如何解决使用R构建决策树的问题

Question

我使用R构建了一个决策树模型，当预测值大于50%时，我想在树中添加一个新列，并在该列中打印"是">

N.B:数据集中的目标库门是布尔值1=心脏病，0=正常

library(rpart)
tree<-rpart(target ~ .,method ='class', data=train)
print(summary(tree))
tree.preds<-predict(tree,test)
print(head(tree.preds))
tree.preds<-as.data.frame(tree.preds)
joiner<-function(x){
if(x>=0.5)
return('yes')

else
return('no')

}
tree.preds$disease<-sapply(tree.preds$yes,joiner)
print(head(tree.preds))

运行后出现此错误：

Error in `$<-.data.frame`(`*tmp*`, t, value = list()) : 
replacement has 0 rows, data has 91

Answer 1

您可以使用ifelse代替sapply:迭代

library(rpart)
dat = iris[,-5]
dat$target = as.numeric(iris$Species=="versicolor")
idx = sample(nrow(dat),100)
train = dat[idx,]
test = dat[-idx,]
tree = rpart(target ~ .,method ='class', data=train)
tree.preds = data.frame(predict(tree,test))
tree.preds$Species = ifelse(tree.preds[,2]>0.5,"yes","no")