Google Cloud Ai Platform V1 Client - Class ExplanationConfig (0.15.0)

Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class ExplanationConfig.

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

Generated from protobuf message google.cloud.aiplatform.v1.ModelMonitoringObjectiveConfig.ExplanationConfig

Methods

__construct

Constructor.

Parameters
NameDescription
data array

Optional. Data for populating the Message object.

↳ enable_feature_attributes bool

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.

↳ explanation_baseline Google\Cloud\AIPlatform\V1\ModelMonitoringObjectiveConfig\ExplanationConfig\ExplanationBaseline

Predictions generated by the BatchPredictionJob using baseline dataset.

getEnableFeatureAttributes

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.

Returns
TypeDescription
bool

setEnableFeatureAttributes

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.

Parameter
NameDescription
var bool
Returns
TypeDescription
$this

getExplanationBaseline

Predictions generated by the BatchPredictionJob using baseline dataset.

Returns
TypeDescription
Google\Cloud\AIPlatform\V1\ModelMonitoringObjectiveConfig\ExplanationConfig\ExplanationBaseline|null

hasExplanationBaseline

clearExplanationBaseline

setExplanationBaseline

Predictions generated by the BatchPredictionJob using baseline dataset.

Parameter
NameDescription
var Google\Cloud\AIPlatform\V1\ModelMonitoringObjectiveConfig\ExplanationConfig\ExplanationBaseline
Returns
TypeDescription
$this