utils.py 文件源码

def Word2Vec_encode(texts, wemb):

    out = np.zeros((len(texts), prm.dim_emb), dtype=np.float32)
    for i, text in enumerate(texts):
        words = wordpunct_tokenize(text)
        n = 0.
        for word in words:
            if word in wemb:
                out[i,:] += wemb[word]
                n += 1.
        out[i,:] /= max(1.,n)

    return out