def test_RobustLinearRegression_warm_start(self):
"""...Test RobustLinearRegression warm start
"""
X, y, weights0, interc0, sample_intercepts0 = self.get_train_data(True)
fit_intercepts = [True, False]
cases = itertools.product(RobustLinearRegression._solvers.keys(),
fit_intercepts)
for solver, fit_intercept in cases:
solver_kwargs = {
'C_sample_intercepts': Test.n_samples / Test.noise_level,
'solver': solver,
'max_iter': 2,
'verbose': False,
'fit_intercept': fit_intercept,
'warm_start': True,
'tol': 0
}
learner = RobustLinearRegression(**solver_kwargs)
learner.fit(X, y)
coeffs_1 = learner.coeffs
learner.fit(X, y)
coeffs_2 = learner.coeffs
# Thanks to warm start objective should have decreased
self.assertLess(learner._solver_obj.objective(coeffs_2),
learner._solver_obj.objective(coeffs_1))
def test_RobustLinearRegression_fit(self):
"""...Test RobustLinearRegression fit with different solvers and penalties
"""
X, y, weights0, interc0, sample_intercepts0 = self.get_train_data(True)
solvers = RobustLinearRegression._solvers.keys()
for i, solver in enumerate(solvers):
learner_keywords = {
'C_sample_intercepts': Test.n_samples / Test.noise_level,
'fit_intercept': True,
'fdr': Test.target_fdr,
'max_iter': 3000,
'tol': 1e-7,
'solver': solver,
'penalty': 'none',
'verbose': False
}
learner = RobustLinearRegression(**learner_keywords)
learner.fit(X, y)
weights = [
1.82145051, 2.32011366, 2.6886905, 2.53289584, 2.86991904
]
interc = -2.9877245464563931
fdp_ = 0.23076923076923078
power = 1.0
np.testing.assert_array_almost_equal(weights, learner.weights, 2)
self.assertAlmostEqual(interc, learner.intercept, 2)
self.assertAlmostEqual(
fdp_, support_fdp(sample_intercepts0,
learner.sample_intercepts), 4)
self.assertAlmostEqual(
power,
support_recall(sample_intercepts0, learner.sample_intercepts),
4)
X, y, weights0, interc0, sample_intercepts0 = self.get_train_data(
False)
for i, solver in enumerate(solvers):
learner_keywords = {
'C_sample_intercepts': Test.n_samples / Test.noise_level,
'fit_intercept': False,
'fdr': Test.target_fdr,
'max_iter': 3000,
'tol': 1e-7,
'solver': solver,
'verbose': False
}
learner = RobustLinearRegression(**learner_keywords)
learner.fit(X, y)
weights = [
1.82341444, 2.3226882, 2.68081823, 2.53942366, 2.86439685
]
interc = None
fdp_ = 0.23076923076923078
power = 1.0
np.testing.assert_array_almost_equal(weights, learner.weights, 2)
self.assertEqual(interc, learner.intercept)
self.assertAlmostEqual(
fdp_, support_fdp(sample_intercepts0,
learner.sample_intercepts), 4)
self.assertAlmostEqual(
power,
support_recall(sample_intercepts0, learner.sample_intercepts),
4)
sample_intercepts0[idx_nnz] = outliers_intensity * np.sqrt(2 * log_linspace) \
* np.sign(sample_intercepts0[idx_nnz])
X = features_normal_cov_toeplitz(n_samples, n_features, 0.5)
y = X.dot(weights0) + noise_level * np.random.randn(n_samples) \
+ intercept0 + sample_intercepts0
target_fdr = 0.1
noise_level = std_iqr(y)
learner = RobustLinearRegression(C_sample_intercepts=2 * n_samples /
noise_level,
penalty='none',
fdr=target_fdr,
verbose=False)
learner.fit(X, y)
fdp_ = support_fdp(sample_intercepts0, learner.sample_intercepts)
power_ = support_recall(sample_intercepts0, learner.sample_intercepts)
fig = plt.figure(figsize=(7, 6))
titles = [
'Model weights', 'Learned weights', 'Sample intercepts',
'Learned intercepts'
]
vectors = [
weights0, learner.weights, sample_intercepts0, learner.sample_intercepts
]
for idx_plot, title, vector in zip(range(221, 225), titles, vectors):
ax = fig.add_subplot(idx_plot)
ax.stem(vector)