Rで遊ぶ　～ワインの等級をrandomForestで予測～ ref: http://qiita.com/Dixhom/items/7c33a1dc85144e1da822

file0.r

library("httr")
geturl <- GET("https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data")
dat <- read.csv(textConnection(content(geturl)), header=F)

file1.r

head(dat)
names(dat) <- c("class", paste0("V", 1:13))
dat <- transform(dat, class = as.factor(class))

file2.r

> str(dat)
'data.frame':   178 obs. of  14 variables:
 $ class: Factor w/ 3 levels "1","2","3": 1 1 1 1 1 1 1 1 1 1 ...
 $ V1   : num  14.2 13.2 13.2 14.4 13.2 ...
 $ V2   : num  1.71 1.78 2.36 1.95 2.59 1.76 1.87 2.15 1.64 1.35 ...
 $ V3   : num  2.43 2.14 2.67 2.5 2.87 2.45 2.45 2.61 2.17 2.27 ...
 $ V4   : num  15.6 11.2 18.6 16.8 21 15.2 14.6 17.6 14 16 ...
 $ V5   : int  127 100 101 113 118 112 96 121 97 98 ...
 $ V6   : num  2.8 2.65 2.8 3.85 2.8 3.27 2.5 2.6 2.8 2.98 ...
 $ V7   : num  3.06 2.76 3.24 3.49 2.69 3.39 2.52 2.51 2.98 3.15 ...
 $ V8   : num  0.28 0.26 0.3 0.24 0.39 0.34 0.3 0.31 0.29 0.22 ...
 $ V9   : num  2.29 1.28 2.81 2.18 1.82 1.97 1.98 1.25 1.98 1.85 ...
 $ V10  : num  5.64 4.38 5.68 7.8 4.32 6.75 5.25 5.05 5.2 7.22 ...
 $ V11  : num  1.04 1.05 1.03 0.86 1.04 1.05 1.02 1.06 1.08 1.01 ...
 $ V12  : num  3.92 3.4 3.17 3.45 2.93 2.85 3.58 3.58 2.85 3.55 ...
 $ V13  : int  1065 1050 1185 1480 735 1450 1290 1295 1045 1045 ...

file3.r

library(caret)
index <- createDataPartition(dat$class, p=.8, list=F)
train <- dat[index, ]
test  <- dat[-index,]

file4.r

tuneRF(train[,-1], train[,1], doBest=T) # 6
rf <- randomForest(class~., data=train, mtry=6)

file5.r

> table(predict(rf, test), test$class)

     1  2  3
  1 11  0  0
  2  0 14  0
  3  0  0  9

file6.r

> importance(rf)
    MeanDecreaseGini
V1        11.7547555
V2         1.3451287
V3         0.7519802
V4         1.1294739
V5         1.7996680
V6         2.4725046
V7        19.0491105
V8         0.3845735
V9         0.7663628
V10       11.6714396
V11        7.4439506
V12       13.1139074
V13       22.4820614