Re: Can some one enlight me regarding the results of megatest?

-------- Original-Nachricht --------
> Datum: Thu, 4 Sep 2008 08:22:24 -0400
> Von: Bill Yerazunis <[email protected]>
> An: "Ger Hobbelt" <[email protected]>
> CC: [email protected], [email protected]
> Betreff: Re: [Crm114-general] Can some one enlight me regarding the results	of megatest?

> 
>    From: "Ger Hobbelt" <[email protected]>
> 
>    Unfortunately, the diff doesn't tell you the Classifier this way so
>    it's kinda hard to see which classifier we're talking about here, but
>    given the NN b0rk just before, I'm heavily betting on this being NN
>    classify going pearshaped as a result.
> 
> Apropos that - I have been using the subterfuge of putting classifier
> specific terms into the individual file output lines.  
> 
> What about this change: instead of
> 
>   CLASSIFY succeeds
> or
>   CLASSIFY fails
> 
> we would have 
> 
>   [Classifier_ID] CLASSIFY succeeds
> and
>   [Classifier_ID] CLASSIFY fails
> 
> where [Classifier_ID] is one of "Markov", "OSB", "OSBF", 
> I don't think this breaks any known script, and it would
> make debugging megatest output much easier.
> 
I would welcome that. Would be a very good addition.


>    feature series for particular classifiers); other count differences
>    are due to the fact that I rewrote the VT code a long time ago and it
>    will produce more feature hashes for boundary cases. The latest
>    mainline is getting much closer to my numbers, though.  Another bit
>    Bill & I need to go through when time allows. As to which is 'better'
>    then? That depends on the bugfix being actually a fix or a tweak due
>    to a misconception. Of course, I am opinionated, but that's not what
>    this is about. It about this:
> 
>    if you see any differences in feature counts or documents (integer)
>    numbers reported, that is enough reason to ask around on the ML if
>    it's okay. It probably is (there are types of bugs, which can be
>    tolerated some times; those bugs are about accuracy instead of
>    operation -- that's also where most of the Blame is shifting around
>    for. :-) )
> 
> Yeah.  That too.
> 
> That's one problem with machine learning code; unlike ( for example )
> calculating the value of pi or a symbolic manipulation, you can't say
> this is "correct" or "incorrect", all you get is "better" or "worse".
> 
> 
>    > 1022,1023c1032,1033
>    [...]
>    >> #1 (q_test.css):documents: 175, features: 37599,  prob: 1.53e-02,
> pR: -18.10
>    > ------------------------------------
> 
>    Bill can probably dream these stats, but I need a diff -u where the
>    classifier print lines show up as well (-C5 ? maybe even -C10 ? or
>    better yet: -B10 for the diff command?); you might benefit from that
>    too.
> 
> No, I look it up.  :)  There's usually enough info in the 
> actual .log file to figure out what went wrong.
> 
>     - Bill

-- 
GMX Kostenlose Spiele: Einfach online spielen und Spaß haben mit Pastry Passion!
http://games.entertainment.gmx.net/de/entertainment/games/free/puzzle/6169196

-------------------------------------------------------------------------
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK & win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
http://moblin-contest.org/redirect.php?banner_id=100&url=/