The steps of loading the libraries, registering multiprocessing, setting a working directory, reading data from a working directory, removing nondiscriminatory features from data, and setting up cross-validation parameters remain the same in the SVMBag and NBBag implementations as well. So, we do not repeat these steps in the SVMBag or NBBag code. Rather, we will focus on discussing the SVMBag or NBBag specific code:

# Setting up SVM predict function as the default svmBag$pred function has some code issue 
svm.predict <- function (object, x) 
{ 
 if (is.character(lev(object))) { 
    out <- predict(object, as.matrix(x), type = "probabilities") 
    colnames(out) <- lev(object) 
    rownames(out) <- NULL 
  } 
  else out <- predict(object, as.matrix(x))[, 1] 
  out 
} 
# setting up parameters to build svm bagging model 
bagctrl <- bagControl(fit = svmBag$fit, 
                      predict = svm.predict , 
                      aggregate = svmBag$aggregate) 
# fit the bagged svm model 
set.seed(300) 
svmbag <- train(Attrition ~ ., data = mydata, method="bag",trControl = cvcontrol, bagControl = bagctrl,allowParallel = TRUE) 
# printing the model results 
svmbag 

Bagged Model  

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

No pre-processing 
Resampling: Cross-Validated (10 fold, repeated 10 times)  
Summary of sample sizes: 1324, 1324, 1323, 1323, 1323, 1323, ...  
Resampling results: 
  Accuracy   Kappa     
  0.8777721  0.4749657 

Tuning parameter 'vars' was held constant at a value of 44