word2vec_wiki.py 文件源码

def load_save_word2vec_model(line_words, model_filename):
    # ????
    feature_size = 500
    content_window = 5
    freq_min_count = 3
    # threads_num = 4
    negative = 3   #best????hierarchical softmax??(??????????)????negative sampling??(??????)?
    iter = 20

    print("word2vec...")
    tic = time.time()
    if os.path.isfile(model_filename):
        model = models.Word2Vec.load(model_filename)
        print(model.vocab)
        print("Loaded word2vec model")
    else:
        bigram_transformer = models.Phrases(line_words)
        model = models.Word2Vec(bigram_transformer[line_words], size=feature_size, window=content_window, iter=iter, min_count=freq_min_count,negative=negative, workers=multiprocessing.cpu_count())
        toc = time.time()
        print("Word2vec completed! Elapsed time is %s." % (toc-tic))
        model.save(model_filename)
        # model.save_word2vec_format(save_model2, binary=False)
        print("Word2vec Saved!")
    return model