partition_data: Partition data in train and test set

In andreaskapou/mpgex: Methylation Profiles predict Gene Expression

Description

partition_data partition data randomly in train and test sets.

Usage

partition_data(x, y, train_ind = NULL, train_perc = 0.7)

Arguments

x	Input / Independent variables
y	Dependent variables
train_ind	Index of traininig data, if NULL a random one is generated.
train_perc	Percentage of training data when partitioning.

Value

A list containing the train, test data and index of training data.

Examples

x <- matrix(c(-20, 0, 15, 20, 20, 10, 4, 5), ncol=2)
y <- c(2, 5, 0, 8)
data <- partition_data(x, y)

##
x <- matrix(c(-20, 0, 15, 20, 20, 10, 4, 5), ncol=2)
y <- c(2, 5, 0, 8)
train_ind <- c(1,4)
data <- partition_data(x, y, train_ind)

andreaskapou/mpgex documentation built on Nov. 25, 2017, 8:08 a.m.