Cloud AI Platform v1 API - Class Explanation (3.11.0) 

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

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

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].

Inheritance

object > Explanation

Namespace

Google.Cloud.AIPlatform.V1

Assembly

Google.Cloud.AIPlatform.V1.dll

Constructors

Explanation()

public Explanation()

Explanation(Explanation)

public Explanation(Explanation other)
Parameter
Name Description
other Explanation

Properties

Attributions

public RepeatedField<Attribution> Attributions { get; }

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.

Property Value
Type Description
RepeatedFieldAttribution

Neighbors

public RepeatedField<Neighbor> Neighbors { get; }

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.

Property Value
Type Description
RepeatedFieldNeighbor