Re: [R] number of Nodes in Random Forest

From: Weiwei Shi <helprhelp_at_gmail.com>
Date: Tue 16 Jan 2007 - 18:00:44 GMT

Hi, Goncalo:

did u use compounds as features when building rf? If so, some compounds are NOT randomly selected in splitting nodes, which might explain what you observed. But you need to provide more info for us to help you, like those parameters you used to build rf.

You can use varImpPlot to see what exactly compounds were used by setting n.var (see ?varImpPlot) or you can use nrow(YourTrainingX$importance) to get that number too.

HTH, w.

On 1/16/07, Gonšalo Carrera <goncalo.carrera@dq.fct.unl.pt> wrote:
> I'm calculating nodes using Random Forest in R but i only get nodes for a
> fraction of the compounds i want to calculate, the rest is ommited and is not
> printed in the output file, (i'm working with 3012 compounds). What can i do to
> have nodes printed for all the compounds. Thanks
>
> Gonšalo
>
> ______________________________________________
> R-help@stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

-- 
Weiwei Shi, Ph.D
Research Scientist
GeneGO, Inc.

"Did you always know?"
"No, I did not. But I believed..."
---Matrix III

______________________________________________
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Received on Wed Jan 17 05:06:06 2007

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Tue 16 Jan 2007 - 18:30:32 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.