def test_get_auto_step_size():
X = np.array([[1, 2, 3], [2, 3, 4], [2, 3, 2]], dtype=np.float64)
alpha = 1.2
fit_intercept = False
# sum the squares of the second sample because that's the largest
max_squared_sum = 4 + 9 + 16
max_squared_sum_ = row_norms(X, squared=True).max()
n_samples = X.shape[0]
assert_almost_equal(max_squared_sum, max_squared_sum_, decimal=4)
for saga in [True, False]:
for fit_intercept in (True, False):
if saga:
L_sqr = max_squared_sum + alpha + int(fit_intercept)
L_log = (max_squared_sum + 4.0 * alpha +
int(fit_intercept)) / 4.0
mun_sqr = min(2 * n_samples * alpha, L_sqr)
mun_log = min(2 * n_samples * alpha, L_log)
step_size_sqr = 1 / (2 * L_sqr + mun_sqr)
step_size_log = 1 / (2 * L_log + mun_log)
else:
step_size_sqr = 1.0 / (max_squared_sum + alpha +
int(fit_intercept))
step_size_log = 4.0 / (max_squared_sum + 4.0 * alpha +
int(fit_intercept))
step_size_sqr_ = get_auto_step_size(
max_squared_sum_,
alpha,
"squared",
fit_intercept,
n_samples=n_samples,
is_saga=saga,
)
step_size_log_ = get_auto_step_size(
max_squared_sum_,
alpha,
"log",
fit_intercept,
n_samples=n_samples,
is_saga=saga,
)
assert_almost_equal(step_size_sqr, step_size_sqr_, decimal=4)
assert_almost_equal(step_size_log, step_size_log_, decimal=4)
msg = "Unknown loss function for SAG solver, got wrong instead of"
with pytest.raises(ValueError, match=msg):
get_auto_step_size(max_squared_sum_, alpha, "wrong", fit_intercept)
tol=tol,
solver="lbfgs",
fit_intercept=fit_intercept), lbfgs_iter_range, [],
[], [], []),
("SGD",
SGDClassifier(alpha=1.0 / C / n_samples,
penalty='l2',
loss='log',
fit_intercept=fit_intercept,
verbose=0), sgd_iter_range, [], [], [], [])]
if lightning_clf is not None and not fit_intercept:
alpha = 1. / C / n_samples
# compute the same step_size than in LR-sag
max_squared_sum = get_max_squared_sum(X)
step_size = get_auto_step_size(max_squared_sum, alpha, "log",
fit_intercept)
clfs.append(("Lightning-SVRG",
lightning_clf.SVRGClassifier(alpha=alpha,
eta=step_size,
tol=tol,
loss="log"), sag_iter_range, [],
[], [], []))
clfs.append(("Lightning-SAG",
lightning_clf.SAGClassifier(alpha=alpha,
eta=step_size,
tol=tol,
loss="log"), sag_iter_range, [],
[], [], []))
# We keep only 200 features, to have a dense dataset,
