Re: Re: Empty message apparently not tokenized

> Cool!  What sort of cleanup do you perform on these small hash files?
> I'd like to add a bit more about the hash format in the readme and
> cleanup is an important factor with that format.

You know, the cleanup is one thing I have struggled with. To be honest for 
a long time I used no cleanup at all. I know the hash collisions are 
overwriting terms but I thought, heck, it's probably more or less throwing 
out random terms.

Recently I have been using cleanup 4 40
But it seems I'm getting more classification errors than when I was doing 
no cleanups. Not sure how to optimally tweak this.

Very happy with the hashes overall though. I liked the fixed size database 
tremendously




-------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc. Do you grep through log files
for problems?  Stop!  Download the new AJAX search engine that makes
searching your log files as easy as surfing the  web.  DOWNLOAD SPLUNK!
http://sel.as-us.falkag.net/sel?cmd=lnk&kid=103432&bid=230486&dat=121642