classification problem, use logistic regression, cross validation, test accuracy using R

First, need to split the dataset into training set 60%, validation set 20% and test set 20%. Then start with 1 most important predictor (predictor 5) model logistic regression, use, validation set to measure error, also do 10 k-fold cross validation to measure error , and use test set to get model accuracy. I know utilize all predictor in this dataset should get most accuracy and least error. I just need someone to do 1 model, and then I can just use same method to do the rest models. Be aware the response variable are binary 0 and 1, it is a classification problem. The dataset is attached you need to first use mydata <- [login to view URL](mydata) mydata <- mydata[[login to view URL](mydata), ] to make this data work