The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
"Multinominal class -
Contributor II
Hi again!
Simple question.. Again searched for the answer but no luck. Here we go:
I have a data set with multinominal class label. I want to use the regular SVM operator as my learning algorithm. Now, I put the SVM operator inside a cross validation block, an expected error is reported: SVM cannot handle multinominal class labels. Then I want to use one of the quick fixes, which seem very handy, polynomial by binomial classification (1 vs 1). When I chose this, as expected, it replaces the SVM which was on the training side of the cross validation with a polynomial by binomial classification operator, and puts the SVM inside it. Everything is fine until now. Then I use apply model at the other (right) side of the cross validation and as always put a performance (classification) operator next to it. Now it gets messy and says
1 error(s): Label and prediction must be of the same type but are polynominal and nominal, respectively.
And no matter what I tried I could not manage to fix this.
Any help is sincerely appriciated.
Thanks.
Simple question.. Again searched for the answer but no luck. Here we go:
I have a data set with multinominal class label. I want to use the regular SVM operator as my learning algorithm. Now, I put the SVM operator inside a cross validation block, an expected error is reported: SVM cannot handle multinominal class labels. Then I want to use one of the quick fixes, which seem very handy, polynomial by binomial classification (1 vs 1). When I chose this, as expected, it replaces the SVM which was on the training side of the cross validation with a polynomial by binomial classification operator, and puts the SVM inside it. Everything is fine until now. Then I use apply model at the other (right) side of the cross validation and as always put a performance (classification) operator next to it. Now it gets messy and says
1 error(s): Label and prediction must be of the same type but are polynominal and nominal, respectively.
And no matter what I tried I could not manage to fix this.
Any help is sincerely appriciated.
Thanks.
Tagged:
0
Answers
The warning message of the ClassificationPerformance operator seems to be a bit useless since it should not make a difference whether the label is polynominal or just nominal. Simply ignore the warning and try to run the process, everything should work without further problems.
Regards,
Helge
When I tried to run the process, everytime it got stuck at that performance operator and did not continue. So the application sort of hanged.
When I changed the label to nominal it worked fine.
Cheers