def test_permutation_importance_correlated_feature_regression_pandas(n_jobs):
pd = pytest.importorskip("pandas")
# Make sure that feature highly correlated to the target have a higher
# importance
rng = np.random.RandomState(42)
n_repeats = 5
dataset = load_iris()
X, y = dataset.data, dataset.target
y_with_little_noise = (y +
rng.normal(scale=0.001, size=y.shape[0])).reshape(
-1, 1)
# Adds feature correlated with y as the last column
X = pd.DataFrame(X, columns=dataset.feature_names)
X['correlated_feature'] = y_with_little_noise
clf = RandomForestClassifier(n_estimators=10, random_state=42)
clf.fit(X, y)
result = permutation_importance(clf,
X,
y,
n_repeats=n_repeats,
random_state=rng,
n_jobs=n_jobs)
assert result.importances.shape == (X.shape[1], n_repeats)
# the correlated feature with y was added as the last column and should
# have the highest importance
assert np.all(result.importances_mean[-1] > result.importances_mean[:-1])
def test_threshold_string():
est = RandomForestClassifier(n_estimators=50, random_state=0)
model = SelectFromModel(est, threshold="0.5*mean")
model.fit(data, y)
X_transform = model.transform(data)
# Calculate the threshold from the estimator directly.
est.fit(data, y)
threshold = 0.5 * np.mean(est.feature_importances_)
mask = est.feature_importances_ > threshold
assert_array_almost_equal(X_transform, data[:, mask])
def test_backend_respected():
clf = RandomForestClassifier(n_estimators=10, n_jobs=2)
with joblib.parallel_backend("testing") as (ba, n_jobs):
clf.fit(X, y)
assert ba.count > 0
# predict_proba requires shared memory. Ensure that's honored.
with joblib.parallel_backend("testing") as (ba, _):
clf.predict_proba(X)
assert ba.count == 0
def test_predict_on_toy_problem():
"""Manually check predicted class labels for toy dataset."""
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
clf3 = GaussianNB()
X = np.array([[-1.1, -1.5], [-1.2, -1.4], [-3.4, -2.2], [1.1, 1.2],
[2.1, 1.4], [3.1, 2.3]])
y = np.array([1, 1, 1, 2, 2, 2])
assert_array_equal(clf1.fit(X, y).predict(X), [1, 1, 1, 2, 2, 2])
assert_array_equal(clf2.fit(X, y).predict(X), [1, 1, 1, 2, 2, 2])
assert_array_equal(clf3.fit(X, y).predict(X), [1, 1, 1, 2, 2, 2])
eclf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2),
('gnb', clf3)],
voting='hard',
weights=[1, 1, 1])
assert_array_equal(eclf.fit(X, y).predict(X), [1, 1, 1, 2, 2, 2])
eclf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2),
('gnb', clf3)],
voting='soft',
weights=[1, 1, 1])
assert_array_equal(eclf.fit(X, y).predict(X), [1, 1, 1, 2, 2, 2])
def test_tie_situation():
"""Check voting classifier selects smaller class label in tie situation."""
clf1 = LogisticRegression(random_state=123, solver='liblinear')
clf2 = RandomForestClassifier(random_state=123)
eclf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2)],
voting='hard')
assert clf1.fit(X, y).predict(X)[73] == 2
assert clf2.fit(X, y).predict(X)[73] == 1
assert eclf.fit(X, y).predict(X)[73] == 1
def test_dtype_convert(n_classes=15):
classifier = RandomForestClassifier(random_state=0, bootstrap=False)
X = np.eye(n_classes)
y = [ch for ch in 'ABCDEFGHIJKLMNOPQRSTU'[:n_classes]]
result = classifier.fit(X, y).predict(X)
assert_array_equal(classifier.classes_, y)
assert_array_equal(result, y)