gensim提取一个句子的关键词_新闻关键词提取

1.	defcombine(word_list, window=2):构造在window下的单词组合，用来构造单词之间的边。word_list  --  list of str, 由单词组成的列表。
2.	ifwindow < 2: window = 2
3.	forx inxrange(1, window):
4.	if  x >= len(word_list):
5.	break
6.	        word_list2 = word_list[x:]
7.	        res = zip(word_list, word_list2)
8.	for r in res:
9.	yield r 

1.	def get_similarity(word_list1, word_list2):word_list1, word_list2  --  分别代表两个句子，都是由单词组成的列表。
2.	words = list(set(word_list1 + word_list2))
3.	vector1 = [float(word_list1.count(word)) for word in words]
4.	 vector2 = [float(word_list2.count(word)) for word in words]
5.	 vector3 = [vector1[x] * vector2[x] for x in xrange(len(vector1))]
6.	 vector4 = [1 for num in vector3 if num > 0.]
7.	co_occur_num = sum(vector4)
8.	    if abs(co_occur_num) <= 1e-12:
9.	        return 0.
10.	denominator = math.log(float(len(word_list1))) + math.log(float(len(word_list2)))  # 分母
11.	Ifabs(denominator) < 1e-12:
12.	        return 0.
13.	    return co_occur_num / denominator

1.	def sort_words(vertex_source, edge_source, window=2, pagerank_config={'alpha': 0.85, }):
2.	    sorted_words = []
3.	    word_index = {}
4.	    index_word = {}
5.	    _vertex_source = vertex_source
6.	    _edge_source = edge_source
7.	    words_number = 0
8.	    for word_list in _vertex_source:
9.	        for word in word_list:
10.	            if not word in word_index:
11.	word_index[word] = words_number
12.	                index_word[words_number] = word
13.	                words_number += 1
14.	graph = np.zeros((words_number, words_number))
15.	    for word_list in _edge_source:
16.	        for w1, w2 in combine(word_list, window):
17.	            if w1 in word_index and w2 in word_index:
18.	 index1 = word_index[w1]
19.	                index2 = word_index[w2]
20.	                graph[index1][index2] = 1.0
21.	                graph[index2][index1] = 1.0
22.	    debug('graph:n', graph)
23.	    nx_graph = nx.from_numpy_matrix(graph)
24.	  scores = nx.pagerank(nx_graph, **pagerank_config)  
25.	sorted_scores = sorted(scores.items(), key=lambda item: item[1], reverse=True)
26.	    for index, score in sorted_scores:
27.	  item = AttrDict(word=index_word[index], weight=score)
28.	        sorted_words.append(item)
29.	    return sorted_words

1.	def sort_sentences(sentences, words, sim_func=get_similarity, pagerank_config={'alpha': 0.85, }):sentences --列表，元素是句子
    words --二维列表，子列表和sentences中的句子对应，子列表由单词组成sim_func --计算两个句子的相似性，参数是两个由单词组成的列表          pagerank_config -- pagerank的设置
2.	sorted_sentences = []
3.	   _source = words
4.	    sentences_num = len(_source)
5.	    graph = np.zeros((sentences_num, sentences_num))
6.	    for x in xrange(sentences_num):
7.	        for y in xrange(x, sentences_num):
8.	 similarity = sim_func(_source[x], _source[y])
9.	            graph[x, y] = similarity
10.	            graph[y, x] = similarity
11.	 nx_graph = nx.from_numpy_matrix(graph)
12.	    scores = nx.pagerank(nx_graph, **pagerank_config)  # this is a dict
13.	    sorted_scores = sorted(scores.items(), key=lambda item: item[1], reverse=True)
14.	    for index, score in sorted_scores:
15.	 item = AttrDict(index=index, sentence=sentences[index], weight=score)
16.	        sorted_sentences.append(item)
17.	  return sorted_sentences

1.	def segment(self, text, lower=True, use_stop_words=True, use_speech_tags_filter=False):lower -- 是否将单词小写（针对英文）                   use_stop_words -- 若为True，则利用停止词集合来过滤（去掉停止词 use_speech_tags_filter -- 是否基于词性进行过滤。若为True，则使用self.default_speech_tag_filter过滤。否则，不过滤。
2.	text = util.as_text(text)
3.	jieba_result = pseg.cut(text)
4.	if use_speech_tags_filter == True:
5.	jieba_result = [w for w in jieba_result if w.flag in self.default_speech_tag_filter]
6.	else:
7.	jieba_result = [w for w in jieba_result]
8.	word_list = [w.word.strip() for w in jieba_result if w.flag != 'x']去除特殊符号
9.	word_list = [word for word in word_list if len(word) > 0]
10.	if  lower:
11.	word_list = [word.lower() for word in word_list]
12.	if  use_stop_words:
13.	word_list = [word.strip() for word in word_list if word.strip() not in self.stop_words]
14.	return word_list

1.	def segment(self, text):
2.	 res = [util.as_text(text)]
3.	 util.debug(res)
4.	    util.debug(self.delimiters)
5.	for sep in self.delimiters:
6.	 text, res = res, []
7.	        for seq in text:
8.	            res += seq.split(sep)
9.	res = [s.strip() for s in res if len(s.strip()) > 0]
10.	    return res

1.	def segment(self, text, lower=False):
2.	text = util.as_text(text)
3.	sentences = self.ss.segment(text)
4.	words_no_filter = self.ws.segment_sentences(sentences=sentences,lower=lower,
use_stop_words=False,use_speech_tags_filter=False)
5.  words_no_stop_words = self.ws.segment_sentences(sentences=sentences,lower=lower,
use_stop_words=True,                    use_speech_tags_filter=False)
6. words_all_filters = self.ws.segment_sentences(sentences=sentences,lower=lower,
use_stop_words=True,use_speech_tags_filter=True)
7.return util.AttrDict(
8.sentences=sentences,
9.words_no_filter=words_no_filter,
10.words_no_stop_words=words_no_stop_words,
11.  words_all_filters=words_all_filters

1.	defanalyze(self, text,window=2,lower=False,vertex_source='all_filters',edge_source='no_stop_words',pagerank_config={'alpha': 0.85, }):text --文本内容，字符串。window --窗口大小，int，用来构造单词之间的边。默认值为2。lower--是否将文本转换为小写。默认为False。vertex_source--选择使用words_no_filter, words_no_stop_words, words_all_filters中的哪一个来构造pagerank对应的图中的节点。默认值为`'all_filters'`，可选值为`'no_filter', 'no_stop_words', 'all_filters'`。关键词也来自`vertex_source`。edge_source --选择使用words_no_filter, words_no_stop_words, words_all_filters中的哪一个来构造pagerank对应的图中的节点之间的边。默认值为`'no_stop_words'`，可选值为`'no_filter', 'no_stop_words', 'all_filters'`。边的构造要结合`window`参数。
2.	  self.text = text
3.	    self.word_index = {}
4.	    self.index_word = {}
5.	    self.keywords = []
6.	    self.graph = None
7.	 result = self.seg.segment(text=text, lower=lower)
8.	    self.sentences = result.sentences
9.	    self.words_no_filter = result.words_no_filter
10.	    self.words_no_stop_words = result.words_no_stop_words
11.	    self.words_all_filters = result.words_all_filters
12.	    options = ['no_filter', 'no_stop_words', 'all_filters']
13.	if vertex_source in options:
14.	  _vertex_source = result['words_' + vertex_source]
15.	else:
16.	 _vertex_source = result['words_all_filters']
17.	ifedge_source in options:
18.	_edge_source = result['words_' + edge_source]
19.	else:
20.	 _edge_source = result['words_no_stop_words']
21.    self.keywords = util.sort_words(_vertex_source, _edge_source,       window=window,pagerank_config=pagerank_config)

1.	def get_keywords(self, num=6, word_min_len=1):
2.	    result = []
3.	    count = 0
4.	for item in self.keywords:
5.	if count >= num:
6.	break
7.	iflen(item.word) >= word_min_len:
8.	 result.append(item)
9.	            count += 1
10.	return result

1.	defget_keyphrases(self, keywords_num=12, min_occur_num=2):
2.	    keywords_set = set([item.word for item in self.get_keywords(num=keywords_num,    word_min_len=1)])
3.	    keyphrases = set()
4.	for sentence in self.words_no_filter:
5.	one = []
6.	        for word in sentence:
7.	ifword in keywords_set:
8.	one.append(word)
9.	else:
10.	if len(one) > 1:
11.	keyphrases.add(''.join(one))
12.	iflen(one) == 0:
13.	 continue
14.	 else:
15.	one = []
16.	if len(one) > 1:
17.	keyphrases.add(''.join(one))
18.	return [phrase for phrase in keyphrases
19.	if self.text.count(phrase) >= min_occur_num]