NAME

Paws::Personalize::CreateSolution - Arguments for method CreateSolution on Paws::Personalize

DESCRIPTION

This class represents the parameters used for calling the method CreateSolution on the Amazon Personalize service. Use the attributes of this class as arguments to method CreateSolution.

You shouldn't make instances of this class. Each attribute should be used as a named argument in the call to CreateSolution.

SYNOPSIS

            

              
              
my $personalize = Paws->service('Personalize');
my $CreateSolutionResponse = $personalize->CreateSolution(
  DatasetGroupArn => 'MyArn',
  Name            => 'MyName',
  EventType       => 'MyEventType',    # OPTIONAL
  PerformAutoML   => 1,                # OPTIONAL
  PerformHPO      => 1,                # OPTIONAL
  RecipeArn       => 'MyArn',          # OPTIONAL
  SolutionConfig  => {
    AlgorithmHyperParameters => {
      'MyParameterName' =>
        'MyParameterValue',            # key: max: 256, value: max: 1000
    },    # max: 100; OPTIONAL
    AutoMLConfig => {
      MetricName => 'MyMetricName',    # max: 256; OPTIONAL
      RecipeList => [
        'MyArn', ...                   # max: 256
      ],    # max: 100; OPTIONAL
    },    # OPTIONAL
    EventValueThreshold => 'MyEventValueThreshold',    # max: 256; OPTIONAL
    FeatureTransformationParameters => {
      'MyParameterName' =>
        'MyParameterValue',    # key: max: 256, value: max: 1000
    },    # max: 100; OPTIONAL
    HpoConfig => {
      AlgorithmHyperParameterRanges => {
        CategoricalHyperParameterRanges => [
          {
            Name   => 'MyParameterName',    # max: 256
            Values => [
              'MyCategoricalValue', ...     # max: 1000
            ],    # max: 100; OPTIONAL
          },
          ...
        ],    # max: 100; OPTIONAL
        ContinuousHyperParameterRanges => [
          {
            MaxValue => 1,                    # min: -1000000; OPTIONAL
            MinValue => 1,                    # min: -1000000; OPTIONAL
            Name     => 'MyParameterName',    # max: 256
          },
          ...
        ],    # max: 100; OPTIONAL
        IntegerHyperParameterRanges => [
          {
            MaxValue => 1,                    # max: 1000000; OPTIONAL
            MinValue => 1,                    # min: -1000000; OPTIONAL
            Name     => 'MyParameterName',    # max: 256
          },
          ...
        ],    # max: 100; OPTIONAL
      },    # OPTIONAL
      HpoObjective => {
        MetricName  => 'MyMetricName',          # max: 256; OPTIONAL
        MetricRegex => 'MyMetricRegex',         # max: 256; OPTIONAL
        Type        => 'MyHPOObjectiveType',    # max: 256; OPTIONAL
      },    # OPTIONAL
      HpoResourceConfig => {
        MaxNumberOfTrainingJobs => 'MyHPOResource',    # max: 256; OPTIONAL
        MaxParallelTrainingJobs => 'MyHPOResource',    # max: 256; OPTIONAL
      },    # OPTIONAL
    },    # OPTIONAL
    OptimizationObjective => {
      ItemAttribute => 'MyItemAttribute',    # min: 1, max: 150; OPTIONAL
      ObjectiveSensitivity =>
        'LOW',    # values: LOW, MEDIUM, HIGH, OFF; OPTIONAL
    },    # OPTIONAL
  },    # OPTIONAL
);
# Results:
my $SolutionArn = $CreateSolutionResponse->SolutionArn;
# Returns a L<Paws::Personalize::CreateSolutionResponse> object.
            
          

Values for attributes that are native types (Int, String, Float, etc) can passed as-is (scalar values). Values for complex Types (objects) can be passed as a HashRef. The keys and values of the hashref will be used to instance the underlying object. For the AWS API documentation, see https://docs.aws.amazon.com/goto/WebAPI/personalize/CreateSolution

ATTRIBUTES

REQUIRED DatasetGroupArn => Str

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

EventType => Str

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.

If you do not provide an eventType, Amazon Personalize will use all interactions for training with equal weight regardless of type.

REQUIRED Name => Str

The name for the solution.

PerformAutoML => Bool

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.

PerformHPO => Bool

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.

RecipeArn => Str

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

SolutionConfig => Paws::Personalize::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.

Amazon Personalize doesn't support configuring the hpoObjective at this time.

SEE ALSO

This class forms part of Paws, documenting arguments for method CreateSolution in Paws::Personalize

BUGS and CONTRIBUTIONS

The source code is located here: https://github.com/pplu/aws-sdk-perl

Please report bugs to: https://github.com/pplu/aws-sdk-perl/issues

cpanm Paws

perl -MCPAN -e shell
install Paws