def test_multi_output_debiased_lasso(self):
"""Test MultiOutputDebiasedLasso."""
# Test that attributes propagate correctly
est = MultiOutputDebiasedLasso()
multioutput_attrs = est.get_params()
debiased_attrs = DebiasedLasso().get_params()
for attr in debiased_attrs:
self.assertTrue(attr in multioutput_attrs)
# Test MultiOutputDebiasedLasso without weights
# --> Check debiased coeffcients without intercept
params = {'fit_intercept': False}
self._check_debiased_coefs(TestLassoExtensions.X, TestLassoExtensions.y_2D_consistent,
sample_weight=None,
expected_coefs=[TestLassoExtensions.coefs1, TestLassoExtensions.coefs2],
params=params)
# --> Check debiased coeffcients with intercept
intercept_2D = np.array([TestLassoExtensions.intercept1, TestLassoExtensions.intercept2])
self._check_debiased_coefs(TestLassoExtensions.X,
TestLassoExtensions.y_2D_consistent + intercept_2D,
sample_weight=None,
expected_coefs=[TestLassoExtensions.coefs1, TestLassoExtensions.coefs2],
expected_intercept=intercept_2D)
# --> Check CI coverage
self._check_debiased_CI_2D(TestLassoExtensions.X,
TestLassoExtensions.y_2D_consistent + intercept_2D,
sample_weight=None,
expected_coefs=np.array([TestLassoExtensions.coefs1, TestLassoExtensions.coefs2]),
expected_intercept=intercept_2D)
# Test MultiOutputDebiasedLasso with weights
# Define weights
sample_weight = np.concatenate((np.ones(TestLassoExtensions.n_samples // 2),
np.ones(TestLassoExtensions.n_samples // 2) * 2))
# Define extended datasets
X_expanded = np.concatenate(
(TestLassoExtensions.X, TestLassoExtensions.X[TestLassoExtensions.n_samples // 2:]))
y_expanded = np.concatenate(
(TestLassoExtensions.y_2D_consistent,
TestLassoExtensions.y_2D_consistent[TestLassoExtensions.n_samples // 2:]))
# --> Check debiased coefficients
weighted_debiased_coefs = self._check_debiased_coefs(
TestLassoExtensions.X,
TestLassoExtensions.y_2D_consistent,
sample_weight=sample_weight,
expected_coefs=[TestLassoExtensions.coefs1, TestLassoExtensions.coefs2],
params=params)
expanded_debiased_coefs = self._check_debiased_coefs(
X_expanded, y_expanded, sample_weight=None,
expected_coefs=[TestLassoExtensions.coefs1, TestLassoExtensions.coefs2],
params=params)
for i in range(2):
self.assertTrue(np.allclose(weighted_debiased_coefs[i], expanded_debiased_coefs[i]))
def __init__(self,
model_y=WeightedLassoCVWrapper(), model_t='auto',
alpha='auto',
max_iter=1000,
tol=1e-4,
featurizer=None,
fit_cate_intercept=True,
linear_first_stages=True,
discrete_treatment=False,
n_splits=2,
random_state=None):
model_final = MultiOutputDebiasedLasso(
alpha=alpha,
fit_intercept=False,
max_iter=max_iter,
tol=tol)
super().__init__(model_y=model_y,
model_t=model_t,
model_final=model_final,
featurizer=featurizer,
fit_cate_intercept=fit_cate_intercept,
linear_first_stages=linear_first_stages,
discrete_treatment=discrete_treatment,
n_splits=n_splits,
random_state=random_state)
def _check_debiased_coefs(self,
X,
y,
sample_weight,
expected_coefs,
expected_intercept=0,
params={}):
debiased_lasso = MultiOutputDebiasedLasso(
) if np.ndim(y) > 1 else DebiasedLasso()
debiased_lasso.set_params(**params)
debiased_lasso.fit(X, y, sample_weight)
all_params = debiased_lasso.get_params()
# Check coeffcients and intercept are the same within tolerance
if np.ndim(y) > 1:
for i in range(y.shape[1]):
np.testing.assert_allclose(debiased_lasso.coef_[i],
expected_coefs[i],
atol=5e-2)
if all_params["fit_intercept"]:
self.assertAlmostEqual(debiased_lasso.intercept_[i],
expected_intercept[i],
delta=1e-2)
else:
np.testing.assert_allclose(debiased_lasso.coef_,
expected_coefs,
atol=5e-2)
if all_params["fit_intercept"]:
self.assertAlmostEqual(debiased_lasso.intercept_,
expected_intercept,
delta=1e-2)
return debiased_lasso.coef_
def _check_debiased_CI_2D(self,
X,
y,
sample_weight,
expected_coefs,
expected_intercept=0,
n_experiments=200,
params={}):
# Unit vectors
X_test = np.eye(TestLassoExtensions.n_dim)
y_test_mean = expected_intercept + expected_coefs.T
is_in_interval = np.zeros(
(y.shape[1], n_experiments, TestLassoExtensions.n_dim))
for i in range(n_experiments):
np.random.seed(i)
X_exp = np.random.normal(size=X.shape)
err = np.random.normal(scale=TestLassoExtensions.error_sd,
size=(X.shape[0], y.shape[1]))
y_exp = expected_intercept + np.dot(X_exp, expected_coefs.T) + err
debiased_lasso = MultiOutputDebiasedLasso()
debiased_lasso.set_params(**params)
debiased_lasso.fit(X_exp, y_exp, sample_weight)
y_lower, y_upper = debiased_lasso.predict_interval(X_test,
alpha=0.1)
for j in range(y.shape[1]):
is_in_interval[j,
i, :] = ((y_test_mean[:, j] >= y_lower[:, j]) &
(y_test_mean[:, j] <= y_upper[:, j]))
for i in range(y.shape[1]):
CI_coverage = np.mean(is_in_interval[i], axis=0)
self.assertTrue(all(CI_coverage >= 0.85))