def test_train_not_enough_instances(self):
cnn = ConvolutionalNeuralNetwork(24)
X_train_set, y_train_set, _, _, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=0.01,
normalize=True)
with pytest.raises(NotEnoughInstancesError):
cnn.train(X_train_set, y_train_set, stats=stats)
def test_train_and_test(self):
cnn = ConvolutionalNeuralNetwork(24)
# just testing, don't care about overfitting
X_train_set, y_train_set, _, _, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=1,
normalize=True)
cnn.train(X_train_set, y_train_set, stats=stats)
predictions = cnn.predict(X_train_set)
assert len(predictions) == X_train_set.shape[0]
def test_update_stats(self):
seq_length = 24
updated_cnn = ConvolutionalNeuralNetwork(seq_length)
X_train_set, y_train_set, _, _, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=0.85,
normalize=True)
updated_cnn.train(X_train_set, y_train_set, stats)
instances = updated_cnn.stats['n_instances_trained']
dataset_stats = updated_cnn.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)
updated_cnn.train(X_train_set, y_train_set, stats)
assert X_train_set.shape[0] + instances == updated_cnn.stats['n_instances_trained']
assert len(cnn.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):
updated_cnn.train(missing_data, y_train_set, stats)
def test_train_and_test_no_uncertainty_not_enough_instances(self):
cnn = ConvolutionalNeuralNetwork(24)
# just testing, don't care about overfitting
X_train_set, y_train_set, X_test, _, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=0.95,
normalize=True)
cnn.train(X_train_set, y_train_set, stats=stats)
predictions = cnn.predict(X_test, uncertainty=False)
n_none_predictions = len(list(filter(lambda x: x[0] is None and x[1] is None, predictions)))
assert n_none_predictions == len(X_test)
def test_predict_not_enough_instances(self):
global cnn
cnn = ConvolutionalNeuralNetwork(24)
X_train_set, y_train_set, X_test, _, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=0.95,
normalize=True)
cnn.train(X_train_set, y_train_set, stats=stats)
predictions = cnn.predict(X_test=X_test, uncertainty=True)
n_none_predictions = len(list(filter(lambda x: x[0] is None and x[1] is None, predictions)))
assert X_test.shape[0] == n_none_predictions
def test_train(self):
seq_length = 24
cnn = ConvolutionalNeuralNetwork(seq_length)
X_train_set, y_train_set, _, _, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=0.85,
normalize=True)
assert not cnn.is_built
assert cnn.n_features is None
assert cnn.seq_length == seq_length
assert cnn.stats['dataset_stats'] != stats
cnn.train(X_train_set, y_train_set, stats)
assert cnn.is_built
assert cnn.n_features == X_train_set.shape[1]
assert cnn.seq_length == seq_length
assert cnn.stats['dataset_stats'] == stats
def test_load_from_json(self):
global cnn
model_params, extra_params = cnn.model_to_json()
model_params_dict = json.loads(model_params)
extra_params_dict = json.loads(extra_params)
loaded_cnn, error_msg = ConvolutionalNeuralNetwork.new_from_json(model_params_dict, extra_params_dict)
assert error_msg is None
assert loaded_cnn.n_features == extra_params_dict['n_features']
assert loaded_cnn.stats == extra_params_dict['stats']
def test_eval_not_enough(self):
cnn = ConvolutionalNeuralNetwork(24)
dataset, err = DB.DBManager.get_dataset(datetime_from=datetime.strptime("01-01-2018 01:00", '%d-%m-%Y %H:%M'),
datetime_to=datetime.strptime("03-01-2018 06:00", '%d-%m-%Y %H:%M'),
# longitude=-1.395778,
# latitude=50.908140,
config=ConfigReader.CONFIG)
# just testing, don't care about overfitting
X_train_set, y_train_set, X_test, y_test, stats = MainTransformer.get_training_and_test_set(dataset,
'Pollutant',
'Uncertainty',
size=0.8,
normalize=True)
cnn.train(X_train_set, y_train_set, stats=stats)
result, predictions, y_test_set = cnn.eval(X_test, y_test)
predictions_size = len(predictions)
assert predictions_size == len(X_test)