def test_partial_dependence_helpers(est, method, target_feature):
# Check that what is returned by _partial_dependence_brute or
# _partial_dependence_recursion is equivalent to manually setting a target
# feature to a given value, and computing the average prediction over all
# samples.
# This also checks that the brute and recursion methods give the same
# output.
# Note that even on the trainset, the brute and the recursion methods
# aren't always strictly equivalent, in particular when the slow method
# generates unrealistic samples that have low mass in the joint
# distribution of the input features, and when some of the features are
# dependent. Hence the high tolerance on the checks.
X, y = make_regression(random_state=0, n_features=5, n_informative=5)
# The 'init' estimator for GBDT (here the average prediction) isn't taken
# into account with the recursion method, for technical reasons. We set
# the mean to 0 to that this 'bug' doesn't have any effect.
y = y - y.mean()
est.fit(X, y)
# target feature will be set to .5 and then to 123
features = np.array([target_feature], dtype=np.int32)
grid = np.array([[.5], [123]])
if method == 'brute':
pdp, predictions = _partial_dependence_brute(est,
grid,
features,
X,
response_method='auto')
else:
pdp = _partial_dependence_recursion(est, grid, features)
mean_predictions = []
for val in (.5, 123):
X_ = X.copy()
X_[:, target_feature] = val
mean_predictions.append(est.predict(X_).mean())
pdp = pdp[0] # (shape is (1, 2) so make it (2,))
# allow for greater margin for error with recursion method
rtol = 1e-1 if method == 'recursion' else 1e-3
assert np.allclose(pdp, mean_predictions, rtol=rtol)
def test_recursion_decision_tree_vs_forest_and_gbdt(seed):
# Make sure that the recursion method gives the same results on a
# DecisionTreeRegressor and a GradientBoostingRegressor or a
# RandomForestRegressor with 1 tree and equivalent parameters.
rng = np.random.RandomState(seed)
# Purely random dataset to avoid correlated features
n_samples = 1000
n_features = 5
X = rng.randn(n_samples, n_features)
y = rng.randn(n_samples) * 10
# The 'init' estimator for GBDT (here the average prediction) isn't taken
# into account with the recursion method, for technical reasons. We set
# the mean to 0 to that this 'bug' doesn't have any effect.
y = y - y.mean()
# set max_depth not too high to avoid splits with same gain but different
# features
max_depth = 5
tree_seed = 0
forest = RandomForestRegressor(n_estimators=1,
max_features=None,
bootstrap=False,
max_depth=max_depth,
random_state=tree_seed)
# The forest will use ensemble.base._set_random_states to set the
# random_state of the tree sub-estimator. We simulate this here to have
# equivalent estimators.
equiv_random_state = check_random_state(tree_seed).randint(
np.iinfo(np.int32).max)
gbdt = GradientBoostingRegressor(n_estimators=1,
learning_rate=1,
criterion='mse',
max_depth=max_depth,
random_state=equiv_random_state)
tree = DecisionTreeRegressor(max_depth=max_depth,
random_state=equiv_random_state)
forest.fit(X, y)
gbdt.fit(X, y)
tree.fit(X, y)
# sanity check: if the trees aren't the same, the PD values won't be equal
try:
assert_is_subtree(tree.tree_, gbdt[0, 0].tree_)
assert_is_subtree(tree.tree_, forest[0].tree_)
except AssertionError:
# For some reason the trees aren't exactly equal on 32bits, so the PDs
# cannot be equal either. See
# https://github.com/scikit-learn/scikit-learn/issues/8853
assert _IS_32BIT, "this should only fail on 32 bit platforms"
return
grid = rng.randn(50).reshape(-1, 1)
for f in range(n_features):
features = np.array([f], dtype=np.int32)
pdp_forest = _partial_dependence_recursion(forest, grid, features)
pdp_gbdt = _partial_dependence_recursion(gbdt, grid, features)
pdp_tree = _partial_dependence_recursion(tree, grid, features)
np.testing.assert_allclose(pdp_gbdt, pdp_tree)
np.testing.assert_allclose(pdp_forest, pdp_tree)
