diff options
| author | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2012-11-05 15:29:46 +0100 |
|---|---|---|
| committer | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2012-11-05 15:29:46 +0100 |
| commit | 6f29f345dc06c1a1033475eac1d1340781d1d603 (patch) | |
| tree | 6fa4cdd7aefd7d54c9585c2c6274db61bb8b159a /gi/pf/make-freq-bins.pl | |
| parent | b510da2e562c695c90d565eb295c749569c59be8 (diff) | |
| parent | c615c37501fa8576584a510a9d2bfe2fdd5bace7 (diff) | |
merge upstream/master
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" -} - - |