Class: Aws::ForecastService::Types::Featurization

Inherits:
Struct
  • Object
show all
Defined in:
gems/aws-sdk-forecastservice/lib/aws-sdk-forecastservice/types.rb

Overview

Note:

When making an API call, you may pass Featurization data as a hash:

{
  attribute_name: "Name", # required
  featurization_pipeline: [
    {
      featurization_method_name: "filling", # required, accepts filling
      featurization_method_parameters: {
        "ParameterKey" => "ParameterValue",
      },
    },
  ],
}

Provides featurization (transformation) information for a dataset field. This object is part of the FeaturizationConfig object.

For example:

\{

"AttributeName": "demand",

FeaturizationPipeline [ \{

"FeaturizationMethodName": "filling",

"FeaturizationMethodParameters": \{"aggregation": "avg", "backfill": "nan"\}

\} ]

\}

Instance Attribute Summary collapse

Instance Attribute Details

#attribute_nameString

The name of the schema attribute that specifies the data field to be featurized. Only the target field of the TARGET_TIME_SERIES dataset type is supported. For example, for the RETAIL domain, the target is demand, and for the CUSTOM domain, the target is target_value.

Returns:

  • (String)


1717
1718
1719
1720
1721
# File 'gems/aws-sdk-forecastservice/lib/aws-sdk-forecastservice/types.rb', line 1717

class Featurization < Struct.new(
  :attribute_name,
  :featurization_pipeline)
  include Aws::Structure
end

#featurization_pipelineArray<Types::FeaturizationMethod>

An array of one FeaturizationMethod object that specifies the feature transformation method.

Returns:



1717
1718
1719
1720
1721
# File 'gems/aws-sdk-forecastservice/lib/aws-sdk-forecastservice/types.rb', line 1717

class Featurization < Struct.new(
  :attribute_name,
  :featurization_pipeline)
  include Aws::Structure
end