def run_fit(seed, param_grid, directed, n_init, n_jobs, co_block):
# run left
graph = load_drosophila_left()
if not directed:
graph = symmetrize(graph, method="avg")
graph = binarize(graph)
sbm_left_df = select_sbm(
graph,
param_grid,
directed=directed,
n_jobs=n_jobs,
n_init=n_init,
co_block=co_block,
)
save_obj(sbm_left_df, file_obs, "cosbm_left_df")
# run right
graph = load_drosophila_right()
if not directed:
graph = symmetrize(graph, method="avg")
graph = binarize(graph)
sbm_right_df = select_sbm(
graph,
param_grid,
directed=directed,
n_jobs=n_jobs,
n_init=n_init,
co_block=co_block,
)
save_obj(sbm_right_df, file_obs, "cosbm_right_df")
return 0
def run_fit(
seed,
n_components_try_range,
n_components_try_rdpg,
n_block_try_range,
directed,
n_sims_sbm,
):
graph = load_drosophila_left()
if not directed:
graph = symmetrize(graph, method="avg")
graph = binarize(graph)
connected = is_fully_connected(graph)
if not connected:
heatmap(graph)
plt.show()
raise ValueError("input graph not connected")
np.random.seed(seed)
columns = columns = [
"n_params_gmm",
"n_params_sbm",
"rss",
"mse",
"score",
"n_components_try",
"n_block_try",
"sim_ind",
]
sbm_master_df = pd.DataFrame(columns=columns)
for i in range(n_sims_sbm):
sbm_df = select_sbm(graph,
n_components_try_range,
n_block_try_range,
directed=directed)
sbm_df["sim_ind"] = i
sbm_master_df = sbm_master_df.append(sbm_df,
ignore_index=True,
sort=True)
rdpg_df = select_rdpg(graph, n_components_try_rdpg, directed)
def metric(assignments, *args):
return -compute_mse_from_assignments(
assignments, graph, directed=directed)
tsbm_master_df = select_sbm(
graph,
n_components_try_range,
n_block_try_range,
directed=directed,
method="bc-metric",
metric=metric,
)
return (sbm_master_df, rdpg_df, tsbm_master_df)
def run_sim(
seed,
n_blocks_range,
n_verts_range,
n_components_try_range,
n_block_try_range,
B_mat,
directed,
):
np.random.seed(seed)
columns = [
"n_params_gmm",
"n_params_sbm",
"rss",
"mse",
"score",
"n_components_try",
"n_block_try",
"n_blocks",
"n_verts",
]
master_sbm_df = pd.DataFrame(columns=columns)
for i, n_blocks in enumerate(n_blocks_range):
B_mat_trunc = B_mat[:n_blocks, :n_blocks]
for j, n_verts in enumerate((n_verts_range)):
graph, labels = gen_sbm(n_verts, n_blocks, B_mat_trunc)
sbm_df = select_sbm(
graph, n_components_try_range, n_block_try_range, directed=directed
)
sbm_df["n_verts"] = n_verts
sbm_df["n_blocks"] = n_blocks
master_sbm_df = master_sbm_df.append(sbm_df, ignore_index=True, sort=True)
return master_sbm_df
def run_fit(
seed,
n_components_try_range,
n_components_try_rdpg,
n_block_try_range,
directed,
n_sims_sbm,
):
graph = load_drosophila_left()
if not directed:
graph = symmetrize(graph, method="avg")
graph = binarize(graph)
connected = is_fully_connected(graph)
if not connected:
heatmap(graph)
plt.show()
raise ValueError("input graph not connected")
np.random.seed(seed)
columns = columns = [
"n_params_gmm",
"n_params_sbm",
"rss",
"mse",
"score",
"n_components_try",
"n_block_try",
"sim_ind",
]
sbm_master_df = pd.DataFrame(columns=columns)
for i in range(n_sims_sbm):
sbm_df = select_sbm(
graph,
n_components_try_range,
n_block_try_range,
directed=directed,
rank="sweep",
)
sbm_df["sim_ind"] = i
sbm_master_df = sbm_master_df.append(sbm_df,
ignore_index=True,
sort=True)
save_obj(sbm_master_df, file_obs, "sbm_master_df")
return 0
#
#
#
##%% #############
show_plots = False
score = "mse"
left_adj, left_labels = load_left()
if show_plots:
heatmap(left_adj, inner_hier_labels=left_labels, cbar=False)
estimator = SBMEstimator()
ap_results = fit_a_priori(estimator, left_adj, left_labels)
param_grid = dict(n_blocks=list(range(1, 10)))
sweep_results = select_sbm(left_adj, param_grid, n_init=25, n_jobs=-2)
sweep_results
best_results = get_best(sweep_results,
"n_params",
score_name=score,
small_better=False)
##%%
sns.scatterplot(data=best_results, x="n_params", y=score)
sns.scatterplot(data=ap_results, x="n_params", y=score)
##%%
estimator = DCSBMEstimator()
ap_results = fit_a_priori(estimator, left_adj, left_labels)