Function main

nlp_class2/glove_theano.py:181–219

(we_file, w2i_file, use_brown=True, n_files=50)

def main(we_file, w2i_file, use_brown=True, n_files=50):
    if use_brown:
        cc_matrix = "cc_matrix_brown.npy"
    else:
        cc_matrix = "cc_matrix_%s.npy" % n_files

    # hacky way of checking if we need to re-load the raw data or not
    # remember, only the co-occurrence matrix is needed for training
    if os.path.exists(cc_matrix):
        with open(w2i_file) as f:
            word2idx = json.load(f)
        sentences = [] # dummy - we won't actually use it
    else:
        if use_brown:
            keep_words = set([
                'king', 'man', 'woman',
                'france', 'paris', 'london', 'rome', 'italy', 'britain', 'england',
                'french', 'english', 'japan', 'japanese', 'chinese', 'italian',
                'australia', 'australian', 'december', 'november', 'june',
                'january', 'february', 'march', 'april', 'may', 'july', 'august',
                'september', 'october',
            ])
            sentences, word2idx = get_sentences_with_word2idx_limit_vocab(n_vocab=5000, keep_words=keep_words)
        else:
            sentences, word2idx = get_wikipedia_data(n_files=n_files, n_vocab=2000)
        
        with open(w2i_file, 'w') as f:
            json.dump(word2idx, f)

    V = len(word2idx)
    model = Glove(100, V, 10)
    model.fit(
        sentences,
        cc_matrix=cc_matrix,
        learning_rate=1e-4,
        reg=0.1,
        epochs=200,
    )
    model.save(we_file)


if __name__ == '__main__':