k-means clustering example with R studio and wine data

hellobird 2019. 5. 28. 17:58

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
41
42
43
44
 
wine = read.csv("wine.data",header = F)
 
t = "     1) Alcohol
     2) Malic acid
     3) Ash
    4) Alcalinity of ash  
     5) Magnesium
    6) Total phenols
     7) Flavanoids
     8) Nonflavanoid phenols
     9) Proanthocyanins
    10)Color intensity
     11)Hue
     12)OD280/OD315 of diluted wines
     13)Proline            
"
 
 
s = str_match_all(t, "\\)\\s*(.+)\n")
 
s = sapply(s, function(x){
  x[,2]
})
s = str_trim(s)
s
 
colnames(wine) = c("class", s)
str(wine)
 
class = wine[ , 1]
x     = wine[-1]
 
 
kc = kmeans(x , 3)
kc
 
length(kc$cluster) 
length(class)
 
 
colSums(table(class , kc$cluster))
table(wine$class)
 
Colored by Color Scripter
cs

저작자표시 (새창열림)