spamassassin-users June 2010 archive
Main Archive Page > Month Archives  > spamassassin-users archives
spamassassin-users: Re: Sa-learn huh

Re: Sa-learn huh

From: Michael Scheidell <scheidell_at_nospam>
Date: Wed Jun 02 2010 - 15:42:49 GMT
To: users@spamassassin.apache.org

On 6/2/10 11:39 AM, Randy Ramsdell wrote:
> [09:23] <botboy> sa-learn { forget,spam,ham} SHOULD change the BAYES
> scores correct?
> [09:24] <botboy> We upgraded spamassassin and it just does not work
> like it did before.
> [09:24] <botboy> I would normally be able to learn as spam and change
> the bayes score to a 3.5
> [09:25] <botboy> but now i relearn as sapm it the score stay at 0.0
> BAYES_50
>
> I do get one error when learning.
> netset: cannot include 127.0.0.1/32 as it has already been included
>
that means nothing.

> Forgot tokens from 1 message(s) (1 message(s) examined)
>
> vscan@:/home/vscan_salearn> sa-learn --spam
> 1275414726.M714825P12557.dfbbl16,W=9799:2,Sb
> netset: cannot include 127.0.0.1/32 as it has already been included
> Learned tokens from 1 message(s) (1 message(s) examined)
>
> I appears to learn the message as spam, but BAYES score does not change.
hopefully, it takes more then one set of tokens to change a properly
trained Bayesian database. if not, then all the poison emails would
trash it.

No, one email isn't going to take Bayesian from bayes_0 to bayes_95

-- Michael Scheidell, CTO Phone: 561-999-5000, x 1259 > *| *SECNAP Network Security Corporation * Certified SNORT Integrator * 2008-9 Hot Company Award Winner, World Executive Alliance * Five-Star Partner Program 2009, VARBusiness * Best Anti-Spam Product 2008, Network Products Guide * King of Spam Filters, SC Magazine 2008 ______________________________________________________________________ This email has been scanned and certified safe by SpammerTrap(r). For Information please see http://www.secnap.com/products/spammertrap/ ______________________________________________________________________