InitializeAnomalyAssessment {datarobot}

Request anomaly assessment insight computation on the specified subset.

Description

Request anomaly assessment insight computation on the specified subset.

Usage

InitializeAnomalyAssessment(
  projectId,
  modelId,
  backtest,
  source,
  seriesId = NULL
)

Arguments

projectId

character. The ID of the project to compute insight for.

modelId

character. The ID of the model to compute insight for.

backtest

integer or "holdout". The backtest to compute insight for.

source

"training" or "validation". The source to compute insight for.

seriesId

character. Optional. The series id to compute insight for. Required for multiseries projects.

Value

An object with anomaly assessment metadata:

• recordId. character. The ID of the record.

• projectId. character. The project ID of the record.

• modelId. character. The model ID of the record.

• backtest. character. The backtest of the record.

• source. character. The source of the record.

• seriesId. character. the series ID of the record.

• status. character. The status of the insight.

• statusDetails. character. The explanation of the status.

• startDate. POSIXct. Timestamp of the first prediction in the subset. Will be NULL if status is not completed.

• endDate. POSIXct. Timestamp of the last prediction in the subset. Will be NULL if status is not completed.

• predictionThreshold. numeric. The threshold, all rows with anomaly scores greater or equal to it have shap explanations computed. Will be NULL if status is not completed.

• previewLocation. character. URL to retrieve predictions preview for the subset. Will be NULL if status is not completed.

• latestExplanationsLocation. character. the URL to retrieve the latest predictions with the shap explanations. Will be NULL if status is not completed.

• deleteLocation. character. the URL to delete anomaly assessment record and relevant insight data.

See Also

Other Anomaly Assessment functions: DeleteAnomalyAssessmentRecord(), GetAnomalyAssessmentExplanations(), GetAnomalyAssessmentPredictionsPreview(), ListAnomalyAssessmentRecords()

Examples

## Not run: 
projectId <- "59a5af20c80891534e3c2bde"
modelId <- "59a5af20c80891534e3c2bdd"
record <- InitializeAnomalyAssessment(projectId, modelId, backtest=0, source="validation",
   seriesId="Baltimore")

## End(Not run)