def test_drcif_on_unit_test_data():
"""Test of DrCIF 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 DrCIF
drcif = DrCIF(n_estimators=10, random_state=0, save_transformed_data=True)
drcif.fit(X_train, y_train)
# assert probabilities are the same
probas = drcif.predict_proba(X_test.iloc[indices])
testing.assert_array_equal(probas, drcif_unit_test_probas)
# test train estimate
train_probas = drcif._get_train_probs(X_train, y_train)
train_preds = drcif.classes_[np.argmax(train_probas, axis=1)]
assert accuracy_score(y_train, train_preds) >= 0.85
def test_drcif_train_estimate():
"""Test of DrCIF on unit test data."""
# load unit test data
X_train, y_train = load_unit_test(split="train")
# train DrCIF
drcif = DrCIF(
n_estimators=2,
n_intervals=2,
att_subsample_size=2,
random_state=0,
save_transformed_data=True,
)
drcif.fit(X_train, y_train)
# test train estimate
train_probas = drcif._get_train_probs(X_train, y_train)
assert train_probas.shape == (20, 2)
train_preds = drcif.classes_[np.argmax(train_probas, axis=1)]
assert accuracy_score(y_train, train_preds) >= 0.6