def summarize4(sents, docs=None):
if not docs:
docs = [list(Tokenize(sent)) for sent in sents]
sim_res = bm25_weights(docs)
rank = TextRank(sim_res)
rank.solve()
top_n_summary = []
for index in sorted(rank.top_index(3)):
top_n_summary.append(sents[index])
return u"。 ".join(top_n_summary).replace("\r", "").replace("\n", "") + u"。"
def summarize4(sents, docs=None):
if not docs:
docs = [list(Tokenize(sent)) for sent in sents]
sim_res = bm25_weights(docs)
rank = TextRank(sim_res)
rank.solve()
top_n_summary = []
for index in sorted(rank.top_index(3)):
top_n_summary.append(sents[index])
return u'。 '.join(top_n_summary).replace('\r', '').replace('\n', '') + u'。'
class Order:
def __init__(self, text, seg=None, tagger=None):
self.text = text
self.tagger = tagger if tagger is not None else self.get_tagger()
self.seg = seg if seg is not None else self.get_seg()
self.words_merge = None
def get_keywords(self, limit=5, merge=False):
doc = []
sentences = self.get_sentences()
for sentence in sentences:
words = list(self.seg.seg(sentence))
words = self.filter_stop(words)
doc.append(words)
self.keywordrank = KeywordRank(doc)
self.keywordrank.solve()
result = []
for w in self.keywordrank.top_index(limit):
result.append(w)
if merge:
wm = self.words_merge.merge(self.text, result)
return wm.merge()
return result
def get_summaries(self, limit=5):
doc = []
sentences = self.get_sentences()
for sentence in sentences:
words = list(self.seg.seg(sentence))
words = self.filter_stop(words)
doc.append(words)
self.textrank = TextRank(doc)
self.textrank.solve()
result = []
for index in self.textrank.top_index(limit):
result.append(sentences[index])
return result
def get_sentences(self):
line_break_re = re.compile('[\r\n]')
delimiter_re = re.compile('[，。？！；]')
sentences = []
for line in line_break_re.split(self.text):
line = line.strip()
if not line:
continue
for sentence in delimiter_re.split(line):
sentence = sentence.strip()
if not sentence:
continue
sentences.append(sentence)
return sentences
def get_seg(self, fname='seg.pickle'):
seg = Seg()
seg.load(fname)
return seg
def get_tagger(self, fname='tag.pickle'):
tagger = Tag()
tagger.load(fname)
return tagger
def filter_stop(self, words):
return list(filter(lambda x: x not in stop_words, words))