Package com.google.cloud.aiplatform.v1

Interface ModelExplanationOrBuilder

All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
All Known Implementing Classes:
ModelExplanation, ModelExplanation.Builder
@Generated public interface ModelExplanationOrBuilder extends com.google.protobuf.MessageOrBuilder

  • Method Details

    • getMeanAttributionsList

      List<Attribution> getMeanAttributionsList()
       Output only. Aggregated attributions explaining the Model's prediction
 outputs over the set of instances. The attributions are grouped by outputs.

 For Models that predict only one output, such as regression Models that
 predict only one score, there is only one attibution that explains the
 predicted output. For Models that predict multiple outputs, such as
 multiclass Models that predict multiple classes, each element explains one
 specific item.
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 can be used to identify which output this attribution is explaining.

 The
 [baselineOutputValue][google.cloud.aiplatform.v1.Attribution.baseline_output_value],
 [instanceOutputValue][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 and
 [featureAttributions][google.cloud.aiplatform.v1.Attribution.feature_attributions]
 fields are averaged over the test data.

 NOTE: Currently AutoML tabular classification Models produce only one
 attribution, which averages attributions over all the classes it predicts.
 [Attribution.approximation_error][google.cloud.aiplatform.v1.Attribution.approximation_error]
 is not populated.
      repeated .google.cloud.aiplatform.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • getMeanAttributions

      Attribution getMeanAttributions(int index)
       Output only. Aggregated attributions explaining the Model's prediction
 outputs over the set of instances. The attributions are grouped by outputs.

 For Models that predict only one output, such as regression Models that
 predict only one score, there is only one attibution that explains the
 predicted output. For Models that predict multiple outputs, such as
 multiclass Models that predict multiple classes, each element explains one
 specific item.
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 can be used to identify which output this attribution is explaining.

 The
 [baselineOutputValue][google.cloud.aiplatform.v1.Attribution.baseline_output_value],
 [instanceOutputValue][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 and
 [featureAttributions][google.cloud.aiplatform.v1.Attribution.feature_attributions]
 fields are averaged over the test data.

 NOTE: Currently AutoML tabular classification Models produce only one
 attribution, which averages attributions over all the classes it predicts.
 [Attribution.approximation_error][google.cloud.aiplatform.v1.Attribution.approximation_error]
 is not populated.
      repeated .google.cloud.aiplatform.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • getMeanAttributionsCount

      int getMeanAttributionsCount()
       Output only. Aggregated attributions explaining the Model's prediction
 outputs over the set of instances. The attributions are grouped by outputs.

 For Models that predict only one output, such as regression Models that
 predict only one score, there is only one attibution that explains the
 predicted output. For Models that predict multiple outputs, such as
 multiclass Models that predict multiple classes, each element explains one
 specific item.
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 can be used to identify which output this attribution is explaining.

 The
 [baselineOutputValue][google.cloud.aiplatform.v1.Attribution.baseline_output_value],
 [instanceOutputValue][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 and
 [featureAttributions][google.cloud.aiplatform.v1.Attribution.feature_attributions]
 fields are averaged over the test data.

 NOTE: Currently AutoML tabular classification Models produce only one
 attribution, which averages attributions over all the classes it predicts.
 [Attribution.approximation_error][google.cloud.aiplatform.v1.Attribution.approximation_error]
 is not populated.
      repeated .google.cloud.aiplatform.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • getMeanAttributionsOrBuilderList

      List<? extends AttributionOrBuilder> getMeanAttributionsOrBuilderList()
       Output only. Aggregated attributions explaining the Model's prediction
 outputs over the set of instances. The attributions are grouped by outputs.

 For Models that predict only one output, such as regression Models that
 predict only one score, there is only one attibution that explains the
 predicted output. For Models that predict multiple outputs, such as
 multiclass Models that predict multiple classes, each element explains one
 specific item.
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 can be used to identify which output this attribution is explaining.

 The
 [baselineOutputValue][google.cloud.aiplatform.v1.Attribution.baseline_output_value],
 [instanceOutputValue][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 and
 [featureAttributions][google.cloud.aiplatform.v1.Attribution.feature_attributions]
 fields are averaged over the test data.

 NOTE: Currently AutoML tabular classification Models produce only one
 attribution, which averages attributions over all the classes it predicts.
 [Attribution.approximation_error][google.cloud.aiplatform.v1.Attribution.approximation_error]
 is not populated.
      repeated .google.cloud.aiplatform.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • getMeanAttributionsOrBuilder

      AttributionOrBuilder getMeanAttributionsOrBuilder(int index)
       Output only. Aggregated attributions explaining the Model's prediction
 outputs over the set of instances. The attributions are grouped by outputs.

 For Models that predict only one output, such as regression Models that
 predict only one score, there is only one attibution that explains the
 predicted output. For Models that predict multiple outputs, such as
 multiclass Models that predict multiple classes, each element explains one
 specific item.
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 can be used to identify which output this attribution is explaining.

 The
 [baselineOutputValue][google.cloud.aiplatform.v1.Attribution.baseline_output_value],
 [instanceOutputValue][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 and
 [featureAttributions][google.cloud.aiplatform.v1.Attribution.feature_attributions]
 fields are averaged over the test data.

 NOTE: Currently AutoML tabular classification Models produce only one
 attribution, which averages attributions over all the classes it predicts.
 [Attribution.approximation_error][google.cloud.aiplatform.v1.Attribution.approximation_error]
 is not populated.
      repeated .google.cloud.aiplatform.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];