bogus bogotuning

[Greg Louis]

On 20040129 (Thu) at 0848:40 +0100, Boris 'pi' Piwinger wrote:
> Greg Louis <glouis at dynamicro.on.ca> wrote:
> 
> >At one point there was actually an
> >option to do just what you wanted, but we took it out again because it
> >wasn't found helpful.  Now you come along and ask for it, we try
> >(persistently) to explain why it's a bad idea,
> 
> I asked many times (and never got an answer) why it would be
> bad for train-on-error. There the database will be
> significantly below the limit, even if you have tens of
> thousands messages to test with.

Sorry about not answering your question.  I haven't any experience with
bogotune and training on error from scratch, as I always do at least a
10,000-of-each full-train before beginning training on error.  The one
experiment I did with training on error from scratch preceded the first
version of bogotune by many months, and gave me no encouragement to do
any more (basically, it worked fine but took longer to get to an
effective volume -- no surprise there).

> BTW: There was this call for message bases to review
> bogofilter's defaults. What was the result? I have never
> seen it. I also have never got an answer how that process
> went with my train-to-exhaustion database (only a
> preliminary test).

Still waiting for a couple more promised large corpora.  You remind me,
though, that I was going to ask about those once the holiday season was
over.  I'll do that off list.

I think David might have tried your train-to-exhaustion but I haven't
done anything with it myself.  When I get the remaining corpora and
start on that project again, I might give it a whirl just for fun.

-- 
| G r e g  L o u i s         | gpg public key: 0x400B1AA86D9E3E64 |
|  http://www.bgl.nu/~glouis |   (on my website or any keyserver) |
|  http://wecanstopspam.org in signatures helps fight junk email. |