TSrepr (version 1.1.0)

repr_windowing: Windowing of time series

Description

The repr_windowing computes representations from windows of a vector.

Usage

repr_windowing(x, win_size, func = NULL, args = NULL)

Arguments

x

the numeric vector (time series)

win_size

the length of the window

func

the function for representation computation. For example repr_feaclip or repr_trend.

args

the list of additional arguments to the func (representation computation function). The args list must be named.

Value

the numeric vector

Details

This function applies specified representation method (function) to every non-overlapping window (subsequence, piece) of a time series.

References

Laurinec P, and Lucka M (2018) Interpretable multiple data streams clustering with clipped streams representation for the improvement of electricity consumption forecasting. Data Mining and Knowledge Discovery. Springer. DOI: 10.1007/s10618-018-0598-2

See Also

repr_paa, repr_matrix

Examples

# NOT RUN {
# func without arguments
repr_windowing(rnorm(48), win_size = 24, func = repr_feaclip)

# func with arguments
repr_windowing(rnorm(48), win_size = 24, func = repr_featrend,
 args = list(func = maxC, order = 2, pieces = 2))

# }