",
"enum": [
"validation",
"crossValidation",
"holdout",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string",
"x-enum-versionadded": [
{
"value": "backtest_2",
"x-versionadded": "v2.23"
},
{
"value": "backtest_3",
"x-versionadded": "v2.23"
},
{
"value": "backtest_4",
"x-versionadded": "v2.23"
},
{
"value": "backtest_5",
"x-versionadded": "v2.23"
},
{
"value": "backtest_6",
"x-versionadded": "v2.23"
},
{
"value": "backtest_7",
"x-versionadded": "v2.23"
},
{
"value": "backtest_8",
"x-versionadded": "v2.23"
},
{
"value": "backtest_9",
"x-versionadded": "v2.23"
},
{
"value": "backtest_10",
"x-versionadded": "v2.23"
},
{
"value": "backtest_11",
"x-versionadded": "v2.23"
},
{
"value": "backtest_12",
"x-versionadded": "v2.23"
},
{
"value": "backtest_13",
"x-versionadded": "v2.23"
},
{
"value": "backtest_14",
"x-versionadded": "v2.23"
},
{
"value": "backtest_15",
"x-versionadded": "v2.23"
},
{
"value": "backtest_16",
"x-versionadded": "v2.23"
},
{
"value": "backtest_17",
"x-versionadded": "v2.23"
},
{
"value": "backtest_18",
"x-versionadded": "v2.23"
},
{
"value": "backtest_19",
"x-versionadded": "v2.23"
},
{
"value": "backtest_20",
"x-versionadded": "v2.23"
}
]
}
},
"required": [
"bins",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[LiftBinResponse] |
true |
|
The lift chart data for that source, as specified below. |
| source |
string |
true |
|
Source of the data. |
Enumerated Values
| Property |
Value |
| source |
[validation, crossValidation, holdout, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
ModelResidualsChartData
{
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
}
Chart data from the validation data source
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| coefficientOfDetermination |
number |
true |
|
Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input |
| data |
[array] |
true |
|
The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. NOTE: In DataRobot v5.2, the row number will not be included. |
| histogram |
[ModelResidualsHistogram] |
true |
|
Data to plot a histogram of residual values |
| residualMean |
number |
true |
|
The arithmetic mean of the predicted value minus the actual value over the downsampled dataset |
| standardDeviation |
number |
true |
|
A measure of deviation from the group as a whole |
ModelResidualsHistogram
{
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| intervalEnd |
number |
true |
|
The interval end. For all but the last interval, the end value is exclusive. |
| intervalStart |
number |
true |
|
The interval start. |
| occurrences |
integer |
true |
|
The number of times the predicted value fits within the interval |
ModelResidualsList
{
"properties": {
"residuals": {
"description": "Residuals chart data from all available sources",
"properties": {
"crossValidation": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"holdout": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"validation": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
}
},
"type": "object"
}
},
"required": [
"residuals"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| residuals |
ModelResidualsSource |
true |
|
Residuals chart data from all available sources |
ModelResidualsSource
{
"description": "Residuals chart data from all available sources",
"properties": {
"crossValidation": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"holdout": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"validation": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
}
},
"type": "object"
}
Residuals chart data from all available sources
Properties
ModelRocCurveListResponse
{
"properties": {
"charts": {
"description": "List of ROC curve data from all available sources.",
"items": {
"properties": {
"auc": {
"description": "AUC value",
"type": [
"number",
"null"
]
},
"kolmogorovSmirnovMetric": {
"description": "Kolmogorov-Smirnov metric value",
"type": [
"number",
"null"
]
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the positive class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "The ROC curve data for that source, as specified below.",
"items": {
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data.",
"enum": [
"validation",
"crossValidation",
"holdout",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string",
"x-enum-versionadded": [
{
"value": "backtest_2",
"x-versionadded": "v2.23"
},
{
"value": "backtest_3",
"x-versionadded": "v2.23"
},
{
"value": "backtest_4",
"x-versionadded": "v2.23"
},
{
"value": "backtest_5",
"x-versionadded": "v2.23"
},
{
"value": "backtest_6",
"x-versionadded": "v2.23"
},
{
"value": "backtest_7",
"x-versionadded": "v2.23"
},
{
"value": "backtest_8",
"x-versionadded": "v2.23"
},
{
"value": "backtest_9",
"x-versionadded": "v2.23"
},
{
"value": "backtest_10",
"x-versionadded": "v2.23"
},
{
"value": "backtest_11",
"x-versionadded": "v2.23"
},
{
"value": "backtest_12",
"x-versionadded": "v2.23"
},
{
"value": "backtest_13",
"x-versionadded": "v2.23"
},
{
"value": "backtest_14",
"x-versionadded": "v2.23"
},
{
"value": "backtest_15",
"x-versionadded": "v2.23"
},
{
"value": "backtest_16",
"x-versionadded": "v2.23"
},
{
"value": "backtest_17",
"x-versionadded": "v2.23"
},
{
"value": "backtest_18",
"x-versionadded": "v2.23"
},
{
"value": "backtest_19",
"x-versionadded": "v2.23"
},
{
"value": "backtest_20",
"x-versionadded": "v2.23"
}
]
}
},
"required": [
"auc",
"kolmogorovSmirnovMetric",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints",
"source"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"charts"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| charts |
[ModelRocCurveResponse] |
true |
|
List of ROC curve data from all available sources. |
ModelRocCurveResponse
{
"properties": {
"auc": {
"description": "AUC value",
"type": [
"number",
"null"
]
},
"kolmogorovSmirnovMetric": {
"description": "Kolmogorov-Smirnov metric value",
"type": [
"number",
"null"
]
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the positive class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "The ROC curve data for that source, as specified below.",
"items": {
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data.",
"enum": [
"validation",
"crossValidation",
"holdout",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string",
"x-enum-versionadded": [
{
"value": "backtest_2",
"x-versionadded": "v2.23"
},
{
"value": "backtest_3",
"x-versionadded": "v2.23"
},
{
"value": "backtest_4",
"x-versionadded": "v2.23"
},
{
"value": "backtest_5",
"x-versionadded": "v2.23"
},
{
"value": "backtest_6",
"x-versionadded": "v2.23"
},
{
"value": "backtest_7",
"x-versionadded": "v2.23"
},
{
"value": "backtest_8",
"x-versionadded": "v2.23"
},
{
"value": "backtest_9",
"x-versionadded": "v2.23"
},
{
"value": "backtest_10",
"x-versionadded": "v2.23"
},
{
"value": "backtest_11",
"x-versionadded": "v2.23"
},
{
"value": "backtest_12",
"x-versionadded": "v2.23"
},
{
"value": "backtest_13",
"x-versionadded": "v2.23"
},
{
"value": "backtest_14",
"x-versionadded": "v2.23"
},
{
"value": "backtest_15",
"x-versionadded": "v2.23"
},
{
"value": "backtest_16",
"x-versionadded": "v2.23"
},
{
"value": "backtest_17",
"x-versionadded": "v2.23"
},
{
"value": "backtest_18",
"x-versionadded": "v2.23"
},
{
"value": "backtest_19",
"x-versionadded": "v2.23"
},
{
"value": "backtest_20",
"x-versionadded": "v2.23"
}
]
}
},
"required": [
"auc",
"kolmogorovSmirnovMetric",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| auc |
number,null |
true |
|
AUC value |
| kolmogorovSmirnovMetric |
number,null |
true |
|
Kolmogorov-Smirnov metric value |
| negativeClassPredictions |
[number] |
true |
|
List of example predictions for the negative class. |
| positiveClassPredictions |
[number] |
true |
|
List of example predictions for the positive class. |
| rocPoints |
[RocPointsResponse] |
true |
|
The ROC curve data for that source, as specified below. |
| source |
string |
true |
|
Source of the data. |
Enumerated Values
| Property |
Value |
| source |
[validation, crossValidation, holdout, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
{
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`, `startstop`.",
"type": "string"
},
"sources": {
"description": "List of sources available for the model.",
"items": {
"enum": [
"training",
"validation",
"holdout"
],
"type": "string"
},
"type": "array"
},
"status": {
"description": "Status of the job.",
"enum": [
"INPROGRESS",
"COMPLETED",
"NOT_COMPLETED"
],
"type": "string"
}
},
"required": [
"backtestIndex",
"sources",
"status"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestIndex |
string |
true |
|
The backtest index. For example: 0, 1, ..., 20, holdout, startstop. |
| sources |
[string] |
true |
|
List of sources available for the model. |
| status |
string |
true |
|
Status of the job. |
Enumerated Values
| Property |
Value |
| status |
[INPROGRESS, COMPLETED, NOT_COMPLETED] |
{
"properties": {
"data": {
"description": "List of objects with status and sources of each backtest.",
"items": {
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`, `startstop`.",
"type": "string"
},
"sources": {
"description": "List of sources available for the model.",
"items": {
"enum": [
"training",
"validation",
"holdout"
],
"type": "string"
},
"type": "array"
},
"status": {
"description": "Status of the job.",
"enum": [
"INPROGRESS",
"COMPLETED",
"NOT_COMPLETED"
],
"type": "string"
}
},
"required": [
"backtestIndex",
"sources",
"status"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data"
],
"type": "object"
}
Properties
{
"properties": {
"sources": {
"description": "List of sources available for the model.",
"items": {
"enum": [
"training",
"validation",
"holdout"
],
"type": "string"
},
"type": "array"
},
"status": {
"description": "Status of the job.",
"enum": [
"INPROGRESS",
"COMPLETED",
"NOT_COMPLETED"
],
"type": "string"
}
},
"required": [
"sources",
"status"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| sources |
[string] |
true |
|
List of sources available for the model. |
| status |
string |
true |
|
Status of the job. |
Enumerated Values
| Property |
Value |
| status |
[INPROGRESS, COMPLETED, NOT_COMPLETED] |
MulticategoricalHistogram
{
"properties": {
"featureName": {
"description": "Feature name.",
"type": "string"
},
"histogram": {
"description": "Feature histogram.",
"items": {
"properties": {
"label": {
"description": "Label name.",
"type": "string"
},
"plot": {
"description": "Relevance histogram for label.",
"items": {
"properties": {
"labelRelevance": {
"description": "Label relevance value.",
"maximum": 1,
"minimum": 0,
"type": "integer"
},
"rowCount": {
"description": "Number of rows for which the label has the given relevance.",
"minimum": 0,
"type": "integer"
},
"rowPct": {
"description": "Percentage of rows for which the label has the given relevance.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"labelRelevance",
"rowCount",
"rowPct"
],
"type": "object"
},
"maxItems": 2,
"minItems": 2,
"type": "array"
}
},
"required": [
"label",
"plot"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
},
"projectId": {
"description": "Project Id.",
"type": "string"
}
},
"required": [
"featureName",
"histogram",
"projectId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureName |
string |
true |
|
Feature name. |
| histogram |
[MulticategoricalHistogramItem] |
true |
maxItems: 1000
minItems: 1
|
Feature histogram. |
| projectId |
string |
true |
|
Project Id. |
MulticategoricalHistogramItem
{
"properties": {
"label": {
"description": "Label name.",
"type": "string"
},
"plot": {
"description": "Relevance histogram for label.",
"items": {
"properties": {
"labelRelevance": {
"description": "Label relevance value.",
"maximum": 1,
"minimum": 0,
"type": "integer"
},
"rowCount": {
"description": "Number of rows for which the label has the given relevance.",
"minimum": 0,
"type": "integer"
},
"rowPct": {
"description": "Percentage of rows for which the label has the given relevance.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"labelRelevance",
"rowCount",
"rowPct"
],
"type": "object"
},
"maxItems": 2,
"minItems": 2,
"type": "array"
}
},
"required": [
"label",
"plot"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| label |
string |
true |
|
Label name. |
| plot |
[LabelRelevancePlot] |
true |
maxItems: 2
minItems: 2
|
Relevance histogram for label. |
{
"description": "Error data.",
"properties": {
"errors": {
"description": "Multicategorical format errors.",
"items": {
"properties": {
"error": {
"description": "Error type.",
"type": "string"
},
"feature": {
"description": "Feature name.",
"type": "string"
},
"rowData": {
"description": "Content of the row containing format error.",
"type": [
"string",
"null"
]
},
"rowIndex": {
"description": "Row index of the row containing format error.",
"type": [
"integer",
"null"
]
}
},
"required": [
"error",
"feature",
"rowData",
"rowIndex"
],
"type": "object"
},
"maxItems": 100,
"type": "array"
}
},
"required": [
"errors"
],
"type": "object"
}
Error data.
Properties
{
"properties": {
"error": {
"description": "Error type.",
"type": "string"
},
"feature": {
"description": "Feature name.",
"type": "string"
},
"rowData": {
"description": "Content of the row containing format error.",
"type": [
"string",
"null"
]
},
"rowIndex": {
"description": "Row index of the row containing format error.",
"type": [
"integer",
"null"
]
}
},
"required": [
"error",
"feature",
"rowData",
"rowIndex"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| error |
string |
true |
|
Error type. |
| feature |
string |
true |
|
Feature name. |
| rowData |
string,null |
true |
|
Content of the row containing format error. |
| rowIndex |
integer,null |
true |
|
Row index of the row containing format error. |
{
"properties": {
"data": {
"description": "Error data.",
"properties": {
"errors": {
"description": "Multicategorical format errors.",
"items": {
"properties": {
"error": {
"description": "Error type.",
"type": "string"
},
"feature": {
"description": "Feature name.",
"type": "string"
},
"rowData": {
"description": "Content of the row containing format error.",
"type": [
"string",
"null"
]
},
"rowIndex": {
"description": "Row index of the row containing format error.",
"type": [
"integer",
"null"
]
}
},
"required": [
"error",
"feature",
"rowData",
"rowIndex"
],
"type": "object"
},
"maxItems": 100,
"type": "array"
}
},
"required": [
"errors"
],
"type": "object"
},
"projectId": {
"description": "The ID of the project this request is associated with.",
"type": "string"
}
},
"required": [
"data",
"projectId"
],
"type": "object"
}
Properties
MulticlassDatetimeFeatureEffectsResponse
{
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`, `startstop`.",
"type": "string"
},
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "A list of feature effects scores for each class in multiclass project.",
"items": {
"properties": {
"class": {
"description": "Target class label.",
"type": "string"
},
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"class",
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model ID",
"type": "string"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID",
"type": "string"
},
"source": {
"description": "Models data source.",
"type": "string"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"backtestIndex",
"data",
"modelId",
"next",
"previous",
"projectId",
"source",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestIndex |
string |
true |
|
The backtest index. For example: 0, 1, ..., 20, holdout, startstop. |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[MulticlassFeatureEffects] |
true |
|
A list of feature effects scores for each class in multiclass project. |
| modelId |
string |
true |
|
The model ID |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| projectId |
string |
true |
|
The project ID |
| source |
string |
true |
|
Models data source. |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
MulticlassFeatureEffectCreate
{
"properties": {
"features": {
"description": "The list of features to use to calculate feature effects.",
"items": {
"type": "string"
},
"maxItems": 20000,
"type": "array"
},
"rowCount": {
"description": "The number of rows from dataset to use for Feature Impact calculation.",
"maximum": 100000,
"minimum": 10,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.21"
},
"topNFeatures": {
"description": "Number of top features (ranked by feature impact) to use to calculate feature effects.",
"exclusiveMinimum": 0,
"maximum": 1000,
"type": [
"integer",
"null"
]
}
},
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| features |
[string] |
false |
maxItems: 20000
|
The list of features to use to calculate feature effects. |
| rowCount |
integer,null |
false |
maximum: 100000
minimum: 10
|
The number of rows from dataset to use for Feature Impact calculation. |
| topNFeatures |
integer,null |
false |
maximum: 1000
|
Number of top features (ranked by feature impact) to use to calculate feature effects. |
MulticlassFeatureEffectDatetimeCreate
{
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`, `startstop`.",
"type": "string"
},
"features": {
"description": "The list of features to use to calculate feature effects.",
"items": {
"type": "string"
},
"maxItems": 20000,
"type": "array"
},
"rowCount": {
"description": "The number of rows from dataset to use for Feature Impact calculation.",
"maximum": 100000,
"minimum": 10,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.21"
},
"topNFeatures": {
"description": "Number of top features (ranked by feature impact) to use to calculate feature effects.",
"exclusiveMinimum": 0,
"maximum": 1000,
"type": [
"integer",
"null"
]
}
},
"required": [
"backtestIndex"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestIndex |
string |
true |
|
The backtest index. For example: 0, 1, ..., 20, holdout, startstop. |
| features |
[string] |
false |
maxItems: 20000
|
The list of features to use to calculate feature effects. |
| rowCount |
integer,null |
false |
maximum: 100000
minimum: 10
|
The number of rows from dataset to use for Feature Impact calculation. |
| topNFeatures |
integer,null |
false |
maximum: 1000
|
Number of top features (ranked by feature impact) to use to calculate feature effects. |
MulticlassFeatureEffects
{
"properties": {
"class": {
"description": "Target class label.",
"type": "string"
},
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"class",
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| class |
string |
true |
|
Target class label. |
| featureImpactScore |
number |
true |
|
Feature impact score. |
| featureName |
string |
true |
|
Name of the feature. |
| featureType |
string |
true |
|
Feature type, either numeric or categorical. |
| isBinnable |
boolean |
true |
|
Whether values can be grouped into bins. |
| isScalable |
boolean,null |
true |
|
Whether numeric feature values can be reported on a log scale. |
| partialDependence |
PartialDependence |
false |
|
Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight. |
| predictedVsActual |
PredictedVsActual |
false |
|
Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight. |
| weightLabel |
string,null |
true |
|
Weight label if weight was configured for the project. |
MulticlassFeatureEffectsResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "A list of feature effects scores for each class in multiclass project.",
"items": {
"properties": {
"class": {
"description": "Target class label.",
"type": "string"
},
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"class",
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model ID",
"type": "string"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID",
"type": "string"
},
"source": {
"description": "Models data source.",
"type": "string"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"modelId",
"next",
"previous",
"projectId",
"source",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[MulticlassFeatureEffects] |
true |
|
A list of feature effects scores for each class in multiclass project. |
| modelId |
string |
true |
|
The model ID |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| projectId |
string |
true |
|
The project ID |
| source |
string |
true |
|
Models data source. |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
MulticlassFeatureImpact
{
"properties": {
"class": {
"description": "Target class label.",
"type": "string"
},
"featureImpacts": {
"description": "A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"parentFeatureName": {
"description": "The name of the parent feature.",
"type": [
"string",
"null"
]
},
"redundantWith": {
"description": "Name of feature that has the highest correlation with this feature.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized",
"redundantWith"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
}
},
"required": [
"class",
"featureImpacts"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| class |
string |
true |
|
Target class label. |
| featureImpacts |
[FeatureImpactItem] |
true |
maxItems: 1000
|
A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned. |
MulticlassFeatureImpactResponse
{
"properties": {
"classFeatureImpacts": {
"description": "A list of feature importance scores for each class in multiclass project.",
"items": {
"properties": {
"class": {
"description": "Target class label.",
"type": "string"
},
"featureImpacts": {
"description": "A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"parentFeatureName": {
"description": "The name of the parent feature.",
"type": [
"string",
"null"
]
},
"redundantWith": {
"description": "Name of feature that has the highest correlation with this feature.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized",
"redundantWith"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
}
},
"required": [
"class",
"featureImpacts"
],
"type": "object"
},
"type": "array"
},
"count": {
"description": "Number of feature impact records in a given batch.",
"type": "integer"
},
"next": {
"description": "URL for the next page of results or `null`.",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL for the next page of results or `null`.",
"format": "uri",
"type": [
"string",
"null"
]
},
"ranRedundancyDetection": {
"description": "Indicates whether redundant feature identification was run while calculating this feature impact. Currently always False, as redundant feature identification isn't supported for multiclass in DataRobot.",
"type": "boolean"
},
"shapBased": {
"description": "Indicates whether feature impact was calculated using Shapley values. Currently always `False`, as SHAP isn't supported for multiclass in DataRobot.",
"type": "boolean"
}
},
"required": [
"classFeatureImpacts",
"count",
"next",
"previous",
"ranRedundancyDetection",
"shapBased"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| classFeatureImpacts |
[MulticlassFeatureImpact] |
true |
|
A list of feature importance scores for each class in multiclass project. |
| count |
integer |
true |
|
Number of feature impact records in a given batch. |
| next |
string,null(uri) |
true |
|
URL for the next page of results or null. |
| previous |
string,null(uri) |
true |
|
URL for the next page of results or null. |
| ranRedundancyDetection |
boolean |
true |
|
Indicates whether redundant feature identification was run while calculating this feature impact. Currently always False, as redundant feature identification isn't supported for multiclass in DataRobot. |
| shapBased |
boolean |
true |
|
Indicates whether feature impact was calculated using Shapley values. Currently always False, as SHAP isn't supported for multiclass in DataRobot. |
MulticlassLiftBinResponse
{
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"targetClass": {
"description": "Target class for the lift chart.",
"type": "string"
}
},
"required": [
"bins",
"targetClass"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[LiftBinResponse] |
true |
|
The lift chart data for that source, as specified below. |
| targetClass |
string |
true |
|
Target class for the lift chart. |
MulticlassLiftChartForDatasetsList
{
"properties": {
"count": {
"description": "Number of results returned on this page.",
"type": "integer"
},
"data": {
"description": "Array of multiclass lift chart data for dataset, as specified below.",
"items": {
"properties": {
"classBins": {
"description": "List of lift chart data for each target class.",
"items": {
"properties": {
"bins": {
"description": "The lift chart data for that source and class, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"targetClass": {
"description": "The target class for the lift chart.",
"type": "string"
}
},
"required": [
"bins",
"targetClass"
],
"type": "object"
},
"type": "array"
},
"datasetId": {
"description": "The dataset id of dataset which was used to compute Lift chart.",
"type": "string"
}
},
"required": [
"classBins",
"datasetId"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model id to which the chart data belongs.",
"type": "string"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project id to which the chart data belongs.",
"type": "string"
},
"totalCount": {
"description": "Total count of multiclass lift charts matching to the query condition.",
"type": "integer"
}
},
"required": [
"count",
"data",
"modelId",
"next",
"previous",
"projectId",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
Number of results returned on this page. |
| data |
[MulticlassLiftData] |
true |
|
Array of multiclass lift chart data for dataset, as specified below. |
| modelId |
string |
true |
|
The model id to which the chart data belongs. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| projectId |
string |
true |
|
The project id to which the chart data belongs. |
| totalCount |
integer |
true |
|
Total count of multiclass lift charts matching to the query condition. |
MulticlassLiftData
{
"properties": {
"classBins": {
"description": "List of lift chart data for each target class.",
"items": {
"properties": {
"bins": {
"description": "The lift chart data for that source and class, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"targetClass": {
"description": "The target class for the lift chart.",
"type": "string"
}
},
"required": [
"bins",
"targetClass"
],
"type": "object"
},
"type": "array"
},
"datasetId": {
"description": "The dataset id of dataset which was used to compute Lift chart.",
"type": "string"
}
},
"required": [
"classBins",
"datasetId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| classBins |
[MulticlassLiftDataClassBins] |
true |
|
List of lift chart data for each target class. |
| datasetId |
string |
true |
|
The dataset id of dataset which was used to compute Lift chart. |
MulticlassLiftDataClassBins
{
"properties": {
"bins": {
"description": "The lift chart data for that source and class, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"targetClass": {
"description": "The target class for the lift chart.",
"type": "string"
}
},
"required": [
"bins",
"targetClass"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| bins |
[LiftChartbins] |
true |
|
The lift chart data for that source and class, as specified below. |
| targetClass |
string |
true |
|
The target class for the lift chart. |
MulticlassModelLiftChartResponse
{
"properties": {
"classBins": {
"description": "List of lift chart data for each target class.",
"items": {
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
},
"targetClass": {
"description": "Target class for the lift chart.",
"type": "string"
}
},
"required": [
"bins",
"targetClass"
],
"type": "object"
},
"type": "array"
},
"source": {
"description": "Source of the data",
"enum": [
"validation",
"crossValidation",
"holdout"
],
"type": "string"
}
},
"required": [
"classBins",
"source"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| classBins |
[MulticlassLiftBinResponse] |
true |
|
List of lift chart data for each target class. |
| source |
string |
true |
|
Source of the data |
Enumerated Values
| Property |
Value |
| source |
[validation, crossValidation, holdout] |
MultiseriesHistogramsBin
{
"properties": {
"count": {
"description": "The value count of the bin",
"type": "integer"
},
"left": {
"description": "The inclusive left boundary of the bin.",
"oneOf": [
{
"type": "number"
},
{
"type": "string"
}
]
},
"right": {
"description": "The exclusive right boundary of the bin. The last bin has an inclusive right boundary.",
"oneOf": [
{
"type": "number"
},
{
"type": "string"
}
]
}
},
"required": [
"count",
"left",
"right"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
The value count of the bin |
| left |
any |
true |
|
The inclusive left boundary of the bin. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
number |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| right |
any |
true |
|
The exclusive right boundary of the bin. The last bin has an inclusive right boundary. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
number |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
MultiseriesHistogramsRetrieveResponse
{
"properties": {
"bins": {
"description": "List of bins representing histogram.",
"items": {
"properties": {
"count": {
"description": "The value count of the bin",
"type": "integer"
},
"left": {
"description": "The inclusive left boundary of the bin.",
"oneOf": [
{
"type": "number"
},
{
"type": "string"
}
]
},
"right": {
"description": "The exclusive right boundary of the bin. The last bin has an inclusive right boundary.",
"oneOf": [
{
"type": "number"
},
{
"type": "string"
}
]
}
},
"required": [
"count",
"left",
"right"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"bins"
],
"type": "object"
}
Properties
Numeric
{
"properties": {
"allData": {
"description": "Statistic value for all data.",
"type": [
"number",
"null"
]
},
"insightName": {
"description": "Insight name.",
"enum": [
"min",
"max",
"median",
"avg",
"firstQuartile",
"thirdQuartile",
"missingRowsPercent"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for for each cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"statistic": {
"description": "Statistic value for this cluster.",
"type": [
"number",
"null"
]
}
},
"required": [
"clusterName",
"statistic"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| allData |
number,null |
true |
|
Statistic value for all data. |
| insightName |
string |
true |
|
Insight name. |
| perCluster |
[PerClusterNumeric] |
true |
|
Statistic values for for each cluster. |
Enumerated Values
| Property |
Value |
| insightName |
[min, max, median, avg, firstQuartile, thirdQuartile, missingRowsPercent] |
NumericFeature
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"numeric"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistic value for all data.",
"type": [
"number",
"null"
]
},
"insightName": {
"description": "Insight name.",
"enum": [
"min",
"max",
"median",
"avg",
"firstQuartile",
"thirdQuartile",
"missingRowsPercent"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for for each cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"statistic": {
"description": "Statistic value for this cluster.",
"type": [
"number",
"null"
]
}
},
"required": [
"clusterName",
"statistic"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureImpact |
number,null |
false |
|
Feature Impact score. |
| featureName |
string |
true |
|
Feature name. |
| featureType |
string |
true |
|
Feature Type. |
| insights |
[Numeric] |
true |
|
A list of Cluster Insights for a feature. |
Enumerated Values
| Property |
Value |
| featureType |
numeric |
PairwiseManualSelectionCreatePayload
{
"properties": {
"columnLabels": {
"description": "Manually selected column labels.",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
"featureName": {
"description": "Name of the feature the request is related to",
"type": [
"string",
"null"
]
},
"multilabelInsightsKey": {
"description": "Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename]",
"type": "string"
},
"name": {
"description": "Name for the set of manually selected labels.",
"maxLength": 100,
"type": "string"
},
"projectId": {
"description": "ID of the project the request is related to.",
"type": [
"string",
"null"
]
},
"rowLabels": {
"description": "Manually selected row labels.",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
}
},
"required": [
"columnLabels",
"featureName",
"multilabelInsightsKey",
"name",
"projectId",
"rowLabels"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| columnLabels |
[string] |
true |
maxItems: 10
minItems: 1
|
Manually selected column labels. |
| featureName |
string,null |
true |
|
Name of the feature the request is related to |
| multilabelInsightsKey |
string |
true |
|
Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename] |
| name |
string |
true |
maxLength: 100
|
Name for the set of manually selected labels. |
| projectId |
string,null |
true |
|
ID of the project the request is related to. |
| rowLabels |
[string] |
true |
maxItems: 10
minItems: 1
|
Manually selected row labels. |
PairwiseManualSelectionCreateResponse
{
"properties": {
"id": {
"description": "ID of the label set.",
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| id |
string |
true |
|
ID of the label set. |
PairwiseManualSelectionCreatedItem
{
"properties": {
"columnLabels": {
"description": "Manually selected column labels.",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
"id": {
"description": "Id of the manually selected labels set",
"type": "string"
},
"name": {
"description": "Name for the set of manually selected labels.",
"maxLength": 100,
"type": "string"
},
"rowLabels": {
"description": "Manually selected row labels.",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
}
},
"required": [
"columnLabels",
"id",
"name",
"rowLabels"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| columnLabels |
[string] |
true |
maxItems: 10
minItems: 1
|
Manually selected column labels. |
| id |
string |
true |
|
Id of the manually selected labels set |
| name |
string |
true |
maxLength: 100
|
Name for the set of manually selected labels. |
| rowLabels |
[string] |
true |
maxItems: 10
minItems: 1
|
Manually selected row labels. |
PairwiseManualSelectionResponse
{
"properties": {
"manualSelectionId": {
"description": "ID of the deleted or updated label set.",
"type": "string"
}
},
"required": [
"manualSelectionId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| manualSelectionId |
string |
true |
|
ID of the deleted or updated label set. |
PairwiseManualSelectionUpdateRequest
{
"properties": {
"name": {
"description": "Name for the set of manually selected labels.",
"maxLength": 100,
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| name |
string |
true |
maxLength: 100
|
Name for the set of manually selected labels. |
PairwiseManualSelectionsRetrieveResponse
{
"properties": {
"data": {
"description": "List of manually selected labels sets",
"items": {
"properties": {
"columnLabels": {
"description": "Manually selected column labels.",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
"id": {
"description": "Id of the manually selected labels set",
"type": "string"
},
"name": {
"description": "Name for the set of manually selected labels.",
"maxLength": 100,
"type": "string"
},
"rowLabels": {
"description": "Manually selected row labels.",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
}
},
"required": [
"columnLabels",
"id",
"name",
"rowLabels"
],
"type": "object"
},
"type": "array"
},
"featureName": {
"description": "Name of the feature the request is related to",
"type": [
"string",
"null"
]
},
"multilabelInsightsKey": {
"description": "Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename]",
"type": "string"
},
"projectId": {
"description": "ID of the project the request is related to.",
"type": [
"string",
"null"
]
}
},
"required": [
"data",
"featureName",
"multilabelInsightsKey",
"projectId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
[PairwiseManualSelectionCreatedItem] |
true |
|
List of manually selected labels sets |
| featureName |
string,null |
true |
|
Name of the feature the request is related to |
| multilabelInsightsKey |
string |
true |
|
Key for multilabel insights, unique per project, feature, and EDA stage. The most recent key can be retrieved via [GET /api/v2/projects/{projectId}/features/][get-apiv2projectsprojectidfeatures] or [GET /api/v2/projects/{projectId}/features/{featurename:featureName}/][get-apiv2projectsprojectidfeaturesfeaturenamefeaturename] |
| projectId |
string,null |
true |
|
ID of the project the request is related to. |
PairwiseStatisticsItem
{
"properties": {
"labelConfiguration": {
"description": "Configuration of all labels.",
"items": {
"properties": {
"label": {
"description": "Label name.",
"type": "string"
},
"relevance": {
"description": "Relevance value of the label.",
"maximum": 1,
"minimum": 0,
"type": "integer"
}
},
"required": [
"label"
],
"type": "object"
},
"maxItems": 2,
"minItems": 2,
"type": "array"
},
"statisticValue": {
"description": "Statistic value for the given label configuration.",
"type": [
"number",
"null"
]
}
},
"required": [
"labelConfiguration",
"statisticValue"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| labelConfiguration |
[PairwiseStatisticsLabelConfiguration] |
true |
maxItems: 2
minItems: 2
|
Configuration of all labels. |
| statisticValue |
number,null |
true |
|
Statistic value for the given label configuration. |
PairwiseStatisticsLabelConfiguration
{
"properties": {
"label": {
"description": "Label name.",
"type": "string"
},
"relevance": {
"description": "Relevance value of the label.",
"maximum": 1,
"minimum": 0,
"type": "integer"
}
},
"required": [
"label"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| label |
string |
true |
|
Label name. |
| relevance |
integer |
false |
maximum: 1
minimum: 0
|
Relevance value of the label. |
PairwiseStatisticsResponse
{
"properties": {
"data": {
"description": "Statistic values.",
"items": {
"properties": {
"labelConfiguration": {
"description": "Configuration of all labels.",
"items": {
"properties": {
"label": {
"description": "Label name.",
"type": "string"
},
"relevance": {
"description": "Relevance value of the label.",
"maximum": 1,
"minimum": 0,
"type": "integer"
}
},
"required": [
"label"
],
"type": "object"
},
"maxItems": 2,
"minItems": 2,
"type": "array"
},
"statisticValue": {
"description": "Statistic value for the given label configuration.",
"type": [
"number",
"null"
]
}
},
"required": [
"labelConfiguration",
"statisticValue"
],
"type": "object"
},
"type": "array"
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"projectId": {
"description": "Project Id.",
"maxLength": 24,
"minLength": 24,
"type": "string"
},
"statisticType": {
"description": "Pairwise statistic type.",
"enum": [
"conditionalProbability",
"correlation",
"jointProbability"
],
"type": "string"
}
},
"required": [
"data",
"featureName",
"projectId",
"statisticType"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
[PairwiseStatisticsItem] |
true |
|
Statistic values. |
| featureName |
string |
true |
|
Feature name. |
| projectId |
string |
true |
maxLength: 24
minLength: 24
minLength: 24
|
Project Id. |
| statisticType |
string |
true |
|
Pairwise statistic type. |
Enumerated Values
| Property |
Value |
| statisticType |
[conditionalProbability, correlation, jointProbability] |
PartialDependence
{
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
}
Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
[PartialDependenceData] |
true |
|
Partial dependence results. |
| isCapped |
boolean |
true |
|
Indicates whether the data for computation is capped. |
PartialDependenceData
{
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| dependence |
number |
true |
|
The value of partial dependence. |
| label |
string |
true |
|
Contains the label for categorical and numeric features as string. |
PayoffMatricesCreate
{
"properties": {
"falseNegativeValue": {
"description": "False negative value to use for profit curve calculation.",
"type": "number"
},
"falsePositiveValue": {
"description": "False positive value to use for profit curve calculation.",
"type": "number"
},
"name": {
"description": "Name of the payoff matrix to be created.",
"type": "string"
},
"trueNegativeValue": {
"description": "True negative value to use for profit curve calculation.",
"type": "number"
},
"truePositiveValue": {
"description": "True positive value to use for profit curve calculation.",
"type": "number"
}
},
"required": [
"falseNegativeValue",
"falsePositiveValue",
"name",
"trueNegativeValue",
"truePositiveValue"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| falseNegativeValue |
number |
true |
|
False negative value to use for profit curve calculation. |
| falsePositiveValue |
number |
true |
|
False positive value to use for profit curve calculation. |
| name |
string |
true |
|
Name of the payoff matrix to be created. |
| trueNegativeValue |
number |
true |
|
True negative value to use for profit curve calculation. |
| truePositiveValue |
number |
true |
|
True positive value to use for profit curve calculation. |
PayoffMatricesListResponse
{
"properties": {
"count": {
"description": "Number of items in current page.",
"type": "integer"
},
"data": {
"description": "Payoff matrices for a project.",
"items": {
"properties": {
"falseNegativeValue": {
"description": "Payoff value for false negatives used in profit curve calculation.",
"type": "number"
},
"falsePositiveValue": {
"description": "Payoff value for false positives used in profit curve calculation.",
"type": "number"
},
"id": {
"description": "ObjectId of the payoff matrix.",
"type": "string"
},
"name": {
"description": "Label for the payoff matrix.",
"type": "string"
},
"projectId": {
"description": "ID of the project associated with the payoff matrix.",
"type": "string"
},
"trueNegativeValue": {
"description": "Payoff value for true negatives used in profit curve calculation.",
"type": "number"
},
"truePositiveValue": {
"description": "Payoff value for true positives used in profit curve calculation.",
"type": "number"
}
},
"required": [
"falseNegativeValue",
"falsePositiveValue",
"id",
"name",
"projectId",
"trueNegativeValue",
"truePositiveValue"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page)",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page)",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "Total number of items.",
"type": "integer"
}
},
"required": [
"count",
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
Number of items in current page. |
| data |
[PayoffMatricesResponse] |
true |
|
Payoff matrices for a project. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page) |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page) |
| totalCount |
integer |
true |
|
Total number of items. |
PayoffMatricesResponse
{
"properties": {
"falseNegativeValue": {
"description": "Payoff value for false negatives used in profit curve calculation.",
"type": "number"
},
"falsePositiveValue": {
"description": "Payoff value for false positives used in profit curve calculation.",
"type": "number"
},
"id": {
"description": "ObjectId of the payoff matrix.",
"type": "string"
},
"name": {
"description": "Label for the payoff matrix.",
"type": "string"
},
"projectId": {
"description": "ID of the project associated with the payoff matrix.",
"type": "string"
},
"trueNegativeValue": {
"description": "Payoff value for true negatives used in profit curve calculation.",
"type": "number"
},
"truePositiveValue": {
"description": "Payoff value for true positives used in profit curve calculation.",
"type": "number"
}
},
"required": [
"falseNegativeValue",
"falsePositiveValue",
"id",
"name",
"projectId",
"trueNegativeValue",
"truePositiveValue"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| falseNegativeValue |
number |
true |
|
Payoff value for false negatives used in profit curve calculation. |
| falsePositiveValue |
number |
true |
|
Payoff value for false positives used in profit curve calculation. |
| id |
string |
true |
|
ObjectId of the payoff matrix. |
| name |
string |
true |
|
Label for the payoff matrix. |
| projectId |
string |
true |
|
ID of the project associated with the payoff matrix. |
| trueNegativeValue |
number |
true |
|
Payoff value for true negatives used in profit curve calculation. |
| truePositiveValue |
number |
true |
|
Payoff value for true positives used in profit curve calculation. |
PerClassAccuracy
{
"properties": {
"className": {
"description": "The name of the class value for the categorical feature.",
"type": "string"
},
"metrics": {
"description": "An array of metric scores.",
"items": {
"properties": {
"metric": {
"description": "The name of the metric.",
"enum": [
"AUC",
"Weighted AUC",
"Area Under PR Curve",
"Weighted Area Under PR Curve",
"Kolmogorov-Smirnov",
"Weighted Kolmogorov-Smirnov",
"FVE Binomial",
"Weighted FVE Binomial",
"Gini Norm",
"Weighted Gini Norm",
"LogLoss",
"Weighted LogLoss",
"Max MCC",
"Weighted Max MCC",
"Rate@Top5%",
"Weighted Rate@Top5%",
"Rate@Top10%",
"Weighted Rate@Top10%",
"Rate@TopTenth%",
"RMSE",
"Weighted RMSE",
"f1",
"accuracy"
],
"type": "string"
},
"value": {
"description": "The calculated score of the metric.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"metric",
"value"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"className",
"metrics"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| className |
string |
true |
|
The name of the class value for the categorical feature. |
| metrics |
[AccuracyMetrics] |
true |
|
An array of metric scores. |
PerClassFairness
{
"properties": {
"absoluteValue": {
"description": "Absolute fairness score for the class",
"minimum": 0,
"type": "number"
},
"className": {
"description": "Name of the protected class the score is calculated for.",
"type": "string"
},
"entriesCount": {
"description": "The number of entries of the class in the analysed data.",
"minimum": 0,
"type": "integer"
},
"isStatisticallySignificant": {
"description": "Flag to tell whether the score can be treated as statistically significant. In other words, whether we are confident enough with the score for this protected class.",
"type": "boolean"
},
"value": {
"description": "The relative fairness score for the class.",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"absoluteValue",
"className",
"entriesCount",
"isStatisticallySignificant",
"value"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| absoluteValue |
number |
true |
minimum: 0
|
Absolute fairness score for the class |
| className |
string |
true |
|
Name of the protected class the score is calculated for. |
| entriesCount |
integer |
true |
minimum: 0
|
The number of entries of the class in the analysed data. |
| isStatisticallySignificant |
boolean |
true |
|
Flag to tell whether the score can be treated as statistically significant. In other words, whether we are confident enough with the score for this protected class. |
| value |
number |
true |
maximum: 1
minimum: 0
|
The relative fairness score for the class. |
PerClusterCategorical
{
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| allOther |
number,null |
false |
maximum: 100
minimum: 0
|
A percentage of rows that do not have any of these values or categories. |
| clusterName |
string |
true |
|
Cluster name. |
| missingRowsPercent |
number,null |
false |
maximum: 100
minimum: 0
|
A percentage of all rows that have a missing value for this feature. |
| perValueStatistics |
[PerValueStatisticsListItem] |
true |
|
Statistic value for feature values in all data or a cluster. |
PerClusterGeospatial
{
"properties": {
"clusterName": {
"description": "Cluster name.",
"maxLength": 50,
"minLength": 1,
"type": "string"
},
"representativeLocations": {
"description": "A list of latitude and longitude location list",
"items": {
"description": "Latitude and longitude list.",
"items": {
"description": "Longitude or latitude, in degrees.",
"maximum": 180,
"minimum": -180,
"type": "number"
},
"type": "array"
},
"maxItems": 1000,
"type": "array"
}
},
"required": [
"clusterName",
"representativeLocations"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| clusterName |
string |
true |
maxLength: 50
minLength: 1
minLength: 1
|
Cluster name. |
| representativeLocations |
[array] |
true |
maxItems: 1000
|
A list of latitude and longitude location list |
PerClusterImage
{
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"images": {
"description": "A list of b64 encoded images.",
"items": {
"description": "b64 encoded image",
"type": "string"
},
"type": "array"
},
"percentageOfMissingImages": {
"description": "A percentage of image rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": "number"
}
},
"required": [
"clusterName",
"images",
"percentageOfMissingImages"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| clusterName |
string |
true |
|
Cluster name. |
| images |
[string] |
true |
|
A list of b64 encoded images. |
| percentageOfMissingImages |
number |
true |
maximum: 100
minimum: 0
|
A percentage of image rows that have a missing value for this feature. |
PerClusterNumeric
{
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"statistic": {
"description": "Statistic value for this cluster.",
"type": [
"number",
"null"
]
}
},
"required": [
"clusterName",
"statistic"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| clusterName |
string |
true |
|
Cluster name. |
| statistic |
number,null |
true |
|
Statistic value for this cluster. |
PerClusterText
{
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| clusterName |
string |
true |
|
Cluster name. |
| missingRowsPercent |
number,null |
false |
maximum: 100
minimum: 0
|
A percentage of all rows that have a missing value for this feature. |
| perValueStatistics |
[PerValueStatisticTextListItem] |
true |
|
Statistic value for feature values in all data or a cluster. |
PerNgramTextExplanations
{
"properties": {
"isUnknown": {
"description": "Whether the ngram is identifiable by the blueprint or not.",
"type": "boolean",
"x-versionadded": "v2.28"
},
"ngrams": {
"description": "List of JSON objects with the ngram starting index, ngram ending index and unknown ngram information.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"maxItems": 1000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly these ngrams's affected the prediction(e.g. '+++', '--', '+', '<+', '<-').",
"type": "string",
"x-versionadded": "v2.28"
},
"strength": {
"description": "The amount these ngrams's affected the prediction.",
"type": "number",
"x-versionadded": "v2.28"
}
},
"required": [
"isUnknown",
"ngrams",
"qualitativateStrength",
"strength"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| isUnknown |
boolean |
true |
|
Whether the ngram is identifiable by the blueprint or not. |
| ngrams |
[PredictionExplanationsPredictionValues] |
true |
maxItems: 1000
|
List of JSON objects with the ngram starting index, ngram ending index and unknown ngram information. |
| qualitativateStrength |
string |
true |
|
A human-readable description of how strongly these ngrams's affected the prediction(e.g. '+++', '--', '+', '<+', '<-'). |
| strength |
number |
true |
|
The amount these ngrams's affected the prediction. |
PerValueStatisticTextListItem
{
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| contextualExtracts |
[string] |
true |
|
Contextual extracts that show context for the n-gram. |
| importance |
number |
true |
|
Importance value for this n-gram. |
| ngram |
string |
true |
|
An n-gram. |
PerValueStatistics
{
"description": "Statistics for all data for different feature values.",
"properties": {
"allOther": {
"description": "A percentage of rows that do not have any of these values or categories.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
}
Statistics for all data for different feature values.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| allOther |
number,null |
false |
maximum: 100
minimum: 0
|
A percentage of rows that do not have any of these values or categories. |
| missingRowsPercent |
number,null |
false |
maximum: 100
minimum: 0
|
A percentage of all rows that have a missing value for this feature. |
| perValueStatistics |
[PerValueStatisticsListItem] |
true |
|
Statistic value for feature values in all data or a cluster. |
PerValueStatisticsListItem
{
"properties": {
"categoryLevel": {
"description": "A category level.",
"type": "string"
},
"frequency": {
"description": "Statistic value for this cluster.",
"type": "number"
}
},
"required": [
"categoryLevel",
"frequency"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| categoryLevel |
string |
true |
|
A category level. |
| frequency |
number |
true |
|
Statistic value for this cluster. |
PermutationFeatureImpactCreatePayload
{
"properties": {
"backtest": {
"description": "The backtest value used for Feature Impact computation. Applicable for datetime aware models.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
}
],
"x-versionadded": "v2.28"
},
"rowCount": {
"description": "The sample size to use for Feature Impact computation. It is possible to re-compute Feature Impact with a different row count.",
"maximum": 100000,
"minimum": 10,
"type": "integer",
"x-versionadded": "v2.21"
}
},
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtest |
any |
false |
|
The backtest value used for Feature Impact computation. Applicable for datetime aware models. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
maximum: 19
minimum: 0
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| rowCount |
integer |
false |
maximum: 100000
minimum: 10
|
The sample size to use for Feature Impact computation. It is possible to re-compute Feature Impact with a different row count. |
Enumerated Values
| Property |
Value |
| anonymous |
holdout |
PermutationFeatureImpactResponse
{
"properties": {
"backtest": {
"description": "The backtest model used to compute Feature Impact.Defined for datetime aware models.",
"oneOf": [
{
"maximum": 19,
"minimum": 0,
"type": "integer"
},
{
"enum": [
"holdout"
],
"type": "string"
},
{
"type": "null"
}
],
"x-versionadded": "v2.29"
},
"count": {
"description": "Number of feature impact records in a given batch.",
"type": "integer"
},
"featureImpacts": {
"description": "A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"parentFeatureName": {
"description": "The name of the parent feature.",
"type": [
"string",
"null"
]
},
"redundantWith": {
"description": "Name of feature that has the highest correlation with this feature.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized",
"redundantWith"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"next": {
"description": "URL for the next page of results or `null`.",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL for the next page of results or `null`.",
"format": "uri",
"type": [
"string",
"null"
]
},
"ranRedundancyDetection": {
"description": "Indicates whether redundant feature identification was run while calculating this feature impact.",
"type": "boolean"
},
"rowCount": {
"description": "The number of rows that was used to calculate feature impact. For the feature impact calculated with the default logic, without specifying the ``rowCount``, we return ``null`` here.",
"type": [
"integer",
"null"
],
"x-versionadded": "v2.21"
},
"shapBased": {
"description": "Indicates whether feature impact was calculated using Shapley values. True for anomaly detection models when the project is unsupervised, as permutation approach is not applicable. Note that supervised projects must use an alternative route for SHAP impact: /api/v2/projects/(projectId)/models/(modelId)/shapImpact/",
"type": "boolean",
"x-versionadded": "v2.18"
}
},
"required": [
"backtest",
"count",
"featureImpacts",
"next",
"previous",
"ranRedundancyDetection",
"rowCount",
"shapBased"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtest |
any |
true |
|
The backtest model used to compute Feature Impact.Defined for datetime aware models. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
maximum: 19
minimum: 0
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
null |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
Number of feature impact records in a given batch. |
| featureImpacts |
[FeatureImpactItem] |
true |
maxItems: 1000
|
A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned. |
| next |
string,null(uri) |
true |
|
URL for the next page of results or null. |
| previous |
string,null(uri) |
true |
|
URL for the next page of results or null. |
| ranRedundancyDetection |
boolean |
true |
|
Indicates whether redundant feature identification was run while calculating this feature impact. |
| rowCount |
integer,null |
true |
|
The number of rows that was used to calculate feature impact. For the feature impact calculated with the default logic, without specifying the rowCount, we return null here. |
| shapBased |
boolean |
true |
|
Indicates whether feature impact was calculated using Shapley values. True for anomaly detection models when the project is unsupervised, as permutation approach is not applicable. Note that supervised projects must use an alternative route for SHAP impact: /api/v2/projects/(projectId)/models/(modelId)/shapImpact/ |
Enumerated Values
| Property |
Value |
| anonymous |
holdout |
PredictedFrequency
{
"properties": {
"otherClassName": {
"description": "The name of the class.",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted (from 0 to 100)",
"maximum": 100,
"minimum": 0,
"type": "number"
},
"value": {
"description": "The count of the times this class was actual `classMetrics.className` when it was predicted",
"minimum": 0,
"type": "integer"
}
},
"required": [
"otherClassName",
"percentage",
"value"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| otherClassName |
string |
true |
|
The name of the class. |
| percentage |
number |
true |
maximum: 100
minimum: 0
|
the percentage of the times this class was actual when classMetrics.className is predicted (from 0 to 100) |
| value |
integer |
true |
minimum: 0
|
The count of the times this class was actual classMetrics.className when it was predicted |
PredictedPercentages
{
"properties": {
"otherClassName": {
"description": "the name of the class",
"type": "string"
},
"percentage": {
"description": "the percentage of the times this class was actual when `classMetrics.className` is predicted",
"type": "number"
}
},
"required": [
"otherClassName",
"percentage"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| otherClassName |
string |
true |
|
the name of the class |
| percentage |
number |
true |
|
the percentage of the times this class was actual when classMetrics.className is predicted |
PredictedVsActual
{
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
}
Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
[PredictedVsActualData] |
true |
|
Predicted versus actual results. |
| isCapped |
boolean |
true |
|
Indicates whether the data for computation is capped. |
| logScaledData |
[PredictedVsActualData] |
true |
|
Predicted versus actual results in a log scale. |
PredictedVsActualData
{
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| actual |
number,null |
true |
|
Actual value. null for 0 rows bins and unsupervised time series models. |
| bin |
[string] |
false |
|
For numeric features contains labels for left and right bin limits |
| label |
string |
true |
|
Contains label for categorical features; For numeric features contains range or numeric value. |
| predicted |
number,null |
true |
|
Predicted value. null for 0 rows bins. |
| rowCount |
integer |
true |
|
Number of rows for the label and bin. |
PredictionExplanation
{
"properties": {
"feature": {
"description": "The name of the feature contributing to the prediction.",
"type": "string"
},
"featureValue": {
"description": "The value the feature took on for this row. For image features, this value is the URL of the input image (New in v2.21).",
"type": "string"
},
"imageExplanationUrl": {
"description": "For image features, the URL of the image containing the input image overlaid by the activation heatmap. For non-image features, this field is null.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"perNgramTextExplanations": {
"description": "For text features, an array of JSON object containing the per ngram based text prediction explanations.",
"items": {
"properties": {
"isUnknown": {
"description": "Whether the ngram is identifiable by the blueprint or not.",
"type": "boolean",
"x-versionadded": "v2.28"
},
"ngrams": {
"description": "List of JSON objects with the ngram starting index, ngram ending index and unknown ngram information.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"maxItems": 1000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly these ngrams's affected the prediction(e.g. '+++', '--', '+', '<+', '<-').",
"type": "string",
"x-versionadded": "v2.28"
},
"strength": {
"description": "The amount these ngrams's affected the prediction.",
"type": "number",
"x-versionadded": "v2.28"
}
},
"required": [
"isUnknown",
"ngrams",
"qualitativateStrength",
"strength"
],
"type": "object"
},
"maxItems": 10000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly the feature affected the prediction. A large positive effect is denoted '+++', medium '++', small '+', very small '<+'. A large negative effect is denoted '---', medium '--', small '-', very small '<-'.",
"type": "string"
},
"strength": {
"description": "The amount this feature's value affected the prediction.",
"type": "number"
}
},
"required": [
"feature",
"featureValue",
"imageExplanationUrl",
"label",
"qualitativateStrength",
"strength"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| feature |
string |
true |
|
The name of the feature contributing to the prediction. |
| featureValue |
string |
true |
|
The value the feature took on for this row. For image features, this value is the URL of the input image (New in v2.21). |
| imageExplanationUrl |
string,null |
true |
|
For image features, the URL of the image containing the input image overlaid by the activation heatmap. For non-image features, this field is null. |
| label |
string |
true |
|
Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score. |
| perNgramTextExplanations |
[PerNgramTextExplanations] |
false |
maxItems: 10000
|
For text features, an array of JSON object containing the per ngram based text prediction explanations. |
| qualitativateStrength |
string |
true |
|
A human-readable description of how strongly the feature affected the prediction. A large positive effect is denoted '+, medium', small '+', very small '<+'. A large negative effect is denoted '---', medium '--', small '-', very small '<-'. |
| strength |
number |
true |
|
The amount this feature's value affected the prediction. |
PredictionExplanationsCreate
{
"properties": {
"classNames": {
"description": "Sets a list of selected class names for which corresponding explanations are returned in each row. This setting is mutually exclusive with numTopClasses. If neither parameter is specified, the default setting is numTopClasses=1.",
"items": {
"type": "string"
},
"maxItems": 100,
"type": "array",
"x-versionadded": "v2.29"
},
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"maxExplanations": {
"default": 3,
"description": "The maximum number of prediction explanations to supply per row of the dataset.",
"maximum": 10,
"minimum": 0,
"type": "integer"
},
"modelId": {
"description": "The model ID.",
"type": "string"
},
"numTopClasses": {
"description": "Sets the number of most probable (top predicted) classes for which corresponding explanations are returned in each row. This setting is mutually exclusive with classNames. If neither parameter is specified, the default setting is numTopClasses=1.",
"maximum": 100,
"minimum": 1,
"type": "integer",
"x-versionadded": "v2.29"
},
"thresholdHigh": {
"default": null,
"description": "The high threshold, above which a prediction must score in order for prediction explanations to be computed. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows.",
"type": [
"number",
"null"
]
},
"thresholdLow": {
"default": null,
"description": "The lower threshold, below which a prediction must score in order for prediction explanations to be computed for a row in the dataset. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows.",
"type": [
"number",
"null"
]
}
},
"required": [
"datasetId",
"modelId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| classNames |
[string] |
false |
maxItems: 100
|
Sets a list of selected class names for which corresponding explanations are returned in each row. This setting is mutually exclusive with numTopClasses. If neither parameter is specified, the default setting is numTopClasses=1. |
| datasetId |
string |
true |
|
The dataset ID. |
| maxExplanations |
integer |
false |
maximum: 10
minimum: 0
|
The maximum number of prediction explanations to supply per row of the dataset. |
| modelId |
string |
true |
|
The model ID. |
| numTopClasses |
integer |
false |
maximum: 100
minimum: 1
|
Sets the number of most probable (top predicted) classes for which corresponding explanations are returned in each row. This setting is mutually exclusive with classNames. If neither parameter is specified, the default setting is numTopClasses=1. |
| thresholdHigh |
number,null |
false |
|
The high threshold, above which a prediction must score in order for prediction explanations to be computed. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows. |
| thresholdLow |
number,null |
false |
|
The lower threshold, below which a prediction must score in order for prediction explanations to be computed for a row in the dataset. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows. |
PredictionExplanationsInitializationCreate
{
"properties": {
"maxExplanations": {
"default": 3,
"description": "The maximum number of prediction explanations to supply per row of the dataset.",
"maximum": 10,
"minimum": 1,
"type": "integer"
},
"thresholdHigh": {
"default": null,
"description": "The high threshold, above which a prediction must score in order for prediction explanations to be computed. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows.",
"type": [
"number",
"null"
]
},
"thresholdLow": {
"default": null,
"description": "The lower threshold, below which a prediction must score in order for prediction explanations to be computed for a row in the dataset. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows.",
"type": [
"number",
"null"
]
}
},
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| maxExplanations |
integer |
false |
maximum: 10
minimum: 1
|
The maximum number of prediction explanations to supply per row of the dataset. |
| thresholdHigh |
number,null |
false |
|
The high threshold, above which a prediction must score in order for prediction explanations to be computed. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows. |
| thresholdLow |
number,null |
false |
|
The lower threshold, below which a prediction must score in order for prediction explanations to be computed for a row in the dataset. If neither thresholdHigh nor thresholdLow is specified, prediction explanations will be computed for all rows. |
PredictionExplanationsInitializationRetrieve
{
"properties": {
"modelId": {
"description": "The model ID.",
"type": "string"
},
"predictionExplanationsSample": {
"description": "Each is a PredictionExplanationsRow. They represent a small sample of prediction explanations that could be generated for a particular dataset. They will have the same schema as the `data` array in the response from [GET /api/v2/projects/{projectId}/predictionExplanations/{predictionExplanationsId}/][get-apiv2projectsprojectidpredictionexplanationspredictionexplanationsid]. As of v2.21 only difference is that there is no forecastPoint in response for time series projects.",
"items": {
"properties": {
"adjustedPrediction": {
"description": "The exposure-adjusted output of the model for this row.",
"type": "number",
"x-versionadded": "v2.8"
},
"adjustedPredictionValues": {
"description": "The exposure-adjusted output of the model for this row.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.8"
},
"forecastDistance": {
"description": "Forecast distance for the row. For time series projects only.",
"type": "integer",
"x-versionadded": "v2.21"
},
"forecastPoint": {
"description": "Forecast point for the row. For time series projects only.",
"type": "string",
"x-versionadded": "v2.21"
},
"prediction": {
"description": "The output of the model for this row.",
"type": "number"
},
"predictionExplanations": {
"description": "A list of prediction explanations.",
"items": {
"properties": {
"feature": {
"description": "The name of the feature contributing to the prediction.",
"type": "string"
},
"featureValue": {
"description": "The value the feature took on for this row. For image features, this value is the URL of the input image (New in v2.21).",
"type": "string"
},
"imageExplanationUrl": {
"description": "For image features, the URL of the image containing the input image overlaid by the activation heatmap. For non-image features, this field is null.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"perNgramTextExplanations": {
"description": "For text features, an array of JSON object containing the per ngram based text prediction explanations.",
"items": {
"properties": {
"isUnknown": {
"description": "Whether the ngram is identifiable by the blueprint or not.",
"type": "boolean",
"x-versionadded": "v2.28"
},
"ngrams": {
"description": "List of JSON objects with the ngram starting index, ngram ending index and unknown ngram information.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"maxItems": 1000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly these ngrams's affected the prediction(e.g. '+++', '--', '+', '<+', '<-').",
"type": "string",
"x-versionadded": "v2.28"
},
"strength": {
"description": "The amount these ngrams's affected the prediction.",
"type": "number",
"x-versionadded": "v2.28"
}
},
"required": [
"isUnknown",
"ngrams",
"qualitativateStrength",
"strength"
],
"type": "object"
},
"maxItems": 10000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly the feature affected the prediction. A large positive effect is denoted '+++', medium '++', small '+', very small '<+'. A large negative effect is denoted '---', medium '--', small '-', very small '<-'.",
"type": "string"
},
"strength": {
"description": "The amount this feature's value affected the prediction.",
"type": "number"
}
},
"required": [
"feature",
"featureValue",
"imageExplanationUrl",
"label",
"qualitativateStrength",
"strength"
],
"type": "object"
},
"type": "array"
},
"predictionThreshold": {
"description": "The threshold value used for classification prediction.",
"type": [
"number",
"null"
]
},
"predictionValues": {
"description": "A list of prediction values.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
},
"rowId": {
"description": "Which row this PredictionExplanationsRow describes.",
"type": "integer"
},
"seriesId": {
"description": "The ID of the series value for the row in a multiseries project. For a single series project this will be null. For time series projects only.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"timestamp": {
"description": "Timestamp for the row. For time series projects only.",
"type": "string",
"x-versionadded": "v2.21"
}
},
"required": [
"adjustedPrediction",
"adjustedPredictionValues",
"forecastDistance",
"forecastPoint",
"prediction",
"predictionExplanations",
"predictionThreshold",
"predictionValues",
"rowId",
"seriesId",
"timestamp"
],
"type": "object"
},
"type": "array"
},
"projectId": {
"description": "The project ID.",
"type": "string"
}
},
"required": [
"modelId",
"predictionExplanationsSample",
"projectId"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| modelId |
string |
true |
|
The model ID. |
| predictionExplanationsSample |
[PredictionExplanationsRow] |
true |
|
Each is a PredictionExplanationsRow. They represent a small sample of prediction explanations that could be generated for a particular dataset. They will have the same schema as the data array in the response from [GET /api/v2/projects/{projectId}/predictionExplanations/{predictionExplanationsId}/][get-apiv2projectsprojectidpredictionexplanationspredictionexplanationsid]. As of v2.21 only difference is that there is no forecastPoint in response for time series projects. |
| projectId |
string |
true |
|
The project ID. |
PredictionExplanationsPredictionValues
{
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| label |
string |
true |
|
Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score. |
| value |
number |
true |
|
The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label. |
PredictionExplanationsRecord
{
"properties": {
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"finishTime": {
"description": "Timestamp referencing when computation for these prediction explanations finished.",
"type": "number"
},
"id": {
"description": "The PredictionExplanationsRecord ID.",
"type": "string"
},
"maxExplanations": {
"description": "The maximum number of codes generated per prediction.",
"type": "integer"
},
"modelId": {
"description": "The model ID.",
"type": "string"
},
"numColumns": {
"description": "The number of columns prediction explanations were computed for.",
"type": "integer"
},
"predictionExplanationsLocation": {
"description": "Where to retrieve the prediction explanations.",
"type": "string"
},
"predictionThreshold": {
"description": "The threshold value used for binary classification prediction.",
"type": [
"number",
"null"
]
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"thresholdHigh": {
"description": "The prediction explanation high threshold. Predictions must be above this value (or below the thresholdLow value) to have PredictionExplanations computed.",
"type": [
"number",
"null"
]
},
"thresholdLow": {
"description": "The prediction explanation low threshold. Predictions must be below this value (or above the thresholdHigh value) to have PredictionExplanations computed.",
"type": [
"number",
"null"
]
}
},
"required": [
"datasetId",
"finishTime",
"id",
"maxExplanations",
"modelId",
"numColumns",
"predictionExplanationsLocation",
"predictionThreshold",
"projectId",
"thresholdHigh",
"thresholdLow"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| datasetId |
string |
true |
|
The dataset ID. |
| finishTime |
number |
true |
|
Timestamp referencing when computation for these prediction explanations finished. |
| id |
string |
true |
|
The PredictionExplanationsRecord ID. |
| maxExplanations |
integer |
true |
|
The maximum number of codes generated per prediction. |
| modelId |
string |
true |
|
The model ID. |
| numColumns |
integer |
true |
|
The number of columns prediction explanations were computed for. |
| predictionExplanationsLocation |
string |
true |
|
Where to retrieve the prediction explanations. |
| predictionThreshold |
number,null |
true |
|
The threshold value used for binary classification prediction. |
| projectId |
string |
true |
|
The project ID. |
| thresholdHigh |
number,null |
true |
|
The prediction explanation high threshold. Predictions must be above this value (or below the thresholdLow value) to have PredictionExplanations computed. |
| thresholdLow |
number,null |
true |
|
The prediction explanation low threshold. Predictions must be below this value (or above the thresholdHigh value) to have PredictionExplanations computed. |
PredictionExplanationsRecordList
{
"properties": {
"count": {
"description": "The number of items returned on this page.",
"minimum": 0,
"type": "integer"
},
"data": {
"description": "Each has the same schema as if retrieving the prediction explanations individually from [GET /api/v2/projects/{projectId}/predictionExplanationsRecords/{predictionExplanationsId}/][get-apiv2projectsprojectidpredictionexplanationsrecordspredictionexplanationsid].",
"items": {
"properties": {
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"finishTime": {
"description": "Timestamp referencing when computation for these prediction explanations finished.",
"type": "number"
},
"id": {
"description": "The PredictionExplanationsRecord ID.",
"type": "string"
},
"maxExplanations": {
"description": "The maximum number of codes generated per prediction.",
"type": "integer"
},
"modelId": {
"description": "The model ID.",
"type": "string"
},
"numColumns": {
"description": "The number of columns prediction explanations were computed for.",
"type": "integer"
},
"predictionExplanationsLocation": {
"description": "Where to retrieve the prediction explanations.",
"type": "string"
},
"predictionThreshold": {
"description": "The threshold value used for binary classification prediction.",
"type": [
"number",
"null"
]
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"thresholdHigh": {
"description": "The prediction explanation high threshold. Predictions must be above this value (or below the thresholdLow value) to have PredictionExplanations computed.",
"type": [
"number",
"null"
]
},
"thresholdLow": {
"description": "The prediction explanation low threshold. Predictions must be below this value (or above the thresholdHigh value) to have PredictionExplanations computed.",
"type": [
"number",
"null"
]
}
},
"required": [
"datasetId",
"finishTime",
"id",
"maxExplanations",
"modelId",
"numColumns",
"predictionExplanationsLocation",
"predictionThreshold",
"projectId",
"thresholdHigh",
"thresholdLow"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "A URL pointing to the next page (if `null`, there is no next page).",
"type": [
"string",
"null"
]
},
"previous": {
"description": "A URL pointing to the previous page (if `null`, there is no previous page).",
"type": [
"string",
"null"
]
}
},
"required": [
"count",
"data",
"next",
"previous"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
minimum: 0
|
The number of items returned on this page. |
| data |
[PredictionExplanationsRecord] |
true |
|
Each has the same schema as if retrieving the prediction explanations individually from [GET /api/v2/projects/{projectId}/predictionExplanationsRecords/{predictionExplanationsId}/][get-apiv2projectsprojectidpredictionexplanationsrecordspredictionexplanationsid]. |
| next |
string,null |
true |
|
A URL pointing to the next page (if null, there is no next page). |
| previous |
string,null |
true |
|
A URL pointing to the previous page (if null, there is no previous page). |
PredictionExplanationsRetrieve
{
"properties": {
"adjustmentMethod": {
"description": "'exposureNormalized' (for regression projects with exposure) or 'N/A' (for classification projects) The value of 'exposureNormalized' indicates that prediction outputs are adjusted (or divided) by exposure. The value of 'N/A' indicates that no adjustments are applied to the adjusted predictions and they are identical to the unadjusted predictions.",
"type": "string",
"x-versionadded": "v2.8"
},
"count": {
"description": "How many rows of prediction explanations were returned.",
"type": "integer"
},
"data": {
"description": "Each is a PredictionExplanationsRow corresponding to one row of the prediction dataset.",
"items": {
"properties": {
"adjustedPrediction": {
"description": "The exposure-adjusted output of the model for this row.",
"type": "number",
"x-versionadded": "v2.8"
},
"adjustedPredictionValues": {
"description": "The exposure-adjusted output of the model for this row.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.8"
},
"forecastDistance": {
"description": "Forecast distance for the row. For time series projects only.",
"type": "integer",
"x-versionadded": "v2.21"
},
"forecastPoint": {
"description": "Forecast point for the row. For time series projects only.",
"type": "string",
"x-versionadded": "v2.21"
},
"prediction": {
"description": "The output of the model for this row.",
"type": "number"
},
"predictionExplanations": {
"description": "A list of prediction explanations.",
"items": {
"properties": {
"feature": {
"description": "The name of the feature contributing to the prediction.",
"type": "string"
},
"featureValue": {
"description": "The value the feature took on for this row. For image features, this value is the URL of the input image (New in v2.21).",
"type": "string"
},
"imageExplanationUrl": {
"description": "For image features, the URL of the image containing the input image overlaid by the activation heatmap. For non-image features, this field is null.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"perNgramTextExplanations": {
"description": "For text features, an array of JSON object containing the per ngram based text prediction explanations.",
"items": {
"properties": {
"isUnknown": {
"description": "Whether the ngram is identifiable by the blueprint or not.",
"type": "boolean",
"x-versionadded": "v2.28"
},
"ngrams": {
"description": "List of JSON objects with the ngram starting index, ngram ending index and unknown ngram information.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"maxItems": 1000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly these ngrams's affected the prediction(e.g. '+++', '--', '+', '<+', '<-').",
"type": "string",
"x-versionadded": "v2.28"
},
"strength": {
"description": "The amount these ngrams's affected the prediction.",
"type": "number",
"x-versionadded": "v2.28"
}
},
"required": [
"isUnknown",
"ngrams",
"qualitativateStrength",
"strength"
],
"type": "object"
},
"maxItems": 10000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly the feature affected the prediction. A large positive effect is denoted '+++', medium '++', small '+', very small '<+'. A large negative effect is denoted '---', medium '--', small '-', very small '<-'.",
"type": "string"
},
"strength": {
"description": "The amount this feature's value affected the prediction.",
"type": "number"
}
},
"required": [
"feature",
"featureValue",
"imageExplanationUrl",
"label",
"qualitativateStrength",
"strength"
],
"type": "object"
},
"type": "array"
},
"predictionThreshold": {
"description": "The threshold value used for classification prediction.",
"type": [
"number",
"null"
]
},
"predictionValues": {
"description": "A list of prediction values.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
},
"rowId": {
"description": "Which row this PredictionExplanationsRow describes.",
"type": "integer"
},
"seriesId": {
"description": "The ID of the series value for the row in a multiseries project. For a single series project this will be null. For time series projects only.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"timestamp": {
"description": "Timestamp for the row. For time series projects only.",
"type": "string",
"x-versionadded": "v2.21"
}
},
"required": [
"adjustedPrediction",
"adjustedPredictionValues",
"forecastDistance",
"forecastPoint",
"prediction",
"predictionExplanations",
"predictionThreshold",
"predictionValues",
"rowId",
"seriesId",
"timestamp"
],
"type": "object"
},
"type": "array"
},
"id": {
"description": "The ID of this group of prediction explanations.",
"type": "string"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"predictionExplanationsRecordLocation": {
"description": "The URL of the PredictionExplanationsRecord associated with these prediction explanations.",
"type": "string"
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"adjustmentMethod",
"count",
"data",
"id",
"next",
"predictionExplanationsRecordLocation",
"previous"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| adjustmentMethod |
string |
true |
|
'exposureNormalized' (for regression projects with exposure) or 'N/A' (for classification projects) The value of 'exposureNormalized' indicates that prediction outputs are adjusted (or divided) by exposure. The value of 'N/A' indicates that no adjustments are applied to the adjusted predictions and they are identical to the unadjusted predictions. |
| count |
integer |
true |
|
How many rows of prediction explanations were returned. |
| data |
[PredictionExplanationsRow] |
true |
|
Each is a PredictionExplanationsRow corresponding to one row of the prediction dataset. |
| id |
string |
true |
|
The ID of this group of prediction explanations. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| predictionExplanationsRecordLocation |
string |
true |
|
The URL of the PredictionExplanationsRecord associated with these prediction explanations. |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
PredictionExplanationsRow
{
"properties": {
"adjustedPrediction": {
"description": "The exposure-adjusted output of the model for this row.",
"type": "number",
"x-versionadded": "v2.8"
},
"adjustedPredictionValues": {
"description": "The exposure-adjusted output of the model for this row.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.8"
},
"forecastDistance": {
"description": "Forecast distance for the row. For time series projects only.",
"type": "integer",
"x-versionadded": "v2.21"
},
"forecastPoint": {
"description": "Forecast point for the row. For time series projects only.",
"type": "string",
"x-versionadded": "v2.21"
},
"prediction": {
"description": "The output of the model for this row.",
"type": "number"
},
"predictionExplanations": {
"description": "A list of prediction explanations.",
"items": {
"properties": {
"feature": {
"description": "The name of the feature contributing to the prediction.",
"type": "string"
},
"featureValue": {
"description": "The value the feature took on for this row. For image features, this value is the URL of the input image (New in v2.21).",
"type": "string"
},
"imageExplanationUrl": {
"description": "For image features, the URL of the image containing the input image overlaid by the activation heatmap. For non-image features, this field is null.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"perNgramTextExplanations": {
"description": "For text features, an array of JSON object containing the per ngram based text prediction explanations.",
"items": {
"properties": {
"isUnknown": {
"description": "Whether the ngram is identifiable by the blueprint or not.",
"type": "boolean",
"x-versionadded": "v2.28"
},
"ngrams": {
"description": "List of JSON objects with the ngram starting index, ngram ending index and unknown ngram information.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"maxItems": 1000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly these ngrams's affected the prediction(e.g. '+++', '--', '+', '<+', '<-').",
"type": "string",
"x-versionadded": "v2.28"
},
"strength": {
"description": "The amount these ngrams's affected the prediction.",
"type": "number",
"x-versionadded": "v2.28"
}
},
"required": [
"isUnknown",
"ngrams",
"qualitativateStrength",
"strength"
],
"type": "object"
},
"maxItems": 10000,
"type": "array",
"x-versionadded": "v2.28"
},
"qualitativateStrength": {
"description": "A human-readable description of how strongly the feature affected the prediction. A large positive effect is denoted '+++', medium '++', small '+', very small '<+'. A large negative effect is denoted '---', medium '--', small '-', very small '<-'.",
"type": "string"
},
"strength": {
"description": "The amount this feature's value affected the prediction.",
"type": "number"
}
},
"required": [
"feature",
"featureValue",
"imageExplanationUrl",
"label",
"qualitativateStrength",
"strength"
],
"type": "object"
},
"type": "array"
},
"predictionThreshold": {
"description": "The threshold value used for classification prediction.",
"type": [
"number",
"null"
]
},
"predictionValues": {
"description": "A list of prediction values.",
"items": {
"properties": {
"label": {
"description": "Describes what this model output corresponds to. For regression projects, it is the name of the target feature. For classification projects, it is a level from the target feature. For Anomaly Detection models it is an Anomaly Score.",
"type": "string"
},
"value": {
"description": "The output of the prediction. For regression projects, it is the predicted value of the target. For classification projects, it is the predicted probability the row belongs to the class identified by the label.",
"type": "number"
}
},
"required": [
"label",
"value"
],
"type": "object"
},
"type": "array"
},
"rowId": {
"description": "Which row this PredictionExplanationsRow describes.",
"type": "integer"
},
"seriesId": {
"description": "The ID of the series value for the row in a multiseries project. For a single series project this will be null. For time series projects only.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"timestamp": {
"description": "Timestamp for the row. For time series projects only.",
"type": "string",
"x-versionadded": "v2.21"
}
},
"required": [
"adjustedPrediction",
"adjustedPredictionValues",
"forecastDistance",
"forecastPoint",
"prediction",
"predictionExplanations",
"predictionThreshold",
"predictionValues",
"rowId",
"seriesId",
"timestamp"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| adjustedPrediction |
number |
true |
|
The exposure-adjusted output of the model for this row. |
| adjustedPredictionValues |
[PredictionExplanationsPredictionValues] |
true |
|
The exposure-adjusted output of the model for this row. |
| forecastDistance |
integer |
true |
|
Forecast distance for the row. For time series projects only. |
| forecastPoint |
string |
true |
|
Forecast point for the row. For time series projects only. |
| prediction |
number |
true |
|
The output of the model for this row. |
| predictionExplanations |
[PredictionExplanation] |
true |
|
A list of prediction explanations. |
| predictionThreshold |
number,null |
true |
|
The threshold value used for classification prediction. |
| predictionValues |
[PredictionExplanationsPredictionValues] |
true |
|
A list of prediction values. |
| rowId |
integer |
true |
|
Which row this PredictionExplanationsRow describes. |
| seriesId |
string,null |
true |
|
The ID of the series value for the row in a multiseries project. For a single series project this will be null. For time series projects only. |
| timestamp |
string |
true |
|
Timestamp for the row. For time series projects only. |
RatingTableCreateResponse
{
"properties": {
"ratingTableId": {
"description": "the ID of the newly created rating table",
"type": "string"
},
"ratingTableName": {
"description": "The name that was used for the rating table. May differ from the ratingTableName in the request, as names are trimmed and a suffix added to ensure all rating tables derived from the same model have unique names",
"type": "string"
}
},
"required": [
"ratingTableId",
"ratingTableName"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| ratingTableId |
string |
true |
|
the ID of the newly created rating table |
| ratingTableName |
string |
true |
|
The name that was used for the rating table. May differ from the ratingTableName in the request, as names are trimmed and a suffix added to ensure all rating tables derived from the same model have unique names |
RatingTableListResponse
{
"properties": {
"count": {
"description": "the number of RatingTable objects returned",
"type": "integer"
},
"data": {
"description": "the actual records. Each element of the array has the same schema\n as if retrieving the table individually from\n GET /api/v2/projects/(projectId)/ratingTables/(ratingTableId)/",
"items": {
"properties": {
"created": {
"description": "ISO-8601 timestamp of when the rating table record was created.",
"type": "number"
},
"id": {
"description": "the ID of the rating table record",
"type": "string"
},
"modelId": {
"description": "the model ID of a model that was created from the rating table.\n May be null if a model has not been created from the rating table.",
"type": "string"
},
"modelJobId": {
"description": "the qid of the job to create a model from this rating table.\n Can be null if a model has not been created from the rating table.",
"type": "integer"
},
"originalFilename": {
"description": "the filename of the uploaded rating table file",
"type": "string"
},
"parentModelId": {
"description": "the model ID of the model the rating table was modified from",
"type": "string"
},
"projectId": {
"description": "the project ID of the rating table record",
"type": "string"
},
"ratingTableName": {
"description": "the name of the rating table",
"type": "string"
},
"validationError": {
"description": "rating table validation error messages. If the rating table\n was validated successfully, it will be an empty string.",
"type": "string"
},
"validationJobId": {
"description": "the qid of the created job to validate the rating table.\n Can be null if the rating table has not been validated.",
"type": "string"
},
"validationWarnings": {
"description": "rating table validation warning messages.",
"type": "string"
}
},
"required": [
"created",
"id",
"modelId",
"modelJobId",
"originalFilename",
"parentModelId",
"projectId",
"ratingTableName",
"validationError",
"validationJobId",
"validationWarnings"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page)",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page)",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"count",
"data",
"next",
"previous"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
the number of RatingTable objects returned |
| data |
[RatingTableRetrieveResponse] |
true |
|
the actual records. Each element of the array has the same schema
as if retrieving the table individually from
GET /api/v2/projects/(projectId)/ratingTables/(ratingTableId)/ |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page) |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page) |
RatingTableModelDetailsResponse
{
"properties": {
"blenderModels": {
"description": "Models that are in the blender.",
"items": {
"type": "integer"
},
"maxItems": 100,
"type": "array",
"x-versionadded": "v2.36"
},
"blueprintId": {
"description": "The blueprint used to construct the model.",
"type": "string"
},
"dataSelectionMethod": {
"description": "Identifies which setting defines the training size of the model when making predictions and scoring. Only used by datetime models.",
"enum": [
"duration",
"rowCount",
"selectedDateRange",
"useProjectSettings"
],
"type": "string"
},
"externalPredictionModel": {
"description": "If the model is an external prediction model.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"featurelistId": {
"description": "The ID of the feature list used by the model.",
"type": [
"string",
"null"
]
},
"featurelistName": {
"description": "The name of the feature list used by the model. If null, themodel was trained on multiple feature lists.",
"type": [
"string",
"null"
]
},
"frozenPct": {
"description": "The training percent used to train the frozen model.",
"type": [
"number",
"null"
],
"x-versionadded": "v2.36"
},
"hasCodegen": {
"description": "If the model has a codegen JAR file.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"hasFinetuners": {
"description": "Whether a model has fine tuners.",
"type": "boolean"
},
"icons": {
"description": "The icons associated with the model.",
"type": [
"integer",
"null"
],
"x-versionadded": "v2.36"
},
"id": {
"description": "The ID of the model.",
"type": "string"
},
"isAugmented": {
"description": "Whether a model was trained using augmentation.",
"type": "boolean"
},
"isBlender": {
"description": "If the model is a blender.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"isCustom": {
"description": "If the model contains custom tasks.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"isFrozen": {
"description": "Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model.",
"type": "boolean"
},
"isNClustersDynamicallyDetermined": {
"description": "Whether number of clusters is dynamically determined. Only valid in unsupervised clustering projects.",
"type": "boolean"
},
"isStarred": {
"description": "Indicates whether the model has been starred.",
"type": "boolean"
},
"isTrainedIntoHoldout": {
"description": "Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size.",
"type": "boolean"
},
"isTrainedIntoValidation": {
"description": "Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size.",
"type": "boolean"
},
"isTrainedOnGpu": {
"description": "Whether the model was trained using GPU workers.",
"type": "boolean",
"x-versionadded": "v2.33"
},
"isTransparent": {
"description": "If the model is a transparent model with exposed coefficients.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"isUserModel": {
"description": "If the model was created with Composable ML.",
"type": "boolean",
"x-versionadded": "v2.36"
},
"lifecycle": {
"description": "Object returning model lifecycle.",
"properties": {
"reason": {
"description": "Reason for lifecycle stage. None if model is active.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.30"
},
"stage": {
"description": "Model lifecycle stage.",
"enum": [
"active",
"deprecated",
"disabled"
],
"type": "string",
"x-versionadded": "v2.30"
}
},
"required": [
"reason",
"stage"
],
"type": "object"
},
"linkFunction": {
"description": "The link function the final modeler uses in the blueprint. If no link function exists, returns null.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"metrics": {
"description": "The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed.",
"type": "object"
},
"modelCategory": {
"description": "Indicates the type of model. Returns `prime` for DataRobot Prime models, `blend` for blender models, `combined` for combined models, and `model` for all other models.",
"enum": [
"model",
"prime",
"blend",
"combined",
"incrementalLearning"
],
"type": "string"
},
"modelFamily": {
"description": "the family model belongs to, e.g. SVM, GBM, etc.",
"type": "string",
"x-versionadded": "v2.21"
},
"modelFamilyFullName": {
"description": "The full name of the family that the model belongs to. For e.g., Support Vector Machine, Gradient Boosting Machine, etc.",
"type": "string",
"x-versionadded": "v2.31"
},
"modelNumber": {
"description": "The model number from the Leaderboard.",
"exclusiveMinimum": 0,
"type": [
"integer",
"null"
]
},
"modelType": {
"description": "Identifies the model (e.g.,`Nystroem Kernel SVM Regressor`).",
"type": "string"
},
"monotonicDecreasingFeaturelistId": {
"description": "the ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"monotonicIncreasingFeaturelistId": {
"description": "the ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.21"
},
"nClusters": {
"description": "The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.",
"type": [
"integer",
"null"
]
},
"parentModelId": {
"description": "The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise.",
"type": [
"string",
"null"
]
},
"predictionThreshold": {
"description": "threshold used for binary classification in predictions.",
"maximum": 1,
"minimum": 0,
"type": "number",
"x-versionadded": "v2.13"
},
"predictionThresholdReadOnly": {
"description": "indicates whether modification of a predictions threshold is forbidden. Since v2.22 threshold modification is allowed.",
"type": "boolean",
"x-versionadded": "v2.13"
},
"processes": {
"description": "The list of processes used by the model.",
"items": {
"type": "string"
},
"maxItems": 100,
"type": "array"
},
"projectId": {
"description": "The ID of the project to which the model belongs.",
"type": "string"
},
"ratingTableId": {
"description": "The rating table ID",
"type": "string"
},
"samplePct": {
"description": "The percentage of the dataset used in training the model.",
"exclusiveMinimum": 0,
"type": [
"number",
"null"
]
},
"samplingMethod": {
"description": "indicates sampling method used to select training data in datetime models. For row-based project this is the way how requested number of rows are selected.For other projects (duration-based, start/end, project settings) - how specified percent of rows (timeWindowSamplePct) is selected from specified time window.",
"enum": [
"random",
"latest"
],
"type": "string"
},
"supportsComposableMl": {
"description": "indicates whether this model is supported in Composable ML.",
"type": "boolean",
"x-versionadded": "2.26"
},
"supportsMonotonicConstraints": {
"description": "whether this model supports enforcing monotonic constraints",
"type": "boolean",
"x-versionadded": "v2.21"
},
"timeWindowSamplePct": {
"description": "An integer between 1 and 99, indicating the percentage of sampling within the time window. The points kept are determined by samplingMethod option. Will be null if no sampling was specified. Only used by datetime models.",
"exclusiveMaximum": 100,
"exclusiveMinimum": 0,
"type": [
"integer",
"null"
]
},
"trainingDuration": {
"description": "the duration spanned by the dates in the partition column for the data used to train the model",
"type": [
"string",
"null"
]
},
"trainingEndDate": {
"description": "the end date of the dates in the partition column for the data used to train the model",
"format": "date-time",
"type": [
"string",
"null"
]
},
"trainingRowCount": {
"description": "The number of rows used to train the model.",
"exclusiveMinimum": 0,
"type": [
"integer",
"null"
]
},
"trainingStartDate": {
"description": "the start date of the dates in the partition column for the data used to train the model",
"format": "date-time",
"type": [
"string",
"null"
]
}
},
"required": [
"blenderModels",
"blueprintId",
"externalPredictionModel",
"featurelistId",
"featurelistName",
"frozenPct",
"hasCodegen",
"icons",
"id",
"isBlender",
"isCustom",
"isFrozen",
"isStarred",
"isTrainedIntoHoldout",
"isTrainedIntoValidation",
"isTrainedOnGpu",
"isTransparent",
"isUserModel",
"lifecycle",
"linkFunction",
"metrics",
"modelCategory",
"modelFamily",
"modelFamilyFullName",
"modelNumber",
"modelType",
"monotonicDecreasingFeaturelistId",
"monotonicIncreasingFeaturelistId",
"parentModelId",
"predictionThreshold",
"predictionThresholdReadOnly",
"processes",
"projectId",
"ratingTableId",
"samplePct",
"supportsComposableMl",
"supportsMonotonicConstraints",
"trainingDuration",
"trainingEndDate",
"trainingRowCount",
"trainingStartDate"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| blenderModels |
[integer] |
true |
maxItems: 100
|
Models that are in the blender. |
| blueprintId |
string |
true |
|
The blueprint used to construct the model. |
| dataSelectionMethod |
string |
false |
|
Identifies which setting defines the training size of the model when making predictions and scoring. Only used by datetime models. |
| externalPredictionModel |
boolean |
true |
|
If the model is an external prediction model. |
| featurelistId |
string,null |
true |
|
The ID of the feature list used by the model. |
| featurelistName |
string,null |
true |
|
The name of the feature list used by the model. If null, themodel was trained on multiple feature lists. |
| frozenPct |
number,null |
true |
|
The training percent used to train the frozen model. |
| hasCodegen |
boolean |
true |
|
If the model has a codegen JAR file. |
| hasFinetuners |
boolean |
false |
|
Whether a model has fine tuners. |
| icons |
integer,null |
true |
|
The icons associated with the model. |
| id |
string |
true |
|
The ID of the model. |
| isAugmented |
boolean |
false |
|
Whether a model was trained using augmentation. |
| isBlender |
boolean |
true |
|
If the model is a blender. |
| isCustom |
boolean |
true |
|
If the model contains custom tasks. |
| isFrozen |
boolean |
true |
|
Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model. |
| isNClustersDynamicallyDetermined |
boolean |
false |
|
Whether number of clusters is dynamically determined. Only valid in unsupervised clustering projects. |
| isStarred |
boolean |
true |
|
Indicates whether the model has been starred. |
| isTrainedIntoHoldout |
boolean |
true |
|
Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size. |
| isTrainedIntoValidation |
boolean |
true |
|
Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size. |
| isTrainedOnGpu |
boolean |
true |
|
Whether the model was trained using GPU workers. |
| isTransparent |
boolean |
true |
|
If the model is a transparent model with exposed coefficients. |
| isUserModel |
boolean |
true |
|
If the model was created with Composable ML. |
| lifecycle |
ModelLifecycle |
true |
|
Object returning model lifecycle. |
| linkFunction |
string,null |
true |
|
The link function the final modeler uses in the blueprint. If no link function exists, returns null. |
| metrics |
object |
true |
|
The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed. |
| modelCategory |
string |
true |
|
Indicates the type of model. Returns prime for DataRobot Prime models, blend for blender models, combined for combined models, and model for all other models. |
| modelFamily |
string |
true |
|
the family model belongs to, e.g. SVM, GBM, etc. |
| modelFamilyFullName |
string |
true |
|
The full name of the family that the model belongs to. For e.g., Support Vector Machine, Gradient Boosting Machine, etc. |
| modelNumber |
integer,null |
true |
|
The model number from the Leaderboard. |
| modelType |
string |
true |
|
Identifies the model (e.g.,Nystroem Kernel SVM Regressor). |
| monotonicDecreasingFeaturelistId |
string,null |
true |
|
the ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced. |
| monotonicIncreasingFeaturelistId |
string,null |
true |
|
the ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced. |
| nClusters |
integer,null |
false |
|
The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects. |
| parentModelId |
string,null |
true |
|
The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise. |
| predictionThreshold |
number |
true |
maximum: 1
minimum: 0
|
threshold used for binary classification in predictions. |
| predictionThresholdReadOnly |
boolean |
true |
|
indicates whether modification of a predictions threshold is forbidden. Since v2.22 threshold modification is allowed. |
| processes |
[string] |
true |
maxItems: 100
|
The list of processes used by the model. |
| projectId |
string |
true |
|
The ID of the project to which the model belongs. |
| ratingTableId |
string |
true |
|
The rating table ID |
| samplePct |
number,null |
true |
|
The percentage of the dataset used in training the model. |
| samplingMethod |
string |
false |
|
indicates sampling method used to select training data in datetime models. For row-based project this is the way how requested number of rows are selected.For other projects (duration-based, start/end, project settings) - how specified percent of rows (timeWindowSamplePct) is selected from specified time window. |
| supportsComposableMl |
boolean |
true |
|
indicates whether this model is supported in Composable ML. |
| supportsMonotonicConstraints |
boolean |
true |
|
whether this model supports enforcing monotonic constraints |
| timeWindowSamplePct |
integer,null |
false |
|
An integer between 1 and 99, indicating the percentage of sampling within the time window. The points kept are determined by samplingMethod option. Will be null if no sampling was specified. Only used by datetime models. |
| trainingDuration |
string,null |
true |
|
the duration spanned by the dates in the partition column for the data used to train the model |
| trainingEndDate |
string,null(date-time) |
true |
|
the end date of the dates in the partition column for the data used to train the model |
| trainingRowCount |
integer,null |
true |
|
The number of rows used to train the model. |
| trainingStartDate |
string,null(date-time) |
true |
|
the start date of the dates in the partition column for the data used to train the model |
Enumerated Values
| Property |
Value |
| dataSelectionMethod |
[duration, rowCount, selectedDateRange, useProjectSettings] |
| modelCategory |
[model, prime, blend, combined, incrementalLearning] |
| samplingMethod |
[random, latest] |
RatingTableRetrieveResponse
{
"properties": {
"created": {
"description": "ISO-8601 timestamp of when the rating table record was created.",
"type": "number"
},
"id": {
"description": "the ID of the rating table record",
"type": "string"
},
"modelId": {
"description": "the model ID of a model that was created from the rating table.\n May be null if a model has not been created from the rating table.",
"type": "string"
},
"modelJobId": {
"description": "the qid of the job to create a model from this rating table.\n Can be null if a model has not been created from the rating table.",
"type": "integer"
},
"originalFilename": {
"description": "the filename of the uploaded rating table file",
"type": "string"
},
"parentModelId": {
"description": "the model ID of the model the rating table was modified from",
"type": "string"
},
"projectId": {
"description": "the project ID of the rating table record",
"type": "string"
},
"ratingTableName": {
"description": "the name of the rating table",
"type": "string"
},
"validationError": {
"description": "rating table validation error messages. If the rating table\n was validated successfully, it will be an empty string.",
"type": "string"
},
"validationJobId": {
"description": "the qid of the created job to validate the rating table.\n Can be null if the rating table has not been validated.",
"type": "string"
},
"validationWarnings": {
"description": "rating table validation warning messages.",
"type": "string"
}
},
"required": [
"created",
"id",
"modelId",
"modelJobId",
"originalFilename",
"parentModelId",
"projectId",
"ratingTableName",
"validationError",
"validationJobId",
"validationWarnings"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| created |
number |
true |
|
ISO-8601 timestamp of when the rating table record was created. |
| id |
string |
true |
|
the ID of the rating table record |
| modelId |
string |
true |
|
the model ID of a model that was created from the rating table.
May be null if a model has not been created from the rating table. |
| modelJobId |
integer |
true |
|
the qid of the job to create a model from this rating table.
Can be null if a model has not been created from the rating table. |
| originalFilename |
string |
true |
|
the filename of the uploaded rating table file |
| parentModelId |
string |
true |
|
the model ID of the model the rating table was modified from |
| projectId |
string |
true |
|
the project ID of the rating table record |
| ratingTableName |
string |
true |
|
the name of the rating table |
| validationError |
string |
true |
|
rating table validation error messages. If the rating table
was validated successfully, it will be an empty string. |
| validationJobId |
string |
true |
|
the qid of the created job to validate the rating table.
Can be null if the rating table has not been validated. |
| validationWarnings |
string |
true |
|
rating table validation warning messages. |
RatingTableUpdate
{
"properties": {
"ratingTableName": {
"description": "the name of the new model",
"type": "string"
}
},
"required": [
"ratingTableName"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| ratingTableName |
string |
true |
|
the name of the new model |
ResidualsChartForDatasets
{
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input.",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be `null`.",
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"histogram": {
"description": "Data to plot a histogram of residual values. The object contains three keys, intervalStart, intervalEnd, and occurrences, the number of times the predicted value fits within that interval. For all but the last interval, the end value is exclusive.",
"items": {
"properties": {
"intervalEnd": {
"description": "The end of the interval.",
"type": "number"
},
"intervalStart": {
"description": "The start of the interval.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within that interval.",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset.",
"type": "number"
},
"standardDeviation": {
"description": "The Standard Deviation value measures variation in the dataset. A low value indicates that the data points tend to be close to the mean; a high value indicates that the data points are spread over a wider range of values.",
"type": "number"
}
},
"required": [
"coefficientOfDetermination",
"data",
"datasetId",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| coefficientOfDetermination |
number |
true |
|
Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input. |
| data |
[array] |
true |
|
The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. |
| datasetId |
string |
true |
|
The dataset ID. |
| histogram |
[Histogram] |
true |
|
Data to plot a histogram of residual values. The object contains three keys, intervalStart, intervalEnd, and occurrences, the number of times the predicted value fits within that interval. For all but the last interval, the end value is exclusive. |
| residualMean |
number |
true |
|
The arithmetic mean of the predicted value minus the actual value over the downsampled dataset. |
| standardDeviation |
number |
true |
|
The Standard Deviation value measures variation in the dataset. A low value indicates that the data points tend to be close to the mean; a high value indicates that the data points are spread over a wider range of values. |
ResidualsChartForDatasetsList
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of residuals charts for dataset.",
"items": {
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input.",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be `null`.",
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"histogram": {
"description": "Data to plot a histogram of residual values. The object contains three keys, intervalStart, intervalEnd, and occurrences, the number of times the predicted value fits within that interval. For all but the last interval, the end value is exclusive.",
"items": {
"properties": {
"intervalEnd": {
"description": "The end of the interval.",
"type": "number"
},
"intervalStart": {
"description": "The start of the interval.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within that interval.",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset.",
"type": "number"
},
"standardDeviation": {
"description": "The Standard Deviation value measures variation in the dataset. A low value indicates that the data points tend to be close to the mean; a high value indicates that the data points are spread over a wider range of values.",
"type": "number"
}
},
"required": [
"coefficientOfDetermination",
"data",
"datasetId",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"type": "array"
},
"modelId": {
"description": "The model ID.",
"type": "string"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"modelId",
"next",
"previous",
"projectId",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[ResidualsChartForDatasets] |
true |
|
List of residuals charts for dataset. |
| modelId |
string |
true |
|
The model ID. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| projectId |
string |
true |
|
The project ID. |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
RetrieveFeatureEffectsIndividualResponse
{
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`.",
"type": [
"string",
"null"
]
},
"data": {
"description": "Feature effects data.",
"properties": {
"featureEffects": {
"description": "Feature Effects computational results for each feature.",
"items": {
"properties": {
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureEffects"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"training",
"backtest_0",
"backtest_1",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20",
"holdout",
"backtest_0_training",
"backtest_1_training",
"backtest_2_training",
"backtest_3_training",
"backtest_4_training",
"backtest_5_training",
"backtest_6_training",
"backtest_7_training",
"backtest_8_training",
"backtest_9_training",
"backtest_10_training",
"backtest_11_training",
"backtest_12_training",
"backtest_13_training",
"backtest_14_training",
"backtest_15_training",
"backtest_16_training",
"backtest_17_training",
"backtest_18_training",
"backtest_19_training",
"backtest_20_training",
"holdout_training"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestIndex |
string,null |
false |
|
The backtest index. For example: 0, 1, ..., 20, holdout. |
| data |
FeatureEffectsInsightResponse |
true |
|
Feature effects data. |
| dataSliceId |
string,null |
false |
|
ID of the data slice. |
| entityId |
string |
false |
|
ID of the model. |
| id |
string |
true |
|
ID of the created insight. |
| projectId |
string |
false |
|
ID of the project. |
| source |
string |
false |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| source |
[validation, training, backtest_0, backtest_1, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20, holdout, backtest_0_training, backtest_1_training, backtest_2_training, backtest_3_training, backtest_4_training, backtest_5_training, backtest_6_training, backtest_7_training, backtest_8_training, backtest_9_training, backtest_10_training, backtest_11_training, backtest_12_training, backtest_13_training, backtest_14_training, backtest_15_training, backtest_16_training, backtest_17_training, backtest_18_training, backtest_19_training, backtest_20_training, holdout_training] |
RetrieveFeatureEffectsPaginatedResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated feature effects insights.",
"items": {
"properties": {
"backtestIndex": {
"description": "The backtest index. For example: `0`, `1`, ..., `20`, `holdout`.",
"type": [
"string",
"null"
]
},
"data": {
"description": "Feature effects data.",
"properties": {
"featureEffects": {
"description": "Feature Effects computational results for each feature.",
"items": {
"properties": {
"featureImpactScore": {
"description": "Feature impact score.",
"type": "number"
},
"featureName": {
"description": "Name of the feature.",
"type": "string"
},
"featureType": {
"description": "Feature type, either numeric or categorical.",
"type": "string"
},
"isBinnable": {
"description": "Whether values can be grouped into bins.",
"type": "boolean"
},
"isScalable": {
"description": "Whether numeric feature values can be reported on a log scale.",
"type": [
"boolean",
"null"
]
},
"partialDependence": {
"description": "Partial dependence results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Partial dependence results.",
"items": {
"properties": {
"dependence": {
"description": "The value of partial dependence.",
"type": "number"
},
"label": {
"description": "Contains the label for categorical and numeric features as string.",
"type": "string"
}
},
"required": [
"dependence",
"label"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
}
},
"required": [
"data",
"isCapped"
],
"type": "object"
},
"predictedVsActual": {
"description": "Predicted versus actual results. Can be missing if no data for the feature was qualified to generate the insight.",
"properties": {
"data": {
"description": "Predicted versus actual results.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
},
"isCapped": {
"description": "Indicates whether the data for computation is capped.",
"type": "boolean"
},
"logScaledData": {
"description": "Predicted versus actual results in a log scale.",
"items": {
"properties": {
"actual": {
"description": "Actual value. `null` for 0 rows bins and unsupervised time series models.",
"type": [
"number",
"null"
]
},
"bin": {
"description": "For numeric features contains labels for left and right bin limits",
"items": {
"type": "string"
},
"type": "array"
},
"label": {
"description": "Contains label for categorical features; For numeric features contains range or numeric value.",
"type": "string"
},
"predicted": {
"description": "Predicted value. `null` for 0 rows bins.",
"type": [
"number",
"null"
]
},
"rowCount": {
"description": "Number of rows for the label and bin.",
"type": "integer"
}
},
"required": [
"actual",
"label",
"predicted",
"rowCount"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"data",
"isCapped",
"logScaledData"
],
"type": "object"
},
"weightLabel": {
"description": "Weight label if weight was configured for the project.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureImpactScore",
"featureName",
"featureType",
"isBinnable",
"isScalable",
"weightLabel"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureEffects"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"training",
"backtest_0",
"backtest_1",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20",
"holdout",
"backtest_0_training",
"backtest_1_training",
"backtest_2_training",
"backtest_3_training",
"backtest_4_training",
"backtest_5_training",
"backtest_6_training",
"backtest_7_training",
"backtest_8_training",
"backtest_9_training",
"backtest_10_training",
"backtest_11_training",
"backtest_12_training",
"backtest_13_training",
"backtest_14_training",
"backtest_15_training",
"backtest_16_training",
"backtest_17_training",
"backtest_18_training",
"backtest_19_training",
"backtest_20_training",
"holdout_training"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[RetrieveFeatureEffectsIndividualResponse] |
true |
maxItems: 10
|
List of paginated feature effects insights. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
RetrieveFeatureImpactIndividualResponse
{
"properties": {
"data": {
"description": "Feature impact data.",
"properties": {
"featureImpacts": {
"description": "A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"parentFeatureName": {
"description": "The name of the parent feature.",
"type": [
"string",
"null"
]
},
"redundantWith": {
"description": "Name of feature that has the highest correlation with this feature.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized",
"redundantWith"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"ranRedundancyDetection": {
"description": "Indicates whether redundant feature identification was run while calculating this feature impact.",
"type": "boolean"
},
"rowCount": {
"description": "The number of rows that was used to calculate feature impact. For the feature impact calculated with the default logic, without specifying the ``rowCount``, we return ``null`` here.",
"type": [
"integer",
"null"
]
}
},
"required": [
"featureImpacts",
"ranRedundancyDetection",
"rowCount"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"training",
"backtest_2Training",
"backtest_3Training",
"backtest_4Training",
"backtest_5Training",
"backtest_6Training",
"backtest_7Training",
"backtest_8Training",
"backtest_9Training",
"backtest_10Training",
"backtest_11Training",
"backtest_12Training",
"backtest_13Training",
"backtest_14Training",
"backtest_15Training",
"backtest_16Training",
"backtest_17Training",
"backtest_18Training",
"backtest_19Training",
"backtest_20Training",
"backtest_1Training",
"holdoutTraining"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
FeatureImpactInsightResponse |
true |
|
Feature impact data. |
| dataSliceId |
string,null |
false |
|
ID of the data slice. |
| entityId |
string |
false |
|
ID of the model. |
| id |
string |
true |
|
ID of the created insight. |
| projectId |
string |
false |
|
ID of the project. |
| source |
string |
false |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| source |
[training, backtest_2Training, backtest_3Training, backtest_4Training, backtest_5Training, backtest_6Training, backtest_7Training, backtest_8Training, backtest_9Training, backtest_10Training, backtest_11Training, backtest_12Training, backtest_13Training, backtest_14Training, backtest_15Training, backtest_16Training, backtest_17Training, backtest_18Training, backtest_19Training, backtest_20Training, backtest_1Training, holdoutTraining] |
RetrieveFeatureImpactPaginatedResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated feature impact insights.",
"items": {
"properties": {
"data": {
"description": "Feature impact data.",
"properties": {
"featureImpacts": {
"description": "A list which contains feature impact scores for each feature used by a model. If the model has more than 1000 features, the most important 1000 features are returned.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"parentFeatureName": {
"description": "The name of the parent feature.",
"type": [
"string",
"null"
]
},
"redundantWith": {
"description": "Name of feature that has the highest correlation with this feature.",
"type": [
"string",
"null"
]
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized",
"redundantWith"
],
"type": "object"
},
"maxItems": 1000,
"type": "array"
},
"ranRedundancyDetection": {
"description": "Indicates whether redundant feature identification was run while calculating this feature impact.",
"type": "boolean"
},
"rowCount": {
"description": "The number of rows that was used to calculate feature impact. For the feature impact calculated with the default logic, without specifying the ``rowCount``, we return ``null`` here.",
"type": [
"integer",
"null"
]
}
},
"required": [
"featureImpacts",
"ranRedundancyDetection",
"rowCount"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"training",
"backtest_2Training",
"backtest_3Training",
"backtest_4Training",
"backtest_5Training",
"backtest_6Training",
"backtest_7Training",
"backtest_8Training",
"backtest_9Training",
"backtest_10Training",
"backtest_11Training",
"backtest_12Training",
"backtest_13Training",
"backtest_14Training",
"backtest_15Training",
"backtest_16Training",
"backtest_17Training",
"backtest_18Training",
"backtest_19Training",
"backtest_20Training",
"backtest_1Training",
"holdoutTraining"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 2,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[RetrieveFeatureImpactIndividualResponse] |
true |
maxItems: 2
|
List of paginated feature impact insights. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
RetrieveLiftChartIndividualResponse
{
"properties": {
"data": {
"description": "Lift chart data.",
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"bins"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
LiftChartResponse |
true |
|
Lift chart data. |
| dataSliceId |
string,null |
false |
|
ID of the data slice. |
| entityId |
string |
false |
|
ID of the model. |
| externalDatasetId |
string,null |
false |
|
The ID of the external dataset. |
| id |
string |
true |
|
ID of the created insight. |
| projectId |
string |
false |
|
ID of the project. |
| source |
string |
false |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| source |
[validation, crossValidation, holdout, externalTestSet, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
RetrieveLiftChartPaginatedResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated lift chart insights.",
"items": {
"properties": {
"data": {
"description": "Lift chart data.",
"properties": {
"bins": {
"description": "The lift chart data for that source, as specified below.",
"items": {
"properties": {
"actual": {
"description": "The average of the actual target values for the rows in the bin.",
"type": "number"
},
"binWeight": {
"description": "How much data is in the bin. For projects with weights, it is the sum of the weights of all rows in the bins; otherwise, it is the number of rows in the bin.",
"type": "number"
},
"predicted": {
"description": "The average of predicted values of the target for the rows in the bin.",
"type": "number"
}
},
"required": [
"actual",
"binWeight",
"predicted"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"bins"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[RetrieveLiftChartIndividualResponse] |
true |
maxItems: 10
|
List of paginated lift chart insights. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
RetrieveResidualsIndividualResponse
{
"properties": {
"data": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
ModelResidualsChartData |
true |
|
Chart data from the validation data source |
| dataSliceId |
string,null |
false |
|
ID of the data slice. |
| entityId |
string |
false |
|
ID of the model. |
| externalDatasetId |
string,null |
false |
|
The ID of the external dataset. |
| id |
string |
true |
|
ID of the created insight. |
| projectId |
string |
false |
|
ID of the project. |
| source |
string |
false |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| source |
[validation, crossValidation, holdout, externalTestSet] |
RetrieveResidualsPaginatedResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated residuals insights.",
"items": {
"properties": {
"data": {
"description": "Chart data from the validation data source",
"properties": {
"coefficientOfDetermination": {
"description": "Also known as the r-squared value. This value is calculated over the downsampled dataset, not the full input",
"type": "number"
},
"data": {
"description": "The rows of chart data in [actual, predicted, residual, row number] form. If the row number was not available at the time of model creation, the row number will be null. **NOTE**: In DataRobot v5.2, the row number will not be included.",
"items": {
"items": {
"type": "number"
},
"maxItems": 4,
"type": "array"
},
"type": "array"
},
"histogram": {
"description": "Data to plot a histogram of residual values",
"items": {
"properties": {
"intervalEnd": {
"description": "The interval end. For all but the last interval, the end value is exclusive.",
"type": "number"
},
"intervalStart": {
"description": "The interval start.",
"type": "number"
},
"occurrences": {
"description": "The number of times the predicted value fits within the interval",
"type": "integer"
}
},
"required": [
"intervalEnd",
"intervalStart",
"occurrences"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.19"
},
"residualMean": {
"description": "The arithmetic mean of the predicted value minus the actual value over the downsampled dataset",
"type": "number"
},
"standardDeviation": {
"description": "A measure of deviation from the group as a whole",
"type": "number",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficientOfDetermination",
"data",
"histogram",
"residualMean",
"standardDeviation"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[RetrieveResidualsIndividualResponse] |
true |
maxItems: 10
|
List of paginated residuals insights. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
RetrieveRocCurveIndividualResponse
{
"properties": {
"data": {
"description": "Roc curve data.",
"properties": {
"auc": {
"description": "AUC value",
"type": [
"number",
"null"
]
},
"kolmogorovSmirnovMetric": {
"description": "Kolmogorov-Smirnov metric value",
"type": [
"number",
"null"
]
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the positive class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "The ROC curve data for that source, as specified below.",
"items": {
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"auc",
"kolmogorovSmirnovMetric",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
RocCurveResponse |
true |
|
Roc curve data. |
| dataSliceId |
string,null |
false |
|
ID of the data slice. |
| entityId |
string |
false |
|
ID of the model. |
| externalDatasetId |
string,null |
false |
|
The ID of the external dataset. |
| id |
string |
true |
|
ID of the created insight. |
| projectId |
string |
false |
|
ID of the project. |
| source |
string |
false |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| source |
[validation, crossValidation, holdout, externalTestSet, backtest_2, backtest_3, backtest_4, backtest_5, backtest_6, backtest_7, backtest_8, backtest_9, backtest_10, backtest_11, backtest_12, backtest_13, backtest_14, backtest_15, backtest_16, backtest_17, backtest_18, backtest_19, backtest_20] |
RetrieveRocCurvePaginatedResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated roc curve insights.",
"items": {
"properties": {
"data": {
"description": "Roc curve data.",
"properties": {
"auc": {
"description": "AUC value",
"type": [
"number",
"null"
]
},
"kolmogorovSmirnovMetric": {
"description": "Kolmogorov-Smirnov metric value",
"type": [
"number",
"null"
]
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the positive class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "The ROC curve data for that source, as specified below.",
"items": {
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"auc",
"kolmogorovSmirnovMetric",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"validation",
"crossValidation",
"holdout",
"externalTestSet",
"backtest_2",
"backtest_3",
"backtest_4",
"backtest_5",
"backtest_6",
"backtest_7",
"backtest_8",
"backtest_9",
"backtest_10",
"backtest_11",
"backtest_12",
"backtest_13",
"backtest_14",
"backtest_15",
"backtest_16",
"backtest_17",
"backtest_18",
"backtest_19",
"backtest_20"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[RetrieveRocCurveIndividualResponse] |
true |
maxItems: 10
|
List of paginated roc curve insights. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
RetrieveShapDistributionsIndividualResponse
{
"properties": {
"data": {
"description": "SHAP distributions data.",
"properties": {
"features": {
"description": "List of SHAP distributions for each requested row.",
"items": {
"properties": {
"feature": {
"description": "The feature name in the dataset.",
"type": "string"
},
"featureType": {
"description": "Feature type.",
"enum": [
"T",
"X",
"B",
"C",
"CI",
"N",
"D",
"DD",
"FD",
"Q",
"CD",
"GEO",
"MC",
"INT",
"DOC"
],
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"shapValues": {
"description": "The SHAP distributions values for this row.",
"items": {
"properties": {
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer"
},
"featureValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The value of the feature for this row."
},
"predictionValue": {
"description": "The prediction value for this row.",
"type": "number"
},
"rowIndex": {
"description": "The index of this row.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number"
},
"weight": {
"description": "Weight of the row in the dataset.",
"type": [
"number",
"null"
],
"x-versionadded": "v2.37"
}
},
"required": [
"featureRank",
"featureValue",
"predictionValue",
"rowIndex",
"shapValue",
"weight"
],
"type": "object",
"x-versionadded": "v2.35"
},
"maxItems": 2500,
"type": "array"
}
},
"required": [
"feature",
"featureType",
"impactNormalized",
"impactUnnormalized",
"shapValues"
],
"type": "object",
"x-versionadded": "v2.35"
},
"maxItems": 100,
"type": "array"
},
"totalFeaturesCount": {
"description": "The total number of features.",
"type": "integer"
}
},
"required": [
"features",
"totalFeaturesCount"
],
"type": "object",
"x-versionadded": "v2.35"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object",
"x-versionadded": "v2.35"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
ShapDistributionsData |
true |
|
SHAP distributions data. |
| dataSliceId |
string,null |
false |
|
ID of the data slice. |
| entityId |
string |
false |
|
ID of the model. |
| externalDatasetId |
string,null |
false |
|
The ID of the external dataset. |
| id |
string |
true |
|
ID of the created insight. |
| projectId |
string |
false |
|
ID of the project. |
| quickCompute |
boolean |
false |
|
Whether the insight was computed using the quickCompute setting. |
| source |
string |
false |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, externalTestSet, holdout, holdout_training, training, validation] |
RetrieveShapDistributionsPaginatedResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of paginated SHAP distributions insights.",
"items": {
"properties": {
"data": {
"description": "SHAP distributions data.",
"properties": {
"features": {
"description": "List of SHAP distributions for each requested row.",
"items": {
"properties": {
"feature": {
"description": "The feature name in the dataset.",
"type": "string"
},
"featureType": {
"description": "Feature type.",
"enum": [
"T",
"X",
"B",
"C",
"CI",
"N",
"D",
"DD",
"FD",
"Q",
"CD",
"GEO",
"MC",
"INT",
"DOC"
],
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"shapValues": {
"description": "The SHAP distributions values for this row.",
"items": {
"properties": {
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer"
},
"featureValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The value of the feature for this row."
},
"predictionValue": {
"description": "The prediction value for this row.",
"type": "number"
},
"rowIndex": {
"description": "The index of this row.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number"
},
"weight": {
"description": "Weight of the row in the dataset.",
"type": [
"number",
"null"
],
"x-versionadded": "v2.37"
}
},
"required": [
"featureRank",
"featureValue",
"predictionValue",
"rowIndex",
"shapValue",
"weight"
],
"type": "object",
"x-versionadded": "v2.35"
},
"maxItems": 2500,
"type": "array"
}
},
"required": [
"feature",
"featureType",
"impactNormalized",
"impactUnnormalized",
"shapValues"
],
"type": "object",
"x-versionadded": "v2.35"
},
"maxItems": 100,
"type": "array"
},
"totalFeaturesCount": {
"description": "The total number of features.",
"type": "integer"
}
},
"required": [
"features",
"totalFeaturesCount"
],
"type": "object",
"x-versionadded": "v2.35"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
]
},
"entityId": {
"description": "ID of the model.",
"type": "string"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
]
},
"id": {
"description": "ID of the created insight.",
"type": "string"
},
"projectId": {
"description": "ID of the project.",
"type": "string"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string"
}
},
"required": [
"data",
"id"
],
"type": "object",
"x-versionadded": "v2.35"
},
"maxItems": 10,
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object",
"x-versionadded": "v2.35"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[RetrieveShapDistributionsIndividualResponse] |
true |
maxItems: 10
|
List of paginated SHAP distributions insights. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
RetrieveShapImpactIndividualResponse
{
"properties": {
"data": {
"description": "SHAP impact data.",
"properties": {
"baseValue": {
"description": "Mean of raw model predictions for the training data.",
"items": {
"type": "number"
},
"type": "array",
"x-versionadded": "v2.33"
},
"link": {
"description": "Link function used to connect the SHAP importance values to the model output.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"quickCompute": {
"default": true,
"description": "When enabled, limits the rows used from the selected source subset by default. When disabled, all rows are used.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"rowCount": {
"description": "(Deprecated) The number of rows used to calculate SHAP impact. If ``rowCount`` is not specified, the value returned is ``null``.",
"type": [
"integer",
"null"
],
"x-versionadded": "v2.33",
"x-versiondeprecated": "v2.35"
},
"shapImpacts": {
"description": "A list that contains SHAP impact scores.",
"items": {
"properties": {
"featureName": {
"description": "The feature name in the dataset.",
"type": "string"
},
"impactNormalized": {
"description": "The normalized impact score value.",
"type": [
"number",
"null"
]
},
"impactUnnormalized": {
"description": "The raw impact score value.",
"type": "number"
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
}
},
"required": [
"baseValue",
"link",
"rowCount",
"shapImpacts"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"entityId": {
"description": "ID of the model.",
"type": "string",
"x-versionadded": "v2.33"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"id": {
"description": "ID of the created insight.",
"type": "string",
"x-versionadded": "v2.33"
},
"projectId": {
"description": "ID of the project.",
"type": "string",
"x-versionadded": "v2.33"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "Subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"id"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
ShapImpactData |
true |
|
SHAP impact data. |
| dataSliceId |
string,null |
false |
|
ID of the data slice. |
| entityId |
string |
false |
|
ID of the model. |
| externalDatasetId |
string,null |
false |
|
The ID of the external dataset. |
| id |
string |
true |
|
ID of the created insight. |
| projectId |
string |
false |
|
ID of the project. |
| quickCompute |
boolean |
false |
|
Whether the insight was computed using the quickCompute setting. |
| source |
string |
false |
|
Subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, externalTestSet, holdout, holdout_training, training, validation] |
RetrieveShapImpactPaginatedResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer",
"x-versionadded": "v2.33"
},
"data": {
"description": "List of paginated SHAP impact insights.",
"items": {
"properties": {
"data": {
"description": "SHAP impact data.",
"properties": {
"baseValue": {
"description": "Mean of raw model predictions for the training data.",
"items": {
"type": "number"
},
"type": "array",
"x-versionadded": "v2.33"
},
"link": {
"description": "Link function used to connect the SHAP importance values to the model output.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"quickCompute": {
"default": true,
"description": "When enabled, limits the rows used from the selected source subset by default. When disabled, all rows are used.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"rowCount": {
"description": "(Deprecated) The number of rows used to calculate SHAP impact. If ``rowCount`` is not specified, the value returned is ``null``.",
"type": [
"integer",
"null"
],
"x-versionadded": "v2.33",
"x-versiondeprecated": "v2.35"
},
"shapImpacts": {
"description": "A list that contains SHAP impact scores.",
"items": {
"properties": {
"featureName": {
"description": "The feature name in the dataset.",
"type": "string"
},
"impactNormalized": {
"description": "The normalized impact score value.",
"type": [
"number",
"null"
]
},
"impactUnnormalized": {
"description": "The raw impact score value.",
"type": "number"
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
}
},
"required": [
"baseValue",
"link",
"rowCount",
"shapImpacts"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"entityId": {
"description": "ID of the model.",
"type": "string",
"x-versionadded": "v2.33"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"id": {
"description": "ID of the created insight.",
"type": "string",
"x-versionadded": "v2.33"
},
"projectId": {
"description": "ID of the project.",
"type": "string",
"x-versionadded": "v2.33"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "Subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array",
"x-versionadded": "v2.33"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[RetrieveShapImpactIndividualResponse] |
true |
maxItems: 10
|
List of paginated SHAP impact insights. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
RetrieveShapMatrixIndividualResponse
{
"properties": {
"data": {
"description": "SHAP matrix data.",
"properties": {
"baseValue": {
"description": "The mean of the raw model predictions for the training data.",
"items": {
"type": "number"
},
"type": "array",
"x-versionadded": "v2.33"
},
"colnames": {
"description": "The names of each column in the SHAP matrix.",
"items": {
"type": "string"
},
"type": "array",
"x-versionadded": "v2.33"
},
"linkFunction": {
"description": "The link function used to connect the feature importance values to the model output.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"matrix": {
"description": "SHAP matrix values.",
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array",
"x-versionadded": "v2.33"
},
"rowIndex": {
"description": "The index of the data row used to compute the SHAP matrix. Not used in time-aware projects.",
"items": {
"type": "integer"
},
"type": "array",
"x-versionadded": "v2.33"
},
"timeSeriesRowIndex": {
"description": "An index composed of the timestamp, series id and forecast distance. Only used in time-aware projects.",
"items": {
"items": {
"oneOf": [
{
"type": "integer"
},
{
"type": "string"
}
]
},
"maxLength": 2,
"minLength": 2,
"type": "array"
},
"type": "array",
"x-versionadded": "v2.36"
}
},
"required": [
"baseValue",
"colnames",
"linkFunction",
"matrix",
"rowIndex"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"entityId": {
"description": "ID of the model.",
"type": "string",
"x-versionadded": "v2.33"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"id": {
"description": "ID of the created insight.",
"type": "string",
"x-versionadded": "v2.33"
},
"projectId": {
"description": "ID of the project.",
"type": "string",
"x-versionadded": "v2.33"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"id"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
ShapMatrixData |
true |
|
SHAP matrix data. |
| dataSliceId |
string,null |
false |
|
ID of the data slice. |
| entityId |
string |
false |
|
ID of the model. |
| externalDatasetId |
string,null |
false |
|
The ID of the external dataset. |
| id |
string |
true |
|
ID of the created insight. |
| projectId |
string |
false |
|
ID of the project. |
| quickCompute |
boolean |
false |
|
Whether the insight was computed using the quickCompute setting. |
| source |
string |
false |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, externalTestSet, holdout, holdout_training, training, validation] |
RetrieveShapMatrixPaginatedResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer",
"x-versionadded": "v2.33"
},
"data": {
"description": "List of paginated SHAP matrix insights.",
"items": {
"properties": {
"data": {
"description": "SHAP matrix data.",
"properties": {
"baseValue": {
"description": "The mean of the raw model predictions for the training data.",
"items": {
"type": "number"
},
"type": "array",
"x-versionadded": "v2.33"
},
"colnames": {
"description": "The names of each column in the SHAP matrix.",
"items": {
"type": "string"
},
"type": "array",
"x-versionadded": "v2.33"
},
"linkFunction": {
"description": "The link function used to connect the feature importance values to the model output.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"matrix": {
"description": "SHAP matrix values.",
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array",
"x-versionadded": "v2.33"
},
"rowIndex": {
"description": "The index of the data row used to compute the SHAP matrix. Not used in time-aware projects.",
"items": {
"type": "integer"
},
"type": "array",
"x-versionadded": "v2.33"
},
"timeSeriesRowIndex": {
"description": "An index composed of the timestamp, series id and forecast distance. Only used in time-aware projects.",
"items": {
"items": {
"oneOf": [
{
"type": "integer"
},
{
"type": "string"
}
]
},
"maxLength": 2,
"minLength": 2,
"type": "array"
},
"type": "array",
"x-versionadded": "v2.36"
}
},
"required": [
"baseValue",
"colnames",
"linkFunction",
"matrix",
"rowIndex"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"entityId": {
"description": "ID of the model.",
"type": "string",
"x-versionadded": "v2.33"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"id": {
"description": "ID of the created insight.",
"type": "string",
"x-versionadded": "v2.33"
},
"projectId": {
"description": "ID of the project.",
"type": "string",
"x-versionadded": "v2.33"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array",
"x-versionadded": "v2.33"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[RetrieveShapMatrixIndividualResponse] |
true |
maxItems: 10
|
List of paginated SHAP matrix insights. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
RetrieveShapPreviewIndividualResponse
{
"properties": {
"data": {
"description": "SHAP preview data.",
"properties": {
"previews": {
"description": "List of SHAP previews for each requested row.",
"items": {
"properties": {
"predictionValue": {
"description": "The prediction value for this row.",
"type": "number",
"x-versionadded": "v2.33"
},
"previewValues": {
"description": "The SHAP preview values for this row.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string",
"x-versionadded": "v2.33"
},
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer",
"x-versionadded": "v2.33"
},
"featureValue": {
"description": "The value of the feature for this row.",
"type": "string",
"x-versionadded": "v2.33"
},
"hasTextExplanations": {
"description": "Whether the feature has text explanations available for this row.",
"type": "boolean",
"x-versionadded": "v2.33"
},
"isImage": {
"description": "Whether the feature is an image or not.",
"type": "boolean",
"x-versionadded": "v2.34"
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number",
"x-versionadded": "v2.33"
},
"textExplanations": {
"description": "List of the text explanations for the feature for this row.",
"items": {
"type": "string"
},
"type": "array",
"x-versionadded": "v2.33"
}
},
"required": [
"featureName",
"featureRank",
"featureValue",
"hasTextExplanations",
"shapValue",
"textExplanations"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
},
"rowIndex": {
"description": "The index of this row.",
"minimum": 0,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.33"
},
"timeSeriesRowIndex": {
"description": "An index composed of the timestamp, series ID, and forecast distance. This index is used only in time-aware projects.",
"items": {
"oneOf": [
{
"type": "integer"
},
{
"type": "string"
}
]
},
"maxLength": 2,
"minLength": 2,
"type": [
"array",
"null"
],
"x-versionadded": "v2.36"
},
"totalPreviewFeatures": {
"description": "The total number of features available after name filters have been applied.",
"minimum": 0,
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"predictionValue",
"previewValues",
"rowIndex",
"totalPreviewFeatures"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
},
"previewsCount": {
"description": "The total number of previews.",
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"previews",
"previewsCount"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"entityId": {
"description": "ID of the model.",
"type": "string",
"x-versionadded": "v2.33"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"id": {
"description": "ID of the created insight.",
"type": "string",
"x-versionadded": "v2.33"
},
"projectId": {
"description": "ID of the project.",
"type": "string",
"x-versionadded": "v2.33"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"id"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
ShapPreviewData |
true |
|
SHAP preview data. |
| dataSliceId |
string,null |
false |
|
ID of the data slice. |
| entityId |
string |
false |
|
ID of the model. |
| externalDatasetId |
string,null |
false |
|
The ID of the external dataset. |
| id |
string |
true |
|
ID of the created insight. |
| projectId |
string |
false |
|
ID of the project. |
| quickCompute |
boolean |
false |
|
Whether the insight was computed using the quickCompute setting. |
| source |
string |
false |
|
The subset of data used to compute the insight. |
Enumerated Values
| Property |
Value |
| source |
[backtest_0, backtest_0_training, backtest_1, backtest_10, backtest_10_training, backtest_11, backtest_11_training, backtest_12, backtest_12_training, backtest_13, backtest_13_training, backtest_14, backtest_14_training, backtest_15, backtest_15_training, backtest_16, backtest_16_training, backtest_17, backtest_17_training, backtest_18, backtest_18_training, backtest_19, backtest_19_training, backtest_1_training, backtest_2, backtest_20, backtest_20_training, backtest_2_training, backtest_3, backtest_3_training, backtest_4, backtest_4_training, backtest_5, backtest_5_training, backtest_6, backtest_6_training, backtest_7, backtest_7_training, backtest_8, backtest_8_training, backtest_9, backtest_9_training, externalTestSet, holdout, holdout_training, training, validation] |
RetrieveShapPreviewPaginatedResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer",
"x-versionadded": "v2.33"
},
"data": {
"description": "List of paginated SHAP preview insights.",
"items": {
"properties": {
"data": {
"description": "SHAP preview data.",
"properties": {
"previews": {
"description": "List of SHAP previews for each requested row.",
"items": {
"properties": {
"predictionValue": {
"description": "The prediction value for this row.",
"type": "number",
"x-versionadded": "v2.33"
},
"previewValues": {
"description": "The SHAP preview values for this row.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string",
"x-versionadded": "v2.33"
},
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer",
"x-versionadded": "v2.33"
},
"featureValue": {
"description": "The value of the feature for this row.",
"type": "string",
"x-versionadded": "v2.33"
},
"hasTextExplanations": {
"description": "Whether the feature has text explanations available for this row.",
"type": "boolean",
"x-versionadded": "v2.33"
},
"isImage": {
"description": "Whether the feature is an image or not.",
"type": "boolean",
"x-versionadded": "v2.34"
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number",
"x-versionadded": "v2.33"
},
"textExplanations": {
"description": "List of the text explanations for the feature for this row.",
"items": {
"type": "string"
},
"type": "array",
"x-versionadded": "v2.33"
}
},
"required": [
"featureName",
"featureRank",
"featureValue",
"hasTextExplanations",
"shapValue",
"textExplanations"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
},
"rowIndex": {
"description": "The index of this row.",
"minimum": 0,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.33"
},
"timeSeriesRowIndex": {
"description": "An index composed of the timestamp, series ID, and forecast distance. This index is used only in time-aware projects.",
"items": {
"oneOf": [
{
"type": "integer"
},
{
"type": "string"
}
]
},
"maxLength": 2,
"minLength": 2,
"type": [
"array",
"null"
],
"x-versionadded": "v2.36"
},
"totalPreviewFeatures": {
"description": "The total number of features available after name filters have been applied.",
"minimum": 0,
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"predictionValue",
"previewValues",
"rowIndex",
"totalPreviewFeatures"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
},
"previewsCount": {
"description": "The total number of previews.",
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"previews",
"previewsCount"
],
"type": "object"
},
"dataSliceId": {
"description": "ID of the data slice.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"entityId": {
"description": "ID of the model.",
"type": "string",
"x-versionadded": "v2.33"
},
"externalDatasetId": {
"description": "The ID of the external dataset.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"id": {
"description": "ID of the created insight.",
"type": "string",
"x-versionadded": "v2.33"
},
"projectId": {
"description": "ID of the project.",
"type": "string",
"x-versionadded": "v2.33"
},
"quickCompute": {
"description": "Whether the insight was computed using the quickCompute setting.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"source": {
"description": "The subset of data used to compute the insight.",
"enum": [
"backtest_0",
"backtest_0_training",
"backtest_1",
"backtest_10",
"backtest_10_training",
"backtest_11",
"backtest_11_training",
"backtest_12",
"backtest_12_training",
"backtest_13",
"backtest_13_training",
"backtest_14",
"backtest_14_training",
"backtest_15",
"backtest_15_training",
"backtest_16",
"backtest_16_training",
"backtest_17",
"backtest_17_training",
"backtest_18",
"backtest_18_training",
"backtest_19",
"backtest_19_training",
"backtest_1_training",
"backtest_2",
"backtest_20",
"backtest_20_training",
"backtest_2_training",
"backtest_3",
"backtest_3_training",
"backtest_4",
"backtest_4_training",
"backtest_5",
"backtest_5_training",
"backtest_6",
"backtest_6_training",
"backtest_7",
"backtest_7_training",
"backtest_8",
"backtest_8_training",
"backtest_9",
"backtest_9_training",
"externalTestSet",
"holdout",
"holdout_training",
"training",
"validation"
],
"type": "string",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"id"
],
"type": "object"
},
"maxItems": 10,
"type": "array",
"x-versionadded": "v2.33"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"totalCount": {
"description": "The total number of items across all pages.",
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"data",
"next",
"previous",
"totalCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[RetrieveShapPreviewIndividualResponse] |
true |
maxItems: 10
|
List of paginated SHAP preview insights. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
| totalCount |
integer |
true |
|
The total number of items across all pages. |
RocCurveForDatasets
{
"description": "ROC curve data for datasets.",
"properties": {
"datasetId": {
"description": "The ID of dataset which was used to compute ROC curve.",
"type": "string"
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
}
},
"required": [
"datasetId",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints"
],
"type": "object"
}
ROC curve data for datasets.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| datasetId |
string |
true |
|
The ID of dataset which was used to compute ROC curve. |
| negativeClassPredictions |
[number] |
true |
|
List of example predictions for the negative class. |
| positiveClassPredictions |
[number] |
true |
|
List of example predictions for the negative class. |
| rocPoints |
RocPointsResponse |
true |
|
ROC curve data for a single source. |
RocCurveForDatasetsList
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "List of ROC curve data for datasets.",
"items": {
"description": "ROC curve data for datasets.",
"properties": {
"datasetId": {
"description": "The ID of dataset which was used to compute ROC curve.",
"type": "string"
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
}
},
"required": [
"datasetId",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"data",
"next",
"previous"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[RocCurveForDatasets] |
true |
|
List of ROC curve data for datasets. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
RocCurveResponse
{
"description": "Roc curve data.",
"properties": {
"auc": {
"description": "AUC value",
"type": [
"number",
"null"
]
},
"kolmogorovSmirnovMetric": {
"description": "Kolmogorov-Smirnov metric value",
"type": [
"number",
"null"
]
},
"negativeClassPredictions": {
"description": "List of example predictions for the negative class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"positiveClassPredictions": {
"description": "List of example predictions for the positive class.",
"items": {
"description": "An example prediction.",
"type": "number"
},
"type": "array"
},
"rocPoints": {
"description": "The ROC curve data for that source, as specified below.",
"items": {
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"auc",
"kolmogorovSmirnovMetric",
"negativeClassPredictions",
"positiveClassPredictions",
"rocPoints"
],
"type": "object"
}
Roc curve data.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| auc |
number,null |
true |
|
AUC value |
| kolmogorovSmirnovMetric |
number,null |
true |
|
Kolmogorov-Smirnov metric value |
| negativeClassPredictions |
[number] |
true |
|
List of example predictions for the negative class. |
| positiveClassPredictions |
[number] |
true |
|
List of example predictions for the positive class. |
| rocPoints |
[RocPointsResponse] |
true |
|
The ROC curve data for that source, as specified below. |
RocPointsResponse
{
"description": "ROC curve data for a single source.",
"properties": {
"accuracy": {
"description": "Accuracy for given threshold.",
"type": "number"
},
"f1Score": {
"description": "F1 score.",
"type": "number"
},
"falseNegativeScore": {
"description": "False negative score.",
"type": "integer"
},
"falsePositiveRate": {
"description": "False positive rate.",
"type": "number"
},
"falsePositiveScore": {
"description": "False positive score.",
"type": "integer"
},
"fractionPredictedAsNegative": {
"description": "Fraction of data that will be predicted as negative.",
"type": "number"
},
"fractionPredictedAsPositive": {
"description": "Fraction of data that will be predicted as positive.",
"type": "number"
},
"liftNegative": {
"description": "Lift for the negative class.",
"type": "number"
},
"liftPositive": {
"description": "Lift for the positive class.",
"type": "number"
},
"matthewsCorrelationCoefficient": {
"description": "Matthews correlation coefficient.",
"type": "number"
},
"negativePredictiveValue": {
"description": "Negative predictive value.",
"type": "number"
},
"positivePredictiveValue": {
"description": "Positive predictive value.",
"type": "number"
},
"threshold": {
"description": "Value of threshold for this ROC point.",
"type": "number"
},
"trueNegativeRate": {
"description": "True negative rate.",
"type": "number"
},
"trueNegativeScore": {
"description": "True negative score.",
"type": "integer"
},
"truePositiveRate": {
"description": "True positive rate.",
"type": "number"
},
"truePositiveScore": {
"description": "True positive score.",
"type": "integer"
}
},
"required": [
"accuracy",
"f1Score",
"falseNegativeScore",
"falsePositiveRate",
"falsePositiveScore",
"fractionPredictedAsNegative",
"fractionPredictedAsPositive",
"liftNegative",
"liftPositive",
"matthewsCorrelationCoefficient",
"negativePredictiveValue",
"positivePredictiveValue",
"threshold",
"trueNegativeRate",
"trueNegativeScore",
"truePositiveRate",
"truePositiveScore"
],
"type": "object"
}
ROC curve data for a single source.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| accuracy |
number |
true |
|
Accuracy for given threshold. |
| f1Score |
number |
true |
|
F1 score. |
| falseNegativeScore |
integer |
true |
|
False negative score. |
| falsePositiveRate |
number |
true |
|
False positive rate. |
| falsePositiveScore |
integer |
true |
|
False positive score. |
| fractionPredictedAsNegative |
number |
true |
|
Fraction of data that will be predicted as negative. |
| fractionPredictedAsPositive |
number |
true |
|
Fraction of data that will be predicted as positive. |
| liftNegative |
number |
true |
|
Lift for the negative class. |
| liftPositive |
number |
true |
|
Lift for the positive class. |
| matthewsCorrelationCoefficient |
number |
true |
|
Matthews correlation coefficient. |
| negativePredictiveValue |
number |
true |
|
Negative predictive value. |
| positivePredictiveValue |
number |
true |
|
Positive predictive value. |
| threshold |
number |
true |
|
Value of threshold for this ROC point. |
| trueNegativeRate |
number |
true |
|
True negative rate. |
| trueNegativeScore |
integer |
true |
|
True negative score. |
| truePositiveRate |
number |
true |
|
True positive rate. |
| truePositiveScore |
integer |
true |
|
True positive score. |
SeriesAccuracyCompute
{
"properties": {
"computeAllSeries": {
"default": false,
"description": "Indicates whether to calculate accuracy for all series or only first 1000 (sorted by name).",
"type": "boolean",
"x-versionadded": "2.22"
}
},
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| computeAllSeries |
boolean |
false |
|
Indicates whether to calculate accuracy for all series or only first 1000 (sorted by name). |
SeriesAccuracyRetrieveDataResponse
{
"properties": {
"backtestingScore": {
"description": "The backtesting score for this series. If backtesting has not been run for this model, this score will be null.",
"type": [
"number",
"null"
]
},
"cluster": {
"description": "The cluster associated with this series. ",
"type": [
"string",
"null"
]
},
"duration": {
"description": "The duration of this series formatted as an ISO 8601 duration string.",
"format": "duration",
"type": "string"
},
"endDate": {
"description": "The ISO-formatted end date of this series.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"holdoutScore": {
"description": "The holdout set score for this series. If holdout is locked for the project, this score will be null.",
"type": [
"number",
"null"
]
},
"multiseriesId": {
"description": "A DataRobot-generated ID corresponding to a single series in a multiseries dataset.",
"type": "string"
},
"multiseriesValues": {
"description": "The actual values of series ID columns from the dataset.",
"items": {
"type": "string"
},
"type": "array"
},
"rowCount": {
"description": "The number of rows available for this series in the input dataset.",
"type": "integer"
},
"startDate": {
"description": "The ISO-formatted start date of this series.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"targetAverage": {
"description": "For regression projects, this is the average (mean) value of target values for this series.For classification projects, this is the ratio of the positive class in the target for this series.",
"oneOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "null"
}
]
},
"validationScore": {
"description": "The validation set score for this series",
"type": [
"number",
"null"
]
}
},
"required": [
"backtestingScore",
"duration",
"multiseriesId",
"multiseriesValues",
"rowCount",
"validationScore"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| backtestingScore |
number,null |
true |
|
The backtesting score for this series. If backtesting has not been run for this model, this score will be null. |
| cluster |
string,null |
false |
|
The cluster associated with this series. |
| duration |
string(duration) |
true |
|
The duration of this series formatted as an ISO 8601 duration string. |
| endDate |
string,null(date-time) |
false |
|
The ISO-formatted end date of this series. |
| holdoutScore |
number,null |
false |
|
The holdout set score for this series. If holdout is locked for the project, this score will be null. |
| multiseriesId |
string |
true |
|
A DataRobot-generated ID corresponding to a single series in a multiseries dataset. |
| multiseriesValues |
[string] |
true |
|
The actual values of series ID columns from the dataset. |
| rowCount |
integer |
true |
|
The number of rows available for this series in the input dataset. |
| startDate |
string,null(date-time) |
false |
|
The ISO-formatted start date of this series. |
| targetAverage |
any |
false |
|
For regression projects, this is the average (mean) value of target values for this series.For classification projects, this is the ratio of the positive class in the target for this series. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
number |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
null |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| validationScore |
number,null |
true |
|
The validation set score for this series |
SeriesAccuracyRetrieveResponse
{
"properties": {
"data": {
"description": "An array of available multiseries identifiers and column values.",
"items": {
"properties": {
"backtestingScore": {
"description": "The backtesting score for this series. If backtesting has not been run for this model, this score will be null.",
"type": [
"number",
"null"
]
},
"cluster": {
"description": "The cluster associated with this series. ",
"type": [
"string",
"null"
]
},
"duration": {
"description": "The duration of this series formatted as an ISO 8601 duration string.",
"format": "duration",
"type": "string"
},
"endDate": {
"description": "The ISO-formatted end date of this series.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"holdoutScore": {
"description": "The holdout set score for this series. If holdout is locked for the project, this score will be null.",
"type": [
"number",
"null"
]
},
"multiseriesId": {
"description": "A DataRobot-generated ID corresponding to a single series in a multiseries dataset.",
"type": "string"
},
"multiseriesValues": {
"description": "The actual values of series ID columns from the dataset.",
"items": {
"type": "string"
},
"type": "array"
},
"rowCount": {
"description": "The number of rows available for this series in the input dataset.",
"type": "integer"
},
"startDate": {
"description": "The ISO-formatted start date of this series.",
"format": "date-time",
"type": [
"string",
"null"
]
},
"targetAverage": {
"description": "For regression projects, this is the average (mean) value of target values for this series.For classification projects, this is the ratio of the positive class in the target for this series.",
"oneOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "null"
}
]
},
"validationScore": {
"description": "The validation set score for this series",
"type": [
"number",
"null"
]
}
},
"required": [
"backtestingScore",
"duration",
"multiseriesId",
"multiseriesValues",
"rowCount",
"validationScore"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "A URL pointing to the next page (if null, there is no next page).",
"type": [
"string",
"null"
]
},
"previous": {
"description": "A URL pointing to the previous page (if null, there is no previous page).",
"type": [
"string",
"null"
]
},
"querySeriesCount": {
"description": "The total number of series after filtering is applied.",
"type": "integer"
},
"totalSeriesCount": {
"description": "The total number of series in the project dataset.",
"type": "integer"
}
},
"required": [
"data",
"querySeriesCount",
"totalSeriesCount"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| data |
[SeriesAccuracyRetrieveDataResponse] |
true |
|
An array of available multiseries identifiers and column values. |
| next |
string,null |
false |
|
A URL pointing to the next page (if null, there is no next page). |
| previous |
string,null |
false |
|
A URL pointing to the previous page (if null, there is no previous page). |
| querySeriesCount |
integer |
true |
|
The total number of series after filtering is applied. |
| totalSeriesCount |
integer |
true |
|
The total number of series in the project dataset. |
ShapDistributionsData
{
"description": "SHAP distributions data.",
"properties": {
"features": {
"description": "List of SHAP distributions for each requested row.",
"items": {
"properties": {
"feature": {
"description": "The feature name in the dataset.",
"type": "string"
},
"featureType": {
"description": "Feature type.",
"enum": [
"T",
"X",
"B",
"C",
"CI",
"N",
"D",
"DD",
"FD",
"Q",
"CD",
"GEO",
"MC",
"INT",
"DOC"
],
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"shapValues": {
"description": "The SHAP distributions values for this row.",
"items": {
"properties": {
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer"
},
"featureValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The value of the feature for this row."
},
"predictionValue": {
"description": "The prediction value for this row.",
"type": "number"
},
"rowIndex": {
"description": "The index of this row.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number"
},
"weight": {
"description": "Weight of the row in the dataset.",
"type": [
"number",
"null"
],
"x-versionadded": "v2.37"
}
},
"required": [
"featureRank",
"featureValue",
"predictionValue",
"rowIndex",
"shapValue",
"weight"
],
"type": "object",
"x-versionadded": "v2.35"
},
"maxItems": 2500,
"type": "array"
}
},
"required": [
"feature",
"featureType",
"impactNormalized",
"impactUnnormalized",
"shapValues"
],
"type": "object",
"x-versionadded": "v2.35"
},
"maxItems": 100,
"type": "array"
},
"totalFeaturesCount": {
"description": "The total number of features.",
"type": "integer"
}
},
"required": [
"features",
"totalFeaturesCount"
],
"type": "object",
"x-versionadded": "v2.35"
}
SHAP distributions data.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| features |
[ShapDistributionsRow] |
true |
maxItems: 100
|
List of SHAP distributions for each requested row. |
| totalFeaturesCount |
integer |
true |
|
The total number of features. |
ShapDistributionsRow
{
"properties": {
"feature": {
"description": "The feature name in the dataset.",
"type": "string"
},
"featureType": {
"description": "Feature type.",
"enum": [
"T",
"X",
"B",
"C",
"CI",
"N",
"D",
"DD",
"FD",
"Q",
"CD",
"GEO",
"MC",
"INT",
"DOC"
],
"type": "string"
},
"impactNormalized": {
"description": "The same as `impactUnnormalized`, but normalized such that the highest value is `1`.",
"maximum": 1,
"type": "number"
},
"impactUnnormalized": {
"description": "How much worse the error metric score is when making predictions on modified data.",
"type": "number"
},
"shapValues": {
"description": "The SHAP distributions values for this row.",
"items": {
"properties": {
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer"
},
"featureValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The value of the feature for this row."
},
"predictionValue": {
"description": "The prediction value for this row.",
"type": "number"
},
"rowIndex": {
"description": "The index of this row.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number"
},
"weight": {
"description": "Weight of the row in the dataset.",
"type": [
"number",
"null"
],
"x-versionadded": "v2.37"
}
},
"required": [
"featureRank",
"featureValue",
"predictionValue",
"rowIndex",
"shapValue",
"weight"
],
"type": "object",
"x-versionadded": "v2.35"
},
"maxItems": 2500,
"type": "array"
}
},
"required": [
"feature",
"featureType",
"impactNormalized",
"impactUnnormalized",
"shapValues"
],
"type": "object",
"x-versionadded": "v2.35"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| feature |
string |
true |
|
The feature name in the dataset. |
| featureType |
string |
true |
|
Feature type. |
| impactNormalized |
number |
true |
maximum: 1
|
The same as impactUnnormalized, but normalized such that the highest value is 1. |
| impactUnnormalized |
number |
true |
|
How much worse the error metric score is when making predictions on modified data. |
| shapValues |
[ShapDistributionsValue] |
true |
maxItems: 2500
|
The SHAP distributions values for this row. |
Enumerated Values
| Property |
Value |
| featureType |
[T, X, B, C, CI, N, D, DD, FD, Q, CD, GEO, MC, INT, DOC] |
ShapDistributionsValue
{
"properties": {
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer"
},
"featureValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The value of the feature for this row."
},
"predictionValue": {
"description": "The prediction value for this row.",
"type": "number"
},
"rowIndex": {
"description": "The index of this row.",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number"
},
"weight": {
"description": "Weight of the row in the dataset.",
"type": [
"number",
"null"
],
"x-versionadded": "v2.37"
}
},
"required": [
"featureRank",
"featureValue",
"predictionValue",
"rowIndex",
"shapValue",
"weight"
],
"type": "object",
"x-versionadded": "v2.35"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureRank |
integer |
true |
|
The SHAP value rank of the feature for this row. |
| featureValue |
any |
true |
|
The value of the feature for this row. |
anyOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
|
none |
or
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
number |
false |
|
none |
or
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
or
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
null |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| predictionValue |
number |
true |
|
The prediction value for this row. |
| rowIndex |
integer,null |
true |
minimum: 0
|
The index of this row. |
| shapValue |
number |
true |
|
The SHAP value of the feature for this row. |
| weight |
number,null |
true |
|
Weight of the row in the dataset. |
ShapExplanationResponse
{
"properties": {
"feature": {
"description": "Feature name",
"type": "string"
},
"featureValue": {
"description": "Feature value for this row. First 50 characters are returned.",
"type": "string"
},
"strength": {
"description": "Shapley value for this feature and row.",
"type": "number"
}
},
"required": [
"feature",
"featureValue",
"strength"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| feature |
string |
true |
|
Feature name |
| featureValue |
string |
true |
|
Feature value for this row. First 50 characters are returned. |
| strength |
number |
true |
|
Shapley value for this feature and row. |
ShapImpactData
{
"description": "SHAP impact data.",
"properties": {
"baseValue": {
"description": "Mean of raw model predictions for the training data.",
"items": {
"type": "number"
},
"type": "array",
"x-versionadded": "v2.33"
},
"link": {
"description": "Link function used to connect the SHAP importance values to the model output.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"quickCompute": {
"default": true,
"description": "When enabled, limits the rows used from the selected source subset by default. When disabled, all rows are used.",
"type": "boolean",
"x-versionadded": "v2.35"
},
"rowCount": {
"description": "(Deprecated) The number of rows used to calculate SHAP impact. If ``rowCount`` is not specified, the value returned is ``null``.",
"type": [
"integer",
"null"
],
"x-versionadded": "v2.33",
"x-versiondeprecated": "v2.35"
},
"shapImpacts": {
"description": "A list that contains SHAP impact scores.",
"items": {
"properties": {
"featureName": {
"description": "The feature name in the dataset.",
"type": "string"
},
"impactNormalized": {
"description": "The normalized impact score value.",
"type": [
"number",
"null"
]
},
"impactUnnormalized": {
"description": "The raw impact score value.",
"type": "number"
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
}
},
"required": [
"baseValue",
"link",
"rowCount",
"shapImpacts"
],
"type": "object"
}
SHAP impact data.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| baseValue |
[number] |
true |
|
Mean of raw model predictions for the training data. |
| link |
string,null |
true |
|
Link function used to connect the SHAP importance values to the model output. |
| quickCompute |
boolean |
false |
|
When enabled, limits the rows used from the selected source subset by default. When disabled, all rows are used. |
| rowCount |
integer,null |
true |
|
(Deprecated) The number of rows used to calculate SHAP impact. If rowCount is not specified, the value returned is null. |
| shapImpacts |
[ShapImpactEntity] |
true |
|
A list that contains SHAP impact scores. |
ShapImpactEntity
{
"properties": {
"featureName": {
"description": "The feature name in the dataset.",
"type": "string"
},
"impactNormalized": {
"description": "The normalized impact score value.",
"type": [
"number",
"null"
]
},
"impactUnnormalized": {
"description": "The raw impact score value.",
"type": "number"
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureName |
string |
true |
|
The feature name in the dataset. |
| impactNormalized |
number,null |
true |
|
The normalized impact score value. |
| impactUnnormalized |
number |
true |
|
The raw impact score value. |
ShapImpactRetrieveResponse
{
"properties": {
"count": {
"description": "The number of shapImpact object returned",
"type": "integer"
},
"rowCount": {
"description": "The number of rows from dataset to use.",
"type": "integer"
},
"shapImpacts": {
"description": "A list which contains shap impact scores for top 1000 features used by a model",
"items": {
"properties": {
"featureName": {
"description": "The feature name in dataset",
"type": "string"
},
"impactNormalized": {
"description": "The normalized impact score value (largest value is 1)",
"type": "number"
},
"impactUnnormalized": {
"description": "The raw impact score value",
"type": "number"
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized"
],
"type": "object"
},
"maxItems": 1000,
"minItems": 1,
"type": "array"
}
},
"required": [
"count",
"shapImpacts"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
true |
|
The number of shapImpact object returned |
| rowCount |
integer |
false |
|
The number of rows from dataset to use. |
| shapImpacts |
[ShapImpactsResponse] |
true |
maxItems: 1000
minItems: 1
|
A list which contains shap impact scores for top 1000 features used by a model |
ShapImpactsResponse
{
"properties": {
"featureName": {
"description": "The feature name in dataset",
"type": "string"
},
"impactNormalized": {
"description": "The normalized impact score value (largest value is 1)",
"type": "number"
},
"impactUnnormalized": {
"description": "The raw impact score value",
"type": "number"
}
},
"required": [
"featureName",
"impactNormalized",
"impactUnnormalized"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureName |
string |
true |
|
The feature name in dataset |
| impactNormalized |
number |
true |
|
The normalized impact score value (largest value is 1) |
| impactUnnormalized |
number |
true |
|
The raw impact score value |
ShapMatrixData
{
"description": "SHAP matrix data.",
"properties": {
"baseValue": {
"description": "The mean of the raw model predictions for the training data.",
"items": {
"type": "number"
},
"type": "array",
"x-versionadded": "v2.33"
},
"colnames": {
"description": "The names of each column in the SHAP matrix.",
"items": {
"type": "string"
},
"type": "array",
"x-versionadded": "v2.33"
},
"linkFunction": {
"description": "The link function used to connect the feature importance values to the model output.",
"type": [
"string",
"null"
],
"x-versionadded": "v2.33"
},
"matrix": {
"description": "SHAP matrix values.",
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array",
"x-versionadded": "v2.33"
},
"rowIndex": {
"description": "The index of the data row used to compute the SHAP matrix. Not used in time-aware projects.",
"items": {
"type": "integer"
},
"type": "array",
"x-versionadded": "v2.33"
},
"timeSeriesRowIndex": {
"description": "An index composed of the timestamp, series id and forecast distance. Only used in time-aware projects.",
"items": {
"items": {
"oneOf": [
{
"type": "integer"
},
{
"type": "string"
}
]
},
"maxLength": 2,
"minLength": 2,
"type": "array"
},
"type": "array",
"x-versionadded": "v2.36"
}
},
"required": [
"baseValue",
"colnames",
"linkFunction",
"matrix",
"rowIndex"
],
"type": "object"
}
SHAP matrix data.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| baseValue |
[number] |
true |
|
The mean of the raw model predictions for the training data. |
| colnames |
[string] |
true |
|
The names of each column in the SHAP matrix. |
| linkFunction |
string,null |
true |
|
The link function used to connect the feature importance values to the model output. |
| matrix |
[array] |
true |
|
SHAP matrix values. |
| rowIndex |
[integer] |
true |
|
The index of the data row used to compute the SHAP matrix. Not used in time-aware projects. |
| timeSeriesRowIndex |
[array] |
false |
|
An index composed of the timestamp, series id and forecast distance. Only used in time-aware projects. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
ShapMatrixListDataField
{
"properties": {
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"id": {
"description": "The ID of the SHAP matrix record.",
"type": "string"
},
"metadata": {
"description": "The metadata containing SHAP matrix calculation details.",
"properties": {
"maxNormalizedMismatch": {
"default": 0,
"description": "The maximal relative normalized mismatch value.",
"type": "number"
},
"mismatchRowCount": {
"default": 0,
"description": "The count of rows for which additivity check failed.",
"type": "integer"
}
},
"type": "object"
},
"modelId": {
"description": "The model ID.",
"type": "string"
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"url": {
"description": "The url at which you can retrieve the SHAP matrix.",
"format": "uri",
"type": "string"
}
},
"required": [
"datasetId",
"id",
"metadata",
"modelId",
"projectId",
"url"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| datasetId |
string |
true |
|
The dataset ID. |
| id |
string |
true |
|
The ID of the SHAP matrix record. |
| metadata |
ShapMatrixMetadataField |
true |
|
The metadata containing SHAP matrix calculation details. |
| modelId |
string |
true |
|
The model ID. |
| projectId |
string |
true |
|
The project ID. |
| url |
string(uri) |
true |
|
The url at which you can retrieve the SHAP matrix. |
ShapMatrixListResponse
{
"properties": {
"count": {
"description": "Number of items returned on this page.",
"type": "integer"
},
"data": {
"description": "Array of SHAP matrix scores records.",
"items": {
"properties": {
"datasetId": {
"description": "The dataset ID.",
"type": "string"
},
"id": {
"description": "The ID of the SHAP matrix record.",
"type": "string"
},
"metadata": {
"description": "The metadata containing SHAP matrix calculation details.",
"properties": {
"maxNormalizedMismatch": {
"default": 0,
"description": "The maximal relative normalized mismatch value.",
"type": "number"
},
"mismatchRowCount": {
"default": 0,
"description": "The count of rows for which additivity check failed.",
"type": "integer"
}
},
"type": "object"
},
"modelId": {
"description": "The model ID.",
"type": "string"
},
"projectId": {
"description": "The project ID.",
"type": "string"
},
"url": {
"description": "The url at which you can retrieve the SHAP matrix.",
"format": "uri",
"type": "string"
}
},
"required": [
"datasetId",
"id",
"metadata",
"modelId",
"projectId",
"url"
],
"type": "object"
},
"type": "array"
},
"next": {
"description": "URL pointing to the next page (if null, there is no next page).",
"format": "uri",
"type": [
"string",
"null"
]
},
"previous": {
"description": "URL pointing to the previous page (if null, there is no previous page).",
"format": "uri",
"type": [
"string",
"null"
]
}
},
"required": [
"data",
"next",
"previous"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| count |
integer |
false |
|
Number of items returned on this page. |
| data |
[ShapMatrixListDataField] |
true |
|
Array of SHAP matrix scores records. |
| next |
string,null(uri) |
true |
|
URL pointing to the next page (if null, there is no next page). |
| previous |
string,null(uri) |
true |
|
URL pointing to the previous page (if null, there is no previous page). |
{
"description": "The metadata containing SHAP matrix calculation details.",
"properties": {
"maxNormalizedMismatch": {
"default": 0,
"description": "The maximal relative normalized mismatch value.",
"type": "number"
},
"mismatchRowCount": {
"default": 0,
"description": "The count of rows for which additivity check failed.",
"type": "integer"
}
},
"type": "object"
}
The metadata containing SHAP matrix calculation details.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| maxNormalizedMismatch |
number |
false |
|
The maximal relative normalized mismatch value. |
| mismatchRowCount |
integer |
false |
|
The count of rows for which additivity check failed. |
ShapMatrixRetrieveResponse
{
"properties": {
"columnNames": {
"description": "The column names for corresponding dataset & their SHAP values.",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"columnNames"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| columnNames |
[string] |
true |
|
The column names for corresponding dataset & their SHAP values. |
ShapPreviewData
{
"description": "SHAP preview data.",
"properties": {
"previews": {
"description": "List of SHAP previews for each requested row.",
"items": {
"properties": {
"predictionValue": {
"description": "The prediction value for this row.",
"type": "number",
"x-versionadded": "v2.33"
},
"previewValues": {
"description": "The SHAP preview values for this row.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string",
"x-versionadded": "v2.33"
},
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer",
"x-versionadded": "v2.33"
},
"featureValue": {
"description": "The value of the feature for this row.",
"type": "string",
"x-versionadded": "v2.33"
},
"hasTextExplanations": {
"description": "Whether the feature has text explanations available for this row.",
"type": "boolean",
"x-versionadded": "v2.33"
},
"isImage": {
"description": "Whether the feature is an image or not.",
"type": "boolean",
"x-versionadded": "v2.34"
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number",
"x-versionadded": "v2.33"
},
"textExplanations": {
"description": "List of the text explanations for the feature for this row.",
"items": {
"type": "string"
},
"type": "array",
"x-versionadded": "v2.33"
}
},
"required": [
"featureName",
"featureRank",
"featureValue",
"hasTextExplanations",
"shapValue",
"textExplanations"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
},
"rowIndex": {
"description": "The index of this row.",
"minimum": 0,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.33"
},
"timeSeriesRowIndex": {
"description": "An index composed of the timestamp, series ID, and forecast distance. This index is used only in time-aware projects.",
"items": {
"oneOf": [
{
"type": "integer"
},
{
"type": "string"
}
]
},
"maxLength": 2,
"minLength": 2,
"type": [
"array",
"null"
],
"x-versionadded": "v2.36"
},
"totalPreviewFeatures": {
"description": "The total number of features available after name filters have been applied.",
"minimum": 0,
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"predictionValue",
"previewValues",
"rowIndex",
"totalPreviewFeatures"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
},
"previewsCount": {
"description": "The total number of previews.",
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"previews",
"previewsCount"
],
"type": "object"
}
SHAP preview data.
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| previews |
[ShapPreviewRow] |
true |
|
List of SHAP previews for each requested row. |
| previewsCount |
integer |
true |
|
The total number of previews. |
ShapPreviewRow
{
"properties": {
"predictionValue": {
"description": "The prediction value for this row.",
"type": "number",
"x-versionadded": "v2.33"
},
"previewValues": {
"description": "The SHAP preview values for this row.",
"items": {
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string",
"x-versionadded": "v2.33"
},
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer",
"x-versionadded": "v2.33"
},
"featureValue": {
"description": "The value of the feature for this row.",
"type": "string",
"x-versionadded": "v2.33"
},
"hasTextExplanations": {
"description": "Whether the feature has text explanations available for this row.",
"type": "boolean",
"x-versionadded": "v2.33"
},
"isImage": {
"description": "Whether the feature is an image or not.",
"type": "boolean",
"x-versionadded": "v2.34"
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number",
"x-versionadded": "v2.33"
},
"textExplanations": {
"description": "List of the text explanations for the feature for this row.",
"items": {
"type": "string"
},
"type": "array",
"x-versionadded": "v2.33"
}
},
"required": [
"featureName",
"featureRank",
"featureValue",
"hasTextExplanations",
"shapValue",
"textExplanations"
],
"type": "object"
},
"type": "array",
"x-versionadded": "v2.33"
},
"rowIndex": {
"description": "The index of this row.",
"minimum": 0,
"type": [
"integer",
"null"
],
"x-versionadded": "v2.33"
},
"timeSeriesRowIndex": {
"description": "An index composed of the timestamp, series ID, and forecast distance. This index is used only in time-aware projects.",
"items": {
"oneOf": [
{
"type": "integer"
},
{
"type": "string"
}
]
},
"maxLength": 2,
"minLength": 2,
"type": [
"array",
"null"
],
"x-versionadded": "v2.36"
},
"totalPreviewFeatures": {
"description": "The total number of features available after name filters have been applied.",
"minimum": 0,
"type": "integer",
"x-versionadded": "v2.33"
}
},
"required": [
"predictionValue",
"previewValues",
"rowIndex",
"totalPreviewFeatures"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| predictionValue |
number |
true |
|
The prediction value for this row. |
| previewValues |
[ShapPreviewValue] |
true |
|
The SHAP preview values for this row. |
| rowIndex |
integer,null |
true |
minimum: 0
|
The index of this row. |
| timeSeriesRowIndex |
array,null |
false |
maxLength: 2
minLength: 2
minLength: 2
|
An index composed of the timestamp, series ID, and forecast distance. This index is used only in time-aware projects. |
oneOf
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
integer |
false |
|
none |
xor
| Name |
Type |
Required |
Restrictions |
Description |
| » anonymous |
string |
false |
|
none |
continued
| Name |
Type |
Required |
Restrictions |
Description |
| totalPreviewFeatures |
integer |
true |
minimum: 0
|
The total number of features available after name filters have been applied. |
ShapPreviewValue
{
"properties": {
"featureName": {
"description": "The name of the feature.",
"type": "string",
"x-versionadded": "v2.33"
},
"featureRank": {
"description": "The SHAP value rank of the feature for this row.",
"exclusiveMinimum": 0,
"type": "integer",
"x-versionadded": "v2.33"
},
"featureValue": {
"description": "The value of the feature for this row.",
"type": "string",
"x-versionadded": "v2.33"
},
"hasTextExplanations": {
"description": "Whether the feature has text explanations available for this row.",
"type": "boolean",
"x-versionadded": "v2.33"
},
"isImage": {
"description": "Whether the feature is an image or not.",
"type": "boolean",
"x-versionadded": "v2.34"
},
"shapValue": {
"description": "The SHAP value of the feature for this row.",
"type": "number",
"x-versionadded": "v2.33"
},
"textExplanations": {
"description": "List of the text explanations for the feature for this row.",
"items": {
"type": "string"
},
"type": "array",
"x-versionadded": "v2.33"
}
},
"required": [
"featureName",
"featureRank",
"featureValue",
"hasTextExplanations",
"shapValue",
"textExplanations"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureName |
string |
true |
|
The name of the feature. |
| featureRank |
integer |
true |
|
The SHAP value rank of the feature for this row. |
| featureValue |
string |
true |
|
The value of the feature for this row. |
| hasTextExplanations |
boolean |
true |
|
Whether the feature has text explanations available for this row. |
| isImage |
boolean |
false |
|
Whether the feature is an image or not. |
| shapValue |
number |
true |
|
The SHAP value of the feature for this row. |
| textExplanations |
[string] |
true |
|
List of the text explanations for the feature for this row. |
TargetBin
{
"properties": {
"targetBinEnd": {
"description": "End value for the target bin",
"type": "number"
},
"targetBinStart": {
"description": "Start value for the target bin",
"type": "number"
}
},
"required": [
"targetBinEnd",
"targetBinStart"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| targetBinEnd |
number |
true |
|
End value for the target bin |
| targetBinStart |
number |
true |
|
Start value for the target bin |
Text
{
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"importantNgrams"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| allData |
AllDataText |
true |
|
Statistics for all data for different feature values. |
| insightName |
string |
true |
|
Insight name. |
| perCluster |
[PerClusterText] |
true |
|
Statistic values for different feature values in this cluster. |
Enumerated Values
| Property |
Value |
| insightName |
importantNgrams |
TextFeature
{
"properties": {
"featureImpact": {
"description": "Feature Impact score.",
"type": [
"number",
"null"
]
},
"featureName": {
"description": "Feature name.",
"type": "string"
},
"featureType": {
"description": "Feature Type.",
"enum": [
"text"
],
"type": "string"
},
"insights": {
"description": "A list of Cluster Insights for a feature.",
"items": {
"properties": {
"allData": {
"description": "Statistics for all data for different feature values.",
"properties": {
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"perValueStatistics"
],
"type": "object"
},
"insightName": {
"description": "Insight name.",
"enum": [
"importantNgrams"
],
"type": "string"
},
"perCluster": {
"description": "Statistic values for different feature values in this cluster.",
"items": {
"properties": {
"clusterName": {
"description": "Cluster name.",
"type": "string"
},
"missingRowsPercent": {
"description": "A percentage of all rows that have a missing value for this feature.",
"maximum": 100,
"minimum": 0,
"type": [
"number",
"null"
]
},
"perValueStatistics": {
"description": "Statistic value for feature values in all data or a cluster.",
"items": {
"properties": {
"contextualExtracts": {
"description": "Contextual extracts that show context for the n-gram.",
"items": {
"type": "string"
},
"type": "array"
},
"importance": {
"description": "Importance value for this n-gram.",
"type": "number"
},
"ngram": {
"description": "An n-gram.",
"type": "string"
}
},
"required": [
"contextualExtracts",
"importance",
"ngram"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"clusterName",
"perValueStatistics"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"allData",
"insightName",
"perCluster"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"featureName",
"featureType",
"insights"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| featureImpact |
number,null |
false |
|
Feature Impact score. |
| featureName |
string |
true |
|
Feature name. |
| featureType |
string |
true |
|
Feature Type. |
| insights |
[Text] |
true |
|
A list of Cluster Insights for a feature. |
Enumerated Values
| Property |
Value |
| featureType |
text |
UploadRatingTable
{
"properties": {
"parentModelId": {
"description": "the parent model this rating table file was derived from",
"type": "string"
},
"ratingTableFile": {
"description": "rating table file to use for the new rating table. Accepts `Content-Type:multipart/form-data`",
"format": "binary",
"type": "string"
},
"ratingTableName": {
"description": "the name of the new rating table to create",
"type": "string"
}
},
"required": [
"parentModelId",
"ratingTableFile",
"ratingTableName"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| parentModelId |
string |
true |
|
the parent model this rating table file was derived from |
| ratingTableFile |
string(binary) |
true |
|
rating table file to use for the new rating table. Accepts Content-Type:multipart/form-data |
| ratingTableName |
string |
true |
|
the name of the new rating table to create |
WordCloudNgram
{
"properties": {
"class": {
"description": "For classification - values of the target class for corresponding word or ngram. For regression - null.",
"type": [
"string",
"null"
]
},
"coefficient": {
"description": "Describes effect of this ngram on the target. A large negative value means a strong effect toward the negative class in classification projects and a smaller predicted target value in regression projects. A large positive value means a strong effect toward the positive class and a larger predicted target value respectively.",
"maximum": 1,
"minimum": -1,
"type": "number"
},
"count": {
"description": "Number of rows in the training sample where this ngram appears.",
"type": "integer"
},
"frequency": {
"description": "Frequency of this ngram relative to the most common ngram.",
"exclusiveMinimum": 0,
"maximum": 1,
"type": "number"
},
"isStopword": {
"description": "True for ngrams that DataRobot evaluates as stopwords.",
"type": "boolean"
},
"ngram": {
"description": "Word or ngram value.",
"type": "string"
},
"variable": {
"description": "String representation of the ngram source - contains column name and, for some models, preprocessing details. E.g. NGRAM_OCCUR_L2_colname will be for ngram occurrences count using L2 normalization from the colname column.",
"type": "string",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficient",
"count",
"frequency",
"isStopword",
"ngram",
"variable"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| class |
string,null |
false |
|
For classification - values of the target class for corresponding word or ngram. For regression - null. |
| coefficient |
number |
true |
maximum: 1
minimum: -1
|
Describes effect of this ngram on the target. A large negative value means a strong effect toward the negative class in classification projects and a smaller predicted target value in regression projects. A large positive value means a strong effect toward the positive class and a larger predicted target value respectively. |
| count |
integer |
true |
|
Number of rows in the training sample where this ngram appears. |
| frequency |
number |
true |
maximum: 1
|
Frequency of this ngram relative to the most common ngram. |
| isStopword |
boolean |
true |
|
True for ngrams that DataRobot evaluates as stopwords. |
| ngram |
string |
true |
|
Word or ngram value. |
| variable |
string |
true |
|
String representation of the ngram source - contains column name and, for some models, preprocessing details. E.g. NGRAM_OCCUR_L2_colname will be for ngram occurrences count using L2 normalization from the colname column. |
WordCloudRetrieveResponse
{
"properties": {
"ngrams": {
"description": "A list of dictionaries containing information about the most important ngrams.",
"items": {
"properties": {
"class": {
"description": "For classification - values of the target class for corresponding word or ngram. For regression - null.",
"type": [
"string",
"null"
]
},
"coefficient": {
"description": "Describes effect of this ngram on the target. A large negative value means a strong effect toward the negative class in classification projects and a smaller predicted target value in regression projects. A large positive value means a strong effect toward the positive class and a larger predicted target value respectively.",
"maximum": 1,
"minimum": -1,
"type": "number"
},
"count": {
"description": "Number of rows in the training sample where this ngram appears.",
"type": "integer"
},
"frequency": {
"description": "Frequency of this ngram relative to the most common ngram.",
"exclusiveMinimum": 0,
"maximum": 1,
"type": "number"
},
"isStopword": {
"description": "True for ngrams that DataRobot evaluates as stopwords.",
"type": "boolean"
},
"ngram": {
"description": "Word or ngram value.",
"type": "string"
},
"variable": {
"description": "String representation of the ngram source - contains column name and, for some models, preprocessing details. E.g. NGRAM_OCCUR_L2_colname will be for ngram occurrences count using L2 normalization from the colname column.",
"type": "string",
"x-versionadded": "v2.19"
}
},
"required": [
"coefficient",
"count",
"frequency",
"isStopword",
"ngram",
"variable"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"ngrams"
],
"type": "object"
}
Properties
| Name |
Type |
Required |
Restrictions |
Description |
| ngrams |
[WordCloudNgram] |
true |
|
A list of dictionaries containing information about the most important ngrams. |