/AWS1/CL_SGMCLARIFYSHAPCONFIG¶
The configuration for SHAP analysis using SageMaker Clarify Explainer.
CONSTRUCTOR¶
IMPORTING¶
Required arguments:¶
io_shapbaselineconfig TYPE REF TO /AWS1/CL_SGMCLARIFYSHAPBASEL00 /AWS1/CL_SGMCLARIFYSHAPBASEL00¶
The configuration for the SHAP baseline of the Kernal SHAP algorithm.
Optional arguments:¶
iv_numberofsamples TYPE /AWS1/SGMCLARIFYSHAPNOOFSAMP00 /AWS1/SGMCLARIFYSHAPNOOFSAMP00¶
The number of samples to be used for analysis by the Kernal SHAP algorithm.
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.
iv_uselogit TYPE /AWS1/SGMCLARIFYSHAPUSELOGIT /AWS1/SGMCLARIFYSHAPUSELOGIT¶
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.
iv_seed TYPE /AWS1/SGMCLARIFYSHAPSEED /AWS1/SGMCLARIFYSHAPSEED¶
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.
io_textconfig TYPE REF TO /AWS1/CL_SGMCLARIFYTEXTCONFIG /AWS1/CL_SGMCLARIFYTEXTCONFIG¶
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.
Queryable Attributes¶
ShapBaselineConfig¶
The configuration for the SHAP baseline of the Kernal SHAP algorithm.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_SHAPBASELINECONFIG() |
Getter for SHAPBASELINECONFIG |
NumberOfSamples¶
The number of samples to be used for analysis by the Kernal SHAP algorithm.
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.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_NUMBEROFSAMPLES() |
Getter for NUMBEROFSAMPLES, with configurable default |
ASK_NUMBEROFSAMPLES() |
Getter for NUMBEROFSAMPLES w/ exceptions if field has no val |
HAS_NUMBEROFSAMPLES() |
Determine if NUMBEROFSAMPLES has a value |
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.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_USELOGIT() |
Getter for USELOGIT, with configurable default |
ASK_USELOGIT() |
Getter for USELOGIT w/ exceptions if field has no value |
HAS_USELOGIT() |
Determine if USELOGIT has a value |
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.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_SEED() |
Getter for SEED, with configurable default |
ASK_SEED() |
Getter for SEED w/ exceptions if field has no value |
HAS_SEED() |
Determine if SEED has a value |
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.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_TEXTCONFIG() |
Getter for TEXTCONFIG |