def network_pro_hashtags():
# Extract interaction networks from proed and pro-recoveryed hashtaged tweeets
# Select only recovery users who have hashtags from ED hashtag topics
# rec_tag_users = set(iot.get_values_one_field('fed', 'tag_com', 'id', {'rec_tageted': True}))
# ped_tag_users = set(iot.get_values_one_field('fed', 'tag_com', 'id', {'ped_tageted': True}))
# rec_tag_users = set(iot.get_values_one_field('fed', 'prorec_tag', 'user.id'))
# ped_tag_users = set(iot.get_values_one_field('fed', 'proed_tag', 'user.id'))
# fedusers = iot.get_values_one_field('fed', 'com', 'id')
fedusers = pickle.load(open('fed-user-id-str.pick', 'r'))
print len(fedusers)
users = [int(uid) for uid in fedusers]
# only_ped = ped_tag_users - rec_tag_users
# only_rec = rec_tag_users - ped_tag_users
# all_users = list(rec_tag_users.union(ped_tag_users))
for btype in ['communication']:
# gb = gt.load_beh_network('fed', 'bnet_ed_tag', btype)
gb = gt.load_beh_network_subset(users, 'fed', 'bnet_ed_tag', btype)
# for v in gb.vs:
# if int(v['name']) in only_ped:
# v['set'] = -1
# elif int(v['name']) in only_rec:
# v['set'] = 1
# else:
# v['set'] = 0
gt.summary(gb)
gb.write_graphml(btype+'-only-fed.graphml')
def network_analysis():
# output network among depression users
# user1 = iot.get_values_one_field('depression', 'users1', 'id')
# user2 = iot.get_values_one_field('depression', 'users2', 'id')
# print len(user1), len(user2)
# alluser = user1 + user2
alluser = iot.get_values_one_field('depression', 'depressive', 'id')
follow_net = gt.load_network_subset('depression', 'net', {
'user': {
'$in': alluser
},
'follower': {
'$in': alluser
}
})
gt.net_stat(follow_net)
follow_net.write_graphml('data/follow_net.graphml')
for beh in ['retweet', 'communication']:
print beh
bnetwork = gt.load_beh_network_subset(userlist=alluser,
db_name='depression',
collection='bnet',
btype=beh)
gt.net_stat(bnetwork)
bnetwork.write_graphml('data/' + beh + '_net.graphml')
def generate(dbname, comname, netname, type):
if type == 'follow':
g = gt.load_network(dbname, netname)
else:
# uids = iot.get_values_one_field(dbname, comname, 'id')
# pickle.dump(uids, open('data/'+dbname+'-ids.pick', 'w'))
uids = pickle.load(open('data/'+dbname+'-ids.pick', 'r'))
g = gt.load_beh_network_subset(uids, dbname, netname, type)
pickle.dump(g, open('data/'+dbname+type+'.pick', 'w'))
def generate(dbname, comname, netname, type):
if type == 'follow':
g = gt.load_network(dbname, netname)
else:
# uids = iot.get_values_one_field(dbname, comname, 'id')
# pickle.dump(uids, open('data/'+dbname+'-ids.pick', 'w'))
uids = pickle.load(open('data/' + dbname + '-ids.pick', 'r'))
g = gt.load_beh_network_subset(uids, dbname, netname, type)
pickle.dump(g, open('data/' + dbname + type + '.pick', 'w'))
def diversity_db(dbname, comname, behavior, netname):
userlist = iot.get_values_one_field(dbname, comname, 'id',
# {'timeline_count': {'$gt': 0}}
)
g = gt.load_beh_network_subset(userlist, dbname, netname, behavior)
gt.summary(g)
# g = bahavior_net(dbname, comname, netname, behavior)
# pickle.dump(g, open('data/'+dbname+'_'+behavior+'.pick', 'w'))
print dbname, behavior
# g = pickle.load(open('data/' + dbname + '_' + behavior + '.pick', 'r'))
return netstatis(dbname, behavior, g, [str(i) for i in userlist], comname)
def behavior_network(dbname, colname, filepath):
'''out retweet and communication network'''
uids = iot.get_values_one_field(dbname, 'com', 'id')
print len(uids)
for beh in ['retweet', 'communication']:
print beh
g = gt.load_beh_network_subset(uids, dbname, colname, beh)
with open(filepath + beh + '.txt', 'wb') as fw:
for e in g.es:
source_vertex_id = e.source
target_vertex_id = e.target
source_vertex = g.vs[source_vertex_id]
target_vertex = g.vs[target_vertex_id]
fw.write('%s\t%s\t%d\n' % ('u' + source_vertex['name'], 'u' +
target_vertex['name'], e['weight']))
def bahavior_net(dbname, comname, bnetname, btype):
userlist = iot.get_values_one_field(dbname, comname, 'id',
{'timeline_count': {'$gt': 0}})
return gt.load_beh_network_subset(userlist, dbname, bnetname, btype)
def bahavior_net(dbname, comname, bnetname, btype):
userlist = iot.get_values_one_field(dbname, comname, 'id',
# {'timeline_count': {'$gt': 0}}
)
return gt.load_beh_network_subset(userlist, dbname, bnetname, btype)
def recover_proed_community_all_connection():
'''
First filter users: pro-recovery and pro-ed, as well as their followings.
Construct interaction networks among these users, including the outlinks from followings to pro-* users
:return:
'''
# Filtering users
# prorec, proed = edrelatedcom.rec_proed() ## based on profiles
# prorec, proed = filter_recovery_sentiment() # based on tweets' sentiments
# users = iot.get_values_one_field('fed', 'recover', 'user.id') # based on tweet content
# prorec = [str(i) for i in users]
# cols = dbt.db_connect_col('fed', 'follownet')
proed, prorec, proboth = pro_tag_user() # based on hashtags
cols = dbt.db_connect_col('fed', 'snet')
name_map, edges, set_map = {}, set(), {}
for row in cols.find({}, no_cursor_timeout=True):
n1 = str(row['follower'])
# if n1 in prorec or n1 in proed:
n2 = str(row['user'])
n1id = name_map.get(n1, len(name_map))
name_map[n1] = n1id
n2id = name_map.get(n2, len(name_map))
name_map[n2] = n2id
edges.add((n1id, n2id))
g = Graph(len(name_map), directed=True)
g.vs["name"] = list(sorted(name_map, key=name_map.get)) # return keys ordered by values
g.add_edges(list(edges))
g.es["weight"] = 1
g.vs["set"] = 0
for v in g.vs:
if v['name'] in prorec:
v['set'] = 1
elif v['name'] in proed:
v['set'] = 2
elif v['name'] in proboth:
v['set'] = 3
gt.summary(g)
# g.vs['deg'] = g.indegree()
# nodes = []
# for v in g.vs:
# if v['set'] == 1 or v['set'] == -1:
# nodes.append(v)
# elif v['deg'] > 3:
# nodes.append(v)
# else:
# pass
# print 'Filtered nodes: %d' %len(nodes)
# g = g.subgraph(nodes)
# gt.summary(g)
g.write_graphml('rec-proed-follow-core-hashtag.graphml')
# sbnet have extended all interactions posted by ED users
edusers = [int(v['name']) for v in g.vs]
# gf = gt.load_network_subset('fed', 'net')
for btype in ['retweet', 'reply', 'mention']:
gb = gt.load_beh_network_subset(edusers, 'fed', 'sbnet', btype)
for v in gb.vs:
v['set'] = g.vs.find(name=v['name'])['set']
gt.summary(gb)
gb.write_graphml('rec-proed-'+btype+'-core-hashtag.graphml')
