def fit(self, X, y):
corr_coefs = np.abs(r_regression(X, y))
cols_to_drop = np.where(corr_coefs <= self.threshold)[0]
if self.verbose:
print(f"Threshold = {self.threshold}")
print(f"Dropping {len(cols_to_drop)} of {X.shape[1]} columns")
print(f"Columns dropped: {self.col_names[cols_to_drop]}")
self.cols_to_drop = cols_to_drop
def test_r_regression(center):
X, y = make_regression(n_samples=2000, n_features=20, n_informative=5,
shuffle=False, random_state=0)
corr_coeffs = r_regression(X, y, center=center)
assert ((-1 < corr_coeffs).all())
assert ((corr_coeffs < 1).all())
sparse_X = _convert_container(X, "sparse")
sparse_corr_coeffs = r_regression(sparse_X, y, center=center)
assert_allclose(sparse_corr_coeffs, corr_coeffs)
# Testing against numpy for reference
Z = np.hstack((X, y[:, np.newaxis]))
correlation_matrix = np.corrcoef(Z, rowvar=False)
np_corr_coeffs = correlation_matrix[:-1, -1]
assert_array_almost_equal(np_corr_coeffs, corr_coeffs, decimal=3)
def test_r_regression_force_finite(X, y, expected_corr_coef, force_finite):
"""Check the behaviour of `force_finite` for some corner cases with `r_regression`.
Non-regression test for:
https://github.com/scikit-learn/scikit-learn/issues/15672
"""
with warnings.catch_warnings():
warnings.simplefilter("error", RuntimeWarning)
corr_coef = r_regression(X, y, force_finite=force_finite)
np.testing.assert_array_almost_equal(corr_coef, expected_corr_coef)
def test_r_regression_force_finite(X, y, expected_corr_coef, force_finite):
"""Check the behaviour of `force_finite` for some corner cases with `r_regression`.
Non-regression test for:
https://github.com/scikit-learn/scikit-learn/issues/15672
"""
with pytest.warns(None) as records:
corr_coef = r_regression(X, y, force_finite=force_finite)
assert not [str(w.message) for w in records]
np.testing.assert_array_almost_equal(corr_coef, expected_corr_coef)