Created
November 11, 2012 01:15
-
-
Save yagays/4053263 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#/usr/bin/env ruby | |
require 'pp' | |
def segment(text, segs) | |
words = [] | |
last = 0 | |
for i in 0..segs.length | |
if segs[i] == "1" | |
words << text[last..i] | |
last = i + 1 | |
end | |
end | |
words << text[last..segs.length] | |
words | |
end | |
def evaluate(text, segs) | |
words = segment(text, segs) | |
text_size = words.length | |
lexicon_size = words.uniq.join(" ").length | |
return text_size + lexicon_size | |
end | |
def flip(segs, pos) | |
if segs[pos] == "0" | |
segs[pos] = "1" | |
else | |
segs[pos] = "0" | |
end | |
segs | |
end | |
def flip_n(segs, n) | |
n.times{ | |
segs = flip(segs, rand(segs.length-1)) | |
} | |
segs | |
end | |
def anneal(text, segs, iterations, cooling_rate) | |
temperature = segs.length.to_f | |
while temperature > 0.5 | |
best_segs,best = segs, evaluate(text, segs) | |
iterations.times{ | |
guess = flip_n(segs, temperature.round) | |
score = evaluate(text, guess) | |
if score < best | |
best, best_segs = score, guess | |
end | |
} | |
score, segs = best, best_segs | |
temperature = temperature / cooling_rate | |
puts evaluate(text, segs).to_s + " " + segment(text, segs).join(" ") | |
end | |
segs | |
end | |
if __FILE__ == $PROGRAM_NAME | |
text = "doyouseethekittyseethedoggydoyoulikethekittylikethedoggy" | |
seg1 = "0000000000000001000000000010000000000000000100000000000" | |
seg2 = "0100100100100001001001000010100100010010000100010010000" | |
seg3 = "0000100100000011001000000110000100010000001100010000001" | |
anneal(text, seg1, 5000, 1.2) | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment