def dcsbm_pvalue(G1,
G2,
max_comm,
num_perm,
pooled_variance=True,
min_comm=1,
epsilon1=1e-3,
epsilon2=1e-3,
Z1=None,
Z2=None):
"""
Estimate p-value via parametric bootstrap, i.e. fit a DC-SBM
"""
# if we are fixing the number of communities, we should also fix the number of latent dimensions of the embedding
# otherwise (when we let the algorithm to automatically choose the number of communities)
# we also let it choose the number of latent dimensions
if min_comm == max_comm:
K = min_comm
else:
K = None
obs_test_stat = gcorr_dcsbm(G1,
G2,
min_comm=min_comm,
max_comm=max_comm,
pooled_variance=pooled_variance,
epsilon1=epsilon1,
epsilon2=epsilon2)
G1_dcsbm = DCSBMEstimator(directed=False,
min_comm=min_comm,
max_comm=max_comm,
n_components=K).fit(G1, y=Z1)
G2_dcsbm = DCSBMEstimator(directed=False,
min_comm=min_comm,
max_comm=max_comm,
n_components=K).fit(G2, y=Z2)
# create bootstrap samples
G1_bootstrap = G1_dcsbm.sample(n_samples=num_perm)
G2_bootstrap = G2_dcsbm.sample(n_samples=num_perm)
null_test_stats = np.zeros(num_perm)
for i in tqdm(range(num_perm)):
null_test_stats[i] = gcorr_dcsbm(G1_bootstrap[i],
G2_bootstrap[i],
min_comm=min_comm,
max_comm=max_comm,
pooled_variance=pooled_variance,
epsilon1=epsilon1,
epsilon2=epsilon2)
num_extreme = np.where(null_test_stats >= obs_test_stat)[0].size
if num_extreme < num_perm / 2:
# P(T > t | H0) is smaller
return (2 * num_extreme + 1) / (num_perm + 1)
else:
# P(T < t | H0) is smaller
return (2 * (num_perm - num_extreme) + 1) / (num_perm + 1)
def test_DCSBM_sample(self):
np.random.seed(8888)
estimator = DCSBMEstimator(directed=True, loops=False)
B = np.array([[0.9, 0.1], [0.1, 0.9]])
dc = np.random.uniform(0.25, 0.75, size=100)
labels = _n_to_labels([50, 50])
p_mat = _block_to_full(B, labels, (100, 100))
p_mat = p_mat * np.outer(dc, dc)
p_mat -= np.diag(np.diag(p_mat))
g = sample_edges(p_mat, directed=True)
with pytest.raises(NotFittedError):
estimator.sample()
estimator.fit(g, y=labels)
with pytest.raises(ValueError):
estimator.sample(n_samples=-1)
with pytest.raises(TypeError):
estimator.sample(n_samples="nope")
estimator.p_mat_ = p_mat
_test_sample(estimator, p_mat, n_samples=1000, atol=0.1)
G1, G2 = sbm_corr(n, p, args.rho)
elif args.sim == 'dcsbm':
theta = np.linspace(100, 1, n[0])
theta /= theta.sum()
theta = np.concatenate([theta, theta])
G1, G2 = dcsbm_corr(n, p, args.rho, theta)
# null by block permutation
Z = community_estimation(G1, G2, min_components=max_comm)
# Z = np.repeat([0, 1], n)
G2_block_perm = block_permutation(G2, Z)
# null by parametric bootstrap
G1_dcsbm = DCSBMEstimator(directed=False).fit(G1)
G2_dcsbm = DCSBMEstimator(directed=False).fit(G2)
G1_bootstrap = G1_dcsbm.sample()[0]
G2_bootstrap = G2_dcsbm.sample()[0]
test_stats_alt['gcorr_block_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_param_bootstrap'][i, rep] = gcorr(G1, G2, Z)
test_stats_null['gcorr_param_bootstrap'][i, rep] = gcorr(G1_bootstrap, G2_bootstrap, Z)
test_stats_alt['gcorrDC_param_bootstrap'][i, rep] = gcorr_dcsbm(G1, G2, max_comm)
test_stats_null['gcorrDC_param_bootstrap'][i, rep] = gcorr_dcsbm(G1_bootstrap, G2_bootstrap, max_comm)
test_stats_alt['gcorrDC_block_perm'][i, rep] = gcorr_dcsbm(G1, G2, max_comm)
test_stats_null['gcorrDC_block_perm'][i, rep] = gcorr_dcsbm(G1, G2_block_perm, max_comm)
# compute power
for i in range(num_vertices.size):
for t in tests: