Skip to content
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

Correctly expand penalties with categoricals and cat_missing_method="convert" #753

Merged
merged 3 commits into from
Jan 29, 2024
Merged

Correctly expand penalties with categoricals and cat_missing_method="convert" #753

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
389cb70
Correctyl expand penalties when cat_missing_method=convert
stanmart Jan 25, 2024
7ddc9c2
Add test
stanmart Jan 25, 2024
745c5c4
Improve variable names
stanmart Jan 29, 2024
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
22 changes: 17 additions & 5 deletions src/glum/_glm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2717,7 +2717,9 @@ def _set_up_and_check_fit_args(

if any(X.dtypes == "category"):

def _expand_categorical_penalties(penalty, X, drop_first):
def _expand_categorical_penalties(
penalty, X, drop_first, has_missing_category
):
"""
If P1 or P2 has the same shape as X before expanding the
categoricals, we assume that the penalty at the location of
Expand All @@ -2741,19 +2743,29 @@ def _expand_categorical_penalties(penalty, X, drop_first):
chain.from_iterable(
[
elmt
for _ in dtype.categories[int(drop_first) :]
for _ in range(
len(dtype.categories)
+ has_missing_category[col]
- drop_first
)
]
if pd.api.types.is_categorical_dtype(dtype)
else [elmt]
for elmt, dtype in zip(penalty, X.dtypes)
for elmt, (col, dtype) in zip(
penalty, X.dtypes.items()
)
)
)
)
else:
return penalty

P1 = _expand_categorical_penalties(self.P1, X, self.drop_first)
P2 = _expand_categorical_penalties(self.P2, X, self.drop_first)
P1 = _expand_categorical_penalties(
self.P1, X, self.drop_first, self.has_missing_category_
)
P2 = _expand_categorical_penalties(
self.P2, X, self.drop_first, self.has_missing_category_
)

X = tm.from_pandas(
X,
Expand Down
39 changes: 38 additions & 1 deletion tests/glm/test_glm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@


def get_small_x_y(
estimator: Union[GeneralizedLinearRegressor, GeneralizedLinearRegressorCV]
estimator: Union[GeneralizedLinearRegressor, GeneralizedLinearRegressorCV],
) -> tuple[np.ndarray, np.ndarray]:
if isinstance(estimator, GeneralizedLinearRegressor):
n_rows = 1
Expand Down Expand Up @@ -362,6 +362,43 @@ def test_P1_P2_expansion_with_categoricals():
np.testing.assert_allclose(mdl1.coef_, mdl2.coef_)


def test_P1_P2_expansion_with_categoricals_missings():
rng = np.random.default_rng(42)
X = pd.DataFrame(
data={
"dense": np.linspace(0, 10, 60),
"cat": pd.Categorical(rng.integers(5, size=60)).remove_categories(0),
}
)
y = rng.normal(size=60)

mdl1 = GeneralizedLinearRegressor(
l1_ratio=0.01,
P1=[1, 2, 2, 2, 2, 2],
P2=[2, 1, 1, 1, 1, 1],
cat_missing_method="convert",
)
mdl1.fit(X, y)

mdl2 = GeneralizedLinearRegressor(
l1_ratio=0.01,
P1=[1, 2],
P2=[2, 1],
cat_missing_method="convert",
)
mdl2.fit(X, y)
np.testing.assert_allclose(mdl1.coef_, mdl2.coef_)

mdl3 = GeneralizedLinearRegressor(
l1_ratio=0.01,
P1=[1, 2],
P2=sparse.diags([2, 1, 1, 1, 1, 1]),
cat_missing_method="convert",
)
mdl3.fit(X, y)
np.testing.assert_allclose(mdl1.coef_, mdl3.coef_)


@pytest.mark.parametrize(
"estimator", [GeneralizedLinearRegressor, GeneralizedLinearRegressorCV]
)
Expand Down
Loading