[R] gbm function

Patrick Connolly p_connolly at slingshot.co.nz
Sat Jun 26 06:06:38 CEST 2010


On Wed, 23-Jun-2010 at 12:05AM -0700, azam jaafari wrote:

|> ?Hello
|> ?
|> I have questions about gbm package.??It seems we have to?devide data to two part (training?set and test set) for first. 
|> ?
|> 1- trainig set for?running of gbm function
|> 2- test set for?gbm.perf???
|> ?
|> is it rigth? 
|> I have 123 sample that I devided 100 for trainig and 23 for test.
|> ?
|> So, parameter of?cv.folds?in gbm function is for what?

There's quite a lot to be known about how to use those functions.  The
vignette gives a bit of an idea, but I came across this article which
helped me work out how to use them.



 A working guide to boosted regression trees J. Elith,
 J. R. Leathwick, T. Hastie Journal of Animal Ecology Volume 77 ,
 Issue 4 , Pages802 - 813 Journal compilation © 2008 British
 Ecological Society


HTH

-- 
~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.   
   ___    Patrick Connolly   
 {~._.~}                   Great minds discuss ideas    
 _( Y )_  	         Average minds discuss events 
(:_~*~_:)                  Small minds discuss people  
 (_)-(_)  	                      ..... Eleanor Roosevelt
	  
~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.



More information about the R-help mailing list