Datetime Partitioning¶
This page outlines the operations, endpoints, parameters, and example requests and responses for the Datetime Partitioning.
GET /api/v2/projects/{projectId}/datetimePartitioning/¶
Retrieve datetime partitioning configuration
The datetime partition object in the response describes the full partitioning parameters. Since it becomes available after the target has been fully specified and the project is ready for modeling, there are some additional fields available compared to the response from POST /api/v2/projects/{projectId}/datetimePartitioning/.
The available training data corresponds to all the data available for training, while the primary training data corresponds to the data that can be used to train while ensuring that all backtests are available. If a model is trained with more data than is available in the primary training data, then all backtests may not have scores available.
All durations and datetimes will be specified in accordance with the :ref:timestamp and duration formatting rules<time_format>.
Code samples¶
# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/datetimePartitioning/ \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| projectId | path | string | true | The project ID |
Example responses¶
200 Response
{
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": true,
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"availableHoldoutEndDate": "2019-08-24T14:15:22Z",
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingRowCount": 0,
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"backtests": [
{
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingRowCount": 0,
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapRowCount": 0,
"gapStartDate": "2019-08-24T14:15:22Z",
"index": 0,
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingRowCount": 0,
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"totalRowCount": 0,
"validationDuration": "string",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationRowCount": 0,
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"calendarName": "string",
"crossSeriesGroupByColumns": [
"string"
],
"dateFormat": "string",
"datetimePartitionColumn": "string",
"datetimePartitioningId": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": true,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapRowCount": 0,
"gapStartDate": "2019-08-24T14:15:22Z",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutRowCount": 0,
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 1,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"numberOfDoNotDeriveFeatures": 0,
"numberOfKnownInAdvanceFeatures": 0,
"partitioningExtendedWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
{
"message": "string",
"title": "string",
"type": "string"
}
]
}
],
"partitioningWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
"string"
]
}
],
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingRowCount": 0,
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"projectId": "string",
"totalRowCount": 0,
"treatAsExponential": "auto",
"unsupervisedMode": true,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": true,
"useTimeSeries": true,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Generated datetime partitioning. | FinalDatetimePartitioningResponse |
| 422 | Unprocessable Entity | Partitioning has not been set. | None |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/projects/{projectId}/datetimePartitioning/¶
Preview the fully specified datetime partitioning generated by the requested configuration. DEPRECATED: Please use the optimized partitioning route instead: POST /api/v2/projects/{projectId}/optimizedDatetimePartitionings/
Populates the full datetime partitioning that would be used if the same arguments were passed to PATCH /api/v2/projects/{projectId}/aim/ based on the requested configuration, generating defaults for all non-specified values, so that potential configurations can be tested prior to setting the target and applying a configuration.
useTimeSeries controls whether a time series project should be created or a normal project that uses datetime partitioning. See :ref:Time-Series Projects<time_series_overview> for more detail on the differences between time series projects and datetime partitioned projects. Time-series projects are only available to some users and use the additional settings of featureDerivationWindowStart and featureDerivationWindowEnd to establish feature derivation window and forecastWindowStart and forecastWindowEnd to establish a forecast window. The overview referenced above provides more information about using feature derivation and forecast windows.
When specifying a feature derivation window of a forecast window, the number of units it spans (end - start) must be an integer multiple of the timeStep of the datetimePartitionColumn.
All durations and datetimes should be specified in accordance with the :ref:timestamp and duration formatting rules<time_format>.
Code samples¶
# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/datetimePartitioning/ \
-H "Content-Type: application/json" \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
Body parameter¶
{
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": false,
"autopilotClusterList": [
2
],
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"backtests": [
{
"gapDuration": "string",
"index": 0,
"validationDuration": "string",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"datetimePartitionColumn": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": false,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 5,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto",
"unsupervisedMode": false,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": false,
"useSupervisedFeatureReduction": true,
"useTimeSeries": false,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| projectId | path | string | true | The project ID |
| body | body | DatetimePartitioningDataForOpenApi | false | none |
Example responses¶
200 Response
{
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": true,
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"availableHoldoutEndDate": "2019-08-24T14:15:22Z",
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"backtests": [
{
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"index": 0,
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"validationDuration": "string",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"calendarName": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"dateFormat": "string",
"datetimePartitionColumn": "string",
"datetimePartitioningId": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": true,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 1,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"numberOfDoNotDeriveFeatures": 0,
"numberOfKnownInAdvanceFeatures": 0,
"partitioningExtendedWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
{
"message": "string",
"title": "string",
"type": "string"
}
]
}
],
"partitioningWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
"string"
]
}
],
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"projectId": "string",
"treatAsExponential": "auto",
"unsupervisedMode": true,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": true,
"useTimeSeries": true,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Generated datetime partitioning. | DatetimePartitioningResponse |
| 404 | Not Found | Requested feature was not found. | None |
| 422 | Unprocessable Entity | Partitioning generation failed. | None |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/projects/{projectId}/optimizedDatetimePartitionings/¶
List all created optimized datetime partitioning configurations
Code samples¶
# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/optimizedDatetimePartitionings/?limit=10 \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
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. |
| projectId | path | string | true | The project ID |
Example responses¶
200 Response
{
"count": 0,
"data": [
{
"datetimePartitionColumn": "string",
"id": "string",
"partitionData": {
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": true,
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"availableHoldoutEndDate": "2019-08-24T14:15:22Z",
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"backtests": [
{
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"index": 0,
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"validationDuration": "string",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"calendarName": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"dateFormat": "string",
"datetimePartitionColumn": "string",
"datetimePartitioningId": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": true,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 1,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"numberOfDoNotDeriveFeatures": 0,
"numberOfKnownInAdvanceFeatures": 0,
"partitioningExtendedWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
{
"message": "string",
"title": "string",
"type": "string"
}
]
}
],
"partitioningWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
"string"
]
}
],
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"projectId": "string",
"treatAsExponential": "auto",
"unsupervisedMode": true,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": true,
"useTimeSeries": true,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
},
"target": "string"
}
],
"next": "http://example.com",
"previous": "http://example.com"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | List of optimized datetime partitionings for projectId | OptimizedDatetimePartitioningListResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/projects/{projectId}/optimizedDatetimePartitionings/¶
Create an optimized datetime partitioning configuration using the target.
Initializes a job to construct an optimized datetime partitioning using the date and target information to ensure that backtests sufficiently cover regions of interest in the target. This is an asynchronous job. The results of the asynchronous job (backtests and other parameters can be used in the synchronous version.
useTimeSeries controls whether a time series project should be created or a normal project that uses datetime partitioning. See :ref:Time-Series Projects<time_series_overview> for more detail on the differences between time series projects and datetime partitioned projects. Time-series projects are only available to some users and use the additional settings of featureDerivationWindowStart and featureDerivationWindowEnd to establish feature derivation window and forecastWindowStart and forecastWindowEnd to establish a forecast window. The overview referenced above provides more information about using feature derivation and forecast windows.
When specifying a feature derivation window of a forecast window, the number of units it spans (end - start) must be an integer multiple of the timeStep of the datetimePartitionColumn.
All durations and datetimes should be specified in accordance with the :ref:timestamp and duration formatting rules<time_format>.
Code samples¶
# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/optimizedDatetimePartitionings/ \
-H "Content-Type: application/json" \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
Body parameter¶
{
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": false,
"autopilotClusterList": [
2
],
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"backtests": [
{
"gapDuration": "string",
"index": 0,
"validationDuration": "string",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"datetimePartitionColumn": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": false,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 5,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"target": "string",
"treatAsExponential": "auto",
"unsupervisedMode": false,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": false,
"useSupervisedFeatureReduction": true,
"useTimeSeries": false,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| projectId | path | string | true | The project ID |
| body | body | OptimizedDatetimePartitioningData | false | none |
Example responses¶
200 Response
{
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": true,
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"availableHoldoutEndDate": "2019-08-24T14:15:22Z",
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"backtests": [
{
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"index": 0,
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"validationDuration": "string",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"calendarName": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"dateFormat": "string",
"datetimePartitionColumn": "string",
"datetimePartitioningId": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": true,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 1,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"numberOfDoNotDeriveFeatures": 0,
"numberOfKnownInAdvanceFeatures": 0,
"partitioningExtendedWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
{
"message": "string",
"title": "string",
"type": "string"
}
]
}
],
"partitioningWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
"string"
]
}
],
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"projectId": "string",
"treatAsExponential": "auto",
"unsupervisedMode": true,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": true,
"useTimeSeries": true,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Generated datetime partitioning. | DatetimePartitioningResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/projects/{projectId}/optimizedDatetimePartitionings/{datetimePartitioningId}/¶
Retrieve optimized datetime partitioning configuration
The optimized datetime partition objects are structurally identical to the original datetime partition objects, however they are retrieved from a mongo database after creation as opposed to being calculated synchronously. The datetime partition object in the response describes the full partitioning parameters.
The available training data corresponds to all the data available for training, while the primary training data corresponds to the data that can be used to train while ensuring that all backtests are available. If a model is trained with more data than is available in the primary training data, then all backtests may not have scores available.
.. note:: All durations and datetimes should be specified in accordance with the :ref:timestamp and duration formatting rules <time_format>.
Code samples¶
# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/optimizedDatetimePartitionings/{datetimePartitioningId}/ \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| projectId | path | string | true | The project ID |
| datetimePartitioningId | path | string | true | The ID of the datetime partitioning to retrieve. |
Example responses¶
200 Response
{
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": true,
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"availableHoldoutEndDate": "2019-08-24T14:15:22Z",
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"backtests": [
{
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"index": 0,
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"validationDuration": "string",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"calendarName": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"dateFormat": "string",
"datetimePartitionColumn": "string",
"datetimePartitioningId": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": true,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 1,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"numberOfDoNotDeriveFeatures": 0,
"numberOfKnownInAdvanceFeatures": 0,
"partitioningExtendedWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
{
"message": "string",
"title": "string",
"type": "string"
}
]
}
],
"partitioningWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
"string"
]
}
],
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"projectId": "string",
"treatAsExponential": "auto",
"unsupervisedMode": true,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": true,
"useTimeSeries": true,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Optimized datetime partitioning configuration | DatetimePartitioningResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/projects/{projectId}/optimizedDatetimePartitionings/{datetimePartitioningId}/datetimePartitioningInput/¶
Retrieve optimized datetime partitioning input
The datetime partition object in the response describes the inputs used to create the full partitioning object.
Code samples¶
# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/optimizedDatetimePartitionings/{datetimePartitioningId}/datetimePartitioningInput/ \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| projectId | path | string | true | The project ID |
| datetimePartitioningId | path | string | true | The ID of the datetime partitioning to retrieve. |
Example responses¶
200 Response
{
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": false,
"autopilotClusterList": [
2
],
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"backtests": [
{
"gapDuration": "string",
"index": 0,
"validationDuration": "string",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"datetimePartitionColumn": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": false,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 5,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"target": "string",
"treatAsExponential": "auto",
"unsupervisedMode": false,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": false,
"useSupervisedFeatureReduction": true,
"useTimeSeries": false,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Optimized datetime partitioning input | OptimizedDatetimePartitioningData |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/projects/{projectId}/optimizedDatetimePartitionings/{datetimePartitioningId}/datetimePartitioningLog/¶
Retrieve the datetime partitioning log content and log length for an optimized datetime partitioning as JSON.
The Date/Time Partitioning Log provides details about the partitioning process for an OTV or Time Series project.
Code samples¶
# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/optimizedDatetimePartitionings/{datetimePartitioningId}/datetimePartitioningLog/ \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
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 |
| datetimePartitioningId | path | string | true | The ID of the datetime partitioning to retrieve. |
Example responses¶
200 Response
{
"count": 0,
"datetimePartitioningLog": "string",
"next": "http://example.com",
"previous": "http://example.com",
"totalLogLines": 0
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | none | DatetimePartitioningLogListControllerResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/projects/{projectId}/optimizedDatetimePartitionings/{datetimePartitioningId}/datetimePartitioningLog/file/¶
Retrieve a text file containing the datetime partitioning log.
The Date/Time Partitioning Log provides details about the partitioning process for an OTV or Time Series project.
Code samples¶
# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/optimizedDatetimePartitionings/{datetimePartitioningId}/datetimePartitioningLog/file/ \
-H "Authorization: Bearer {access-token}"
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| projectId | path | string | true | The project ID |
| datetimePartitioningId | path | string | true | The ID of the datetime partitioning to retrieve. |
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | none | None |
Response Headers¶
| Status | Header | Type | Format | Description |
|---|---|---|---|---|
| 200 | Content-Disposition | string | attachment;filename=<filename>.txt The suggested filename is dynamically generated |
|
| 200 | Content-Type | string | MIME type of the returned data |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/projects/{projectId}/timeSeriesFeatureLog/¶
Retrieve the feature derivation log content and log length for a time series project as JSON.
The Time Series Feature Log provides details about the feature generation process for a time series project. It includes information about which features are generated and their priority,as well as the detected properties of the time series data such as whether the series is stationary, and periodicities detected.
This route is only supported for time series projects that have finished partitioning.
The feature derivation log will include information about:
- Detected stationarity of the series, e.g.,
Series detected as non-stationary - Detected presence of multiplicative trend in the series, e.g.,
Multiplicative trend detected - Detected periodicities in the series, e.g.,
Detected periodicities: 7 day - Maximum number of feature to be generated, e.g.,
Maximum number of feature to be generated is 1440 - Window sizes used in rolling statistics / lag extractors, e.g.,
The window sizes chosen to be: 2 months - Features that are specified as known-in-advance, e.g.,
Variables treated as apriori: holiday - Details about features generated as timeseries features, and their priority, e.g.,
Generating feature "date (actual)" from "date" (priority: 1) - Details about why certain variables are transformed in the input data, e.g.,
Generating variable "y (log)" from "y" because multiplicative trend is detected
Code samples¶
# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/timeSeriesFeatureLog/ \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
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
{
"count": 0,
"featureLog": "string",
"next": "http://example.com",
"previous": "http://example.com",
"totalLogLines": 0
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | none | TimeSeriesFeatureLogListControllerResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/projects/{projectId}/timeSeriesFeatureLog/file/¶
Retrieve a text file containing the time series project feature log.
The Time Series Feature Log provides details about the feature generation process for a time series project. It includes information about which features are generated and their priority,as well as the detected properties of the time series data such as whether the series is stationary, and periodicities detected.
This route is only supported for time series projects that have finished partitioning.
The feature derivation log will include information about:
- Maximum number of feature to be generated, e.g.,
Limit on the maximum number of feature in this project is 500 - Number of derived features tested during the feature generation process, e.g.,
Total number of derived features during the feature generation process is 571 - Number of generated features removed during the feature reduction process e.g.
Total number of features removed during the feature reduction process is 472 - Number of remaining features after the combined feature generation and reduction process, e.g.,
The finalized number of features is 99 - Detected stationarity of the series, e.g.,
Series detected as non-stationary - Detected presence of multiplicative trend in the series, e.g.,
Multiplicative trend detected - Detected periodicities in the series, e.g.,
Detected periodicities: 7 day - Window sizes used in rolling statistics / lag extractors, e.g.,
The window sizes chosen to be: 2 months (because the time step is 1 month and Feature Derivation Window is 2 months) - Features that are specified as known-in-advance, e.g.,
Variables treated as apriori: holiday - Details about why certain variables are transformed in the input data, e.g.,
Generating variable "y (log)" from "y" because multiplicative trend is detected - Details about features generated as time series features, and their priority, e.g.,
Generating feature "date (actual)" from "date" (priority: 1)
Code samples¶
# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/timeSeriesFeatureLog/file/ \
-H "Authorization: Bearer {access-token}"
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| projectId | path | string | true | The project ID |
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | none | None |
Response Headers¶
| Status | Header | Type | Format | Description |
|---|---|---|---|---|
| 200 | Content-Disposition | string | attachment;filename=<filename>.txt The suggested filename is dynamically generated |
|
| 200 | Content-Type | string | MIME type of the returned data |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
Schemas¶
BacktestNewMethodForOpenApi
{
"index": 0,
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationStartDate": "2019-08-24T14:15:22Z"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| index | integer | true | The index from zero of the backtest. | |
| primaryTrainingEndDate | string(date-time) | true | A datetime string representing the end date of the primary training data for this backtest. | |
| primaryTrainingStartDate | string(date-time) | true | A datetime string representing the start date of the primary training data for this backtest. | |
| validationEndDate | string(date-time) | true | A datetime string representing the end date of the validation data for this backtest. | |
| validationStartDate | string(date-time) | true | A datetime string representing the start date of the validation data for this backtest. |
BacktestOldMethodForOpenApi
{
"gapDuration": "string",
"index": 0,
"validationDuration": "string",
"validationStartDate": "2019-08-24T14:15:22Z"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| gapDuration | string(duration) | true | A duration string representing the duration of the gap between the training and the validation data for this backtest. | |
| index | integer | true | The index from zero of the backtest. | |
| validationDuration | string(duration) | true | A duration string representing the duration of the validation data for this backtest. | |
| validationStartDate | string(date-time) | true | A datetime string representing the start date of the validation data for this backtest. |
BacktestResponse
{
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"index": 0,
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"validationDuration": "string",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationStartDate": "2019-08-24T14:15:22Z"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| availableTrainingDuration | string(duration) | true | The duration of the available training data for this backtest. | |
| availableTrainingEndDate | string(date-time) | true | The end date of the available training data for this backtest. | |
| availableTrainingStartDate | string(date-time) | true | The start date of the available training data for this backtest. | |
| gapDuration | string(duration) | true | The duration of the gap between the training and the validation scoring data for this backtest. | |
| gapEndDate | string(date-time) | true | The end date of the gap between the training and validation scoring data for this backtest. | |
| gapStartDate | string(date-time) | true | The start date of the gap between the training and validation scoring data for this backtest. | |
| index | integer | true | The index from zero of this backtest. | |
| primaryTrainingDuration | string(duration) | true | The duration of the primary training data for this backtest. | |
| primaryTrainingEndDate | string(date-time) | true | The end date of the primary training data for this backtest. | |
| primaryTrainingStartDate | string(date-time) | true | The start date of the primary training data for this backtest. | |
| validationDuration | string | true | The duration of the validation scoring data for this backtest. | |
| validationEndDate | string(date-time) | true | The end date of the validation scoring data for this backtest. | |
| validationStartDate | string(date-time) | true | The start date of the validation scoring data for this backtest. |
DatetimePartitioningDataForOpenApi
{
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": false,
"autopilotClusterList": [
2
],
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"backtests": [
{
"gapDuration": "string",
"index": 0,
"validationDuration": "string",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"datetimePartitionColumn": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": false,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 5,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto",
"unsupervisedMode": false,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": false,
"useSupervisedFeatureReduction": true,
"useTimeSeries": false,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| aggregationType | string | false | For multiseries projects only. The aggregation type to apply when creating cross-series features. | |
| allowPartialHistoryTimeSeriesPredictions | boolean | false | Specifies whether the time series predictions can use partial historical data. | |
| autopilotClusterList | [integer]¦null | false | maxItems: 10 |
A list of integers where each value will be used as the number of clusters in Autopilot model(s) for unsupervised clustering projects. Cannot be specified unless unsupervisedMode is true and unsupervisedType is set to clustering. |
| autopilotDataSamplingMethod | string | false | Defines how autopilot will select subsample from training dataset in OTV/TS projects. Defaults to 'latest' for 'rowCount' dataSelectionMethod and to 'random' for 'duration'. | |
| autopilotDataSelectionMethod | string | false | The Data Selection method to be used by autopilot when creating models for datetime-partitioned datasets. | |
| backtests | [oneOf] | false | maxItems: 20 minItems: 1 |
An array specifying individual backtests. |
oneOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | BacktestOldMethodForOpenApi | false | Method 1 - pass validation and gap durations |
xor
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | BacktestNewMethodForOpenApi | false | Method 2 - directly configure the start and end dates of each partition, including the training partition. |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| calendarId | string | false | The ID of the calendar to be used in this project. | |
| clusteringBufferDisabled | boolean | false | A boolean value indicating whether an clustering buffer creation should be disabled for unsupervised time series clustering project. | |
| crossSeriesGroupByColumns | [string] | false | maxItems: 1 |
For multiseries projects with cross-series features enabled only. List of columns (currently of length 1). Setting that indicates how to further split series into related groups. For example, if every series is sales of an individual product, the series group-by could be the product category with values like "men's clothing", "sports equipment", etc. |
| datetimePartitionColumn | string | true | The date column that will be used as a datetime partition column. | |
| defaultToAPriori | boolean | false | Renamed to defaultToKnownInAdvance. |
|
| defaultToDoNotDerive | boolean | false | For time series projects only. Sets whether all features default to being treated as do-not-derive features, excluding them from feature derivation. Individual features can be set to a value different than the default by using the featureSettings parameter. |
|
| defaultToKnownInAdvance | boolean | false | For time series projects only. Sets whether all features default to being treated as known in advance features, which are features that are known into the future. Features marked as known in advance must be specified into the future when making predictions. The default is false, all features are not known in advance. Individual features can be set to a value different than the default using the featureSettings parameter. See the :ref:Time Series Overview <time_series_overview> for more context. |
|
| differencingMethod | string | false | For time series projects only. Used to specify which differencing method to apply if the data is stationary. For classification problems simple and seasonal are not allowed. Parameter periodicities must be specified if seasonal is chosen. Defaults to auto. |
|
| disableHoldout | boolean | false | Whether to suppress allocating a holdout fold. If disableHoldout is set to true, holdoutStartDate and holdoutDuration must not be set. |
|
| featureDerivationWindowEnd | integer | false | maximum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the past relative to the forecast point the feature derivation window should end. |
| featureDerivationWindowStart | integer | false | maximum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the past relative to the forecast point the feature derivation window should begin. |
| featureSettings | [FeatureSetting] | false | An array specifying per feature settings. Features can be left unspecified. | |
| forecastWindowEnd | integer | false | minimum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should end. |
| forecastWindowStart | integer | false | minimum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should start. |
| gapDuration | string(duration) | false | The duration of the gap between holdout training and holdout scoring data. For time series projects, defaults to the duration of the gap between the end of the feature derivation window and the beginning of the forecast window. For OTV projects, defaults to a zero duration (P0Y0M0D). | |
| holdoutDuration | string(duration) | false | The duration of holdout scoring data. When specifying holdoutDuration, holdoutStartDate must also be specified. This attribute cannot be specified when disableHoldout is true. |
|
| holdoutEndDate | string(date-time) | false | The end date of holdout scoring data. When specifying holdoutEndDate, holdoutStartDate must also be specified. This attribute cannot be specified when disableHoldout is true. |
|
| holdoutStartDate | string(date-time) | false | The start date of holdout scoring data. When specifying holdoutStartDate, one of holdoutEndDate or holdoutDuration must also be specified. This attribute cannot be specified when disableHoldout is true. |
|
| isHoldoutModified | boolean | false | A boolean value indicating whether holdout settings (start/end dates) have been modified by user. | |
| modelSplits | integer | false | maximum: 10 minimum: 1 |
Sets the cap on the number of jobs per model used when building models to control number of jobs in the queue. Higher number of modelSplits will allow for less downsampling leading to the use of more post-processed data. |
| multiseriesIdColumns | [string] | false | minItems: 1 |
May be used only with time series projects. An array of the column names identifying the series to which each row of the dataset belongs. Currently only one multiseries ID column is supported. See the :ref:multiseries <multiseries> section of the time series documentation for more context. |
| numberOfBacktests | integer | false | maximum: 20 minimum: 1 |
The number of backtests to use. If omitted, defaults to a positive value selected by the server based on the validation and gap durations. |
| periodicities | [Periodicity] | false | A list of periodicities for time series projects only. For classification problems periodicities are not allowed. If this is provided, parameter 'differencing_method' will default to 'seasonal' if not provided or 'auto'. | |
| treatAsExponential | string | false | For time series projects only. Used to specify whether to treat data as exponential trend and apply transformations like log-transform. For classification problems always is not allowed. Defaults to auto. |
|
| unsupervisedMode | boolean | false | A boolean value indicating whether an unsupervised project should be created. | |
| unsupervisedType | string¦null | false | The type of unsupervised project. Only valid when unsupervisedMode is true. If unsupervisedMode, defaults to anomaly. |
|
| useCrossSeriesFeatures | boolean | false | For multiseries projects only. Indicating whether to use cross-series features. | |
| useSupervisedFeatureReduction | boolean | false | When true, during feature generation DataRobot runs a supervised algorithm that identifies those features with predictive impact on the target and builds feature lists using only qualifying features. Setting false can severely impact autopilot duration, especially for datasets with many features. | |
| useTimeSeries | boolean | false | A boolean value indicating whether a time series project should be created instead of a regular project which uses datetime partitioning. | |
| validationDuration | string(duration) | false | The default validation duration for all backtests. If the primary date/time feature in a time series project is irregular, you cannot set a default validation length. Instead, set each duration individually. For an OTV project setting the validation duration will always use regular partitioning. Omitting it will use irregular partitioning if the date/time feature is irregular. | |
| windowsBasisUnit | string | false | For time series projects only. Indicates which unit is basis for feature derivation window and forecast window. Valid options are detected time unit or ROW. If omitted, the default value is detected time unit. |
Enumerated Values¶
| Property | Value |
|---|---|
| aggregationType | [total, average] |
| autopilotDataSamplingMethod | [random, latest] |
| autopilotDataSelectionMethod | [duration, rowCount] |
| differencingMethod | [auto, none, simple, seasonal] |
| treatAsExponential | [auto, never, always] |
| unsupervisedType | [anomaly, clustering] |
| windowsBasisUnit | [MILLISECOND, SECOND, MINUTE, HOUR, DAY, WEEK, MONTH, QUARTER, YEAR, ROW] |
DatetimePartitioningLogListControllerResponse
{
"count": 0,
"datetimePartitioningLog": "string",
"next": "http://example.com",
"previous": "http://example.com",
"totalLogLines": 0
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of items returned on this page. | |
| datetimePartitioningLog | string | true | The content of the date/time partitioning log. | |
| next | string(uri)¦null | true | URL pointing to the next page (if null, there is no next page). | |
| previous | string(uri)¦null | true | URL pointing to the previous page (if null, there is no previous page). | |
| totalLogLines | integer | true | The total number of lines in feature derivation log. |
DatetimePartitioningResponse
{
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": true,
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"availableHoldoutEndDate": "2019-08-24T14:15:22Z",
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"backtests": [
{
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"index": 0,
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"validationDuration": "string",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"calendarName": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"dateFormat": "string",
"datetimePartitionColumn": "string",
"datetimePartitioningId": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": true,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 1,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"numberOfDoNotDeriveFeatures": 0,
"numberOfKnownInAdvanceFeatures": 0,
"partitioningExtendedWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
{
"message": "string",
"title": "string",
"type": "string"
}
]
}
],
"partitioningWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
"string"
]
}
],
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"projectId": "string",
"treatAsExponential": "auto",
"unsupervisedMode": true,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": true,
"useTimeSeries": true,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| aggregationType | string¦null | false | For multiseries projects only. The aggregation type to apply when creating cross-series features. | |
| allowPartialHistoryTimeSeriesPredictions | boolean¦null | false | Specifies whether the time series predictions can use partial historical data. | |
| autopilotDataSamplingMethod | string | true | The Data Sampling method to be used by autopilot when creating models for datetime-partitioned datasets. | |
| autopilotDataSelectionMethod | string | true | The Data Selection method to be used by autopilot when creating models for datetime-partitioned datasets. | |
| availableHoldoutEndDate | string(date-time)¦null | true | The maximum valid date of holdout scoring data. | |
| availableTrainingDuration | string(duration) | true | The duration of available training duration for scoring the holdout. | |
| availableTrainingEndDate | string(date-time) | true | The end date of available training data for scoring the holdout. | |
| availableTrainingStartDate | string(date-time) | true | The start date of available training data for scoring the holdout. | |
| backtests | [BacktestResponse] | true | maxItems: 20 minItems: 1 |
An array of the configured backtests. |
| calendarId | string¦null | false | The ID of the calendar to be used in this project. | |
| calendarName | string¦null | false | The name of the calendar used in this project. | |
| clusteringBufferDisabled | boolean | false | A boolean value indicating whether an clustering buffer creation should be disabled for unsupervised time series clustering project. | |
| crossSeriesGroupByColumns | [string]¦null | false | maxItems: 1 |
For multiseries projects with cross-series features enabled only. List of columns (currently of length 1). Setting that indicates how to further split series into related groups. For example, if every series is sales of an individual product, the series group-by could be the product category with values like "men's clothing", "sports equipment", etc. |
| dateFormat | string | true | The date format of the partition column. | |
| datetimePartitionColumn | string | true | The date column that will be used as a datetime partition column. | |
| datetimePartitioningId | string | false | The ID of the current optimized datetime partitioning | |
| defaultToAPriori | boolean | true | Renamed to defaultToKnownInAdvance. |
|
| defaultToDoNotDerive | boolean | true | For time series projects only. Sets whether all features default to being treated as do-not-derive features, excluding them from feature derivation. Individual features can be set to a value different than the default by using the featureSettings parameter. |
|
| defaultToKnownInAdvance | boolean | true | For time series projects only. Sets whether all features default to being treated as known in advance features, which are features that are known into the future. Features marked as known in advance must be specified into the future when making predictions. The default is false, all features are not known in advance. Individual features can be set to a value different than the default using the featureSettings parameter. See the :ref:Time Series Overview <time_series_overview> for more context. |
|
| differencingMethod | string¦null | true | For time series projects only. Used to specify which differencing method to apply if the data is stationary. For classification problems simple and seasonal are not allowed. Parameter periodicities must be specified if seasonal is chosen. Defaults to auto. |
|
| disableHoldout | boolean | true | A boolean value indicating whether date partitioning skipped allocating a holdout fold. | |
| featureDerivationWindowEnd | integer¦null | true | maximum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the past relative to the forecast point the feature derivation window should end. |
| featureDerivationWindowStart | integer¦null | true | maximum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the past relative to the forecast point the feature derivation window should begin. |
| featureSettings | [FeatureSetting] | true | An array specifying per feature settings. Features can be left unspecified. | |
| forecastWindowEnd | integer¦null | true | minimum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should end. |
| forecastWindowStart | integer¦null | true | minimum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should start. |
| gapDuration | string(duration) | true | The duration of the gap between the training and holdout scoring data. | |
| gapEndDate | string(date-time) | true | The end date of the gap between the training and holdout scoring data. | |
| gapStartDate | string(date-time) | true | The start date of the gap between the training and holdout scoring data. | |
| holdoutDuration | string(duration) | true | The duration of the holdout scoring data. | |
| holdoutEndDate | string(date-time) | true | The end date of holdout scoring data. | |
| holdoutStartDate | string(date-time) | true | The start date of holdout scoring data. | |
| isHoldoutModified | boolean | false | A boolean value indicating whether holdout settings (start/end dates) have been modified by user. | |
| modelSplits | integer | false | maximum: 10 minimum: 1 |
Sets the cap on the number of jobs per model used when building models to control number of jobs in the queue. Higher number of modelSplits will allow for less downsampling leading to the use of more post-processed data. |
| multiseriesIdColumns | [string]¦null | true | minItems: 1 |
May be used only with time series projects. An array of the column names identifying the series to which each row of the dataset belongs. Currently only one multiseries ID column is supported. See the :ref:multiseries <multiseries> section of the time series documentation for more context. |
| numberOfBacktests | integer | true | maximum: 20 minimum: 1 |
The number of backtests to use. If omitted, defaults to a positive value selected by the server based on the validation and gap durations. |
| numberOfDoNotDeriveFeatures | integer | true | Number of features that are marked as "do not derive". | |
| numberOfKnownInAdvanceFeatures | integer | true | Number of features that are marked as "known in advance". | |
| partitioningExtendedWarnings | [PartitioningExtendedWarning] | false | An array of available warnings about potential problems with the chosen partitioning that could cause issues during modeling, although the partitioning may be successfully submitted. | |
| partitioningWarnings | [PartitioningWarning] | true | An array of available warnings about potential problems with the chosen partitioning that could cause issues during modeling, although the partitioning may be successfully submitted. | |
| periodicities | [Periodicity]¦null | true | A list of periodicities for time series projects only. For classification problems periodicities are not allowed. If this is provided, parameter 'differencing_method' will default to 'seasonal' if not provided or 'auto'. | |
| primaryTrainingDuration | string(duration) | true | The duration of primary training duration for scoring the holdout. | |
| primaryTrainingEndDate | string(date-time) | true | The end date of primary training data for scoring the holdout. | |
| primaryTrainingStartDate | string(date-time) | true | The start date of primary training data for scoring the holdout. | |
| projectId | string | true | The ID of the project. | |
| treatAsExponential | string¦null | true | For time series projects only. Used to specify whether to treat data as exponential trend and apply transformations like log-transform. For classification problems always is not allowed. Defaults to auto. |
|
| unsupervisedMode | boolean¦null | false | A boolean value indicating whether an unsupervised project should be created. | |
| unsupervisedType | string¦null | false | The type of unsupervised project. | |
| useCrossSeriesFeatures | boolean¦null | false | For multiseries projects only. Indicating whether to use cross-series features. | |
| useTimeSeries | boolean | true | A boolean value indicating whether a time series project should be created instead of a regular project which uses datetime partitioning. | |
| validationDuration | string(duration)¦null | true | The default validation duration for all backtests. If the primary date/time feature in a time series project is irregular, you cannot set a default validation length. Instead, set each duration individually. | |
| windowsBasisUnit | string¦null | true | For time series projects only. Indicates which unit is basis for feature derivation window and forecast window. Valid options are detected time unit or ROW. If omitted, the default value is detected time unit. |
Enumerated Values¶
| Property | Value |
|---|---|
| aggregationType | [total, average] |
| autopilotDataSamplingMethod | [random, latest] |
| autopilotDataSelectionMethod | [duration, rowCount] |
| differencingMethod | [auto, none, simple, seasonal] |
| treatAsExponential | [auto, never, always] |
| unsupervisedType | [anomaly, clustering] |
| windowsBasisUnit | [MILLISECOND, SECOND, MINUTE, HOUR, DAY, WEEK, MONTH, QUARTER, YEAR, ROW] |
FeatureSetting
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| aPriori | boolean | false | Renamed to knownInAdvance. |
|
| doNotDerive | boolean | false | For time series projects only. Sets whether the feature is do-not-derive, i.e., is excluded from feature derivation. If not specified, the feature uses the value from the defaultToDoNotDerive flag. |
|
| featureName | string | true | The name of the feature being specified. | |
| knownInAdvance | boolean | false | For time series projects only. Sets whether the feature is known in advance, i.e., values for future dates are known at prediction time. If not specified, the feature uses the value from the defaultToKnownInAdvance flag. |
FinalBacktestResponse
{
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingRowCount": 0,
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapRowCount": 0,
"gapStartDate": "2019-08-24T14:15:22Z",
"index": 0,
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingRowCount": 0,
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"totalRowCount": 0,
"validationDuration": "string",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationRowCount": 0,
"validationStartDate": "2019-08-24T14:15:22Z"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| availableTrainingDuration | string(duration) | true | The duration of the available training data for this backtest. | |
| availableTrainingEndDate | string(date-time) | true | The end date of the available training data for this backtest. | |
| availableTrainingRowCount | integer | true | The number of rows in the available training data for this backtest. | |
| availableTrainingStartDate | string(date-time) | true | The start date of the available training data for this backtest. | |
| gapDuration | string(duration) | true | The duration of the gap between the training and the validation scoring data for this backtest. | |
| gapEndDate | string(date-time) | true | The end date of the gap between the training and validation scoring data for this backtest. | |
| gapRowCount | integer | true | The number of rows in the gap between the training and the validation scoring data for this backtest. | |
| gapStartDate | string(date-time) | true | The start date of the gap between the training and validation scoring data for this backtest. | |
| index | integer | true | The index from zero of this backtest. | |
| primaryTrainingDuration | string(duration) | true | The duration of the primary training data for this backtest. | |
| primaryTrainingEndDate | string(date-time) | true | The end date of the primary training data for this backtest. | |
| primaryTrainingRowCount | integer | true | The number of rows in the primary training data for this backtest. | |
| primaryTrainingStartDate | string(date-time) | true | The start date of the primary training data for this backtest. | |
| totalRowCount | integer | true | The total number of rows in this backtest | |
| validationDuration | string | true | The duration of the validation scoring data for this backtest. | |
| validationEndDate | string(date-time) | true | The end date of the validation scoring data for this backtest. | |
| validationRowCount | integer | true | The number of rows in the validation scoring data for this backtest. | |
| validationStartDate | string(date-time) | true | The start date of the validation scoring data for this backtest. |
FinalDatetimePartitioningResponse
{
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": true,
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"availableHoldoutEndDate": "2019-08-24T14:15:22Z",
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingRowCount": 0,
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"backtests": [
{
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingRowCount": 0,
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapRowCount": 0,
"gapStartDate": "2019-08-24T14:15:22Z",
"index": 0,
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingRowCount": 0,
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"totalRowCount": 0,
"validationDuration": "string",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationRowCount": 0,
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"calendarName": "string",
"crossSeriesGroupByColumns": [
"string"
],
"dateFormat": "string",
"datetimePartitionColumn": "string",
"datetimePartitioningId": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": true,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapRowCount": 0,
"gapStartDate": "2019-08-24T14:15:22Z",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutRowCount": 0,
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 1,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"numberOfDoNotDeriveFeatures": 0,
"numberOfKnownInAdvanceFeatures": 0,
"partitioningExtendedWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
{
"message": "string",
"title": "string",
"type": "string"
}
]
}
],
"partitioningWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
"string"
]
}
],
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingRowCount": 0,
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"projectId": "string",
"totalRowCount": 0,
"treatAsExponential": "auto",
"unsupervisedMode": true,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": true,
"useTimeSeries": true,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| aggregationType | string¦null | true | For multiseries projects only. The aggregation type to apply when creating cross-series features. | |
| allowPartialHistoryTimeSeriesPredictions | boolean¦null | false | Specifies whether the time series predictions can use partial historical data. | |
| autopilotDataSamplingMethod | string | true | The Data Sampling method to be used by autopilot when creating models for datetime-partitioned datasets. | |
| autopilotDataSelectionMethod | string | true | The Data Selection method to be used by autopilot when creating models for datetime-partitioned datasets. | |
| availableHoldoutEndDate | string(date-time)¦null | true | The maximum valid date of holdout scoring data. | |
| availableTrainingDuration | string(duration) | true | The duration of available training duration for scoring the holdout. | |
| availableTrainingEndDate | string(date-time) | true | The end date of available training data for scoring the holdout. | |
| availableTrainingRowCount | integer | true | The number of rows in the available training data for scoring the holdout | |
| availableTrainingStartDate | string(date-time) | true | The start date of available training data for scoring the holdout. | |
| backtests | [FinalBacktestResponse] | true | maxItems: 20 minItems: 1 |
An array of the configured backtests. |
| calendarId | string¦null | true | The ID of the calendar to be used in this project. | |
| calendarName | string¦null | true | The name of the calendar used in this project. | |
| crossSeriesGroupByColumns | [string]¦null | true | maxItems: 1 |
For multiseries projects with cross-series features enabled only. List of columns (currently of length 1). Setting that indicates how to further split series into related groups. For example, if every series is sales of an individual product, the series group-by could be the product category with values like "men's clothing", "sports equipment", etc. |
| dateFormat | string | true | The date format of the partition column. | |
| datetimePartitionColumn | string | true | The date column that will be used as a datetime partition column. | |
| datetimePartitioningId | string | false | The ID of the current optimized datetime partitioning | |
| defaultToAPriori | boolean | true | Renamed to defaultToKnownInAdvance. |
|
| defaultToDoNotDerive | boolean | true | For time series projects only. Sets whether all features default to being treated as do-not-derive features, excluding them from feature derivation. Individual features can be set to a value different than the default by using the featureSettings parameter. |
|
| defaultToKnownInAdvance | boolean | true | For time series projects only. Sets whether all features default to being treated as known in advance features, which are features that are known into the future. Features marked as known in advance must be specified into the future when making predictions. The default is false, all features are not known in advance. Individual features can be set to a value different than the default using the featureSettings parameter. See the :ref:Time Series Overview <time_series_overview> for more context. |
|
| differencingMethod | string¦null | true | For time series projects only. Used to specify which differencing method to apply if the data is stationary. For classification problems simple and seasonal are not allowed. Parameter periodicities must be specified if seasonal is chosen. Defaults to auto. |
|
| disableHoldout | boolean | true | A boolean value indicating whether date partitioning skipped allocating a holdout fold. | |
| featureDerivationWindowEnd | integer¦null | true | maximum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the past relative to the forecast point the feature derivation window should end. |
| featureDerivationWindowStart | integer¦null | true | maximum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the past relative to the forecast point the feature derivation window should begin. |
| featureSettings | [FeatureSetting] | true | An array specifying per feature settings. Features can be left unspecified. | |
| forecastWindowEnd | integer¦null | true | minimum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should end. |
| forecastWindowStart | integer¦null | true | minimum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should start. |
| gapDuration | string(duration) | true | The duration of the gap between the training and holdout scoring data. | |
| gapEndDate | string(date-time) | true | The end date of the gap between the training and holdout scoring data. | |
| gapRowCount | integer | true | The number of rows in the gap between the training and holdout scoring data | |
| gapStartDate | string(date-time) | true | The start date of the gap between the training and holdout scoring data. | |
| holdoutDuration | string(duration) | true | The duration of the holdout scoring data. | |
| holdoutEndDate | string(date-time) | true | The end date of holdout scoring data. | |
| holdoutRowCount | integer | true | The number of rows in the holdout scoring data | |
| holdoutStartDate | string(date-time) | true | The start date of holdout scoring data. | |
| isHoldoutModified | boolean | false | A boolean value indicating whether holdout settings (start/end dates) have been modified by user. | |
| modelSplits | integer¦null | true | maximum: 10 minimum: 1 |
Sets the cap on the number of jobs per model used when building models to control number of jobs in the queue. Higher number of modelSplits will allow for less downsampling leading to the use of more post-processed data. |
| multiseriesIdColumns | [string]¦null | true | minItems: 1 |
May be used only with time series projects. An array of the column names identifying the series to which each row of the dataset belongs. Currently only one multiseries ID column is supported. See the :ref:multiseries <multiseries> section of the time series documentation for more context. |
| numberOfBacktests | integer | true | maximum: 20 minimum: 1 |
The number of backtests to use. If omitted, defaults to a positive value selected by the server based on the validation and gap durations. |
| numberOfDoNotDeriveFeatures | integer | true | Number of features that are marked as "do not derive". | |
| numberOfKnownInAdvanceFeatures | integer | true | Number of features that are marked as "known in advance". | |
| partitioningExtendedWarnings | [PartitioningExtendedWarning] | false | An array of available warnings about potential problems with the chosen partitioning that could cause issues during modeling, although the partitioning may be successfully submitted. | |
| partitioningWarnings | [PartitioningWarning] | true | An array of available warnings about potential problems with the chosen partitioning that could cause issues during modeling, although the partitioning may be successfully submitted. | |
| periodicities | [Periodicity]¦null | true | A list of periodicities for time series projects only. For classification problems periodicities are not allowed. If this is provided, parameter 'differencing_method' will default to 'seasonal' if not provided or 'auto'. | |
| primaryTrainingDuration | string(duration) | true | The duration of primary training duration for scoring the holdout. | |
| primaryTrainingEndDate | string(date-time) | true | The end date of primary training data for scoring the holdout. | |
| primaryTrainingRowCount | integer | true | The number of rows in the primary training data for scoring the holdout | |
| primaryTrainingStartDate | string(date-time) | true | The start date of primary training data for scoring the holdout. | |
| projectId | string | true | The ID of the project. | |
| totalRowCount | integer | true | The total number of rows in the project dataset | |
| treatAsExponential | string¦null | true | For time series projects only. Used to specify whether to treat data as exponential trend and apply transformations like log-transform. For classification problems always is not allowed. Defaults to auto. |
|
| unsupervisedMode | boolean¦null | false | A boolean value indicating whether an unsupervised project should be created. | |
| unsupervisedType | string¦null | false | The type of unsupervised project. | |
| useCrossSeriesFeatures | boolean¦null | true | For multiseries projects only. Indicating whether to use cross-series features. | |
| useTimeSeries | boolean | true | A boolean value indicating whether a time series project should be created instead of a regular project which uses datetime partitioning. | |
| validationDuration | string(duration)¦null | true | The default validation duration for all backtests. If the primary date/time feature in a time series project is irregular, you cannot set a default validation length. Instead, set each duration individually. | |
| windowsBasisUnit | string¦null | true | For time series projects only. Indicates which unit is basis for feature derivation window and forecast window. Valid options are detected time unit or ROW. If omitted, the default value is detected time unit. |
Enumerated Values¶
| Property | Value |
|---|---|
| aggregationType | [total, average] |
| autopilotDataSamplingMethod | [random, latest] |
| autopilotDataSelectionMethod | [duration, rowCount] |
| differencingMethod | [auto, none, simple, seasonal] |
| treatAsExponential | [auto, never, always] |
| unsupervisedType | [anomaly, clustering] |
| windowsBasisUnit | [MILLISECOND, SECOND, MINUTE, HOUR, DAY, WEEK, MONTH, QUARTER, YEAR, ROW] |
OptimizedDatetimePartitioningData
{
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": false,
"autopilotClusterList": [
2
],
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"backtests": [
{
"gapDuration": "string",
"index": 0,
"validationDuration": "string",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"datetimePartitionColumn": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": false,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 5,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"target": "string",
"treatAsExponential": "auto",
"unsupervisedMode": false,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": false,
"useSupervisedFeatureReduction": true,
"useTimeSeries": false,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| aggregationType | string | false | For multiseries projects only. The aggregation type to apply when creating cross-series features. | |
| allowPartialHistoryTimeSeriesPredictions | boolean | false | Specifies whether the time series predictions can use partial historical data. | |
| autopilotClusterList | [integer]¦null | false | maxItems: 10 |
A list of integers where each value will be used as the number of clusters in Autopilot model(s) for unsupervised clustering projects. Cannot be specified unless unsupervisedMode is true and unsupervisedType is set to clustering. |
| autopilotDataSamplingMethod | string | false | Defines how autopilot will select subsample from training dataset in OTV/TS projects. Defaults to 'latest' for 'rowCount' dataSelectionMethod and to 'random' for 'duration'. | |
| autopilotDataSelectionMethod | string | false | The Data Selection method to be used by autopilot when creating models for datetime-partitioned datasets. | |
| backtests | [oneOf] | false | maxItems: 20 minItems: 1 |
An array specifying individual backtests. |
oneOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | BacktestOldMethodForOpenApi | false | Method 1 - pass validation and gap durations |
xor
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | BacktestNewMethodForOpenApi | false | Method 2 - directly configure the start and end dates of each partition, including the training partition. |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| calendarId | string | false | The ID of the calendar to be used in this project. | |
| clusteringBufferDisabled | boolean | false | A boolean value indicating whether an clustering buffer creation should be disabled for unsupervised time series clustering project. | |
| crossSeriesGroupByColumns | [string] | false | maxItems: 1 |
For multiseries projects with cross-series features enabled only. List of columns (currently of length 1). Setting that indicates how to further split series into related groups. For example, if every series is sales of an individual product, the series group-by could be the product category with values like "men's clothing", "sports equipment", etc. |
| datetimePartitionColumn | string | true | The date column that will be used as a datetime partition column. | |
| defaultToAPriori | boolean | false | Renamed to defaultToKnownInAdvance. |
|
| defaultToDoNotDerive | boolean | false | For time series projects only. Sets whether all features default to being treated as do-not-derive features, excluding them from feature derivation. Individual features can be set to a value different than the default by using the featureSettings parameter. |
|
| defaultToKnownInAdvance | boolean | false | For time series projects only. Sets whether all features default to being treated as known in advance features, which are features that are known into the future. Features marked as known in advance must be specified into the future when making predictions. The default is false, all features are not known in advance. Individual features can be set to a value different than the default using the featureSettings parameter. See the :ref:Time Series Overview <time_series_overview> for more context. |
|
| differencingMethod | string | false | For time series projects only. Used to specify which differencing method to apply if the data is stationary. For classification problems simple and seasonal are not allowed. Parameter periodicities must be specified if seasonal is chosen. Defaults to auto. |
|
| disableHoldout | boolean | false | Whether to suppress allocating a holdout fold. If disableHoldout is set to true, holdoutStartDate and holdoutDuration must not be set. |
|
| featureDerivationWindowEnd | integer | false | maximum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the past relative to the forecast point the feature derivation window should end. |
| featureDerivationWindowStart | integer | false | maximum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the past relative to the forecast point the feature derivation window should begin. |
| featureSettings | [FeatureSetting] | false | An array specifying per feature settings. Features can be left unspecified. | |
| forecastWindowEnd | integer | false | minimum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should end. |
| forecastWindowStart | integer | false | minimum: 0 |
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should start. |
| gapDuration | string(duration) | false | The duration of the gap between holdout training and holdout scoring data. For time series projects, defaults to the duration of the gap between the end of the feature derivation window and the beginning of the forecast window. For OTV projects, defaults to a zero duration (P0Y0M0D). | |
| holdoutDuration | string(duration) | false | The duration of holdout scoring data. When specifying holdoutDuration, holdoutStartDate must also be specified. This attribute cannot be specified when disableHoldout is true. |
|
| holdoutEndDate | string(date-time) | false | The end date of holdout scoring data. When specifying holdoutEndDate, holdoutStartDate must also be specified. This attribute cannot be specified when disableHoldout is true. |
|
| holdoutStartDate | string(date-time) | false | The start date of holdout scoring data. When specifying holdoutStartDate, one of holdoutEndDate or holdoutDuration must also be specified. This attribute cannot be specified when disableHoldout is true. |
|
| isHoldoutModified | boolean | false | A boolean value indicating whether holdout settings (start/end dates) have been modified by user. | |
| modelSplits | integer | false | maximum: 10 minimum: 1 |
Sets the cap on the number of jobs per model used when building models to control number of jobs in the queue. Higher number of modelSplits will allow for less downsampling leading to the use of more post-processed data. |
| multiseriesIdColumns | [string] | false | minItems: 1 |
May be used only with time series projects. An array of the column names identifying the series to which each row of the dataset belongs. Currently only one multiseries ID column is supported. See the :ref:multiseries <multiseries> section of the time series documentation for more context. |
| numberOfBacktests | integer | false | maximum: 20 minimum: 1 |
The number of backtests to use. If omitted, defaults to a positive value selected by the server based on the validation and gap durations. |
| periodicities | [Periodicity] | false | A list of periodicities for time series projects only. For classification problems periodicities are not allowed. If this is provided, parameter 'differencing_method' will default to 'seasonal' if not provided or 'auto'. | |
| target | string | false | Name of the target column. | |
| treatAsExponential | string | false | For time series projects only. Used to specify whether to treat data as exponential trend and apply transformations like log-transform. For classification problems always is not allowed. Defaults to auto. |
|
| unsupervisedMode | boolean | false | A boolean value indicating whether an unsupervised project should be created. | |
| unsupervisedType | string¦null | false | The type of unsupervised project. Only valid when unsupervisedMode is true. If unsupervisedMode, defaults to anomaly. |
|
| useCrossSeriesFeatures | boolean | false | For multiseries projects only. Indicating whether to use cross-series features. | |
| useSupervisedFeatureReduction | boolean | false | When true, during feature generation DataRobot runs a supervised algorithm that identifies those features with predictive impact on the target and builds feature lists using only qualifying features. Setting false can severely impact autopilot duration, especially for datasets with many features. | |
| useTimeSeries | boolean | false | A boolean value indicating whether a time series project should be created instead of a regular project which uses datetime partitioning. | |
| validationDuration | string(duration) | false | The default validation duration for all backtests. If the primary date/time feature in a time series project is irregular, you cannot set a default validation length. Instead, set each duration individually. For an OTV project setting the validation duration will always use regular partitioning. Omitting it will use irregular partitioning if the date/time feature is irregular. | |
| windowsBasisUnit | string | false | For time series projects only. Indicates which unit is basis for feature derivation window and forecast window. Valid options are detected time unit or ROW. If omitted, the default value is detected time unit. |
Enumerated Values¶
| Property | Value |
|---|---|
| aggregationType | [total, average] |
| autopilotDataSamplingMethod | [random, latest] |
| autopilotDataSelectionMethod | [duration, rowCount] |
| differencingMethod | [auto, none, simple, seasonal] |
| treatAsExponential | [auto, never, always] |
| unsupervisedType | [anomaly, clustering] |
| windowsBasisUnit | [MILLISECOND, SECOND, MINUTE, HOUR, DAY, WEEK, MONTH, QUARTER, YEAR, ROW] |
OptimizedDatetimePartitioningList
{
"datetimePartitionColumn": "string",
"id": "string",
"partitionData": {
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": true,
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"availableHoldoutEndDate": "2019-08-24T14:15:22Z",
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"backtests": [
{
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"index": 0,
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"validationDuration": "string",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"calendarName": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"dateFormat": "string",
"datetimePartitionColumn": "string",
"datetimePartitioningId": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": true,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 1,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"numberOfDoNotDeriveFeatures": 0,
"numberOfKnownInAdvanceFeatures": 0,
"partitioningExtendedWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
{
"message": "string",
"title": "string",
"type": "string"
}
]
}
],
"partitioningWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
"string"
]
}
],
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"projectId": "string",
"treatAsExponential": "auto",
"unsupervisedMode": true,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": true,
"useTimeSeries": true,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
},
"target": "string"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| datetimePartitionColumn | string | true | The date column that will be used as a datetime partition column. | |
| id | string | true | The ID of the datetime partitioning. | |
| partitionData | DatetimePartitioningResponse | true | The datetime partitioning configuration. | |
| target | string | true | The name of the target column. |
OptimizedDatetimePartitioningListResponse
{
"count": 0,
"data": [
{
"datetimePartitionColumn": "string",
"id": "string",
"partitionData": {
"aggregationType": "total",
"allowPartialHistoryTimeSeriesPredictions": true,
"autopilotDataSamplingMethod": "random",
"autopilotDataSelectionMethod": "duration",
"availableHoldoutEndDate": "2019-08-24T14:15:22Z",
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"backtests": [
{
"availableTrainingDuration": "string",
"availableTrainingEndDate": "2019-08-24T14:15:22Z",
"availableTrainingStartDate": "2019-08-24T14:15:22Z",
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"index": 0,
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"validationDuration": "string",
"validationEndDate": "2019-08-24T14:15:22Z",
"validationStartDate": "2019-08-24T14:15:22Z"
}
],
"calendarId": "string",
"calendarName": "string",
"clusteringBufferDisabled": false,
"crossSeriesGroupByColumns": [
"string"
],
"dateFormat": "string",
"datetimePartitionColumn": "string",
"datetimePartitioningId": "string",
"defaultToAPriori": true,
"defaultToDoNotDerive": true,
"defaultToKnownInAdvance": true,
"differencingMethod": "auto",
"disableHoldout": true,
"featureDerivationWindowEnd": 0,
"featureDerivationWindowStart": 0,
"featureSettings": [
{
"aPriori": true,
"doNotDerive": true,
"featureName": "string",
"knownInAdvance": true
}
],
"forecastWindowEnd": 0,
"forecastWindowStart": 0,
"gapDuration": "string",
"gapEndDate": "2019-08-24T14:15:22Z",
"gapStartDate": "2019-08-24T14:15:22Z",
"holdoutDuration": "string",
"holdoutEndDate": "2019-08-24T14:15:22Z",
"holdoutStartDate": "2019-08-24T14:15:22Z",
"isHoldoutModified": true,
"modelSplits": 1,
"multiseriesIdColumns": [
"string"
],
"numberOfBacktests": 1,
"numberOfDoNotDeriveFeatures": 0,
"numberOfKnownInAdvanceFeatures": 0,
"partitioningExtendedWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
{
"message": "string",
"title": "string",
"type": "string"
}
]
}
],
"partitioningWarnings": [
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
"string"
]
}
],
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"primaryTrainingDuration": "string",
"primaryTrainingEndDate": "2019-08-24T14:15:22Z",
"primaryTrainingStartDate": "2019-08-24T14:15:22Z",
"projectId": "string",
"treatAsExponential": "auto",
"unsupervisedMode": true,
"unsupervisedType": "anomaly",
"useCrossSeriesFeatures": true,
"useTimeSeries": true,
"validationDuration": "string",
"windowsBasisUnit": "MILLISECOND"
},
"target": "string"
}
],
"next": "http://example.com",
"previous": "http://example.com"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | false | Number of items returned on this page. | |
| data | [OptimizedDatetimePartitioningList] | true | A list of datetime partitionings returned in order of creation. | |
| next | string(uri)¦null | true | URL pointing to the next page (if null, there is no next page). | |
| previous | string(uri)¦null | true | URL pointing to the previous page (if null, there is no previous page). |
PartitioningExtendedWarning
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
{
"message": "string",
"title": "string",
"type": "string"
}
]
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| backtestIndex | integer¦null | true | Backtest index. Null if the warning does not correspond to a single backtest. | |
| partition | string | true | Partition name. | |
| warnings | [PartitioningSingleExtendedWarning] | true | A list of strings representing warnings for the specified partition |
PartitioningSingleExtendedWarning
{
"message": "string",
"title": "string",
"type": "string"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| message | string | true | Warning message. | |
| title | string | true | Warning short title. | |
| type | string | true | Warning severity type. |
PartitioningWarning
{
"backtestIndex": 0,
"partition": "string",
"warnings": [
"string"
]
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| backtestIndex | integer¦null | true | Backtest index. Null if the warning does not correspond to a single backtest. | |
| partition | string | true | Partition name. | |
| warnings | [string] | true | A list of strings representing warnings for the specified partition |
Periodicity
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| timeSteps | integer | true | minimum: 0 |
The number of time steps. |
| timeUnit | string | true | The time unit or ROW if windowsBasisUnit is ROW |
Enumerated Values¶
| Property | Value |
|---|---|
| timeUnit | [MILLISECOND, SECOND, MINUTE, HOUR, DAY, WEEK, MONTH, QUARTER, YEAR, ROW] |
TimeSeriesFeatureLogListControllerResponse
{
"count": 0,
"featureLog": "string",
"next": "http://example.com",
"previous": "http://example.com",
"totalLogLines": 0
}
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of items returned on this page. | |
| featureLog | string | true | The content of the feature log. | |
| next | string(uri)¦null | true | URL pointing to the next page (if null, there is no next page). | |
| previous | string(uri)¦null | true | URL pointing to the previous page (if null, there is no previous page). | |
| totalLogLines | integer | true | The total number of lines in feature derivation log. |
更新しました April 24, 2024
このページは役に立ちましたか？
ありがとうございます。どのような点が役に立ちましたか？
より良いコンテンツを提供するには、どうすればよいでしょうか？
アンケートにご協力いただき、ありがとうございました。