def main(): t = normal.zh2hans(text) sents = normal.get_sentences(t) doc = [] for sent in sents: words = seg.seg(sent) words = normal.filter_stop(words) doc.append(words) rank = textrank.TextRank(doc) rank.solve() for index in rank.top_index(5): print(sents[index]) keyword_rank = textrank.KeywordTextRank(doc) keyword_rank.solve() for w in keyword_rank.top_index(5): print(w)
def summaryTextRank(docs, limit=5): ''' docs = [ '第一篇微博', '第二篇微博', ... ] ''' merged_doc = [] for doc in docs: words = jieba.lcut(doc) words = normal.filter_stop(words) merged_doc.append(words) rank = textrank.TextRank(merged_doc) rank.solve() ret = [] for index in rank.top_index(limit): ret.append(docs[index]) return ret
def query_xym(): offset = request.values['offset'] pagesize = request.values['pageSize'] resp = XymTripModel.query.offset(offset).limit(pagesize) t = normal.zh2hans( "随着智能手机和平板电脑的普及,相机也变得无处不在,而且分享照片也越来越简单。MOOC的明星教授说,把45分钟的讲座变成10分钟一段的视频让他们被迫“升级课程”。不是每个老师都能通过这种方式吸引一批学生,但是他们可以参考这个经验,为课堂制作自己的视频,例如实地考察录像。让整个班都出去跑一趟可能不可行,但利用视频和照片,可以把考察点“带”到课室中来。利用智能手机耳机上配备的话筒,还可以为视频配上讲解,从而高效地用多个视频介绍完一个知识点。" ) sents = normal.get_sentences(t) doc = [] for sent in sents: words = seg.seg(sent) words = normal.filter_stop(words) doc.append(words) rank = textrank.TextRank(doc) rank.solve() for index in rank.top_index(5): print(sents[index]) keyword_rank = textrank.KeywordTextRank(doc) keyword_rank.solve() for w in keyword_rank.top_index(5): print(w) return "\'..."
def summaryOfSents(docs, limit=5): ''' docs = [ '第一篇微博', '第二篇微博', ... ] ''' merged_doc = [] sents = [] for doc in docs: sents_t = normal.get_sentences(doc) sents += sents_t for sent in sents_t: words = jieba.lcut(sent) words = normal.filter_stop(words) merged_doc.append(words) rank = textrank.TextRank(merged_doc) rank.solve() ret = [] for index in rank.top_index(limit): ret.append(sents[index]) return ret
def getJson(fold, filename): result = {} try: count = 0 cotent = u'' title = '' time = '' abstract = '' path = fold + '/' + filename # ======================================== # 读取文件的时间、标题、内容 # ======================================== for line in open(path, 'r'): if (count == 0): title = line count += 1 # print (title) continue if (count == 1): time = line count += 1 # print (time) continue if (count > 1): count += 1 cotent += line # print (line) # ======================================== # 生成摘要 # ======================================= t = normal.zh2hans(cotent) sents = normal.get_sentences(t) doc = [] for sent in sents: words = seg.seg(sent) words = normal.filter_stop(words) doc.append(words) rank = textrank.TextRank(doc) rank.solve() for index in rank.top_index(5): abstract = abstract + sents[index] + ' ' keyword_rank = textrank.KeywordTextRank(doc) keyword_rank.solve() word0 = {} word1 = {} word2 = {} word3 = {} word4 = {} wordcount = 0 for w in keyword_rank.top_index(5): if wordcount == 0: word0["word"] = w word0["frequency"] = float(cotent.count(w)) / float( len(cotent)) if wordcount == 1: word1["word"] = w word1["frequency"] = float(cotent.count(w)) / float( len(cotent)) if wordcount == 2: word2["word"] = w word2["frequency"] = float(cotent.count(w)) / float( len(cotent)) if wordcount == 3: word3["word"] = w word3["frequency"] = float(cotent.count(w)) / float( len(cotent)) if wordcount == 4: word4["word"] = w word4["frequency"] = float(cotent.count(w)) / float( len(cotent)) wordcount += 1 s = SnowNLP(cotent) score = (s.sentiments - 0.5) * 2 # -1-1规范化 keywords = [word0, word1, word2, word3, word4] result["code"] = 0 result["message"] = "sucess" except IOError: result["code"] = 1 result["message"] = "wrong format" return result result["tilte"] = title.strip() result["time"] = time.strip() result['abstract'] = abstract result['sentiment'] = score result["keywords"] = keywords return result
6.用好你的相机 随着智能手机和平板电脑的普及,相机也变得无处不在,而且分享照片也越来越简单。MOOC的明星教授说,把45分钟的讲座变成10分钟一段的视频让他们被迫“升级课程”。不是每个老师都能通过这种方式吸引一批学生,但是他们可以参考这个经验,为课堂制作自己的视频,例如实地考察录像。让整个班都出去跑一趟可能不可行,但利用视频和照片,可以把考察点“带”到课室中来。利用智能手机耳机上配备的话筒,还可以为视频配上讲解,从而高效地用多个视频介绍完一个知识点。 将MOOC应用到传统课堂教学 随着大规模网络公开课的发展,教师可以考虑把在线教育的方法应用到自己的课堂教学中。MOOC的课程制作涉及比较复杂的技术,但使用这些课程几乎不费吹灰之力,而且成本也远远不及课程制作。没有加入edX或Coursera的大部分学校可以进行更多自创内容的尝试,就像自出版一样,这也是许多cMOOC的尝试。教师也可以向自己的目标努力。通过打开课堂,建立网络社区和制作教学视频,可以让更多的教师和学生享受到MOOC的投入带来的收益。 ''' from snownlp import normal from snownlp import seg from snownlp.summary import textrank if __name__ == '__main__': t = normal.zh2hans(text) sents = normal.get_sentences(t) doc = [] for sent in sents: words = seg.seg(sent) words = normal.filter_stop(words) doc.append(words) rank = textrank.TextRank(doc) rank.solve() for index in rank.top_index(5): print(sents[index]) keyword_rank = textrank.KeywordTextRank(doc) keyword_rank.solve() for w in keyword_rank.top_index(5): print(w)
if __name__ == '__main__': # 获取文本和停用词 doc = get_doc(text_file) stopWords = get_text(file_name=stopwords_file) # print(doc) # 切分成句子 sents = doc2sent(doc) # print(sents) # 摘要提取 word_list = [segment_jieba(sent, stopWords) for sent in sents] # print(word_list) rank = textrank.TextRank(word_list) rank.solve() # key_sents = [sents[index] for index in rank.top_index(5)] # print(key_sents) for index in rank.top_index(5): print(sents[index]) # keyword_rank = textrank.KeywordTextRank(word_list) # keyword_rank.solve() # for w in keyword_rank.top_index(10): # print(w) # xmnlp摘要提取 xmnlp.set_stopword('/home/kdd/nlp/stop_words.txt') xmnlp.set_userdict('/home/kdd/nlp/userdict.txt') t = xmnlp.keyphrase(doc)