def test_gnb_prior():
# Test whether class priors are properly set.
clf = GaussianNB().fit(X, y)
assert_array_almost_equal(np.array([3, 3]) / 6.0, clf.class_prior_, 8)
clf.fit(X1, y1)
# Check that the class priors sum to 1
assert_array_almost_equal(clf.class_prior_.sum(), 1)
def test_gnb_pfit_wrong_nb_features():
"""Test whether an error is raised when the number of feature changes
between two partial fit"""
clf = GaussianNB()
# Fit for the first time the GNB
clf.fit(X, y)
# Partial fit a second time with an incoherent X
assert_raises(ValueError, clf.partial_fit, np.hstack((X, X)), y)
def test_gnb_priors_sum_isclose():
# test whether the class prior sum is properly tested"""
X = np.array([[-1, -1], [-2, -1], [-3, -2], [-4, -5], [-5, -4], [1, 1],
[2, 1], [3, 2], [4, 4], [5, 5]])
priors = np.array(
[0.08, 0.14, 0.03, 0.16, 0.11, 0.16, 0.07, 0.14, 0.11, 0.0])
Y = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
clf = GaussianNB(priors)
# smoke test for issue #9633
clf.fit(X, Y)
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 all(clf1.fit(X, y).predict(X)) == all([1, 1, 1, 2, 2, 2])
assert all(clf2.fit(X, y).predict(X)) == all([1, 1, 1, 2, 2, 2])
assert all(clf3.fit(X, y).predict(X)) == all([1, 1, 1, 2, 2, 2])
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='hard',
weights=[1, 1, 1])
assert all(eclf.fit(X, y).predict(X)) == all([1, 1, 1, 2, 2, 2])
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft',
weights=[1, 1, 1])
assert all(eclf.fit(X, y).predict(X)) == all([1, 1, 1, 2, 2, 2])
def test_gnb():
# Gaussian Naive Bayes classification.
# This checks that GaussianNB implements fit and predict and returns
# correct values for a simple toy dataset.
clf = GaussianNB()
y_pred = clf.fit(X, y).predict(X)
assert_array_equal(y_pred, y)
y_pred_proba = clf.predict_proba(X)
y_pred_log_proba = clf.predict_log_proba(X)
assert_array_almost_equal(np.log(y_pred_proba), y_pred_log_proba, 8)
# Test whether label mismatch between target y and classes raises
# an Error
# FIXME Remove this test once the more general partial_fit tests are merged
assert_raises(ValueError, GaussianNB().partial_fit, X, y, classes=[0, 1])
def test_gnb_prior_large_bias():
"""Test if good prediction when class prior favor largely one class"""
clf = GaussianNB(priors=np.array([0.01, 0.99]))
clf.fit(X, y)
assert clf.predict([[-0.1, -0.1]]) == np.array([2])
cluster_std=1.0,
centers=centers,
shuffle=False,
random_state=42)
y[:n_samples // 2] = 0
y[n_samples // 2:] = 1
sample_weight = np.random.RandomState(42).rand(y.shape[0])
# split train, test for calibration
X_train, X_test, y_train, y_test, sw_train, sw_test = \
train_test_split(X, y, sample_weight, test_size=0.9, random_state=42)
# Gaussian Naive-Bayes with no calibration
clf = GaussianNB()
clf.fit(X_train, y_train) # GaussianNB itself does not support sample-weights
prob_pos_clf = clf.predict_proba(X_test)[:, 1]
# Gaussian Naive-Bayes with isotonic calibration
clf_isotonic = CalibratedClassifierCV(clf, cv=2, method='isotonic')
clf_isotonic.fit(X_train, y_train, sw_train)
prob_pos_isotonic = clf_isotonic.predict_proba(X_test)[:, 1]
# Gaussian Naive-Bayes with sigmoid calibration
clf_sigmoid = CalibratedClassifierCV(clf, cv=2, method='sigmoid')
clf_sigmoid.fit(X_train, y_train, sw_train)
prob_pos_sigmoid = clf_sigmoid.predict_proba(X_test)[:, 1]
print("Brier scores: (the smaller the better)")
clf_score = brier_score_loss(y_test, prob_pos_clf, sw_test)
