Cloud AI Platform v1 API - Class Attribution (2.22.0)

public sealed class Attribution : IMessage<Attribution>, IEquatable<Attribution>, IDeepCloneable<Attribution>, IBufferMessage, IMessage

Reference documentation and code samples for the Cloud AI Platform v1 API class Attribution.

Attribution that explains a particular prediction output.

Inheritance

object > Attribution

Namespace

Google.Cloud.AIPlatform.V1

Assembly

Google.Cloud.AIPlatform.V1.dll

Constructors

Attribution()

public Attribution()

Attribution(Attribution)

public Attribution(Attribution other)
Parameter
NameDescription
otherAttribution

Properties

ApproximationError

public double ApproximationError { get; set; }

Output only. Error of [feature_attributions][google.cloud.aiplatform.v1.Attribution.feature_attributions] caused by approximation used in the explanation method. Lower value means more precise attributions.

  • For Sampled Shapley [attribution][google.cloud.aiplatform.v1.ExplanationParameters.sampled_shapley_attribution], increasing [path_count][google.cloud.aiplatform.v1.SampledShapleyAttribution.path_count] might reduce the error.
  • For Integrated Gradients [attribution][google.cloud.aiplatform.v1.ExplanationParameters.integrated_gradients_attribution], increasing [step_count][google.cloud.aiplatform.v1.IntegratedGradientsAttribution.step_count] might reduce the error.
  • For [XRAI attribution][google.cloud.aiplatform.v1.ExplanationParameters.xrai_attribution], increasing [step_count][google.cloud.aiplatform.v1.XraiAttribution.step_count] might reduce the error.

See this introduction for more information.

Property Value
TypeDescription
double

BaselineOutputValue

public double BaselineOutputValue { get; set; }

Output only. Model predicted output if the input instance is constructed from the baselines of all the features defined in [ExplanationMetadata.inputs][google.cloud.aiplatform.v1.ExplanationMetadata.inputs]. The field name of the output is determined by the key in [ExplanationMetadata.outputs][google.cloud.aiplatform.v1.ExplanationMetadata.outputs].

If the Model's predicted output has multiple dimensions (rank > 1), this is the value in the output located by [output_index][google.cloud.aiplatform.v1.Attribution.output_index].

If there are multiple baselines, their output values are averaged.

Property Value
TypeDescription
double

FeatureAttributions

public Value FeatureAttributions { get; set; }

Output only. Attributions of each explained feature. Features are extracted from the [prediction instances][google.cloud.aiplatform.v1.ExplainRequest.instances] according to [explanation metadata for inputs][google.cloud.aiplatform.v1.ExplanationMetadata.inputs].

The value is a struct, whose keys are the name of the feature. The values are how much the feature in the [instance][google.cloud.aiplatform.v1.ExplainRequest.instances] contributed to the predicted result.

The format of the value is determined by the feature's input format:

  • If the feature is a scalar value, the attribution value is a [floating number][google.protobuf.Value.number_value].

  • If the feature is an array of scalar values, the attribution value is an [array][google.protobuf.Value.list_value].

  • If the feature is a struct, the attribution value is a [struct][google.protobuf.Value.struct_value]. The keys in the attribution value struct are the same as the keys in the feature struct. The formats of the values in the attribution struct are determined by the formats of the values in the feature struct.

The [ExplanationMetadata.feature_attributions_schema_uri][google.cloud.aiplatform.v1.ExplanationMetadata.feature_attributions_schema_uri] field, pointed to by the [ExplanationSpec][google.cloud.aiplatform.v1.ExplanationSpec] field of the [Endpoint.deployed_models][google.cloud.aiplatform.v1.Endpoint.deployed_models] object, points to the schema file that describes the features and their attribution values (if it is populated).

Property Value
TypeDescription
Value

InstanceOutputValue

public double InstanceOutputValue { get; set; }

Output only. Model predicted output on the corresponding [explanation instance][ExplainRequest.instances]. The field name of the output is determined by the key in [ExplanationMetadata.outputs][google.cloud.aiplatform.v1.ExplanationMetadata.outputs].

If the Model predicted output has multiple dimensions, this is the value in the output located by [output_index][google.cloud.aiplatform.v1.Attribution.output_index].

Property Value
TypeDescription
double

OutputDisplayName

public string OutputDisplayName { get; set; }

Output only. The display name of the output identified by [output_index][google.cloud.aiplatform.v1.Attribution.output_index]. For example, the predicted class name by a multi-classification Model.

This field is only populated iff the Model predicts display names as a separate field along with the explained output. The predicted display name must has the same shape of the explained output, and can be located using output_index.

Property Value
TypeDescription
string

OutputIndex

public RepeatedField<int> OutputIndex { get; }

Output only. The index that locates the explained prediction output.

If the prediction output is a scalar value, output_index is not populated. If the prediction output has multiple dimensions, the length of the output_index list is the same as the number of dimensions of the output. The i-th element in output_index is the element index of the i-th dimension of the output vector. Indices start from 0.

Property Value
TypeDescription
RepeatedFieldint

OutputName

public string OutputName { get; set; }

Output only. Name of the explain output. Specified as the key in [ExplanationMetadata.outputs][google.cloud.aiplatform.v1.ExplanationMetadata.outputs].

Property Value
TypeDescription
string