Package software.amazon.awssdk.services.sagemaker.model

Interface AutoMLJobConfig.Builder

All Superinterfaces:
Buildable, CopyableBuilder<AutoMLJobConfig.Builder,AutoMLJobConfig>, SdkBuilder<AutoMLJobConfig.Builder,AutoMLJobConfig>, SdkPojo
Enclosing class:
AutoMLJobConfig
public static interface AutoMLJobConfig.Builder extends SdkPojo, CopyableBuilder<AutoMLJobConfig.Builder,AutoMLJobConfig>

  • Method Details

    • completionCriteria

      AutoMLJobConfig.Builder completionCriteria(AutoMLJobCompletionCriteria completionCriteria)

      How long an AutoML job is allowed to run, or how many candidates a job is allowed to generate.

      Parameters:
      completionCriteria - How long an AutoML job is allowed to run, or how many candidates a job is allowed to generate.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • completionCriteria

      default AutoMLJobConfig.Builder completionCriteria(Consumer<AutoMLJobCompletionCriteria.Builder> completionCriteria)

      How long an AutoML job is allowed to run, or how many candidates a job is allowed to generate.

      This is a convenience method that creates an instance of the AutoMLJobCompletionCriteria.Builder avoiding the need to create one manually via AutoMLJobCompletionCriteria.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to completionCriteria(AutoMLJobCompletionCriteria).

      Parameters:
      completionCriteria - a consumer that will call methods on AutoMLJobCompletionCriteria.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • securityConfig

      AutoMLJobConfig.Builder securityConfig(AutoMLSecurityConfig securityConfig)

      The security configuration for traffic encryption or Amazon VPC settings.

      Parameters:
      securityConfig - The security configuration for traffic encryption or Amazon VPC settings.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • securityConfig

      default AutoMLJobConfig.Builder securityConfig(Consumer<AutoMLSecurityConfig.Builder> securityConfig)

      The security configuration for traffic encryption or Amazon VPC settings.

      This is a convenience method that creates an instance of the AutoMLSecurityConfig.Builder avoiding the need to create one manually via AutoMLSecurityConfig.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to securityConfig(AutoMLSecurityConfig).

      Parameters:
      securityConfig - a consumer that will call methods on AutoMLSecurityConfig.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • dataSplitConfig

      AutoMLJobConfig.Builder dataSplitConfig(AutoMLDataSplitConfig dataSplitConfig)

      The configuration for splitting the input training dataset.

      Type: AutoMLDataSplitConfig

      Parameters:
      dataSplitConfig - The configuration for splitting the input training dataset.

      Type: AutoMLDataSplitConfig

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • dataSplitConfig

      default AutoMLJobConfig.Builder dataSplitConfig(Consumer<AutoMLDataSplitConfig.Builder> dataSplitConfig)

      The configuration for splitting the input training dataset.

      Type: AutoMLDataSplitConfig

      This is a convenience method that creates an instance of the AutoMLDataSplitConfig.Builder avoiding the need to create one manually via AutoMLDataSplitConfig.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to dataSplitConfig(AutoMLDataSplitConfig).

      Parameters:
      dataSplitConfig - a consumer that will call methods on AutoMLDataSplitConfig.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • candidateGenerationConfig

      AutoMLJobConfig.Builder candidateGenerationConfig(AutoMLCandidateGenerationConfig candidateGenerationConfig)

      The configuration for generating a candidate for an AutoML job (optional).

      Parameters:
      candidateGenerationConfig - The configuration for generating a candidate for an AutoML job (optional).
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • candidateGenerationConfig

      default AutoMLJobConfig.Builder candidateGenerationConfig(Consumer<AutoMLCandidateGenerationConfig.Builder> candidateGenerationConfig)

      The configuration for generating a candidate for an AutoML job (optional).

      This is a convenience method that creates an instance of the AutoMLCandidateGenerationConfig.Builder avoiding the need to create one manually via AutoMLCandidateGenerationConfig.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to candidateGenerationConfig(AutoMLCandidateGenerationConfig).

      Parameters:
      candidateGenerationConfig - a consumer that will call methods on AutoMLCandidateGenerationConfig.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • mode

      AutoMLJobConfig.Builder mode(String mode)

      The method that Autopilot uses to train the data. You can either specify the mode manually or let Autopilot choose for you based on the dataset size by selecting AUTO. In AUTO mode, Autopilot chooses ENSEMBLING for datasets smaller than 100 MB, and HYPERPARAMETER_TUNING for larger ones.

      The ENSEMBLING mode uses a multi-stack ensemble model to predict classification and regression tasks directly from your dataset. This machine learning mode combines several base models to produce an optimal predictive model. It then uses a stacking ensemble method to combine predictions from contributing members. A multi-stack ensemble model can provide better performance over a single model by combining the predictive capabilities of multiple models. See Autopilot algorithm support for a list of algorithms supported by ENSEMBLING mode.

      The HYPERPARAMETER_TUNING (HPO) mode uses the best hyperparameters to train the best version of a model. HPO automatically selects an algorithm for the type of problem you want to solve. Then HPO finds the best hyperparameters according to your objective metric. See Autopilot algorithm support for a list of algorithms supported by HYPERPARAMETER_TUNING mode.

      Parameters:
      mode - The method that Autopilot uses to train the data. You can either specify the mode manually or let Autopilot choose for you based on the dataset size by selecting AUTO. In AUTO mode, Autopilot chooses ENSEMBLING for datasets smaller than 100 MB, and HYPERPARAMETER_TUNING for larger ones.

      The ENSEMBLING mode uses a multi-stack ensemble model to predict classification and regression tasks directly from your dataset. This machine learning mode combines several base models to produce an optimal predictive model. It then uses a stacking ensemble method to combine predictions from contributing members. A multi-stack ensemble model can provide better performance over a single model by combining the predictive capabilities of multiple models. See Autopilot algorithm support for a list of algorithms supported by ENSEMBLING mode.

      The HYPERPARAMETER_TUNING (HPO) mode uses the best hyperparameters to train the best version of a model. HPO automatically selects an algorithm for the type of problem you want to solve. Then HPO finds the best hyperparameters according to your objective metric. See Autopilot algorithm support for a list of algorithms supported by HYPERPARAMETER_TUNING mode.

      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • mode

      AutoMLJobConfig.Builder mode(AutoMLMode mode)

      The method that Autopilot uses to train the data. You can either specify the mode manually or let Autopilot choose for you based on the dataset size by selecting AUTO. In AUTO mode, Autopilot chooses ENSEMBLING for datasets smaller than 100 MB, and HYPERPARAMETER_TUNING for larger ones.

      The ENSEMBLING mode uses a multi-stack ensemble model to predict classification and regression tasks directly from your dataset. This machine learning mode combines several base models to produce an optimal predictive model. It then uses a stacking ensemble method to combine predictions from contributing members. A multi-stack ensemble model can provide better performance over a single model by combining the predictive capabilities of multiple models. See Autopilot algorithm support for a list of algorithms supported by ENSEMBLING mode.

      The HYPERPARAMETER_TUNING (HPO) mode uses the best hyperparameters to train the best version of a model. HPO automatically selects an algorithm for the type of problem you want to solve. Then HPO finds the best hyperparameters according to your objective metric. See Autopilot algorithm support for a list of algorithms supported by HYPERPARAMETER_TUNING mode.

      Parameters:
      mode - The method that Autopilot uses to train the data. You can either specify the mode manually or let Autopilot choose for you based on the dataset size by selecting AUTO. In AUTO mode, Autopilot chooses ENSEMBLING for datasets smaller than 100 MB, and HYPERPARAMETER_TUNING for larger ones.

      The ENSEMBLING mode uses a multi-stack ensemble model to predict classification and regression tasks directly from your dataset. This machine learning mode combines several base models to produce an optimal predictive model. It then uses a stacking ensemble method to combine predictions from contributing members. A multi-stack ensemble model can provide better performance over a single model by combining the predictive capabilities of multiple models. See Autopilot algorithm support for a list of algorithms supported by ENSEMBLING mode.

      The HYPERPARAMETER_TUNING (HPO) mode uses the best hyperparameters to train the best version of a model. HPO automatically selects an algorithm for the type of problem you want to solve. Then HPO finds the best hyperparameters according to your objective metric. See Autopilot algorithm support for a list of algorithms supported by HYPERPARAMETER_TUNING mode.

      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also: