Capítulo 10, Lab 2

Lab 2: Clustering

K-Means Clustering

set.seed(2)
x = matrix(rnorm(50*2), ncol = 2)
x[1:25, 1] = x[1:25, 1] + 3
x[1:25, 2] = x[1:25, 2] - 4

km.out = kmeans(x, 2, nstart = 20)

km.out$cluster

 [1] 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
[24] 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
[47] 1 1 1 1

plot(x, col = (km.out$cluster + 1), main = "K-Means Clustering Results with K = 2", xlab = "", ylab = "", pch = 20, cex = 2)

set.seed(4)
km.out = kmeans(x, 3, nstart = 20)
km.out

K-means clustering with 3 clusters of sizes 10, 23, 17

Cluster means:
        [,1]        [,2]
1  2.3001545 -2.69622023
2 -0.3820397 -0.08740753
3  3.7789567 -4.56200798

Clustering vector:
 [1] 3 1 3 1 3 3 3 1 3 1 3 1 3 1 3 1 3 3 3 3 3 1 3
[24] 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 1
[47] 2 2 2 2

Within cluster sum of squares by cluster:
[1] 19.56137 52.67700 25.74089
 (between_SS / total_SS =  79.3 %)

Available components:

[1] "cluster"      "centers"      "totss"       
[4] "withinss"     "tot.withinss" "betweenss"   
[7] "size"         "iter"         "ifault"      

plot(x, col = (km.out$cluster + 1), main = "K-Means Clustering Results with K = 3", xlab = "", ylab = "", pch = 20, cex = 2)

set.seed(3)
km.out = kmeans(x, 3, nstart = 1)
km.out$tot.withinss

[1] 104.3319

km.out = kmeans(x, 3, nstart = 20)
km.out$tot.withinss

[1] 97.97927

Hierarchical Clustering

hc.complete = hclust(dist(x), method = "complete")

hc.average = hclust(dist(x), method = "average")
hc.single = hclust(dist(x), method = "single")

par(mfrow = c(1,3))
plot(hc.complete, main = "Complete LInkage", xlab = "", sub = "", cex = 0.9)
plot(hc.average, main = "Average LInkage", xlab = "", sub = "", cex = 0.9)

plot(hc.single, main = "Single LInkage", xlab = "", sub = "", cex = 0.9)

cutree(hc.complete, 2)

 [1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
[24] 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
[47] 2 2 2 2

cutree(hc.average, 2)

 [1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
[24] 1 1 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 1 2 1
[47] 2 2 2 2

cutree(hc.single, 2)

 [1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1
[24] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
[47] 1 1 1 1

cutree(hc.single, 4)

 [1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1
[24] 1 1 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 4 3 3 3 3
[47] 3 3 3 3

xsc = scale(x)
plot(hclust(dist(xsc), method = "complete"), main = "Hierarchical Clustering with Scaled Features")

x = matrix(rnorm(30 * 3), ncol = 3)
dd = as.dist(1 - cor(t(x)))
plot(hclust(dd, method = "complete"), main = "Complete Linkage with Correlation-Based Distance", xlab = "", sub = "")