m = matrix(rnorm(120, 100, 10), nrow = 20, ncol = 6) %>% data.frame()indx = 1:(0.8*nrow(m))colnames(m) = c('True', 1:(ncol(m)-1))tree(True~., data = m, subset = indx)在使用上述代码构建决策树模型时，我遇到了以下错误：
在[.data.frame(frame, predictors)中选择了未定义的列
这个错误是否与我的列名有关？列名1到5确实有特定的含义，因此我可能不容易更改它们，有没有其他方法可以解决这个问题？
谢谢！
回答：
这确实似乎是你的列名的问题（R不喜欢数字作为列名）；如果我们更改列名，错误就会消失
# 样本数据框set.seed(2018)df <- setNames(as.data.frame(replicate(6, rnorm(20, 100, 10))), c("True", paste0("Var", 1:5)))df# True Var1 Var2 Var3 Var4 Var5#1 95.77016 112.63864 96.40558 108.35183 86.35395 103.70908#2 84.50122 102.50198 87.00464 105.89023 116.49011 106.73337#3 99.35571 102.58195 91.30130 101.70094 92.20744 92.77447#4 102.70881 117.85534 110.54362 95.62828 109.83104 94.29125#5 117.35284 87.80294 98.51360 99.19792 105.05784 97.30385#6 97.35289 97.59878 110.18077 90.72457 83.00285 108.04330#7 120.99471 89.41338 92.78413 115.18867 125.97463 87.78891#8 108.63351 104.19409 92.21222 100.85730 95.77344 110.74260#9 93.89413 97.29043 93.81834 121.52795 92.66463 106.51900#10 106.37056 93.68175 116.05205 86.34069 102.75945 101.69782#11 93.56965 97.71588 94.12557 103.45906 90.17478 94.36445#12 89.69971 111.78680 94.72556 105.65181 106.54766 79.04253#13 107.12481 97.33727 105.96021 99.93902 114.74087 104.90003#14 95.54228 105.28141 87.28688 95.61219 102.12982 105.78960#15 102.48980 82.31341 97.98745 106.88891 84.50630 95.60654#16 89.25806 95.10209 104.55634 95.00581 102.77174 102.21734#17 81.72738 114.10522 90.65173 81.31385 109.83210 82.33406#18 100.15492 89.24736 127.28318 107.43425 107.59388 90.73533#19 83.15639 102.92395 103.46645 99.10825 93.42645 129.55945#20 102.04468 97.93336 93.62290 110.81164 109.22904 102.45278library(tree)tr <- tree(True ~ ., data = df)#node), split, n, deviance, yval# * denotes terminal node##1) root 20 2089.0 98.59# 2) Var1 < 94.3919 5 340.1 109.50 *# 3) Var1 > 94.3919 15 958.3 94.96# 6) Var3 < 99.5236 6 346.3 91.62 *# 7) Var3 > 99.5236 9 501.0 97.18 *plot(tr)text(tr)
