Re: [R] Fwd: varimp_in_party_package

2011-06-21 Thread Torsten Hothorn
On Thu, 16 Jun 2011, Jinrui Xu wrote: Thanks for your feedback. I think the problem is not because of many levels. There is only 1 column with two levels as class labels in my input data. Below is my code. The commandline "data.cforest.varimp <- varimp(data.cforest, conditional = TRUE)" rep

Re: [R] Fwd: varimp_in_party_package

2011-06-16 Thread Jinrui Xu
Sorry, Patrick and other victims. My bad~~ The data file can be accessed at http://zhanglab.ccmb.med.umich.edu/TM-fold/featureSelection_rec.vectors The code is attached below. Error happens at "data.cforest.varimp <- varimp(data.cforest, conditional = TRUE)": "Error in model.matrix.default

Re: [R] Fwd: varimp_in_party_package

2011-06-16 Thread Patrick Connolly
On Thu, 16-Jun-2011 at 09:19AM -0400, Jinrui Xu wrote: > Thanks for your feedback. > I think the problem is not because of many levels. There is only 1 > column with two levels as class labels in my input data. > > Below is my code. The commandline "data.cforest.varimp <- > varimp(data.cforest

Re: [R] Fwd: varimp_in_party_package

2011-06-16 Thread Torsten Hothorn
Hello everyone, I use the following command lines to get important variable from training dataset. data.controls <- cforest_unbiased(ntree=500, mtry=3) data.cforest <- cforest(V1~.,data=rawinput,controls=data.controls) data.cforest.varimp <- varimp(data.cforest, conditional = TRUE) I got er