def domain_classfiy_by_text(user_weibo):#根据用户微博文本进行领域分类
'''
输入数据：字典
{uid:weibo字符串(多条微博用逗号连接),...}
输出数据：字典
{uid:label1,uid2:label2,...}
'''
domain_dict,domain_count = load_train()
len_dict = dict()
total = 0
for k,v in domain_dict.items():
len_dict[k] = len(v)
total = total + len(v)
sw = load_scws()
black = load_black_words()
result_data = dict()
p_data = dict()
for k,v in user_weibo.items():
start = time.time()
words = sw.participle(v)
domain_p = start_p()
word_list = dict()
for word in words:
if (word[1] in cx_dict) and 3 < len(word[0]) < 30 and (word[0] not in black) and (word[0] not in single_word_whitelist):#选择分词结果的名词、动词、形容词，并去掉单个词
if word_list.has_key(word[0]):
word_list[word[0]] = word_list[word[0]] + 1
else:
word_list[word[0]] = 1
for d_k in domain_p.keys():
start_time = time.time()
domain_p[d_k] = com_p(word_list,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
end_time = time.time()
print '%s domain takes %s second...' % (d_k,(end_time-start_time))
label,rank_data = rank_dict(domain_p)
result_data[k] = label
p_data[k] = rank_data
end = time.time()
print '%s takes %s second...' % (k,(end-start))
return result_data,p_data
mediaw = getMediaWords()
def getBusinessWords():
businessw = []
f = open('./domain_dict/businessw.txt', 'r')
for line in f:
businessw.append(line.strip()) # 商业人士词汇
return businessw
businessw = getBusinessWords()
s = load_scws()
def user_domain_classifier_v2(user):
r = user
label = labels[11]
verified_type = r['verified_type']
location = r['location'].encode('utf-8')
province = location.split(' ')[0]
followers_count = r['followers_count']
statuses_count = r['statuses_count']
name = r['name']
description = r['description']
return mediaw
mediaw = getMediaWords()
def getBusinessWords():
businessw = []
f = open('./domain_dict/businessw.txt', 'r')
for line in f:
businessw.append(line.strip()) # 商业人士词汇
return businessw
businessw = getBusinessWords()
s = load_scws()
def user_domain_classifier_v2(user):
r = user
label = labels[11]
verified_type = r['verified_type']
location = r['location'].encode('utf-8')
province = location.split(' ')[0]
followers_count = r['followers_count']
statuses_count = r['statuses_count']
name = r['name']
description = r['description']
