# loading required libraries and registering multiple cores to enable parallel processing 
library(doMC) 
library(caret) 
registerDoMC(cores=4) 
# setting the working directory and reading the dataset 
setwd("~/Desktop/chapter 15") 
mydata <- read.csv("WA_Fn-UseC_-HR-Employee-Attrition.csv") 
# removing the non-discriminatory features from the dataset as identified during EDA step 
mydata$EmployeeNumber=mydata$Over18=mydata$EmployeeCount=mydata$StandardHours = NULL 
# setting the seed for reproducibility 
set.seed(10000) 
# setting the cross validation parameters 
fitControl = trainControl(method="repeatedcv", number=10,repeats=10) 
# creating the caret model with random forest algorithm 
caretmodel = train(Attrition~., data=mydata, method="rf", trControl=fitControl, verbose=F) 
# printing the model summary 
caretmodel 

This will result in the following output:

Random Forest  

1470 samples 
  30 predictors 
   2 classes: 'No', 'Yes'  

No pre-processing 
Resampling: Cross-Validated (10 fold, repeated 10 times)  
Summary of sample sizes: 1323, 1323, 1324, 1323, 1324, 1322, ...  
Resampling results across tuning parameters: 

  mtry  Accuracy   Kappa     
   2    0.8485765  0.1014859 
  23    0.8608271  0.2876406 
  44    0.8572929  0.2923997 

Accuracy was used to select the optimal model using the largest value. 
The final value used for the model was mtry = 23. 

We see the best random forest model achieved a better accuracy of 86% compared to KNN's 84%.