D<-read.csv("cars2.csv", header = TRUE, row.names=1)
dim(D)
head(D)

apply(D , 2, mean)
apply(D , 2, var)

D.sd<-scale(D)
head(D.sd)

## AHC

hc.sing<-hclust(dist(D.sd), method="single")
plot(hc.sing, cex=0.5)

hc.ave<-hclust(dist(D.sd), method="average")
plot(hc.ave, cex=0.5)

hc.com<-hclust(dist(D.sd), method="complete")
plot(hc.com, cex=0.5)

library(cluster)
hc.ward<-agnes(D.sd, method="ward")
pltree(hc.ward, cex=0.5, hang = -1)

cl3<-cutree(hc.ward, 3)
#cl5<-cutree(hc.ward, 5)

table(cl3)
labels<-row.names(D)
labels[cl3==1]
labels[cl3==2]
labels[cl3==3]

# PAM with 3 groups
pam.out3<-pam(D.sd,3) 
pam.out3$silinfo$avg.width
pam.out3$medoids  
#D[pam.out3$id.med, ]

# with 5 groups
pam.out5<-pam(D.sd,5) 
pam.out5$silinfo$avg.width
#D[pam.out5$id.med, ]

par(mfrow=c(1,2))
plot(pam.out3, which=1, main=" ")
plot(pam.out3, which=2, main=" ")

par(mfrow=c(1,2))
plot(pam.out5, which=1, main=" ")
plot(pam.out5, which=2, main=" ")

D$Group <- as.factor(pam.out3$clustering)

par(mfrow=c(2,2), mar=c(2,2,2,2))
plot(D$Group, D$pw, col=2:4, main="Power", xlab="cluster")
plot(D$Group, D$speed, col=2:4, main="Max. Speed", xlab="cluster")
plot(D$Group, D$acc, col=2:4, main="Acceleration", xlab="cluster")
plot(D$Group, D$cons, col=2:4, main="Fuel Consumption", xlab="cluster")