def test_serialization_deserialization():
basepath = 'shac'
params = get_hyperparameter_list()
h = hp.HyperParameterList(params)
dataset = data.Dataset(h)
# models
clfs = []
# fit samples
num_samples = 16
for i in range(3):
samples = [h.sample() for _ in range(num_samples)]
labels = [np.sum(sample) for sample in samples]
x, y = samples, labels
x, y = dataset.encode_dataset(x, y)
model = xgb_utils.train_single_model(x, y)
clfs.append(model)
xgb_utils.save_classifiers(clfs, basepath)
assert os.path.exists(os.path.join(basepath, 'classifiers', 'classifiers.pkl'))
models = xgb_utils.restore_classifiers(basepath)
assert len(models) == len(clfs)
with pytest.raises(FileNotFoundError):
models = xgb_utils.restore_classifiers('none')
def restore_data(self):
"""
Recover the serialized class objects by loading the dataset and the trained models
from the default save directories.
"""
try:
self.dataset = data.Dataset.load_from_directory()
except FileNotFoundError:
pass
try:
self.classifiers = xgb_utils.restore_classifiers(self.clf_dir)
except FileNotFoundError:
pass
self.parameters = self.dataset.parameters
self._dataset_index = len(self.dataset)
if len(self.dataset) > 0:
print("\nFound and restored dataset containing %d samples" %
(len(self.dataset)))
if len(self.classifiers) > 0:
print("Found and restored %d classifiers" %
(len(self.classifiers)))
print()