Questions about spamicity

[Michael Rensing]

On Thu, 2003-05-29 at 16:10, Greg Louis wrote:
> On 20030529 (Thu) at 1525:25 -0700, Michael Rensing wrote:
> > Does it make sense for a message to have spamicity=0.000000? That's
> > what's getting put into my message headers. As in:
> > 
> > X-Bogosity:  No, tests=bogofilter, spamicity=0.000000,
version=0.13.2.1
> 
> > When I run bogofilter -M -v against my spam mailbox, only a few have
a
> > non-zero spamicity. Any ideas what's going on? Do I need to reset
the
> > database somehow? If so, how?
> 
> You don't mention a few things we'd need to know to be able to help
> effectively:
> - what version of bogofilter are you running?

Look at the X-Bogosity message again :) Version 0.13.2.1

> - how did you create your training database?

It's the database I had from the previous version of bogofilter I was
running. I believe that was a 0.9 something version.

> - how many spam and nonspam messages were used in that process?

[michael at opus michael]$ bogoutil -w ~/.bogofilter .MSG_COUNT
                       spam   good
.MSG_COUNT             1907   2101

[michael at opus michael]$ bogoutil -w ~/.bogofilter .ROBX
                       spam   good
.ROBX                372050      0

> - how did you decide what was spam and what was nonspam for purposes
of
>   training?

I was using the old (version 0.9) recipe for procmail where anything
identified as non-spam was added to the ham list, and spam was added to
the spam. If a message was mis-identified, I corrected it with -N and
-H. (or was that -n and -h; I forget but always checked the usage...)

> I suspect the solution to your problem can be deduced from the answers
> to those four questions (mainly the last 3 of course).

I just didn't know what info to send at first.

-- 
Michael Rensing <michael.rensing at shaw.ca>