I use the same method, mailwatch to train bayes and now I have +170k of tokens and rarely have spam get into any inbox.<br><br>Regards,<br>-- <br>Pedro Cardoso<br>[ <a href="mailto:xmasterx@gmail.com">xmasterx@gmail.com</a>
]<br><br><div><span class="gmail_quote">On 10/7/07, <b class="gmail_sendername"><a href="mailto:hvdkooij@vanderkooij.org">hvdkooij@vanderkooij.org</a></b> <<a href="mailto:hvdkooij@vanderkooij.org">hvdkooij@vanderkooij.org
</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">Jan Agermose wrote:<br><br>> 2) is it possible to download and install a "base bayes database"? The
<br>> result of training the database from some sort of standard accepted<br>> training set of spam/ham mail?<br><br>No. Each network is unique and you must train your bayesian database to<br>fit YOUR traffic and not fit someone elses traffic.
<br><br>I would even recommend against autolearning. If you manually select 200<br>SPAM and 200 HAM messages you make the database work for you. In this<br>regard read the instructions from the competition:<br><a href="http://www.barracudanetworks.com/ns/downloads/Barracuda_Bayes.pdf">
http://www.barracudanetworks.com/ns/downloads/Barracuda_Bayes.pdf</a><br><br>If you do it this way in MailScanner you get pretty good results. I<br>actually disable autolearn and use mailwatch to train the database. For<br>
that you need to store all messages in quarantaine.<br><br>Hugo.<br><br>--<br><a href="mailto:hvdkooij@vanderkooij.org">hvdkooij@vanderkooij.org</a> <a href="http://hugo.vanderkooij.org/">http://hugo.vanderkooij.org/
</a><br> Don't meddle in the affairs of sysadmins,<br> for they are subtle and quick to anger.<br>--<br>MailScanner mailing list<br><a href="mailto:mailscanner@lists.mailscanner.info">mailscanner@lists.mailscanner.info
</a><br><a href="http://lists.mailscanner.info/mailman/listinfo/mailscanner">http://lists.mailscanner.info/mailman/listinfo/mailscanner</a><br><br>Before posting, read <a href="http://wiki.mailscanner.info/posting">http://wiki.mailscanner.info/posting
</a><br><br>Support MailScanner development - buy the book off the website!<br></blockquote></div>