#------------------
# 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 - Univariate analysis - Binning
#--------------------------------------------------

#variable
x <- train$BUSAGE

#graph layout
def.par <- par(no.readonly = TRUE)
layout(mat=rbind(1:2,3:4))

#equal width
table(discretize(x, categories=3))
hist(x, breaks=20, main="Equal Width", xlab="BUSAGE")
abline(v=discretize(x, categories=3, onlycuts=TRUE), col="red")

#equal frequency
table(discretize(x, "frequency", categories=3))
hist(x, breaks=20, main="Equal Frequency", xlab="BUSAGE")
abline(v=discretize(x, method="frequency", categories=3, onlycuts=TRUE), col="red")


#user-specified
table(discretize(x, "fixed", categories =c(-Inf, 100, Inf), labels=c("low", "high")))
hist(x, breaks=20, main="Fixed", xlab="BUSAGE")
abline(v=discretize(x, method="fixed", c(-Inf, 100, Inf) , onlycuts=TRUE), col="red")

#log
y <- as.factor(floor(log1p(x)))
plot(y, main="Log Normal", xlab="BUSAGE")

#reset graph
par(def.par)