def test_bagging_classifier_with_missing_inputs():
# Check that BaggingClassifier can accept X with missing/infinite data
X = np.array([
[1, 3, 5],
[2, None, 6],
[2, np.nan, 6],
[2, np.inf, 6],
[2, np.NINF, 6],
])
y = np.array([3, 6, 6, 6, 6])
classifier = DecisionTreeClassifier()
pipeline = make_pipeline(FunctionTransformer(replace), classifier)
pipeline.fit(X, y).predict(X)
bagging_classifier = BaggingClassifier(pipeline)
bagging_classifier.fit(X, y)
y_hat = bagging_classifier.predict(X)
assert y.shape == y_hat.shape
bagging_classifier.predict_log_proba(X)
bagging_classifier.predict_proba(X)
# Verify that exceptions can be raised by wrapper classifier
classifier = DecisionTreeClassifier()
pipeline = make_pipeline(classifier)
assert_raises(ValueError, pipeline.fit, X, y)
bagging_classifier = BaggingClassifier(pipeline)
assert_raises(ValueError, bagging_classifier.fit, X, y)
def test_plot_roc_curve_error_non_binary(pyplot, data):
X, y = data
clf = DecisionTreeClassifier()
clf.fit(X, y)
msg = "DecisionTreeClassifier should be a binary classifier"
with pytest.raises(ValueError, match=msg):
plot_roc_curve(clf, X, y)
def test_deprecated_scorer():
X, y = make_blobs(random_state=0, centers=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)
deprecated_scorer = get_scorer('brier_score_loss')
with pytest.warns(FutureWarning):
deprecated_scorer(clf, X_test, y_test)
def test_ovr_pipeline():
# Test with pipeline of length one
# This test is needed because the multiclass estimators may fail to detect
# the presence of predict_proba or decision_function.
clf = Pipeline([("tree", DecisionTreeClassifier())])
ovr_pipe = OneVsRestClassifier(clf)
ovr_pipe.fit(iris.data, iris.target)
ovr = OneVsRestClassifier(DecisionTreeClassifier())
ovr.fit(iris.data, iris.target)
assert_array_equal(ovr.predict(iris.data), ovr_pipe.predict(iris.data))
def test_pickle_version_warning_is_not_raised_with_matching_version():
iris = datasets.load_iris()
tree = DecisionTreeClassifier().fit(iris.data, iris.target)
tree_pickle = pickle.dumps(tree)
assert b"version" in tree_pickle
tree_restored = assert_no_warnings(pickle.loads, tree_pickle)
# test that we can predict with the restored decision tree classifier
score_of_original = tree.score(iris.data, iris.target)
score_of_restored = tree_restored.score(iris.data, iris.target)
assert score_of_original == score_of_restored
def test_parallel_classification():
# Check parallel classification.
rng = check_random_state(0)
# Classification
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
random_state=rng)
ensemble = BaggingClassifier(DecisionTreeClassifier(),
n_jobs=3,
random_state=0).fit(X_train, y_train)
# predict_proba
ensemble.set_params(n_jobs=1)
y1 = ensemble.predict_proba(X_test)
ensemble.set_params(n_jobs=2)
y2 = ensemble.predict_proba(X_test)
assert_array_almost_equal(y1, y2)
ensemble = BaggingClassifier(DecisionTreeClassifier(),
n_jobs=1,
random_state=0).fit(X_train, y_train)
y3 = ensemble.predict_proba(X_test)
assert_array_almost_equal(y1, y3)
# decision_function
ensemble = BaggingClassifier(SVC(decision_function_shape='ovr'),
n_jobs=3,
random_state=0).fit(X_train, y_train)
ensemble.set_params(n_jobs=1)
decisions1 = ensemble.decision_function(X_test)
ensemble.set_params(n_jobs=2)
decisions2 = ensemble.decision_function(X_test)
assert_array_almost_equal(decisions1, decisions2)
X_err = np.hstack((X_test, np.zeros((X_test.shape[0], 1))))
assert_raise_message(
ValueError, "Number of features of the model "
"must match the input. Model n_features is {0} "
"and input n_features is {1} "
"".format(X_test.shape[1], X_err.shape[1]), ensemble.decision_function,
X_err)
ensemble = BaggingClassifier(SVC(decision_function_shape='ovr'),
n_jobs=1,
random_state=0).fit(X_train, y_train)
decisions3 = ensemble.decision_function(X_test)
assert_array_almost_equal(decisions1, decisions3)
def test_thresholded_scorers():
# Test scorers that take thresholds.
X, y = make_blobs(random_state=0, centers=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = LogisticRegression(random_state=0)
clf.fit(X_train, y_train)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, clf.decision_function(X_test))
score3 = roc_auc_score(y_test, clf.predict_proba(X_test)[:, 1])
assert_almost_equal(score1, score2)
assert_almost_equal(score1, score3)
logscore = get_scorer('neg_log_loss')(clf, X_test, y_test)
logloss = log_loss(y_test, clf.predict_proba(X_test))
assert_almost_equal(-logscore, logloss)
# same for an estimator without decision_function
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, clf.predict_proba(X_test)[:, 1])
assert_almost_equal(score1, score2)
# test with a regressor (no decision_function)
reg = DecisionTreeRegressor()
reg.fit(X_train, y_train)
score1 = get_scorer('roc_auc')(reg, X_test, y_test)
score2 = roc_auc_score(y_test, reg.predict(X_test))
assert_almost_equal(score1, score2)
# Test that an exception is raised on more than two classes
X, y = make_blobs(random_state=0, centers=3)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf.fit(X_train, y_train)
with pytest.raises(ValueError, match="multiclass format is not supported"):
get_scorer('roc_auc')(clf, X_test, y_test)
# test error is raised with a single class present in model
# (predict_proba shape is not suitable for binary auc)
X, y = make_blobs(random_state=0, centers=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = DecisionTreeClassifier()
clf.fit(X_train, np.zeros_like(y_train))
with pytest.raises(ValueError, match="need classifier with two classes"):
get_scorer('roc_auc')(clf, X_test, y_test)
# for proba scorers
with pytest.raises(ValueError, match="need classifier with two classes"):
get_scorer('neg_log_loss')(clf, X_test, y_test)
def test_export_text_errors():
clf = DecisionTreeClassifier(max_depth=2, random_state=0)
clf.fit(X, y)
err_msg = "max_depth bust be >= 0, given -1"
with pytest.raises(ValueError, match=err_msg):
export_text(clf, max_depth=-1)
err_msg = "feature_names must contain 2 elements, got 1"
with pytest.raises(ValueError, match=err_msg):
export_text(clf, feature_names=['a'])
err_msg = "decimals must be >= 0, given -1"
with pytest.raises(ValueError, match=err_msg):
export_text(clf, decimals=-1)
err_msg = "spacing must be > 0, given 0"
with pytest.raises(ValueError, match=err_msg):
export_text(clf, spacing=0)
def test_classification():
# Check classification for various parameter settings.
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
random_state=rng)
grid = ParameterGrid({
"max_samples": [0.5, 1.0],
"max_features": [1, 2, 4],
"bootstrap": [True, False],
"bootstrap_features": [True, False]
})
for base_estimator in [
None,
DummyClassifier(),
Perceptron(),
DecisionTreeClassifier(),
KNeighborsClassifier(),
SVC()
]:
for params in grid:
BaggingClassifier(base_estimator=base_estimator,
random_state=rng,
**params).fit(X_train, y_train).predict(X_test)
def test_error():
# Test that it gives proper exception on deficient input.
X, y = iris.data, iris.target
base = DecisionTreeClassifier()
# Test max_samples
assert_raises(ValueError,
BaggingClassifier(base, max_samples=-1).fit, X, y)
assert_raises(ValueError,
BaggingClassifier(base, max_samples=0.0).fit, X, y)
assert_raises(ValueError,
BaggingClassifier(base, max_samples=2.0).fit, X, y)
assert_raises(ValueError,
BaggingClassifier(base, max_samples=1000).fit, X, y)
assert_raises(ValueError,
BaggingClassifier(base, max_samples="foobar").fit, X, y)
# Test max_features
assert_raises(ValueError,
BaggingClassifier(base, max_features=-1).fit, X, y)
assert_raises(ValueError,
BaggingClassifier(base, max_features=0.0).fit, X, y)
assert_raises(ValueError,
BaggingClassifier(base, max_features=2.0).fit, X, y)
assert_raises(ValueError,
BaggingClassifier(base, max_features=5).fit, X, y)
assert_raises(ValueError,
BaggingClassifier(base, max_features="foobar").fit, X, y)
# Test support of decision_function
assert not hasattr(BaggingClassifier(base).fit(X, y), 'decision_function')
def test_oob_score_classification():
# Check that oob prediction is a good estimation of the generalization
# error.
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
random_state=rng)
for base_estimator in [DecisionTreeClassifier(), SVC()]:
clf = BaggingClassifier(base_estimator=base_estimator,
n_estimators=100,
bootstrap=True,
oob_score=True,
random_state=rng).fit(X_train, y_train)
test_score = clf.score(X_test, y_test)
assert abs(test_score - clf.oob_score_) < 0.1
# Test with few estimators
assert_warns(
UserWarning,
BaggingClassifier(base_estimator=base_estimator,
n_estimators=1,
bootstrap=True,
oob_score=True,
random_state=rng).fit, X_train, y_train)
def test_probability():
# Predict probabilities.
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
random_state=rng)
with np.errstate(divide="ignore", invalid="ignore"):
# Normal case
ensemble = BaggingClassifier(base_estimator=DecisionTreeClassifier(),
random_state=rng).fit(X_train, y_train)
assert_array_almost_equal(
np.sum(ensemble.predict_proba(X_test), axis=1),
np.ones(len(X_test)))
assert_array_almost_equal(ensemble.predict_proba(X_test),
np.exp(ensemble.predict_log_proba(X_test)))
# Degenerate case, where some classes are missing
ensemble = BaggingClassifier(base_estimator=LogisticRegression(),
random_state=rng,
max_samples=5).fit(X_train, y_train)
assert_array_almost_equal(
np.sum(ensemble.predict_proba(X_test), axis=1),
np.ones(len(X_test)))
assert_array_almost_equal(ensemble.predict_proba(X_test),
np.exp(ensemble.predict_log_proba(X_test)))
def test_plot_tree_gini(pyplot):
# mostly smoke tests
# Check correctness of export_graphviz for criterion = gini
clf = DecisionTreeClassifier(max_depth=3,
min_samples_split=2,
criterion="gini",
random_state=2)
clf.fit(X, y)
# Test export code
feature_names = ['first feat', 'sepal_width']
nodes = plot_tree(clf, feature_names=feature_names)
assert len(nodes) == 3
assert nodes[0].get_text() == ("first feat <= 0.0\ngini = 0.5\n"
"samples = 6\nvalue = [3, 3]")
assert nodes[1].get_text() == "gini = 0.0\nsamples = 3\nvalue = [3, 0]"
assert nodes[2].get_text() == "gini = 0.0\nsamples = 3\nvalue = [0, 3]"
def test_ovr_coef_exceptions():
# Not fitted exception!
ovr = OneVsRestClassifier(LinearSVC(random_state=0))
# lambda is needed because we don't want coef_ to be evaluated right away
assert_raises(ValueError, lambda x: ovr.coef_, None)
# Doesn't have coef_ exception!
ovr = OneVsRestClassifier(DecisionTreeClassifier())
ovr.fit(iris.data, iris.target)
assert_raises(AttributeError, lambda x: ovr.coef_, None)
def test_raises_on_score_list():
# Test that when a list of scores is returned, we raise proper errors.
X, y = make_blobs(random_state=0)
f1_scorer_no_average = make_scorer(f1_score, average=None)
clf = DecisionTreeClassifier()
with pytest.raises(ValueError):
cross_val_score(clf, X, y, scoring=f1_scorer_no_average)
grid_search = GridSearchCV(clf, scoring=f1_scorer_no_average,
param_grid={'max_depth': [1, 2]})
with pytest.raises(ValueError):
grid_search.fit(X, y)
def test_graphviz_errors():
# Check for errors of export_graphviz
clf = DecisionTreeClassifier(max_depth=3, min_samples_split=2)
# Check not-fitted decision tree error
out = StringIO()
with pytest.raises(NotFittedError):
export_graphviz(clf, out)
clf.fit(X, y)
# Check if it errors when length of feature_names
# mismatches with number of features
message = ("Length of feature_names, "
"1 does not match number of features, 2")
with pytest.raises(ValueError, match=message):
export_graphviz(clf, None, feature_names=["a"])
message = ("Length of feature_names, "
"3 does not match number of features, 2")
with pytest.raises(ValueError, match=message):
export_graphviz(clf, None, feature_names=["a", "b", "c"])
# Check error when argument is not an estimator
message = "is not an estimator instance"
with pytest.raises(TypeError, match=message):
export_graphviz(clf.fit(X, y).tree_)
# Check class_names error
out = StringIO()
with pytest.raises(IndexError):
export_graphviz(clf, out, class_names=[])
# Check precision error
out = StringIO()
with pytest.raises(ValueError, match="should be greater or equal"):
export_graphviz(clf, out, precision=-1)
with pytest.raises(ValueError, match="should be an integer"):
export_graphviz(clf, out, precision="1")
def _make_estimators(X_train, y_train, y_ml_train):
# Make estimators that make sense to test various scoring methods
sensible_regr = DecisionTreeRegressor(random_state=0)
# some of the regressions scorers require strictly positive input.
sensible_regr.fit(X_train, y_train + 1)
sensible_clf = DecisionTreeClassifier(random_state=0)
sensible_clf.fit(X_train, y_train)
sensible_ml_clf = DecisionTreeClassifier(random_state=0)
sensible_ml_clf.fit(X_train, y_ml_train)
return dict(
[(name, sensible_regr) for name in REGRESSION_SCORERS] +
[(name, sensible_clf) for name in CLF_SCORERS] +
[(name, sensible_clf) for name in CLUSTER_SCORERS] +
[(name, sensible_ml_clf) for name in MULTILABEL_ONLY_SCORERS]
)
def test_multimetric_scorer_sanity_check():
# scoring dictionary returned is the same as calling each scorer separately
scorers = {'a1': 'accuracy', 'a2': 'accuracy',
'll1': 'neg_log_loss', 'll2': 'neg_log_loss',
'ra1': 'roc_auc', 'ra2': 'roc_auc'}
X, y = make_classification(random_state=0)
clf = DecisionTreeClassifier()
clf.fit(X, y)
scorer_dict, _ = _check_multimetric_scoring(clf, scorers)
multi_scorer = _MultimetricScorer(**scorer_dict)
result = multi_scorer(clf, X, y)
separate_scores = {
name: get_scorer(name)(clf, X, y)
for name in ['accuracy', 'neg_log_loss', 'roc_auc']}
for key, value in result.items():
score_name = scorers[key]
assert_allclose(value, separate_scores[score_name])
def test_errors(pyplot):
X, y_multiclass = make_classification(n_classes=3,
n_samples=50,
n_informative=3,
random_state=0)
y_binary = y_multiclass == 0
# Unfitted classifer
binary_clf = DecisionTreeClassifier()
with pytest.raises(NotFittedError):
plot_precision_recall_curve(binary_clf, X, y_binary)
binary_clf.fit(X, y_binary)
multi_clf = DecisionTreeClassifier().fit(X, y_multiclass)
# Fitted multiclass classifier with binary data
msg = "DecisionTreeClassifier should be a binary classifier"
with pytest.raises(ValueError, match=msg):
plot_precision_recall_curve(multi_clf, X, y_binary)
reg = DecisionTreeRegressor().fit(X, y_multiclass)
msg = "DecisionTreeRegressor should be a binary classifier"
with pytest.raises(ValueError, match=msg):
plot_precision_recall_curve(reg, X, y_binary)
def test_gridsearch():
# Check that base trees can be grid-searched.
# AdaBoost classification
boost = AdaBoostClassifier(base_estimator=DecisionTreeClassifier())
parameters = {
'n_estimators': (1, 2),
'base_estimator__max_depth': (1, 2),
'algorithm': ('SAMME', 'SAMME.R')
}
clf = GridSearchCV(boost, parameters)
clf.fit(iris.data, iris.target)
# AdaBoost regression
boost = AdaBoostRegressor(base_estimator=DecisionTreeRegressor(),
random_state=0)
parameters = {'n_estimators': (1, 2), 'base_estimator__max_depth': (1, 2)}
clf = GridSearchCV(boost, parameters)
clf.fit(boston.data, boston.target)
def test_base_estimator():
# Check base_estimator and its default values.
rng = check_random_state(0)
# Classification
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
random_state=rng)
ensemble = BaggingClassifier(None, n_jobs=3,
random_state=0).fit(X_train, y_train)
assert isinstance(ensemble.base_estimator_, DecisionTreeClassifier)
ensemble = BaggingClassifier(DecisionTreeClassifier(),
n_jobs=3,
random_state=0).fit(X_train, y_train)
assert isinstance(ensemble.base_estimator_, DecisionTreeClassifier)
ensemble = BaggingClassifier(Perceptron(), n_jobs=3,
random_state=0).fit(X_train, y_train)
assert isinstance(ensemble.base_estimator_, Perceptron)
# Regression
X_train, X_test, y_train, y_test = train_test_split(boston.data,
boston.target,
random_state=rng)
ensemble = BaggingRegressor(None, n_jobs=3,
random_state=0).fit(X_train, y_train)
assert isinstance(ensemble.base_estimator_, DecisionTreeRegressor)
ensemble = BaggingRegressor(DecisionTreeRegressor(),
n_jobs=3,
random_state=0).fit(X_train, y_train)
assert isinstance(ensemble.base_estimator_, DecisionTreeRegressor)
ensemble = BaggingRegressor(SVR(), n_jobs=3,
random_state=0).fit(X_train, y_train)
assert isinstance(ensemble.base_estimator_, SVR)
def test_precision():
rng_reg = RandomState(2)
rng_clf = RandomState(8)
for X, y, clf in zip(
(rng_reg.random_sample((5, 2)),
rng_clf.random_sample((1000, 4))),
(rng_reg.random_sample((5, )),
rng_clf.randint(2, size=(1000, ))),
(DecisionTreeRegressor(criterion="friedman_mse", random_state=0,
max_depth=1),
DecisionTreeClassifier(max_depth=1, random_state=0))):
clf.fit(X, y)
for precision in (4, 3):
dot_data = export_graphviz(clf, out_file=None, precision=precision,
proportion=True)
# With the current random state, the impurity and the threshold
# will have the number of precision set in the export_graphviz
# function. We will check the number of precision with a strict
# equality. The value reported will have only 2 precision and
# therefore, only a less equal comparison will be done.
# check value
for finding in finditer(r"value = \d+\.\d+", dot_data):
assert (
len(search(r"\.\d+", finding.group()).group()) <=
precision + 1)
# check impurity
if is_classifier(clf):
pattern = r"gini = \d+\.\d+"
else:
pattern = r"friedman_mse = \d+\.\d+"
# check impurity
for finding in finditer(pattern, dot_data):
assert (len(search(r"\.\d+", finding.group()).group()) ==
precision + 1)
# check threshold
for finding in finditer(r"<= \d+\.\d+", dot_data):
assert (len(search(r"\.\d+", finding.group()).group()) ==
precision + 1)
def test_score_sample_weight():
rng = np.random.RandomState(0)
# test both ClassifierMixin and RegressorMixin
estimators = [
DecisionTreeClassifier(max_depth=2),
DecisionTreeRegressor(max_depth=2)
]
sets = [datasets.load_iris(), datasets.load_boston()]
for est, ds in zip(estimators, sets):
est.fit(ds.data, ds.target)
# generate random sample weights
sample_weight = rng.randint(1, 10, size=len(ds.target))
# check that the score with and without sample weights are different
assert (est.score(ds.data, ds.target) != est.score(
ds.data, ds.target,
sample_weight=sample_weight)), ("Unweighted and weighted scores "
"are unexpectedly equal")
def test_thresholded_scorers_multilabel_indicator_data():
# Test that the scorer work with multilabel-indicator format
# for multilabel and multi-output multi-class classifier
X, y = make_multilabel_classification(allow_unlabeled=False,
random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
# Multi-output multi-class predict_proba
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)
y_proba = clf.predict_proba(X_test)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, np.vstack([p[:, -1] for p in y_proba]).T)
assert_almost_equal(score1, score2)
# Multi-output multi-class decision_function
# TODO Is there any yet?
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)
clf._predict_proba = clf.predict_proba
clf.predict_proba = None
clf.decision_function = lambda X: [p[:, 1] for p in clf._predict_proba(X)]
y_proba = clf.decision_function(X_test)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, np.vstack([p for p in y_proba]).T)
assert_almost_equal(score1, score2)
# Multilabel predict_proba
clf = OneVsRestClassifier(DecisionTreeClassifier())
clf.fit(X_train, y_train)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, clf.predict_proba(X_test))
assert_almost_equal(score1, score2)
# Multilabel decision function
clf = OneVsRestClassifier(LinearSVC(random_state=0))
clf.fit(X_train, y_train)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, clf.decision_function(X_test))
assert_almost_equal(score1, score2)
def test_bagging_with_pipeline():
estimator = BaggingClassifier(make_pipeline(SelectKBest(k=1),
DecisionTreeClassifier()),
max_features=2)
estimator.fit(iris.data, iris.target)
assert isinstance(estimator[0].steps[-1][1].random_state, int)
def test_export_text():
clf = DecisionTreeClassifier(max_depth=2, random_state=0)
clf.fit(X, y)
expected_report = dedent("""
|--- feature_1 <= 0.00
| |--- class: -1
|--- feature_1 > 0.00
| |--- class: 1
""").lstrip()
assert export_text(clf) == expected_report
# testing that leaves at level 1 are not truncated
assert export_text(clf, max_depth=0) == expected_report
# testing that the rest of the tree is truncated
assert export_text(clf, max_depth=10) == expected_report
expected_report = dedent("""
|--- b <= 0.00
| |--- class: -1
|--- b > 0.00
| |--- class: 1
""").lstrip()
assert export_text(clf, feature_names=['a', 'b']) == expected_report
expected_report = dedent("""
|--- feature_1 <= 0.00
| |--- weights: [3.00, 0.00] class: -1
|--- feature_1 > 0.00
| |--- weights: [0.00, 3.00] class: 1
""").lstrip()
assert export_text(clf, show_weights=True) == expected_report
expected_report = dedent("""
|- feature_1 <= 0.00
| |- class: -1
|- feature_1 > 0.00
| |- class: 1
""").lstrip()
assert export_text(clf, spacing=1) == expected_report
X_l = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [-1, 1]]
y_l = [-1, -1, -1, 1, 1, 1, 2]
clf = DecisionTreeClassifier(max_depth=4, random_state=0)
clf.fit(X_l, y_l)
expected_report = dedent("""
|--- feature_1 <= 0.00
| |--- class: -1
|--- feature_1 > 0.00
| |--- truncated branch of depth 2
""").lstrip()
assert export_text(clf, max_depth=0) == expected_report
X_mo = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1]]
y_mo = [[-1, -1], [-1, -1], [-1, -1], [1, 1], [1, 1], [1, 1]]
reg = DecisionTreeRegressor(max_depth=2, random_state=0)
reg.fit(X_mo, y_mo)
expected_report = dedent("""
|--- feature_1 <= 0.0
| |--- value: [-1.0, -1.0]
|--- feature_1 > 0.0
| |--- value: [1.0, 1.0]
""").lstrip()
assert export_text(reg, decimals=1) == expected_report
assert export_text(reg, decimals=1, show_weights=True) == expected_report
X_single = [[-2], [-1], [-1], [1], [1], [2]]
reg = DecisionTreeRegressor(max_depth=2, random_state=0)
reg.fit(X_single, y_mo)
expected_report = dedent("""
|--- first <= 0.0
| |--- value: [-1.0, -1.0]
|--- first > 0.0
| |--- value: [1.0, 1.0]
""").lstrip()
assert export_text(reg, decimals=1,
feature_names=['first']) == expected_report
assert export_text(reg, decimals=1, show_weights=True,
feature_names=['first']) == expected_report
def test_set_params_updates_valid_params():
# Check that set_params tries to set SVC().C, not
# DecisionTreeClassifier().C
gscv = GridSearchCV(DecisionTreeClassifier(), {})
gscv.set_params(estimator=SVC(), estimator__C=42.0)
assert gscv.estimator.C == 42.0
def test_graphviz_toy():
# Check correctness of export_graphviz
clf = DecisionTreeClassifier(max_depth=3,
min_samples_split=2,
criterion="gini",
random_state=2)
clf.fit(X, y)
# Test export code
contents1 = export_graphviz(clf, out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box] ;\n' \
'0 [label="X[0] <= 0.0\\ngini = 0.5\\nsamples = 6\\n' \
'value = [3, 3]"] ;\n' \
'1 [label="gini = 0.0\\nsamples = 3\\nvalue = [3, 0]"] ;\n' \
'0 -> 1 [labeldistance=2.5, labelangle=45, ' \
'headlabel="True"] ;\n' \
'2 [label="gini = 0.0\\nsamples = 3\\nvalue = [0, 3]"] ;\n' \
'0 -> 2 [labeldistance=2.5, labelangle=-45, ' \
'headlabel="False"] ;\n' \
'}'
assert contents1 == contents2
# Test with feature_names
contents1 = export_graphviz(clf, feature_names=["feature0", "feature1"],
out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box] ;\n' \
'0 [label="feature0 <= 0.0\\ngini = 0.5\\nsamples = 6\\n' \
'value = [3, 3]"] ;\n' \
'1 [label="gini = 0.0\\nsamples = 3\\nvalue = [3, 0]"] ;\n' \
'0 -> 1 [labeldistance=2.5, labelangle=45, ' \
'headlabel="True"] ;\n' \
'2 [label="gini = 0.0\\nsamples = 3\\nvalue = [0, 3]"] ;\n' \
'0 -> 2 [labeldistance=2.5, labelangle=-45, ' \
'headlabel="False"] ;\n' \
'}'
assert contents1 == contents2
# Test with class_names
contents1 = export_graphviz(clf, class_names=["yes", "no"], out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box] ;\n' \
'0 [label="X[0] <= 0.0\\ngini = 0.5\\nsamples = 6\\n' \
'value = [3, 3]\\nclass = yes"] ;\n' \
'1 [label="gini = 0.0\\nsamples = 3\\nvalue = [3, 0]\\n' \
'class = yes"] ;\n' \
'0 -> 1 [labeldistance=2.5, labelangle=45, ' \
'headlabel="True"] ;\n' \
'2 [label="gini = 0.0\\nsamples = 3\\nvalue = [0, 3]\\n' \
'class = no"] ;\n' \
'0 -> 2 [labeldistance=2.5, labelangle=-45, ' \
'headlabel="False"] ;\n' \
'}'
assert contents1 == contents2
# Test plot_options
contents1 = export_graphviz(clf, filled=True, impurity=False,
proportion=True, special_characters=True,
rounded=True, out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box, style="filled, rounded", color="black", ' \
'fontname=helvetica] ;\n' \
'edge [fontname=helvetica] ;\n' \
'0 [label=<X<SUB>0</SUB> ≤ 0.0<br/>samples = 100.0%<br/>' \
'value = [0.5, 0.5]>, fillcolor="#ffffff"] ;\n' \
'1 [label=<samples = 50.0%<br/>value = [1.0, 0.0]>, ' \
'fillcolor="#e58139"] ;\n' \
'0 -> 1 [labeldistance=2.5, labelangle=45, ' \
'headlabel="True"] ;\n' \
'2 [label=<samples = 50.0%<br/>value = [0.0, 1.0]>, ' \
'fillcolor="#399de5"] ;\n' \
'0 -> 2 [labeldistance=2.5, labelangle=-45, ' \
'headlabel="False"] ;\n' \
'}'
assert contents1 == contents2
# Test max_depth
contents1 = export_graphviz(clf, max_depth=0,
class_names=True, out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box] ;\n' \
'0 [label="X[0] <= 0.0\\ngini = 0.5\\nsamples = 6\\n' \
'value = [3, 3]\\nclass = y[0]"] ;\n' \
'1 [label="(...)"] ;\n' \
'0 -> 1 ;\n' \
'2 [label="(...)"] ;\n' \
'0 -> 2 ;\n' \
'}'
assert contents1 == contents2
# Test max_depth with plot_options
contents1 = export_graphviz(clf, max_depth=0, filled=True,
out_file=None, node_ids=True)
contents2 = 'digraph Tree {\n' \
'node [shape=box, style="filled", color="black"] ;\n' \
'0 [label="node #0\\nX[0] <= 0.0\\ngini = 0.5\\n' \
'samples = 6\\nvalue = [3, 3]", fillcolor="#ffffff"] ;\n' \
'1 [label="(...)", fillcolor="#C0C0C0"] ;\n' \
'0 -> 1 ;\n' \
'2 [label="(...)", fillcolor="#C0C0C0"] ;\n' \
'0 -> 2 ;\n' \
'}'
assert contents1 == contents2
# Test multi-output with weighted samples
clf = DecisionTreeClassifier(max_depth=2,
min_samples_split=2,
criterion="gini",
random_state=2)
clf = clf.fit(X, y2, sample_weight=w)
contents1 = export_graphviz(clf, filled=True,
impurity=False, out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box, style="filled", color="black"] ;\n' \
'0 [label="X[0] <= 0.0\\nsamples = 6\\n' \
'value = [[3.0, 1.5, 0.0]\\n' \
'[3.0, 1.0, 0.5]]", fillcolor="#ffffff"] ;\n' \
'1 [label="samples = 3\\nvalue = [[3, 0, 0]\\n' \
'[3, 0, 0]]", fillcolor="#e58139"] ;\n' \
'0 -> 1 [labeldistance=2.5, labelangle=45, ' \
'headlabel="True"] ;\n' \
'2 [label="X[0] <= 1.5\\nsamples = 3\\n' \
'value = [[0.0, 1.5, 0.0]\\n' \
'[0.0, 1.0, 0.5]]", fillcolor="#f1bd97"] ;\n' \
'0 -> 2 [labeldistance=2.5, labelangle=-45, ' \
'headlabel="False"] ;\n' \
'3 [label="samples = 2\\nvalue = [[0, 1, 0]\\n' \
'[0, 1, 0]]", fillcolor="#e58139"] ;\n' \
'2 -> 3 ;\n' \
'4 [label="samples = 1\\nvalue = [[0.0, 0.5, 0.0]\\n' \
'[0.0, 0.0, 0.5]]", fillcolor="#e58139"] ;\n' \
'2 -> 4 ;\n' \
'}'
assert contents1 == contents2
# Test regression output with plot_options
clf = DecisionTreeRegressor(max_depth=3,
min_samples_split=2,
criterion="mse",
random_state=2)
clf.fit(X, y)
contents1 = export_graphviz(clf, filled=True, leaves_parallel=True,
out_file=None, rotate=True, rounded=True)
contents2 = 'digraph Tree {\n' \
'node [shape=box, style="filled, rounded", color="black", ' \
'fontname=helvetica] ;\n' \
'graph [ranksep=equally, splines=polyline] ;\n' \
'edge [fontname=helvetica] ;\n' \
'rankdir=LR ;\n' \
'0 [label="X[0] <= 0.0\\nmse = 1.0\\nsamples = 6\\n' \
'value = 0.0", fillcolor="#f2c09c"] ;\n' \
'1 [label="mse = 0.0\\nsamples = 3\\nvalue = -1.0", ' \
'fillcolor="#ffffff"] ;\n' \
'0 -> 1 [labeldistance=2.5, labelangle=-45, ' \
'headlabel="True"] ;\n' \
'2 [label="mse = 0.0\\nsamples = 3\\nvalue = 1.0", ' \
'fillcolor="#e58139"] ;\n' \
'0 -> 2 [labeldistance=2.5, labelangle=45, ' \
'headlabel="False"] ;\n' \
'{rank=same ; 0} ;\n' \
'{rank=same ; 1; 2} ;\n' \
'}'
assert contents1 == contents2
# Test classifier with degraded learning set
clf = DecisionTreeClassifier(max_depth=3)
clf.fit(X, y_degraded)
contents1 = export_graphviz(clf, filled=True, out_file=None)
contents2 = 'digraph Tree {\n' \
'node [shape=box, style="filled", color="black"] ;\n' \
'0 [label="gini = 0.0\\nsamples = 6\\nvalue = 6.0", ' \
'fillcolor="#ffffff"] ;\n' \
'}'
voter = clone(voter)
voter.fit(X, y, sample_weight=np.ones(y.shape))
voter.set_params(lr=drop)
with pytest.warns(None) as record:
voter.fit(X, y, sample_weight=np.ones(y.shape))
assert record if drop is None else not record
y_pred = voter.predict(X)
assert y_pred.shape == y.shape
@pytest.mark.parametrize("estimator", [
VotingRegressor(estimators=[(
'lr',
LinearRegression()), ('tree', DecisionTreeRegressor(random_state=0))]),
VotingClassifier(estimators=[('lr', LogisticRegression(
random_state=0)), ('tree', DecisionTreeClassifier(random_state=0))])
],
ids=['VotingRegressor', 'VotingClassifier'])
def test_check_estimators_voting_estimator(estimator):
# FIXME: to be removed when meta-estimators can specified themselves
# their testing parameters (for required parameters).
check_estimator(estimator)
check_no_attributes_set_in_init(estimator.__class__.__name__, estimator)
# TODO: Remove in 0.24 when None is removed in Voting*
@pytest.mark.parametrize("Voter, BaseEstimator",
[(VotingClassifier, DecisionTreeClassifier),
(VotingRegressor, DecisionTreeRegressor)])
def test_deprecate_none_transformer(Voter, BaseEstimator):
est = Voter(estimators=[('lr',