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)
adj,
meta=meta,
sort_class=["hemisphere", "lvl0_labels"],
colors="merge_class",
palette=CLASS_COLOR_DICT,
class_order=["signal_flow"],
item_order=["te"],
plot_type="scattermap",
sizes=(0.5, 0.5),
ax=ax,
ticks=False,
)
estimator = DCSBMEstimator(degree_directed=True, directed=True, loops=False)
estimator.fit(adj, meta["lvl0_labels"].values)
sample = np.squeeze(estimator.sample())
ax = axs[0]
adjplot(
sample,
meta=meta,
sort_class=["hemisphere", "lvl0_labels"],
colors="merge_class",
palette=CLASS_COLOR_DICT,
class_order=["signal_flow"],
item_order=["te"],
plot_type="scattermap",
sizes=(0.5, 0.5),
ax=ax,
ticks=False,
)
pairplot(embed, labels=pred_labels, palette=cc.glasbey_light)
# %% [markdown]
# ##
sbm = DCSBMEstimator(directed=True,
degree_directed=True,
loops=False,
max_comm=30)
sbm.fit(binarize(adj))
pred_labels = sbm.vertex_assignments_
print(len(np.unique(pred_labels)))
meta["pred_labels"] = pred_labels
graph = np.squeeze(sbm.sample())
meta["adj_sf"] = -signal_flow(binarize(adj))
block_sf = -signal_flow(sbm.block_p_)
block_map = pd.Series(data=block_sf)
meta["block_sf"] = meta["pred_labels"].map(block_map)
#%%
graph_type = "G"
fig, axs = plt.subplots(1, 2, figsize=(20, 10))
ax = axs[0]
ax, _, tax, _ = matrixplot(
binarize(adj),
ax=ax,
plot_type="scattermap",
)
side_label_kws = dict(labelpad=45, fontsize=24)
fig, ax = plt.subplots(3, 2, figsize=(10, 17))
# SBM
heatmap(sbm.p_mat_, ax=ax[0, 0], title="Probability matrix", **heatmap_kws)
heatmap(np.squeeze(sbm.sample()),
ax=ax[0, 1],
title="Random sample",
**heatmap_kws)
ax[0, 0].set_ylabel("SBM", **side_label_kws)
# DCSBM
heatmap(dcsbm.p_mat_, ax=ax[1, 0], **heatmap_kws)
heatmap(np.squeeze(dcsbm.sample()), ax=ax[1, 1], **heatmap_kws)
ax[1, 0].set_ylabel("DCSBM", **side_label_kws)
# RDPG
heatmap(rdpg.p_mat_, ax=ax[2, 0], **heatmap_kws)
heatmap(np.squeeze(rdpg.sample()), ax=ax[2, 1], **heatmap_kws)
ax[2, 0].set_ylabel("RDPG", **side_label_kws)
plt.tight_layout()
# Add colorbar
sm = plt.cm.ScalarMappable(cmap=cmap, norm=norm)
sm.set_array(rdpg.p_mat_)
cbar = fig.colorbar(sm,
ax=ax,
orientation="horizontal",
dcsbme = DCSBMEstimator(directed=True,loops=False)
dcsbme.fit(adj, y=labels)
print("DCSBM \"B\" matrix:")
print(dcsbme.block_p_)
heatmap(dcsbme.p_mat_,
inner_hier_labels=labels,
font_scale=1.5,
title="DCSBM probability matrix",
vmin=0,
vmax=1,
sort_nodes=True)
plt.savefig("DCSBMProbabilityMatrix", bbox_inches='tight')
heatmap(dcsbme.sample()[0],
inner_hier_labels=labels,
title="DCSBM sample",
font_scale=1.5,
sort_nodes=True)
plt.savefig("DCSBMSample", bbox_inches='tight')
rdpge = RDPGEstimator(loops=False)
rdpge.fit(adj, y=labels)
heatmap(rdpge.p_mat_,
inner_hier_labels=labels,
vmin=0,
vmax=1,
font_scale=1.5,
title="RDPG probability matrix",