Mmmm....replying to my own mail....oh well...,

> PROBLEM: Despite sa-learn declaring "Learned from 27 message(s)
> (30 message(s) examined)" the nspam count has not risen, i.e it was 81
> before and after running sa-learn.

Seems I have solved this issue. I copied my previous 'user based' bayes
db, that had well in excess of 200 ham/spam messages already.

sa-learn then DID update the db.

I can only assume that either there was a problem with my old bayes db, or
that a minimum of 200 messages needs to be fed to bayes in one hit PRIOR
to first use (not drip fed 1--20 at a time)...........anyway it all seems
to work now.

Thanks to the list and the archives for helping.

-- 
Regards,

Roland Hill                                  Registered Linux User #330226
http://pl.net/~rnrhill/rhweb.htm                   @ http://counter.li.org

Reply via email to