MailScanner, SA and Bayes : still problems

Julian Field mailscanner at ecs.soton.ac.uk
Fri Oct 1 14:43:45 IST 2004


<x-flowed>
At 14:24 01/10/2004, you wrote:
>What happens with the sa-learn process is very strange.
>
>I have run sa-learn on several files downloaded from spamarchive.org and
>when I run spamassassin --lint -D, it seems that content of Bayes DB is
>removed !
>
>Learned from 913 message(s) (1117 message(s) examined).
>debug: Initialising learner
>debug: bayes: 31672 tie-ing to DB file
>R/O /usr/var/spool/MailScanner/spamassassin/bayes_toks
>debug: bayes: 31672 tie-ing to DB file
>R/O /usr/var/spool/MailScanner/spamassassin/bayes_seen
>debug: bayes: found bayes db version 2
>debug: bayes: Not available for scanning, only 15 ham(s) in Bayes DB < 200
>
>Should I shutdown spamd before running the spamassassin command ? How can I
>rebuild a fresh new Bayes DB ?

If you have only taught it lots of spam, and 15 ham (i.e. 15 non-spam
messages), then you will see this. It has to have at least 200 non-spam
messages as well as lots of spam messages before it will start using it.
Just let it run on your system for a while to let it auto-learn enough
non-spam and it should all start working.
--
Julian Field
www.MailScanner.info
MailScanner thanks transtec Computers for their support
Buy the MailScanner book at www.MailScanner.info/store

PGP footprint: EE81 D763 3DB0 0BFD E1DC 7222 11F6 5947 1415 B654

------------------------ MailScanner list ------------------------
To unsubscribe, email jiscmail at jiscmail.ac.uk with the words:
'leave mailscanner' in the body of the email.
Before posting, read the MAQ (http://www.mailscanner.biz/maq/) and
the archives (http://www.jiscmail.ac.uk/lists/mailscanner.html).
</x-flowed>



More information about the MailScanner mailing list