train_vector_model.py 文件源码

def trainWord2Vector(sentence_count, vector_dimension, train_count):

    lines, model_out, vector_out = "sources/splited_words.txt", "result/word2vec.model", "result/pre_word2vec.vector"
    logging.info("??????")
    sentences = LineSentence(lines)
    # ??min_count=3??????3?? ????????????word2vec.vector?
    # workers????????????CPU??  ???3
    # sg?????????
    model = Word2Vec(sentences, sg=1, size=vector_dimension, window=8,
                     min_count=0, workers=multiprocessing.cpu_count())
    # ?????  ??????
    for i in range(train_count):
        model.train(sentences=sentences, total_examples=sentence_count, epochs=model.iter)

    # trim unneeded model memory = use(much) less RAM
    # model.init_sims(replace=True)
    model.save(model_out)
    model.wv.save_word2vec_format(vector_out)