def test_StackingClassifier_drop_last_proba():
np.random.seed(123)
lr1 = LogisticRegression(solver='liblinear', multi_class='ovr')
sclf1 = StackingClassifier(classifiers=[lr1, lr1],
use_probas=True,
drop_last_proba=False,
meta_classifier=lr1)
sclf1.fit(X, y)
r1 = sclf1.predict_meta_features(X[:2])
assert r1.shape == (2, 6)
sclf2 = StackingClassifier(classifiers=[lr1, lr1],
use_probas=True,
drop_last_proba=True,
meta_classifier=lr1)
sclf2.fit(X, y)
r2 = sclf2.predict_meta_features(X[:2])
assert r2.shape == (2, 4), r2.shape
sclf3 = StackingClassifier(classifiers=[lr1, lr1],
use_probas=True,
drop_last_proba=True,
meta_classifier=lr1)
sclf3.fit(X[0:100], y[0:100]) # only 2 classes
r3 = sclf3.predict_meta_features(X[:2])
assert r3.shape == (2, 2), r3.shape
def test_StackingClassifier_avg_vs_concat():
np.random.seed(123)
lr1 = LogisticRegression(solver='liblinear', multi_class='ovr')
sclf1 = StackingClassifier(classifiers=[lr1, lr1],
use_probas=True,
average_probas=True,
meta_classifier=lr1)
sclf1.fit(X, y)
r1 = sclf1.predict_meta_features(X[:2])
assert r1.shape == (2, 3)
assert_almost_equal(np.sum(r1[0]), 1.0, decimal=6)
assert_almost_equal(np.sum(r1[1]), 1.0, decimal=6)
sclf2 = StackingClassifier(classifiers=[lr1, lr1],
use_probas=True,
average_probas=False,
meta_classifier=lr1)
sclf2.fit(X, y)
r2 = sclf2.predict_meta_features(X[:2])
assert r2.shape == (2, 6)
assert_almost_equal(np.sum(r2[0]), 2.0, decimal=6)
assert_almost_equal(np.sum(r2[1]), 2.0, decimal=6)
np.array_equal(r2[0][:3], r2[0][3:])
def test_StackingClassifier_avg_vs_concat():
np.random.seed(123)
lr1 = LogisticRegression()
sclf1 = StackingClassifier(classifiers=[lr1, lr1],
use_probas=True,
average_probas=True,
meta_classifier=lr1)
sclf1.fit(X, y)
r1 = sclf1.predict_meta_features(X[:2])
assert r1.shape == (2, 3)
assert_almost_equal(np.sum(r1[0]), 1.0, places=6)
assert_almost_equal(np.sum(r1[1]), 1.0, places=6)
sclf2 = StackingClassifier(classifiers=[lr1, lr1],
use_probas=True,
average_probas=False,
meta_classifier=lr1)
sclf2.fit(X, y)
r2 = sclf2.predict_meta_features(X[:2])
assert r2.shape == (2, 6)
assert_almost_equal(np.sum(r2[0]), 2.0, places=6)
assert_almost_equal(np.sum(r2[1]), 2.0, places=6)
np.array_equal(r2[0][:3], r2[0][3:])
def test_StackingClassifier_drop_last_proba():
np.random.seed(123)
lr1 = LogisticRegression(solver='liblinear',
multi_class='ovr')
sclf1 = StackingClassifier(classifiers=[lr1, lr1],
use_probas=True,
drop_last_proba=False,
meta_classifier=lr1)
sclf1.fit(X, y)
r1 = sclf1.predict_meta_features(X[:2])
assert r1.shape == (2, 6)
sclf2 = StackingClassifier(classifiers=[lr1, lr1],
use_probas=True,
drop_last_proba=True,
meta_classifier=lr1)
sclf2.fit(X, y)
r2 = sclf2.predict_meta_features(X[:2])
assert r2.shape == (2, 4), r2.shape
sclf3 = StackingClassifier(classifiers=[lr1, lr1],
use_probas=True,
drop_last_proba=True,
meta_classifier=lr1)
sclf3.fit(X[0:100], y[0:100]) # only 2 classes
r3 = sclf3.predict_meta_features(X[:2])
assert r3.shape == (2, 2), r3.shape
def fit(self, X, y):
meta_features = X
target = y
stack_clf = None
for layer_num, classifiers in zip(range(self.layer_num),
self.multi_classifiers):
classifiers = [clf() for clf in classifiers]
meta_classifier = self.meta_classifier()
stack_clf = StackingClassifier(classifiers=classifiers,
meta_classifier=meta_classifier)
stack_clf.fit(meta_features, target)
if layer_num != self.layer_num - 1:
meta_features = stack_clf.predict_meta_features(meta_features)
self._meta_clf.append(stack_clf)
else:
self._stack_slf = stack_clf
