How to get an importance of a class using random forest? - variables

Question

I am using randomForest package in my dataset to do a classification, but with the importance command I only get the importance of variables. So, if I want the variable importance by specific categories of variables? Like a specific location in a region variable, how much that region impact in the total. I thought in transformer every class in a dummy, but i don't know if this is really a good idea.

Answer 1

I think you mean "variable importance by specific categories of variables". That has not been implemented, but I guess it would be possible, meaningful and perhaps useful. Of course it would not be meaningful for variables with only two categories.
I would implement it something like:
Train model -> compute out-of-bag prediction performance (OOB-cv1) -> permute specific category by specific variable (reassign this category randomly to other categories, weighted by other category prevalence) -> re-compute out-of-bag- prediction performance (OOB-cv2) -> subtract OOB-cv1 from OOB-cv2
And then I wrote the a function implementing categorical specific variable importance.
library(randomForest)
#Create some classification problem, with mixed categorical and numeric vars
#Cat A of var 1, cat B of var 2 and Cat C of var 3 influence class the most.
X.cat = replicate(3,sample(c("A","B","C"),600,rep=T))
X.val = replicate(2,rnorm(600))
y.cat = 3*(X.cat[,1]=="A") + 3*(X.cat[,2]=="B") + 3*(X.cat[,3]=="C")
y.cat.err = y.cat+rnorm(600)
y.lim = quantile(y.cat.err,c(1/3,2/3))
y.class = apply(replicate(2,y.cat.err),1,function(x) sum(x>y.lim)+1)
y.class = factor(y.class,labels=c("ann","bob","chris"))
X.full = data.frame(X.cat,X.val)
X.full[1:3] = lapply(X.full[1:3],as.factor)
#train forest
rf=randomForest(X.full,y.class,keep.inbag=T,replace=T)
#make function to compute crovalidated classification error
oobErr = function(rf,X) {
preds = predict(rf,X,type="vote",predict.all = T)$individual
preds[rf$inbag!=0]=NA
oob.pred = apply(preds,1,function(x) {
tabx=sort(table(x),dec=T)
majority.vote = names(tabx)[1]
})
return(mean(as.character(rf$y)!=oob.pred))
}
#make function to iterate all categories of categorical variables
#and compute change of OOB class error due to permutation of category
catVar = function(rf,X,nPerm=2) {
ref = oobErr(rf,X)
catVars = which(rf$forest$ncat>1)
lapply(catVars, function(iVar) {
catImp = replicate(nPerm,{
sapply(levels(X[[iVar]]), function(thisCat) {
thisCat.ind = which(thisCat==X[[iVar]])
X[thisCat.ind,iVar] = head(sample(X[[iVar]]),length(thisCat.ind))
varImp = oobErr(rf,X)-ref
})
})
if(nPerm==1) catImp else apply(catImp,1,mean)
})
}
#try it out
out = catVar(rf,X.full,nPerm=4)
print(out) #seems like it works as it should
$X1
A B C
0.14000 0.07125 0.06875
$X2
A B C
0.07458333 0.16083333 0.07666667
$X3
A B C
0.05333333 0.08083333 0.15375000