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_huber_better_r2_score():
# Test that huber returns a better r2 score than non-outliers"""
X, y = make_regression_with_outliers()
huber = HuberRegressor(alpha=0.01)
huber.fit(X, y)
linear_loss = np.dot(X, huber.coef_) + huber.intercept_ - y
mask = np.abs(linear_loss) < huber.epsilon * huber.scale_
huber_score = huber.score(X[mask], y[mask])
huber_outlier_score = huber.score(X[~mask], y[~mask])
# The Ridge regressor should be influenced by the outliers and hence
# give a worse score on the non-outliers as compared to the huber
# regressor.
ridge = Ridge(alpha=0.01)
ridge.fit(X, y)
ridge_score = ridge.score(X[mask], y[mask])
ridge_outlier_score = ridge.score(X[~mask], y[~mask])
assert huber_score > ridge_score
# The huber model should also fit poorly on the outliers.
assert ridge_outlier_score > huber_outlier_score