def test_iris():
# Check consistency on dataset iris.
classes = np.unique(iris.target)
clf_samme = prob_samme = None
for alg in ['SAMME', 'SAMME.R']:
clf = SMOTEBoost(algorithm=alg, random_state=0)
clf.fit(iris.data, iris.target)
assert_array_equal(classes, clf.classes_)
proba = clf.predict_proba(iris.data)
if alg == "SAMME":
clf_samme = clf
prob_samme = proba
assert_equal(proba.shape[1], len(classes))
assert_equal(clf.decision_function(iris.data).shape[1], len(classes))
score = clf.score(iris.data, iris.target)
assert score > 0.9, "Failed with algorithm %s and score = %f" % \
(alg, score)
# Check we used multiple estimators
assert_greater(len(clf.estimators_), 1)
# Check for distinct random states (see issue #7408)
assert_equal(len(set(est.random_state for est in clf.estimators_)),
len(clf.estimators_))
# Somewhat hacky regression test: prior to
# ae7adc880d624615a34bafdb1d75ef67051b8200,
# predict_proba returned SAMME.R values for SAMME.
clf_samme.algorithm = "SAMME.R"
assert_array_less(0,
np.abs(clf_samme.predict_proba(iris.data) - prob_samme))
def test_oneclass_adaboost_proba():
# Test predict_proba robustness for one class label input.
# In response to issue #7501
# https://github.com/scikit-learn/scikit-learn/issues/7501
y_t = np.ones(len(X))
clf = SMOTEBoost().fit(X, y_t)
assert_array_equal(clf.predict_proba(X), np.ones((len(X), 1)))
def test_classification_toy():
# Check classification on a toy dataset.
for alg in ['SAMME', 'SAMME.R']:
clf = SMOTEBoost(algorithm=alg, k_neighbors=3, random_state=0)
clf.fit(X, y_class)
assert_array_equal(clf.predict(T), y_t_class)
assert_array_equal(np.unique(np.asarray(y_t_class)), clf.classes_)
assert_equal(clf.predict_proba(T).shape, (len(T), 2))
assert_equal(clf.decision_function(T).shape, (len(T),))