随机森林呼叫错误

时间:2018-01-28 02:01:47

标签: random-forest

enter image description here

enter image description here

库(随机森林) rfModel2 = randomForest(formula = Purchased~。,data = Network,ntree = 50,importance = TRUE,replace = TRUE)

eval(predvars,data,env)中的错误:object' User ID'找不到

用户ID是唯一且不需要,如何让函数忽略这一点并处理1/0已购买列?

1 个答案:

答案 0 :(得分:0)

购买的是价值还是因素?

假设它是一个因素(0:未购买,1:为实例购买),您将使用以下代码进行分类:

df$Purchased<-as.factor(as.character(df$Purchased))
df$Gender<-as.factor(as.character(df$Gender))
rfModel2<-randomForest(Purchased~.,data=df[,-1])

UserID未包含在计算中

现在,如果“购买”是一个数字,即购买的商品数量,那么您应该使用回归:

df$Gender<-as.factor(df$Gender)
rfModel2<-randomForest(Purchased~.,data=df[,-1])

并且由于您的响应变量似乎是一个因素

,您将收到警告
> df$Gender<-as.factor(df$Gender)
> rfModel2<-randomForest(Purchased~.,data=df[,-1])
Warning message:
In randomForest.default(m, y, ...) :
  The response has five or fewer unique values.  Are you sure you want to do regression?
> 

希望这会有所帮助