[pre-commit.ci] pre-commit autoupdate (#1926)

* [pre-commit.ci] pre-commit autoupdate updates: - [github.com/astral-sh/ruff-pre-commit: v0.8.6 → v0.9.4](astral-sh/ruff-pre-commit@v0.8.6...v0.9.4) - [github.com/codespell-project/codespell: v2.3.0 → v2.4.1](codespell-project/codespell@v2.3.0...v2.4.1) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix mkdocs * fix precommit --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Edoardo Abati <[email protected]>
narwhals-dev · Feb 3, 2025 · d63da25 · d63da25
1 parent a770707
commit d63da25
Show file tree

Hide file tree

Showing 24 changed files with 132 additions and 78 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -3,7 +3,7 @@ ci:
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
-  rev: 'v0.8.6'
+  rev: 'v0.9.4'
   hooks:
     # Run the formatter.
     - id: ruff-format
@@ -20,7 +20,7 @@ repos:
       additional_dependencies: ['polars==1.4.1', 'pytest==8.3.2']
       files: ^(narwhals|tests)/
 - repo: https://github.com/codespell-project/codespell
-  rev: 'v2.3.0'
+  rev: 'v2.4.1'
   hooks:
     - id: codespell
       files: \.(py|rst|md)$

diff --git a/mkdocs.yml b/mkdocs.yml
@@ -105,11 +105,10 @@ plugins:
 - mkdocstrings:
     handlers:
       python:
-        import:
+        inventories:
         - https://installer.readthedocs.io/en/stable/objects.inv
-        rendering:
-          show_signature_annotations: true
         options:
+          show_signature_annotations: true
           members_order: alphabetical
     enable_inventory: true
 

diff --git a/narwhals/_arrow/expr.py b/narwhals/_arrow/expr.py
@@ -56,11 +56,7 @@ def __init__(
         self._kwargs = kwargs
 
     def __repr__(self: Self) -> str:  # pragma: no cover
-        return (
-            f"ArrowExpr("
-            f"depth={self._depth}, "
-            f"function_name={self._function_name}, "
-        )
+        return f"ArrowExpr(depth={self._depth}, function_name={self._function_name}, "
 
     def __call__(self: Self, df: ArrowDataFrame) -> Sequence[ArrowSeries]:
         return self._call(df)

diff --git a/narwhals/_arrow/selectors.py b/narwhals/_arrow/selectors.py
@@ -111,11 +111,7 @@ def func(df: ArrowDataFrame) -> list[ArrowSeries]:
 
 class ArrowSelector(ArrowExpr):
     def __repr__(self: Self) -> str:  # pragma: no cover
-        return (
-            f"ArrowSelector("
-            f"depth={self._depth}, "
-            f"function_name={self._function_name})"
-        )
+        return f"ArrowSelector(depth={self._depth}, function_name={self._function_name})"
 
     def _to_expr(self: Self) -> ArrowExpr:
         return ArrowExpr(

diff --git a/narwhals/_dask/expr_dt.py b/narwhals/_dask/expr_dt.py
@@ -110,7 +110,7 @@ def weekday(self: Self) -> DaskExpr:
 
     def to_string(self: Self, format: str) -> DaskExpr:  # noqa: A002
         return self._compliant_expr._from_call(
-            lambda _input, format: _input.dt.strftime(format.replace("%.f", ".%f")),
+            lambda _input, format: _input.dt.strftime(format.replace("%.f", ".%f")),  # noqa: A006
             "strftime",
             format=format,
             returns_scalar=self._compliant_expr._returns_scalar,

diff --git a/narwhals/_dask/expr_str.py b/narwhals/_dask/expr_str.py
@@ -96,7 +96,7 @@ def slice(self: Self, offset: int, length: int | None) -> DaskExpr:
 
     def to_datetime(self: Self, format: str | None) -> DaskExpr:  # noqa: A002
         return self._compliant_expr._from_call(
-            lambda _input, format: dd.to_datetime(_input, format=format),
+            lambda _input, format: dd.to_datetime(_input, format=format),  # noqa: A006
             "to_datetime",
             format=format,
             returns_scalar=self._compliant_expr._returns_scalar,

diff --git a/narwhals/_dask/selectors.py b/narwhals/_dask/selectors.py
@@ -121,11 +121,7 @@ def func(df: DaskLazyFrame) -> list[dx.Series]:
 
 class DaskSelector(DaskExpr):
     def __repr__(self: Self) -> str:  # pragma: no cover
-        return (
-            f"DaskSelector("
-            f"depth={self._depth}, "
-            f"function_name={self._function_name})"
-        )
+        return f"DaskSelector(depth={self._depth}, function_name={self._function_name})"
 
     def _to_expr(self: Self) -> DaskExpr:
         return DaskExpr(

diff --git a/narwhals/_duckdb/selectors.py b/narwhals/_duckdb/selectors.py
@@ -114,7 +114,7 @@ def func(df: DuckDBLazyFrame) -> list[duckdb.Expression]:
 
 class DuckDBSelector(DuckDBExpr):
     def __repr__(self: Self) -> str:  # pragma: no cover
-        return f"DuckDBSelector(" f"function_name={self._function_name})"
+        return f"DuckDBSelector(function_name={self._function_name})"
 
     def _to_expr(self: Self) -> DuckDBExpr:
         return DuckDBExpr(

diff --git a/narwhals/_pandas_like/expr.py b/narwhals/_pandas_like/expr.py
@@ -75,10 +75,7 @@ def __call__(self: Self, df: PandasLikeDataFrame) -> Sequence[PandasLikeSeries]:
 
     def __repr__(self) -> str:  # pragma: no cover
         return (
-            f"PandasLikeExpr("
-            f"depth={self._depth}, "
-            f"function_name={self._function_name}, "
-            ")"
+            f"PandasLikeExpr(depth={self._depth}, function_name={self._function_name}, )"
         )
 
     def __narwhals_namespace__(self: Self) -> PandasLikeNamespace:

diff --git a/narwhals/_pandas_like/selectors.py b/narwhals/_pandas_like/selectors.py
@@ -120,9 +120,7 @@ def func(df: PandasLikeDataFrame) -> list[PandasLikeSeries]:
 class PandasSelector(PandasLikeExpr):
     def __repr__(self) -> str:  # pragma: no cover
         return (
-            f"PandasSelector("
-            f"depth={self._depth}, "
-            f"function_name={self._function_name}, "
+            f"PandasSelector(depth={self._depth}, function_name={self._function_name}, "
         )
 
     def _to_expr(self: Self) -> PandasLikeExpr:

diff --git a/narwhals/_spark_like/selectors.py b/narwhals/_spark_like/selectors.py
@@ -117,7 +117,7 @@ def func(df: SparkLikeLazyFrame) -> list[Column]:
 
 class SparkLikeSelector(SparkLikeExpr):
     def __repr__(self: Self) -> str:  # pragma: no cover
-        return f"SparkLikeSelector(" f"function_name={self._function_name})"
+        return f"SparkLikeSelector(function_name={self._function_name})"
 
     def _to_expr(self: Self) -> SparkLikeExpr:
         return SparkLikeExpr(

diff --git a/narwhals/dataframe.py b/narwhals/dataframe.py
@@ -1699,7 +1699,9 @@ def iter_rows(
             We define a library agnostic function:
 
             >>> def agnostic_iter_rows(df_native: IntoDataFrame, *, named: bool):
-            ...     return nw.from_native(df_native, eager_only=True).iter_rows(named=named)
+            ...     return nw.from_native(df_native, eager_only=True).iter_rows(
+            ...         named=named
+            ...     )
 
             We can then pass any supported library such as Pandas, Polars, or PyArrow
             to `agnostic_iter_rows`:
@@ -2376,7 +2378,9 @@ def filter(
 
             >>> def agnostic_filter(df_native: IntoFrameT) -> IntoFrameT:
             ...     df = nw.from_native(df_native)
-            ...     return df.filter((nw.col("foo") < 3) & (nw.col("ham") == "a")).to_native()
+            ...     return df.filter(
+            ...         (nw.col("foo") < 3) & (nw.col("ham") == "a")
+            ...     ).to_native()
             >>> agnostic_filter(df_pd)
                foo  bar ham
             0    1    6   a
@@ -2555,7 +2559,12 @@ def group_by(
 
             >>> def agnostic_group_by_agg(df_native: IntoDataFrameT) -> IntoDataFrameT:
             ...     df = nw.from_native(df_native, eager_only=True)
-            ...     return df.group_by(["a", "b"]).agg(nw.max("c")).sort("a", "b").to_native()
+            ...     return (
+            ...         df.group_by(["a", "b"])
+            ...         .agg(nw.max("c"))
+            ...         .sort("a", "b")
+            ...         .to_native()
+            ...     )
 
             >>> agnostic_group_by_agg(df_pd)
                a  b  c
@@ -2850,7 +2859,9 @@ def join_asof(
             ... ) -> IntoFrameT:
             ...     df = nw.from_native(df_native)
             ...     other = nw.from_native(other_native)
-            ...     return df.join_asof(other, on="datetime", strategy=strategy).to_native()
+            ...     return df.join_asof(
+            ...         other, on="datetime", strategy=strategy
+            ...     ).to_native()
 
             We can then pass any supported library such as Pandas or Polars
             to `agnostic_join_asof_datetime`:
@@ -3055,14 +3066,22 @@ def is_empty(self: Self) -> bool:
             >>> df_pd = pd.DataFrame(data)
             >>> df_pl = pl.DataFrame(data)
             >>> df_pa = pa.table(data)
-            >>> agnostic_is_empty(df_pd), agnostic_is_empty(df_pl), agnostic_is_empty(df_pa)
+            >>> (
+            ...     agnostic_is_empty(df_pd),
+            ...     agnostic_is_empty(df_pl),
+            ...     agnostic_is_empty(df_pa),
+            ... )
             (True, True, True)
 
             >>> data = {"foo": [100, 2, 3], "bar": [4, 5, 6]}
             >>> df_pd = pd.DataFrame(data)
             >>> df_pl = pl.DataFrame(data)
             >>> df_pa = pa.table(data)
-            >>> agnostic_is_empty(df_pd), agnostic_is_empty(df_pl), agnostic_is_empty(df_pa)
+            >>> (
+            ...     agnostic_is_empty(df_pd),
+            ...     agnostic_is_empty(df_pl),
+            ...     agnostic_is_empty(df_pa),
+            ... )
             (False, False, False)
         """
         return self._compliant_frame.is_empty()  # type: ignore[no-any-return]
@@ -3395,7 +3414,9 @@ def pivot(
 
             >>> def agnostic_pivot(df_native: IntoDataFrameT) -> IntoDataFrameT:
             ...     df = nw.from_native(df_native, eager_only=True)
-            ...     return df.pivot("col", index="ix", aggregate_function="sum").to_native()
+            ...     return df.pivot(
+            ...         "col", index="ix", aggregate_function="sum"
+            ...     ).to_native()
 
             We can then pass any supported library such as Pandas or Polars
             to `agnostic_pivot`:
@@ -4306,7 +4327,9 @@ def with_columns(
             >>> def agnostic_with_columns(df_native: IntoFrameT) -> IntoFrameT:
             ...     df = nw.from_native(df_native)
             ...     return (
-            ...         df.with_columns((nw.col("a") * 2).alias("2a")).collect().to_native()
+            ...         df.with_columns((nw.col("a") * 2).alias("2a"))
+            ...         .collect()
+            ...         .to_native()
             ...     )
 
             We can then pass any supported library such as Polars or Dask to `agnostic_with_columns`:
@@ -4422,7 +4445,9 @@ def select(
 
             >>> def agnostic_select(df_native: IntoFrameT) -> IntoFrameT:
             ...     df = nw.from_native(df_native)
-            ...     return df.select(nw.col("foo"), nw.col("bar") + 1).collect().to_native()
+            ...     return (
+            ...         df.select(nw.col("foo"), nw.col("bar") + 1).collect().to_native()
+            ...     )
 
             >>> agnostic_select(lf_pl)
             shape: (3, 2)
@@ -5047,7 +5072,9 @@ def sort(
 
             >>> def agnostic_sort(df_native: IntoFrameT) -> IntoFrameT:
             ...     df = nw.from_native(df_native)
-            ...     return df.sort("c", "a", descending=[False, True]).collect().to_native()
+            ...     return (
+            ...         df.sort("c", "a", descending=[False, True]).collect().to_native()
+            ...     )
 
             We can then pass any supported library such as Polars or Dask to `agnostic_sort`:
 
@@ -5262,7 +5289,9 @@ def join_asof(
             │ 2018-08-01 00:00:00 ┆ 82.66      ┆ 4566 │
             │ 2019-01-01 00:00:00 ┆ 83.12      ┆ 4696 │
             └─────────────────────┴────────────┴──────┘
-            >>> agnostic_join_asof_datetime(population_dask, gdp_dask, strategy="backward")
+            >>> agnostic_join_asof_datetime(
+            ...     population_dask, gdp_dask, strategy="backward"
+            ... )
                 datetime  population   gdp
             0 2016-03-01       82.19  4164
             1 2018-08-01       82.66  4566

diff --git a/narwhals/dtypes.py b/narwhals/dtypes.py
@@ -472,7 +472,9 @@ class Datetime(TemporalType):
         ...     .astype("datetime64[ms, Africa/Accra]")
         ... )
         >>> ser_pl = (
-        ...     pl.Series(data).cast(pl.Datetime("ms")).dt.replace_time_zone("Africa/Accra")
+        ...     pl.Series(data)
+        ...     .cast(pl.Datetime("ms"))
+        ...     .dt.replace_time_zone("Africa/Accra")
         ... )
         >>> ser_pa = pc.assume_timezone(
         ...     pa.chunked_array([data], type=pa.timestamp("ms")), "Africa/Accra"

diff --git a/narwhals/expr.py b/narwhals/expr.py
@@ -1437,7 +1437,9 @@ def is_nan(self: Self) -> Self:
             ...     "SELECT * FROM VALUES (null, CAST('NaN' AS DOUBLE)), (2, 2.) df(a, b)"
             ... )
             >>> df = nw.from_native(df_native)
-            >>> df.with_columns(a_is_nan=nw.col("a").is_nan(), b_is_nan=nw.col("b").is_nan())
+            >>> df.with_columns(
+            ...     a_is_nan=nw.col("a").is_nan(), b_is_nan=nw.col("b").is_nan()
+            ... )
             ┌────────────────────────────────────────┐
             |           Narwhals LazyFrame           |
             |----------------------------------------|
@@ -1507,7 +1509,9 @@ def fill_null(
             ...     }
             ... )
             >>> df = nw.from_native(df_native)
-            >>> df.with_columns(nw.col("a", "b").fill_null(0).name.suffix("_nulls_filled"))
+            >>> df.with_columns(
+            ...     nw.col("a", "b").fill_null(0).name.suffix("_nulls_filled")
+            ... )
             ┌────────────────────────────────────────────────┐
             |               Narwhals DataFrame               |
             |------------------------------------------------|
@@ -1771,7 +1775,9 @@ def null_count(self: Self) -> Self:
         Examples:
             >>> import pandas as pd
             >>> import narwhals as nw
-            >>> df_native = pd.DataFrame({"a": [1, 2, None, 1], "b": ["a", None, "b", None]})
+            >>> df_native = pd.DataFrame(
+            ...     {"a": [1, 2, None, 1], "b": ["a", None, "b", None]}
+            ... )
             >>> df = nw.from_native(df_native)
             >>> df.select(nw.all().null_count())
             ┌──────────────────┐
@@ -1830,7 +1836,9 @@ def is_last_distinct(self: Self) -> Self:
             >>> import narwhals as nw
             >>> df_native = pd.DataFrame({"a": [1, 2, 3, 1], "b": ["a", "a", "b", "c"]})
             >>> df = nw.from_native(df_native)
-            >>> df.with_columns(nw.all().is_last_distinct().name.suffix("_is_last_distinct"))
+            >>> df.with_columns(
+            ...     nw.all().is_last_distinct().name.suffix("_is_last_distinct")
+            ... )
             ┌───────────────────────────────────────────────┐
             |              Narwhals DataFrame               |
             |-----------------------------------------------|
@@ -1872,7 +1880,9 @@ def quantile(
         Examples:
             >>> import pandas as pd
             >>> import narwhals as nw
-            >>> df_native = pd.DataFrame({"a": list(range(50)), "b": list(range(50, 100))})
+            >>> df_native = pd.DataFrame(
+            ...     {"a": list(range(50)), "b": list(range(50, 100))}
+            ... )
             >>> df = nw.from_native(df_native)
             >>> df.select(nw.col("a", "b").quantile(0.5, interpolation="linear"))
             ┌──────────────────┐

diff --git a/narwhals/expr_dt.py b/narwhals/expr_dt.py
@@ -34,7 +34,9 @@ def date(self: Self) -> ExprT:
             >>> import narwhals as nw
             >>> from narwhals.typing import IntoFrameT
             >>>
-            >>> data = {"a": [datetime(2012, 1, 7, 10, 20), datetime(2023, 3, 10, 11, 32)]}
+            >>> data = {
+            ...     "a": [datetime(2012, 1, 7, 10, 20), datetime(2023, 3, 10, 11, 32)]
+            ... }
             >>> df_pd = pd.DataFrame(data).convert_dtypes(dtype_backend="pyarrow")
             >>> df_pl = pl.DataFrame(data)
             >>> df_pa = pa.table(data)
@@ -913,7 +915,9 @@ def total_seconds(self: Self) -> ExprT:
             >>> import narwhals as nw
             >>> from narwhals.typing import IntoFrameT
             >>>
-            >>> data = {"a": [timedelta(seconds=10), timedelta(seconds=20, milliseconds=40)]}
+            >>> data = {
+            ...     "a": [timedelta(seconds=10), timedelta(seconds=20, milliseconds=40)]
+            ... }
             >>> df_pd = pd.DataFrame(data)
             >>> df_pl = pl.DataFrame(data)
             >>> df_pa = pa.table(data)

diff --git a/narwhals/expr_name.py b/narwhals/expr_name.py
@@ -44,7 +44,9 @@ def keep(self: Self) -> ExprT:
 
             >>> def agnostic_name_keep(df_native: IntoFrame) -> list[str]:
             ...     df = nw.from_native(df_native)
-            ...     return df.select(nw.col("foo").alias("alias_for_foo").name.keep()).columns
+            ...     return df.select(
+            ...         nw.col("foo").alias("alias_for_foo").name.keep()
+            ...     ).columns
 
             We can then pass any supported library such as pandas, Polars, or
             PyArrow to `agnostic_name_keep`:

diff --git a/narwhals/expr_str.py b/narwhals/expr_str.py
@@ -180,7 +180,9 @@ def replace_all(
 
             >>> def agnostic_str_replace_all(df_native: IntoFrameT) -> IntoFrameT:
             ...     df = nw.from_native(df_native)
-            ...     df = df.with_columns(replaced=nw.col("foo").str.replace_all("abc", ""))
+            ...     df = df.with_columns(
+            ...         replaced=nw.col("foo").str.replace_all("abc", "")
+            ...     )
             ...     return df.to_native()
 
             We can then pass any supported library such as pandas, Polars, or
@@ -429,7 +431,9 @@ def contains(self: Self, pattern: str, *, literal: bool = False) -> ExprT:
             ...     df = nw.from_native(df_native)
             ...     return df.with_columns(
             ...         default_match=nw.col("pets").str.contains("parrot|Dove"),
-            ...         case_insensitive_match=nw.col("pets").str.contains("(?i)parrot|Dove"),
+            ...         case_insensitive_match=nw.col("pets").str.contains(
+            ...             "(?i)parrot|Dove"
+            ...         ),
             ...         literal_match=nw.col("pets").str.contains(
             ...             "parrot|Dove", literal=True
             ...         ),