Interface ModelExplanationOrBuilder (3.16.0) 

public interface ModelExplanationOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getMeanAttributions(int index)

public abstract 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 can be used to identify which output this attribution is explaining. The baselineOutputValue, instanceOutputValue and featureAttributions 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 is not populated.

repeated .google.cloud.aiplatform.v1beta1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
NameDescription
indexint
Returns
TypeDescription
Attribution

getMeanAttributionsCount()

public abstract 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 can be used to identify which output this attribution is explaining. The baselineOutputValue, instanceOutputValue and featureAttributions 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 is not populated.

repeated .google.cloud.aiplatform.v1beta1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
TypeDescription
int

getMeanAttributionsList()

public abstract 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 can be used to identify which output this attribution is explaining. The baselineOutputValue, instanceOutputValue and featureAttributions 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 is not populated.

repeated .google.cloud.aiplatform.v1beta1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
TypeDescription
List<Attribution>

getMeanAttributionsOrBuilder(int index)

public abstract 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 can be used to identify which output this attribution is explaining. The baselineOutputValue, instanceOutputValue and featureAttributions 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 is not populated.

repeated .google.cloud.aiplatform.v1beta1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
NameDescription
indexint
Returns
TypeDescription
AttributionOrBuilder

getMeanAttributionsOrBuilderList()

public abstract 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 can be used to identify which output this attribution is explaining. The baselineOutputValue, instanceOutputValue and featureAttributions 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 is not populated.

repeated .google.cloud.aiplatform.v1beta1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
TypeDescription
List<? extends com.google.cloud.aiplatform.v1beta1.AttributionOrBuilder>