<P><FONT SIZE=4 FACE="Courier"><BR>> From: David White <dwhite@ling.ohio-state.edu><BR>> Sent by: owner-r-help@stat.math.ethz.ch<BR>> Date: 07/19/2001 11:28 AM AST<BR>> To: r-help@stat.math.ethz.ch<BR>> Subject: [R] classification tree out put</FONT></P><P><FONT SIZE=4 FACE="Courier">>Hello,<BR>><BR>>I'm attempting to classify data using tree(). summary(tree()) indicates<BR>>that I have a very good classification rate. What I'd like to know is<BR>>which tokens in the data set are correctly classified and which are not.<BR>><BR>>Is there a method for associating the classification with the token?<BR>>I've been reading Chambers and Hastie (1992) chapter 9 on tree-based<BR>>models, but find no indication of this. Any suggestion as to sources I<BR>>should consult would also be appreciated.<BR>><BR>>Thank in advance.</FONT></P><P><FONT SIZE=4 FACE="Courier">atree <- tree (some.dat)</FONT></P><P><FONT SIZE=4 FACE="Courier">misclass <- atree$y != atree$frame$yval[atree$where]</FONT></P><P> </P><P><FONT SIZE=4 FACE="Courier">Denis White</FONT></P><P><FONT SIZE=4 FACE="Courier"> US EPA, 200 SW 35th St, Corvallis, Oregon, USA</FONT></P><P><FONT SIZE=4 FACE="Courier"> white.denis@epa.gov, voice 541.754.4476</FONT></P>-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._