u## K means clustering

## read input dataset "iris"

data(iris)

head(iris)

newiris<-iris

head(newiris)

newiris$Species<-NULL

head(newiris)

​

kc<-kmeans(newiris,3)

kc

​

## Compare the species label with the clustering result

table(iris$Species, kc$cluster)

​

## Plot the clusters and their centers

plot(newiris[c("Sepal.Length", "Sepal.Width")], col = kc$cluster)

points(kc$centers[, c("Sepal.Length", "Sepal.Width")], col = 1:3, pch = 8, cex = 2)

​

data(iris)

mydata <- na.omit(iris[, -5])

mydata <- scale(mydata)

wss <- 0

for (i in 1:15) wss[i] <- sum(kmeans(mydata, centers = i)$withinss)

plot(1:15, wss, type = "b", xlab = "Number of Clusters", ylab = "Within group sum of squares")