def test_quantile_attributes():
for est in estimators:
est.fit(X_train, y_train)
# If a sample is not present in a particular tree, that
# corresponding leaf is marked as -1.
assert_array_equal(
np.vstack(np.where(est.y_train_leaves_ == -1)),
np.vstack(np.where(est.y_weights_ == 0))
)
# Should sum up to number of leaf nodes.
assert_array_equal(
np.sum(est.y_weights_, axis=1),
[sum(tree.tree_.children_left == -1) for tree in est.estimators_]
)
n_est = est.n_estimators
est.set_params(bootstrap=False)
est.fit(X_train, y_train)
assert_array_equal(
np.sum(est.y_weights_, axis=1),
[sum(tree.tree_.children_left == -1) for tree in est.estimators_]
)
assert_true(np.all(est.y_train_leaves_ != -1))
def test_min_samples_split():
min_samples_split = 4
for curr_ensemble in ensembles:
ensemble = clone(curr_ensemble)
ensemble.set_params(min_samples_split=min_samples_split,
n_estimators=100)
ensemble.fit(X, y)
for est in ensemble.estimators_:
n_samples = est.tree_.n_node_samples
leaves = est.tree_.children_left == -1
assert_true(np.all(n_samples[~leaves] >= min_samples_split))
def check_decision_path(ensemble):
indicator, col_inds = ensemble.decision_path(X)
indices, indptr = indicator.indices, indicator.indptr
n_nodes = [est.tree_.node_count for est in ensemble.estimators_]
assert_equal(indicator.shape[0], X.shape[0])
assert_equal(indicator.shape[1], sum(n_nodes))
assert_array_equal(np.diff(col_inds), n_nodes)
# Check that all leaf nodes are in the decision path.
leaf_indices = ensemble.apply(X) + np.reshape(col_inds[:-1], (1, -1))
for sample_ind, curr_leaf in enumerate(leaf_indices):
sample_indices = indices[indptr[sample_ind]:indptr[sample_ind + 1]]
assert_true(np.all(np.in1d(curr_leaf, sample_indices)))
def test_tree_forest_equivalence():
"""
Test that a DecisionTree and RandomForest give equal quantile
predictions when bootstrap is set to False.
"""
rfqr = RandomForestQuantileRegressor(
random_state=0, bootstrap=False, max_depth=2)
rfqr.fit(X_train, y_train)
dtqr = DecisionTreeQuantileRegressor(random_state=0, max_depth=2)
dtqr.fit(X_train, y_train)
assert_true(np.all(rfqr.y_train_leaves_ == dtqr.y_train_leaves_))
assert_array_almost_equal(
rfqr.predict(X_test, quantile=10),
dtqr.predict(X_test, quantile=10), 5)
def test_base_forest_quantile():
"""
Test that the base estimators belong to the correct class.
"""
rng = np.random.RandomState(0)
X = rng.randn(10, 1)
y = np.linspace(0.0, 100.0, 10)
rfqr = RandomForestQuantileRegressor(random_state=0, max_depth=1)
rfqr.fit(X, y)
for est in rfqr.estimators_:
assert_true(isinstance(est, DecisionTreeQuantileRegressor))
etqr = ExtraTreesQuantileRegressor(random_state=0, max_depth=1)
etqr.fit(X, y)
for est in etqr.estimators_:
assert_true(isinstance(est, ExtraTreeQuantileRegressor))
def test_tree_identical_labels():
rng = np.random.RandomState(0)
for est in estimators:
X = rng.randn(100, 5)
y = np.ones(100)
c_est = clone(est)
c_est.set_params(min_samples_split=2, max_depth=None)
c_est.fit(X, y)
assert_equal(c_est.tree_.n_node_samples, [100])
if isinstance(c_est, ClassifierMixin):
assert_equal(c_est.tree_.value, [[[100]]])
else:
assert_equal(c_est.tree_.value, [[[1.0]]])
X = np.reshape(np.linspace(0.0, 1.0, 100), (-1, 1))
y = np.array([0.0] * 50 + [1.0] * 50)
c_est.fit(X, y)
leaf_ids = c_est.tree_.children_left == -1
assert_true(np.any(c_est.tree_.n_node_samples[leaf_ids] > 2))
def test_tree_identical_labels():
rng = np.random.RandomState(0)
for ensemble in ensembles:
X = rng.randn(100, 5)
y = np.ones(100)
ensemble.fit(X, y)
for est in ensemble.estimators_:
assert_equal(est.tree_.n_node_samples, [100])
if isinstance(est, ClassifierMixin):
assert_equal(est.tree_.value, [[[100]]])
else:
assert_equal(est.tree_.value, [[[1.0]]])
X = np.reshape(np.linspace(0.0, 1.0, 100), (-1, 1))
y = np.array([0.0] * 50 + [1.0] * 50)
ensemble.fit(X, y)
for est in ensemble.estimators_:
leaf_ids = est.tree_.children_left == -1
assert_true(np.any(est.tree_.n_node_samples[leaf_ids] > 2))
def test_apply():
X_train, X_test, y_train, y_test = load_scaled_boston()
y_train = np.round(y_train)
for est in estimators:
est_clone = clone(est)
est_clone.fit(X_train, y_train)
train_leaves = est_clone.tree_.children_left[est_clone.apply(X_train)]
test_leaves = est_clone.tree_.children_left[est_clone.apply(X_test)]
assert_true(np.all(train_leaves == -1))
assert_true(np.all(test_leaves == -1))
est_clone.partial_fit(X_train, y_train)
train_leaves = est_clone.tree_.children_left[est_clone.apply(X_train)]
test_leaves = est_clone.tree_.children_left[est_clone.apply(X_test)]
assert_true(np.all(train_leaves == -1))
assert_true(np.all(test_leaves == -1))
def test_forest_attributes():
mr = MondrianForestRegressor(n_estimators=5, random_state=0)
mr.fit([[1, 2, 3], [4, 5, 6]], [1, 2])
assert_false(hasattr(mr, "classes_"))
assert_false(hasattr(mr, "n_classes_"))
mr.partial_fit([[1, 2, 3], [4, 5, 6]], [1, 2])
assert_false(hasattr(mr, "classes_"))
assert_false(hasattr(mr, "n_classes_"))
mr = MondrianForestClassifier(n_estimators=5, random_state=0)
mr.fit([[1, 2, 3], [4, 5, 6]], [1, 2])
assert_true(hasattr(mr, "classes_"))
assert_true(hasattr(mr, "n_classes_"))
mr = MondrianForestClassifier(n_estimators=5, random_state=0)
mr.partial_fit([[1, 2, 3], [4, 5, 6]], [1, 2])
assert_true(hasattr(mr, "classes_"))
assert_true(hasattr(mr, "n_classes_"))