Too many "unsures"

[Kirrily Robert]

On Mon, May 07, 2007 at 11:07:57PM -0400, David Relson wrote:
> >From the info on your training regime I'm surprised to hear of your
> hundreds of unsures.  Have you looked at the X-Bogosity: lines for
> them?  Of particular value might be looking at the scores for messages
> that are (1) spam and that are (2) ham.  You might wish to change the
> spam/ham/unsure boundaries in bogofilter's config file.

Having now confirmed that training worked, I think you're right.

>   bogoutil -p /path/to/wordlist .MSG_COUNT

... is what I needed.  I think there was a linewrap in the email thread
I was reading in the archives, and I didn't realise I needed to put
".MSG_COUNT" in the command there.

Here's the output I got:

mailbox at ugh:~> bogoutil -p .bogofilter/wordlist.db .MSG_COUNT
                                 spam    good    Fisher
.MSG_COUNT                       4464    2482  0.500000

So that looks good.  Now I'll go see about my spam/ham boundaries.  Do 
people have any recommendations for common/sensible cutoffs?  I assumed 
that the default would be reasonably sensible, but that seems not to be 
the case.

K.


-- 
Kirrily Robert
skud at infotrope.net
http://infotrope.net