def tags_two_user_moduls():
#load network from gephi output
g = gt.Graph.Read_GraphML('communication-3-moduls.graphml')
cluster0, cluster1, cluster2 = set(), set(), set()
for v in g.vs:
if v['Modularity Class'] == 0:
cluster0.add(int(v['name']))
elif v['Modularity Class'] == 1:
cluster1.add(int(v['name']))
elif v['Modularity Class'] == 2:
cluster2.add(int(v['name']))
g = gt.load_hashtag_coocurrent_network_undir('fed', 'ed_tag',
list(cluster0))
gt.summary(g)
filename = 'communication_fed_cluster0'
g.write_graphml(filename + '_tag_undir.graphml')
g = gt.load_hashtag_coocurrent_network_undir('fed', 'ed_tag',
list(cluster1))
gt.summary(g)
filename = 'communication__fed_cluster1'
g.write_graphml(filename + '_tag_undir.graphml')
g = gt.load_hashtag_coocurrent_network_undir('fed', 'ed_tag',
list(cluster2))
gt.summary(g)
filename = 'communication_fed_cluster2'
g.write_graphml(filename + '_tag_undir.graphml')
def cluster_hashtag(filepath= 'user-durations-iv-following-senti.csv'):
# read hashtag networks for dropouts and non-dropouts
df = pd.read_csv(filepath)
df['f_ratio'] = df.f_num/df.u_friends_count
datat = df[df['f_ratio']>0.01]
data = datat[datat['group']=='ED']
uids_nondropout = [int(uid) for uid in data[(data['dropout']==0)]['uid']]
uids_dropout = [int(uid) for uid in data[(data['dropout']==1)]['uid']]
print len(uids_nondropout), len(uids_dropout)
net_nondropout = gt.load_hashtag_coocurrent_network_undir('fed', 'timeline', uids_nondropout)
net_dropout = gt.load_hashtag_coocurrent_network_undir('fed', 'timeline', uids_dropout)
net_nondropout.write_graphml('nondropout-tag.graphml')
net_dropout.write_graphml('dropout-tag.graphml')
def compare_dropouts_withemotions(filepath= 'user-durations-iv-following-senti-TE.csv'):
# out hashtags network for users with different emotions
df = pd.read_csv(filepath)
df['f_ratio'] = df.f_num/df.u_friends_count
data = df[df['f_ratio']>0.01]
datasub = data[data['group'].isin(['ED', 'YG'])]
mean_edu_prior = np.mean(datasub[datasub.group=='ED']['u_prior_scalem'])
mean_edf_prior = np.mean(datasub[datasub.group=='ED']['f_prior_scalem'])
mean_ygu_prior = np.mean(datasub[datasub.group=='YG']['u_prior_scalem'])
mean_ygf_prior = np.mean(datasub[datasub.group=='YG']['f_prior_scalem'])
datasub['u_prior_scalem'] = np.where((datasub.u_prior_scalem==0.0) & (datasub.group=='ED'), mean_edu_prior, datasub['u_prior_scalem'])
datasub['f_prior_scalem'] = np.where((datasub.f_prior_scalem==0.0) & (datasub.group=='ED'), mean_edf_prior, datasub['f_prior_scalem'])
datasub['u_prior_scalem'] = np.where((datasub.u_prior_scalem==0.0) & (datasub.group=='YG'), mean_ygu_prior, datasub['u_prior_scalem'])
datasub['f_prior_scalem'] = np.where((datasub.f_prior_scalem==0.0) & (datasub.group=='YG'), mean_ygf_prior, datasub['f_prior_scalem'])
datasub['u_changes'] = (datasub.u_post_scalem - datasub.u_prior_scalem)/(datasub.u_prior_scalem)
datasub['f_changes'] = (datasub.f_post_scalem - datasub.f_prior_scalem)/(datasub.f_prior_scalem)
dropouts = datasub[(datasub.group=='ED') & (datasub.dropout==0)][['u_whole_scalem', 'u_changes', 'uid', 'u_eigenvector']]
print len(dropouts)
dropouts = dropouts.sort('u_eigenvector', ascending='True') ## small to large
print dropouts
for i in xrange(2):
start, end = i*len(dropouts)/2, (i+1)*len(dropouts)/2
print start, end
uidlist = []
for uid in dropouts['uid'][start: end]:
uidlist.append(int(uid))
net_dropout = gt.load_hashtag_coocurrent_network_undir('fed', 'timeline', uidlist)
net_dropout.write_graphml(str(i) + 'dropout-tag-centrality2-rank.graphml')
uidlist = [int(uid) for uid in dropouts['uid']]
net_dropout = gt.load_hashtag_coocurrent_network_undir('fed', 'timeline', uidlist)
net_dropout.write_graphml('dropout-tag-centrality2-rank-all.graphml')
def tags_user_cluster(graph_file_path, filename):
# put tweet of two cluster into two set
g = gt.Graph.Read_GraphML(graph_file_path)
# g_mention = gt.Graph.Read_GraphML('ed-communication'+'-hashtag-only-fed-cluster.graphml')
gt.summary(g)
# gt.summary(g_mention)
# for i in range(2):
# g = [g_retweet, g_mention][i]
cluster0, cluster1, cluster2 = set(), set(), set()
for v in g.vs:
if v['cluster'] == 0:
cluster0.add(int(v['name']))
elif v['cluster'] == 1:
cluster1.add(int(v['name']))
elif v['cluster'] == -1:
cluster2.add(int(v['name']))
print 'cluster size;', len(cluster0)
g = gt.load_hashtag_coocurrent_network_undir('fed', 'ed_tag',
list(cluster0))
gt.summary(g)
# filename = ['ed_retweet', 'ed_communication'][i] + '_fed_cluster0'
vs = g.vs(weight_gt=3, user_gt=3)
g = g.subgraph(vs)
gt.summary(g)
g.write_graphml(filename + 'tag_undir_cluster0.graphml')
print 'cluster size;', len(cluster1)
g = gt.load_hashtag_coocurrent_network_undir('fed', 'ed_tag',
list(cluster1))
gt.summary(g)
# filename = ['ed_retweet', 'ed_communication'][i] + '_fed_cluster1'
vs = g.vs(weight_gt=3, user_gt=3)
g = g.subgraph(vs)
gt.summary(g)
g.write_graphml(filename + 'tag_undir_cluster1.graphml')
def tag_record(dbname, colname, filename):
g = gt.load_hashtag_coocurrent_network_undir(dbname, colname)
gt.summary(g)
g.write_graphml(filename + '_tag_undir.graphml')
return g
# g.write_graphml('alled_tag.graphml')
# gt.summary(g)
# # g = gt.Graph.Read_GraphML('core_ed_tag_undir.graphml')
# nodes = g.vs.select(weight_gt=3)
# print 'Filtered nodes: %d' %len(nodes)
# g = g.subgraph(nodes)
# nodes = g.vs.select(user_gt=3)
# print 'Filtered nodes: %d' %len(nodes)
# g = g.subgraph(nodes)
# # g = pmi(g)
# g.write_graphml('alled_tag_filter.graphml')
'''undirected network'''
# users_net = gt.Graph.Read_GraphML('communication-only-fed-filter.graphml')
# users = [int(uid) for uid in users_net.vs['name']]
print 'Read fed timeline excluding all retweets'
g = gt.load_hashtag_coocurrent_network_undir('fed', 'timeline')
g.write_graphml('fed_tag_undir_nort.graphml')
# # g = gt.Graph.Read_GraphML('core_ed_tag_undir.graphml')
# gt.summary(g)
# nodes = g.vs.select(weight_gt=3)
# print 'Filtered nodes: %d' %len(nodes)
# g = g.subgraph(nodes)
# nodes = g.vs.select(user_gt=3)
# print 'Filtered nodes: %d' %len(nodes)
# g = g.subgraph(nodes)
# g.write_graphml('ed_tag_undir_filter.graphml')
#-----------------------Filter network-----------------------------------------------
#-----------------------Community detection-----------------------------------------------
# g = gt.Graph.Read_GraphML('core_ed_hashtag_filter.graphml')
def tag_net(dbname, colname, filename):
# All tags excluding retweets
g = gt.load_hashtag_coocurrent_network_undir(dbname, colname)
gt.summary(g)
g.write_graphml(filename + '_tag_undir.graphml')
def hashtag_net(dbname, colname):
# built hashtag_net
g = gt.load_hashtag_coocurrent_network_undir(dbname, colname)
g.write_graphml('tag.graphml')
