Package com.google.cloud.aiplatform.v1beta1

Interface ExplanationOrBuilder

  • All Superinterfaces:
    com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
    All Known Implementing Classes:
    Explanation, Explanation.Builder
    public interface ExplanationOrBuilder
extends com.google.protobuf.MessageOrBuilder

    • Method Detail

      • getAttributionsList

        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.v1beta1.Attribution.output_index]
 can be used to identify which output this attribution is explaining.

 If users set
 [ExplanationParameters.top_k][google.cloud.aiplatform.v1beta1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][Attributions.instance_output_value] in descending
 order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1beta1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1beta1.Attribution.output_index]
 in the same order as they appear in the output_indices.
        repeated .google.cloud.aiplatform.v1beta1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

      • getAttributions

        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.v1beta1.Attribution.output_index]
 can be used to identify which output this attribution is explaining.

 If users set
 [ExplanationParameters.top_k][google.cloud.aiplatform.v1beta1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][Attributions.instance_output_value] in descending
 order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1beta1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1beta1.Attribution.output_index]
 in the same order as they appear in the output_indices.
        repeated .google.cloud.aiplatform.v1beta1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

      • getAttributionsCount

        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.v1beta1.Attribution.output_index]
 can be used to identify which output this attribution is explaining.

 If users set
 [ExplanationParameters.top_k][google.cloud.aiplatform.v1beta1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][Attributions.instance_output_value] in descending
 order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1beta1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1beta1.Attribution.output_index]
 in the same order as they appear in the output_indices.
        repeated .google.cloud.aiplatform.v1beta1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

      • getAttributionsOrBuilderList

        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.v1beta1.Attribution.output_index]
 can be used to identify which output this attribution is explaining.

 If users set
 [ExplanationParameters.top_k][google.cloud.aiplatform.v1beta1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][Attributions.instance_output_value] in descending
 order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1beta1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1beta1.Attribution.output_index]
 in the same order as they appear in the output_indices.
        repeated .google.cloud.aiplatform.v1beta1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

      • getAttributionsOrBuilder

        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.v1beta1.Attribution.output_index]
 can be used to identify which output this attribution is explaining.

 If users set
 [ExplanationParameters.top_k][google.cloud.aiplatform.v1beta1.ExplanationParameters.top_k],
 the attributions are sorted by
 [instance_output_value][Attributions.instance_output_value] in descending
 order. If
 [ExplanationParameters.output_indices][google.cloud.aiplatform.v1beta1.ExplanationParameters.output_indices]
 is specified, the attributions are stored by
 [Attribution.output_index][google.cloud.aiplatform.v1beta1.Attribution.output_index]
 in the same order as they appear in the output_indices.
        repeated .google.cloud.aiplatform.v1beta1.Attribution attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

      • getNeighborsList

        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.v1beta1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

      • getNeighbors

        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.v1beta1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

      • getNeighborsCount

        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.v1beta1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

      • getNeighborsOrBuilderList

        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.v1beta1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

      • getNeighborsOrBuilder

        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.v1beta1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];