Error in eval(predvars, data, env) : object ‘Rm’ not found

dataset = read.csv('dataset/housing.header.binary.txt')
dataset1 = dataset[6] #higest positive correlation
dataset2 = dataset[13] #lowest negative correlation
dependentVal= dataset[14] #dependent value
new_dataset = cbind(dataset1,dataset2, dependentVal) # new matrix 

#split dataset
#install.packages('caTools')
library(caTools)

set.seed(123) #this is needed to garantee that every run will produce the same output
split = sample.split(new_dataset, SplitRatio = 0.75)
train_set = subset(new_dataset, split == TRUE)
test_set = subset(new_dataset, split == FALSE)


#Fitting Decision Tree to training set
install.packages('rpart')
library(rpart)
classifier = rpart(formula = Medv ~ Rm + Lstat,
                   data = train_set)

#predicting the test set results
y_pred = predict(classifier, newdata = test_set[3], type ='class')

I want to predict column 3 of test_set, but I keep getting

Error in eval(predvars, data, env) : object ‘Rm’ not found

Even though I specify test_set[3] not test_set[1] which contain Rm

The column names are as follows: Rm, Lstat, and Medv.

test_set[3] and test_set[2] give the same following error:

Error in eval(predvars, data, env) : object Rm not found

and test_set[1] gives:

Error in eval(predvars, data, env) : object ‘Lstat’ not found

I have tried the following:

1. names(test_set) <- c('Rm', 'Lstat','Medv'): I renamed explicitly.
2. is.data.frame(test_set): i checked if test_set is a dataframe.