Class Explanation.Builder (1.40.0)

publicstaticfinalclass Explanation.BuilderextendsGeneratedMessageV3.Builder<Explanation.Builder>implementsExplanationOrBuilder

Explanation of a prediction (provided in PredictResponse.predictions) produced by the Model on a given instance.

Protobuf type google.cloud.vertexai.v1.Explanation

Inheritance

Object > AbstractMessageLite.Builder<MessageType,BuilderType> > AbstractMessage.Builder<BuilderType> > GeneratedMessageV3.Builder > Explanation.Builder

Implements

ExplanationOrBuilder

Inherited Members

publicstaticfinalDescriptors.DescriptorgetDescriptor()

publicExplanation.BuilderaddAllAttributions(Iterable<?extendsAttribution>values)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderaddAllNeighbors(Iterable<?extendsNeighbor>values)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderaddAttributions(Attributionvalue)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderaddAttributions(Attribution.BuilderbuilderForValue)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderaddAttributions(intindex,Attributionvalue)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderaddAttributions(intindex,Attribution.BuilderbuilderForValue)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicAttribution.BuilderaddAttributionsBuilder()

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicAttribution.BuilderaddAttributionsBuilder(intindex)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderaddNeighbors(Neighborvalue)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderaddNeighbors(Neighbor.BuilderbuilderForValue)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderaddNeighbors(intindex,Neighborvalue)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderaddNeighbors(intindex,Neighbor.BuilderbuilderForValue)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicNeighbor.BuilderaddNeighborsBuilder()

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicNeighbor.BuilderaddNeighborsBuilder(intindex)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderaddRepeatedField(Descriptors.FieldDescriptorfield,Objectvalue)

GeneratedMessageV3.Builder<BuilderType>.addRepeatedField(Descriptors.FieldDescriptor field, Object value)

publicExplanationbuild()

publicExplanationbuildPartial()

publicExplanation.Builderclear()

GeneratedMessageV3.Builder<BuilderType>.clear()

publicExplanation.BuilderclearAttributions()

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderclearField(Descriptors.FieldDescriptorfield)

GeneratedMessageV3.Builder<BuilderType>.clearField(Descriptors.FieldDescriptor field)

publicExplanation.BuilderclearNeighbors()

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderclearOneof(Descriptors.OneofDescriptoroneof)

GeneratedMessageV3.Builder<BuilderType>.clearOneof(Descriptors.OneofDescriptor oneof)

publicExplanation.Builderclone()

GeneratedMessageV3.Builder<BuilderType>.clone()

publicAttributiongetAttributions(intindex)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicAttribution.BuildergetAttributionsBuilder(intindex)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicList<Attribution.Builder>getAttributionsBuilderList()

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicintgetAttributionsCount()

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicList<Attribution>getAttributionsList()

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicAttributionOrBuildergetAttributionsOrBuilder(intindex)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicList<?extendsAttributionOrBuilder>getAttributionsOrBuilderList()

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanationgetDefaultInstanceForType()

publicDescriptors.DescriptorgetDescriptorForType()

GeneratedMessageV3.Builder<BuilderType>.getDescriptorForType()

publicNeighborgetNeighbors(intindex)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicNeighbor.BuildergetNeighborsBuilder(intindex)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicList<Neighbor.Builder>getNeighborsBuilderList()

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicintgetNeighborsCount()

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicList<Neighbor>getNeighborsList()

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicNeighborOrBuildergetNeighborsOrBuilder(intindex)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicList<?extendsNeighborOrBuilder>getNeighborsOrBuilderList()

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

protectedGeneratedMessageV3.FieldAccessorTableinternalGetFieldAccessorTable()

GeneratedMessageV3.Builder<BuilderType>.internalGetFieldAccessorTable()

publicfinalbooleanisInitialized()

GeneratedMessageV3.Builder<BuilderType>.isInitialized()

publicExplanation.BuildermergeFrom(Explanationother)

publicExplanation.BuildermergeFrom(CodedInputStreaminput,ExtensionRegistryLiteextensionRegistry)

AbstractMessage.Builder<BuilderType>.mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

publicExplanation.BuildermergeFrom(Messageother)

AbstractMessage.Builder<BuilderType>.mergeFrom(Message other)

publicfinalExplanation.BuildermergeUnknownFields(UnknownFieldSetunknownFields)

GeneratedMessageV3.Builder<BuilderType>.mergeUnknownFields(UnknownFieldSet unknownFields)

publicExplanation.BuilderremoveAttributions(intindex)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuilderremoveNeighbors(intindex)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuildersetAttributions(intindex,Attributionvalue)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuildersetAttributions(intindex,Attribution.BuilderbuilderForValue)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

repeated .google.cloud.vertexai.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuildersetField(Descriptors.FieldDescriptorfield,Objectvalue)

GeneratedMessageV3.Builder<BuilderType>.setField(Descriptors.FieldDescriptor field, Object value)

publicExplanation.BuildersetNeighbors(intindex,Neighborvalue)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuildersetNeighbors(intindex,Neighbor.BuilderbuilderForValue)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

publicExplanation.BuildersetRepeatedField(Descriptors.FieldDescriptorfield,intindex,Objectvalue)

GeneratedMessageV3.Builder<BuilderType>.setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

publicfinalExplanation.BuildersetUnknownFields(UnknownFieldSetunknownFields)

GeneratedMessageV3.Builder<BuilderType>.setUnknownFields(UnknownFieldSet unknownFields)