TEXT_PATH = '../jsjs.txt'  # 文本路径
DICT_PATH = 'person.txt'  # 人物字典路径
SYNONYMOUS_DICT_PATH = 'synonymous_dict.txt'  # 同义词路径
SAVE_NODE_PATH = 'node.csv'
SAVE_EDGE_PATH = 'edge.csv''''
person_counter是一个计数器，用来统计人物出现的次数。{'a':1,'b':2}
person_per_paragraph每段文字中出现的人物[['a','b'],[]]
relationships保存的是人物间的关系。key为人物A，value为字典，包含人物B和权值。
'''
person_counter = defaultdict(int)  # 人物出场次数计数器
person_per_paragraph = []
relationships = {}
synonymous_dict = {}

def count_person(self):'''统计人物出场次数，添加每段的人物:return:'''paragraphs = self.get_clean_paragraphs()synonymous = self.synonymous_names()print('start process node')with codecs.open(self._dict_path, 'r', 'utf-8') as f:name_list = f.read().split(' 10 nrrn')  # 获取干净的name_listfor p in paragraphs:jieba.load_userdict(self._dict_path)# 分词，为每一段初始化新字典poss = jieba.cut(p)self._person_per_paragraph.append([])for w in poss:# 判断是否在姓名字典以及同义词区分if w not in name_list:continueif synonymous.get(w):w = synonymous[w]# 往每段中添加人物self._person_per_paragraph[-1].append(w)# 初始化人物关系，计数if self._person_counter.get(w) is None:self._relationships[w] = {}self._person_counter[w] += 1return self._person_counter

def calc_relationship(self):'''统计人物关系权值:return:'''print("start to process edge")# 遍历每一段落，笛卡尔积形式，统计人物关系for p in self._person_per_paragraph:for name1 in p:for name2 in p:if name1 == name2:continueif self._relationships[name1].get(name2) is None:self._relationships[name1][name2] = 1else:self._relationships[name1][name2] += 1return self._relationships

def save_node_and_edge(self):'''根据dephi格式保存为csv:return:'''with codecs.open(SAVE_NODE_PATH, "a+", "utf-8") as f:f.write("Id,Label,Weightrn")for name, times in self._person_counter.items():f.write(name + "," + name + "," + str(times) + "rn")with codecs.open(SAVE_EDGE_PATH, "a+", "utf-8") as f:f.write("Source,Target,Weightrn")for name, edges in self._relationships.items():for v, w in edges.items():if w > 3:f.write(name + "," + v + "," + str(w) + "rn")print('save file successful!')