[R] Erros with RVM and LSSVM from kernlab library

Steve Lianoglou mailinglist.honeypot at gmail.com
Wed Aug 19 21:09:11 CEST 2009


On Aug 19, 2009, at 2:54 PM, Noah Silverman wrote:

> Hi Steve,
> No custom kernel. (This is the exact same data that I call svm  
> with.  svm works without a complaint.)
> traindata is just a dataframe of numerical attributes
> trainlabels is just a vector of labels. ("good", "bad")
> Then I call
> model <- rvm(x,y)

is x really a data.frame? Can you try to turn it into a matrix to see  
if it will get you over this speed bump?

model <- rvm(as.matrix(x), y)

I reckon if x is a data.frame, R is invoking the rvm function that's  
meant to work on list(s), rather than the matrix which you think  
you're passing in.

Does that do the trick?


Steve Lianoglou
Graduate Student: Computational Systems Biology
  |  Memorial Sloan-Kettering Cancer Center
  |  Weill Medical College of Cornell University
Contact Info: http://cbio.mskcc.org/~lianos/contact

More information about the R-help mailing list