create_probability_hash(1) Expaminator create_probability_hash(1)



NAME
       create_probability_hash

SYNOPSIS
       Usage:  create_probability_hash  [-v] [-d] [-f] \
                     probability-hash  good-hash  spam-hash


DESCRIPTION
       create_probability_hash  creates a dictionary of all words
       found in both the "normal", or "good"  word-hash  and  the
       spam word-hash.
       Currently, the probability assigned to each word is calcu­
       lated exactly as outlined in Paul  Graham's  "A  Plan  for
       Spam", <http://www.paulgraham.com/spam.html>.

       Command-line options:

       -v   be  verbose;  print  a  dot for every 1000 words pro­
           cessed.

       -d  write debugging messages (frequency &  probability  of
           each word)

       -f   'force'; if 'probability-hash' already exists, delete
           and re-ceate it.

       probability-hash - probability hash to be created

       good-hash        - hash of all words in non-spam messages

       spam-hash        - hash of all words in spams

       If a hashfile name is a bare file name, then the  environ­
       ment variable '$SPAMDIR' will be prepended.  If a hashfile
       name is a bare file name, and '$SPAMDIR' is not  set,  the
       current  working  directory  is  used.  To use the current
       working directory, use the form: './hashfile-name'



ENVIRONMENT
       $SPAMDIR, as discussed above.


FILES
       Required:  A "normal" (non-spam) hash  and  a  spam  hash,
       both created by 'create_word_hash'


SEE ALSO
       make_new_database, create_word_hash


COPYRIGHT
       Copyright (c) 2002, J.B.Ward
       <bward2@users.sourceforge.net>




Expaminator                Nov.29,2002 create_probability_hash(1)