public static final class ModelExplanation.Builder extends GeneratedMessageV3.Builder<ModelExplanation.Builder> implements ModelExplanationOrBuilder
Aggregated explanation metrics for a Model over a set of instances.
Protobuf type google.cloud.aiplatform.v1beta1.ModelExplanation
Inherited Members
com.google.protobuf.GeneratedMessageV3.Builder.getUnknownFieldSetBuilder()
com.google.protobuf.GeneratedMessageV3.Builder.mergeUnknownLengthDelimitedField(int,com.google.protobuf.ByteString)
com.google.protobuf.GeneratedMessageV3.Builder.mergeUnknownVarintField(int,int)
com.google.protobuf.GeneratedMessageV3.Builder.parseUnknownField(com.google.protobuf.CodedInputStream,com.google.protobuf.ExtensionRegistryLite,int)
com.google.protobuf.GeneratedMessageV3.Builder.setUnknownFieldSetBuilder(com.google.protobuf.UnknownFieldSet.Builder)
Static Methods
public static final Descriptors.Descriptor getDescriptor()
Methods
public ModelExplanation.Builder addAllMeanAttributions(Iterable<? extends Attribution> values)
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 |
|---|
| Name | Description |
values | Iterable<? extends com.google.cloud.aiplatform.v1beta1.Attribution>
|
public ModelExplanation.Builder addMeanAttributions(Attribution value)
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 ModelExplanation.Builder addMeanAttributions(Attribution.Builder builderForValue)
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 ModelExplanation.Builder addMeanAttributions(int index, Attribution value)
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 ModelExplanation.Builder addMeanAttributions(int index, Attribution.Builder builderForValue)
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 Attribution.Builder addMeanAttributionsBuilder()
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 Attribution.Builder addMeanAttributionsBuilder(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 |
|---|
| Name | Description |
index | int
|
public ModelExplanation.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Overrides
public ModelExplanation build()
public ModelExplanation buildPartial()
public ModelExplanation.Builder clear()
Overrides
public ModelExplanation.Builder clearField(Descriptors.FieldDescriptor field)
Overrides
public ModelExplanation.Builder clearMeanAttributions()
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 ModelExplanation.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Overrides
public ModelExplanation.Builder clone()
Overrides
public ModelExplanation getDefaultInstanceForType()
public Descriptors.Descriptor getDescriptorForType()
Overrides
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];
| Parameter |
|---|
| Name | Description |
index | int
|
public Attribution.Builder getMeanAttributionsBuilder(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 |
|---|
| Name | Description |
index | int
|
public List<Attribution.Builder> getMeanAttributionsBuilderList()
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];
| Returns |
|---|
| Type | Description |
int | |
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];
| Parameter |
|---|
| Name | Description |
index | int
|
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];
| Returns |
|---|
| Type | Description |
List<? extends com.google.cloud.aiplatform.v1beta1.AttributionOrBuilder> | |
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Overrides
public final boolean isInitialized()
Overrides
public ModelExplanation.Builder mergeFrom(ModelExplanation other)
public ModelExplanation.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Overrides
public ModelExplanation.Builder mergeFrom(Message other)
| Parameter |
|---|
| Name | Description |
other | Message
|
Overrides
public final ModelExplanation.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Overrides
public ModelExplanation.Builder removeMeanAttributions(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 |
|---|
| Name | Description |
index | int
|
public ModelExplanation.Builder setField(Descriptors.FieldDescriptor field, Object value)
Overrides
public ModelExplanation.Builder setMeanAttributions(int index, Attribution value)
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 ModelExplanation.Builder setMeanAttributions(int index, Attribution.Builder builderForValue)
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 ModelExplanation.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Overrides
public final ModelExplanation.Builder setUnknownFields(UnknownFieldSet unknownFields)
Overrides
