Spam Filter ISP Support Forum

  New Posts New Posts RSS Feed - Bayesian Database
  FAQ FAQ  Forum Search   Register Register  Login Login

Bayesian Database

 Post Reply Post Reply
Author
kelsky View Drop Down
Guest Group
Guest Group
Post Options Post Options   Thanks (0) Thanks(0)   Quote kelsky Quote  Post ReplyReply Direct Link To This Post Topic: Bayesian Database
    Posted: 08 May 2004 at 8:12am

I understand that the Bayesian filter doesn't start until 5000 emails have went through.   Is there a way to apply someone else's database into mine?  It will take a long time for me to hit 5000 emails.  Also, any instructions on how to read the following messages in the log file?

05/08/04 07:00:05:062 -- (5932) Begin Sync Corpus.db
05/08/04 07:00:05:062 -- (5932) Sync Corpus.db pass 0a
05/08/04 07:00:05:062 -- (5932) Sync Corpus.db pass 0b
05/08/04 07:00:05:062 -- (5932) Sync Corpus.db pass 0c
05/08/04 07:00:05:062 -- (5932) Sync Corpus.db - 24488 - 0
05/08/04 07:00:05:062 -- (5932) Sync Corpus.db pass 1 (0)
05/08/04 07:00:05:109 -- (5932) Sync Corpus.db pass 2 (46)
05/08/04 07:00:05:109 -- (5932) Sync Corpus.db pass 3 (46)
05/08/04 07:00:05:109 -- (5932) Sync Corpus.db pass 4 (46)
05/08/04 07:00:05:125 -- (5932) Sync Corpus.db pass 5 (63)
05/08/04 07:00:05:187 -- (5932) Sync Corpus.db pass 6 (124)
05/08/04 07:00:05:187 -- (5932) Sync Corpus.db pass 7 (124)
05/08/04 07:00:05:187 -- (5932) Sync Corpus.db pass 8 (124)
05/08/04 07:00:05:187 -- (5932) End Sync Corpus.db (124)
05/08/04 07:00:06:015 -- (3044) BayesianThread starting
05/08/04 07:00:06:015 -- (3044) TBayesianThread - Begin LoadFromFile for corpus.db (db.dat)
05/08/04 07:00:06:015 -- (3044) TBayesianThread - LoadFromFile for Corpus.db - copied db.dat -> Ind15EE.tmp
05/08/04 07:00:06:015 -- (3044) TBayesianThread - LoadFromFile for Corpus.db - copied db.dat.prb -> Ind15EF.tmp
05/08/04 07:00:06:046 -- (3044) TBayesianThread - LoadFromFile for Corpus.db - loaded files in memory - Ind15EE.tmp
05/08/04 07:00:06:046 -- (3044) TBayesianThread - LoadFromFile for Corpus.db - loaded files in memory - Ind15EF.tmp
05/08/04 07:00:06:109 -- (3044) TBayesianThread - End LoadFromFile for corpus.db (db.dat) (94)

 

 

Back to Top
LogSat View Drop Down
Admin Group
Admin Group
Avatar

Joined: 25 January 2005
Location: United States
Status: Offline
Points: 4065
Post Options Post Options   Thanks (0) Thanks(0)   Quote LogSat Quote  Post ReplyReply Direct Link To This Post Posted: 08 May 2004 at 5:54pm

Kelsky,

Each company's spam is different, this is what makes our statistical filter so efficient, since it "learns" the spam you receive and adapts to it. If you wish to use someone else's database you can surely do so, but please note that the results may not be as accurate as they could.

All you need to do is to stop SpamFilter, replace the db.dat, db.dat.prb and corpus.ini files in the SpamFilter\corpus directory with the new ones, and restart SpamFilter.

The entries you refer to are logged to indicate that SpamFilter is updating the token corpus with the updated values it has learned in the previous 10-30 minutes. They're there for troubleshooting problems.

Roberto F.
LogSat Software

Back to Top
 Post Reply Post Reply
  Share Topic   

Forum Jump Forum Permissions View Drop Down



This page was generated in 0.109 seconds.