8000 [MRG + 1] ElasticNetCV: raise ValueError if l1_ratio=0 by erikcs · Pull Request #7591 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

[MRG + 1] ElasticNetCV: raise ValueError if l1_ratio=0 #7591

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 13 commits into from
Oct 25, 2016
Merged

[MRG + 1] ElasticNetCV: raise ValueError if l1_ratio=0 #7591

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
1671707
Raise ValueError if l1_ratio=0
erikcs Oct 15, 2016
b6b78c4
Add test
erikcs Oct 16, 2016
3fa201b
Add test - fix typo
erikcs Oct 16, 2016
02f0d4d
Extend test
erikcs Oct 17, 2016
6b81830
Blank commit to restart AppVeyor
erikcs Oct 17, 2016
8bf6966
Same as test passing commit #3fa201b with diff commmented out
erikcs Oct 17, 2016
5171932
Recommit extended test (with warnings supressed)
erikcs Oct 17, 2016
043e6a6
See what happens with different assert_almost_equal function
erikcs Oct 17, 2016
fc4f570
Trigger build one more time
erikcs Oct 18, 2016
0122cc0 8000
Replace weird expression
erikcs Oct 18, 2016
2842246
Try and trigger build one more time
erikcs Oct 23, 2016
6de9d1a
Add random state to test
erikcs Oct 24, 2016
50b1b36
Add random state to failed test, test_logistic_regression_sample_weights
erikcs Oct 24, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 9 additions & 4 deletions sklearn/linear_model/coordinate_descent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,10 +49,10 @@ def _alpha_grid(X, y, Xy=None, l1_ratio=1.0, fit_intercept=True,
Xy = np.dot(X.T, y) that can be precomputed.

l1_ratio : float
The elastic net mixing parameter, with ``0 <= l1_ratio <= 1``.
For ``l1_ratio = 0`` the penalty is an L2 penalty. ``For
l1_ratio = 1`` it is an L1 penalty. For ``0 < l1_ratio <
1``, the penalty is a combination of L1 and L2.
The elastic net mixing parameter, with ``0 < l1_ratio <= 1``.
For ``l1_ratio = 0`` the penalty is an L2 penalty. (currently not
supported) ``For l1_ratio = 1`` it is an L1 penalty. For
``0 < l1_ratio <1``, the penalty is a combination of L1 and L2.

eps : float, optional
Length of the path. ``eps=1e-3`` means that
Expand All @@ -77,6 +77,11 @@ def _alpha_grid(X, y, Xy=None, l1_ratio=1.0, fit_intercept=True,
copy_X : boolean, optional, default True
If ``True``, X will be copied; else, it may be overwritten.
"""
if l1_ratio == 0:
raise ValueError("Automatic alpha grid generation is not supported for"
" l1_ratio=0. Please supply a grid by providing "
"your estimator with the appropriate `alphas=` "
"argument.")
n_samples = len(y)

sparse_center = False
Expand Down
33 changes: 33 additions & 0 deletions sklearn/linear_model/tests/test_coordinate_descent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
from sklearn.utils.testing import assert_greater
from sklearn.utils.testing import assert_raises
from sklearn.utils.testing import assert_raises_regex
from sklearn.utils.testing import assert_raise_message
from sklearn.utils.testing import assert_warns
from sklearn.utils.testing import assert_warns_message
from sklearn.utils.testing import ignore_warnings
Expand Down Expand Up @@ -712,3 +713,35 @@ def test_enet_float_precision():
assert_array_almost_equal(intercept[np.float32],
intercept[np.float64],
decimal=4)


def test_enet_l1_ratio():
# Test that an error message is raised if an estimator that
# uses _alpha_grid is called with l1_ratio=0
msg = ("Automatic alpha grid generation is not supported for l1_ratio=0. "
"Please supply a grid by providing your estimator with the "
"appropriate `alphas=` argument.")
X = np.array([[1, 2, 4, 5, 8], [3, 5, 7, 7, 8]]).T
y = np.array([12, 10, 11, 21, 5])

assert_raise_message(ValueError, msg, ElasticNetCV(
l1_ratio=0, random_state=42).fit, X, y)
assert_raise_message(ValueError, msg, MultiTaskElasticNetCV(
l1_ratio=0, random_state=42).fit, X, y[:, None])

# Test that l1_ratio=0 is allowed if we supply a grid manually
alphas = [0.1, 10]
estkwds = {'alphas': alphas, 'random_state': 42}
est_desired = ElasticNetCV(l1_ratio=0.00001, **estkwds)
est = ElasticNetCV(l1_ratio=0, **estkwds)
with ignore_warnings():
est_desired.fit(X, y)
est.fit(X, y)
assert_array_almost_equal(est.coef_, est_desired.coef_, decimal=5)

est_desired = MultiTaskElasticNetCV(l1_ratio=0.00001, **estkwds)
est = MultiTaskElasticNetCV(l1_ratio=0, **estkwds)
with ignore_warnings():
est.fit(X, y[:, None])
est_desired.fit(X, y[:, None])
assert_array_almost_equal(est.coef_, est_desired.coef_, decimal=5)
30 changes: 18 additions & 12 deletions sklearn/linear_model/tests/test_logistic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -588,24 +588,28 @@ def test_logistic_regression_sample_weights():
# Test that passing sample_weight as ones is the same as
# not passing them at all (default None)
for solver in ['lbfgs', 'liblinear']:
clf_sw_none = LR(solver=solver, fit_intercept=False)
clf_sw_none = LR(solver=solver, fit_intercept=False,
random_state=42)
clf_sw_none.fit(X, y)
clf_sw_ones = LR(solver=solver, fit_intercept=False)
clf_sw_ones = LR(solver=solver, fit_intercept=False,
random_state=42)
clf_sw_ones.fit(X, y, sample_weight=np.ones(y.shape[0]))
assert_array_almost_equal(
clf_sw_none.coef_, clf_sw_ones.coef_, decimal=4)

# Test that sample weights work the same with the lbfgs,
# newton-cg, and 'sag' solvers
clf_sw_lbfgs = LR(solver='lbfgs', fit_intercept=False)
clf_sw_lbfgs = LR(solver='lbfgs', fit_intercept=False, random_state=42)
clf_sw_lbfgs.fit(X, y, sample_weight=sample_weight)
clf_sw_n = LR(solver='newton-cg', fit_intercept=False)
clf_sw_n = LR(solver='newton-cg', fit_intercept=False, random_state=42)
clf_sw_n.fit(X, y, sample_weight=sample_weight)
clf_sw_sag = LR(solver='sag', fit_intercept=False, tol=1e-10)
clf_sw_sag = LR(solver='sag', fit_intercept=False, tol=1e-10,
random_state=42)
# ignore convergence warning due to small dataset
with ignore_warnings():
clf_sw_sag.fit(X, y, sample_weight=sample_weight)
clf_sw_liblinear = LR(solver='liblinear', fit_intercept=False)
clf_sw_liblinear = LR(solver='liblinear', fit_intercept=False,
random_state=42)
clf_sw_liblinear.fit(X, y, sample_weight=sample_weight)
assert_array_almost_equal(
clf_sw_lbfgs.coef_, clf_sw_n.coef_, decimal=4)
Expand All @@ -619,9 +623,9 @@ def test_logistic_regression_sample_weights():
# to be 2 for all instances of class 2
for solver in ['lbfgs', 'liblinear']:
clf_cw_12 = LR(solver=solver, fit_intercept=False,
class_weight={0: 1, 1: 2})
class_weight={0: 1, 1: 2}, random_state=42)
clf_cw_12.fit(X, y)
clf_sw_12 = LR(solver=solver, fit_intercept=False)
clf_sw_12 = LR(solver=solver, fit_intercept=False, random_state=42)
clf_sw_12.fit(X, y, sample_weight=sample_weight)
assert_array_almost_equal(
clf_cw_12.coef_, clf_sw_12.coef_, decimal=4)
Expand All @@ -630,19 +634,21 @@ def test_logistic_regression_sample_weights():
# since the patched liblinear code is different.
clf_cw = LogisticRegression(
solver="liblinear", fit_intercept=False, class_weight={0: 1, 1: 2},
penalty="l1", tol=1e-5)
penalty="l1", tol=1e-5, random_state=42)
clf_cw.fit(X, y)
clf_sw = LogisticRegression(
solver="liblinear", fit_intercept=False, penalty="l1", tol=1e-5)
solver="liblinear", fit_intercept=False, penalty="l1", tol=1e-5,
random_state=42)
clf_sw.fit(X, y, sample_weight)
assert_array_almost_equal(clf_cw.coef_, clf_sw.coef_, decimal=4)

clf_cw = LogisticRegression(
solver="liblinear", fit_intercept=False, class_weight={0: 1, 1: 2},
penalty="l2", dual=True)
penalty="l2", dual=True, random_state=42)
clf_cw.fit(X, y)
clf_sw = LogisticRegression(
solver="liblinear", fit_intercept=False, penalty="l2", dual=True)
solver="liblinear", fit_intercept=False, penalty="l2", dual=True,
random_state=42)
clf_sw.fit(X, y, sample_weight)
assert_array_almost_equal(clf_cw.coef_, clf_sw.coef_, decimal=4)

Expand Down
0