Amazonka.Forecast.Types.Featurization

Documentation

data Featurization

This object belongs to the CreatePredictor operation. If you created your predictor with CreateAutoPredictor, see AttributeConfig.

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"}

} ]

}

See: newFeaturization smart constructor.

Constructors

Featurization'

Fields

• featurizationPipeline :: Maybe (NonEmpty FeaturizationMethod)

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

• attributeName :: Text

  The name of the schema attribute that specifies the data field to be featurized. Amazon Forecast supports the target field of the TARGET_TIME_SERIES and the RELATED_TIME_SERIES datasets. For example, for the RETAIL domain, the target is demand, and for the CUSTOM domain, the target is target_value. For more information, see howitworks-missing-values.

Instances

FromJSON Featurization

Defined in Amazonka.Forecast.Types.Featurization

Methods

parseJSON :: Value -> Parser Featurization

parseJSONList :: Value -> Parser [Featurization]

ToJSON Featurization

Defined in Amazonka.Forecast.Types.Featurization

Methods

toJSON :: Featurization -> Value

toEncoding :: Featurization -> Encoding

toJSONList :: [Featurization] -> Value

toEncodingList :: [Featurization] -> Encoding

Generic Featurization

Defined in Amazonka.Forecast.Types.Featurization

Associated Types

type Rep Featurization :: Type -> Type

Methods

from :: Featurization -> Rep Featurization x

to :: Rep Featurization x -> Featurization

Read Featurization

Defined in Amazonka.Forecast.Types.Featurization

Methods

readsPrec :: Int -> ReadS Featurization

readList :: ReadS [Featurization]

readPrec :: ReadPrec Featurization

readListPrec :: ReadPrec [Featurization]

Show Featurization

Defined in Amazonka.Forecast.Types.Featurization

Methods

showsPrec :: Int -> Featurization -> ShowS

show :: Featurization -> String

showList :: [Featurization] -> ShowS

NFData Featurization

Defined in Amazonka.Forecast.Types.Featurization

Methods

rnf :: Featurization -> ()

Eq Featurization

Defined in Amazonka.Forecast.Types.Featurization

Methods

(==) :: Featurization -> Featurization -> Bool

(/=) :: Featurization -> Featurization -> Bool

Hashable Featurization

Defined in Amazonka.Forecast.Types.Featurization

Methods

hashWithSalt :: Int -> Featurization -> Int

hash :: Featurization -> Int

type Rep Featurization

Defined in Amazonka.Forecast.Types.Featurization

type Rep Featurization = D1 ('MetaData "Featurization" "Amazonka.Forecast.Types.Featurization" "amazonka-forecast-2.0-HHvJwvxGrDPBJtUcnmLBqf" 'False) (C1 ('MetaCons "Featurization'" 'PrefixI 'True) (S1 ('MetaSel ('Just "featurizationPipeline") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe (NonEmpty FeaturizationMethod))) :*: S1 ('MetaSel ('Just "attributeName") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Text)))

newFeaturization

Arguments

:: Text

$sel:attributeName:Featurization'

-> Featurization

Create a value of Featurization with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

$sel:featurizationPipeline:Featurization', featurization_featurizationPipeline - An array of one FeaturizationMethod object that specifies the feature transformation method.

$sel:attributeName:Featurization', featurization_attributeName - The name of the schema attribute that specifies the data field to be featurized. Amazon Forecast supports the target field of the TARGET_TIME_SERIES and the RELATED_TIME_SERIES datasets. For example, for the RETAIL domain, the target is demand, and for the CUSTOM domain, the target is target_value. For more information, see howitworks-missing-values.

featurization_featurizationPipeline :: Lens' Featurization (Maybe (NonEmpty FeaturizationMethod))

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

featurization_attributeName :: Lens' Featurization Text

The name of the schema attribute that specifies the data field to be featurized. Amazon Forecast supports the target field of the TARGET_TIME_SERIES and the RELATED_TIME_SERIES datasets. For example, for the RETAIL domain, the target is demand, and for the CUSTOM domain, the target is target_value. For more information, see howitworks-missing-values.