[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.6
+    rev: v0.9.4
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -41,7 +41,7 @@ repos:
         pass_filenames: true
         require_serial: false
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.3.0
+    rev: v2.4.1
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown, cython, c]
@@ -70,7 +70,7 @@ repos:
     -   id: trailing-whitespace
         args: [--markdown-linebreak-ext=md]
 -   repo: https://github.com/PyCQA/isort
-    rev: 5.13.2
+    rev: 6.0.0
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
@@ -95,14 +95,14 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v19.1.6
+    rev: v19.1.7
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include
       args: [-i]
       types_or: [c, c++]
 -   repo: https://github.com/trim21/pre-commit-mirror-meson
-    rev: v1.6.1
+    rev: v1.7.0
     hooks:
     - id: meson-fmt
       args: ['--inplace']

asv_bench/benchmarks/io/style.py

@@ -13,8 +13,8 @@ class Render:
     def setup(self, cols, rows):
         self.df = DataFrame(
             np.random.randn(rows, cols),
-            columns=[f"float_{i+1}" for i in range(cols)],
-            index=[f"row_{i+1}" for i in range(rows)],
+            columns=[f"float_{i + 1}" for i in range(cols)],
+            index=[f"row_{i + 1}" for i in range(rows)],
         )
 
     def time_apply_render(self, cols, rows):

doc/make.py

@@ -260,8 +260,7 @@ def latex(self, force=False):
                 for i in range(3):
                     self._run_os("pdflatex", "-interaction=nonstopmode", "pandas.tex")
                 raise SystemExit(
-                    "You should check the file "
-                    '"build/latex/pandas.pdf" for problems.'
+                    'You should check the file "build/latex/pandas.pdf" for problems.'
                 )
             self._run_os("make")
             return ret_code
@@ -343,8 +342,7 @@ def main():
         dest="verbosity",
         default=0,
         help=(
-            "increase verbosity (can be repeated), "
-            "passed to the sphinx build command"
+            "increase verbosity (can be repeated), passed to the sphinx build command"
         ),
     )
     argparser.add_argument(

doc/source/user_guide/style.ipynb

@@ -1288,7 +1288,7 @@
    "outputs": [],
    "source": [
     "df2.loc[:4].style.highlight_max(\n",
-    "    axis=1, props=(\"color:white; \" \"font-weight:bold; \" \"background-color:darkblue;\")\n",
+    "    axis=1, props=(\"color:white; font-weight:bold; background-color:darkblue;\")\n",
     ")"
    ]
   },

pandas/core/apply.py

@@ -1645,8 +1645,7 @@ def reconstruct_func(
             # GH 28426 will raise error if duplicated function names are used and
             # there is no reassigned name
             raise SpecificationError(
-                "Function names must be unique if there is no new column names "
-                "assigned"
+                "Function names must be unique if there is no new column names assigned"
             )
         if func is None:
             # nicer error message

pandas/core/arrays/base.py

@@ -1791,9 +1791,11 @@ def take(self, indices, allow_fill=False, fill_value=None):
                # type for the array, to the physical storage type for
                # the data, before passing to take.
 
-               result = take(data, indices, fill_value=fill_value, allow_fill=allow_fill)
+               result = take(
+                   data, indices, fill_value=fill_value, allow_fill=allow_fill
+               )
                return self._from_sequence(result, dtype=self.dtype)
-        """  # noqa: E501
+        """
         # Implementer note: The `fill_value` parameter should be a user-facing
         # value, an instance of self.dtype.type. When passed `fill_value=None`,
         # the default of `self.dtype.na_value` should be used.

pandas/core/arrays/datetimes.py

@@ -2707,8 +2707,7 @@ def _maybe_infer_tz(tz: tzinfo | None, inferred_tz: tzinfo | None) -> tzinfo | N
         pass
     elif not timezones.tz_compare(tz, inferred_tz):
         raise TypeError(
-            f"data is already tz-aware {inferred_tz}, unable to "
-            f"set specified tz: {tz}"
+            f"data is already tz-aware {inferred_tz}, unable to set specified tz: {tz}"
         )
     return tz
 

pandas/core/computation/eval.py

@@ -204,7 +204,7 @@ def eval(
 
         By default, with the numexpr engine, the following operations are supported:
 
-        - Arthimetic operations: ``+``, ``-``, ``*``, ``/``, ``**``, ``%``
+        - Arithmetic operations: ``+``, ``-``, ``*``, ``/``, ``**``, ``%``
         - Boolean operations: ``|`` (or), ``&`` (and), and ``~`` (not)
         - Comparison operators: ``<``, ``<=``, ``==``, ``!=``, ``>=``, ``>``
 

pandas/core/computation/expr.py

@@ -698,7 +698,7 @@ 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]
+                        f"keyword error in function call '{node.func.id}'"  # type: ignore[attr-defined]
                     )
 
                 if key.arg:

pandas/core/computation/ops.py

@@ -512,8 +512,7 @@ def __init__(self, op: Literal["+", "-", "~", "not"], operand) -> None:
             self.func = _unary_ops_dict[op]
         except KeyError as err:
             raise ValueError(
-                f"Invalid unary operator {op!r}, "
-                f"valid operators are {UNARY_OPS_SYMS}"
+                f"Invalid unary operator {op!r}, valid operators are {UNARY_OPS_SYMS}"
             ) from err
 
     def __call__(self, env) -> MathCall:

pandas/core/dtypes/cast.py

@@ -1651,7 +1651,7 @@ def maybe_cast_to_integer_array(arr: list | np.ndarray, dtype: np.dtype) -> np.n
                 # (test_constructor_coercion_signed_to_unsigned) so safe to ignore.
                 warnings.filterwarnings(
                     "ignore",
-                    "NumPy will stop allowing conversion of " "out-of-bound Python int",
+                    "NumPy will stop allowing conversion of out-of-bound Python int",
                     DeprecationWarning,
                 )
                 casted = np.asarray(arr, dtype=dtype)

pandas/core/dtypes/dtypes.py

@@ -605,8 +605,7 @@ def update_dtype(self, dtype: str_type | CategoricalDtype) -> CategoricalDtype:
             return self
         elif not self.is_dtype(dtype):
             raise ValueError(
-                f"a CategoricalDtype must be passed to perform an update, "
-                f"got {dtype!r}"
+                f"a CategoricalDtype must be passed to perform an update, got {dtype!r}"
             )
         else:
             # from here on, dtype is a CategoricalDtype

pandas/core/generic.py

@@ -5537,8 +5537,7 @@ def filter(
         nkw = common.count_not_none(items, like, regex)
         if nkw > 1:
             raise TypeError(
-                "Keyword arguments `items`, `like`, or `regex` "
-                "are mutually exclusive"
+                "Keyword arguments `items`, `like`, or `regex` are mutually exclusive"
             )
 
         if axis is None:

pandas/core/groupby/groupby.py

@@ -2632,8 +2632,7 @@ def _value_counts(
                 doesnt_exist = subsetted - unique_cols
                 if doesnt_exist:
                     raise ValueError(
-                        f"Keys {doesnt_exist} in subset do not "
-                        f"exist in the DataFrame."
+                        f"Keys {doesnt_exist} in subset do not exist in the DataFrame."
                     )
             else:
                 subsetted = unique_cols

pandas/core/groupby/grouper.py

@@ -516,8 +516,7 @@ def __init__(
             ):
                 grper = pprint_thing(grouping_vector)
                 errmsg = (
-                    "Grouper result violates len(labels) == "
-                    f"len(data)\nresult: {grper}"
+                    f"Grouper result violates len(labels) == len(data)\nresult: {grper}"
                 )
                 raise AssertionError(errmsg)
 

pandas/core/indexers/objects.py

@@ -478,9 +478,9 @@ def get_window_bounds(
             )
             start = start.astype(np.int64)
             end = end.astype(np.int64)
-            assert len(start) == len(
-                end
-            ), "these should be equal in length from get_window_bounds"
+            assert len(start) == len(end), (
+                "these should be equal in length from get_window_bounds"
+            )
             # Cannot use groupby_indices as they might not be monotonic with the object
             # we're rolling over
             window_indices = np.arange(

pandas/core/indexing.py

@@ -975,8 +975,7 @@ def _validate_tuple_indexer(self, key: tuple) -> tuple:
                 self._validate_key(k, i)
             except ValueError as err:
                 raise ValueError(
-                    "Location based indexing can only have "
-                    f"[{self._valid_types}] types"
+                    f"Location based indexing can only have [{self._valid_types}] types"
                 ) from err
         return key
 
@@ -1589,8 +1588,7 @@ def _validate_key(self, key, axis: AxisInt) -> None:
                         "is not available"
                     )
                 raise ValueError(
-                    "iLocation based boolean indexing cannot use "
-                    "an indexable as a mask"
+                    "iLocation based boolean indexing cannot use an indexable as a mask"
                 )
             return
 
@@ -1994,8 +1992,7 @@ def _setitem_with_indexer_split_path(self, indexer, value, name: str):
                     return self._setitem_with_indexer((pi, info_axis[0]), value[0])
 
                 raise ValueError(
-                    "Must have equal len keys and value "
-                    "when setting with an iterable"
+                    "Must have equal len keys and value when setting with an iterable"
                 )
 
             elif lplane_indexer == 0 and len(value) == len(self.obj.index):
@@ -2023,8 +2020,7 @@ def _setitem_with_indexer_split_path(self, indexer, value, name: str):
 
             else:
                 raise ValueError(
-                    "Must have equal len keys and value "
-                    "when setting with an iterable"
+                    "Must have equal len keys and value when setting with an iterable"
                 )
 
         else:

pandas/core/interchange/buffer.py

@@ -31,8 +31,7 @@ def __init__(self, x: np.ndarray, allow_copy: bool = True) -> None:
                 x = x.copy()
             else:
                 raise RuntimeError(
-                    "Exports cannot be zero-copy in the case "
-                    "of a non-contiguous buffer"
+                    "Exports cannot be zero-copy in the case of a non-contiguous buffer"
                 )
 
         # Store the numpy array in which the data resides as a private

pandas/core/internals/blocks.py

@@ -2264,8 +2264,7 @@ def check_ndim(values, placement: BlockPlacement, ndim: int) -> None:
     if values.ndim > ndim:
         # Check for both np.ndarray and ExtensionArray
         raise ValueError(
-            "Wrong number of dimensions. "
-            f"values.ndim > ndim [{values.ndim} > {ndim}]"
+            f"Wrong number of dimensions. values.ndim > ndim [{values.ndim} > {ndim}]"
         )
 
     if not is_1d_only_ea_dtype(values.dtype):

pandas/core/internals/construction.py

@@ -907,8 +907,7 @@ def _validate_or_indexify_columns(
         if not is_mi_list and len(columns) != len(content):  # pragma: no cover
             # caller's responsibility to check for this...
             raise AssertionError(
-                f"{len(columns)} columns passed, passed data had "
-                f"{len(content)} columns"
+                f"{len(columns)} columns passed, passed data had {len(content)} columns"
             )
         if is_mi_list:
             # check if nested list column, length of each sub-list should be equal

pandas/core/ops/array_ops.py

@@ -164,7 +164,7 @@ def _masked_arith_op(x: np.ndarray, y, op) -> np.ndarray:
     else:
         if not is_scalar(y):
             raise TypeError(
-                f"Cannot broadcast np.ndarray with operand of type { type(y) }"
+                f"Cannot broadcast np.ndarray with operand of type {type(y)}"
             )
 
         # mask is only meaningful for x

pandas/core/reshape/encoding.py

@@ -495,8 +495,7 @@ def from_dummies(
 
     if col_isna_mask.any():
         raise ValueError(
-            "Dummy DataFrame contains NA value in column: "
-            f"'{col_isna_mask.idxmax()}'"
+            f"Dummy DataFrame contains NA value in column: '{col_isna_mask.idxmax()}'"
         )
 
     # index data with a list of all columns that are dummies

pandas/core/reshape/merge.py

@@ -1929,9 +1929,9 @@ def get_join_indexers(
     np.ndarray[np.intp] or None
         Indexer into the right_keys.
     """
-    assert len(left_keys) == len(
-        right_keys
-    ), "left_keys and right_keys must be the same length"
+    assert len(left_keys) == len(right_keys), (
+        "left_keys and right_keys must be the same length"
+    )
 
     # fast-path for empty left/right
     left_n = len(left_keys[0])

pandas/core/tools/datetimes.py

@@ -192,9 +192,9 @@ def should_cache(
         else:
             check_count = 500
     else:
-        assert (
-            0 <= check_count <= len(arg)
-        ), "check_count must be in next bounds: [0; len(arg)]"
+        assert 0 <= check_count <= len(arg), (
+            "check_count must be in next bounds: [0; len(arg)]"
+        )
         if check_count == 0:
             return False
 

pandas/io/excel/_odswriter.py

@@ -270,7 +270,7 @@ def _process_style(self, style: dict[str, Any] | None) -> str | None:
         style_key = json.dumps(style)
         if style_key in self._style_dict:
             return self._style_dict[style_key]
-        name = f"pd{len(self._style_dict)+1}"
+        name = f"pd{len(self._style_dict) + 1}"
         self._style_dict[style_key] = name
         odf_style = Style(name=name, family="table-cell")
         if "font" in style:

pandas/io/formats/printing.py

@@ -336,8 +336,8 @@ def format_object_summary(
 
     if indent_for_name:
         name_len = len(name)
-        space1 = f'\n{(" " * (name_len + 1))}'
-        space2 = f'\n{(" " * (name_len + 2))}'
+        space1 = f"\n{(' ' * (name_len + 1))}"
+        space2 = f"\n{(' ' * (name_len + 2))}"
     else:
         space1 = "\n"
         space2 = "\n "  # space for the opening '['

pandas/io/formats/style.py

@@ -2588,7 +2588,7 @@ def set_sticky(
                 for i, level in enumerate(levels_):
                     styles.append(
                         {
-                            "selector": f"thead tr:nth-child({level+1}) th",
+                            "selector": f"thead tr:nth-child({level + 1}) th",
                             "props": props
                             + (
                                 f"top:{i * pixel_size}px; height:{pixel_size}px; "
@@ -2599,7 +2599,7 @@ def set_sticky(
                 if not all(name is None for name in self.index.names):
                     styles.append(
                         {
-                            "selector": f"thead tr:nth-child({obj.nlevels+1}) th",
+                            "selector": f"thead tr:nth-child({obj.nlevels + 1}) th",
                             "props": props
                             + (
                                 f"top:{(len(levels_)) * pixel_size}px; "
@@ -2619,7 +2619,7 @@ def set_sticky(
                     styles.extend(
                         [
                             {
-                                "selector": f"thead tr th:nth-child({level+1})",
+                                "selector": f"thead tr th:nth-child({level + 1})",
                                 "props": props_ + "z-index:3 !important;",
                             },
                             {
@@ -4214,8 +4214,10 @@ def css_bar(start: float, end: float, color: str) -> str:
         if end > start:
             cell_css += "background: linear-gradient(90deg,"
             if start > 0:
-                cell_css += f" transparent {start*100:.1f}%, {color} {start*100:.1f}%,"
-            cell_css += f" {color} {end*100:.1f}%, transparent {end*100:.1f}%)"
+                cell_css += (
+                    f" transparent {start * 100:.1f}%, {color} {start * 100:.1f}%,"
+                )
+            cell_css += f" {color} {end * 100:.1f}%, transparent {end * 100:.1f}%)"
         return cell_css
 
     def css_calc(x, left: float, right: float, align: str, color: str | list | tuple):