Last active
July 15, 2016 12:41
-
-
Save mudge/ff8da1b92d00a82f3d5ec04e3ad3a7d9 to your computer and use it in GitHub Desktop.
Markov chain generator in JavaScript (with a Ruby "compiler")
This file contains hidden or 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
| <!doctype html> | |
| <meta charset="utf-8"> | |
| <input id="input" type="text"> <a href="#" id="scifi">Sci-Fi it!</a> | |
| <p id="output"></p> | |
| <script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.1.0/jquery.min.js"></script> | |
| <script> | |
| function sampleWithFrequency(coll) { | |
| var choice = Math.random(), | |
| length = coll.length; | |
| for (var i = 0; i < length; i += 1) { | |
| var word = coll[i][0], | |
| frequency = coll[i][1]; | |
| if (frequency > choice) { | |
| return word; | |
| } | |
| } | |
| } | |
| function titleize(sentence) { | |
| var words = sentence.split(/\s+/), | |
| output = [], | |
| word; | |
| for (var i = 0, length = words.length; i < length; i += 1) { | |
| word = words[i]; | |
| output.push(word.charAt(0).toUpperCase() + word.slice(1)); | |
| } | |
| return output.join(' '); | |
| } | |
| function markov(seed, numberOfWords, dict) { | |
| var wordCount = 0, | |
| word = seed, | |
| words = [word], | |
| nextWord; | |
| while (wordCount < numberOfWords) { | |
| if (!dict.words.hasOwnProperty(word)) { | |
| break; | |
| } | |
| nextWord = sampleWithFrequency(dict.words[word]); | |
| words.push(nextWord); | |
| word = nextWord; | |
| wordCount += 1; | |
| } | |
| return words.join(' '); | |
| } | |
| $.getJSON('/wells.json', function (dict) { | |
| $('#output').text(markov(sampleWithFrequency(dict.startWords), 10, dict)); | |
| $('#scifi').on('click', function (e) { | |
| e.preventDefault(); | |
| var words = $('#input').val().split(/\s+/), | |
| length = words.length, | |
| sentence = []; | |
| for (var i = 0; i < words.length; i += 1) { | |
| var word = words[i], | |
| numberOfWords = Math.floor(Math.random() * 3) + 1; | |
| sentence.push(markov(word, numberOfWords, dict)); | |
| } | |
| $('#output').text(titleize(sentence.join(' '))); | |
| }); | |
| }); | |
| </script> |
This file contains hidden or 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
| require 'json' | |
| words = Hash.new { |h, k| h[k] = Hash.new(0) } | |
| start_words = Hash.new(0) | |
| end_words = Hash.new(0) | |
| ARGF.read.split(/\s+/).each_cons(2) do |(word, next_word)| | |
| words[word][next_word] += 1 | |
| if word =~ /[.?!]\z/ | |
| start_words[next_word] += 1 | |
| end_words[word] += 1 | |
| end | |
| end | |
| words.each do |word, next_words| | |
| total = next_words.values.inject(:+).to_f | |
| cumulative_frequency = 0 | |
| next_words.each do |next_word, count| | |
| cumulative_frequency += count / total | |
| next_words[next_word] = cumulative_frequency | |
| end | |
| words[word] = next_words.to_a | |
| end | |
| total = start_words.values.inject(:+).to_f | |
| cumulative_frequency = 0 | |
| start_words.each do |word, count| | |
| cumulative_frequency += count / total | |
| start_words[word] = cumulative_frequency | |
| end | |
| total = end_words.values.inject(:+).to_f | |
| cumulative_frequency = 0 | |
| end_words.each do |word, count| | |
| cumulative_frequency += count / total | |
| end_words[word] = cumulative_frequency | |
| end | |
| puts JSON.dump( | |
| words: words, | |
| startWords: start_words.to_a, | |
| endWords: end_words.to_a | |
| ) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment