RiskTableMapping

Risk table mapping step for categorical features

SageMaker step type	Processing
Node type	internal (consumes upstream, produces downstream)
Container entry point	risk_table_mapping.py
Interface file	steps/interfaces/risk_table_mapping.step.yaml

Compute

Compute kind	framework
SDK class	SKLearn (SageMaker DLC via image_uris.retrieve)

Functionality

Risk table mapping script. Creates risk tables for categorical features and handles missing value imputation for numeric features. Training mode creates tables; inference applies.

Inputs (dependencies)

Input	Type	Required	Compatible producers
input_data	processing_output	yes	TabularPreprocessing, MissingValueImputation, ProcessingStep
hyperparameters_s3_uri	hyperparameters	no	HyperparameterPrep, ProcessingStep, ConfigurationStep
model_artifacts_input	processing_output	no	RiskTableMapping_Training, ProcessingStep

Outputs

Output	Type
processed_data	processing_output
model_artifacts_output	processing_output

Consumers (downstream steps)

Steps that declare this step as a compatible input source:

• CurrencyConversion

• FeatureSelection

• LabelRulesetExecution

• LightGBMMTModelEval

• LightGBMMTModelInference

• LightGBMMTTraining

• LightGBMModelEval

• LightGBMModelInference

• LightGBMTraining

• MissingValueImputation

• ModelMetricsComputation

• PiperMetricGeneration

• PseudoLabelMerge

• PyTorchModelEval

• PyTorchModelInference

• PyTorchTraining

• XGBoostModelEval

• XGBoostModelInference

• XGBoostTraining

• XgboostMtModelEval

• XgboostMtTraining

Framework requirements

Package	Version
pandas	>=1.3.0
numpy	>=1.21.0
scikit-learn	>=1.0.0

---

← Back to the Step Catalog