baselines.py 文件源码

def parseToBOW():
    vectorizer = CountVectorizer(min_df=1)
    texts = pickle.load(open(OUTFILE, 'rb'))[0]
    tdm = vectorizer.fit_transform(texts)
    transformer = TfidfTransformer()
    tdidf = transformer.fit_transform(tdm)
    f = open(DATASET_PATH + "BOW.p", "wb")
    pickle.dump(tdm, f)
    f.close()
    f = open(DATASET_PATH + "BOW_TDIDF.p", "wb")
    pickle.dump(tdidf, f)
    f.close()