You can find quite a bit of discussion about this with a Google search for '"no filterable" spambayes". I didn't read much, but http://mail.python.org/pipermail/spambayes-bugs/2005-September/003746.ht ml has a lot of discussion. Looks like it could be a bug; I'm not sure whether anyone ever found a way to fix it. You could always try one of the 1.1 alphas. (I've been running one for years. It's not flawless, but it's pretty darned good.)
I'm with Skip: 400 messages is more than a minimal training set. I usually get good results after I've trained on a few dozen messages (which I try to keep fairly evenly split between ham and spam). I've trained on about 210 messages in the last several months and I'm starting to think about starting over. (The quickness with which SpamBayes learns to discern spam impresses me, so I retrain periodically just to watch it learn. Perhaps I am in need of professional help.) -----Original Message----- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED] Sent: Tuesday, October 14, 2008 3:02 PM To: Bob Shipley Cc: [email protected] Subject: Re: [Spambayes] "No filterable mail items are selected." Bob> I am running the binary version. I recently installed Spambayes Bob> 1.0.4. I used a minimum of training - ~400 messages. When I click Bob> on a spam message in my in box, I get the following: "no filterable Bob> mail items are selected." Bob> Can you help me? I can't help you with Outlook issues, but approximately 400 messages is hardly "a minimum of training". Assuming you've trained on about equal numbers of ham and spam I would think maybe 20 messages would be a minimum of training. Are those 400 messages mostly spam or approximately equal numbers of ham and spam? Skip _______________________________________________ [email protected] http://mail.python.org/mailman/listinfo/spambayes Info/Unsubscribe: http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html _______________________________________________ [email protected] http://mail.python.org/mailman/listinfo/spambayes Info/Unsubscribe: http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html
