text2numpy.py 文件源码

def main():
    args = docopt("""
    Usage:
        text2numpy.py <path>
    """)

    path = args['<path>']

    matrix = read_vectors(path)
    iw = sorted(matrix.keys())

    new_matrix = np.zeros(shape=(len(iw), len(matrix[iw[0]])), dtype=np.float32)
    for i, word in enumerate(iw):
        if word in matrix:
            new_matrix[i, :] = matrix[word]

    np.save(path + '.npy', new_matrix)
    save_vocabulary(path + '.vocab', iw)