process_data.py 文件源码

def load_bin_vec(fname, vocab):
    """
    Loads word vecs from word2vec bin file
    """
    word_vecs = OrderedDict()
    with open(fname, "rb") as f:
        header = f.readline()
        vocab_size, layer1_size = map(int, header.split())
        binary_len = np.dtype('float32').itemsize * layer1_size
        for line in xrange(vocab_size):
            word = []
            while True:
                ch = f.read(1)
                if ch == ' ':
                    word = ''.join(word)
                    break
                if ch != '\n':
                    word.append(ch)
            if word in vocab:
                idx = vocab[word]
                word_vecs[idx] = np.fromstring(f.read(binary_len), dtype='float32')
            else:
                f.read(binary_len)
    return word_vecs