k-means clustering example with R studio and wine data

 
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)