Package com.google.cloud.aiplatform.v1

Class Explanation.Builder

java.lang.Object
com.google.protobuf.AbstractMessageLite.Builder
com.google.protobuf.AbstractMessage.Builder<BuilderT>
com.google.protobuf.GeneratedMessage.Builder<Explanation.Builder>
com.google.cloud.aiplatform.v1.Explanation.Builder
All Implemented Interfaces:
ExplanationOrBuilder, com.google.protobuf.Message.Builder, com.google.protobuf.MessageLite.Builder, com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder, Cloneable
Enclosing class:
Explanation
public static final class Explanation.Builder extends com.google.protobuf.GeneratedMessage.Builder<Explanation.Builder> implements ExplanationOrBuilder
 Explanation of a prediction (provided in
 [PredictResponse.predictions][google.cloud.aiplatform.v1.PredictResponse.predictions])
 produced by the Model on a given
 [instance][google.cloud.aiplatform.v1.ExplainRequest.instances].
Protobuf type google.cloud.aiplatform.v1.Explanation

  • Method Details

    • getDescriptor

      public static final com.google.protobuf.Descriptors.Descriptor getDescriptor()

    • internalGetFieldAccessorTable

      protected com.google.protobuf.GeneratedMessage.FieldAccessorTable internalGetFieldAccessorTable()
      Specified by:
      internalGetFieldAccessorTable in class com.google.protobuf.GeneratedMessage.Builder<Explanation.Builder>

    • clear

      public Explanation.Builder clear()
      Specified by:
      clear in interface com.google.protobuf.Message.Builder
      Specified by:
      clear in interface com.google.protobuf.MessageLite.Builder
      Overrides:
      clear in class com.google.protobuf.GeneratedMessage.Builder<Explanation.Builder>

    • getDescriptorForType

      public com.google.protobuf.Descriptors.Descriptor getDescriptorForType()
      Specified by:
      getDescriptorForType in interface com.google.protobuf.Message.Builder
      Specified by:
      getDescriptorForType in interface com.google.protobuf.MessageOrBuilder
      Overrides:
      getDescriptorForType in class com.google.protobuf.GeneratedMessage.Builder<Explanation.Builder>

    • getDefaultInstanceForType

      public Explanation getDefaultInstanceForType()
      Specified by:
      getDefaultInstanceForType in interface com.google.protobuf.MessageLiteOrBuilder
      Specified by:
      getDefaultInstanceForType in interface com.google.protobuf.MessageOrBuilder

    • build

      public Explanation build()
      Specified by:
      build in interface com.google.protobuf.Message.Builder
      Specified by:
      build in interface com.google.protobuf.MessageLite.Builder

    • buildPartial

      public Explanation buildPartial()
      Specified by:
      buildPartial in interface com.google.protobuf.Message.Builder
      Specified by:
      buildPartial in interface com.google.protobuf.MessageLite.Builder

    • mergeFrom

      public Explanation.Builder mergeFrom(com.google.protobuf.Message other)
      Specified by:
      mergeFrom in interface com.google.protobuf.Message.Builder
      Overrides:
      mergeFrom in class com.google.protobuf.AbstractMessage.Builder<Explanation.Builder>

    • mergeFrom

      public Explanation.Builder mergeFrom(Explanation other)

    • isInitialized

      public final boolean isInitialized()
      Specified by:
      isInitialized in interface com.google.protobuf.MessageLiteOrBuilder
      Overrides:
      isInitialized in class com.google.protobuf.GeneratedMessage.Builder<Explanation.Builder>

    • mergeFrom

      public Explanation.Builder mergeFrom(com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException
      Specified by:
      mergeFrom in interface com.google.protobuf.Message.Builder
      Specified by:
      mergeFrom in interface com.google.protobuf.MessageLite.Builder
      Overrides:
      mergeFrom in class com.google.protobuf.AbstractMessage.Builder<Explanation.Builder>
      Throws:
      IOException

    • getAttributionsList

      public List<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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];
      Specified by:
      getAttributionsList in interface ExplanationOrBuilder

    • getAttributionsCount

      public int getAttributionsCount()
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];
      Specified by:
      getAttributionsCount in interface ExplanationOrBuilder

    • getAttributions

      public Attribution getAttributions(int index)
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];
      Specified by:
      getAttributions in interface ExplanationOrBuilder

    • setAttributions

      public Explanation.Builder setAttributions(int index, Attribution value)
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • setAttributions

      public Explanation.Builder setAttributions(int index, Attribution.Builder builderForValue)
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addAttributions

      public Explanation.Builder addAttributions(Attribution value)
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addAttributions

      public Explanation.Builder addAttributions(int index, Attribution value)
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addAttributions

      public Explanation.Builder addAttributions(Attribution.Builder builderForValue)
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addAttributions

      public Explanation.Builder addAttributions(int index, Attribution.Builder builderForValue)
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addAllAttributions

      public Explanation.Builder addAllAttributions(Iterable<? extends Attribution> 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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • clearAttributions

      public Explanation.Builder clearAttributions()
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • removeAttributions

      public Explanation.Builder removeAttributions(int index)
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • getAttributionsBuilder

      public Attribution.Builder getAttributionsBuilder(int index)
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • getAttributionsOrBuilder

      public AttributionOrBuilder getAttributionsOrBuilder(int index)
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];
      Specified by:
      getAttributionsOrBuilder in interface ExplanationOrBuilder

    • getAttributionsOrBuilderList

      public List<? extends AttributionOrBuilder> 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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];
      Specified by:
      getAttributionsOrBuilderList in interface ExplanationOrBuilder

    • addAttributionsBuilder

      public Attribution.Builder addAttributionsBuilder()
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addAttributionsBuilder

      public Attribution.Builder addAttributionsBuilder(int index)
       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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • getAttributionsBuilderList

      public List<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][google.cloud.aiplatform.v1.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][google.cloud.aiplatform.v1.Attribution.instance_output_value]
 in descending order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index]
 in the same order as they appear in the output_indices.
      repeated .google.cloud.aiplatform.v1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • getNeighborsList

      public List<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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];
      Specified by:
      getNeighborsList in interface ExplanationOrBuilder

    • getNeighborsCount

      public int getNeighborsCount()
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];
      Specified by:
      getNeighborsCount in interface ExplanationOrBuilder

    • getNeighbors

      public Neighbor getNeighbors(int index)
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];
      Specified by:
      getNeighbors in interface ExplanationOrBuilder

    • setNeighbors

      public Explanation.Builder setNeighbors(int index, Neighbor value)
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • setNeighbors

      public Explanation.Builder setNeighbors(int index, Neighbor.Builder builderForValue)
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addNeighbors

      public Explanation.Builder addNeighbors(Neighbor value)
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addNeighbors

      public Explanation.Builder addNeighbors(int index, Neighbor value)
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addNeighbors

      public Explanation.Builder addNeighbors(Neighbor.Builder builderForValue)
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addNeighbors

      public Explanation.Builder addNeighbors(int index, Neighbor.Builder builderForValue)
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addAllNeighbors

      public Explanation.Builder addAllNeighbors(Iterable<? extends Neighbor> 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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • clearNeighbors

      public Explanation.Builder clearNeighbors()
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • removeNeighbors

      public Explanation.Builder removeNeighbors(int index)
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • getNeighborsBuilder

      public Neighbor.Builder getNeighborsBuilder(int index)
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • getNeighborsOrBuilder

      public NeighborOrBuilder getNeighborsOrBuilder(int index)
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];
      Specified by:
      getNeighborsOrBuilder in interface ExplanationOrBuilder

    • getNeighborsOrBuilderList

      public List<? extends NeighborOrBuilder> 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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];
      Specified by:
      getNeighborsOrBuilderList in interface ExplanationOrBuilder

    • addNeighborsBuilder

      public Neighbor.Builder addNeighborsBuilder()
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • addNeighborsBuilder

      public Neighbor.Builder addNeighborsBuilder(int index)
       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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

    • getNeighborsBuilderList

      public List<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.aiplatform.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];