Copyright	(c) 2013-2023 Brendan Hay
License	Mozilla Public License, v. 2.0.
Maintainer	Brendan Hay
Stability	auto-generated
Portability	non-portable (GHC extensions)
Safe Haskell	Safe-Inferred
Language	Haskell2010

Amazonka.SageMaker.Types.ClarifyShapConfig

Description

Documentation

data ClarifyShapConfig Source #

The configuration for SHAP analysis using SageMaker Clarify Explainer.

See: newClarifyShapConfig smart constructor.

Constructors

ClarifyShapConfig'

Fields

numberOfSamples :: Maybe Natural
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.
seed :: Maybe Int
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.
textConfig :: Maybe ClarifyTextConfig
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.
useLogit :: Maybe Bool
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.
shapBaselineConfig :: ClarifyShapBaselineConfig
The configuration for the SHAP baseline of the Kernal SHAP algorithm.

Instances

Instances details

FromJSON ClarifyShapConfig Source #
Instance details Defined in Amazonka.SageMaker.Types.ClarifyShapConfig Methods parseJSON :: Value -> Parser ClarifyShapConfig # parseJSONList :: Value -> Parser [ClarifyShapConfig] #
ToJSON ClarifyShapConfig Source #
Instance details Defined in Amazonka.SageMaker.Types.ClarifyShapConfig Methods toJSON :: ClarifyShapConfig -> Value # toEncoding :: ClarifyShapConfig -> Encoding # toJSONList :: [ClarifyShapConfig] -> Value # toEncodingList :: [ClarifyShapConfig] -> Encoding #
Generic ClarifyShapConfig Source #
Instance details Defined in Amazonka.SageMaker.Types.ClarifyShapConfig Associated Types type Rep ClarifyShapConfig :: Type -> Type # Methods from :: ClarifyShapConfig -> Rep ClarifyShapConfig x # to :: Rep ClarifyShapConfig x -> ClarifyShapConfig #
Read ClarifyShapConfig Source #
Instance details Defined in Amazonka.SageMaker.Types.ClarifyShapConfig Methods readsPrec :: Int -> ReadS ClarifyShapConfig # readList :: ReadS [ClarifyShapConfig] # readPrec :: ReadPrec ClarifyShapConfig # readListPrec :: ReadPrec [ClarifyShapConfig] #
Show ClarifyShapConfig Source #
Instance details Defined in Amazonka.SageMaker.Types.ClarifyShapConfig Methods showsPrec :: Int -> ClarifyShapConfig -> ShowS # show :: ClarifyShapConfig -> String # showList :: [ClarifyShapConfig] -> ShowS #
NFData ClarifyShapConfig Source #
Instance details Defined in Amazonka.SageMaker.Types.ClarifyShapConfig Methods rnf :: ClarifyShapConfig -> () #
Eq ClarifyShapConfig Source #
Instance details Defined in Amazonka.SageMaker.Types.ClarifyShapConfig Methods (==) :: ClarifyShapConfig -> ClarifyShapConfig -> Bool # (/=) :: ClarifyShapConfig -> ClarifyShapConfig -> Bool #
Hashable ClarifyShapConfig Source #
Instance details Defined in Amazonka.SageMaker.Types.ClarifyShapConfig Methods hashWithSalt :: Int -> ClarifyShapConfig -> Int # hash :: ClarifyShapConfig -> Int #
type Rep ClarifyShapConfig Source #
Instance details Defined in Amazonka.SageMaker.Types.ClarifyShapConfig type Rep ClarifyShapConfig = D1 ('MetaData "ClarifyShapConfig" "Amazonka.SageMaker.Types.ClarifyShapConfig" "amazonka-sagemaker-2.0-9SyrKZ4KqhsL1qX9u3ILA3" 'False) (C1 ('MetaCons "ClarifyShapConfig'" 'PrefixI 'True) ((S1 ('MetaSel ('Just "numberOfSamples") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Natural)) :: S1 ('MetaSel ('Just "seed") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Int))) :: (S1 ('MetaSel ('Just "textConfig") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe ClarifyTextConfig)) :: (S1 ('MetaSel ('Just "useLogit") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Bool)) :: S1 ('MetaSel ('Just "shapBaselineConfig") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 ClarifyShapBaselineConfig)))))

newClarifyShapConfig Source #

Arguments

:: ClarifyShapBaselineConfig	`$sel:shapBaselineConfig:ClarifyShapConfig'`
-> ClarifyShapConfig

Create a value of ClarifyShapConfig with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

$sel:numberOfSamples:ClarifyShapConfig', clarifyShapConfig_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.

$sel:seed:ClarifyShapConfig', clarifyShapConfig_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.

$sel:textConfig:ClarifyShapConfig', clarifyShapConfig_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.

$sel:useLogit:ClarifyShapConfig', clarifyShapConfig_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.

$sel:shapBaselineConfig:ClarifyShapConfig', clarifyShapConfig_shapBaselineConfig - The configuration for the SHAP baseline of the Kernal SHAP algorithm.

clarifyShapConfig_numberOfSamples :: Lens' ClarifyShapConfig (Maybe Natural) Source #

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.

clarifyShapConfig_seed :: Lens' ClarifyShapConfig (Maybe Int) Source #

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.

clarifyShapConfig_textConfig :: Lens' ClarifyShapConfig (Maybe ClarifyTextConfig) Source #

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.

clarifyShapConfig_useLogit :: Lens' ClarifyShapConfig (Maybe Bool) Source #

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.

clarifyShapConfig_shapBaselineConfig :: Lens' ClarifyShapConfig ClarifyShapBaselineConfig Source #

The configuration for the SHAP baseline of the Kernal SHAP algorithm.