#  The data is related with direct marketing campaigns (phone calls) of a Portuguese banking institution. 
#  The classification goal is to predict if the client will subscribe a term deposit (variable y).
#
# https://archive.ics.uci.edu/ml/datasets/Bank+Marketing#
#
# Input variables:
# 1 - age (numeric)
# 2 - job : type of job (categorical: "admin.","unknown","unemployed","management","housemaid",
#                                     "entrepreneur","student","blue-collar","self-employed",
#                                     "retired","technician","services") 
# 3 - marital : marital status (categorical: "married","divorced","single"; 
#     note: "divorced" means divorced or widowed)
# 4 - education (categorical: "unknown","secondary","primary","tertiary")
# 5 - default: has credit in default? (binary: "yes","no")
# 6 - balance: average yearly balance, in euros (numeric) 
# 7 - housing: has housing loan? (binary: "yes","no")
# 8 - loan: has personal loan? (binary: "yes","no")
# 
# related with the last contact of the current campaign:
# 9 - contact: contact communication type (categorical: "unknown","telephone","cellular") 
# 10 - day: last contact day of the month (numeric)
# 11 - month: last contact month of year (categorical: "jan", "feb", "mar", ..., "nov", "dec")
# 12 - duration: last contact duration, in seconds (numeric)
# 
# other attributes:
# 13 - campaign: number of contacts performed during this campaign and for this client 
#      (numeric, includes last contact)
# 14 - pdays: number of days that passed by after the client was last contacted from a 
#      previous campaign (numeric, -1 means client was not previously contacted)
# 15 - previous: number of contacts performed before this campaign and for this client (numeric)
# 16 - poutcome: outcome of the previous marketing campaign 
#      (categorical: "unknown","other","failure","success")
#
# Output variable (desired target):
# 17 - y - has the client subscribed a term deposit? (binary: "yes","no")

bank = read.csv("bank.csv",sep=";")


summary(bank)


table = rbind(c(mean(bank$balance<0),mean(bank$balance==0)),
c(mean(bank$balance[bank$y=="yes"]<0),mean(bank$balance[bank$y=="yes"]==0)),
c(mean(bank$balance[bank$y=="no"]<0),mean(bank$balance[bank$y=="no"]==0)))

rownames(table) = c("all","yes","no")
colnames(table) = c("negative","zero")
round(table,3)

par(mfrow=c(1,2))
boxplot(balance~y,data=bank)
boxplot(balance~y,data=bank,outline=FALSE)

tab=table(bank$job,bank$y)
round(tab/apply(tab,1,sum),3)
round(t(rbind(tab[,1]/sum(tab[,1]),tab[,2]/sum(tab[,2]))),3)

tab=table(bank$marital,bank$y)
round(tab/apply(tab,1,sum),3)
round(t(rbind(tab[,1]/sum(tab[,1]),tab[,2]/sum(tab[,2]))),3)

tab = table(bank$education,bank$y)
round(tab/apply(tab,1,sum),3)
round(t(rbind(tab[,1]/sum(tab[,1]),tab[,2]/sum(tab[,2]))),3)

tab=table(bank$housing,bank$y)
round(tab/apply(tab,1,sum),3)
round(t(rbind(tab[,1]/sum(tab[,1]),tab[,2]/sum(tab[,2]))),3)

tab=table(bank$loan,bank$y)
round(tab/apply(tab,1,sum),3)
round(t(rbind(tab[,1]/sum(tab[,1]),tab[,2]/sum(tab[,2]))),3)

tab=table(bank$contact,bank$y)
round(tab/apply(tab,1,sum),3)
round(t(rbind(tab[,1]/sum(tab[,1]),tab[,2]/sum(tab[,2]))),3)

tab=table(bank$month,bank$y)
round(tab/apply(tab,1,sum),3)
round(t(rbind(tab[,1]/sum(tab[,1]),tab[,2]/sum(tab[,2]))),3)

tab=table(bank$campaign,bank$y)
plot(round(tab/apply(tab,1,sum),3))
round(t(rbind(tab[,1]/sum(tab[,1]),tab[,2]/sum(tab[,2]))),3)






glout = glm(y~.,data=bank,family=binomial)

summary(glout)

library("MASS")

stepout = stepAIC(glout)

stepout

length(coef(stepout))

yhat1 = round(glout$fitted.values)

yhat2 = round(stepout$fitted.values)

n = nrow(bank)

y = rep(0,n)

y[bank$y=="yes"]=1

mean(yhat1 == y)


mean(yhat2 == y)