def influenced_user_detail(uid, date, origin_retweeted_mid, retweeted_retweeted_mid, message_type, default_number=20):
query_body = {
"query":{
"filtered":{
"filter":{
"bool":{
"must": [
]
}
}
}
},
"size":20000,
}
if RUN_TYPE == 1:
query_body["sort"] = {"user_fansnum":{"order":"desc"}}
#详细影响到的人
date1 = str(date).replace('-', '')
index_name = pre_index + date1
index_flow_text = pre_text_index + date
origin_retweeted_uid = [] # influenced user uid_list
retweeted_retweeted_uid = []
origin_comment_uid = []
retweeted_comment_uid = []
query_origin = copy.deepcopy(query_body)
query_retweeted = copy.deepcopy(query_body)
if origin_retweeted_mid: # 所有转发该条原创微博的用户
query_origin["query"]["filtered"]["filter"]["bool"]["must"].append({"terms": {"root_mid": origin_retweeted_mid}})
query_origin["query"]["filtered"]["filter"]["bool"]["must"].extend([{"term":{"message_type": message_type}}, {"term":{"root_uid": uid}}])
origin_retweeted_result = es.search(index=index_flow_text, doc_type=flow_text_index_type, body=query_origin, fields=["uid"])["hits"]["hits"]
if origin_retweeted_result:
for item in origin_retweeted_result:
origin_retweeted_uid.append(item["fields"]["uid"][0])
if retweeted_retweeted_mid: # 所有评论该条原创微博的用户
query_retweeted["query"]["filtered"]["filter"]["bool"]["must"].append({"terms": {"root_mid": retweeted_retweeted_mid}})
query_retweeted["query"]["filtered"]["filter"]["bool"]["must"].extend([{"term":{"message_type": message_type}},{"term": {"directed_uid": uid}}])
retweeted_retweeted_result = es.search(index=index_flow_text, doc_type=flow_text_index_type, body=query_retweeted, fields=["uid"])["hits"]["hits"]
if retweeted_retweeted_result:
for item in retweeted_retweeted_result:
retweeted_retweeted_uid.append(item["fields"]["uid"][0])
retweeted_uid_list = [] # all retweeted user list
retweeted_results = {} # statistics of all retweeted uid information
retweeted_domain = {}
retweeted_topic = {}
retweeted_geo = {}
bci_results = {}
in_portrait = []
out_portrait = []
average_influence = 0
total_influence = 0
count = 0
all_uid_set = set(origin_retweeted_uid) | set(retweeted_retweeted_uid)
retweeted_uid_list.extend(origin_retweeted_uid)
retweeted_uid_list.extend(retweeted_retweeted_uid)
retweeted_uid_list = list(set(retweeted_uid_list) - set([uid])) # filter uids
if retweeted_uid_list:
user_portrait_result = es_user_portrait.mget(index=user_portrait, doc_type=portrait_index_type, body={"ids": retweeted_uid_list}, fields=["domain", "topic_string", "activity_geo_dict","importance", "influence"])["docs"]
bci_index = "bci_" + date.replace('-', '')
bci_results = es_cluster.mget(index=bci_index, doc_type="bci", body={"ids":retweeted_uid_list}, fields=['user_index'])["docs"]
for item in user_portrait_result:
if item["found"]:
temp = []
count += 1
temp.append(item['_id'])
temp.append(item["fields"]["importance"][0])
in_portrait.append(temp)
temp_domain = item["fields"]["domain"][0].split('&')
temp_topic = item["fields"]["topic_string"][0].split('&')
temp_geo = json.loads(item["fields"]["activity_geo_dict"][0])[-1].keys()
#total_influence += item["fields"]["influence"][0]
retweeted_domain = aggregation(temp_domain, retweeted_domain)
retweeted_topic = aggregation(temp_topic, retweeted_topic)
retweeted_geo = aggregation(temp_geo, retweeted_geo)
else:
out_portrait.append(item['_id'])
retweeted_domain = proportion(retweeted_domain)
retweeted_topic = proportion(retweeted_topic)
retweeted_geo = proportion(retweeted_geo)
if bci_results:
total_influence = 0
for item in bci_results:
if item['found']:
total_influence += item['fields']['user_index'][0]
try:
average_influence = total_influence/len(retweeted_uid_list)
except:
average_influence = 0
sorted_retweeted_domain = sorted(retweeted_domain.items(),key=lambda x:x[1], reverse=True)
sorted_retweeted_topic = sorted(retweeted_topic.items(),key=lambda x:x[1], reverse=True)
sorted_retweeted_geo = sorted(retweeted_geo.items(), key=lambda x:x[1], reverse=True)
retweeted_results["domian"] = sorted_retweeted_domain[:5]
retweeted_results["topic"] = sorted_retweeted_topic[:5]
retweeted_results["geo"] = sorted_retweeted_geo[:5]
retweeted_results["influence"] = average_influence
in_portrait = sorted(in_portrait, key=lambda x:x[1], reverse=True)
temp_list = []
for item in in_portrait:
temp_list.append(item[0])
retweeted_results['in_portrait_number'] = len(temp_list)
retweeted_results['out_portrait_number'] = len(out_portrait)
in_portrait_url = get_user_url(temp_list[:default_number])
out_portrait_url = get_user_url(out_portrait[:default_number])
retweeted_results["in_portrait"] = in_portrait_url
retweeted_results["out_portrait"] = out_portrait_url
retweeted_results["total_number"] = len(temp_list) + len(out_portrait)
return retweeted_results
def influenced_people(uid, mid, influence_style, date, default_number=20):
# uid
# which weibo----mid, retweeted weibo ---seek for root_mid
# influence_style: retweeted(0) or comment(1)
date1 = ts2datetime(datetime2ts(date)).replace('-', '')
index_name = pre_index + date1
index_flow_text = pre_text_index + date
text_result = es.get(index=index_flow_text, doc_type=flow_text_index_type, id=mid)["_source"]
temp_mid = text_result.get("root_mid",'') #判断微博是否是原创微博
if temp_mid:
mid_type = 1 # 非原创微博
else:
mid_type = 0 # 原创微博
query_body = {
"query":{
"filtered":{
"filter":{
"bool":{
"must":[
]
}
}
}
},
"size": 30000
}
if RUN_TYPE:
query_body["sort"] = {"user_fansnum":{"order":"desc"}}
if int(mid_type) == 0:
if int(influence_style) == 0: # origin weibo, all retweeted people
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend([{"term": {"root_uid": uid}}, {"term": {"message_type": 3}}, {"term": {"root_mid": mid}}])
else: # commented people
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend([{"term": {"directed_uid": uid}}, {"term": {"message_type": 2}}, {"term": {"root_mid": mid}}])
else:
if int(influence_style) == 0: # origin weibo, all retweeted people
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend([{"term": {"directed_uid": uid}}, {"term": {"message_type": 3}}, {"term": {"root_mid": temp_mid}}])
else: # commented people
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend([{"term": {"directed_uid": uid}}, {"term": {"message_type": 2}}, {"term": {"root_mid": temp_mid}}])
search_results = es.search(index=index_flow_text, doc_type=flow_text_index_type, body=query_body, _source=False, fields=["uid"], timeout=30)["hits"]["hits"]
results = [] # uid_list
if search_results:
for item in search_results:
if int(item["fields"]["uid"][0]) == int(uid):
pass
else:
results.append(item["fields"]["uid"][0])
results = list(set(results))
else:
results = []
bci_index = "bci_" + date.replace('-','')
if results:
portrait_results = es_user_portrait.mget(index=user_portrait, doc_type=portrait_index_type, body={"ids": results}, fields=["domain", "topic_string", "activity_geo_dict","importance", "influence"])["docs"]
bci_results = es_cluster.mget(index=bci_index, doc_type='bci', body={"ids":results}, fields=['user_index'])['docs']
else:
portrait_results = {}
bci_results = {}
in_portrait = []
out_portrait = []
in_portrait_info = []
retweeted_domain = {}
retweeted_topic = {}
retweeted_geo = {}
average_influence = 0
total_influence = 0
count = 0
if bci_results:
total_influence = 0
for item in bci_results:
if item['found']:
total_influence += item['fields']['user_index'][0]
try:
average_influence = total_influence/len(results)
except:
average_influence = 0
if portrait_results:
for item in portrait_results:
if item["found"]:
temp = []
count += 1
temp.append(item['_id'])
temp.append(item["fields"]["importance"][0])
in_portrait.append(temp)
temp_domain = item["fields"]["domain"][0].split('&')
temp_topic = item["fields"]["topic_string"][0].split('&')
temp_geo = json.loads(item["fields"]["activity_geo_dict"][0])[-1].keys()
#total_influence += item["fields"]["influence"][0]
retweeted_domain = aggregation(temp_domain, retweeted_domain)
retweeted_topic = aggregation(temp_topic, retweeted_topic)
retweeted_geo = aggregation(temp_geo, retweeted_geo)
else:
out_portrait.append(item['_id'])
retweeted_domain = proportion(retweeted_domain)
retweeted_topic = proportion(retweeted_topic)
retweeted_geo = proportion(retweeted_geo)
#try:
# average_influence = total_influence/count
#except:
# average_influence = 0
sorted_retweeted_domain = sorted(retweeted_domain.items(),key=lambda x:x[1], reverse=True)
sorted_retweeted_topic = sorted(retweeted_topic.items(),key=lambda x:x[1], reverse=True)
sorted_retweeted_geo = sorted(retweeted_geo.items(), key=lambda x:x[1], reverse=True)
retweeted_results = dict()
retweeted_results["domian"] = sorted_retweeted_domain[:5]
retweeted_results["topic"] = sorted_retweeted_topic[:5]
retweeted_results["geo"] = sorted_retweeted_geo[:5]
retweeted_results["influence"] = average_influence
in_portrait = sorted(in_portrait, key=lambda x:x[1], reverse=True)
temp_list = []
for item in in_portrait:
temp_list.append(item[0])
retweeted_results['in_portrait_number'] = len(temp_list)
retweeted_results['out_portrait_number'] = len(out_portrait)
in_portrait_url = get_user_url(temp_list[:default_number])
out_portrait_url = get_user_url(out_portrait[:default_number])
return_results = dict()
return_results["influence_users"] = [in_portrait_url, out_portrait_url]
return_results["influence_distribution"] = retweeted_results
return return_results
def influenced_user_detail(uid, date, origin_retweeted_mid, retweeted_retweeted_mid, message_type, default_number=20):
query_body = {"query": {"filtered": {"filter": {"bool": {"should": [], "must": []}}}}, "size": 10000}
# 详细影响到的人
date1 = str(date).replace("-", "")
index_name = pre_index + date1
index_flow_text = pre_text_index + date
origin_retweeted_uid = [] # influenced user uid_list
retweeted_retweeted_uid = []
origin_comment_uid = []
retweeted_comment_uid = []
if origin_retweeted_mid: # 所有转发该条原创微博的用户
length = len(origin_retweeted_mid)
if length != 1:
for iter_mid in origin_retweeted_mid:
query_body["query"]["filtered"]["filter"]["bool"]["should"].append({"term": {"root_mid": iter_mid}})
else:
iter_mid = origin_retweeted_mid[0]
query_body["query"]["filtered"]["filter"]["bool"]["must"].append({"term": {"root_mid": iter_mid}})
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend(
[{"term": {"message_type": message_type}}, {"term": {"root_uid": uid}}]
)
origin_retweeted_result = es.search(
index=index_flow_text, doc_type=flow_text_index_type, body=query_body, fields=["uid"]
)["hits"]["hits"]
if origin_retweeted_result:
for item in origin_retweeted_result:
origin_retweeted_uid.append(item["fields"]["uid"][0])
if retweeted_retweeted_mid: # 所有评论该条原创微博的用户
length = len(retweeted_retweeted_mid)
if length != 1:
for iter_mid in retweeted_retweeted_mid:
query_body["query"]["filtered"]["filter"]["bool"]["should"].append({"term": {"root_mid": iter_mid}})
else:
iter_mid = retweeted_retweeted_mid[0]
query_body["query"]["filtered"]["filter"]["bool"]["must"].append({"term": {"root_mid": iter_mid}})
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend(
[{"term": {"message_type": message_type}}, {"term": {"directed_uid": uid}}]
)
retweeted_retweeted_result = es.search(
index=index_flow_text, doc_type=flow_text_index_type, body=query_body, fields=["uid"]
)["hits"]["hits"]
if retweeted_retweeted_result:
for item in retweeted_retweeted_result:
retweeted_retweeted_uid.append(item["fields"]["uid"][0])
retweeted_uid_list = [] # all retweeted user list
retweeted_results = {} # statistics of all retweeted uid information
retweeted_domain = {}
retweeted_topic = {}
retweeted_geo = {}
in_portrait = []
out_portrait = []
average_influence = 0
total_influence = 0
count = 0
retweeted_uid_list.extend(origin_retweeted_uid)
retweeted_uid_list.extend(retweeted_retweeted_uid)
retweeted_uid_list = list(set(retweeted_uid_list) - set([uid])) # filter uids
if retweeted_uid_list:
user_portrait_result = es_user_portrait.mget(
index=user_portrait,
doc_type=portrait_index_type,
body={"ids": retweeted_uid_list},
fields=["domain", "topic_string", "activity_geo_dict", "importance", "influence"],
)["docs"]
for item in user_portrait_result:
if item["found"]:
temp = []
count += 1
temp.append(item["_id"])
temp.append(item["fields"]["importance"][0])
in_portrait.append(temp)
temp_domain = item["fields"]["domain"][0].split("&")
temp_topic = item["fields"]["topic_string"][0].split("&")
temp_geo = json.loads(item["fields"]["activity_geo_dict"][0])[-1].keys()
total_influence += item["fields"]["influence"][0]
retweeted_domain = aggregation(temp_domain, retweeted_domain)
retweeted_topic = aggregation(temp_topic, retweeted_topic)
retweeted_geo = aggregation(temp_geo, retweeted_geo)
else:
out_portrait.append(item["_id"])
retweeted_domain = proportion(retweeted_domain)
retweeted_topic = proportion(retweeted_topic)
retweeted_geo = proportion(retweeted_geo)
try:
average_influence = total_influence / count
except:
average_influence = 0
sorted_retweeted_domain = sorted(retweeted_domain.items(), key=lambda x: x[1], reverse=True)
sorted_retweeted_topic = sorted(retweeted_topic.items(), key=lambda x: x[1], reverse=True)
sorted_retweeted_geo = sorted(retweeted_geo.items(), key=lambda x: x[1], reverse=True)
retweeted_results["domian"] = sorted_retweeted_domain[:5]
retweeted_results["topic"] = sorted_retweeted_topic[:5]
retweeted_results["geo"] = sorted_retweeted_geo[:5]
retweeted_results["influence"] = average_influence
in_portrait = sorted(in_portrait, key=lambda x: x[1], reverse=True)
temp_list = []
for item in in_portrait:
temp_list.append(item[0])
# print temp_list[:20]
# print out_portrait[:20]
retweeted_results["in_portrait_number"] = len(temp_list)
retweeted_results["out_portrait_number"] = len(out_portrait)
in_portrait_url = get_user_url(temp_list[:default_number])
out_portrait_url = get_user_url(out_portrait[:default_number])
retweeted_results["in_portrait"] = in_portrait_url
retweeted_results["out_portrait"] = out_portrait_url
return retweeted_results
def influenced_user_detail(uid,
date,
origin_retweeted_mid,
retweeted_retweeted_mid,
message_type,
default_number=20):
query_body = {
"query": {
"filtered": {
"filter": {
"bool": {
"should": [],
"must": []
}
}
}
},
"size": 10000
}
#详细影响到的人
date1 = str(date).replace('-', '')
index_name = pre_index + date1
index_flow_text = pre_text_index + date
origin_retweeted_uid = [] # influenced user uid_list
retweeted_retweeted_uid = []
origin_comment_uid = []
retweeted_comment_uid = []
if origin_retweeted_mid: # 所有转发该条原创微博的用户
length = len(origin_retweeted_mid)
if length != 1:
for iter_mid in origin_retweeted_mid:
query_body["query"]["filtered"]["filter"]["bool"][
"should"].append({"term": {
"root_mid": iter_mid
}})
else:
iter_mid = origin_retweeted_mid[0]
query_body["query"]["filtered"]["filter"]["bool"]["must"].append(
{"term": {
"root_mid": iter_mid
}})
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend([{
"term": {
"message_type": message_type
}
}, {
"term": {
"root_uid": uid
}
}])
origin_retweeted_result = es.search(index=index_flow_text,
doc_type=flow_text_index_type,
body=query_body,
fields=["uid"])["hits"]["hits"]
if origin_retweeted_result:
for item in origin_retweeted_result:
origin_retweeted_uid.append(item["fields"]["uid"][0])
if retweeted_retweeted_mid: # 所有评论该条原创微博的用户
length = len(retweeted_retweeted_mid)
if length != 1:
for iter_mid in retweeted_retweeted_mid:
query_body["query"]["filtered"]["filter"]["bool"][
"should"].append({"term": {
"root_mid": iter_mid
}})
else:
iter_mid = retweeted_retweeted_mid[0]
query_body["query"]["filtered"]["filter"]["bool"]["must"].append(
{"term": {
"root_mid": iter_mid
}})
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend([{
"term": {
"message_type": message_type
}
}, {
"term": {
"directed_uid": uid
}
}])
retweeted_retweeted_result = es.search(index=index_flow_text,
doc_type=flow_text_index_type,
body=query_body,
fields=["uid"])["hits"]["hits"]
if retweeted_retweeted_result:
for item in retweeted_retweeted_result:
retweeted_retweeted_uid.append(item["fields"]["uid"][0])
retweeted_uid_list = [] # all retweeted user list
retweeted_results = {} # statistics of all retweeted uid information
retweeted_domain = {}
retweeted_topic = {}
retweeted_geo = {}
in_portrait = []
out_portrait = []
average_influence = 0
total_influence = 0
count = 0
retweeted_uid_list.extend(origin_retweeted_uid)
retweeted_uid_list.extend(retweeted_retweeted_uid)
retweeted_uid_list = list(set(retweeted_uid_list) -
set([uid])) # filter uids
if retweeted_uid_list:
user_portrait_result = es_user_portrait.mget(
index=user_portrait,
doc_type=portrait_index_type,
body={"ids": retweeted_uid_list},
fields=[
"domain", "topic_string", "activity_geo_dict", "importance",
"influence"
])["docs"]
for item in user_portrait_result:
if item["found"]:
temp = []
count += 1
temp.append(item['_id'])
temp.append(item["fields"]["importance"][0])
in_portrait.append(temp)
temp_domain = item["fields"]["domain"][0].split('&')
temp_topic = item["fields"]["topic_string"][0].split('&')
temp_geo = json.loads(
item["fields"]["activity_geo_dict"][0])[-1].keys()
total_influence += item["fields"]["influence"][0]
retweeted_domain = aggregation(temp_domain, retweeted_domain)
retweeted_topic = aggregation(temp_topic, retweeted_topic)
retweeted_geo = aggregation(temp_geo, retweeted_geo)
else:
out_portrait.append(item['_id'])
retweeted_domain = proportion(retweeted_domain)
retweeted_topic = proportion(retweeted_topic)
retweeted_geo = proportion(retweeted_geo)
try:
average_influence = total_influence / count
except:
average_influence = 0
sorted_retweeted_domain = sorted(retweeted_domain.items(),
key=lambda x: x[1],
reverse=True)
sorted_retweeted_topic = sorted(retweeted_topic.items(),
key=lambda x: x[1],
reverse=True)
sorted_retweeted_geo = sorted(retweeted_geo.items(),
key=lambda x: x[1],
reverse=True)
retweeted_results["domian"] = sorted_retweeted_domain[:5]
retweeted_results["topic"] = sorted_retweeted_topic[:5]
retweeted_results["geo"] = sorted_retweeted_geo[:5]
retweeted_results["influence"] = average_influence
in_portrait = sorted(in_portrait, key=lambda x: x[1], reverse=True)
temp_list = []
for item in in_portrait:
temp_list.append(item[0])
#print temp_list[:20]
#print out_portrait[:20]
retweeted_results['in_portrait_number'] = len(temp_list)
retweeted_results['out_portrait_number'] = len(out_portrait)
in_portrait_url = get_user_url(temp_list[:default_number])
out_portrait_url = get_user_url(out_portrait[:default_number])
retweeted_results["in_portrait"] = in_portrait_url
retweeted_results["out_portrait"] = out_portrait_url
return retweeted_results
def influenced_people(uid, mid, influence_style, date, default_number=20):
# uid
# which weibo----mid, retweeted weibo ---seek for root_mid
# influence_style: retweeted(0) or comment(1)
date1 = str(date).replace("-", "")
index_name = pre_index + date1
index_flow_text = pre_text_index + date
text_result = es.get(index=index_flow_text, doc_type=flow_text_index_type, id=mid)["_source"]
temp_mid = text_result.get("root_mid", "") # 判断微博是否是原创微博
print temp_mid
if temp_mid:
mid_type = 1 # 非原创微博
else:
mid_type = 0 # 原创微博
query_body = {"query": {"filtered": {"filter": {"bool": {"must": []}}}}, "size": 100000}
if mid_type == 0:
if int(influence_style) == 0: # origin weibo, all retweeted people
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend(
[{"term": {"root_uid": uid}}, {"term": {"message_type": 3}}, {"term": {"root_mid": mid}}]
)
else: # commented people
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend(
[{"term": {"directed_uid": uid}}, {"term": {"message_type": 2}}, {"term": {"root_mid": mid}}]
)
else:
if int(influence_style) == 0: # origin weibo, all retweeted people
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend(
[{"term": {"directed_uid": uid}}, {"term": {"message_type": 3}}, {"term": {"root_mid": temp_mid}}]
)
else: # commented people
query_body["query"]["filtered"]["filter"]["bool"]["must"].extend(
[{"term": {"directed_uid": uid}}, {"term": {"message_type": 2}}, {"term": {"root_mid": temp_mid}}]
)
search_results = es.search(
index=index_flow_text, doc_type=flow_text_index_type, body=query_body, fields=["uid"], timeout=30
)["hits"]["hits"]
results = []
if search_results:
for item in search_results:
if int(item["fields"]["uid"][0]) == int(uid):
pass
else:
results.append(item["fields"]["uid"][0])
results = list(set(results))
else:
results = []
if results:
portrait_results = es_user_portrait.mget(
index=user_portrait,
doc_type=portrait_index_type,
body={"ids": results},
fields=["domain", "topic_string", "activity_geo_dict", "importance", "influence"],
)["docs"]
else:
portrait_results = {}
in_portrait = []
out_portrait = []
in_portrait_info = []
retweeted_domain = {}
retweeted_topic = {}
retweeted_geo = {}
average_influence = 0
total_influence = 0
count = 0
if portrait_results:
for item in portrait_results:
if item["found"]:
temp = []
count += 1
temp.append(item["_id"])
temp.append(item["fields"]["importance"][0])
in_portrait.append(temp)
temp_domain = item["fields"]["domain"][0].split("&")
temp_topic = item["fields"]["topic_string"][0].split("&")
temp_geo = json.loads(item["fields"]["activity_geo_dict"][0])[-1].keys()
total_influence += item["fields"]["influence"][0]
retweeted_domain = aggregation(temp_domain, retweeted_domain)
retweeted_topic = aggregation(temp_topic, retweeted_topic)
retweeted_geo = aggregation(temp_geo, retweeted_geo)
else:
out_portrait.append(item["_id"])
retweeted_domain = proportion(retweeted_domain)
retweeted_topic = proportion(retweeted_topic)
retweeted_geo = proportion(retweeted_geo)
try:
average_influence = total_influence / count
except:
average_influence = 0
sorted_retweeted_domain = sorted(retweeted_domain.items(), key=lambda x: x[1], reverse=True)
sorted_retweeted_topic = sorted(retweeted_topic.items(), key=lambda x: x[1], reverse=True)
sorted_retweeted_geo = sorted(retweeted_geo.items(), key=lambda x: x[1], reverse=True)
retweeted_results = dict()
retweeted_results["domian"] = sorted_retweeted_domain[:5]
retweeted_results["topic"] = sorted_retweeted_topic[:5]
retweeted_results["geo"] = sorted_retweeted_geo[:5]
retweeted_results["influence"] = average_influence
in_portrait = sorted(in_portrait, key=lambda x: x[1], reverse=True)
temp_list = []
for item in in_portrait:
temp_list.append(item[0])
print temp_list[:20]
print out_portrait[:20]
retweeted_results["in_portrait_number"] = len(temp_list)
retweeted_results["out_portrait_number"] = len(out_portrait)
in_portrait_url = get_user_url(temp_list[:default_number])
out_portrait_url = get_user_url(out_portrait[:default_number])
return_results = dict()
return_results["influence_users"] = [in_portrait_url, out_portrait_url]
return_results["influence_distribution"] = retweeted_results
return return_results
return [in_portrait_url[:default_number], out_portrait_url[:default_number]]
