Skip to content

GH1045 Split overload of groupby on as_index for all cases #1046

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
Nov 21, 2024
Merged

GH1045 Split overload of groupby on as_index for all cases #1046

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cb09ac2
GH1045 Split overload of groupby on as_index for all cases
loicdiridollou Nov 21, 2024
6db4aee
GH1045 PR Feedback
loicdiridollou Nov 21, 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
100 changes: 86 additions & 14 deletions pandas-stubs/core/frame.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1112,7 +1112,7 @@ class DataFrame(NDFrame, OpsMixin):
dropna: _bool = ...,
) -> DataFrameGroupBy[Timestamp, Literal[True]]: ...
@overload
def groupby(
def groupby( # pyright: ignore reportOverlappingOverload
self,
by: DatetimeIndex,
axis: AxisIndex | NoDefault = ...,
Expand All @@ -1124,77 +1124,149 @@ class DataFrame(NDFrame, OpsMixin):
dropna: _bool = ...,
) -> DataFrameGroupBy[Timestamp, Literal[False]]: ...
@overload
def groupby(
def groupby( # pyright: ignore reportOverlappingOverload
self,
by: TimedeltaIndex,
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: _bool = ...,
as_index: Literal[True] = True,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[Timedelta, bool]: ...
) -> DataFrameGroupBy[Timedelta, Literal[True]]: ...
@overload
def groupby(
self,
by: TimedeltaIndex,
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: Literal[False] = ...,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[Timedelta, Literal[False]]: ...
@overload
def groupby( # pyright: ignore reportOverlappingOverload
self,
by: PeriodIndex,
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: _bool = ...,
as_index: Literal[True] = True,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[Period, bool]: ...
) -> DataFrameGroupBy[Period, Literal[True]]: ...
@overload
def groupby(
self,
by: PeriodIndex,
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: Literal[False] = ...,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[Period, Literal[False]]: ...
@overload
def groupby( # pyright: ignore reportOverlappingOverload
self,
by: IntervalIndex[IntervalT],
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: _bool = ...,
as_index: Literal[True] = True,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[IntervalT, bool]: ...
) -> DataFrameGroupBy[IntervalT, Literal[True]]: ...
@overload
def groupby(
self,
by: IntervalIndex[IntervalT],
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: Literal[False] = ...,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[IntervalT, Literal[False]]: ...
@overload
def groupby( # type: ignore[overload-overlap] # pyright: ignore reportOverlappingOverload
self,
by: MultiIndex | GroupByObjectNonScalar | None = ...,
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: _bool = ...,
as_index: Literal[True] = True,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[tuple, bool]: ...
) -> DataFrameGroupBy[tuple, Literal[True]]: ...
@overload
def groupby( # type: ignore[overload-overlap]
self,
by: MultiIndex | GroupByObjectNonScalar | None = ...,
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: Literal[False] = ...,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[tuple, Literal[False]]: ...
@overload
def groupby( # pyright: ignore reportOverlappingOverload
self,
by: Series[SeriesByT],
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: Literal[True] = True,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[SeriesByT, Literal[True]]: ...
@overload
def groupby(
self,
by: Series[SeriesByT],
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: _bool = ...,
as_index: Literal[False] = ...,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[SeriesByT, Literal[False]]: ...
@overload
def groupby(
self,
by: CategoricalIndex | Index | Series,
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: Literal[True] = True,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[SeriesByT, bool]: ...
) -> DataFrameGroupBy[Any, Literal[True]]: ...
@overload
def groupby(
self,
by: CategoricalIndex | Index | Series,
axis: AxisIndex | NoDefault = ...,
level: IndexLabel | None = ...,
as_index: _bool = ...,
as_index: Literal[False] = ...,
sort: _bool = ...,
group_keys: _bool = ...,
observed: _bool | NoDefault = ...,
dropna: _bool = ...,
) -> DataFrameGroupBy[Any, bool]: ...
) -> DataFrameGroupBy[Any, Literal[False]]: ...
def pivot(
self,
*,
Expand Down
41 changes: 37 additions & 4 deletions tests/test_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -504,8 +504,8 @@ def test_types_mean() -> None:
s2: pd.Series = df.mean(axis=0)
df2: pd.DataFrame = df.groupby(level=0).mean()
if TYPE_CHECKING_INVALID_USAGE:
df3: pd.DataFrame = df.groupby(axis=1, level=0).mean() # type: ignore[call-overload] # pyright: ignore[reportArgumentType]
df4: pd.DataFrame = df.groupby(axis=1, level=0, dropna=True).mean() # type: ignore[call-overload] # pyright: ignore[reportArgumentType]
df3: pd.DataFrame = df.groupby(axis=1, level=0).mean() # type: ignore[call-overload] # pyright: ignore[reportArgumentType, reportCallIssue]
df4: pd.DataFrame = df.groupby(axis=1, level=0, dropna=True).mean() # type: ignore[call-overload] # pyright: ignore[reportArgumentType, reportCallIssue]
s3: pd.Series = df.mean(axis=1, skipna=True, numeric_only=False)


Expand All @@ -515,8 +515,8 @@ def test_types_median() -> None:
s2: pd.Series = df.median(axis=0)
df2: pd.DataFrame = df.groupby(level=0).median()
if TYPE_CHECKING_INVALID_USAGE:
df3: pd.DataFrame = df.groupby(axis=1, level=0).median() # type: ignore[call-overload] # pyright: ignore[reportArgumentType]
df4: pd.DataFrame = df.groupby(axis=1, level=0, dropna=True).median() # type: ignore[call-overload] # pyright: ignore[reportArgumentType]
df3: pd.DataFrame = df.groupby(axis=1, level=0).median() # type: ignore[call-overload] # pyright: ignore[reportArgumentType, reportCallIssue]
df4: pd.DataFrame = df.groupby(axis=1, level=0, dropna=True).median() # type: ignore[call-overload] # pyright: ignore[reportArgumentType, reportCallIssue]
s3: pd.Series = df.median(axis=1, skipna=True, numeric_only=False)


Expand Down Expand Up @@ -1064,6 +1064,39 @@ def test_types_groupby_as_index() -> None:
),
pd.Series,
)
check(
assert_type(
df.groupby("a").size(),
"pd.Series[int]",
),
pd.Series,
)


def test_types_groupby_as_index_list() -> None:
"""Test type of groupby.size method depending on list of grouper GH1045."""
df = pd.DataFrame({"a": [1, 1, 2], "b": [2, 3, 2]})
check(
assert_type(
df.groupby(["a", "b"], as_index=False).size(),
pd.DataFrame,
),
pd.DataFrame,
)
check(
assert_type(
df.groupby(["a", "b"], as_index=True).size(),
"pd.Series[int]",
),
pd.Series,
)
check(
assert_type(
df.groupby(["a", "b"]).size(),
"pd.Series[int]",
),
pd.Series,
)

Copy link
Collaborator

Choose a reason for hiding this comment

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

can you add a test that doesn't include the as_index argument?

Copy link
Member Author

Choose a reason for hiding this comment

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

Sorry the issue wasn't there, I did a bad copy paste so it was the same test.
Now the tests are different. which includes the test case from the issue.
As well I have added a third case in both tests where we don't specify as_index as you mentioned above.


def test_types_groupby_as_index_value_counts() -> None:
Expand Down
Loading