Bayse problem?

[Scott Silva]

Rob Morin spake the following on 10/11/2006 8:47 AM:
> interesting...  :)
> 
> postfix at peter:~$ sa-learn --dump magic
> bayes: cannot open bayes databases /opt/MailScanner/bayes/bayes_* R/O:
> tie failed: Permission denied
> bayes: cannot open bayes databases /opt/MailScanner/bayes/bayes_* R/O:
> tie failed: Permission denied
> ERROR: Bayes dump returned an error, please re-run with -D for more
> information
> 
> after making postfix the owner
> postfix at peter:~$ sa-learn --dump magic
> 0.000          0          3          0  non-token data: bayes db version
> 0.000          0          0          0  non-token data: nspam
> 0.000          0          0          0  non-token data: nham
> 0.000          0          0          0  non-token data: ntokens
> 0.000          0          0          0  non-token data: oldest atime
> 0.000          0          0          0  non-token data: newest atime
> 0.000          0          0          0  non-token data: last journal
> sync atime
> 0.000          0          0          0  non-token data: last expiry atime
> 0.000          0          0          0  non-token data: last expire
> atime delta
> 0.000          0          0          0  non-token data: last expire
> reduction count
> 
> After a few minutes....
> 
> peter:/opt/MailScanner/bayes# sa-learn --dump magic
> 0.000          0          3          0  non-token data: bayes db version
> 0.000          0         10          0  non-token data: nspam
> 0.000          0          1          0  non-token data: nham
> 0.000          0       1974          0  non-token data: ntokens
> 0.000          0 1160581441          0  non-token data: oldest atime
> 0.000          0 1160581687          0  non-token data: newest atime
> 0.000          0          0          0  non-token data: last journal
> sync atime
> 0.000          0          0          0  non-token data: last expiry atime
> 0.000          0          0          0  non-token data: last expire
> atime delta
> 0.000          0          0          0  non-token data: last expire
> reduction count
> 
> 
> So should bayes learn now? or do i need to check somethign else...
> thanks for the quick reply!
> :)
> 
As you can see in the nham and nspam counts above, bayes is now learning. It
won't start scoring with bayes until you have 200 of each. You will either
have to wait, or get a starter database from the Fortress site..
www.fsl.com/support.html
It could train itself in a week or so, maybe less depending on your traffic.
You can help the process by manually training things it misses.

-- 

MailScanner is like deodorant...
You hope everybody uses it, and
you notice quickly if they don't!!!!