def _save_results(self,
suffix: str,
info_path: str,
results: List[Dict],
k_values: List[List]):
path = Tools.splice_save_problemsets_dictionaries(
results,
metadata_fpath=info_path,
suffix=suffix,
test_data=not train_phase)
Tools.save_k_vals_as_df(k_vals=k_values, suffix=suffix,
test_data=not train_phase,
cop_kmeans_frac=constraints_fraction)
return path
# (comparing different runs of HDP on a problem set)
seed=max(33, 70*(ps == 41)) + (3 * (ps in problematics)),
infer_lss=False,
verbose=False,
configuration=config_neutral,
drop_uncommon=True)
problemsets_results.append(ps_result)
ks = clu.cand_k.copy()
ks.append(1+max(clu.true_labels))
k_vals.append(ks)
my_suffix = "_training_neutral_common"
info_json = r"..\..\Datasets\pan17_train\info.json"
Tools.splice_save_problemsets_dictionaries(problemsets_results,
metadata_fpath=info_json,
suffix=my_suffix)
Tools.save_k_vals_as_df(k_vals=k_vals, suffix=my_suffix)
print("==================== SPARSE ====================")
problemsets_results = []
k_vals = []
for ps in range(1, 61):
print(f"Executing on problem set ► {ps:03d} ◄ ..")
ps_result, l, lss, plain, clu = problem_set_run(
problem_set_id=ps,
n_clusters=None,
# Emperically specify a random seed that's compatible with
# hyper sampling and certain problem sets due to a bug in HDP
# as it seems. However, the seeds would be consistant across
# runs and yield comparable results for our experiments
# (comparing different runs of HDP on a problem set)
seed=13712 * ps,