public final class ModelExplanation extends GeneratedMessageV3 implements ModelExplanationOrBuilder
Aggregated explanation metrics for a Model over a set of instances.
Protobuf type google.cloud.aiplatform.v1beta1.ModelExplanation
Fields
public static final int MEAN_ATTRIBUTIONS_FIELD_NUMBER
Field Value
Methods
public boolean equals(Object obj)
Parameter
Returns
Overrides
public static ModelExplanation getDefaultInstance()
Returns
public ModelExplanation getDefaultInstanceForType()
Returns
public static final Descriptors.Descriptor getDescriptor()
Returns
public 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];
public 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];
public 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];
public 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];
public 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];
| Type | Description |
| List<? extends com.google.cloud.aiplatform.v1beta1.AttributionOrBuilder> | |
public Parser<ModelExplanation> getParserForType()
Returns
Overrides
public int getSerializedSize()
Returns
Overrides
public final UnknownFieldSet getUnknownFields()
Returns
Overrides
Returns
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Overrides
public final boolean isInitialized()
Returns
Overrides
public static ModelExplanation.Builder newBuilder()
Returns
public static ModelExplanation.Builder newBuilder(ModelExplanation prototype)
Parameter
Returns
public ModelExplanation.Builder newBuilderForType()
Returns
protected ModelExplanation.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Returns
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Returns
Overrides
public static ModelExplanation parseDelimitedFrom(InputStream input)
Parameter
Returns
Exceptions
public static ModelExplanation parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ModelExplanation parseFrom(byte[] data)
Parameter
| Name | Description |
| data | byte[]
|
Returns
Exceptions
public static ModelExplanation parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ModelExplanation parseFrom(ByteString data)
Parameter
Returns
Exceptions
public static ModelExplanation parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ModelExplanation parseFrom(CodedInputStream input)
Parameter
Returns
Exceptions
public static ModelExplanation parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ModelExplanation parseFrom(InputStream input)
Parameter
Returns
Exceptions
public static ModelExplanation parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ModelExplanation parseFrom(ByteBuffer data)
Parameter
Returns
Exceptions
public static ModelExplanation parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static Parser<ModelExplanation> parser()
Returns
public ModelExplanation.Builder toBuilder()
Returns
public void writeTo(CodedOutputStream output)
Parameter
Overrides
Exceptions
