Part 1: Read the data

# reading external data and storing into a dataframe called "credit.df"
setwd("C:/Users/adi/Downloads/MLM 2019")
credit.df <- read.csv("MCICreditCardDefault.csv")

Part 2: Data table

#install.packages("data.table")
library(data.table)
credit.dt <- data.table(credit.df)
attach(credit.dt)
str(credit.dt)
## Classes 'data.table' and 'data.frame':   29601 obs. of  9 variables:
##  $ Id             : int  1 2 3 4 5 6 7 8 9 10 ...
##  $ CreditLimit    : int  20000 120000 90000 50000 50000 50000 500000 100000 140000 20000 ...
##  $ Male           : int  0 0 0 0 1 1 1 0 0 1 ...
##  $ Education      : int  2 2 2 2 2 1 1 2 3 3 ...
##  $ MaritalStatus  : int  1 2 2 1 1 2 2 2 1 2 ...
##  $ Age            : int  24 26 34 37 57 37 29 23 28 35 ...
##  $ BillOutstanding: int  3913 2682 29239 46990 8617 64400 367965 11876 11285 0 ...
##  $ LastPayment    : int  0 0 1518 2000 2000 2500 55000 380 3329 0 ...
##  $ Default        : int  1 1 0 0 0 0 0 0 0 0 ...
##  - attr(*, ".internal.selfref")=<externalptr>

#dimensions

# dimension of the data table
dim(credit.dt)
## [1] 29601     9

#Converting Data Type Structure

#credit.dt[, Id := as.factor(Id)]
# convert 'Male' as a factor
credit.dt[, Male := as.factor(Male)]
# convert 'Education' as a factor
credit.dt[, Education := as.factor(Education)]
# convert 'MaritalStatus' as a factor
credit.dt[, MaritalStatus := as.factor(MaritalStatus)]
# convert 'Default' as a factor
credit.dt[, Default := as.factor(Default)]
# Changing the lavels of 'Default' variable
levels(credit.dt$Default) <- c("No","Yes")
# verifying conversion
str(credit.dt)
## Classes 'data.table' and 'data.frame':   29601 obs. of  9 variables:
##  $ Id             : int  1 2 3 4 5 6 7 8 9 10 ...
##  $ CreditLimit    : int  20000 120000 90000 50000 50000 50000 500000 100000 140000 20000 ...
##  $ Male           : Factor w/ 2 levels "0","1": 1 1 1 1 2 2 2 1 1 2 ...
##  $ Education      : Factor w/ 4 levels "1","2","3","4": 2 2 2 2 2 1 1 2 3 3 ...
##  $ MaritalStatus  : Factor w/ 3 levels "1","2","3": 1 2 2 1 1 2 2 2 1 2 ...
##  $ Age            : int  24 26 34 37 57 37 29 23 28 35 ...
##  $ BillOutstanding: int  3913 2682 29239 46990 8617 64400 367965 11876 11285 0 ...
##  $ LastPayment    : int  0 0 1518 2000 2000 2500 55000 380 3329 0 ...
##  $ Default        : Factor w/ 2 levels "No","Yes": 2 2 1 1 1 1 1 1 1 1 ...
##  - attr(*, ".internal.selfref")=<externalptr>
# levels of the target variable
levels(credit.dt$Default)
## [1] "No"  "Yes"

#setting the levels

# ordering the levels
credit.dt$Default <- ordered(credit.dt$Default, levels = c("Yes", "No"))
require('ggplot2')
## Loading required package: ggplot2
# verifying the new order of levels
levels(credit.dt$Default)
## [1] "Yes" "No"

#splitting the Data into Train & Test Set

library(caret)
## Loading required package: lattice
# data partition
set.seed(2341)
trainIndex <- createDataPartition(credit.dt$Default, p = 0.80, list = FALSE)

80% training data

trainData.dt <- credit.dt[trainIndex, ]

20% testing data

testData.dt <- credit.dt[-trainIndex, ]

dimension of training dataset

dim(trainData.dt)
## [1] 23681     9

dimension of testing dataset

dim(testData.dt)
## [1] 5920    9

proportion of defaulters in training dataset

round(prop.table(table(trainData.dt$Default))*100,2)
## 
##   Yes    No 
## 22.31 77.69

proportion of defaulters in test dataset

round(prop.table(table(testData.dt$Default))*100,2)
## 
##   Yes    No 
## 22.31 77.69

#kNN Analysis

# Set control parameters
trctrl <- trainControl(method = "repeatedcv",
                       number = 10,
                       repeats = 3)
set.seed(3333)
#install.packages('e1071', dependencies=TRUE)

# Run kNN Classifier in package caret
knn_fit  <- train(Default ~ ., 
                  data = trainData.dt,
                  method = "knn",
                  trControl = trctrl,
                  preProcess = c("center", "scale"),
                  tuneLength = 10)
# kNN model summary
knn_fit 
## k-Nearest Neighbors 
## 
## 23681 samples
##     8 predictor
##     2 classes: 'Yes', 'No' 
## 
## Pre-processing: centered (11), scaled (11) 
## Resampling: Cross-Validated (10 fold, repeated 3 times) 
## Summary of sample sizes: 21313, 21314, 21313, 21313, 21312, 21314, ... 
## Resampling results across tuning parameters:
## 
##   k   Accuracy   Kappa     
##    5  0.7327261  0.04264164
##    7  0.7467312  0.04021462
##    9  0.7529805  0.02928387
##   11  0.7581885  0.02459777
##   13  0.7627492  0.02378213
##   15  0.7662680  0.02270087
##   17  0.7686751  0.01919706
##   19  0.7708850  0.01794406
##   21  0.7722223  0.01641531
##   23  0.7731231  0.01487522
## 
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was k = 23.
#memory.limit()
#gc()

#Testing the Model

kNNPred <- predict(knn_fit, testData.dt, type = "raw")
# confusion matrix
table(Predicted = kNNPred, Actual = testData.dt$Default)
##          Actual
## Predicted  Yes   No
##       Yes   28   48
##       No  1293 4551

loading the package

library(ROCR)
## Loading required package: gplots
## 
## Attaching package: 'gplots'
## The following object is masked from 'package:stats':
## 
##     lowess

#Testing the Model

kNNPred <- predict(knn_fit, testData.dt,type = "raw")
kNNPredObj <- prediction(as.numeric(kNNPred),as.numeric(testData.dt$Default))
kNNPerfObj <- performance(kNNPredObj, "tpr","fpr")

plotting ROC curve

plot(kNNPerfObj,main = "ROC Curve",col = 2,lwd = 2)
abline(a = 0,b = 1,lwd = 2,lty = 3,col = "black")

area under curve

aucLR <- performance(kNNPredObj, measure = "auc")
aucLR <- aucLR@y.values[[1]]
aucLR
## [1] 0.5053795