Skip to content
Back to formatted view

Raw Message

Message-ID: <39B6DDB9048D0F4DAD42CB26AAFF0AFA0562C2D5@usctmx1106.merck.com>
Date: 2008-03-11T18:38:10Z
From: Liaw, Andy
Subject: randomForest get tree
In-Reply-To: <20080311132215.0a8xvn9kg8osgw0k@www.mail.yale.edu>

Graphing:  Not really.  You might do somw work and get Rgraphviz to
produce the tree, but I'm not sure how useful that is.

Interpretation:  You can read the tree just like any other decision
trees.  However, remember that the splits are chosen with some
randomness, so I'm not sure how much trust I would place on any
particular tree.  Breiman did not design random forests so that the
trees can be interpreted the usual way.

Andy 

From: helen.mills at yale.edu
 
> All,
> What purpose does the getTree function have in Random Forest? 
> Can you graph it
> as you can in rpart and can it be interpreted in the same way?
> 
> Helen Mills Poulos
> Yale School of Forestry
> 
> ______________________________________________
> R-help at r-project.org 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.
> 
> 
> 


------------------------------------------------------------------------------
Notice:  This e-mail message, together with any attachme...{{dropped:15}}