def deal_bulk_action(user_info_list, fansnum_max):
start_ts = time.time()
uid_list = user_info_list.keys()
#acquire bulk user weibo data
if WEIBO_API_INPUT_TYPE == 0:
user_keywords_dict, user_weibo_dict, character_start_ts = read_flow_text_sentiment(
uid_list)
else:
user_keywords_dict, user_weibo_dict, character_start_ts = read_flow_text(
uid_list)
#compute attribute--domain, character, importance
#get user domain
domain_results = domain_classfiy(uid_list, user_keywords_dict)
domain_results_dict = domain_results[0]
domain_results_label = domain_results[1]
#get user character
character_start_time = ts2datetime(character_start_ts)
character_end_time = ts2datetime(character_start_ts +
DAY * CHARACTER_TIME_GAP - DAY)
character_sentiment_result_dict = classify_sentiment(
uid_list, user_weibo_dict, character_start_time, character_end_time,
WEIBO_API_INPUT_TYPE)
character_text_result_dict = classify_topic(uid_list, user_keywords_dict)
bulk_action = []
for uid in uid_list:
results = {}
results['uid'] = uid
#add user domain attribute
user_domain_dict = domain_results_dict[uid]
user_label_dict = domain_results_label[uid]
results['domain_v3'] = json.dumps(user_domain_dict)
results['domain'] = domain_en2ch(user_label_dict)
#add user character_sentiment attribute
character_sentiment = character_sentiment_result_dict[uid]
results['character_sentiment'] = character_sentiment
#add user character_text attribute
character_text = character_text_result_dict[uid]
results['character_text'] = character_text
#get user importance
user_topic_string = user_info_list[uid]['topic_string'].encode('utf-8')
user_fansnum = user_info_list[uid]['fansnum']
results['importnace'] = get_importance(results['domain'],
user_topic_string, user_fansnum,
fansnum_max)
#bulk action
action = {'update': {'_id': uid}}
bulk_action.extend([action, {'doc': results}])
es_user_portrait.bulk(bulk_action,
index=portrait_index_name,
doc_type=portrait_index_type)
end_ts = time.time()
#log_should_delete
print '%s sec count %s' % (end_ts - start_ts, len(uid_list))
def deal_bulk_action(user_info_list, fansnum_max):
start_ts = time.time()
uid_list = user_info_list.keys()
#acquire bulk user weibo data
if WEIBO_API_INPUT_TYPE == 0:
user_keywords_dict, user_weibo_dict, character_start_ts = read_flow_text_sentiment(uid_list)
else:
user_keywords_dict, user_weibo_dict, character_start_ts = read_flow_text(uid_list)
#compute attribute--domain, character, importance
#get user domain
domain_results = domain_classfiy(uid_list, user_keywords_dict)
domain_results_dict = domain_results[0]
domain_results_label = domain_results[1]
#get user character
character_end_time = ts2datetime(character_start_ts)
character_start_time = ts2datetime(character_start_ts - DAY * CHARACTER_TIME_GAP)
character_sentiment_result_dict = classify_sentiment(uid_list, user_weibo_dict, character_start_time, character_end_time, WEIBO_API_INPUT_TYPE)
character_text_result_dict = classify_topic(uid_list, user_keywords_dict)
bulk_action = []
for uid in uid_list:
results = {}
results['uid'] = uid
#add user domain attribute
user_domain_dict = domain_results_dict[uid]
user_label_dict = domain_results_label[uid]
results['domain_v3'] = json.dumps(user_domain_dict)
results['domain'] = domain_en2ch(user_label_dict)
#add user character_sentiment attribute
character_sentiment = character_sentiment_result_dict[uid]
results['character_sentiment'] = character_sentiment
#add user character_text attribute
character_text = character_text_result_dict[uid]
results['character_text'] = character_text
#get user importance
user_topic_string = user_info_list[uid]['topic_string'].encode('utf-8')
user_fansnum = user_info_list[uid]['fansnum']
results['importnace'] = get_importance(results['domain'], user_topic_string, user_fansnum, fansnum_max)
#bulk action
action = {'update':{'_id': uid}}
bulk_action.extend([action, {'doc': results}])
es_user_portrait.bulk(bulk_action, index=portrait_index_name, doc_type=portrait_index_type)
end_ts = time.time()
#log_should_delete
print '%s sec count %s' % (end_ts - start_ts, len(uid_list))
def deal_bulk_action(user_info_list, fansnum_max):
start_ts = time.time()
uid_list = user_info_list.keys()
#acquire bulk user weibo data
if WEIBO_API_INPUT_TYPE == 0:
user_keywords_dict, user_weibo_dict, online_pattern_dict, character_start_ts = read_flow_text_sentiment(uid_list)
else:
user_keywords_dict, user_weibo_dict, online_pattern_dict, character_start_ts = read_flow_text(uid_list)
#compute attribute--keywords, topic, online_pattern
#get user topic results by bulk action
topic_results_dict, topic_results_label = topic_classfiy(uid_list, user_keywords_dict)
domain_results = domain_classfiy(uid_list, user_keywords_dict)
politics_results = political_classify(uid_list, user_keywords_dict)
#update school attribute---is_school/school_string/school_dict
#school_results_dict = get_school(uid_list)
#get bulk action
bulk_action = []
for uid in uid_list:
results = {}
results['uid'] = uid
#results['is_school'] = school_results_dict[uid]['is_school']
#results['school_string'] = school_results_dict[uid]['school_string']
#results['school_dict'] = school_results_dict[uid]['school_dict']
#print 'is_school, school_string, school_dict:', results['is_school'],type(results['is_school']) ,results['school_string'],type(results['school_string']), results['school_dict'], type(results['school_dict'])
#add user topic attribute
user_topic_dict = topic_results_dict[uid]
user_label_dict = topic_results_label[uid]
results['topic'] = json.dumps(user_topic_dict)
results['topic_string'] = topic_en2ch(user_label_dict)
#add user domain attribute
user_domain_dict = domain_results[uid]
domain_list = domain_en2ch(user_domain_dict)
if domain_list:
results['domain_list'] = json.dumps(domain_list)
results['domain'] = domain_list[0]
else:
results['domain'] = "其他"
results['domain_list'] = json.dumps(["其他"])
politics_label = politics_results[uid]
results['politics'] = politics_en2ch(politics_label)
#add user keywords attribute
try:
keywords_dict = user_keywords_dict[uid]
except:
keywords_dict = {}
keywords_top50 = sorted(keywords_dict.items(), key=lambda x:x[1], reverse=True)[:50]
keywords_top50_string = '&'.join([keyword_item[0] for keyword_item in keywords_top50])
results['keywords'] = json.dumps(keywords_top50)
results['keywords_string'] = keywords_top50_string
#add online_pattern
try:
user_online_pattern = json.dumps(online_pattern_dict[uid])
except:
user_online_pattern = json.dumps({})
results['online_pattern'] = user_online_pattern
try:
results['online_pattern_aggs'] = '&'.join(user_online_pattern.keys())
except:
results['online_pattern_aggs'] = ''
#add user importance
user_domain = user_info_list[uid]['domain'].encode('utf-8')
user_fansnum = user_info_list[uid]['fansnum']
results['importance'] = get_importance(user_domain, results['topic_string'], user_fansnum, fansnum_max)
# politics
politics_label = politics_results[user]
results['politics'] = politics_en2ch(politics_label)
#bulk action
action = {'update':{'_id': uid}}
bulk_action.extend([action, {'doc': results}])
print 'bulk_action:', bulk_action
#es_user_portrait.bulk(bulk_action, index=portrait_index_name, doc_type=portrait_index_type)
end_ts = time.time()
#log_should_delete
#print '%s sec count %s' % (end_ts - start_ts, len(uid_list))
#log_should_delete
start_ts = end_ts
