splitting a given dataset into train and test

data_split.R

# Method 1: Easiest and does not require any library
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, ]

# Method 2: 
# This gist is derived from a post that I had published on wordpress few years ago. 
# reference: https://edumine.wordpress.com/2015/04/06/splitting-a-data-frame-into-training-and-testing-sets-in-r/
# Reference: https://stackoverflow.com/questions/17200114/how-to-split-data-into-training-testing-sets-using-sample-function

# Load data
iris.data<- read.csv(url("http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"),
                          header = FALSE, sep = ",",
                          col.names = c("sepal.length","sepal.width","petal.length","petal.width",    
                                        "species")
                          )
# divide the data into train and test
# reference: https://edumine.wordpress.com/2015/04/06/splitting-a-data-frame-into-training-and-testing-sets-in-r/

# set a seed value for reproducibility
set.seed(1208)
library(caTools)

# Make sure that the data set is shuffled and that you have the same ratio between species in your training and test sets. You use the sample() function to take a sample with a size that is set as the number of rows of the Iris data set which is 150.
# Also you will create a new vector variable in the Iris dataset that will have the TRUE and FALSE values basis on which you will later split the dataset into training and test.
# By using the sample.split() you are actually creating a vector with two values TRUE and FALSE. By setting the SplitRatio to 0.7, you are splitting the original Iris dataset of 150 rows to 70% training and 30% testing data.

iris.data$spl<- sample.split(iris.data, SplitRatio = 0.7) 

# where spl== TRUE means to add only those rows that have value true for spl in the training dataframe
iris.data.train<- subset(iris.data, iris.data$spl==TRUE) 
iris.data.test<- subset(iris.data, iris.data$spl==FALSE)

# drop the spl column from both training and test set
iris.data.train$spl<- NULL
iris.data.test$spl<- NULL