Eric> I've been working with crm114 as a content filter for the past few
Eric> years and lately it has delivered disappointing results. I'd like
Eric> to see if my test sets and training methods fail in the same way
Eric> with another content filter. Are there any pointers to creating a
Eric> standalone analyzer with spambayes?
I'm not sure what you mean by "standalone analyzer". There are a pair of
Unix filters, sb_filter.py and sb_bnfilter.py which take a message in and
either score it against an existing training database or train it as ham or
spam. There are also tools to help you test SpamBayes itself by break up a
training set into multiple pieces for regression testing (train on n-1
groups, score the nth group).
--
Skip Montanaro - [EMAIL PROTECTED] - http://www.webfast.com/~skip/
"Be different, express yourself like everyone else."
_______________________________________________
SpamBayes@python.org
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
