Optimizing problem

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

Optimizing problem

Hua Ai
Hi All,

While training the tree classifier, is there any parameter I can use to tell
weka that I want my precision to be as high as possible while I don't care
other values like F-score or recall?

Thanks a lot!
Hua

_________________________________________________________________
Don't just search. Find. Check out the new MSN Search!
http://search.msn.click-url.com/go/onm00200636ave/direct/01/


_______________________________________________
Wekalist mailing list
[hidden email]
https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
Reply | Threaded
Open this post in threaded view
|

Re: Optimizing problem

Eibe Frank
Your best bet is probably to hack
weka.classifiers.meta.ThresholdSelector (which chooses the threshold
that maximizes the F-measure).

Cheers,
Eibe

On Jul 7, 2005, at 9:17 AM, Hua Ai wrote:

> Hi All,
>
> While training the tree classifier, is there any parameter I can use
> to tell
> weka that I want my precision to be as high as possible while I don't
> care
> other values like F-score or recall?
>
> Thanks a lot!
> Hua
>
> _________________________________________________________________
> Don't just search. Find. Check out the new MSN Search!
> http://search.msn.click-url.com/go/onm00200636ave/direct/01/
>
>
> _______________________________________________
> Wekalist mailing list
> [hidden email]
> https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist


_______________________________________________
Wekalist mailing list
[hidden email]
https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist