Skip to content

GH1217 Modify items/iterros/itertuples methods to return Iterator #1225

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 5 commits into from
May 21, 2025
Merged

GH1217 Modify items/iterros/itertuples methods to return Iterator #1225

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
fe68e48
GH1217 Modify items/iterros/itertuples methods to return Iterator
loicdiridollou May 19, 2025
6d15f0c
GH1217 PR feedback
loicdiridollou May 20, 2025
5a7fe40
GH1217 PR feedback
loicdiridollou May 20, 2025
1f91170
GH1217 PR feedback
loicdiridollou May 21, 2025
d0a5bf2
GH1217 PR feedback
loicdiridollou May 21, 2025
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
8 changes: 4 additions & 4 deletions pandas-stubs/core/frame.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -328,16 +328,16 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
def shape(self) -> tuple[int, int]: ...
@property
def style(self) -> Styler: ...
def items(self) -> Iterable[tuple[Hashable, Series]]: ...
def iterrows(self) -> Iterable[tuple[Hashable, Series]]: ...
def items(self) -> Iterator[tuple[Hashable, Series]]: ...
def iterrows(self) -> Iterator[tuple[Hashable, Series]]: ...
@overload
def itertuples(
self, index: _bool = ..., name: _str = ...
) -> Iterable[_PandasNamedTuple]: ...
) -> Iterator[_PandasNamedTuple]: ...
@overload
def itertuples(
self, index: _bool = ..., name: None = None
) -> Iterable[tuple[Any, ...]]: ...
) -> Iterator[tuple[Any, ...]]: ...
def __len__(self) -> int: ...
@overload
def dot(self, other: DataFrame | ArrayLike) -> Self: ...
Expand Down
2 changes: 1 addition & 1 deletion pandas-stubs/core/series.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -615,7 +615,7 @@ class Series(IndexOpsMixin[S1], NDFrame):
mode: Literal["w"] = ...,
) -> _str: ...
def to_xarray(self) -> xr.DataArray: ...
def items(self) -> Iterable[tuple[Hashable, S1]]: ...
def items(self) -> Iterator[tuple[Hashable, S1]]: ...
def keys(self) -> Index: ...
@overload
def to_dict(self, *, into: type[dict] = ...) -> dict[Any, S1]: ...
Expand Down
29 changes: 22 additions & 7 deletions tests/test_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -599,32 +599,47 @@ def test_types_median() -> None:
def test_types_iterrows() -> None:
df = pd.DataFrame(data={"col1": [2, 1], "col2": [3, 4]})
check(
assert_type(df.iterrows(), "Iterable[tuple[Hashable, pd.Series]]"),
assert_type(df.iterrows(), "Iterator[tuple[Hashable, pd.Series]]"),
Iterable,
tuple,
)
Comment on lines 601 to 605
Copy link
Collaborator

Choose a reason for hiding this comment

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

Can we add a test of this form for iterrows() and itertuples():

for t1, t2 in df.iterrows():
    check(assert_type(t1, Hashable), Hashable)
    check(assert_type(t2, pd.Series), pd.Series)

for t1, t2 in df.iterrows():
check(assert_type(t1, Hashable), Hashable)
check(assert_type(t2, pd.Series), pd.Series)


def test_types_itertuples() -> None:
df = pd.DataFrame(data={"col1": [2, 1], "col2": [3, 4]})
check(
assert_type(df.itertuples(), Iterable[_PandasNamedTuple]),
Iterable,
assert_type(df.itertuples(), Iterator[_PandasNamedTuple]),
Iterator,
_PandasNamedTuple,
)
check(
assert_type(
df.itertuples(index=False, name="Foobar"), Iterable[_PandasNamedTuple]
df.itertuples(index=False, name="Foobar"), Iterator[_PandasNamedTuple]
),
Iterable,
Iterator,
_PandasNamedTuple,
)
check(
assert_type(df.itertuples(index=False, name=None), Iterable[tuple[Any, ...]]),
Iterable,
assert_type(df.itertuples(index=False, name=None), Iterator[tuple[Any, ...]]),
Iterator,
object,
)

for t1 in df.itertuples():
check(assert_type(t1, _PandasNamedTuple), _PandasNamedTuple)

Copy link
Collaborator

Choose a reason for hiding this comment

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

We shouldn't be using _PandasNamedTuple here in the call to check because what is happening internally is that pandas is creating a new class of type pandas.core.foo.Pandas, and if you use the name="Foobar" argument, the class is of the type pandas.core.foo.Foobar

But it's a dynamic class, so I think something like this would be appropriate:

for t1 in df.itertuples():
    assert_type(t1, _PandasNamedTuple)
    assert(t1.__class__.__name__ == "Pandas")
    assert(isinstance(t1.Index, int))
    assert(isinstance(t1.col1, int))  
    assert(isinstance(t1.col2, int))
    for k in [0, 1, 2]:
        assert(isinstance(t1[k], int))

And you could add a similar test for having name="Foobar" as the argument, and only the line that checks the name of the class would need to be changed.


def test_frame_iterator() -> None:
"""Test iterator methods for a dataframe GH1217."""
df = pd.DataFrame(data={"col1": [2, 1], "col2": [3, 4]})

check(assert_type(next(df.items()), tuple[Hashable, "pd.Series"]), tuple)
check(assert_type(next(df.iterrows()), tuple[Hashable, "pd.Series"]), tuple)
check(assert_type(next(df.itertuples()), _PandasNamedTuple), _PandasNamedTuple)


def test_types_sum() -> None:
df = pd.DataFrame(data={"col1": [2, 1], "col2": [3, 4]})
Expand Down
7 changes: 7 additions & 0 deletions tests/test_series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
from __future__ import annotations

from collections.abc import (
Hashable,
Iterable,
Iterator,
Sequence,
Expand Down Expand Up @@ -3797,3 +3798,9 @@ def foo(sf: pd.Series) -> None:

foo(s)
check(assert_type(s + pd.Series([1]), pd.Series), pd.Series)


def test_series_items() -> None:
s = pd.Series(data=[1, 2, 3, 4], index=["cow", "coal", "coalesce", ""])
check(assert_type(next(s.items()), tuple[Hashable, int]), tuple)
check(assert_type(s.items(), Iterator[tuple[Hashable, int]]), Iterator)