def test_model_output_lda_tomotopy(data_dir):
dataset = Dataset()
dataset.load_custom_dataset_from_folder(data_dir + '/M10')
num_topics = 3
model = LDATOMOTO(num_topics=num_topics, alpha=0.1)
output = model.train_model(dataset)
assert 'topics' in output.keys()
assert 'topic-word-matrix' in output.keys()
assert 'test-topic-document-matrix' in output.keys()
# check topics format
assert type(output['topics']) == list
assert len(output['topics']) == num_topics
# check topic-word-matrix format
assert type(output['topic-word-matrix']) == np.ndarray
assert output['topic-word-matrix'].shape == (num_topics,
len(dataset.get_vocabulary()))
# check topic-document-matrix format
assert type(output['topic-document-matrix']) == np.ndarray
assert output['topic-document-matrix'].shape == (
num_topics, len(dataset.get_partitioned_corpus()[0]))
# check test-topic-document-matrix format
assert type(output['test-topic-document-matrix']) == np.ndarray
assert output['test-topic-document-matrix'].shape == (
num_topics, len(dataset.get_partitioned_corpus()[2]))
def test_model_output_ctm_combined(data_dir):
dataset = Dataset()
dataset.load_custom_dataset_from_folder(data_dir + '/M10')
num_topics = 3
model = CTM(num_topics=num_topics, num_epochs=5, inference_type='combined')
output = model.train_model(dataset)
assert 'topics' in output.keys()
assert 'topic-word-matrix' in output.keys()
assert 'test-topic-document-matrix' in output.keys()
# check topics format
assert type(output['topics']) == list
assert len(output['topics']) == num_topics
# check topic-word-matrix format
assert type(output['topic-word-matrix']) == np.ndarray
assert output['topic-word-matrix'].shape == (num_topics,
len(dataset.get_vocabulary()))
# check topic-document-matrix format
assert type(output['topic-document-matrix']) == np.ndarray
assert output['topic-document-matrix'].shape == (
num_topics, len(dataset.get_partitioned_corpus()[0]))
# check test-topic-document-matrix format
assert type(output['test-topic-document-matrix']) == np.ndarray
assert output['test-topic-document-matrix'].shape == (
num_topics, len(dataset.get_partitioned_corpus()[2]))
def test_model_output_nmf(data_dir):
dataset = Dataset()
dataset.load_custom_dataset_from_folder(data_dir + '/M10')
num_topics = 3
model = NMF(num_topics=num_topics,
w_max_iter=10,
h_max_iter=10,
use_partitions=True)
output = model.train_model(dataset)
assert 'topics' in output.keys()
assert 'topic-word-matrix' in output.keys()
assert 'test-topic-document-matrix' in output.keys()
# check topics format
assert type(output['topics']) == list
assert len(output['topics']) == num_topics
# check topic-word-matrix format
assert type(output['topic-word-matrix']) == np.ndarray
assert output['topic-word-matrix'].shape == (num_topics,
len(dataset.get_vocabulary()))
# check topic-document-matrix format
assert type(output['topic-document-matrix']) == np.ndarray
assert output['topic-document-matrix'].shape == (
num_topics, len(dataset.get_partitioned_corpus()[0]))
# check test-topic-document-matrix format
assert type(output['test-topic-document-matrix']) == np.ndarray
assert output['test-topic-document-matrix'].shape == (
num_topics, len(dataset.get_partitioned_corpus()[2]))
def test_model_output_prodlda_not_partitioned(data_dir):
dataset = Dataset()
dataset.load_custom_dataset_from_folder(data_dir + '/M10')
num_topics = 3
model = ProdLDA(num_topics=num_topics, num_epochs=5, use_partitions=False)
output = model.train_model(dataset)
assert 'topics' in output.keys()
assert 'topic-word-matrix' in output.keys()
assert 'test-topic-document-matrix' not in output.keys()
# check topics format
assert type(output['topics']) == list
assert len(output['topics']) == num_topics
# check topic-word-matrix format
assert type(output['topic-word-matrix']) == np.ndarray
assert output['topic-word-matrix'].shape == (num_topics, len(dataset.get_vocabulary()))
# check topic-document-matrix format
assert type(output['topic-document-matrix']) == np.ndarray
assert output['topic-document-matrix'].shape == (num_topics, len(dataset.get_corpus()))
def test_partitions_custom(data_dir):
dataset = Dataset()
dataset.load_custom_dataset_from_folder(data_dir + "M10")
partitions = dataset.get_partitioned_corpus()
assert len(partitions[0]) == 5847
assert len(partitions[1]) == 1254
def dataset(data_dir):
# Load dataset
dataset = Dataset()
dataset.load_custom_dataset_from_folder(data_dir + '/M10')
return dataset
def dataset(root_dir):
dataset = Dataset()
dataset.load_custom_dataset_from_folder(root_dir + "/../preprocessed_datasets/" + '/M10')
return dataset
def _restore_parameters(self, name_path):
"""
Restore the BO parameters from the json file
:param name_path: name of the json file
:type name_path: str
:return: result of BO optimization (scikit-optimize object), surrogate model (scikit-learn object)
:rtype: tuple
"""
# Load the previous results
with open(name_path, 'rb') as file:
optimization_object = json.load(file)
self.search_space = load_search_space(optimization_object["search_space"])
self.acq_func = optimization_object["acq_func"]
self.surrogate_model = optimization_object["surrogate_model"]
self.kernel = eval(optimization_object["kernel"])
self.optimization_type = optimization_object["optimization_type"]
self.model_runs = optimization_object["model_runs"]
self.save_models = optimization_object["save_models"]
self.save_step = optimization_object["save_step"]
self.save_name = optimization_object["save_name"]
self.save_models = optimization_object["save_models"]
self.save_path = optimization_object["save_path"]
self.early_stop = optimization_object["early_stop"]
self.early_step = optimization_object["early_step"]
self.plot_model = optimization_object["plot_model"]
self.plot_best_seen = optimization_object["plot_best_seen"]
self.plot_name = optimization_object["plot_name"]
self.log_scale_plot = optimization_object["log_scale_plot"]
self.random_state = optimization_object["random_state"]
self.dict_model_runs = optimization_object['dict_model_runs']
self.number_of_previous_calls = optimization_object['current_call'] + 1
self.current_call = optimization_object['current_call'] + 1
self.number_of_call = optimization_object['number_of_call']
self.save_path = optimization_object['save_path']
self.x0 = optimization_object['x0']
self.y0 = optimization_object['y0']
self.n_random_starts = optimization_object['n_random_starts']
self.initial_point_generator = optimization_object['initial_point_generator']
self.topk = optimization_object['topk']
self.time_eval = optimization_object["time_eval"]
res = None
# Load the dataset
dataset = Dataset()
if not optimization_object["is_cached"]:
dataset.load_custom_dataset_from_folder(optimization_object["dataset_path"])
else:
dp = optimization_object["dataset_path"][:-(len(optimization_object["dataset_name"]) + len("_py3.pkz"))]
dataset.fetch_dataset(optimization_object["dataset_name"], data_home=dp)
self.dataset = dataset
# Load the metric
self._load_metric(optimization_object, dataset)
# Load the model
self.model = load_model(optimization_object)
# Creation of the hyperparameters
self.hyperparameters = list(sorted(self.search_space.keys()))
# Choice of the optimizer
opt = choose_optimizer(self)
# Update number_of_call for restarting
for i in range(self.number_of_previous_calls):
next_x = [optimization_object["x_iters"][key][i] for key in self.hyperparameters]
f_val = -optimization_object["f_val"][i] if self.optimization_type == 'Maximize' else \
optimization_object["f_val"][i]
res = opt.tell(next_x, f_val)
# Create the directory where the results are saved
Path(self.save_path).mkdir(parents=True, exist_ok=True)
self.model_path_models = self.save_path + "models/"
return res, opt