sa-learn --dump magic gives the vital statistics of how many tokens were learned from how many hams and spams. But since each token can have a unique score, it's hard to show their distribution. After long periods of auto-learning, tokens seem to gravitate toward one end of the spectrum or the other (at least in SA 2.63).
Pierre Thomson BIC -----Original Message----- From: Bill Landry [mailto:[EMAIL PROTECTED] Sent: Monday, August 23, 2004 2:54 PM To: [email protected] Subject: Bayes question Is there a way to query the bayes database to get a quick output of the spam/ham token distribution? I didn't see a flag option for sa-learn, other than --dump, but that's not really what I'm looking for. Thanks, Bill
