Nominal to Numeric

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

Nominal to Numeric

neha.bologna
Hi

I haveĀ a dataset which has output variables True or False.. How can I convert it to numeric such that I get RMSE values rather than Accuracy or AUC.

Kind regards

_______________________________________________
Wekalist mailing list -- [hidden email]
Send posts to [hidden email]
To unsubscribe send an email to [hidden email]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/postorius/lists/wekalist.list.waikato.ac.nz
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|

Re: Nominal to Numeric

Peter Reutemann
> I have a dataset which has output variables True or False.. How can I convert it to numeric such that I get RMSE values rather than Accuracy or AUC.

RMSE (root mean squared error) is calculated for classification as well.

Converting T/F to 1/0 (or something like that) changes the discrete
classes to a continuous regression problem and interpreting
predictions (-0.1? 9.1? 0.3? 0.51?) may become a problem.

In terms of your query: You could just use a text editor to replace
the strings. Otherwise, use the RenameNominalValues filter and then
change the attribute type in the ARFF file header to "numeric" (using
a text editor).

Cheers, Peter
--
Peter Reutemann
Dept. of Computer Science
University of Waikato, NZ
+64 (7) 577-5304
http://www.cms.waikato.ac.nz/~fracpete/
http://www.data-mining.co.nz/
_______________________________________________
Wekalist mailing list -- [hidden email]
Send posts to [hidden email]
To unsubscribe send an email to [hidden email]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/postorius/lists/wekalist.list.waikato.ac.nz
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html