Mytfidf.py 文件源码

def runmytfidf(completeComment, topNumber):
    commentList = []

    #preprocessing the comments
    for i in range(0,10):
        commentList.append(tb(preprocessing(completeComment[i])))

    returnList=[]
    #Obtaing the Top Key words for all the pages
    for i, page in enumerate(commentList):
        scores = {word: tfidf(word, page, commentList) for word in page.words}
        sorted_words = sorted(scores.items(), key=lambda x: x[1], reverse=True)
        topWords=[]
        for word, score in sorted_words[:topNumber]:
            topWords.append(word)
        returnList.append(topWords)

    return returnList