def export(hp_item: HPItem, path: Path) -> Path:
PathBuilder.build(path)
preproc_filename = MLExporter._store_preprocessing_sequence(
hp_item.hp_setting.preproc_sequence, path).name
encoder_filename = MLExporter._store_encoder(
hp_item.hp_setting.encoder, path).name
hp_item.method.store(path, hp_item.method.get_feature_names())
labels_with_values = {
hp_item.method.get_label(): hp_item.method.get_classes()
}
method_config = MLMethodConfiguration(
labels_with_values=labels_with_values,
software_used=hp_item.method.get_package_info(),
encoding_name=hp_item.hp_setting.encoder_name,
encoding_parameters=hp_item.hp_setting.encoder_params,
encoding_file=encoder_filename,
encoding_class=type(hp_item.hp_setting.encoder).__name__,
ml_method=type(hp_item.method).__name__,
ml_method_name=hp_item.method.name,
train_dataset_id=hp_item.train_dataset.identifier,
train_dataset_name=hp_item.train_dataset.name,
preprocessing_sequence_name=hp_item.hp_setting.
preproc_sequence_name,
preprocessing_file=os.path.basename(preproc_filename),
preprocessing_parameters={
type(seq).__name__: vars(seq)
for seq in hp_item.hp_setting.preproc_sequence
})
method_config.store(path / 'ml_config.yaml')
return path
def import_hp_setting(config_dir: Path) -> Tuple[HPSetting, Label]:
config = MLMethodConfiguration()
config.load(config_dir / 'ml_config.yaml')
ml_method = ReflectionHandler.get_class_by_name(
config.ml_method, 'ml_methods/')()
ml_method.load(config_dir)
encoder = MLImport.import_encoder(config, config_dir)
preprocessing_sequence = MLImport.import_preprocessing_sequence(
config, config_dir)
labels = list(config.labels_with_values.keys())
assert len(
labels
) == 1, "MLImport: Multiple labels set in a single ml_config file."
label = Label(labels[0], config.labels_with_values[labels[0]])
return HPSetting(
encoder=encoder,
encoder_params=config.encoding_parameters,
encoder_name=config.encoding_name,
ml_method=ml_method,
ml_method_name=config.ml_method_name,
ml_params={},
preproc_sequence=preprocessing_sequence,
preproc_sequence_name=config.preprocessing_sequence_name), label
def test_load(self):
x = np.array([[1, 0, 0], [0, 1, 1], [1, 1, 1], [0, 1, 1]])
y = {"default": np.array([1, 0, 2, 0])}
knn = KNN()
knn.fit(EncodedData(examples=sparse.csr_matrix(x), labels=y), Label("default"))
path = EnvironmentSettings.root_path / "test/tmp/loadtestsklearn/"
PathBuilder.build(path)
with open(path / "knn.pickle", "wb") as file:
pickle.dump(knn.model, file)
config = MLMethodConfiguration()
config.labels_with_values = {"default": [0, 1, 2]}
config.store(path / "config.json")
knn2 = KNN()
knn2.load(path)
self.assertTrue(isinstance(knn2.model, KNeighborsClassifier))
shutil.rmtree(path)