Testing fisher

[David Relson]

At 09:40 AM 1/28/03, Boris 'pi' Piwinger wrote:

>David Relson wrote:
>
> > An interesting table.  Your best value of min_dev seems to depend on
> > whether a non-zero F-P is acceptable to you.
>
>Yes, but as I said that single failure really looks like spam.
>
> > min_dev=0.2 gives 184 F-N and 0 F-P, while min_dev of 0.015, 0.02, and
> > 0.025 give essentially identical results of 89-92 F-N and 1 F-P.  (I've
> > extracted the min_dev lines I mention.)
> >
> >     fisher-2        0.20          0.60     4221   184   15140  0
> >
> >     fisher-2        0.025         0.60     4262    89   15251  1
> >     fisher-2        0.02          0.60     4297    92   15362  1
> >     fisher-2        0.015         0.60     4295    92   15361  1
> >
> > So, having done your testing, what values are you actually using?
>
>0.025 for two days now with great success. Still my
>.procmailrc has to do some work, but there is basically
>nothing I see.

With min_dev=0.025 you're discarding tokens with scores from 0.475 to 
0.525.  What values are you using for robs and robx?