Class ModelMonitoringObjectiveConfig.Types.ExplanationConfig (1.6.0)

public sealed class ExplanationConfig : IMessage<ModelMonitoringObjectiveConfig.Types.ExplanationConfig>, IEquatable<ModelMonitoringObjectiveConfig.Types.ExplanationConfig>, IDeepCloneable<ModelMonitoringObjectiveConfig.Types.ExplanationConfig>, IBufferMessage, IMessage

The config for integrating with Vertex Explainable AI. Only applicable if the Model has explanation_spec populated.

Inheritance

Object > ModelMonitoringObjectiveConfig.Types.ExplanationConfig

Implements

IMessage<ModelMonitoringObjectiveConfig.Types.ExplanationConfig>, IEquatable<ModelMonitoringObjectiveConfig.Types.ExplanationConfig>, IDeepCloneable<ModelMonitoringObjectiveConfig.Types.ExplanationConfig>, IBufferMessage, IMessage

Inherited Members

Object.GetHashCode()

Object.GetType()

Object.MemberwiseClone()

Object.ToString()

Namespace

Google.Cloud.AIPlatform.V1

Assembly

Google.Cloud.AIPlatform.V1.dll

Constructors

ExplanationConfig()

public ExplanationConfig()

ExplanationConfig(ModelMonitoringObjectiveConfig.Types.ExplanationConfig)

public ExplanationConfig(ModelMonitoringObjectiveConfig.Types.ExplanationConfig other)

Parameter
Name	Description
`other`	`ModelMonitoringObjectiveConfig.Types.ExplanationConfig`

Properties

EnableFeatureAttributes

public bool EnableFeatureAttributes { get; set; }

If want to analyze the Vertex Explainable AI feature attribute scores or not. If set to true, Vertex AI will log the feature attributions from explain response and do the skew/drift detection for them.

Property Value
Type	Description
`Boolean`

ExplanationBaseline

public ModelMonitoringObjectiveConfig.Types.ExplanationConfig.Types.ExplanationBaseline ExplanationBaseline { get; set; }

Predictions generated by the BatchPredictionJob using baseline dataset.

Property Value
Type	Description
`ModelMonitoringObjectiveConfig.Types.ExplanationConfig.Types.ExplanationBaseline`