on Mon Jul 30 2007, skip-AT-pobox.com wrote:
> Dave> OK, I have some hams that scored as high as 0.85
>
> I will assert without any further evidence that you have one or more
> classification mistakes in your database.
I'm pretty careful about that. It was just an unusual, terse message
from my brother in law.
> Can you post the evidence header from that message?
There's no evidence header (I guess I don't have that option enabled),
but I'll enclose the entire message.
> Dave> Is everything between the ham_cutoff and spam_cutoff classified as
> Dave> unsure? Moving my spam_cutoff to 0.86 probably would make only a
> Dave> small dent in my results.
>
> If everything is properly trained SpamBayes should produce a distribution of
> scores with a bimodal distribution, hams near 0.0 and spams near 1.0. A ham
> scoring above 0.5 tells me that you have classified a number of hams as
> spam.
When something is misclassified, it makes my tte.py runs take more
than 5 iterations. I notice almost immediately. I'm not having that
problem now.
Return-Path: <[EMAIL PROTECTED]>
Received: from murder ([unix socket])
(authenticated user=dave bits=0)
by boost-consulting.com (Cyrus v2.3.7) with LMTPA;
Sat, 28 Jul 2007 17:40:22 +0000
X-Sieve: CMU Sieve 2.3
Received: from bay0-omc3-s1.bay0.hotmail.com (bay0-omc3-s1.bay0.hotmail.com
[65.54.246.201])
by boost-consulting.com (8.13.8/8.13.8) with ESMTP id l6SHeMLl093047
for <[EMAIL PROTECTED]>; Sat, 28 Jul 2007 17:40:22 GMT
(envelope-from [EMAIL PROTECTED])
Received: from hotmail.com ([65.54.161.46]) by bay0-omc3-s1.bay0.hotmail.com
with Microsoft SMTPSVC(6.0.3790.2668);
Sat, 28 Jul 2007 10:40:00 -0700
Received: from mail pickup service by hotmail.com with Microsoft SMTPSVC;
Sat, 28 Jul 2007 10:40:00 -0700
Message-ID: <[EMAIL PROTECTED]>
Received: from 65.54.161.200 by by106fd.bay106.hotmail.msn.com with HTTP;
Sat, 28 Jul 2007 17:39:59 GMT
X-Originating-IP: [67.169.217.150]
X-Originating-Email: [EMAIL PROTECTED]
X-Sender: [EMAIL PROTECTED]
From: "The Cheese" <[EMAIL PROTECTED]>
To: [EMAIL PROTECTED]
Subject: Hey!
Date: Sat, 28 Jul 2007 10:39:59 -0700
Mime-Version: 1.0
Content-Type: text/plain; format=flowed
X-OriginalArrivalTime: 28 Jul 2007 17:40:00.0782 (UTC)
FILETIME=[52A12AE0:01C7D13E]
X-Spambayes-Classification: unsure; 0.85
Please to be calling me at home! 503 690 9095
-Matt
--
Dave Abrahams
Boost Consulting
http://www.boost-consulting.com
The Astoria Seminar ==> http://www.astoriaseminar.com
_______________________________________________
SpamBayes@python.org
http://mail.python.org/mailman/listinfo/spambayes
Check the FAQ before asking: http://spambayes.sf.net/faq.html
