Skip to content

On-premise users: click in-app to access the full platform documentation for your version of DataRobot.

Deployments

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

GET /api/v2/deletedDeployments/

List deleted deployments.Only available as part of an enterprise (on-prem) installation. Requires a CAN_DELETE_APP_PROJECTS permission to execute.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deletedDeployments/?offset=0&limit=20 \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
offset query integer true The number of deleted deployments to skip.
limit query integer true The number of deleted deployments to return.

Example responses

200 Response

{
  "count": 0,
  "data": [
    {
      "deletedAt": "2019-08-24T14:15:22Z",
      "id": "string",
      "label": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Responses

Status Meaning Description Schema
200 OK The deleted deployments DeletedDeploymentListResponse

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

BearerAuth

PATCH /api/v2/deletedDeployments/

Permanently erase data for deleted deployments. Only available as part of an on-premise or private/hybrid cloud deployment. Requires a CAN_DELETE_APP_PROJECTS permission to execute.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deletedDeployments/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "action": "PermanentlyErase",
  "deploymentIds": [
    "string"
  ]
}

Parameters

Name In Type Required Description
body body DeploymentPermanentDelete false none

Responses

Status Meaning Description Schema
202 Accepted Job submitted. See Location header. None

Response Headers

Status Header Type Format Description
202 Location string URL for tracking deployment permanently erase job status.

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

BearerAuth

GET /api/v2/deployments/

List deployments a user can view.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/?offset=0&limit=20 \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
offset query integer true The number of deployments to skip. Defaults to 0.
limit query integer true The number of deployments (greater than zero, max 100) to return. Defaults to 20.
orderBy query string false The order to sort the deployments.Defaults to order by deployment last prediction timestamp in descending order.
search query string false Case insensitive search against deployment's label and description.
serviceHealth query array[string] false Filters deployments by their service health status.
modelHealth query array[string] false Filters deployments by their model health status.
accuracyHealth query array[string] false Filters deployments by their accuracy health status.
role query string false Filter deployments to only those that the authenticated user has the specified role for.
status query array[string] false Filters deployments by their status
importance query array[string] false Filters deployments by their importance
lastPredictionTimestampStart query string(date-time) false Only include deployments that have had a prediction request on or after the specified timestamp.
lastPredictionTimestampEnd query string(date-time) false Only include deployments that have had a prediction request before the specified timestamp.
predictionUsageDailyAvgGreaterThan query integer false only include deployments that have had more than the specified number of predictions per day on average over the past week.
predictionUsageDailyAvgLessThan query integer false Only include deployments that have had fewer than the specified number of predictions per day on average over the past week.
defaultPredictionServerId query array[string] false Filter deployments to those whose default prediction server has the specified id.
buildEnvironmentType query array[string] false Filter deployments based on the type of their current model's build environment type.
executionEnvironmentType query array[string] false Filter deployments based on the type of their execution environment.
predictionEnvironmentPlatform query array[string] false Filter deployments based on prediction environment platform
hasDecisionFlow query string false Filter deployments based if it is a decision flow
createdByMe query string false Filter deployments to those created by the current user.

Enumerated Values

Parameter Value
orderBy [label, -label, serviceHealth, -serviceHealth, modelHealth, -modelHealth, accuracyHealth, -accuracyHealth, recentPredictions, -recentPredictions, lastPredictionTimestamp, -lastPredictionTimestamp, currentModelDeployedTimestamp, -currentModelDeployedTimestamp, createdAtTimestamp, -createdAtTimestamp, importance, -importance, fairnessHealth, -fairnessHealth, customMetricsHealth, -customMetricsHealth, actualsTimelinessHealth, -actualsTimelinessHealth, predictionsTimelinessHealth, -predictionsTimelinessHealth]
serviceHealth [failing, not_started, passing, unavailable, unknown, warning]
modelHealth [failing, not_started, passing, unavailable, unknown, warning]
accuracyHealth [failing, not_started, passing, unavailable, unknown, warning]
role [OWNER, USER]
status [active, archived, errored, inactive, launching, replacingModel, stopping]
importance [CRITICAL, HIGH, MODERATE, LOW]
buildEnvironmentType [DataRobot, Python, R, Java, Julia, Legacy, Other]
executionEnvironmentType [datarobot, external]
predictionEnvironmentPlatform [aws, gcp, azure, onPremise, datarobot, openShift, other, snowflake]
hasDecisionFlow [false, False, true, True]
createdByMe [false, False, true, True]

Example responses

200 Response

{
  "count": 0,
  "data": [
    {
      "accuracyHealth": {
        "endDate": "2019-08-24T14:15:22Z",
        "message": "string",
        "startDate": "2019-08-24T14:15:22Z",
        "status": "failing"
      },
      "approvalStatus": "PENDING",
      "capabilities": {
        "supportsAutomaticActuals": true,
        "supportsChallengerModels": true,
        "supportsFeatureDriftTracking": true,
        "supportsFeatureTypeInfoValidation": true,
        "supportsHumilityRecommendedRules": true,
        "supportsHumilityRules": true,
        "supportsHumilityRulesDefaultCalculations": true,
        "supportsModelReplacement": true,
        "supportsPortablePredictionServer": true,
        "supportsPredictionIntervals": true,
        "supportsPredictionWarning": true,
        "supportsRetraining": true,
        "supportsScoringCodeDownload": true,
        "supportsSecondaryDatasets": true,
        "supportsSegmentedAnalysisDriftAndAccuracy": true,
        "supportsShapBasedPredictionExplanations": true,
        "supportsTargetDriftTracking": true
      },
      "createdAt": "2019-08-24T14:15:22Z",
      "defaultPredictionServer": {
        "datarobot-key": "string",
        "id": "string",
        "url": "string"
      },
      "description": "string",
      "governance": {
        "approvalStatus": "PENDING",
        "hasOpenedChangeRequests": true
      },
      "hasError": true,
      "id": "string",
      "importance": "CRITICAL",
      "label": "string",
      "model": {
        "buildEnvironmentType": "string",
        "customModelImage": {
          "customModelId": "string",
          "customModelName": "string",
          "customModelVersionId": "string",
          "customModelVersionLabel": "string",
          "executionEnvironmentId": "string",
          "executionEnvironmentName": "string",
          "executionEnvironmentVersionId": "string",
          "executionEnvironmentVersionLabel": "string"
        },
        "decisionFlowId": "string",
        "decisionFlowVersionId": "string",
        "deployedAt": "2019-08-24T14:15:22Z",
        "hasDecisionFlow": true,
        "id": "string",
        "isDeprecated": true,
        "projectId": "string",
        "projectName": "string",
        "targetName": "string",
        "targetType": "string",
        "type": "string",
        "unstructuredModelKind": true,
        "unsupervisedMode": true,
        "unsupervisedType": "anomaly"
      },
      "modelHealth": {
        "endDate": "2019-08-24T14:15:22Z",
        "message": "string",
        "startDate": "2019-08-24T14:15:22Z",
        "status": "failing"
      },
      "modelPackage": {
        "id": "string",
        "name": "string",
        "registeredModelId": "string"
      },
      "modelPackageInitialDownload": {
        "timestamp": "2019-08-24T14:15:22Z"
      },
      "openedChangeRequests": [
        "string"
      ],
      "owners": {
        "count": 0,
        "preview": [
          {
            "email": "string",
            "firstName": "string",
            "id": "string",
            "lastName": "string"
          }
        ]
      },
      "permissions": [
        "CAN_ADD_CHALLENGERS"
      ],
      "predictionEnvironment": {
        "id": "string",
        "isManagedByManagementAgent": true,
        "name": "string",
        "platform": "aws",
        "plugin": "string",
        "supportedModelFormats": [
          "datarobot"
        ]
      },
      "predictionUsage": {
        "dailyRates": [
          0
        ],
        "lastTimestamp": "2019-08-24T14:15:22Z"
      },
      "scoringCodeInitialDownload": {
        "timestamp": "2019-08-24T14:15:22Z"
      },
      "serviceHealth": {
        "endDate": "2019-08-24T14:15:22Z",
        "startDate": "2019-08-24T14:15:22Z",
        "status": "failing"
      },
      "settings": {
        "batchMonitoringEnabled": true,
        "humbleAiEnabled": true,
        "predictionIntervalsEnabled": true,
        "predictionWarningEnabled": true
      },
      "status": "active",
      "userProvidedId": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Responses

Status Meaning Description Schema
200 OK The deployments DeploymentListResponse

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

BearerAuth

POST /api/v2/deployments/fromLearningModel/

Create a deployment from a DataRobot model.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/fromLearningModel/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "defaultPredictionServerId": "string",
  "description": null,
  "importance": "CRITICAL",
  "label": "string",
  "modelId": "string",
  "predictionThreshold": 1,
  "status": "active"
}

Parameters

Name In Type Required Description
body body DeploymentCreateFromLearningModel false none

Example responses

202 Response

{
  "id": "string"
}

Responses

Status Meaning Description Schema
202 Accepted Deployment successfully created. DeploymentCreateResponse
403 Forbidden User does not have permission to create a deployment. None
409 Conflict User's organization has reached the maximum number of deployments. None
422 Unprocessable Entity Unable to process the deployment creation request. None

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

BearerAuth

DELETE /api/v2/deployments/{deploymentId}/

Delete a deployment.

Code samples

# You can also use wget
curl -X DELETE https://app.datarobot.com/api/v2/deployments/{deploymentId}/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
ignoreManagementAgent query string false Do not wait for management agent to delete the deployment first.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
ignoreManagementAgent [false, False, true, True]

Responses

Status Meaning Description Schema
204 No Content Deployment successfully deleted. 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/deployments/{deploymentId}/

Retrieve a deployment.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.

Example responses

200 Response

{
  "accuracyHealth": {
    "endDate": "2019-08-24T14:15:22Z",
    "message": "string",
    "startDate": "2019-08-24T14:15:22Z",
    "status": "failing"
  },
  "approvalStatus": "PENDING",
  "capabilities": {
    "supportsAutomaticActuals": true,
    "supportsChallengerModels": true,
    "supportsFeatureDriftTracking": true,
    "supportsFeatureTypeInfoValidation": true,
    "supportsHumilityRecommendedRules": true,
    "supportsHumilityRules": true,
    "supportsHumilityRulesDefaultCalculations": true,
    "supportsModelReplacement": true,
    "supportsPortablePredictionServer": true,
    "supportsPredictionIntervals": true,
    "supportsPredictionWarning": true,
    "supportsRetraining": true,
    "supportsScoringCodeDownload": true,
    "supportsSecondaryDatasets": true,
    "supportsSegmentedAnalysisDriftAndAccuracy": true,
    "supportsShapBasedPredictionExplanations": true,
    "supportsTargetDriftTracking": true
  },
  "createdAt": "2019-08-24T14:15:22Z",
  "defaultPredictionServer": {
    "datarobot-key": "string",
    "id": "string",
    "url": "string"
  },
  "description": "string",
  "governance": {
    "approvalStatus": "PENDING",
    "hasOpenedChangeRequests": true
  },
  "hasError": true,
  "id": "string",
  "importance": "CRITICAL",
  "label": "string",
  "model": {
    "buildEnvironmentType": "string",
    "customModelImage": {
      "customModelId": "string",
      "customModelName": "string",
      "customModelVersionId": "string",
      "customModelVersionLabel": "string",
      "executionEnvironmentId": "string",
      "executionEnvironmentName": "string",
      "executionEnvironmentVersionId": "string",
      "executionEnvironmentVersionLabel": "string"
    },
    "decisionFlowId": "string",
    "decisionFlowVersionId": "string",
    "deployedAt": "2019-08-24T14:15:22Z",
    "hasDecisionFlow": true,
    "id": "string",
    "isDeprecated": true,
    "projectId": "string",
    "projectName": "string",
    "targetName": "string",
    "targetType": "string",
    "type": "string",
    "unstructuredModelKind": true,
    "unsupervisedMode": true,
    "unsupervisedType": "anomaly"
  },
  "modelHealth": {
    "endDate": "2019-08-24T14:15:22Z",
    "message": "string",
    "startDate": "2019-08-24T14:15:22Z",
    "status": "failing"
  },
  "modelPackage": {
    "id": "string",
    "name": "string",
    "registeredModelId": "string"
  },
  "modelPackageInitialDownload": {
    "timestamp": "2019-08-24T14:15:22Z"
  },
  "openedChangeRequests": [
    "string"
  ],
  "owners": {
    "count": 0,
    "preview": [
      {
        "email": "string",
        "firstName": "string",
        "id": "string",
        "lastName": "string"
      }
    ]
  },
  "permissions": [
    "CAN_ADD_CHALLENGERS"
  ],
  "predictionEnvironment": {
    "id": "string",
    "isManagedByManagementAgent": true,
    "name": "string",
    "platform": "aws",
    "plugin": "string",
    "supportedModelFormats": [
      "datarobot"
    ]
  },
  "predictionUsage": {
    "dailyRates": [
      0
    ],
    "lastTimestamp": "2019-08-24T14:15:22Z"
  },
  "scoringCodeInitialDownload": {
    "timestamp": "2019-08-24T14:15:22Z"
  },
  "serviceHealth": {
    "endDate": "2019-08-24T14:15:22Z",
    "startDate": "2019-08-24T14:15:22Z",
    "status": "failing"
  },
  "settings": {
    "batchMonitoringEnabled": true,
    "humbleAiEnabled": true,
    "predictionIntervalsEnabled": true,
    "predictionWarningEnabled": true
  },
  "status": "active",
  "userProvidedId": "string"
}

Responses

Status Meaning Description Schema
200 OK The deployment DeploymentRetrieveResponse

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

BearerAuth

PATCH /api/v2/deployments/{deploymentId}/

Update a deployment's label and description.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "description": "string",
  "importance": "CRITICAL",
  "label": "string"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body DeploymentUpdate false none

Responses

Status Meaning Description Schema
204 No Content Deployment successfully updated None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/accuracy/

Retrieve accuracy metric for a certain time period.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/accuracy/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
modelId query string false The id of the model for which metrics are being retrieved.
batchId query any false The id of the batch for which metrics are being retrieved.
segmentAttribute query string false The name of the segment on which segment analysis is being performed.
segmentValue query string false The value of the segmentAttribute to segment on.
targetClasses query string false Comma separated list of target classes to filter out response
targetClass query any false Target class to filter out results.
deploymentId path string true Unique identifier of the deployment.

Example responses

200 Response

{
  "batchIds": [
    "string"
  ],
  "metrics": "\n                {\"metrics\": {\n                    \"LogLoss\": {\n                        \"baselineValue\": 0.454221484838069,\n                        \"value\": 0.880778024500618,\n                        \"percentChange\": -93.91\n                    },\n                    \"AUC\": {\n                        \"baselineValue\": 0.8690358459556535,\n                        \"value\": 0.5294117647058824,\n                        \"percentChange\": -39.08\n                    },\n                    \"Kolmogorov-Smirnov\": {\n                        \"baselineValue\": 0.5753202944706626,\n                        \"value\": 0.4117647058823529,\n                        \"percentChange\": -28.43\n                    },\n                    \"Rate@Top10%\": {\n                        \"baselineValue\": 0.9603223806571606,\n                        \"value\": 1.0,\n                        \"percentChange\": 4.13\n                    },\n                    \"Gini Norm\": {\n                        \"baselineValue\": 0.7380716919113071,\n                        \"value\": 0.05882352941176472,\n                        \"percentChange\": -92.03\n                    }\n                }\n                ",
  "modelId": "string",
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "segmentAttribute": "string",
  "segmentValue": "",
  "targetClasses": "string"
}

Responses

Status Meaning Description Schema
200 OK Deployment accuracy metrics are retrieved. AccuracyResponse

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/accuracyOverTime/

Retrieve accuracy metric baseline, and metric value calculated for each time bucket dividing a longer time period.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/accuracyOverTime/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
bucketSize query string(duration) false The time duration of a bucket. Needs to be multiple of one hour. Can not be longer than the total length of the period. If not set, a default value will be calculated based on the start and end time.
modelId query any false The id of the models for which metrics are being retrieved.
metric query string false Name of the metric.
segmentAttribute query string false The name of the segment on which segment analysis is being performed.
segmentValue query string false The value of the segmentAttribute to segment on.
targetClasses query string false List of target classes to filter out response
targetClass query any false Target class to filter out results.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
metric [AUC, Accuracy, Balanced Accuracy, F1, FPR, FVE Binomial, FVE Gamma, FVE Multinomial, FVE Poisson, FVE Tweedie, Gamma Deviance, Gini Norm, Kolmogorov-Smirnov, LogLoss, MAD, MAE, MAPE, MCC, NPV, PPV, Poisson Deviance, R Squared, RMSE, RMSLE, Rate@Top10%, Rate@Top5%, TNR, TPR, Tweedie Deviance]

Example responses

200 Response

{
  "baseline": {
    "period": {
      "end": "2019-08-24T14:15:22Z",
      "start": "2019-08-24T14:15:22Z"
    },
    "sampleSize": 0,
    "value": 0,
    "valuePerClass": "\n                {\n                    \"class1\": 0.880778024500618,\n                    \"class2\": 0.5294117647058824,\n                    \"class3\": 0.4117647058823529\n                }\n            "
  },
  "baselines": [
    {
      "modelId": "string",
      "perClass": [
        {
          "className": "string",
          "value": 0
        }
      ],
      "sampleSize": 0,
      "value": 0
    }
  ],
  "buckets": [
    {
      "modelId": "string",
      "perClass": [
        {
          "className": "string",
          "value": 0
        }
      ],
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "sampleSize": 0,
      "value": 0,
      "valuePerClass": "\n                {\n                    \"class1\": 0.880778024500618,\n                    \"class2\": 0.5294117647058824,\n                    \"class3\": 0.4117647058823529\n                }\n            "
    }
  ],
  "metric": "AUC",
  "modelId": "string",
  "segmentAttribute": "string",
  "segmentValue": "",
  "summary": {
    "period": {
      "end": "2019-08-24T14:15:22Z",
      "start": "2019-08-24T14:15:22Z"
    },
    "sampleSize": 0,
    "value": 0,
    "valuePerClass": "\n                {\n                    \"class1\": 0.880778024500618,\n                    \"class2\": 0.5294117647058824,\n                    \"class3\": 0.4117647058823529\n                }\n            "
  }
}

Responses

Status Meaning Description Schema
200 OK Accuracy over time. AccuracyOverTimeResponse

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/actuals/fromDataset/

Submit actuals values for processing using catalog item. Submission of actuals is limited to 10,000,000 actuals per hour. For time series deployments, total actuals = number of actuals * number of forecast distances. For example, submitting 10 actuals for a deployment with 50 forecast distances = 500 total actuals. For multiclass deployments, a similar calculation is made where total actuals = number of actuals * number of classes. For example, submitting 10 actuals for a deployment with 20 classes = 200 actuals.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/actuals/fromDataset/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "actualValueColumn": "string",
  "associationIdColumn": "string",
  "datasetId": "string",
  "datasetVersionId": "string",
  "keepActualsWithoutPredictions": true,
  "password": "string",
  "timestampColumn": "string",
  "user": "string",
  "wasActedOnColumn": "string"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body DeploymentDatasetCreate false none

Responses

Status Meaning Description Schema
202 Accepted Submitted successfully. See Location header. None
422 Unprocessable Entity Unable to process the Actuals submission request. None
429 Too Many Requests The number of actuals uploaded this hour exceeds the limit of 10000000 rows. None

Response Headers

Status Header Type Format Description
202 Location string URL for tracking async job status.

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/actuals/fromJSON/

Submit actuals values for processing. Values are not processed immediately and may take some time to propagate through deployment systems. Submission of actuals is limited to 10,000,000 actuals per hour. For time series deployments, total actuals = number of actuals * number of forecast distances. For example, submitting 10 actuals for a deployment with 50 forecast distances = 500 total actuals. For multiclass deployments, a similar calculation is made where total actuals = number of actuals * number of classes. For example, submitting 10 actuals for a deployment with 20 classes = 200 actuals.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/actuals/fromJSON/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "data": [
    {
      "actualValue": 0,
      "associationId": "string",
      "timestamp": "2019-08-24T14:15:22Z",
      "wasActedOn": true
    }
  ],
  "keepActualsWithoutPredictions": true
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body DeploymentActuals false none

Responses

Status Meaning Description Schema
202 Accepted Submitted successfully. See Location header. None
422 Unprocessable Entity Unable to process the Actuals submission request. None
429 Too Many Requests The number of actuals uploaded this hour exceeds the limit of 10000000 rows. None

Response Headers

Status Header Type Format Description
202 Location string URL for tracking async job status.

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/capabilities/

Retrieve the capabilities for the deployment.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/capabilities/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.

Example responses

200 Response

{
  "data": [
    {
      "messages": [
        "string"
      ],
      "name": "string",
      "supported": true
    }
  ]
}

Responses

Status Meaning Description Schema
200 OK none DeploymentCapabilitiesRetrieveResponse

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/challengerPredictions/

Score main model prediction requests against challenger model requests.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/challengerPredictions/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "timestamp": "2019-08-24T14:15:22Z"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body ChallengerScore false none

Responses

Status Meaning Description Schema
202 Accepted Job submitted. See Location header. None
422 Unprocessable Entity Unable to process the challenger scoring request. None
429 Too Many Requests Another challenger scoring job is running. See the Location header to track the running job. None

Response Headers

Status Header Type Format Description
202 Location string URL to poll to track challenger scoring progress.

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/challengers/

List challenger models for deployment.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/challengers/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.

Example responses

200 Response

{
  "data": [
    {
      "id": "string",
      "model": {
        "datasetName": "string",
        "description": "string",
        "executionType": "string",
        "id": "string",
        "isDeprecated": true,
        "name": "string",
        "projectId": "string",
        "projectName": "string"
      },
      "modelPackage": {
        "id": "string",
        "name": "string",
        "registeredModelId": "string"
      },
      "name": "string",
      "predictionEnvironment": {
        "id": "string",
        "name": "string"
      }
    }
  ]
}

Responses

Status Meaning Description Schema
200 OK The challenger models ChallengerListResponse

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/challengers/

Create new challenger model.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/challengers/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "modelPackageId": "string",
  "name": "string",
  "predictionEnvironmentId": "string"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body ChallengerCreate false none

Responses

Status Meaning Description Schema
202 Accepted Job submitted successfully. See Location header. None
422 Unprocessable Entity Unable to process the challenger creation request. None

Response Headers

Status Header Type Format Description
202 Location string URL to poll to track challenger creation has finished.

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

BearerAuth

DELETE /api/v2/deployments/{deploymentId}/challengers/{challengerId}/

Delete challenger model.

Code samples

# You can also use wget
curl -X DELETE https://app.datarobot.com/api/v2/deployments/{deploymentId}/challengers/{challengerId}/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
challengerId path string true Unique identifier of the challenger.

Responses

Status Meaning Description Schema
204 No Content Model successfully deleted. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/challengers/{challengerId}/

Retrieve challenger model.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/challengers/{challengerId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
challengerId path string true Unique identifier of the challenger.

Example responses

200 Response

{
  "id": "string",
  "model": {
    "datasetName": "string",
    "description": "string",
    "executionType": "string",
    "id": "string",
    "isDeprecated": true,
    "name": "string",
    "projectId": "string",
    "projectName": "string"
  },
  "modelPackage": {
    "id": "string",
    "name": "string",
    "registeredModelId": "string"
  },
  "name": "string",
  "predictionEnvironment": {
    "id": "string",
    "name": "string"
  }
}

Responses

Status Meaning Description Schema
200 OK The challenger model ChallengerResponse

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

BearerAuth

PATCH /api/v2/deployments/{deploymentId}/challengers/{challengerId}/

Update challenger model.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/challengers/{challengerId}/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "name": "string",
  "predictionEnvironmentId": "string"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
challengerId path string true Unique identifier of the challenger.
body body ChallengerUpdate false none

Example responses

200 Response

{
  "id": "string",
  "model": {
    "datasetName": "string",
    "description": "string",
    "executionType": "string",
    "id": "string",
    "isDeprecated": true,
    "name": "string",
    "projectId": "string",
    "projectName": "string"
  },
  "modelPackage": {
    "id": "string",
    "name": "string",
    "registeredModelId": "string"
  },
  "name": "string",
  "predictionEnvironment": {
    "id": "string",
    "name": "string"
  }
}

Responses

Status Meaning Description Schema
200 OK Model successfully updated. ChallengerResponse

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/customMetrics/

Retrieve a list of custom metrics.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/customMetrics/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
offset query integer false Offset this number of objects to retrieve
limit query integer false At most this number of objects to retrieve
deploymentId path string true Unique identifier of the deployment.

Example responses

200 Response

{
  "count": 0,
  "data": [
    {
      "baselineValues": [
        {
          "value": 0
        }
      ],
      "createdAt": "2019-08-24T14:15:22Z",
      "createdBy": {
        "id": "string"
      },
      "description": "string",
      "directionality": "higherIsBetter",
      "displayChart": true,
      "id": "string",
      "isModelSpecific": true,
      "name": "string",
      "sampleCount": {
        "columnName": "string"
      },
      "timeStep": "hour",
      "timestamp": {
        "columnName": "string",
        "timeFormat": "%m/%d/%Y"
      },
      "type": "average",
      "units": "string",
      "value": {
        "columnName": "string"
      }
    }
  ],
  "next": "string",
  "previous": "string",
  "totalCount": 0
}

Responses

Status Meaning Description Schema
200 OK Success MetricListResponse
403 Forbidden User does not have permission to access a particular deployment or create a custom metric. None

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/customMetrics/

Create a deployment custom metric.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/customMetrics/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "baselineValues": [],
  "description": "string",
  "directionality": "higherIsBetter",
  "isModelSpecific": true,
  "name": "string",
  "sampleCount": {
    "columnName": "string"
  },
  "timeStep": "hour",
  "timestamp": {
    "columnName": "string",
    "timeFormat": "%m/%d/%Y"
  },
  "type": "average",
  "units": "string",
  "value": {
    "columnName": "string"
  }
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body MetricCreatePayload false none

Example responses

201 Response

{
  "baselineValues": [
    {
      "value": 0
    }
  ],
  "createdAt": "2019-08-24T14:15:22Z",
  "createdBy": {
    "id": "string"
  },
  "description": "string",
  "directionality": "higherIsBetter",
  "displayChart": true,
  "id": "string",
  "isModelSpecific": true,
  "name": "string",
  "sampleCount": {
    "columnName": "string"
  },
  "timeStep": "hour",
  "timestamp": {
    "columnName": "string",
    "timeFormat": "%m/%d/%Y"
  },
  "type": "average",
  "units": "string",
  "value": {
    "columnName": "string"
  }
}

Responses

Status Meaning Description Schema
201 Created Custom metric is successfully created. MetricEntity
403 Forbidden User does not have permission to create a custom metric. None

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

BearerAuth

DELETE /api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/

Delete a custom metric.

Code samples

# You can also use wget
curl -X DELETE https://app.datarobot.com/api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true ID of the deployment
customMetricId path string true ID of the custom metric

Responses

Status Meaning Description Schema
204 No Content A custom metric was successfully deleted. None
403 Forbidden User does not have permission to delete a custom metric. None
404 Not Found Custom metric was not found. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/

Retrieve a single custom metric metadata.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true ID of the deployment
customMetricId path string true ID of the custom metric

Example responses

200 Response

{
  "baselineValues": [
    {
      "value": 0
    }
  ],
  "createdAt": "2019-08-24T14:15:22Z",
  "createdBy": {
    "id": "string"
  },
  "description": "string",
  "directionality": "higherIsBetter",
  "displayChart": true,
  "id": "string",
  "isModelSpecific": true,
  "name": "string",
  "sampleCount": {
    "columnName": "string"
  },
  "timeStep": "hour",
  "timestamp": {
    "columnName": "string",
    "timeFormat": "%m/%d/%Y"
  },
  "type": "average",
  "units": "string",
  "value": {
    "columnName": "string"
  }
}

Responses

Status Meaning Description Schema
200 OK A given custom metric metadata. MetricEntity
403 Forbidden User does not have permission to access a particular deployment or custom metric metadata. None

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

BearerAuth

PATCH /api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/

Update given custom metric settings.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "baselineValues": [
    {
      "value": 0
    }
  ],
  "batch": {
    "columnName": "string"
  },
  "description": "string",
  "directionality": "higherIsBetter",
  "name": "string",
  "sampleCount": {
    "columnName": "string"
  },
  "timestamp": {
    "columnName": "string",
    "timeFormat": "%m/%d/%Y"
  },
  "type": "average",
  "units": "string",
  "value": {
    "columnName": "string"
  }
}

Parameters

Name In Type Required Description
deploymentId path string true ID of the deployment
customMetricId path string true ID of the custom metric
body body MetricUpdatePayload false none

Example responses

200 Response

{
  "baselineValues": [
    {
      "value": 0
    }
  ],
  "createdAt": "2019-08-24T14:15:22Z",
  "createdBy": {
    "id": "string"
  },
  "description": "string",
  "directionality": "higherIsBetter",
  "displayChart": true,
  "id": "string",
  "isModelSpecific": true,
  "name": "string",
  "sampleCount": {
    "columnName": "string"
  },
  "timeStep": "hour",
  "timestamp": {
    "columnName": "string",
    "timeFormat": "%m/%d/%Y"
  },
  "type": "average",
  "units": "string",
  "value": {
    "columnName": "string"
  }
}

Responses

Status Meaning Description Schema
200 OK Custom metric settings updated. MetricEntity
403 Forbidden User does not have permission to update the custom metric. None

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/fromDataset/

Upload custom metric values from dataset.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/fromDataset/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "associationId": {
    "columnName": "string"
  },
  "batch": {
    "columnName": "string"
  },
  "datasetId": "string",
  "modelId": null,
  "modelPackageId": null,
  "sampleCount": {
    "columnName": "string"
  },
  "segments": [
    {
      "column": "string",
      "name": "string",
      "value": "string"
    }
  ],
  "timestamp": {
    "columnName": "string",
    "timeFormat": "%m/%d/%Y"
  },
  "value": {
    "columnName": "string"
  }
}

Parameters

Name In Type Required Description
deploymentId path string true ID of the deployment
customMetricId path string true ID of the custom metric
body body MetricValuesFromDatasetPayload false none

Responses

Status Meaning Description Schema
202 Accepted Custom metric values import started None
403 Forbidden User does not have permission to import custom metric values. None

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/fromJSON/

Upload custom metric values from JSON.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/fromJSON/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "buckets": [
    {
      "sampleSize": 1,
      "timestamp": "2019-08-24T14:15:22Z",
      "value": 0
    }
  ],
  "dryRun": false,
  "modelId": null,
  "modelPackageId": null
}

Parameters

Name In Type Required Description
deploymentId path string true ID of the deployment
customMetricId path string true ID of the custom metric
body body MetricValuesFromJSONPayload false none

Example responses

202 Response

{
  "baselineValues": [
    {
      "value": 0
    }
  ],
  "createdAt": "2019-08-24T14:15:22Z",
  "createdBy": {
    "id": "string"
  },
  "description": "string",
  "directionality": "higherIsBetter",
  "displayChart": true,
  "id": "string",
  "isModelSpecific": true,
  "name": "string",
  "sampleCount": {
    "columnName": "string"
  },
  "timeStep": "hour",
  "timestamp": {
    "columnName": "string",
    "timeFormat": "%m/%d/%Y"
  },
  "type": "average",
  "units": "string",
  "value": {
    "columnName": "string"
  }
}

Responses

Status Meaning Description Schema
202 Accepted Custom metric values import started MetricEntity
403 Forbidden User does not have permission to import custom metric values. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/summary/

Retrieve the summary of deployment custom metric.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/summary/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring stats, defaults to 7 days ago from the end of the period.
end query string(date-time) false End of the period to retrieve monitoring stats, defaults to the next top of the hour from now.
modelPackageId query string false The model package ID of related champion/challenger to retrieve custom metric values for.
modelId query string false The model ID of related champion/challenger to retrieve custom metric values for.
batchId query any false The id of the batch for which metrics are being retrieved.
deploymentId path string true ID of the deployment
customMetricId path string true ID of the custom metric

Example responses

200 Response

{
  "metric": {
    "baselineValue": 0,
    "id": "string",
    "name": "string",
    "percentChange": 0,
    "sampleCount": 0,
    "value": 0
  },
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  }
}

Responses

Status Meaning Description Schema
200 OK Summary retrieved successfully. CustomMetricSummary
403 Forbidden User does not have permission to read the custom metric summary. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/valuesOverTime/

Retrieve custom metric values over time.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/customMetrics/{customMetricId}/valuesOverTime/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring stats, defaults to 7 days ago from the end of the period.
end query string(date-time) false End of the period to retrieve monitoring stats, defaults to the next top of the hour from now.
modelPackageId query string false The model package ID of related champion/challenger to retrieve custom metric values for.
modelId query string false The model ID of related champion/challenger to retrieve custom metric values for.
bucketSize query string(duration) false Time duration of a bucket, default to seven days.
deploymentId path string true ID of the deployment
customMetricId path string true ID of the custom metric

Example responses

200 Response

{
  "buckets": [
    {
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "sampleSize": 0,
      "value": 0
    }
  ],
  "metric": {
    "baselineValues": [
      {
        "value": 0
      }
    ],
    "createdAt": "2019-08-24T14:15:22Z",
    "createdBy": {
      "id": "string"
    },
    "description": "string",
    "directionality": "higherIsBetter",
    "displayChart": true,
    "id": "string",
    "isModelSpecific": true,
    "name": "string",
    "sampleCount": {
      "columnName": "string"
    },
    "timeStep": "hour",
    "timestamp": {
      "columnName": "string",
      "timeFormat": "%m/%d/%Y"
    },
    "type": "average",
    "units": "string",
    "value": {
      "columnName": "string"
    }
  },
  "summary": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  }
}

Responses

Status Meaning Description Schema
200 OK Data retrieved successfully MetricValuesOverTimeResponse
403 Forbidden User does not have permission to read custom metric values. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/customMetricsSummary/

Retrieve the bulk summary of deployment custom metrics.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/customMetricsSummary/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring stats, defaults to 7 days ago from the end of the period.
end query string(date-time) false End of the period to retrieve monitoring stats, defaults to the next top of the hour from now.
modelPackageId query string false The model package ID of related champion/challenger to retrieve custom metric values for.
modelId query string false The model ID of related champion/challenger to retrieve custom metric values for.
batchId query any false The id of the batch for which metrics are being retrieved.
deploymentId path string true Unique identifier of the deployment.

Example responses

200 Response

{
  "details": {
    "earliestDate": "2019-08-24T14:15:22Z",
    "latestDate": "2019-08-24T14:15:22Z"
  },
  "metrics": [],
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  }
}

Responses

Status Meaning Description Schema
200 OK Bulk summary retrieved successfully. CustomMetricsBulkSummary
403 Forbidden User does not have permission to read the custom metrics summary. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/fairnessScoresOverTime/

Retrieve fairness scores for all features, or for different classes of a single feature changes over a specific time period.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/fairnessScoresOverTime/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
bucketSize query string false Time duration of buckets
modelId query string false The ID of the model to retrieve the statistics for.
fairnessMetric query string false The name of the fairness metric to compute fairness over time.
protectedFeature query string false Name of the protected feature. When present, will return per class fairness score of the protected feature, otherwise returning fairness score of all protected features.
orderBy query string false The type of FairnessScore to order the response by.
includePrivilegedClass query string false Always include privileged class in response.
onlyStatisticallySignificant query string false Include only statistically significant attributes.
limit query integer false Max number of features in response.
offset query integer false Number of features to offset in response.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
bucketSize [PT1H, P1D, P7D, P1M]
fairnessMetric [proportionalParity, equalParity, favorableClassBalance, unfavorableClassBalance, trueUnfavorableRateParity, trueFavorableRateParity, favorablePredictiveValueParity, unfavorablePredictiveValueParity]
orderBy [absoluteFairnessScore, relativeFairnessScore, -absoluteFairnessScore, -relativeFairnessScore]
includePrivilegedClass [false, False, true, True]
onlyStatisticallySignificant [false, False, true, True]

Example responses

200 Response

{
  "buckets": [
    {
      "metricName": "proportionalParity",
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "scores": [
        {
          "absoluteValue": 0,
          "classesCount": 0,
          "healthyClassesCount": 0,
          "healthyCount": 0,
          "isStatisticallySignificant": true,
          "label": "string",
          "message": "string",
          "privilegedClass": "string",
          "sampleSize": 0,
          "totalCount": 1,
          "value": 1
        }
      ]
    }
  ],
  "fairnessThreshold": 1,
  "favorableTargetOutcome": true,
  "modelId": "string",
  "modelPackageId": "string",
  "protectedFeature": "string",
  "summary": {
    "metricName": "proportionalParity",
    "period": {
      "end": "2019-08-24T14:15:22Z",
      "start": "2019-08-24T14:15:22Z"
    },
    "scores": [
      {
        "absoluteValue": 0,
        "classesCount": 0,
        "healthyClassesCount": 0,
        "healthyCount": 0,
        "isStatisticallySignificant": true,
        "label": "string",
        "message": "string",
        "privilegedClass": "string",
        "sampleSize": 0,
        "totalCount": 1,
        "value": 1
      }
    ]
  }
}

Responses

Status Meaning Description Schema
200 OK Fairness summary and over time. FairnessOverTimeResponse

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/featureDrift/

Retrieve drift scores for features of the deployment.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/featureDrift/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
modelId query string false ID of the model in the deployment. If not set, defaults to the deployment current model.
metric query string false Name of the metric used to calculate the drift. Can be one of psi, kl_divergence, dissimilarity, hellinger, and js_divergence. Defaults to psi.
offset query integer false The number of features to skip, defaults to 0.
limit query integer false The number of features to return, defaults to 25.
segmentAttribute query string false The name of a segment attribute used for segment analysis.
segmentValue query string false The value of the segmentAttribute to segment on.
batchId query any false The id of the batch for which metrics are being retrieved.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
metric [psi, kl_divergence, dissimilarity, hellinger, js_divergence]

Example responses

200 Response

{
  "batchId": [],
  "count": 0,
  "data": [
    {
      "baselineSampleSize": 0,
      "driftScore": 0,
      "featureImpact": 0,
      "name": "string",
      "sampleSize": 0,
      "type": "numeric"
    }
  ],
  "metric": "psi",
  "modelId": "string",
  "next": "string",
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "previous": "string",
  "segmentAttribute": "string",
  "segmentValue": "string"
}

Responses

Status Meaning Description Schema
200 OK Features drift over specified time period retrieved. FeatureDriftResponse

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/featureDriftOverTime/

Retrieve drift over time info for a feature of the deployment.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/featureDriftOverTime/?featureNames=string \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
bucketSize query string(duration) false The time duration of a bucket. Needs to be multiple of one hour. Can not be longer than the total length of the period. If not set, a default value will be calculated based on the start and end time.
modelId query string false The id of the model for which the features drift is being retrieved.
featureNames query any true List of feature names, limited to two per request.
metric query string false Name of the metric used to calculate the drift. Can be one of psi, kl_divergence, dissimilarity, hellinger, and js_divergence. Defaults to psi.
segmentAttribute query string false The name of the segment on which segment analysis is being performed.
segmentValue query string false The value of the segmentAttribute to segment on.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
metric [psi, kl_divergence, dissimilarity, hellinger, js_divergence]

Example responses

200 Response

{
  "buckets": [
    {
      "baselineSampleSize": 0,
      "driftScore": 0,
      "featureImpact": 0,
      "featureName": "string",
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "sampleSize": 0
    }
  ],
  "features": [
    {
      "featureName": "string",
      "featureType": "numeric"
    }
  ],
  "metric": "string",
  "summaries": [
    {
      "featureImpact": 0,
      "featureName": "string"
    }
  ]
}

Responses

Status Meaning Description Schema
200 OK Feature drift over time info of the deployment retrieved. FeatureDriftOverTimeResponse
400 Bad Request Request invalid, refer to messages for detail. None
403 Forbidden Model Deployments and/or Monitoring are not enabled. None
404 Not Found Either the deployment does not exist or user does not have permission to view the deployment. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/features/

Retrieve features contained within the universe dataset associated with a specific deployment. By default, this returns all raw features required for predictions.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/features/?offset=0&limit=50 \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
offset query integer true The number of features to skip, defaults to 0.
limit query integer true The number of features to return, defaults to 0.
includeNonPredictionFeatures query string false When True will return all raw features in the universe dataset associated with the deployment, and when False will return only those raw features used to make predictions on the deployment.
forSegmentedAnalysis query string false When True, features returned will be filtered to those usable for segmented analysis.
search query string false Case insensitive search against names of the deployment's features.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
includeNonPredictionFeatures [false, False, true, True]
forSegmentedAnalysis [false, False, true, True]

Example responses

200 Response

{
  "count": 0,
  "data": [
    {
      "dateFormat": "string",
      "featureType": "string",
      "importance": 0,
      "knownInAdvance": true,
      "name": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Responses

Status Meaning Description Schema
200 OK The deployment's features FeatureListResponse
422 Unprocessable Entity Feature list retrieval is not supported on this deployment. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/humilityStats/

Retrieve humility rule service triggers statistics overview.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/humilityStats/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
bucketSize query string(duration) false The time duration of a bucket. Needs to be multiple of one hour. Can not be longer than the total length of the period. If not set, a default value will be calculated based on the start and end time.
modelId query string false The id of the model for which metrics are being retrieved.
segmentAttribute query string false The name of a segment attribute used for segment analysis.
segmentValue query string false The value of the segmentAttribute to segment on.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
segmentAttribute [DataRobot-Consumer, DataRobot-Remote-IP, DataRobot-Host-IP]

Example responses

200 Response

{
  "data": [
    {
      "ruleId": "string",
      "ruleName": "string",
      "value": 0
    }
  ],
  "modelId": "string",
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "segmentAttribute": "string",
  "segmentValue": ""
}

Responses

Status Meaning Description Schema
200 OK Humility service health statistics overview retrieved. HumilityStatsResponse
403 Forbidden Model Deployments and/or Monitoring are not enabled. None
404 Not Found Either the deployment does not exist or user does not have permission to view the deployment. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/humilityStatsOverTime/

Retrieve humility service statistics over time.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/humilityStatsOverTime/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
bucketSize query string(duration) false The time duration of a bucket. Needs to be multiple of one hour. Can not be longer than the total length of the period. If not set, a default value will be calculated based on the start and end time.
modelId query string false The id of the model for which metrics are being retrieved.
segmentAttribute query string false The name of a segment attribute used for segment analysis.
segmentValue query string false The value of the segmentAttribute to segment on.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
segmentAttribute [DataRobot-Consumer, DataRobot-Remote-IP, DataRobot-Host-IP]

Example responses

200 Response

{
  "buckets": [
    {
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "values": [
        {
          "ruleId": "string",
          "ruleName": "string",
          "value": 0
        }
      ]
    }
  ],
  "modelId": "string",
  "segmentAttribute": "string",
  "segmentValue": "",
  "summary": {
    "period": {
      "end": "2019-08-24T14:15:22Z",
      "start": "2019-08-24T14:15:22Z"
    },
    "values": [
      {
        "ruleId": "string",
        "ruleName": "string",
        "value": 0
      }
    ]
  }
}

Responses

Status Meaning Description Schema
200 OK Humility statistics for deployment retrieved. HumilityStatsOverTimeResponse
403 Forbidden Model Deployments and/or Monitoring are not enabled. None
404 Not Found Either the deployment does not exist or user does not have permission to view the deployment. None

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

BearerAuth

PATCH /api/v2/deployments/{deploymentId}/model/

Replace the model used to make predictions for the deployment. A validation process will be performed to make sure the new model is eligible as a replacement. If the validation fails, the model replacement will not occur.The Model Replacement Validation endpoint can be used to confirm the new model is eligible as a replacement.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/model/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "modelId": "string",
  "modelPackageId": "string",
  "reason": "ACCURACY"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body ModelReplacementSubmission false none

Example responses

202 Response

{
  "checks": {
    "combinedModelSegments": {
      "message": "string",
      "status": "failing"
    },
    "containsTrackedSegmentAttributes": {
      "message": "string",
      "status": "failing"
    },
    "driftTracking": {
      "message": "string",
      "status": "failing"
    },
    "featureDataTypes": {
      "message": "string",
      "status": "failing"
    },
    "features": {
      "message": "string",
      "status": "failing"
    },
    "humilityRules": {
      "message": "string",
      "status": "failing"
    },
    "modelCanBeDeployed": {
      "message": "string",
      "status": "failing"
    },
    "modelStatus": {
      "message": "string",
      "status": "failing"
    },
    "notCurrentModel": {
      "message": "string",
      "status": "failing"
    },
    "permission": {
      "message": "string",
      "status": "failing"
    },
    "predictionIntervals": {
      "message": "string",
      "status": "failing"
    },
    "predictionReady": {
      "message": "string",
      "status": "failing"
    },
    "seriesType": {
      "message": "string",
      "status": "failing"
    },
    "supported": {
      "message": "string",
      "status": "failing"
    },
    "target": {
      "message": "string",
      "status": "failing"
    },
    "targetClasses": {
      "message": "string",
      "status": "failing"
    },
    "targetType": {
      "message": "string",
      "status": "failing"
    },
    "timeSeriesCompatibility": {
      "message": "string",
      "status": "failing"
    },
    "validChallenger": {
      "message": "string",
      "status": "failing"
    }
  },
  "message": "string",
  "status": "failing"
}

Responses

Status Meaning Description Schema
202 Accepted Job submitted. See Location header. ModelReplacementValidationResponse

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/deployments/{deploymentId}/model/secondaryDatasetConfiguration/

Retrieve the secondary datasets configuration used by a deployed Feature discovery model.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/model/secondaryDatasetConfiguration/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.

Example responses

200 Response

{
  "created": "2019-08-24T14:15:22Z",
  "creatorFullName": "string",
  "creatorUserId": "string",
  "credentialIds": [
    {
      "catalogVersionId": "string",
      "credentialId": "string",
      "url": "string"
    }
  ],
  "featurelistId": "string",
  "isDefault": true,
  "isDeleted": true,
  "name": "string",
  "projectId": "string",
  "secondaryDatasetConfigId": "string",
  "secondaryDatasets": [
    {
      "catalogId": "string",
      "catalogVersionId": "string",
      "identifier": "string",
      "snapshotPolicy": "specified"
    }
  ]
}

Responses

Status Meaning Description Schema
200 OK Secondary datasets configuration. SecondaryDatasetConfigResponse
404 Not Found Deployment or secondary datasets configuration cannot be found for the deployed model. None

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

BearerAuth

PATCH /api/v2/deployments/{deploymentId}/model/secondaryDatasetConfiguration/

Update the secondary datasets configuration used by the deployed feature discovery model.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/model/secondaryDatasetConfiguration/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "credentialsIds": [
    {
      "catalogVersionId": "string",
      "credentialId": "string",
      "url": "string"
    }
  ],
  "secondaryDatasetConfigId": "string"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body SecondaryDatasetConfigUpdate false none

Responses

Status Meaning Description Schema
204 No Content Secondary Datasets Configuration updated successfully. None
403 Forbidden Invalid credentials for secondary datasets configuration. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/model/secondaryDatasetConfigurationHistory/

List all the secondary datasets configuration used by a given Feature Discovery deployment

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/model/secondaryDatasetConfigurationHistory/?offset=0&limit=100 \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
offset query integer true Number of items to skip. Defaults to 0 if not provided.
limit query integer true Number of items to return, defaults to 100 if not provided.
deploymentId path string true Unique identifier of the deployment.

Example responses

200 Response

{
  "count": 0,
  "data": [
    {
      "configId": "string",
      "configName": "string",
      "updated": "string",
      "username": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Responses

Status Meaning Description Schema
200 OK Secondary Datasets Configuration history. SecondaryDatasetsConfigListResponse

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/model/validation/

Validate that a model can be used to replace the current model of the deployment.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/model/validation/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "modelId": "string",
  "modelPackageId": "string"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body ModelReplacementValidationRequest false none

Example responses

200 Response

{
  "checks": {
    "combinedModelSegments": {
      "message": "string",
      "status": "failing"
    },
    "containsTrackedSegmentAttributes": {
      "message": "string",
      "status": "failing"
    },
    "driftTracking": {
      "message": "string",
      "status": "failing"
    },
    "featureDataTypes": {
      "message": "string",
      "status": "failing"
    },
    "features": {
      "message": "string",
      "status": "failing"
    },
    "humilityRules": {
      "message": "string",
      "status": "failing"
    },
    "modelCanBeDeployed": {
      "message": "string",
      "status": "failing"
    },
    "modelStatus": {
      "message": "string",
      "status": "failing"
    },
    "notCurrentModel": {
      "message": "string",
      "status": "failing"
    },
    "permission": {
      "message": "string",
      "status": "failing"
    },
    "predictionIntervals": {
      "message": "string",
      "status": "failing"
    },
    "predictionReady": {
      "message": "string",
      "status": "failing"
    },
    "seriesType": {
      "message": "string",
      "status": "failing"
    },
    "supported": {
      "message": "string",
      "status": "failing"
    },
    "target": {
      "message": "string",
      "status": "failing"
    },
    "targetClasses": {
      "message": "string",
      "status": "failing"
    },
    "targetType": {
      "message": "string",
      "status": "failing"
    },
    "timeSeriesCompatibility": {
      "message": "string",
      "status": "failing"
    },
    "validChallenger": {
      "message": "string",
      "status": "failing"
    }
  },
  "message": "string",
  "status": "failing"
}

Responses

Status Meaning Description Schema
200 OK none ModelReplacementValidationResponse

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/monitoringDataDeletions/

Delete deployment monitoring data.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/monitoringDataDeletions/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "end": "2019-08-24T14:15:22Z",
  "modelId": "string",
  "start": "2019-08-24T14:15:22Z"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body MonitoringDataDeletePayload false none

Responses

Status Meaning Description Schema
200 OK none None
404 Not Found Deployment or model not found. None

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/onDemandReports/

Add report to execution queue.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/onDemandReports/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "id": "string"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body ScheduledReportOnDemmand false none

Responses

Status Meaning Description Schema
200 OK Scheduled report job was addded to execution. None

Response Headers

Status Header Type Format Description
200 Location string URL to poll to track report generation has finished.

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/predictionInputs/fromDataset/

Assigns prediction dataset to the external deployment to enable the analysis of historical model performance. Multiple datasets containing historical predictions for the external deployment can be uploaded. This requires one request for each dataset. For a regression deployment, predictions can be either an int or float. For a classification (binary/multiclass) deployment, predictions must be lists with each list containing probabilities for each class.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/predictionInputs/fromDataset/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "datasetId": "string",
  "datasetVersionId": "string"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body PredictionDatasetAssignment false none

Responses

Status Meaning Description Schema
202 Accepted Submitted successfully. None
405 Method Not Allowed Data can only be uploaded to an external deployment. None
422 Unprocessable Entity Unable to process predictions upload. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/predictionResults/

Retrieve predictions results of the deployment.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/predictionResults/ \
  -H "Accept: application/json" \
  -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.
modelId query string false The id of the model for which prediction results are being retrieved.
start query string(date-time) false Start of the period for which prediction results are being retrieved.
end query string(date-time) false End of the period for which prediction results are being retrieved.
batchId query any false The id of the batch for which prediction results are being retrieved.
actualsPresent query boolean false Filters predictions results to only those who have actuals present or with missing actuals.
deploymentId path string true Unique identifier of the deployment.
Accept header string false Requested MIME type for the returned data

Enumerated Values

Parameter Value
Accept [application/json, text/csv]

Example responses

200 Response

{
  "associationIdColumnNames": [
    "string"
  ],
  "count": 0,
  "data": [
    {
      "actual": 0,
      "associationId": "string",
      "forecastDistance": 0,
      "modelId": "string",
      "predicted": 0,
      "timestamp": "2019-08-24T14:15:22Z"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Responses

Status Meaning Description Schema
200 OK none string

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/predictionsOverTime/

Retrieve metrics about predictions, such as row count, mean predicted value, mean probabilities, and class distribution, over a specific time range.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/predictionsOverTime/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
bucketSize query string false Time duration of buckets
segmentAttribute query string false The name of the segment on which segment analysis is being performed.
segmentValue query string false The value of the segmentAttribute to segment on.
modelId query any false The id of the models for which metrics are being retrieved.
targetClass query any false Target class to filter out results.
includePercentiles query string false Include percentiles in the response, only applicable to deployments with binary classification and regression target.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
bucketSize [PT1H, P1D, P7D, P1M]
includePercentiles [false, False, true, True]

Example responses

200 Response

{
  "baselines": [
    {
      "classDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "meanPredictedValue": 0,
      "meanProbabilities": [
        {
          "className": "string",
          "value": 0
        }
      ],
      "modelId": "string",
      "percentiles": [
        {
          "percent": 0,
          "value": 0
        }
      ],
      "predictionsWarningCount": 0,
      "rowCount": 0
    }
  ],
  "buckets": [
    {
      "classDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "meanPredictedValue": 0,
      "meanProbabilities": [
        {
          "className": "string",
          "value": 0
        }
      ],
      "modelId": "string",
      "percentiles": [
        {
          "percent": 0,
          "value": 0
        }
      ],
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "predictionsWarningCount": 0,
      "rowCount": 0
    }
  ],
  "segmentAttribute": "string",
  "segmentValue": ""
}

Responses

Status Meaning Description Schema
200 OK Predictions over time info retrieved. PredictionsOverTimeResponse

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/predictionsVsActualsOverTime/

Retrieve metrics about predictions and actuals, such as mean predicted & actual value, predicted & actual class distribution, over a specific time range.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/predictionsVsActualsOverTime/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
bucketSize query string false Time duration of buckets
segmentAttribute query string false The name of the segment on which segment analysis is being performed.
segmentValue query string false The value of the segmentAttribute to segment on.
modelId query any false The id of the models for which metrics are being retrieved.
targetClass query any false Target class to filter out results.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
bucketSize [PT1H, P1D, P7D, P1M]

Example responses

200 Response

{
  "baselines": [
    {
      "actualClassDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "meanActualValue": 0,
      "meanPredictedValue": 0,
      "modelId": "string",
      "predictedClassDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "rowCountTotal": 0,
      "rowCountWithActual": 0
    }
  ],
  "buckets": [
    {
      "actualClassDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "meanActualValue": 0,
      "meanPredictedValue": 0,
      "modelId": "string",
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "predictedClassDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "rowCountTotal": 0,
      "rowCountWithActual": 0
    }
  ],
  "segmentAttribute": "string",
  "segmentValue": "",
  "summary": {
    "rowCountTotal": 0,
    "rowCountWithActual": 0
  }
}

Responses

Status Meaning Description Schema
200 OK Predictions vs actuals over time info. PredictionsVsActualsOverTimeResponse

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/retrainingPolicies/

Retrieve a list of deployment retraining policies.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/ \
  -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.
deploymentId path string true Unique identifier of the deployment.

Example responses

200 Response

{
  "count": 0,
  "data": [
    {
      "action": "create_challenger",
      "autopilotOptions": {
        "blendBestModels": true,
        "mode": "auto",
        "runLeakageRemovedFeatureList": true,
        "scoringCodeOnly": true,
        "shapOnlyMode": true
      },
      "description": "string",
      "featureListStrategy": "informative_features",
      "id": "string",
      "latestRun": {
        "challengerId": "string",
        "errorMessage": "string",
        "finishTime": "2019-08-24T14:15:22Z",
        "id": "string",
        "modelPackageId": "string",
        "projectId": "string",
        "registeredModelId": "string",
        "startTime": "2019-08-24T14:15:22Z",
        "status": "string"
      },
      "modelSelectionStrategy": "autopilot_recommended",
      "name": "string",
      "projectOptions": {
        "cvMethod": "RandomCV",
        "holdoutPct": null,
        "metric": "Accuracy",
        "reps": null,
        "validationPct": null,
        "validationType": "CV"
      },
      "projectOptionsStrategy": "same_as_champion",
      "timeSeriesOptions": {
        "calendarId": "string",
        "differencingMethod": "auto",
        "exponentiallyWeightedMovingAlpha": 0,
        "periodicities": [
          {
            "timeSteps": 0,
            "timeUnit": "MILLISECOND"
          }
        ],
        "treatAsExponential": "auto"
      },
      "trigger": {
        "minIntervalBetweenRuns": "string",
        "schedule": {
          "dayOfMonth": [
            "*"
          ],
          "dayOfWeek": [
            "*"
          ],
          "hour": [
            "*"
          ],
          "minute": [
            "*"
          ],
          "month": [
            "*"
          ]
        },
        "statusDeclinesToFailing": true,
        "statusDeclinesToWarning": true,
        "statusStillInDecline": true,
        "type": "schedule"
      }
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Responses

Status Meaning Description Schema
200 OK Retrieve a list of deployment retraining policies. RetrainingPolicyListResponse
404 Not Found Deployment not found. None

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/retrainingPolicies/

Create a deployment retraining policy.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "action": "create_challenger",
  "autopilotOptions": {
    "blendBestModels": true,
    "mode": "auto",
    "runLeakageRemovedFeatureList": true,
    "scoringCodeOnly": true,
    "shapOnlyMode": true
  },
  "description": null,
  "featureListStrategy": "informative_features",
  "modelSelectionStrategy": "autopilot_recommended",
  "name": "string",
  "projectOptions": {
    "cvMethod": "RandomCV",
    "holdoutPct": null,
    "metric": "Accuracy",
    "reps": null,
    "validationPct": null,
    "validationType": "CV"
  },
  "projectOptionsStrategy": "same_as_champion",
  "timeSeriesOptions": {
    "calendarId": "string",
    "differencingMethod": "auto",
    "exponentiallyWeightedMovingAlpha": 0,
    "periodicities": [
      {
        "timeSteps": 0,
        "timeUnit": "MILLISECOND"
      }
    ],
    "treatAsExponential": "auto"
  },
  "trigger": {
    "minIntervalBetweenRuns": "string",
    "schedule": {
      "dayOfMonth": [
        "*"
      ],
      "dayOfWeek": [
        "*"
      ],
      "hour": [
        "*"
      ],
      "minute": [
        "*"
      ],
      "month": [
        "*"
      ]
    },
    "statusDeclinesToFailing": true,
    "statusDeclinesToWarning": true,
    "statusStillInDecline": true,
    "type": "schedule"
  }
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body RetrainingPolicyCreate false none

Example responses

200 Response

{
  "action": "create_challenger",
  "autopilotOptions": {
    "blendBestModels": true,
    "mode": "auto",
    "runLeakageRemovedFeatureList": true,
    "scoringCodeOnly": true,
    "shapOnlyMode": true
  },
  "description": "string",
  "featureListStrategy": "informative_features",
  "id": "string",
  "latestRun": {
    "challengerId": "string",
    "errorMessage": "string",
    "finishTime": "2019-08-24T14:15:22Z",
    "id": "string",
    "modelPackageId": "string",
    "projectId": "string",
    "registeredModelId": "string",
    "startTime": "2019-08-24T14:15:22Z",
    "status": "string"
  },
  "modelSelectionStrategy": "autopilot_recommended",
  "name": "string",
  "projectOptions": {
    "cvMethod": "RandomCV",
    "holdoutPct": null,
    "metric": "Accuracy",
    "reps": null,
    "validationPct": null,
    "validationType": "CV"
  },
  "projectOptionsStrategy": "same_as_champion",
  "timeSeriesOptions": {
    "calendarId": "string",
    "differencingMethod": "auto",
    "exponentiallyWeightedMovingAlpha": 0,
    "periodicities": [
      {
        "timeSteps": 0,
        "timeUnit": "MILLISECOND"
      }
    ],
    "treatAsExponential": "auto"
  },
  "trigger": {
    "minIntervalBetweenRuns": "string",
    "schedule": {
      "dayOfMonth": [
        "*"
      ],
      "dayOfWeek": [
        "*"
      ],
      "hour": [
        "*"
      ],
      "minute": [
        "*"
      ],
      "month": [
        "*"
      ]
    },
    "statusDeclinesToFailing": true,
    "statusDeclinesToWarning": true,
    "statusStillInDecline": true,
    "type": "schedule"
  }
}

Responses

Status Meaning Description Schema
200 OK none RetrainingPolicyRetrieve
404 Not Found Deployment not found. None

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

BearerAuth

DELETE /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/

Delete a deployment retraining policy.

Code samples

# You can also use wget
curl -X DELETE https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
retrainingPolicyId path string true ID of the retraining policy.

Responses

Status Meaning Description Schema
200 OK Delete a deployment retraining policy. None
404 Not Found Deployment or retraining policy not found. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/

Retrieve a deployment retraining policy.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
retrainingPolicyId path string true ID of the retraining policy.

Example responses

200 Response

{
  "action": "create_challenger",
  "autopilotOptions": {
    "blendBestModels": true,
    "mode": "auto",
    "runLeakageRemovedFeatureList": true,
    "scoringCodeOnly": true,
    "shapOnlyMode": true
  },
  "description": "string",
  "featureListStrategy": "informative_features",
  "id": "string",
  "latestRun": {
    "challengerId": "string",
    "errorMessage": "string",
    "finishTime": "2019-08-24T14:15:22Z",
    "id": "string",
    "modelPackageId": "string",
    "projectId": "string",
    "registeredModelId": "string",
    "startTime": "2019-08-24T14:15:22Z",
    "status": "string"
  },
  "modelSelectionStrategy": "autopilot_recommended",
  "name": "string",
  "projectOptions": {
    "cvMethod": "RandomCV",
    "holdoutPct": null,
    "metric": "Accuracy",
    "reps": null,
    "validationPct": null,
    "validationType": "CV"
  },
  "projectOptionsStrategy": "same_as_champion",
  "timeSeriesOptions": {
    "calendarId": "string",
    "differencingMethod": "auto",
    "exponentiallyWeightedMovingAlpha": 0,
    "periodicities": [
      {
        "timeSteps": 0,
        "timeUnit": "MILLISECOND"
      }
    ],
    "treatAsExponential": "auto"
  },
  "trigger": {
    "minIntervalBetweenRuns": "string",
    "schedule": {
      "dayOfMonth": [
        "*"
      ],
      "dayOfWeek": [
        "*"
      ],
      "hour": [
        "*"
      ],
      "minute": [
        "*"
      ],
      "month": [
        "*"
      ]
    },
    "statusDeclinesToFailing": true,
    "statusDeclinesToWarning": true,
    "statusStillInDecline": true,
    "type": "schedule"
  }
}

Responses

Status Meaning Description Schema
200 OK Retrieve a deployment retraining policy. RetrainingPolicyRetrieve
404 Not Found Deployment or retraining policy not found. None

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

BearerAuth

PATCH /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/

Update a deployment retraining policy.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "action": "create_challenger",
  "autopilotOptions": {
    "blendBestModels": true,
    "mode": "auto",
    "runLeakageRemovedFeatureList": true,
    "scoringCodeOnly": true,
    "shapOnlyMode": true
  },
  "description": "string",
  "featureListStrategy": "informative_features",
  "modelSelectionStrategy": "autopilot_recommended",
  "name": "string",
  "projectOptions": {
    "cvMethod": "RandomCV",
    "holdoutPct": null,
    "metric": "Accuracy",
    "reps": null,
    "validationPct": null,
    "validationType": "CV"
  },
  "projectOptionsStrategy": "same_as_champion",
  "timeSeriesOptions": {
    "calendarId": "string",
    "differencingMethod": "auto",
    "exponentiallyWeightedMovingAlpha": 0,
    "periodicities": [
      {
        "timeSteps": 0,
        "timeUnit": "MILLISECOND"
      }
    ],
    "treatAsExponential": "auto"
  },
  "trigger": {
    "minIntervalBetweenRuns": "string",
    "schedule": {
      "dayOfMonth": [
        "*"
      ],
      "dayOfWeek": [
        "*"
      ],
      "hour": [
        "*"
      ],
      "minute": [
        "*"
      ],
      "month": [
        "*"
      ]
    },
    "statusDeclinesToFailing": true,
    "statusDeclinesToWarning": true,
    "statusStillInDecline": true,
    "type": "schedule"
  }
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
retrainingPolicyId path string true ID of the retraining policy.
body body RetrainingPolicyUpdate false none

Example responses

200 Response

{
  "action": "create_challenger",
  "autopilotOptions": {
    "blendBestModels": true,
    "mode": "auto",
    "runLeakageRemovedFeatureList": true,
    "scoringCodeOnly": true,
    "shapOnlyMode": true
  },
  "description": "string",
  "featureListStrategy": "informative_features",
  "id": "string",
  "latestRun": {
    "challengerId": "string",
    "errorMessage": "string",
    "finishTime": "2019-08-24T14:15:22Z",
    "id": "string",
    "modelPackageId": "string",
    "projectId": "string",
    "registeredModelId": "string",
    "startTime": "2019-08-24T14:15:22Z",
    "status": "string"
  },
  "modelSelectionStrategy": "autopilot_recommended",
  "name": "string",
  "projectOptions": {
    "cvMethod": "RandomCV",
    "holdoutPct": null,
    "metric": "Accuracy",
    "reps": null,
    "validationPct": null,
    "validationType": "CV"
  },
  "projectOptionsStrategy": "same_as_champion",
  "timeSeriesOptions": {
    "calendarId": "string",
    "differencingMethod": "auto",
    "exponentiallyWeightedMovingAlpha": 0,
    "periodicities": [
      {
        "timeSteps": 0,
        "timeUnit": "MILLISECOND"
      }
    ],
    "treatAsExponential": "auto"
  },
  "trigger": {
    "minIntervalBetweenRuns": "string",
    "schedule": {
      "dayOfMonth": [
        "*"
      ],
      "dayOfWeek": [
        "*"
      ],
      "hour": [
        "*"
      ],
      "minute": [
        "*"
      ],
      "month": [
        "*"
      ]
    },
    "statusDeclinesToFailing": true,
    "statusDeclinesToWarning": true,
    "statusStillInDecline": true,
    "type": "schedule"
  }
}

Responses

Status Meaning Description Schema
200 OK none RetrainingPolicyRetrieve
404 Not Found Deployment or retraining policy not found. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/

Retrieve a list of deployment retraining policy runs.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/ \
  -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.
deploymentId path string true Unique identifier of the deployment.
retrainingPolicyId path string true ID of the retraining policy.

Example responses

200 Response

{
  "count": 0,
  "data": [
    {
      "challengerId": "string",
      "errorMessage": "string",
      "finishTime": "2019-08-24T14:15:22Z",
      "id": "string",
      "modelPackageId": "string",
      "projectId": "string",
      "registeredModelId": "string",
      "startTime": "2019-08-24T14:15:22Z",
      "status": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Responses

Status Meaning Description Schema
200 OK Retrieve a list of deployment retraining policy runs. RetrainingPolicyRunListResponse
404 Not Found Deployment or retraining policy not found. None

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/

Initiate a deployment retraining policy run.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
retrainingPolicyId path string true ID of the retraining policy.

Responses

Status Meaning Description Schema
200 OK none None
404 Not Found Deployment or retraining policy not found. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/{runId}/

Retrieve a single deployment retraining policy run.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/{runId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
retrainingPolicyId path string true ID of the retraining policy.
runId path string true ID of the retraining policy run.

Example responses

200 Response

{
  "challengerId": "string",
  "errorMessage": "string",
  "finishTime": "2019-08-24T14:15:22Z",
  "id": "string",
  "modelPackageId": "string",
  "projectId": "string",
  "registeredModelId": "string",
  "startTime": "2019-08-24T14:15:22Z",
  "status": "string"
}

Responses

Status Meaning Description Schema
200 OK Retrieve a single deployment retraining policy run. RetrainingPolicyRunRetrieve
404 Not Found Deployment or retraining policy not found. None

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

BearerAuth

PATCH /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/{runId}/

Update a single deployment retraining policy run.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/{runId}/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "status": "cancelled"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
retrainingPolicyId path string true ID of the retraining policy.
runId path string true ID of the retraining policy run.
body body RetrainingPolicyRunUpdate false none

Example responses

200 Response

{
  "challengerId": "string",
  "errorMessage": "string",
  "finishTime": "2019-08-24T14:15:22Z",
  "id": "string",
  "modelPackageId": "string",
  "projectId": "string",
  "registeredModelId": "string",
  "startTime": "2019-08-24T14:15:22Z",
  "status": "string"
}

Responses

Status Meaning Description Schema
200 OK Update a single deployment retraining policy run. RetrainingPolicyRunRetrieve
404 Not Found Deployment or retraining policy not found. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/retrainingSettings/

Retrieve deployment retraining settings.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingSettings/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.

Example responses

200 Response

{
  "dataset": {
    "id": "string",
    "name": "string"
  },
  "predictionEnvironment": {
    "id": "string",
    "name": "string"
  },
  "retrainingUser": {
    "id": "string",
    "username": "string"
  }
}

Responses

Status Meaning Description Schema
200 OK Retrieve deployment retraining settings. RetrainingSettingsRetrieve
404 Not Found Deployment not found. None

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

BearerAuth

PATCH /api/v2/deployments/{deploymentId}/retrainingSettings/

Update deployment retraining settings.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingSettings/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "credentialId": "string",
  "datasetId": "string",
  "predictionEnvironmentId": "string",
  "retrainingUserId": "string"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body RetrainingSettingsUpdate false none

Responses

Status Meaning Description Schema
200 OK Update deployment retraining settings. None
404 Not Found Deployment not found. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/scoringCode/

Retrieve Scoring Code of the current deployed model for making predictions outside of a DataRobot prediction server. 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 at https://javadoc.io/doc/com.datarobot/datarobot-prediction/latest/index.html to be able to use it inside an existing Java application.

With 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" documentation in DataRobot application for more information.

Note Cannot retrieve source code if agent is included.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/scoringCode/ \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
sourceCode query string false Whether source code or binary of the Scoring Code will be retrieved
includeAgent query string false Whether the Scoring code retrieved will include tracking agent
includePe query string false Please use includePredictionExplanations parameter instead
includePredictionExplanations query string false Whether the Scoring Code retrieved will include prediction explanations
includePredictionIntervals query string false Whether the Scoring Code retrieved will include prediction intervals
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
sourceCode [false, False, true, True]
includeAgent [false, False, true, True]
includePe [false, False, true, True]
includePredictionExplanations [false, False, true, True]
includePredictionIntervals [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 Indicating the content is supposed to be downloaded as an attachment
200 Content-Type string application/java-archive

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

BearerAuth

POST /api/v2/deployments/{deploymentId}/scoringCodeBuilds/

Build Java package containing Scoring Code with agent integration.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/scoringCodeBuilds/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "includeAgent": true,
  "includePredictionExplanations": true,
  "includePredictionIntervals": true
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body DeploymentsScoringCodeBuildPayload false none

Responses

Status Meaning Description Schema
200 OK none None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/serviceStats/

Retrieve all deployment service health metrics over a single period of time.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/serviceStats/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
executionTimeQuantile query number false Quantile for executionTime metric.
responseTimeQuantile query number false Quantile for responseTime metric.
slowRequestsThreshold query integer false Threshold for slowRequests metric.
segmentAttribute query string false The name of a segment attribute used for segment analysis.
segmentValue query string false The value of the segmentAttribute to segment on.
modelId query string false The id of the model for which metrics are being retrieved.
monitoringType query string false The monitoring type for which segment attributes and segment values are being retrieved. Can be one of three options which corresponds to a deployment monitoring tab
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
segmentAttribute [DataRobot-Consumer, DataRobot-Remote-IP, DataRobot-Host-IP]
monitoringType [serviceHealth, dataDrift, accuracy, humility, batchServiceHealth, batchDataDrift, batchAccuracy, customMetrics, batchCustomMetrics]

Example responses

200 Response

{
  "metrics": {
    "cacheHitRatio": 0,
    "executionTime": 0,
    "medianLoad": 0,
    "numConsumers": 0,
    "peakLoad": 0,
    "responseTime": 0,
    "serverErrorRate": 0,
    "slowRequests": 0,
    "totalPredictions": 0,
    "totalRequests": 0,
    "userErrorRate": 0
  },
  "modelId": "string",
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "segmentAttribute": "string",
  "segmentValue": ""
}

Responses

Status Meaning Description Schema
200 OK Service health metric data retrieved. ServiceStatsForTimeRangeResponse

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/serviceStatsOverTime/

Retrieve values for one single deployment service health metric over time.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/serviceStatsOverTime/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
bucketSize query string(duration) false The time duration of a bucket. Needs to be multiple of one hour. Can not be longer than the total length of the period. If not set, a default value will be calculated based on the start and end time.
metric query string false Name of the metric. See below for a list of supported metrics.
quantile query number false A quantile for resulting data, used if metric is executionTime or responseTime, defaults to 0.5.
threshold query integer false A threshold for filtering results, used if metric is slowQueries, defaults to 1000.
segmentAttribute query string false The name of a segment attribute used for segment analysis.
segmentValue query string false The value of the segmentAttribute to segment on.
modelId query string false The id of the model for which metrics are being retrieved.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
metric [totalPredictions, totalRequests, slowRequests, executionTime, responseTime, userErrorRate, serverErrorRate, numConsumers, cacheHitRatio, medianLoad, peakLoad]
segmentAttribute [DataRobot-Consumer, DataRobot-Remote-IP, DataRobot-Host-IP]

Example responses

200 Response

{
  "buckets": [
    {
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "value": 0
    }
  ],
  "metric": "string",
  "modelId": "string",
  "segmentAttribute": "string",
  "segmentValue": "",
  "summary": {
    "period": {
      "end": "2019-08-24T14:15:22Z",
      "start": "2019-08-24T14:15:22Z"
    },
    "value": 0
  }
}

Responses

Status Meaning Description Schema
200 OK Service health metric data retrieved. ServiceStatsOverTimeResponse

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/settings/

Retrieve deployment settings.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/settings/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.

Example responses

200 Response

{
  "associationId": {
    "columnNames": [
      "string"
    ],
    "requiredInPredictionRequests": true
  },
  "automaticActuals": {
    "enabled": true
  },
  "biasAndFairness": {
    "fairnessMetricsSet": "proportionalParity",
    "fairnessThreshold": 1,
    "preferableTargetValue": true,
    "protectedFeatures": [
      "string"
    ]
  },
  "challengerModels": {
    "enabled": true
  },
  "featureDrift": {
    "enabled": true
  },
  "humility": {
    "enabled": true
  },
  "predictionIntervals": {
    "enabled": true,
    "percentiles": [
      0
    ]
  },
  "predictionWarning": {
    "customBoundaries": {
      "lower": 0,
      "upper": 0
    },
    "enabled": true
  },
  "predictionsByForecastDate": {
    "columnName": "string",
    "datetimeFormat": "string",
    "enabled": true
  },
  "predictionsDataCollection": {
    "enabled": true
  },
  "segmentAnalysis": {
    "attributes": [
      "string"
    ],
    "enabled": true
  },
  "targetDrift": {
    "enabled": true
  }
}

Responses

Status Meaning Description Schema
200 OK The deployment settings DeploymentSettingsResponse
404 Not Found Either the deployment does not exist or the user does not have permission to view the deployment. None

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

BearerAuth

PATCH /api/v2/deployments/{deploymentId}/settings/

Updates deployment settings.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/settings/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "associationId": {
    "columnNames": [
      "string"
    ],
    "requiredInPredictionRequests": true
  },
  "automaticActuals": {
    "enabled": true
  },
  "biasAndFairness": {
    "fairnessMetricsSet": "proportionalParity",
    "fairnessThreshold": 1,
    "preferableTargetValue": true,
    "protectedFeatures": [
      "string"
    ]
  },
  "challengerModels": {
    "enabled": true
  },
  "featureDrift": {
    "enabled": true
  },
  "humility": {
    "enabled": true
  },
  "predictionIntervals": {
    "enabled": true,
    "percentiles": [
      0
    ]
  },
  "predictionWarning": {
    "customBoundaries": {
      "lower": 0,
      "upper": 0
    },
    "enabled": true
  },
  "predictionsByForecastDate": {
    "columnName": "string",
    "datetimeFormat": "string",
    "enabled": true
  },
  "predictionsDataCollection": {
    "enabled": true
  },
  "segmentAnalysis": {
    "attributes": [
      "string"
    ],
    "enabled": true
  },
  "targetDrift": {
    "enabled": true
  }
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body DeploymentSettingsUpdate false none

Responses

Status Meaning Description Schema
202 Accepted Job submitted. See Location header. None
403 Forbidden User can view deployment but does not have permission to update settings. None
404 Not Found Either the deployment does not exist or the user does not have permission to view the deployment. None
409 Conflict The proposed settings changes are invalid and would result in a logical conflict. None
422 Unprocessable Entity The provided settings changes could not be processed. None

Response Headers

Status Header Type Format Description
202 Location string url the location to poll for settings update status

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/sharedRoles/

Get a list of users, groups and organizations who have access to this deployment and their roles.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/sharedRoles/?offset=0&limit=10 \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
id query string false Only return roles for a user, group or organization with this identifier.
offset query integer true This many results will be skipped
limit query integer true At most this many results are returned
name query string false Only return roles for a user, group or organization with this name.
shareRecipientType query string false List access controls for recipients with this type.
deploymentId path string true The deployment ID.

Enumerated Values

Parameter Value
shareRecipientType [user, group, organization]

Example responses

200 Response

{
  "count": 0,
  "data": [
    {
      "id": "string",
      "name": "string",
      "role": "ADMIN",
      "shareRecipientType": "user"
    }
  ],
  "next": "string",
  "previous": "string",
  "totalCount": 0
}

Responses

Status Meaning Description Schema
200 OK none SharingListV2Response
404 Not Found Either the deployment does not exist or the user does not have permissions to view the deployment. None
422 Unprocessable Entity Both username and userId were specified None

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

BearerAuth

PATCH /api/v2/deployments/{deploymentId}/sharedRoles/

Set roles for users on this model deployment.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/sharedRoles/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "operation": "updateRoles",
  "roles": [
    {
      "canShare": true,
      "role": "string",
      "shareRecipientType": "user",
      "username": "string"
    }
  ]
}

Parameters

Name In Type Required Description
deploymentId path string true The deployment ID.
body body SharedRolesUpdateWithGrant false none

Responses

Status Meaning Description Schema
204 No Content Roles updated successfully. None
409 Conflict The request would leave the project without an owner. None
422 Unprocessable Entity One of the users in the request does not exist, or the request is otherwise invalid None

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

BearerAuth

PATCH /api/v2/deployments/{deploymentId}/status/

Change deployment status.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/status/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "status": "active"
}

Parameters

Name In Type Required Description
deploymentId path string true Unique identifier of the deployment.
body body DeploymentStatusUpdate false none

Responses

Status Meaning Description Schema
202 Accepted Job submitted. See Location header. None
409 Conflict Deployment is already in process of status change or already in requested status. None
422 Unprocessable Entity Deployment status change request could not be processed. None

Response Headers

Status Header Type Format Description
202 Location string URL for tracking async job status.

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/targetDrift/

Retrieve target drift data.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/targetDrift/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
start query string(date-time) false Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
end query string(date-time) false End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
modelId query string false An ID of the model in the deployment. If not set, defaults to the deployment current model.
metric query string false Metric used to calculate drift score.
segmentAttribute query string false The name of a segment attribute used for segment analysis.
segmentValue query string false The value of the segmentAttribute to segment on.
batchId query any false The id of the batch for which metrics are being retrieved.
deploymentId path string true Unique identifier of the deployment.

Enumerated Values

Parameter Value
metric [psi, kl_divergence, dissimilarity, hellinger, js_divergence]

Example responses

200 Response

{
  "baselineSampleSize": 0,
  "batchId": [],
  "driftScore": 0,
  "metric": "psi",
  "modelId": "string",
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "sampleSize": 0,
  "segmentAttribute": "string",
  "segmentValue": "",
  "targetName": "string",
  "type": "numeric"
}

Responses

Status Meaning Description Schema
200 OK Target drift over specified time period retrieved. TargetDriftResponse

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

BearerAuth

GET /api/v2/predictionServers/

List prediction servers available for a user.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/predictionServers/ \
  -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.

Example responses

200 Response

{
  "count": 0,
  "data": [
    {
      "batchPredictions": {
        "processing": 0,
        "queued": 0
      },
      "datarobot-key": "string",
      "id": "string",
      "url": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Responses

Status Meaning Description Schema
200 OK none PredictionServerListResponse

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

BearerAuth

Schemas

AccessControlV2

{
  "id": "string",
  "name": "string",
  "role": "ADMIN",
  "shareRecipientType": "user"
}

Properties

Name Type Required Restrictions Description
id string true The identifier of the recipient.
name string true The name of the recipient.
role string true The role of the recipient on this entity.
shareRecipientType string true The type of the recipient.

Enumerated Values

Property Value
role [ADMIN, CONSUMER, DATA_SCIENTIST, EDITOR, OBSERVER, OWNER, READ_ONLY, READ_WRITE, USER]
shareRecipientType [user, group, organization]

AccuracyLegacyTimeBucket

{
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "sampleSize": 0,
  "value": 0,
  "valuePerClass": "\n                {\n                    \"class1\": 0.880778024500618,\n                    \"class2\": 0.5294117647058824,\n                    \"class3\": 0.4117647058823529\n                }\n            "
}

Properties

Name Type Required Restrictions Description
period TimeRange true Start and end of the bucket's queried period, null if bucket is calculated on training data.
sampleSize integer¦null true Number of predictions used to calculate the metric.
value number¦null true Value of the metric, null if no value.
valuePerClass object¦null false A dict keyed by class names with metric calculated for specific classes as values, if targetClass is set. Deprecated and to be removed in v2.35, use perClass instead.

AccuracyOverTimeResponse

{
  "baseline": {
    "period": {
      "end": "2019-08-24T14:15:22Z",
      "start": "2019-08-24T14:15:22Z"
    },
    "sampleSize": 0,
    "value": 0,
    "valuePerClass": "\n                {\n                    \"class1\": 0.880778024500618,\n                    \"class2\": 0.5294117647058824,\n                    \"class3\": 0.4117647058823529\n                }\n            "
  },
  "baselines": [
    {
      "modelId": "string",
      "perClass": [
        {
          "className": "string",
          "value": 0
        }
      ],
      "sampleSize": 0,
      "value": 0
    }
  ],
  "buckets": [
    {
      "modelId": "string",
      "perClass": [
        {
          "className": "string",
          "value": 0
        }
      ],
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "sampleSize": 0,
      "value": 0,
      "valuePerClass": "\n                {\n                    \"class1\": 0.880778024500618,\n                    \"class2\": 0.5294117647058824,\n                    \"class3\": 0.4117647058823529\n                }\n            "
    }
  ],
  "metric": "AUC",
  "modelId": "string",
  "segmentAttribute": "string",
  "segmentValue": "",
  "summary": {
    "period": {
      "end": "2019-08-24T14:15:22Z",
      "start": "2019-08-24T14:15:22Z"
    },
    "sampleSize": 0,
    "value": 0,
    "valuePerClass": "\n                {\n                    \"class1\": 0.880778024500618,\n                    \"class2\": 0.5294117647058824,\n                    \"class3\": 0.4117647058823529\n                }\n            "
  }
}

Properties

Name Type Required Restrictions Description
baseline AccuracyLegacyTimeBucket true A bucket object containing metric info calculated on training baseline. Deprecated and to be removed in v2.35, use baselines field instead.
baselines [AccuracyTimeBaselineBucket] true Accuracy metric training baseline.
buckets [AccuracyTimeBucket] true Accuracy metric for requested models and time buckets.
metric string true The metric being retrieved.
modelId string false The id of the model for which metrics are being retrieved. Deprecated and to be removed in v2.35, use modelId in each baseline or bucket object.
segmentAttribute string¦null false The name of the segment on which segment analysis is being performed.
segmentValue string¦null false The value of the segmentAttribute to segment on.
summary AccuracyLegacyTimeBucket true A bucket object containing metric info calculated. Deprecated and to be removed in v2.35, use summaries field with includeSummaries query param to get accuracy metrics computed over the whole time range.

Enumerated Values

Property Value
metric [AUC, Accuracy, Balanced Accuracy, F1, FPR, FVE Binomial, FVE Gamma, FVE Multinomial, FVE Poisson, FVE Tweedie, Gamma Deviance, Gini Norm, Kolmogorov-Smirnov, LogLoss, MAD, MAE, MAPE, MCC, NPV, PPV, Poisson Deviance, R Squared, RMSE, RMSLE, Rate@Top10%, Rate@Top5%, TNR, TPR, Tweedie Deviance]

AccuracyPerClass

{
  "className": "string",
  "value": 0
}

Properties

Name Type Required Restrictions Description
className string true Name of the class.
value number¦null true Value of the metric.

AccuracyResponse

{
  "batchIds": [
    "string"
  ],
  "metrics": "\n                {\"metrics\": {\n                    \"LogLoss\": {\n                        \"baselineValue\": 0.454221484838069,\n                        \"value\": 0.880778024500618,\n                        \"percentChange\": -93.91\n                    },\n                    \"AUC\": {\n                        \"baselineValue\": 0.8690358459556535,\n                        \"value\": 0.5294117647058824,\n                        \"percentChange\": -39.08\n                    },\n                    \"Kolmogorov-Smirnov\": {\n                        \"baselineValue\": 0.5753202944706626,\n                        \"value\": 0.4117647058823529,\n                        \"percentChange\": -28.43\n                    },\n                    \"Rate@Top10%\": {\n                        \"baselineValue\": 0.9603223806571606,\n                        \"value\": 1.0,\n                        \"percentChange\": 4.13\n                    },\n                    \"Gini Norm\": {\n                        \"baselineValue\": 0.7380716919113071,\n                        \"value\": 0.05882352941176472,\n                        \"percentChange\": -92.03\n                    }\n                }\n                ",
  "modelId": "string",
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "segmentAttribute": "string",
  "segmentValue": "",
  "targetClasses": "string"
}

Properties

Name Type Required Restrictions Description
batchIds [string] false ID of the batches used to calculate accuracy metrics.
metrics object true Accuracy metrics of the deployment, keyed by metric names,
each value is a metric object with detail on a single metric.
For classification deployments:
- LogLoss
- AUC
- Kolmogorov - Smirnov
- Gini Norm
- Rate @ Top10 %
For regression deployments:
- RMSE
- MAE
- Gamma Deviance
- Tweedie Deviance
- R Squared
modelId string false The id of the model for which metrics are being retrieved.
period TimeRange false Time Range used to calculate accuracy metrics.
segmentAttribute string¦null false The name of the segment on which segment analysis is being performed.
segmentValue string¦null false The value of the segmentAttribute to segment on.
targetClasses string¦null false Target classes provided in the request.

AccuracyTimeBaselineBucket

{
  "modelId": "string",
  "perClass": [
    {
      "className": "string",
      "value": 0
    }
  ],
  "sampleSize": 0,
  "value": 0
}

Properties

Name Type Required Restrictions Description
modelId string false The id of the model for which metrics are being retrieved.
perClass [AccuracyPerClass] false Accuracy metric values for selected classes, only available for multiclass deployments.
sampleSize integer true Number of rows used to calculate the metric.
value number¦null true Accuracy metric value.

AccuracyTimeBucket

{
  "modelId": "string",
  "perClass": [
    {
      "className": "string",
      "value": 0
    }
  ],
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "sampleSize": 0,
  "value": 0,
  "valuePerClass": "\n                {\n                    \"class1\": 0.880778024500618,\n                    \"class2\": 0.5294117647058824,\n                    \"class3\": 0.4117647058823529\n                }\n            "
}

Properties

Name Type Required Restrictions Description
modelId string false The id of the model for which metrics are being retrieved.
perClass [AccuracyPerClass] false Accuracy metric values for selected classes, only available for multiclass deployments.
period TimeRange true Time period of the bucket.
sampleSize integer true Number of rows used to calculate the metric.
value number¦null true Accuracy metric value.
valuePerClass object¦null false A dict keyed by class names with metric calculated for specific classes as values, if targetClass is set. Deprecated and to be removed in v2.35, use perClass instead.

Actual

{
  "actualValue": 0,
  "associationId": "string",
  "timestamp": "2019-08-24T14:15:22Z",
  "wasActedOn": true
}

Properties

Name Type Required Restrictions Description
actualValue any true The actual value of a prediction. Will be numeric for regression models and a string label for classification models.

anyOf

Name Type Required Restrictions Description
» anonymous integer false none

or

Name Type Required Restrictions Description
» anonymous number false none

or

Name Type Required Restrictions Description
» anonymous string false none

continued

Name Type Required Restrictions Description
associationId string true maxLength: 128
A unique identifier used with a predicted row.
timestamp string(date-time)¦null false The datetime when actual values were obtained, formatted according to RFC3339.
wasActedOn boolean¦null false Indicates if the prediction was acted on in a way that could have affected the actual outcome. For example, if a hospital patient is predicted to be readmitted in 30 days, extra procedures or new medication might be given to mitigate this problem, influencing the actual outcome of the prediction.

ActualClassDistribution

{
  "className": "string",
  "count": 0,
  "percent": 0
}

Properties

Name Type Required Restrictions Description
className string true Name of the class.
count integer true Count of actual rows labeled with a class in the bucket.
percent number true Percent of actual rows labeled with a class in the bucket.

AssociationID

{
  "columnNames": [
    "string"
  ],
  "requiredInPredictionRequests": true
}

Properties

Name Type Required Restrictions Description
columnNames [string]¦null true Indicates the columns that will be used to associate actuals with predictions.
requiredInPredictionRequests boolean true Indicates whether the association ID is required in prediction requests.

AssociationIDUpdate

{
  "columnNames": [
    "string"
  ],
  "requiredInPredictionRequests": true
}

Properties

Name Type Required Restrictions Description
columnNames [string]¦null false maxItems: 1
minItems: 1

List of column names used to represent an association id. Currently, exactly one column name may be provided.
requiredInPredictionRequests boolean false Whether or not association id values are required in each prediction request for this deployment. Note that you may not change an association ID's column names after they have been set and predictions including those columns have been made

AutomatiActuals

{
  "enabled": true
}

Properties

Name Type Required Restrictions Description
enabled boolean true Indicates whether automatic actuals is enabled for the deployment.

AutopilotOptions

{
  "blendBestModels": true,
  "mode": "auto",
  "runLeakageRemovedFeatureList": true,
  "scoringCodeOnly": true,
  "shapOnlyMode": true
}

Properties

Name Type Required Restrictions Description
blendBestModels boolean false Blend best models during Autopilot run. This option is not supported in SHAP-only mode.
mode string false The autopilot mode.
runLeakageRemovedFeatureList boolean false Run Autopilot on Leakage Removed feature list (if exists).
scoringCodeOnly boolean false Keep only models that can be converted to scorable java code during Autopilot run.
shapOnlyMode boolean false Include only models with SHAP value support.

Enumerated Values

Property Value
mode [auto, comprehensive, quick]

BatchField

{
  "columnName": "string"
}

Properties

Name Type Required Restrictions Description
columnName string¦null true Column name

BatchPeriod

{
  "end": "2019-08-24T14:15:22Z",
  "start": "2019-08-24T14:15:22Z"
}

Properties

Name Type Required Restrictions Description
end string(date-time)¦null true End time of the bucket
start string(date-time)¦null true Start time of the bucket

BatchPredictionStatus

{
  "processing": 0,
  "queued": 0
}

Properties

Name Type Required Restrictions Description
processing integer true minimum: 0
Number of jobs processing
queued integer true minimum: 0
Number of jobs queued

BiasAndFairness

{
  "fairnessMetricsSet": "proportionalParity",
  "fairnessThreshold": 1,
  "preferableTargetValue": true,
  "protectedFeatures": [
    "string"
  ]
}

Properties

Name Type Required Restrictions Description
fairnessMetricsSet string true A set of fairness metrics to use for calculating fairness.
fairnessThreshold number true maximum: 1
minimum: 0

Threshold value of the fairness metric.
preferableTargetValue any true A target value that should be treated as a positive outcome for the prediction.

anyOf

Name Type Required Restrictions Description
» anonymous boolean false none

or

Name Type Required Restrictions Description
» anonymous integer false none

or

Name Type Required Restrictions Description
» anonymous string false none

continued

Name Type Required Restrictions Description
protectedFeatures [string] true maxItems: 10
minItems: 1

A list of feature to mark as protected for Bias and Fairness measurement.

Enumerated Values

Property Value
fairnessMetricsSet [proportionalParity, equalParity, predictionBalance, trueFavorableAndUnfavorableRateParity, favorableAndUnfavorablePredictiveValueParity]

ChallengerCreate

{
  "modelPackageId": "string",
  "name": "string",
  "predictionEnvironmentId": "string"
}

Properties

Name Type Required Restrictions Description
modelPackageId string true ID of the model package to add as a challenger.
name string true maxLength: 512
Human-readable name for the challenger.
predictionEnvironmentId string false ID of the Prediction Environment the challenger should use. If prediction environments are enabled, this is required

ChallengerListResponse

{
  "data": [
    {
      "id": "string",
      "model": {
        "datasetName": "string",
        "description": "string",
        "executionType": "string",
        "id": "string",
        "isDeprecated": true,
        "name": "string",
        "projectId": "string",
        "projectName": "string"
      },
      "modelPackage": {
        "id": "string",
        "name": "string",
        "registeredModelId": "string"
      },
      "name": "string",
      "predictionEnvironment": {
        "id": "string",
        "name": "string"
      }
    }
  ]
}

Properties

Name Type Required Restrictions Description
data [ChallengerResponse] true List of challengers.

ChallengerResponse

{
  "id": "string",
  "model": {
    "datasetName": "string",
    "description": "string",
    "executionType": "string",
    "id": "string",
    "isDeprecated": true,
    "name": "string",
    "projectId": "string",
    "projectName": "string"
  },
  "modelPackage": {
    "id": "string",
    "name": "string",
    "registeredModelId": "string"
  },
  "name": "string",
  "predictionEnvironment": {
    "id": "string",
    "name": "string"
  }
}

Properties

Name Type Required Restrictions Description
id string true ID of the challenger.
model ModelResponse true Model of the challenger.
modelPackage ModelPackageResponse true modelPackage of the challenger.
name string true Name of the challenger.
predictionEnvironment PredictionEnvironmentResponse false Prediction environment used by the challenger

ChallengerScore

{
  "timestamp": "2019-08-24T14:15:22Z"
}

Properties

Name Type Required Restrictions Description
timestamp string(date-time) false The date and time in ISO8601 format, challenger models will be scored on data starting from deployment creation until timestamp. If not specified UTC current time is used.

ChallengerUpdate

{
  "name": "string",
  "predictionEnvironmentId": "string"
}

Properties

Name Type Required Restrictions Description
name string false maxLength: 512
Human-readable name for the challenger.
predictionEnvironmentId string false ID of the Prediction Environment the challenger should use.

Challengers

{
  "enabled": true
}

Properties

Name Type Required Restrictions Description
enabled boolean true Indicates whether challenger models are enabled for the deployment.

ClassDistribution

{
  "className": "string",
  "count": 0,
  "percent": 0
}

Properties

Name Type Required Restrictions Description
className string true Name of the class
count integer true Count of rows labeled with a class in the bucket
percent number true Percent of rows labeled with a class in the bucket

CustomBoundaries

{
  "lower": 0,
  "upper": 0
}

Properties

Name Type Required Restrictions Description
lower number true All predictions less than provided value are considered anomalous.
upper number true All predictions greater than provided value are considered anomalous.

CustomMetricDetails

{
  "earliestDate": "2019-08-24T14:15:22Z",
  "latestDate": "2019-08-24T14:15:22Z"
}

Properties

Name Type Required Restrictions Description
earliestDate string(date-time)¦null true The earliest date of the custom metrics values.
latestDate string(date-time)¦null true The latest date of the custom metrics values.

CustomMetricSegmentDataset

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

Properties

Name Type Required Restrictions Description
column string false Name of the column that contains segment values.
name string true Name of the segment on which segment analysis is being performed.
value string false Value of the segment attribute to segment on.

CustomMetricSummary

{
  "metric": {
    "baselineValue": 0,
    "id": "string",
    "name": "string",
    "percentChange": 0,
    "sampleCount": 0,
    "value": 0
  },
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  }
}

Properties

Name Type Required Restrictions Description
metric MetricSummary true Summary of the custom metric.
period MetricPeriodBucket true A time period defined by a start and end time.

CustomMetricsBulkSummary

{
  "details": {
    "earliestDate": "2019-08-24T14:15:22Z",
    "latestDate": "2019-08-24T14:15:22Z"
  },
  "metrics": [],
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  }
}

Properties

Name Type Required Restrictions Description
details CustomMetricDetails true Additional information related to custom metrics.
metrics [MetricSummary] true maxItems: 10
Custom metrics summaries.
period MetricPeriodBucket true A time period defined by a start and end time.

Dataset

{
  "id": "string",
  "name": "string"
}

Properties

Name Type Required Restrictions Description
id string true ID of the retraining dataset.
name string true Name of the retraining dataset.

DatasetsCredential

{
  "catalogVersionId": "string",
  "credentialId": "string",
  "url": "string"
}

Properties

Name Type Required Restrictions Description
catalogVersionId string true ID of the catalog version
credentialId string true ID of the credential store to be used for the given catalog version
url string¦null false The URL of the datasource

DeletedDeploymentListResponse

{
  "count": 0,
  "data": [
    {
      "deletedAt": "2019-08-24T14:15:22Z",
      "id": "string",
      "label": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Properties

Name Type Required Restrictions Description
count integer false Number of items returned on this page.
data [DeletedDeploymentResponse] true List of deleted deployments.
next string(uri)¦null true URL pointing to the next page (if null, there is no next page).
previous string(uri)¦null true URL pointing to the previous page (if null, there is no previous page).

DeletedDeploymentResponse

{
  "deletedAt": "2019-08-24T14:15:22Z",
  "id": "string",
  "label": "string"
}

Properties

Name Type Required Restrictions Description
deletedAt string(date-time) true The date and time of when the deployment was deleted, in ISO 8601 format.
id string true ID of the deployment.
label string true maxLength: 512
Label of the deployment.

DeploymentAccuracyHealthResponse

{
  "endDate": "2019-08-24T14:15:22Z",
  "message": "string",
  "startDate": "2019-08-24T14:15:22Z",
  "status": "failing"
}

Properties

Name Type Required Restrictions Description
endDate string(date-time)¦null true End date of accuracy health period.
message string true A message providing more detail on the status.
startDate string(date-time)¦null true Start date of accuracy health period.
status string true Accuracy health status.

Enumerated Values

Property Value
status [failing, notStarted, passing, unavailable, unknown, warning]

DeploymentActuals

{
  "data": [
    {
      "actualValue": 0,
      "associationId": "string",
      "timestamp": "2019-08-24T14:15:22Z",
      "wasActedOn": true
    }
  ],
  "keepActualsWithoutPredictions": true
}

Properties

Name Type Required Restrictions Description
data [Actual] true minItems: 1
A list of actual objects that describes actual values. Minimum size of the list is 1 and maximum size is 10000 items. An actual object has the following schema.
keepActualsWithoutPredictions boolean false Indicates if actual without predictions are kept.

DeploymentCapabilitiesResponse

{
  "supportsAutomaticActuals": true,
  "supportsChallengerModels": true,
  "supportsFeatureDriftTracking": true,
  "supportsFeatureTypeInfoValidation": true,
  "supportsHumilityRecommendedRules": true,
  "supportsHumilityRules": true,
  "supportsHumilityRulesDefaultCalculations": true,
  "supportsModelReplacement": true,
  "supportsPortablePredictionServer": true,
  "supportsPredictionIntervals": true,
  "supportsPredictionWarning": true,
  "supportsRetraining": true,
  "supportsScoringCodeDownload": true,
  "supportsSecondaryDatasets": true,
  "supportsSegmentedAnalysisDriftAndAccuracy": true,
  "supportsShapBasedPredictionExplanations": true,
  "supportsTargetDriftTracking": true
}

Properties

Name Type Required Restrictions Description
supportsAutomaticActuals boolean false With this feature enabled, DataRobot infers actual values from time series history data and automatically feeds them back for accuracy estimation.
supportsChallengerModels boolean true If the deployment supports challenger models.
supportsFeatureDriftTracking boolean true If the deployment supports feature drift tracking.
supportsFeatureTypeInfoValidation boolean false If the deployment supports feature type information validation. This will be True for deployments created from imported model packages whose feature data contains feature type information.
supportsHumilityRecommendedRules boolean true If the deployment supports calculating values for humility recommended rules.
supportsHumilityRules boolean true If the deployment supports humble ai.
supportsHumilityRulesDefaultCalculations boolean true If the deployment supports calculating default values for humility rules.
supportsModelReplacement boolean true If the deployment supports model replacement.
supportsPortablePredictionServer boolean false If the deployment supports portable prediction servers. this enables to downloada dedicated model package to be deployed on external prediction environments
supportsPredictionIntervals boolean true if the deployment supports prediction intervals.
supportsPredictionWarning boolean true If the deployment supports prediction warnings.
supportsRetraining boolean false Whether deployment supports retraining.
supportsScoringCodeDownload boolean false If the currently deployed model supports scoring code download.
supportsSecondaryDatasets boolean true If the deployments supports secondary datasets.
supportsSegmentedAnalysisDriftAndAccuracy boolean false If the deployment supports tracking features in training and predictions data for segmented analysis of drift and accuracy.
supportsShapBasedPredictionExplanations boolean false If the currently deployed model supports shap based prediction explanations.
supportsTargetDriftTracking boolean true If the deployment supports target drift tracking.

DeploymentCapabilitiesRetrieveResponse

{
  "data": [
    {
      "messages": [
        "string"
      ],
      "name": "string",
      "supported": true
    }
  ]
}

Properties

Name Type Required Restrictions Description
data [DeploymentCapability] true List of all capabilities.

DeploymentCapability

{
  "messages": [
    "string"
  ],
  "name": "string",
  "supported": true
}

Properties

Name Type Required Restrictions Description
messages [string] true Messages explaining why the capability is supported or not supported.
name string true The name of the capability.
supported boolean true If the capability is supported.

DeploymentCreateFromLearningModel

{
  "defaultPredictionServerId": "string",
  "description": null,
  "importance": "CRITICAL",
  "label": "string",
  "modelId": "string",
  "predictionThreshold": 1,
  "status": "active"
}

Properties

Name Type Required Restrictions Description
defaultPredictionServerId string false ID of the default prediction server for deployment. Required for DataRobot Cloud, must be omitted for Enterprise installations.
description string¦null true maxLength: 10000
A description for the deployment.
importance string¦null false Importance of the deployment. Defaults to LOW when MLOps is enabled, must not be provided when MLOps disabled.
label string true maxLength: 512
A human-readable name for the deployment.
modelId string true ID of the model to be deployed.
predictionThreshold number false maximum: 1
minimum: 0
Prediction threshold used for binary classification. If not specified, model default prediction threshold will be used.
status string¦null false Status of the deployment

Enumerated Values

Property Value
importance [CRITICAL, HIGH, MODERATE, LOW]
status [active, inactive]

DeploymentCreateResponse

{
  "id": "string"
}

Properties

Name Type Required Restrictions Description
id string true The ID of the created deployment.

DeploymentDatasetCreate

{
  "actualValueColumn": "string",
  "associationIdColumn": "string",
  "datasetId": "string",
  "datasetVersionId": "string",
  "keepActualsWithoutPredictions": true,
  "password": "string",
  "timestampColumn": "string",
  "user": "string",
  "wasActedOnColumn": "string"
}

Properties

Name Type Required Restrictions Description
actualValueColumn string true Column name that contains actual values.
associationIdColumn string true Column name that contains unique identifiers used with a predicted rows.
datasetId string true The ID of dataset from catalog.
datasetVersionId string¦null false Version of dataset to retrieve.
keepActualsWithoutPredictions boolean false Indicates if actual without predictions are kept.
password string false The password for database authentication.
timestampColumn string false Column name that contain datetime when actual values were obtained.
user string false The username for database authentication.
wasActedOnColumn string false Column name that contains boolean values if any action was made based on predictions data.

DeploymentDefaultPredictionServerResponse

{
  "datarobot-key": "string",
  "id": "string",
  "url": "string"
}

Properties

Name Type Required Restrictions Description
datarobot-key string true The datarobot-key header used in requests to this prediction server.
id string¦null true ID of the prediction server for the deployment.
url string true URL of the prediction server.

DeploymentGovernanceResponse

{
  "approvalStatus": "PENDING",
  "hasOpenedChangeRequests": true
}

Properties

Name Type Required Restrictions Description
approvalStatus string true Status to show whether the deployment was approved or not. It also shows up as a part of metadata within the prediction response.
hasOpenedChangeRequests boolean true If there are change request related to this deployment with PENDING status.

Enumerated Values

Property Value
approvalStatus [PENDING, APPROVED]

DeploymentListResponse

{
  "count": 0,
  "data": [
    {
      "accuracyHealth": {
        "endDate": "2019-08-24T14:15:22Z",
        "message": "string",
        "startDate": "2019-08-24T14:15:22Z",
        "status": "failing"
      },
      "approvalStatus": "PENDING",
      "capabilities": {
        "supportsAutomaticActuals": true,
        "supportsChallengerModels": true,
        "supportsFeatureDriftTracking": true,
        "supportsFeatureTypeInfoValidation": true,
        "supportsHumilityRecommendedRules": true,
        "supportsHumilityRules": true,
        "supportsHumilityRulesDefaultCalculations": true,
        "supportsModelReplacement": true,
        "supportsPortablePredictionServer": true,
        "supportsPredictionIntervals": true,
        "supportsPredictionWarning": true,
        "supportsRetraining": true,
        "supportsScoringCodeDownload": true,
        "supportsSecondaryDatasets": true,
        "supportsSegmentedAnalysisDriftAndAccuracy": true,
        "supportsShapBasedPredictionExplanations": true,
        "supportsTargetDriftTracking": true
      },
      "createdAt": "2019-08-24T14:15:22Z",
      "defaultPredictionServer": {
        "datarobot-key": "string",
        "id": "string",
        "url": "string"
      },
      "description": "string",
      "governance": {
        "approvalStatus": "PENDING",
        "hasOpenedChangeRequests": true
      },
      "hasError": true,
      "id": "string",
      "importance": "CRITICAL",
      "label": "string",
      "model": {
        "buildEnvironmentType": "string",
        "customModelImage": {
          "customModelId": "string",
          "customModelName": "string",
          "customModelVersionId": "string",
          "customModelVersionLabel": "string",
          "executionEnvironmentId": "string",
          "executionEnvironmentName": "string",
          "executionEnvironmentVersionId": "string",
          "executionEnvironmentVersionLabel": "string"
        },
        "decisionFlowId": "string",
        "decisionFlowVersionId": "string",
        "deployedAt": "2019-08-24T14:15:22Z",
        "hasDecisionFlow": true,
        "id": "string",
        "isDeprecated": true,
        "projectId": "string",
        "projectName": "string",
        "targetName": "string",
        "targetType": "string",
        "type": "string",
        "unstructuredModelKind": true,
        "unsupervisedMode": true,
        "unsupervisedType": "anomaly"
      },
      "modelHealth": {
        "endDate": "2019-08-24T14:15:22Z",
        "message": "string",
        "startDate": "2019-08-24T14:15:22Z",
        "status": "failing"
      },
      "modelPackage": {
        "id": "string",
        "name": "string",
        "registeredModelId": "string"
      },
      "modelPackageInitialDownload": {
        "timestamp": "2019-08-24T14:15:22Z"
      },
      "openedChangeRequests": [
        "string"
      ],
      "owners": {
        "count": 0,
        "preview": [
          {
            "email": "string",
            "firstName": "string",
            "id": "string",
            "lastName": "string"
          }
        ]
      },
      "permissions": [
        "CAN_ADD_CHALLENGERS"
      ],
      "predictionEnvironment": {
        "id": "string",
        "isManagedByManagementAgent": true,
        "name": "string",
        "platform": "aws",
        "plugin": "string",
        "supportedModelFormats": [
          "datarobot"
        ]
      },
      "predictionUsage": {
        "dailyRates": [
          0
        ],
        "lastTimestamp": "2019-08-24T14:15:22Z"
      },
      "scoringCodeInitialDownload": {
        "timestamp": "2019-08-24T14:15:22Z"
      },
      "serviceHealth": {
        "endDate": "2019-08-24T14:15:22Z",
        "startDate": "2019-08-24T14:15:22Z",
        "status": "failing"
      },
      "settings": {
        "batchMonitoringEnabled": true,
        "humbleAiEnabled": true,
        "predictionIntervalsEnabled": true,
        "predictionWarningEnabled": true
      },
      "status": "active",
      "userProvidedId": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com",
  "totalCount": 0
}

Properties

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

DeploymentModelCustomModelImageResponse

{
  "customModelId": "string",
  "customModelName": "string",
  "customModelVersionId": "string",
  "customModelVersionLabel": "string",
  "executionEnvironmentId": "string",
  "executionEnvironmentName": "string",
  "executionEnvironmentVersionId": "string",
  "executionEnvironmentVersionLabel": "string"
}

Properties

Name Type Required Restrictions Description
customModelId string true ID of the custom model.
customModelName string true Name of the custom model.
customModelVersionId string true ID of the custom model version.
customModelVersionLabel string true Label of the custom model version.
executionEnvironmentId string true ID of the execution environment.
executionEnvironmentName string true Name of the execution environment.
executionEnvironmentVersionId string true ID of the execution environment version.
executionEnvironmentVersionLabel string true Label of the execution environment version.

DeploymentModelHealthResponse

{
  "endDate": "2019-08-24T14:15:22Z",
  "message": "string",
  "startDate": "2019-08-24T14:15:22Z",
  "status": "failing"
}

Properties

Name Type Required Restrictions Description
endDate string(date-time)¦null true End date of model health period.
message string true A message providing more detail on the status.
startDate string(date-time)¦null true Start date of model health period.
status string true Model health status.

Enumerated Values

Property Value
status [failing, notStarted, passing, unavailable, unknown, warning]

DeploymentModelPackageInitialDownloadResponse

{
  "timestamp": "2019-08-24T14:15:22Z"
}

Properties

Name Type Required Restrictions Description
timestamp string(date-time)¦null true Timestamp of the first time model package was downloaded.

DeploymentModelPackageResponse

{
  "id": "string",
  "name": "string",
  "registeredModelId": "string"
}

Properties

Name Type Required Restrictions Description
id string true ID of the ModelPackage.
name string true Name of the ModelPackage.
registeredModelId string¦null true ID of the associated registered model

DeploymentModelResponse

{
  "buildEnvironmentType": "string",
  "customModelImage": {
    "customModelId": "string",
    "customModelName": "string",
    "customModelVersionId": "string",
    "customModelVersionLabel": "string",
    "executionEnvironmentId": "string",
    "executionEnvironmentName": "string",
    "executionEnvironmentVersionId": "string",
    "executionEnvironmentVersionLabel": "string"
  },
  "decisionFlowId": "string",
  "decisionFlowVersionId": "string",
  "deployedAt": "2019-08-24T14:15:22Z",
  "hasDecisionFlow": true,
  "id": "string",
  "isDeprecated": true,
  "projectId": "string",
  "projectName": "string",
  "targetName": "string",
  "targetType": "string",
  "type": "string",
  "unstructuredModelKind": true,
  "unsupervisedMode": true,
  "unsupervisedType": "anomaly"
}

Properties

Name Type Required Restrictions Description
buildEnvironmentType string¦null false Build environment type of the current model.
customModelImage DeploymentModelCustomModelImageResponse false Information related to the custom model image of the deployment.
decisionFlowId string¦null false The ID of the decision flow if the deployment has one.
decisionFlowVersionId string¦null false The ID of the decision flow version if the deployment has one.
deployedAt string(date-time)¦null false Timestamp of when current model was deployed.
hasDecisionFlow boolean false True if this deployment contains a Decision Flow
id string true ID of the current model.
isDeprecated boolean true Whether the current model is deprecated model. eg. python2 based model.
projectId string¦null false Project ID of the current model.
projectName string¦null true Project name of the current model.
targetName string true Target name of the current model.
targetType string true Target type of the current model.
type string true Type of the current model.
unstructuredModelKind boolean true Whether the current model is an unstructured model.
unsupervisedMode boolean true Whether the current model's project is unsupervised.
unsupervisedType string¦null false Only valid when unsupervisedMode is True. The type of unsupervised project, anomaly or clustering. If unsupervisedMode, defaults to 'anomaly'.

Enumerated Values

Property Value
unsupervisedType [anomaly, clustering]

DeploymentOwnerResponse

{
  "email": "string",
  "firstName": "string",
  "id": "string",
  "lastName": "string"
}

Properties

Name Type Required Restrictions Description
email string¦null true Email address of the owner.
firstName string¦null true First name of the owner.
id string true ID of the owner.
lastName string¦null true Last name of the owner.

DeploymentOwnersResponse

{
  "count": 0,
  "preview": [
    {
      "email": "string",
      "firstName": "string",
      "id": "string",
      "lastName": "string"
    }
  ]
}

Properties

Name Type Required Restrictions Description
count integer true Total count of owners.
preview [DeploymentOwnerResponse] true A list of owner objects.

DeploymentPermanentDelete

{
  "action": "PermanentlyErase",
  "deploymentIds": [
    "string"
  ]
}

Properties

Name Type Required Restrictions Description
action string true Action to perform on these deleted deployments.
deploymentIds [string] true maxItems: 100
minItems: 1
ID of a list of deleted deployments to perform action on.

Enumerated Values

Property Value
action PermanentlyErase

DeploymentPredictionEnvironmentResponse

{
  "id": "string",
  "isManagedByManagementAgent": true,
  "name": "string",
  "platform": "aws",
  "plugin": "string",
  "supportedModelFormats": [
    "datarobot"
  ]
}

Properties

Name Type Required Restrictions Description
id string¦null true ID of the PredictionEnvironment.
isManagedByManagementAgent boolean true True if PredictionEnvironment is using Management Agent.
name string true Name of the PredictionEnvironment.
platform string true Platform of the PredictionEnvironment.
plugin string¦null false Plugin name of the PredictionEnvironment.
supportedModelFormats [string] false maxItems: 4
minItems: 1
Model formats that the PredictionEnvironment supports.

Enumerated Values

Property Value
platform [aws, gcp, azure, onPremise, datarobot, openShift, other, snowflake]

DeploymentPredictionUsageResponse

{
  "dailyRates": [
    0
  ],
  "lastTimestamp": "2019-08-24T14:15:22Z"
}

Properties

Name Type Required Restrictions Description
dailyRates [integer] true Number of predictions made in the last 7 days.
lastTimestamp string(date-time)¦null true Timestamp of the last prediction request.

DeploymentRetrieveResponse

{
  "accuracyHealth": {
    "endDate": "2019-08-24T14:15:22Z",
    "message": "string",
    "startDate": "2019-08-24T14:15:22Z",
    "status": "failing"
  },
  "approvalStatus": "PENDING",
  "capabilities": {
    "supportsAutomaticActuals": true,
    "supportsChallengerModels": true,
    "supportsFeatureDriftTracking": true,
    "supportsFeatureTypeInfoValidation": true,
    "supportsHumilityRecommendedRules": true,
    "supportsHumilityRules": true,
    "supportsHumilityRulesDefaultCalculations": true,
    "supportsModelReplacement": true,
    "supportsPortablePredictionServer": true,
    "supportsPredictionIntervals": true,
    "supportsPredictionWarning": true,
    "supportsRetraining": true,
    "supportsScoringCodeDownload": true,
    "supportsSecondaryDatasets": true,
    "supportsSegmentedAnalysisDriftAndAccuracy": true,
    "supportsShapBasedPredictionExplanations": true,
    "supportsTargetDriftTracking": true
  },
  "createdAt": "2019-08-24T14:15:22Z",
  "defaultPredictionServer": {
    "datarobot-key": "string",
    "id": "string",
    "url": "string"
  },
  "description": "string",
  "governance": {
    "approvalStatus": "PENDING",
    "hasOpenedChangeRequests": true
  },
  "hasError": true,
  "id": "string",
  "importance": "CRITICAL",
  "label": "string",
  "model": {
    "buildEnvironmentType": "string",
    "customModelImage": {
      "customModelId": "string",
      "customModelName": "string",
      "customModelVersionId": "string",
      "customModelVersionLabel": "string",
      "executionEnvironmentId": "string",
      "executionEnvironmentName": "string",
      "executionEnvironmentVersionId": "string",
      "executionEnvironmentVersionLabel": "string"
    },
    "decisionFlowId": "string",
    "decisionFlowVersionId": "string",
    "deployedAt": "2019-08-24T14:15:22Z",
    "hasDecisionFlow": true,
    "id": "string",
    "isDeprecated": true,
    "projectId": "string",
    "projectName": "string",
    "targetName": "string",
    "targetType": "string",
    "type": "string",
    "unstructuredModelKind": true,
    "unsupervisedMode": true,
    "unsupervisedType": "anomaly"
  },
  "modelHealth": {
    "endDate": "2019-08-24T14:15:22Z",
    "message": "string",
    "startDate": "2019-08-24T14:15:22Z",
    "status": "failing"
  },
  "modelPackage": {
    "id": "string",
    "name": "string",
    "registeredModelId": "string"
  },
  "modelPackageInitialDownload": {
    "timestamp": "2019-08-24T14:15:22Z"
  },
  "openedChangeRequests": [
    "string"
  ],
  "owners": {
    "count": 0,
    "preview": [
      {
        "email": "string",
        "firstName": "string",
        "id": "string",
        "lastName": "string"
      }
    ]
  },
  "permissions": [
    "CAN_ADD_CHALLENGERS"
  ],
  "predictionEnvironment": {
    "id": "string",
    "isManagedByManagementAgent": true,
    "name": "string",
    "platform": "aws",
    "plugin": "string",
    "supportedModelFormats": [
      "datarobot"
    ]
  },
  "predictionUsage": {
    "dailyRates": [
      0
    ],
    "lastTimestamp": "2019-08-24T14:15:22Z"
  },
  "scoringCodeInitialDownload": {
    "timestamp": "2019-08-24T14:15:22Z"
  },
  "serviceHealth": {
    "endDate": "2019-08-24T14:15:22Z",
    "startDate": "2019-08-24T14:15:22Z",
    "status": "failing"
  },
  "settings": {
    "batchMonitoringEnabled": true,
    "humbleAiEnabled": true,
    "predictionIntervalsEnabled": true,
    "predictionWarningEnabled": true
  },
  "status": "active",
  "userProvidedId": "string"
}

Properties

Name Type Required Restrictions Description
accuracyHealth DeploymentAccuracyHealthResponse true Accuracy health of the deployment.
approvalStatus string false Status to show whether the deployment was approved or not. It also shows up as a part of metadata within the prediction response.
capabilities DeploymentCapabilitiesResponse true Capabilities of the deployment.
createdAt string(date-time) true The date and time of when the deployment was created, in ISO 8601 format.
defaultPredictionServer DeploymentDefaultPredictionServerResponse true The prediction server associated with the deployment.
description string¦null true Description of the deployment.
governance DeploymentGovernanceResponse false Deployment governance info.
hasError boolean false Whether the deployment is not operational because it failed to start properly.
id string true ID of the deployment.
importance string false Shows how important this deployment is.
label string true maxLength: 512
Label of the deployment.
model DeploymentModelResponse true Information related to the current model of the deployment.
modelHealth DeploymentModelHealthResponse true Model health of the deployment.
modelPackage DeploymentModelPackageResponse false Information related to the current ModelPackage.
modelPackageInitialDownload DeploymentModelPackageInitialDownloadResponse false If a model package has been downloaded for this deployment, then this will tell you when it was first downloaded.
openedChangeRequests [string] false An array of the change request IDs related to this deployment that have.
owners DeploymentOwnersResponse false Count and preview of owners of the deployment.
permissions [string] true Permissions that the user making the request has on the deployment.
predictionEnvironment DeploymentPredictionEnvironmentResponse false Information related to the current PredictionEnvironment.
predictionUsage DeploymentPredictionUsageResponse true Prediction usage of the deployment.
scoringCodeInitialDownload DeploymentScoringCodeInitialDownloadResponse false If scoring code has been downloaded for this deployment, then this will tell you when it was first downloaded.
serviceHealth DeploymentServiceHealthResponse true Service health of the deployment.
settings DeploymentSettingsInfo true Settings of the deployment.
status string true Displays current deployment status.
userProvidedId string false maxLength: 100
A user-provided unique ID associated with a deployment definition in a remote git repository.

Enumerated Values

Property Value
approvalStatus [PENDING, APPROVED]
importance [CRITICAL, HIGH, MODERATE, LOW]
status [active, archived, errored, inactive, launching, replacingModel, stopping]

DeploymentScoringCodeInitialDownloadResponse

{
  "timestamp": "2019-08-24T14:15:22Z"
}

Properties

Name Type Required Restrictions Description
timestamp string(date-time)¦null true Timestamp of the first time scoring code was downloaded.

DeploymentSecondaryDataset

{
  "catalogId": "string",
  "catalogVersionId": "string",
  "identifier": "string",
  "snapshotPolicy": "specified"
}

Properties

Name Type Required Restrictions Description
catalogId string true ID of the catalog item
catalogVersionId string true ID of the catalog version
identifier string true maxLength: 45
minLength: 1
minLength: 1
Short name of this table (used directly as part of generated feature names)
snapshotPolicy string true Policy to use by a dataset while making prediction

Enumerated Values

Property Value
snapshotPolicy [specified, latest, dynamic]

DeploymentServiceHealthResponse

{
  "endDate": "2019-08-24T14:15:22Z",
  "startDate": "2019-08-24T14:15:22Z",
  "status": "failing"
}

Properties

Name Type Required Restrictions Description
endDate string(date-time)¦null true End date of model service period.
startDate string(date-time)¦null true Start date of service health period.
status string true Service health status.

Enumerated Values

Property Value
status [failing, notStarted, passing, unavailable, unknown, warning]

DeploymentSettingsInfo

{
  "batchMonitoringEnabled": true,
  "humbleAiEnabled": true,
  "predictionIntervalsEnabled": true,
  "predictionWarningEnabled": true
}

Properties

Name Type Required Restrictions Description
batchMonitoringEnabled boolean false if batch monitoring is enabled.
humbleAiEnabled boolean false if humble ai is enabled.
predictionIntervalsEnabled boolean false If prediction intervals are enabled.
predictionWarningEnabled boolean false If prediction warning is enabled.

DeploymentSettingsResponse

{
  "associationId": {
    "columnNames": [
      "string"
    ],
    "requiredInPredictionRequests": true
  },
  "automaticActuals": {
    "enabled": true
  },
  "biasAndFairness": {
    "fairnessMetricsSet": "proportionalParity",
    "fairnessThreshold": 1,
    "preferableTargetValue": true,
    "protectedFeatures": [
      "string"
    ]
  },
  "challengerModels": {
    "enabled": true
  },
  "featureDrift": {
    "enabled": true
  },
  "humility": {
    "enabled": true
  },
  "predictionIntervals": {
    "enabled": true,
    "percentiles": [
      0
    ]
  },
  "predictionWarning": {
    "customBoundaries": {
      "lower": 0,
      "upper": 0
    },
    "enabled": true
  },
  "predictionsByForecastDate": {
    "columnName": "string",
    "datetimeFormat": "string",
    "enabled": true
  },
  "predictionsDataCollection": {
    "enabled": true
  },
  "segmentAnalysis": {
    "attributes": [
      "string"
    ],
    "enabled": true
  },
  "targetDrift": {
    "enabled": true
  }
}

Properties

Name Type Required Restrictions Description
associationId AssociationID true The association ID setting for the deployment.
automaticActuals AutomatiActuals false Automatic actuals setting for the deployment.
biasAndFairness BiasAndFairness false Bias and fairness setting for the deployment.
challengerModels Challengers false Challenger models setting for the deployment.
featureDrift FeatureDriftSetting true The feature drift setting for the deployment.
humility Humility false Humility setting for the deployment.
predictionIntervals PredictionIntervals true The prediction intervals setting for the deployment.
predictionWarning PredictionWarning false The prediction warning setting for the deployment.
predictionsByForecastDate ForecastDate false Forecast date setting for the deployment.
predictionsDataCollection PredictionsDataCollection false The predictions data collection setting for the deployment.
segmentAnalysis SegmentAnalysis false The segment analysis setting for the deployment.
targetDrift TargetDriftSetting true The target drift setting for the deployment.

DeploymentSettingsUpdate

{
  "associationId": {
    "columnNames": [
      "string"
    ],
    "requiredInPredictionRequests": true
  },
  "automaticActuals": {
    "enabled": true
  },
  "biasAndFairness": {
    "fairnessMetricsSet": "proportionalParity",
    "fairnessThreshold": 1,
    "preferableTargetValue": true,
    "protectedFeatures": [
      "string"
    ]
  },
  "challengerModels": {
    "enabled": true
  },
  "featureDrift": {
    "enabled": true
  },
  "humility": {
    "enabled": true
  },
  "predictionIntervals": {
    "enabled": true,
    "percentiles": [
      0
    ]
  },
  "predictionWarning": {
    "customBoundaries": {
      "lower": 0,
      "upper": 0
    },
    "enabled": true
  },
  "predictionsByForecastDate": {
    "columnName": "string",
    "datetimeFormat": "string",
    "enabled": true
  },
  "predictionsDataCollection": {
    "enabled": true
  },
  "segmentAnalysis": {
    "attributes": [
      "string"
    ],
    "enabled": true
  },
  "targetDrift": {
    "enabled": true
  }
}

Properties

Name Type Required Restrictions Description
associationId AssociationIDUpdate false Association id settings for the deployment.
automaticActuals AutomatiActuals false Automatic actuals setting for the deployment.
biasAndFairness BiasAndFairness false Bias and fairness setting for the deployment.
challengerModels Challengers false Challenger models setting for the deployment.
featureDrift FeatureDriftUpdate false Feature drift setting for the deployment.
humility Humility false Humility setting for the deployment.
predictionIntervals PredictionIntervalsUpdate false Prediction intervals setting for the deployment. Requires that the requested interval size is calculated prior to setting in this request.
predictionWarning PredictionWarningUpdate false Prediction warning setting for the deployment.
predictionsByForecastDate ForecastDate false Forecast date setting for the deployment.
predictionsDataCollection PredictionsDataCollection false The predictions data collection setting for the deployment.
segmentAnalysis SegmentAnalysisUpdate false The segment analysis setting for the deployment.
targetDrift TargetDriftUpdate false Target drift setting for the deployment.

DeploymentStatusUpdate

{
  "status": "active"
}

Properties

Name Type Required Restrictions Description
status string true Status that deployment should be transition in.

Enumerated Values

Property Value
status [active, inactive]

DeploymentUpdate

{
  "description": "string",
  "importance": "CRITICAL",
  "label": "string"
}

Properties

Name Type Required Restrictions Description
description string¦null false maxLength: 10000
A description for the deployment.
importance string false Shows how important this deployment is.
label string¦null false maxLength: 512
A human-readable name for the deployment.

Enumerated Values

Property Value
importance [CRITICAL, HIGH, MODERATE, LOW]

DeploymentsScoringCodeBuildPayload

{
  "includeAgent": true,
  "includePredictionExplanations": true,
  "includePredictionIntervals": true
}

Properties

Name Type Required Restrictions Description
includeAgent boolean false Whether the Scoring Code built will include tracking agent
includePredictionExplanations boolean false Whether the Scoring Code built will include prediction explanations
includePredictionIntervals boolean false Whether the Scoring Code built will include prediction intervals

FairnessOverTimeBucket

{
  "metricName": "proportionalParity",
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "scores": [
    {
      "absoluteValue": 0,
      "classesCount": 0,
      "healthyClassesCount": 0,
      "healthyCount": 0,
      "isStatisticallySignificant": true,
      "label": "string",
      "message": "string",
      "privilegedClass": "string",
      "sampleSize": 0,
      "totalCount": 1,
      "value": 1
    }
  ]
}

Properties

Name Type Required Restrictions Description
metricName string true Name of the metric.
period TimeRange true Time range for which fairness over time is computed.
scores [FairnessOverTimeScore] true List of per-feature fairness details.

Enumerated Values

Property Value
metricName [proportionalParity, equalParity, favorableClassBalance, unfavorableClassBalance, trueUnfavorableRateParity, trueFavorableRateParity, favorablePredictiveValueParity, unfavorablePredictiveValueParity]

FairnessOverTimeResponse

{
  "buckets": [
    {
      "metricName": "proportionalParity",
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "scores": [
        {
          "absoluteValue": 0,
          "classesCount": 0,
          "healthyClassesCount": 0,
          "healthyCount": 0,
          "isStatisticallySignificant": true,
          "label": "string",
          "message": "string",
          "privilegedClass": "string",
          "sampleSize": 0,
          "totalCount": 1,
          "value": 1
        }
      ]
    }
  ],
  "fairnessThreshold": 1,
  "favorableTargetOutcome": true,
  "modelId": "string",
  "modelPackageId": "string",
  "protectedFeature": "string",
  "summary": {
    "metricName": "proportionalParity",
    "period": {
      "end": "2019-08-24T14:15:22Z",
      "start": "2019-08-24T14:15:22Z"
    },
    "scores": [
      {
        "absoluteValue": 0,
        "classesCount": 0,
        "healthyClassesCount": 0,
        "healthyCount": 0,
        "isStatisticallySignificant": true,
        "label": "string",
        "message": "string",
        "privilegedClass": "string",
        "sampleSize": 0,
        "totalCount": 1,
        "value": 1
      }
    ]
  }
}

Properties

Name Type Required Restrictions Description
buckets [FairnessOverTimeBucket] true Per bucket summary.
fairnessThreshold number true maximum: 1
minimum: 0
Threshold used to compute fairness results.
favorableTargetOutcome any true Preferable class of target.

oneOf

Name Type Required Restrictions Description
» anonymous boolean false none

xor

Name Type Required Restrictions Description
» anonymous string false none

xor

Name Type Required Restrictions Description
» anonymous integer false none

continued

Name Type Required Restrictions Description
modelId string true Model Id for which fairness is computed.
modelPackageId string true Model package Id.
protectedFeature string false Name of the protected feature.
summary FairnessOverTimeBucket true Summary of per feature fairness.

FairnessOverTimeScore

{
  "absoluteValue": 0,
  "classesCount": 0,
  "healthyClassesCount": 0,
  "healthyCount": 0,
  "isStatisticallySignificant": true,
  "label": "string",
  "message": "string",
  "privilegedClass": "string",
  "sampleSize": 0,
  "totalCount": 1,
  "value": 1
}

Properties

Name Type Required Restrictions Description
absoluteValue number false Absolute fairness score.
classesCount integer false Count of occurences of the class within the data the fairness is calculated on.
healthyClassesCount integer false Count of statistically significant classes above fairness threshold.
healthyCount integer false minimum: 0
Total number of classes with fairness score above the threshold.
isStatisticallySignificant boolean false Class is statistically significant.
label string false Name of the feature.
message string false Explanation message.
privilegedClass string false Name of the privileged class (the one with the highest fairness score) within the feature.
sampleSize integer false minimum: 0 (exclusive)
Sample size used for fairness status calculation
totalCount integer false minimum: 1
Total number of classes.
value number false maximum: 1
minimum: 0
Fairness score in relation to the privileged class fairness score.

Feature

{
  "dateFormat": "string",
  "featureType": "string",
  "importance": 0,
  "knownInAdvance": true,
  "name": "string"
}

Properties

Name Type Required Restrictions Description
dateFormat string¦null true The date format string for how this feature was interpreted.
featureType string¦null true Feature type.
importance number¦null true Numeric measure of the relationship strength between the feature and target (independent of model or other features).
knownInAdvance boolean true Whether the feature was selected as known in advance in a time-series model, false for non-time-series models.
name string true Feature name.

FeatureDrift

{
  "baselineSampleSize": 0,
  "driftScore": 0,
  "featureImpact": 0,
  "name": "string",
  "sampleSize": 0,
  "type": "numeric"
}

Properties

Name Type Required Restrictions Description
baselineSampleSize integer true The sample size of the training data.
driftScore number¦null true The drift score for this feature.
featureImpact number true The feature impact score for this feature.
name string true The name of the feature.
sampleSize integer true The number of predictions used to compute the drift score.
type string true Type of the feature.

Enumerated Values

Property Value
type [numeric, categorical, text]

FeatureDriftOverTimeBucket

{
  "baselineSampleSize": 0,
  "driftScore": 0,
  "featureImpact": 0,
  "featureName": "string",
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "sampleSize": 0
}

Properties

Name Type Required Restrictions Description
baselineSampleSize integer true The sample size of the training data used during model creation
driftScore number¦null true The aggregated drift score for the target.
featureImpact number true The feature impact score of the feature.
featureName string true Name of the feature.
period TimeRange true Time range for which feature drift is computed.
sampleSize integer true The sample size in the query period used to calculate drift score.

FeatureDriftOverTimeFeature

{
  "featureName": "string",
  "featureType": "numeric"
}

Properties

Name Type Required Restrictions Description
featureName string true Name of the requested feature.
featureType string true Data type of the requested feature.

Enumerated Values

Property Value
featureType [numeric, categorical, text]

FeatureDriftOverTimeResponse

{
  "buckets": [
    {
      "baselineSampleSize": 0,
      "driftScore": 0,
      "featureImpact": 0,
      "featureName": "string",
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "sampleSize": 0
    }
  ],
  "features": [
    {
      "featureName": "string",
      "featureType": "numeric"
    }
  ],
  "metric": "string",
  "summaries": [
    {
      "featureImpact": 0,
      "featureName": "string"
    }
  ]
}

Properties

Name Type Required Restrictions Description
buckets [FeatureDriftOverTimeBucket] true A list of aggregated drift scores by feature over a given period.
features [FeatureDriftOverTimeFeature] true A list of the requested features and their feature type.
metric string true Name of requested metric.
summaries [FeatureDriftOverTimeSummary] true A list of aggregated drift scores by feature over a given period.

FeatureDriftOverTimeSummary

{
  "featureImpact": 0,
  "featureName": "string"
}

Properties

Name Type Required Restrictions Description
featureImpact number true The feature impact score of the feature.
featureName string true Name of the feature.

FeatureDriftResponse

{
  "batchId": [],
  "count": 0,
  "data": [
    {
      "baselineSampleSize": 0,
      "driftScore": 0,
      "featureImpact": 0,
      "name": "string",
      "sampleSize": 0,
      "type": "numeric"
    }
  ],
  "metric": "psi",
  "modelId": "string",
  "next": "string",
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "previous": "string",
  "segmentAttribute": "string",
  "segmentValue": "string"
}

Properties

Name Type Required Restrictions Description
batchId any false The id of the batch for which metrics are being retrieved.

oneOf

Name Type Required Restrictions Description
» anonymous string false none

xor

Name Type Required Restrictions Description
» anonymous [string] false maxItems: 25
none

continued

Name Type Required Restrictions Description
count integer false The number of items returned on this page.
data [FeatureDrift] true An array [DriftObject], each in the form described below
metric string false Metric used to calculate drift score.
modelId string true The id of the model for which the features drift is being retrieved.
next string¦null false A URL pointing to the next page (if null, there is no next page)
period TimeRange false An object with the keys "start" and "end" defining the period to retrieve features drift.
previous string¦null false A URL pointing to the previous page (if null, there is no previous page)
segmentAttribute string¦null false The name of the segment on which segment analysis is being performed.
segmentValue string¦null false The value of the segmentAttribute to segment on.

Enumerated Values

Property Value
metric [psi, kl_divergence, dissimilarity, hellinger, js_divergence]

FeatureDriftSetting

{
  "enabled": true
}

Properties

Name Type Required Restrictions Description
enabled boolean true Indicates whether feature drift tracking is enabled for this deployment.

FeatureDriftUpdate

{
  "enabled": true
}

Properties

Name Type Required Restrictions Description
enabled boolean true True if feature drift tracking is enabled for this deployment, false if otherwise.

FeatureListResponse

{
  "count": 0,
  "data": [
    {
      "dateFormat": "string",
      "featureType": "string",
      "importance": 0,
      "knownInAdvance": true,
      "name": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Properties

Name Type Required Restrictions Description
count integer false Number of items returned on this page.
data [Feature] true An array of dataset details.
next string(uri)¦null true URL pointing to the next page (if null, there is no next page).
previous string(uri)¦null true URL pointing to the previous page (if null, there is no previous page).

ForecastDate

{
  "columnName": "string",
  "datetimeFormat": "string",
  "enabled": true
}

Properties

Name Type Required Restrictions Description
columnName string¦null false The column name in prediction datasets to be used as forecast date
datetimeFormat string¦null false The datetime format of the forecast date column in prediction datasets.
enabled boolean true Indicates whether predictions by forecast dates is enabled for the deployment.

GrantAccessControlWithIdWithGrant

{
  "canShare": true,
  "id": "string",
  "role": "string",
  "shareRecipientType": "user"
}

Properties

Name Type Required Restrictions Description
canShare boolean false Whether the org/group/user should be able to share with others.If true, the org/group/user will be able to grant any role up to and includingtheir own to other orgs/groups/user. If role is NO_ROLE canShare is ignored.
id string true The ID of the recipient.
role string true The role of the recipient on this entity. One of OWNER, USER, OBSERVER.
shareRecipientType string true Describes the recipient type, either user, group, or organization.

Enumerated Values

Property Value
shareRecipientType [user, group, organization]

GrantAccessControlWithUsernameWithGrant

{
  "canShare": true,
  "role": "string",
  "shareRecipientType": "user",
  "username": "string"
}

Properties

Name Type Required Restrictions Description
canShare boolean false Whether the org/group/user should be able to share with others.If true, the org/group/user will be able to grant any role up to and includingtheir own to other orgs/groups/user. If role is NO_ROLE canShare is ignored.
role string true The role of the recipient on this entity. One of OWNER, USER, OBSERVER.
shareRecipientType string true Describes the recipient type, either user, group, or organization.
username string true Username of the user to update the access role for.

Enumerated Values

Property Value
shareRecipientType [user, group, organization]

Humility

{
  "enabled": true
}

Properties

Name Type Required Restrictions Description
enabled boolean true Indicates whether humility rules are enabled for the deployment.

HumilityStatsBucket

{
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "values": [
    {
      "ruleId": "string",
      "ruleName": "string",
      "value": 0
    }
  ]
}

Properties

Name Type Required Restrictions Description
period TimeRange true An object with the keys "start" and "end" defining the period.
values [HumilityStatsRule] true Rules response objects.

HumilityStatsOverTimeResponse

{
  "buckets": [
    {
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "values": [
        {
          "ruleId": "string",
          "ruleName": "string",
          "value": 0
        }
      ]
    }
  ],
  "modelId": "string",
  "segmentAttribute": "string",
  "segmentValue": "",
  "summary": {
    "period": {
      "end": "2019-08-24T14:15:22Z",
      "start": "2019-08-24T14:15:22Z"
    },
    "values": [
      {
        "ruleId": "string",
        "ruleName": "string",
        "value": 0
      }
    ]
  }
}

Properties

Name Type Required Restrictions Description
buckets [HumilityStatsBucket] true An array of bucket objects, representing service health stats of the deployment over time
modelId string false The id of the model for which metrics are being retrieved.
segmentAttribute string¦null false The name of the segment on which segment analysis is being performed.
segmentValue string¦null false The value of the segmentAttribute to segment on.
summary HumilityStatsBucket true A bucket object covering whole start/end time range

HumilityStatsResponse

{
  "data": [
    {
      "ruleId": "string",
      "ruleName": "string",
      "value": 0
    }
  ],
  "modelId": "string",
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "segmentAttribute": "string",
  "segmentValue": ""
}

Properties

Name Type Required Restrictions Description
data [HumilityStatsRule] true metrics rules
modelId string false The id of the model for which metrics are being retrieved.
period TimeRange true An object with the keys "start" and "end" defining the period.
segmentAttribute string¦null false The name of the segment on which segment analysis is being performed.
segmentValue string¦null false The value of the segmentAttribute to segment on.

HumilityStatsRule

{
  "ruleId": "string",
  "ruleName": "string",
  "value": 0
}

Properties

Name Type Required Restrictions Description
ruleId string true Id of the humility rule.
ruleName string true Name of the rule.
value integer true Number of times the rule was triggered.

MeanProbability

{
  "className": "string",
  "value": 0
}

Properties

Name Type Required Restrictions Description
className string true Name of the class
value number true Mean predicted probability for a class for all rows in the bucket

MetricBaselineValue

{
  "value": 0
}

Properties

Name Type Required Restrictions Description
value number true A reference value in given metric units.

MetricCreatePayload

{
  "baselineValues": [],
  "description": "string",
  "directionality": "higherIsBetter",
  "isModelSpecific": true,
  "name": "string",
  "sampleCount": {
    "columnName": "string"
  },
  "timeStep": "hour",
  "timestamp": {
    "columnName": "string",
    "timeFormat": "%m/%d/%Y"
  },
  "type": "average",
  "units": "string",
  "value": {
    "columnName": "string"
  }
}

Properties

Name Type Required Restrictions Description
baselineValues [MetricBaselineValue] true maxItems: 5
Baseline values
description string false maxLength: 1000
A description of the custom metric.
directionality string true Directionality of the custom metric.
isModelSpecific boolean true Determines whether the metric is related to the model or deployment.
name string true Name of the custom metric.
sampleCount SampleCountField false Points to a weight column if users provide pre-aggregated metric values. Used with columnar datasets.
timeStep string true Custom metric time bucket size.
timestamp MetricTimestampSpoofing false A custom metric timestamp spoofing when reading values from file, like dataset. By default, we replicate pd.to_datetime formatting behaviour.
type string true Type (and aggregation character) of a metric.
units string true Units or Y Label of given custom metric.
value ValueField false A custom metric value source when reading values from columnar dataset like a file.

Enumerated Values

Property Value
directionality [higherIsBetter, lowerIsBetter]
timeStep hour
type [average, gauge, sum]

MetricCreatedBy

{
  "id": "string"
}

Properties

Name Type Required Restrictions Description
id string true The ID of user who created custom metric.

MetricEntity

{
  "baselineValues": [
    {
      "value": 0
    }
  ],
  "createdAt": "2019-08-24T14:15:22Z",
  "createdBy": {
    "id": "string"
  },
  "description": "string",
  "directionality": "higherIsBetter",
  "displayChart": true,
  "id": "string",
  "isModelSpecific": true,
  "name": "string",
  "sampleCount": {
    "columnName": "string"
  },
  "timeStep": "hour",
  "timestamp": {
    "columnName": "string",
    "timeFormat": "%m/%d/%Y"
  },
  "type": "average",
  "units": "string",
  "value": {
    "columnName": "string"
  }
}

Properties

Name Type Required Restrictions Description
baselineValues [MetricBaselineValue] true maxItems: 5
Baseline values
createdAt string(date-time) true Custom metric creation timestamp.
createdBy MetricCreatedBy true The user that created custom metric.
description string false maxLength: 1000
A description of the custom metric.
directionality string true Directionality of the custom metric.
displayChart boolean false Indicates if UI should show chart by default.
id string true The ID of the custom metric.
isModelSpecific boolean true Determines whether the metric is related to the model or deployment.
name string true Name of the custom metric.
sampleCount SampleCountField false Points to a weight column if users provide pre-aggregated metric values. Used with columnar datasets.
timeStep string true Custom metric time bucket size.
timestamp MetricTimestampSpoofing false A custom metric timestamp spoofing when reading values from file, like dataset. By default, we replicate pd.to_datetime formatting behaviour.
type string true Type (and aggregation character) of a metric.
units string true Units or Y Label of given custom metric.
value ValueField false A custom metric value source when reading values from columnar dataset like a file.

Enumerated Values

Property Value
directionality [higherIsBetter, lowerIsBetter]
timeStep hour
type [average, gauge, sum]

MetricInputValueBucket

{
  "sampleSize": 1,
  "timestamp": "2019-08-24T14:15:22Z",
  "value": 0
}

Properties

Name Type Required Restrictions Description
sampleSize integer false Custom metric value sample size.
timestamp string(date-time)¦null false Value timestamp.
value number true Custom metric value to ingest.

MetricListResponse

{
  "count": 0,
  "data": [
    {
      "baselineValues": [
        {
          "value": 0
        }
      ],
      "createdAt": "2019-08-24T14:15:22Z",
      "createdBy": {
        "id": "string"
      },
      "description": "string",
      "directionality": "higherIsBetter",
      "displayChart": true,
      "id": "string",
      "isModelSpecific": true,
      "name": "string",
      "sampleCount": {
        "columnName": "string"
      },
      "timeStep": "hour",
      "timestamp": {
        "columnName": "string",
        "timeFormat": "%m/%d/%Y"
      },
      "type": "average",
      "units": "string",
      "value": {
        "columnName": "string"
      }
    }
  ],
  "next": "string",
  "previous": "string",
  "totalCount": 0
}

Properties

Name Type Required Restrictions Description
count integer true minimum: 0
Number of paginated entries.
data [MetricEntity] true A list of custom metrics.
next string¦null true URL to the next page, or null if there is no such page
previous string¦null true URL to the previous page, or null if there is no such page
totalCount integer true minimum: 0
Total number of entries.

MetricPeriodBucket

{
  "end": "2019-08-24T14:15:22Z",
  "start": "2019-08-24T14:15:22Z"
}

Properties

Name Type Required Restrictions Description
end string(date-time) true End of the bucket.
start string(date-time) true Start of the bucket.

MetricSummary

{
  "baselineValue": 0,
  "id": "string",
  "name": "string",
  "percentChange": 0,
  "sampleCount": 0,
  "value": 0
}

Properties

Name Type Required Restrictions Description
baselineValue number¦null true Baseline value.
id string true The ID of the custom metric.
name string true Name of the custom metric.
percentChange number¦null true Percentage change of the baseline over its baseline.
sampleCount integer¦null true Number of samples used to calculate the aggregated value.
value number¦null true Aggregated value of the custom metric.

MetricTimestampSpoofing

{
  "columnName": "string",
  "timeFormat": "%m/%d/%Y"
}

Properties

Name Type Required Restrictions Description
columnName string¦null false Column name
timeFormat string¦null false Format

Enumerated Values

Property Value
timeFormat [%m/%d/%Y, %m/%d/%y, %d/%m/%y, %m-%d-%Y, %m-%d-%y, %Y/%m/%d, %Y-%m-%d, %Y-%m-%d %H:%M:%S, %Y/%m/%d %H:%M:%S, %Y.%m.%d %H:%M:%S, %Y-%m-%d %H:%M, %Y/%m/%d %H:%M, %y/%m/%d, %y-%m-%d, %y-%m-%d %H:%M:%S, %y.%m.%d %H:%M:%S, %y/%m/%d %H:%M:%S, %y-%m-%d %H:%M, %y.%m.%d %H:%M, %y/%m/%d %H:%M, %m/%d/%Y %H:%M, %m/%d/%y %H:%M, %d/%m/%Y %H:%M, %d/%m/%y %H:%M, %m-%d-%Y %H:%M, %m-%d-%y %H:%M, %d-%m-%Y %H:%M, %d-%m-%y %H:%M, %m.%d.%Y %H:%M, %m/%d.%y %H:%M, %d.%m.%Y %H:%M, %d.%m.%y %H:%M, %m/%d/%Y %H:%M:%S, %m/%d/%y %H:%M:%S, %m-%d-%Y %H:%M:%S, %m-%d-%y %H:%M:%S, %m.%d.%Y %H:%M:%S, %m.%d.%y %H:%M:%S, %d/%m/%Y %H:%M:%S, %d/%m/%y %H:%M:%S, %Y-%m-%d %H:%M:%S.%f, %y-%m-%d %H:%M:%S.%f, %Y-%m-%dT%H:%M:%S.%fZ, %y-%m-%dT%H:%M:%S.%fZ, %Y-%m-%dT%H:%M:%S.%f, %y-%m-%dT%H:%M:%S.%f, %Y-%m-%dT%H:%M:%S, %y-%m-%dT%H:%M:%S, %Y-%m-%dT%H:%M:%SZ, %y-%m-%dT%H:%M:%SZ, %Y.%m.%d %H:%M:%S.%f, %y.%m.%d %H:%M:%S.%f, %Y.%m.%dT%H:%M:%S.%fZ, %y.%m.%dT%H:%M:%S.%fZ, %Y.%m.%dT%H:%M:%S.%f, %y.%m.%dT%H:%M:%S.%f, %Y.%m.%dT%H:%M:%S, %y.%m.%dT%H:%M:%S, %Y.%m.%dT%H:%M:%SZ, %y.%m.%dT%H:%M:%SZ, %Y%m%d, %m %d %Y %H %M %S, %m %d %y %H %M %S, %H:%M, %M:%S, %H:%M:%S, %Y %m %d %H %M %S, %y %m %d %H %M %S, %Y %m %d, %y %m %d, %d/%m/%Y, %Y-%d-%m, %y-%d-%m, %Y/%d/%m %H:%M:%S.%f, %Y/%d/%m %H:%M:%S.%fZ, %Y/%m/%d %H:%M:%S.%f, %Y/%m/%d %H:%M:%S.%fZ, %y/%d/%m %H:%M:%S.%f, %y/%d/%m %H:%M:%S.%fZ, %y/%m/%d %H:%M:%S.%f, %y/%m/%d %H:%M:%S.%fZ, %m.%d.%Y, %m.%d.%y, %d.%m.%y, %d.%m.%Y, %Y.%m.%d, %Y.%d.%m, %y.%m.%d, %y.%d.%m, %Y-%m-%d %I:%M:%S %p, %Y/%m/%d %I:%M:%S %p, %Y.%m.%d %I:%M:%S %p, %Y-%m-%d %I:%M %p, %Y/%m/%d %I:%M %p, %y-%m-%d %I:%M:%S %p, %y.%m.%d %I:%M:%S %p, %y/%m/%d %I:%M:%S %p, %y-%m-%d %I:%M %p, %y.%m.%d %I:%M %p, %y/%m/%d %I:%M %p, %m/%d/%Y %I:%M %p, %m/%d/%y %I:%M %p, %d/%m/%Y %I:%M %p, %d/%m/%y %I:%M %p, %m-%d-%Y %I:%M %p, %m-%d-%y %I:%M %p, %d-%m-%Y %I:%M %p, %d-%m-%y %I:%M %p, %m.%d.%Y %I:%M %p, %m/%d.%y %I:%M %p, %d.%m.%Y %I:%M %p, %d.%m.%y %I:%M %p, %m/%d/%Y %I:%M:%S %p, %m/%d/%y %I:%M:%S %p, %m-%d-%Y %I:%M:%S %p, %m-%d-%y %I:%M:%S %p, %m.%d.%Y %I:%M:%S %p, %m.%d.%y %I:%M:%S %p, %d/%m/%Y %I:%M:%S %p, %d/%m/%y %I:%M:%S %p, %Y-%m-%d %I:%M:%S.%f %p, %y-%m-%d %I:%M:%S.%f %p, %Y-%m-%dT%I:%M:%S.%fZ %p, %y-%m-%dT%I:%M:%S.%fZ %p, %Y-%m-%dT%I:%M:%S.%f %p, %y-%m-%dT%I:%M:%S.%f %p, %Y-%m-%dT%I:%M:%S %p, %y-%m-%dT%I:%M:%S %p, %Y-%m-%dT%I:%M:%SZ %p, %y-%m-%dT%I:%M:%SZ %p, %Y.%m.%d %I:%M:%S.%f %p, %y.%m.%d %I:%M:%S.%f %p, %Y.%m.%dT%I:%M:%S.%fZ %p, %y.%m.%dT%I:%M:%S.%fZ %p, %Y.%m.%dT%I:%M:%S.%f %p, %y.%m.%dT%I:%M:%S.%f %p, %Y.%m.%dT%I:%M:%S %p, %y.%m.%dT%I:%M:%S %p, %Y.%m.%dT%I:%M:%SZ %p, %y.%m.%dT%I:%M:%SZ %p, %m %d %Y %I %M %S %p, %m %d %y %I %M %S %p, %I:%M %p, %I:%M:%S %p, %Y %m %d %I %M %S %p, %y %m %d %I %M %S %p, %Y/%d/%m %I:%M:%S.%f %p, %Y/%d/%m %I:%M:%S.%fZ %p, %Y/%m/%d %I:%M:%S.%f %p, %Y/%m/%d %I:%M:%S.%fZ %p, %y/%d/%m %I:%M:%S.%f %p, %y/%d/%m %I:%M:%S.%fZ %p, %y/%m/%d %I:%M:%S.%f %p, %y/%m/%d %I:%M:%S.%fZ %p]

MetricUpdatePayload

{
  "baselineValues": [
    {
      "value": 0
    }
  ],
  "batch": {
    "columnName": "string"
  },
  "description": "string",
  "directionality": "higherIsBetter",
  "name": "string",
  "sampleCount": {
    "columnName": "string"
  },
  "timestamp": {
    "columnName": "string",
    "timeFormat": "%m/%d/%Y"
  },
  "type": "average",
  "units": "string",
  "value": {
    "columnName": "string"
  }
}

Properties

Name Type Required Restrictions Description
baselineValues [MetricBaselineValue] false maxItems: 5
Baseline values
batch BatchField false A custom metric batch ID source when reading values from columnar dataset like a file.
description string false maxLength: 1000
A description of the custom metric.
directionality string false Directionality of the custom metric.
name string false Name of the custom metric.
sampleCount SampleCountField false Points to a weight column if users provide pre-aggregated metric values. Used with columnar datasets.
timestamp MetricTimestampSpoofing false A custom metric timestamp spoofing when reading values from file, like dataset. By default, we replicate pd.to_datetime formatting behaviour.
type string false Type (and aggregation character) of a metric.
units string false Units or Y Label of given custom metric.
value ValueField false A custom metric value source when reading values from columnar dataset like a file.

Enumerated Values

Property Value
directionality [higherIsBetter, lowerIsBetter]
type [average, gauge, sum]

MetricValuesFromDatasetPayload

{
  "associationId": {
    "columnName": "string"
  },
  "batch": {
    "columnName": "string"
  },
  "datasetId": "string",
  "modelId": null,
  "modelPackageId": null,
  "sampleCount": {
    "columnName": "string"
  },
  "segments": [
    {
      "column": "string",
      "name": "string",
      "value": "string"
    }
  ],
  "timestamp": {
    "columnName": "string",
    "timeFormat": "%m/%d/%Y"
  },
  "value": {
    "columnName": "string"
  }
}

Properties

Name Type Required Restrictions Description
associationId BatchField false Points to a custom metric associationId column, for saving predictions feedback.
batch BatchField false A custom metric batch ID source when reading values from columnar dataset like a file.
datasetId string true Dataset ID to process.
modelId string¦null false For a model metric: the ID of the model of related champion/challenger to update the metric values.For a deployment metric: the ID of the model is not needed.
modelPackageId string¦null false For a model metric: the ID of the model package of related champion/challenger to update the metric values.For a deployment metric: the ID of the model package is not needed.
sampleCount SampleCountField false Points to a weight column if users provide pre-aggregated metric values. Used with columnar datasets.
segments [CustomMetricSegmentDataset] false maxItems: 10
minItems: 1
A list of segments for a custom metric used in segmented analysis.
timestamp MetricTimestampSpoofing false A custom metric timestamp spoofing when reading values from file, like dataset. By default, we replicate pd.to_datetime formatting behaviour.
value ValueField false A custom metric value source when reading values from columnar dataset like a file.

MetricValuesFromJSONPayload

{
  "buckets": [
    {
      "sampleSize": 1,
      "timestamp": "2019-08-24T14:15:22Z",
      "value": 0
    }
  ],
  "dryRun": false,
  "modelId": null,
  "modelPackageId": null
}

Properties

Name Type Required Restrictions Description
buckets [MetricInputValueBucket] true maxItems: 10000
A list of timestamped buckets with custom metric values.
dryRun boolean true Determines whether the data is sent to the modmon or not.
modelId string¦null false For a model metric: the ID of the model of related champion/challenger to update the metric values.For a deployment metric: the ID of the model is not needed.
modelPackageId string¦null false For a model metric: the ID of the model package of related champion/challenger to update the metric values.For a deployment metric: the ID of the model package is not needed.

MetricValuesOverTimeBucket

{
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "sampleSize": 0,
  "value": 0
}

Properties

Name Type Required Restrictions Description
period MetricPeriodBucket true A time period defined by a start and end time
sampleSize integer¦null true Total number of values aggregated in the bucket.
value number¦null true Aggregated custom metric value in the bucket.

MetricValuesOverTimeResponse

{
  "buckets": [
    {
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "sampleSize": 0,
      "value": 0
    }
  ],
  "metric": {
    "baselineValues": [
      {
        "value": 0
      }
    ],
    "createdAt": "2019-08-24T14:15:22Z",
    "createdBy": {
      "id": "string"
    },
    "description": "string",
    "directionality": "higherIsBetter",
    "displayChart": true,
    "id": "string",
    "isModelSpecific": true,
    "name": "string",
    "sampleCount": {
      "columnName": "string"
    },
    "timeStep": "hour",
    "timestamp": {
      "columnName": "string",
      "timeFormat": "%m/%d/%Y"
    },
    "type": "average",
    "units": "string",
    "value": {
      "columnName": "string"
    }
  },
  "summary": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  }
}

Properties

Name Type Required Restrictions Description
buckets [MetricValuesOverTimeBucket] true maxItems: 100
A list of bucketed time periods and the custom metric values aggregated over that period.
metric MetricEntity true A custom metric definition.
summary MetricValuesOverTimeSummary true Summary of values over time retrieval.

MetricValuesOverTimeSummary

{
  "end": "2019-08-24T14:15:22Z",
  "start": "2019-08-24T14:15:22Z"
}

Properties

Name Type Required Restrictions Description
end string(date-time) true End of the retrieval range.
start string(date-time) true Start of the retrieval range.

ModelPackageResponse

{
  "id": "string",
  "name": "string",
  "registeredModelId": "string"
}

Properties

Name Type Required Restrictions Description
id string true ID of the model package.
name string true Type of the current model.
registeredModelId string¦null false ID of the associated registered model

ModelReplacementSubmission

{
  "modelId": "string",
  "modelPackageId": "string",
  "reason": "ACCURACY"
}

Properties

Name Type Required Restrictions Description
modelId string false ID of the model used to replace deployment's champion model. Required if modelPackageId is not provided.
modelPackageId string false ID of the model package used to replace deployment's champion model. Required if modelId is not provided.
reason string true Reason for the model replacement.

Enumerated Values

Property Value
reason [ACCURACY, DATA_DRIFT, ERRORS, SCHEDULED_REFRESH, SCORING_SPEED, DEPRECATION, OTHER]

ModelReplacementValidationRequest

{
  "modelId": "string",
  "modelPackageId": "string"
}

Properties

Name Type Required Restrictions Description
modelId string false ID of the model used to replace deployment's champion model. Required if modelPackageId is not provided.
modelPackageId string false ID of the model package used to replace deployment's champion model. Required if modelId is not provided.

ModelReplacementValidationResponse

{
  "checks": {
    "combinedModelSegments": {
      "message": "string",
      "status": "failing"
    },
    "containsTrackedSegmentAttributes": {
      "message": "string",
      "status": "failing"
    },
    "driftTracking": {
      "message": "string",
      "status": "failing"
    },
    "featureDataTypes": {
      "message": "string",
      "status": "failing"
    },
    "features": {
      "message": "string",
      "status": "failing"
    },
    "humilityRules": {
      "message": "string",
      "status": "failing"
    },
    "modelCanBeDeployed": {
      "message": "string",
      "status": "failing"
    },
    "modelStatus": {
      "message": "string",
      "status": "failing"
    },
    "notCurrentModel": {
      "message": "string",
      "status": "failing"
    },
    "permission": {
      "message": "string",
      "status": "failing"
    },
    "predictionIntervals": {
      "message": "string",
      "status": "failing"
    },
    "predictionReady": {
      "message": "string",
      "status": "failing"
    },
    "seriesType": {
      "message": "string",
      "status": "failing"
    },
    "supported": {
      "message": "string",
      "status": "failing"
    },
    "target": {
      "message": "string",
      "status": "failing"
    },
    "targetClasses": {
      "message": "string",
      "status": "failing"
    },
    "targetType": {
      "message": "string",
      "status": "failing"
    },
    "timeSeriesCompatibility": {
      "message": "string",
      "status": "failing"
    },
    "validChallenger": {
      "message": "string",
      "status": "failing"
    }
  },
  "message": "string",
  "status": "failing"
}

Properties

Name Type Required Restrictions Description
checks ValidationChecks true A more granular explanation of why the replacement model was eligible or ineligible.
message string true Message of the overall validation check.
status string true Status of the overall validation check.

Enumerated Values

Property Value
status [failing, passing, warning]

ModelResponse

{
  "datasetName": "string",
  "description": "string",
  "executionType": "string",
  "id": "string",
  "isDeprecated": true,
  "name": "string",
  "projectId": "string",
  "projectName": "string"
}

Properties

Name Type Required Restrictions Description
datasetName string true Name of dataset used to train challenger model
description string true Description of the model.
executionType string true Type of the current model.
id string true ID of the current model.
isDeprecated boolean true Whether the current model is deprecated model. eg. python2 based model.
name string true Name of the model.
projectId string true Project ID of the current model.
projectName string true Project name of the current model.

MonitoringDataDeletePayload

{
  "end": "2019-08-24T14:15:22Z",
  "modelId": "string",
  "start": "2019-08-24T14:15:22Z"
}

Properties

Name Type Required Restrictions Description
end string(date-time)¦null false End of the period to delete monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.
modelId string true The id of the model for which monitoring data are being deleted.
start string(date-time)¦null false Start of the period to delete monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: 2019-08-01T00:00:00Z.

Percentile

{
  "percent": 0,
  "value": 0
}

Properties

Name Type Required Restrictions Description
percent number true Percent of the percentile
value number true Predicted value or probability at a percentile

Periodicity

{
  "timeSteps": 0,
  "timeUnit": "MILLISECOND"
}

Properties

Name Type Required Restrictions Description
timeSteps integer true minimum: 0
The number of time steps.
timeUnit string true The time unit or ROW if windowsBasisUnit is ROW

Enumerated Values

Property Value
timeUnit [MILLISECOND, SECOND, MINUTE, HOUR, DAY, WEEK, MONTH, QUARTER, YEAR, ROW]

PredictedClassDistribution

{
  "className": "string",
  "count": 0,
  "percent": 0
}

Properties

Name Type Required Restrictions Description
className string true Name of the class.
count integer true Count of prediction rows labeled with a class in the bucket.
percent number true Percent of prediction rows labeled with a class in the bucket.

PredictionDatasetAssignment

{
  "datasetId": "string",
  "datasetVersionId": "string"
}

Properties

Name Type Required Restrictions Description
datasetId string true the ID of the dataset
datasetVersionId string false the ID of the dataset version

PredictionEnvironment

{
  "id": "string",
  "name": "string"
}

Properties

Name Type Required Restrictions Description
id string true ID of the prediction environment.
name string true Name of the prediction environment.

PredictionEnvironmentResponse

{
  "id": "string",
  "name": "string"
}

Properties

Name Type Required Restrictions Description
id string true ID of the prediction environment.
name string true Name of the prediction environment.

PredictionIntervals

{
  "enabled": true,
  "percentiles": [
    0
  ]
}

Properties

Name Type Required Restrictions Description
enabled boolean true Indicates whether prediction intervals are enabled for this deployment.
percentiles [integer] false The percentiles used for this deployment. Currently, we support at most one percentile at a time.

PredictionIntervalsUpdate

{
  "enabled": true,
  "percentiles": [
    0
  ]
}

Properties

Name Type Required Restrictions Description
enabled boolean true True if prediction intervals are enabled for this deployment, false if otherwise
percentiles [integer] false if prediction intervals are enabled, the percentiles to use for this deployment. Currently, we support at most one percentile at a time.

PredictionResultResponse

{
  "actual": 0,
  "associationId": "string",
  "forecastDistance": 0,
  "modelId": "string",
  "predicted": 0,
  "timestamp": "2019-08-24T14:15:22Z"
}

Properties

Name Type Required Restrictions Description
actual any true Actual value of the prediction

oneOf

Name Type Required Restrictions Description
» anonymous integer false none

xor

Name Type Required Restrictions Description
» anonymous number false none

xor

Name Type Required Restrictions Description
» anonymous string false none

continued

Name Type Required Restrictions Description
associationId string true Association id of the prediction, which is used to associate a prediction with its actual value and calculate accuracy.
forecastDistance integer¦null false The number of time units this prediction is away from the forecastPoint. The unit of time is determined by the timeUnit of the datetime partition column. For time series models only.
modelId string true ID of the model used to make these predictions
predicted any true Predicted value of the prediction

oneOf

Name Type Required Restrictions Description
» anonymous integer false none

xor

Name Type Required Restrictions Description
» anonymous number false none

xor

Name Type Required Restrictions Description
» anonymous string false none

continued

Name Type Required Restrictions Description
timestamp string(date-time) true When the prediction was made.

PredictionResultsListResponse

{
  "associationIdColumnNames": [
    "string"
  ],
  "count": 0,
  "data": [
    {
      "actual": 0,
      "associationId": "string",
      "forecastDistance": 0,
      "modelId": "string",
      "predicted": 0,
      "timestamp": "2019-08-24T14:15:22Z"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Properties

Name Type Required Restrictions Description
associationIdColumnNames [string]¦null true List of column names used to represent an association id, which is used to unique identify individual prediction rows.
count integer false Number of items returned on this page.
data [PredictionResultResponse] true An array of prediction requests.
next string(uri)¦null true URL pointing to the next page (if null, there is no next page).
previous string(uri)¦null true URL pointing to the previous page (if null, there is no previous page).

PredictionServerListResponse

{
  "count": 0,
  "data": [
    {
      "batchPredictions": {
        "processing": 0,
        "queued": 0
      },
      "datarobot-key": "string",
      "id": "string",
      "url": "string"
    }
  ],
  "next": "http://example.com",
  "previous": "http://example.com"
}

Properties

Name Type Required Restrictions Description
count integer false Number of items returned on this page.
data [PredictionServerResponse] true List of prediction servers.
next string(uri)¦null true URL pointing to the next page (if null, there is no next page).
previous string(uri)¦null true URL pointing to the previous page (if null, there is no previous page).

PredictionServerResponse

{
  "batchPredictions": {
    "processing": 0,
    "queued": 0
  },
  "datarobot-key": "string",
  "id": "string",
  "url": "string"
}

Properties

Name Type Required Restrictions Description
batchPredictions BatchPredictionStatus true Batch Prediction status for this instance
datarobot-key string¦null true The datarobot-key header used in requests to this prediction server.
id string¦null true ID of the prediction server.
url string true URL of the prediction server.

PredictionWarning

{
  "customBoundaries": {
    "lower": 0,
    "upper": 0
  },
  "enabled": true
}

Properties

Name Type Required Restrictions Description
customBoundaries CustomBoundaries true Null if default boundaries for the model are used
enabled boolean true Indicates whether prediction warnings are enabled for this deployment.

PredictionWarningUpdate

{
  "customBoundaries": {
    "lower": 0,
    "upper": 0
  },
  "enabled": true
}

Properties

Name Type Required Restrictions Description
customBoundaries CustomBoundaries false If omitted, boundaries will not be changed. Null if default boundaries for the model should be used.
enabled boolean true True if prediction warnings are enabled for this deployment, false otherwise.

PredictionsDataCollection

{
  "enabled": true
}

Properties

Name Type Required Restrictions Description
enabled boolean true Indicates whether incoming prediction requests and results should be stored in record-level storage.

PredictionsOverTimeBucket

{
  "classDistribution": [
    {
      "className": "string",
      "count": 0,
      "percent": 0
    }
  ],
  "meanPredictedValue": 0,
  "meanProbabilities": [
    {
      "className": "string",
      "value": 0
    }
  ],
  "modelId": "string",
  "percentiles": [
    {
      "percent": 0,
      "value": 0
    }
  ],
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "predictionsWarningCount": 0,
  "rowCount": 0
}

Properties

Name Type Required Restrictions Description
classDistribution [ClassDistribution]¦null false Class distribution for all classes in the bucket, only for classification deployments.
meanPredictedValue number¦null false Mean predicted value for all rows in the bucket, only for regression deployments.
meanProbabilities [MeanProbability]¦null false Mean predicted probabilities for all classes in the bucket, only for classification deployments
modelId string true ID of the model
percentiles [Percentile]¦null false Predicted value or positive class predicted probability at specific percentiles in the bucket, only for regression and binary classification deployments.
period TimeRange true Info of the time period associated with the bucket.
predictionsWarningCount integer¦null false The number of predictions with warning in the bucket
rowCount integer¦null true Number of rows in the bucket.

PredictionsOverTimeResponse

{
  "baselines": [
    {
      "classDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "meanPredictedValue": 0,
      "meanProbabilities": [
        {
          "className": "string",
          "value": 0
        }
      ],
      "modelId": "string",
      "percentiles": [
        {
          "percent": 0,
          "value": 0
        }
      ],
      "predictionsWarningCount": 0,
      "rowCount": 0
    }
  ],
  "buckets": [
    {
      "classDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "meanPredictedValue": 0,
      "meanProbabilities": [
        {
          "className": "string",
          "value": 0
        }
      ],
      "modelId": "string",
      "percentiles": [
        {
          "percent": 0,
          "value": 0
        }
      ],
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "predictionsWarningCount": 0,
      "rowCount": 0
    }
  ],
  "segmentAttribute": "string",
  "segmentValue": ""
}

Properties

Name Type Required Restrictions Description
baselines [TargetBaseline] true Target baselines
buckets [PredictionsOverTimeBucket] true Predictions over time buckets
segmentAttribute string¦null false The name of the segment on which segment analysis is being performed.
segmentValue string¦null false The value of the segmentAttribute to segment on.

PredictionsVsActualsBaseline

{
  "actualClassDistribution": [
    {
      "className": "string",
      "count": 0,
      "percent": 0
    }
  ],
  "meanActualValue": 0,
  "meanPredictedValue": 0,
  "modelId": "string",
  "predictedClassDistribution": [
    {
      "className": "string",
      "count": 0,
      "percent": 0
    }
  ],
  "rowCountTotal": 0,
  "rowCountWithActual": 0
}

Properties

Name Type Required Restrictions Description
actualClassDistribution [ActualClassDistribution]¦null false Class distribution for all actuals in the bucket, only for classification deployments.
meanActualValue number¦null false Mean actual value for all rows in the bucket, only for regression deployments.
meanPredictedValue number¦null false Mean predicted value for all rows in the bucket, only for regression deployments.
modelId string true ID of the model.
predictedClassDistribution [PredictedClassDistribution]¦null false Class distribution for all rows with actual in the bucket, only for classification deployments.
rowCountTotal integer true Number of rows in the bucket.
rowCountWithActual integer true Number of rows with actual in the bucket.

PredictionsVsActualsOverTimeResponse

{
  "baselines": [
    {
      "actualClassDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "meanActualValue": 0,
      "meanPredictedValue": 0,
      "modelId": "string",
      "predictedClassDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "rowCountTotal": 0,
      "rowCountWithActual": 0
    }
  ],
  "buckets": [
    {
      "actualClassDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "meanActualValue": 0,
      "meanPredictedValue": 0,
      "modelId": "string",
      "period": {
        "end": "2019-08-24T14:15:22Z",
        "start": "2019-08-24T14:15:22Z"
      },
      "predictedClassDistribution": [
        {
          "className": "string",
          "count": 0,
          "percent": 0
        }
      ],
      "rowCountTotal": 0,
      "rowCountWithActual": 0
    }
  ],
  "segmentAttribute": "string",
  "segmentValue": "",
  "summary": {
    "rowCountTotal": 0,
    "rowCountWithActual": 0
  }
}

Properties

Name Type Required Restrictions Description
baselines [PredictionsVsActualsBaseline] true Predictions vs actuals baselines.
buckets [PredictionsVsActualsTimeBucket] true Predictions vs actuals buckets.
segmentAttribute string¦null false The name of the segment on which segment analysis is being performed.
segmentValue string¦null false The value of the segmentAttribute to segment on.
summary PredictionsVsActualsSummaryBucket true Predictions vs actuals summary.

PredictionsVsActualsSummaryBucket

{
  "rowCountTotal": 0,
  "rowCountWithActual": 0
}

Properties

Name Type Required Restrictions Description
rowCountTotal integer true Number of rows for all buckets.
rowCountWithActual integer true Number of rows with actual for all buckets.

PredictionsVsActualsTimeBucket

{
  "actualClassDistribution": [
    {
      "className": "string",
      "count": 0,
      "percent": 0
    }
  ],
  "meanActualValue": 0,
  "meanPredictedValue": 0,
  "modelId": "string",
  "period": {
    "end": "2019-08-24T14:15:22Z",
    "start": "2019-08-24T14:15:22Z"
  },
  "predictedClassDistribution": [
    {
      "className": "string",
      "count": 0,
      "percent": 0
    }
  ],
  "rowCountTotal": 0,
  "rowCountWithActual": 0
}

Properties

Name Type Required Restrictions Description
actualClassDistribution [ActualClassDistribution]¦null false Class distribution for all actuals in the bucket, only for classification deployments.
meanActualValue number¦null false Mean actual value for all rows in the bucket, only for regression deployments.
meanPredictedValue number¦null false Mean predicted value for all rows in the bucket, only for regression deployments.
modelId string true ID of the model.
period BatchPeriod true Time period of the bucket.
predictedClassDistribution [PredictedClassDistribution]¦null false Class distribution for all rows with actual in the bucket, only for classification deployments.
rowCountTotal integer true Number of rows in the bucket.
rowCountWithActual integer true Number of rows with actual in the bucket.

ProjectOptions

{
  "cvMethod": "RandomCV",
  "holdoutPct": null,
  "metric": "Accuracy",
  "reps": null,
  "validationPct": null,
  "validationType": "CV"
}

Properties

Name Type Required Restrictions Description
cvMethod string false The partitioning method for projects used to build new models.
holdoutPct number¦null false maximum: 98
minimum: 0
The percentage of dataset to assign to holdout set in projects used to build new models.
metric string¦null false The model selection metric in projects used to build new models.
reps integer¦null false maximum: 50
minimum: 2
The number of cross validation folds to use for projects used to build new models.
validationPct number¦null false maximum: 99
minimum: 1
The percentage of dataset to assign to validation set in projects used to build new models.
validationType string false The validation type for projects used to build new models.

Enumerated Values

Property Value
cvMethod [RandomCV, StratifiedCV]
metric [Accuracy, AUC, Balanced Accuracy, FVE Binomial, Gini Norm, Kolmogorov-Smirnov, LogLoss, Rate@Top5%, Rate@Top10%, TPR, FPR, TNR, PPV, NPV, F1, MCC, FVE Gamma, FVE Poisson, FVE Tweedie, Gamma Deviance, MAE, MAPE, Poisson Deviance, R Squared, RMSE, RMSLE, Tweedie Deviance]
validationType [CV, TVH]

RetrainingPolicyCreate

{
  "action": "create_challenger",
  "autopilotOptions": {
    "blendBestModels": true,
    "mode": "auto",
    "runLeakageRemovedFeatureList": true,
    "scoringCodeOnly": true,
    "shapOnlyMode": true
  },
  "description": null,
  "featureListStrategy": "informative_features",
  "modelSelectionStrategy": "autopilot_recommended",
  "name": "string",
  "projectOptions": {
    "cvMethod": "RandomCV",
    "holdoutPct": null,
    "metric": "Accuracy",
    "reps": null,
    "validationPct": null,
    "validationType": "CV"
  },
  "projectOptionsStrategy": "same_as_champion",
  "timeSeriesOptions": {
    "calendarId": "string",
    "differencingMethod": "auto",
    "exponentiallyWeightedMovingAlpha": 0,
    "periodicities": [
      {
        "timeSteps": 0,
        "timeUnit": "MILLISECOND"
      }
    ],
    "treatAsExponential": "auto"
  },
  "trigger": {
    "minIntervalBetweenRuns": "string",
    "schedule": {
      "dayOfMonth": [
        "*"
      ],
      "dayOfWeek": [
        "*"
      ],
      "hour": [
        "*"
      ],
      "minute": [
        "*"
      ],
      "month": [
        "*"
      ]
    },
    "statusDeclinesToFailing": true,
    "statusDeclinesToWarning": true,
    "statusStillInDecline": true,
    "type": "schedule"
  }
}

Properties

Name Type Required Restrictions Description
action string false Configure the action to take on the resultant new model.
autopilotOptions AutopilotOptions false Will override the corresponding fields when reusing champion's project options.
description string¦null true maxLength: 10000
Description of the retraining policy.
featureListStrategy string false Configure the feature list strategy used for modeling.
modelSelectionStrategy string false Configure how new model is selected when the retraining policy runs.
name string true maxLength: 512
Name of the retraining policy.
projectOptions ProjectOptions false Options for projects used to build new models.
projectOptionsStrategy string false Configure the project option strategy used for modeling.
timeSeriesOptions TimeSeriesOptions false Time Series project option used to build new models.
trigger Trigger false Retraining policy trigger.

Enumerated Values

Property Value
action [create_challenger, create_model_package, model_replacement]
featureListStrategy [informative_features, same_as_champion]
modelSelectionStrategy [autopilot_recommended, same_blueprint, same_hyperparameters]
projectOptionsStrategy [same_as_champion, override_champion, custom]

RetrainingPolicyListResponse

{
  "count": 0,
  "data": [
    {
      "action": "create_challenger",
      "autopilotOptions": {
        "blendBestModels": true,
        "mode": "auto",
        "runLeakageRemovedFeatureList": true,
        "scoringCodeOnly": true,
        "shapOnlyMode": true
      },
      "description": "string",
      "featureListStrategy": "informative_features",
      "id": "string",
      "latestRun": {
        "challengerId": "string",
        "errorMessage": "string",
        "finishTime": "2019-08-24T14:15:22Z",
        "id": "string",
        "modelPackageId": "string",
        "projectId": "string",
        "registeredModelId": "string",
        "startTime": "2019-08-24T14:15:22Z",
        "status": "string"
      },
      "modelSelectionStrategy": "autopilot_recommended",
      "name": "string",
      "projectOptions": {
        "cvMethod": "RandomCV",
        "holdoutPct": null,
        "metric": "Accuracy",
        "reps": null,
        "validationPct": null,
        "validationType": "CV"
      },
      "projectOptionsStrategy": "same_as_champion",
      "timeSeriesOptions": {
        "calendarId": "string",
        "differencingMethod": "auto",
        "exponentiallyWeightedMovingAlpha": 0,
        "periodicities": [
          {
            "timeSteps": 0,
            "timeUnit": "MILLISECOND"
          }
        ],
        "treatAsExponential": "auto"
      },
      "trigger": {
        "minIntervalBetweenRuns": "string"