def test_stacking_classifier_iris(cv, final_estimator, passthrough):
# prescale the data to avoid convergence warning without using a pipeline
# for later assert
X_train, X_test, y_train, y_test = train_test_split(scale(X_iris),
y_iris,
stratify=y_iris,
random_state=42)
estimators = [('lr', LogisticRegression()), ('svc', LinearSVC())]
clf = StackingClassifier(estimators=estimators,
final_estimator=final_estimator,
cv=cv,
passthrough=passthrough)
clf.fit(X_train, y_train)
clf.predict(X_test)
clf.predict_proba(X_test)
assert clf.score(X_test, y_test) > 0.8
X_trans = clf.transform(X_test)
expected_column_count = 10 if passthrough else 6
assert X_trans.shape[1] == expected_column_count
if passthrough:
assert_allclose(X_test, X_trans[:, -4:])
clf.set_params(lr='drop')
clf.fit(X_train, y_train)
clf.predict(X_test)
clf.predict_proba(X_test)
if final_estimator is None:
# LogisticRegression has decision_function method
clf.decision_function(X_test)
X_trans = clf.transform(X_test)
expected_column_count_drop = 7 if passthrough else 3
assert X_trans.shape[1] == expected_column_count_drop
if passthrough:
assert_allclose(X_test, X_trans[:, -4:])
def test_stacking_classifier_drop_column_binary_classification():
# check that a column is dropped in binary classification
X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, _ = train_test_split(scale(X),
y,
stratify=y,
random_state=42)
# both classifiers implement 'predict_proba' and will both drop one column
estimators = [('lr', LogisticRegression()),
('rf', RandomForestClassifier(random_state=42))]
clf = StackingClassifier(estimators=estimators, cv=3)
clf.fit(X_train, y_train)
X_trans = clf.transform(X_test)
assert X_trans.shape[1] == 2
# LinearSVC does not implement 'predict_proba' and will not drop one column
estimators = [('lr', LogisticRegression()), ('svc', LinearSVC())]
clf.set_params(estimators=estimators)
clf.fit(X_train, y_train)
X_trans = clf.transform(X_test)
assert X_trans.shape[1] == 2
def test_stacking_classifier_sparse_passthrough(fmt):
# Check passthrough behavior on a sparse X matrix
X_train, X_test, y_train, _ = train_test_split(
sparse.coo_matrix(scale(X_iris)).asformat(fmt),
y_iris, random_state=42
)
estimators = [('lr', LogisticRegression()), ('svc', LinearSVC())]
rf = RandomForestClassifier(n_estimators=10, random_state=42)
clf = StackingClassifier(
estimators=estimators, final_estimator=rf, cv=5, passthrough=True
)
clf.fit(X_train, y_train)
X_trans = clf.transform(X_test)
assert_allclose_dense_sparse(X_test, X_trans[:, -4:])
assert sparse.issparse(X_trans)
assert X_test.format == X_trans.format
