RStudio(5) Cluster分析

前回と同じデータを使ってCluster分析をしてみます。

(1)凝集型階層

> library(cluster)

> cluster.agnes <- agnes="" mysql.data="" span="" stand="T)">> plot(cluster.agnes, which = 2, main = "", xlab = "", ylab = "")

(2) 区分型階層

> cluster.diana <- diana="" mysql.data="" span="" stand="T)">> plot(cluster.diana, which = 2, main = "", xlab = "", ylab = "")

(3) k-means法

> cluster.kmeans = kmeans(dist(mysql.data), 6)
> cluster.kmeans$cluster
 1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 
 5  5  5  5  5  5  5  5  5  5  5  1  1  1  1  1  6  1  3  3  3  3  3  3  2  4  4  4  4  4  4  4  4  4  4  4  4  4  2  6 

> cluster.kmeans$size
[1]  6  2  6 13 11  2

> cluster.kmeans$withinss
[1]  57677.519   5325.897  82998.094 383242.093  83159.601 102326.957 

> clusplot(mysql.data, cluster.kmeans$cluster, color=TRUE, shade=TRUE, labels=2, lines=0)

 (4) 階層クラスタリング

> rect.hclust(hclust(dist(mysql.data), method="ward.D"), k = 5, border = "red")

[Cluster.R]

	cluster.agnes <- function(name){
	cluster.agnes <- agnes(name, stand = T)
	plot(cluster.agnes, which = 2, main = "", xlab = "", ylab = "")
	}
	cluster.diana <- function(name){
	cluster.diana <- agnes(name, stand = T)
	plot(cluster.diana, which = 2, main = "", xlab = "", ylab = "")
	}
	cluster.kmeans <- function(name){
	cluster.kmeans = kmeans(dist(name), 6)
	cluster.kmeans$cluster
	cluster.kmeans$size
	clusplot(name, cluster.kmeans$cluster, color=TRUE, shade=TRUE, labels=2, lines=0)
	}
	cluster.hclust <- function(name){
	rect.hclust(hclust(dist(name), method="ward.D"), k = 5, border = "red")
	}

view raw Cluster.R hosted with ❤ by GitHub

参考
http://catcher-in-the-tech.net/2035/
http://d.hatena.ne.jp/maito610/20120810/p1