def run_pvalue():
num_graphs = graphs.shape[0]
pvalues = np.zeros((num_graphs, num_graphs))
for i in range(num_graphs):
for j in range(i + 1, num_graphs):
print('{}, {}'.format(i, j))
G1 = graphs[i, ...]
G2 = graphs[j, ...]
if args.test == 1:
if args.Z == 1:
Z = Ztrue
elif args.Z == 2:
Z = Zhat[(i, j)]
elif args.Z == 3:
Z = community_estimation(G1,
G2,
min_components=max_comm,
max_components=max_comm)
pvalues[i,
j] = block_permutation_pvalue(G1,
G2,
test='gcorr',
num_perm=args.num_iter,
Z=Z)
elif args.test == 2:
Z = None
if args.Z == 3:
min_comm = max_comm
elif args.Z == 2:
min_comm = 1
elif args.Z == 1:
min_comm = 1 # is NOT used
Z = Ztrue
pvalues[i,
j] = dcsbm_pvalue(G1,
G2,
min_comm=min_comm,
max_comm=max_comm,
epsilon1=epsilon1,
epsilon2=epsilon2,
pooled_variance=args.pooled_variance,
num_perm=args.num_iter,
Z1=Z,
Z2=Z)
elif args.test == 3:
pvalues[i, j] = pearson_exact_pvalue(G1, G2)
return pvalues
# each row stores the optimal community assignment for a pair of graphs
# easier for iterating over
Zhat = np.zeros((num_tests, num_vertices))
# key: (i, j), value: optimal assignment for graph i and j
# easier for access
Zhat_dict = {}
count = 0
for i in range(num_graphs):
for j in range(i, num_graphs):
print('{}, {}'.format(i, j))
G1 = graphs[i, ...]
if i == j:
assignment = community_estimation(G1,
min_components=2,
max_components=max_comp)
else:
G2 = graphs[j, ...]
assignment = community_estimation(G1,
G2,
min_components=2,
max_components=max_comp)
Zhat[count, :] = assignment
count += 1
Zhat_dict[(i, j)] = assignment
with open('outputs/{}_Zhat_{}.pkl'.format(args.data, args.transformation),
'wb') as f:
pickle.dump(Zhat, f)
with open('outputs/{}_Zhat_dict_{}.pkl'.format(args.data, args.transformation),
n = num_vertices[i]
Z = np.repeat([0], n)
if sim == 'bern':
if 'sbm' in setting:
G1, G2 = sbm_corr_diffmarg(n, p, q, r)
else:
G1, G2 = er_corr_diffmarg(n, p, q, r)
elif sim == 'gauss':
if 'sbm' in setting:
G1, G2 = sbm_corr_weighted(n, mu1, mu2, Sigma)
else:
G1, G2 = er_corr_weighted(n, mu1, mu2, Sigma)
if setting == 'sbm_estblock':
Z = community_estimation(G1, G2, min_components=5)
G2_vertex_perm = vertex_permutation(G2)
G2_block_perm = block_permutation(G2, Z)
test_stats_null['pearson_vertex_perm'][i, rep] = pearson_graph(G1, G2_vertex_perm)
test_stats_alt['pearson_vertex_perm'][i, rep] = pearson_graph(G1, G2)
test_stats_null['pearson_block_perm'][i, rep] = pearson_graph(G1, G2_block_perm)
test_stats_alt['pearson_block_perm'][i, rep] = pearson_graph(G1, G2)
test_stats_null['gcorr_vertex_perm'][i, rep] = gcorr(G1, G2_vertex_perm, Z)
test_stats_alt['gcorr_vertex_perm'][i, rep] = gcorr(G1, G2, Z)
test_stats_null['gcorr_block_perm'][i, rep] = gcorr(G1, G2_block_perm, Z)
test_stats_alt['gcorr_block_perm'][i, rep] = gcorr(G1, G2, Z)
pearson_exact_pvals[i, rep] = pearson_exact_pvalue(G1, G2)
# compute power
result = {
'true': corr,
'gcorr_pooled': np.zeros((num_corr, num_rep)),
'gcorr_unpooled': np.zeros((num_corr, num_rep)),
'gcorr_dcsbm_pooled': np.zeros((num_corr, num_rep)),
'gcorr_dcsbm_unpooled': np.zeros((num_corr, num_rep))
}
for i, r in enumerate(corr):
print('iteration {} in {}: r = {}'.format(i + 1, num_corr, r))
for j in tqdm(range(num_rep)):
g1, g2 = dcsbm_corr(n, p, r, theta)
if args.sim == 'estblock':
# note `community_estimation` uses MASE
# whereas `graspologic.DCSBM` uses LSE
zest = community_estimation(g1, g2, maxcomm)
result['gcorr_pooled'][i, j] = gcorr(g1,
g2,
zest,
pooled_variance=True)
result['gcorr_unpooled'][i, j] = gcorr(g1,
g2,
zest,
pooled_variance=False)
result['gcorr_dcsbm_pooled'][i,
j] = gcorr_dcsbm(g1,
g2,
maxcomm,
pooled_variance=True,
Z=None)
result['gcorr_dcsbm_unpooled'][i, j] = gcorr_dcsbm(
def run_test_stats():
num_graphs = graphs.shape[0]
test_stats = np.zeros((num_graphs, num_graphs))
if args.return_fit:
dcsbm_fit = {}
for i in range(num_graphs):
for j in range(i + 1, num_graphs):
print('{}, {}'.format(i, j))
G1 = graphs[i, ...]
G2 = graphs[j, ...]
if args.test == 1:
if args.Z == 1:
Z = Ztrue
elif args.Z == 2:
Z = Zhat[(i, j)]
elif args.Z == 3:
Z = community_estimation(G1,
G2,
min_components=max_comm,
max_components=max_comm)
test_stats[i, j] = gcorr(G1,
G2,
Z,
pooled_variance=args.pooled_variance)
elif args.test == 2:
Z = None
if args.Z == 3:
min_comm = max_comm
elif args.Z == 2:
min_comm = 1
elif args.Z == 1:
min_comm = 1 # is NOT used
Z = Ztrue
if args.return_fit:
ts, fit = gcorr_dcsbm(G1,
G2,
min_comm=min_comm,
max_comm=max_comm,
epsilon1=epsilon1,
epsilon2=epsilon2,
pooled_variance=args.pooled_variance,
Z1=Z,
Z2=Z,
return_fit=True,
seed=seed)
test_stats[i, j] = ts
dcsbm_fit[(i, j)] = fit
else:
ts = gcorr_dcsbm(G1,
G2,
min_comm=min_comm,
max_comm=max_comm,
epsilon1=epsilon1,
epsilon2=epsilon2,
pooled_variance=args.pooled_variance,
Z1=Z,
Z2=Z,
seed=seed)
test_stats[i, j] = ts
elif args.test == 3:
test_stats[i, j] = pearson_graph(G1, G2)
if args.return_fit:
return test_stats, dcsbm_fit
else:
return test_stats