def test_trim_2D(random):
node = Pipeline(steps=dummy_classifier)
data = DummyData(rate=1).next(20)
node._X_train = data.values
node._X_train_indices = np.array(data.index.values, dtype=np.datetime64)
start = np.datetime64('2018-01-01T00:00:05')
stop = np.datetime64('2018-01-01T00:00:15')
node._dimensions = 2
node._accumulate(start, stop)
assert len(node._X_train_indices) == 10
assert len(node._X_train) == 10
def test_fit_reset(caplog):
caplog.set_level(logging.DEBUG)
node = Pipeline(steps=dummy_classifier, event_reset='reset')
node._status = -1 # bypass accumulation
node._X_train = np.array([-1, 1, 1, 1])
node._y_train = np.array([0, 1, 1, 1])
node.i_events.data = make_event('training_starts')
node.update()
node.i_events.data = make_event('reset')
node.update()
assert caplog.record_tuples[0][2] == 'Start training'
assert caplog.record_tuples[1][2] == 'Reset'
assert node._status == 0
def test_fit_success(caplog):
caplog.set_level(logging.DEBUG)
node = Pipeline(steps=dummy_classifier)
node._status = -1 # bypass accumulation
assert hasattr(node._pipeline[0], 'n_classes_') == False
node._X_train = np.array([-1, 1, 1, 1])
node._y_train = np.array([0, 1, 1, 1])
node.i_events.data = make_event('training_starts')
while node._status != 3:
node.update()
assert node._pipeline[0].n_classes_ == 2
assert caplog.record_tuples[0][2] == 'Start training'
assert caplog.record_tuples[1][2].startswith('Model fitted in')