Hello M.Lewis, Sunday, October 16, 2005, 4:13:24 PM, you wrote:
ML> Thanks Bob. Very interesting. ML> After you do the sa-learn for both the spam and ham, do you then delete ML> those files in order to keep them small ? We concatenate those files to comprehensive "user flagged as spam" and "user flagged as not spam" mbox files. These are then useful a) in case we need to restart the bayes database -- we have a few thousand recently confirmed spam and non-spam to immediately learn, b) we save these as a mass-check corpus for testing new rules. Bob Menschel
