From dfbc278c1057555fda9312291c8024049e00b7d8 Mon Sep 17 00:00:00 2001
From: Chris Dyer <cdyer@cs.cmu.edu>
Date: Sat, 10 Mar 2012 16:42:12 -0500
Subject: frequency-based binning

---
 gi/pf/make-freq-bins.pl | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)
 create mode 100755 gi/pf/make-freq-bins.pl

(limited to 'gi/pf/make-freq-bins.pl')

diff --git a/gi/pf/make-freq-bins.pl b/gi/pf/make-freq-bins.pl
new file mode 100755
index 00000000..fdcd3555
--- /dev/null
+++ b/gi/pf/make-freq-bins.pl
@@ -0,0 +1,26 @@
+#!/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"
+}
+
+
-- 
cgit v1.2.3