Spam Filter ISP Forums : Bayesian filter https://www.logsat.com/spamfilter/forums/ Sun, 12 Jul 2026 19:45:15 +0000 Tue, 11 Oct 2005 23:11:26 +0000 http://blogs.law.harvard.edu/tech/rss Web Wiz Forums 11.04 360 https://www.logsat.com/spamfilter/forums/RSS_post_feed.asp?TID=5355 <![CDATA[Spam Filter ISP Forums]]> https://www.logsat.com/spamfilter/forums/forum_images/web_wiz_forums.png https://www.logsat.com/spamfilter/forums/ <![CDATA[Bayesian filter : Eilif, The &#034;dump corpus&#034;...]]> https://www.logsat.com/spamfilter/forums/forum_posts.asp?TID=5355&PID=6632&title=bayesian-filter#6632 Author: LogSat
Subject: 5355
Posted: 11 October 2005 at 11:11pm

Eilif,

The "dump corpus" does a very basic memory dump of the corpus databaseto a text format, using a hard-coded comma to separate the fields. It'sused for troubleshooting purposes only.

Internally, the numeric data is stored in native, binary format (not intext mode), and the same applies when storing it in the corpus databasefile. As such, there should not be any issues with the locale beingused.
]]> Tue, 11 Oct 2005 23:11:26 +0000 https://www.logsat.com/spamfilter/forums/forum_posts.asp?TID=5355&PID=6632&title=bayesian-filter#6632 <![CDATA[Bayesian filter : I forgot to tell you that I&#039;m...]]> https://www.logsat.com/spamfilter/forums/forum_posts.asp?TID=5355&PID=6629&title=bayesian-filter#6629 Author: eilif
Subject: 5355
Posted: 11 October 2005 at 8:21am

I forgot to tell you that I'm using v.2.6.3.487 on W2K.

Regards
Eilif Skappel

]]> Tue, 11 Oct 2005 08:21:50 +0000 https://www.logsat.com/spamfilter/forums/forum_posts.asp?TID=5355&PID=6629&title=bayesian-filter#6629 <![CDATA[Bayesian filter : Hi.The filter has only kicked...]]> https://www.logsat.com/spamfilter/forums/forum_posts.asp?TID=5355&PID=6628&title=bayesian-filter#6628 Author: Guests
Subject: 5355
Posted: 11 October 2005 at 4:49am

Hi.
The filter has only kicked in a very few times. Last time I checked Corpus.ini 1.500.000 SPAMS and 900.00 GOOD mails had passed the filter. I deleted the Corpus-folder to "restart" it.

When I dump the Corpus I found that the Probabilityfigure is written with the Norwegian standard, using , (comma) and not . (period) as the decimaldelimiter. Is this a problem or will SPAMfilter handle this?

*Token ,Good, Spam, ProbSpam, ModDate
*!&nbsp,1,0,0,400000005960464,2005-10-11
*!jx,0,1,0,400000005960464,2005-10-11
*$0*12,1,1,0,400000005960464,2005-10-11

 

Regards
Eilif Skappel

]]> Tue, 11 Oct 2005 04:49:16 +0000 https://www.logsat.com/spamfilter/forums/forum_posts.asp?TID=5355&PID=6628&title=bayesian-filter#6628