'data.frame':   4521 obs. of  17 variables:
 $ age      : int  30 33 35 30 59 35 36 39 41 43 ...
 $ job      : chr  "unemployed" "services" "management" "management" ...
 $ marital  : chr  "married" "married" "single" "married" ...
 $ education: chr  "primary" "secondary" "tertiary" "tertiary" ...
 $ default  : chr  "no" "no" "no" "no" ...
 $ balance  : int  1787 4789 1350 1476 0 747 307 147 221 -88 ...
 $ housing  : chr  "no" "yes" "yes" "yes" ...
 $ loan     : chr  "no" "yes" "no" "yes" ...
 $ contact  : chr  "cellular" "cellular" "cellular" "unknown" ...
 $ day      : int  19 11 16 3 5 23 14 6 14 17 ...
 $ month    : chr  "oct" "may" "apr" "jun" ...
 $ duration : int  79 220 185 199 226 141 341 151 57 313 ...
 $ campaign : int  1 1 1 4 1 2 1 2 2 1 ...
 $ pdays    : int  -1 339 330 -1 -1 176 330 -1 -1 147 ...
 $ previous : int  0 4 1 0 0 3 2 0 0 2 ...
 $ poutcome : chr  "unknown" "failure" "failure" "unknown" ...
 $ y        : chr  "no" "no" "no" "no" ...

#Import data to R

bank <- read.table(file="bank.csv", sep=";", header=TRUE,stringsAsFactors = FALSE)

# character data into numeric format
bank$job <- as.numeric(as.factor(bank$job))
bank$marital <- as.numeric(as.factor(bank$marital))
bank$education <- as.numeric(as.factor(bank$education))
bank$default<- ifelse(bank$default == "yes", 1, 0)
bank$housing <- ifelse(bank$housing== "yes", 1, 0)
bank$loan<- ifelse(bank$loan== "yes", 1, 0)
bank$month <- as.numeric(as.factor(bank$month))
bank$contact <- as.numeric(as.factor(bank$contact))
bank$poutcome <- as.numeric(as.factor(bank$poutcome))
bank$y <- ifelse(bank$y== "yes", 1, 0)

# create normalization function
normalize <- function(x) {
  return ((x - min(x)) / (max(x) - min(x)))
}
#normalize the data to get rid of outliers if present in the data set
bank <- as.data.frame(lapply(bank, normalize))

set.seed(20)
bank_cluster <- kmeans(bank, 17, nstart = 20)
#plotting
bank_cluster$cluster <- as.factor(bank_cluster$cluster)
# doesn't really work
ggplot(bank, aes(bank, color = bank$cluster)) + geom_point()

#install.packages("dbscan")
library("dbscan")
db <- dbscan(bank, eps=??)
# Plot DBSCAN results
plot(db, df, main = "DBSCAN", frame = FALSE)

clusters <- hclust(dist(bank))
plot(clusters)
clusterCut <- cutree(clusters, 17) # I think number of clusters should be 17