def network(dbname, colname, netname):
'''Get users' friendship network'''
# # ed_usersd = ed_user(dbname, colname)
# # pickle.dump(ed_usersd, open('data/ed_users.pick', 'w'))
# ed_usersd = pickle.load(open('data/ed_users.pick', 'r'))
#
# # rec_usersd = rec_user(dbname, colname)
# # pickle.dump(rec_usersd, open('data/rec_users.pick', 'w'))
# rec_usersd = pickle.load(open('data/rec_users.pick', 'r'))
#
#
# inlist = list(set(ed_usersd).union(set(rec_usersd)))
#
# print len(inlist)
# g = gt.load_network_subset(inlist, dbname, netname)
# g.vs['rec'] = 0
# for uid in rec_usersd:
# exist = True
# try:
# v = g.vs.find(name=str(uid))
# except ValueError:
# exist = False
# if exist:
# v['rec'] = 1
# pickle.dump(g, open('data/rec_friendship.pick', 'w'))
rg = pickle.load(open('data/rec_friendship.pick', 'r'))
# g.write_gml('data/rec_friendship.GML')
# g.write_dot('data/rec_friendship.DOT')
gc = gt.giant_component(rg, 'WEAK')
comm = gt.fast_community(gc, False)
fclus = comm.as_clustering(2)
communit_topinflu(fclus, None)
def network(dbname, colname, netname):
'''Get users' friendship network'''
# # ed_usersd = ed_user(dbname, colname)
# # pickle.dump(ed_usersd, open('data/ed_users.pick', 'w'))
# ed_usersd = pickle.load(open('data/ed_users.pick', 'r'))
#
# # rec_usersd = rec_user(dbname, colname)
# # pickle.dump(rec_usersd, open('data/rec_users.pick', 'w'))
# rec_usersd = pickle.load(open('data/rec_users.pick', 'r'))
#
#
# inlist = list(set(ed_usersd).union(set(rec_usersd)))
#
# print len(inlist)
# g = gt.load_network_subset(inlist, dbname, netname)
# g.vs['rec'] = 0
# for uid in rec_usersd:
# exist = True
# try:
# v = g.vs.find(name=str(uid))
# except ValueError:
# exist = False
# if exist:
# v['rec'] = 1
# pickle.dump(g, open('data/rec_friendship.pick', 'w'))
rg = pickle.load(open('data/rec_friendship.pick', 'r'))
# g.write_gml('data/rec_friendship.GML')
# g.write_dot('data/rec_friendship.DOT')
gc = gt.giant_component(rg, 'WEAK')
comm = gt.fast_community(gc, False)
fclus = comm.as_clustering(2)
communit_topinflu(fclus, None)
def communtiy_feature(dbname, typename):
fg = ntt.loadnet(dbname, typename)
fcoms = gt.fast_community(fg)
pickle.dump(fcoms, open('data/'+dbname+typename+'com.pick', 'w'))
fcoms = pickle.load(open('data/'+dbname+typename+'com.pick', 'r'))
fclus = fcoms.as_clustering()
gt.summary(fclus)
"""Compare difference of features in cummunities"""
features = [
'liwc_anal.result.i',
'liwc_anal.result.we',
'liwc_anal.result.bio',
'liwc_anal.result.body',
'liwc_anal.result.health',
'liwc_anal.result.posemo',
'liwc_anal.result.negemo',
'liwc_anal.result.ingest',
'liwc_anal.result.anx',
'liwc_anal.result.anger',
'liwc_anal.result.sad'
]
therh = 0.1 * fg.vcount()
for feature in features:
data = []
for clu in fclus:
if len(clu) > therh:
ulist = set()
for v in clu:
ulist.add(int(fg.vs[v]['name']))
ulist = list(ulist)
clu_values = iot.get_values_one_field(dbname, 'com', feature, {'id': {'$in': ulist}})
data.append(clu_values)
plot.plot_config()
for i in xrange(len(data)):
sns.distplot(data[i], hist=False, label=str(i)+':'+str(len(data[i])))
plt.xlabel(feature)
plt.ylabel('PDF')
# plt.show()
plt.savefig(feature+typename+'_com.pdf')
plt.clf()
def communtiy_feature(dbname, typename):
fg = ntt.loadnet(dbname, typename)
fcoms = gt.fast_community(fg)
pickle.dump(fcoms, open('data/' + dbname + typename + 'com.pick', 'w'))
fcoms = pickle.load(open('data/' + dbname + typename + 'com.pick', 'r'))
fclus = fcoms.as_clustering()
gt.summary(fclus)
"""Compare difference of features in cummunities"""
features = [
'liwc_anal.result.i', 'liwc_anal.result.we', 'liwc_anal.result.bio',
'liwc_anal.result.body', 'liwc_anal.result.health',
'liwc_anal.result.posemo', 'liwc_anal.result.negemo',
'liwc_anal.result.ingest', 'liwc_anal.result.anx',
'liwc_anal.result.anger', 'liwc_anal.result.sad'
]
therh = 0.1 * fg.vcount()
for feature in features:
data = []
for clu in fclus:
if len(clu) > therh:
ulist = set()
for v in clu:
ulist.add(int(fg.vs[v]['name']))
ulist = list(ulist)
clu_values = iot.get_values_one_field(dbname, 'com', feature,
{'id': {
'$in': ulist
}})
data.append(clu_values)
plot.plot_config()
for i in xrange(len(data)):
sns.distplot(data[i],
hist=False,
label=str(i) + ':' + str(len(data[i])))
plt.xlabel(feature)
plt.ylabel('PDF')
# plt.show()
plt.savefig(feature + typename + '_com.pdf')
plt.clf()
def benetwork(dbname, type, netname):
'''Get users' behavior networks'''
# ed_usersd = pickle.load(open('data/ed_users.pick', 'r'))
# rec_usersd = pickle.load(open('data/rec_users.pick', 'r'))
# inlist = list(set(ed_usersd).union(set(rec_usersd)))
# g = gt.load_beh_network_subset(inlist, dbname, netname, type)
# g.vs['rec'] = 0
# for uid in rec_usersd:
# exist = True
# try:
# v = g.vs.find(name=str(uid))
# except ValueError
# exist = False
# if exist:
# v['rec'] = 1
# pickle.dump(g, open('data/rec_'+type+'.pick', 'w'))
rg = pickle.load(open('data/rec_'+type+'.pick', 'r'))
# plot_graph(g)
gc = gt.giant_component(rg, 'WEAK')
comm = gt.fast_community(gc, True)
fclus = comm.as_clustering(2)
communit_topinflu(fclus, 'weight')
def benetwork(dbname, type, netname):
'''Get users' behavior networks'''
# ed_usersd = pickle.load(open('data/ed_users.pick', 'r'))
# rec_usersd = pickle.load(open('data/rec_users.pick', 'r'))
# inlist = list(set(ed_usersd).union(set(rec_usersd)))
# g = gt.load_beh_network_subset(inlist, dbname, netname, type)
# g.vs['rec'] = 0
# for uid in rec_usersd:
# exist = True
# try:
# v = g.vs.find(name=str(uid))
# except ValueError:
# exist = False
# if exist:
# v['rec'] = 1
# pickle.dump(g, open('data/rec_'+type+'.pick', 'w'))
rg = pickle.load(open('data/rec_'+type+'.pick', 'r'))
# plot_graph(g)
gc = gt.giant_component(rg, 'WEAK')
comm = gt.fast_community(gc, True)
fclus = comm.as_clustering(2)
communit_topinflu(fclus, 'weight')