STY: Use ruff instead of black for formatting (#56704)

* STY: Use ruff instead of black for formatting

* mypy

* move pylint

* Remove trailing comma:

Author: mroeschke

.pre-commit-config.yaml

@@ -18,11 +18,6 @@ ci:
     # manual stage hooks
     skip: [pylint, pyright, mypy]
 repos:
--   repo: https://github.com/hauntsaninja/black-pre-commit-mirror
-    # black compiled with mypyc
-    rev: 23.11.0
-    hooks:
-      - id: black
 -   repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.1.6
     hooks:
@@ -35,6 +30,9 @@ repos:
         files: ^pandas
         exclude: ^pandas/tests
         args: [--select, "ANN001,ANN2", --fix-only, --exit-non-zero-on-fix]
+    -   id: ruff-format
+        # TODO: "." not needed in ruff 0.1.8
+        args: ["."]
 -   repo: https://github.com/jendrikseipp/vulture
     rev: 'v2.10'
     hooks:

asv_bench/benchmarks/indexing.py

@@ -84,9 +84,7 @@ def time_loc_slice(self, index, index_structure):
 
 class NumericMaskedIndexing:
     monotonic_list = list(range(10**6))
-    non_monotonic_list = (
-        list(range(50)) + [54, 53, 52, 51] + list(range(55, 10**6 - 1))
-    )
+    non_monotonic_list = list(range(50)) + [54, 53, 52, 51] + list(range(55, 10**6 - 1))
 
     params = [
         ("Int64", "UInt64", "Float64"),

asv_bench/benchmarks/io/style.py

@@ -76,7 +76,8 @@ def _style_format(self):
         # apply a formatting function
         # subset is flexible but hinders vectorised solutions
         self.st = self.df.style.format(
-            "{:,.3f}", subset=IndexSlice["row_1":f"row_{ir}", "float_1":f"float_{ic}"]
+            "{:,.3f}",
+            subset=IndexSlice["row_1" : f"row_{ir}", "float_1" : f"float_{ic}"],
         )
 
     def _style_apply_format_hide(self):

doc/source/development/contributing_codebase.rst

@@ -38,7 +38,7 @@ Pre-commit
 ----------
 
 Additionally, :ref:`Continuous Integration <contributing.ci>` will run code formatting checks
-like ``black``, ``ruff``,
+like ``ruff``,
 ``isort``, and ``clang-format`` and more using `pre-commit hooks <https://pre-commit.com/>`_.
 Any warnings from these checks will cause the :ref:`Continuous Integration <contributing.ci>` to fail; therefore,
 it is helpful to run the check yourself before submitting code. This

pandas/_libs/hashtable.pyi

@@ -196,15 +196,18 @@ class HashTable:
         *,
         return_inverse: Literal[True],
         mask: None = ...,
-    ) -> tuple[np.ndarray, npt.NDArray[np.intp],]: ...  # np.ndarray[subclass-specific]
+    ) -> tuple[np.ndarray, npt.NDArray[np.intp]]: ...  # np.ndarray[subclass-specific]
     @overload
     def unique(
         self,
         values: np.ndarray,  # np.ndarray[subclass-specific]
         *,
         return_inverse: Literal[False] = ...,
         mask: npt.NDArray[np.bool_],
-    ) -> tuple[np.ndarray, npt.NDArray[np.bool_],]: ...  # np.ndarray[subclass-specific]
+    ) -> tuple[
+        np.ndarray,
+        npt.NDArray[np.bool_],
+    ]: ...  # np.ndarray[subclass-specific]
     def factorize(
         self,
         values: np.ndarray,  # np.ndarray[subclass-specific]

pandas/_libs/lib.pyi

@@ -179,7 +179,8 @@ def indices_fast(
     sorted_labels: list[npt.NDArray[np.int64]],
 ) -> dict[Hashable, npt.NDArray[np.intp]]: ...
 def generate_slices(
-    labels: np.ndarray, ngroups: int  # const intp_t[:]
+    labels: np.ndarray,
+    ngroups: int,  # const intp_t[:]
 ) -> tuple[npt.NDArray[np.int64], npt.NDArray[np.int64]]: ...
 def count_level_2d(
     mask: np.ndarray,  # ndarray[uint8_t, ndim=2, cast=True],
@@ -209,5 +210,6 @@ def get_reverse_indexer(
 def is_bool_list(obj: list) -> bool: ...
 def dtypes_all_equal(types: list[DtypeObj]) -> bool: ...
 def is_range_indexer(
-    left: np.ndarray, n: int  # np.ndarray[np.int64, ndim=1]
+    left: np.ndarray,
+    n: int,  # np.ndarray[np.int64, ndim=1]
 ) -> bool: ...

pandas/_testing/_hypothesis.py

@@ -54,12 +54,8 @@
     DATETIME_NO_TZ = st.datetimes()
 
 DATETIME_JAN_1_1900_OPTIONAL_TZ = st.datetimes(
-    min_value=pd.Timestamp(
-        1900, 1, 1
-    ).to_pydatetime(),  # pyright: ignore[reportGeneralTypeIssues]
-    max_value=pd.Timestamp(
-        1900, 1, 1
-    ).to_pydatetime(),  # pyright: ignore[reportGeneralTypeIssues]
+    min_value=pd.Timestamp(1900, 1, 1).to_pydatetime(),  # pyright: ignore[reportGeneralTypeIssues]
+    max_value=pd.Timestamp(1900, 1, 1).to_pydatetime(),  # pyright: ignore[reportGeneralTypeIssues]
     timezones=st.one_of(st.none(), dateutil_timezones(), pytz_timezones()),
 )
 

pandas/core/apply.py

@@ -1010,7 +1010,8 @@ def wrapper(*args, **kwargs):
             # [..., Any] | str] | dict[Hashable,Callable[..., Any] | str |
             # list[Callable[..., Any] | str]]"; expected "Hashable"
             nb_looper = generate_apply_looper(
-                self.func, **engine_kwargs  # type: ignore[arg-type]
+                self.func,  # type: ignore[arg-type]
+                **engine_kwargs,
             )
             result = nb_looper(self.values, self.axis)
             # If we made the result 2-D, squeeze it back to 1-D

pandas/core/arrays/_arrow_string_mixins.py

@@ -58,7 +58,8 @@ def _str_get(self, i: int) -> Self:
             self._pa_array, start=start, stop=stop, step=step
         )
         null_value = pa.scalar(
-            None, type=self._pa_array.type  # type: ignore[attr-defined]
+            None,
+            type=self._pa_array.type,  # type: ignore[attr-defined]
         )
         result = pc.if_else(not_out_of_bounds, selected, null_value)
         return type(self)(result)

pandas/core/arrays/_mixins.py

@@ -347,7 +347,9 @@ def fillna(
         # error: Argument 2 to "check_value_size" has incompatible type
         # "ExtensionArray"; expected "ndarray"
         value = missing.check_value_size(
-            value, mask, len(self)  # type: ignore[arg-type]
+            value,
+            mask,  # type: ignore[arg-type]
+            len(self),
         )
 
         if mask.any():

pandas/core/arrays/arrow/array.py

@@ -2855,7 +2855,8 @@ def _dt_tz_localize(
             "shift_backward": "earliest",
             "shift_forward": "latest",
         }.get(
-            nonexistent, None  # type: ignore[arg-type]
+            nonexistent,  # type: ignore[arg-type]
+            None,
         )
         if nonexistent_pa is None:
             raise NotImplementedError(f"{nonexistent=} is not supported")

pandas/core/arrays/base.py

@@ -1121,7 +1121,9 @@ def fillna(
         # error: Argument 2 to "check_value_size" has incompatible type
         # "ExtensionArray"; expected "ndarray"
         value = missing.check_value_size(
-            value, mask, len(self)  # type: ignore[arg-type]
+            value,
+            mask,  # type: ignore[arg-type]
+            len(self),
         )
 
         if mask.any():
@@ -1490,9 +1492,7 @@ def factorize(
         uniques_ea = self._from_factorized(uniques, self)
         return codes, uniques_ea
 
-    _extension_array_shared_docs[
-        "repeat"
-    ] = """
+    _extension_array_shared_docs["repeat"] = """
         Repeat elements of a %(klass)s.
 
         Returns a new %(klass)s where each element of the current %(klass)s

pandas/core/arrays/datetimelike.py

@@ -1236,7 +1236,9 @@ def _add_timedeltalike(self, other: Timedelta | TimedeltaArray) -> Self:
 
         # error: Unexpected keyword argument "freq" for "_simple_new" of "NDArrayBacked"
         return type(self)._simple_new(
-            res_values, dtype=self.dtype, freq=new_freq  # type: ignore[call-arg]
+            res_values,
+            dtype=self.dtype,
+            freq=new_freq,  # type: ignore[call-arg]
         )
 
     @final
@@ -1256,7 +1258,9 @@ def _add_nat(self) -> Self:
         result = result.view(self._ndarray.dtype)  # preserve reso
         # error: Unexpected keyword argument "freq" for "_simple_new" of "NDArrayBacked"
         return type(self)._simple_new(
-            result, dtype=self.dtype, freq=None  # type: ignore[call-arg]
+            result,
+            dtype=self.dtype,
+            freq=None,  # type: ignore[call-arg]
         )
 
     @final
@@ -2162,7 +2166,9 @@ def as_unit(self, unit: str, round_ok: bool = True) -> Self:
         # error: Unexpected keyword argument "freq" for "_simple_new" of
         # "NDArrayBacked"  [call-arg]
         return type(self)._simple_new(
-            new_values, dtype=new_dtype, freq=self.freq  # type: ignore[call-arg]
+            new_values,
+            dtype=new_dtype,
+            freq=self.freq,  # type: ignore[call-arg]
         )
 
     # TODO: annotate other as DatetimeArray | TimedeltaArray | Timestamp | Timedelta

pandas/core/arrays/interval.py

@@ -122,9 +122,7 @@
 }
 
 
-_interval_shared_docs[
-    "class"
-] = """
+_interval_shared_docs["class"] = """
 %(summary)s
 
 Parameters
@@ -1489,9 +1487,7 @@ def set_closed(self, closed: IntervalClosedType) -> Self:
         dtype = IntervalDtype(left.dtype, closed=closed)
         return self._simple_new(left, right, dtype=dtype)
 
-    _interval_shared_docs[
-        "is_non_overlapping_monotonic"
-    ] = """
+    _interval_shared_docs["is_non_overlapping_monotonic"] = """
         Return a boolean whether the %(klass)s is non-overlapping and monotonic.
 
         Non-overlapping means (no Intervals share points), and monotonic means

pandas/core/arrays/masked.py

@@ -1089,7 +1089,8 @@ def value_counts(self, dropna: bool = True) -> Series:
         arr = IntegerArray(value_counts, mask)
         index = Index(
             self.dtype.construct_array_type()(
-                keys, mask_index  # type: ignore[arg-type]
+                keys,  # type: ignore[arg-type]
+                mask_index,
             )
         )
         return Series(arr, index=index, name="count", copy=False)

pandas/core/arrays/sparse/array.py

@@ -454,7 +454,8 @@ def __init__(
             # error: Argument "dtype" to "asarray" has incompatible type
             # "Union[ExtensionDtype, dtype[Any], None]"; expected "None"
             sparse_values = np.asarray(
-                data.sp_values, dtype=dtype  # type: ignore[arg-type]
+                data.sp_values,
+                dtype=dtype,  # type: ignore[arg-type]
             )
         elif sparse_index is None:
             data = extract_array(data, extract_numpy=True)

pandas/core/base.py

@@ -1207,9 +1207,7 @@ def factorize(
             uniques = Index(uniques)
         return codes, uniques
 
-    _shared_docs[
-        "searchsorted"
-    ] = """
+    _shared_docs["searchsorted"] = """
         Find indices where elements should be inserted to maintain order.
 
         Find the indices into a sorted {klass} `self` such that, if the

pandas/core/computation/expr.py

@@ -695,8 +695,7 @@ def visit_Call(self, node, side=None, **kwargs):
                 if not isinstance(key, ast.keyword):
                     # error: "expr" has no attribute "id"
                     raise ValueError(
-                        "keyword error in function call "
-                        f"'{node.func.id}'"  # type: ignore[attr-defined]
+                        "keyword error in function call " f"'{node.func.id}'"  # type: ignore[attr-defined]
                     )
 
                 if key.arg:

pandas/core/dtypes/cast.py

@@ -589,7 +589,9 @@ def maybe_promote(dtype: np.dtype, fill_value=np.nan):
         # error: Argument 3 to "__call__" of "_lru_cache_wrapper" has incompatible type
         # "Type[Any]"; expected "Hashable"  [arg-type]
         dtype, fill_value = _maybe_promote_cached(
-            dtype, fill_value, type(fill_value)  # type: ignore[arg-type]
+            dtype,
+            fill_value,
+            type(fill_value),  # type: ignore[arg-type]
         )
     except TypeError:
         # if fill_value is not hashable (required for caching)

pandas/core/frame.py

@@ -1405,9 +1405,7 @@ def style(self) -> Styler:
 
         return Styler(self)
 
-    _shared_docs[
-        "items"
-    ] = r"""
+    _shared_docs["items"] = r"""
         Iterate over (column name, Series) pairs.
 
         Iterates over the DataFrame columns, returning a tuple with
@@ -2030,8 +2028,7 @@ def to_dict(
         orient: Literal[
             "dict", "list", "series", "split", "tight", "records", "index"
         ] = "dict",
-        into: type[MutableMappingT]
-        | MutableMappingT = dict,  # type: ignore[assignment]
+        into: type[MutableMappingT] | MutableMappingT = dict,  # type: ignore[assignment]
         index: bool = True,
     ) -> MutableMappingT | list[MutableMappingT]:
         """
@@ -9137,9 +9134,7 @@ def groupby(
             dropna=dropna,
         )
 
-    _shared_docs[
-        "pivot"
-    ] = """
+    _shared_docs["pivot"] = """
         Return reshaped DataFrame organized by given index / column values.
 
         Reshape data (produce a "pivot" table) based on column values. Uses
@@ -9283,9 +9278,7 @@ def pivot(
 
         return pivot(self, index=index, columns=columns, values=values)
 
-    _shared_docs[
-        "pivot_table"
-    ] = """
+    _shared_docs["pivot_table"] = """
         Create a spreadsheet-style pivot table as a DataFrame.
 
         The levels in the pivot table will be stored in MultiIndex objects
@@ -12529,7 +12522,7 @@ def _to_dict_of_blocks(self):
         mgr = cast(BlockManager, mgr_to_mgr(mgr, "block"))
         return {
             k: self._constructor_from_mgr(v, axes=v.axes).__finalize__(self)
-            for k, v, in mgr.to_dict().items()
+            for k, v in mgr.to_dict().items()
         }
 
     @property

pandas/core/generic.py

@@ -8006,8 +8006,6 @@ def replace(
             if items:
                 keys, values = zip(*items)
             else:
-                # error: Incompatible types in assignment (expression has type
-                # "list[Never]", variable has type "tuple[Any, ...]")
                 keys, values = ([], [])  # type: ignore[assignment]
 
             are_mappings = [is_dict_like(v) for v in values]
@@ -8825,15 +8823,11 @@ def _clip_with_scalar(self, lower, upper, inplace: bool_t = False):
 
         if lower is not None:
             cond = mask | (self >= lower)
-            result = result.where(
-                cond, lower, inplace=inplace
-            )  # type: ignore[assignment]
+            result = result.where(cond, lower, inplace=inplace)  # type: ignore[assignment]
         if upper is not None:
             cond = mask | (self <= upper)
             result = self if inplace else result
-            result = result.where(
-                cond, upper, inplace=inplace
-            )  # type: ignore[assignment]
+            result = result.where(cond, upper, inplace=inplace)  # type: ignore[assignment]
 
         return result
 
@@ -12242,7 +12236,12 @@ def _accum_func(
 
         if axis == 1:
             return self.T._accum_func(
-                name, func, axis=0, skipna=skipna, *args, **kwargs  # noqa: B026
+                name,
+                func,
+                axis=0,
+                skipna=skipna,
+                *args,  # noqa: B026
+                **kwargs,
             ).T
 
         def block_accum_func(blk_values):
@@ -12720,14 +12719,16 @@ def __imul__(self, other) -> Self:
     def __itruediv__(self, other) -> Self:
         # error: Unsupported left operand type for / ("Type[NDFrame]")
         return self._inplace_method(
-            other, type(self).__truediv__  # type: ignore[operator]
+            other,
+            type(self).__truediv__,  # type: ignore[operator]
         )
 
     @final
     def __ifloordiv__(self, other) -> Self:
         # error: Unsupported left operand type for // ("Type[NDFrame]")
         return self._inplace_method(
-            other, type(self).__floordiv__  # type: ignore[operator]
+            other,
+            type(self).__floordiv__,  # type: ignore[operator]
         )
 
     @final
@@ -13495,9 +13496,7 @@ def last_valid_index(self) -> Hashable | None:
 Series([], dtype: bool)
 """
 
-_shared_docs[
-    "stat_func_example"
-] = """
+_shared_docs["stat_func_example"] = """
 
 Examples
 --------