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)
ListOfNodes = list(G.nodes())
sample = int(len(ListOfNodes) * node_drop_percent)
RandomSample = random.sample(ListOfNodes, sample)
for n in G.nodes():
if (n not in RandomSample):
G.nodes[n][label_name] = G.nodes[n]['value']
return (G, RandomSample)
def test_generator():
n = 250
tau1 = 3
tau2 = 1.5
mu = 0.1
G = LFR_benchmark_graph(n, tau1, tau2, mu, average_degree=5,
min_community=20, seed=10)
assert_equal(len(G), 250)
C = {frozenset(G.nodes[v]['community']) for v in G}
assert_true(is_partition(G.nodes(), C))
def test_generator():
n = 250
tau1 = 3
tau2 = 1.5
mu = 0.1
G = LFR_benchmark_graph(n, tau1, tau2, mu, average_degree=5,
min_community=20, seed=10)
assert_equal(len(G), 250)
C = {frozenset(G.node[v]['community']) for v in G}
assert_true(is_partition(G.nodes(), C))
# SLURM_PROCID starts from 0 to 50.
SLURM_PROCID = int(argv[1])
rho = rhos[SLURM_PROCID]
num_seeds = int(rho * num_nodes)
for u in us:
for i in range(num_runs):
G = LFR_benchmark_graph(num_nodes,
tau1,
tau2,
u,
average_degree=avg_degree,
max_degree=max_degree,
seed=10)
seeds = random.sample(G.nodes(), num_seeds)
activation_time, step = simulation_ltm(G, thsh, seeds, frac=f)
activation_per_step = [0] * step
for node in activation_time:
atime = activation_time[node]
activation_per_step[atime] += 1
sweeping_results[u].append(
(len(activation_time), step, activation_per_step))
Data_Root = '/auto/rcf-proj/ef/hp_273/Diffusion/LFR/per_step_data/'
with open(
Data_Root + 'phase_simu_nodes_%sk_z_%s_thsh_%s_f_%s_%s.pickle' %
(num_nodes // 1000, avg_degree, thsh, f, SLURM_PROCID), 'wb') as file:
pickle.dump(dict(sweeping_results), file)
for mu in mu_list:
print('\nNode Prediction when mu is', mu, r'and 20% of nodes are dropped')
G = LFR_benchmark_graph(n, tau1, tau2, mu, average_degree, min_community=minimum_community)
#print('First Node:',G.nodes[0])
communities = {frozenset(G.nodes[v]['community']) for v in G}
#print('Communities:\n', communities)
#print('Number of Ground Turth Communities:', len(communities))
labels_truth = get_labels_from_community(communities, n)
#print('Ground Truth Labels:\n', labels_truth)
G = apply_community_value_to_graph(G, labels_truth)
#print('First Node Modified:',G.nodes[0])
for node in random.sample(G.nodes(), int(n*drop_factor)):
del G.node[node]['value']
nmi, ars = calculate_node_classification_accuracy(G, 'value', labels_truth, method)
nmi_list.append(nmi)
ars_list.append(ars)
print_scatter_plot([mu_list, nmi_list, ars_list], 'Mu', 'Average NMI', 'Average ARS', 'LFR Benchmark Graph Node Classification')
with open(name+'-'+method+'.csv', mode='w') as file:
file_writer = csv.writer(file, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
file_writer.writerow(['Mu', 'NMI Score', 'ARS Score'])
for i in range(len(mu_list)):
