Class: AWSCDK::Sagemaker::CfnEndpointConfig::ClarifyShapConfigProperty

Inherits:

Jsii::Struct

• Object
• Jsii::Struct
• AWSCDK::Sagemaker::CfnEndpointConfig::ClarifyShapConfigProperty

Defined in:

sagemaker/cfn_endpoint_config.rb

Overview

The configuration for SHAP analysis using SageMaker Clarify Explainer.

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-sagemaker-endpointconfig-clarifyshapconfig.html

Instance Attribute Summary

• #number_of_samples ⇒ Numeric^? readonly

  The number of samples to be used for analysis by the Kernal SHAP algorithm.

• #seed ⇒ Numeric^? readonly

  The starting value used to initialize the random number generator in the explainer.

• #shap_baseline_config ⇒ AWSCDK::IResolvable, AWSCDK::Sagemaker::CfnEndpointConfig::ClarifyShapBaselineConfigProperty readonly

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

• #text_config ⇒ AWSCDK::IResolvable, ... readonly

  A parameter that indicates if text features are treated as text and explanations are provided for individual units of text.

• #use_logit ⇒ Boolean, ... readonly

  A Boolean toggle to indicate if you want to use the logit function (true) or log-odds units (false) for model predictions.

Class Method Summary

• .jsii_properties ⇒ Object

Instance Method Summary

• #initialize(shap_baseline_config:, number_of_samples: nil, seed: nil, text_config: nil, use_logit: nil) ⇒ ClarifyShapConfigProperty constructor

  A new instance of ClarifyShapConfigProperty.

• #to_jsii ⇒ Object

Constructor Details

#initialize(shap_baseline_config:, number_of_samples: nil, seed: nil, text_config: nil, use_logit: nil) ⇒ ClarifyShapConfigProperty

Returns a new instance of ClarifyShapConfigProperty.

Parameters:

• shap_baseline_config (AWSCDK::IResolvable, AWSCDK::Sagemaker::CfnEndpointConfig::ClarifyShapBaselineConfigProperty) —

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

• number_of_samples (Numeric, nil) (defaults to: nil) —

  The number of samples to be used for analysis by the Kernal SHAP algorithm.

• seed (Numeric, nil) (defaults to: nil) —

  The starting value used to initialize the random number generator in the explainer.

• text_config (AWSCDK::IResolvable, AWSCDK::Sagemaker::CfnEndpointConfig::ClarifyTextConfigProperty, nil) (defaults to: nil) —

  A parameter that indicates if text features are treated as text and explanations are provided for individual units of text.

• use_logit (Boolean, AWSCDK::IResolvable, nil) (defaults to: nil) —

  A Boolean toggle to indicate if you want to use the logit function (true) or log-odds units (false) for model predictions.

# File 'sagemaker/cfn_endpoint_config.rb', line 1248

def initialize(shap_baseline_config:, number_of_samples: nil, seed: nil, text_config: nil, use_logit: nil)
  @shap_baseline_config = shap_baseline_config.is_a?(Hash) ? ::AWSCDK::Sagemaker::CfnEndpointConfig::ClarifyShapBaselineConfigProperty.new(**shap_baseline_config.transform_keys(&:to_sym)) : shap_baseline_config
  Jsii::Type.check_type(@shap_baseline_config, JSON.parse(Base64.strict_decode64("eyJ1bmlvbiI6eyJ0eXBlcyI6W3siZnFuIjoiYXdzLWNkay1saWIuSVJlc29sdmFibGUifSx7ImZxbiI6ImF3cy1jZGstbGliLmF3c19zYWdlbWFrZXIuQ2ZuRW5kcG9pbnRDb25maWcuQ2xhcmlmeVNoYXBCYXNlbGluZUNvbmZpZ1Byb3BlcnR5In1dfX0=")), "shapBaselineConfig")
  @number_of_samples = number_of_samples
  Jsii::Type.check_type(@number_of_samples, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJudW1iZXIifQ==")), "numberOfSamples") unless @number_of_samples.nil?
  @seed = seed
  Jsii::Type.check_type(@seed, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJudW1iZXIifQ==")), "seed") unless @seed.nil?
  @text_config = text_config.is_a?(Hash) ? ::AWSCDK::Sagemaker::CfnEndpointConfig::ClarifyTextConfigProperty.new(**text_config.transform_keys(&:to_sym)) : text_config
  Jsii::Type.check_type(@text_config, JSON.parse(Base64.strict_decode64("eyJ1bmlvbiI6eyJ0eXBlcyI6W3siZnFuIjoiYXdzLWNkay1saWIuSVJlc29sdmFibGUifSx7ImZxbiI6ImF3cy1jZGstbGliLmF3c19zYWdlbWFrZXIuQ2ZuRW5kcG9pbnRDb25maWcuQ2xhcmlmeVRleHRDb25maWdQcm9wZXJ0eSJ9XX19")), "textConfig") unless @text_config.nil?
  @use_logit = use_logit
  Jsii::Type.check_type(@use_logit, JSON.parse(Base64.strict_decode64("eyJ1bmlvbiI6eyJ0eXBlcyI6W3sicHJpbWl0aXZlIjoiYm9vbGVhbiJ9LHsiZnFuIjoiYXdzLWNkay1saWIuSVJlc29sdmFibGUifV19fQ==")), "useLogit") unless @use_logit.nil?
end

Instance Attribute Details

#number_of_samples ⇒ Numeric^? (readonly)

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 .

Returns:

• (Numeric, nil)

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-sagemaker-endpointconfig-clarifyshapconfig.html#cfn-sagemaker-endpointconfig-clarifyshapconfig-numberofsamples

# File 'sagemaker/cfn_endpoint_config.rb', line 1272

def number_of_samples
  @number_of_samples
end

#seed ⇒ Numeric^? (readonly)

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.

Returns:

• (Numeric, nil)

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-sagemaker-endpointconfig-clarifyshapconfig.html#cfn-sagemaker-endpointconfig-clarifyshapconfig-seed

# File 'sagemaker/cfn_endpoint_config.rb', line 1279

def seed
  @seed
end

#shap_baseline_config ⇒ AWSCDK::IResolvable, AWSCDK::Sagemaker::CfnEndpointConfig::ClarifyShapBaselineConfigProperty (readonly)

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

Returns:

• (AWSCDK::IResolvable, AWSCDK::Sagemaker::CfnEndpointConfig::ClarifyShapBaselineConfigProperty)

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-sagemaker-endpointconfig-clarifyshapconfig.html#cfn-sagemaker-endpointconfig-clarifyshapconfig-shapbaselineconfig

# File 'sagemaker/cfn_endpoint_config.rb', line 1265

def shap_baseline_config
  @shap_baseline_config
end

#text_config ⇒ AWSCDK::IResolvable, ... (readonly)

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.

Returns:

• (AWSCDK::IResolvable, AWSCDK::Sagemaker::CfnEndpointConfig::ClarifyTextConfigProperty, nil)

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-sagemaker-endpointconfig-clarifyshapconfig.html#cfn-sagemaker-endpointconfig-clarifyshapconfig-textconfig

# File 'sagemaker/cfn_endpoint_config.rb', line 1286

def text_config
  @text_config
end

#use_logit ⇒ Boolean, ... (readonly)

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.

Returns:

• (Boolean, AWSCDK::IResolvable, nil)

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-sagemaker-endpointconfig-clarifyshapconfig.html#cfn-sagemaker-endpointconfig-clarifyshapconfig-uselogit

# File 'sagemaker/cfn_endpoint_config.rb', line 1293

def use_logit
  @use_logit
end

Class Method Details

.jsii_properties ⇒ Object

# File 'sagemaker/cfn_endpoint_config.rb', line 1295

def self.jsii_properties
  {
    :shap_baseline_config => "shapBaselineConfig",
    :number_of_samples => "numberOfSamples",
    :seed => "seed",
    :text_config => "textConfig",
    :use_logit => "useLogit",
  }
end

Instance Method Details

#to_jsii ⇒ Object

# File 'sagemaker/cfn_endpoint_config.rb', line 1305

def to_jsii
  result = {}
  result.merge!({
    "shapBaselineConfig" => @shap_baseline_config,
    "numberOfSamples" => @number_of_samples,
    "seed" => @seed,
    "textConfig" => @text_config,
    "useLogit" => @use_logit,
  })
  result.compact
end