def test_n_iter():
# Test that self.n_iter_ is correct.
n_targets = 2
X, y = X_diabetes, y_diabetes
y_n = np.tile(y, (n_targets, 1)).T
for max_iter in range(1, 4):
for solver in ('sag', 'saga', 'lsqr'):
reg = Ridge(solver=solver, max_iter=max_iter, tol=1e-12)
reg.fit(X, y_n)
assert_array_equal(reg.n_iter_, np.tile(max_iter, n_targets))
for solver in ('sparse_cg', 'svd', 'cholesky'):
reg = Ridge(solver=solver, max_iter=1, tol=1e-1)
reg.fit(X, y_n)
assert reg.n_iter_ is None
def test_step_size_alpha_error():
X = [[0, 0], [0, 0]]
y = [1, -1]
fit_intercept = False
alpha = 1.
msg = ("Current sag implementation does not handle the case"
" step_size * alpha_scaled == 1")
clf1 = LogisticRegression(solver='sag',
C=1. / alpha,
fit_intercept=fit_intercept)
assert_raise_message(ZeroDivisionError, msg, clf1.fit, X, y)
clf2 = Ridge(fit_intercept=fit_intercept, solver='sag', alpha=alpha)
assert_raise_message(ZeroDivisionError, msg, clf2.fit, X, y)
def test_ovr_multilabel():
# Toy dataset where features correspond directly to labels.
X = np.array([[0, 4, 5], [0, 5, 0], [3, 3, 3], [4, 0, 6], [6, 0, 0]])
y = np.array([[0, 1, 1],
[0, 1, 0],
[1, 1, 1],
[1, 0, 1],
[1, 0, 0]])
for base_clf in (MultinomialNB(), LinearSVC(random_state=0),
LinearRegression(), Ridge(),
ElasticNet(), Lasso(alpha=0.5)):
clf = OneVsRestClassifier(base_clf).fit(X, y)
y_pred = clf.predict([[0, 4, 4]])[0]
assert_array_equal(y_pred, [0, 1, 1])
assert clf.multilabel_
def test_ridge_fit_intercept_sparse_sag():
X, y = _make_sparse_offset_regression(n_features=5,
n_samples=20,
random_state=0,
X_offset=5.)
X_csr = sp.csr_matrix(X)
params = dict(alpha=1.,
solver='sag',
fit_intercept=True,
tol=1e-10,
max_iter=100000)
dense_ridge = Ridge(**params)
sparse_ridge = Ridge(**params)
dense_ridge.fit(X, y)
with pytest.warns(None) as record:
sparse_ridge.fit(X_csr, y)
assert len(record) == 0
assert np.allclose(dense_ridge.intercept_,
sparse_ridge.intercept_,
rtol=1e-4)
assert np.allclose(dense_ridge.coef_, sparse_ridge.coef_, rtol=1e-4)
with pytest.warns(UserWarning, match='"sag" solver requires.*'):
Ridge(solver='sag').fit(X_csr, y)
def test_ridge_shapes():
# Test shape of coef_ and intercept_
rng = np.random.RandomState(0)
n_samples, n_features = 5, 10
X = rng.randn(n_samples, n_features)
y = rng.randn(n_samples)
Y1 = y[:, np.newaxis]
Y = np.c_[y, 1 + y]
ridge = Ridge()
ridge.fit(X, y)
assert ridge.coef_.shape == (n_features, )
assert ridge.intercept_.shape == ()
ridge.fit(X, Y1)
assert ridge.coef_.shape == (1, n_features)
assert ridge.intercept_.shape == (1, )
ridge.fit(X, Y)
assert ridge.coef_.shape == (2, n_features)
assert ridge.intercept_.shape == (2, )
def test_ridge_intercept():
# Test intercept with multiple targets GH issue #708
rng = np.random.RandomState(0)
n_samples, n_features = 5, 10
X = rng.randn(n_samples, n_features)
y = rng.randn(n_samples)
Y = np.c_[y, 1. + y]
ridge = Ridge()
ridge.fit(X, y)
intercept = ridge.intercept_
ridge.fit(X, Y)
assert_almost_equal(ridge.intercept_[0], intercept)
assert_almost_equal(ridge.intercept_[1], intercept + 1.)
def test_sag_pobj_matches_ridge_regression():
"""tests if the sag pobj matches ridge reg"""
n_samples = 100
n_features = 10
alpha = 1.0
n_iter = 100
fit_intercept = False
rng = np.random.RandomState(10)
X = rng.normal(size=(n_samples, n_features))
true_w = rng.normal(size=n_features)
y = X.dot(true_w)
clf1 = Ridge(fit_intercept=fit_intercept,
tol=.00000000001,
solver='sag',
alpha=alpha,
max_iter=n_iter,
random_state=42)
clf2 = clone(clf1)
clf3 = Ridge(fit_intercept=fit_intercept,
tol=.00001,
solver='lsqr',
alpha=alpha,
max_iter=n_iter,
random_state=42)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
clf3.fit(X, y)
pobj1 = get_pobj(clf1.coef_, alpha, X, y, squared_loss)
pobj2 = get_pobj(clf2.coef_, alpha, X, y, squared_loss)
pobj3 = get_pobj(clf3.coef_, alpha, X, y, squared_loss)
assert_array_almost_equal(pobj1, pobj2, decimal=4)
assert_array_almost_equal(pobj1, pobj3, decimal=4)
assert_array_almost_equal(pobj3, pobj2, decimal=4)
def test_ridgecv_sample_weight():
rng = np.random.RandomState(0)
alphas = (0.1, 1.0, 10.0)
# There are different algorithms for n_samples > n_features
# and the opposite, so test them both.
for n_samples, n_features in ((6, 5), (5, 10)):
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
sample_weight = 1.0 + rng.rand(n_samples)
cv = KFold(5)
ridgecv = RidgeCV(alphas=alphas, cv=cv)
ridgecv.fit(X, y, sample_weight=sample_weight)
# Check using GridSearchCV directly
parameters = {'alpha': alphas}
gs = GridSearchCV(Ridge(), parameters, cv=cv)
gs.fit(X, y, sample_weight=sample_weight)
assert ridgecv.alpha_ == gs.best_estimator_.alpha
assert_array_almost_equal(ridgecv.coef_, gs.best_estimator_.coef_)
def test_toy_ridge_object():
# Test BayesianRegression ridge classifier
# TODO: test also n_samples > n_features
X = np.array([[1], [2]])
Y = np.array([1, 2])
reg = Ridge(alpha=0.0)
reg.fit(X, Y)
X_test = [[1], [2], [3], [4]]
assert_almost_equal(reg.predict(X_test), [1., 2, 3, 4])
assert len(reg.coef_.shape) == 1
assert type(reg.intercept_) == np.float64
Y = np.vstack((Y, Y)).T
reg.fit(X, Y)
X_test = [[1], [2], [3], [4]]
assert len(reg.coef_.shape) == 2
assert type(reg.intercept_) == np.ndarray
def test_ridge_fit_intercept_sparse(solver):
X, y = _make_sparse_offset_regression(n_features=20, random_state=0)
X_csr = sp.csr_matrix(X)
# for now only sparse_cg can correctly fit an intercept with sparse X with
# default tol and max_iter.
# sag is tested separately in test_ridge_fit_intercept_sparse_sag
# because it requires more iterations and should raise a warning if default
# max_iter is used.
# other solvers raise an exception, as checked in
# test_ridge_fit_intercept_sparse_error
#
# "auto" should switch to "sparse_cg" when X is sparse
# so the reference we use for both ("auto" and "sparse_cg") is
# Ridge(solver="sparse_cg"), fitted using the dense representation (note
# that "sparse_cg" can fit sparse or dense data)
dense_ridge = Ridge(solver='sparse_cg')
sparse_ridge = Ridge(solver=solver)
dense_ridge.fit(X, y)
with pytest.warns(None) as record:
sparse_ridge.fit(X_csr, y)
assert len(record) == 0
assert np.allclose(dense_ridge.intercept_, sparse_ridge.intercept_)
assert np.allclose(dense_ridge.coef_, sparse_ridge.coef_)
def test_ovr_binary():
# Toy dataset where features correspond directly to labels.
X = np.array([[0, 0, 5], [0, 5, 0], [3, 0, 0], [0, 0, 6], [6, 0, 0]])
y = ["eggs", "spam", "spam", "eggs", "spam"]
Y = np.array([[0, 1, 1, 0, 1]]).T
classes = set("eggs spam".split())
def conduct_test(base_clf, test_predict_proba=False):
clf = OneVsRestClassifier(base_clf).fit(X, y)
assert set(clf.classes_) == classes
y_pred = clf.predict(np.array([[0, 0, 4]]))[0]
assert_array_equal(y_pred, ["eggs"])
if hasattr(base_clf, 'decision_function'):
dec = clf.decision_function(X)
assert dec.shape == (5,)
if test_predict_proba:
X_test = np.array([[0, 0, 4]])
probabilities = clf.predict_proba(X_test)
assert 2 == len(probabilities[0])
assert (clf.classes_[np.argmax(probabilities, axis=1)] ==
clf.predict(X_test))
# test input as label indicator matrix
clf = OneVsRestClassifier(base_clf).fit(X, Y)
y_pred = clf.predict([[3, 0, 0]])[0]
assert y_pred == 1
for base_clf in (LinearSVC(random_state=0), LinearRegression(),
Ridge(), ElasticNet()):
conduct_test(base_clf)
for base_clf in (MultinomialNB(), SVC(probability=True),
LogisticRegression()):
conduct_test(base_clf, test_predict_proba=True)
def test_ovr_multiclass():
# Toy dataset where features correspond directly to labels.
X = np.array([[0, 0, 5], [0, 5, 0], [3, 0, 0], [0, 0, 6], [6, 0, 0]])
y = ["eggs", "spam", "ham", "eggs", "ham"]
Y = np.array([[0, 0, 1],
[0, 1, 0],
[1, 0, 0],
[0, 0, 1],
[1, 0, 0]])
classes = set("ham eggs spam".split())
for base_clf in (MultinomialNB(), LinearSVC(random_state=0),
LinearRegression(), Ridge(),
ElasticNet()):
clf = OneVsRestClassifier(base_clf).fit(X, y)
assert set(clf.classes_) == classes
y_pred = clf.predict(np.array([[0, 0, 4]]))[0]
assert_array_equal(y_pred, ["eggs"])
# test input as label indicator matrix
clf = OneVsRestClassifier(base_clf).fit(X, Y)
y_pred = clf.predict([[0, 0, 4]])[0]
assert_array_equal(y_pred, [0, 0, 1])
def test_ridge_vs_lstsq():
# On alpha=0., Ridge and OLS yield the same solution.
rng = np.random.RandomState(0)
# we need more samples than features
n_samples, n_features = 5, 4
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=0., fit_intercept=False)
ols = LinearRegression(fit_intercept=False)
ridge.fit(X, y)
ols.fit(X, y)
assert_almost_equal(ridge.coef_, ols.coef_)
ridge.fit(X, y)
ols.fit(X, y)
assert_almost_equal(ridge.coef_, ols.coef_)
def test_raises_value_error_if_sample_weights_greater_than_1d():
# Sample weights must be either scalar or 1D
n_sampless = [2, 3]
n_featuress = [3, 2]
rng = np.random.RandomState(42)
for n_samples, n_features in zip(n_sampless, n_featuress):
X = rng.randn(n_samples, n_features)
y = rng.randn(n_samples)
sample_weights_OK = rng.randn(n_samples)**2 + 1
sample_weights_OK_1 = 1.
sample_weights_OK_2 = 2.
sample_weights_not_OK = sample_weights_OK[:, np.newaxis]
sample_weights_not_OK_2 = sample_weights_OK[np.newaxis, :]
ridge = Ridge(alpha=1)
# make sure the "OK" sample weights actually work
ridge.fit(X, y, sample_weights_OK)
ridge.fit(X, y, sample_weights_OK_1)
ridge.fit(X, y, sample_weights_OK_2)
def fit_ridge_not_ok():
ridge.fit(X, y, sample_weights_not_OK)
def fit_ridge_not_ok_2():
ridge.fit(X, y, sample_weights_not_OK_2)
assert_raise_message(ValueError,
"Sample weights must be 1D array or scalar",
fit_ridge_not_ok)
assert_raise_message(ValueError,
"Sample weights must be 1D array or scalar",
fit_ridge_not_ok_2)
def test_ridge(solver):
# Ridge regression convergence test using score
# TODO: for this test to be robust, we should use a dataset instead
# of np.random.
rng = np.random.RandomState(0)
alpha = 1.0
# With more samples than features
n_samples, n_features = 6, 5
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert ridge.coef_.shape == (X.shape[1], )
assert ridge.score(X, y) > 0.47
if solver in ("cholesky", "sag"):
# Currently the only solvers to support sample_weight.
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert ridge.score(X, y) > 0.47
# With more features than samples
n_samples, n_features = 5, 10
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert ridge.score(X, y) > .9
if solver in ("cholesky", "sag"):
# Currently the only solvers to support sample_weight.
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert ridge.score(X, y) > 0.9
def test_kernel_ridge():
pred = Ridge(alpha=1, fit_intercept=False).fit(X, y).predict(X)
pred2 = KernelRidge(kernel="linear", alpha=1).fit(X, y).predict(X)
assert_array_almost_equal(pred, pred2)
def test_kernel_ridge_csc():
pred = Ridge(alpha=1, fit_intercept=False,
solver="cholesky").fit(Xcsc, y).predict(Xcsc)
pred2 = KernelRidge(kernel="linear", alpha=1).fit(Xcsc, y).predict(Xcsc)
assert_array_almost_equal(pred, pred2)
def _test_ridge_diabetes(filter_):
ridge = Ridge(fit_intercept=False)
ridge.fit(filter_(X_diabetes), y_diabetes)
return np.round(ridge.score(filter_(X_diabetes), y_diabetes), 5)
def test_ridge_sparse_svd():
X = sp.csc_matrix(rng.rand(100, 10))
y = rng.rand(100)
ridge = Ridge(solver='svd', fit_intercept=False)
assert_raises(TypeError, ridge.fit, X, y)
def test_sparse_cg_max_iter():
reg = Ridge(solver="sparse_cg", max_iter=1)
reg.fit(X_diabetes, y_diabetes)
assert reg.coef_.shape[0] == X_diabetes.shape[1]