Hi,
On Fri, 7 Nov 2003, Evan Platt wrote:
> --On Friday, November 07, 2003 12:06 PM -0800 Jeff Lasman
> <[EMAIL PROTECTED]> wrote:
>
> > What's likely to happen if I run these 563 spams without running any
> > hams?
>
> I thought I recall the help file stating that running HAMS without SPAM (or
> SPAM without HAM) won't have any effect on the learning process - i.e. it's
> a waste of time?
No, Bayes will learn but SA won't start tagging mail with Bayes scores
until 200 each of ham and spam have been learned. Autolearning couldn't
work otherwise. :)
I'd suggest training with the ham and spam you have. Sure, your ham
scores will be biased toward mailing list traffic but that shouldn't
affect Bayes ability to detect spam (unless your mailing list traffic is
spam-heavy.) At worst, Bayes will score your normal non-mailing list
traffic around 50% ("don't know") and pass it through as it does now.
-- Bob
-------------------------------------------------------
This SF.Net email sponsored by: ApacheCon 2003,
16-19 November in Las Vegas. Learn firsthand the latest
developments in Apache, PHP, Perl, XML, Java, MySQL,
WebDAV, and more! http://www.apachecon.com/
_______________________________________________
Spamassassin-talk mailing list
[EMAIL PROTECTED]
https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
