SpamBayes should be able to train on ham or spam
separately.
If you go to the train-menu and only select ham folders,
the content in the folders should be added to the "good
words"-list, and vica versa for the spam list.
Thanks for your report. This bug has previously been reported,
and has already been fixed in the source-code - so you can expect
to see the fix in the next binary release.
If you are technically minded, you may like to run from the CVS
version of the source-code, and you should find the fix
immediately - see the main SpamBayes pages for details.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Logged In: YES
user_id=552329
Thanks for your report. This bug has previously been reported,
and has already been fixed in the source-code - so you can expect
to see the fix in the next binary release.
You may wish to subscribe to the spambayes-announce list to see
when each version is released - details at
http://mail.python.org/mailman-21/listinfo/spambayes-announce
If you are technically minded, you may like to run from the CVS
version of the source-code, and you should find the fix
immediately - see the main SpamBayes pages for details.
Logged In: YES
user_id=552329
(To clarify, this will actually be in the first 1.1 release).