Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigExplanationConfig
- Inherits:
-
Object
- Object
- Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigExplanationConfig
- Includes:
- Core::Hashable, Core::JsonObjectSupport
- Defined in:
- lib/google/apis/aiplatform_v1/classes.rb,
lib/google/apis/aiplatform_v1/representations.rb,
lib/google/apis/aiplatform_v1/representations.rb
Overview
The config for integrating with Vertex Explainable AI. Only applicable if the Model has explanation_spec populated.
Instance Attribute Summary collapse
-
#enable_feature_attributes ⇒ Boolean
(also: #enable_feature_attributes?)
If want to analyze the Vertex Explainable AI feature attribute scores or not.
-
#explanation_baseline ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigExplanationConfigExplanationBaseline
Output from BatchPredictionJob for Model Monitoring baseline dataset, which can be used to generate baseline attribution scores.
Instance Method Summary collapse
-
#initialize(**args) ⇒ GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigExplanationConfig
constructor
A new instance of GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigExplanationConfig.
-
#update!(**args) ⇒ Object
Update properties of this object.
Constructor Details
#initialize(**args) ⇒ GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigExplanationConfig
Returns a new instance of GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigExplanationConfig.
16058 16059 16060 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16058 def initialize(**args) update!(**args) end |
Instance Attribute Details
#enable_feature_attributes ⇒ Boolean Also known as: enable_feature_attributes?
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.
Corresponds to the JSON property enableFeatureAttributes
16049 16050 16051 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16049 def enable_feature_attributes @enable_feature_attributes end |
#explanation_baseline ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigExplanationConfigExplanationBaseline
Output from BatchPredictionJob for Model Monitoring baseline dataset, which
can be used to generate baseline attribution scores.
Corresponds to the JSON property explanationBaseline
16056 16057 16058 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16056 def explanation_baseline @explanation_baseline end |
Instance Method Details
#update!(**args) ⇒ Object
Update properties of this object
16063 16064 16065 16066 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16063 def update!(**args) @enable_feature_attributes = args[:enable_feature_attributes] if args.key?(:enable_feature_attributes) @explanation_baseline = args[:explanation_baseline] if args.key?(:explanation_baseline) end |