AutoMLAlgorithmConfig — AWS SDK for Ruby V3 (original) (raw)

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

Inherits:

Struct

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

Defined in:

gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb

Overview

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

Constant Summarycollapse

SENSITIVE =

[]

Instance Attribute Summary collapse

• #auto_ml_algorithms ⇒ Array
  The selection of algorithms trained on your dataset to generate the model candidates for an Autopilot job.

Instance Attribute Details

#auto_ml_algorithms ⇒ Array

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

• For the tabular problem type TabularJobConfig:
  Selected algorithms must belong to the list corresponding to the training mode set in AutoMLJobConfig.Mode (ENSEMBLING orHYPERPARAMETER_TUNING). Choose a minimum of 1 algorithm.
  • 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 typeTimeSeriesForecastingJobConfig:
  • Choose your algorithms from this list.
    * "cnn-qr"
    * "deepar"
    * "prophet"
    * "arima"
    * "npts"
    * "ets"