def _load_default_texts():
"""
Loads default general texts
Returns
-------
result : default 20newsgroup texts
"""
dataset = Dataset()
dataset.fetch_dataset("20NewsGroup")
return dataset.get_corpus()
def test_load_20ng():
data_home = get_data_home(data_home=None)
cache_path = _pkl_filepath(data_home, "20NewsGroup" + ".pkz")
if os.path.exists(cache_path):
os.remove(cache_path)
dataset = Dataset()
dataset.fetch_dataset("20NewsGroup")
assert len(dataset.get_corpus()) == 16309
assert len(dataset.get_labels()) == 16309
assert os.path.exists(cache_path)
dataset = Dataset()
dataset.fetch_dataset("20NewsGroup")
assert len(dataset.get_corpus()) == 16309
def test_partitions_fetch():
dataset = Dataset()
dataset.fetch_dataset("M10")
partitions = dataset.get_partitioned_corpus()
assert len(partitions[0]) == 5847
assert len(partitions[1]) == 1254
def test_load_M10():
dataset = Dataset()
dataset.fetch_dataset("M10")
assert len(set(dataset.get_labels())) == 10
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