def test_warm_start(fit_intercept):
n_samples, n_features = 110, 10
X, y = make_regression(
n_samples=n_samples,
n_features=n_features,
n_informative=n_features - 2,
noise=0.5,
random_state=42,
)
glm1 = _GeneralizedLinearRegressor(warm_start=False,
fit_intercept=fit_intercept,
max_iter=1000)
glm1.fit(X, y)
glm2 = _GeneralizedLinearRegressor(warm_start=True,
fit_intercept=fit_intercept,
max_iter=1)
# As we intentionally set max_iter=1, L-BFGS-B will issue a
# ConvergenceWarning which we here simply ignore.
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=ConvergenceWarning)
glm2.fit(X, y)
assert glm1.score(X, y) > glm2.score(X, y)
glm2.set_params(max_iter=1000)
glm2.fit(X, y)
# The two model are not exactly identical since the lbfgs solver
# computes the approximate hessian from previous iterations, which
# will not be strictly identical in the case of a warm start.
assert_allclose(glm1.coef_, glm2.coef_, rtol=1e-5)
assert_allclose(glm1.score(X, y), glm2.score(X, y), rtol=1e-4)
def test_glm_solver_argument(solver):
"""Test GLM for invalid solver argument."""
y = np.array([1, 2])
X = np.array([[1], [2]])
glm = _GeneralizedLinearRegressor(solver=solver)
with pytest.raises(ValueError):
glm.fit(X, y)
def test_glm_fit_intercept_argument(fit_intercept):
"""Test GLM for invalid fit_intercept argument."""
y = np.array([1, 2])
X = np.array([[1], [1]])
glm = _GeneralizedLinearRegressor(fit_intercept=fit_intercept)
with pytest.raises(ValueError, match="fit_intercept must be bool"):
glm.fit(X, y)
def test_glm_warm_start_argument(warm_start):
"""Test GLM for invalid warm_start argument."""
y = np.array([1, 2])
X = np.array([[1], [1]])
glm = _GeneralizedLinearRegressor(warm_start=warm_start)
with pytest.raises(ValueError, match="warm_start must be bool"):
glm.fit(X, y)
def test_normal_ridge_comparison(n_samples, n_features, fit_intercept,
sample_weight, request):
"""Compare with Ridge regression for Normal distributions."""
test_size = 10
X, y = make_regression(
n_samples=n_samples + test_size,
n_features=n_features,
n_informative=n_features - 2,
noise=0.5,
random_state=42,
)
if n_samples > n_features:
ridge_params = {"solver": "svd"}
else:
ridge_params = {"solver": "saga", "max_iter": 1000000, "tol": 1e-7}
(
X_train,
X_test,
y_train,
y_test,
) = train_test_split(X, y, test_size=test_size, random_state=0)
alpha = 1.0
if sample_weight is None:
sw_train = None
alpha_ridge = alpha * n_samples
else:
sw_train = np.random.RandomState(0).rand(len(y_train))
alpha_ridge = alpha * sw_train.sum()
# GLM has 1/(2*n) * Loss + 1/2*L2, Ridge has Loss + L2
ridge = Ridge(
alpha=alpha_ridge,
normalize=False,
random_state=42,
fit_intercept=fit_intercept,
**ridge_params,
)
ridge.fit(X_train, y_train, sample_weight=sw_train)
glm = _GeneralizedLinearRegressor(
alpha=alpha,
fit_intercept=fit_intercept,
max_iter=300,
tol=1e-5,
)
glm.fit(X_train, y_train, sample_weight=sw_train)
assert glm.coef_.shape == (X.shape[1], )
assert_allclose(glm.coef_, ridge.coef_, atol=5e-5)
assert_allclose(glm.intercept_, ridge.intercept_, rtol=1e-5)
assert_allclose(glm.predict(X_train), ridge.predict(X_train), rtol=2e-4)
assert_allclose(glm.predict(X_test), ridge.predict(X_test), rtol=2e-4)
def test_glm_identity_regression(fit_intercept):
"""Test GLM regression with identity link on a simple dataset."""
coef = [1.0, 2.0]
X = np.array([[1, 1, 1, 1, 1], [0, 1, 2, 3, 4]]).T
y = np.dot(X, coef)
glm = _GeneralizedLinearRegressor(
alpha=0,
fit_intercept=fit_intercept,
tol=1e-12,
)
if fit_intercept:
glm.fit(X[:, 1:], y)
assert_allclose(glm.coef_, coef[1:], rtol=1e-10)
assert_allclose(glm.intercept_, coef[0], rtol=1e-10)
else:
glm.fit(X, y)
assert_allclose(glm.coef_, coef, rtol=1e-12)
def test_sample_weights_validation():
"""Test the raised errors in the validation of sample_weight."""
# scalar value but not positive
X = [[1]]
y = [1]
weights = 0
glm = _GeneralizedLinearRegressor()
# Positive weights are accepted
glm.fit(X, y, sample_weight=1)
# 2d array
weights = [[0]]
with pytest.raises(ValueError, match="must be 1D array or scalar"):
glm.fit(X, y, weights)
# 1d but wrong length
weights = [1, 0]
msg = r"sample_weight.shape == \(2,\), expected \(1,\)!"
with pytest.raises(ValueError, match=msg):
glm.fit(X, y, weights)
def test_convergence_warning(regression_data):
X, y = regression_data
est = _GeneralizedLinearRegressor(max_iter=1, tol=1e-20)
with pytest.warns(ConvergenceWarning):
est.fit(X, y)