ModelExplainabilityCheckConfig: Model Explainability Check Config

In DyfanJones/sagemaker-r-workflow: sagemaker pipeline and workflows

Model Explainability Check Config

Description

Model Explainability Check Config

Model Explainability Check Config

Super class

sagemaker.workflow::ClarifyCheckConfig -> ModelExplainabilityCheckConfig

Public fields

model_config

Config of the model and its endpoint to be created

explainability_config

Config of the specific explainability method

model_scores

Index or JSONPath location in the model output

Methods

Public methods

• ModelExplainabilityCheckConfig$new()

• ModelExplainabilityCheckConfig$clone()

Inherited methods

• sagemaker.workflow::ClarifyCheckConfig$format()

---

Method new()

Initialize ModelExplainabilityCheckConfig class

Usage

ModelExplainabilityCheckConfig$new(
  model_config,
  explainability_config,
  model_scores = NULL,
  ...
)

Arguments

model_config

(ModelConfig): Config of the model and its endpoint to be created.

explainability_config

(SHAPConfig): Config of the specific explainability method. Currently, only SHAP is supported.

model_scores

(str or int or ModelPredictedLabelConfig): Index or JSONPath location in the model output for the predicted scores to be explained (default: None). This is not required if the model output is a single score. Alternatively, an instance of ModelPredictedLabelConfig can be provided but this field CANNOT be any of PipelineNonPrimitiveInputTypes.

...

: Parameters from ClarifyCheckConfig

---

Method clone()

The objects of this class are cloneable with this method.

Usage

ModelExplainabilityCheckConfig$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

DyfanJones/sagemaker-r-workflow documentation built on April 3, 2022, 11:28 p.m.