On June 24, 2018 6:13:31 PM GMT+12:00, Fernando Lavin <fernandolavin78(a)gmail.com>
Thank you for the prompt reply.
Do you mean that although cross-validation is used, still there are no
In such cases, do you suggest deleting the *classes* of those instances
form the training set?
On Sun, Jun 24, 2018 at 2:07 PM, Peter Reutemann <fracpete(a)gmail.com>
On June 24, 2018 5:38:59 PM GMT+12:00, Fernando
What is the meaning of these "?" in the result, please see the
Text attachment would be nice... ;-)
There are no test instances for these classes available, hence
> to calculate statistics.
> Cheers, Peter
> Peter Reutemann
> Dept. of Computer Science
> University of Waikato, NZ
> +64 (7) 858-5174
> Wekalist mailing list
> Send posts to: Wekalist(a)list.waikato.ac.nz
> List info and subscription status: https://list.waikato.ac.nz/
> List etiquette: http://www.cs.waikato.ac.nz/~
I don't know anything about your test setup, whether you used cross-validation or
explicit test set. All I can tell from the statistics that you sent through, is that there
are only test instances for two classes.
Probably makes no difference, whether you leave these empty classes in or not. But give it
Dept. of Computer Science
University of Waikato, NZ
+64 (7) 858-5174