{ "version":"2.0", "metadata":{ "apiVersion":"2018-06-26", "endpointPrefix":"forecast", "jsonVersion":"1.1", "protocol":"json", "serviceFullName":"Amazon Forecast Service", "serviceId":"forecast", "signatureVersion":"v4", "signingName":"forecast", "targetPrefix":"AmazonForecast", "uid":"forecast-2018-06-26" }, "operations":{ "CreateDataset":{ "name":"CreateDataset", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"CreateDatasetRequest"}, "output":{"shape":"CreateDatasetResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceAlreadyExistsException"}, {"shape":"LimitExceededException"} ], "documentation":"

Creates an Amazon Forecast dataset. The information about the dataset that you provide helps Forecast understand how to consume the data for model training. This includes the following:

After creating a dataset, you import your training data into the dataset and add the dataset to a dataset group. You then use the dataset group to create a predictor. For more information, see howitworks-datasets-groups.

To get a list of all your datasets, use the ListDatasets operation.

The Status of a dataset must be ACTIVE before you can import training data. Use the DescribeDataset operation to get the status.

" }, "CreateDatasetGroup":{ "name":"CreateDatasetGroup", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"CreateDatasetGroupRequest"}, "output":{"shape":"CreateDatasetGroupResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceAlreadyExistsException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"}, {"shape":"LimitExceededException"} ], "documentation":"

Creates an Amazon Forecast dataset group, which holds a collection of related datasets. You can add datasets to the dataset group when you create the dataset group, or you can add datasets later with the UpdateDatasetGroup operation.

After creating a dataset group and adding datasets, you use the dataset group when you create a predictor. For more information, see howitworks-datasets-groups.

To get a list of all your datasets groups, use the ListDatasetGroups operation.

The Status of a dataset group must be ACTIVE before you can create a predictor using the dataset group. Use the DescribeDatasetGroup operation to get the status.

" }, "CreateDatasetImportJob":{ "name":"CreateDatasetImportJob", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"CreateDatasetImportJobRequest"}, "output":{"shape":"CreateDatasetImportJobResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceAlreadyExistsException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"}, {"shape":"LimitExceededException"} ], "documentation":"

Imports your training data to an Amazon Forecast dataset. You provide the location of your training data in an Amazon Simple Storage Service (Amazon S3) bucket and the Amazon Resource Name (ARN) of the dataset that you want to import the data to.

You must specify a DataSource object that includes an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the data. For more information, see aws-forecast-iam-roles.

Two properties of the training data are optionally specified:

When Amazon Forecast uploads your training data, it verifies that the data was collected at the DataFrequency specified when the target dataset was created. For more information, see CreateDataset and howitworks-datasets-groups. Amazon Forecast also verifies the delimiter and timestamp format.

You can use the ListDatasetImportJobs operation to get a list of all your dataset import jobs, filtered by specified criteria.

To get a list of all your dataset import jobs, filtered by the specified criteria, use the ListDatasetGroups operation.

" }, "CreateForecast":{ "name":"CreateForecast", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"CreateForecastRequest"}, "output":{"shape":"CreateForecastResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceAlreadyExistsException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"}, {"shape":"LimitExceededException"} ], "documentation":"

Creates a forecast for each item in the TARGET_TIME_SERIES dataset that was used to train the predictor. This is known as inference. To retrieve the forecast for a single item at low latency, use the operation. To export the complete forecast into your Amazon Simple Storage Service (Amazon S3), use the CreateForecastExportJob operation.

The range of the forecast is determined by the ForecastHorizon, specified in the CreatePredictor request, multiplied by the DataFrequency, specified in the CreateDataset request. When you query a forecast, you can request a specific date range within the complete forecast.

To get a list of all your forecasts, use the ListForecasts operation.

The forecasts generated by Amazon Forecast are in the same timezone as the dataset that was used to create the predictor.

For more information, see howitworks-forecast.

The Status of the forecast must be ACTIVE before you can query or export the forecast. Use the DescribeForecast operation to get the status.

" }, "CreateForecastExportJob":{ "name":"CreateForecastExportJob", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"CreateForecastExportJobRequest"}, "output":{"shape":"CreateForecastExportJobResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceAlreadyExistsException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"}, {"shape":"LimitExceededException"} ], "documentation":"

Exports a forecast created by the CreateForecast operation to your Amazon Simple Storage Service (Amazon S3) bucket.

You must specify a DataDestination object that includes an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the Amazon S3 bucket. For more information, see aws-forecast-iam-roles.

For more information, see howitworks-forecast.

To get a list of all your forecast export jobs, use the ListForecastExportJobs operation.

The Status of the forecast export job must be ACTIVE before you can access the forecast in your Amazon S3 bucket. Use the DescribeForecastExportJob operation to get the status.

" }, "CreatePredictor":{ "name":"CreatePredictor", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"CreatePredictorRequest"}, "output":{"shape":"CreatePredictorResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceAlreadyExistsException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"}, {"shape":"LimitExceededException"} ], "documentation":"

Creates an Amazon Forecast predictor.

In the request, you provide a dataset group and either specify an algorithm or let Amazon Forecast choose the algorithm for you using AutoML. If you specify an algorithm, you also can override algorithm-specific hyperparameters.

Amazon Forecast uses the chosen algorithm to train a model using the latest version of the datasets in the specified dataset group. The result is called a predictor. You then generate a forecast using the CreateForecast operation.

After training a model, the CreatePredictor operation also evaluates it. To see the evaluation metrics, use the GetAccuracyMetrics operation. Always review the evaluation metrics before deciding to use the predictor to generate a forecast.

Optionally, you can specify a featurization configuration to fill and aggragate the data fields in the TARGET_TIME_SERIES dataset to improve model training. For more information, see FeaturizationConfig.

AutoML

If you set PerformAutoML to true, Amazon Forecast evaluates each algorithm and chooses the one that minimizes the objective function. The objective function is defined as the mean of the weighted p10, p50, and p90 quantile losses. For more information, see EvaluationResult.

When AutoML is enabled, the following properties are disallowed:

To get a list of all your predictors, use the ListPredictors operation.

The Status of the predictor must be ACTIVE, signifying that training has completed, before you can use the predictor to create a forecast. Use the DescribePredictor operation to get the status.

" }, "DeleteDataset":{ "name":"DeleteDataset", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DeleteDatasetRequest"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"} ], "documentation":"

Deletes an Amazon Forecast dataset created using the CreateDataset operation. To be deleted, the dataset must have a status of ACTIVE or CREATE_FAILED. Use the DescribeDataset operation to get the status.

", "idempotent":true }, "DeleteDatasetGroup":{ "name":"DeleteDatasetGroup", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DeleteDatasetGroupRequest"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"} ], "documentation":"

Deletes a dataset group created using the CreateDatasetGroup operation. To be deleted, the dataset group must have a status of ACTIVE, CREATE_FAILED, or UPDATE_FAILED. Use the DescribeDatasetGroup operation to get the status.

The operation deletes only the dataset group, not the datasets in the group.

", "idempotent":true }, "DeleteDatasetImportJob":{ "name":"DeleteDatasetImportJob", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DeleteDatasetImportJobRequest"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"} ], "documentation":"

Deletes a dataset import job created using the CreateDatasetImportJob operation. To be deleted, the import job must have a status of ACTIVE or CREATE_FAILED. Use the DescribeDatasetImportJob operation to get the status.

", "idempotent":true }, "DeleteForecast":{ "name":"DeleteForecast", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DeleteForecastRequest"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"} ], "documentation":"

Deletes a forecast created using the CreateForecast operation. To be deleted, the forecast must have a status of ACTIVE or CREATE_FAILED. Use the DescribeForecast operation to get the status.

You can't delete a forecast while it is being exported.

", "idempotent":true }, "DeleteForecastExportJob":{ "name":"DeleteForecastExportJob", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DeleteForecastExportJobRequest"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"} ], "documentation":"

Deletes a forecast export job created using the CreateForecastExportJob operation. To be deleted, the export job must have a status of ACTIVE or CREATE_FAILED. Use the DescribeForecastExportJob operation to get the status.

", "idempotent":true }, "DeletePredictor":{ "name":"DeletePredictor", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DeletePredictorRequest"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"} ], "documentation":"

Deletes a predictor created using the CreatePredictor operation. To be deleted, the predictor must have a status of ACTIVE or CREATE_FAILED. Use the DescribePredictor operation to get the status.

Any forecasts generated by the predictor will no longer be available.

", "idempotent":true }, "DescribeDataset":{ "name":"DescribeDataset", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DescribeDatasetRequest"}, "output":{"shape":"DescribeDatasetResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"} ], "documentation":"

Describes an Amazon Forecast dataset created using the CreateDataset operation.

In addition to listing the properties provided by the user in the CreateDataset request, this operation includes the following properties:

", "idempotent":true }, "DescribeDatasetGroup":{ "name":"DescribeDatasetGroup", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DescribeDatasetGroupRequest"}, "output":{"shape":"DescribeDatasetGroupResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"} ], "documentation":"

Describes a dataset group created using the CreateDatasetGroup operation.

In addition to listing the properties provided by the user in the CreateDatasetGroup request, this operation includes the following properties:

", "idempotent":true }, "DescribeDatasetImportJob":{ "name":"DescribeDatasetImportJob", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DescribeDatasetImportJobRequest"}, "output":{"shape":"DescribeDatasetImportJobResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"} ], "documentation":"

Describes a dataset import job created using the CreateDatasetImportJob operation.

In addition to listing the properties provided by the user in the CreateDatasetImportJob request, this operation includes the following properties:

", "idempotent":true }, "DescribeForecast":{ "name":"DescribeForecast", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DescribeForecastRequest"}, "output":{"shape":"DescribeForecastResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"} ], "documentation":"

Describes a forecast created using the CreateForecast operation.

In addition to listing the properties provided by the user in the CreateForecast request, this operation includes the following properties:

", "idempotent":true }, "DescribeForecastExportJob":{ "name":"DescribeForecastExportJob", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DescribeForecastExportJobRequest"}, "output":{"shape":"DescribeForecastExportJobResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"} ], "documentation":"

Describes a forecast export job created using the CreateForecastExportJob operation.

In addition to listing the properties provided by the user in the CreateForecastExportJob request, this operation includes the following properties:

", "idempotent":true }, "DescribePredictor":{ "name":"DescribePredictor", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"DescribePredictorRequest"}, "output":{"shape":"DescribePredictorResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"} ], "documentation":"

Describes a predictor created using the CreatePredictor operation.

In addition to listing the properties provided by the user in the CreatePredictor request, this operation includes the following properties:

", "idempotent":true }, "GetAccuracyMetrics":{ "name":"GetAccuracyMetrics", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"GetAccuracyMetricsRequest"}, "output":{"shape":"GetAccuracyMetricsResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"} ], "documentation":"

Provides metrics on the accuracy of the models that were trained by the CreatePredictor operation. Use metrics to see how well the model performed and to decide whether to use the predictor to generate a forecast.

Metrics are generated for each backtest window evaluated. For more information, see EvaluationParameters.

The parameters of the filling method determine which items contribute to the metrics. If zero is specified, all items contribute. If nan is specified, only those items that have complete data in the range being evaluated contribute. For more information, see FeaturizationMethod.

For an example of how to train a model and review metrics, see getting-started.

", "idempotent":true }, "ListDatasetGroups":{ "name":"ListDatasetGroups", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"ListDatasetGroupsRequest"}, "output":{"shape":"ListDatasetGroupsResponse"}, "errors":[ {"shape":"InvalidNextTokenException"} ], "documentation":"

Returns a list of dataset groups created using the CreateDatasetGroup operation. For each dataset group, a summary of its properties, including its Amazon Resource Name (ARN), is returned. You can retrieve the complete set of properties by using the ARN with the DescribeDatasetGroup operation.

", "idempotent":true }, "ListDatasetImportJobs":{ "name":"ListDatasetImportJobs", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"ListDatasetImportJobsRequest"}, "output":{"shape":"ListDatasetImportJobsResponse"}, "errors":[ {"shape":"InvalidNextTokenException"}, {"shape":"InvalidInputException"} ], "documentation":"

Returns a list of dataset import jobs created using the CreateDatasetImportJob operation. For each import job, a summary of its properties, including its Amazon Resource Name (ARN), is returned. You can retrieve the complete set of properties by using the ARN with the DescribeDatasetImportJob operation. You can filter the list by providing an array of Filter objects.

", "idempotent":true }, "ListDatasets":{ "name":"ListDatasets", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"ListDatasetsRequest"}, "output":{"shape":"ListDatasetsResponse"}, "errors":[ {"shape":"InvalidNextTokenException"} ], "documentation":"

Returns a list of datasets created using the CreateDataset operation. For each dataset, a summary of its properties, including its Amazon Resource Name (ARN), is returned. You can retrieve the complete set of properties by using the ARN with the DescribeDataset operation.

", "idempotent":true }, "ListForecastExportJobs":{ "name":"ListForecastExportJobs", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"ListForecastExportJobsRequest"}, "output":{"shape":"ListForecastExportJobsResponse"}, "errors":[ {"shape":"InvalidNextTokenException"}, {"shape":"InvalidInputException"} ], "documentation":"

Returns a list of forecast export jobs created using the CreateForecastExportJob operation. For each forecast export job, a summary of its properties, including its Amazon Resource Name (ARN), is returned. You can retrieve the complete set of properties by using the ARN with the DescribeForecastExportJob operation. The list can be filtered using an array of Filter objects.

", "idempotent":true }, "ListForecasts":{ "name":"ListForecasts", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"ListForecastsRequest"}, "output":{"shape":"ListForecastsResponse"}, "errors":[ {"shape":"InvalidNextTokenException"}, {"shape":"InvalidInputException"} ], "documentation":"

Returns a list of forecasts created using the CreateForecast operation. For each forecast, a summary of its properties, including its Amazon Resource Name (ARN), is returned. You can retrieve the complete set of properties by using the ARN with the DescribeForecast operation. The list can be filtered using an array of Filter objects.

", "idempotent":true }, "ListPredictors":{ "name":"ListPredictors", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"ListPredictorsRequest"}, "output":{"shape":"ListPredictorsResponse"}, "errors":[ {"shape":"InvalidNextTokenException"}, {"shape":"InvalidInputException"} ], "documentation":"

Returns a list of predictors created using the CreatePredictor operation. For each predictor, a summary of its properties, including its Amazon Resource Name (ARN), is returned. You can retrieve the complete set of properties by using the ARN with the DescribePredictor operation. The list can be filtered using an array of Filter objects.

", "idempotent":true }, "UpdateDatasetGroup":{ "name":"UpdateDatasetGroup", "http":{ "method":"POST", "requestUri":"/" }, "input":{"shape":"UpdateDatasetGroupRequest"}, "output":{"shape":"UpdateDatasetGroupResponse"}, "errors":[ {"shape":"InvalidInputException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ResourceInUseException"} ], "documentation":"

Replaces any existing datasets in the dataset group with the specified datasets.

The Status of the dataset group must be ACTIVE before creating a predictor using the dataset group. Use the DescribeDatasetGroup operation to get the status.

", "idempotent":true } }, "shapes":{ "Arn":{ "type":"string", "max":256, "pattern":"^[a-zA-Z0-9\\-\\_\\.\\/\\:]+$" }, "ArnList":{ "type":"list", "member":{"shape":"Arn"} }, "AttributeType":{ "type":"string", "enum":[ "string", "integer", "float", "timestamp" ] }, "Boolean":{"type":"boolean"}, "CategoricalParameterRange":{ "type":"structure", "required":[ "Name", "Values" ], "members":{ "Name":{ "shape":"Name", "documentation":"

The name of the categorical hyperparameter to tune.

" }, "Values":{ "shape":"Values", "documentation":"

A list of the tunable categories for the hyperparameter.

" } }, "documentation":"

Specifies a categorical hyperparameter and it's range of tunable values. This object is part of the ParameterRanges object.

" }, "CategoricalParameterRanges":{ "type":"list", "member":{"shape":"CategoricalParameterRange"}, "max":20, "min":1 }, "ContinuousParameterRange":{ "type":"structure", "required":[ "Name", "MaxValue", "MinValue" ], "members":{ "Name":{ "shape":"Name", "documentation":"

The name of the hyperparameter to tune.

" }, "MaxValue":{ "shape":"Double", "documentation":"

The maximum tunable value of the hyperparameter.

" }, "MinValue":{ "shape":"Double", "documentation":"

The minimum tunable value of the hyperparameter.

" }, "ScalingType":{ "shape":"ScalingType", "documentation":"

The scale that hyperparameter tuning uses to search the hyperparameter range. For information about choosing a hyperparameter scale, see Hyperparameter Scaling. One of the following values:

Auto

Amazon Forecast hyperparameter tuning chooses the best scale for the hyperparameter.

Linear

Hyperparameter tuning searches the values in the hyperparameter range by using a linear scale.

Logarithmic

Hyperparameter tuning searches the values in the hyperparameter range by using a logarithmic scale.

Logarithmic scaling works only for ranges that have only values greater than 0.

ReverseLogarithmic

Hyperparemeter tuning searches the values in the hyperparameter range by using a reverse logarithmic scale.

Reverse logarithmic scaling works only for ranges that are entirely within the range 0 <= x < 1.0.

" } }, "documentation":"

Specifies a continuous hyperparameter and it's range of tunable values. This object is part of the ParameterRanges object.

" }, "ContinuousParameterRanges":{ "type":"list", "member":{"shape":"ContinuousParameterRange"}, "max":20, "min":1 }, "CreateDatasetGroupRequest":{ "type":"structure", "required":[ "DatasetGroupName", "Domain" ], "members":{ "DatasetGroupName":{ "shape":"Name", "documentation":"

A name for the dataset group.

" }, "Domain":{ "shape":"Domain", "documentation":"

The domain associated with the dataset group. The Domain and DatasetType that you choose determine the fields that must be present in the training data that you import to the dataset. For example, if you choose the RETAIL domain and TARGET_TIME_SERIES as the DatasetType, Amazon Forecast requires item_id, timestamp, and demand fields to be present in your data. For more information, see howitworks-datasets-groups.

" }, "DatasetArns":{ "shape":"ArnList", "documentation":"

An array of Amazon Resource Names (ARNs) of the datasets that you want to include in the dataset group.

" } } }, "CreateDatasetGroupResponse":{ "type":"structure", "members":{ "DatasetGroupArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset group.

" } } }, "CreateDatasetImportJobRequest":{ "type":"structure", "required":[ "DatasetImportJobName", "DatasetArn", "DataSource" ], "members":{ "DatasetImportJobName":{ "shape":"Name", "documentation":"

The name for the dataset import job. It is recommended to include the current timestamp in the name to guard against getting a ResourceAlreadyExistsException exception, for example, 20190721DatasetImport.

" }, "DatasetArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the Amazon Forecast dataset that you want to import data to.

" }, "DataSource":{ "shape":"DataSource", "documentation":"

The location of the training data to import and an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the data.

" }, "TimestampFormat":{ "shape":"TimestampFormat", "documentation":"

The format of timestamps in the dataset. Two formats are supported, dependent on the DataFrequency specified when the dataset was created.

" } } }, "CreateDatasetImportJobResponse":{ "type":"structure", "members":{ "DatasetImportJobArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset import job.

" } } }, "CreateDatasetRequest":{ "type":"structure", "required":[ "DatasetName", "Domain", "DatasetType", "Schema" ], "members":{ "DatasetName":{ "shape":"Name", "documentation":"

A name for the dataset.

" }, "Domain":{ "shape":"Domain", "documentation":"

The domain associated with the dataset. The Domain and DatasetType that you choose determine the fields that must be present in the training data that you import to the dataset. For example, if you choose the RETAIL domain and TARGET_TIME_SERIES as the DatasetType, Amazon Forecast requires item_id, timestamp, and demand fields to be present in your data. For more information, see howitworks-datasets-groups.

" }, "DatasetType":{ "shape":"DatasetType", "documentation":"

The dataset type. Valid values depend on the chosen Domain.

" }, "DataFrequency":{ "shape":"Frequency", "documentation":"

The frequency of data collection.

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, \"D\" indicates every day and \"15min\" indicates every 15 minutes.

" }, "Schema":{ "shape":"Schema", "documentation":"

The schema for the dataset. The schema attributes and their order must match the fields in your data. The dataset Domain and DatasetType that you choose determine the minimum required fields in your training data. For information about the required fields for a specific dataset domain and type, see howitworks-domains-ds-types.

" }, "EncryptionConfig":{ "shape":"EncryptionConfig", "documentation":"

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

" } } }, "CreateDatasetResponse":{ "type":"structure", "members":{ "DatasetArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset.

" } } }, "CreateForecastExportJobRequest":{ "type":"structure", "required":[ "ForecastExportJobName", "ForecastArn", "Destination" ], "members":{ "ForecastExportJobName":{ "shape":"Name", "documentation":"

The name for the forecast export job.

" }, "ForecastArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the forecast that you want to export.

" }, "Destination":{ "shape":"DataDestination", "documentation":"

The path to the Amazon S3 bucket where you want to save the forecast and an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the bucket.

" } } }, "CreateForecastExportJobResponse":{ "type":"structure", "members":{ "ForecastExportJobArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the export job.

" } } }, "CreateForecastRequest":{ "type":"structure", "required":[ "ForecastName", "PredictorArn" ], "members":{ "ForecastName":{ "shape":"Name", "documentation":"

The name for the forecast.

" }, "PredictorArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the predictor to use to generate the forecast.

" } } }, "CreateForecastResponse":{ "type":"structure", "members":{ "ForecastArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the forecast.

" } } }, "CreatePredictorRequest":{ "type":"structure", "required":[ "PredictorName", "ForecastHorizon", "InputDataConfig", "FeaturizationConfig" ], "members":{ "PredictorName":{ "shape":"Name", "documentation":"

A name for the predictor.

" }, "AlgorithmArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the algorithm to use for model training. Required if PerformAutoML is not set to true.

Supported algorithms

" }, "ForecastHorizon":{ "shape":"Integer", "documentation":"

Specifies the number of time-steps that the model is trained to predict. The forecast horizon is also called the prediction length.

For example, if you configure a dataset for daily data collection (using the DataFrequency parameter of the CreateDataset operation) and set the forecast horizon to 10, the model returns predictions for 10 days.

" }, "PerformAutoML":{ "shape":"Boolean", "documentation":"

Whether to perform AutoML. The default value is false. In this case, you are required to specify an algorithm.

If you want Amazon Forecast to evaluate the algorithms it provides and choose the best algorithm and configuration for your training dataset, set PerformAutoML to true. This is a good option if you aren't sure which algorithm is suitable for your application.

" }, "PerformHPO":{ "shape":"Boolean", "documentation":"

Whether to perform hyperparameter optimization (HPO). HPO finds optimal hyperparameter values for your training data. The process of performing HPO is known as a hyperparameter tuning job.

The default value is false. In this case, Amazon Forecast uses default hyperparameter values from the chosen algorithm.

To override the default values, set PerformHPO to true and supply the HyperParameterTuningJobConfig object. The tuning job specifies an objective metric, the hyperparameters to optimize, and the valid range for each hyperparameter.

The following algorithms support HPO:

" }, "TrainingParameters":{ "shape":"TrainingParameters", "documentation":"

The training parameters to override for model training. The parameters that you can override are listed in the individual algorithms in aws-forecast-choosing-recipes.

" }, "EvaluationParameters":{ "shape":"EvaluationParameters", "documentation":"

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.

" }, "HPOConfig":{ "shape":"HyperParameterTuningJobConfig", "documentation":"

Provides hyperparameter override values for the algorithm. If you don't provide this parameter, Amazon Forecast uses default values. The individual algorithms specify which hyperparameters support hyperparameter optimization (HPO). For more information, see aws-forecast-choosing-recipes.

" }, "InputDataConfig":{ "shape":"InputDataConfig", "documentation":"

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

" }, "FeaturizationConfig":{ "shape":"FeaturizationConfig", "documentation":"

The featurization configuration.

" }, "EncryptionConfig":{ "shape":"EncryptionConfig", "documentation":"

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

" } } }, "CreatePredictorResponse":{ "type":"structure", "members":{ "PredictorArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the predictor.

" } } }, "DataDestination":{ "type":"structure", "required":["S3Config"], "members":{ "S3Config":{ "shape":"S3Config", "documentation":"

The path to an Amazon Simple Storage Service (Amazon S3) bucket along with the credentials to access the bucket.

" } }, "documentation":"

The destination of an exported forecast and credentials to access the location. This object is submitted in the CreateForecastExportJob request.

" }, "DataSource":{ "type":"structure", "required":["S3Config"], "members":{ "S3Config":{ "shape":"S3Config", "documentation":"

The path to the training data stored in an Amazon Simple Storage Service (Amazon S3) bucket along with the credentials to access the data.

" } }, "documentation":"

The source of your training data and credentials to access the data. This object is submitted in the CreateDatasetImportJob request.

" }, "DatasetGroupSummary":{ "type":"structure", "members":{ "DatasetGroupArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset group.

" }, "DatasetGroupName":{ "shape":"Name", "documentation":"

The name of the dataset group.

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the datase group was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

When the dataset group was created or last updated from a call to the UpdateDatasetGroup operation. While the dataset group is being updated, LastModificationTime is the current query time.

" } }, "documentation":"

Provides a summary of the dataset group properties used in the ListDatasetGroups operation. To get the complete set of properties, call the DescribeDatasetGroup operation, and provide the listed DatasetGroupArn.

" }, "DatasetGroups":{ "type":"list", "member":{"shape":"DatasetGroupSummary"} }, "DatasetImportJobSummary":{ "type":"structure", "members":{ "DatasetImportJobArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset import job.

" }, "DatasetImportJobName":{ "shape":"Name", "documentation":"

The name of the dataset import job.

" }, "DataSource":{ "shape":"DataSource", "documentation":"

The location of the Amazon S3 bucket that contains the training data.

" }, "Status":{ "shape":"Status", "documentation":"

The status of the dataset import job. The status is reflected in the status of the dataset. For example, when the import job status is CREATE_IN_PROGRESS, the status of the dataset is UPDATE_IN_PROGRESS. States include:

" }, "Message":{ "shape":"ErrorMessage", "documentation":"

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

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the dataset import job was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

Dependent on the status as follows:

" } }, "documentation":"

Provides a summary of the dataset import job properties used in the ListDatasetImportJobs operation. To get the complete set of properties, call the DescribeDatasetImportJob operation, and provide the listed DatasetImportJobArn.

" }, "DatasetImportJobs":{ "type":"list", "member":{"shape":"DatasetImportJobSummary"} }, "DatasetSummary":{ "type":"structure", "members":{ "DatasetArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset.

" }, "DatasetName":{ "shape":"Name", "documentation":"

The name of the dataset.

" }, "DatasetType":{ "shape":"DatasetType", "documentation":"

The dataset type.

" }, "Domain":{ "shape":"Domain", "documentation":"

The domain associated with the dataset.

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the dataset was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

When the dataset is created, LastModificationTime is the same as CreationTime. After a CreateDatasetImportJob operation is called, LastModificationTime is when the import job finished or failed. While data is being imported to the dataset, LastModificationTime is the current query time.

" } }, "documentation":"

Provides a summary of the dataset properties used in the ListDatasets operation. To get the complete set of properties, call the DescribeDataset operation, and provide the listed DatasetArn.

" }, "DatasetType":{ "type":"string", "enum":[ "TARGET_TIME_SERIES", "RELATED_TIME_SERIES", "ITEM_METADATA" ] }, "Datasets":{ "type":"list", "member":{"shape":"DatasetSummary"} }, "DeleteDatasetGroupRequest":{ "type":"structure", "required":["DatasetGroupArn"], "members":{ "DatasetGroupArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset group to delete.

" } } }, "DeleteDatasetImportJobRequest":{ "type":"structure", "required":["DatasetImportJobArn"], "members":{ "DatasetImportJobArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset import job to delete.

" } } }, "DeleteDatasetRequest":{ "type":"structure", "required":["DatasetArn"], "members":{ "DatasetArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset to delete.

" } } }, "DeleteForecastExportJobRequest":{ "type":"structure", "required":["ForecastExportJobArn"], "members":{ "ForecastExportJobArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the forecast export job to delete.

" } } }, "DeleteForecastRequest":{ "type":"structure", "required":["ForecastArn"], "members":{ "ForecastArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the forecast to delete.

" } } }, "DeletePredictorRequest":{ "type":"structure", "required":["PredictorArn"], "members":{ "PredictorArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the predictor to delete.

" } } }, "DescribeDatasetGroupRequest":{ "type":"structure", "required":["DatasetGroupArn"], "members":{ "DatasetGroupArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset group.

" } } }, "DescribeDatasetGroupResponse":{ "type":"structure", "members":{ "DatasetGroupName":{ "shape":"Name", "documentation":"

The name of the dataset group.

" }, "DatasetGroupArn":{ "shape":"Arn", "documentation":"

The ARN of the dataset group.

" }, "DatasetArns":{ "shape":"ArnList", "documentation":"

An array of Amazon Resource Names (ARNs) of the datasets contained in the dataset group.

" }, "Domain":{ "shape":"Domain", "documentation":"

The domain associated with the dataset group. The Domain and DatasetType that you choose determine the fields that must be present in the training data that you import to the dataset. For example, if you choose the RETAIL domain and TARGET_TIME_SERIES as the DatasetType, Amazon Forecast requires item_id, timestamp, and demand fields to be present in your data. For more information, see howitworks-datasets-groups.

" }, "Status":{ "shape":"Status", "documentation":"

The status of the dataset group. States include:

The UPDATE states apply when the UpdateDatasetGroup operation is called.

The Status of the dataset group must be ACTIVE before creating a predictor using the dataset group.

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the dataset group was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

When the dataset group was created or last updated from a call to the UpdateDatasetGroup operation. While the dataset group is being updated, LastModificationTime is the current query time.

" } } }, "DescribeDatasetImportJobRequest":{ "type":"structure", "required":["DatasetImportJobArn"], "members":{ "DatasetImportJobArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset import job.

" } } }, "DescribeDatasetImportJobResponse":{ "type":"structure", "members":{ "DatasetImportJobName":{ "shape":"Name", "documentation":"

The name of the dataset import job.

" }, "DatasetImportJobArn":{ "shape":"Arn", "documentation":"

The ARN of the dataset import job.

" }, "DatasetArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset that the training data was imported to.

" }, "TimestampFormat":{ "shape":"TimestampFormat", "documentation":"

The format of timestamps in the dataset. Two formats are supported dependent on the DataFrequency specified when the dataset was created.

" }, "DataSource":{ "shape":"DataSource", "documentation":"

The location of the training data to import. The training data must be stored in an Amazon S3 bucket.

" }, "FieldStatistics":{ "shape":"FieldStatistics", "documentation":"

Statistical information about each field in the input data.

" }, "DataSize":{ "shape":"Double", "documentation":"

The size of the dataset in gigabytes (GB) after completion of the import job.

" }, "Status":{ "shape":"Status", "documentation":"

The status of the dataset import job. The status is reflected in the status of the dataset. For example, when the import job status is CREATE_IN_PROGRESS, the status of the dataset is UPDATE_IN_PROGRESS. States include:

" }, "Message":{ "shape":"Message", "documentation":"

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

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the dataset import job was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

Dependent on the status as follows:

" } } }, "DescribeDatasetRequest":{ "type":"structure", "required":["DatasetArn"], "members":{ "DatasetArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset.

" } } }, "DescribeDatasetResponse":{ "type":"structure", "members":{ "DatasetArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset.

" }, "DatasetName":{ "shape":"Name", "documentation":"

The name of the dataset.

" }, "Domain":{ "shape":"Domain", "documentation":"

The dataset domain.

" }, "DatasetType":{ "shape":"DatasetType", "documentation":"

The dataset type.

" }, "DataFrequency":{ "shape":"Frequency", "documentation":"

The frequency of data collection.

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, \"M\" indicates every month and \"30min\" indicates every 30 minutes.

" }, "Schema":{ "shape":"Schema", "documentation":"

An array of SchemaAttribute objects that specify the dataset fields. Each SchemaAttribute specifies the name and data type of a field.

" }, "EncryptionConfig":{ "shape":"EncryptionConfig", "documentation":"

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

" }, "Status":{ "shape":"Status", "documentation":"

The status of the dataset. States include:

The UPDATE states apply while data is imported to the dataset from a call to the CreateDatasetImportJob operation. During this time, the status reflects the status of the dataset import job. For example, when the import job status is CREATE_IN_PROGRESS, the status of the dataset is UPDATE_IN_PROGRESS.

The Status of the dataset must be ACTIVE before you can import training data.

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the dataset was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

When the dataset is created, LastModificationTime is the same as CreationTime. After a CreateDatasetImportJob operation is called, LastModificationTime is when the import job finished or failed. While data is being imported to the dataset, LastModificationTime is the current query time.

" } } }, "DescribeForecastExportJobRequest":{ "type":"structure", "required":["ForecastExportJobArn"], "members":{ "ForecastExportJobArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the forecast export job.

" } } }, "DescribeForecastExportJobResponse":{ "type":"structure", "members":{ "ForecastExportJobArn":{ "shape":"Arn", "documentation":"

The ARN of the forecast export job.

" }, "ForecastExportJobName":{ "shape":"Name", "documentation":"

The name of the forecast export job.

" }, "ForecastArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the exported forecast.

" }, "Destination":{ "shape":"DataDestination", "documentation":"

The path to the AWS S3 bucket where the forecast is exported.

" }, "Message":{ "shape":"Message", "documentation":"

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

" }, "Status":{ "shape":"Status", "documentation":"

The status of the forecast export job. One of the following states:

The Status of the forecast export job must be ACTIVE before you can access the forecast in your Amazon S3 bucket.

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the forecast export job was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

When the last successful export job finished.

" } } }, "DescribeForecastRequest":{ "type":"structure", "required":["ForecastArn"], "members":{ "ForecastArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the forecast.

" } } }, "DescribeForecastResponse":{ "type":"structure", "members":{ "ForecastArn":{ "shape":"Arn", "documentation":"

The same forecast ARN as given in the request.

" }, "ForecastName":{ "shape":"Name", "documentation":"

The name of the forecast.

" }, "PredictorArn":{ "shape":"Arn", "documentation":"

The ARN of the predictor used to generate the forecast.

" }, "DatasetGroupArn":{ "shape":"Arn", "documentation":"

The ARN of the dataset group that provided the data used to train the predictor.

" }, "Status":{ "shape":"String", "documentation":"

The status of the forecast. States include:

The Status of the forecast must be ACTIVE before you can query or export the forecast.

" }, "Message":{ "shape":"ErrorMessage", "documentation":"

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

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the forecast creation task was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

Initially, the same as CreationTime (status is CREATE_PENDING). Updated when inference (creating the forecast) starts (status changed to CREATE_IN_PROGRESS), and when inference is complete (status changed to ACTIVE) or fails (status changed to CREATE_FAILED).

" } } }, "DescribePredictorRequest":{ "type":"structure", "required":["PredictorArn"], "members":{ "PredictorArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the predictor that you want information about.

" } } }, "DescribePredictorResponse":{ "type":"structure", "members":{ "PredictorArn":{ "shape":"Name", "documentation":"

The ARN of the predictor.

" }, "PredictorName":{ "shape":"Name", "documentation":"

The name of the predictor.

" }, "AlgorithmArn":{ "shape":"Arn", "documentation":"

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

" }, "ForecastHorizon":{ "shape":"Integer", "documentation":"

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

" }, "PerformAutoML":{ "shape":"Boolean", "documentation":"

Whether the predictor is set to perform AutoML.

" }, "PerformHPO":{ "shape":"Boolean", "documentation":"

Whether the predictor is set to perform HPO.

" }, "TrainingParameters":{ "shape":"TrainingParameters", "documentation":"

The training parameters to override for model training. The parameters that you can override are listed in the individual algorithms in aws-forecast-choosing-recipes.

" }, "EvaluationParameters":{ "shape":"EvaluationParameters", "documentation":"

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.

" }, "HPOConfig":{ "shape":"HyperParameterTuningJobConfig", "documentation":"

The hyperparameter override values for the algorithm.

" }, "InputDataConfig":{ "shape":"InputDataConfig", "documentation":"

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

" }, "FeaturizationConfig":{ "shape":"FeaturizationConfig", "documentation":"

The featurization configuration.

" }, "EncryptionConfig":{ "shape":"EncryptionConfig", "documentation":"

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

" }, "DatasetImportJobArns":{ "shape":"ArnList", "documentation":"

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

" }, "AutoMLAlgorithmArns":{ "shape":"ArnList", "documentation":"

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

" }, "Status":{ "shape":"Status", "documentation":"

The status of the predictor. States include:

The Status of the predictor must be ACTIVE before using the predictor to create a forecast.

" }, "Message":{ "shape":"Message", "documentation":"

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

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the model training task was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

Initially, the same as CreationTime (status is CREATE_PENDING). Updated when training starts (status changed to CREATE_IN_PROGRESS), and when training is complete (status changed to ACTIVE) or fails (status changed to CREATE_FAILED).

" } } }, "Domain":{ "type":"string", "enum":[ "RETAIL", "CUSTOM", "INVENTORY_PLANNING", "EC2_CAPACITY", "WORK_FORCE", "WEB_TRAFFIC", "METRICS" ] }, "Double":{"type":"double"}, "EncryptionConfig":{ "type":"structure", "required":[ "RoleArn", "KMSKeyArn" ], "members":{ "RoleArn":{ "shape":"Arn", "documentation":"

The ARN of the AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the AWS KMS key.

Cross-account pass role is not allowed. If you pass a role that doesn't belong to your account, an InvalidInputException is thrown.

" }, "KMSKeyArn":{ "shape":"KMSKeyArn", "documentation":"

The Amazon Resource Name (ARN) of an AWS Key Management Service (KMS) key.

" } }, "documentation":"

An AWS Key Management Service (KMS) key and an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key. This object is optionally submitted in the CreateDataset and CreatePredictor requests.

" }, "ErrorMessage":{"type":"string"}, "EvaluationParameters":{ "type":"structure", "members":{ "NumberOfBacktestWindows":{ "shape":"Integer", "documentation":"

The number of times to split the input data. The default is 1. The range is 1 through 5.

" }, "BackTestWindowOffset":{ "shape":"Integer", "documentation":"

The point from the end of the dataset where you want to split the data for model training and evaluation. The value is specified as the number of data points.

" } }, "documentation":"

Parameters that define how to split a dataset into training data and testing data, and the number of iterations to perform. These parameters are specified in the predefined algorithms and can be overridden in the CreatePredictor request.

For example, suppose that you have a dataset with data collection frequency set to every day and you have 200 days worth of data (that is, 200 data points). Now suppose that you set the NumberOfBacktestWindows to 2 and the BackTestWindowOffset parameter to 20. The algorithm splits the data twice. The first time, the algorithm trains the model using the first 180 data points and uses the last 20 data points for evaluation. The second time, the algorithm trains the model using the first 160 data points and uses the last 40 data points for evaluation.

" }, "EvaluationResult":{ "type":"structure", "members":{ "AlgorithmArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the algorithm that was evaluated.

" }, "TestWindows":{ "shape":"TestWindows", "documentation":"

The array of test windows used for evaluating the algorithm. The NumberOfBacktestWindows from the EvaluationParameters object determines the number of windows in the array.

" } }, "documentation":"

The results of evaluating an algorithm. Returned as part of the GetAccuracyMetrics response.

" }, "EvaluationType":{ "type":"string", "enum":[ "SUMMARY", "COMPUTED" ] }, "Featurization":{ "type":"structure", "required":["AttributeName"], "members":{ "AttributeName":{ "shape":"Name", "documentation":"

The name of the schema attribute specifying the data field to be featurized. In this release, 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.

" }, "FeaturizationPipeline":{ "shape":"FeaturizationPipeline", "documentation":"

An array FeaturizationMethod objects that specifies the feature transformation methods. For this release, the number of methods is limited to one.

" } }, "documentation":"

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\"}

} ]

}

" }, "FeaturizationConfig":{ "type":"structure", "required":["ForecastFrequency"], "members":{ "ForecastFrequency":{ "shape":"Frequency", "documentation":"

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.

" }, "ForecastDimensions":{ "shape":"ForecastDimensions", "documentation":"

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.

" }, "Featurizations":{ "shape":"Featurizations", "documentation":"

An array of featurization (transformation) information for the fields of a dataset. In this release, only a single featurization is supported.

" } }, "documentation":"

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 in your CreatePredictor request. Amazon Forecast applies the featurization to the TARGET_TIME_SERIES dataset before model training.

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

" }, "FeaturizationMethod":{ "type":"structure", "required":["FeaturizationMethodName"], "members":{ "FeaturizationMethodName":{ "shape":"FeaturizationMethodName", "documentation":"

The name of the method. In this release, \"filling\" is the only supported method.

" }, "FeaturizationMethodParameters":{ "shape":"FeaturizationMethodParameters", "documentation":"

The method parameters (key-value pairs). Specify these to override the default values. The following list shows the parameters and their valid values. Bold signifies the default value.

" } }, "documentation":"

Provides information about a method that featurizes (transforms) a dataset field. The method is part of the FeaturizationPipeline of the Featurization object. If FeaturizationMethodParameters isn't specified, Amazon Forecast uses default parameters.

For example:

{

\"FeaturizationMethodName\": \"filling\",

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

}

" }, "FeaturizationMethodName":{ "type":"string", "enum":["filling"] }, "FeaturizationMethodParameters":{ "type":"map", "key":{"shape":"ParameterKey"}, "value":{"shape":"ParameterValue"}, "max":20, "min":1 }, "FeaturizationPipeline":{ "type":"list", "member":{"shape":"FeaturizationMethod"}, "max":1, "min":1 }, "Featurizations":{ "type":"list", "member":{"shape":"Featurization"}, "max":1, "min":1 }, "FieldStatistics":{ "type":"map", "key":{"shape":"String"}, "value":{"shape":"Statistics"} }, "Filter":{ "type":"structure", "required":[ "Key", "Value", "Condition" ], "members":{ "Key":{ "shape":"String", "documentation":"

The name of the parameter to filter on.

" }, "Value":{ "shape":"Arn", "documentation":"

A valid value for Key.

" }, "Condition":{ "shape":"FilterConditionString", "documentation":"

The condition to apply.

" } }, "documentation":"

Describes a filter for choosing a subset of objects. Each filter consists of a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude, respectively, the objects that match the statement. The match statement consists of a key and a value.

" }, "FilterConditionString":{ "type":"string", "enum":[ "IS", "IS_NOT" ] }, "Filters":{ "type":"list", "member":{"shape":"Filter"} }, "ForecastDimensions":{ "type":"list", "member":{"shape":"Name"}, "max":5, "min":1 }, "ForecastExportJobSummary":{ "type":"structure", "members":{ "ForecastExportJobArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the forecast export job.

" }, "ForecastExportJobName":{ "shape":"Name", "documentation":"

The name of the forecast export job.

" }, "Destination":{ "shape":"DataDestination", "documentation":"

The path to the S3 bucket where the forecast is stored.

" }, "Status":{ "shape":"Status", "documentation":"

The status of the forecast export job. One of the following states:

The Status of the forecast export job must be ACTIVE before you can access the forecast in your Amazon S3 bucket.

" }, "Message":{ "shape":"ErrorMessage", "documentation":"

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

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the forecast export job was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

When the last successful export job finished.

" } }, "documentation":"

Provides a summary of the forecast export job properties used in the ListForecastExportJobs operation. To get the complete set of properties, call the DescribeForecastExportJob operation, and provide the listed ForecastExportJobArn.

" }, "ForecastExportJobs":{ "type":"list", "member":{"shape":"ForecastExportJobSummary"} }, "ForecastSummary":{ "type":"structure", "members":{ "ForecastArn":{ "shape":"Arn", "documentation":"

The ARN of the forecast.

" }, "ForecastName":{ "shape":"Name", "documentation":"

The name of the forecast.

" }, "PredictorArn":{ "shape":"String", "documentation":"

The ARN of the predictor used to generate the forecast.

" }, "DatasetGroupArn":{ "shape":"String", "documentation":"

The Amazon Resource Name (ARN) of the dataset group that provided the data used to train the predictor.

" }, "Status":{ "shape":"Status", "documentation":"

The status of the forecast. States include:

The Status of the forecast must be ACTIVE before you can query or export the forecast.

" }, "Message":{ "shape":"ErrorMessage", "documentation":"

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

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the forecast creation task was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

Initially, the same as CreationTime (status is CREATE_PENDING). Updated when inference (creating the forecast) starts (status changed to CREATE_IN_PROGRESS), and when inference is complete (status changed to ACTIVE) or fails (status changed to CREATE_FAILED).

" } }, "documentation":"

Provides a summary of the forecast properties used in the ListForecasts operation. To get the complete set of properties, call the DescribeForecast operation, and provide the listed ForecastArn.

" }, "Forecasts":{ "type":"list", "member":{"shape":"ForecastSummary"} }, "Frequency":{ "type":"string", "pattern":"^Y|M|W|D|H|30min|15min|10min|5min|1min$" }, "GetAccuracyMetricsRequest":{ "type":"structure", "required":["PredictorArn"], "members":{ "PredictorArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the predictor to get metrics for.

" } } }, "GetAccuracyMetricsResponse":{ "type":"structure", "members":{ "PredictorEvaluationResults":{ "shape":"PredictorEvaluationResults", "documentation":"

An array of results from evaluating the predictor.

" } } }, "HyperParameterTuningJobConfig":{ "type":"structure", "members":{ "ParameterRanges":{ "shape":"ParameterRanges", "documentation":"

Specifies the ranges of valid values for the hyperparameters.

" } }, "documentation":"

Configuration information for a hyperparameter tuning job. This object is specified in the CreatePredictor request.

A hyperparameter is a parameter that governs the model training process and is set before training starts. This is as opposed to a model parameter that is determined during training. The values of the hyperparameters have an effect on the chosen model parameters.

A hyperparameter tuning job is the process of choosing the optimum set of hyperparameter values that optimize a specified metric. This is accomplished by running many training jobs over a range of hyperparameter values. The optimum set of values is dependent on the algorithm, the training data, and the given metric objective.

" }, "InputDataConfig":{ "type":"structure", "required":["DatasetGroupArn"], "members":{ "DatasetGroupArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset group.

" }, "SupplementaryFeatures":{ "shape":"SupplementaryFeatures", "documentation":"

An array of supplementary features. For this release, the only supported feature is a holiday calendar.

" } }, "documentation":"

The data used to train a predictor. The data includes a dataset group and any supplementary features. This object is specified in the CreatePredictor request.

" }, "Integer":{"type":"integer"}, "IntegerParameterRange":{ "type":"structure", "required":[ "Name", "MaxValue", "MinValue" ], "members":{ "Name":{ "shape":"Name", "documentation":"

The name of the hyperparameter to tune.

" }, "MaxValue":{ "shape":"Integer", "documentation":"

The maximum tunable value of the hyperparameter.

" }, "MinValue":{ "shape":"Integer", "documentation":"

The minimum tunable value of the hyperparameter.

" }, "ScalingType":{ "shape":"ScalingType", "documentation":"

The scale that hyperparameter tuning uses to search the hyperparameter range. For information about choosing a hyperparameter scale, see Hyperparameter Scaling. One of the following values:

Auto

Amazon Forecast hyperparameter tuning chooses the best scale for the hyperparameter.

Linear

Hyperparameter tuning searches the values in the hyperparameter range by using a linear scale.

Logarithmic

Hyperparameter tuning searches the values in the hyperparameter range by using a logarithmic scale.

Logarithmic scaling works only for ranges that have only values greater than 0.

ReverseLogarithmic

Not supported for IntegerParameterRange.

Reverse logarithmic scaling works only for ranges that are entirely within the range 0 <= x < 1.0.

" } }, "documentation":"

Specifies an integer hyperparameter and it's range of tunable values. This object is part of the ParameterRanges object.

" }, "IntegerParameterRanges":{ "type":"list", "member":{"shape":"IntegerParameterRange"}, "max":20, "min":1 }, "InvalidInputException":{ "type":"structure", "members":{ "Message":{"shape":"ErrorMessage"} }, "documentation":"

We can't process the request because it includes an invalid value or a value that exceeds the valid range.

", "exception":true }, "InvalidNextTokenException":{ "type":"structure", "members":{ "Message":{"shape":"ErrorMessage"} }, "documentation":"

The token is not valid. Tokens expire after 24 hours.

", "exception":true }, "KMSKeyArn":{ "type":"string", "max":256, "pattern":"arn:aws:kms:.*:key/.*" }, "LimitExceededException":{ "type":"structure", "members":{ "Message":{"shape":"ErrorMessage"} }, "documentation":"

The limit on the number of requests per second has been exceeded.

", "exception":true }, "ListDatasetGroupsRequest":{ "type":"structure", "members":{ "NextToken":{ "shape":"NextToken", "documentation":"

If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.

" }, "MaxResults":{ "shape":"MaxResults", "documentation":"

The number of items to return in the response.

" } } }, "ListDatasetGroupsResponse":{ "type":"structure", "members":{ "DatasetGroups":{ "shape":"DatasetGroups", "documentation":"

An array of objects that summarize each dataset group's properties.

" }, "NextToken":{ "shape":"NextToken", "documentation":"

If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.

" } } }, "ListDatasetImportJobsRequest":{ "type":"structure", "members":{ "NextToken":{ "shape":"NextToken", "documentation":"

If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.

" }, "MaxResults":{ "shape":"MaxResults", "documentation":"

The number of items to return in the response.

" }, "Filters":{ "shape":"Filters", "documentation":"

An array of filters. For each filter, you provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude, respectively, from the list, the predictors that match the statement. The match statement consists of a key and a value. In this release, Name is the only valid key, which filters on the DatasetImportJobName property.

For example, to list all dataset import jobs named my_dataset_import_job, you would specify:

\"Filters\": [ { \"Condition\": \"IS\", \"Key\": \"Name\", \"Value\": \"my_dataset_import_job\" } ]

" } } }, "ListDatasetImportJobsResponse":{ "type":"structure", "members":{ "DatasetImportJobs":{ "shape":"DatasetImportJobs", "documentation":"

An array of objects that summarize each dataset import job's properties.

" }, "NextToken":{ "shape":"NextToken", "documentation":"

If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.

" } } }, "ListDatasetsRequest":{ "type":"structure", "members":{ "NextToken":{ "shape":"NextToken", "documentation":"

If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.

" }, "MaxResults":{ "shape":"MaxResults", "documentation":"

The number of items to return in the response.

" } } }, "ListDatasetsResponse":{ "type":"structure", "members":{ "Datasets":{ "shape":"Datasets", "documentation":"

An array of objects that summarize each dataset's properties.

" }, "NextToken":{ "shape":"NextToken", "documentation":"

If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.

" } } }, "ListForecastExportJobsRequest":{ "type":"structure", "members":{ "NextToken":{ "shape":"NextToken", "documentation":"

If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.

" }, "MaxResults":{ "shape":"MaxResults", "documentation":"

The number of items to return in the response.

" }, "Filters":{ "shape":"Filters", "documentation":"

An array of filters. For each filter, you provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude, respectively, from the list, the predictors that match the statement. The match statement consists of a key and a value. In this release, Name is the only valid key, which filters on the ForecastExportJobName property.

For example, to list all forecast export jobs named my_forecast_export_job, you would specify:

\"Filters\": [ { \"Condition\": \"IS\", \"Key\": \"Name\", \"Value\": \"my_forecast_export_job\" } ]

" } } }, "ListForecastExportJobsResponse":{ "type":"structure", "members":{ "ForecastExportJobs":{ "shape":"ForecastExportJobs", "documentation":"

An array of objects that summarize each export job's properties.

" }, "NextToken":{ "shape":"NextToken", "documentation":"

If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.

" } } }, "ListForecastsRequest":{ "type":"structure", "members":{ "NextToken":{ "shape":"NextToken", "documentation":"

If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.

" }, "MaxResults":{ "shape":"MaxResults", "documentation":"

The number of items to return in the response.

" }, "Filters":{ "shape":"Filters", "documentation":"

An array of filters. For each filter, you provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude, respectively, from the list, the predictors that match the statement. The match statement consists of a key and a value. In this release, Name is the only valid key, which filters on the ForecastName property.

For example, to list all forecasts named my_forecast, you would specify:

\"Filters\": [ { \"Condition\": \"IS\", \"Key\": \"Name\", \"Value\": \"my_forecast\" } ]

" } } }, "ListForecastsResponse":{ "type":"structure", "members":{ "Forecasts":{ "shape":"Forecasts", "documentation":"

An array of objects that summarize each forecast's properties.

" }, "NextToken":{ "shape":"NextToken", "documentation":"

If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.

" } } }, "ListPredictorsRequest":{ "type":"structure", "members":{ "NextToken":{ "shape":"NextToken", "documentation":"

If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.

" }, "MaxResults":{ "shape":"MaxResults", "documentation":"

The number of items to return in the response.

" }, "Filters":{ "shape":"Filters", "documentation":"

An array of filters. For each filter, you provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude, respectively, from the list, the predictors that match the statement. The match statement consists of a key and a value. In this release, Name is the only valid key, which filters on the PredictorName property.

For example, to list all predictors named my_predictor, you would specify:

\"Filters\": [ { \"Condition\": \"IS\", \"Key\": \"Name\", \"Value\": \"my_predictor\" } ]

" } } }, "ListPredictorsResponse":{ "type":"structure", "members":{ "Predictors":{ "shape":"Predictors", "documentation":"

An array of objects that summarize each predictor's properties.

" }, "NextToken":{ "shape":"NextToken", "documentation":"

If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.

" } } }, "MaxResults":{ "type":"integer", "max":100, "min":1 }, "Message":{"type":"string"}, "Metrics":{ "type":"structure", "members":{ "RMSE":{ "shape":"Double", "documentation":"

The root mean square error (RMSE).

" }, "WeightedQuantileLosses":{ "shape":"WeightedQuantileLosses", "documentation":"

An array of weighted quantile losses. Quantiles divide a probability distribution into regions of equal probability. The distribution in this case is the loss function.

" } }, "documentation":"

Provides metrics used to evaluate the performance of a predictor. This object is part of the WindowSummary object.

" }, "Name":{ "type":"string", "max":63, "min":1, "pattern":"^[a-zA-Z0-9][a-zA-Z0-9_]*" }, "NextToken":{ "type":"string", "max":3000, "min":1 }, "ParameterKey":{ "type":"string", "max":256, "pattern":"^[a-zA-Z0-9\\-\\_\\.\\/\\[\\]\\,\\\\]+$" }, "ParameterRanges":{ "type":"structure", "members":{ "CategoricalParameterRanges":{ "shape":"CategoricalParameterRanges", "documentation":"

Specifies the tunable range for each categorical hyperparameter.

" }, "ContinuousParameterRanges":{ "shape":"ContinuousParameterRanges", "documentation":"

Specifies the tunable range for each continuous hyperparameter.

" }, "IntegerParameterRanges":{ "shape":"IntegerParameterRanges", "documentation":"

Specifies the tunable range for each integer hyperparameter.

" } }, "documentation":"

Specifies the categorical, continuous, and integer hyperparameters, and their ranges of tunable values. The range of tunable values determines which values that a hyperparameter tuning job can choose for the specified hyperparameter. This object is part of the HyperParameterTuningJobConfig object.

" }, "ParameterValue":{ "type":"string", "max":256, "pattern":"^[a-zA-Z0-9\\-\\_\\.\\/\\[\\]\\,\\\"\\\\\\s]+$" }, "PredictorEvaluationResults":{ "type":"list", "member":{"shape":"EvaluationResult"} }, "PredictorSummary":{ "type":"structure", "members":{ "PredictorArn":{ "shape":"Arn", "documentation":"

The ARN of the predictor.

" }, "PredictorName":{ "shape":"Name", "documentation":"

The name of the predictor.

" }, "DatasetGroupArn":{ "shape":"Arn", "documentation":"

The Amazon Resource Name (ARN) of the dataset group that contains the data used to train the predictor.

" }, "Status":{ "shape":"Status", "documentation":"

The status of the predictor. States include:

The Status of the predictor must be ACTIVE before using the predictor to create a forecast.

" }, "Message":{ "shape":"ErrorMessage", "documentation":"

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

" }, "CreationTime":{ "shape":"Timestamp", "documentation":"

When the model training task was created.

" }, "LastModificationTime":{ "shape":"Timestamp", "documentation":"

Initially, the same as CreationTime (status is CREATE_PENDING). Updated when training starts (status changed to CREATE_IN_PROGRESS), and when training is complete (status changed to ACTIVE) or fails (status changed to CREATE_FAILED).

" } }, "documentation":"

Provides a summary of the predictor properties used in the ListPredictors operation. To get the complete set of properties, call the DescribePredictor operation, and provide the listed PredictorArn.

" }, "Predictors":{ "type":"list", "member":{"shape":"PredictorSummary"} }, "ResourceAlreadyExistsException":{ "type":"structure", "members":{ "Message":{"shape":"ErrorMessage"} }, "documentation":"

There is already a resource with that Amazon Resource Name (ARN). Try again with a different ARN.

", "exception":true }, "ResourceInUseException":{ "type":"structure", "members":{ "Message":{"shape":"ErrorMessage"} }, "documentation":"

The specified resource is in use.

", "exception":true }, "ResourceNotFoundException":{ "type":"structure", "members":{ "Message":{"shape":"ErrorMessage"} }, "documentation":"

We can't find a resource with that Amazon Resource Name (ARN). Check the ARN and try again.

", "exception":true }, "S3Config":{ "type":"structure", "required":[ "Path", "RoleArn" ], "members":{ "Path":{ "shape":"S3Path", "documentation":"

The path to an Amazon Simple Storage Service (Amazon S3) bucket or file(s) in an Amazon S3 bucket.

" }, "RoleArn":{ "shape":"Arn", "documentation":"

The ARN of the AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the Amazon S3 bucket or file(s).

Cross-account pass role is not allowed. If you pass a role that doesn't belong to your account, an InvalidInputException is thrown.

" }, "KMSKeyArn":{ "shape":"KMSKeyArn", "documentation":"

The Amazon Resource Name (ARN) of an AWS Key Management Service (KMS) key.

" } }, "documentation":"

The path to the file(s) in an Amazon Simple Storage Service (Amazon S3) bucket, and an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the file(s). Optionally, includes an AWS Key Management Service (KMS) key. This object is submitted in the CreateDatasetImportJob and CreateForecastExportJob requests.

" }, "S3Path":{ "type":"string", "pattern":"^s3://.+$" }, "ScalingType":{ "type":"string", "enum":[ "Auto", "Linear", "Logarithmic", "ReverseLogarithmic" ] }, "Schema":{ "type":"structure", "members":{ "Attributes":{ "shape":"SchemaAttributes", "documentation":"

An array of attributes specifying the name and type of each field in a dataset.

" } }, "documentation":"

Defines the fields of a dataset. This object is specified in the CreateDataset request.

" }, "SchemaAttribute":{ "type":"structure", "members":{ "AttributeName":{ "shape":"Name", "documentation":"

The name of the dataset field.

" }, "AttributeType":{ "shape":"AttributeType", "documentation":"

The data type of the field.

" } }, "documentation":"

An attribute of a schema, which defines a field of a dataset. A schema attribute is required for every field in a dataset. The Schema object contains an array of SchemaAttribute objects.

" }, "SchemaAttributes":{ "type":"list", "member":{"shape":"SchemaAttribute"} }, "Statistics":{ "type":"structure", "members":{ "Count":{ "shape":"Integer", "documentation":"

The number of values in the field.

" }, "CountDistinct":{ "shape":"Integer", "documentation":"

The number of distinct values in the field.

" }, "CountNull":{ "shape":"Integer", "documentation":"

The number of null values in the field.

" }, "CountNan":{ "shape":"Integer", "documentation":"

The number of NAN (not a number) values in the field.

" }, "Min":{ "shape":"String", "documentation":"

For a numeric field, the minimum value in the field.

" }, "Max":{ "shape":"String", "documentation":"

For a numeric field, the maximum value in the field.

" }, "Avg":{ "shape":"Double", "documentation":"

For a numeric field, the average value in the field.

" }, "Stddev":{ "shape":"Double", "documentation":"

For a numeric field, the standard deviation.

" } }, "documentation":"

Provides statistics for each data field imported to an Amazon Forecast dataset with the CreateDatasetImportJob operation.

" }, "Status":{ "type":"string", "max":256 }, "String":{ "type":"string", "max":256, "pattern":"^[a-zA-Z0-9\\_]+$" }, "SupplementaryFeature":{ "type":"structure", "required":[ "Name", "Value" ], "members":{ "Name":{ "shape":"Name", "documentation":"

The name of the feature. This must be \"holiday\".

" }, "Value":{ "shape":"Value", "documentation":"

One of the following 2 letter country codes:

" } }, "documentation":"

Describes a supplementary feature of a dataset group. This object is part of the InputDataConfig object.

For this release, the only supported feature is a holiday calendar. If the calendar is used, all data should belong to the same country as the calendar. For the calendar data, see http://jollyday.sourceforge.net/data.html.

" }, "SupplementaryFeatures":{ "type":"list", "member":{"shape":"SupplementaryFeature"}, "max":1, "min":1 }, "TestWindows":{ "type":"list", "member":{"shape":"WindowSummary"} }, "Timestamp":{"type":"timestamp"}, "TimestampFormat":{ "type":"string", "max":256, "pattern":"^[a-zA-Z0-9\\-\\:\\.\\,\\'\\s]+$" }, "TrainingParameters":{ "type":"map", "key":{"shape":"ParameterKey"}, "value":{"shape":"ParameterValue"}, "max":100, "min":0 }, "UpdateDatasetGroupRequest":{ "type":"structure", "required":[ "DatasetGroupArn", "DatasetArns" ], "members":{ "DatasetGroupArn":{ "shape":"Arn", "documentation":"

The ARN of the dataset group.

" }, "DatasetArns":{ "shape":"ArnList", "documentation":"

An array of Amazon Resource Names (ARNs) of the datasets to add to the dataset group.

" } } }, "UpdateDatasetGroupResponse":{ "type":"structure", "members":{ } }, "Value":{ "type":"string", "max":256, "pattern":"^[a-zA-Z0-9\\_\\-]+$" }, "Values":{ "type":"list", "member":{"shape":"Value"}, "max":20, "min":1 }, "WeightedQuantileLoss":{ "type":"structure", "members":{ "Quantile":{ "shape":"Double", "documentation":"

The quantile. Quantiles divide a probability distribution into regions of equal probability. For example, if the distribution was divided into 5 regions of equal probability, the quantiles would be 0.2, 0.4, 0.6, and 0.8.

" }, "LossValue":{ "shape":"Double", "documentation":"

The difference between the predicted value and actual value over the quantile, weighted (normalized) by dividing by the sum over all quantiles.

" } }, "documentation":"

The weighted loss value for a quantile. This object is part of the Metrics object.

" }, "WeightedQuantileLosses":{ "type":"list", "member":{"shape":"WeightedQuantileLoss"} }, "WindowSummary":{ "type":"structure", "members":{ "TestWindowStart":{ "shape":"Timestamp", "documentation":"

The timestamp that defines the start of the window.

" }, "TestWindowEnd":{ "shape":"Timestamp", "documentation":"

The timestamp that defines the end of the window.

" }, "ItemCount":{ "shape":"Integer", "documentation":"

The number of data points within the window.

" }, "EvaluationType":{ "shape":"EvaluationType", "documentation":"

The type of evaluation.

" }, "Metrics":{"shape":"Metrics"} }, "documentation":"

The metrics for a time range within the evaluation portion of a dataset. This object is part of the EvaluationResult object.

The TestWindowStart and TestWindowEnd parameters are determined by the BackTestWindowOffset parameter of the EvaluationParameters object.

" } }, "documentation":"

Provides APIs for creating and managing Amazon Forecast resources.

" }