Re: Saving ifile database source files

Joe Kelsey <[email protected]> Sun, 31 Aug 2003 11:06:37 -0700
Newsgroups gmane.mail.ifile.general
Message-ID <1062353197.18799.20.camel@zircon>
On Sat, 2003-08-30 at 05:54, Clemens Fischer wrote:
> * Joe Kelsey:
> 
> > Currently, I plan to delete old database files to keep the directory
> > sizes under control.
> 
> you don't have to do this:  ifile keeps only so many words in its
> database.  for this it has a stoplist and throws out rarely used
> words.  back when i used ifile for spam/non-spam cassification, my
> database never grew beyond a few hundred kilobytes and i never had to
> trim it.

AFAIK, ifile keeps a single .ifile database.  When I say "database
source file" I mean what you call a spam corpus.  Why do I need a
complete spam corpus?  I think a week or two of spam sufficies to
provide 99% classification, as long as I include facilities for moving
mis-calssified objects back and forth.

You still have not addressed the need for a so-called "spam corpus".  I
believe that these caches of spam emails serve no useful purpose that
cannot be achieved by a one or two week cache.

/Joe