On 03/25/2012 07:40 PM, Peter Prettenhofer wrote:
> 2012/3/25 Scott White<[email protected]>:
>    
>> Btw, another thing I think we should add is the ability to monitor the
>> out-of-bag estimates after each iteration and allow the fitting to be
>> terminated early. It's usually hard to guess the right number of
>> iterations required and if one can terminate the fitting early based
>> on good oob results that can help speed things up a lot.
>>
>> cheers,
>> Scott
>>
>>      
> +1 - we should really start sketching the API for monitoring the
> progress of our models during training.
>
> ``oob_scores_`` only allows you to do "early-stopping" after the fact :-)
>
>
>    
+1 on that. Didn't want to bloat the code without having
a real design when I wrote this. Should be pretty useful!


------------------------------------------------------------------------------
This SF email is sponsosred by:
Try Windows Azure free for 90 days Click Here 
http://p.sf.net/sfu/sfd2d-msazure
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to