def get_user_portrait(uid_list, specify_field=[]):
if not uid_list:
return []
results = []
max_result = get_evaluate_max()
fields_list = ['uname','domain','topic_string','politics','fansnum','statusnum','friendsnum','location']
index_list = ["activeness", 'importance', 'influence', 'sensitive']
search_results = es.mget(index=portrait_index_name,doc_type=portrait_index_type,body={"ids":uid_list}, _source=False, \
fields=['uname','domain','topic_string','politics','fansnum','statusnum','friendsnum','location','activeness','importance','influence','sensitive'])["docs"]
if specify_field:
fields_list = specify_field
for item in search_results:
iter_result = []
iter_result.append(item['_id'])
if item['found']:
for iter_field in fields_list:
if iter_field == "topic_string":
iter_result.append(item['fields'][iter_field][0].split('&'))
else:
iter_result.append(item['fields'][iter_field][0])
for iter_field in index_list:
index_value = item['fields'][iter_field][0]
normal_value = normalize_index(index_value, max_result[iter_field])
iter_result.append(normal_value)
else:
iter_result.extend(['']*12)
results.append(iter_result)
return results
def get_user_portrait(uid_list, specify_field=[]):
if not uid_list:
return []
results = []
max_result = get_evaluate_max()
fields_list = [
'uname', 'domain', 'topic_string', 'politics', 'fansnum', 'statusnum',
'friendsnum', 'location'
]
index_list = ["activeness", 'importance', 'influence', 'sensitive']
search_results = es.mget(index=portrait_index_name,doc_type=portrait_index_type,body={"ids":uid_list}, _source=False, \
fields=['uname','domain','topic_string','politics','fansnum','statusnum','friendsnum','location','activeness','importance','influence','sensitive'])["docs"]
if specify_field:
fields_list = specify_field
for item in search_results:
iter_result = []
iter_result.append(item['_id'])
if item['found']:
for iter_field in fields_list:
if iter_field == "topic_string":
iter_result.append(
item['fields'][iter_field][0].split('&'))
else:
iter_result.append(item['fields'][iter_field][0])
for iter_field in index_list:
index_value = item['fields'][iter_field][0]
normal_value = normalize_index(index_value,
max_result[iter_field])
iter_result.append(normal_value)
else:
iter_result.extend([''] * 12)
results.append(iter_result)
return results
def get_user_portrait_byidname(uid, isuid=True, specify_field=[]):
uid_list = [uid]
results = []
max_result = get_evaluate_max()
fields_list = ['uname','domain','topic_string','politics','fansnum','statusnum','friendsnum','location', 'hashtag', 'activity_geo', 'keywords_string']
if specify_field:
fields_list = specify_field
if isuid:
search_results = es.mget(index=portrait_index_name,doc_type=portrait_index_type,body={"ids":uid_list}, _source=False, \
fields=['uname','domain','topic_string','politics','fansnum','statusnum', 'hashtag_string', 'activity_geo', 'friendsnum','location','activeness','importance','influence','sensitive', 'keywords_dict'])["docs"]
for item in search_results:
iter_result = []
iter_result.append(item['_id'])
if item['found']:
for iter_field in fields_list:
if iter_field == "topic_string":
iter_result.append(item['fields'][iter_field][0])
#iter_result.append(item['fields'][iter_field][0].split('&'))
elif iter_field == "keywords_dict":
iter_result.append(json.loads(item['fields'][iter_field][0]))
else:
iter_result.append(item['fields'][iter_field][0])
else:
iter_result = None
results.append(iter_result)
else:
query_body = {
"query":{
"bool": {
"should": [
{"term": {"uname": uid}}
]
}
},
"size": 1
}
search_results = es.search(index=portrait_index_name,doc_type=portrait_index_type,body=query_body, \
fields=['uname','domain','topic_string','politics','fansnum','statusnum', 'hashtag_string', 'activity_geo', 'friendsnum','location','activeness','importance','influence','sensitive', 'keywords_dict'])['hits']['hits']
if len(search_results) == 0:
results.append(None)
for item in search_results:
iter_result = []
iter_result.append(item['_id'])
for iter_field in fields_list:
if iter_field == "topic_string":
iter_result.append(item['fields'][iter_field][0])
#iter_result.append(item['fields'][iter_field][0].split('&'))
elif iter_field == "keywords_dict":
iter_result.append(json.loads(item['fields'][iter_field][0]))
else:
iter_result.append(item['fields'][iter_field][0])
results.append(iter_result)
return results
def filter_in(top_user_set):
results = []
try:
in_results = es_sensitive_user_portrait.mget(index=portrait_index_name, doc_type=portrait_index_type, body={'ids':list(top_user_set)})
except Exception as e:
print Exception, e
filter_list = [item['_id'] for item in in_results['docs'] if item['found'] is True]
results = set(top_user_set) - set(filter_list)
return results
def filter_in(top_user_set):
results = []
try:
in_results = es_sensitive_user_portrait.mget(index='user_portrait', doc_type='user', body={'ids':list(top_user_set)})
except Exception as e:
raise e
filter_list = [item['_id'] for item in in_results['docs'] if item['found'] is True]
print 'before filter in: ', len(top_user_set)
print 'filter_list: ', len(filter_list)
results = set(top_user_set) - set(filter_list)
#print 'after filter in: ', len(results)
return results
def filter_in(top_user_set):
results = []
try:
in_results = es_sensitive_user_portrait.mget(
index=portrait_index_name,
doc_type=portrait_index_type,
body={'ids': list(top_user_set)})
except Exception as e:
print Exception, e
filter_list = [
item['_id'] for item in in_results['docs'] if item['found'] is True
]
results = set(top_user_set) - set(filter_list)
return results
def filter_in(top_user_set):
results = []
try:
in_results = es_sensitive_user_portrait.mget(
index='user_portrait',
doc_type='user',
body={'ids': list(top_user_set)})
except Exception as e:
raise e
filter_list = [
item['_id'] for item in in_results['docs'] if item['found'] is True
]
print 'before filter in: ', len(top_user_set)
print 'filter_list: ', len(filter_list)
results = set(top_user_set) - set(filter_list)
#print 'after filter in: ', len(results)
return results
def get_user_portrait_byidname(uid, isuid=True, specify_field=[]):
uid_list = [uid]
results = []
max_result = get_evaluate_max()
fields_list = [
'uname', 'domain', 'topic_string', 'politics', 'fansnum', 'statusnum',
'friendsnum', 'location', 'hashtag', 'activity_geo', 'keywords_string'
]
if specify_field:
fields_list = specify_field
if isuid:
search_results = es.mget(index=portrait_index_name,doc_type=portrait_index_type,body={"ids":uid_list}, _source=False, \
fields=['uname','domain','topic_string','politics','fansnum','statusnum', 'hashtag_string', 'activity_geo', 'friendsnum','location','activeness','importance','influence','sensitive', 'keywords_dict'])["docs"]
for item in search_results:
iter_result = []
iter_result.append(item['_id'])
if item['found']:
for iter_field in fields_list:
if iter_field == "topic_string":
iter_result.append(item['fields'][iter_field][0])
#iter_result.append(item['fields'][iter_field][0].split('&'))
elif iter_field == "keywords_dict":
iter_result.append(
json.loads(item['fields'][iter_field][0]))
else:
iter_result.append(item['fields'][iter_field][0])
else:
iter_result = None
results.append(iter_result)
else:
query_body = {
"query": {
"bool": {
"should": [{
"term": {
"uname": uid
}
}]
}
},
"size": 1
}
search_results = es.search(index=portrait_index_name,doc_type=portrait_index_type,body=query_body, \
fields=['uname','domain','topic_string','politics','fansnum','statusnum', 'hashtag_string', 'activity_geo', 'friendsnum','location','activeness','importance','influence','sensitive', 'keywords_dict'])['hits']['hits']
if len(search_results) == 0:
results.append(None)
for item in search_results:
iter_result = []
iter_result.append(item['_id'])
for iter_field in fields_list:
if iter_field == "topic_string":
iter_result.append(item['fields'][iter_field][0])
#iter_result.append(item['fields'][iter_field][0].split('&'))
elif iter_field == "keywords_dict":
iter_result.append(
json.loads(item['fields'][iter_field][0]))
else:
iter_result.append(item['fields'][iter_field][0])
results.append(iter_result)
return results
