Skip to content

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

DataRobot API resources > API reference documentation > DataRobot REST API > Deployments > Actuals configuration

Deployment Configuration

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

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

Retrieve deployment health settings.

Code samples

curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/healthSettings/ \
  -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

{
  "accuracy": {
    "batchCount": 1,
    "failingThreshold": 0,
    "measurement": "percent",
    "metric": "AUC",
    "warningThreshold": 0
  },
  "actualsTimeliness": {
    "enabled": true,
    "expectedFrequency": "string"
  },
  "customMetrics": {
    "failingConditions": [
      {
        "compareOperator": "lt",
        "metricId": "string",
        "threshold": 0
      }
    ],
    "warningConditions": [
      {
        "compareOperator": "lt",
        "metricId": "string",
        "threshold": 0
      }
    ]
  },
  "dataDrift": {
    "batchCount": 1,
    "driftThreshold": 1,
    "excludedFeatures": [
      "string"
    ],
    "highImportanceFailingCount": 1,
    "highImportanceWarningCount": 1,
    "importanceThreshold": 1,
    "lowImportanceFailingCount": 1,
    "lowImportanceWarningCount": 1,
    "starredFeatures": [
      "string"
    ],
    "timeInterval": "T2H"
  },
  "fairness": {
    "protectedClassFailingCount": 1,
    "protectedClassWarningCount": 1
  },
  "predictionsTimeliness": {
    "enabled": true,
    "expectedFrequency": "string"
  },
  "service": {
    "batchCount": 1
  }
}

Responses

Status Meaning Description Schema
200 OK Deployment health settings. HealthSettings

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

BearerAuth

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

Update deployment health settings.

Code samples

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

Body parameter

{
  "accuracy": {
    "batchCount": 1,
    "failingThreshold": 0,
    "measurement": "percent",
    "metric": "AUC",
    "warningThreshold": 0
  },
  "actualsTimeliness": {
    "enabled": true,
    "expectedFrequency": "string"
  },
  "customMetrics": {
    "failingConditions": [
      {
        "compareOperator": "lt",
        "metricId": "string",
        "threshold": 0
      }
    ],
    "warningConditions": [
      {
        "compareOperator": "lt",
        "metricId": "string",
        "threshold": 0
      }
    ]
  },
  "dataDrift": {
    "batchCount": 1,
    "driftThreshold": 1,
    "excludedFeatures": [
      "string"
    ],
    "highImportanceFailingCount": 1,
    "highImportanceWarningCount": 1,
    "importanceThreshold": 1,
    "lowImportanceFailingCount": 1,
    "lowImportanceWarningCount": 1,
    "starredFeatures": [
      "string"
    ],
    "timeInterval": "T2H"
  },
  "fairness": {
    "protectedClassFailingCount": 1,
    "protectedClassWarningCount": 1
  },
  "predictionsTimeliness": {
    "enabled": true,
    "expectedFrequency": "string"
  },
  "service": {
    "batchCount": 1
  }
}

Parameters

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

Responses

Status Meaning Description Schema
200 OK Updated deployment health settings. None

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

BearerAuth

GET /api/v2/deployments/{deploymentId}/healthSettings/defaults/

Retrieve default deployment health settings.

Code samples

curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/healthSettings/defaults/ \
  -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

{
  "accuracy": {
    "batchCount": 1,
    "failingThreshold": 0,
    "measurement": "percent",
    "metric": "AUC",
    "warningThreshold": 0
  },
  "actualsTimeliness": {
    "enabled": true,
    "expectedFrequency": "string"
  },
  "customMetrics": {
    "failingConditions": [
      {
        "compareOperator": "lt",
        "metricId": "string",
        "threshold": 0
      }
    ],
    "warningConditions": [
      {
        "compareOperator": "lt",
        "metricId": "string",
        "threshold": 0
      }
    ]
  },
  "dataDrift": {
    "batchCount": 1,
    "driftThreshold": 1,
    "excludedFeatures": [
      "string"
    ],
    "highImportanceFailingCount": 1,
    "highImportanceWarningCount": 1,
    "importanceThreshold": 1,
    "lowImportanceFailingCount": 1,
    "lowImportanceWarningCount": 1,
    "starredFeatures": [
      "string"
    ],
    "timeInterval": "T2H"
  },
  "fairness": {
    "protectedClassFailingCount": 1,
    "protectedClassWarningCount": 1
  },
  "predictionsTimeliness": {
    "enabled": true,
    "expectedFrequency": "string"
  },
  "service": {
    "batchCount": 1
  }
}

Responses

Status Meaning Description Schema
200 OK Default deployment health settings. HealthSettings

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

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

curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/model/secondaryDatasetConfiguration/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {access-token}" \
  -d '{undefined}'

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

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

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

Retrieve deployment settings.

Code samples

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
  },
  "processingLimits": {
    "interval": "hour"
  },
  "segmentAnalysis": {
    "attributes": [
      "string"
    ],
    "enabled": true
  },
  "targetDrift": {
    "enabled": true
  }
}

Responses

Status Meaning Description Schema
200 OK The deployment settings DeploymentSettingsResponse

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

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

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
  },
  "processingLimits": {
    "interval": "hour"
  },
  "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

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

Schemas

AccuracyHealth

{
  "batchCount": 1,
  "failingThreshold": 0,
  "measurement": "percent",
  "metric": "AUC",
  "warningThreshold": 0
}

Accuracy health status setting.

Properties

Name Type Required Restrictions Description
batchCount integer false Number of recent batches used to compute accuracy health status, only applicable to deployments with batch monitoring enabled.
failingThreshold number,null false Threshold for failing status.
measurement string,null false Measurement for calculating accuracy health status.
metric string,null false Metric used for calculating accuracy health status.
warningThreshold number,null false Threshold for warning status.

Enumerated Values

Property Value
batchCount [1, 5, 10, 50, 100, 1000, 10000]
measurement [percent, 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, MAE, MAPE, MCC, NPV, PPV, Poisson Deviance, R Squared, RMSE, RMSLE, Rate@Top10%, Rate@Top5%, TNR, TPR, Tweedie Deviance, WGS84 MAE, WGS84 RMSE]

AssociationID

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

The association ID setting for the deployment.

Properties

Name Type Required Restrictions Description
columnNames [string] false maxItems: 1
minItems: 1
 List of column names used to represent an association ID.
requiredInPredictionRequests boolean false Indicates whether the association ID is required in prediction requests.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.

AutomaticActuals

{
  "enabled": true
}

Automatic actuals setting for the deployment.

Properties

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

BiasAndFairness

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

Bias and fairness setting for the deployment.

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 features to mark as protected for bias and fairness measurement.

Enumerated Values

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

Challengers

{
  "enabled": true
}

Challenger models setting for the deployment.

Properties

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

CustomBoundaries

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

Null if default boundaries for the model are used

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.

CustomMetricCondition

{
  "compareOperator": "lt",
  "metricId": "string",
  "threshold": 0
}

Properties

Name Type Required Restrictions Description
compareOperator string true Defines how custom metric value is compared against the threshold.
metricId string true Custom metric ID.
threshold number true Threshold value used to determine if the condition is met.

Enumerated Values

Property Value
compareOperator [lt, lte, gt, gte]

CustomMetricsHealth

{
  "failingConditions": [
    {
      "compareOperator": "lt",
      "metricId": "string",
      "threshold": 0
    }
  ],
  "warningConditions": [
    {
      "compareOperator": "lt",
      "metricId": "string",
      "threshold": 0
    }
  ]
}

Custom metrics health status setting.

Properties

Name Type Required Restrictions Description
failingConditions [CustomMetricCondition] false maxItems: 25
 Conditions for failing status.
warningConditions [CustomMetricCondition] false maxItems: 25
 Conditions for warning status.

DataDriftHealth

{
  "batchCount": 1,
  "driftThreshold": 1,
  "excludedFeatures": [
    "string"
  ],
  "highImportanceFailingCount": 1,
  "highImportanceWarningCount": 1,
  "importanceThreshold": 1,
  "lowImportanceFailingCount": 1,
  "lowImportanceWarningCount": 1,
  "starredFeatures": [
    "string"
  ],
  "timeInterval": "T2H"
}

Data drift health status setting.

Properties

Name Type Required Restrictions Description
batchCount integer false Number of recent batches used to compute data drift health status, only applicable to deployments with batch monitoring enabled.
driftThreshold number false maximum: 1
minimum: 0
 The drift metric threshold above which the feature is considered as drifted.
excludedFeatures [string] false maxItems: 100
 Features that are excluded from data drift status consideration.
highImportanceFailingCount integer,null false minimum: 1
 Threshold of drifted high importance feature count for failing status.
highImportanceWarningCount integer,null false minimum: 1
 Threshold of drifted high importance feature count for warning status.
importanceThreshold number false maximum: 1
minimum: 0
 The feature importance threshold above which the feature is considered as important.
lowImportanceFailingCount integer,null false minimum: 1
 Threshold of drifted low importance feature count for failing status.
lowImportanceWarningCount integer,null false minimum: 1
 Threshold of drifted low importance feature count for warning status.
starredFeatures [string] false maxItems: 100
 Features that are deemed to be of high importance, regardless of how their feature importance values compare against the threshold.
timeInterval string false Time duration used to compute data drift health status, only applicable to deployments with batch monitoring disabled.

Enumerated Values

Property Value
batchCount [1, 5, 10, 50, 100, 1000, 10000]
timeInterval [T2H, P1D, P7D, P30D, P90D, P180D, P365D]

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

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]

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
  },
  "processingLimits": {
    "interval": "hour"
  },
  "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 AutomaticActuals 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 PredictionsByForecastDate false Forecast date setting for the deployment.
predictionsDataCollection PredictionsDataCollection false The predictions data collection setting for the deployment.
processingLimits ProcessingLimits false Processing limits 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
  },
  "processingLimits": {
    "interval": "hour"
  },
  "segmentAnalysis": {
    "attributes": [
      "string"
    ],
    "enabled": true
  },
  "targetDrift": {
    "enabled": true
  }
}

Properties

Name Type Required Restrictions Description
associationId AssociationID false The association ID setting for the deployment.
automaticActuals AutomaticActuals 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 false The feature drift setting for the deployment.
humility Humility false Humility setting for the deployment.
predictionIntervals PredictionIntervals false The prediction intervals setting for the deployment.
predictionWarning PredictionWarning false The prediction warning setting for the deployment.
predictionsByForecastDate PredictionsByForecastDate false Forecast date setting for the deployment.
predictionsDataCollection PredictionsDataCollection false The predictions data collection setting for the deployment.
processingLimits ProcessingLimits false Processing limits setting for the deployment.
segmentAnalysis SegmentAnalysis false The segment analysis setting for the deployment.
targetDrift TargetDriftSetting false The target drift setting for the deployment.

FairnessHealth

{
  "protectedClassFailingCount": 1,
  "protectedClassWarningCount": 1
}

Fairness health status setting. Only available if deployment supports fairness.

Properties

Name Type Required Restrictions Description
protectedClassFailingCount integer false minimum: 1
 Number of protected class below fairness threshold for failing status.
protectedClassWarningCount integer false minimum: 1
 Number of protected class below fairness threshold for warning status.

FeatureDriftSetting

{
  "enabled": true
}

The feature drift setting for the deployment.

Properties

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

HealthSettings

{
  "accuracy": {
    "batchCount": 1,
    "failingThreshold": 0,
    "measurement": "percent",
    "metric": "AUC",
    "warningThreshold": 0
  },
  "actualsTimeliness": {
    "enabled": true,
    "expectedFrequency": "string"
  },
  "customMetrics": {
    "failingConditions": [
      {
        "compareOperator": "lt",
        "metricId": "string",
        "threshold": 0
      }
    ],
    "warningConditions": [
      {
        "compareOperator": "lt",
        "metricId": "string",
        "threshold": 0
      }
    ]
  },
  "dataDrift": {
    "batchCount": 1,
    "driftThreshold": 1,
    "excludedFeatures": [
      "string"
    ],
    "highImportanceFailingCount": 1,
    "highImportanceWarningCount": 1,
    "importanceThreshold": 1,
    "lowImportanceFailingCount": 1,
    "lowImportanceWarningCount": 1,
    "starredFeatures": [
      "string"
    ],
    "timeInterval": "T2H"
  },
  "fairness": {
    "protectedClassFailingCount": 1,
    "protectedClassWarningCount": 1
  },
  "predictionsTimeliness": {
    "enabled": true,
    "expectedFrequency": "string"
  },
  "service": {
    "batchCount": 1
  }
}

Properties

Name Type Required Restrictions Description
accuracy AccuracyHealth false Accuracy health status setting.
actualsTimeliness TimelinessSettings false Predictions timeliness health setting.
customMetrics CustomMetricsHealth false Custom metrics health status setting.
dataDrift DataDriftHealth false Data drift health status setting.
fairness FairnessHealth false Fairness health status setting. Only available if deployment supports fairness.
predictionsTimeliness TimelinessSettings false Predictions timeliness health setting.
service ServiceHealth false Service health status setting.

Humility

{
  "enabled": true
}

Humility setting for the deployment.

Properties

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

PredictionIntervals

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

The prediction intervals setting for the deployment.

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.

PredictionWarning

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

The prediction warning setting for the deployment.

Properties

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

PredictionsByForecastDate

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

Forecast date setting for the deployment.

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.

PredictionsDataCollection

{
  "enabled": true
}

The predictions data collection setting for the deployment.

Properties

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

ProcessingLimits

{
  "interval": "hour"
}

Processing limits setting for the deployment.

Properties

Name Type Required Restrictions Description
interval string true A time interval that is applied when calculating processing limits.

Enumerated Values

Property Value
interval [hour, day, week]

SecondaryDatasetConfigResponse

{
  "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"
    }
  ]
}

Properties

Name Type Required Restrictions Description
created string,null(date-time) true DR-formatted datetime, null for legacy (before DR 6.0) db records
creatorFullName string,null true Fullname or email of the user created this config. null for legacy (before DR 6.0) db records
creatorUserId string,null true ID of the user created this config, null for legacy (before DR 6.0) db records
credentialIds [DatasetsCredential] false List of credentials used by the secondary datasets if the datasets used in the configuration are from datasource
featurelistId string,null true Id of the feature list
isDefault boolean true Secondary datasets config is default config or not
isDeleted boolean true Secondary datasets config is soft deleted or not
name string,null true Name of the secondary datasets config
projectId string,null true ID of the project
secondaryDatasetConfigId string true ID of the secondary datasets configuration
secondaryDatasets [DeploymentSecondaryDataset] false List of secondary datasets used in the config

SecondaryDatasetConfigUpdate

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

Properties

Name Type Required Restrictions Description
credentialsIds [DatasetsCredential] false List of credentials used by the secondary datasets
secondaryDatasetConfigId string true ID of the secondary datasets configuration to be used at the time of prediction

SecondaryDatasetsConfig

{
  "configId": "string",
  "configName": "string",
  "updated": "string",
  "username": "string"
}

Properties

Name Type Required Restrictions Description
configId string true ID of the secondary datasets configuration
configName string true Name of the secondary datasets config
updated string true Timestamp when configuration was updated on the given deployment
username string true Name of the user who made the update

SecondaryDatasetsConfigListResponse

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

Properties

Name Type Required Restrictions Description
count integer true Number of items
data [SecondaryDatasetsConfig] true Secondary datasets configuration history.
next string,null(uri) true URL pointing to the next page (if null, there is no next page)
previous string,null(uri) true URL pointing to the previous page (if null, there is no previous page)

SegmentAnalysis

{
  "attributes": [
    "string"
  ],
  "enabled": true
}

The segment analysis setting for the deployment.

Properties

Name Type Required Restrictions Description
attributes [string] false The segment attributes to be tracked. Note that only categorical columns can be specified as tracked segment attributes. The target column may not be specified
enabled boolean true Indicates whether service health, drift, and accuracy are tracked for segments of prediction data.

ServiceHealth

{
  "batchCount": 1
}

Service health status setting.

Properties

Name Type Required Restrictions Description
batchCount integer true Number of recent batches used to compute service health status, only applicable to deployments with batch monitoring enabled.

Enumerated Values

Property Value
batchCount [1, 5, 10, 50, 100, 1000, 10000]

TargetDriftSetting

{
  "enabled": true
}

The target drift setting for the deployment.

Properties

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

TimelinessSettings

{
  "enabled": true,
  "expectedFrequency": "string"
}

Predictions timeliness health setting.

Properties

Name Type Required Restrictions Description
enabled boolean false Indicates if timeliness status is enabled.
expectedFrequency string false Expected frequency for receiving data as an ISO 8601 duration string.
Updated March 25, 2025