Re: weka - failed to make a prediction

Michael Hall <[email protected]> Wed, 13 Jul 2022 07:28:21 -0500
Newsgroups gmane.comp.ai.weka
Message-ID <[email protected]>

> On Jul 13, 2022, at 7:01 AM, Michael Hall <[email protected]> wrote:
> 
> 
> 
>> On Jul 13, 2022, at 4:18 AM, Bob Matthews <[email protected] <mailto:[email protected]>> wrote:
>> 
>> Thanks Michael
>> 
>> A little confusion at this end re weka vs autoweka
>> 
>> I will recheck and correct my approach to simply using weka with classifier JRip
>> 
>> 
> Or if AutoWeka is available as a package. Check on Peter’s suggestion to see that packages are getting properly initialized. They get added to class path dynamically somehow.
> 

Also if you want to see what AutoWeka suggests you could then use the classifier and parameters it ends up with in your normal production runs.
As I remember AutoWeka would probably be too high overhead for using every time.

_______________________________________________
Wekalist mailing list -- [email protected]
Send posts to [email protected]
To unsubscribe send an email to [email protected]
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