K-means algorithm to find clusters

script.R

# Auth: Abhijeet Chopra
# CWID: 50180612 
# Date: 30 Apr 2017
# Prog: K-means
# Desc: R Script to find cluster using k-means algorithm
# Meth: Classification Trees using C5.0
# -----------------------------------------

setwd("C:/Users/abhij/Desktop")
mydata <- read.csv("C:/Users/abhij/Desktop/mydata.csv", header = TRUE, stringsAsFactors=FALSE)

# Prepare Data
mydata <- na.omit(mydata) # listwise deletion of missing
mydata <- scale(mydata) # standardize variables 

# Determine number of clusters
wss <- (nrow(mydata)-1)*sum(apply(mydata,2,var))
for (i in 2:15) wss[i] <- sum(kmeans(mydata,
                                     centers=i)$withinss)
plot(1:15, wss, type="b", xlab="Number of Clusters",
     ylab="Within groups sum of squares") 

# K-Means Cluster Analysis
fit <- kmeans(mydata, 3) # 3 cluster solution
# get cluster means
aggregate(mydata,by=list(fit$cluster),FUN=mean)
# append cluster assignment
mydata <- data.frame(mydata, fit$cluster) 

head(mydata)

write.csv(mydata, file = "output.csv", row.names = FALSE)