Class Google::Cloud::AIPlatform::V1::ModelMonitoringObjectiveConfig::PredictionDriftDetectionConfig (v0.1.0)

The config for Prediction data drift detection.

Inherits

  • Object

Extended By

  • Google::Protobuf::MessageExts::ClassMethods

Includes

  • Google::Protobuf::MessageExts

Methods

#attribution_score_drift_thresholds

def attribution_score_drift_thresholds() -> ::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ThresholdConfig}
Returns
  • (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ThresholdConfig}) — Key is the feature name and value is the threshold. The threshold here is against attribution score distance between different time windows.

#attribution_score_drift_thresholds=

def attribution_score_drift_thresholds=(value) -> ::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ThresholdConfig}
Parameter
  • value (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ThresholdConfig}) — Key is the feature name and value is the threshold. The threshold here is against attribution score distance between different time windows.
Returns
  • (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ThresholdConfig}) — Key is the feature name and value is the threshold. The threshold here is against attribution score distance between different time windows.

#drift_thresholds

def drift_thresholds() -> ::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ThresholdConfig}
Returns
  • (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ThresholdConfig}) — Key is the feature name and value is the threshold. If a feature needs to be monitored for drift, a value threshold must be configured for that feature. The threshold here is against feature distribution distance between different time windws.

#drift_thresholds=

def drift_thresholds=(value) -> ::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ThresholdConfig}
Parameter
  • value (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ThresholdConfig}) — Key is the feature name and value is the threshold. If a feature needs to be monitored for drift, a value threshold must be configured for that feature. The threshold here is against feature distribution distance between different time windws.
Returns
  • (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ThresholdConfig}) — Key is the feature name and value is the threshold. If a feature needs to be monitored for drift, a value threshold must be configured for that feature. The threshold here is against feature distribution distance between different time windws.