def Edmundson(result, answer):
# result 机器摘要
# answer 参考摘要
r_s = set(TFIDF.cut_by_sentence(result))
r_a = set(TFIDF.cut_by_sentence(answer))
share = r_s & r_a
return len(share) / len(r_a)
def textrank_sentence(self, doc, threshold):
'''
使用 TextRank 算法抽取关键句，使用论文中提供的相似度计算公式，详见实验报告
抽取 `size` 个句子作为下一次喂给 MMR 的输入
'''
# create the undirect graph for the textrank sentences
graphh = Graph(self.d, self.iteration)
sentences = TFIDF.cut_by_sentence(doc)
# change the size_word dynamicly
if len(sentences) < 9:
size_word = 2
else:
# maybe 6
size_word = 5
if len(sentences) <= 4:
print("The content is too short, do not need to summary !")
return sentences
# size may need to large as 0.6
size = round(len(sentences) * 0.3)
if size == 0:
size = min(1, len(sentences))
# use TextRank to get the keywords from the sentence
# Get Keywords, need to fix
# get the data
sentences_array = []
for sent in sentences:
result = self.textrank_words(sent, size_word)
if result == False:
# do not find the keywords with the TextRank
result = []
# TFIDF 补充关键字,并考虑合并关键词组
result = append_keywords(sent, result, self.keywords_doc)
# result = join_result(result, sent)
# add the keywords with the TFIDF
if result == False:
words = []
else:
words = list(map(lambda x: x[0], result))
sentences_array.append(words)
# Get Keywords Over, need to finish fix operator
# 初始化 TextRank 图
for i, sent1 in enumerate(sentences_array):
for j, sent2 in enumerate(sentences_array):
if i == j or len(sent1) == 0 or len(sent2) == 0:
continue
weights = textrank_similiar(np.array(sent1), np.array(sent2))
if weights > threshold:
# similiar
graphh.add_edge(i, j, weights)
# 图排序开始
graphh.rank()
result = graphh.WS
if result is None:
print("Error, because of the high threshold !")
return False
result = sorted(result.items(), key=itemgetter(1), reverse=True)
if size > len(result):
print("Overload !")
size = len(result)
result = result[:size]
# 句子抽取
result_sent = []
for i, j in result:
result_sent.append(sentences[i])
return result_sent
