summaryrefslogtreecommitdiff
path: root/gi/pf/make-freq-bins.pl
diff options
context:
space:
mode:
authorChris Dyer <cdyer@cs.cmu.edu>2012-10-11 14:06:32 -0400
committerChris Dyer <cdyer@cs.cmu.edu>2012-10-11 14:06:32 -0400
commit9339c80d465545aec5a6dccfef7c83ca715bf11f (patch)
tree64c56d558331edad1db3832018c80e799551c39a /gi/pf/make-freq-bins.pl
parent438dac41810b7c69fa10203ac5130d20efa2da9f (diff)
parentafd7da3b2338661657ad0c4e9eec681e014d37bf (diff)
Merge branch 'master' of https://github.com/redpony/cdec
Diffstat (limited to 'gi/pf/make-freq-bins.pl')
-rwxr-xr-xgi/pf/make-freq-bins.pl26
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"
-}
-
-