def test_DCER_fit(self):
np.random.seed(8888)
graph = self.graph
p_mat = self.p_mat
dcsbe = DCSBMEstimator(directed=True, loops=False)
dcsbe.fit(graph)
assert_allclose(p_mat, dcsbe.p_mat_, atol=0.12)
def test_DCSBM_fit_supervised(self):
p_mat = self.p_mat
labels = self.labels
g = self.g
dcsbe = DCSBMEstimator(directed=True, loops=False)
dcsbe.fit(g, y=labels)
assert_allclose(dcsbe.p_mat_, p_mat, atol=0.1)
def test_DCSBM_score(self):
p_mat = self.p_mat
graph = self.g
estimator = DCSBMEstimator()
_test_score(estimator, p_mat, graph)
with pytest.raises(ValueError):
estimator.score_samples(graph=graph[1:100, 1:100])
def test_DCSBM_fit_unsupervised(self):
np.random.seed(12345)
n_verts = 1500
distances = np.random.beta(4, 1, n_verts)
B = np.array([[0.7, 0.1, 0.1], [0.1, 0.9, 0.1], [0.05, 0.1, 0.75]])
n = np.array([500, 500, 500])
labels = _n_to_labels(n)
p_mat = _block_to_full(B, labels, (n_verts, n_verts))
p_mat = p_mat * np.outer(distances, distances)
p_mat -= np.diag(np.diag(p_mat))
graph = sample_edges(p_mat, directed=True, loops=False)
dcsbe = DCSBMEstimator(directed=True, loops=False)
dcsbe.fit(graph)
assert adjusted_rand_score(labels, dcsbe.vertex_assignments_) > 0.95
assert_allclose(p_mat, dcsbe.p_mat_, atol=0.12)
def run_fit(seed, directed):
# run left
graph, labels = load_left()
print(labels)
if not directed:
graph = symmetrize(graph, method="avg")
# fit SBM
sbm = SBMEstimator(directed=True, loops=False)
sbm_left_df = fit_a_priori(sbm, graph, labels)
print(sbm_left_df["n_params"])
save_obj(sbm_left_df, file_obs, "sbm_left_df")
# fit DCSBM
dcsbm = DCSBMEstimator(directed=True, loops=False, degree_directed=False)
dcsbm_left_df = fit_a_priori(dcsbm, graph, labels)
save_obj(dcsbm_left_df, file_obs, "dcsbm_left_df")
# fit dDCSBM
ddcsbm = DCSBMEstimator(directed=True, loops=False, degree_directed=True)
ddcsbm_left_df = fit_a_priori(ddcsbm, graph, labels)
save_obj(ddcsbm_left_df, file_obs, "ddcsbm_left_df")
# run right
graph, labels = load_right()
if not directed:
graph = symmetrize(graph, method="avg")
# fit SBM
sbm = SBMEstimator(directed=True, loops=False)
sbm_right_df = fit_a_priori(sbm, graph, labels)
save_obj(sbm_right_df, file_obs, "sbm_right_df")
# fit DCSBM
dcsbm = DCSBMEstimator(directed=True, loops=False, degree_directed=False)
dcsbm_right_df = fit_a_priori(dcsbm, graph, labels)
save_obj(dcsbm_right_df, file_obs, "dcsbm_right_df")
# fit dDCSBM
ddcsbm = DCSBMEstimator(directed=True, loops=False, degree_directed=True)
ddcsbm_right_df = fit_a_priori(ddcsbm, graph, labels)
save_obj(ddcsbm_right_df, file_obs, "ddcsbm_right_df")
return 0
def select_dcsbm(
graph,
param_grid,
directed=True,
degree_directed=False,
metric="mse",
c=0,
rank="full",
n_jobs=1,
n_init=1,
):
# common parameters of all estimators
dcsbm = DCSBMEstimator(directed=directed,
degree_directed=degree_directed,
loops=False,
metric=metric)
# define scoring functions to evaluate models
scorers = gen_scorers(dcsbm, graph)
# run the grid search
grid_search = GridSearchUS(
dcsbm,
param_grid,
scoring=scorers,
n_jobs=n_jobs,
verbose=0,
refit=False,
n_init=n_init,
)
grid_search.fit(graph)
# format outputs
out_df = grid_search.cv_results_
if "param_embed_kws" in out_df.columns:
out_df["param_regularizer"] = [
v["regularizer"] for v in out_df["param_embed_kws"].values
]
return out_df
def test_DCSBM_nparams(self):
n_verts = 3000
n_class = 4
graph = self.g
labels = self.labels
e = DCSBMEstimator(directed=True)
e.fit(graph)
assert e._n_parameters() == (n_verts + n_class - 1 + n_class**2)
e = DCSBMEstimator(directed=True)
e.fit(graph, y=labels)
assert e._n_parameters() == (n_verts + n_class**2)
e = DCSBMEstimator(directed=True, degree_directed=True)
e.fit(graph, y=labels)
assert e._n_parameters() == (2 * n_verts + n_class**2)
e = DCSBMEstimator(directed=False)
e.fit(graph, y=labels)
assert e._n_parameters() == (n_verts + 10)
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)
def test_DCSBM_inputs(self):
with pytest.raises(TypeError):
DCSBMEstimator(directed="hey")
with pytest.raises(TypeError):
DCSBMEstimator(loops=6)
with pytest.raises(TypeError):
DCSBMEstimator(n_components="XD")
with pytest.raises(ValueError):
DCSBMEstimator(n_components=-1)
with pytest.raises(TypeError):
DCSBMEstimator(min_comm="1")
with pytest.raises(ValueError):
DCSBMEstimator(min_comm=-1)
with pytest.raises(TypeError):
DCSBMEstimator(max_comm="ay")
with pytest.raises(ValueError):
DCSBMEstimator(max_comm=-1)
with pytest.raises(ValueError):
DCSBMEstimator(min_comm=4, max_comm=2)
graph = er_np(100, 0.5)
bad_y = np.zeros(99)
dcsbe = DCSBMEstimator()
with pytest.raises(ValueError):
dcsbe.fit(graph, y=bad_y)
with pytest.raises(ValueError):
dcsbe.fit(graph[:, :99])
with pytest.raises(ValueError):
dcsbe.fit(graph[..., np.newaxis])
with pytest.raises(TypeError):
DCSBMEstimator(cluster_kws=1)
with pytest.raises(TypeError):
DCSBMEstimator(embed_kws=1)
vmax=1,
font_scale=1.5,
title="SBM probability matrix",
sort_nodes=True)
plt.savefig("SBMProbabilityMatrix", bbox_inches='tight')
heatmap(sbme.sample()[0],
inner_hier_labels=labels,
font_scale=1.5,
title="SBM sample",
sort_nodes=True)
plt.savefig("SBMSample", bbox_inches='tight')
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,
right_graph,
inner_hier_labels=pred_labels,
title="Right MB (by SBM block)",
ax=ax[1, 0],
**heatmap_kws,
)
heatmap(
gs.model_.p_mat_,
inner_hier_labels=pred_labels,
title=f"Fit SBM, lik = {lik:.2f}",
ax=ax[1, 1],
**heatmap_kws,
)
# A priori DCSBM
ap_estimator = DCSBMEstimator()
ap_estimator.fit(right_graph, y=right_labels)
lik = ap_estimator.score(right_graph, clip=clip)
heatmap(
right_graph,
inner_hier_labels=right_labels,
title="Right MB (by cell type)",
ax=ax[2, 0],
**heatmap_kws,
)
heatmap(
ap_estimator.p_mat_,
inner_hier_labels=right_labels,
title=f"A priori DCSBM, lik = {lik:.2f}",
ax=ax[2, 1],
**heatmap_kws,
import matplotlib as mpl
import numpy as np
from graspy.models import DCSBMEstimator, RDPGEstimator, SBMEstimator
from graspy.plot import heatmap
from src.data import load_right
# Load data
right_adj, right_labels = load_right()
# Fit the models
sbm = SBMEstimator(directed=True, loops=False)
sbm.fit(right_adj, y=right_labels)
dcsbm = DCSBMEstimator(degree_directed=False, directed=True, loops=False)
dcsbm.fit(right_adj, y=right_labels)
rdpg = RDPGEstimator(loops=False, n_components=3)
rdpg.fit(right_adj)
# Plotting
np.random.seed(8888)
cmap = mpl.cm.get_cmap("RdBu_r")
center = 0
vmin = 0
vmax = 1
norm = mpl.colors.Normalize(0, 1)
cc = np.linspace(0.5, 1, 256)
cmap = mpl.colors.ListedColormap(cmap(cc))
#%%
from src.data import load_left
from graspy.models import DCSBMEstimator
graph, labels = load_left()
dcsbm = DCSBMEstimator(directed=True, loops=False, degree_directed=True)
dcsbm.fit(graph, y=labels)
dcsbm.mse(graph)
#%%
from src.models import GridSearchUS
from src.models import select_rdpg
n_init = 3
n_components_try = range(1, 5)
param_grid = dict(n_components=n_components_try)
select_rdpg(graph, param_grid)
#%%
from graspy.utils import cartprod
import numpy as np
s = range(20, 25)
f = np.random.uniform(size=5)
out = cartprod(s, f)
from itertools import product
out = product(s, f)
for i, j in product(s, f):
print(i)
from graspy.utils import remove_loops
X = ase_flat_embed[:, :d]
n_pairs = len(X) // 2
new_lp_inds = np.arange(n_pairs)
new_rp_inds = np.arange(n_pairs).copy() + n_pairs
rows = []
for l in range(n_levels):
labels = new_meta[f"lvl{l}_labels"].values
left_adj = binarize(new_adj[np.ix_(new_lp_inds, new_lp_inds)])
left_adj = remove_loops(left_adj)
right_adj = binarize(new_adj[np.ix_(new_rp_inds, new_rp_inds)])
right_adj = remove_loops(right_adj)
dcsbm = DCSBMEstimator(directed=True, loops=False)
uni_labels, inv = np.unique(labels, return_inverse=True)
dcsbm.fit(left_adj, inv[new_lp_inds])
train_left_p = dcsbm.p_mat_
train_left_p[train_left_p == 0] = 1 / train_left_p.size
score = poisson.logpmf(left_adj, train_left_p).sum()
rows.append(
dict(train_side="left",
test="same",
test_side="left",
score=score,
level=l))
score = poisson.logpmf(right_adj, train_left_p).sum()
rows.append(
dict(train_side="left",
# %% [markdown]
# ##
# %% [markdown]
# ##
# %% [markdown]
# ##
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)
temp_dict = base_dict.copy()
temp_dict["Metric"] = "GMM BIC"
temp_dict["Score"] = score
out_dicts.append(temp_dict)
# SBM likelihood
sbm = SBMEstimator(directed=True, loops=False)
sbm.fit(bin_adj, y=pred_labels)
score = sbm.score(bin_adj)
temp_dict = base_dict.copy()
temp_dict["Metric"] = "SBM likelihood"
temp_dict["Score"] = score
out_dicts.append(temp_dict)
# DCSBM likelihood
dcsbm = DCSBMEstimator(directed=True, loops=False)
dcsbm.fit(bin_adj, y=pred_labels)
score = dcsbm.score(bin_adj)
temp_dict = base_dict.copy()
temp_dict["Metric"] = "DCSBM likelihood"
temp_dict["Score"] = score
out_dicts.append(temp_dict)
# ARI of the subset with labels
score = sub_ari(known_inds, class_labels, pred_labels)
temp_dict = base_dict.copy()
temp_dict["Metric"] = "Simple ARI"
temp_dict["Score"] = score
out_dicts.append(temp_dict)
# ARI vs K - 1
ax = axs[1]
adjplot(
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,
def test_DCSBM_score(self):
p_mat = self.p_mat
graph = self.g
estimator = DCSBMEstimator()
_test_score(estimator, p_mat, graph)
