Package software.amazon.awssdk.services.forecast.model

Interface EvaluationParameters.Builder

All Superinterfaces:
Buildable, CopyableBuilder<EvaluationParameters.Builder,EvaluationParameters>, SdkBuilder<EvaluationParameters.Builder,EvaluationParameters>, SdkPojo
Enclosing class:
EvaluationParameters
public static interface EvaluationParameters.Builder extends SdkPojo, CopyableBuilder<EvaluationParameters.Builder,EvaluationParameters>

  • Method Details

    • numberOfBacktestWindows

      EvaluationParameters.Builder numberOfBacktestWindows(Integer numberOfBacktestWindows)

      The number of times to split the input data. The default is 1. Valid values are 1 through 5.

      Parameters:
      numberOfBacktestWindows - The number of times to split the input data. The default is 1. Valid values are 1 through 5.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • backTestWindowOffset

      EvaluationParameters.Builder backTestWindowOffset(Integer backTestWindowOffset)

      The point from the end of the dataset where you want to split the data for model training and testing (evaluation). Specify the value as the number of data points. The default is the value of the forecast horizon. BackTestWindowOffset can be used to mimic a past virtual forecast start date. This value must be greater than or equal to the forecast horizon and less than half of the TARGET_TIME_SERIES dataset length.

      ForecastHorizon <= BackTestWindowOffset < 1/2 * TARGET_TIME_SERIES dataset length

      Parameters:
      backTestWindowOffset - The point from the end of the dataset where you want to split the data for model training and testing (evaluation). Specify the value as the number of data points. The default is the value of the forecast horizon. BackTestWindowOffset can be used to mimic a past virtual forecast start date. This value must be greater than or equal to the forecast horizon and less than half of the TARGET_TIME_SERIES dataset length.

      ForecastHorizon <= BackTestWindowOffset < 1/2 * TARGET_TIME_SERIES dataset length

      Returns:
      Returns a reference to this object so that method calls can be chained together.