Skip to content

/AWS1/CL_FCSDESCRPREDICTORRSP

DescribePredictorResponse

CONSTRUCTOR

IMPORTING

Optional arguments:

IV_PREDICTORARN TYPE /AWS1/FCSNAME /AWS1/FCSNAME

The ARN of the predictor.

IV_PREDICTORNAME TYPE /AWS1/FCSNAME /AWS1/FCSNAME

The name of the predictor.

IV_ALGORITHMARN TYPE /AWS1/FCSARN /AWS1/FCSARN

The Amazon Resource Name (ARN) of the algorithm used for model training.

IT_AUTOMLALGORITHMARNS TYPE /AWS1/CL_FCSARNLIST_W=>TT_ARNLIST TT_ARNLIST

When PerformAutoML is specified, the ARN of the chosen algorithm.

IV_FORECASTHORIZON TYPE /AWS1/FCSINTEGER /AWS1/FCSINTEGER

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

IT_FORECASTTYPES TYPE /AWS1/CL_FCSFORECASTTYPES_W=>TT_FORECASTTYPES TT_FORECASTTYPES

The forecast types used during predictor training. Default value is ["0.1","0.5","0.9"]

IV_PERFORMAUTOML TYPE /AWS1/FCSBOOLEAN /AWS1/FCSBOOLEAN

Whether the predictor is set to perform AutoML.

IV_AUTOMLOVERRIDESTRATEGY TYPE /AWS1/FCSAUTOMLOVERRIDESTRAG /AWS1/FCSAUTOMLOVERRIDESTRAG

The LatencyOptimized AutoML override strategy is only available in private beta. Contact Amazon Web Services Support or your account manager to learn more about access privileges.

The AutoML strategy used to train the predictor. Unless LatencyOptimized is specified, the AutoML strategy optimizes predictor accuracy.

This parameter is only valid for predictors trained using AutoML.

IV_PERFORMHPO TYPE /AWS1/FCSBOOLEAN /AWS1/FCSBOOLEAN

Whether the predictor is set to perform hyperparameter optimization (HPO).

IT_TRAININGPARAMETERS TYPE /AWS1/CL_FCSTRAININGPARAMS_W=>TT_TRAININGPARAMETERS TT_TRAININGPARAMETERS

The default training parameters or overrides selected during model training. When running AutoML or choosing HPO with CNN-QR or DeepAR+, the optimized values for the chosen hyperparameters are returned. For more information, see aws-forecast-choosing-recipes.

IO_EVALUATIONPARAMETERS TYPE REF TO /AWS1/CL_FCSEVALPARAMETERS /AWS1/CL_FCSEVALPARAMETERS

Used to override the default evaluation parameters of the specified algorithm. Amazon Forecast evaluates a predictor by splitting a dataset into training data and testing data. The evaluation parameters define how to perform the split and the number of iterations.

IO_HPOCONFIG TYPE REF TO /AWS1/CL_FCSHYPPARAMTUNJOBCFG /AWS1/CL_FCSHYPPARAMTUNJOBCFG

The hyperparameter override values for the algorithm.

IO_INPUTDATACONFIG TYPE REF TO /AWS1/CL_FCSINPUTDATACONFIG /AWS1/CL_FCSINPUTDATACONFIG

Describes the dataset group that contains the data to use to train the predictor.

IO_FEATURIZATIONCONFIG TYPE REF TO /AWS1/CL_FCSFEATCONFIG /AWS1/CL_FCSFEATCONFIG

The featurization configuration.

IO_ENCRYPTIONCONFIG TYPE REF TO /AWS1/CL_FCSENCRYPTIONCONFIG /AWS1/CL_FCSENCRYPTIONCONFIG

An Key Management Service (KMS) key and the Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.

IO_PREDICTOREXECUTIONDETAILS TYPE REF TO /AWS1/CL_FCSPREDICTOREXECDETS /AWS1/CL_FCSPREDICTOREXECDETS

Details on the the status and results of the backtests performed to evaluate the accuracy of the predictor. You specify the number of backtests to perform when you call the operation.

IV_ESTIMATEDTIMEREMAININGI00 TYPE /AWS1/FCSLONG /AWS1/FCSLONG

The estimated time remaining in minutes for the predictor training job to complete.

IV_ISAUTOPREDICTOR TYPE /AWS1/FCSBOOLEAN /AWS1/FCSBOOLEAN

Whether the predictor was created with CreateAutoPredictor.

IT_DATASETIMPORTJOBARNS TYPE /AWS1/CL_FCSARNLIST_W=>TT_ARNLIST TT_ARNLIST

An array of the ARNs of the dataset import jobs used to import training data for the predictor.

IV_STATUS TYPE /AWS1/FCSSTATUS /AWS1/FCSSTATUS

The status of the predictor. States include:

  • ACTIVE

  • CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED

  • DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED

  • CREATE_STOPPING, CREATE_STOPPED

The Status of the predictor must be ACTIVE before you can use the predictor to create a forecast.

IV_MESSAGE TYPE /AWS1/FCSMESSAGE /AWS1/FCSMESSAGE

If an error occurred, an informational message about the error.

IV_CREATIONTIME TYPE /AWS1/FCSTIMESTAMP /AWS1/FCSTIMESTAMP

When the model training task was created.

IV_LASTMODIFICATIONTIME TYPE /AWS1/FCSTIMESTAMP /AWS1/FCSTIMESTAMP

The last time the resource was modified. The timestamp depends on the status of the job:

  • CREATE_PENDING - The CreationTime.

  • CREATE_IN_PROGRESS - The current timestamp.

  • CREATE_STOPPING - The current timestamp.

  • CREATE_STOPPED - When the job stopped.

  • ACTIVE or CREATE_FAILED - When the job finished or failed.

IV_OPTIMIZATIONMETRIC TYPE /AWS1/FCSOPTIMIZATIONMETRIC /AWS1/FCSOPTIMIZATIONMETRIC

The accuracy metric used to optimize the predictor.

Queryable Attributes

PredictorArn

The ARN of the predictor.

Accessible with the following methods

Method Description
GET_PREDICTORARN() Getter for PREDICTORARN, with configurable default
ASK_PREDICTORARN() Getter for PREDICTORARN w/ exceptions if field has no value
HAS_PREDICTORARN() Determine if PREDICTORARN has a value

PredictorName

The name of the predictor.

Accessible with the following methods

Method Description
GET_PREDICTORNAME() Getter for PREDICTORNAME, with configurable default
ASK_PREDICTORNAME() Getter for PREDICTORNAME w/ exceptions if field has no value
HAS_PREDICTORNAME() Determine if PREDICTORNAME has a value

AlgorithmArn

The Amazon Resource Name (ARN) of the algorithm used for model training.

Accessible with the following methods

Method Description
GET_ALGORITHMARN() Getter for ALGORITHMARN, with configurable default
ASK_ALGORITHMARN() Getter for ALGORITHMARN w/ exceptions if field has no value
HAS_ALGORITHMARN() Determine if ALGORITHMARN has a value

AutoMLAlgorithmArns

When PerformAutoML is specified, the ARN of the chosen algorithm.

Accessible with the following methods

Method Description
GET_AUTOMLALGORITHMARNS() Getter for AUTOMLALGORITHMARNS, with configurable default
ASK_AUTOMLALGORITHMARNS() Getter for AUTOMLALGORITHMARNS w/ exceptions if field has no
HAS_AUTOMLALGORITHMARNS() Determine if AUTOMLALGORITHMARNS has a value

ForecastHorizon

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

Accessible with the following methods

Method Description
GET_FORECASTHORIZON() Getter for FORECASTHORIZON, with configurable default
ASK_FORECASTHORIZON() Getter for FORECASTHORIZON w/ exceptions if field has no val
HAS_FORECASTHORIZON() Determine if FORECASTHORIZON has a value

ForecastTypes

The forecast types used during predictor training. Default value is ["0.1","0.5","0.9"]

Accessible with the following methods

Method Description
GET_FORECASTTYPES() Getter for FORECASTTYPES, with configurable default
ASK_FORECASTTYPES() Getter for FORECASTTYPES w/ exceptions if field has no value
HAS_FORECASTTYPES() Determine if FORECASTTYPES has a value

PerformAutoML

Whether the predictor is set to perform AutoML.

Accessible with the following methods

Method Description
GET_PERFORMAUTOML() Getter for PERFORMAUTOML, with configurable default
ASK_PERFORMAUTOML() Getter for PERFORMAUTOML w/ exceptions if field has no value
HAS_PERFORMAUTOML() Determine if PERFORMAUTOML has a value

AutoMLOverrideStrategy

The LatencyOptimized AutoML override strategy is only available in private beta. Contact Amazon Web Services Support or your account manager to learn more about access privileges.

The AutoML strategy used to train the predictor. Unless LatencyOptimized is specified, the AutoML strategy optimizes predictor accuracy.

This parameter is only valid for predictors trained using AutoML.

Accessible with the following methods

Method Description
GET_AUTOMLOVERRIDESTRATEGY() Getter for AUTOMLOVERRIDESTRATEGY, with configurable default
ASK_AUTOMLOVERRIDESTRATEGY() Getter for AUTOMLOVERRIDESTRATEGY w/ exceptions if field has
HAS_AUTOMLOVERRIDESTRATEGY() Determine if AUTOMLOVERRIDESTRATEGY has a value

PerformHPO

Whether the predictor is set to perform hyperparameter optimization (HPO).

Accessible with the following methods

Method Description
GET_PERFORMHPO() Getter for PERFORMHPO, with configurable default
ASK_PERFORMHPO() Getter for PERFORMHPO w/ exceptions if field has no value
HAS_PERFORMHPO() Determine if PERFORMHPO has a value

TrainingParameters

The default training parameters or overrides selected during model training. When running AutoML or choosing HPO with CNN-QR or DeepAR+, the optimized values for the chosen hyperparameters are returned. For more information, see aws-forecast-choosing-recipes.

Accessible with the following methods

Method Description
GET_TRAININGPARAMETERS() Getter for TRAININGPARAMETERS, with configurable default
ASK_TRAININGPARAMETERS() Getter for TRAININGPARAMETERS w/ exceptions if field has no
HAS_TRAININGPARAMETERS() Determine if TRAININGPARAMETERS has a value

EvaluationParameters

Used to override the default evaluation parameters of the specified algorithm. Amazon Forecast evaluates a predictor by splitting a dataset into training data and testing data. The evaluation parameters define how to perform the split and the number of iterations.

Accessible with the following methods

Method Description
GET_EVALUATIONPARAMETERS() Getter for EVALUATIONPARAMETERS

HPOConfig

The hyperparameter override values for the algorithm.

Accessible with the following methods

Method Description
GET_HPOCONFIG() Getter for HPOCONFIG

InputDataConfig

Describes the dataset group that contains the data to use to train the predictor.

Accessible with the following methods

Method Description
GET_INPUTDATACONFIG() Getter for INPUTDATACONFIG

FeaturizationConfig

The featurization configuration.

Accessible with the following methods

Method Description
GET_FEATURIZATIONCONFIG() Getter for FEATURIZATIONCONFIG

EncryptionConfig

An Key Management Service (KMS) key and the Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.

Accessible with the following methods

Method Description
GET_ENCRYPTIONCONFIG() Getter for ENCRYPTIONCONFIG

PredictorExecutionDetails

Details on the the status and results of the backtests performed to evaluate the accuracy of the predictor. You specify the number of backtests to perform when you call the operation.

Accessible with the following methods

Method Description
GET_PREDICTOREXECDETAILS() Getter for PREDICTOREXECUTIONDETAILS

EstimatedTimeRemainingInMinutes

The estimated time remaining in minutes for the predictor training job to complete.

Accessible with the following methods

Method Description
GET_ESTIMATEDTIMEREMAINING00() Getter for ESTIMATEDTIMEREMAININGINMINS, with configurable d
ASK_ESTIMATEDTIMEREMAINING00() Getter for ESTIMATEDTIMEREMAININGINMINS w/ exceptions if fie
HAS_ESTIMATEDTIMEREMAINING00() Determine if ESTIMATEDTIMEREMAININGINMINS has a value

IsAutoPredictor

Whether the predictor was created with CreateAutoPredictor.

Accessible with the following methods

Method Description
GET_ISAUTOPREDICTOR() Getter for ISAUTOPREDICTOR, with configurable default
ASK_ISAUTOPREDICTOR() Getter for ISAUTOPREDICTOR w/ exceptions if field has no val
HAS_ISAUTOPREDICTOR() Determine if ISAUTOPREDICTOR has a value

DatasetImportJobArns

An array of the ARNs of the dataset import jobs used to import training data for the predictor.

Accessible with the following methods

Method Description
GET_DATASETIMPORTJOBARNS() Getter for DATASETIMPORTJOBARNS, with configurable default
ASK_DATASETIMPORTJOBARNS() Getter for DATASETIMPORTJOBARNS w/ exceptions if field has n
HAS_DATASETIMPORTJOBARNS() Determine if DATASETIMPORTJOBARNS has a value

Status

The status of the predictor. States include:

  • ACTIVE

  • CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED

  • DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED

  • CREATE_STOPPING, CREATE_STOPPED

The Status of the predictor must be ACTIVE before you can use the predictor to create a forecast.

Accessible with the following methods

Method Description
GET_STATUS() Getter for STATUS, with configurable default
ASK_STATUS() Getter for STATUS w/ exceptions if field has no value
HAS_STATUS() Determine if STATUS has a value

Message

If an error occurred, an informational message about the error.

Accessible with the following methods

Method Description
GET_MESSAGE() Getter for MESSAGE, with configurable default
ASK_MESSAGE() Getter for MESSAGE w/ exceptions if field has no value
HAS_MESSAGE() Determine if MESSAGE has a value

CreationTime

When the model training task was created.

Accessible with the following methods

Method Description
GET_CREATIONTIME() Getter for CREATIONTIME, with configurable default
ASK_CREATIONTIME() Getter for CREATIONTIME w/ exceptions if field has no value
HAS_CREATIONTIME() Determine if CREATIONTIME has a value

LastModificationTime

The last time the resource was modified. The timestamp depends on the status of the job:

  • CREATE_PENDING - The CreationTime.

  • CREATE_IN_PROGRESS - The current timestamp.

  • CREATE_STOPPING - The current timestamp.

  • CREATE_STOPPED - When the job stopped.

  • ACTIVE or CREATE_FAILED - When the job finished or failed.

Accessible with the following methods

Method Description
GET_LASTMODIFICATIONTIME() Getter for LASTMODIFICATIONTIME, with configurable default
ASK_LASTMODIFICATIONTIME() Getter for LASTMODIFICATIONTIME w/ exceptions if field has n
HAS_LASTMODIFICATIONTIME() Determine if LASTMODIFICATIONTIME has a value

OptimizationMetric

The accuracy metric used to optimize the predictor.

Accessible with the following methods

Method Description
GET_OPTIMIZATIONMETRIC() Getter for OPTIMIZATIONMETRIC, with configurable default
ASK_OPTIMIZATIONMETRIC() Getter for OPTIMIZATIONMETRIC w/ exceptions if field has no
HAS_OPTIMIZATIONMETRIC() Determine if OPTIMIZATIONMETRIC has a value