def test_regression_corrupted_weights(weighting):
reg = RobustWeightedRegressor(
max_iter=100,
weighting=weighting,
k=5,
c=1,
burn_in=0,
random_state=rng,
)
reg.fit(X_rc, y_rc)
assert reg.weights_[0] < np.mean(reg.weights_[1:])
def test_corrupted_regression(loss, weighting, k, c):
reg = RobustWeightedRegressor(
loss=loss,
max_iter=50,
weighting=weighting,
k=k,
c=None,
random_state=rng,
)
reg.fit(X_rc, y_rc)
score = median_absolute_error(reg.predict(X_rc), y_rc)
assert score < 0.2
def test_corrupted_regression(loss, weighting, k, c):
reg = RobustWeightedRegressor(
loss=loss,
max_iter=50,
weighting=weighting,
k=k,
c=c,
random_state=rng,
n_iter_no_change=20,
)
reg.fit(X_rc, y_rc)
assert np.abs(reg.coef_[0] - 1) < 0.1
assert np.abs(reg.intercept_[0]) < 0.1
def test_vs_huber():
reg1 = RobustWeightedRegressor(
max_iter=100,
weighting="huber",
k=5,
c=1,
burn_in=0,
sgd_args={"learning_rate": "adaptive"}, # test sgd_args
random_state=rng,
)
reg2 = HuberRegressor()
reg1.fit(X_rcy, y_rcy)
reg2.fit(X_rcy, y_rcy)
assert np.abs(reg1.coef_[0] - reg2.coef_[0]) < 1e-2
def test_not_robust_regression(loss, weighting):
clf = RobustWeightedRegressor(
loss=loss,
max_iter=100,
weighting=weighting,
k=0,
c=1e7,
burn_in=0,
random_state=rng,
)
clf_not_rob = SGDRegressor(loss=loss, random_state=rng)
clf.fit(X_r, y_r)
clf_not_rob.fit(X_r, y_r)
pred1 = clf.predict(X_r)
pred2 = clf_not_rob.predict(X_r)
difference = [
np.linalg.norm(pred1[i] - pred2[i]) for i in range(len(pred1))
]
assert np.mean(difference) < 1e-1
def test_not_robust_regression(loss, weighting):
reg = RobustWeightedRegressor(
loss=loss,
max_iter=100,
weighting=weighting,
k=0,
c=1e7,
burn_in=0,
random_state=rng,
)
reg_not_rob = SGDRegressor(loss=loss, random_state=rng)
reg.fit(X_r, y_r)
reg_not_rob.fit(X_r, y_r)
pred1 = reg.predict(X_r)
pred2 = reg_not_rob.predict(X_r)
difference = [
np.linalg.norm(pred1[i] - pred2[i]) for i in range(len(pred1))
]
assert np.mean(difference) < 1
assert_almost_equal(reg.score(X_r, y_r), r2_score(y_r, reg.predict(X_r)))