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_tolerance(filter_):
ridge = Ridge(tol=1e-5, fit_intercept=False)
ridge.fit(filter_(X_diabetes), y_diabetes)
score = ridge.score(filter_(X_diabetes), y_diabetes)
ridge2 = Ridge(tol=1e-3, fit_intercept=False)
ridge2.fit(filter_(X_diabetes), y_diabetes)
score2 = ridge2.score(filter_(X_diabetes), y_diabetes)
assert score >= score2
def test_sag_regressor():
"""tests if the sag regressor performs well"""
xmin, xmax = -5, 5
n_samples = 20
tol = .001
max_iter = 50
alpha = 0.1
rng = np.random.RandomState(0)
X = np.linspace(xmin, xmax, n_samples).reshape(n_samples, 1)
# simple linear function without noise
y = 0.5 * X.ravel()
clf1 = Ridge(tol=tol,
solver='sag',
max_iter=max_iter,
alpha=alpha * n_samples,
random_state=rng)
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
score1 = clf1.score(X, y)
score2 = clf2.score(X, y)
assert score1 > 0.99
assert score2 > 0.99
# simple linear function with noise
y = 0.5 * X.ravel() + rng.randn(n_samples, 1).ravel()
clf1 = Ridge(tol=tol,
solver='sag',
max_iter=max_iter,
alpha=alpha * n_samples)
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
score1 = clf1.score(X, y)
score2 = clf2.score(X, y)
score2 = clf2.score(X, y)
assert score1 > 0.5
assert score2 > 0.5
def test_ridge_singular():
# test on a singular matrix
rng = np.random.RandomState(0)
n_samples, n_features = 6, 6
y = rng.randn(n_samples // 2)
y = np.concatenate((y, y))
X = rng.randn(n_samples // 2, n_features)
X = np.concatenate((X, X), axis=0)
ridge = Ridge(alpha=0)
ridge.fit(X, y)
assert ridge.score(X, y) > 0.9
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)