def group_all(self):
"""
先将基于不同数量亲友团的聚类结果进行清理、删除被包含在更大团中的团，然后将清洗后的聚类结果进行结合并输出
:return:
"""
group_all = []
group_name = []
for i in range(max_relatives_nums, min_relatives_nums-1, -1):
group_path = os.path.join("data", "group"+str(i)+".csv.pkl")
group_name.append("group"+str(i))
group_all.append(group_clean(group_path))
# print("group_all:", group_all)
write_csv(group_name, group_all_path, group_all) # 将不同亲友团数量下的所有聚类结果进行输出
group_all_dict = {} # 记录各个团出现的次数
self.group_all_2 = [] # 用于保存所有亲友团数量下的功效团
for group_list in group_all:
for group in group_list:
group_all_dict[tuple(group)] = group_all_dict[tuple(group)]+1 if tuple(group) in group_all_dict else 1
print("group_all_dict:", group_all_dict)
for group in group_all_dict.keys():
self.group_all_2.append(group) # 确保self.group_all_2中不出现重复的团
print("self.group_all_2:", self.group_all_2)
# 人工审核找到信息利用率最高的亲友团数量，即最佳的亲友团数量，然后以该亲友团数量下的结果作为最佳结果
group_best_name = []
group_best = []
for i in range(12, 13):
group_path = os.path.join("data", "group"+str(i)+".csv.pkl")
group_best_name.append("group"+str(i))
group_best.append(group_clean(group_path))
write_csv(group_best_name, group_best_path, group_best)
self.group_best = group_best[0]
print(self.group_best)
def merge_loop(double_set, root_name, file=None):
"""
进行团合并操作，循环直到不能合并
:param double_set:强相关的两两组合
:param root_name:词根列表
:param file:对聚类结果进行dump的目标路径
:return:团成员最大数，最终的团
"""
best_set = set()
old_set = double_set
num_list = []
count_list = []
group_list = []
while len(old_set) > 0:
# oldSet为需要继续进行合并操作的团
print('成员数:', len(list(old_set)[0])) # oldSet中团的成员数量
print('个数:', len(old_set)) # oldSet中团的数量
# print("old_set", old_set)
num_list.append(len(list(old_set)[0]))
count_list.append(len(old_set))
group_list.append(old_set)
best_set = old_set
old_set = merge_group(old_set, double_set) # 返回新组合成的团，对这些团继续进行合并操作
# 若oldSet不存在，则说明聚类收敛、合并到最大的团了，无法继续合并了
if file is not None:
group_list = index_2_word(root_name, group_list)
write_csv(['成员数', '个数', '团'], file, [num_list, count_list, group_list])
save_pickle(file + '.pkl', group_list)
# print("best_set", best_set)
return len(list(best_set)[0]), best_set
def search_relatives(self):
"""
先计算每一对两两组合之间的互信息，然后根据最大亲友团数量找到每个词根的亲友团
:return:
"""
correlation = calculate_correlation(self.combine_index, self.combine_fre, self.root_fre)
self.combine_name = index_2_word(self.root_name, self.combine_index) # 将单独的词根和组合中的索引转换为词
# 将互信息按照大小降序排列大小，然后再写入到csv中
data = write_csv(['组合', '关联度系数'], correlation_path, [self.combine_name, correlation])
# 获取每个症状的亲友团list
self.relatives_list = create_relatives(self.root_name, data, max_relatives_nums)
print("relatives_list", self.relatives_list) # 这里的亲友团是用嵌套列表存储的，用字典存储应该更好吧？键值对为变量-亲友团列表