def load_weibo(uid_weibo):
result_data = dict()
p_data = dict()
for k,v in uid_weibo.iteritems():
domain_p = sta_dict()
for d_k in domain_p.keys():
domain_p[d_k] = com_p(v,DOMAIN_DICT[d_k],DOMAIN_COUNT[d_k],LEN_DICT[d_k],TOTAL)#计算文档属于每一个类的概率
result_data[k] = domain_p
p_data[k] = rank_result(domain_p)
return result_data,p_data
def topic_classfiy(uid_list,uid_weibo):#话题分类主函数
'''
用户话题分类主函数
输入数据示例：
uidlist:uid列表（[uid1,uid2,uid3,...]）
uid_weibo:分词之后的词频字典（{uid1:{'key1':f1,'key2':f2...}...}）
输出数据示例：字典
用户18个话题的分布：
{uid1:{'art':0.1,'social':0.2...}...}
用户关注较多的话题（最多有3个）：
{uid1:['art','social','media']...}
'''
if not len(uid_weibo) and len(uid_list):
result_data = dict()
uid_topic = dict()
for uid in uid_list:
result_data[uid] = sta_dict()
uid_topic[uid] = ['life']
return result_data,uid_topic
elif len(uid_weibo) and not len(uid_list):
uid_list = uid_weibo.keys()
elif not len(uid_weibo) and not len(uid_list):
result_data = dict()
uid_topic = dict()
return result_data,uid_topic
else:
pass
result_data,uid_topic = load_weibo(uid_weibo)#话题分类主函数
for uid in uid_list:
if not result_data.has_key(uid):
result_data[uid] = sta_dict()
uid_topic[uid] = ['life']
return result_data,uid_topic