Skip to content

REF: simplify aggregate_frame, column-name-pinning #51226

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 2 commits into from
Feb 8, 2023
Merged

REF: simplify aggregate_frame, column-name-pinning #51226

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1cd4037
REF: simplify aggregate_frame
jbrockmendel Feb 8, 2023
b554ab5
simplify column name-pinning
jbrockmendel Feb 8, 2023
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
37 changes: 8 additions & 29 deletions pandas/core/groupby/generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,11 +269,8 @@ def aggregate(self, func=None, *args, engine=None, engine_kwargs=None, **kwargs)
result = self._aggregate_named(func, *args, **kwargs)

# result is a dict whose keys are the elements of result_index
index = self.grouper.result_index
result = Series(result, index=index)
if not self.as_index:
result = self._insert_inaxis_grouper(result)
result.index = default_index(len(result))
result = Series(result, index=self.grouper.result_index)
result = self._wrap_aggregated_output(result)
return result

agg = aggregate
Expand Down Expand Up @@ -1314,19 +1311,9 @@ def aggregate(self, func=None, *args, engine=None, engine_kwargs=None, **kwargs)
result = self._aggregate_frame(func)

else:
sobj = self._selected_obj

if isinstance(sobj, Series):
# GH#35246 test_groupby_as_index_select_column_sum_empty_df
result.columns = self._obj_with_exclusions.columns.copy()
else:
# Retain our column names
result.columns._set_names(
sobj.columns.names, level=list(range(sobj.columns.nlevels))
)
# select everything except for the last level, which is the one
# containing the name of the function(s), see GH#32040
result.columns = result.columns.droplevel(-1)
# GH#32040, GH#35246
# e.g. test_groupby_as_index_select_column_sum_empty_df
result.columns = self._obj_with_exclusions.columns.copy()

if not self.as_index:
result = self._insert_inaxis_grouper(result)
Expand Down Expand Up @@ -1358,17 +1345,9 @@ def _aggregate_frame(self, func, *args, **kwargs) -> DataFrame:
obj = self._obj_with_exclusions

result: dict[Hashable, NDFrame | np.ndarray] = {}
if self.axis == 0:
# test_pass_args_kwargs_duplicate_columns gets here with non-unique columns
for name, data in self.grouper.get_iterator(obj, self.axis):
fres = func(data, *args, **kwargs)
result[name] = fres
else:
# we get here in a number of test_multilevel tests
for name in self.indices:
grp_df = self.get_group(name, obj=obj)
fres = func(grp_df, *args, **kwargs)
result[name] = fres
for name, grp_df in self.grouper.get_iterator(obj, self.axis):
fres = func(grp_df, *args, **kwargs)
result[name] = fres

result_index = self.grouper.result_index
other_ax = obj.axes[1 - self.axis]
Expand Down