How to split data into training/testing sets using sample function

Question

How to split data into training/testing sets using sample function

I've quite recently started utilizing R and I don't know how to incorporate my dataset with the following example code:

sample(x, size, replace = FALSE, prob = NULL)

I have a dataset that I need to place into a training (75%) and testing (25%) set. I don't know what information I should place into the x and size? Is x the dataset file, and size what number of samples I have?

sample split r-language

3 years ago by vishaljlf39

3 Answers

Login / Signup to Answer the Question.

Login Signup

**espadacoder11** · Answer 1 · 2021-07-07T13:10:05

There are numerous approaches to achieve data partitioning. For a more complete approach take a look at the createDataPartition function in the caTools package.

Here is a simple example:



data(mtcars)



## 75% of the sample size

smp_size <- floor(0.75 * nrow(mtcars))



## set the seed to make your partition reproducible

set.seed(123)

train_ind <- sample(seq_len(nrow(mtcars)), size = smp_size)



train <- mtcars[train_ind, ]

test <- mtcars[-train_ind, ]

**sandhya6gczb** · Answer 2 · 2021-07-08T14:21:26

I would use dplyr for this, makes it super simple. It does require an id variable in your data set, which is a good idea anyway, not only for creating sets but also for traceability during your project. Add it if doesn't contain already.



mtcars$id <- 1:nrow(mtcars)

train <- mtcars %>% dplyr::sample_frac(.75)

test  <- dplyr::anti_join(mtcars, train, by = 'id')

**pankajshivnani123** · Answer 3 · 2021-07-12T11:55:38

It can be easily done by:



set.seed(101) # Set Seed so that same sample can be reproduced in future also

# Now Selecting 75% of data as sample from total 'n' rows of the data  

sample <- sample.int(n = nrow(data), size = floor(.75*nrow(data)), replace = F)

train <- data[sample, ]

test  <- data[-sample, ]

By using caTools package:

require(caTools)

set.seed(101) 

sample = sample.split(data$anycolumn, SplitRatio = .75)

train = subset(data, sample == TRUE)

test  = subset(data, sample == FALSE)

C TUTORIAL

C PROGRAMS

INTERVIEW TESTS

EXECUTE CODE

C++ TUTORIAL

C++ PROGRAMS

INTERVIEW TESTS

EXECUTE CODE

PYTHON TUTORIAL

PYTHON HOW TOS

INTERVIEW TESTS

EXECUTE CODE

JAVA TUTORIAL

JAVA CODE EXAMPLES

SPRING TUTORIAL

MORE IN JAVA

COMPUTER ARCHITECTURE

COMPUTER NETWORK

OPERATING SYSTEM

DBMS & SQL

PL/SQL

MongoDB

EXECUTE SQL

ANDROID DEVELOPMENT

GO LANGUAGE

LINUX

DOCKER

HTML TAGS (A to Z)

CSS REFERENCES

SASS/SCSS

KOTLIN

GAME DEVELOPMENT

PHP

GIT GUIDE

JAVASCRIPT

ADVANCED DSA

How to split data into training/testing sets using sample function

3 Answers

Login / Signup to Answer the Question.