def test_model_n_trees_invalid():
case_kwargs = copy.deepcopy(toy_kwargs)
case_kwargs.update({"n_trees": [42]})
model = CascadeForestRegressor(**case_kwargs)
with pytest.raises(ValueError) as excinfo:
model._set_n_trees(0)
assert "Invalid value for n_trees." in str(excinfo.value)
def test_model_n_trees_non_positive():
case_kwargs = copy.deepcopy(toy_kwargs)
case_kwargs.update({"n_trees": 0})
model = CascadeForestRegressor(**case_kwargs)
with pytest.raises(ValueError) as excinfo:
model._set_n_trees(0)
assert "should be strictly positive." in str(excinfo.value)
def test_custom_base_estimator_invalid_n_splits():
model = CascadeForestRegressor()
n_estimators = 4
estimators = [DecisionTreeClassifier() for _ in range(n_estimators)]
with pytest.raises(ValueError) as excinfo:
model.set_estimator(estimators, n_splits=1)
assert "should be at least 2" in str(excinfo.value)
def test_model_n_trees_auto():
case_kwargs = copy.deepcopy(toy_kwargs)
case_kwargs.update({"n_trees": "auto"})
model = CascadeForestRegressor(**case_kwargs)
n_trees = model._set_n_trees(0)
assert n_trees == 100
n_trees = model._set_n_trees(2)
assert n_trees == 300
n_trees = model._set_n_trees(10)
assert n_trees == 500
def test_model_invalid_training_params(param):
case_kwargs = copy.deepcopy(toy_kwargs)
case_kwargs.update(param[1])
model = CascadeForestRegressor(**case_kwargs)
with pytest.raises(ValueError) as excinfo:
model.fit(X_train, y_train)
if param[0] == 0:
assert "max_layers" in str(excinfo.value)
elif param[0] == 1:
assert "n_tolerant_rounds" in str(excinfo.value)
elif param[0] == 2:
assert "delta " in str(excinfo.value)
def test_custom_base_estimator_missing_predict():
class tmp_estimator:
def __init__(self):
pass
def fit(self, X, y):
pass
model = CascadeForestRegressor()
with pytest.raises(AttributeError) as excinfo:
model.set_estimator([tmp_estimator()])
assert "The `predict` method" in str(excinfo.value)
with pytest.raises(AttributeError) as excinfo:
model.set_predictor(tmp_estimator())
assert "The `predict` method of the predictor" in str(excinfo.value)
records = []
for idx, random_state in enumerate(random_states):
msg = "Currently processing {} with trial {}..."
print(msg.format(dataset, idx))
model = CascadeForestRegressor(
n_bins=n_bins,
bin_subsample=bin_subsample,
max_layers=max_layers,
criterion=criterion,
n_estimators=n_estimators,
n_trees=n_trees,
max_depth=max_depth,
min_samples_leaf=min_samples_leaf,
use_predictor=use_predictor,
predictor=predictor,
n_tolerant_rounds=n_tolerant_rounds,
partial_mode=partial_mode,
delta=delta,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
)
tic = time.time()
model.fit(X_train, y_train)
toc = time.time()
training_time = toc - tic
tic = time.time()
def test_model_workflow_in_memory():
"""Run the workflow of deep forest with in-memory mode."""
case_kwargs = copy.deepcopy(kwargs)
case_kwargs.update({"partial_mode": False})
model = CascadeForestRegressor(**case_kwargs)
model.fit(X_train, y_train)
# Predictions before saving
y_pred_before = model.predict(X_test).astype(np.float32)
# Save and Reload
model.save(save_dir)
model = CascadeForestRegressor(**case_kwargs)
model.load(save_dir)
# Make sure the same predictions before and after model serialization
y_pred_after = model.predict(X_test).astype(np.float32)
assert_array_equal(y_pred_before, y_pred_after)
shutil.rmtree(save_dir)
def test_model_workflow_partial_mode():
"""Run the workflow of deep forest with a local buffer."""
case_kwargs = copy.deepcopy(kwargs)
case_kwargs.update({"partial_mode": True})
model = CascadeForestRegressor(**case_kwargs)
model.fit(X_train, y_train)
# Predictions before saving
y_pred_before = model.predict(X_test).astype(np.float32)
# Save and Reload
model.save(save_dir)
model = CascadeForestRegressor(**case_kwargs)
model.load(save_dir)
# Predictions after loading
y_pred_after = model.predict(X_test).astype(np.float32)
# Make sure the same predictions before and after model serialization
assert_array_equal(y_pred_before, y_pred_after)
model.clean() # clear the buffer
shutil.rmtree(save_dir)
def test_model_properties_after_fitting():
"""Check the model properties after fitting a deep forest model."""
model = CascadeForestRegressor(**toy_kwargs)
model.fit(X_train, y_train)
assert len(model) == model.n_layers_
assert model[0] is model._get_layer(0)
with pytest.raises(ValueError) as excinfo:
model._get_layer(model.n_layers_)
assert "The layer index should be in the range" in str(excinfo.value)
with pytest.raises(RuntimeError) as excinfo:
model._set_layer(0, None)
assert "already exists in the internal container" in str(excinfo.value)
with pytest.raises(ValueError) as excinfo:
model._get_binner(model.n_layers_ + 1)
assert "The binner index should be in the range" in str(excinfo.value)
with pytest.raises(RuntimeError) as excinfo:
model._set_binner(0, None)
assert "already exists in the internal container" in str(excinfo.value)
def test_regressor_custom_cascade_layer_workflow_in_memory(y_train):
model = CascadeForestRegressor()
n_estimators = 4
estimators = [DecisionTreeRegressor() for _ in range(n_estimators)]
model.set_estimator(estimators) # set custom base estimators
predictor = DecisionTreeRegressor()
model.set_predictor(predictor)
model.fit(X_train_reg, y_train)
y_pred_before = model.predict(X_test_reg)
# Save and Reload
model.save(save_dir)
model = CascadeForestRegressor()
model.load(save_dir)
# Predictions after loading
y_pred_after = model.predict(X_test_reg)
# Make sure the same predictions before and after model serialization
assert_array_equal(y_pred_before, y_pred_after)
assert (model.get_estimator(0, 0, "custom") is
model._get_layer(0).estimators_["0-0-custom"].estimator_)
model.clean() # clear the buffer
shutil.rmtree(save_dir)
