For people interested in a cleaned-up, commented and de-obfuscated word2vec, I recently ported the original C code to Python [1].<p>My HN submission of this endeavour received no love, but I think it's worthwhile nevertheless as the Python code is not only more concise, readable and extendable, but the training's actually faster too [2].<p>[1] <a href="https://github.com/piskvorky/gensim/blob/develop/gensim/models/word2vec.py" rel="nofollow">https://github.com/piskvorky/gensim/blob/develop/gensim/mode...</a><p>[2] <a href="http://radimrehurek.com/2013/09/word2vec-in-python-part-two-optimizing/" rel="nofollow">http://radimrehurek.com/2013/09/word2vec-in-python-part-two-...</a>