[R] Question about random Forest function in R

Liu, Weifeng Aaron weifeng at amazon.com
Tue May 29 18:30:08 CEST 2012


This is a well-known limitation. You have to group categorical attributes together to work around.

--------------------------------------------------------------------------------------
Weifeng (aaron) liu  |  retail systems pricing  |  sr research scientist


-----Original Message-----
From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On Behalf Of Kelly Cool
Sent: Tuesday, May 29, 2012 7:47 AM
To: r-help at r-project.org
Subject: [R] Question about random Forest function in R



Hello, 

I am trying to run the random Forest function on a data.frame using the following code..

myrf <- randomForest (y=sample_data_metal, x=Train, importance=TRUE, proximity=TRUE)


However, an error occurs saying, "can not handle categorical predictors with more than 32 categories". 

My "x=Train" data.frame is quite large and my "y=sample_data_metal" is one column. 

I'm not sure how to go about fixing this error or if there is even a way to get around this error. Thanks in advance for any help. 

	[[alternative HTML version deleted]]



More information about the R-help mailing list