# 加载中文停用词 stop_words = set(stopwords.words('chinese')) broadcastVar = spark.sparkContext.broadcast(stop_words)  # 中文文本分词 def tokenize(text):     return list(jieba.cut(text))  # 删除中文停用词 def delete_stopwords(tokens, stop_words):     filtered_words = [word for word in tokens if word not in stop_words]     filtered_text = ' '.join(filtered_words)     return filtered_text  # 删除标点符号和特定字符 def remove_punctuation(input_string):     punctuation = string.punctuation + "！？｡。＂＃＄％＆＇（）＊＋，－／：；＜＝＞＠［＼］＾＿｀｛｜｝～｟｠｢｣､、〃》「」『』【】〔〕〖〗〘〙〚〛〜〝〞〟〾〿–—‘’‛“”„‟…‧﹏.t n很好是去还不人太都中"     translator = str.maketrans('', '', punctuation)     no_punct = input_string.translate(translator)     return no_punct  def Thematic_focus(text):     from gensim import corpora, models     num_words = min(len(text) // 50 + 3, 10) # 动态调整主题词数量      tokens = tokenize(text)     stop_words = broadcastVar.value     text = delete_stopwords(tokens, stop_words)     text = remove_punctuation(text)     tokens = tokenize(text)      dictionary = corpora.Dictionary([tokens])     corpus = [dictionary.doc2bow(tokens)]     lda_model = models.LdaModel(corpus, num_topics=1, id2word=dictionary, passes=50)     topics = lda_model.show_topics(num_words=num_words)     for topic in topics:         return str(topic)