AWS::SageMaker::EndpointConfig ClarifyShapConfig
The configuration for SHAP analysis using SageMaker Clarify Explainer.
Syntax
To declare this entity in your Amazon CloudFormation template, use the following syntax:
JSON
{ "NumberOfSamples" :Integer, "Seed" :Integer, "ShapBaselineConfig" :ClarifyShapBaselineConfig, "TextConfig" :ClarifyTextConfig, "UseLogit" :Boolean}
YAML
NumberOfSamples:IntegerSeed:IntegerShapBaselineConfig:ClarifyShapBaselineConfigTextConfig:ClarifyTextConfigUseLogit:Boolean
Properties
NumberOfSamples-
The number of samples to be used for analysis by the Kernal SHAP algorithm.
Note
The number of samples determines the size of the synthetic dataset, which has an impact on latency of explainability requests. For more information, see the Synthetic data of Configure and create an endpoint.
Required: No
Type: Integer
Minimum:
1Update requires: Replacement
Seed-
The starting value used to initialize the random number generator in the explainer. Provide a value for this parameter to obtain a deterministic SHAP result.
Required: No
Type: Integer
Update requires: Replacement
ShapBaselineConfig-
The configuration for the SHAP baseline of the Kernal SHAP algorithm.
Required: Yes
Type: ClarifyShapBaselineConfig
Update requires: Replacement
TextConfig-
A parameter that indicates if text features are treated as text and explanations are provided for individual units of text. Required for natural language processing (NLP) explainability only.
Required: No
Type: ClarifyTextConfig
Update requires: Replacement
UseLogit-
A Boolean toggle to indicate if you want to use the logit function (true) or log-odds units (false) for model predictions. Defaults to false.
Required: No
Type: Boolean
Update requires: Replacement