my %good;  # count of token occurance in "good" email
my %bad;   # count of token occurance in "bad" email
my $ngood; # number of "good" messages
my $nbad;  # number of "bad" messages

sub findProb {
    my $word = shift;

    my $g = 2 * $good{$word} || 0;
    my $b =     $bad{$word}  || 0;

    return undef unless ($g + $b) > 5;

    my $num = min(1.0, $b/$nbad);
    my $denom = min(1.0, $g/$ngood) + min(1.0, $b/$nbad);
    my $prob = $num / $denom;

    return 0.99 if $prob > 0.99;
    return 0.01 if $prob < 0.01;
    return $prob;
}