I have version 2.43.
Where are the BAYES filter settings?
How do I configure them.
--
"Remember, extremism in the nondefense of moderation is not a virtue."
-- Peter Neumann, about usenet
---
This SF.net email is sponsored by: Microsoft Visual
HI,
I have run sa-learn-spam on my spam folders , but
when I forward a mail message again to me that
had already been learned by spamassassin, it scores
very low points to it (bayes_20, bayes_30) , but never
considers the message spam.
What is it? Do I have to define rules for every spam
On Wed, Dec 04, 2002 at 06:03:33AM -0500, Tom Allison wrote:
> I have version 2.43.
> Where are the BAYES filter settings?
> How do I configure them.
Bayes is a 2.50 (CVS/development) feature. You shouldn't run 2.50 unless
you like living on the edge.
--
Randomly Generated Tagline:
"It timed me
SA 2.5 had its first miss for me today. It was a 'you are watching this
thread' from The Edge website... OK they deserved it (there was no
'To:', it had faked Outlook when it clearly wasn't, etc.
By the time I caught it, there had been a couple of dozen of these
(active thread, presumably).
> -Original Message-
> From: Justin Mason [mailto:[EMAIL PROTECTED]]
> Sent: Thursday, February 20, 2003 1:13 PM
> To: Larry Rosenman
> Cc: Louis LeBlanc; [EMAIL PROTECTED]; David Rees
> Subject: Re: [SAtalk] Bayes
>
>
>
> Larry Rosenman said:
>
&g
"Dallas Engelken" said:
> > > Is auto-learn supposed to need a sa-learn --rebuild on a "periodic"
> > > basis, or will it do it by itself?
> >
> > It'll do it iteslf, but if you have a really busy site, you
> > may want to
> > pick a time yourself, and run this script from cron.
> >
> > --j.
>
sandra said:
>I have run sa-learn-spam on my spam folders , but
> when I forward a mail message again to me that
> had already been learned by spamassassin, it scores
> very low points to it (bayes_20, bayes_30) , but never
> considers the message spam.
have you run sa-learn-nonspam as well?
Justin Mason said:
> To examine how SpamAssassin is making its diagnosis, run with -D --
> this will print out debugging lines for each of the top tokens it
> uses to compute the overall result.
hmm, I should go into this in more detail: you want to keep an eye out
for lines like:
debug: bayes
sandra wrote:
HI,
I have run sa-learn-spam on my spam folders , but
when I forward a mail message again to me that
had already been learned by spamassassin, it scores
very low points to it (bayes_20, bayes_30) , but never
considers the message spam.
What is it? Do I have to define rules
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED]]On
> Behalf Of Brian
> May
> Sent: Friday, February 07, 2003 2:32 PM
> To: [EMAIL PROTECTED]
> Subject: [SAtalk] Bayes binding...
>
>
> when I start the latest CVS tar.gz f
I have a bunchn of bayes.lock.host. files piling up in my
~/.spamassassin directory. Is there a cleanup problem?
---
This SF.net email is sponsored by: SlickEdit Inc. Develop an edge.
The most comprehensive and flexible code editor you can
Okay .. I found tools, no problem...
But .. since SA runs as a non-privledged user with no logon on a site-wide
install, how do you run the tools to see what that db has in it? SA wants
to see the db under /root/.spamassassin. SA runs as the user "filter" which
has no logon.
Ray
Is it OK to run sa-learn-spam and sa-learn-nonspam on messages that include
spamassassin markup (just headers, no body reports)? Or is bayes going to
start turning SA headers into tokens and potentially getting strange
results?
While I'm at it, does mass-check ignore SA markup or do I need to remo
Yo!
I didn't follow this mailing list long enough - how does the bayes
algorithm of 2.5 compare to bogofilter?
I find bogofilter does a very good job currently, no false positives at
all; and most false negatives get caught by sa and are fed back to
bogofilter so it can learn...
cheers
-- vbi
-
After upgrading the perl db for SA, do you have to do anything to the
existing databases?
Or does it just work…
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Simon
Byrnand
2.50 by default auto-learns from ham with scores less than -2 an
I updated from CVS about an hours ago and bayes has stopped
working. It seems as though it is now trying to use different files
than it did before. Is there anything that needs to be done to make
Bayes continue to work?
---
This sf.net email is
On Sat, 4 Jan 2003 the voices made Adrian 'Dagurashibanipal' von Bidder write:
ADvB> I find bogofilter does a very good job currently, no false positives at
ADvB> all; and most false negatives get caught by sa and are fed back to
ADvB> bogofilter so it can learn...
Take a closer look at those fa
On Sun, 23 Feb 2003, Theo Van Dinter wrote:
> On Mon, Feb 24, 2003 at 12:10:59PM +1300, Simon Byrnand wrote:
> > Anyone agree/disagree with this ? The question is what to do about it,
>
> Well, all I can say is that it works pretty well for me.
2.50 has been picking off the Nigerian spams for m
Graham Murray said:
> I updated from CVS about an hours ago and bayes has stopped
> working. It seems as though it is now trying to use different files
> than it did before. Is there anything that needs to be done to make
> Bayes continue to work?
I just checked in a change which makes major imp
Hi folks,
finally BAYES works with MailScanner. Now I noticed that it only works
in mails that are not marked as spam anyways... Not a single mail in my
spam folder has a BAYES score assigned to it. When I run this mail
throug spamassassin -t it gets a score. I wrote a debug file overnight
and fou
Hi,
I've setup another server to try out version 2.5.0. I already trained it to
identify spam but not yet non-spam messages. How do I know it's working?
---
francis a. vidal [bitstop network services] | http://www.bitstop.ph
streaming media + web hosting | http://www.keystone.ph
On Friday 22 November 2002 11:08 pm, [EMAIL PROTECTED] wrote:
> Hi,
>
> I've setup another server to try out version 2.5.0. I already trained
> it to identify spam but not yet non-spam messages. How do I know it's
> working?
You can't, not until you train it with a non-spam corpus as well. How
t
Bug? The bayes code in 2.50 doesn't get invoked from spamd because there
is no hook from handle_user to [re]open the bayes databases.
I have to think this is an oversight, but I thought I'd better ask.
* Should spamd do this?
The learn code is a bit slow and if the authors are open to code
submis
Don't know if this one of your problems or not, but you might want to
look at adding: bayes_file_mode since you are using a site wide
configuration. Also make sure the user that spamassassin is running as
has the proper read and write permissions to the files defined in your
bayes_path stateme
Liudvikas Bukys said:
> Bug? The bayes code in 2.50 doesn't get invoked from spamd because there
> is no hook from handle_user to [re]open the bayes databases.
> I have to think this is an oversight, but I thought I'd better ask.
> * Should spamd do this?
This should now be fixed in CVS...
> T
25 matches
Mail list logo
