def test_label_encoder():
y = ['one', 'one', 'one', 'zero', 'zero', 'two']
X = np.random.rand(6, 3)
pool = [DecisionTreeClassifier().fit(X, y) for _ in range(5)]
stacked = StackedClassifier(pool).fit(X, y)
pred = stacked.predict(X)
assert np.array_equal(pred, y)
def test_one_class_meta_dataset(create_X_y):
X, y = create_X_y
pool = [DecisionTreeClassifier().fit(X, y) for _ in range(5)]
stacked = StackedClassifier(pool)
X_meta = np.random.rand(10, 2)
y_meta = np.zeros(10, dtype=int)
with pytest.raises(ValueError):
stacked.fit(X_meta, y_meta)
def test_label_encoder_base_ensemble():
from sklearn.ensemble import RandomForestClassifier
X, y = make_classification()
y[y == 1] = 2
y = y.astype(np.float)
pool = RandomForestClassifier().fit(X, y)
st = StackedClassifier(pool)
st.fit(X, y)
pred = st.predict(X)
assert np.isin(st.classes_, pred).all()
def test_not_predict_proba(create_X_y):
X, y = create_X_y
clf1 = Perceptron()
clf1.fit(X, y)
with pytest.raises(ValueError):
StackedClassifier([clf1, clf1]).fit(X, y)
def test_not_predict_proba_meta(create_X_y, create_pool_classifiers):
X, y = create_X_y
pool = create_pool_classifiers
with pytest.raises(ValueError):
meta_clf = StackedClassifier(pool_classifiers=pool,
meta_classifier=Perceptron())
meta_clf.fit(X, y)
meta_clf.predict_proba(X)
def test_single_model_pool(create_X_y):
X, y = create_X_y
pool = [DecisionTreeClassifier().fit(X, y)]
with pytest.raises(ValueError):
StackedClassifier(pool_classifiers=pool).fit(X, y)
def test_passthrough_false(create_X_y):
X, y = create_X_y
pool = [DecisionTreeClassifier().fit(X, y) for _ in range(5)]
stacked = StackedClassifier(pool, passthrough=False)
stacked.fit(X, y)
assert stacked.meta_classifier_.coef_.shape == (1, 5)
def test_check_estimator():
check_estimator(StackedClassifier())
random_state=rng)
RF = RandomForestClassifier(random_state=rng)
RF.fit(X_train, y_train)
X_train, X_dsel, y_train, y_dsel = train_test_split(X_train, y_train,
test_size=0.50,
random_state=rng)
# Training a random forest to be used as the pool of classifiers.
# We set the maximum depth of the tree so that it
# can estimate probabilities
pool_classifiers = RandomForestClassifier(n_estimators=100, max_depth=5,
random_state=rng)
pool_classifiers.fit(X_train, y_train)
stacked = StackedClassifier(pool_classifiers, LogisticRegression())
stacked.fit(X_dsel, y_dsel)
# Initialize a DS technique. Here we specify the size of
# the region of competence (5 neighbors)
knorau = KNORAU(pool_classifiers, random_state=rng)
kne = KNORAE(pool_classifiers, k=5, random_state=rng)
desp = DESP(pool_classifiers, k=5, random_state=rng)
ola = OLA(pool_classifiers, k=5, random_state=rng)
mcb = MCB(pool_classifiers, k=5, random_state=rng)
meta = METADES(pool_classifiers, k=5, random_state=rng)
# Fit the DS techniques
knorau.fit(X_dsel, y_dsel)
kne.fit(X_dsel, y_dsel)
desp.fit(X_dsel, y_dsel)
