K-Medoids-abdullah–3-.R

#
#K-Medoids Clustering in R
#PREPARED BY MOSTADAWI KADER ABDULLAH
homedir <- "C:/Users/Mostafa/Desktop/Thesis"
setwd(homedir)
library(factoextra)

## Warning: package 'factoextra' was built under R version 4.1.3

## Loading required package: ggplot2

## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa

library(cluster)

#load data
df <- USArrests

#remove rows with missing values
df <- na.omit(df)

#scale each variable to have a mean of 0 and sd of 1
df <- scale(df)

#plot clusters vs within sum of squares
fviz_nbclust(df, pam, method = "wss")

#calculate gap statistic based on number of clusters
gap_stat <- clusGap(df,
                    FUN = pam,
                    K.max = 10, #max clusters to consider
                    B = 50) #total bootstrapped iterations

#plot number of clusters vs. gap statistic
fviz_gap_stat(gap_stat)

#make this example reproducible
set.seed(1)

#perform k-medoids clustering with k = 4 clusters
kmed <- pam(df, k = 4)

#view results
kmed

## Medoids:
##               ID     Murder    Assault   UrbanPop         Rape
## Alabama        1  1.2425641  0.7828393 -0.5209066 -0.003416473
## Michigan      22  0.9900104  1.0108275  0.5844655  1.480613993
## Oklahoma      36 -0.2727580 -0.2371077  0.1699510 -0.131534211
## New Hampshire 29 -1.3059321 -1.3650491 -0.6590781 -1.252564419
## Clustering vector:
##        Alabama         Alaska        Arizona       Arkansas     California 
##              1              2              2              1              2 
##       Colorado    Connecticut       Delaware        Florida        Georgia 
##              2              3              3              2              1 
##         Hawaii          Idaho       Illinois        Indiana           Iowa 
##              3              4              2              3              4 
##         Kansas       Kentucky      Louisiana          Maine       Maryland 
##              3              3              1              4              2 
##  Massachusetts       Michigan      Minnesota    Mississippi       Missouri 
##              3              2              4              1              3 
##        Montana       Nebraska         Nevada  New Hampshire     New Jersey 
##              3              3              2              4              3 
##     New Mexico       New York North Carolina   North Dakota           Ohio 
##              2              2              1              4              3 
##       Oklahoma         Oregon   Pennsylvania   Rhode Island South Carolina 
##              3              3              3              3              1 
##   South Dakota      Tennessee          Texas           Utah        Vermont 
##              4              1              2              3              4 
##       Virginia     Washington  West Virginia      Wisconsin        Wyoming 
##              3              3              4              4              3 
## Objective function:
##    build     swap 
## 1.035116 1.027102 
## 
## Available components:
##  [1] "medoids"    "id.med"     "clustering" "objective"  "isolation" 
##  [6] "clusinfo"   "silinfo"    "diss"       "call"       "data"

#plot results of final k-medoids model
fviz_cluster(kmed, data = df)

#add cluster assignment to original data
final_data <- cbind(USArrests, cluster = kmed$cluster)

#view final data
head(final_data)

##            Murder Assault UrbanPop Rape cluster
## Alabama      13.2     236       58 21.2       1
## Alaska       10.0     263       48 44.5       2
## Arizona       8.1     294       80 31.0       2
## Arkansas      8.8     190       50 19.5       1
## California    9.0     276       91 40.6       2
## Colorado      7.9     204       78 38.7       2