Full_Name: Daniel Normolle Version: 2.0.1 OS: Linux/Fedora Core 3 Submission from: (NULL) (141.214.17.5) varImpPlot in Random Forests 4.5-10 produces the error "incorrect number of subscripts on matrix" (and no plot) when applied to a randomForest object. This error did not occur with 4.5-4 or earlier versions.
Please read the R FAQ on how to report bugs on contributed packages: Not to R-bug: as that's not a bug in R itself. example(varImpPlot) ran just fine in R-2.1.0. Please show _the_ example where you got the error. Andy> From: monk@umich.edu > > Full_Name: Daniel Normolle > Version: 2.0.1 > OS: Linux/Fedora Core 3 > Submission from: (NULL) (141.214.17.5) > > > varImpPlot in Random Forests 4.5-10 produces the error > "incorrect number of > subscripts on matrix" (and no plot) when applied to a > randomForest object. This > > error did not occur with 4.5-4 or earlier versions. > > ______________________________________________ > R-devel@stat.math.ethz.ch mailing list > https://stat.ethz.ch/mailman/listinfo/r-devel > > >
Apparently Analagous Threads
- question regarding "varImpPlot" results vs. model$importance data on package "RandomForest"
- strange error from R CMD check about xaxp
- use "caret" to rank predictors by random forest model
- Error on random forest variable importance estimates
- randomForest - NaN in %IncMSE