Skip to content

TST replace assert_raise_* by pytest.raises in ensemble module #19399

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Feb 11, 2021
Merged

TST replace assert_raise_* by pytest.raises in ensemble module #19399

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
05f2c9b
TST replace assert_raise_* by pytest.raises in ensemble module
hassanalsawadi Feb 8, 2021
00f621e
Merge branch 'main' of https://github.com/scikit-learn/scikit-learn i…
hassanalsawadi Feb 8, 2021
d217a02
Merge branch 'main' of https://github.com/scikit-learn/scikit-learn i…
hassanalsawadi Feb 10, 2021
cdbdb1b
TST fix long strings matching
hassanalsawadi Feb 10, 2021
8547ce1
TST fix long strings matching using +
hassanalsawadi Feb 10, 2021
8ac23b6
TST fix strings matching
hassanalsawadi Feb 10, 2021
f9fba9f
nitpicks
glemaitre Feb 11, 2021
4644552
Merge remote-tracking branch 'origin/main' into pr/halsawadi/19399
glemaitre Feb 11, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
81 changes: 44 additions & 37 deletions sklearn/ensemble/tests/test_bagging.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,9 +14,6 @@

from sklearn.utils._testing import assert_array_equal
from sklearn.utils._testing import assert_array_almost_equal
from sklearn.utils._testing import assert_raises
from sklearn.utils._testing import assert_raise_message

from sklearn.dummy import DummyClassifier, DummyRegressor
from sklearn.model_selection import GridSearchCV, ParameterGrid
from sklearn.ensemble import BaggingClassifier, BaggingRegressor
Expand Down Expand Up @@ -418,28 +415,28 @@ def test_error():
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)
with pytest.raises(ValueError):
BaggingClassifier(base, max_samples=-1).fit(X, y)
with pytest.raises(ValueError):
BaggingClassifier(base, max_samples=0.0).fit(X, y)
with pytest.raises(ValueError):
BaggingClassifier(base, max_samples=2.0).fit(X, y)
with pytest.raises(ValueError):
BaggingClassifier(base, max_samples=1000).fit(X, y)
with pytest.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)
with pytest.raises(ValueError):
BaggingClassifier(base, max_features=-1).fit(X, y)
with pytest.raises(ValueError):
BaggingClassifier(base, max_features=0.0).fit(X, y)
with pytest.raises(ValueError):
BaggingClassifier(base, max_features=2.0).fit(X, y)
with pytest.raises(ValueError):
BaggingClassifier(base, max_features=5).fit(X, y)
with pytest.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')
Expand Down Expand Up @@ -484,11 +481,13 @@ def test_parallel_classification():
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)
err_msg = (
f"Number of features of the model must match the input. Model "
f"n_features is {X_test.shape[1]} and input n_features is "
f"{X_err.shape[1]} "
)
with pytest.raises(ValueError, match=err_msg):
ensemble.decision_function(X_err)

ensemble = BaggingClassifier(SVC(decision_function_shape='ovr'),
n_jobs=1,
Expand Down Expand Up @@ -612,8 +611,9 @@ def test_bagging_sample_weight_unsupported_but_passed():
rng = check_random_state(0)

estimator.fit(iris.data, iris.target).predict(iris.data)
assert_raises(ValueError, estimator.fit, iris.data, iris.target,
sample_weight=rng.randint(10, size=(iris.data.shape[0])))
with pytest.raises(ValueError):
estimator.fit(iris.data, iris.target,
sample_weight=rng.randint(10, size=(iris.data.shape[0])))


def test_warm_start(random_state=42):
Expand Down Expand Up @@ -646,7 +646,8 @@ def test_warm_start_smaller_n_estimators():
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)
with pytest.raises(ValueError):
clf.fit(X, y)


def test_warm_start_equal_n_estimators():
Expand Down Expand Up @@ -692,7 +693,8 @@ 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)
with pytest.raises(ValueError):
clf.fit(X, y)


def test_oob_score_removed_on_warm_start():
Expand All @@ -704,7 +706,8 @@ def test_oob_score_removed_on_warm_start():
clf.set_params(warm_start=True, oob_score=False, n_estimators=100)
clf.fit(X, y)

assert_raises(AttributeError, getattr, clf, "oob_score_")
with pytest.raises(AttributeError):
getattr(clf, "oob_score_")


def test_oob_score_consistency():
Expand Down Expand Up @@ -848,9 +851,11 @@ def test_bagging_regressor_with_missing_inputs():
# Verify that exceptions can be raised by wrapper regressor
regressor = DecisionTreeRegressor()
pipeline = make_pipeline(regressor)
assert_raises(ValueError, pipeline.fit, X, y)
with pytest.raises(ValueError):
pipeline.fit(X, y)
bagging_regressor = BaggingRegressor(pipeline)
assert_raises(ValueError, bagging_regressor.fit, X, y)
with pytest.raises(ValueError):
bagging_regressor.fit(X, y)


def test_bagging_classifier_with_missing_inputs():
Expand Down Expand Up @@ -878,9 +883,11 @@ def test_bagging_classifier_with_missing_inputs():
# Verify that exceptions can be raised by wrapper classifier
classifier = DecisionTreeClassifier()
pipeline = make_pipeline(classifier)
assert_raises(ValueError, pipeline.fit, X, y)
with pytest.raises(ValueError):
pipeline.fit(X, y)
bagging_classifier = BaggingClassifier(pipeline)
assert_raises(ValueError, bagging_classifier.fit, X, y)
with pytest.raises(ValueError):
bagging_classifier.fit(X, y)


def test_bagging_small_max_features():
Expand Down
19 changes: 8 additions & 11 deletions sklearn/ensemble/tests/test_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,7 @@
# License: BSD 3 clause

import numpy as np

from sklearn.utils._testing import assert_raise_message
import pytest

from sklearn.datasets import load_iris
from sklearn.ensemble import BaggingClassifier
Expand Down Expand Up @@ -54,9 +53,9 @@ def test_base_zero_n_estimators():
ensemble = BaggingClassifier(base_estimator=Perceptron(),
n_estimators=0)
iris = load_iris()
assert_raise_message(ValueError,
"n_estimators must be greater than zero, got 0.",
ensemble.fit, iris.data, iris.target)
err_msg = "n_estimators must be greater than zero, got 0."
with pytest.raises(ValueError, match=err_msg):
ensemble.fit(iris.data, iris.target)


def test_base_not_int_n_estimators():
Expand All @@ -65,14 +64,12 @@ def test_base_not_int_n_estimators():
string_ensemble = BaggingClassifier(base_estimator=Perceptron(),
n_estimators='3')
iris = load_iris()
assert_raise_message(ValueError,
"n_estimators must be an integer",
string_ensemble.fit, iris.data, iris.target)
with pytest.raises(ValueError, match="n_estimators must be an integer"):
string_ensemble.fit(iris.data, iris.target)
float_ensemble = BaggingClassifier(base_estimator=Perceptron(),
n_estimators=3.0)
assert_raise_message(ValueError,
"n_estimators must be an integer",
float_ensemble.fit, iris.data, iris.target)
with pytest.raises(ValueError, match="n_estimators must be an integer"):
float_ensemble.fit(iris.data, iris.target)


def test_set_random_states():
Expand Down
43 changes: 24 additions & 19 deletions sklearn/ensemble/tests/test_forest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@
from sklearn.utils._testing import assert_almost_equal
from sklearn.utils._testing import assert_array_almost_equal
from sklearn.utils._testing import assert_array_equal
from sklearn.utils._testing import assert_raises
from sklearn.utils._testing import _convert_container
from sklearn.utils._testing import ignore_warnings
from sklearn.utils._testing import skip_if_no_parallel
Expand Down Expand Up @@ -833,12 +832,12 @@ def check_min_samples_split(name):
ForestEstimator = FOREST_ESTIMATORS[name]

# test boundary value
assert_raises(ValueError,
ForestEstimator(min_samples_split=-1).fit, X, y)
assert_raises(ValueError,
ForestEstimator(min_samples_split=0).fit, X, y)
assert_raises(ValueError,
ForestEstimator(min_samples_split=1.1).fit, X, y)
with pytest.raises(ValueError):
ForestEstimator(min_samples_split=-1).fit(X, y)
with pytest.raises(ValueError):
ForestEstimator(min_samples_split=0).fit(X, y)
with pytest.raises(ValueError):
ForestEstimator(min_samples_split=1.1).fit(X, y)

est = ForestEstimator(min_samples_split=10, n_estimators=1, random_state=0)
est.fit(X, y)
Expand Down Expand Up @@ -870,10 +869,10 @@ def check_min_samples_leaf(name):
ForestEstimator = FOREST_ESTIMATORS[name]

# test boundary value
assert_raises(ValueError,
ForestEstimator(min_samples_leaf=-1).fit, X, y)
assert_raises(ValueError,
ForestEstimator(min_samples_leaf=0).fit, X, y)
with pytest.raises(ValueError):
ForestEstimator(min_samples_leaf=-1).fit(X, y)
with pytest.raises(ValueError):
ForestEstimator(min_samples_leaf=0).fit(X, y)

est = ForestEstimator(min_samples_leaf=5, n_estimators=1, random_state=0)
est.fit(X, y)
Expand Down Expand Up @@ -1026,14 +1025,15 @@ def test_memory_layout(name, dtype):
@ignore_warnings
def check_1d_input(name, X, X_2d, y):
ForestEstimator = FOREST_ESTIMATORS[name]
assert_raises(ValueError, ForestEstimator(n_estimators=1,
random_state=0).fit, X, y)
with pytest.raises(ValueError):
ForestEstimator(n_estimators=1, random_state=0).fit(X, y)

est = ForestEstimator(random_state=0)
est.fit(X_2d, y)

if name in FOREST_CLASSIFIERS or name in FOREST_REGRESSORS:
assert_raises(ValueError, est.predict, X)
with pytest.raises(ValueError):
est.predict(X)


@pytest.mark.parametrize('name', FOREST_ESTIMATORS)
Expand Down Expand Up @@ -1120,8 +1120,10 @@ def check_class_weight_errors(name):

# Invalid preset string
clf = ForestClassifier(class_weight='the larch', random_state=0)
assert_raises(ValueError, clf.fit, X, y)
assert_raises(ValueError, clf.fit, X, _y)
with pytest.raises(ValueError):
clf.fit(X, y)
with pytest.raises(ValueError):
clf.fit(X, _y)

# Warning warm_start with preset
clf = ForestClassifier(class_weight='balanced', warm_start=True,
Expand All @@ -1137,11 +1139,13 @@ def check_class_weight_errors(name):

# Not a list or preset for multi-output
clf = ForestClassifier(class_weight=1, random_state=0)
assert_raises(ValueError, clf.fit, X, _y)
with pytest.raises(ValueError):
clf.fit(X, _y)

# Incorrect length list for multi-output
clf = ForestClassifier(class_weight=[{-1: 0.5, 1: 1.}], random_state=0)
assert_raises(ValueError, clf.fit, X, _y)
with pytest.raises(ValueError):
clf.fit(X, _y)


@pytest.mark.parametrize('name', FOREST_CLASSIFIERS)
Expand Down Expand Up @@ -1210,7 +1214,8 @@ def check_warm_start_smaller_n_estimators(name):
est = ForestEstimator(n_estimators=5, max_depth=1, warm_start=True)
est.fit(X, y)
est.set_params(n_estimators=4)
assert_raises(ValueError, est.fit, X, y)
with pytest.raises(ValueError):
est.fit(X, y)


@pytest.mark.parametrize('name', FOREST_ESTIMATORS)
Expand Down
Loading