def merge_loop(double_set, list_name, file=None):
"""
进行团合并操作，循环直到不能合并
:param double_set:
:return:团成员最大数，最终的团
"""
bestSet = set()
oldSet = double_set
num_list = []
count_list = []
group_list = []
while len(oldSet) > 0:
print('成员数:', len(list(oldSet)[0]))
print('个数:', len(oldSet))
print(oldSet)
num_list.append(len(list(oldSet)[0]))
count_list.append(len(oldSet))
group_list.append(oldSet)
bestSet = oldSet
oldSet = merge_group(oldSet, double_set)
if file is not None:
group_list = utils.num_2_word(list_name, group_list)
utils.write_csv(['成员数', '个数', '团'], file, num_list, count_list,
group_list)
utils.save_pickle(file + '.pkl', group_list)
return len(list(bestSet)[0]), bestSet
def calculate(series, list_name, group_list_word):
"""
统计显示每个药方对应的团
:param series:
:param list_name:
:param group_list_word:
:return:
"""
group_list = utils.word_2_num(list_name, group_list_word)
series_list,index_list = series_2_list(series, list_name)
pattern_list = []
for item in series_list:
pattern = []
for group in group_list:
if (utils.is_in(group, item)):
pattern.append(group)
pattern_list.append(pattern)
series_list = utils.num_2_word(list_name, series_list)
pattern_list = utils.num_2_word(list_name, pattern_list)
utils.write_csv(['主治', '功能团'], 'data/pattern.csv', series_list, pattern_list)
def cluster_main2(relatives_list, list_name):
list_qyt = duplicate_removal(relatives_list, list_name)
# 使用数字代替列表中的项
list_num = utils.word_2_num(list_name, list_qyt)
for group_num in range(3, 9):
new_list = utils.cut_by_num(list_num, group_num)
list_num2 = del_by_correlation(new_list)
reWord = utils.num_2_word(list_name, list_num2)
# 创建二元组
doubleSet = create_double_set(list_num2)
max_num, bestSet = merge_loop(doubleSet, list_name,
'data/group' + str(group_num) + '.csv')
# 信息利用率
print(max_num, '/', group_num, '=', max_num / group_num)
for i, item in enumerate(relatives_list):
name = list_name[i]
for j in item:
if (name != j[0]):
relative_list[i].append(j[0])
if (name != j[1]):
relative_list[i].append(j[1])
utils.write_csv(['症状', '亲友团'], 'data/relatives.csv', list_name,
relative_list)
if __name__ == "__main__":
dd = calculate_correlation([(0, 1)], [0.1], [0.2, 0.3])
dd2 = calculate_correlation([(1, 0)], [0.1], [0.2, 0.3])
list_name = utils.load_pickle('list_name.txt')
list_fre = utils.load_pickle('list_fre.txt')
combinations_list = utils.load_pickle('combinations_list.txt')
combinations_fre = utils.load_pickle('combinations_fre.txt')
correlation = calculate_correlation(combinations_list, combinations_fre,
list_fre)
# combinations_name = comb_names(list_name,combinations_list)
combinations_name = utils.num_2_word(list_name, combinations_list)
column_1 = pd.Series(combinations_name, name='组合')
column_2 = pd.Series(correlation, name='关联度系数')
data = pd.concat([column_1, column_2], axis=1)
data = data.sort_values(by='关联度系数', ascending=False)
data.to_csv('rel2.csv', index=False, encoding='utf-8')
# relatives_list = relatives(list_name, data, 5)#舍弃改方法
relatives_list = relatives_2(list_name, data, 8)
utils.save_pickle('relatives_list.txt', relatives_list)