create_cv_timeslices: Create time-slices for time-series cross-validation

In fnoorian/mltsp: Tools for machine-learning based time-series prediction

Description

Create time-slices for time-series cross-validation

Usage

create_cv_timeslices(y, initial_window, horizon = 1, fixed_window = TRUE,
  skip = 0)

Arguments

y	The input time-series
initial_window	initial number of consecutive values in each training set sample
horizon	number of consecutive values in test set sample
fixed_window	To use a fixed window of size initial_window for training every stride. If FALSE, we use the maximum possible length for the training set.
skip	How many slices are to be skipped and not used for cross-validation

Details

It is ensured that initial_windowlength + horizonlength <= length(y).

Value

Time-slices, for use with ts_crossval

References

See https://github.com/topepo/caret/blob/master/pkg/caret/R/createTimeSlices.R

fnoorian/mltsp documentation built on May 16, 2019, 1:48 p.m.