Skip to content

REF: Minimize operations in recode_for_groupby #59618

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 1 commit into from
Aug 26, 2024
Merged

REF: Minimize operations in recode_for_groupby #59618

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 7 additions & 7 deletions pandas/core/groupby/categorical.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,9 +46,8 @@ def recode_for_groupby(c: Categorical, sort: bool, observed: bool) -> Categorica
# In cases with c.ordered, this is equivalent to
# return c.remove_unused_categories(), c

unique_codes = unique1d(c.codes) # type: ignore[no-untyped-call]
take_codes = unique1d(c.codes[c.codes != -1]) # type: ignore[no-untyped-call]

take_codes = unique_codes[unique_codes != -1]
if sort:
take_codes = np.sort(take_codes)

Expand All @@ -67,17 +66,18 @@ def recode_for_groupby(c: Categorical, sort: bool, observed: bool) -> Categorica

# sort=False should order groups in as-encountered order (GH-8868)

# xref GH:46909: Re-ordering codes faster than using (set|add|reorder)_categories
all_codes = np.arange(c.categories.nunique())
# GH:46909: Re-ordering codes faster than using (set|add|reorder)_categories
# GH 38140: exclude nan from indexer for categories
unique_notnan_codes = unique1d(c.codes[c.codes != -1]) # type: ignore[no-untyped-call]
if sort:
unique_notnan_codes = np.sort(unique_notnan_codes)
if len(all_codes) > len(unique_notnan_codes):
if (num_cat := len(c.categories)) > len(unique_notnan_codes):
# GH 13179: All categories need to be present, even if missing from the data
missing_codes = np.setdiff1d(all_codes, unique_notnan_codes, assume_unique=True)
missing_codes = np.setdiff1d(
np.arange(num_cat), unique_notnan_codes, assume_unique=True
)
take_codes = np.concatenate((unique_notnan_codes, missing_codes))
else:
take_codes = unique_notnan_codes

return Categorical(c, c.unique().categories.take(take_codes))
return Categorical(c, c.categories.take(take_codes))