| -----Original Message----- | From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] | Sent: Wednesday, October 01, 2003 5:58 PM | It's got to be reading the wrong files. | | Do an "sa-learn" of a small number of mails with -D on. Then run | "sa-learn -D --dump magic". Post the 2 log files and let's see | if that makes any sense... | | --j.
I finally got my Bayes to learn my spam and ham files. I ran both of them using my mbox files. Then I ran both of them with --forget. Then I relearned them again. Now my magic is looking better. Before: ==== snip ==== 0.000 0 2 0 non-token data: bayes db version 0.000 0 1687 0 non-token data: nspam 0.000 0 0 0 non-token data: nham 0.000 0 36864 0 non-token data: ntokens 0.000 0 0 0 non-token data: oldest atime 0.000 0 0 0 non-token data: newest atime 0.000 0 0 0 non-token data: last journal sync atime 0.000 0 0 0 non-token data: last expiry atime 0.000 0 0 0 non-token data: last expire atime delta 0.000 0 0 0 non-token data: last expire reduction count After forgetting and relearning... 0.000 0 2 0 non-token data: bayes db version 0.000 0 21692 0 non-token data: nspam 0.000 0 3674 0 non-token data: nham 0.000 0 63226 0 non-token data: ntokens 0.000 0 1049222211 0 non-token data: oldest atime 0.000 0 1065039199 0 non-token data: newest atime 0.000 0 1065039199 0 non-token data: last journal sync atime 0.000 0 0 0 non-token data: last expiry atime 0.000 0 0 0 non-token data: last expire atime delta 0.000 0 0 0 non-token data: last expire reduction count Seems like the sa-learn process is not working correctly. <<Dan>> ------------------------------------------------------- This sf.net email is sponsored by:ThinkGeek Welcome to geek heaven. http://thinkgeek.com/sf _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
