pred_vae.py 文件源码

def test(args):
    corpus = load_corpus(args.input)
    vocab, docs = corpus['vocab'], corpus['docs']
    n_vocab = len(vocab)

    doc_keys = docs.keys()
    X_docs = []
    for k in doc_keys:
        X_docs.append(vecnorm(doc2vec(docs[k], n_vocab), 'logmax1', 0))
        del docs[k]
    X_docs = np.r_[X_docs]

    vae = load_vae_model(args.load_model)

    doc_codes = vae.predict(X_docs)
    dump_json(dict(zip(doc_keys, doc_codes.tolist())), args.output)
    print 'Saved doc codes file to %s' % args.output

    # if args.save_topics:
    #     topics = get_topics(vae, revdict(vocab), topn=10)
    #     write_file(topics, args.save_topics)
    #     print 'Saved topics file to %s' % args.save_topics