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.

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

feat: add DataFrame.rows #351

Merged
merged 1 commit into from
Jun 29, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 1 addition & 0 deletions docs/api-reference/dataframe.md
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@
- null_count
- pipe
- rename
- rows
- schema
- select
- shape
Expand Down
8 changes: 8 additions & 0 deletions narwhals/_pandas_like/dataframe.py
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,14 @@ def __getitem__(self, item: str | range | slice) -> PandasSeries | PandasDataFra
def columns(self) -> list[str]:
return self._dataframe.columns.tolist() # type: ignore[no-any-return]

def rows(
self, *, named: bool = False
) -> list[tuple[Any, ...]] | list[dict[str, Any]]:
if not named:
return list(self._dataframe.itertuples(index=False, name=None))

return self._dataframe.to_dict("records") # type: ignore[no-any-return]

def iter_rows(
self,
*,
Expand Down
61 changes: 61 additions & 0 deletions narwhals/dataframe.py
Original file line number Diff line number Diff line change
Expand Up @@ -629,6 +629,67 @@ def columns(self) -> list[str]:
"""
return super().columns

@overload
def rows(
self,
*,
named: Literal[False],
) -> tuple[Any, ...]: ...

@overload
def rows(
self,
*,
named: Literal[True],
) -> dict[str, Any]: ...

@overload
def rows(
self,
*,
named: bool,
) -> tuple[Any, ...] | dict[str, Any]: ...

def rows(
self,
*,
named: bool = False,
) -> tuple[Any, ...] | dict[str, Any]:
"""
Returns all data in the DataFrame as a list of rows of python-native values.

Arguments:
named: By default, each row is returned as a tuple of values given
in the same order as the frame columns. Setting named=True will
return rows of dictionaries instead.

Examples:
>>> import pandas as pd
>>> import polars as pl
>>> import narwhals as nw
>>> df = {"foo": [1, 2, 3], "bar": [6.0, 7.0, 8.0], "ham": ["a", "b", "c"]}
>>> df_pd = pd.DataFrame(df)
>>> df_pl = pl.DataFrame(df)

We define a library agnostic function:

>>> def func(df_any, *, named):
... df = nw.from_native(df_any)
... return df.rows(named=named)

We can then pass either pandas or Polars to `func`:

>>> func(df_pd, named=False)
[(1, 6.0, 'a'), (2, 7.0, 'b'), (3, 8.0, 'c')]
>>> func(df_pd, named=True)
[{'foo': 1, 'bar': 6.0, 'ham': 'a'}, {'foo': 2, 'bar': 7.0, 'ham': 'b'}, {'foo': 3, 'bar': 8.0, 'ham': 'c'}]
>>> func(df_pl, named=False)
[(1, 6.0, 'a'), (2, 7.0, 'b'), (3, 8.0, 'c')]
>>> func(df_pl, named=True)
[{'foo': 1, 'bar': 6.0, 'ham': 'a'}, {'foo': 2, 'bar': 7.0, 'ham': 'b'}, {'foo': 3, 'bar': 8.0, 'ham': 'c'}]
"""
return self._dataframe.rows(named=named) # type: ignore[no-any-return]

@overload
def iter_rows(
self, *, named: Literal[False], buffer_size: int = ...
Expand Down
4 changes: 3 additions & 1 deletion tests/frame/rows_test.py
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@
df_polars_na = pl.DataFrame({"a": [None, 3, 2], "b": [4, 4, 6], "z": [7.0, None, 9]})


@pytest.mark.parametrize("method_name", ["iter_rows", "rows"])
@pytest.mark.parametrize(
"df_raw", [df_pandas, df_pandas_nullable, df_pandas_pyarrow, df_mpd, df_polars]
)
Expand All @@ -59,6 +60,7 @@
)
@pytest.mark.filterwarnings("ignore::FutureWarning")
def test_rows(
method_name: str,
df_raw: Any,
named: bool, # noqa: FBT001
expected: list[tuple[Any, ...]] | list[dict[str, Any]],
Expand All @@ -67,7 +69,7 @@ def test_rows(
df = nw.DataFrame(df_raw)

# WHEN
result = list(df.iter_rows(named=named))
result = list(getattr(df, method_name)(named=named))

# THEN
assert result == expected
Expand Down
Loading