diff options
author | Chris Dyer <cdyer@cab.ark.cs.cmu.edu> | 2012-10-02 00:19:43 -0400 |
---|---|---|
committer | Chris Dyer <cdyer@cab.ark.cs.cmu.edu> | 2012-10-02 00:19:43 -0400 |
commit | e26434979adc33bd949566ba7bf02dff64e80a3e (patch) | |
tree | d1c72495e3af6301bd28e7e66c42de0c7a944d1f /gi/pf/make-freq-bins.pl | |
parent | 0870d4a1f5e14cc7daf553b180d599f09f6614a2 (diff) |
cdec cleanup, remove bayesian stuff, parsing stuff
Diffstat (limited to 'gi/pf/make-freq-bins.pl')
-rwxr-xr-x | gi/pf/make-freq-bins.pl | 26 |
1 files changed, 0 insertions, 26 deletions
diff --git a/gi/pf/make-freq-bins.pl b/gi/pf/make-freq-bins.pl deleted file mode 100755 index fdcd3555..00000000 --- a/gi/pf/make-freq-bins.pl +++ /dev/null @@ -1,26 +0,0 @@ -#!/usr/bin/perl -w -use strict; - -my $BASE = 6; -my $CUTOFF = 3; - -my %d; -my $num = 0; -while(<>){ - chomp; - my @words = split /\s+/; - for my $w (@words) {$d{$w}++; $num++;} -} - -my @vocab = sort {$d{$b} <=> $d{$a}} keys %d; - -for (my $i=0; $i<scalar @vocab; $i++) { - my $most = $d{$vocab[$i]}; - my $least = 1; - - my $nl = -int(log($most / $num) / log($BASE) + $CUTOFF); - if ($nl < 0) { $nl = 0; } - print "$vocab[$i] $nl\n" -} - - |