def test_boss_on_power_demand():
# load power demand data
X_train, y_train = load_italy_power_demand(split='train', return_X_y=True)
X_test, y_test = load_italy_power_demand(split='test', return_X_y=True)
indices = np.random.RandomState(0).permutation(100)
# train BOSS
boss = BOSSEnsemble(random_state=47)
boss.fit(X_train, y_train)
score = boss.score(X_test.iloc[indices], y_test[indices])
assert (score >= 0.80)
def test_boss_on_gunpoint():
# load gunpoint data
X_train, y_train = load_gunpoint(split='train', return_X_y=True)
X_test, y_test = load_gunpoint(split='test', return_X_y=True)
indices = np.random.RandomState(0).permutation(10)
# train boss
boss = BOSSEnsemble(random_state=0)
boss.fit(X_train.iloc[indices], y_train[indices])
# assert probabilities are the same
probas = boss.predict_proba(X_test.iloc[indices])
testing.assert_array_equal(probas, boss_gunpoint_probas)
def test_boss_train_estimate():
"""Test of BOSS train estimate on unit test data."""
# load unit test data
X_train, y_train = load_unit_test(split="train")
# train BOSS
boss = BOSSEnsemble(max_ensemble_size=2,
random_state=0,
save_train_predictions=True)
boss.fit(X_train, y_train)
# test train estimate
train_probas = boss._get_train_probs(X_train, y_train)
assert train_probas.shape == (20, 2)
train_preds = boss.classes_[np.argmax(train_probas, axis=1)]
assert accuracy_score(y_train, train_preds) >= 0.6
def test_boss_on_unit_test_data():
"""Test of BOSS on unit test data."""
# load unit test data
X_train, y_train = load_unit_test(split="train", return_X_y=True)
X_test, y_test = load_unit_test(split="test", return_X_y=True)
indices = np.random.RandomState(0).choice(len(y_train), 10, replace=False)
# train BOSS
boss = BOSSEnsemble(max_ensemble_size=5,
random_state=0,
save_train_predictions=True)
boss.fit(X_train, y_train)
# assert probabilities are the same
probas = boss.predict_proba(X_test.iloc[indices])
testing.assert_array_almost_equal(probas, boss_unit_test_probas, decimal=2)
# test train estimate
train_probas = boss._get_train_probs(X_train, y_train)
train_preds = boss.classes_[np.argmax(train_probas, axis=1)]
assert accuracy_score(y_train, train_preds) >= 0.75