Amazonka.Forecast.CreateAutoPredictor

Creates an Amazon Forecast predictor.

Amazon Forecast creates predictors with AutoPredictor, which involves applying the optimal combination of algorithms to each time series in your datasets. You can use CreateAutoPredictor to create new predictors or upgrade/retrain existing predictors.

Creating new predictors

The following parameters are required when creating a new predictor:

• PredictorName - A unique name for the predictor.
• DatasetGroupArn - The ARN of the dataset group used to train the predictor.
• ForecastFrequency - The granularity of your forecasts (hourly, daily, weekly, etc).
• ForecastHorizon - The number of time-steps that the model predicts. The forecast horizon is also called the prediction length.

When creating a new predictor, do not specify a value for ReferencePredictorArn.

Upgrading and retraining predictors

The following parameters are required when retraining or upgrading a predictor:

• PredictorName - A unique name for the predictor.
• ReferencePredictorArn - The ARN of the predictor to retrain or upgrade.

When upgrading or retraining a predictor, only specify values for the ReferencePredictorArn and PredictorName.

Creating a Request

data CreateAutoPredictor

See: newCreateAutoPredictor smart constructor.

Constructors

CreateAutoPredictor'

Fields

• dataConfig :: Maybe DataConfig

  The data configuration for your dataset group and any additional datasets.

• encryptionConfig :: Maybe EncryptionConfig
• explainPredictor :: Maybe Bool

  Create an Explainability resource for the predictor.

• forecastDimensions :: Maybe (NonEmpty Text)

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

  For example, if you are generating forecasts for item sales across all your stores, and your dataset contains a store_id field, you would specify store_id as a dimension to group sales forecasts for each store.

• forecastFrequency :: Maybe 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.

• forecastHorizon :: Maybe Int

  The number of time-steps that the model predicts. The forecast horizon is also called the prediction length.

  The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the TARGET_TIME_SERIES dataset length. If you are retraining an existing AutoPredictor, then the maximum forecast horizon is the lesser of 500 time-steps or 1/3 of the TARGET_TIME_SERIES dataset length.

  If you are upgrading to an AutoPredictor or retraining an existing AutoPredictor, you cannot update the forecast horizon parameter. You can meet this requirement by providing longer time-series in the dataset.

• forecastTypes :: Maybe (NonEmpty Text)

  The forecast types used to train a predictor. You can specify up to five forecast types. Forecast types can be quantiles from 0.01 to 0.99, by increments of 0.01 or higher. You can also specify the mean forecast with mean.

• monitorConfig :: Maybe MonitorConfig

  The configuration details for predictor monitoring. Provide a name for the monitor resource to enable predictor monitoring.

  Predictor monitoring allows you to see how your predictor's performance changes over time. For more information, see Predictor Monitoring.

• optimizationMetric :: Maybe OptimizationMetric

  The accuracy metric used to optimize the predictor.

• referencePredictorArn :: Maybe Text

  The ARN of the predictor to retrain or upgrade. This parameter is only used when retraining or upgrading a predictor. When creating a new predictor, do not specify a value for this parameter.

  When upgrading or retraining a predictor, only specify values for the ReferencePredictorArn and PredictorName. The value for PredictorName must be a unique predictor name.

• tags :: Maybe [Tag]

  Optional metadata to help you categorize and organize your predictors. Each tag consists of a key and an optional value, both of which you define. Tag keys and values are case sensitive.

  The following restrictions apply to tags:

  • For each resource, each tag key must be unique and each tag key must have one value.
  • Maximum number of tags per resource: 50.
  • Maximum key length: 128 Unicode characters in UTF-8.
  • Maximum value length: 256 Unicode characters in UTF-8.
  • Accepted characters: all letters and numbers, spaces representable in UTF-8, and + - = . _ : / @. If your tagging schema is used across other services and resources, the character restrictions of those services also apply.
  • Key prefixes cannot include any upper or lowercase combination of aws: or AWS:. Values can have this prefix. If a tag value has aws as its prefix but the key does not, Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit. You cannot edit or delete tag keys with this prefix.
• timeAlignmentBoundary :: Maybe TimeAlignmentBoundary

  The time boundary Forecast uses to align and aggregate any data that doesn't align with your forecast frequency. Provide the unit of time and the time boundary as a key value pair. For more information on specifying a time boundary, see Specifying a Time Boundary. If you don't provide a time boundary, Forecast uses a set of Default Time Boundaries.

• predictorName :: Text

  A unique name for the predictor

Instances

ToJSON CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

toJSON :: CreateAutoPredictor -> Value

toEncoding :: CreateAutoPredictor -> Encoding

toJSONList :: [CreateAutoPredictor] -> Value

toEncodingList :: [CreateAutoPredictor] -> Encoding

ToHeaders CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

toHeaders :: CreateAutoPredictor -> [Header]

ToPath CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

toPath :: CreateAutoPredictor -> ByteString

ToQuery CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

toQuery :: CreateAutoPredictor -> QueryString

AWSRequest CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

Associated Types

type AWSResponse CreateAutoPredictor

Methods

request :: (Service -> Service) -> CreateAutoPredictor -> Request CreateAutoPredictor

response :: MonadResource m => (ByteStringLazy -> IO ByteStringLazy) -> Service -> Proxy CreateAutoPredictor -> ClientResponse ClientBody -> m (Either Error (ClientResponse (AWSResponse CreateAutoPredictor)))

Generic CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

Associated Types

type Rep CreateAutoPredictor :: Type -> Type

Methods

from :: CreateAutoPredictor -> Rep CreateAutoPredictor x

to :: Rep CreateAutoPredictor x -> CreateAutoPredictor

Show CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

showsPrec :: Int -> CreateAutoPredictor -> ShowS

show :: CreateAutoPredictor -> String

showList :: [CreateAutoPredictor] -> ShowS

NFData CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

rnf :: CreateAutoPredictor -> ()

Eq CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

(==) :: CreateAutoPredictor -> CreateAutoPredictor -> Bool

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

Hashable CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

hashWithSalt :: Int -> CreateAutoPredictor -> Int

hash :: CreateAutoPredictor -> Int

type AWSResponse CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

type AWSResponse CreateAutoPredictor = CreateAutoPredictorResponse

type Rep CreateAutoPredictor

Defined in Amazonka.Forecast.CreateAutoPredictor

type Rep CreateAutoPredictor = D1 ('MetaData "CreateAutoPredictor" "Amazonka.Forecast.CreateAutoPredictor" "amazonka-forecast-2.0-HHvJwvxGrDPBJtUcnmLBqf" 'False) (C1 ('MetaCons "CreateAutoPredictor'" 'PrefixI 'True) (((S1 ('MetaSel ('Just "dataConfig") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe DataConfig)) :*: (S1 ('MetaSel ('Just "encryptionConfig") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe EncryptionConfig)) :*: S1 ('MetaSel ('Just "explainPredictor") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Bool)))) :*: (S1 ('MetaSel ('Just "forecastDimensions") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe (NonEmpty Text))) :*: (S1 ('MetaSel ('Just "forecastFrequency") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "forecastHorizon") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Int))))) :*: ((S1 ('MetaSel ('Just "forecastTypes") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe (NonEmpty Text))) :*: (S1 ('MetaSel ('Just "monitorConfig") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe MonitorConfig)) :*: S1 ('MetaSel ('Just "optimizationMetric") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe OptimizationMetric)))) :*: ((S1 ('MetaSel ('Just "referencePredictorArn") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "tags") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe [Tag]))) :*: (S1 ('MetaSel ('Just "timeAlignmentBoundary") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe TimeAlignmentBoundary)) :*: S1 ('MetaSel ('Just "predictorName") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Text))))))

newCreateAutoPredictor

Arguments

:: Text

CreateAutoPredictor

-> CreateAutoPredictor

Create a value of CreateAutoPredictor 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:dataConfig:CreateAutoPredictor', createAutoPredictor_dataConfig - The data configuration for your dataset group and any additional datasets.

$sel:encryptionConfig:CreateAutoPredictor', createAutoPredictor_encryptionConfig - Undocumented member.

$sel:explainPredictor:CreateAutoPredictor', createAutoPredictor_explainPredictor - Create an Explainability resource for the predictor.

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

For example, if you are generating forecasts for item sales across all your stores, and your dataset contains a store_id field, you would specify store_id as a dimension to group sales forecasts for each store.

CreateAutoPredictor, createAutoPredictor_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.

$sel:forecastHorizon:CreateAutoPredictor', createAutoPredictor_forecastHorizon - The number of time-steps that the model predicts. The forecast horizon is also called the prediction length.

The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the TARGET_TIME_SERIES dataset length. If you are retraining an existing AutoPredictor, then the maximum forecast horizon is the lesser of 500 time-steps or 1/3 of the TARGET_TIME_SERIES dataset length.

If you are upgrading to an AutoPredictor or retraining an existing AutoPredictor, you cannot update the forecast horizon parameter. You can meet this requirement by providing longer time-series in the dataset.

$sel:forecastTypes:CreateAutoPredictor', createAutoPredictor_forecastTypes - The forecast types used to train a predictor. You can specify up to five forecast types. Forecast types can be quantiles from 0.01 to 0.99, by increments of 0.01 or higher. You can also specify the mean forecast with mean.

$sel:monitorConfig:CreateAutoPredictor', createAutoPredictor_monitorConfig - The configuration details for predictor monitoring. Provide a name for the monitor resource to enable predictor monitoring.

Predictor monitoring allows you to see how your predictor's performance changes over time. For more information, see Predictor Monitoring.

$sel:optimizationMetric:CreateAutoPredictor', createAutoPredictor_optimizationMetric - The accuracy metric used to optimize the predictor.

$sel:referencePredictorArn:CreateAutoPredictor', createAutoPredictor_referencePredictorArn - The ARN of the predictor to retrain or upgrade. This parameter is only used when retraining or upgrading a predictor. When creating a new predictor, do not specify a value for this parameter.

When upgrading or retraining a predictor, only specify values for the ReferencePredictorArn and PredictorName. The value for PredictorName must be a unique predictor name.

$sel:tags:CreateAutoPredictor', createAutoPredictor_tags - Optional metadata to help you categorize and organize your predictors. Each tag consists of a key and an optional value, both of which you define. Tag keys and values are case sensitive.

The following restrictions apply to tags:

• For each resource, each tag key must be unique and each tag key must have one value.
• Maximum number of tags per resource: 50.
• Maximum key length: 128 Unicode characters in UTF-8.
• Maximum value length: 256 Unicode characters in UTF-8.
• Accepted characters: all letters and numbers, spaces representable in UTF-8, and + - = . _ : / @. If your tagging schema is used across other services and resources, the character restrictions of those services also apply.
• Key prefixes cannot include any upper or lowercase combination of aws: or AWS:. Values can have this prefix. If a tag value has aws as its prefix but the key does not, Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit. You cannot edit or delete tag keys with this prefix.

$sel:timeAlignmentBoundary:CreateAutoPredictor', createAutoPredictor_timeAlignmentBoundary - The time boundary Forecast uses to align and aggregate any data that doesn't align with your forecast frequency. Provide the unit of time and the time boundary as a key value pair. For more information on specifying a time boundary, see Specifying a Time Boundary. If you don't provide a time boundary, Forecast uses a set of Default Time Boundaries.

CreateAutoPredictor, createAutoPredictor_predictorName - A unique name for the predictor

Request Lenses

createAutoPredictor_dataConfig :: Lens' CreateAutoPredictor (Maybe DataConfig)

The data configuration for your dataset group and any additional datasets.

createAutoPredictor_encryptionConfig :: Lens' CreateAutoPredictor (Maybe EncryptionConfig)

Undocumented member.

createAutoPredictor_explainPredictor :: Lens' CreateAutoPredictor (Maybe Bool)

Create an Explainability resource for the predictor.

createAutoPredictor_forecastDimensions :: Lens' CreateAutoPredictor (Maybe (NonEmpty Text))

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

For example, if you are generating forecasts for item sales across all your stores, and your dataset contains a store_id field, you would specify store_id as a dimension to group sales forecasts for each store.

createAutoPredictor_forecastFrequency :: Lens' CreateAutoPredictor (Maybe 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.

createAutoPredictor_forecastHorizon :: Lens' CreateAutoPredictor (Maybe Int)

The number of time-steps that the model predicts. The forecast horizon is also called the prediction length.

The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the TARGET_TIME_SERIES dataset length. If you are retraining an existing AutoPredictor, then the maximum forecast horizon is the lesser of 500 time-steps or 1/3 of the TARGET_TIME_SERIES dataset length.

If you are upgrading to an AutoPredictor or retraining an existing AutoPredictor, you cannot update the forecast horizon parameter. You can meet this requirement by providing longer time-series in the dataset.

createAutoPredictor_forecastTypes :: Lens' CreateAutoPredictor (Maybe (NonEmpty Text))

The forecast types used to train a predictor. You can specify up to five forecast types. Forecast types can be quantiles from 0.01 to 0.99, by increments of 0.01 or higher. You can also specify the mean forecast with mean.

createAutoPredictor_monitorConfig :: Lens' CreateAutoPredictor (Maybe MonitorConfig)

The configuration details for predictor monitoring. Provide a name for the monitor resource to enable predictor monitoring.

Predictor monitoring allows you to see how your predictor's performance changes over time. For more information, see Predictor Monitoring.

createAutoPredictor_optimizationMetric :: Lens' CreateAutoPredictor (Maybe OptimizationMetric)

The accuracy metric used to optimize the predictor.

createAutoPredictor_referencePredictorArn :: Lens' CreateAutoPredictor (Maybe Text)

The ARN of the predictor to retrain or upgrade. This parameter is only used when retraining or upgrading a predictor. When creating a new predictor, do not specify a value for this parameter.

When upgrading or retraining a predictor, only specify values for the ReferencePredictorArn and PredictorName. The value for PredictorName must be a unique predictor name.

createAutoPredictor_tags :: Lens' CreateAutoPredictor (Maybe [Tag])

Optional metadata to help you categorize and organize your predictors. Each tag consists of a key and an optional value, both of which you define. Tag keys and values are case sensitive.

The following restrictions apply to tags:

• For each resource, each tag key must be unique and each tag key must have one value.
• Maximum number of tags per resource: 50.
• Maximum key length: 128 Unicode characters in UTF-8.
• Maximum value length: 256 Unicode characters in UTF-8.
• Accepted characters: all letters and numbers, spaces representable in UTF-8, and + - = . _ : / @. If your tagging schema is used across other services and resources, the character restrictions of those services also apply.
• Key prefixes cannot include any upper or lowercase combination of aws: or AWS:. Values can have this prefix. If a tag value has aws as its prefix but the key does not, Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit. You cannot edit or delete tag keys with this prefix.

createAutoPredictor_timeAlignmentBoundary :: Lens' CreateAutoPredictor (Maybe TimeAlignmentBoundary)

The time boundary Forecast uses to align and aggregate any data that doesn't align with your forecast frequency. Provide the unit of time and the time boundary as a key value pair. For more information on specifying a time boundary, see Specifying a Time Boundary. If you don't provide a time boundary, Forecast uses a set of Default Time Boundaries.

createAutoPredictor_predictorName :: Lens' CreateAutoPredictor Text

A unique name for the predictor

Destructuring the Response

data CreateAutoPredictorResponse

See: newCreateAutoPredictorResponse smart constructor.

Constructors

CreateAutoPredictorResponse'

Fields

• predictorArn :: Maybe Text

  The Amazon Resource Name (ARN) of the predictor.

• httpStatus :: Int

  The response's http status code.

Instances

Generic CreateAutoPredictorResponse

Defined in Amazonka.Forecast.CreateAutoPredictor

Associated Types

type Rep CreateAutoPredictorResponse :: Type -> Type

Methods

from :: CreateAutoPredictorResponse -> Rep CreateAutoPredictorResponse x

to :: Rep CreateAutoPredictorResponse x -> CreateAutoPredictorResponse

Read CreateAutoPredictorResponse

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

readsPrec :: Int -> ReadS CreateAutoPredictorResponse

readList :: ReadS [CreateAutoPredictorResponse]

readPrec :: ReadPrec CreateAutoPredictorResponse

readListPrec :: ReadPrec [CreateAutoPredictorResponse]

Show CreateAutoPredictorResponse

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

showsPrec :: Int -> CreateAutoPredictorResponse -> ShowS

show :: CreateAutoPredictorResponse -> String

showList :: [CreateAutoPredictorResponse] -> ShowS

NFData CreateAutoPredictorResponse

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

rnf :: CreateAutoPredictorResponse -> ()

Eq CreateAutoPredictorResponse

Defined in Amazonka.Forecast.CreateAutoPredictor

Methods

(==) :: CreateAutoPredictorResponse -> CreateAutoPredictorResponse -> Bool

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

type Rep CreateAutoPredictorResponse

Defined in Amazonka.Forecast.CreateAutoPredictor

type Rep CreateAutoPredictorResponse = D1 ('MetaData "CreateAutoPredictorResponse" "Amazonka.Forecast.CreateAutoPredictor" "amazonka-forecast-2.0-HHvJwvxGrDPBJtUcnmLBqf" 'False) (C1 ('MetaCons "CreateAutoPredictorResponse'" 'PrefixI 'True) (S1 ('MetaSel ('Just "predictorArn") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "httpStatus") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Int)))

newCreateAutoPredictorResponse

Arguments

:: Int

$sel:httpStatus:CreateAutoPredictorResponse'

-> CreateAutoPredictorResponse

Create a value of CreateAutoPredictorResponse 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:

CreateAutoPredictorResponse, createAutoPredictorResponse_predictorArn - The Amazon Resource Name (ARN) of the predictor.

$sel:httpStatus:CreateAutoPredictorResponse', createAutoPredictorResponse_httpStatus - The response's http status code.

Response Lenses

createAutoPredictorResponse_predictorArn :: Lens' CreateAutoPredictorResponse (Maybe Text)

The Amazon Resource Name (ARN) of the predictor.

createAutoPredictorResponse_httpStatus :: Lens' CreateAutoPredictorResponse Int

The response's http status code.