Dear Jeff Newmiller, I apologize if then I did not clarify what I am looking properly. I used the combination you suggested in the query but I did not see any of the resultings adressing what I asked in my title: Rusboost implemented over AdaBoost.M2. Searching for the words 'rusboost', 'smoteboost', 'multiclass classification *imbalance*', 'adaboost.m2' did not yield any result.
My question is not really theoretical, I am not asking what is any of those algorithms. They are known and have been published already. I just found it strange that I couldn't find any of those coded in R. I was hoping that, perhaps, some other naming convention could have been used in R to address this problem. I hope I made myself more clear now. Thank you, Carlos Andrade http://carlosandrade.co 2012/10/14 Jeff Newmiller <jdnew...@dcn.davis.ca.us> > Asking questions and giving answers about R is what this mailing list is > about. It is not really a theory list. If you understand the theory you can > search among the libraries yourself. But when the first search I make > brings up what to me looks like the answer to your question, then you > either did not search before posting or you did not clarify what you were > really looking for properly. > --------------------------------------------------------------------------- > Jeff Newmiller The ..... ..... Go Live... > DCN:<jdnew...@dcn.davis.ca.us> Basics: ##.#. ##.#. Live > Go... > Live: OO#.. Dead: OO#.. Playing > Research Engineer (Solar/Batteries O.O#. #.O#. with > /Software/Embedded Controllers) .OO#. .OO#. rocks...1k > --------------------------------------------------------------------------- > Sent from my phone. Please excuse my brevity. > > Carlos Andrade <carlosvia...@gmail.com> wrote: > > >Dear Jeff Newmiller, > > > >Thanks for the suggestion I did not know the website but the problem is > >more dry than simple multiclass classification. In fact, there are even > >few > >papers addressing the problem. I was in hope that if not yet available > >in > >CRAN someone from the R community could point out any 'pre release' > >version > >of it. I hope it is inappropriate to ask such questions here. > > > >Thanks, > > > >Carlos Andrade > >http://carlosandrade.co > > > > > > > >2012/10/14 Jeff Newmiller <jdnew...@dcn.davis.ca.us> > > > >> May I suggest you use a more appropriate tool for your search: > >> > >> RSiteSearch("multiclass classification") > >> > >> > >> On Sun, 14 Oct 2012, Carlos Andrade wrote: > >> > >> Hi, > >>> > >>> I have been searching everywhere for an implementation of those > >>> algorithms, > >>> but I have only observed them in Matlab and on the literature. > >>> > >>> I noticed a package called 'ada' in CRAN but it is not for multi > >class. I > >>> would be happy with just Adaboost.m2, Smoteboost over adaboost.m2 or > >any > >>> other combination that could account for imbalanced multiclass > >>> classification problems. > >>> > >>> Thanks! > >>> > >>> Carlos Andrade > >>> http://carlosandrade.co > >>> > >>> [[alternative HTML version deleted]] > >>> > >>> ______________________________**________________ > >>> R-help@r-project.org mailing list > >>> > >https://stat.ethz.ch/mailman/**listinfo/r-help< > https://stat.ethz.ch/mailman/listinfo/r-help> > >>> PLEASE do read the posting guide http://www.R-project.org/** > >>> posting-guide.html <http://www.R-project.org/posting-guide.html> > >>> and provide commented, minimal, self-contained, reproducible code. > >>> > >>> > >> ------------------------------**------------------------------** > >> --------------- > >> Jeff Newmiller The ..... ..... Go > >Live... > >> DCN:<jdnew...@dcn.davis.ca.us> Basics: ##.#. ##.#. Live > >> Go... > >> Live: OO#.. Dead: OO#.. > >Playing > >> Research Engineer (Solar/Batteries O.O#. #.O#. with > >> /Software/Embedded Controllers) .OO#. .OO#. > >rocks...1k > >> ------------------------------**------------------------------** > >> --------------- > >> > > [[alternative HTML version deleted]] ______________________________________________ R-help@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.
