def _load_phi(self, num_topics: int, subsample_number: int) -> pd.DataFrame:
topic_model = TopicModel.load(
self._folder_path_model(
num_topics, subsample_number=subsample_number
)
)
return topic_model.get_phi()
def test_optimize_for_model(self, keep_in_memory, model_family):
# Thetaless currently fails
# see https://github.com/machine-intelligence-laboratory/TopicNet/issues/79
artm_score_name = 'perplexity_score'
artm_score = PerplexityScore(
name=artm_score_name,
class_ids=[self.main_modality, self.other_modality])
custom_score_name = 'diversity_score'
custom_score = DiversityScore(custom_score_name,
class_ids=self.main_modality)
self.text_collection._set_dataset_kwargs(keep_in_memory=keep_in_memory)
min_num_topics = 1
max_num_topics = 2
num_topics_interval = 1
num_fit_iterations = 3
num_search_points = len(
list(range(min_num_topics, max_num_topics + 1,
num_topics_interval)))
num_restarts = 3
experiment_name = model_family.value
experiment_folder = self.working_folder_path
optimizer = OptimizeScoresMethod(
scores=[artm_score, custom_score],
model_family=model_family,
min_num_topics=min_num_topics,
max_num_topics=max_num_topics,
num_topics_interval=num_topics_interval,
num_fit_iterations=num_fit_iterations,
num_restarts=num_restarts,
one_model_num_processors=1,
separate_thread=False,
experiment_name=experiment_name,
experiment_directory=experiment_folder,
)
optimizer.search_for_optimum(text_collection=self.text_collection)
restart_folder_names = os.listdir(experiment_folder)
assert len(restart_folder_names) == num_restarts
for restart_folder_name in restart_folder_names:
assert restart_folder_name.startswith(experiment_name)
restart_folder_path = os.path.join(experiment_folder,
restart_folder_name)
model_folder_names = os.listdir(restart_folder_path)
assert len(model_folder_names) == num_search_points
for model_folder_name in model_folder_names:
topic_model = TopicModel.load(
os.path.join(restart_folder_path, model_folder_name))
assert artm_score_name in topic_model.scores
assert custom_score_name in topic_model.scores
assert len(
topic_model.scores[artm_score_name]) == num_fit_iterations
assert len(topic_model.scores[custom_score_name]) == 1
assert all(
isinstance(v, Number)
for v in topic_model.scores[artm_score_name])
assert all(
isinstance(v, Number)
for v in topic_model.scores[custom_score_name])