def test_create_ml_dataset_week_interval(test_dataset):
model = RadiusVariance(seq_size=1,
radius=0,
time_interval=TimeInterval.WEEK)
ml_dataset = model.create_ml_dataset(test_dataset)
assert ml_dataset.inputs[0] == np.array([[4.]])
def test_create_ml_dataset_empty():
model = RadiusVariance(seq_size=3, radius=2)
dataset = DataSet([])
ml_dataset = model.create_ml_dataset(dataset)
assert np.array_equal(ml_dataset.inputs[0], np.array([]))
assert np.array_equal(ml_dataset.inputs[1], np.empty((0, 43)))
assert np.array_equal(ml_dataset.outputs[0], np.empty((0, 2)))
def test_write_to_disk():
"""SRS: MOD-3"""
model = RadiusVariance()
file_name = str(uuid.uuid4()) + '.h5'
model.get_model().save(file_name)
assert os.path.isfile(file_name)
os.remove(file_name)
assert not os.path.isfile(file_name)
def test_train_model(test_dataset):
"""SRS: MOD-2"""
model = RadiusVariance(seq_size=2, radius=1)
ml_dataset = model.create_ml_dataset(test_dataset)
weights = model.get_model().get_weights()
model.get_model().compile(optimizer=Adam(lr=0.001), loss='mse')
model.get_model().fit(x=ml_dataset.inputs, y=ml_dataset.outputs, epochs=1)
new_weights = model.get_model().get_weights()
assert not np.all(
[np.array_equal(w, new_w) for (w, new_w) in zip(weights, new_weights)])
def run(years=1, year_target=5, epochs=100, epochs_target=500):
print(f'Generating {years} year(s) of data...')
data_start = time.time()
data = create_data(datetime(2020 - years, 1, 1), datetime(2020, 1, 1))
dataset = DataSet(data)
print('Data generation done')
print(f'Took {time.time() - data_start}s\n')
model = RadiusVariance(seq_size=30, radius=15)
ml_dataset = model.create_ml_dataset(dataset)
print(f'Training for {epochs} epochs...')
train_start = time.time()
model.get_model().compile(optimizer=Adam(lr=0.001), loss='mse')
model.get_model().fit(x=ml_dataset.inputs,
y=ml_dataset.outputs,
epochs=epochs)
print('Training done')
train_time = int(time.time() - train_start)
print(f'Took {train_time}s\n')
total_time = train_time * (year_target / years) * (epochs_target / epochs)
print(
f'It would take this machine an estimated {int(total_time // 60)}m{int(total_time % 60)}s '
+ f'to train {year_target} years of data for {epochs_target} epochs.')
def test_prediction_batch(test_dataset):
model = RadiusVariance(seq_size=2, radius=1)
ml_dataset = model.create_ml_dataset(test_dataset)
model.get_model().compile(optimizer=Adam(lr=0.001), loss='mse')
y_hat = model.get_model().predict([x[0:2] for x in ml_dataset.inputs])
assert y_hat.shape == (2, 2)
def train(dataset: DataSet,
epochs: int,
lr=0.001,
valid_split=0.2,
output_file='weights.h5'):
rv_model = RadiusVariance(seq_size=30,
radius=15,
time_interval=TimeInterval.WEEK)
rv_model.get_model().summary()
ml_dataset = rv_model.create_ml_dataset(dataset)
train_data, test_data = ml_dataset.split(1 - valid_split)
print(len(train_data.inputs[0]), len(test_data.inputs[0]))
rv_model.get_model().compile(optimizer=Adam(lr=lr), loss=loss)
history = rv_model.get_model().fit(x=train_data.inputs,
y=train_data.outputs,
validation_data=(test_data.inputs,
test_data.outputs),
epochs=epochs)
rv_model.get_model().save(output_file)
return rv_model, train_data, test_data, history
def test_prediction(test_dataset):
"""SRS: MOD-7"""
model = RadiusVariance(seq_size=2, radius=1)
ml_dataset = model.create_ml_dataset(test_dataset)
model.get_model().compile(optimizer=Adam(lr=0.001), loss='mse')
y_hat = model.get_model().predict(
[x[np.newaxis, 0] for x in ml_dataset.inputs])
assert y_hat.shape == (1, 2)
def test_create_ml_dataset_radius_affects_length(test_dataset):
model = RadiusVariance(seq_size=3, radius=3)
dataset = DataSet(test_dataset)
ml_dataset = model.create_ml_dataset(dataset)
assert ml_dataset.inputs[0].shape[0] == 2
def test_create_ml_dataset_correct_length(test_dataset):
model = RadiusVariance(seq_size=1, radius=1)
dataset = DataSet(test_dataset)
ml_dataset = model.create_ml_dataset(dataset)
assert ml_dataset.inputs[0].shape[0] == 8
def test_create_ml_dataset(test_dataset):
model = RadiusVariance(seq_size=2, radius=3)
ml_dataset = model.create_ml_dataset(test_dataset)
assert np.array_equal(ml_dataset.inputs[0],
np.array([[[1], [1]], [[1], [0]], [[0], [4]]]))
def test_get_model():
model = RadiusVariance()
model.get_model().summary()