Amazonka.Forecast.Types.FeaturizationConfig

Documentation

data FeaturizationConfig

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

In a CreatePredictor operation, the specified algorithm trains a model using the specified dataset group. You can optionally tell the operation to modify data fields prior to training a model. These modifications are referred to as featurization.

You define featurization using the FeaturizationConfig object. You specify an array of transformations, one for each field that you want to featurize. You then include the FeaturizationConfig object in your CreatePredictor request. Amazon Forecast applies the featurization to the TARGET_TIME_SERIES and RELATED_TIME_SERIES datasets before model training.

You can create multiple featurization configurations. For example, you might call the CreatePredictor operation twice by specifying different featurization configurations.

See: newFeaturizationConfig smart constructor.

Constructors

FeaturizationConfig'

Fields

• featurizations :: Maybe (NonEmpty Featurization)

  An array of featurization (transformation) information for the fields of a dataset.

• forecastDimensions :: Maybe (NonEmpty Text)

  An array of dimension (field) names that specify how to group the generated forecast.

  For example, suppose that you are generating a forecast for item sales across all of your stores, and your dataset contains a store_id field. If you want the sales forecast for each item by store, you would specify store_id as the dimension.

  All forecast dimensions specified in the TARGET_TIME_SERIES dataset don't need to be specified in the CreatePredictor request. All forecast dimensions specified in the RELATED_TIME_SERIES dataset must be specified in the CreatePredictor request.

• forecastFrequency :: Text

  The frequency of predictions in a forecast.

  Valid intervals are Y (Year), M (Month), W (Week), D (Day), H (Hour), 30min (30 minutes), 15min (15 minutes), 10min (10 minutes), 5min (5 minutes), and 1min (1 minute). For example, "Y" indicates every year and "5min" indicates every five minutes.

  The frequency must be greater than or equal to the TARGET_TIME_SERIES dataset frequency.

  When a RELATED_TIME_SERIES dataset is provided, the frequency must be equal to the RELATED_TIME_SERIES dataset frequency.

Instances

FromJSON FeaturizationConfig

Defined in Amazonka.Forecast.Types.FeaturizationConfig

Methods

parseJSON :: Value -> Parser FeaturizationConfig

parseJSONList :: Value -> Parser [FeaturizationConfig]

ToJSON FeaturizationConfig

Defined in Amazonka.Forecast.Types.FeaturizationConfig

Methods

toJSON :: FeaturizationConfig -> Value

toEncoding :: FeaturizationConfig -> Encoding

toJSONList :: [FeaturizationConfig] -> Value

toEncodingList :: [FeaturizationConfig] -> Encoding

Generic FeaturizationConfig

Defined in Amazonka.Forecast.Types.FeaturizationConfig

Associated Types

type Rep FeaturizationConfig :: Type -> Type

Methods

from :: FeaturizationConfig -> Rep FeaturizationConfig x

to :: Rep FeaturizationConfig x -> FeaturizationConfig

Read FeaturizationConfig

Defined in Amazonka.Forecast.Types.FeaturizationConfig

Methods

readsPrec :: Int -> ReadS FeaturizationConfig

readList :: ReadS [FeaturizationConfig]

readPrec :: ReadPrec FeaturizationConfig

readListPrec :: ReadPrec [FeaturizationConfig]

Show FeaturizationConfig

Defined in Amazonka.Forecast.Types.FeaturizationConfig

Methods

showsPrec :: Int -> FeaturizationConfig -> ShowS

show :: FeaturizationConfig -> String

showList :: [FeaturizationConfig] -> ShowS

NFData FeaturizationConfig

Defined in Amazonka.Forecast.Types.FeaturizationConfig

Methods

rnf :: FeaturizationConfig -> ()

Eq FeaturizationConfig

Defined in Amazonka.Forecast.Types.FeaturizationConfig

Methods

(==) :: FeaturizationConfig -> FeaturizationConfig -> Bool

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

Hashable FeaturizationConfig

Defined in Amazonka.Forecast.Types.FeaturizationConfig

Methods

hashWithSalt :: Int -> FeaturizationConfig -> Int

hash :: FeaturizationConfig -> Int

type Rep FeaturizationConfig

Defined in Amazonka.Forecast.Types.FeaturizationConfig

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

newFeaturizationConfig

Arguments

:: Text

$sel:forecastFrequency:FeaturizationConfig'

-> FeaturizationConfig

Create a value of FeaturizationConfig 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:featurizations:FeaturizationConfig', featurizationConfig_featurizations - An array of featurization (transformation) information for the fields of a dataset.

$sel:forecastDimensions:FeaturizationConfig', featurizationConfig_forecastDimensions - An array of dimension (field) names that specify how to group the generated forecast.

For example, suppose that you are generating a forecast for item sales across all of your stores, and your dataset contains a store_id field. If you want the sales forecast for each item by store, you would specify store_id as the dimension.

All forecast dimensions specified in the TARGET_TIME_SERIES dataset don't need to be specified in the CreatePredictor request. All forecast dimensions specified in the RELATED_TIME_SERIES dataset must be specified in the CreatePredictor request.

$sel:forecastFrequency:FeaturizationConfig', featurizationConfig_forecastFrequency - The frequency of predictions in a forecast.

Valid intervals are Y (Year), M (Month), W (Week), D (Day), H (Hour), 30min (30 minutes), 15min (15 minutes), 10min (10 minutes), 5min (5 minutes), and 1min (1 minute). For example, "Y" indicates every year and "5min" indicates every five minutes.

The frequency must be greater than or equal to the TARGET_TIME_SERIES dataset frequency.

When a RELATED_TIME_SERIES dataset is provided, the frequency must be equal to the RELATED_TIME_SERIES dataset frequency.

featurizationConfig_featurizations :: Lens' FeaturizationConfig (Maybe (NonEmpty Featurization))

An array of featurization (transformation) information for the fields of a dataset.

featurizationConfig_forecastDimensions :: Lens' FeaturizationConfig (Maybe (NonEmpty Text))

An array of dimension (field) names that specify how to group the generated forecast.

For example, suppose that you are generating a forecast for item sales across all of your stores, and your dataset contains a store_id field. If you want the sales forecast for each item by store, you would specify store_id as the dimension.

All forecast dimensions specified in the TARGET_TIME_SERIES dataset don't need to be specified in the CreatePredictor request. All forecast dimensions specified in the RELATED_TIME_SERIES dataset must be specified in the CreatePredictor request.

featurizationConfig_forecastFrequency :: Lens' FeaturizationConfig Text

The frequency of predictions in a forecast.

Valid intervals are Y (Year), M (Month), W (Week), D (Day), H (Hour), 30min (30 minutes), 15min (15 minutes), 10min (10 minutes), 5min (5 minutes), and 1min (1 minute). For example, "Y" indicates every year and "5min" indicates every five minutes.

The frequency must be greater than or equal to the TARGET_TIME_SERIES dataset frequency.

When a RELATED_TIME_SERIES dataset is provided, the frequency must be equal to the RELATED_TIME_SERIES dataset frequency.