partition: Partition Data

In liver: Toolkit and Datasets for Data Science

Partition Data

Description

Randomly partitions data into two or more subsets according to the supplied ratios. Optionally, stratified partitioning can be performed using a categorical or numerical variable.

Usage

partition(data, ratio = c(0.7, 0.3), strata = NULL, set.seed = NULL)

Arguments

data	An (n \times p) matrix or data.frame.
ratio	A numeric vector specifying the proportions of observations assigned to the partitions.
strata	Optional variable used for stratified partitioning. For categorical variables, the proportions of the levels are approximately preserved across partitions. For numerical variables, observations are distributed across partitions according to their ordered values.
set.seed	A single value, interpreted as an integer, or NULL.

Value

A list containing the data partitions.

Author(s)

Reza Mohammadi [e-mail]

Examples

data(iris)

parts <- partition(iris, ratio = c(0.7, 0.3), set.seed = 42)
sapply(parts, nrow)

liver documentation built on Sept. 10, 2026, 5:09 p.m.