def test_cron_text_attribute_v2(user_keywords_dict, user_weibo_dict, online_pattern_dict, character_start_ts,filter_keywords_dict):
status = False
print 'start cron_text_attribute'
uid_list = user_keywords_dict.keys()
#get user flow information: hashtag, activity_geo, keywords
print 'get flow result'
flow_result = get_flow_information_v2(uid_list, user_keywords_dict)
print 'flow result len:', len(flow_result)
#get user profile information
print 'get register result'
register_result = get_profile_information(uid_list)
print 'register result len:', len(register_result)
#print user_keywords_dict
#get user topic and domain by bulk action
print 'get topic and domain'
topic_results_dict, topic_results_label = topic_classfiy(uid_list, user_keywords_dict)
print topic_results_dict,topic_results_label
domain_results = domain_classfiy(uid_list, user_keywords_dict)
domain_results_dict = domain_results[0]
domain_results_label = domain_results[1]
print 'topic result len:', len(topic_results_dict)
print 'domain result len:', len(domain_results_dict)
#get user character attribute
print 'get character result'
#type_mark = 0/1 for identify the task input status---just sentiment or text
character_start_time = ts2datetime(character_start_ts)
character_end_time = ts2datetime(character_start_ts + DAY * CHARACTER_TIME_GAP - DAY)
print 'character_start_time:', character_start_time
print 'character_end_time:', character_end_time
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)
print 'character result len:', len(character_sentiment_result_dict), len(character_text_result_dict)
#get user fansnum max
fansnum_max = get_fansnum_max()
#get user activeness by bulk_action
print 'get activeness results'
activeness_results = get_activity_time(uid_list)
print 'activeness result len:', len(activeness_results)
#get user inlfuence by bulk action
print 'get influence'
influence_results = get_influence(uid_list)
print 'influence results len:', len(influence_results)
#get user sensitive by bulk action
print 'get sensitive'
sensitive_results, sensitive_string_results, sensitive_dict_results = get_sensitive(uid_list)
print 'sensitive results len:', len(sensitive_results)
# compute text attribute
bulk_action = []
count = 0
for user in uid_list:
count += 1
results = {}
#get user text attribute: online_pattern
results['online_pattern'] = json.dumps(online_pattern_dict[user])
try:
results['online_pattern_aggs'] = '&'.join(online_pattern_dict[user].keys())
except:
results['online_pattern_aggs'] = ''
results['uid'] = str(user)
#add user flow information: hashtag, activity_geo, keywords
flow_dict = flow_result[str(user)]
results = dict(results, **flow_dict)
#jln filter keyword
results['filter_keywords'] = json.dumps(filter_keywords_dict[user])
#add user topic attribute
user_topic_dict = topic_results_dict[user]
user_label_dict = topic_results_label[user]
results['topic'] = json.dumps(user_topic_dict) # {'topic1_en':pro1, 'topic2_en':pro2...}
results['topic_string'] = topic_en2ch(user_label_dict) # 'topic1_ch&topic2_ch&topic3_ch'
#add user domain attribute
user_domain_dict = domain_results_dict[user]
user_label_dict = domain_results_label[user]
results['domain_v3'] = json.dumps(user_domain_dict) # [label1_en, label2_en, label3_en]
results['domain'] = domain_en2ch(user_label_dict) # label_ch
#add user character_sentiment attribute
character_sentiment = character_sentiment_result_dict[user]
results['character_sentiment'] = character_sentiment
#add user character_text attribtue
character_text = character_text_result_dict[user]
results['character_text'] = character_text
#add user profile attribute
register_dict = register_result[str(user)]
results = dict(results, **register_dict)
#add user_evaluate attribute---importance
results['importance'] = get_importance(results['domain'], results['topic_string'], results['fansnum'], fansnum_max)
#add user_evaluate attribute---activeness
user_activeness_time = activeness_results[user]
user_activeness_geo = json.loads(results['activity_geo_dict'])[-1]
results['activeness'] = get_activeness(user_activeness_geo, user_activeness_time)
#add user_evaluate attribute---influence
results['influence'] = influence_results[user]
#add user sensitive attribute
results['sensitive'] = sensitive_results[user]
results['sensitive_dict'] = sensitive_dict_results[user]
results['sensitive_string'] = sensitive_string_results[user]
#bulk_action
action = {'index':{'_id': str(user)}}
bulk_action.extend([action, results])
status = save_user_results(bulk_action)
return status
def test_cron_text_attribute_v2(user_keywords_dict, user_weibo_dict,
online_pattern_dict, character_start_ts,
relation_mark_dict, task_mark,
submit_user_dict, submit_ts_dict):
#mark index or update
if submit_user_dict and submit_ts_dict:
save_type = 'index'
else:
save_type = 'update'
status = False
print 'start cron_text_attribute'
uid_list = user_keywords_dict.keys()
#get user flow information: hashtag, activity_geo, keywords, ip
print 'get flow result'
flow_result = get_flow_information_v2(uid_list, user_keywords_dict)
print 'flow result len:', len(flow_result)
#get user profile information
print 'get register result'
register_result = get_profile_information(uid_list)
print 'register result len:', len(register_result)
#get user topic and domain by bulk action
print 'get topic and domain'
topic_results_dict, topic_results_label = topic_classfiy(
uid_list, user_keywords_dict)
domain_results = domain_classfiy(uid_list, user_keywords_dict)
domain_results_dict = domain_results[0]
domain_results_label = domain_results[1]
print 'topic result len:', len(topic_results_dict)
print 'domain result len:', len(domain_results_dict)
#get user fansnum max
fansnum_max, user_fansnum_dict = get_fansnum_max(uid_list)
print 'fansnum len:', len(user_fansnum_dict)
#get user activeness by bulk_action
print 'get activeness results'
activeness_results = get_activity_time(uid_list)
print 'activeness result len:', len(activeness_results)
#get user inlfuence by bulk action
print 'get influence'
influence_results = get_influence(uid_list)
print 'influence results len:', len(influence_results)
# compute text attribute
bulk_action = []
count = 0
for user in uid_list:
count += 1
results = {}
#add submit_user and submit_ts
if save_type == 'index':
results['submit_user'] = submit_user_dict[user]
results['submit_ts'] = submit_ts_dict[user]
#get user text attribute: online_pattern
results['online_pattern'] = json.dumps(online_pattern_dict[user])
try:
results['online_pattern_aggs'] = '&'.join(
online_pattern_dict[user].keys())
except:
results['online_pattern_aggs'] = ''
results['uid'] = str(user)
#add user flow information: hashtag, activity_geo, keywords, ip
flow_dict = flow_result[str(user)]
results = dict(results, **flow_dict)
#add user topic attribute
user_topic_dict = topic_results_dict[user]
user_label_dict = topic_results_label[user]
results['topic'] = json.dumps(
user_topic_dict) # {'topic1_en':pro1, 'topic2_en':pro2...}
results['topic_string'] = topic_en2ch(
user_label_dict) # 'topic1_ch&topic2_ch&topic3_ch'
#add user domain attribute
user_domain_dict = domain_results_dict[user]
user_label_dict = domain_results_label[user]
results['domain_v3'] = json.dumps(
user_domain_dict) # [label1_en, label2_en, label3_en]
results['domain'] = domain_en2ch(user_label_dict) # label_ch
#add user profile attribute
register_dict = register_result[str(user)]
results = dict(results, **register_dict)
#add user_evaluate attribute---importance
results['importance'] = get_importance(results['domain'],
results['topic_string'],
user_fansnum_dict[user],
fansnum_max)
#add user_evaluate attribute---activeness
user_activeness_time = activeness_results[user]
user_activeness_geo = json.loads(results['activity_geo_dict'])[-1]
results['activeness'] = get_activeness(user_activeness_geo,
user_activeness_time)
#add user_evaluate attribute---influence
results['influence'] = influence_results[user]
#bulk_action
if save_type == 'index':
action = {'index': {'_id': str(user)}}
bulk_action.extend([action, results])
else:
action = {'update': {'_id': str(user)}}
bulk_action.extend([action, {'doc': results}])
status = save_user_results(bulk_action)
print 'save es_user_portrait:', status
#compute relation
if task_mark == 'user':
save_status = person_organization(uid_list, relation_mark_dict)
print 'save_status:', save_status
if status and save_status:
status = True
else:
status = False
#print 'save neo4j:', save_status
return status