roll: Generate rolling windows

In jrnold/resamplr: Resampling methods

Description

Generate resample objects of rolling windows over elements of a data frame.

Usage

roll(data, ...)

## S3 method for class 'data.frame'
roll(data, width = 1L, align = c("left", "right",
  "center"), partial = TRUE, indices = NULL, from = 1L, to = n,
  by = 1L, offsets = NULL, ...)

## S3 method for class 'grouped_df'
roll(data, width = 1L, align = c("left", "right",
  "center"), partial = TRUE, indices = NULL, from = 1L, to = n,
  by = 1L, offsets = NULL, ...)

Arguments

data	A data frame
...	Arguments passed to methods
width	The window width.
align	Is the window left-aligned, right-aligned, or centered relative to the reference index of the window.
partial	logical or numeric. If FALSE all indexes of a rolling window must be within the rows (or groups) of data. If TRUE, then the subset of indexes that are in range are used. A numeric argument to partial can be used to determine the minimal window size for partial windows.
indices, from, to, by	The indices at which to generate windows. If indices is non-NULL, then it is used. Otherwise, the indices are generated from seq(from, to, by).
offsets	An integer vector or NULL. If non-NULL, then it is the offsets of elements in the window relative to the reference index of the window; 0 is the reference index, negative numbers are indices before the index, while positive numbers are after the index. If NULL, the offsets are generated from the width and align arguments.

Value

A data frame with rows equal to the number of windows and the following columns:

train

A list of resample objects. Training sets.

test

A list of resample objects. Test sets.

.id

An integer vector of identifiers

Methods (by class)

• data.frame: Generate windows from the rows of the data frame.

• grouped_df: Generate windows from the groups of the data frame.

jrnold/resamplr documentation built on May 20, 2019, 1:05 a.m.