Dealing with wordlist mails
David Fries
dfries at mail.win.org
Sat Jan 31 19:30:51 CET 2004
On Wed, Jan 28, 2004 at 08:11:46AM -0500, David Relson wrote:
> On Wed, 28 Jan 2004 06:57:08 -0600
> David Fries wrote:
> >
> > My current database is over nine megs and it used to be around 1 meg
> > before these darn e-mails started showing up.
>
> Hi David,
>
> They have little effect for _me_. FWIW, my wordlist has 100,000+
> messages, approx 1,000,000 tokens, and is about 50MB. Of course, I've
> been doing this a bit longer.
>
> Question: how do you train bogofilter? what are the numbers for your
> wordlist?
>
> David
I forget how I started, but I am using `bogofilter -u` for my incoming
e-mail and `bogofilter -Ns -vv` or `bogofilter -Sn -vv` when it gets
it wrong.
bogofilter version 0.16.1
algorithm = fisher
robx = 0.415000 (4.15e-01)
robs = 0.010000 (1.00e-02)
min_dev = 0.100000 (1.00e-01)
ham_cutoff = 0.000000 (0.00e+00)
spam_cutoff = 0.950000 (9.50e-01)
block_on_subnets = no
replace_nonascii_characters = no
What is the option for finding out the size of the word list and
number of messages?
--
David Fries <dfries at mail.win.org>
http://fries.net/~david/pgpkey.txt
More information about the Bogofilter
mailing list