def get_keywords(self, text, keywords_num=None):
self.__text = text #original raw text
# text = text.replace('\n', '')
# text = text.replace('\r', '')
text = util.as_text(text) #处理编码问题
sentences = util.cut_sentences(
text) # this text here means a full text content ; all in one line
#sentences用于记录已分词文章最原本的句子，wordlist_sents用于提取关键词
sentences, wordlist_sents = util.psegcut_filter_words(
sentences, self.__stop_words, self.__use_stopword)
self.__sentences = sentences
word_index, index_word, words_number = self.build_worddict(
wordlist_sents)
graph = self.build_word_grah(wordlist_sents,
words_number,
word_index,
window=self.__window)
scores = util.weight_map_rank(graph,
max_iter=self.__max_iter,
tol=self.__tol)
if keywords_num is None:
keywords_num = int(words_number / 3)
keywords_selected = nlargest(keywords_num, zip(scores, count()))
else:
keywords_selected = nlargest(keywords_num, zip(scores, count()))
return [(index_word[item[1]], item[0]) for item in keywords_selected
] # item: [(score,word_index) list]
def summarize(self,text,n):
text = text.replace('\n', '')
text = text.replace('\r', '')
text = util.as_text(text)#处理编码问题
tokens=util.cut_sentences(text)
#sentences用于记录文章最原本的句子，sents用于各种计算操作
sentences, sents=util.cut_filter_words(tokens,self.__stop_words,self.__use_stopword)
if self.__use_w2v:
sents = self.filter_dictword(sents)
graph = self.create_graph_sentence(sents,self.__use_w2v)
scores = util.weight_map_rank(graph,self.__max_iter,self.__tol)
sent_selected = nlargest(n, zip(scores, count()))
sent_index = []
for i in range(n):
sent_index.append(sent_selected[i][1]) # 添加入关键词在原来文章中的下标
return [sentences[i] for i in sent_index]
def summarize(self,text,n):
text = text.replace('\n', '')
text = text.replace('\r', '')
text = util.as_text(text)#处理编码问题
tokens=util.cut_sentences(text)
#sentences用于记录文章最原本的句子，sents用于各种计算操作
sentences,sents=util.psegcut_filter_words(tokens,self.__stop_words,self.__use_stopword)
word_index, index_word, words_number=self.build_worddict(sents)
graph=self.build_word_grah(sents,words_number,word_index,window=self.__window)
scores = util.weight_map_rank(graph,max_iter=self.__max_iter,tol=self.__tol)
sent_selected = nlargest(n, zip(scores, count()))
sent_index = []
for i in range(n):
sent_index.append(sent_selected[i][1]) # 添加入关键词在原来文章中的下标
return [index_word[i] for i in sent_index]