def get_community_userinfo(uid_list,core_uidlist,outer_uidlist):
user_list = []
# print 'es_user_profile::',es_user_profile
user_result = es_user_profile.mget(index = profile_index_name,doc_type = profile_index_type,body = {'ids':uid_list})['docs']
core_user = []
for item in user_result:
user_dict = dict()
user_dict['uid'] = item['_id']
if item['found']:
user_dict['photo_url']=item['_source']['photo_url']
user_dict['nick_name']=item['_source']['nick_name']
user_dict['sex']=item['_source']['sex']
user_dict['friendsnum']=item['_source']['friendsnum']
user_dict['fansnum']=item['_source']['fansnum']
user_dict['user_location']=item['_source']['user_location']
else:
user_dict['photo_url']=''
user_dict['nick_name']=''
user_dict['sex']=''
user_dict['friendsnum']=''
user_dict['fansnum']=''
user_dict['user_location']=''
#核心人物判断
core_mark = len(list(set(item['_id'].split())&set(core_uidlist)))
if core_mark > 0:
user_dict['core_user'] = 1
core_user.append(user_dict)
else:
user_dict['core_user'] = 0
user_list.append(user_dict)
#社区外人物信息
outer_userlist = []
outeruser_result = es_user_profile.mget(index = profile_index_name,doc_type = profile_index_type,body = {'ids':outer_uidlist})['docs']
for item in outeruser_result:
user_dict = dict()
user_dict['uid'] = item['_id']
if item['found']:
user_dict['photo_url']=item['_source']['photo_url']
user_dict['nick_name']=item['_source']['nick_name']
user_dict['sex']=item['_source']['sex']
user_dict['friendsnum']=item['_source']['friendsnum']
user_dict['fansnum']=item['_source']['fansnum']
user_dict['user_location']=item['_source']['user_location']
else:
user_dict['photo_url']=''
user_dict['nick_name']=''
user_dict['sex']=''
user_dict['friendsnum']=''
user_dict['fansnum']=''
user_dict['user_location']=''
outer_userlist.append(user_dict)
return json.dumps(user_list),json.dumps(core_user),json.dumps(outer_userlist)
def group_evaluate(xnr_user_no, nodes, all_influence, all_sensitive, G=None):
result = {}
result['xnr_user_no'] = xnr_user_no
result['nodes'] = nodes
result['num'] = len(nodes)
if G:
sub_g = G.subgraph(nodes)
else:
sub_g = get_users(xnr_user_no, nodes)
result['density'] = round(nx.density(sub_g), 4)
result['cluster'] = round(nx.average_clustering(sub_g), 4)
result['transitivity'] = round(nx.transitivity(sub_g), 4)
# for i in user_es.mget(index=sensitive_index, doc_type=sensitive_type,body={'ids':nodes}, fields=['sensitive_week_ave'],_source=False)['docs']:
# print i#['fields']['sensitive_week_ave']
influence_result = [
float(i['fields']['bci_week_ave'][0]) if i['found'] else 0
for i in es_user_profile.mget(index=influence_index,
doc_type=influence_type,
body={'ids': nodes},
fields=['bci_week_ave'],
_source=False)['docs']
]
sensitive_result = [
float(i['fields']['sensitive_week_ave'][0]) if i['found'] else 0
for i in es_user_profile.mget(index=sensitive_index,
doc_type=sensitive_type,
body={'ids': nodes},
fields=['sensitive_week_ave'],
_source=False)['docs']
]
result['max_influence'] = round(
(max(influence_result) / float(all_influence)) * 100, 4)
result['mean_influence'] = round(
((sum(influence_result) / len(influence_result)) /
float(all_influence)) * 100, 4)
max_sensitive = round((max(sensitive_result) / float(all_sensitive)) * 100,
4)
result['mean_sensitive'] = round(
((sum(sensitive_result) / len(sensitive_result)) /
float(all_sensitive)) * 100, 4)
if max_sensitive > 100:
result['max_sensitive'] = 100.0000
else:
result['max_sensitive'] = max_sensitive
# result['mean_sensitive'] = 0.4670
# result['mean_influence'] = 25.9874
# result['density'] = 0.0068
return result
def get_user_profile(uid_list, specify_field=[]):
if not uid_list:
return []
results = []
search_results = es_user_profile.mget(index=profile_index_name,
doc_type=profile_index_type,
body={"ids": uid_list})['docs']
field_list = [
"nick_name", "fansnum", "friendsnum", "photo_url", 'description',
"statusnum", "sp_type", "user_location", "create_at", "sex",
"verified_type", "isreal", "user_email"
]
for item in search_results:
iter_result = []
iter_result.append(item['_id'])
if item['found']:
if specify_field:
field_list = specify_field
for iter_field in field_list:
iter_result.append(item['_source'][iter_field])
else:
if specify_field:
iter_result.extend([''] * len(specify_field))
else:
iter_result.extend([''] * len(field_list))
iter_result[1] = item['_id']
results.append(iter_result)
return results
def es_mget_source(ids):
try:
source = es.mget(index=INDEX_NAME, doc_type=DOC_TYPE, body={'ids': ids})
except Exception as e:
raise e
source = [item['_source'] for item in source['docs'] if item['found'] is True]
return source
def get_profile_information(uid_list):
#print 'len uid list:', len(uid_list)
result_dict = dict()
search_result = es.mget(index=index_name,
doc_type=index_type,
body={'ids': uid_list},
_source=True)['docs']
#print 'search_result:', search_result
for item in search_result:
user_dict = {}
for field in fields_dict:
try:
user_dict[field] = item['_source'][fields_dict[field]]
except:
if field == 'statusnum':
user_dict[field] = 0
elif field == 'fansnum':
user_dict[field] = 0
elif field == 'friendsnum':
user_dict[field] = 0
elif field == 'uname':
user_dict[field] = "unknown"
else:
user_dict[field] = 0
result_dict[item['_id']] = user_dict
#print 'uname type:', type(user_dict['uname'])
#print 'result_dict:', result_dict
#print 'len result_dict:', len(search_result)
return result_dict
def get_user_info(uid_list):
user_list = []
# print 'user_list::',user_list
user_result = es_user_profile.mget(index=profile_index_name,
doc_type=profile_index_type,
body={'ids': uid_list})['docs']
core_user = []
for item in user_result:
user_dict = dict()
user_dict['uid'] = item['_id']
if item['found']:
user_dict['photo_url'] = item['_source']['photo_url']
user_dict['nick_name'] = item['_source']['nick_name']
user_dict['sex'] = item['_source']['sex']
user_dict['friendsnum'] = item['_source']['friendsnum']
user_dict['fansnum'] = item['_source']['fansnum']
user_dict['user_location'] = item['_source']['user_location']
else:
user_dict['photo_url'] = ''
user_dict['nick_name'] = ''
user_dict['sex'] = ''
user_dict['friendsnum'] = ''
user_dict['fansnum'] = ''
user_dict['user_location'] = ''
user_list.append(user_dict)
return json.dumps(user_list)
def get_profile_information(uid_list):
#print 'len uid list:', len(uid_list)
result_dict = dict()
search_result = es.mget(index=index_name, doc_type=index_type, body={'ids':uid_list}, _source=True)['docs']
#print 'search_result:', search_result
for item in search_result:
user_dict = {}
for field in fields_dict:
try:
user_dict[field] = item['_source'][fields_dict[field]]
except:
if field=='statusnum':
user_dict[field] = 0
elif field=='fansnum':
user_dict[field] =0
elif field=='friendsnum':
user_dict[field] = 0
elif field=='uname':
user_dict[field] = 0
else:
user_dict[field] = 0
result_dict[item['_id']] = user_dict
#print 'uname type:', type(user_dict['uname'])
#print 'result_dict:', result_dict
#print 'len result_dict:', len(search_result)
return result_dict
def get_profile_information(uid_list):
result_dict = dict()
search_result = es.mget(index=index_name,
doc_type=index_type,
body={'ids': uid_list},
_source=True)['docs']
for item in search_result:
user_dict = {}
for field in fields_dict:
try:
user_dict[field] = item['_source'][fields_dict[field]]
except:
if field == 'statusnum':
user_dict[field] = 0
elif field == 'fansnum':
user_dict[field] = 0
elif field == 'friendsnum':
user_dict[field] = 0
elif field == 'gender':
user_dict[field] = 0
elif field == 'uname':
user_dict[field] = item['_id']
else:
user_dict[field] = ''
result_dict[item['_id']] = user_dict
return result_dict
def main():
uid_list = []
with open("uid_list_0520.txt", 'rb') as f:
for item in f:
uid_list.append(item.strip())
bci_results = es_user_profile.mget(index="bci_history", doc_type="bci", body={"ids":uid_list})["docs"]
sen_results = es_user_profile.mget(index="sensitive_history", doc_type="sensitive", body={"ids":uid_list})["docs"]
with open("bci_history.txt", 'wb') as f_bci:
for item in bci_results:
if item['found']:
f_bci.write(json.dumps(item['_source'])+"\n")
with open("sen_history.txt", "wb") as f_sen:
for item in sen_results:
if item['found']:
f_sen.write(json.dumps(item['_source'])+"\n")
def main():
uid_list = []
with open("uid_list_0520.txt", 'rb') as f:
for item in f:
uid_list.append(item.strip())
bci_results = es_user_profile.mget(index="bci_history",
doc_type="bci",
body={"ids": uid_list})["docs"]
sen_results = es_user_profile.mget(index="sensitive_history",
doc_type="sensitive",
body={"ids": uid_list})["docs"]
with open("bci_history.txt", 'wb') as f_bci:
for item in bci_results:
if item['found']:
f_bci.write(json.dumps(item['_source']) + "\n")
with open("sen_history.txt", "wb") as f_sen:
for item in sen_results:
if item['found']:
f_sen.write(json.dumps(item['_source']) + "\n")
def search_hot_mid(task_name, ts):
query_body = {
"query": {
"range":{
"timestamp":{
"lt": ts
}
}
},
"aggs":{
"hot_mid":{
"terms":{"field": "root_mid", "size": 100}
}
}
}
mid_list = []
return_list = [] # return hot mid
uid_list = []
es_results = es.search(index=task_name, doc_type="text", body=query_body)["aggregations"]["hot_mid"]["buckets"]
for item in es_results:
if item["doc_count"] >= 500:
mid_list.append(item["key"])
if mid_list:
weibo_results = es.mget(index=task_name, doc_type="text", body={"ids":mid_list})["docs"]
for item in weibo_results:
if item["found"]:
mid = item["_id"]
retweet, comment = search_retweet_comment(task_name, mid)
detail = item["_source"]
detail["retweet"] = retweet
detail["comment"] = comment
uid_list.append(detail["uid"])
return_list.append(detail)
if uid_list:
profile_results = es_user_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={"ids":uid_list})["docs"]
for i in range(len(uid_list)):
detail = profile_results[i]
if detail["found"]:
return_list[i]["uname"] = detail["_source"]["nick_name"]
return_list[i]["photo_url"] = detail["_source"]["photo_url"]
return_list[i]["fansnum"] = detail["_source"]["fansnum"]
return_list[i]["statusnum"] = detail["_source"]["statusnum"]
else:
return_list[i]["uname"] = detail["_id"]
return_list[i]["photo_url"] = ""
return_list[i]["fansnum"] = ""
return_list[i]["statusnum"] = ""
return return_list
def get_user_name(uid_list):
try:
portrait_exist_result = es_user_profile.mget(index=profile_index_name,\
doc_type=profile_index_type,body={'ids':uid_list})['docs']
except:
portrait_exist_result = []
uid2uname_dict = {}
print portrait_exist_result
for portrait_item in portrait_exist_result:
uid = portrait_item['_id']
if portrait_item['found'] == True:
source = portrait_item['_source']
uname = source['nick_name']
else:
uname = uid
uid2uname_dict[uid] = uname
return uid2uname_dict
def get_profile_information(uid_list):
result_dict = dict()
search_result = es.mget(index=index_name,
doc_type=index_type,
body={'ids': uid_list},
_source=True)['docs']
iter_count = 0
for item in search_result:
user_dict = {}
for field in fields_dict:
try:
user_dict[field] = item['_source'][fields_dict[field]]
except:
user_dict[field] = ''
result_dict[item['_id']] = user_dict
iter_count += 1
return result_dict
def get_future_user(uid_list):
return_list = []
if uid_list:
profile_results = es_user_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={"ids":uid_list})["docs"]
for item in profile_results:
tmp = []
tmp.append(item["_id"])
if item["found"]:
tmp.append(item["_source"]["nick_name"])
tmp.append(item["_source"]["photo_url"])
tmp.append(item["_source"]["fansnum"])
tmp.append(item["_source"]["statusnum"])
else:
tmp.append(item["_id"])
tmp.extend(["","",""])
return_list.append(tmp)
return return_list
def search_attention(uid):
stat_results = dict()
results = dict()
for db_num in R_DICT:
r = R_DICT[db_num]
ruid_results = r.hgetall('retweet_'+str(uid))
if ruid_results:
for ruid in ruid_results:
if ruid != uid:
try:
stat_results[ruid] += ruid_results[ruid]
except:
stat_results[ruid] = ruid_results[ruid]
# print 'results:', stat_results
if not stat_results:
return [None, 0]
try:
sort_state_results = sorted(stat_results.items(), key=lambda x:x[1], reverse=True)[:20]
except:
return [None, 0]
print 'sort_state_results:', sort_state_results
uid_list = [item[0] for item in sort_state_results]
es_profile_results = es_user_profile.mget(index='weibo_user', doc_type='user', body={'ids':uid_list})['docs']
es_portrait_results = es_user_portrait.mget(index='user_portrait', doc_type='user', body={'ids':uid_list})['docs']
result_list = dict()
for i in range(len(es_profile_results)):
item = es_profile_results[i]
uid = item['_id']
try:
source = item['_source']
uname = source['nick_name']
except:
uname = u'未知'
# identify uid is in the user_portrait
portrait_item = es_portrait_results[i]
try:
source = portrait_item[i]
in_status = 1
except:
in_status = 0
result_list[uid] = [uid,[uname, stat_results[uid], in_status]]
return [result_list, len(stat_results)]
def search_attention(uid):
stat_results = dict()
results = dict()
for db_num in R_DICT:
r = R_DICT[db_num]
ruid_results = r.hgetall("retweet_" + str(uid))
if ruid_results:
for ruid in ruid_results:
if ruid != uid:
try:
stat_results[ruid] += ruid_results[ruid]
except:
stat_results[ruid] = ruid_results[ruid]
# print 'results:', stat_results
if not stat_results:
return [None, 0]
try:
sort_state_results = sorted(stat_results.items(), key=lambda x: x[1], reverse=True)[:20]
except:
return [None, 0]
print "sort_state_results:", sort_state_results
uid_list = [item[0] for item in sort_state_results]
es_profile_results = es_user_profile.mget(index="weibo_user", doc_type="user", body={"ids": uid_list})["docs"]
es_portrait_results = es_user_portrait.mget(index="user_portrait", doc_type="user", body={"ids": uid_list})["docs"]
result_list = dict()
for i in range(len(es_profile_results)):
item = es_profile_results[i]
uid = item["_id"]
try:
source = item["_source"]
uname = source["nick_name"]
except:
uname = u"未知"
# identify uid is in the user_portrait
portrait_item = es_portrait_results[i]
try:
source = portrait_item[i]
in_status = 1
except:
in_status = 0
result_list[uid] = [uid, [uname, stat_results[uid], in_status]]
return [result_list, len(stat_results)]
def search_profile(uid_list):
'''
输入：uid列表
'''
es_profile_results = es_user_profile.mget(index='user_portrait_1222', doc_type='user', body={'ids':uid_list})['docs']
result_list = dict()
for i in range(len(es_profile_results)):
item = es_profile_results[i]
uid = item['_id'].encode('utf-8')
if item['found']:#有数据
source = item['_source']
topic = source['topic_string']
else:
topic = ''
result_list[uid] = topic
return result_list
def search_user_type(uid_list):
type_list = es_user_profile.mget(index=profile_index_name, doc_type=profile_index_type, \
body={'ids': uid_list},_source=False, fields=['id', 'verified_type'])['docs']
user_list = []
org_list = []
for i in type_list:
if i['found'] == False:
user_list.append(i['_id'])
else:
# print i
if not i.has_key('verified_type'):
user_list.append(i['_id'])
continue
verified_type = i['fields']['verified_type'][0]
if verified_type in org_list:
org_list.append(i['_id'])
else:
user_list.append(i['_id'])
return user_list, org_list
def get_user_profile(uid_list,specify_field=[]):
if not uid_list:
return []
results = []
search_results = es_user_profile.mget(index=profile_index_name, doc_type=profile_index_type,body={"ids":uid_list})['docs']
field_list = ["nick_name", "fansnum", "friendsnum","photo_url", 'description', "statusnum","sp_type", "user_location", "create_at", "sex", "verified_type", "isreal", "user_email"]
for item in search_results:
iter_result = []
iter_result.append(item['_id'])
if item['found']:
if specify_field:
field_list = specify_field
for iter_field in field_list:
iter_result.append(item['_source'][iter_field])
else:
iter_result.extend(['']*len(field_list))
results.append(iter_result)
return results
def search_profile(uid_list):
'''
输入：uid列表
'''
es_profile_results = es_user_profile.mget(index='user_portrait_1222',
doc_type='user',
body={'ids': uid_list})['docs']
result_list = dict()
for i in range(len(es_profile_results)):
item = es_profile_results[i]
uid = item['_id'].encode('utf-8')
if item['found']: #有数据
source = item['_source']
topic = source['topic_string']
else:
topic = ''
result_list[uid] = topic
return result_list
def reducer():
count = 0
ts = time.time()
while 1:
user_set = r_flow.rpop('update_bci_list')
bulk_action = []
if user_set:
items = json.loads(user_set)
uid_list = []
for item in items:
uid_list.append(item['id'])
if uid_list:
search_results = es.mget(index=BCIHIS_INDEX_NAME, doc_type=BCIHIS_INDEX_TYPE, body={"ids":uid_list})["docs"]
cal_num_for_bci_history(uid_list, items, search_results)
count += len(uid_list)
if count % 10000 == 0:
te = time.time()
#print "count: %s, cost time: %s" %(count, te-ts)
ts = te
else:
print count
break
def get_profile_information(uid_list):
result_dict = dict()
search_result = es.mget(index=index_name, doc_type=index_type, body={'ids':uid_list}, _source=True)['docs']
for item in search_result:
user_dict = {}
for field in fields_dict:
try:
user_dict[field] = item['_source'][fields_dict[field]]
except:
if field=='statusnum':
user_dict[field] = 0
elif field=='fansnum':
user_dict[field] =0
elif field=='friendsnum':
user_dict[field] = 0
elif field=='gender':
user_dict[field] = 0
elif field=='uname':
user_dict[field] = u'unknown'
else:
user_dict[field] = 'unknown'
result_dict[item['_id']] = user_dict
return result_dict
def get_topic_top_user(topic_top):
result = {}
topic_user = {}
index_name = 'weibo_user'
index_type = 'user'
#test user list
test_user_list = [['1499104401', '1265965213', '3270699555', '2073915493', '1686474312'],\
['2803301701', '2105426467', '1665372775', '3716504593', '2892376557'],\
['1457530250', '1698513182', '2793591492', '2218894100', '1737961042'],\
['1656818110', '1660127070', '1890124610', '1182391230', '1243861100'],\
['1680430844', '2998045524', '2202896360', '1639498782', '3494698730'],\
['2587093162', '1677675054', '1871767009', '1193111400', '1672418622'],\
['1730726640', '1752502540', '1868725480', '1262486750', '1235733080'],\
['1250041100', '2275231150', '1268642530', '1658606270', '1857599860'],\
['1929496477', '2167425990', '1164667670', '2417139911', '1708853044'],\
['1993292930', '1645823930', '1890926610', '1641561810', '2023833990'],\
['2005471590', '1233628160', '2074684140', '1396715380', '1236762250'],\
['1423592890', '2612799560', '1926127090', '2684951180', '1760607220']]
count = 0
for item in topic_top:
topic = item[0]
#test
user_list = test_user_list[count]
result[topic] = []
profile_result = es_user_profile.mget(index=index_name, doc_type=index_type, body={'ids':user_list})['docs']
for profile in profile_result:
uid = profile['_id']
try:
uname = profile['_source']['nick_name']
photo_url = profile['_source']['photo_url']
except:
uname = 'unknown'
photo_url = 'unknown'
result[topic].append([uid, uname, photo_url])
count += 1
return result
def reducer():
count = 0
ts = time.time()
while 1:
user_set = r_flow.rpop('update_bci_list')
bulk_action = []
if user_set:
items = json.loads(user_set)
uid_list = []
for item in items:
uid_list.append(item['id'])
if uid_list:
search_results = es.mget(index=BCIHIS_INDEX_NAME,
doc_type=BCIHIS_INDEX_TYPE,
body={"ids": uid_list})["docs"]
cal_num_for_bci_history(uid_list, items, search_results)
count += len(uid_list)
if count % 10000 == 0:
te = time.time()
#print "count: %s, cost time: %s" %(count, te-ts)
ts = te
else:
print count
break
def get_domain_top_user(domain_top):
result = {}
domain_user = {}
index_name = 'weibo_user'
index_type = 'user'
#test user list
test_user_list = [['2803301701', '1639498782', '2656274875', '1402977920', '3114175427'], \
['3575186384', '1316683401', '1894603174', '1641542052', '1068248497'], \
['1729736051', '1396715380', '2377610962', '1828183230', '2718018210'], \
['1250748474', '3270699555', '1417037145', '1193111400', '1403915120'], \
['1671342103', '1255849511', '1647497355', '1989660417', '1189729754'], \
['1182391231', '1670071920', '1689618340', '1494850741', '1708942053'],\
['3400918220', '2685504141', '2056115850', '1768001547', '3317008062'],\
['2001627641', '1773489534', '2458194884', '1822155333', '1799201635'],\
['1709157165', '2074370833', '2167425990', '3204839810', '3690518992'],\
['1664065962', '3299094722', '1942531237', '2799434700', '1784404677'],\
['1218353337', '1761179351', '3482911112', '1220291284', '2504433601'],\
['3682473195', '1627673351', '1779065471', '3316144700', '1896701827']]
count = 0
for item in domain_top:
domain = item[0]
#test
user_list = test_user_list[count]
result[domain] = []
profile_result = es_user_profile.mget(index=index_name, doc_type=index_type, body={'ids':user_list})['docs']
for profile in profile_result:
uid = profile['_id']
try:
uname = profile['_source']['nick_name']
photo_url = profile['_source']['photo_url']
except:
uname = 'unknown'
photo_url = 'unknown'
result[domain].append([uid, uname, photo_url])
count += 1
return result
query_sensitive_body = {
"query":{
"match_all":{}
},
"size":1,
"sort":{sensitive_string:{"order":"desc"}}
}
try:
top_sensitive_result = es_bci_history.search(index=ES_SENSITIVE_INDEX, doc_type=DOCTYPE_SENSITIVE_INDEX, body=query_sensitive_body, _source=False, fields=[sensitive_string])['hits']['hits']
top_sensitive = top_sensitive_result[0]['fields'][sensitive_string][0]
except Exception, reason:
print Exception, reason
top_sensitive = 400
index_type = 'bci'
user_bci_result = es_cluster.mget(index=index_name, doc_type=index_type, body={'ids':uid_list}, _source=True)['docs']
user_profile_result = es_user_profile.mget(index='weibo_user', doc_type='user', body={'ids':uid_list}, _source=True)['docs']
bci_history_result = es_bci_history.mget(index=bci_history_index_name, doc_type=bci_history_index_type, body={"ids":uid_list}, fields=['user_fansnum', 'weibo_month_sum'])['docs']
sensitive_history_result = es_bci_history.mget(index=ES_SENSITIVE_INDEX, doc_type=DOCTYPE_SENSITIVE_INDEX, body={'ids':uid_list}, fields=[sensitive_string], _source=False)['docs']
max_evaluate_influ = get_evaluate_max(index_name)
for i in range(0, len(uid_list)):
uid = uid_list[i]
bci_dict = user_bci_result[i]
profile_dict = user_profile_result[i]
bci_history_dict = bci_history_result[i]
sensitive_history_dict = sensitive_history_result[i]
#print sensitive_history_dict
try:
bci_source = bci_dict['_source']
except:
bci_source = None
if bci_source:
def main():
if RUN_TYPE:
now_ts = time.time() - DAY # 前一天
ts = str(datetime2ts(ts2datetime(now_ts)))
else:
ts = str(datetime2ts('2016-03-16'))
now_ts = int(ts)
print now_ts
sensitive_string = "sensitive_" + ts
date_string = ts
update_sensitive_key = "sensitive_score_" + ts # 更新的键
sensitive_dict_key = "sensitive_dict_" + ts
sensitive_string_key = "sensitive_string_" + ts
sensitive_day_change_key = "sensitive_" + ts + "_day_change"
del_month = datetime2ts(ts2datetime(now_ts - MONTH))
del_sensitive_key = "sensitive_score_" + str(del_month) # 要删除的键
former_ts = int(ts) - DAY
former_date = str(datetime2ts(ts2datetime(former_ts)))
former_sensitive_key = "sensitive_score_" + former_date
iter_count = 0
bulk_action = []
mappings(ES_SENSITIVE_INDEX)
total_number = r.hlen(sensitive_string)
scan_cursor = 0
print total_number
while 1:
re_scan = r.hscan(sensitive_string, scan_cursor, count=1000)
scan_cursor = re_scan[0]
if len(re_scan[1]) != 0:
sensitive_info = re_scan[1] # 字典形式，uid：sensitive_words_dict
uid_list = sensitive_info.keys()
sensitive_results = es.mget(index=ES_SENSITIVE_INDEX,
doc_type=DOCTYPE_SENSITIVE_INDEX,
body={"ids": uid_list})['docs']
if sensitive_results:
for item in sensitive_results:
uid = item['_id']
sensitive_words_dict = json.loads(
sensitive_info[uid]) # json.loads
current_sensitive_score = 0
for k, v in sensitive_words_dict.iteritems():
tmp_stage = r_sensitive.hget("sensitive_words", k)
if tmp_stage:
current_sensitive_score += v * sensitive_score_dict[
str(tmp_stage)]
if item['found']: # 之前存在相关信息
revise_item = item["_source"]
if del_sensitive_key in revise_item:
item.remove(del_sensitive_key)
revise_item['uid'] = uid
# 新更新的敏感度
revise_item[
update_sensitive_key] = current_sensitive_score
# 新更新的敏感词
revise_item[sensitive_dict_key] = sensitive_info[uid]
# 新更新的string
revise_item[sensitive_string_key] = "&".join(
sensitive_words_dict.keys())
# 当天和之前一天、一周和一月均值的差异
revise_item[
'sensitive_day_change'] = current_sensitive_score - revise_item.get(
former_sensitive_key, 0)
revise_item[
'sensitive_week_change'] = current_sensitive_score - revise_item.get(
'sensitive_week_ave', 0)
revise_item[
'sensitive_month_change'] = current_sensitive_score - revise_item.get(
'sensitive_month_ave', 0)
# 更新后week、month的均值和方差
revise_item['sensitive_week_ave'], revise_item[
'sensitive_week_var'], revise_item[
'sensitive_week_sum'] = compute_week(
revise_item, now_ts)
revise_item['senstiive_month_ave'], revise_item[
'sensitive_month_var'], revise_item[
'sensitive_month_sum'] = compute_month(
revise_item, now_ts)
else:
revise_item = dict()
revise_item['uid'] = uid
revise_item[
update_sensitive_key] = current_sensitive_score
revise_item[sensitive_dict_key] = sensitive_info[uid]
revise_item[sensitive_string_key] = "&".join(
sensitive_words_dict.keys())
revise_item[
'sensitive_day_change'] = current_sensitive_score
revise_item[
'sensitive_week_change'] = current_sensitive_score
revise_item[
'sensitive_month_change'] = current_sensitive_score
revise_item['sensitive_week_ave'], revise_item[
'sensitive_week_var'], revise_item[
'sensitive_week_sum'] = compute_week(
revise_item, now_ts)
revise_item['senstiive_month_ave'], revise_item[
'sensitive_month_var'], revise_item[
'sensitive_month_sum'] = compute_month(
revise_item, now_ts)
action = {'index': {'_id': uid}}
bulk_action.extend([action, revise_item])
iter_count += 1
if iter_count % 1000 == 0:
es.bulk(bulk_action,
index=ES_SENSITIVE_INDEX,
doc_type=DOCTYPE_SENSITIVE_INDEX)
bulk_action = []
print iter_count
if int(scan_cursor) == 0:
break
if bulk_action:
es.bulk(bulk_action,
index=ES_SENSITIVE_INDEX,
doc_type=DOCTYPE_SENSITIVE_INDEX)
print iter_count
def key_words_search(task_id,
search_type,
pre,
during,
start_time,
keyword_list,
search_key='',
sort_norm='',
sort_scope='',
time=1,
isall=False,
number=100):
number = int(number)
should = []
for key in keyword_list:
if search_type == "hashtag":
should.append({"prefix": {"text": "#" + key + "#"}})
else:
should.append({"wildcard": {"text": "*" + key + "*"}})
index_list = []
date = ts2datetime(start_time)
index_name = pre + date
while during:
if es_flow_text.indices.exists(index=index_name):
index_list.append(index_name)
start_time = start_time + DAY
date = ts2datetime(start_time)
index_name = pre + date
during -= 1
print index_list
uid_set = set()
text_results = []
query_body = {
"query": {
"bool": {
"must": should
}
},
"sort": {
"user_fansnum": {
"order": "desc"
}
},
"size": 5000
}
results = es_flow_text.search(index=index_list,
doc_type='text',
body=query_body,
_source=False,
fields=[
"uid", "user_fansnum", "text",
"message_type", "sentiment", "timestamp",
"geo", "retweeted", "comment"
])["hits"]["hits"]
id_index = 0
index_list = []
un_uid_list = []
for item in results:
if item['fields']['uid'][0] not in uid_set:
uid_set.add(item['fields']['uid'][0])
un_uid_list.append(item['fields']['uid'][0])
index_list.append(id_index)
id_index += 1
uid_list = []
print "un_uid_list: ", len(un_uid_list)
portrait_list = []
count = 0
in_index = 0
if not isall and un_uid_list: # 库内
portrait_results = es_user_portrait.mget(index=USER_INDEX_NAME,
doc_type=USER_INDEX_TYPE,
body={"ids": un_uid_list},
_source=False,
fields=['uname'])["docs"]
for item in portrait_results:
if item["found"]:
portrait_list.append(item['_id'])
nick_name = item['fields']['uname'][0]
if nick_name == 'unknown':
nick_name = item['_id']
index = index_list[in_index]
weibo_url = weiboinfo2url(results[index]['fields']['uid'][0],
results[index]['_id'])
text_results.extend([
results[index]['fields']['uid'][0],
results[index]['fields']['user_fansnum'][0],
results[index]['fields']['text'][0],
results[index]['fields']['message_type'][0],
results[index]['fields']['sentiment'][0],
ts2date(results[index]['fields']['timestamp'][0]),
results[index]['fields']['geo'][0],
results[index]['fields']['retweeted'][0],
results[index]['fields']['comment'][0], nick_name,
weibo_url
])
count += 1
if count == number:
break
print "portrait_len, ", len(portrait_list)
in_index += 1
if portrait_list:
uid_list = in_sort_filter(time, sort_norm, sort_scope, None,
portrait_list, True, number) # sort
elif un_uid_list:
profile_result = es_user_profile.mget(index="weibo_user",
doc_type="user",
body={"ids": un_uid_list},
fields=['nick_name'])["docs"]
for i in range(len(profile_result)):
index = index_list[i]
try:
nick_name = profile_result[i]['fields']['nick_name'][0]
except:
nick_name = un_uid_list[i]
item = results[index]
weibo_url = weiboinfo2url(item['fields']['uid'][0],
results[index]['_id'])
text_results.append([
item['fields']['uid'][0], item['fields']['user_fansnum'][0],
item['fields']['text'][0], item['fields']['message_type'][0],
item['fields']['sentiment'][0],
ts2date(item['fields']['timestamp'][0]),
results[index]['fields']['geo'][0],
results[index]['fields']['retweeted'][0],
results[index]['fields']['comment'][0], nick_name, weibo_url
])
if i == number:
break
uid_list = all_sort_filter(un_uid_list[:number], sort_norm, time, True,
number)
print "filter_uid_list: ", len(uid_list)
if uid_list:
results = make_up_user_info(uid_list, isall, time, sort_norm)
else:
results = []
print "results: ", len(results)
# 修改状态
task_detail = es_user_portrait.get(index=USER_RANK_KEYWORD_TASK_INDEX,
doc_type=USER_RANK_KEYWORD_TASK_TYPE,
id=task_id)
item = task_detail['_source']
item['status'] = 1
item['result'] = json.dumps(results)
item['text_results'] = json.dumps(text_results)
item['number'] = len(results)
es_user_portrait.index(index=USER_RANK_KEYWORD_TASK_INDEX,
doc_type=USER_RANK_KEYWORD_TASK_TYPE,
id=task_id,
body=item)
return "1"
def get_retweet_weibo_detail(ts, size, text_type, type_value):
task_detail = es_prediction.get(index=index_sensing_task, doc_type=_id, id=ts)['_source']
origin_weibo_detail = json.loads(task_detail['origin_weibo_detail'])
retweeted_weibo_detail = json.loads(task_detail['retweeted_weibo_detail'])
mid_list = []
mid_list.extend(origin_weibo_detail.keys())
mid_list.extend(retweeted_weibo_detail.keys())
query_body = {
"query":{
"filtered":{
"filter":{
"bool":{
"must":[
{"range":{
"timestamp":{
"gte": ts - time_interval,
"lt": ts
}
}},
{"terms": {"root_mid": mid_list}}
]
}
}
}
},
"sort": {"timestamp": {"order": "desc"}},
"size": 100
}
if text_type == "message_type":
query_body['query']['filtered']['filter']['bool']['must'].append({"term":{text_type: type_value}})
if text_type == "sentiment":
#if isinstance(type_value, str):
if len(type_value) == 1:
query_body['query']['filtered']['filter']['bool']['must'].append({"term":{text_type: type_value}})
else:
query_body['query']['filtered']['filter']['bool']['must'].append({"terms":{text_type: type_value}})
datetime = ts2datetime(ts)
datetime_1 = ts2datetime(ts-time_interval)
index_name = flow_text_index_name_pre + datetime
exist_es = es_text.indices.exists(index_name)
index_name_1 = flow_text_index_name_pre + datetime_1
exist_es_1 = es_text.indices.exists(index_name_1)
# 1. 查询微博
if datetime == datetime_1 and exist_es:
search_results = es_text.search(index=index_name, doc_type=flow_text_index_type, body=query_body)["hits"]["hits"]
elif datetime != datetime_1 and exist_es_1:
search_results = es_text.search(index=index_name_1, doc_type=flow_text_index_type, body=query_body)["hits"]["hits"]
else:
search_results = []
#print search_results
# 2. 获取微博相关信息
results = []
uid_list = []
if search_results:
for item in search_results:
uid_list.append(item["_source"]['uid'])
if uid_list:
portrait_result = es_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={"ids":uid_list}, fields=['nick_name', 'photo_url'])["docs"]
for i in range(len(uid_list)):
item = search_results[i]['_source']
temp = []
# uid, nick_name, photo_url, text, sentiment, timestamp, geo, common_keywords, message_type
temp.append(item['uid'])
if portrait_result[i]['found']:
temp.append(portrait_result[i]["fields"]["nick_name"][0])
temp.append(portrait_result[i]["fields"]["photo_url"][0])
else:
temp.append(item['uid'])
temp.append("")
temp.append(item["text"])
#print item['text']
temp.append(item["sentiment"])
temp.append(ts2date(item['timestamp']))
temp.append(item['geo'])
temp.append(item["message_type"])
results.append(temp)
return results
def get_origin_weibo_detail(ts, size, order, message_type=1):
#print r.get("topic_value_dict")
#error:topic_value_dict里存的为空
#topic_value_dict = json.loads(r.get("topic_value_dict"))
task_detail = es_prediction.get(index=index_sensing_task, doc_type=_id, id=ts)['_source']
mid_value = json.loads(task_detail['mid_topic_value'])
duplicate_dict = json.loads(task_detail['duplicate_dict'])
tmp_duplicate_dict = dict()
for k,v in duplicate_dict.iteritems():
try:
tmp_duplicate_dict[v].append(k)
except:
tmp_duplicate_dict[v] = [k, v]
if message_type == 1:
weibo_detail = json.loads(task_detail['origin_weibo_detail'])
elif message_type == 2:
weibo_detail = json.loads(task_detail['retweeted_weibo_detail'])
else:
weibo_detail = json.loads(task_detail['sensitive_weibo_detail'])
weibo_detail_list = []
if weibo_detail:
for iter_mid, item in weibo_detail.iteritems():
tmp = []
tmp.append(iter_mid)
tmp.append(item[iter_mid])
tmp.append(item['retweeted'])
tmp.append(item['comment'])
weibo_detail_list.append(tmp)
mid_list = weibo_detail.keys()
results = []
query_body = {
"query":{
"filtered":{
"filter":{
"terms":{"mid": mid_list}
}
}
},
"size": 1000,
"sort": {"timestamp": {"order": "desc"}}
}
index_list = []
datetime = ts2datetime(ts)
datetime_1 = ts2datetime(ts-DAY)
index_name = flow_text_index_name_pre + datetime
exist_es = es_text.indices.exists(index_name)
if exist_es:
index_list.append(index_name)
index_name_1 = flow_text_index_name_pre + datetime_1
exist_es_1 = es_text.indices.exists(index_name_1)
if exist_es_1:
index_list.append(index_name_1)
if index_list and mid_list:
search_results = es_text.search(index=index_list, doc_type=flow_text_index_type, body=query_body)["hits"]["hits"]
else:
search_results = []
uid_list = []
text_dict = dict() # 文本信息
portrait_dict = dict() # 背景信息
sort_results = []
if search_results:
for item in search_results:
uid_list.append(item["_source"]['uid'])
text_dict[item['_id']] = item['_source'] # _id是mid
if uid_list:
portrait_result = es_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={"ids":uid_list}, fields=['nick_name', 'photo_url'])["docs"]
for item in portrait_result:
if item['found']:
portrait_dict[item['_id']] = {"nick_name": item["fields"]["nick_name"][0], "photo_url": item["fields"]["photo_url"][0]}
else:
portrait_dict[item['_id']] = {"nick_name": item['_id'], "photo_url":""}
if order == "total":
sorted_list = sorted(weibo_detail_list, key=lambda x:x[1], reverse=True)
elif order == "retweeted":
sorted_list = sorted(weibo_detail_list, key=lambda x:x[2], reverse=True)
elif order == "comment":
sorted_list = sorted(weibo_detail_list, key=lambda x:x[3], reverse=True)
else:
sorted_list = weibo_detail_list
count_n = 0
results_dict = dict()
mid_index_dict = dict()
for item in sorted_list: # size
mid = item[0]
iter_text = text_dict.get(mid, {})
temp = []
# uid, nick_name, photo_url, text, sentiment, timestamp, geo, common_keywords, message_type
if iter_text:
uid = iter_text['uid']
temp.append(uid)
iter_portrait = portrait_dict.get(uid, {})
if iter_portrait:
temp.append(iter_portrait['nick_name'])
temp.append(iter_portrait['photo_url'])
else:
temp.extend([uid,''])
temp.append(iter_text["text"])
temp.append(iter_text["sentiment"])
temp.append(ts2date(iter_text['timestamp']))
temp.append(iter_text['geo'])
if message_type == 1:
temp.append(1)
elif message_type == 2:
temp.append(3)
else:
temp.append(iter_text['message_type'])
temp.append(item[2])
temp.append(item[3])
temp.append(iter_text.get('sensitive', 0))
temp.append(iter_text['timestamp'])
temp.append(mid_value[mid])
temp.append(mid)
results.append(temp)
count_n += 1
results = sorted(results, key=operator.itemgetter(-4, -2, -6), reverse=True) # -4 -2 -3
sort_results = []
count = 0
for item in results:
sort_results.append([item])
mid_index_dict[item[-1]] = count
count += 1
if tmp_duplicate_dict:
remove_list = []
value_list = tmp_duplicate_dict.values() # [[mid, mid], ]
for item in value_list:
tmp = []
for mid in item:
if mid_index_dict.get(mid, 0):
tmp.append(mid_index_dict[mid])
if len(tmp) > 1:
tmp_min = min(tmp)
else:
continue
tmp.remove(tmp_min)
for iter_count in tmp:
sort_results[tmp_min].extend(sort_results[iter_count])
remove_list.append(sort_results[iter_count])
if remove_list:
for item in remove_list:
sort_results.remove(item)
return sort_results
def get_positive_weibo_detail(ts, social_sensors, keywords_list, size, sentiment_type=1):
former_mid_list = query_mid_list(ts-time_interval, keywords_list, time_segment, social_sensors) # 前一段时间内的微博mid list
current_mid_list = query_mid_list(ts, keywords_list, time_interval, social_sensors)
mid_list = []
mid_list.extend(former_mid_list)
mid_list.extend(current_mid_list)
query_body = {
"query":{
"filtered":{
"filter":{
"bool":{
"must":[
{"range":{
"timestamp":{
"gte": ts - time_interval,
"lt": ts
}
}},
],
"should":[
{"terms": {"root_mid": mid_list}},
{"terms": {"mid": mid_list}},
{"terms":{"keywords_string": keywords_list}}
]
}
}
}
},
"sort": {"timestamp": {"order": "desc"}},
"size": 100
}
#if social_sensors and int(sentiment_type) == 1:
# query_body["query"]["filtered"]["filter"]["bool"]["must"].append({"terms":{"uid": social_sensors}})
if int(sentiment_type) == 1 or int(sentiment_type) == 0:
query_body["query"]["filtered"]["filter"]["bool"]["must"].append({"term":{"sentiment":sentiment_type}})
else:
query_body["query"]["filtered"]["filter"]["bool"]["must"] = [{"terms":{"sentiment": ["2", "3"]}}]
# 判断当前ts和ts-time_interval是否属于同一天，确定查询哪个es
datetime = ts2datetime(ts)
datetime_1 = ts2datetime(ts-time_interval)
index_name = flow_text_index_name_pre + datetime
exist_es = es_text.indices.exists(index_name)
index_name_1 = flow_text_index_name_pre + datetime_1
exist_es_1 = es_text.indices.exists(index_name_1)
# 1. 聚合原创微博mid list
if datetime == datetime_1 and exist_es:
search_results = es_text.search(index=index_name, doc_type=flow_text_index_type, body=query_body)["hits"]["hits"]
elif datetime != datetime_1 and exist_es_1:
search_results = es_text.search(index=index_name_1, doc_type=flow_text_index_type, body=query_body)["hits"]["hits"]
else:
search_results = []
uid_list = []
results = []
if search_results:
for item in search_results:
uid_list.append(item["_source"]['uid'])
if uid_list:
portrait_result = es_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={"ids":uid_list}, fields=['nick_name', 'photo_url'])["docs"]
for i in range(len(uid_list)):
item = search_results[i]['_source']
temp = []
# uid, nick_name, photo_url, text, sentiment, timestamp, geo, common_keywords, message_type
temp.append(item['uid'])
if portrait_result[i]['found']:
temp.append(portrait_result[i]["fields"]["nick_name"][0])
temp.append(portrait_result[i]["fields"]["photo_url"][0])
else:
temp.append("unknown")
temp.append("")
temp.append(item["text"])
temp.append(item["sentiment"])
temp.append(ts2date(item['timestamp']))
temp.append(item['geo'])
keywords_set = set(item['keywords_string'].split('&'))
common_keywords = set(keywords_list) & keywords_set
temp.append(list(common_keywords))
temp.append(item['message_type'])
results.append(temp)
return results
def key_words_search(task_id, search_type , pre , during , start_time , keyword_list , search_key = '' , sort_norm = '', sort_scope = '' ,time = 7 , isall = False, number = 100):
number = int(number)
should = []
for key in keyword_list:
if search_type == "hashtag":
should.append({"prefix":{"text": "#" + key + "#"}})
else:
should.append({"wildcard":{"text": "*" +key + "*"}})
index_list = []
date = ts2datetime(start_time)
index_name = pre + date
while during:
if es_flow_text.indices.exists(index=index_name):
index_list.append(index_name)
start_time = start_time + DAY
date = ts2datetime(start_time)
index_name = pre + date
during -= 1
print index_list
uid_set = set()
text_results = []
sorted_text_results = []
query_body = {
"query":{
"bool":{
"must":should
}
},
"sort":{"user_fansnum":{"order":"desc"}},
"size":5000
}
results = es_flow_text.search(index = index_list , doc_type = 'text' , body = query_body, _source=False, fields=["uid", "user_fansnum","text", "message_type", "sentiment","timestamp", "geo", "retweeted", "comment"])["hits"]["hits"]
id_index = 0
index_list = []
un_uid_list = []
for item in results :
if item['fields']['uid'][0] not in uid_set:
uid_set.add(item['fields']['uid'][0])
un_uid_list.append(item['fields']['uid'][0])
index_list.append(id_index)
id_index += 1
#get_all_filed(sort_norm , time)
uid_list = []
print "un_uid_list: ", len(un_uid_list)
portrait_list = []
count = 0
in_index = 0
if not isall and un_uid_list : # 库内
portrait_results = es_user_portrait.mget(index=USER_INDEX_NAME, doc_type=USER_INDEX_TYPE, body={"ids":un_uid_list}, _source=False, fields=['uname'])["docs"]
for item in portrait_results:
if item["found"]:
portrait_list.append(item['_id'])
nick_name = item['fields']['uname'][0]
if nick_name == 'unknown':
nick_name = item['_id']
index = index_list[in_index]
weibo_url = weiboinfo2url(results[index]['fields']['uid'][0], results[index]['_id'])
text_results.extend([results[index]['fields']['uid'][0], results[index]['fields']['user_fansnum'][0], results[index]['fields']['text'][0], results[index]['fields']['message_type'][0], results[index]['fields']['sentiment'][0], ts2date(results[index]['fields']['timestamp'][0]), results[index]['fields']['geo'][0], results[index]['fields']['retweeted'][0], results[index]['fields']['comment'][0], nick_name, weibo_url])
count += 1
if count == number:
break
print "portrait_len, ", len(portrait_list)
in_index += 1
if portrait_list:
uid_list = in_sort_filter(time,sort_norm ,sort_scope ,None , portrait_list , True, number) # sort
for iter_uid in uid_list:
iter_index = portrait_list.index(iter_uid)
sorted_text_results.append(text_results[i])
elif un_uid_list:
profile_result = es_user_profile.mget(index="weibo_user", doc_type="user", body={"ids":un_uid_list}, fields=['nick_name'])["docs"]
for i in range(len(profile_result)):
index = index_list[i]
try:
nick_name = profile_result[i]['fields']['nick_name'][0]
except:
nick_name = un_uid_list[i]
item = results[index]
weibo_url = weiboinfo2url(item['fields']['uid'][0], results[index]['_id'])
text_results.append([item['fields']['uid'][0], item['fields']['user_fansnum'][0], item['fields']['text'][0], item['fields']['message_type'][0], item['fields']['sentiment'][0], ts2date(item['fields']['timestamp'][0]), results[index]['fields']['geo'][0], results[index]['fields']['retweeted'][0], results[index]['fields']['comment'][0], nick_name, weibo_url])
if i == number:
break
uid_list = all_sort_filter(un_uid_list[:number] , sort_norm , time ,True, number)
sorted_text_results = []
f = open("small.txt", "wb")
for iter_uid in uid_list:
iter_index = un_uid_list.index(iter_uid)
f.write(str(iter_uid)+"\n")
sorted_text_results.append(text_results[iter_index])
f.close()
print "filter_uid_list: ", len(uid_list)
if uid_list:
results = make_up_user_info(uid_list,isall,time,sort_norm)
else:
results = []
print "results: ", len(results)
# 修改状态
task_detail = es_user_portrait.get(index=USER_RANK_KEYWORD_TASK_INDEX , doc_type=USER_RANK_KEYWORD_TASK_TYPE, id=task_id)
item = task_detail['_source']
item['status'] = 1
item['result'] = json.dumps(results)
item['text_results'] = json.dumps(sorted_text_results)
item['number'] = len(results)
es_user_portrait.index(index = USER_RANK_KEYWORD_TASK_INDEX , doc_type=USER_RANK_KEYWORD_TASK_TYPE , id=task_id, body=item)
return "1"
def potential_user(task_name, ts):
index_name = "stimulation_"+task_name
index_type = "stimulation_results"
#查询当前root_mid
query_body = {
"query": {
"bool":{
"must":[
{"range":{
"timestamp":{
"lt": ts
}
}},
{"term":{"message_type":1}},
{"range":{
"user_fansnum":{
"gte": 10000
}
}}
]
}
},
"size": 10000
}
es_results = es.search(index=task_name, doc_type="text", body=query_body)["hits"]["hits"]
mid_list = []
uid_list = []
feature_list = []
prediction_uid = []
prediction_weibo = []
with open("prediction_uid.pkl", "r") as f:
uid_model = pickle.load(f)
with open("prediction_weibo.pkl", "r") as f:
weibo_model = pickle.load(f)
for item in es_results:
mid_list.append(item["_id"])
uid_list.append(item["_source"]["uid"])
tmp_feature_list = organize_feature(task_name,item["_id"], ts)
feature_list.append(tmp_feature_list)
weibo_prediction_result = weibo_model.predict(feature_list)
uid_prediction_result = uid_model.predict(feature_list)
future_total = 0
current_total = 0
results_dict = dict()
in_potential_list = []
for i in range(len(mid_list)):
mid = mid_list[i]
uid = uid_list[i]
iter_count = es.count(index=task_name, doc_type="text", body={"query":{"term":{"root_mid":mid}}})["count"]
pre_count = weibo_prediction_result[i]
future_total += abs(pre_count-iter_count)
if pre_count >= 500 and iter_count <= 500:
current_total += abs(pre_count-iter_count)
if not results_dict.has_key(uid):
results_dict[uid] = dict()
tmp = dict()
tmp["mid"] = mid
tmp["current_count"] = iter_count
tmp["prediction_count"] = int(pre_count)
weibo_detail = es.get(index=task_name, doc_type="text", id=mid)["_source"]
tmp.update(weibo_detail)
retweet, comment = search_retweet_comment(task_name, mid)
tmp["retweeted"] = retweet
tmp["comment"] = comment
results_dict[uid][mid] = tmp
# user profile
tmp_in_list = results_dict.keys()
if tmp_in_list:
profile_results = es_user_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={"ids":tmp_in_list})["docs"]
for i in range(len(tmp_in_list)):
detail = profile_results[i]
tmp = []
uid = tmp_in_list[i]
if detail["found"]:
tmp.append(detail["_source"]["nick_name"])
tmp.append(detail["_source"]["photo_url"])
tmp.append(detail["_source"]["fansnum"])
tmp.append(detail["_source"]["statusnum"])
else:
tmp.append(detail["_id"])
tmp.extend(["","",""])
results_dict[uid]["user_profile"] = tmp
return results_dict, future_total, current_total
def create_event_warning(xnr_user_no,start_time,end_time):
#获取事件名称
today_datetime = start_time
hashtag_list = get_hashtag(today_datetime)
#print 'hashtag_list::',hashtag_list
flow_text_index_name = get_day_flow_text_index_list(today_datetime)
#虚拟人的粉丝列表和关注列表
try:
es_xnr_result=es_xnr.get(index=weibo_xnr_fans_followers_index_name,doc_type=weibo_xnr_fans_followers_index_type,id=xnr_user_no)['_source']
followers_list=es_xnr_result['followers_list']
fans_list=es_xnr_result['fans_list']
except:
followers_list=[]
fans_list=[]
event_warming_list=[]
event_num=0
for event_item in hashtag_list:
event_sensitive_count=0
event_warming_content=dict() #事件名称、主要参与用户、典型微博、事件影响力、事件平均时间
event_warming_content['event_name']=event_item['event_name']
print 'event_name:',event_item
event_num=event_num+1
print 'event_num:::',event_num
print 'first_time:::',int(time.time())
event_influence_sum=0
event_time_sum=0
query_body={
'query':{
# 'bool':{
# 'must':[{'wildcard':{'text':'*'+event_item[0]+'*'}},
# {'range':{'sensitive':{'gte':1}}}]
# }
'filtered':{
'filter':{
'bool':{
'must':[
{'term':{'hashtag':event_item['event_name']}},
{'range':{'sensitive':{'gte':1}}},
{'range':{'timestamp':{'gte':start_time,'lte':end_time}}}
]
}
}
}
},
'size':MAX_WARMING_SIZE,
'sort':{'sensitive':{'order':'desc'}}
}
#try:
event_results=es_flow_text.search(index=flow_text_index_name,doc_type=flow_text_index_type,body=query_body)['hits']['hits']
print 'event:::',len(event_results),start_time,end_time
if event_results:
weibo_result=[]
fans_num_dict=dict()
followers_num_dict=dict()
alluser_num_dict=dict()
print 'sencond_time:::',int(time.time())
for item in event_results:
#print 'event_content:',item['_source']['text']
#统计用户信息
if alluser_num_dict.has_key(str(item['_source']['uid'])):
followers_mark=set_intersection(item['_source']['uid'],followers_list)
if followers_mark > 0:
alluser_num_dict[str(item['_source']['uid'])]=alluser_num_dict[str(item['_source']['uid'])]+1*2
else:
alluser_num_dict[str(item['_source']['uid'])]=alluser_num_dict[str(item['_source']['uid'])]+1
else:
alluser_num_dict[str(item['_source']['uid'])]=1
#计算影响力
origin_influence_value=(1+item['_source']['comment']+item['_source']['retweeted'])*(1+item['_source']['sensitive'])
# fans_value=judge_user_type(item['_source']['uid'],fans_list)
followers_value=judge_user_type(item['_source']['uid'],followers_list)
item['_source']['weibo_influence_value']=origin_influence_value*(followers_value)
item['_source']['nick_name']=get_user_nickname(item['_source']['uid'])
weibo_result.append(item['_source'])
#统计影响力、时间
event_influence_sum=event_influence_sum+item['_source']['weibo_influence_value']
event_time_sum=event_time_sum+item['_source']['timestamp']
print 'third_time:::',int(time.time())
#典型微博信息
the_weibo_result=remove_repeat_v2(weibo_result)
the_weibo_result.sort(key=lambda k:(k.get('weibo_influence_value',0)),reverse=True)
event_warming_content['main_weibo_info']=json.dumps(the_weibo_result)
#事件影响力和事件时间
number=len(event_results)
event_warming_content['event_influence']=event_influence_sum/number
event_warming_content['event_time']=event_time_sum/number
# except:
# event_warming_content['main_weibo_info']=[]
# event_warming_content['event_influence']=0
# event_warming_content['event_time']=0
# try:
#对用户进行排序
alluser_num_dict=sorted(alluser_num_dict.items(),key=lambda d:d[1],reverse=True)
main_userid_list=[]
for i in xrange(0,len(alluser_num_dict)):
main_userid_list.append(alluser_num_dict[i][0])
#主要参与用户信息
main_user_info=[]
user_es_result=es_user_profile.mget(index=profile_index_name,doc_type=profile_index_type,body={'ids':main_userid_list})['docs']
for item in user_es_result:
user_dict=dict()
if item['found']:
user_dict['photo_url']=item['_source']['photo_url']
user_dict['uid']=item['_id']
user_dict['nick_name']=item['_source']['nick_name']
user_dict['favoritesnum']=item['_source']['favoritesnum']
user_dict['fansnum']=item['_source']['fansnum']
else:
user_dict['photo_url']=''
user_dict['uid']=item['_id']
user_dict['nick_name']=''
user_dict['favoritesnum']=0
user_dict['fansnum']=0
main_user_info.append(user_dict)
event_warming_content['main_user_info']=json.dumps(main_user_info)
# except:
# event_warming_content['main_user_info']=[]
print 'fourth_time:::',int(time.time())
event_warming_content['xnr_user_no']=xnr_user_no
event_warming_content['validity']=0
event_warming_content['timestamp']=today_datetime
event_warming_list.append(event_warming_content)
else:
pass
print 'fifth_time:::',int(time.time())
return event_warming_list
def get_profile_information(uid_list):
result_dict = dict()
search_result = es.mget(index=index_name,
doc_type=index_type,
body={'ids': uid_list},
_source=True)['docs']
try:
bci_history_result = es_bci_history.mget(
index=bci_history_index_name,
doc_type=bci_history_index_type,
body={'ids': uid_list},
fields=['user_fansnum', 'weibo_month_sum',
'user_friendsnum'])['docs']
except:
bci_history_result = []
iter_count = 0
for item in search_result:
user_dict = {}
try:
bci_history_item = bci_history_result[iter_count]
except:
bci_history_item = {}
for field in fields_dict:
try:
if field == 'statusnum':
if bci_history_item and bci_history_item['found'] == True:
if isinstance(
bci_history_item['fields']['weibo_month_num']
[0], int):
user_dict[field] = bci_history_item['fields'][
'weibo_month_sum'][0]
else:
user_dict[field] = 0
else:
user_dict[field] = 0
elif field == 'fansnum':
if bci_history_item and bci_history_item['found'] == True:
if isinstance(
bci_history_item['fields']['user_fansnum'][0],
int):
user_dict[field] = bci_history_item['fields'][
'user_fansnum'][0]
else:
user_dict[field] = 0
else:
user_dict[field] = 0
elif field == 'friendsnum':
if bci_history_item and bci_history_item['found'] == True:
if isinstance(
bci_history_item['fields']['user_friendsnum']
[0], int):
user_dict[field] = bci_history_item['fields'][
'user_friendsnum'][0]
else:
user_dict[field] = 0
else:
user_dict[field] = 0
else:
try:
user_dict[field] = item['_source'][field]
except:
user_dict[field] = ''
except:
if field == 'statusnum':
user_dict[field] = 0
elif field == 'fansnum':
user_dict[field] = 0
elif field == 'friendsnum':
user_dict[field] = 0
elif field == 'gender':
user_dict[field] = 0
elif field == 'uname':
user_dict[field] = u'unknown'
else:
user_dict[field] = 'unknown'
result_dict[item['_id']] = user_dict
iter_count += 1
return result_dict
def get_profile_information(uid_list):
result_dict = dict()
search_result = es.mget(index=index_name, doc_type=index_type, body={'ids':uid_list}, _source=True)['docs']
try:
bci_history_result = es_bci_history.mget(index=bci_history_index_name, doc_type=bci_history_index_type, body={'ids': uid_list}, fields=['user_fansnum', 'weibo_month_sum', 'user_friendsnum'])['docs']
except:
bci_history_result = []
iter_count = 0
for item in search_result:
user_dict = {}
try:
bci_history_item = bci_history_result[iter_count]
except:
bci_history_item = {}
for field in fields_dict:
try:
if field == 'statusnum':
if bci_history_item and bci_history_item['found']==True:
if isinstance(bci_history_item['fields']['weibo_month_num'][0], int):
user_dict[field] = bci_history_item['fields']['weibo_month_sum'][0]
else:
user_dict[field] = 0
else:
user_dict[field] = 0
elif field == 'fansnum':
if bci_history_item and bci_history_item['found']==True:
if isinstance(bci_history_item['fields']['user_fansnum'][0], int):
user_dict[field] = bci_history_item['fields']['user_fansnum'][0]
else:
user_dict[field] = 0
else:
user_dict[field] = 0
elif field == 'friendsnum':
if bci_history_item and bci_history_item['found']==True:
if isinstance(bci_history_item['fields']['user_friendsnum'][0], int):
user_dict[field] = bci_history_item['fields']['user_friendsnum'][0]
else:
user_dict[field] = 0
else:
user_dict[field] = 0
else:
try:
user_dict[field] = item['_source'][field]
except:
user_dict[field] = ''
except:
if field=='statusnum':
user_dict[field] = 0
elif field=='fansnum':
user_dict[field] =0
elif field=='friendsnum':
user_dict[field] = 0
elif field=='gender':
user_dict[field] = 0
elif field=='uname':
user_dict[field] = u'unknown'
else:
user_dict[field] = 'unknown'
result_dict[item['_id']] = user_dict
iter_count += 1
return result_dict
def main():
if RUN_TYPE:
now_ts = time.time()-DAY # 前一天
now_ts = datetime2ts('2016-03-24')
ts = str(datetime2ts(ts2datetime(now_ts)))
else:
ts = str(datetime2ts('2016-03-16'))
now_ts = int(ts)
print now_ts
sensitive_string = "sensitive_" + ts
date_string = ts
update_sensitive_key = "sensitive_score_" + ts # 更新的键
sensitive_dict_key = "sensitive_dict_" + ts
sensitive_string_key = "sensitive_string_" + ts
sensitive_day_change_key = "sensitive_" + ts +"_day_change"
del_month = datetime2ts(ts2datetime(now_ts - MONTH))
del_sensitive_key = "sensitive_score_"+str(del_month) # 要删除的键
former_ts = int(ts) - DAY
former_date = str(datetime2ts(ts2datetime(former_ts)))
former_sensitive_key = "sensitive_score_" + former_date
iter_count = 0
bulk_action = []
mappings(ES_SENSITIVE_INDEX)
total_number = r.hlen(sensitive_string)
scan_cursor = 0
print total_number
while 1:
re_scan = r.hscan(sensitive_string, scan_cursor, count=1000)
scan_cursor = re_scan[0]
if len(re_scan[1]) != 0:
sensitive_info = re_scan[1] # 字典形式，uid：sensitive_words_dict
uid_list = sensitive_info.keys()
sensitive_results = es.mget(index=ES_SENSITIVE_INDEX, doc_type=DOCTYPE_SENSITIVE_INDEX, body={"ids":uid_list})['docs']
if sensitive_results:
for item in sensitive_results:
uid = item['_id']
sensitive_words_dict = json.loads(sensitive_info[uid]) # json.loads
current_sensitive_score = 0
for k,v in sensitive_words_dict.iteritems():
tmp_stage = r_sensitive.hget("sensitive_words", k)
if tmp_stage:
current_sensitive_score += v*sensitive_score_dict[str(tmp_stage)]
if item['found']: # 之前存在相关信息
revise_item = item["_source"]
if del_sensitive_key in revise_item:
item.remove(del_sensitive_key)
revise_item['uid'] = uid
# 新更新的敏感度
revise_item[update_sensitive_key] = current_sensitive_score
# 新更新的敏感词
revise_item[sensitive_dict_key] = sensitive_info[uid]
# 新更新的string
revise_item[sensitive_string_key] = "&".join(sensitive_words_dict.keys())
# 当天和之前一天、一周和一月均值的差异
revise_item['sensitive_day_change'] = current_sensitive_score - revise_item.get(former_sensitive_key, 0)
revise_item['sensitive_week_change'] = current_sensitive_score - revise_item.get('sensitive_week_ave', 0)
revise_item['sensitive_month_change'] = current_sensitive_score - revise_item.get('sensitive_month_ave', 0)
# 更新后week、month的均值和方差
revise_item['sensitive_week_ave'], revise_item['sensitive_week_var'], revise_item['sensitive_week_sum'] = compute_week(revise_item, now_ts)
revise_item['senstiive_month_ave'], revise_item['sensitive_month_var'], revise_item['sensitive_month_sum'] = compute_month(revise_item, now_ts)
else:
revise_item = dict()
revise_item['uid'] = uid
revise_item[update_sensitive_key] = current_sensitive_score
revise_item[sensitive_dict_key] = sensitive_info[uid]
revise_item[sensitive_string_key] = "&".join(sensitive_words_dict.keys())
revise_item['sensitive_day_change'] = current_sensitive_score
revise_item['sensitive_week_change'] = current_sensitive_score
revise_item['sensitive_month_change'] = current_sensitive_score
revise_item['sensitive_week_ave'], revise_item['sensitive_week_var'], revise_item['sensitive_week_sum'] = compute_week(revise_item, now_ts)
revise_item['senstiive_month_ave'], revise_item['sensitive_month_var'], revise_item['sensitive_month_sum'] = compute_month(revise_item, now_ts)
action = {'index':{'_id': uid}}
bulk_action.extend([action, revise_item])
iter_count += 1
if iter_count % 1000 == 0:
es.bulk(bulk_action, index=ES_SENSITIVE_INDEX, doc_type=DOCTYPE_SENSITIVE_INDEX)
bulk_action = []
print iter_count
if int(scan_cursor) == 0:
break
if bulk_action:
es.bulk(bulk_action, index=ES_SENSITIVE_INDEX, doc_type=DOCTYPE_SENSITIVE_INDEX)
print iter_count
