def test_efdt_split_reevaluation():
dataset = synth.SEA(seed=7, variant=2).take(500)
model = tree.ExtremelyFastDecisionTreeClassifier(
leaf_prediction="nb",
grace_period=50,
min_samples_reevaluate=10,
split_criterion="hellinger",
split_confidence=0.1,
)
max_depth = -1
for x, y in dataset:
model.learn_one(x, y)
if model.height > max_depth:
max_depth = model.height
assert model.height != max_depth
(
get_classification_data(),
tree.HoeffdingAdaptiveTreeClassifier(
leaf_prediction="mc",
max_size=0.025,
grace_period=50,
memory_estimate_period=50,
splitter=tree.splitter.ExhaustiveSplitter(),
),
),
(
get_classification_data(),
tree.ExtremelyFastDecisionTreeClassifier(
leaf_prediction="mc",
max_size=0.025,
grace_period=50,
memory_estimate_period=50,
splitter=tree.splitter.ExhaustiveSplitter(),
),
),
],
)
def test_memory_usage_class(dataset, model):
for x, y in dataset:
model.learn_one(x, y)
assert model._raw_memory_usage / (2 ** 20) < 0.025
@pytest.mark.parametrize(
"dataset, model",