5.1、聚类之Kmeans聚类实例

k-means实例

junjun

2016年2月9日

利用k-means对iris分类

#1、加载数据
data(iris)
str(iris)

## 'data.frame':    150 obs. of  5 variables:
##  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##  $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
##  $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
##  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
##  $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

#2、建模
model_kmeans <- kmeans(iris[, 1:4], 3)

#3、模型评估
model_kmeans

## K-means clustering with 3 clusters of sizes 38, 50, 62
## 
## Cluster means:
##   Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1     6.850000    3.073684     5.742105    2.071053
## 2     5.006000    3.428000     1.462000    0.246000
## 3     5.901613    2.748387     4.393548    1.433871
## 
## Clustering vector:
##   [1] 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
##  [36] 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 1 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3
##  [71] 3 3 3 3 3 3 3 1 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 1 3 1 1 1
## [106] 1 3 1 1 1 1 1 1 3 3 1 1 1 1 3 1 3 1 3 1 1 3 3 1 1 1 1 1 3 1 1 1 1 3 1
## [141] 1 1 3 1 1 1 3 1 1 3
## 
## Within cluster sum of squares by cluster:
## [1] 23.87947 15.15100 39.82097
##  (between_SS / total_SS =  88.4 %)
## 
## Available components:
## 
## [1] "cluster"      "centers"      "totss"        "withinss"    
## [5] "tot.withinss" "betweenss"    "size"         "iter"        
## [9] "ifault"

str(model_kmeans)

## List of 9
##  $ cluster     : int [1:150] 2 2 2 2 2 2 2 2 2 2 ...
##  $ centers     : num [1:3, 1:4] 6.85 5.01 5.9 3.07 3.43 ...
##   ..- attr(*, "dimnames")=List of 2
##   .. ..$ : chr [1:3] "1" "2" "3"
##   .. ..$ : chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
##  $ totss       : num 681
##  $ withinss    : num [1:3] 23.9 15.2 39.8
##  $ tot.withinss: num 78.9
##  $ betweenss   : num 603
##  $ size        : int [1:3] 38 50 62
##  $ iter        : int 2
##  $ ifault      : int 0
##  - attr(*, "class")= chr "kmeans"

table(model_kmeans$cluster, iris[, 5])

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

#4、绘制所有的簇以及簇的中心，注意多次运行得到的K-means聚类结果可能不同，因为初始的簇中心是随机选择的
plot(iris[c("Sepal.Length", "Sepal.Width")], col=model_kmeans$cluster)

#画出簇的中心点
points(model_kmeans$centers[, c("Sepal.Length", "Sepal.Width")], col=1:3, pch=8, cex=2)

#5、生成聚类图
library(fpc)

plotcluster((iris[, 1:4]), model_kmeans$cluster)