DataRobot API resources > API reference documentation > DataRobot REST API > Modeling > DataRobot models

Datarobot Models¶

This page outlines the operations, endpoints, parameters, and example requests and responses for the Datarobot Models.

GET /api/v2/projects/{projectId}/biasMitigatedModels/¶

List of bias mitigated models for the selected project.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/biasMitigatedModels/ \
  -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	false	At most this many results are returned.
parentModelId	query	string	false	Retrieve a list of mitigated models for the parent model if specified. Otherwise retrieve a list of all mitigated models for the project.
projectId	path	string	true	The project ID

Example responses¶


{
  "count": 0,
  "data": [
    {
      "biasMitigationTechnique": "preprocessingReweighing",
      "includeBiasMitigationFeatureAsPredictorVariable": true,
      "modelId": "string",
      "parentModelId": "string",
      "protectedFeature": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Returns Bias Mitigated models results.	BiasMitigatedModelsListResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/biasMitigatedModels/¶

Add a request to the queue to train a model with bias mitigation applied. If the job has been previously submitted, the request will return the jobId of the previously submitted job. Use this jobId to check status of the previously submitted job.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/biasMitigatedModels/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "biasMitigationFeature": "string",
  "biasMitigationParentLid": "string",
  "biasMitigationTechnique": "preprocessingReweighing",
  "includeBiasMitigationFeatureAsPredictorVariable": true
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	BiasMitigationModelCreate	false	none

Responses¶

Status	Meaning	Description	Schema
202	Accepted	The model training request has been successfully submitted. See Location header.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/biasMitigationFeatureInfo/¶

Get bias mitigation data quality information for a given projectId and featureName.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/biasMitigationFeatureInfo/?featureName=string \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
featureName	query	string	true	Name of feature for mitigation info.
projectId	path	string	true	The project ID

Example responses¶


{
  "messages": [
    {
      "additionalInfo": [
        "string"
      ],
      "messageLevel": "CRITICAL",
      "messageText": "string"
    }
  ]
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Dictionary with one entry ("messages") with list of data quality information about a feature.	MessagesInfo

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/biasMitigationFeatureInfo/{featureName}/¶

Submit a job to create bias mitigation data quality information for a given projectId and featureName.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/biasMitigationFeatureInfo/{featureName}/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
featureName	path	string	true	Name of feature for mitigation info.

Responses¶

Status	Meaning	Description	Schema
202	Accepted	A URI of the newly submitted job in the "Location" header.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/blenderModels/¶

List all blenders in a project.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/blenderModels/?offset=0&limit=0 \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
offset	query	integer	true	This many results will be skipped.
limit	query	integer	true	At most this many results are returned. If 0, all results.
projectId	path	string	true	The project ID

Example responses¶


{
  "count": 0,
  "data": [
    {
      "blenderMethod": "string",
      "blenderModels": [
        0
      ],
      "blueprintId": "string",
      "dataSelectionMethod": "duration",
      "externalPredictionModel": true,
      "featurelistId": "string",
      "featurelistName": "string",
      "frozenPct": 0,
      "hasCodegen": true,
      "hasFinetuners": true,
      "icons": 0,
      "id": "string",
      "isAugmented": true,
      "isBlender": true,
      "isCustom": true,
      "isFrozen": true,
      "isNClustersDynamicallyDetermined": true,
      "isStarred": true,
      "isTrainedIntoHoldout": true,
      "isTrainedIntoValidation": true,
      "isTrainedOnGpu": true,
      "isTransparent": true,
      "isUserModel": true,
      "lifecycle": {
        "reason": "string",
        "stage": "active"
      },
      "linkFunction": "string",
      "metrics": {},
      "modelCategory": "model",
      "modelFamily": "string",
      "modelFamilyFullName": "string",
      "modelIds": [
        "string"
      ],
      "modelNumber": 0,
      "modelType": "string",
      "monotonicDecreasingFeaturelistId": "string",
      "monotonicIncreasingFeaturelistId": "string",
      "nClusters": 0,
      "parentModelId": "string",
      "predictionThreshold": 1,
      "predictionThresholdReadOnly": true,
      "processes": [
        "string"
      ],
      "projectId": "string",
      "samplePct": 0,
      "samplingMethod": "random",
      "supportsComposableMl": true,
      "supportsMonotonicConstraints": true,
      "timeWindowSamplePct": 99,
      "trainingDuration": "string",
      "trainingEndDate": "2019-08-24T14:15:22Z",
      "trainingRowCount": 0,
      "trainingStartDate": "2019-08-24T14:15:22Z"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	A list of all of the blenders in a project.	BlenderListResponse
404	Not Found	This resource does not exist.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/blenderModels/¶

Create a blender from other models using a specified blender method. Note: Time Series projects only allow the following blender methods: "AVG", "MED", "FORECAST_DISTANCE_ENET", and "FORECAST_DISTANCE_AVG".

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/blenderModels/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "blenderMethod": "PLS",
  "modelIds": [
    "string"
  ]
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	BlenderCreate	false	none

Responses¶

Status	Meaning	Description	Schema
202	Accepted	Model job successfully added to queue. See the Location header.	None
404	Not Found	This resource does not exist.	None
422	Unprocessable Entity	Unable to create a blender or request is not supported in this context.	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string	url	A url that can be polled to check the status of the job.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/blenderModels/blendCheck/¶

Check if models can be blended.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/blenderModels/blendCheck/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "blenderMethod": "PLS",
  "modelIds": [
    "string"
  ]
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	BlenderCreate	false	none

Example responses¶


{
  "blendable": true,
  "reason": "string"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Information on whether models can be blended and why.	BlenderInfoRetrieveResponse
404	Not Found	This resource does not exist.	None
422	Unprocessable Entity	Unable to process request.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/blenderModels/{modelId}/¶

Retrieve a blender. Blenders are a special type of models, so the response includes all attributes that would be in a response to GET /api/v2/projects/{projectId}/models/{modelId}/ as well as some additional ones.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/blenderModels/{modelId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "blenderMethod": "string",
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "dataSelectionMethod": "duration",
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "frozenPct": 0,
  "hasCodegen": true,
  "hasFinetuners": true,
  "icons": 0,
  "id": "string",
  "isAugmented": true,
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isNClustersDynamicallyDetermined": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "lifecycle": {
    "reason": "string",
    "stage": "active"
  },
  "linkFunction": "string",
  "metrics": {},
  "modelCategory": "model",
  "modelFamily": "string",
  "modelFamilyFullName": "string",
  "modelIds": [
    "string"
  ],
  "modelNumber": 0,
  "modelType": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 0,
  "parentModelId": "string",
  "predictionThreshold": 1,
  "predictionThresholdReadOnly": true,
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": 0,
  "samplingMethod": "random",
  "supportsComposableMl": true,
  "supportsMonotonicConstraints": true,
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	The blender model.	BlenderRetrieveResponse
404	Not Found	Specified blender not found.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/combinedModels/¶

Retrieve all existing combined models for this project. .. note::


To retrieve information on the segments for a combined model, retrieve the combined model using [GET /api/v2/projects/{projectId}/combinedModels/{combinedModelId}/][get-apiv2projectsprojectidcombinedmodelscombinedmodelid]

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/combinedModels/ \
  -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¶


{
  "count": 0,
  "data": [
    {
      "combinedModelId": "string",
      "isActiveCombinedModel": false,
      "modelCategory": "combined",
      "projectId": "string",
      "segmentationTaskId": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Responses¶

Status	Meaning	Description	Schema
200	OK	none	CombinedModelListResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/combinedModels/{combinedModelId}/¶

Retrieve an existing combined model. If available, contains information on which champion model is used for each segment.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/combinedModels/{combinedModelId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The ID of the project.
combinedModelId	path	string	true	The ID of combined model.

Example responses¶


{
  "combinedModelId": "string",
  "isActiveCombinedModel": false,
  "modelCategory": "combined",
  "projectId": "string",
  "segmentationTaskId": "string",
  "segments": [
    {
      "modelId": "string",
      "projectId": "string",
      "segment": "string"
    }
  ]
}

Responses¶

Status	Meaning	Description	Schema
200	OK	none	CombinedModelResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/combinedModels/{combinedModelId}/segments/¶

Retrieve Combined Model segments info (name, related project & model details).

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/combinedModels/{combinedModelId}/segments/ \
  -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.
searchSegmentName	query	string	false	Case insensitive search against segment name.
projectId	path	string	true	The ID of the project.
combinedModelId	path	string	true	The ID of combined model.

Example responses¶


{
  "count": 0,
  "data": [
    {
      "autopilotDone": true,
      "holdoutUnlocked": true,
      "isFrozen": true,
      "modelAssignedBy": "string",
      "modelAwardTime": "2019-08-24T14:15:22Z",
      "modelCount": 0,
      "modelIcon": [
        0
      ],
      "modelId": "string",
      "modelMetrics": {},
      "modelType": "string",
      "projectId": "string",
      "projectPaused": true,
      "projectStage": "modeling",
      "projectStageDescription": "string",
      "projectStatusError": "string",
      "rowCount": 0,
      "rowPercentage": 0,
      "segment": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Responses¶

Status	Meaning	Description	Schema
200	OK	none	CombinedModelSegmentsPaginatedResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/combinedModels/{combinedModelId}/segments/download/¶

Download Combined Model segments info (name, related project & model details) as a CSV.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/combinedModels/{combinedModelId}/segments/download/ \
  -H "Accept: text/csv" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The ID of the project.
combinedModelId	path	string	true	The ID of combined model.

Example responses¶

Responses¶

Status	Meaning	Description	Schema
200	OK	none	string

Response Headers¶

Status	Header	Type	Format	Description
200	Content-Disposition	string		Contains an auto generated filename for this download.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/datetimeModels/¶

List all the models from a datetime partitioned project.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/datetimeModels/ \
  -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.
bulkOperationId	query	string	false	the ID of the bulk model operation. If specified, only models submitted in scope of this operation will be shown.
projectId	path	string	true	The project ID

Example responses¶


{
  "count": 0,
  "data": [
    {
      "backtests": [
        {
          "index": 0,
          "score": 0,
          "status": "COMPLETED",
          "trainingDuration": "string",
          "trainingEndDate": "2019-08-24T14:15:22Z",
          "trainingRowCount": 0,
          "trainingStartDate": "2019-08-24T14:15:22Z"
        }
      ],
      "blenderModels": [
        0
      ],
      "blueprintId": "string",
      "dataSelectionMethod": "duration",
      "effectiveFeatureDerivationWindowEnd": 0,
      "effectiveFeatureDerivationWindowStart": 0,
      "externalPredictionModel": true,
      "featurelistId": "string",
      "featurelistName": "string",
      "forecastWindowEnd": 0,
      "forecastWindowStart": 0,
      "frozenPct": 0,
      "hasCodegen": true,
      "hasFinetuners": true,
      "holdoutScore": 0,
      "holdoutStatus": "COMPLETED",
      "icons": 0,
      "id": "string",
      "isAugmented": true,
      "isBlender": true,
      "isCustom": true,
      "isFrozen": true,
      "isNClustersDynamicallyDetermined": true,
      "isStarred": true,
      "isTrainedIntoHoldout": true,
      "isTrainedIntoValidation": true,
      "isTrainedOnGpu": true,
      "isTransparent": true,
      "isUserModel": true,
      "lifecycle": {
        "reason": "string",
        "stage": "active"
      },
      "linkFunction": "string",
      "metrics": "\n        {\n            \"metrics\": {\n                \"FVE Poisson\": {\n                    \"holdout\": null,\n                    \"validation\": 0.56269,\n                    \"backtesting\": 0.50166,\n                    \"backtestingScores\": [0.51206, 0.49436, null, 0.62516],\n                    \"crossValidation\": null\n                },\n                \"RMSE\": {\n                    \"holdout\": null,\n                    \"validation\": 21.0836,\n                    \"backtesting\": 23.361932,\n                    \"backtestingScores\": [0.4403, 0.4213, null, 0.5132],\n                    \"crossValidation\": null\n                }\n            }\n        }\n",
      "modelCategory": "model",
      "modelFamily": "string",
      "modelFamilyFullName": "string",
      "modelNumber": 0,
      "modelType": "string",
      "monotonicDecreasingFeaturelistId": "string",
      "monotonicIncreasingFeaturelistId": "string",
      "nClusters": 0,
      "parentModelId": "string",
      "predictionThreshold": 1,
      "predictionThresholdReadOnly": true,
      "processes": [
        "string"
      ],
      "projectId": "string",
      "samplePct": null,
      "samplingMethod": "random",
      "supportsComposableMl": true,
      "supportsMonotonicConstraints": true,
      "timeWindowSamplePct": 99,
      "trainingDuration": "string",
      "trainingEndDate": "2019-08-24T14:15:22Z",
      "trainingInfo": {
        "holdoutTrainingDuration": "string",
        "holdoutTrainingEndDate": "2019-08-24T14:15:22Z",
        "holdoutTrainingRowCount": 0,
        "holdoutTrainingStartDate": "2019-08-24T14:15:22Z",
        "predictionTrainingDuration": "string",
        "predictionTrainingEndDate": "2019-08-24T14:15:22Z",
        "predictionTrainingRowCount": 0,
        "predictionTrainingStartDate": "2019-08-24T14:15:22Z"
      },
      "trainingRowCount": 0,
      "trainingStartDate": "2019-08-24T14:15:22Z",
      "windowsBasisUnit": "MILLISECOND"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	The datetime partitioned project's models	DatetimeModelsResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/datetimeModels/¶

Train a new datetime model.

All durations and datetimes should be specified in accordance with the :ref:timestamp and duration formatting rules<time_format>.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/datetimeModels/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "blueprintId": "string",
  "featurelistId": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 2,
  "samplingMethod": "random",
  "sourceProjectId": "string",
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingRowCount": 0,
  "useProjectSettings": true
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	TrainDatetimeModel	false	none

Example responses¶


{
  "message": "string"
}

Responses¶

Status	Meaning	Description	Schema
202	Accepted	The model has been successfully submitted.	DatetimeModelSubmissionResponse
422	Unprocessable Entity	There was an error submitting the specified job. See the `message` field for more details.	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string		A url that can be polled to check the status.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/datetimeModels/fromModel/¶

Retrain an existing datetime model using a new training period for the model training set (with optional time window sampling) or different feature list.

All durations and datetimes should be specified in accordance with the :ref:timestamp and duration formatting rules<time_format>.

Note that only one of trainingDuration or trainingRowCount or trainingStartDate and trainingEndDate should be specified. If trainingStartDate and trainingEndDate are specified, the source model must be frozen.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/datetimeModels/fromModel/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "featurelistId": "string",
  "modelId": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 2,
  "samplingMethod": "random",
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z",
  "useProjectSettings": true
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	RetrainDatetimeModel	false	none

Example responses¶


{
  "message": "string"
}

Responses¶

Status	Meaning	Description	Schema
202	Accepted	Retrain an existing datetime model using a new sample size and/or feature list.	DatetimeModelSubmissionResponse
403	Forbidden	User does not have permissions to manage models.	None
404	Not Found	Model with specified `modelId` doesn't exist, or user does not have access to the project.	None
422	Unprocessable Entity	Model with specified `modelId` is deprecated, or it doesn't support retraining with specified parameters.	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string		A url that can be polled to check the status.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/¶

Look up a particular datetime model All durations and datetimes are specified in accordance with :ref:timestamp and duration formatting rules <time_format>.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/datetimeModels/{modelId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "backtests": [
    {
      "index": 0,
      "score": 0,
      "status": "COMPLETED",
      "trainingDuration": "string",
      "trainingEndDate": "2019-08-24T14:15:22Z",
      "trainingRowCount": 0,
      "trainingStartDate": "2019-08-24T14:15:22Z"
    }
  ],
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "dataSelectionMethod": "duration",
  "effectiveFeatureDerivationWindowEnd": 0,
  "effectiveFeatureDerivationWindowStart": 0,
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "forecastWindowEnd": 0,
  "forecastWindowStart": 0,
  "frozenPct": 0,
  "hasCodegen": true,
  "hasFinetuners": true,
  "holdoutScore": 0,
  "holdoutStatus": "COMPLETED",
  "icons": 0,
  "id": "string",
  "isAugmented": true,
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isNClustersDynamicallyDetermined": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "lifecycle": {
    "reason": "string",
    "stage": "active"
  },
  "linkFunction": "string",
  "metrics": "\n        {\n            \"metrics\": {\n                \"FVE Poisson\": {\n                    \"holdout\": null,\n                    \"validation\": 0.56269,\n                    \"backtesting\": 0.50166,\n                    \"backtestingScores\": [0.51206, 0.49436, null, 0.62516],\n                    \"crossValidation\": null\n                },\n                \"RMSE\": {\n                    \"holdout\": null,\n                    \"validation\": 21.0836,\n                    \"backtesting\": 23.361932,\n                    \"backtestingScores\": [0.4403, 0.4213, null, 0.5132],\n                    \"crossValidation\": null\n                }\n            }\n        }\n",
  "modelCategory": "model",
  "modelFamily": "string",
  "modelFamilyFullName": "string",
  "modelNumber": 0,
  "modelType": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 0,
  "parentModelId": "string",
  "predictionThreshold": 1,
  "predictionThresholdReadOnly": true,
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": null,
  "samplingMethod": "random",
  "supportsComposableMl": true,
  "supportsMonotonicConstraints": true,
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingInfo": {
    "holdoutTrainingDuration": "string",
    "holdoutTrainingEndDate": "2019-08-24T14:15:22Z",
    "holdoutTrainingRowCount": 0,
    "holdoutTrainingStartDate": "2019-08-24T14:15:22Z",
    "predictionTrainingDuration": "string",
    "predictionTrainingEndDate": "2019-08-24T14:15:22Z",
    "predictionTrainingRowCount": 0,
    "predictionTrainingStartDate": "2019-08-24T14:15:22Z"
  },
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z",
  "windowsBasisUnit": "MILLISECOND"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Datetime model	DatetimeModelDetailsResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/datetimeModels/{modelId}/backtests/¶

Score all the available backtests of a datetime model.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/datetimeModels/{modelId}/backtests/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Responses¶

Status	Meaning	Description	Schema
202	Accepted	Scoring of all the available backtests of a datetime model has been successfully requested.	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string		A url that can be polled to check the status.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/deploymentReadyModels/¶

Prepare a specific model for deployment. This model will go through the recommendation stages.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/deploymentReadyModels/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "modelId": "string"
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	PrepareForDeployment	false	none

Responses¶

Status	Meaning	Description	Schema
201	Created	Start preparing the model for deployment.	None
422	Unprocessable Entity	An error occurred when submitting the model job	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/eureqaDistributionPlot/{solutionId}/¶

Retrieve Eureqa model details plot.

Available for classification projects only

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/eureqaDistributionPlot/{solutionId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
solutionId	path	string	true	The ID of the solution to return data for.

Example responses¶


{
  "bins": [
    {
      "binEnd": 0,
      "binStart": 0,
      "negatives": 0,
      "positives": 0
    }
  ],
  "complexity": 0,
  "error": 0,
  "errorMetric": "string",
  "eureqaSolutionId": "string",
  "expression": "string",
  "expressionAnnotated": "string",
  "threshold": 0
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Eureqa model details plot.	EureqaDistributionDetailResponse
404	Not Found	Data was not found.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/eureqaModelDetail/{solutionId}/¶

Retrieve Eureqa model details plot.

Available for regression projects only

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/eureqaModelDetail/{solutionId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
solutionId	path	string	true	The ID of the solution to return data for.

Example responses¶


{
  "complexity": 0,
  "error": 0,
  "errorMetric": "string",
  "eureqaSolutionId": "string",
  "expression": "string",
  "expressionAnnotated": "string",
  "plotData": [
    {
      "actual": 0,
      "predicted": 0,
      "row": 0
    }
  ]
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Eureqa model details plot.	EureqaModelDetailResponse
404	Not Found	Data was not found.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/eureqaModels/¶

Create a new model from an existing eureqa solution.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/eureqaModels/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "parentModelId": "string",
  "solutionId": "string"
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	EureqaLeaderboardEntryPayload	false	none

Responses¶

Status	Meaning	Description	Schema
200	OK	Request accepted, creation is underway.	None
404	Not Found	Data not found.	None
422	Unprocessable Entity	Model for this solution already exists.	None

Response Headers¶

Status	Header	Type	Format	Description
200	Location	string		The location at which the new model can be retrieved.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/eureqaModels/{modelId}/¶

Retrieve the pareto front for the specified Eureqa model.

Only the best solution in the pareto front will have a corresponding model initially. Models can be created for other solutions using POST /api/v2/projects/{projectId}/eureqaModels/.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/eureqaModels/{modelId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "errorMetric": "string",
  "hyperparameters": {
    "buildingBlocks": {},
    "errorMetric": "string",
    "maxGenerations": 32,
    "numThreads": 0,
    "priorSolutions": [
      "string"
    ],
    "randomSeed": 0,
    "splitMode": "custom",
    "syncMigrations": true,
    "targetExpressionFormat": "None",
    "targetExpressionString": "string",
    "timeoutSec": 0,
    "trainingFraction": 1,
    "trainingSplitExpr": "string",
    "validationFraction": 1,
    "validationSplitExpr": "string",
    "weightExpr": "string"
  },
  "projectId": "string",
  "solutions": [
    {
      "bestModel": true,
      "complexity": 0,
      "error": 0,
      "eureqaSolutionId": "string",
      "expression": "string",
      "expressionAnnotated": "string"
    }
  ],
  "targetType": "Regression"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Pareto front for the Eureqa model.	ParetoFrontResponse
404	Not Found	Data was not found.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/frozenDatetimeModels/¶

Train a frozen datetime model. If no training data is specified, the frozen datetime model will be trained on the most recent data using an amount of data that is equivalent to the original model. However, if the equivalent duration does not provide enough rows for training, then the duration will be extended until the minimum is met. Note that this will require the holdout of the project to be unlocked.

All durations and datetimes should be specified in accordance with the :ref:timestamp and duration formatting rules<time_format>.

Note that only one of trainingDuration, trainingRowCount, trainingStartDate and trainingEndDate, or useProjectSettings may be specified.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/frozenDatetimeModels/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "modelId": "string",
  "samplingMethod": "random",
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z",
  "useProjectSettings": true
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	TrainDatetimeFrozenModel	false	none

Example responses¶


{
  "message": "string"
}

Responses¶

Status	Meaning	Description	Schema
202	Accepted	The model has been successfully submitted.	DatetimeModelSubmissionResponse
403	Forbidden	User does not have permissions to manage models.	None
404	Not Found	Model with specified `modelId` does not exist, or user does not have access to the project.	None
422	Unprocessable Entity	Model with specified `modelId` is deprecated, or it does not support retraining with specified parameters.	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string		A url that can be polled to check the status.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/frozenModels/¶

List all frozen models from a project.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/frozenModels/?offset=0&limit=0 \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
offset	query	integer	true	This many results will be skipped.
limit	query	integer	true	At most this many results are returned. If 0, all results.
withMetric	query	string	false	If specified, the returned models will only have scores for this metric. If not, all metrics will be included.
projectId	path	string	true	The project ID

Example responses¶


{
  "count": 0,
  "data": [
    {
      "blenderModels": [
        0
      ],
      "blueprintId": "string",
      "dataSelectionMethod": "duration",
      "externalPredictionModel": true,
      "featurelistId": "string",
      "featurelistName": "string",
      "frozenPct": 0,
      "hasCodegen": true,
      "hasFinetuners": true,
      "icons": 0,
      "id": "string",
      "isAugmented": true,
      "isBlender": true,
      "isCustom": true,
      "isFrozen": true,
      "isNClustersDynamicallyDetermined": true,
      "isStarred": true,
      "isTrainedIntoHoldout": true,
      "isTrainedIntoValidation": true,
      "isTrainedOnGpu": true,
      "isTransparent": true,
      "isUserModel": true,
      "lifecycle": {
        "reason": "string",
        "stage": "active"
      },
      "linkFunction": "string",
      "metrics": {},
      "modelCategory": "model",
      "modelFamily": "string",
      "modelFamilyFullName": "string",
      "modelNumber": 0,
      "modelType": "string",
      "monotonicDecreasingFeaturelistId": "string",
      "monotonicIncreasingFeaturelistId": "string",
      "nClusters": 0,
      "parentModelId": "string",
      "predictionThreshold": 1,
      "predictionThresholdReadOnly": true,
      "processes": [
        "string"
      ],
      "projectId": "string",
      "samplePct": 0,
      "samplingMethod": "random",
      "supportsComposableMl": true,
      "supportsMonotonicConstraints": true,
      "timeWindowSamplePct": 99,
      "trainingDuration": "string",
      "trainingEndDate": "2019-08-24T14:15:22Z",
      "trainingRowCount": 0,
      "trainingStartDate": "2019-08-24T14:15:22Z"
    }
  ],
  "next": "string",
  "previous": "string",
  "totalCount": 0
}

Responses¶

Status	Meaning	Description	Schema
200	OK	A list of frozen models in the project.	FrozenModelListResponse
404	Not Found	This resource does not exist.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/frozenModels/¶

Train a new frozen model with parameters from an existing model. Frozen models use tuning parameters from another model on the leaderboard, allowing them to be retrained on a larger amount of the training data more efficiently. To specify the amount of data to use to train the model, use either samplePct to express a percentage of the rows of the dataset to use or trainingRowCount to express the number of rows to use. If neither samplePct or trainingRowCount is specified, the model will be trained on the maximum available training data that can be used to train an in-memory model. For projects using smart sampling, samplePct and trainingRowCount will be interpreted as a percent or number of rows of the minority class. When configuring retraining sample sizes for models in projects with large row counts, DataRobot recommends requesting sample sizes using integer row counts instead of percentages. This is because percentages map to many actual possible row counts and only one of which is the actual sample size for up to validation. For example, if a project has 199,408 rows and you request a 64% sample size, any number of rows between 126,625 rows and 128,618 rows maps to 64% of the data. Using actual integer row counts (or project.max_training_rows) avoids ambiguity around how many rows of data you want the model to use.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/frozenModels/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "modelId": "string",
  "nClusters": 2,
  "samplePct": 0,
  "trainingRowCount": 0
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	FrozenModelCreate	false	none

Responses¶

Status	Meaning	Description	Schema
204	No Content	The frozen model has been successfully submitted.	None
404	Not Found	This resource does not exist.	None
422	Unprocessable Entity	Unable to process request.	None

Response Headers¶

Status	Header	Type	Format	Description
204	Location	string	url	Contains a url at which the job processing the model can be retrieved as with GET /api/v2/projects/{projectId}/modelJobs/{jobId}/..

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/frozenModels/{modelId}/¶

Look up a particular frozen model. If model with given ID exists but it's not frozen, returns 404 Not Found.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/frozenModels/{modelId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "dataSelectionMethod": "duration",
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "frozenPct": 0,
  "hasCodegen": true,
  "hasFinetuners": true,
  "icons": 0,
  "id": "string",
  "isAugmented": true,
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isNClustersDynamicallyDetermined": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "lifecycle": {
    "reason": "string",
    "stage": "active"
  },
  "linkFunction": "string",
  "metrics": {},
  "modelCategory": "model",
  "modelFamily": "string",
  "modelFamilyFullName": "string",
  "modelNumber": 0,
  "modelType": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 0,
  "parentModelId": "string",
  "predictionThreshold": 1,
  "predictionThresholdReadOnly": true,
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": 0,
  "samplingMethod": "random",
  "supportsComposableMl": true,
  "supportsMonotonicConstraints": true,
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	The frozen model.	ModelDetailsResponse
404	Not Found	No such frozen model found.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/incrementalLearningModels/fromModel/¶

Train a new incremental learning model based on an existing model and external data, that was not seen during partitioning.

Notice: Endpoint is currently in [PUBLIC_PREVIEW]. Do not use it in production workflows to reduce risk. See details:

This endpoint depends on the following features that are subject to change.

Feature Flag	Maturity	Enabled by default	Description
INCREMENTAL_LEARNING	PUBLIC_PREVIEW	true	Enables Incremental Learning. This allows model retraining to continue with an infinite amount of data.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/incrementalLearningModels/fromModel/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "dataStageCompression": "zip",
  "dataStageDelimiter": "string",
  "dataStageEncoding": "UTF-8",
  "dataStageId": "string",
  "dataStageStorageType": "csv",
  "modelId": "string",
  "trainingDataName": "string"
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	TrainIncrementalLearningModel	false	none

Example responses¶


{
  "message": "string"
}

Responses¶

Status	Meaning	Description	Schema
202	Accepted	Incremental learning model submission response	ModelRetrainResponse

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string		A url that can be polled to check the status.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/modelJobs/¶

List modeling jobs.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/modelJobs/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
status	query	string	false	If provided, only jobs with the same status will be included in the results; otherwise, queued and inprogress jobs (but not errored jobs) will be returned.
projectId	path	string	true	The project ID.

Enumerated Values¶

Parameter	Value
status	[`queue`, `inprogress`, `error`]

Example responses¶


[
  {
    "data": [
      {
        "blueprintId": "string",
        "featurelistId": "string",
        "id": "string",
        "isBlocked": true,
        "isTrainedOnGpu": true,
        "modelCategory": "model",
        "modelId": "string",
        "modelType": "string",
        "processes": [
          "string"
        ],
        "projectId": "string",
        "samplePct": 0,
        "status": "queue"
      }
    ]
  }
]

Responses¶

Status	Meaning	Description	Schema
200	OK	List of modeling jobs.	Inline

Response Schema¶

Status Code 200

Name	Type	Required	Description
anonymous	[ModelingJobListResponse]	false	none
» data	[ModelJobResponse]	true	List of modeling jobs.
»» blueprintId	string	true	The blueprint used by the model - note that this is not an ObjectId.
»» featurelistId	string	true	The ID of the featurelist the model is using.
»» id	string	true	The job ID.
»» isBlocked	boolean	true	True if a job is waiting for its dependencies to be resolved first.
»» isTrainedOnGpu	boolean	false	True if the job was trained using GPU capabilities
»» modelCategory	string	true	Indicates what kind of model this is. Will be `combined` for combined models.
»» modelId	string	true	The ID of the model
»» modelType	string	true	The type of model used by the job.
»» processes	[string]	true	List of processes the modeling job includes
»» projectId	string	true	The project the job belongs to.
»» samplePct	number	false	The percentage of the dataset the job is using.
»» status	string	true	The status of the job.

Enumerated Values¶

Property	Value
modelCategory	[`model`, `prime`, `blend`]
status	[`queue`, `inprogress`, `error`, `ABORTED`, `COMPLETED`]

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

DELETE /api/v2/projects/{projectId}/modelJobs/{jobId}/¶

Cancel a modeling job

Code samples¶


curl -X DELETE https://app.datarobot.com/api/v2/projects/{projectId}/modelJobs/{jobId}/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID.
jobId	path	string	true	The job ID

Responses¶

Status	Meaning	Description	Schema
204	No Content	The job has been successfully cancelled.	None
404	Not Found	no job with jobId found, or the job has already completed	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/modelJobs/{jobId}/¶

Look up a particular modeling job

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/modelJobs/{jobId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID.
jobId	path	string	true	The job ID

Example responses¶


{
  "blueprintId": "string",
  "featurelistId": "string",
  "id": "string",
  "isBlocked": true,
  "isTrainedOnGpu": true,
  "modelCategory": "model",
  "modelId": "string",
  "modelType": "string",
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": 0,
  "status": "queue"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	A modeling job	ModelJobResponse
303	See Other	Task is completed, see Location header for the location of a new resource	None

Response Headers¶

Status	Header	Type	Format	Description
200	Location	string	url	if a status code 303 was returned, will contain a url at which the completed model can be retrieved`

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/modelRecords/¶

Retrieve model records, supports filtering and search

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/modelRecords/?offset=0&limit=100 \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
withMetric	query	string	false	If specified, the returned models will only have scores for this metric. If not, all metrics will be included.
showInSampleScores	query	boolean	false	If specified, will return metric scores for models trained into validation/holdout for projects that do not have stacked predictions.
characteristics	query	array[string]	false	A characteristics to filter models with. Only those models which have all specified characteristics are returned.
searchTerm	query	string	false	Filter models by the string expression in the description, case insensitive.
labels	query	array[string]	false	Filter models by labels. Only those models which have all specified labels are returned.
blueprints	query	string	false	Filter models by blueprint ids.
families	query	array[string]	false	Filter models by families.
featurelists	query	string	false	Filter models by featurelist names.
trainingFilters	query	string	false	Filter models by training length or type. Could be training duration in string representation, 'Start/end date', 'Project settings' constants or number of rows. Training duration for datetime partitioned projects may have up to three parts: --.Example of the training duration: `P6Y0M0D-78-Random`, returns models trained on6 years, with sampling rate 78%, randomly taken from the training window. Example of the row count with sampling method: `150-Random`
numberOfClusters	query	string	false	Filter models by number of clusters. Applicable only in unsupervised clustering projects.
sortByMetric	query	string	false	Metric to order models by. If omitted, the project metric is used.
sortByPartition	query	string	false	Partition to use when ordering models by metric. If omitted, the validation partition is used.
offset	query	integer	true	Number of results that are skipped.
limit	query	integer	true	Maximum number of models to return.
projectId	path	string	true	The project ID.

Enumerated Values¶

Parameter	Value
characteristics	[`frozen`, `new series optimized`, `trained on gpu`, `with exportable coefficients`, `with mono constraints`, `with rating table`, `with scoring code`]
labels	[`prepared for deployment`, `starred`]
families	[`Adaptive Boosting`, `Anomaly Detection`, `Blender`, `Calibrator`, `Clustering`, `Custom`, `Decision Tree`, `Document`, `Naive`, `ElasticNet Generalized Linear Model`, `Eureqa`, `Eureqa Time-Series`, `External Prediction Model`, `Factorization Machine`, `Generalized Additive Model`, `Generalized Linear Model`, `Gradient Boosting Machine`, `Image`, `K Nearest Neighbors`, `Naive Bayes`, `Neural Network`, `Other`, `Random Forest`, `Rule Induction`, `Summarized Categorical`, `Support Vector Machine`, `Text Mining`, `Time-Series Neural Network`, `Traditional Time-Series`, `Two Stage`, `Vowpal Wabbit`]
sortByPartition	[`backtesting`, `crossValidation`, `validation`, `holdout`]

Example responses¶


{
  "count": 0,
  "data": [
    {
      "blenderModels": [
        0
      ],
      "blueprintId": "string",
      "externalPredictionModel": true,
      "featurelistId": "string",
      "featurelistName": "string",
      "frozenPct": 0,
      "hasCodegen": true,
      "icons": 0,
      "id": "string",
      "isBlender": true,
      "isCustom": true,
      "isFrozen": true,
      "isStarred": true,
      "isTrainedIntoHoldout": true,
      "isTrainedIntoValidation": true,
      "isTrainedOnGpu": true,
      "isTransparent": true,
      "isUserModel": true,
      "metrics": {},
      "modelCategory": "model",
      "modelFamily": "string",
      "modelNumber": 0,
      "modelType": "string",
      "parentModelId": "string",
      "processes": [
        "string"
      ],
      "projectId": "string",
      "samplePct": 0,
      "trainingRowCount": 0
    }
  ],
  "next": "string",
  "previous": "string",
  "totalCount": 0
}

Responses¶

Status	Meaning	Description	Schema
200	OK	none	ModelRecordsResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/¶

Lists all the models from a project.

.. minversion:: v2.34 .. deprecated:: v2.34


    Use [GET /api/v2/projects/{projectId}/modelRecords/][get-apiv2projectsprojectidmodelrecords] instead.
    Fewer attributes are returned in the response of model records route.

    Removed attributes:

    monotonic_increasing_featurelist_id -- Retrievable from the blueprint level
    monotonic_decreasing_featurelist_id -- Retrievable from the blueprint level.
    supports_composable_ml -- Retrievable from the blueprint level.
    supports_monotonic_constraints -- Retrievable from the blueprint level.
    has_empty_clusters -- Retrievable from the individual model level.
    is_n_clusters_dynamically_determined -- Retrievable from the individual model level.
    prediction_threshold -- Retrievable from the individual model level.
    prediction_threshold_read_only - Retrievable from the individual model level.

    Changed attributes:
    n_clusters becomes number_of_clusters and is returned for unsupervised clustering models.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
withMetric	query	string	false	If specified, the returned models will only have scores for this metric. If not, all metrics will be included.
showInSampleScores	query	boolean	false	If specified, will return metric scores for models trained into validation/holdout for projects that do not have stacked predictions.
name	query	string	false	If specified, filters for models with a model type matching `name`.
samplePct	query	number	false	If specified, filters for models with a matching sample percentage.
isStarred	query	string	false	If specified, filters for models marked as starred.
orderBy	query	string	false	A comma-separated list of metrics to sort by. If metric is prefixed with a '-', models are sorted by this metric in descending order, otherwise are sorted in ascending order. Valid sorting metrics are `metric` and `samplePct`. Use of `metric` sorts models by metric value selected for this project using the validation score. Use of the prefix accounts for the direction of the metric, so `-metric` will sort in order of decreasing 'goodness', which may be opposite to the natural numerical order. If not specified, `-metric` will be used.
projectId	path	string	true	The project ID.

Enumerated Values¶

Parameter	Value
isStarred	[`false`, `False`, `true`, `True`]
orderBy	[`metric`, `-metric`, `samplePct`, `-samplePct`]

Example responses¶


[
  {
    "blenderModels": [
      0
    ],
    "blueprintId": "string",
    "dataSelectionMethod": "duration",
    "externalPredictionModel": true,
    "featurelistId": "string",
    "featurelistName": "string",
    "frozenPct": 0,
    "hasCodegen": true,
    "hasFinetuners": true,
    "icons": 0,
    "id": "string",
    "isAugmented": true,
    "isBlender": true,
    "isCustom": true,
    "isFrozen": true,
    "isNClustersDynamicallyDetermined": true,
    "isStarred": true,
    "isTrainedIntoHoldout": true,
    "isTrainedIntoValidation": true,
    "isTrainedOnGpu": true,
    "isTransparent": true,
    "isUserModel": true,
    "lifecycle": {
      "reason": "string",
      "stage": "active"
    },
    "linkFunction": "string",
    "metrics": {},
    "modelCategory": "model",
    "modelFamily": "string",
    "modelFamilyFullName": "string",
    "modelNumber": 0,
    "modelType": "string",
    "monotonicDecreasingFeaturelistId": "string",
    "monotonicIncreasingFeaturelistId": "string",
    "nClusters": 0,
    "parentModelId": "string",
    "predictionThreshold": 1,
    "predictionThresholdReadOnly": true,
    "processes": [
      "string"
    ],
    "projectId": "string",
    "samplePct": 0,
    "samplingMethod": "random",
    "supportsComposableMl": true,
    "supportsMonotonicConstraints": true,
    "timeWindowSamplePct": 99,
    "trainingDuration": "string",
    "trainingEndDate": "2019-08-24T14:15:22Z",
    "trainingRowCount": 0,
    "trainingStartDate": "2019-08-24T14:15:22Z"
  }
]

Responses¶

Status	Meaning	Description	Schema
200	OK	The project's models	Inline

Response Schema¶

Status Code 200

Name	Type	Required	Restrictions	Description
anonymous	[ModelDetailsResponse]	false		none
» blenderModels	[integer]	true	maxItems: 100	Models that are in the blender.
» blueprintId	string	true		The blueprint used to construct the model.
» dataSelectionMethod	string	false		Identifies which setting defines the training size of the model when making predictions and scoring. Only used by datetime models.
» externalPredictionModel	boolean	true		If the model is an external prediction model.
» featurelistId	string,null	true		The ID of the feature list used by the model.
» featurelistName	string,null	true		The name of the feature list used by the model. If null, themodel was trained on multiple feature lists.
» frozenPct	number,null	true		The training percent used to train the frozen model.
» hasCodegen	boolean	true		If the model has a codegen JAR file.
» hasFinetuners	boolean	false		Whether a model has fine tuners.
» icons	integer,null	true		The icons associated with the model.
» id	string	true		The ID of the model.
» isAugmented	boolean	false		Whether a model was trained using augmentation.
» isBlender	boolean	true		If the model is a blender.
» isCustom	boolean	true		If the model contains custom tasks.
» isFrozen	boolean	true		Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model.
» isNClustersDynamicallyDetermined	boolean	false		Whether number of clusters is dynamically determined. Only valid in unsupervised clustering projects.
» isStarred	boolean	true		Indicates whether the model has been starred.
» isTrainedIntoHoldout	boolean	true		Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size.
» isTrainedIntoValidation	boolean	true		Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size.
» isTrainedOnGpu	boolean	true		Whether the model was trained using GPU workers.
» isTransparent	boolean	true		If the model is a transparent model with exposed coefficients.
» isUserModel	boolean	true		If the model was created with Composable ML.
» lifecycle	ModelLifecycle	true		Object returning model lifecycle.
»» reason	string,null	true		Reason for lifecycle stage. None if model is active.
»» stage	string	true		Model lifecycle stage.
» linkFunction	string,null	true		The link function the final modeler uses in the blueprint. If no link function exists, returns null.
» metrics	object	true		The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed.
» modelCategory	string	true		Indicates the type of model. Returns `prime` for DataRobot Prime models, `blend` for blender models, `combined` for combined models, and `model` for all other models.
» modelFamily	string	true		the family model belongs to, e.g. SVM, GBM, etc.
» modelFamilyFullName	string	true		The full name of the family that the model belongs to. For e.g., Support Vector Machine, Gradient Boosting Machine, etc.
» modelNumber	integer,null	true		The model number from the Leaderboard.
» modelType	string	true		Identifies the model (e.g.,`Nystroem Kernel SVM Regressor`).
» monotonicDecreasingFeaturelistId	string,null	true		the ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced.
» monotonicIncreasingFeaturelistId	string,null	true		the ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced.
» nClusters	integer,null	false		The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.
» parentModelId	string,null	true		The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise.
» predictionThreshold	number	true	maximum: 1 minimum: 0	threshold used for binary classification in predictions.
» predictionThresholdReadOnly	boolean	true		indicates whether modification of a predictions threshold is forbidden. Since v2.22 threshold modification is allowed.
» processes	[string]	true	maxItems: 100	The list of processes used by the model.
» projectId	string	true		The ID of the project to which the model belongs.
» samplePct	number,null	true		The percentage of the dataset used in training the model.
» samplingMethod	string	false		indicates sampling method used to select training data in datetime models. For row-based project this is the way how requested number of rows are selected.For other projects (duration-based, start/end, project settings) - how specified percent of rows (timeWindowSamplePct) is selected from specified time window.
» supportsComposableMl	boolean	true		indicates whether this model is supported in Composable ML.
» supportsMonotonicConstraints	boolean	true		whether this model supports enforcing monotonic constraints
» timeWindowSamplePct	integer,null	false		An integer between 1 and 99, indicating the percentage of sampling within the time window. The points kept are determined by samplingMethod option. Will be null if no sampling was specified. Only used by datetime models.
» trainingDuration	string,null	true		the duration spanned by the dates in the partition column for the data used to train the model
» trainingEndDate	string,null(date-time)	true		the end date of the dates in the partition column for the data used to train the model
» trainingRowCount	integer,null	true		The number of rows used to train the model.
» trainingStartDate	string,null(date-time)	true		the start date of the dates in the partition column for the data used to train the model

Enumerated Values¶

Property	Value
dataSelectionMethod	[`duration`, `rowCount`, `selectedDateRange`, `useProjectSettings`]
stage	[`active`, `deprecated`, `disabled`]
modelCategory	[`model`, `prime`, `blend`, `combined`, `incrementalLearning`]
samplingMethod	[`random`, `latest`]

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/models/¶

Train a new model. To specify the amount of data to use to train the model, use either samplePct to express a percentage of the rows of the dataset to use or trainingRowCount to express the number of rows to use. If neither samplePct or trainingRowCount is specified, the model will be trained on the maximum available training data that can be used to train an in-memory model. For projects using smart sampling, samplePct and trainingRowCount will be interpreted as a percent or number of rows of the minority class. When configuring retraining sample sizes for models in projects with large row counts, DataRobot recommends requesting sample sizes using integer row counts instead of percentages. This is because percentages map to many actual possible row counts and only one of which is the actual sample size for up to validation. For example, if a project has 199,408 rows and you request a 64% sample size, any number of rows between 126,625 rows and 128,618 rows maps to 64% of the data. Using actual integer row counts (or project.max_training_rows) avoids ambiguity around how many rows of data you want the model to use.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/models/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "blueprintId": "string",
  "featurelistId": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 2,
  "samplePct": 100,
  "scoringType": "validation",
  "sourceProjectId": "string",
  "trainingRowCount": 0
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID.
body	body	TrainModel	false	none

Responses¶

Status	Meaning	Description	Schema
202	Accepted	Creation has successfully started. See the Location header.	None
422	Unprocessable Entity	Could not create new job	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string		A url that can be polled to check the status.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/models/fromModel/¶

Retrain an existing model using a new sample size and/or feature list.When configuring retraining sample sizes for models in projects with large row counts, DataRobot recommends requesting sample sizes using integer row counts instead of percentages. This is because percentages map to many actual possible row counts and only one of which is the actual sample size for up to validation. For example, if a project has 199,408 rows and you request a 64% sample size, any number of rows between 126,625 rows and 128,618 rows maps to 64% of the data. Using actual integer row counts (or project.max_training_rows) avoids ambiguity around how many rows of data you want the model to use. Note that only one of samplePct or trainingRowCount should be specified.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/models/fromModel/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "featurelistId": "string",
  "modelId": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 2,
  "samplePct": 100,
  "scoringType": "validation",
  "trainingRowCount": 0
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	RetrainModel	false	none

Example responses¶


{
  "message": "string"
}

Responses¶

Status	Meaning	Description	Schema
202	Accepted	Retrain an existing model using a new sample size and/or feature list.	ModelRetrainResponse
422	Unprocessable Entity	model with specified `modelId` is deprecated, or it doesn't support retraining using a new sample size and/or feature list	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string		A url that can be polled to check the status.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

DELETE /api/v2/projects/{projectId}/models/{modelId}/¶

Delete a model from the leaderboard

Code samples¶


curl -X DELETE https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Responses¶

Status	Meaning	Description	Schema
204	No Content	The model has been successfully deleted.	None
404	Not Found	This resource does not exist.	None
422	Unprocessable Entity	Unable to process the request.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/¶

Look up a particular model.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "dataSelectionMethod": "duration",
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "frozenPct": 0,
  "hasCodegen": true,
  "hasFinetuners": true,
  "icons": 0,
  "id": "string",
  "isAugmented": true,
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isNClustersDynamicallyDetermined": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "lifecycle": {
    "reason": "string",
    "stage": "active"
  },
  "linkFunction": "string",
  "metrics": {},
  "modelCategory": "model",
  "modelFamily": "string",
  "modelFamilyFullName": "string",
  "modelNumber": 0,
  "modelType": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 0,
  "parentModelId": "string",
  "predictionThreshold": 1,
  "predictionThresholdReadOnly": true,
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": 0,
  "samplingMethod": "random",
  "supportsComposableMl": true,
  "supportsMonotonicConstraints": true,
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	The model	ModelDetailsResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

PATCH /api/v2/projects/{projectId}/models/{modelId}/¶

Updates a model's attribute(s)

Code samples¶


curl -X PATCH https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "isStarred": true,
  "predictionThreshold": 1
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID
body	body	ModelUpdate	false	none

Responses¶

Status	Meaning	Description	Schema
204	No Content	The model has been successfully updated with new attributes.	None
404	Not Found	This resource does not exist.	None
422	Unprocessable Entity	Unable to process the request.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/models/{modelId}/advancedTuning/¶

Submit a job to make a new version of the model with different advanced tuning parameters. Note: This route currently supports all models other than: OSS, blenders, prime, scaleout, baseline and user-created. Currently, only single-stage models (most simple models) are supported. Blueprints that run multiple steps, for example one step to predict zero vs nonzero and a second step to determine the value of nonzero predictions, are not supported. (:ref:Advanced Tuning documentation <grid_search>). Parameters may be omitted from this endpoint. If a parameter is omitted, its currentValue will be used. To see the possible parameter IDs and constraints on possible values, see GET /api/v2/projects/{projectId}/models/{modelId}/advancedTuning/parameters/.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/advancedTuning/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "tuningDescription": "string",
  "tuningParameters": [
    {
      "parameterId": "string",
      "value": "string"
    }
  ]
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID
body	body	ModelAdvancedTuning	false	none

Responses¶

Status	Meaning	Description	Schema
202	Accepted	The job has been successfully submitted. See the Location header.	None
403	Forbidden	Permission denied creating advanced tuned model	None
404	Not Found	This resource does not exist.	None
413	Payload Too Large	Tuning request is too large	None
422	Unprocessable Entity	Could not create new job.	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string	url	A url at which the job processing the model can be retrieved.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/advancedTuning/parameters/¶

Retrieve information about all advanced tuning parameters available for the specified model. Note: This route currently supports all models other than: OSS, blenders, prime, scaleout, baseline and user-created

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/advancedTuning/parameters/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "tuningDescription": "string",
  "tuningParameters": [
    {
      "constraints": {
        "ascii": {
          "supportsGridSearch": true
        },
        "float": {
          "max": 0,
          "min": 0,
          "supportsGridSearch": true
        },
        "floatList": {
          "maxLength": 0,
          "maxVal": 0,
          "minLength": 0,
          "minVal": 0,
          "supportsGridSearch": true
        },
        "int": {
          "max": 0,
          "min": 0,
          "supportsGridSearch": true
        },
        "intList": {
          "maxLength": 0,
          "maxVal": 0,
          "minLength": 0,
          "minVal": 0,
          "supportsGridSearch": true
        },
        "select": {
          "supportsGridSearch": true,
          "values": [
            "string"
          ]
        },
        "selectgrid": {
          "supportsGridSearch": true,
          "values": [
            "string"
          ]
        },
        "unicode": {
          "supportsGridSearch": true
        }
      },
      "currentValue": "string",
      "defaultValue": "string",
      "parameterId": "string",
      "parameterName": "string",
      "taskName": "string",
      "vertexId": "string"
    }
  ]
}

Responses¶

Status	Meaning	Description	Schema
200	OK	The information about all advanced tuning parameters available for the specified model.	AdvancedTuningArgumentsRetrieveResponse
403	Forbidden	Permission denied creating advanced tuned model.	None
404	Not Found	This resource does not exist.	None
422	Unprocessable Entity	This model does not support advanced tuning.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/clusterNames/¶

Retrieve all cluster names assigned to an unsupervised cluster model

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/clusterNames/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "clusters": [
    {
      "name": "string",
      "percent": 100
    },
    {
      "name": "string",
      "percent": 100
    }
  ],
  "modelId": "string",
  "projectId": "string"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Retrieve all cluster names for the model	ClusterNamesResponse
404	Not Found	Could not find unsupervised clustering model. Possible reasons include: 1. Provided model id points to a model that does not exist in specified project. 2. Provided model has incompatible type. Method requires model to be unsupervised clustering model.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

PATCH /api/v2/projects/{projectId}/models/{modelId}/clusterNames/¶

Update and then retrieve all cluster names assigned to an unsupervised cluster model

Code samples¶


curl -X PATCH https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/clusterNames/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "clusterNameMappings": [
    {
      "currentName": "string",
      "newName": "string"
    }
  ]
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID
body	body	ClusterNamesUpdateParam	false	none

Example responses¶


{
  "clusters": [
    {
      "name": "string",
      "percent": 100
    },
    {
      "name": "string",
      "percent": 100
    }
  ],
  "modelId": "string",
  "projectId": "string"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Update cluster names and then retrieve all cluster names for the model	ClusterNamesResponse
404	Not Found	Could not find unsupervised clustering model. Possible reasons include: 1. Provided model id points to a model which does not exists in specified project. 2. Provided model has incompatible type. Method requires model to be unsupervised clustering model.	None
422	Unprocessable Entity	The request cannot be processed. Possible reasons include: 1. Mapping contains invalid current cluster name and referenced cluster was not found. 2. Mapping is invalid as after update, clusters will not be uniquely identifiable by name.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/models/{modelId}/crossValidation/¶

Run Cross Validation on a model.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/crossValidation/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶

{}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID
body	body	Empty	false	none

Responses¶

Status	Meaning	Description	Schema
202	Accepted	The model has been successfully submitted.	None
422	Unprocessable Entity	Unable to process the request.	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string	url	Contains a url at which the job processing the model can be retrieved

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/crossValidationScores/¶


    Get Cross Validation scores for each partition in a model.
    .. note:: Individual partition scores are only available for newer models; older models that
              have cross validation score calculated will need to be retrained.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/crossValidationScores/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
metric	query	string	false	Set to the name of a metric to only return results for that metric.
partition	query	number	false	Set to a value such as 1.0, 2.0 to only return results for the specified partition.
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "cvScores": "\n        {\n            \"cvScores\": {\n                \"FVE Gamma\": {\n                    \"0.0\": 0.24334,\n                    \"1.0\": 0.17757,\n                    \"2.0\": 0.21803,\n                    \"3.0\": 0.20185,\n                    \"4.0\": 0.20576\n                },\n                \"FVE Poisson\": {\n                    \"0.0\": 0.24527,\n                    \"1.0\": 0.22092,\n                    \"2.0\": 0.22451,\n                    \"3.0\": 0.24417,\n                    \"4.0\": 0.21654\n                }\n            }\n        }\n"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	The Cross Validation scores for each partition in a model.	CrossValidationRetrieveResponse
404	Not Found	Not found.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/features/¶

List the features used in a model

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/features/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "aPrioriFeatureNames": [
    "string"
  ],
  "featureNames": [
    "string"
  ],
  "knownInAdvanceFeatureNames": [
    "string"
  ]
}

Responses¶

Status	Meaning	Description	Schema
200	OK	The features used in a model.	ModelFeatureListResponse
404	Not Found	This resource does not exist.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/missingReport/¶

Retrieve a summary of how the model's subtasks handle missing values Only models built after the missing value report feature was added will have reports, and only models with at least one imputation or encoding task, e.g. ordinal encoding, missing value imputation. Blenders and scaleout models do not support Missing Value reports.


    The report will describe how each feature's missing values were treated, and report how many
    missing values were present in the training data. Features which were not processed by a
    given blueprint task will not mention it: for instance, a categorical feature with many
    unique values may not be considered eligible for processing by a One-Hot Encoding

    Report is collected for those features which are considered eligible by given
    blueprint task. For instance, categorical feature with a lot of unique values may not be
    considered as eligible in One-Hot Encoding Task.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/missingReport/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "missingValuesReport": [
    {
      "feature": "string",
      "missingCount": 0,
      "missingPercentage": 1,
      "tasks": {
        "property1": {
          "descriptions": [
            "string"
          ],
          "name": "string"
        },
        "property2": {
          "descriptions": [
            "string"
          ],
          "name": "string"
        }
      },
      "type": "string"
    }
  ]
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Retrieve a summary of how the model's subtasks handle missing values.	MissingReportRetrieve
404	Not Found	Could not found missing value report for provided project & model id.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/numIterationsTrained/¶

Retrieve the actual number of iterations or estimators trained by a tree-based early stopping model.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/numIterationsTrained/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "data": [
    {
      "numIterations": 0,
      "stage": "string"
    }
  ],
  "modelId": "string",
  "projectId": "string"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	The number of estimators/iterations trained	NumIterationsTrainedResponse
404	Not Found	Cannot retrieve early stopping information for this model.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/parameters/¶

Retrieve model parameters. These are the parameters that appear in the webapp on the Coefficients tab. Note that they are only available for some models.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/parameters/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "derivedFeatures": [
    {
      "coefficient": 0,
      "derivedFeature": "string",
      "originalFeature": "string",
      "stageCoefficients": [
        {
          "coefficient": 0,
          "stage": "string"
        }
      ],
      "transformations": [
        {
          "name": "string",
          "value": "string"
        }
      ],
      "type": "string"
    }
  ],
  "parameters": [
    {
      "name": "string",
      "value": "string"
    }
  ]
}

Responses¶

Status	Meaning	Description	Schema
200	OK	The parameters of the model.	ModelParametersRetrieveResponse
422	Unprocessable Entity	Unable to process the request.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/predictionIntervals/¶

Retrieve prediction intervals (in descending order) that are already calculated for this model. Note that the project this model belongs to must be a time series project.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/predictionIntervals/ \
  -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	false	At most this many results are returned.
projectId	path	string	true	The project to retrieve prediction intervals for. Must be a time series project.
modelId	path	string	true	The model to retrieve prediction intervals for.

Example responses¶


{
  "count": 0,
  "data": [
    100
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Request was successful.	PredictionIntervalsListResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/models/{modelId}/predictionIntervals/¶

Submit a job to calculate prediction intervals for the specified percentiles for this model. Note that the project this model belongs to must be a time series project.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/predictionIntervals/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "percentiles": [
    100
  ]
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project to calculate prediction intervals for. Must be a time series project.
modelId	path	string	true	The model to calculate prediction intervals for.
body	body	PredictionIntervalsCreate	false	none

Example responses¶


{
  "message": "string"
}

Responses¶

Status	Meaning	Description	Schema
202	Accepted	Job was successfully submitted. See Location header.	PredictionIntervalsCreateResponse

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string		A url that can be polled to check the status.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/primeInfo/¶

Check if a model can be approximated by DataRobot Prime. Deprecated in v2.35.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/primeInfo/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	the project the model belongs to
modelId	path	string	true	the model to check

Example responses¶


{
  "canMakePrime": true,
  "message": "string",
  "messageId": 0
}

Responses¶

Status	Meaning	Description	Schema
200	OK	none	PrimeInfoRetrieveResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/primeRulesets/¶

List all the rulesets approximating a model

When rulesets are created for the parent model, all of the rulesets are created at once, but not all rulesets have corresponding Prime models (until they are directly requested).

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/primeRulesets/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	the project the model belongs to
modelId	path	string	true	the model to find approximating rulesets for

Example responses¶


[
  {
    "modelId": "string",
    "parentModelId": "string",
    "projectId": "string",
    "ruleCount": 0,
    "rulesetId": 0,
    "score": 0
  }
]

Responses¶

Status	Meaning	Description	Schema
200	OK	none	Inline

Response Schema¶

Status Code 200

Name	Type	Required	Description
anonymous	[PrimeRulesetsListResponse]	false	none
» modelId	string	true	the ID of the Prime model using this ruleset (if it exists) or null
» parentModelId	string	true	ID of the model this ruleset approximates
» projectId	string	true	the project this ruleset belongs to
» ruleCount	integer	true	the number of rules used by this ruleset
» rulesetId	integer	true	the ID of the ruleset
» score	number	true	the validation score of the ruleset

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/models/{modelId}/primeRulesets/¶

Approximate an existing model on the leaderboard with DataRobot Prime. A request body should be an empty JSON {}. Deprecated in v2.35.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/primeRulesets/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶

{}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	the project the model to approximate belongs to
modelId	path	string	true	the model to approximate
body	body	PrimeRulesetsCreatePayload	false	none

Responses¶

Status	Meaning	Description	Schema
202	Accepted	The request was understood and accepted, and is now being worked on. See the Location header	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string	url	a url that can be polled to check the status of the job

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/scoringCode/¶

Retrieve Scoring Code for making new predictions from an existing model offline. You need the "Scoring Code" feature enabled to use this route.

By default, returns a compiled executable JAR that can be executed locally to calculate model predictions, or it can be used as a library for a Java application. Execute it with the '--help` parameters to learn how to use it as a command-line utility. See model API documentation (https://javadoc.io/doc/com.datarobot/datarobot-prediction/latest/index.html) to be able to use it inside an existing Java application.

With the sourceCode query parameter set to 'true', returns a source code archive that can be used to review internal calculations of the model. This JAR is NOT executable.

See "https://docs.datarobot.com/en/docs/predictions/port-pred/scoring-code/index.html" in DataRobot application for more information.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/scoringCode/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
sourceCode	query	string	false	If set to "true", the downloaded JAR file will contain only the source code and will not be executable.
projectId	path	string	true	the project that created the model
modelId	path	string	true	the model to use

Enumerated Values¶

Parameter	Value
sourceCode	[`false`, `False`, `true`, `True`]

Responses¶

Status	Meaning	Description	Schema
200	OK	JAR file	None

Response Headers¶

Status	Header	Type	Format	Description
200	Content-Disposition	string		attachment; filename="<"filename">".jar The suggested filename for the scoring code is dynamically generated
200	Content-Type	string		application/java-archive

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/models/{modelId}/supportedCapabilities/¶

Get supported capabilities for a model.

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/models/{modelId}/supportedCapabilities/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
modelId	path	string	true	The model ID

Example responses¶


{
  "eligibleForPrime": true,
  "hasParameters": true,
  "hasWordCloud": true,
  "reasons": {
    "supportsAccuracyOverTime": "string",
    "supportsAnomalyAssessment": "string",
    "supportsAnomalyOverTime": "string",
    "supportsClusterInsights": "string",
    "supportsConfusionMatrix": "string",
    "supportsDocumentTextExtractionSampleInsight": "string",
    "supportsForecastAccuracy": "string",
    "supportsForecastVsActual": "string",
    "supportsImageActivationMaps": "string",
    "supportsImageEmbedding": "string",
    "supportsLiftChart": "string",
    "supportsPeriodAccuracy": "string",
    "supportsPredictionExplanations": "string",
    "supportsPredictionIntervals": "string",
    "supportsResiduals": "string",
    "supportsRocCurve": "string",
    "supportsSeriesInsights": "string",
    "supportsStability": "string"
  },
  "supportsAccuracyOverTime": true,
  "supportsAdvancedTuning": true,
  "supportsAnomalyAssessment": true,
  "supportsAnomalyOverTime": true,
  "supportsBlending": true,
  "supportsClusterInsights": true,
  "supportsCodeGeneration": true,
  "supportsCoefficients": true,
  "supportsConfusionMatrix": true,
  "supportsDocumentTextExtractionSampleInsight": true,
  "supportsEarlyStopping": true,
  "supportsForecastAccuracy": true,
  "supportsForecastVsActual": true,
  "supportsImageActivationMaps": true,
  "supportsImageEmbedding": true,
  "supportsLiftChart": true,
  "supportsModelPackageExport": true,
  "supportsModelTrainingMetrics": true,
  "supportsMonotonicConstraints": true,
  "supportsNNVisualizations": true,
  "supportsPerLabelMetrics": true,
  "supportsPeriodAccuracy": true,
  "supportsPredictionExplanations": true,
  "supportsPredictionIntervals": true,
  "supportsResiduals": true,
  "supportsRocCurve": true,
  "supportsSeriesInsights": true,
  "supportsShap": true,
  "supportsStability": true
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Successfully returned model capability information.	ModelCapabilitiesRetrieveResponse
404	Not Found	Resource not found.	None

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/primeFiles/¶

List all DataRobot Prime files available for download

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/primeFiles/ \
  -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	false	at most this many results are returned. To specify no limit, use 0. The default may change and a maximum limit may be imposed without notice.
parentModelId	query	string	false	if specified only Prime files approximating the specified parent model will be returned; otherwise all applicable Prime files will be returned.
modelId	query	string	false	if specified only Prime files with code used in the specified prime model will be returned; otherwise all applicable Prime files will be returned
projectId	path	string	true	the project to list available files for

Example responses¶


{
  "count": 0,
  "data": [
    {
      "id": "string",
      "isValid": true,
      "language": "Python",
      "modelId": "string",
      "parentModelId": "string",
      "projectId": "string",
      "rulesetId": 0
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	none	PrimeFileListResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/primeFiles/¶

Request creation and validation of source code from a Prime model. Deprecated in v2.35.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/primeFiles/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "language": "Python",
  "modelId": "string"
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	the project the Prime model belongs to
body	body	PrimeFileCreate	false	none

Responses¶

Status	Meaning	Description	Schema
202	Accepted	prime validation job added to queue. See the Location header.	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string	url	a url that can be polled to check the status of prime validation job

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/primeFiles/{primeFileId}/¶

Retrieve metadata about a DataRobot Prime file available for download

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/primeFiles/{primeFileId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	the project the file belongs to
primeFileId	path	string	true	the file to retrieve

Example responses¶


{
  "id": "string",
  "isValid": true,
  "language": "Python",
  "modelId": "string",
  "parentModelId": "string",
  "projectId": "string",
  "rulesetId": 0
}

Responses¶

Status	Meaning	Description	Schema
200	OK	none	PrimeFileResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/primeFiles/{primeFileId}/download/¶

Download code from an existing Prime file

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/primeFiles/{primeFileId}/download/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	the project the file belongs to
primeFileId	path	string	true	the Prime file to download code from

Responses¶

Status	Meaning	Description	Schema
200	OK	The response will contain a file with the executable code from the Prime file	None

Response Headers¶

Status	Header	Type	Format	Description
200	Content-Disposition	string		Will be attachment;filename="<"filename">". The suggested filename will depend on the language Prime file was generated for.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/primeModels/¶

List all Prime models in a project

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/primeModels/ \
  -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 to list models from

Example responses¶


{
  "count": 0,
  "data": [
    {
      "blenderModels": [
        0
      ],
      "blueprintId": "string",
      "dataSelectionMethod": "duration",
      "externalPredictionModel": true,
      "featurelistId": "string",
      "featurelistName": "string",
      "frozenPct": 0,
      "hasCodegen": true,
      "hasFinetuners": true,
      "icons": 0,
      "id": "string",
      "isAugmented": true,
      "isBlender": true,
      "isCustom": true,
      "isFrozen": true,
      "isNClustersDynamicallyDetermined": true,
      "isStarred": true,
      "isTrainedIntoHoldout": true,
      "isTrainedIntoValidation": true,
      "isTrainedOnGpu": true,
      "isTransparent": true,
      "isUserModel": true,
      "lifecycle": {
        "reason": "string",
        "stage": "active"
      },
      "linkFunction": "string",
      "metrics": {},
      "modelCategory": "model",
      "modelFamily": "string",
      "modelFamilyFullName": "string",
      "modelNumber": 0,
      "modelType": "string",
      "monotonicDecreasingFeaturelistId": "string",
      "monotonicIncreasingFeaturelistId": "string",
      "nClusters": 0,
      "parentModelId": "string",
      "predictionThreshold": 1,
      "predictionThresholdReadOnly": true,
      "processes": [
        "string"
      ],
      "projectId": "string",
      "ruleCount": 0,
      "rulesetId": 0,
      "samplePct": 0,
      "samplingMethod": "random",
      "score": 0,
      "supportsComposableMl": true,
      "supportsMonotonicConstraints": true,
      "timeWindowSamplePct": 99,
      "trainingDuration": "string",
      "trainingEndDate": "2019-08-24T14:15:22Z",
      "trainingRowCount": 0,
      "trainingStartDate": "2019-08-24T14:15:22Z"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	none	PrimeModelListResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/primeModels/¶

Create a Prime model using a particular ruleset.

DataRobot Prime is not available for multiclass projects.

Once rulesets approximating a parent model have been created, using POST /api/v2/projects/(projectId)/models/(modelId)/primeRulesets/, this route will allow creation of a Prime model using one of those rulesets.

Available rulesets can be retrieved via GET /api/v2/projects/(projectId)/models/(modelId)/primeRulesets/. Deprecated in v2.35.

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/primeModels/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "parentModelId": "string",
  "rulesetId": 0
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	the project in which to create the model
body	body	PrimeModelCreatePayload	false	none

Responses¶

Status	Meaning	Description	Schema
202	Accepted	Prime model creation job successfully added to queue. See the Location header.	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string	url	a url that can be polled to check the status of the job

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/primeModels/{modelId}/¶

Retrieve a Prime model details

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/primeModels/{modelId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	the project to retrieve the model from
modelId	path	string	true	the model to retrieve

Example responses¶


{
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "dataSelectionMethod": "duration",
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "frozenPct": 0,
  "hasCodegen": true,
  "hasFinetuners": true,
  "icons": 0,
  "id": "string",
  "isAugmented": true,
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isNClustersDynamicallyDetermined": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "lifecycle": {
    "reason": "string",
    "stage": "active"
  },
  "linkFunction": "string",
  "metrics": {},
  "modelCategory": "model",
  "modelFamily": "string",
  "modelFamilyFullName": "string",
  "modelNumber": 0,
  "modelType": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 0,
  "parentModelId": "string",
  "predictionThreshold": 1,
  "predictionThresholdReadOnly": true,
  "processes": [
    "string"
  ],
  "projectId": "string",
  "ruleCount": 0,
  "rulesetId": 0,
  "samplePct": 0,
  "samplingMethod": "random",
  "score": 0,
  "supportsComposableMl": true,
  "supportsMonotonicConstraints": true,
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Prime models are an extension of models, so the response includes all attributes that would be in a response to GET /api/v2/projects/(projectId)/models/(modelId)/ as well as some additional ones.	PrimeModelDetailsRetrieveResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/recommendedModels/¶

Retrieves all of the current recommended models for the project

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/recommendedModels/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID

Example responses¶


[
  {
    "modelId": "string",
    "recommendationType": "MOSTACCURATE"
  }
]

Responses¶

Status	Meaning	Description	Schema
200	OK	The list of recommended models	Inline

Response Schema¶

Status Code 200

Name	Type	Required	Description
anonymous	[RecommendedModelResponse]	false	none
» modelId	string	true	the ID of the recommended model
» recommendationType	string	true	the type of model recommendation

Enumerated Values¶

Property	Value
recommendationType	[`MOSTACCURATE`, `LIMITEDACCURATE`, `FASTACCURATE`, `RECOMMENDEDFORDEPLOYMENT`, `PREPAREDFORDEPLOYMENT`]

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/recommendedModels/recommendedModel/¶

This route returns the simplest recommended model available. To see all the available recommended models, use GET /api/v2/projects/{projectId}/recommendedModels/

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/recommendedModels/recommendedModel/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID

Example responses¶


{
  "modelId": "string",
  "recommendationType": "MOSTACCURATE"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	The recommended model	RecommendedModelResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/ruleFitFiles/¶

List all RuleFit code files available for download

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/ruleFitFiles/?offset=0&limit=100 \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
modelId	query	string	false	if specified only RuleFit code files with code used in the specified RuleFit model will be returned; otherwise all applicable RuleFit files will be returned
offset	query	integer	true	This many files will be skipped.
limit	query	integer	true	At most this many files are returned.
projectId	path	string	true	the project to list available files for

Example responses¶


{
  "count": 0,
  "data": [
    {
      "id": "string",
      "isValid": true,
      "language": "Python",
      "modelId": "string",
      "projectId": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	none	RuleFitCodeFileListResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

POST /api/v2/projects/{projectId}/ruleFitFiles/¶

Request creation and validation of source code from a RuleFit model

Code samples¶


curl -X POST https://app.datarobot.com/api/v2/projects/{projectId}/ruleFitFiles/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "language": "Python",
  "modelId": "string"
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	the project the file belongs to
body	body	RuleFitCodeFileCreate	false	none

Responses¶

Status	Meaning	Description	Schema
202	Accepted	RuleFit code validation job added to queue. See the Location header.	None

Response Headers¶

Status	Header	Type	Format	Description
202	Location	string	url	a url that can be polled to check the status of RuleFit code validation job

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/ruleFitFiles/{ruleFitFileId}/¶

Get information about a RuleFit code file available for download

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/ruleFitFiles/{ruleFitFileId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
ruleFitFileId	path	string	true	the ID of the file
projectId	path	string	true	the project to list available files for

Example responses¶


{
  "id": "string",
  "isValid": true,
  "language": "Python",
  "modelId": "string",
  "projectId": "string"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	none	RuleFitCodeFileResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

GET /api/v2/projects/{projectId}/ruleFitFiles/{ruleFitFileId}/download/¶

Download code from an existing RuleFit file

Code samples¶


curl -X GET https://app.datarobot.com/api/v2/projects/{projectId}/ruleFitFiles/{ruleFitFileId}/download/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name	In	Type	Required	Description
ruleFitFileId	path	string	true	the ID of the file
projectId	path	string	true	the project to list available files for

Responses¶

Status	Meaning	Description	Schema
200	OK	The response will contain a file with the executable code from the RuleFit model	None

Response Headers¶

Status	Header	Type	Format	Description
200	Content-Disposition	string		Will be attachment;filename="<"filename">". The suggested filename will depend on the language RuleFit file was generated for.

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

PUT /api/v2/projects/{projectId}/segmentChampion/¶

Update champion model for a segment project.

Code samples¶


curl -X PUT https://app.datarobot.com/api/v2/projects/{projectId}/segmentChampion/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

Body parameter¶


{
  "clone": false,
  "modelId": "string"
}

Parameters

Name	In	Type	Required	Description
projectId	path	string	true	The project ID
body	body	SegmentChampionModelUpdate	false	none

Example responses¶


{
  "combinedModelId": "string"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	The ID of Combined model that has been updated with new segment champion model.	SegmentChampionModelUpdateResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

Schemas¶

AdvancedTuningArgumentsRetrieveResponse


{
  "tuningDescription": "string",
  "tuningParameters": [
    {
      "constraints": {
        "ascii": {
          "supportsGridSearch": true
        },
        "float": {
          "max": 0,
          "min": 0,
          "supportsGridSearch": true
        },
        "floatList": {
          "maxLength": 0,
          "maxVal": 0,
          "minLength": 0,
          "minVal": 0,
          "supportsGridSearch": true
        },
        "int": {
          "max": 0,
          "min": 0,
          "supportsGridSearch": true
        },
        "intList": {
          "maxLength": 0,
          "maxVal": 0,
          "minLength": 0,
          "minVal": 0,
          "supportsGridSearch": true
        },
        "select": {
          "supportsGridSearch": true,
          "values": [
            "string"
          ]
        },
        "selectgrid": {
          "supportsGridSearch": true,
          "values": [
            "string"
          ]
        },
        "unicode": {
          "supportsGridSearch": true
        }
      },
      "currentValue": "string",
      "defaultValue": "string",
      "parameterId": "string",
      "parameterName": "string",
      "taskName": "string",
      "vertexId": "string"
    }
  ]
}

Properties¶

Name	Type	Required	Restrictions	Description
tuningDescription	string,null	true		Human-readable description of the tuned model, if specified by the user. `null` if unspecified.
tuningParameters	[TuningParameters]	true		An array of objects containing information about tuning parameters that are supported by the specified model.

BacktestStatusResponse


{
  "index": 0,
  "score": 0,
  "status": "COMPLETED",
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z"
}

Properties¶

Name	Type	Required	Description
index	integer	true	the index of the fold
score	number,null	true	the score of the model for this backtesting fold, if computed
status	string	true	the status of the current backtest model job
trainingDuration	string(duration)	true	the duration of the data used to train the model for this backtesting fold
trainingEndDate	string(date-time)	true	the end date of the training for this backtesting fold
trainingRowCount	integer	true	the number of rows used to train the model for this backtesting fold
trainingStartDate	string(date-time)	true	the start date of the training for this backtesting fold

Enumerated Values¶

Property	Value
status	[`COMPLETED`, `NOT_COMPLETED`, `INSUFFICIENT_DATA`, `ERRORED`, `BACKTEST_BOUNDARIES_EXCEEDED`]

BaseConstraintType


{
  "supportsGridSearch": true
}

Indicates that the value can contain free-form ASCII text. If present, is an empty object. Note that ascii fields must be valid ASCII-encoded strings. Additionally, they may not contain semicolons or newlines.

Properties¶

Name	Type	Required	Restrictions	Description
supportsGridSearch	boolean	true		When True, Grid Search is supported for this parameter.

BiasMitigatedModelsDataResponse


{
  "biasMitigationTechnique": "preprocessingReweighing",
  "includeBiasMitigationFeatureAsPredictorVariable": true,
  "modelId": "string",
  "parentModelId": "string",
  "protectedFeature": "string"
}

Properties¶

Name	Type	Required	Description
biasMitigationTechnique	string	true	Method applied to perform bias mitigation.
includeBiasMitigationFeatureAsPredictorVariable	boolean	true	Specifies whether the mitigation feature will be used as a predictor variable (i.e., treated like other categorical features in the input to train the modeler), in addition to being used for bias mitigation. If false, the mitigation feature will be used only for bias mitigation, and not for training the modeler task.
modelId	string	true	Mitigated model ID
parentModelId	string,null	true	Parent model ID
protectedFeature	string	true	Protected feature that will be used in a bias mitigation task to mitigate bias

Enumerated Values¶

Property	Value
biasMitigationTechnique	[`preprocessingReweighing`, `postProcessingRejectionOptionBasedClassification`]

BiasMitigatedModelsListResponse


{
  "count": 0,
  "data": [
    {
      "biasMitigationTechnique": "preprocessingReweighing",
      "includeBiasMitigationFeatureAsPredictorVariable": true,
      "modelId": "string",
      "parentModelId": "string",
      "protectedFeature": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Properties¶

Name	Type	Required	Description
count	integer	false	Number of items returned on this page.
data	[BiasMitigatedModelsDataResponse]	true	Retrieve list of mitigated models for project.
next	string,null(uri)	true	URL pointing to the next page (if null, there is no next page).
previous	string,null(uri)	true	URL pointing to the previous page (if null, there is no previous page).
totalCount	integer	true	The total number of items across all pages.

BiasMitigationModelCreate


{
  "biasMitigationFeature": "string",
  "biasMitigationParentLid": "string",
  "biasMitigationTechnique": "preprocessingReweighing",
  "includeBiasMitigationFeatureAsPredictorVariable": true
}

Properties¶

Name	Type	Required	Restrictions	Description
biasMitigationFeature	string	true	minLength: 1 minLength: 1	The name of the protected feature used to mitigate bias on models.
biasMitigationParentLid	string	true		The ID of the model to modify with a bias-mitigation task.
biasMitigationTechnique	string	true		Method applied to perform bias mitigation.
includeBiasMitigationFeatureAsPredictorVariable	boolean	true		Specifies whether the mitigation feature will be used as a predictor variable (i.e., treated like other categorical features in the input to train the modeler), in addition to being used for bias mitigation. If false, the mitigation feature will be used only for bias mitigation, and not for training the modeler task.

Enumerated Values¶

Property	Value
biasMitigationTechnique	[`preprocessingReweighing`, `postProcessingRejectionOptionBasedClassification`]

BlenderCreate


{
  "blenderMethod": "PLS",
  "modelIds": [
    "string"
  ]
}

Properties¶

Name	Type	Required	Restrictions	Description
blenderMethod	string	true		The blender method, one of "PLS", "GLM", "AVG", "ENET", "MED", "MAE", "MAEL1", "TF", "RF", "LGBM", "FORECAST_DISTANCE_ENET" (new in v2.18), "FORECAST_DISTANCE_AVG" (new in v2.18), "MIN", "MAX".
modelIds	[string]	true	minItems: 1	The list of models to use in blender.

Enumerated Values¶

Property	Value
blenderMethod	[`PLS`, `GLM`, `ENET`, `AVG`, `MED`, `MAE`, `MAEL1`, `FORECAST_DISTANCE_AVG`, `FORECAST_DISTANCE_ENET`, `MAX`, `MIN`]

BlenderInfoRetrieveResponse


{
  "blendable": true,
  "reason": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
blendable	boolean	true		If True, the models can be blended.
reason	string	true		Useful info as to why a model can't be blended.

BlenderListResponse


{
  "count": 0,
  "data": [
    {
      "blenderMethod": "string",
      "blenderModels": [
        0
      ],
      "blueprintId": "string",
      "dataSelectionMethod": "duration",
      "externalPredictionModel": true,
      "featurelistId": "string",
      "featurelistName": "string",
      "frozenPct": 0,
      "hasCodegen": true,
      "hasFinetuners": true,
      "icons": 0,
      "id": "string",
      "isAugmented": true,
      "isBlender": true,
      "isCustom": true,
      "isFrozen": true,
      "isNClustersDynamicallyDetermined": true,
      "isStarred": true,
      "isTrainedIntoHoldout": true,
      "isTrainedIntoValidation": true,
      "isTrainedOnGpu": true,
      "isTransparent": true,
      "isUserModel": true,
      "lifecycle": {
        "reason": "string",
        "stage": "active"
      },
      "linkFunction": "string",
      "metrics": {},
      "modelCategory": "model",
      "modelFamily": "string",
      "modelFamilyFullName": "string",
      "modelIds": [
        "string"
      ],
      "modelNumber": 0,
      "modelType": "string",
      "monotonicDecreasingFeaturelistId": "string",
      "monotonicIncreasingFeaturelistId": "string",
      "nClusters": 0,
      "parentModelId": "string",
      "predictionThreshold": 1,
      "predictionThresholdReadOnly": true,
      "processes": [
        "string"
      ],
      "projectId": "string",
      "samplePct": 0,
      "samplingMethod": "random",
      "supportsComposableMl": true,
      "supportsMonotonicConstraints": true,
      "timeWindowSamplePct": 99,
      "trainingDuration": "string",
      "trainingEndDate": "2019-08-24T14:15:22Z",
      "trainingRowCount": 0,
      "trainingStartDate": "2019-08-24T14:15:22Z"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Properties¶

Name	Type	Required	Description
count	integer	true	Number of items returned on this page.
data	[BlenderRetrieveResponse]	true	Each has the same schema as if retrieving the model individually from GET /api/v2/projects/{projectId}/blenderModels/{modelId}/.
next	string,null(uri)	true	URL pointing to the next page (if null, there is no next page).
previous	string,null(uri)	true	URL pointing to the previous page (if null, there is no previous page).

BlenderRetrieveResponse


{
  "blenderMethod": "string",
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "dataSelectionMethod": "duration",
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "frozenPct": 0,
  "hasCodegen": true,
  "hasFinetuners": true,
  "icons": 0,
  "id": "string",
  "isAugmented": true,
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isNClustersDynamicallyDetermined": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "lifecycle": {
    "reason": "string",
    "stage": "active"
  },
  "linkFunction": "string",
  "metrics": {},
  "modelCategory": "model",
  "modelFamily": "string",
  "modelFamilyFullName": "string",
  "modelIds": [
    "string"
  ],
  "modelNumber": 0,
  "modelType": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 0,
  "parentModelId": "string",
  "predictionThreshold": 1,
  "predictionThresholdReadOnly": true,
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": 0,
  "samplingMethod": "random",
  "supportsComposableMl": true,
  "supportsMonotonicConstraints": true,
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z"
}

Properties¶

Name	Type	Required	Restrictions	Description
blenderMethod	string	true		Method used to blend results of underlying models.
blenderModels	[integer]	true	maxItems: 100	Models that are in the blender.
blueprintId	string	true		The blueprint used to construct the model.
dataSelectionMethod	string	false		Identifies which setting defines the training size of the model when making predictions and scoring. Only used by datetime models.
externalPredictionModel	boolean	true		If the model is an external prediction model.
featurelistId	string,null	true		The ID of the feature list used by the model.
featurelistName	string,null	true		The name of the feature list used by the model. If null, themodel was trained on multiple feature lists.
frozenPct	number,null	true		The training percent used to train the frozen model.
hasCodegen	boolean	true		If the model has a codegen JAR file.
hasFinetuners	boolean	false		Whether a model has fine tuners.
icons	integer,null	true		The icons associated with the model.
id	string	true		The ID of the model.
isAugmented	boolean	false		Whether a model was trained using augmentation.
isBlender	boolean	true		If the model is a blender.
isCustom	boolean	true		If the model contains custom tasks.
isFrozen	boolean	true		Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model.
isNClustersDynamicallyDetermined	boolean	false		Whether number of clusters is dynamically determined. Only valid in unsupervised clustering projects.
isStarred	boolean	true		Indicates whether the model has been starred.
isTrainedIntoHoldout	boolean	true		Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size.
isTrainedIntoValidation	boolean	true		Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size.
isTrainedOnGpu	boolean	true		Whether the model was trained using GPU workers.
isTransparent	boolean	true		If the model is a transparent model with exposed coefficients.
isUserModel	boolean	true		If the model was created with Composable ML.
lifecycle	ModelLifecycle	true		Object returning model lifecycle.
linkFunction	string,null	true		The link function the final modeler uses in the blueprint. If no link function exists, returns null.
metrics	object	true		The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed.
modelCategory	string	true		Indicates the type of model. Returns `prime` for DataRobot Prime models, `blend` for blender models, `combined` for combined models, and `model` for all other models.
modelFamily	string	true		the family model belongs to, e.g. SVM, GBM, etc.
modelFamilyFullName	string	true		The full name of the family that the model belongs to. For e.g., Support Vector Machine, Gradient Boosting Machine, etc.
modelIds	[string]	true		List of models used in blender.
modelNumber	integer,null	true		The model number from the Leaderboard.
modelType	string	true		Identifies the model (e.g.,`Nystroem Kernel SVM Regressor`).
monotonicDecreasingFeaturelistId	string,null	true		the ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced.
monotonicIncreasingFeaturelistId	string,null	true		the ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced.
nClusters	integer,null	false		The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.
parentModelId	string,null	true		The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise.
predictionThreshold	number	true	maximum: 1 minimum: 0	threshold used for binary classification in predictions.
predictionThresholdReadOnly	boolean	true		indicates whether modification of a predictions threshold is forbidden. Since v2.22 threshold modification is allowed.
processes	[string]	true	maxItems: 100	The list of processes used by the model.
projectId	string	true		The ID of the project to which the model belongs.
samplePct	number,null	true		The percentage of the dataset used in training the model.
samplingMethod	string	false		indicates sampling method used to select training data in datetime models. For row-based project this is the way how requested number of rows are selected.For other projects (duration-based, start/end, project settings) - how specified percent of rows (timeWindowSamplePct) is selected from specified time window.
supportsComposableMl	boolean	true		indicates whether this model is supported in Composable ML.
supportsMonotonicConstraints	boolean	true		whether this model supports enforcing monotonic constraints
timeWindowSamplePct	integer,null	false		An integer between 1 and 99, indicating the percentage of sampling within the time window. The points kept are determined by samplingMethod option. Will be null if no sampling was specified. Only used by datetime models.
trainingDuration	string,null	true		the duration spanned by the dates in the partition column for the data used to train the model
trainingEndDate	string,null(date-time)	true		the end date of the dates in the partition column for the data used to train the model
trainingRowCount	integer,null	true		The number of rows used to train the model.
trainingStartDate	string,null(date-time)	true		the start date of the dates in the partition column for the data used to train the model

Enumerated Values¶

Property	Value
dataSelectionMethod	[`duration`, `rowCount`, `selectedDateRange`, `useProjectSettings`]
modelCategory	[`model`, `prime`, `blend`, `combined`, `incrementalLearning`]
samplingMethod	[`random`, `latest`]

ClassificationBinDataResponse


{
  "binEnd": 0,
  "binStart": 0,
  "negatives": 0,
  "positives": 0
}

Properties¶

Name	Type	Required	Description
binEnd	number	true	The end of the numeric range for the current bin. Note that `binEnd` - `binStart` should be a constant, modulo floating-point rounding error, for all bins in a single plot.
binStart	number	true	The start of the numeric range for the current bin. Must be equal to the `binEnd` of the previous bin.
negatives	integer	true	The number of records in the dataset where the model's predicted value falls into this bin and the target is negative.
positives	integer	true	The number of records in the dataset where the model's predicted value falls into this bin and the target is positive.

ClusterInfoList


{
  "name": "string",
  "percent": 100
}

Properties¶

Name	Type	Required	Restrictions	Description
name	string	true	maxLength: 50 minLength: 1 minLength: 1	A cluster name.
percent	number	false	maximum: 100 minimum: 0	The percentage of rows in the dataset this cluster contains.

ClusterNamesMappingValidation


{
  "currentName": "string",
  "newName": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
currentName	string	true	maxLength: 50 minLength: 1 minLength: 1	Current cluster name.
newName	string	true	maxLength: 50 minLength: 1 minLength: 1	New cluster name.

ClusterNamesResponse


{
  "clusters": [
    {
      "name": "string",
      "percent": 100
    },
    {
      "name": "string",
      "percent": 100
    }
  ],
  "modelId": "string",
  "projectId": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
clusters	[ClusterInfoList]	true	maxItems: 100 minItems: 2	A list of the model's cluster information entries.
modelId	string	true		The model ID
projectId	string	true		The project ID

ClusterNamesUpdateParam


{
  "clusterNameMappings": [
    {
      "currentName": "string",
      "newName": "string"
    }
  ]
}

Properties¶

Name	Type	Required	Restrictions	Description
clusterNameMappings	[ClusterNamesMappingValidation]	true	maxItems: 100	A list of the mappings from a cluster's current name to its new name. After update, value passed as a new name will become cluster's current name. All cluster names should be unique and should identify one and only one cluster.

CombinedModelListResponse


{
  "count": 0,
  "data": [
    {
      "combinedModelId": "string",
      "isActiveCombinedModel": false,
      "modelCategory": "combined",
      "projectId": "string",
      "segmentationTaskId": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Properties¶

Name	Type	Required	Description
count	integer	false	Number of items returned on this page.
data	[CommonGetAndListCombinedModel]	true	List of combined models.
next	string,null(uri)	true	URL pointing to the next page (if null, there is no next page).
previous	string,null(uri)	true	URL pointing to the previous page (if null, there is no previous page).
totalCount	integer	true	The total number of items across all pages.

CombinedModelResponse


{
  "combinedModelId": "string",
  "isActiveCombinedModel": false,
  "modelCategory": "combined",
  "projectId": "string",
  "segmentationTaskId": "string",
  "segments": [
    {
      "modelId": "string",
      "projectId": "string",
      "segment": "string"
    }
  ]
}

Properties¶

Name	Type	Required	Description
combinedModelId	string	true	The ID of combined model.
isActiveCombinedModel	boolean	true	Indicates whether this model is the active one in segmented modeling project.
modelCategory	string	true	Indicates what kind of model this is. Will be `combined` for combined models.
projectId	string	true	The ID of the project.
segmentationTaskId	string	true	The ID of the segmentation task used to generate this combined model.
segments	[SegmentProjectModelResponse]	true	Information for each segment. Maps each segment to the project and model used for it.

Enumerated Values¶

Property	Value
modelCategory	`combined`

CombinedModelSegmentsPaginatedResponse


{
  "count": 0,
  "data": [
    {
      "autopilotDone": true,
      "holdoutUnlocked": true,
      "isFrozen": true,
      "modelAssignedBy": "string",
      "modelAwardTime": "2019-08-24T14:15:22Z",
      "modelCount": 0,
      "modelIcon": [
        0
      ],
      "modelId": "string",
      "modelMetrics": {},
      "modelType": "string",
      "projectId": "string",
      "projectPaused": true,
      "projectStage": "modeling",
      "projectStageDescription": "string",
      "projectStatusError": "string",
      "rowCount": 0,
      "rowPercentage": 0,
      "segment": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Properties¶

Name	Type	Required	Description
count	integer	false	Number of items returned on this page.
data	[CombinedModelSegmentsResponse]	true	List of combined model segments info.
next	string,null(uri)	true	URL pointing to the next page (if null, there is no next page).
previous	string,null(uri)	true	URL pointing to the previous page (if null, there is no previous page).
totalCount	integer	true	The total number of items across all pages.

CombinedModelSegmentsResponse


{
  "autopilotDone": true,
  "holdoutUnlocked": true,
  "isFrozen": true,
  "modelAssignedBy": "string",
  "modelAwardTime": "2019-08-24T14:15:22Z",
  "modelCount": 0,
  "modelIcon": [
    0
  ],
  "modelId": "string",
  "modelMetrics": {},
  "modelType": "string",
  "projectId": "string",
  "projectPaused": true,
  "projectStage": "modeling",
  "projectStageDescription": "string",
  "projectStatusError": "string",
  "rowCount": 0,
  "rowPercentage": 0,
  "segment": "string"
}

Properties¶

Name	Type	Required	Description
autopilotDone	boolean,null	true	Is autopilot done for the project.
holdoutUnlocked	boolean,null	true	Is holdout unlocked for the project.
isFrozen	boolean,null	true	Indicates whether the segment champion model is frozen, i.e. uses tuning parameters from a parent model
modelAssignedBy	string,null	true	Who assigned model as segment champion. Default is `DataRobot`.
modelAwardTime	string,null(date-time)	true	Time when model was awarded as segment champion.
modelCount	integer,null	true	Count of trained models in project.
modelIcon	[integer]	true	The number for the icon representing the given champion model.
modelId	string,null	true	ID of segment champion model.
modelMetrics	object,null	true	The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or `null` if they have not been computed.
modelType	string,null	true	The description of the model type of the given champion model.
projectId	string,null	true	The ID of the project.
projectPaused	boolean,null	false	Is project paused right now.
projectStage	string,null	true	The current stage of the project, where modeling indicates that the target has been successfully set and modeling and predictions may proceed.
projectStageDescription	string,null	true	A description of the current stage of the project.
projectStatusError	string,null	false	Project status error message.
rowCount	integer,null	true	Count of rows in project's dataset.
rowPercentage	number,null	true	Percentage of rows in segment project's dataset comparing to original dataset.
segment	string	true	Segment name.

Enumerated Values¶

Property	Value
projectStage	[`modeling`, `aim`, `fasteda`, `eda`, `eda2`, `empty`]

CommonGetAndListCombinedModel


{
  "combinedModelId": "string",
  "isActiveCombinedModel": false,
  "modelCategory": "combined",
  "projectId": "string",
  "segmentationTaskId": "string"
}

Properties¶

Name	Type	Required	Description
combinedModelId	string	true	The ID of combined model.
isActiveCombinedModel	boolean	true	Indicates whether this model is the active one in segmented modeling project.
modelCategory	string	true	Indicates what kind of model this is. Will be `combined` for combined models.
projectId	string	true	The ID of the project.
segmentationTaskId	string	true	The ID of the segmentation task used to generate this combined model.

Enumerated Values¶

Property	Value
modelCategory	`combined`

Constraints


{
  "ascii": {
    "supportsGridSearch": true
  },
  "float": {
    "max": 0,
    "min": 0,
    "supportsGridSearch": true
  },
  "floatList": {
    "maxLength": 0,
    "maxVal": 0,
    "minLength": 0,
    "minVal": 0,
    "supportsGridSearch": true
  },
  "int": {
    "max": 0,
    "min": 0,
    "supportsGridSearch": true
  },
  "intList": {
    "maxLength": 0,
    "maxVal": 0,
    "minLength": 0,
    "minVal": 0,
    "supportsGridSearch": true
  },
  "select": {
    "supportsGridSearch": true,
    "values": [
      "string"
    ]
  },
  "selectgrid": {
    "supportsGridSearch": true,
    "values": [
      "string"
    ]
  },
  "unicode": {
    "supportsGridSearch": true
  }
}

Constraints on valid values for this parameter. Note that any of these fields may be omitted but at least one will always be present. The presence of a field indicates that the parameter in question will accept values in the corresponding format.

Properties¶

Name	Type	Required	Description
ascii	BaseConstraintType	false	Indicates that the value can contain free-form ASCII text. If present, is an empty object. Note that `ascii` fields must be valid ASCII-encoded strings. Additionally, they may not contain semicolons or newlines.
float	Float	false	Numeric constraints on a floating-point value. If present, indicates that this parameter's value may be a JSON number (integer or floating point).
floatList	FloatList	false	Numeric constraints on a value of an array of floating-point numbers. If present, indicates that this parameter's value may be a JSON array of numbers (integer or floating point).
int	Int	false	Numeric constraints on an integer value. If present, indicates that this parameter's value may be a JSON integer.
intList	IntList	false	Numeric constraints on a value of an array of floating-point numbers. If present, indicates that this parameter's value may be a JSON array of integers.
select	Select	false	Indicates that the value can be one selected from a list of known values.
selectgrid	Select	false	Indicates that the value can be one selected from a list of known values.
unicode	BaseConstraintType	false	Indicates that the value can contain free-form ASCII text. If present, is an empty object. Note that `ascii` fields must be valid ASCII-encoded strings. Additionally, they may not contain semicolons or newlines.

CrossValidationRetrieveResponse


{
  "cvScores": "\n        {\n            \"cvScores\": {\n                \"FVE Gamma\": {\n                    \"0.0\": 0.24334,\n                    \"1.0\": 0.17757,\n                    \"2.0\": 0.21803,\n                    \"3.0\": 0.20185,\n                    \"4.0\": 0.20576\n                },\n                \"FVE Poisson\": {\n                    \"0.0\": 0.24527,\n                    \"1.0\": 0.22092,\n                    \"2.0\": 0.22451,\n                    \"3.0\": 0.24417,\n                    \"4.0\": 0.21654\n                }\n            }\n        }\n"
}

Properties¶

Name	Type	Required	Restrictions	Description
cvScores	object	true		A dictionary `cvScores` with sub-dictionary keyed by `partition_id`, each `partition_id` is itself a dictionary keyed by `metric_name` where the value is the reading for that particular metric for the partition_id.

DatetimeModelDetailsResponse


{
  "backtests": [
    {
      "index": 0,
      "score": 0,
      "status": "COMPLETED",
      "trainingDuration": "string",
      "trainingEndDate": "2019-08-24T14:15:22Z",
      "trainingRowCount": 0,
      "trainingStartDate": "2019-08-24T14:15:22Z"
    }
  ],
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "dataSelectionMethod": "duration",
  "effectiveFeatureDerivationWindowEnd": 0,
  "effectiveFeatureDerivationWindowStart": 0,
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "forecastWindowEnd": 0,
  "forecastWindowStart": 0,
  "frozenPct": 0,
  "hasCodegen": true,
  "hasFinetuners": true,
  "holdoutScore": 0,
  "holdoutStatus": "COMPLETED",
  "icons": 0,
  "id": "string",
  "isAugmented": true,
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isNClustersDynamicallyDetermined": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "lifecycle": {
    "reason": "string",
    "stage": "active"
  },
  "linkFunction": "string",
  "metrics": "\n        {\n            \"metrics\": {\n                \"FVE Poisson\": {\n                    \"holdout\": null,\n                    \"validation\": 0.56269,\n                    \"backtesting\": 0.50166,\n                    \"backtestingScores\": [0.51206, 0.49436, null, 0.62516],\n                    \"crossValidation\": null\n                },\n                \"RMSE\": {\n                    \"holdout\": null,\n                    \"validation\": 21.0836,\n                    \"backtesting\": 23.361932,\n                    \"backtestingScores\": [0.4403, 0.4213, null, 0.5132],\n                    \"crossValidation\": null\n                }\n            }\n        }\n",
  "modelCategory": "model",
  "modelFamily": "string",
  "modelFamilyFullName": "string",
  "modelNumber": 0,
  "modelType": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 0,
  "parentModelId": "string",
  "predictionThreshold": 1,
  "predictionThresholdReadOnly": true,
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": null,
  "samplingMethod": "random",
  "supportsComposableMl": true,
  "supportsMonotonicConstraints": true,
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingInfo": {
    "holdoutTrainingDuration": "string",
    "holdoutTrainingEndDate": "2019-08-24T14:15:22Z",
    "holdoutTrainingRowCount": 0,
    "holdoutTrainingStartDate": "2019-08-24T14:15:22Z",
    "predictionTrainingDuration": "string",
    "predictionTrainingEndDate": "2019-08-24T14:15:22Z",
    "predictionTrainingRowCount": 0,
    "predictionTrainingStartDate": "2019-08-24T14:15:22Z"
  },
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z",
  "windowsBasisUnit": "MILLISECOND"
}

Properties¶

Name	Type	Required	Restrictions	Description
backtests	[BacktestStatusResponse]	true		information on each backtesting fold of the model
blenderModels	[integer]	true	maxItems: 100	Models that are in the blender.
blueprintId	string	true		The blueprint used to construct the model.
dataSelectionMethod	string	false		Identifies which setting defines the training size of the model when making predictions and scoring. Only used by datetime models.
effectiveFeatureDerivationWindowEnd	integer	true	maximum: 0	Only available for time series projects. How many timeUnits into the past relative to the forecast point the feature derivation window should end.
effectiveFeatureDerivationWindowStart	integer	true		Only available for time series projects. How many timeUnits into the past relative to the forecast point the user needs to provide history for at prediction time. This can differ from the `featureDerivationWindowStart` set on the project due to the differencing method and period selected.
externalPredictionModel	boolean	true		If the model is an external prediction model.
featurelistId	string,null	true		The ID of the feature list used by the model.
featurelistName	string,null	true		The name of the feature list used by the model. If null, themodel was trained on multiple feature lists.
forecastWindowEnd	integer	true	minimum: 0	Only available for time series projects. How many timeUnits into the future relative to the forecast point the forecast window should end.
forecastWindowStart	integer	true	minimum: 0	Only available for time series projects. How many timeUnits into the future relative to the forecast point the forecast window should start.
frozenPct	number,null	true		The training percent used to train the frozen model.
hasCodegen	boolean	true		If the model has a codegen JAR file.
hasFinetuners	boolean	false		Whether a model has fine tuners.
holdoutScore	number,null	true		the holdout score of the model according to the project metric, if the score is available and the holdout is unlocked
holdoutStatus	string	true		the status of the holdout fold
icons	integer,null	true		The icons associated with the model.
id	string	true		The ID of the model.
isAugmented	boolean	false		Whether a model was trained using augmentation.
isBlender	boolean	true		If the model is a blender.
isCustom	boolean	true		If the model contains custom tasks.
isFrozen	boolean	true		Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model.
isNClustersDynamicallyDetermined	boolean	false		Whether number of clusters is dynamically determined. Only valid in unsupervised clustering projects.
isStarred	boolean	true		Indicates whether the model has been starred.
isTrainedIntoHoldout	boolean	true		Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size.
isTrainedIntoValidation	boolean	true		Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size.
isTrainedOnGpu	boolean	true		Whether the model was trained using GPU workers.
isTransparent	boolean	true		If the model is a transparent model with exposed coefficients.
isUserModel	boolean	true		If the model was created with Composable ML.
lifecycle	ModelLifecycle	true		Object returning model lifecycle.
linkFunction	string,null	true		The link function the final modeler uses in the blueprint. If no link function exists, returns null.
metrics	object	true		Object where each metric has validation, backtesting, backtestingScores and holdout scores reported, or null if they have not been computed. The `validation` score will be the score of the first backtest, which will be computed during initial model training. The `backtesting` and `backtestingScores` scores are computed when requested via POST /api/v2/projects/{projectId}/datetimeModels/{modelId}/backtests/. The `backtesting` score is the average score across all backtests. The `backtestingScores` is an array of scores for each backtest, with the scores reported as null if the backtest score is unavailable. The `holdout` score is the score against the holdout data, using the training data defined in `trainingInfo`.
modelCategory	string	true		Indicates the type of model. Returns `prime` for DataRobot Prime models, `blend` for blender models, `combined` for combined models, and `model` for all other models.
modelFamily	string	true		the family model belongs to, e.g. SVM, GBM, etc.
modelFamilyFullName	string	true		The full name of the family that the model belongs to. For e.g., Support Vector Machine, Gradient Boosting Machine, etc.
modelNumber	integer,null	true		The model number from the Leaderboard.
modelType	string	true		Identifies the model (e.g.,`Nystroem Kernel SVM Regressor`).
monotonicDecreasingFeaturelistId	string,null	true		the ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced.
monotonicIncreasingFeaturelistId	string,null	true		the ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced.
nClusters	integer,null	false		The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.
parentModelId	string,null	true		The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise.
predictionThreshold	number	true	maximum: 1 minimum: 0	threshold used for binary classification in predictions.
predictionThresholdReadOnly	boolean	true		indicates whether modification of a predictions threshold is forbidden. Since v2.22 threshold modification is allowed.
processes	[string]	true	maxItems: 100	The list of processes used by the model.
projectId	string	true		The ID of the project to which the model belongs.
samplePct	string	true		always null for datetime models
samplingMethod	string	false		indicates sampling method used to select training data in datetime models. For row-based project this is the way how requested number of rows are selected.For other projects (duration-based, start/end, project settings) - how specified percent of rows (timeWindowSamplePct) is selected from specified time window.
supportsComposableMl	boolean	true		indicates whether this model is supported in Composable ML.
supportsMonotonicConstraints	boolean	true		whether this model supports enforcing monotonic constraints
timeWindowSamplePct	integer,null	false		An integer between 1 and 99, indicating the percentage of sampling within the time window. The points kept are determined by samplingMethod option. Will be null if no sampling was specified. Only used by datetime models.
trainingDuration	string,null	true		the duration spanned by the dates in the partition column for the data used to train the model
trainingEndDate	string,null(date-time)	true		the end date of the dates in the partition column for the data used to train the model
trainingInfo	TrainingInfoResponse	true		holdout and prediction training data details
trainingRowCount	integer,null	true		The number of rows used to train the model.
trainingStartDate	string,null(date-time)	true		the start date of the dates in the partition column for the data used to train the model
windowsBasisUnit	string	true		Only available for time series projects. Indicates which unit is the basis for the feature derivation window and the forecast window.

Enumerated Values¶

Property	Value
dataSelectionMethod	[`duration`, `rowCount`, `selectedDateRange`, `useProjectSettings`]
holdoutStatus	[`COMPLETED`, `INSUFFICIENT_DATA`, `HOLDOUT_BOUNDARIES_EXCEEDED`]
modelCategory	[`model`, `prime`, `blend`, `combined`, `incrementalLearning`]
samplePct	`null`
samplingMethod	[`random`, `latest`]
windowsBasisUnit	[`MILLISECOND`, `SECOND`, `MINUTE`, `HOUR`, `DAY`, `WEEK`, `MONTH`, `QUARTER`, `YEAR`, `ROW`]

DatetimeModelRecordResponse


{
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "dataSelectionMethod": "duration",
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "frozenPct": 0,
  "hasCodegen": true,
  "icons": 0,
  "id": "string",
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "metrics": {},
  "modelCategory": "model",
  "modelFamily": "string",
  "modelNumber": 0,
  "modelType": "string",
  "parentModelId": "string",
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": 0,
  "samplingMethod": "random",
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z"
}

Properties¶

Name	Type	Required	Restrictions	Description
blenderModels	[integer]	true	maxItems: 100	Models that are in the blender.
blueprintId	string	true		The blueprint used to construct the model.
dataSelectionMethod	string	false		Identifies which setting defines the training size of the model when making predictions and scoring. Only used by datetime models.
externalPredictionModel	boolean	true		If the model is an external prediction model.
featurelistId	string,null	true		The ID of the feature list used by the model.
featurelistName	string,null	true		The name of the feature list used by the model. If null, themodel was trained on multiple feature lists.
frozenPct	number,null	true		The training percent used to train the frozen model.
hasCodegen	boolean	true		If the model has a codegen JAR file.
icons	integer,null	true		The icons associated with the model.
id	string	true		The ID of the model.
isBlender	boolean	true		If the model is a blender.
isCustom	boolean	true		If the model contains custom tasks.
isFrozen	boolean	true		Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model.
isStarred	boolean	true		Indicates whether the model has been starred.
isTrainedIntoHoldout	boolean	true		Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size.
isTrainedIntoValidation	boolean	true		Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size.
isTrainedOnGpu	boolean	true		Whether the model was trained using GPU workers.
isTransparent	boolean	true		If the model is a transparent model with exposed coefficients.
isUserModel	boolean	true		If the model was created with Composable ML.
metrics	object	true		The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed.
modelCategory	string	true		Indicates the type of model. Returns `prime` for DataRobot Prime models, `blend` for blender models, `combined` for combined models, and `model` for all other models.
modelFamily	string	true		The full name of the family that the model belongs to (e.g., Support Vector Machine, Gradient Boosting Machine, etc.).
modelNumber	integer,null	true		The model number from the Leaderboard.
modelType	string	true		Identifies the model (e.g.,`Nystroem Kernel SVM Regressor`).
parentModelId	string,null	true		The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise.
processes	[string]	true	maxItems: 100	The list of processes used by the model.
projectId	string	true		The ID of the project to which the model belongs.
samplePct	number,null	true		The percentage of the dataset used in training the model.
samplingMethod	string	false		indicates sampling method used to select training data in datetime models. For row-based project this is the way how requested number of rows are selected.For other projects (duration-based, start/end, project settings) - how specified percent of rows (timeWindowSamplePct) is selected from specified time window.
timeWindowSamplePct	integer,null	false		An integer between 1 and 99, indicating the percentage of sampling within the time window. The points kept are determined by samplingMethod option. Will be null if no sampling was specified. Only used by datetime models.
trainingDuration	string,null	true		the duration spanned by the dates in the partition column for the data used to train the model
trainingEndDate	string,null(date-time)	true		the end date of the dates in the partition column for the data used to train the model
trainingRowCount	integer,null	true		The number of rows used to train the model.
trainingStartDate	string,null(date-time)	true		the start date of the dates in the partition column for the data used to train the model

Enumerated Values¶

Property	Value
dataSelectionMethod	[`duration`, `rowCount`, `selectedDateRange`, `useProjectSettings`]
modelCategory	[`model`, `prime`, `blend`, `combined`, `incrementalLearning`]
samplingMethod	[`random`, `latest`]

DatetimeModelSubmissionResponse


{
  "message": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
message	string	true		Any extended message to include about the result. For example, if a job is submitted that is a duplicate of a job that has already been added to the queue, the message will mention that no new job was created.

DatetimeModelsResponse


{
  "count": 0,
  "data": [
    {
      "backtests": [
        {
          "index": 0,
          "score": 0,
          "status": "COMPLETED",
          "trainingDuration": "string",
          "trainingEndDate": "2019-08-24T14:15:22Z",
          "trainingRowCount": 0,
          "trainingStartDate": "2019-08-24T14:15:22Z"
        }
      ],
      "blenderModels": [
        0
      ],
      "blueprintId": "string",
      "dataSelectionMethod": "duration",
      "effectiveFeatureDerivationWindowEnd": 0,
      "effectiveFeatureDerivationWindowStart": 0,
      "externalPredictionModel": true,
      "featurelistId": "string",
      "featurelistName": "string",
      "forecastWindowEnd": 0,
      "forecastWindowStart": 0,
      "frozenPct": 0,
      "hasCodegen": true,
      "hasFinetuners": true,
      "holdoutScore": 0,
      "holdoutStatus": "COMPLETED",
      "icons": 0,
      "id": "string",
      "isAugmented": true,
      "isBlender": true,
      "isCustom": true,
      "isFrozen": true,
      "isNClustersDynamicallyDetermined": true,
      "isStarred": true,
      "isTrainedIntoHoldout": true,
      "isTrainedIntoValidation": true,
      "isTrainedOnGpu": true,
      "isTransparent": true,
      "isUserModel": true,
      "lifecycle": {
        "reason": "string",
        "stage": "active"
      },
      "linkFunction": "string",
      "metrics": "\n        {\n            \"metrics\": {\n                \"FVE Poisson\": {\n                    \"holdout\": null,\n                    \"validation\": 0.56269,\n                    \"backtesting\": 0.50166,\n                    \"backtestingScores\": [0.51206, 0.49436, null, 0.62516],\n                    \"crossValidation\": null\n                },\n                \"RMSE\": {\n                    \"holdout\": null,\n                    \"validation\": 21.0836,\n                    \"backtesting\": 23.361932,\n                    \"backtestingScores\": [0.4403, 0.4213, null, 0.5132],\n                    \"crossValidation\": null\n                }\n            }\n        }\n",
      "modelCategory": "model",
      "modelFamily": "string",
      "modelFamilyFullName": "string",
      "modelNumber": 0,
      "modelType": "string",
      "monotonicDecreasingFeaturelistId": "string",
      "monotonicIncreasingFeaturelistId": "string",
      "nClusters": 0,
      "parentModelId": "string",
      "predictionThreshold": 1,
      "predictionThresholdReadOnly": true,
      "processes": [
        "string"
      ],
      "projectId": "string",
      "samplePct": null,
      "samplingMethod": "random",
      "supportsComposableMl": true,
      "supportsMonotonicConstraints": true,
      "timeWindowSamplePct": 99,
      "trainingDuration": "string",
      "trainingEndDate": "2019-08-24T14:15:22Z",
      "trainingInfo": {
        "holdoutTrainingDuration": "string",
        "holdoutTrainingEndDate": "2019-08-24T14:15:22Z",
        "holdoutTrainingRowCount": 0,
        "holdoutTrainingStartDate": "2019-08-24T14:15:22Z",
        "predictionTrainingDuration": "string",
        "predictionTrainingEndDate": "2019-08-24T14:15:22Z",
        "predictionTrainingRowCount": 0,
        "predictionTrainingStartDate": "2019-08-24T14:15:22Z"
      },
      "trainingRowCount": 0,
      "trainingStartDate": "2019-08-24T14:15:22Z",
      "windowsBasisUnit": "MILLISECOND"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Properties¶

Name	Type	Required	Description
count	integer	false	Number of items returned on this page.
data	[DatetimeModelDetailsResponse]	true	each has the same schema as if retrieving the model individually from GET /api/v2/projects/{projectId}/datetimeModels/{modelId}/.
next	string,null(uri)	true	URL pointing to the next page (if null, there is no next page).
previous	string,null(uri)	true	URL pointing to the previous page (if null, there is no previous page).

DerivedFeatures


{
  "coefficient": 0,
  "derivedFeature": "string",
  "originalFeature": "string",
  "stageCoefficients": [
    {
      "coefficient": 0,
      "stage": "string"
    }
  ],
  "transformations": [
    {
      "name": "string",
      "value": "string"
    }
  ],
  "type": "string"
}

Properties¶

Name	Type	Required	Description
coefficient	number	true	The coefficient for this feature.
derivedFeature	string	true	The name of the derived feature.
originalFeature	string	true	The name of the feature used to derive this feature.
stageCoefficients	[StageCoefficients]	true	An array of json objects describing separate coefficients for every stage of model (empty for single stage models).
transformations	[Transformations]	true	An array of json objects describing the transformations applied to create this derived feature.
type	string	true	The type of this feature.

Empty

{}

Properties¶

None

EureqaDistributionDetailResponse


{
  "bins": [
    {
      "binEnd": 0,
      "binStart": 0,
      "negatives": 0,
      "positives": 0
    }
  ],
  "complexity": 0,
  "error": 0,
  "errorMetric": "string",
  "eureqaSolutionId": "string",
  "expression": "string",
  "expressionAnnotated": "string",
  "threshold": 0
}

Properties¶

Name	Type	Required	Description
bins	[ClassificationBinDataResponse]	true	The distribution plot data.
complexity	integer	true	The complexity score for this solution. Complexity score is a function of the mathematical operators used in the current solution. The complexity calculation can be tuned via model hyperparameters.
error	number,null	true	The error for the current solution, as computed by eureqa using the `errorMetric` error metric. None if Eureqa model refitted existing solutions.
errorMetric	string	true	The Eureqa error metric identifier used to compute error metrics for this search. Note that Eureqa error metrics do not correspond 1:1 with DataRobot error metrics - the available metrics are not the same, and even equivalent metrics may be computed slightly differently.
eureqaSolutionId	string	true	The ID of the solution.
expression	string	true	The eureqa "solution string". This is a mathematical expression; human-readable but with strict syntax specifications defined by Eureqa.
expressionAnnotated	string	true	The `expression`, rendered with additional tags to assist in automatic parsing.
threshold	number	true	Classifier threshold selected by the backend, used to determine which model values are binned as positive and which are binned as negative. Must have a value between the `binStart` of the first bin and `binEnd` of the last bin.

EureqaLeaderboardEntryPayload


{
  "parentModelId": "string",
  "solutionId": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
parentModelId	string	false		The ID of the model to clone from. If omitted, will automatically search for and find the first leaderboard model created by the blueprint run that also created the solution associated with `solutionId`.
solutionId	string	true		the ID of the solution to be cloned.

EureqaModelDetailResponse


{
  "complexity": 0,
  "error": 0,
  "errorMetric": "string",
  "eureqaSolutionId": "string",
  "expression": "string",
  "expressionAnnotated": "string",
  "plotData": [
    {
      "actual": 0,
      "predicted": 0,
      "row": 0
    }
  ]
}

Properties¶

Name	Type	Required	Description
complexity	integer	true	The complexity score for this solution. Complexity score is a function of the mathematical operators used in the current solution. The complexity calculation can be tuned via model hyperparameters.
error	number,null	true	The error for the current solution, as computed by eureqa using the `errorMetric` error metric. None if Eureqa model refitted existing solutions.
errorMetric	string	true	The Eureqa error metric identifier used to compute error metrics for this search. Note that Eureqa error metrics do not correspond 1:1 with DataRobot error metrics - the available metrics are not the same, and even equivalent metrics may be computed slightly differently.
eureqaSolutionId	string	true	The ID of the solution.
expression	string	true	The eureqa "solution string". This is a mathematical expression; human-readable but with strict syntax specifications defined by Eureqa.
expressionAnnotated	string	true	The `expression`, rendered with additional tags to assist in automatic parsing.
plotData	[PlotDataResponse]	true	The plot data.

Float


{
  "max": 0,
  "min": 0,
  "supportsGridSearch": true
}

Numeric constraints on a floating-point value. If present, indicates that this parameter's value may be a JSON number (integer or floating point).

Properties¶

Name	Type	Required	Description
max	number	true	Maximum value for the parameter.
min	number	true	Minimum value for the parameter.
supportsGridSearch	boolean	true	When True, Grid Search is supported for this parameter.

FloatList


{
  "maxLength": 0,
  "maxVal": 0,
  "minLength": 0,
  "minVal": 0,
  "supportsGridSearch": true
}

Numeric constraints on a value of an array of floating-point numbers. If present, indicates that this parameter's value may be a JSON array of numbers (integer or floating point).

Properties¶

Name	Type	Required	Restrictions	Description
maxLength	integer	true	minimum: 0	Maximum permitted length of the list.
maxVal	number	true		Maximum permitted value.
minLength	integer	true	minimum: 0	Minimum permitted length of the list.
minVal	number	true		Minimum permitted value.
supportsGridSearch	boolean	true		When True, Grid Search is supported for this parameter.

FrozenModelCreate


{
  "modelId": "string",
  "nClusters": 2,
  "samplePct": 0,
  "trainingRowCount": 0
}

Properties¶

Name	Type	Required	Restrictions	Description
modelId	string	true		the ID of an existing model to use as a source of training parameters.
nClusters	integer	false	maximum: 100 minimum: 2	The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.
samplePct	number	false		the percentage of the dataset to use with the model. Only one of `samplePct` and `trainingRowCount` should be specified. The specified percentage should be between 0.0 and 100.0.
trainingRowCount	integer	false		the integer number of rows of the dataset to use with the model. Only one of `samplePct` and `trainingRowCount` should be specified.

FrozenModelListResponse


{
  "count": 0,
  "data": [
    {
      "blenderModels": [
        0
      ],
      "blueprintId": "string",
      "dataSelectionMethod": "duration",
      "externalPredictionModel": true,
      "featurelistId": "string",
      "featurelistName": "string",
      "frozenPct": 0,
      "hasCodegen": true,
      "hasFinetuners": true,
      "icons": 0,
      "id": "string",
      "isAugmented": true,
      "isBlender": true,
      "isCustom": true,
      "isFrozen": true,
      "isNClustersDynamicallyDetermined": true,
      "isStarred": true,
      "isTrainedIntoHoldout": true,
      "isTrainedIntoValidation": true,
      "isTrainedOnGpu": true,
      "isTransparent": true,
      "isUserModel": true,
      "lifecycle": {
        "reason": "string",
        "stage": "active"
      },
      "linkFunction": "string",
      "metrics": {},
      "modelCategory": "model",
      "modelFamily": "string",
      "modelFamilyFullName": "string",
      "modelNumber": 0,
      "modelType": "string",
      "monotonicDecreasingFeaturelistId": "string",
      "monotonicIncreasingFeaturelistId": "string",
      "nClusters": 0,
      "parentModelId": "string",
      "predictionThreshold": 1,
      "predictionThresholdReadOnly": true,
      "processes": [
        "string"
      ],
      "projectId": "string",
      "samplePct": 0,
      "samplingMethod": "random",
      "supportsComposableMl": true,
      "supportsMonotonicConstraints": true,
      "timeWindowSamplePct": 99,
      "trainingDuration": "string",
      "trainingEndDate": "2019-08-24T14:15:22Z",
      "trainingRowCount": 0,
      "trainingStartDate": "2019-08-24T14:15:22Z"
    }
  ],
  "next": "string",
  "previous": "string",
  "totalCount": 0
}

Properties¶

Name	Type	Required	Description
count	integer	true	Number of items returned on this page.
data	[ModelDetailsResponse]	true	An array of the frozen models in a project.
next	string,null	true	URL pointing to the next page (if null, there is no next page).
previous	string,null	true	URL pointing to the previous page (if null, there is no previous page)
totalCount	integer	false	Total number of records.

HyperparametersResponse


{
  "buildingBlocks": {},
  "errorMetric": "string",
  "maxGenerations": 32,
  "numThreads": 0,
  "priorSolutions": [
    "string"
  ],
  "randomSeed": 0,
  "splitMode": "custom",
  "syncMigrations": true,
  "targetExpressionFormat": "None",
  "targetExpressionString": "string",
  "timeoutSec": 0,
  "trainingFraction": 1,
  "trainingSplitExpr": "string",
  "validationFraction": 1,
  "validationSplitExpr": "string",
  "weightExpr": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
buildingBlocks	object,null	true		Mathematical operators and other components that comprise Eureqa Expressions.
errorMetric	string,null	false		Error Metric Eureqa used internally, to evaluate which models to keep on its internal Pareto Front.
maxGenerations	integer,null	true	minimum: 32	The maximum number of evolutionary generations to run.
numThreads	integer,null	true	minimum: 0	The number of threads Eureqa will run with.
priorSolutions	[string]	true		Prior Eureqa Solutions.
randomSeed	integer,null	true	minimum: 0	Constant to seed Eureqa's pseudo-random number generator.
splitMode	string,null	true		Whether to perform in-order (2) or random (1) splitting within the training set, for evolutionary re-training and re-validatoon.
syncMigrations	boolean,null	true		Whether Eureqa's migrations are synchronized.
targetExpressionFormat	string,null	true		Constrain the target expression to the specified format.
targetExpressionString	string,null	true		Eureqa Expression to constrain the form of the models that Eureqa will consider.
timeoutSec	number,null	true	minimum: 0	The duration of time to run the Eureqa search algorithm for Eureqa will run until either of max_generations or timeout_sec is reached.
trainingFraction	number,null	true	maximum: 1 minimum: 0	The fraction of the DataRobot training data to use for Eureqa evolutionary training.
trainingSplitExpr	string,null	true		Valid Eureqa Expression to do Eureqa internal training splits.
validationFraction	number,null	true	maximum: 1 minimum: 0	The fraction of the DataRobot training data to use for Eureqa evolutionary validation.
validationSplitExpr	string,null	true		Valid Eureqa Expression to do Eureqa internal validation splits.
weightExpr	string,null	true		Eureqa Weight Expression.

Enumerated Values¶

Property	Value
splitMode	[`custom`, `1`, `2`]
targetExpressionFormat	[`None`, `exponential`, `featureInteraction`]

Int


{
  "max": 0,
  "min": 0,
  "supportsGridSearch": true
}

Numeric constraints on an integer value. If present, indicates that this parameter's value may be a JSON integer.

Properties¶

Name	Type	Required	Description
max	integer	true	Maximum value for the parameter.
min	integer	true	Minimum value for the parameter.
supportsGridSearch	boolean	true	When True, Grid Search is supported for this parameter.

IntList


{
  "maxLength": 0,
  "maxVal": 0,
  "minLength": 0,
  "minVal": 0,
  "supportsGridSearch": true
}

Numeric constraints on a value of an array of floating-point numbers. If present, indicates that this parameter's value may be a JSON array of integers.

Properties¶

Name	Type	Required	Restrictions	Description
maxLength	integer	true	minimum: 0	Maximum permitted length of the list.
maxVal	integer	true		Maximum permitted value.
minLength	integer	true	minimum: 0	Minimum permitted length of the list.
minVal	integer	true		Minimum permitted value.
supportsGridSearch	boolean	true		When True, Grid Search is supported for this parameter.

MessagesInfo


{
  "messages": [
    {
      "additionalInfo": [
        "string"
      ],
      "messageLevel": "CRITICAL",
      "messageText": "string"
    }
  ]
}

Properties¶

Name	Type	Required	Restrictions	Description
messages	[OneMessageInfo]	true	maxItems: 50 minItems: 1	List of data quality messages. The list may include reports on more than one data quality issue, if present.

MissingReportRetrieve


{
  "missingValuesReport": [
    {
      "feature": "string",
      "missingCount": 0,
      "missingPercentage": 1,
      "tasks": {
        "property1": {
          "descriptions": [
            "string"
          ],
          "name": "string"
        },
        "property2": {
          "descriptions": [
            "string"
          ],
          "name": "string"
        }
      },
      "type": "string"
    }
  ]
}

Properties¶

Name	Type	Required	Restrictions	Description
missingValuesReport	[PerFeatureMissingReport]	true		Missing values report, which contains an array of reports for individual features

ModelAdvancedTuning


{
  "tuningDescription": "string",
  "tuningParameters": [
    {
      "parameterId": "string",
      "value": "string"
    }
  ]
}

Properties¶

Name	Type	Required	Restrictions	Description
tuningDescription	string	false		Human-readable description of this advanced-tuning request.
tuningParameters	[TuningParameter]	true		Parameters to tune.

ModelCapabilitiesRetrieveResponse


{
  "eligibleForPrime": true,
  "hasParameters": true,
  "hasWordCloud": true,
  "reasons": {
    "supportsAccuracyOverTime": "string",
    "supportsAnomalyAssessment": "string",
    "supportsAnomalyOverTime": "string",
    "supportsClusterInsights": "string",
    "supportsConfusionMatrix": "string",
    "supportsDocumentTextExtractionSampleInsight": "string",
    "supportsForecastAccuracy": "string",
    "supportsForecastVsActual": "string",
    "supportsImageActivationMaps": "string",
    "supportsImageEmbedding": "string",
    "supportsLiftChart": "string",
    "supportsPeriodAccuracy": "string",
    "supportsPredictionExplanations": "string",
    "supportsPredictionIntervals": "string",
    "supportsResiduals": "string",
    "supportsRocCurve": "string",
    "supportsSeriesInsights": "string",
    "supportsStability": "string"
  },
  "supportsAccuracyOverTime": true,
  "supportsAdvancedTuning": true,
  "supportsAnomalyAssessment": true,
  "supportsAnomalyOverTime": true,
  "supportsBlending": true,
  "supportsClusterInsights": true,
  "supportsCodeGeneration": true,
  "supportsCoefficients": true,
  "supportsConfusionMatrix": true,
  "supportsDocumentTextExtractionSampleInsight": true,
  "supportsEarlyStopping": true,
  "supportsForecastAccuracy": true,
  "supportsForecastVsActual": true,
  "supportsImageActivationMaps": true,
  "supportsImageEmbedding": true,
  "supportsLiftChart": true,
  "supportsModelPackageExport": true,
  "supportsModelTrainingMetrics": true,
  "supportsMonotonicConstraints": true,
  "supportsNNVisualizations": true,
  "supportsPerLabelMetrics": true,
  "supportsPeriodAccuracy": true,
  "supportsPredictionExplanations": true,
  "supportsPredictionIntervals": true,
  "supportsResiduals": true,
  "supportsRocCurve": true,
  "supportsSeriesInsights": true,
  "supportsShap": true,
  "supportsStability": true
}

Properties¶

Name	Type	Required	Description
eligibleForPrime	boolean	true	`True` if the model is eligible for prime. Use GET /api/v2/projects/{projectId}/models/{modelId}/primeInfo/ to request additional details if the model is not eligible.
hasParameters	boolean	true	`True` if the model has parameters that can be retrieved. Use GET /api/v2/projects/{projectId}/models/{modelId}/parameters/ to retrieve the model parameters.
hasWordCloud	boolean	true	True` if the model has word cloud data available. Use GET /api/v2/projects/{projectId}/models/{modelId}/wordCloud/ to retrieve a word cloud.
reasons	Reasons	false	Information on why capability is unsupported for the model.
supportsAccuracyOverTime	boolean	true	`True` if Accuracy Over Time plots can be generated.
supportsAdvancedTuning	boolean	true	`True` if model supports Advanced Tuning.
supportsAnomalyAssessment	boolean	true	`True` if Anomaly Assessment insights can be generated.
supportsAnomalyOverTime	boolean	true	`True` if Anomaly Over Time plots can be generated.
supportsBlending	boolean	true	`True` if the model supports blending. See POST /api/v2/projects/{projectId}/blenderModels/blendCheck/ to check specific blending combinations.
supportsClusterInsights	boolean	true	`True` if Cluster Insights can be generated.
supportsCodeGeneration	boolean	true	`True` if the model supports export of model's source code or compiled Java executable.
supportsCoefficients	boolean	true	`True` if model coefficients are available.
supportsConfusionMatrix	boolean	true	`True` if Confusion Matrix can be generated.
supportsDocumentTextExtractionSampleInsight	boolean	true	`True` if the model has document column(s) and document text extraction samples can be generated.
supportsEarlyStopping	boolean	false	`True` if this is an early stopping tree-based model and number of trained iterations can be retrieved.
supportsForecastAccuracy	boolean	true	`True` if Forecast Accuracy plots can be generated.
supportsForecastVsActual	boolean	true	`True` if Forecast vs Actual plots can be generated.
supportsImageActivationMaps	boolean	true	`True` if the model has image column(s) and activation maps can be generated.
supportsImageEmbedding	boolean	true	`True` if the model has image column(s) and image embeddings can be generated.
supportsLiftChart	boolean	true	`True` if Lift Chart can be generated.
supportsModelPackageExport	boolean	false	`True` if the model can be exported as a model package.
supportsModelTrainingMetrics	boolean	true	When `True` , the model will track and save key training metrics in an effort to communicate model accuracy throughout training, rather than at training completion.
supportsMonotonicConstraints	boolean	true	`True` if the model supports monotonic constraints.
supportsNNVisualizations	boolean	true	`True` if the model supports neuralNetworkVisualizations.
supportsPerLabelMetrics	boolean	true	`True` if the experiment qualifies as a multilabel project.
supportsPeriodAccuracy	boolean	false	`True` if Period Accuracy insights can be generated.
supportsPredictionExplanations	boolean	true	`True` if the model supports Prediction Explanations.
supportsPredictionIntervals	boolean	true	`True` if Prediction Intervals can be computed for predictions generated by this model.
supportsResiduals	boolean	true	When `True`, the model supports residuals and residuals data can be retrieved.
supportsRocCurve	boolean	true	`True` if ROC Curve can be generated.
supportsSeriesInsights	boolean	true	`True` if Series Insights can be generated.
supportsShap	boolean	true	`True` if the model supports Shapley package. i.e. Shapley based feature Importance
supportsStability	boolean	true	`True` if Stability plots can be generated.

ModelDetailsResponse


{
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "dataSelectionMethod": "duration",
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "frozenPct": 0,
  "hasCodegen": true,
  "hasFinetuners": true,
  "icons": 0,
  "id": "string",
  "isAugmented": true,
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isNClustersDynamicallyDetermined": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "lifecycle": {
    "reason": "string",
    "stage": "active"
  },
  "linkFunction": "string",
  "metrics": {},
  "modelCategory": "model",
  "modelFamily": "string",
  "modelFamilyFullName": "string",
  "modelNumber": 0,
  "modelType": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 0,
  "parentModelId": "string",
  "predictionThreshold": 1,
  "predictionThresholdReadOnly": true,
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": 0,
  "samplingMethod": "random",
  "supportsComposableMl": true,
  "supportsMonotonicConstraints": true,
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z"
}

Properties¶

Name	Type	Required	Restrictions	Description
blenderModels	[integer]	true	maxItems: 100	Models that are in the blender.
blueprintId	string	true		The blueprint used to construct the model.
dataSelectionMethod	string	false		Identifies which setting defines the training size of the model when making predictions and scoring. Only used by datetime models.
externalPredictionModel	boolean	true		If the model is an external prediction model.
featurelistId	string,null	true		The ID of the feature list used by the model.
featurelistName	string,null	true		The name of the feature list used by the model. If null, themodel was trained on multiple feature lists.
frozenPct	number,null	true		The training percent used to train the frozen model.
hasCodegen	boolean	true		If the model has a codegen JAR file.
hasFinetuners	boolean	false		Whether a model has fine tuners.
icons	integer,null	true		The icons associated with the model.
id	string	true		The ID of the model.
isAugmented	boolean	false		Whether a model was trained using augmentation.
isBlender	boolean	true		If the model is a blender.
isCustom	boolean	true		If the model contains custom tasks.
isFrozen	boolean	true		Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model.
isNClustersDynamicallyDetermined	boolean	false		Whether number of clusters is dynamically determined. Only valid in unsupervised clustering projects.
isStarred	boolean	true		Indicates whether the model has been starred.
isTrainedIntoHoldout	boolean	true		Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size.
isTrainedIntoValidation	boolean	true		Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size.
isTrainedOnGpu	boolean	true		Whether the model was trained using GPU workers.
isTransparent	boolean	true		If the model is a transparent model with exposed coefficients.
isUserModel	boolean	true		If the model was created with Composable ML.
lifecycle	ModelLifecycle	true		Object returning model lifecycle.
linkFunction	string,null	true		The link function the final modeler uses in the blueprint. If no link function exists, returns null.
metrics	object	true		The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed.
modelCategory	string	true		Indicates the type of model. Returns `prime` for DataRobot Prime models, `blend` for blender models, `combined` for combined models, and `model` for all other models.
modelFamily	string	true		the family model belongs to, e.g. SVM, GBM, etc.
modelFamilyFullName	string	true		The full name of the family that the model belongs to. For e.g., Support Vector Machine, Gradient Boosting Machine, etc.
modelNumber	integer,null	true		The model number from the Leaderboard.
modelType	string	true		Identifies the model (e.g.,`Nystroem Kernel SVM Regressor`).
monotonicDecreasingFeaturelistId	string,null	true		the ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced.
monotonicIncreasingFeaturelistId	string,null	true		the ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced.
nClusters	integer,null	false		The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.
parentModelId	string,null	true		The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise.
predictionThreshold	number	true	maximum: 1 minimum: 0	threshold used for binary classification in predictions.
predictionThresholdReadOnly	boolean	true		indicates whether modification of a predictions threshold is forbidden. Since v2.22 threshold modification is allowed.
processes	[string]	true	maxItems: 100	The list of processes used by the model.
projectId	string	true		The ID of the project to which the model belongs.
samplePct	number,null	true		The percentage of the dataset used in training the model.
samplingMethod	string	false		indicates sampling method used to select training data in datetime models. For row-based project this is the way how requested number of rows are selected.For other projects (duration-based, start/end, project settings) - how specified percent of rows (timeWindowSamplePct) is selected from specified time window.
supportsComposableMl	boolean	true		indicates whether this model is supported in Composable ML.
supportsMonotonicConstraints	boolean	true		whether this model supports enforcing monotonic constraints
timeWindowSamplePct	integer,null	false		An integer between 1 and 99, indicating the percentage of sampling within the time window. The points kept are determined by samplingMethod option. Will be null if no sampling was specified. Only used by datetime models.
trainingDuration	string,null	true		the duration spanned by the dates in the partition column for the data used to train the model
trainingEndDate	string,null(date-time)	true		the end date of the dates in the partition column for the data used to train the model
trainingRowCount	integer,null	true		The number of rows used to train the model.
trainingStartDate	string,null(date-time)	true		the start date of the dates in the partition column for the data used to train the model

Enumerated Values¶

Property	Value
dataSelectionMethod	[`duration`, `rowCount`, `selectedDateRange`, `useProjectSettings`]
modelCategory	[`model`, `prime`, `blend`, `combined`, `incrementalLearning`]
samplingMethod	[`random`, `latest`]

ModelFeatureListResponse


{
  "aPrioriFeatureNames": [
    "string"
  ],
  "featureNames": [
    "string"
  ],
  "knownInAdvanceFeatureNames": [
    "string"
  ]
}

Properties¶

Name	Type	Required	Description
aPrioriFeatureNames	[string]	true	(Deprecated in version v2.11) Renamed to `knownInAdvanceFeatureNames`. This parameter always has the same value as `knownInAdvanceFeatureNames` and will be removed in a future release.
featureNames	[string]	true	An array of the names of all features used by the specified model.
knownInAdvanceFeatureNames	[string]	true	An array of the names of time series known-in-advance features used by the specified model.

ModelJobResponse


{
  "blueprintId": "string",
  "featurelistId": "string",
  "id": "string",
  "isBlocked": true,
  "isTrainedOnGpu": true,
  "modelCategory": "model",
  "modelId": "string",
  "modelType": "string",
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": 0,
  "status": "queue"
}

Properties¶

Name	Type	Required	Description
blueprintId	string	true	The blueprint used by the model - note that this is not an ObjectId.
featurelistId	string	true	The ID of the featurelist the model is using.
id	string	true	The job ID.
isBlocked	boolean	true	True if a job is waiting for its dependencies to be resolved first.
isTrainedOnGpu	boolean	false	True if the job was trained using GPU capabilities
modelCategory	string	true	Indicates what kind of model this is. Will be `combined` for combined models.
modelId	string	true	The ID of the model
modelType	string	true	The type of model used by the job.
processes	[string]	true	List of processes the modeling job includes
projectId	string	true	The project the job belongs to.
samplePct	number	false	The percentage of the dataset the job is using.
status	string	true	The status of the job.

Enumerated Values¶

Property	Value
modelCategory	[`model`, `prime`, `blend`]
status	[`queue`, `inprogress`, `error`, `ABORTED`, `COMPLETED`]

ModelLifecycle


{
  "reason": "string",
  "stage": "active"
}

Object returning model lifecycle.

Properties¶

Name	Type	Required	Restrictions	Description
reason	string,null	true		Reason for lifecycle stage. None if model is active.
stage	string	true		Model lifecycle stage.

Enumerated Values¶

Property	Value
stage	[`active`, `deprecated`, `disabled`]

ModelParametersRetrieveResponse


{
  "derivedFeatures": [
    {
      "coefficient": 0,
      "derivedFeature": "string",
      "originalFeature": "string",
      "stageCoefficients": [
        {
          "coefficient": 0,
          "stage": "string"
        }
      ],
      "transformations": [
        {
          "name": "string",
          "value": "string"
        }
      ],
      "type": "string"
    }
  ],
  "parameters": [
    {
      "name": "string",
      "value": "string"
    }
  ]
}

Properties¶

Name	Type	Required	Restrictions	Description
derivedFeatures	[DerivedFeatures]	true		An array of preprocessing information about derived features used in the model.
parameters	[Parameters]	true		An array of parameters that are related to the whole model.

ModelRecordResponse


{
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "frozenPct": 0,
  "hasCodegen": true,
  "icons": 0,
  "id": "string",
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "metrics": {},
  "modelCategory": "model",
  "modelFamily": "string",
  "modelNumber": 0,
  "modelType": "string",
  "parentModelId": "string",
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": 0,
  "trainingRowCount": 0
}

Properties¶

Name	Type	Required	Restrictions	Description
blenderModels	[integer]	true	maxItems: 100	Models that are in the blender.
blueprintId	string	true		The blueprint used to construct the model.
externalPredictionModel	boolean	true		If the model is an external prediction model.
featurelistId	string,null	true		The ID of the feature list used by the model.
featurelistName	string,null	true		The name of the feature list used by the model. If null, themodel was trained on multiple feature lists.
frozenPct	number,null	true		The training percent used to train the frozen model.
hasCodegen	boolean	true		If the model has a codegen JAR file.
icons	integer,null	true		The icons associated with the model.
id	string	true		The ID of the model.
isBlender	boolean	true		If the model is a blender.
isCustom	boolean	true		If the model contains custom tasks.
isFrozen	boolean	true		Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model.
isStarred	boolean	true		Indicates whether the model has been starred.
isTrainedIntoHoldout	boolean	true		Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size.
isTrainedIntoValidation	boolean	true		Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size.
isTrainedOnGpu	boolean	true		Whether the model was trained using GPU workers.
isTransparent	boolean	true		If the model is a transparent model with exposed coefficients.
isUserModel	boolean	true		If the model was created with Composable ML.
metrics	object	true		The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed.
modelCategory	string	true		Indicates the type of model. Returns `prime` for DataRobot Prime models, `blend` for blender models, `combined` for combined models, and `model` for all other models.
modelFamily	string	true		The full name of the family that the model belongs to (e.g., Support Vector Machine, Gradient Boosting Machine, etc.).
modelNumber	integer,null	true		The model number from the Leaderboard.
modelType	string	true		Identifies the model (e.g.,`Nystroem Kernel SVM Regressor`).
parentModelId	string,null	true		The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise.
processes	[string]	true	maxItems: 100	The list of processes used by the model.
projectId	string	true		The ID of the project to which the model belongs.
samplePct	number,null	true		The percentage of the dataset used in training the model.
trainingRowCount	integer,null	true		The number of rows used to train the model.

Enumerated Values¶

Property	Value
modelCategory	[`model`, `prime`, `blend`, `combined`, `incrementalLearning`]

ModelRecordsResponse


{
  "count": 0,
  "data": [
    {
      "blenderModels": [
        0
      ],
      "blueprintId": "string",
      "externalPredictionModel": true,
      "featurelistId": "string",
      "featurelistName": "string",
      "frozenPct": 0,
      "hasCodegen": true,
      "icons": 0,
      "id": "string",
      "isBlender": true,
      "isCustom": true,
      "isFrozen": true,
      "isStarred": true,
      "isTrainedIntoHoldout": true,
      "isTrainedIntoValidation": true,
      "isTrainedOnGpu": true,
      "isTransparent": true,
      "isUserModel": true,
      "metrics": {},
      "modelCategory": "model",
      "modelFamily": "string",
      "modelNumber": 0,
      "modelType": "string",
      "parentModelId": "string",
      "processes": [
        "string"
      ],
      "projectId": "string",
      "samplePct": 0,
      "trainingRowCount": 0
    }
  ],
  "next": "string",
  "previous": "string",
  "totalCount": 0
}

Properties¶

Name	Type	Required	Restrictions	Description
count	integer	true	minimum: 0	The number of models returned on this page.
data	[oneOf]	true		Model records.

oneOf

Name	Type	Required	Restrictions	Description
» anonymous	ModelRecordResponse	false		none

xor

Name	Type	Required	Restrictions	Description
» anonymous	DatetimeModelRecordResponse	false		none

xor

Name	Type	Required	Restrictions	Description
» anonymous	UnsupervisedClusteringModelRecordResponse	false		none

continued

Name	Type	Required	Restrictions	Description
next	string,null	true		A URL pointing to the next page (if `null`, there is no next page).
previous	string,null	true		A URL pointing to the previous page (if `null`, there is no previous page).
totalCount	integer	true	minimum: 0	Total number of models after filters applied.

ModelRetrainResponse


{
  "message": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
message	string	true		any extended message to include about the result. For example, if a job is submitted that is a duplicate of a job that has already been added to the queue, the message will mention that no new job was created.

ModelUpdate


{
  "isStarred": true,
  "predictionThreshold": 1
}

Properties¶

Name	Type	Required	Restrictions	Description
isStarred	boolean	false		Mark model either as starred or unstarred.
predictionThreshold	number	false	maximum: 1 minimum: 0	Threshold used for binary classification in predictions. Default value is 0.5.

ModelingJobListResponse


{
  "data": [
    {
      "blueprintId": "string",
      "featurelistId": "string",
      "id": "string",
      "isBlocked": true,
      "isTrainedOnGpu": true,
      "modelCategory": "model",
      "modelId": "string",
      "modelType": "string",
      "processes": [
        "string"
      ],
      "projectId": "string",
      "samplePct": 0,
      "status": "queue"
    }
  ]
}

Properties¶

Name	Type	Required	Restrictions	Description
data	[ModelJobResponse]	true		List of modeling jobs.

NumIterationsTrainedData


{
  "numIterations": 0,
  "stage": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
numIterations	integer	true	minimum: 0	The number of iterations run in this stage of modeling.
stage	string,null	true		Modeling stage or None if it is a single-stage model

NumIterationsTrainedResponse


{
  "data": [
    {
      "numIterations": 0,
      "stage": "string"
    }
  ],
  "modelId": "string",
  "projectId": "string"
}

Properties¶

Name	Type	Required	Description
data	[NumIterationsTrainedData]	true	Number of estimators or iterations for a single model stage
modelId	string	true	The model ID
projectId	string	true	The project ID

OneMessageInfo


{
  "additionalInfo": [
    "string"
  ],
  "messageLevel": "CRITICAL",
  "messageText": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
additionalInfo	[string]	false	maxItems: 50	Zero or more text strings for secondary display after user clicks for more information.
messageLevel	string	true		Message severity level.
messageText	string	true	maxLength: 500 minLength: 1 minLength: 1	Text for primary display in UI.

Enumerated Values¶

Property	Value
messageLevel	[`CRITICAL`, `INFORMATIONAL`, `NO_ISSUES`, `WARNING`]

Parameters


{
  "name": "string",
  "value": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
name	string	true		The name of the parameter identifying what it means for the model, e.g. "Intercept".
value	string	true		The value of the parameter.

ParetoFrontResponse


{
  "errorMetric": "string",
  "hyperparameters": {
    "buildingBlocks": {},
    "errorMetric": "string",
    "maxGenerations": 32,
    "numThreads": 0,
    "priorSolutions": [
      "string"
    ],
    "randomSeed": 0,
    "splitMode": "custom",
    "syncMigrations": true,
    "targetExpressionFormat": "None",
    "targetExpressionString": "string",
    "timeoutSec": 0,
    "trainingFraction": 1,
    "trainingSplitExpr": "string",
    "validationFraction": 1,
    "validationSplitExpr": "string",
    "weightExpr": "string"
  },
  "projectId": "string",
  "solutions": [
    {
      "bestModel": true,
      "complexity": 0,
      "error": 0,
      "eureqaSolutionId": "string",
      "expression": "string",
      "expressionAnnotated": "string"
    }
  ],
  "targetType": "Regression"
}

Properties¶

Name	Type	Required	Description
errorMetric	string	true	The Eureqa error metric identifier used to compute error metrics for this search. Note that Eureqa error metrics do not correspond 1:1 with DataRobot error metrics - the available metrics are not the same, and even equivalent metrics may be computed slightly differently.
hyperparameters	HyperparametersResponse	true	The hyperparameters used by this run of the Eureqa blueprint.
projectId	string	true	The project ID of the Eureqa model.
solutions	[SolutionResponse]	true	The Eureqa model solutions.
targetType	string	true	The type of the target variable.

Enumerated Values¶

Property	Value
targetType	[`Regression`, `Binary`]

PerFeatureMissingReport


{
  "feature": "string",
  "missingCount": 0,
  "missingPercentage": 1,
  "tasks": {
    "property1": {
      "descriptions": [
        "string"
      ],
      "name": "string"
    },
    "property2": {
      "descriptions": [
        "string"
      ],
      "name": "string"
    }
  },
  "type": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
feature	string	true		The name of the feature
missingCount	integer	true		The number of missing values in the training data
missingPercentage	number	true	maximum: 1 minimum: 0	The percentage of missing values in the training data
tasks	object	true		Information on individual tasks of the model which were used to process the feature. The names of properties will be task ids (which correspond to the ids used in the blueprint chart endpoints like GET /api/v2/projects/{projectId}/blueprints/{blueprintId}/blueprintChart/) The corresponding value for each task will be of the form `task` described.
» additionalProperties	PerFeatureTaskMissingReport	false		none
type	string	true		The type of the feature, e.g. `Categorical` or `Numeric`

PerFeatureTaskMissingReport


{
  "descriptions": [
    "string"
  ],
  "name": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
descriptions	[string]	true		Human readable aggregated information about how the task handles missing values. The following descriptions may be present: what value is imputed for missing values, whether the feature being missing is treated as a feature by the task, whether missing values are treated as infrequent values, whether infrequent values are treated as missing values, and whether missing values are ignored.
name	string	true		Task name, e.g. 'Ordinal encoding of categorical variables'

PlotDataResponse


{
  "actual": 0,
  "predicted": 0,
  "row": 0
}

Properties¶

Name	Type	Required	Description
actual	number	true	The actual value of the target variable for the specified row.
predicted	number	true	The predicted value of the target by the solution for the specified row.
row	integer	true	The row number from the raw source data. Used as the X axis for the plot when rendered in the web application.

PredictionIntervalsCreate


{
  "percentiles": [
    100
  ]
}

Properties¶

Name	Type	Required	Restrictions	Description
percentiles	[integer]	true	maxItems: 1 minItems: 1	The list of prediction intervals percentiles to calculate. Currently we only allow requesting one interval at a time.

PredictionIntervalsCreateResponse


{
  "message": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
message	string	true		Any extended message to include about the result. For example, if a job is submitted that is a duplicate of a job that has already been added to the queue, the message will mention that no new job was created.

PredictionIntervalsListResponse


{
  "count": 0,
  "data": [
    100
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Properties¶

Name	Type	Required	Description
count	integer	false	Number of items returned on this page.
data	[integer]	true	A descending-ordered array of already-calculated prediction intervals percentiles.
next	string,null(uri)	true	URL pointing to the next page (if null, there is no next page).
previous	string,null(uri)	true	URL pointing to the previous page (if null, there is no previous page).
totalCount	integer	true	The total number of items across all pages.

PrepareForDeployment


{
  "modelId": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
modelId	string	true		The model to prepare for deployment.

PrimeFileCreate


{
  "language": "Python",
  "modelId": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
language	string	true		The desired language of the generated code
modelId	string	true		the Prime model to generate code for

Enumerated Values¶

Property	Value
language	[`Python`, `Java`]

PrimeFileListResponse


{
  "count": 0,
  "data": [
    {
      "id": "string",
      "isValid": true,
      "language": "Python",
      "modelId": "string",
      "parentModelId": "string",
      "projectId": "string",
      "rulesetId": 0
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Properties¶

Name	Type	Required	Description
count	integer	true	number of items returned on this page
data	[PrimeFileResponse]	true	each has the same schema as if retrieving the file individually from GET /api/v2/projects/(projectId)/primeFiles/(primeFileId)/.
next	string,null(uri)	true	URL pointing to the next page (if null, there is no next page)
previous	string,null(uri)	true	URL pointing to the previous page (if null, there is no previous page)

PrimeFileResponse


{
  "id": "string",
  "isValid": true,
  "language": "Python",
  "modelId": "string",
  "parentModelId": "string",
  "projectId": "string",
  "rulesetId": 0
}

Properties¶

Name	Type	Required	Description
id	string	true	the ID of the file
isValid	boolean	true	whether the code passed basic validation checks
language	string	true	the language the code is written in (e.g. Python
modelId	string	true	the Id of the Prime model
parentModelId	string	true	the ID of the model this code approximates
projectId	string	true	the ID of the project the file belongs to
rulesetId	integer	true	the ID of the ruleset this code uses to approximate the parent model

Enumerated Values¶

Property	Value
language	[`Python`, `Java`]

PrimeInfoRetrieveResponse


{
  "canMakePrime": true,
  "message": "string",
  "messageId": 0
}

Properties¶

Name	Type	Required	Description
canMakePrime	boolean	true	Indicating whether the requested model is a valid input for creating a Prime mode
message	string	true	May contain details about why a model is not eligible for DataRobotPrime
messageId	integer	true	An error code representing the reason the model cannot be approximated with DataRobot Prime; 0 for eligible models

PrimeModelCreatePayload


{
  "parentModelId": "string",
  "rulesetId": 0
}

Properties¶

Name	Type	Required	Restrictions	Description
parentModelId	string	true		the model being approximated
rulesetId	integer	true		the ID of the ruleset to use

PrimeModelDetailsRetrieveResponse


{
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "dataSelectionMethod": "duration",
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "frozenPct": 0,
  "hasCodegen": true,
  "hasFinetuners": true,
  "icons": 0,
  "id": "string",
  "isAugmented": true,
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isNClustersDynamicallyDetermined": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "lifecycle": {
    "reason": "string",
    "stage": "active"
  },
  "linkFunction": "string",
  "metrics": {},
  "modelCategory": "model",
  "modelFamily": "string",
  "modelFamilyFullName": "string",
  "modelNumber": 0,
  "modelType": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 0,
  "parentModelId": "string",
  "predictionThreshold": 1,
  "predictionThresholdReadOnly": true,
  "processes": [
    "string"
  ],
  "projectId": "string",
  "ruleCount": 0,
  "rulesetId": 0,
  "samplePct": 0,
  "samplingMethod": "random",
  "score": 0,
  "supportsComposableMl": true,
  "supportsMonotonicConstraints": true,
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z"
}

Properties¶

Name	Type	Required	Restrictions	Description
blenderModels	[integer]	true	maxItems: 100	Models that are in the blender.
blueprintId	string	true		The blueprint used to construct the model.
dataSelectionMethod	string	false		Identifies which setting defines the training size of the model when making predictions and scoring. Only used by datetime models.
externalPredictionModel	boolean	true		If the model is an external prediction model.
featurelistId	string,null	true		The ID of the feature list used by the model.
featurelistName	string,null	true		The name of the feature list used by the model. If null, themodel was trained on multiple feature lists.
frozenPct	number,null	true		The training percent used to train the frozen model.
hasCodegen	boolean	true		If the model has a codegen JAR file.
hasFinetuners	boolean	false		Whether a model has fine tuners.
icons	integer,null	true		The icons associated with the model.
id	string	true		The ID of the model.
isAugmented	boolean	false		Whether a model was trained using augmentation.
isBlender	boolean	true		If the model is a blender.
isCustom	boolean	true		If the model contains custom tasks.
isFrozen	boolean	true		Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model.
isNClustersDynamicallyDetermined	boolean	false		Whether number of clusters is dynamically determined. Only valid in unsupervised clustering projects.
isStarred	boolean	true		Indicates whether the model has been starred.
isTrainedIntoHoldout	boolean	true		Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size.
isTrainedIntoValidation	boolean	true		Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size.
isTrainedOnGpu	boolean	true		Whether the model was trained using GPU workers.
isTransparent	boolean	true		If the model is a transparent model with exposed coefficients.
isUserModel	boolean	true		If the model was created with Composable ML.
lifecycle	ModelLifecycle	true		Object returning model lifecycle.
linkFunction	string,null	true		The link function the final modeler uses in the blueprint. If no link function exists, returns null.
metrics	object	true		The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed.
modelCategory	string	true		Indicates the type of model. Returns `prime` for DataRobot Prime models, `blend` for blender models, `combined` for combined models, and `model` for all other models.
modelFamily	string	true		the family model belongs to, e.g. SVM, GBM, etc.
modelFamilyFullName	string	true		The full name of the family that the model belongs to. For e.g., Support Vector Machine, Gradient Boosting Machine, etc.
modelNumber	integer,null	true		The model number from the Leaderboard.
modelType	string	true		Identifies the model (e.g.,`Nystroem Kernel SVM Regressor`).
monotonicDecreasingFeaturelistId	string,null	true		the ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced.
monotonicIncreasingFeaturelistId	string,null	true		the ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced.
nClusters	integer,null	false		The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.
parentModelId	string,null	true		The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise.
predictionThreshold	number	true	maximum: 1 minimum: 0	threshold used for binary classification in predictions.
predictionThresholdReadOnly	boolean	true		indicates whether modification of a predictions threshold is forbidden. Since v2.22 threshold modification is allowed.
processes	[string]	true	maxItems: 100	The list of processes used by the model.
projectId	string	true		The ID of the project to which the model belongs.
ruleCount	integer	true		the number of rules used to create this model
rulesetId	integer	true		the ID of the ruleset this model uses
samplePct	number,null	true		The percentage of the dataset used in training the model.
samplingMethod	string	false		indicates sampling method used to select training data in datetime models. For row-based project this is the way how requested number of rows are selected.For other projects (duration-based, start/end, project settings) - how specified percent of rows (timeWindowSamplePct) is selected from specified time window.
score	number	true		the validation score of the models ruleset
supportsComposableMl	boolean	true		indicates whether this model is supported in Composable ML.
supportsMonotonicConstraints	boolean	true		whether this model supports enforcing monotonic constraints
timeWindowSamplePct	integer,null	false		An integer between 1 and 99, indicating the percentage of sampling within the time window. The points kept are determined by samplingMethod option. Will be null if no sampling was specified. Only used by datetime models.
trainingDuration	string,null	true		the duration spanned by the dates in the partition column for the data used to train the model
trainingEndDate	string,null(date-time)	true		the end date of the dates in the partition column for the data used to train the model
trainingRowCount	integer,null	true		The number of rows used to train the model.
trainingStartDate	string,null(date-time)	true		the start date of the dates in the partition column for the data used to train the model

Enumerated Values¶

Property	Value
dataSelectionMethod	[`duration`, `rowCount`, `selectedDateRange`, `useProjectSettings`]
modelCategory	[`model`, `prime`, `blend`, `combined`, `incrementalLearning`]
samplingMethod	[`random`, `latest`]

PrimeModelListResponse


{
  "count": 0,
  "data": [
    {
      "blenderModels": [
        0
      ],
      "blueprintId": "string",
      "dataSelectionMethod": "duration",
      "externalPredictionModel": true,
      "featurelistId": "string",
      "featurelistName": "string",
      "frozenPct": 0,
      "hasCodegen": true,
      "hasFinetuners": true,
      "icons": 0,
      "id": "string",
      "isAugmented": true,
      "isBlender": true,
      "isCustom": true,
      "isFrozen": true,
      "isNClustersDynamicallyDetermined": true,
      "isStarred": true,
      "isTrainedIntoHoldout": true,
      "isTrainedIntoValidation": true,
      "isTrainedOnGpu": true,
      "isTransparent": true,
      "isUserModel": true,
      "lifecycle": {
        "reason": "string",
        "stage": "active"
      },
      "linkFunction": "string",
      "metrics": {},
      "modelCategory": "model",
      "modelFamily": "string",
      "modelFamilyFullName": "string",
      "modelNumber": 0,
      "modelType": "string",
      "monotonicDecreasingFeaturelistId": "string",
      "monotonicIncreasingFeaturelistId": "string",
      "nClusters": 0,
      "parentModelId": "string",
      "predictionThreshold": 1,
      "predictionThresholdReadOnly": true,
      "processes": [
        "string"
      ],
      "projectId": "string",
      "ruleCount": 0,
      "rulesetId": 0,
      "samplePct": 0,
      "samplingMethod": "random",
      "score": 0,
      "supportsComposableMl": true,
      "supportsMonotonicConstraints": true,
      "timeWindowSamplePct": 99,
      "trainingDuration": "string",
      "trainingEndDate": "2019-08-24T14:15:22Z",
      "trainingRowCount": 0,
      "trainingStartDate": "2019-08-24T14:15:22Z"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Properties¶

Name	Type	Required	Description
count	integer	true	number of items returned on this page
data	[PrimeModelDetailsRetrieveResponse]	true	each has the same schema as if retrieving the file individually from GET /api/v2/projects/(projectId)/primeFiles/(primeFileId)/.
next	string,null(uri)	true	URL pointing to the next page (if null, there is no next page)
previous	string,null(uri)	true	URL pointing to the previous page (if null, there is no previous page)

PrimeRulesetsCreatePayload

{}

Properties¶

None

PrimeRulesetsListResponse


{
  "modelId": "string",
  "parentModelId": "string",
  "projectId": "string",
  "ruleCount": 0,
  "rulesetId": 0,
  "score": 0
}

Properties¶

Name	Type	Required	Description
modelId	string	true	the ID of the Prime model using this ruleset (if it exists) or null
parentModelId	string	true	ID of the model this ruleset approximates
projectId	string	true	the project this ruleset belongs to
ruleCount	integer	true	the number of rules used by this ruleset
rulesetId	integer	true	the ID of the ruleset
score	number	true	the validation score of the ruleset

Reasons


{
  "supportsAccuracyOverTime": "string",
  "supportsAnomalyAssessment": "string",
  "supportsAnomalyOverTime": "string",
  "supportsClusterInsights": "string",
  "supportsConfusionMatrix": "string",
  "supportsDocumentTextExtractionSampleInsight": "string",
  "supportsForecastAccuracy": "string",
  "supportsForecastVsActual": "string",
  "supportsImageActivationMaps": "string",
  "supportsImageEmbedding": "string",
  "supportsLiftChart": "string",
  "supportsPeriodAccuracy": "string",
  "supportsPredictionExplanations": "string",
  "supportsPredictionIntervals": "string",
  "supportsResiduals": "string",
  "supportsRocCurve": "string",
  "supportsSeriesInsights": "string",
  "supportsStability": "string"
}

Information on why capability is unsupported for the model.

Properties¶

Name	Type	Required	Description
supportsAccuracyOverTime	string	false	If present, the reason why Accuracy Over Time plots cannot be generated for the model.
supportsAnomalyAssessment	string	false	If present, the reason why the Anomaly Assessment insight cannot be generated for the model.
supportsAnomalyOverTime	string	false	If present, the reason why Anomaly Over Time plots cannot be generated for the model.
supportsClusterInsights	string	false	If present, the reason why Cluster Insights cannot be generated for the model.
supportsConfusionMatrix	string	false	If present, the reason why Confusion Matrix cannot be generated for the model. There are some cases where Confusion Matrix is available but it was calculated using stacked predictions or in-sample predictions.
supportsDocumentTextExtractionSampleInsight	string	false	If present, the reason document text extraction sample insights are not supported for the model.
supportsForecastAccuracy	string	false	If present, the reason why Forecast Accuracy plots cannot be generated for the model.
supportsForecastVsActual	string	false	If present, the reason why Forecast vs Actual plots cannot be generated for the model.
supportsImageActivationMaps	string	false	If present, the reason image activation maps are not supported for the model.
supportsImageEmbedding	string	false	If present, the reason image embeddings are not supported for the model.
supportsLiftChart	string	false	If present, the reason why Lift Chart cannot be generated for the model. There are some cases where Lift Chart is available but it was calculated using stacked predictions or in-sample predictions.
supportsPeriodAccuracy	string	false	If present, the reason why Period Accuracy insights cannot be generated for the model.
supportsPredictionExplanations	string	false	If present, the reason why Prediction Explanations cannot be computed for the model.
supportsPredictionIntervals	string	false	If present, the reason why Prediction Intervals cannot be computed for the model.
supportsResiduals	string	false	If present, the reason why residuals are not available for the model. There are some cases where Residuals are available but they were calculated using stacked predictions or in-sample predictions.
supportsRocCurve	string	false	If present, the reason why ROC Curve cannot be generated for the model. There are some cases where ROC Curve is available but it was calculated using stacked predictions or in-sample predictions.
supportsSeriesInsights	string	false	If present, the reason why Series Insights cannot be generated for the model.
supportsStability	string	false	If present, the reason why Stability plots cannot be generated for the model.

RecommendedModelResponse


{
  "modelId": "string",
  "recommendationType": "MOSTACCURATE"
}

Properties¶

Name	Type	Required	Restrictions	Description
modelId	string	true		the ID of the recommended model
recommendationType	string	true		the type of model recommendation

Enumerated Values¶

Property	Value
recommendationType	[`MOSTACCURATE`, `LIMITEDACCURATE`, `FASTACCURATE`, `RECOMMENDEDFORDEPLOYMENT`, `PREPAREDFORDEPLOYMENT`]

RetrainDatetimeModel


{
  "featurelistId": "string",
  "modelId": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 2,
  "samplingMethod": "random",
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z",
  "useProjectSettings": true
}

Properties¶

Name	Type	Required	Restrictions	Description
featurelistId	string	false		If specified, the new model will be trained using this featurelist. Otherwise, the model will be trained on the same feature list as the source model.
modelId	string	true		The ID of an existing model to use as the source for the training parameters.
monotonicDecreasingFeaturelistId	string,null	false		The ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If `null`, no such constraints are enforced.
monotonicIncreasingFeaturelistId	string,null	false		The ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If `null`, no such constraints are enforced.
nClusters	integer	false	maximum: 100 minimum: 2	The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.
samplingMethod	string	false		Defines how training data is selected if subsampling is used (e.g., if `timeWindowSamplePct` is specified). Can be either `random` or `latest`. If omitted, defaults to `latest` if `trainingRowCount` is used and `random` for other cases (e.g., if `trainingDuration` or `useProjectSettings` is specified). May only be specified for OTV projects.
timeWindowSamplePct	integer	false		An integer between 1 and 99 indicating the percentage of sampling within the time window. The points kept are determined by the value provided for the `samplingMethod` option. If specified, `trainingRowCount` may not be specified, and the specified model must either be a duration or selectedDateRange model, or one of `trainingDuration` or `trainingStartDate` and `trainingEndDate` must be specified.
trainingDuration	string(duration)	false		A duration string representing the training duration to use for training the new model. If specified, the model will be trained using the specified training duration. Otherwise, the original model's duration will be used. Only one of `trainingRowCount`, `trainingDuration`, `trainingStartDate` and `trainingEndDate`, or `useProjectSettings` may be specified.
trainingEndDate	string(date-time)	false		A datetime string representing the end date of the data to use for training this model. Note that only one of `trainingDuration` or `trainingRowCount` or `trainingStartDate` and `trainingEndDate` should be specified. If `trainingStartDate` and `trainingEndDate` are specified, the source model must be frozen.
trainingRowCount	integer	false		The number of rows of data that should be used to train the model. If not specified, the original model's row count will be used. Only one of `trainingRowCount`, `trainingDuration`, `trainingStartDate` and `trainingEndDate`, or `useProjectSettings` may be specified.
trainingStartDate	string(date-time)	false		A datetime string representing the start date of the data to use for training this model. Note that only one of `trainingDuration` or `trainingRowCount` or `trainingStartDate` and `trainingEndDate` should be specified. If `trainingStartDate` and `trainingEndDate` are specified, the source model must be frozen.
useProjectSettings	boolean	false		If `True`, the model will be trained using the previously-specified custom backtest training settings. Only one of `trainingRowCount`, `trainingDuration`, `trainingStartDate` and `trainingEndDate`, or `useProjectSettings` may be specified.

Enumerated Values¶

Property	Value
samplingMethod	[`random`, `latest`]

RetrainModel


{
  "featurelistId": "string",
  "modelId": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 2,
  "samplePct": 100,
  "scoringType": "validation",
  "trainingRowCount": 0
}

Properties¶

Name	Type	Required	Restrictions	Description
featurelistId	string	false		If specified, the model will be trained using that featurelist, otherwise the model will be trained on the same feature list as before.
modelId	string	true		The model to be retrained
monotonicDecreasingFeaturelistId	string,null	false		The ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced.
monotonicIncreasingFeaturelistId	string,null	false		The ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced.
nClusters	integer	false	maximum: 100 minimum: 2	The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.
samplePct	number	false	maximum: 100	The percentage of the dataset to use to use to train the model. The specified percentage should be between 0 and 100. If not specified, original model sample percent will be used.
scoringType	string	false		Validation is available for any partitioning. If the project uses cross validation, `crossValidation` may be used to indicate that all available training/validation combinations should be used.
trainingRowCount	integer	false		The number of rows to use to train the model. If not specified, original model training row count will be used.

Enumerated Values¶

Property	Value
scoringType	[`validation`, `crossValidation`]

RuleFitCodeFileCreate


{
  "language": "Python",
  "modelId": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
language	string	true		The desired language of the generated code
modelId	string	true		the RuleFit model to generate code for

Enumerated Values¶

Property	Value
language	[`Python`, `Java`]

RuleFitCodeFileListResponse


{
  "count": 0,
  "data": [
    {
      "id": "string",
      "isValid": true,
      "language": "Python",
      "modelId": "string",
      "projectId": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Properties¶

Name	Type	Required	Description
count	integer	true	number of items returned on this page
data	[RuleFitCodeFileResponse]	true	each has the same schema as if retrieving the file individually from GET /api/v2/projects/(projectId)/ruleFitFiles/(ruleFitFileId)/.
next	string,null(uri)	true	URL pointing to the next page (if null, there is no next page)
previous	string,null(uri)	true	URL pointing to the previous page (if null, there is no previous page)

RuleFitCodeFileResponse


{
  "id": "string",
  "isValid": true,
  "language": "Python",
  "modelId": "string",
  "projectId": "string"
}

Properties¶

Name	Type	Required	Description
id	string	true	the ID of the file
isValid	boolean	true	whether the code passed basic validation checks
language	string	true	the language the code is written in (e.g. Python
modelId	string	true	the ID of the RuleFit model
projectId	string	true	the ID of the project the file belongs to

Enumerated Values¶

Property	Value
language	[`Python`, `Java`]

SegmentChampionModelUpdate


{
  "clone": false,
  "modelId": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
clone	boolean	false		Clone current combined model and assign champion to the new combined model.
modelId	string	true		The ID of segment champion model.

SegmentChampionModelUpdateResponse


{
  "combinedModelId": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
combinedModelId	string	true		The ID of the combined model that has been updated.

SegmentProjectModelResponse


{
  "modelId": "string",
  "projectId": "string",
  "segment": "string"
}

Properties¶

Name	Type	Required	Description
modelId	string,null	true	ID of segment champion model.
projectId	string,null	true	ID of the project used for this segment.
segment	string	true	Segment name.

Select


{
  "supportsGridSearch": true,
  "values": [
    "string"
  ]
}

Indicates that the value can be one selected from a list of known values.

Properties¶

Name	Type	Required	Restrictions	Description
supportsGridSearch	boolean	true		When True, Grid Search is supported for this parameter.
values	[string]	true		List of valid values for this field.

SolutionResponse


{
  "bestModel": true,
  "complexity": 0,
  "error": 0,
  "eureqaSolutionId": "string",
  "expression": "string",
  "expressionAnnotated": "string"
}

Properties¶

Name	Type	Required	Description
bestModel	boolean	true	True if this solution generates the best model.
complexity	integer	true	The complexity score for this solution. Complexity score is a function of the mathematical operators used in the current solution. The complexity calculation can be tuned via model hyperparameters.
error	number,null	true	The error for the current solution, as computed by eureqa using the `errorMetric` error metric. None if Eureqa model refitted existing solutions.
eureqaSolutionId	string	true	The ID of the solution.
expression	string	true	The eureqa "solution string". This is a mathematical expression; human-readable but with strict syntax specifications defined by Eureqa.
expressionAnnotated	string	true	The `expression`, rendered with additional tags to assist in automatic parsing.

StageCoefficients


{
  "coefficient": 0,
  "stage": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
coefficient	number	true		The corresponding value of the coefficient for that stage.
stage	string	true		The name of the stage.

TrainDatetimeFrozenModel


{
  "modelId": "string",
  "samplingMethod": "random",
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingEndDate": "2019-08-24T14:15:22Z",
  "trainingRowCount": 0,
  "trainingStartDate": "2019-08-24T14:15:22Z",
  "useProjectSettings": true
}

Properties¶

Name	Type	Required	Description
modelId	string	true	The ID of an existing model to use as the source for the training parameters.
samplingMethod	string	false	Defines how training data is selected if subsampling is used (e.g., if `timeWindowSamplePct` is specified). Can be either `random` or `latest`. If omitted, defaults to `latest` if `trainingRowCount` is used and `random` for other cases (e.g., if `trainingDuration` or `useProjectSettings` is specified). May only be specified for OTV projects.
timeWindowSamplePct	integer	false	An integer between 1 and 99 indicating the percentage of sampling within the time window. The points kept are determined by the value provided for the `samplingMethod` option. If specified, `trainingRowCount` may not be specified, and the specified model must either be a duration or selectedDateRange model, or one of `trainingDuration` or `trainingStartDate` and `trainingEndDate` must be specified.
trainingDuration	string(duration)	false	A duration string representing the training duration for the submitted model. Only one of `trainingDuration`, `trainingRowCount`, `trainingStartDate` and `trainingEndDate`, or `useProjectSettings` may be specified.
trainingEndDate	string(date-time)	false	A datetime string representing the end date of the data to use for training this model. If specified, `trainingStartDate` must also be specified. Only one of `trainingDuration`, `trainingRowCount`, `trainingStartDate` and `trainingEndDate`, or `useProjectSettings` may be specified.
trainingRowCount	integer	false	The number of rows of data that should be used when training this model. Only one of `trainingDuration`, `trainingRowCount`, `trainingStartDate` and `trainingEndDate`, or `useProjectSettings` may be specified.
trainingStartDate	string(date-time)	false	A datetime string representing the start date of the data to use for training this model. If specified, `trainingEndDate` must also be specified. Only one of `trainingDuration`, `trainingRowCount`, `trainingStartDate` and `trainingEndDate`, or `useProjectSettings` may be specified.
useProjectSettings	boolean	false	If `True`, the model will be trained using the previously-specified custom backtest training settings. Only one of `trainingDuration`, `trainingRowCount`, `trainingStartDate` and `trainingEndDate`, or `useProjectSettings` may be specified.

Enumerated Values¶

Property	Value
samplingMethod	[`random`, `latest`]

TrainDatetimeModel


{
  "blueprintId": "string",
  "featurelistId": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 2,
  "samplingMethod": "random",
  "sourceProjectId": "string",
  "timeWindowSamplePct": 99,
  "trainingDuration": "string",
  "trainingRowCount": 0,
  "useProjectSettings": true
}

Properties¶

Name	Type	Required	Restrictions	Description
blueprintId	string	true		The ID of a blueprint to use to generate the model. Allowed blueprints can be retrieved using GET /api/v2/projects/{projectId}/blueprints/ or taken from existing models.
featurelistId	string	false		If specified, the model will be trained using this featurelist. If not specified, the recommended featurelist for the specified blueprint will be used. If there is no recommended featurelist, the project's default will be used.
monotonicDecreasingFeaturelistId	string,null	false		The ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If `null`, no constraints will be enforced. If omitted, the project default is used. May only be specified for OTV projects.
monotonicIncreasingFeaturelistId	string,null	false		The ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If `null`, no constraints will be enforced. If omitted, the project default is used. May only be specified for OTV projects.
nClusters	integer	false	maximum: 100 minimum: 2	The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.
samplingMethod	string	false		Defines how training data is selected if subsampling is used (e.g., if `timeWindowSamplePct` is specified). Can be either `random` or `latest`. If omitted, defaults to `latest` if `trainingRowCount` is used and `random` for other cases (e.g., if `trainingDuration` or `useProjectSettings` is specified). May only be specified for OTV projects.
sourceProjectId	string	false		The project the blueprint comes from. Required only if the `blueprintId` comes from a different project.
timeWindowSamplePct	integer	false		An integer between 1 and 99 indicating the percentage of sampling within the time window. The points kept are determined by the value provided for the `samplingMethod` option. If specified, `trainingRowCount` may not be specified, and the specified model must either be a duration or selectedDateRange model, or one of `trainingDuration` or `trainingStartDate` and `trainingEndDate` must be specified.
trainingDuration	string(duration)	false		A duration string representing the training duration for the submitted model.
trainingRowCount	integer	false		The number of rows of data that should be used when training this model.
useProjectSettings	boolean	false		If `True`, the model will be trained using the previously-specified custom backtest training settings.

Enumerated Values¶

Property	Value
samplingMethod	[`random`, `latest`]

TrainIncrementalLearningModel


{
  "dataStageCompression": "zip",
  "dataStageDelimiter": "string",
  "dataStageEncoding": "UTF-8",
  "dataStageId": "string",
  "dataStageStorageType": "csv",
  "modelId": "string",
  "trainingDataName": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
dataStageCompression	string	false		File compression for the data stage. Only supports CSV storage type.
dataStageDelimiter	string	false		File delimiter for the data stage specified as a string.
dataStageEncoding	string	false		File encoding for the data stage.
dataStageId	string	true		Data stage ID. Data stage must be finalized and not expired.
dataStageStorageType	string	false		File type of the data stage contents.
modelId	string	true		Parent model ID. This model must support incremental learning.
trainingDataName	string	false	maxLength: 500	String identifier for the current iteration.

Enumerated Values¶

Property	Value
dataStageCompression	[`zip`, `bz2`, `gzip`]
dataStageEncoding	[`UTF-8`, `ASCII`, `WINDOWS-1252`]
dataStageStorageType	[`csv`, `parquet`]

TrainModel


{
  "blueprintId": "string",
  "featurelistId": "string",
  "monotonicDecreasingFeaturelistId": "string",
  "monotonicIncreasingFeaturelistId": "string",
  "nClusters": 2,
  "samplePct": 100,
  "scoringType": "validation",
  "sourceProjectId": "string",
  "trainingRowCount": 0
}

Properties¶

Name	Type	Required	Restrictions	Description
blueprintId	string	true		The ID of a blueprint to use to generate the model. Allowed blueprints can be retrieved using GET /api/v2/projects/{projectId}/blueprints/ or taken from existing models.
featurelistId	string	false		If specified, the model will be trained using this featurelist. If not specified, the recommended featurelist for the specified blueprint will be used. If there is no recommended featurelist, the project's default will be used.
monotonicDecreasingFeaturelistId	string,null	false		The ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If `null`, no constraints will be enforced. If omitted, the project default is used.
monotonicIncreasingFeaturelistId	string,null	false		The ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If `null`, no constraints will be enforced. If omitted, the project default is used.
nClusters	integer	false	maximum: 100 minimum: 2	The number of clusters to use in the specified unsupervised clustering model. Only valid in unsupervised clustering projects.
samplePct	number	false	maximum: 100	The percentage of the dataset to use with the model. Only one of `samplePct` and `trainingRowCount` should be specified. The specified percentage should be between 0 and 100.
scoringType	string	false		Validation is available for any partitioning. If the project uses cross validation, `crossValidation` may be used to indicate that all available training/validation combinations should be used.
sourceProjectId	string	false		The project the blueprint comes from. Required only if the `blueprintId` comes from a different project.
trainingRowCount	integer	false		An integer representing the number of rows of the dataset to use with the model. Only one of `samplePct` and `trainingRowCount` should be specified.

Enumerated Values¶

Property	Value
scoringType	[`validation`, `crossValidation`]

TrainingInfoResponse


{
  "holdoutTrainingDuration": "string",
  "holdoutTrainingEndDate": "2019-08-24T14:15:22Z",
  "holdoutTrainingRowCount": 0,
  "holdoutTrainingStartDate": "2019-08-24T14:15:22Z",
  "predictionTrainingDuration": "string",
  "predictionTrainingEndDate": "2019-08-24T14:15:22Z",
  "predictionTrainingRowCount": 0,
  "predictionTrainingStartDate": "2019-08-24T14:15:22Z"
}

holdout and prediction training data details

Properties¶

Name	Type	Required	Description
holdoutTrainingDuration	string(duration)	true	the duration of the data used to train a model to score the holdout
holdoutTrainingEndDate	string(date-time)	true	the end date of the data used to train a model to score the holdout
holdoutTrainingRowCount	integer	true	the number of rows used to train a model to score the holdout
holdoutTrainingStartDate	string(date-time)	true	the start date of data used to train a model to score the holdout
predictionTrainingDuration	string(duration)	true	the duration of the data used to train a model to make predictions
predictionTrainingEndDate	string(date-time)	true	the end date of the data used to train a model to make predictions
predictionTrainingRowCount	integer	true	the number of rows used to train a model to make predictions
predictionTrainingStartDate	string(date-time)	true	the start date of data used to train a model to make predictions

Transformations


{
  "name": "string",
  "value": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
name	string	true		The name of the transformation.
value	string	true		The value used in carrying it out.

TuningParameter


{
  "parameterId": "string",
  "value": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
parameterId	string	true		ID of the parameter whose value to set.
value	any	true		Value for the specified parameter.

oneOf

Name	Type	Required	Restrictions	Description
» anonymous	any	false		none

anyOf

Name	Type	Required	Restrictions	Description
»» anonymous	string	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	integer	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	boolean	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	number	false		none

xor

Name	Type	Required	Restrictions	Description
» anonymous	[anyOf]	false		none

anyOf

Name	Type	Required	Restrictions	Description
»» anonymous	string	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	integer	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	boolean	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	number	false		none

TuningParameters


{
  "constraints": {
    "ascii": {
      "supportsGridSearch": true
    },
    "float": {
      "max": 0,
      "min": 0,
      "supportsGridSearch": true
    },
    "floatList": {
      "maxLength": 0,
      "maxVal": 0,
      "minLength": 0,
      "minVal": 0,
      "supportsGridSearch": true
    },
    "int": {
      "max": 0,
      "min": 0,
      "supportsGridSearch": true
    },
    "intList": {
      "maxLength": 0,
      "maxVal": 0,
      "minLength": 0,
      "minVal": 0,
      "supportsGridSearch": true
    },
    "select": {
      "supportsGridSearch": true,
      "values": [
        "string"
      ]
    },
    "selectgrid": {
      "supportsGridSearch": true,
      "values": [
        "string"
      ]
    },
    "unicode": {
      "supportsGridSearch": true
    }
  },
  "currentValue": "string",
  "defaultValue": "string",
  "parameterId": "string",
  "parameterName": "string",
  "taskName": "string",
  "vertexId": "string"
}

Properties¶

Name	Type	Required	Restrictions	Description
constraints	Constraints	true		Constraints on valid values for this parameter. Note that any of these fields may be omitted but at least one will always be present. The presence of a field indicates that the parameter in question will accept values in the corresponding format.
currentValue	any	true		The single value or list of values of the parameter that were grid searched. Depending on the grid search specification, could be a single fixed value (no grid search), a list of discrete values, or a range.

oneOf

Name	Type	Required	Restrictions	Description
» anonymous	any	false		none

anyOf

Name	Type	Required	Restrictions	Description
»» anonymous	string	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	integer	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	boolean	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	number	false		none

xor

Name	Type	Required	Restrictions	Description
» anonymous	[anyOf]	false		none

anyOf

Name	Type	Required	Restrictions	Description
»» anonymous	string	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	integer	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	boolean	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	number	false		none

continued

Name	Type	Required	Restrictions	Description
defaultValue	any	true		The actual value used to train the model; either the single value of the parameter specified before training, or the best value from the list of grid-searched values (based on `current_value`).

oneOf

Name	Type	Required	Restrictions	Description
» anonymous	any	false		none

anyOf

Name	Type	Required	Restrictions	Description
»» anonymous	string	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	integer	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	boolean	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	number	false		none

xor

Name	Type	Required	Restrictions	Description
» anonymous	[anyOf]	false		none

anyOf

Name	Type	Required	Restrictions	Description
»» anonymous	string	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	integer	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	boolean	false		none

or

Name	Type	Required	Restrictions	Description
»» anonymous	number	false		none

continued

Name	Type	Required	Description
parameterId	string	true	Unique (per-blueprint) identifier of this parameter. This is the identifier used to specify which parameter to tune when make a new advanced tuning request.
parameterName	string	true	Name of the parameter.
taskName	string	true	Human-readable name of the task that this parameter belongs to.
vertexId	string	true	Id of the vertex this parameter belongs to.

UnsupervisedClusteringModelRecordResponse


{
  "blenderModels": [
    0
  ],
  "blueprintId": "string",
  "externalPredictionModel": true,
  "featurelistId": "string",
  "featurelistName": "string",
  "frozenPct": 0,
  "hasCodegen": true,
  "icons": 0,
  "id": "string",
  "isBlender": true,
  "isCustom": true,
  "isFrozen": true,
  "isStarred": true,
  "isTrainedIntoHoldout": true,
  "isTrainedIntoValidation": true,
  "isTrainedOnGpu": true,
  "isTransparent": true,
  "isUserModel": true,
  "metrics": {},
  "modelCategory": "model",
  "modelFamily": "string",
  "modelNumber": 0,
  "modelType": "string",
  "numberOfClusters": 0,
  "parentModelId": "string",
  "processes": [
    "string"
  ],
  "projectId": "string",
  "samplePct": 0,
  "trainingRowCount": 0
}

Properties¶

Name	Type	Required	Restrictions	Description
blenderModels	[integer]	true	maxItems: 100	Models that are in the blender.
blueprintId	string	true		The blueprint used to construct the model.
externalPredictionModel	boolean	true		If the model is an external prediction model.
featurelistId	string,null	true		The ID of the feature list used by the model.
featurelistName	string,null	true		The name of the feature list used by the model. If null, themodel was trained on multiple feature lists.
frozenPct	number,null	true		The training percent used to train the frozen model.
hasCodegen	boolean	true		If the model has a codegen JAR file.
icons	integer,null	true		The icons associated with the model.
id	string	true		The ID of the model.
isBlender	boolean	true		If the model is a blender.
isCustom	boolean	true		If the model contains custom tasks.
isFrozen	boolean	true		Indicates whether the model is frozen, i.e., uses tuning parameters from a parent model.
isStarred	boolean	true		Indicates whether the model has been starred.
isTrainedIntoHoldout	boolean	true		Indicates if model used holdout data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed validation size.
isTrainedIntoValidation	boolean	true		Indicates if model used validation data for training. This can happen for time-aware models using trainingStartDate/trainingEndDate parameters or when the model's training row count was greater than the max allowed training size.
isTrainedOnGpu	boolean	true		Whether the model was trained using GPU workers.
isTransparent	boolean	true		If the model is a transparent model with exposed coefficients.
isUserModel	boolean	true		If the model was created with Composable ML.
metrics	object	true		The performance of the model according to various metrics, where each metric has validation, crossValidation, holdout, and training scores reported, or null if they have not been computed.
modelCategory	string	true		Indicates the type of model. Returns `prime` for DataRobot Prime models, `blend` for blender models, `combined` for combined models, and `model` for all other models.
modelFamily	string	true		The full name of the family that the model belongs to (e.g., Support Vector Machine, Gradient Boosting Machine, etc.).
modelNumber	integer,null	true		The model number from the Leaderboard.
modelType	string	true		Identifies the model (e.g.,`Nystroem Kernel SVM Regressor`).
numberOfClusters	integer,null	true		The number of clusters in the unsupervised clustering model. Only present in unsupervised clustering projects.
parentModelId	string,null	true		The ID of the parent model if the model is frozen or a result of incremental learning. Null otherwise.
processes	[string]	true	maxItems: 100	The list of processes used by the model.
projectId	string	true		The ID of the project to which the model belongs.
samplePct	number,null	true		The percentage of the dataset used in training the model.
trainingRowCount	integer,null	true		The number of rows used to train the model.

Enumerated Values¶

Property	Value
modelCategory	[`model`, `prime`, `blend`, `combined`, `incrementalLearning`]

Was this page helpful?

Great! Let us know what you found helpful.

What can we do to improve the content?

Thanks for your feedback!