loadFile.py 文件源码

def file2mat(filename):
    transformer = TfidfTransformer()
    vectorizer = CountVectorizer(min_df=1, ngram_range=(1,1))
    data = load(filename)
    reviews = [each_data['review'] for each_data in data]
    bag_of_word = vectorizer.fit_transform(reviews)
    tfidf = transformer.fit_transform(bag_of_word)

    aspect_label = collect_aspect_label(data)
    rating_label = collect_rating_label(data)
    return tfidf, aspect_label, rating_label

# ??wordVec ????? ?????????