Clustering_PAM

library(factoextra)

## Warning: package 'factoextra' was built under R version 3.4.4

## Loading required package: ggplot2

## Welcome! Related Books: `Practical Guide To Cluster Analysis in R` at https://goo.gl/13EFCZ

library(cluster)

## Warning: package 'cluster' was built under R version 3.4.3

data("USArrests")
my_data.scaled =scale(USArrests)
fviz_nbclust(my_data.scaled, pam, method="silhouette")

pam.res = pam(my_data.scaled, 2)
print(pam.res)

## Medoids:
##            ID     Murder    Assault   UrbanPop       Rape
## New Mexico 31  0.8292944  1.3708088  0.3081225  1.1603196
## Nebraska   27 -0.8008247 -0.8250772 -0.2445636 -0.5052109
## Clustering vector:
##        Alabama         Alaska        Arizona       Arkansas     California 
##              1              1              1              2              1 
##       Colorado    Connecticut       Delaware        Florida        Georgia 
##              1              2              2              1              1 
##         Hawaii          Idaho       Illinois        Indiana           Iowa 
##              2              2              1              2              2 
##         Kansas       Kentucky      Louisiana          Maine       Maryland 
##              2              2              1              2              1 
##  Massachusetts       Michigan      Minnesota    Mississippi       Missouri 
##              2              1              2              1              1 
##        Montana       Nebraska         Nevada  New Hampshire     New Jersey 
##              2              2              1              2              2 
##     New Mexico       New York North Carolina   North Dakota           Ohio 
##              1              1              1              2              2 
##       Oklahoma         Oregon   Pennsylvania   Rhode Island South Carolina 
##              2              2              2              2              1 
##   South Dakota      Tennessee          Texas           Utah        Vermont 
##              2              1              1              2              2 
##       Virginia     Washington  West Virginia      Wisconsin        Wyoming 
##              2              2              2              2              2 
## Objective function:
##    build     swap 
## 1.441358 1.368969 
## 
## Available components:
##  [1] "medoids"    "id.med"     "clustering" "objective"  "isolation" 
##  [6] "clusinfo"   "silinfo"    "diss"       "call"       "data"

#for reference, add cluster column
my_data_withpam = cbind(USArrests, cluster=pam.res$cluster) 

#다섯 번째 컬럼에 cluster 추가 된 것 확인하기
head(my_data_withpam, 5) 

##            Murder Assault UrbanPop Rape cluster
## Alabama      13.2     236       58 21.2       1
## Alaska       10.0     263       48 44.5       1
## Arizona       8.1     294       80 31.0       1
## Arkansas      8.8     190       50 19.5       2
## California    9.0     276       91 40.6       1

fviz_cluster(pam.res, palette = c("blue", "red"), ellipse.type="t", #Concentration ellipse
              repel = TRUE, #Avoid label overplotting
              ggtheme = theme_classic())