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

Do not fail when an estimator misses class members that are new in v3 #757

Merged
merged 8 commits into from
Jan 31, 2024
Merged

Do not fail when an estimator misses class members that are new in v3 #757

Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
e86c62b
do not fail on missing class members that are new in v3
MatthiasSchmidtblaicherQC Jan 30, 2024
f87a772
simplify
MatthiasSchmidtblaicherQC Jan 30, 2024
8504c03
convert
MatthiasSchmidtblaicherQC Jan 30, 2024
04314cd
shorten the comment
MatthiasSchmidtblaicherQC Jan 30, 2024
bb155f7
simplify
MatthiasSchmidtblaicherQC Jan 30, 2024
f8532b6
don't use getattr unnecessarily
MatthiasSchmidtblaicherQC Jan 30, 2024
d0c9863
cosmetics
MatthiasSchmidtblaicherQC Jan 30, 2024
8e6e48f
fix unrelated typo
MatthiasSchmidtblaicherQC Jan 30, 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
31 changes: 22 additions & 9 deletions src/glum/_glm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -883,16 +883,23 @@ def _convert_from_pandas(
if hasattr(self, "X_model_spec_"):
return self.X_model_spec_.get_model_matrix(df, context=context)

cat_missing_method_after_alignment = self.cat_missing_method
cat_missing_method_after_alignment = getattr(self, "cat_missing_method", "fail")

if hasattr(self, "feature_dtypes_"):
df = _align_df_categories(
df,
self.feature_dtypes_,
self.has_missing_category_,
self.cat_missing_method,
getattr(
self,
"has_missing_category_",
{f: False for f in self.feature_dtypes_.keys()},
),
getattr(self, "cat_missing_method", "fail"),
)
if self.cat_missing_method == "convert":
if (
hasattr(self, "categorical_format")
and self.cat_missing_method == "convert"
):
df = _add_missing_categories(
df=df,
dtypes=self.feature_dtypes_,
Expand All @@ -906,7 +913,10 @@ def _convert_from_pandas(
X = tm.from_pandas(
df,
drop_first=self.drop_first,
categorical_format=self.categorical_format,
# prior to v3, categorical format used underscore
categorical_format=getattr(
self, "categorical_format", "{name}__{category}"
),
cat_missing_method=cat_missing_method_after_alignment,
)

Expand Down Expand Up @@ -2724,7 +2734,8 @@ def _set_up_and_check_fit_args(

self.feature_dtypes_ = X.dtypes.to_dict()
self.has_missing_category_ = {
col: (self.cat_missing_method == "convert") and X[col].isna().any()
col: (getattr(self, "cat_missing_method", "fail") == "convert")
and X[col].isna().any()
for col, dtype in self.feature_dtypes_.items()
if isinstance(dtype, pd.CategoricalDtype)
}
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Note that, because self.has_missing_category_ is created here, we don't need to use getattr(self, "has_missing_category_", ...) in 2789 and 2792 anymore.

Expand Down Expand Up @@ -2784,9 +2795,11 @@ def _expand_categorical_penalties(
X = tm.from_pandas(
X,
drop_first=self.drop_first,
categorical_format=self.categorical_format,
cat_missing_method=self.cat_missing_method,
cat_missing_name=self.cat_missing_name,
categorical_format=getattr(
self, "categorical_format", "{name}__{category}"
),
cat_missing_method=getattr(self, "cat_missing_method", "fail"),
cat_missing_name=getattr(self, "cat_missing_name", "(MISSING)"),
)

if y is None:
Expand Down
Loading