diff options
author | Nathan Lasseter <nathan@4574.co.uk> | 2014-01-19 12:31:23 +0000 |
---|---|---|
committer | Nathan Lasseter <nathan@4574.co.uk> | 2014-01-19 12:31:23 +0000 |
commit | 6dd179efd69946dc8c68dc1875db2eb945c5c6dd (patch) | |
tree | 5cfbbf7c1b956247cd21447215b7356454e91c9f /markov-serialise.rb | |
parent | 9a43e1e56d6aea5dc36ddfabfb3f5e679927878e (diff) |
Renames and refactored serialise
Diffstat (limited to 'markov-serialise.rb')
-rwxr-xr-x | markov-serialise.rb | 27 |
1 files changed, 0 insertions, 27 deletions
diff --git a/markov-serialise.rb b/markov-serialise.rb deleted file mode 100755 index 1199453..0000000 --- a/markov-serialise.rb +++ /dev/null @@ -1,27 +0,0 @@ -#!/usr/bin/env ruby - -CHUNK = ARGV[1].to_i - -stats = {"__SETTINGS__" => {"__CHUNK__" => CHUNK}} - -words = File.readlines(ARGV[0]) - .map(&:split) - .flatten - -(0 .. (words.length - CHUNK - CHUNK)).each do |i| - k = words[i...(i+CHUNK)] - v = words[(i+CHUNK)] - if stats.include?(k) then - t = stats[k] - if t.include?(v) then - t[v] += 1 - else - t[v] = 1 - end - else - stats[k] = Hash.new - stats[k][v] = 1 - end -end - -File.new(ARGV[2], "w").print(Marshal::dump(stats)) |