Hi! I have a question concerning the svm in the e1071 package. I trained the svm by a set of samples, doing a 10 cross validation. The summary function then prints out the total accuracy and single accuracies, works fine. My question is then: Is it possible to get classification results per cross validation out the svm? I mean e.g. numbers about the true positives ,fp,fn,tf ? How do I get a list of the classified examples ? Thanks, -- Frank G. Zoellner AG Angewandte Informatik Technische Fakult"at Universit"at Bielefeld phone: +49(0)521-106-2951 fax: +49(0)521-106-2992 email: fzoellne at techfak.uni-bielefeld.de
>I have a question concerning the svm in the e1071 package. >I trained the svm by a set of samples, doing a 10 cross validation. >The summary function then prints out the total accuracy and single >accuracies, >works fine.>My question is then: Is it possible to get classification results per >cross >validation out the svm? I mean e.g. numbers about the true >positives ,fp,fn,tf ?No, because the accuracies are not computed using a confusion matrix. The computation is internally done in C.>How do I get a list of the classified examples ?-- Dr. David Meyer Department of Information Systems Vienna University of Economics and Business Administration Augasse 2-6, A-1090 Wien, Austria, Europe Fax: +43-1-313 36x746 Tel: +43-1-313 36x4393 HP: http://wi.wu-wien.ac.at/Wer_sind_wir/meyer/
On Mon, Mar 22, 2004 at 01:14:06PM +0100, David Meyer wrote:> >I have a question concerning the svm in the e1071 package. > >I trained the svm by a set of samples, doing a 10 cross validation. > >The summary function then prints out the total accuracy and single > >accuracies, >works fine. > > >My question is then: Is it possible to get classification results per > >cross >validation out the svm? I mean e.g. numbers about the true > >positives ,fp,fn,tf ? > > No, because the accuracies are not computed using a confusion matrix. > The computation is internally done in C.So there is no way to recieve a list of the examples and its assigned class which has been used for testing the svm during the cross validation? Yours, -- Frank G. Zoellner AG Angewandte Informatik Technische Fakult"at Universit"at Bielefeld phone: +49(0)521-106-2951 fax: +49(0)521-106-2992 email: fzoellne at techfak.uni-bielefeld.de
If you really want such features, you have two options: - Modify the C and R code yourself. - Send request to the author of libsvm, Chih-Jen Lin. Andy> From: Frank Gerrit Zoellner > > On Mon, Mar 22, 2004 at 01:14:06PM +0100, David Meyer wrote: > > >I have a question concerning the svm in the e1071 package. > > >I trained the svm by a set of samples, doing a 10 cross validation. > > >The summary function then prints out the total accuracy and single > > >accuracies, >works fine. > > > > >My question is then: Is it possible to get classification > results per > > >cross >validation out the svm? I mean e.g. numbers about the true > > >positives ,fp,fn,tf ? > > > > No, because the accuracies are not computed using a > confusion matrix. > > The computation is internally done in C. > > So there is no way to recieve a list of the examples and its > assigned class which has been used for testing the svm during > the cross validation? > > Yours, > > -- > Frank G. Zoellner > AG Angewandte Informatik > Technische Fakult"at > Universit"at Bielefeld > phone: +49(0)521-106-2951 > fax: +49(0)521-106-2992 > email: fzoellne at techfak.uni-bielefeld.de > > ______________________________________________ > R-help at stat.math.ethz.ch mailing list > https://www.stat.math.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide! > http://www.R-project.org/posting-guide.html > >------------------------------------------------------------------------------ Notice: This e-mail message, together with any attachments,...{{dropped}}
Hi! I have another SVM question. I run and train a C-Classification using the SVM, works fine. Now I want to receive the output (the classified examples): pred <- fitted(model) where pred is then a list of the classification result of each input elememt i supposed. But if I compare the number of entries in pred with the original numer of input values there is a difference. How can this happen and how can I get back all the classified examples? Yours, Frank -- Frank G. Zoellner AG Angewandte Informatik Technische Fakult"at Universit"at Bielefeld phone: +49(0)521-106-2951 fax: +49(0)521-106-2992 email: fzoellne at techfak.uni-bielefeld.de