You are viewing documentation for version 2 of the AWS SDK for Ruby. Version 3 documentation can be found here.

Class: Aws::Personalize::Types::CreateSolutionRequest

Inherits:
Struct
  • Object
show all
Defined in:
(unknown)

Overview

Note:

When passing CreateSolutionRequest as input to an Aws::Client method, you can use a vanilla Hash:

{
  name: "Name", # required
  perform_hpo: false,
  perform_auto_ml: false,
  recipe_arn: "Arn",
  dataset_group_arn: "Arn", # required
  event_type: "EventType",
  solution_config: {
    event_value_threshold: "EventValueThreshold",
    hpo_config: {
      hpo_objective: {
        type: "HPOObjectiveType",
        metric_name: "MetricName",
        metric_regex: "MetricRegex",
      },
      hpo_resource_config: {
        max_number_of_training_jobs: "HPOResource",
        max_parallel_training_jobs: "HPOResource",
      },
      algorithm_hyper_parameter_ranges: {
        integer_hyper_parameter_ranges: [
          {
            name: "ParameterName",
            min_value: 1,
            max_value: 1,
          },
        ],
        continuous_hyper_parameter_ranges: [
          {
            name: "ParameterName",
            min_value: 1.0,
            max_value: 1.0,
          },
        ],
        categorical_hyper_parameter_ranges: [
          {
            name: "ParameterName",
            values: ["CategoricalValue"],
          },
        ],
      },
    },
    algorithm_hyper_parameters: {
      "ParameterName" => "ParameterValue",
    },
    feature_transformation_parameters: {
      "ParameterName" => "ParameterValue",
    },
    auto_ml_config: {
      metric_name: "MetricName",
      recipe_list: ["Arn"],
    },
  },
}

See Also:

Instance Attribute Summary collapse

Instance Attribute Details

#dataset_group_arn ⇒ String

The Amazon Resource Name (ARN) of the dataset group that provides the training data.

Returns:

  • (String) —

    The Amazon Resource Name (ARN) of the dataset group that provides the training data.

#event_type ⇒ String

When your have multiple event types (using an EVENT_TYPE schema field), this parameter specifies which event type (for example, \'click\' or \'like\') is used for training the model.

Returns:

  • (String) —

    When your have multiple event types (using an EVENT_TYPE schema field), this parameter specifies which event type (for example, \'click\' or \'like\') is used for training the model.

#name ⇒ String

The name for the solution.

Returns:

  • (String) —

    The name for the solution.

#perform_auto_ml ⇒ Boolean

Whether to perform automated machine learning (AutoML). The default is false. For this case, you must specify recipeArn.

When set to true, Amazon Personalize analyzes your training data and selects the optimal USER_PERSONALIZATION recipe and hyperparameters. In this case, you must omit recipeArn. Amazon Personalize determines the optimal recipe by running tests with different values for the hyperparameters. AutoML lengthens the training process as compared to selecting a specific recipe.

Returns:

  • (Boolean) —

    Whether to perform automated machine learning (AutoML).

#perform_hpo ⇒ Boolean

Whether to perform hyperparameter optimization (HPO) on the specified or selected recipe. The default is false.

When performing AutoML, this parameter is always true and you should not set it to false.

Returns:

  • (Boolean) —

    Whether to perform hyperparameter optimization (HPO) on the specified or selected recipe.

#recipe_arn ⇒ String

The ARN of the recipe to use for model training. Only specified when performAutoML is false.

Returns:

  • (String) —

    The ARN of the recipe to use for model training.

#solution_config ⇒ Types::SolutionConfig

The configuration to use with the solution. When performAutoML is set to true, Amazon Personalize only evaluates the autoMLConfig section of the solution configuration.

Returns: