flaw in spamicity calculation
Doug Beardsley
dgbeards at southern.edu
Wed Sep 18 23:26:49 CEST 2002
On Wed, Sep 18, 2002 at 05:18:28PM -0400, David Relson wrote:
>
> When I started testing with Eric Seppanen's multi-list patch, I split out
> that calculation so I could compare original (esr's) and new (eds's)
> algorithms. He called them old_examine_word() and old_examine_word(). I
> called them compute_probability_esr() and compute_probability_eds(). I
> needed to have them both present to resolve the different results they gave.
>
> If we can decide on a name for the function, I'll change the code and put
> it into the cvs repository.
I don't have a burder for a particular function name. I just didn't
know that it had been done. Your names are fine with me.
Doug Beardsley
More information about the bogofilter-dev
mailing list