Class: Aws::ForecastService::Types::EvaluationParameters

Inherits:

Struct

• Object
• Struct
• Aws::ForecastService::Types::EvaluationParameters

Defined in:

(unknown)

Overview

Note:

When passing EvaluationParameters as input to an Aws::Client method, you can use a vanilla Hash:

{
  number_of_backtest_windows: 1,
  back_test_window_offset: 1,
}

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 but you can override them in the CreatePredictor request.

Returned by:

• CreatePredictorRequest#evaluation_parameters
• DescribePredictorResponse#evaluation_parameters

See Also:

• AWS API Documentation

Instance Attribute Summary

• #back_test_window_offset ⇒ Integer

  The point from the end of the dataset where you want to split the data for model training and testing (evaluation).

• #number_of_backtest_windows ⇒ Integer

  The number of times to split the input data.

Instance Attribute Details

#back_test_window_offset ⇒ Integer

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:

• (Integer) —

  The point from the end of the dataset where you want to split the data for model training and testing (evaluation).

#number_of_backtest_windows ⇒ Integer

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

Returns:

• (Integer) —

  The number of times to split the input data.