# K mean clustering
###### tags: `R教學` `基礎統計`

# Loading package
library(cluster)

# Removing initial label of 
# Species from original dataset
iris_1 <- iris[, -5]

# Fitting K-Means clustering Model 
# to training dataset
set.seed(240) # Setting seed
kmeans.re <- kmeans(iris_1, centers = 3, nstart = 20)
kmeans.re

# Cluster identification for 
# each observation
kmeans.re$cluster

# Confusion Matrix
cm <- table(iris$Species, kmeans.re$cluster)
cm

jpeg(filename = "k-mean.jpg",
     width = 510*2, height = 380*2, pointsize = 20, quality = 75)
# Model Evaluation and visualization
plot(iris_1[c("Sepal.Length", "Sepal.Width")], 
     col = kmeans.re$cluster)
## Plotiing cluster centers
kmeans.re$centers
kmeans.re$centers[, c("Sepal.Length", "Sepal.Width")]
# cex is font size, pch is symbol
points (kmeans.re$centers[,1:2], pch = 19, col = 1:3, cex = 3)
dev.off()