split_train_test {ssr}R Documentation

Splits a data frame into train and test sets.

Description

Utility function to randomly split a data frame into train and test sets.

Usage

split_train_test(df, pctTrain)

Arguments

df

a data frame.

pctTrain

numeric value that specifies the percentage of rows to be included in the train set. The remaining rows are added to the test set.

Value

a list with the first element being the train set and the second element the test set.

Examples

set.seed(1234)

dataset <- friedman1

nrow(dataset) # print number of rows

split1 <- split_train_test(dataset, pctTrain = 70) # select 70% for training

nrow(split1$trainset) # number of rows of the train set

nrow(split1$testset) # number of rows of the test set

head(split1$trainset) # display first rows of train set


[Package ssr version 0.1.1 Index]