Class: Aws::SageMaker::Types::AutoMLAlgorithmConfig

Inherits:

Struct

• Object
• Struct
• Aws::SageMaker::Types::AutoMLAlgorithmConfig

Includes:

Aws::Structure

Defined in:

lib/aws-sdk-sagemaker/types.rb

Overview

The selection of algorithms trained on your dataset to generate the model candidates for an Autopilot job.

See Also:

• AWS API Documentation

Constant Summary

SENSITIVE =

[]

Instance Attribute Summary

• #auto_ml_algorithms ⇒ Array<String>

  The selection of algorithms trained on your dataset to generate the model candidates for an Autopilot job.

Instance Attribute Details

#auto_ml_algorithms ⇒ Array<String>

The selection of algorithms trained on your dataset to generate the model candidates for an Autopilot job.

• **For the tabular problem type ‘TabularJobConfig`:**

  <note markdown=“1”> Selected algorithms must belong to the list corresponding to the training mode set in [AutoMLJobConfig.Mode] (‘ENSEMBLING` or `HYPERPARAMETER_TUNING`). Choose a minimum of 1 algorithm.

  </note>
  

  • In ‘ENSEMBLING` mode:

    • “catboost”

    • “extra-trees”

    • “fastai”

    • “lightgbm”

    • “linear-learner”

    • “nn-torch”

    • “randomforest”

    • “xgboost”

  • In ‘HYPERPARAMETER_TUNING` mode:

    • “linear-learner”

    • “mlp”

    • “xgboost”

• **For the time-series forecasting problem type ‘TimeSeriesForecastingJobConfig`:**

  • Choose your algorithms from this list.

    • “cnn-qr”

    • “deepar”

    • “prophet”

    • “arima”

    • “npts”

    • “ets”

[1]: docs.aws.amazon.com/sagemaker/latest/APIReference/API_AutoMLJobConfig.html#sagemaker-Type-AutoMLJobConfig-Mode

Returns:

• (Array<String>)

# File 'lib/aws-sdk-sagemaker/types.rb', line 1850

class AutoMLAlgorithmConfig < Struct.new(
  :auto_ml_algorithms)
  SENSITIVE = []
  include Aws::Structure
end