zero count tokens in decision matrix

Burton:

Am I correct tokens with ham and spam counts of zero may appear in a
decision matrix?
I tested this by building an empty database,
then classifying a simple message.
All slots of the decision matrix were given to tokens with probabilities of 0.3,
and the combined probability was 0.3.

Granted, this should be a very rare thing (only when the database is
extremely small),
but if this is true, why do you advocate forcing these tokens into the
decision matrix?

I guess the other approach would be to just not consider any token
that hasn't reached maturity (combined count of 5 or whatever).
Then if you don't have enough tokens to fill the decision matrix, so be it.

Again, this should be a very rare occurrence, but interesting to note.
Your thoughts?


-------------------------------------------------------
This SF.Net email is sponsored by xPML, a groundbreaking scripting language
that extends applications into web and mobile media. Attend the live webcast
and join the prime developer group breaking into this new coding territory!
http://sel.as-us.falkag.net/sel?cmd=lnk&kid0944&bid$1720&dat1642