R help - Jan 2009 - a first opinion on rattle

Graham
 
I have installed rattle and is pretty intuitive and friendly. However, I miss
some features of the original packages which cannot be invoked from rattle. For
example, 'randomForest' package is used but random forests cannot be
used in one of  -in my opinion- most powerful aspects like regression. The same
about SVM . I would also say include RVM which the scientific literature suggest
is mugh powerful than SVM.
 
Anyway, I must congratulate you and your team for providing the scientific
community with rattle.
 
Best regards and thanks
 
 
Dr. Gabriel Ibarra-Berastegi. 
University of the Basque Country
Spain


      
	[[alternative HTML version deleted]]

Received Fri 09 Jan 2009  7:49pm +1100 from Gabriel Ibarra:
[...]
> I have installed rattle and is pretty intuitive and
> friendly. However, I miss some features of the original packages
> which cannot be invoked from rattle. For example, 'randomForest'
> package is??used but random??forests cannot be used in one of ??-in
> my opinion- most powerful aspects like regression. The same about
> SVM??. I would also say include RVM which the scientific literature
> suggest is mugh powerful than SVM.
> Anyway,??I must congratulate you and your team for providing the
> scientific community with rattle.
Thanks for the most kind feedback Gabriel. It is appreciated.

I am always open to suggestions. I should turn the randomForest
regression option on. Thanks for suggesting that. 

RVM from kernlab is in the todo list now. Do you have some simple
examples using rvm for regression? I should have a look to get that
into Rattle. Help (i.e., code or just code examples) is always welcome
:-)

Thanks,
Graham