def test_retrain(self, dataset_one, dataset_two):
X_train_set, y_train_set, X_test, y_test, stats = MainTransformer.get_training_and_test_set(dataset_one,
'Pollutant',
'Uncertainty',
size=0.6,
normalize=True)
gp = GaussianProcesses()
gp.train(X_train_set, y_train_set, stats=stats)
instances = gp.stats['n_instances_trained']
model_stats = gp.stats['dataset_stats']
assert instances == X_train_set.shape[0]
assert model_stats == stats
X_train_set, y_train_set, X_test, y_test, stats = MainTransformer.get_training_and_test_set(dataset_two,
'Pollutant',
'Uncertainty',
size=0.5,
normalize=True)
gp.train(X_train_set, y_train_set, stats)
assert instances + X_train_set.shape[0] == gp.stats['n_instances_trained']
assert model_stats != gp.stats['dataset_stats'] != stats
def test_save_wrong(self, config):
X_train_set, y_train_set, X_test, y_test, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=0.5,
normalize=True)
gp = GaussianProcesses()
gp.train(X_train_set, y_train_set, stats=stats)
result, msg = gp.save_model(config)
assert not result and isinstance(msg, str)
def test_eval(self, error_func):
X_train_set, y_train_set, X_test, y_test, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=0.5,
normalize=True)
gp = GaussianProcesses()
gp.train(X_train_set, y_train_set, stats=stats)
result, predictions, y_test_set = gp.eval(X_test, y_test, error_func=error_func)
predictions_size = len(predictions)
assert predictions_size == len(X_test)
def test_save(self, config):
X_train_set, y_train_set, X_test, y_test, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=0.5,
normalize=True)
gp = GaussianProcesses()
gp.train(X_train_set, y_train_set, stats=stats)
result, msg = gp.save_model(config)
global full_gp
full_gp = gp
assert result and msg is None
def test_train_and_test_various_datasets(self, given_dataset):
X_train_set, y_train_set, X_test, y_test, stats = MainTransformer.get_training_and_test_set(given_dataset,
'Pollutant',
'Uncertainty',
size=0.5,
normalize=True)
gp = GaussianProcesses()
gp.train(X_train_set, y_train_set, stats=stats)
assert gp.stats['n_instances_trained'] == X_train_set.shape[0]
assert gp.stats['dataset_stats'] == stats
predictions = gp.predict(X_test, uncertainty=True)
assert len(predictions) == X_test.shape[0]
def test_update_stats(self):
full_gp = GaussianProcesses()
X_train_set, y_train_set, _, _, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=0.85,
normalize=True)
full_gp.train(X_train_set, y_train_set, stats=stats)
instances = full_gp.stats['n_instances_trained']
dataset_stats = full_gp.stats['dataset_stats']
assert X_train_set.shape[0] == instances
assert stats == dataset_stats
X_train_set, y_train_set, _, _, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=0.5,
normalize=True)
full_gp.train(X_train_set, y_train_set, stats)
assert X_train_set.shape[0] + instances == full_gp.stats['n_instances_trained']
assert len(full_gp.stats['dataset_stats'].keys()) == len(stats.keys()) == len(dataset_stats.keys())
missing_data = X_train_set.drop(axis=1, columns='Temperature', inplace=False, errors='ignore')
with pytest.raises(WrongNumberOfFeatures):
full_gp.train(missing_data, y_train_set, stats)
def test_train_and_test(self, uncertainty):
X_train_set, y_train_set, X_test, y_test, stats = MainTransformer.get_training_and_test_set(dataset_gp,
'Pollutant',
'Uncertainty',
size=0.5,
normalize=True)
gp = GaussianProcesses()
gp.train(X_train_set, y_train_set, stats=stats)
assert gp.stats['n_instances_trained'] == X_train_set.shape[0]
assert gp.stats['dataset_stats'] == stats
predictions = gp.predict(X_test, uncertainty=uncertainty)
assert len(predictions) == X_test.shape[0]
if uncertainty:
values_without_uncertainty = list(filter(lambda x: len(x) != 2, predictions))
assert len(values_without_uncertainty) == 0
if not isinstance(uncertainty, bool):
assert len(list(filter(lambda x: not isinstance(x, tuple), predictions))) == X_test.shape[0]