def test_warm_start_smaller_n_estimators():
# Test if warm start'ed second fit with smaller n_estimators raises error.
X, y = make_hastie_10_2(n_samples=20, random_state=1)
clf = BaggingClassifier(n_estimators=5, warm_start=True)
clf.fit(X, y)
clf.set_params(n_estimators=4)
assert_raises(ValueError, clf.fit, X, y)
def test_oob_score_consistency():
# Make sure OOB scores are identical when random_state, estimator, and
# training data are fixed and fitting is done twice
X, y = make_hastie_10_2(n_samples=200, random_state=1)
bagging = BaggingClassifier(KNeighborsClassifier(),
max_samples=0.5,
max_features=0.5,
oob_score=True,
random_state=1)
assert bagging.fit(X, y).oob_score_ == bagging.fit(X, y).oob_score_
def test_oob_score_removed_on_warm_start():
X, y = make_hastie_10_2(n_samples=2000, random_state=1)
clf = BaggingClassifier(n_estimators=50, oob_score=True)
clf.fit(X, y)
clf.set_params(warm_start=True, oob_score=False, n_estimators=100)
clf.fit(X, y)
assert_raises(AttributeError, getattr, clf, "oob_score_")
def test_max_samples_consistency():
# Make sure validated max_samples and original max_samples are identical
# when valid integer max_samples supplied by user
max_samples = 100
X, y = make_hastie_10_2(n_samples=2 * max_samples, random_state=1)
bagging = BaggingClassifier(KNeighborsClassifier(),
max_samples=max_samples,
max_features=0.5,
random_state=1)
bagging.fit(X, y)
assert bagging._max_samples == max_samples
def test_min_impurity_decrease():
X, y = datasets.make_hastie_10_2(n_samples=100, random_state=1)
all_estimators = [
RandomForestClassifier, RandomForestRegressor, ExtraTreesClassifier,
ExtraTreesRegressor
]
for Estimator in all_estimators:
est = Estimator(min_impurity_decrease=0.1)
est.fit(X, y)
for tree in est.estimators_:
# Simply check if the parameter is passed on correctly. Tree tests
# will suffice for the actual working of this param
assert tree.min_impurity_decrease == 0.1
def test_min_impurity_split():
# Test if min_impurity_split of base estimators is set
# Regression test for #8006
X, y = datasets.make_hastie_10_2(n_samples=100, random_state=1)
all_estimators = [
RandomForestClassifier, RandomForestRegressor, ExtraTreesClassifier,
ExtraTreesRegressor
]
for Estimator in all_estimators:
est = Estimator(min_impurity_split=0.1)
est = assert_warns_message(FutureWarning, "min_impurity_decrease",
est.fit, X, y)
for tree in est.estimators_:
assert tree.min_impurity_split == 0.1
def test_warm_start_equal_n_estimators():
# Test that nothing happens when fitting without increasing n_estimators
X, y = make_hastie_10_2(n_samples=20, random_state=1)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=43)
clf = BaggingClassifier(n_estimators=5, warm_start=True, random_state=83)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
# modify X to nonsense values, this should not change anything
X_train += 1.
assert_warns_message(
UserWarning,
"Warm-start fitting without increasing n_estimators does not", clf.fit,
X_train, y_train)
assert_array_equal(y_pred, clf.predict(X_test))
def test_warm_start_equivalence():
# warm started classifier with 5+5 estimators should be equivalent to
# one classifier with 10 estimators
X, y = make_hastie_10_2(n_samples=20, random_state=1)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=43)
clf_ws = BaggingClassifier(n_estimators=5,
warm_start=True,
random_state=3141)
clf_ws.fit(X_train, y_train)
clf_ws.set_params(n_estimators=10)
clf_ws.fit(X_train, y_train)
y1 = clf_ws.predict(X_test)
clf = BaggingClassifier(n_estimators=10,
warm_start=False,
random_state=3141)
clf.fit(X_train, y_train)
y2 = clf.predict(X_test)
assert_array_almost_equal(y1, y2)
def test_warm_start(random_state=42):
# Test if fitting incrementally with warm start gives a forest of the
# right size and the same results as a normal fit.
X, y = make_hastie_10_2(n_samples=20, random_state=1)
clf_ws = None
for n_estimators in [5, 10]:
if clf_ws is None:
clf_ws = BaggingClassifier(n_estimators=n_estimators,
random_state=random_state,
warm_start=True)
else:
clf_ws.set_params(n_estimators=n_estimators)
clf_ws.fit(X, y)
assert len(clf_ws) == n_estimators
clf_no_ws = BaggingClassifier(n_estimators=10,
random_state=random_state,
warm_start=False)
clf_no_ws.fit(X, y)
assert (set([tree.random_state for tree in clf_ws
]) == set([tree.random_state for tree in clf_no_ws]))
def test_estimators_samples():
# Check that format of estimators_samples_ is correct and that results
# generated at fit time can be identically reproduced at a later time
# using data saved in object attributes.
X, y = make_hastie_10_2(n_samples=200, random_state=1)
bagging = BaggingClassifier(LogisticRegression(),
max_samples=0.5,
max_features=0.5,
random_state=1,
bootstrap=False)
bagging.fit(X, y)
# Get relevant attributes
estimators_samples = bagging.estimators_samples_
estimators_features = bagging.estimators_features_
estimators = bagging.estimators_
# Test for correct formatting
assert len(estimators_samples) == len(estimators)
assert len(estimators_samples[0]) == len(X) // 2
assert estimators_samples[0].dtype.kind == 'i'
# Re-fit single estimator to test for consistent sampling
estimator_index = 0
estimator_samples = estimators_samples[estimator_index]
estimator_features = estimators_features[estimator_index]
estimator = estimators[estimator_index]
X_train = (X[estimator_samples])[:, estimator_features]
y_train = y[estimator_samples]
orig_coefs = estimator.coef_
estimator.fit(X_train, y_train)
new_coefs = estimator.coef_
assert_array_almost_equal(orig_coefs, new_coefs)
def test_warm_start_with_oob_score_fails():
# Check using oob_score and warm_start simultaneously fails
X, y = make_hastie_10_2(n_samples=20, random_state=1)
clf = BaggingClassifier(n_estimators=5, warm_start=True, oob_score=True)
assert_raises(ValueError, clf.fit, X, y)
def test_make_hastie_10_2():
X, y = make_hastie_10_2(n_samples=100, random_state=0)
assert X.shape == (100, 10), "X shape mismatch"
assert y.shape == (100, ), "y shape mismatch"
assert np.unique(y).shape == (2, ), "Unexpected number of classes"
# and randomly permute it
iris = datasets.load_iris()
rng = check_random_state(0)
perm = rng.permutation(iris.target.size)
iris.data = iris.data[perm]
iris.target = iris.target[perm]
# also load the boston dataset
# and randomly permute it
boston = datasets.load_boston()
perm = rng.permutation(boston.target.size)
boston.data = boston.data[perm]
boston.target = boston.target[perm]
# also make a hastie_10_2 dataset
hastie_X, hastie_y = datasets.make_hastie_10_2(n_samples=20, random_state=1)
hastie_X = hastie_X.astype(np.float32)
# Get the default backend in joblib to test parallelism and interaction with
# different backends
DEFAULT_JOBLIB_BACKEND = joblib.parallel.get_active_backend()[0].__class__
FOREST_CLASSIFIERS = {
"ExtraTreesClassifier": ExtraTreesClassifier,
"RandomForestClassifier": RandomForestClassifier,
}
FOREST_REGRESSORS = {
"ExtraTreesRegressor": ExtraTreesRegressor,
"RandomForestRegressor": RandomForestRegressor,
}