data_utils.py 文件源码

def export_trimmed_glove_vectors(vocab, glove_filename, trimmed_filename, dim):
    """
    Saves glove vectors in numpy array

    Args:
        vocab: dictionary vocab[word] = index
        glove_filename: a path to a glove file
        trimmed_filename: a path where to store a matrix in npy
        dim: (int) dimension of embeddings
    """
    embeddings = np.zeros([len(vocab), dim])
    with open(glove_filename,encoding="utf-8") as f:
        for line in f:
            line = line.strip().split()
            word = line[0]
            embedding = map(float, line[1:])
            if word in vocab:
                word_idx = vocab[word]
                embeddings[word_idx] = np.asarray(list(embedding))
    np.savez_compressed(trimmed_filename, embeddings=embeddings)