Question

我想在过滤过程中删除“ dan”，但没有用。这是我的代码

for row in readCSV:
        _word = []
        username = row[0]
        date = row[1]
        text = row[2].lower()
        text = re.sub(r'@[A-Za-z0-9_]+','',text)
        text = re.sub(r'http\S+', '',text)

        text = replaceMultiple(text, ["!","@","#","$","%","^","&","*","(",
                                      ")","_","-","+","=","{","}","[","]",
                                      "\\","/",",",".","?","<",">",":",";",
                                      "'",'"',"~","0","1","2","3","4","5","6","7","8","9"], '')
        text = text.strip()
        nltk_tokens = nltk.word_tokenize(text)
        stop_words = set(stopwords.words("indonesian"))
        stop_words_new = ['aku','dan','duh','hhhmmm','thn','nih','tgl',
                          'hai','jazz','bro','broo','msh','']
        new_stopwords_list = stop_words.union(stop_words_new)

stop_words_new中的

words被删除，但'dan'除外。为什么？

Answer 1

该代码不起作用，因为您正在将一个带有列表的集合加入其中。尝试将stop_words_new设置为集合而不是列表

停用词未删除一个词

1 个答案: