def test_LogisticRegression(sparse_X):
np.random.seed(1409)
X, y = build_dataset(
n_samples=30, n_features=60, sparse_X=sparse_X)
y = np.sign(y)
alpha_max = norm(X.T.dot(y), ord=np.inf) / 2
C = 30. / alpha_max
tol = 1e-8
clf1 = LogisticRegression(C=C, tol=tol, verbose=2)
clf1.fit(X, y)
clf2 = sklearn_Logreg(
C=C, penalty='l1', solver='liblinear', fit_intercept=False, tol=tol)
clf2.fit(X, y)
np.testing.assert_allclose(clf1.coef_, clf2.coef_, rtol=1e-3, atol=1e-5)
# this uses float32 so we increase the tol else there are precision issues
clf1.tol = 1e-4
check_estimator(clf1)
# multinomial test, need to have a slightly lower tol
# for results to be comparable
y = np.random.choice(4, len(y))
clf3 = LogisticRegression(C=C, tol=tol, verbose=2)
clf3.fit(X, y)
clf4 = sklearn_Logreg(
C=C, penalty='l1', solver='liblinear', fit_intercept=False, tol=tol)
clf4.fit(X, y)
np.testing.assert_allclose(clf3.coef_, clf4.coef_, rtol=1e-3, atol=1e-3)
clf3.tol = 1e-3
check_estimator(clf3)
def test_dropin_logreg():
np.random.seed(1409)
check_estimator(LogisticRegression)
X, y, _, _ = build_dataset(n_samples=100, n_features=100, sparse_X=True)
y = np.sign(y)
alpha_max = norm(X.T.dot(y), ord=np.inf) / 2
C = 30. / alpha_max
tol = 1e-8
clf1 = LogisticRegression(C=C, tol=tol)
clf1.fit(X, y)
clf2 = sklearn_Logreg(C=C,
penalty='l1',
solver='liblinear',
fit_intercept=False,
tol=tol)
clf2.fit(X, y)
np.testing.assert_allclose(clf1.coef_, clf2.coef_, rtol=1e-3, atol=1e-5)
# multinomial test:
y = np.random.choice(4, len(y))
clf3 = LogisticRegression(C=C, tol=tol)
clf3.fit(X, y)
clf4 = sklearn_Logreg(C=C,
penalty='l1',
solver='liblinear',
fit_intercept=False,
tol=tol)
clf4.fit(X, y)
np.testing.assert_allclose(clf3.coef_, clf4.coef_, rtol=1e-3, atol=1e-4)
def test_zero_iter():
X, y = build_dataset(n_samples=30, n_features=50)
# convergence warning is raised bc we return -1 as gap
with warnings.catch_warnings(record=True):
assert_allclose(Lasso(max_iter=0).fit(X, y).coef_, 0)
y = 2 * (y > 0) - 1
assert_allclose(
LogisticRegression(max_iter=0, solver="celer-pn").fit(X, y).coef_,
0)
assert_allclose(
LogisticRegression(max_iter=0, solver="celer").fit(X, y).coef_, 0)
def test_binary(sparse_X):
np.random.seed(1409)
X, y = build_dataset(n_samples=30, n_features=60, sparse_X=sparse_X)
y = np.sign(y)
alpha_max = norm(X.T.dot(y), ord=np.inf) / 2
C = 20. / alpha_max
clf = LogisticRegression(C=-1)
np.testing.assert_raises(ValueError, clf.fit, X, y)
tol = 1e-8
clf = LogisticRegression(C=C, tol=tol, verbose=0)
clf.fit(X, y)
clf_sk = sklearn_Logreg(C=C,
penalty='l1',
solver='liblinear',
fit_intercept=False,
tol=tol)
clf_sk.fit(X, y)
assert_allclose(clf.coef_, clf_sk.coef_, rtol=1e-3, atol=1e-5)
def test_multinomial(sparse_X):
np.random.seed(1409)
X, y = build_dataset(n_samples=30, n_features=60, sparse_X=sparse_X)
y = np.random.choice(4, len(y))
tol = 1e-8
clf = LogisticRegression(C=1, tol=tol, verbose=0)
clf.fit(X, y)
clf_sk = sklearn_Logreg(C=1,
penalty='l1',
solver='liblinear',
fit_intercept=False,
tol=tol)
clf_sk.fit(X, y)
assert_allclose(clf.coef_, clf_sk.coef_, rtol=1e-3, atol=1e-3)
def test_check_estimator(solver):
# sklearn fits on unnormalized data for which there are convergence issues
# fix with increased tolerance:
clf = LogisticRegression(C=1, solver=solver, tol=0.1)
check_estimator(clf)