AI4OPT - DE&M II - Clustering - Part 3 - Practice

set.seed(1234)  #setting a seedfor the random number generator
data(iris)
ir3 <- kmeans(iris[ , -5], center=3, iter.max=200)  #not using species info
ir3

## K-means clustering with 3 clusters of sizes 50, 62, 38
## 
## Cluster means:
##   Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1     5.006000    3.428000     1.462000    0.246000
## 2     5.901613    2.748387     4.393548    1.433871
## 3     6.850000    3.073684     5.742105    2.071053
## 
## Clustering vector:
##   [1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##  [38] 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
##  [75] 2 2 2 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 2 3 3 3 3 2 3 3 3 3
## [112] 3 3 2 2 3 3 3 3 2 3 2 3 2 3 3 2 2 3 3 3 3 3 2 3 3 3 3 2 3 3 3 2 3 3 3 2 3
## [149] 3 2
## 
## Within cluster sum of squares by cluster:
## [1] 15.15100 39.82097 23.87947
##  (between_SS / total_SS =  88.4 %)
## 
## Available components:
## 
## [1] "cluster"      "centers"      "totss"        "withinss"     "tot.withinss"
## [6] "betweenss"    "size"         "iter"         "ifault"

Clustering Methods - K-Means Clustering - Torgo, P. 123

table(ir3$cluster, iris$Species)

##    
##     setosa versicolor virginica
##   1     50          0         0
##   2      0         48        14
##   3      0          2        36

cm <- table(ir3$cluster, iris$Species)
1-sum(diag(cm))/sum(cm)

## [1] 0.1066667