def load_synthetic(mu, n=1000, tau1=3, tau2=1.5, edge_drop_percent=0.2):
G = LFR_benchmark_graph(n,
tau1,
tau2,
mu,
average_degree=5,
min_community=30,
seed=10)
for n in G.nodes:
G.nodes[n]['value'] = list(G.nodes[n]['community'])[0]
true_coms = list(nx.get_node_attributes(G, 'value').values())
com_keys = list(Counter(true_coms).keys())
for i in range(0, len(true_coms)):
G.nodes[i]['value'] = com_keys.index(true_coms[i])
#remove self edges
selfE = list(G.selfloop_edges())
for (i, j) in selfE:
G.remove_edge(i, j)
#convert all graph to undirected
G = nx.Graph(G)
ListOfEdges = [e for e in G.edges]
sample = int(len(ListOfEdges) * edge_drop_percent)
RandomSample = random.sample(ListOfEdges, sample)
G.remove_edges_from(RandomSample)
return (G, RandomSample)
def get_lfr_network_data(n, tau1, tau2, mu):
graph = LFR_benchmark_graph(n,
tau1,
tau2,
mu,
average_degree=5,
min_community=30,
seed=10)
all_edges = list(graph.edges)
idx = np.arange(len(all_edges))
np.random.shuffle(idx)
test_idx = idx[:int(0.2 * len(graph.edges))]
pos_test_links = [all_edges[i] for i in test_idx]
n_test = len(test_idx)
neg_test_links = sample_neg(graph, num_neg_links=n_test)
graph.remove_edges_from(pos_test_links)
return graph, pos_test_links, neg_test_links
def LFR(n, tau1, tau2, mu):
#n = 1000 #(int)number of nodes
#tau1 = 3 #(float) Power law exponent for the degree distribution of the created graph. This value must be strictly greater than one.
#tau2 = 1.1 #(float) Power law exponent for the community size distribution in the created graph. This value must be strictly greater than one.
#mu = 0.1 #(float) Fraction of intra-community edges incident to each node. This value must be in the interval [0, 1].
#greater mu => pio asafeis koinothtes!
#average_degree and min_degree must be in [0, n]. One of these must be specified.
#max_degree if not specified is set to n.
#min_community if not specified is set to min_degree.
#max_community if not specified is set to n.
#tol(float) Tolerance when comparing floats, specifically when comparing average degree values.
#max_iters (int) Maximum number of iterations to try to create the community sizes, degree distribution, and community affiliations.
#seed (integer, random_state, or None (default)) Indicator of random number generation state.
os.chdir('experiments/datasets/lfr')
G = LFR_benchmark_graph(n,
tau1,
tau2,
mu,
average_degree=10,
max_degree=50,
min_community=10,
max_community=50)
#remove self loops
G.remove_edges_from(G.selfloop_edges())
numberOfEdges = G.number_of_edges()
print("Number of edges of graph G: ", numberOfEdges)
print("------------------------------")
#na mh sxediazontai oi aksones
#plt.axis('off')
#sxediasmos grafou
#nx.draw(G)
communities = {frozenset(G.nodes[v]['community']) for v in G}
adjacency_list_filename = 'lfrAdjlistN' + str(n) + 'MU' + str(mu) + '*.txt'
edge_list_filename = 'lfrEdgelistN' + str(n) + 'MU' + str(mu) + '*.txt'
community_list_filename = 'lfrCommN' + str(n) + 'MU' + str(mu) + '*.txt'
#print('Communities: ', communities)
with open('lfrCommN' + str(n) + 'MU' + str(mu) + '*.txt', 'w') as fc:
fc.write(str([list(x) for x in communities]))
nx.write_adjlist(G, adjacency_list_filename)
fh = open(adjacency_list_filename, 'wb')
nx.write_adjlist(G, fh)
edge_list = []
with open(adjacency_list_filename, 'r') as f:
for line in f:
if line.startswith("#"): #skip first comment lines
continue
else:
line = line.rstrip('\n').split(' ')
source = line[0]
for target in line[1:]:
#edge_list.append("%s %s 1" % (source, target)) #1 is for the weight
edge_list.append("%s %s" % (source, target))
with open(edge_list_filename, 'w') as f:
f.write('%s\n' % ('\n'.join(edge_list)))
with open(community_list_filename, 'w') as f:
for item in communities:
f.write("%s\n" % str(list(item)))
#remove unecessary symbols like []
with open(community_list_filename, 'r') as my_file:
text = my_file.read()
text = text.replace("[", "")
text = text.replace("]", "")
text = text.replace(",", "")
with open(community_list_filename, 'w') as my_file:
my_file.write(text)
#convert edge txt file to csv file appending also weight 1 to all edges
with open('lfrEdgelistN' + str(n) + 'MU' + str(mu) + '*.txt') as data_file:
reader = csv.reader(data_file, delimiter=' ')
with open('lfrEdgelistN' + str(n) + 'MU' + str(mu) + '*.csv',
'w') as out_file:
writer = csv.writer(out_file, delimiter=';')
for row in reader:
writer.writerow([row[0], row[1], 1])
return 'lfrEdgelistN' + str(n) + 'MU' + str(mu) + '*.csv'
