GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigTrainingPredictionSkewDetectionConfig constructor

const GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigTrainingPredictionSkewDetectionConfig({
  1. Input<Map<String, String>>? attributionScoreSkewThresholds,
  2. Input<GoogleCloudAiplatformV1ThresholdConfig>? defaultSkewThreshold,
  3. Input<Map<String, String>>? skewThresholds,
})

Creates a new GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigTrainingPredictionSkewDetectionConfig. attributionScoreSkewThresholds Key is the feature name and value is the threshold. The threshold here is against attribution score distance between the training and prediction feature. defaultSkewThreshold Skew anomaly detection threshold used by all features. When the per-feature thresholds are not set, this field can be used to specify a threshold for all features. skewThresholds Key is the feature name and value is the threshold. If a feature needs to be monitored for skew, a value threshold must be configured for that feature. The threshold here is against feature distribution distance between the training and prediction feature.

Implementation

const GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigTrainingPredictionSkewDetectionConfig({
  this.attributionScoreSkewThresholds,
  this.defaultSkewThreshold,
  this.skewThresholds,
});