def main(args):
'''
Pipeline for representational learning for all nodes in a graph.
'''
# nx_G = read_graph()
nx_G = nt.load_network('fed', 'net')
nx_G = nt.get_gaint_comp(nx_G)
G = node2vec.Graph(nx_G, args.directed, args.p, args.q)
G.preprocess_transition_probs()
walks = G.simulate_walks(args.num_walks, args.walk_length)
learn_embeddings(walks)
def main(args):
'''
Pipeline for representational learning for all nodes in a graph.
'''
# nx_G = read_graph()
nx_G = nt.load_network('fed', 'net')
nx_G = nt.get_gaint_comp(nx_G)
G = node2vec.Graph(nx_G, args.directed, args.p, args.q)
G.preprocess_transition_probs()
walks = G.simulate_walks(args.num_walks, args.walk_length)
learn_embeddings(walks)
def network_stat(dbname, comname, fnetname, bnetname):
db = dbt.db_connect_no_auth(dbname)
com = db[comname]
G = nt.load_network(dbname, fnetname)
# print G.number_of_nodes()
BG = nt.load_behavior_network(dbname, bnetname, 'retweet')
close_cen = nt.closeness_centrality(G) # normalized=True
between_cen = nt.betweenness_centrality(G, weight='weight') # normalized=True, weight=None
eigen_cen = nt.eigenvector_centrality_numpy(G) # weight='weight'
kt_cen = nt.katz_centrality_numpy(G) # normalized=True, weight='weight'
diff_cen = nt.diffusion_centrality(BG, G)
indegree_all = sum(G.in_degree().values())
outdegree_all = sum(G.out_degree().values())
close_cen_all = sum(close_cen.values())
between_cen_all = sum(between_cen.values())
eigen_cen_all = sum(eigen_cen.values())
kt_cen_all = sum(kt_cen.values())
diff_cen_all = sum([diff_cen[item][0] for item in diff_cen])
goss_all = sum([diff_cen[item][1] for item in diff_cen])
for v in G.nodes():
values = com.find_one({'id': v}, ['id', 'net_anal']).get('net_anal', {'mined': True})
net_sta = {}
net_sta['node_no'] = G.number_of_nodes()
net_sta['indegree'] = G.in_degree(v)
net_sta['indegree_all'] = indegree_all
net_sta['outdegree'] = G.out_degree(v)
net_sta['outdegree_all'] = outdegree_all
net_sta['closeness_centrality'] = close_cen[v]
net_sta['closeness_centrality_all'] = close_cen_all
net_sta['betweenness_centrality'] = between_cen[v]
net_sta['betweenness_centrality_all'] = between_cen_all
net_sta['eigenvector_centrality'] = eigen_cen[v]
net_sta['eigenvector_centrality_all'] = eigen_cen_all
net_sta['katz_centrality'] = kt_cen[v]
net_sta['katz_centrality_all'] = kt_cen_all
net_sta['diffusion_centrality'] = diff_cen.get(v, [0.0, 0.0])[0]
net_sta['diffusion_centrality_all'] = diff_cen_all
net_sta['gossip'] = diff_cen.get(v, [0.0, 0.0])[1]
net_sta['gossip_all'] = goss_all
values['friendship_net'] = net_sta
com.update_one({'id': v}, {'$set': {'net_anal': values}}, upsert=True)