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():