[Spambayes] lots of unsures, heavily biased towards spam

[David Abrahams]

skip at pobox.com writes:

>     Dave> I know that; I meant the technical implications.  In particular, I
>     Dave> asked:
>
>     >> > I know spambayes keeps a database; when I delete already-trained
>     >> > emails from my xxx-training folders does it forget everything about
>     >> > those messages and rebuild the database using the other messages as
>     >> > though from scratch, or is some of the information about those
>     >> > deleted messages retained?
>
> Sorry.  Yes, when a message is "untrained" the database forgets about it
> completely (message count is decremented, all token counts adjusted
> down).

And deleting a messgae from the training set will cause it to be
"untrained" at the next training?

>
>     >> I know this won't help you with the imap filter, however...  
>
>     Dave> Why not?
>
> I don't use the imap filter.  I presume it has its own way of managing your
> hams and spams.

It doesn't sound different to me.  There's a ham training mailbox and
a spam training mailbox.

>     >> I use the train-to-exhaustion script in the contrib directory which
>     >> helps keep my ham:spam ratio tractable....
>
>     Dave> Can that procedure be applied to my IMAP folders?
>
> In theory I suppose it can.  The ham and spam mailboxes are opened using
> mboxutils.getmbox() which presumes to be fairly format agnostic but I don't
> know if it will work with IMAP folders.  I see no mention of IMAP at all in
> mboxutils.py.  I suppose this might be a case of "patches cheerfully
> accepted". :-)

:/

-- 
Dave Abrahams
Boost Consulting
www.boost-consulting.com