Explain with a case study how to implement logistic regression using R.

We will read the dataset which is a bank data

bank <- read.csv(file.choose(),sep=";") # Choose the bank-full Data set

sum(is.na(bank))

bank <- na.omit(bank)

colnames(bank)

Now we will create dummy variables for those column having categories

#created dummy var

install.packages("dummies")

library("dummies")

bank.new <- dummy.data.frame(bank, sep = ".")

dummy(bank$job, sep = ".")

Now we will perform splitting for training and testing

#splitted train and test

library(caTools)

set.seed(123)

split = sample.split(bank$y, SplitRatio = 0.75)

training_set = subset(bank, split == TRUE)

test_set = subset(bank, split == FALSE)

Now we will prepare the model

# Preparing a model

classifier = glm(formula = y ~ .,

                 family = binomial,

                 data = training_set)

Classifier

Now we will predict the test data

#predict y of test set

pred1 <- predict(classifier,test_set)

pred1

y_pred = ifelse(pred1 > 0.5, 1, 0)

summary(classifier)

Now we will evaluate the model

#conf matrix

cm = table(test_set[, 17], y_pred > 0.5)

cm

#accuracy

Accuracy<-sum(diag(cm)/sum(cm))

Accuracy

Now we can plot the ROC curve to see the rate of misclassification

#ROC

library(ROCR)

data(ROCR.simple)

pred <- prediction( ROCR.simple$predictions, ROCR.simple$labels)

perf <- performance(pred,"tpr","fpr")

plot(perf)

#AUC

auc.tmp <- performance(pred,"auc"); auc <- as.numeric(auc.tmp@y.values)