Skip to content

Create Forecast

forecastservice_create_forecast R Documentation

Creates a forecast for each item in the TARGET_TIME_SERIES dataset that was used to train the predictor

Description

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) bucket, use the create_forecast_export_job operation.

The range of the forecast is determined by the ForecastHorizon value, which you specify in the create_predictor request. When you query a forecast, you can request a specific date range within the forecast.

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

The forecasts generated by Amazon Forecast are in the same time zone 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 describe_forecast operation to get the status.

By default, a forecast includes predictions for every item (item_id) in the dataset group that was used to train the predictor. However, you can use the TimeSeriesSelector object to generate a forecast on a subset of time series. Forecast creation is skipped for any time series that you specify that are not in the input dataset. The forecast export file will not contain these time series or their forecasted values.

Usage

forecastservice_create_forecast(ForecastName, PredictorArn,
  ForecastTypes, Tags, TimeSeriesSelector)

Arguments

ForecastName

[required] A name for the forecast.

PredictorArn

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

ForecastTypes

The quantiles at which probabilistic forecasts are generated. You can currently specify up to 5 quantiles per forecast. Accepted values include ⁠0.01 to 0.99⁠ (increments of .01 only) and mean. The mean forecast is different from the median (0.50) when the distribution is not symmetric (for example, Beta and Negative Binomial).

The default quantiles are the quantiles you specified during predictor creation. If you didn't specify quantiles, the default values are ⁠["0.1", "0.5", "0.9"]⁠.

Tags

The optional metadata that you apply to the forecast to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define.

The following basic restrictions apply to tags:

  • Maximum number of tags per resource - 50.

  • For each resource, each tag key must be unique, and each tag key can have only one value.

  • Maximum key length - 128 Unicode characters in UTF-8.

  • Maximum value length - 256 Unicode characters in UTF-8.

  • If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @.

  • Tag keys and values are case sensitive.

  • Do not use ⁠aws:⁠, ⁠AWS:⁠, or any upper or lowercase combination of such as a prefix for keys as it is reserved for Amazon Web Services use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.

TimeSeriesSelector

Defines the set of time series that are used to create the forecasts in a TimeSeriesIdentifiers object.

The TimeSeriesIdentifiers object needs the following information:

  • DataSource

  • Format

  • Schema

Value

A list with the following syntax: 

list(
  ForecastArn = "string"
)

Request syntax

svc$create_forecast(
  ForecastName = "string",
  PredictorArn = "string",
  ForecastTypes = list(
    "string"
  ),
  Tags = list(
    list(
      Key = "string",
      Value = "string"
    )
  ),
  TimeSeriesSelector = list(
    TimeSeriesIdentifiers = list(
      DataSource = list(
        S3Config = list(
          Path = "string",
          RoleArn = "string",
          KMSKeyArn = "string"
        )
      ),
      Schema = list(
        Attributes = list(
          list(
            AttributeName = "string",
            AttributeType = "string"|"integer"|"float"|"timestamp"|"geolocation"
          )
        )
      ),
      Format = "string"
    )
  )
)