#------------------
# Data Preparation
#------------------

#Read datasets
#Download the data from http://www.saedsayad.com/datasets/CreditData.zip
train <- read.csv("Credit_train.csv")
test <- read.csv("Credit_test.csv")

#Rows and Cols
dim(train)
dim(test)

#Columns name
colnames(train)
colnames(test)

#Show  
head(train)
head(test)

#-------------------------------------------------------------------
# Data Exploration - Bivariate analysis - Categorical and Numerical
#-------------------------------------------------------------------

#DEFAULT and MAXLINEUTIL
boxplot(MAXLINEUTIL~DEFAULT, data=train, main="Maximum number of lines being utilized" 
        , sub="train", col="darkgreen", xlab="DEFAULT", ylab="MAXLINEUTIL")
boxplot(MAXLINEUTIL~DEFAULT, data=test, main="Maximum number of lines being utilized" 
        , sub="test", col="brown", xlab="DEFAULT", ylab="MAXLINEUTIL")

#DEFAULT and DAYSDELQ
boxplot(DAYSDELQ~DEFAULT, data=train, main="Number of delinquent days" 
        , sub="train", col="darkgreen", xlab="DEFAULT", ylab="DAYSDELQ")
boxplot(DAYSDELQ~DEFAULT, data=test, main="Number of delinquent days" 
        , sub="test", col="brown", xlab="DEFAULT", ylab="DAYSDELQ")

#DEFAULT and TOTACBAL
boxplot(TOTACBAL~DEFAULT, data=train, main="Total balance of business account" 
        , sub="train", col="darkgreen", xlab="DEFAULT", ylab="TOTACBAL")
boxplot(TOTACBAL~DEFAULT, data=test, main="Total balance of business account" 
        , sub="test", col="brown", xlab="DEFAULT", ylab="TOTACBAL")



#Z-test for two variables - DEFAULT and DAYSDELQ
train <- na.omit(train)
a <- subset(train$DAYSDELQ,train$DEFAULT=='Y')
b <- subset(train$DAYSDELQ,train$DEFAULT=='N')
n1 <- length(a)
n2 <- length(b)
z <- (mean(a) - mean(b)) / (sqrt(var(a)/n1 + var(b)/n2))
pz <- 1-(pnorm(abs(z))-0.5)*2


#ANOVA - BUSTYPE and TOTACBAL 
fit <- aov(train$TOTACBAL ~ train$BUSTYPE)
summary(fit)