[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

asv_bench/benchmarks/frame_methods.py

@@ -517,7 +517,7 @@ def setup(self):
         self.df = DataFrame(np.random.randn(1000, 100))
 
         self.s = Series(np.arange(1028.0))
-        self.df2 = DataFrame({i: self.s for i in range(1028)})
+        self.df2 = DataFrame(dict.fromkeys(range(1028), self.s))
         self.df3 = DataFrame(np.random.randn(1000, 3), columns=list("ABC"))
 
     def time_apply_user_func(self):

pandas/_config/config.py

@@ -775,7 +775,7 @@ def inner(key: str, *args, **kwds):
             pkey = f"{prefix}.{key}"
             return func(pkey, *args, **kwds)
 
-        return cast(F, inner)
+        return cast("F", inner)
 
     _register_option = register_option
     _get_option = get_option

pandas/_config/localization.py

@@ -156,7 +156,9 @@ def get_locales(
         out_locales = []
         for x in split_raw_locales:
             try:
-                out_locales.append(str(x, encoding=cast(str, options.display.encoding)))
+                out_locales.append(
+                    str(x, encoding=cast("str", options.display.encoding))
+                )
             except UnicodeError:
                 # 'locale -a' is used to populated 'raw_locales' and on
                 # Redhat 7 Linux (and maybe others) prints locale names

pandas/_testing/_warnings.py

@@ -121,7 +121,7 @@ class for all warnings. To raise multiple types of exceptions,
                         )
                 else:
                     expected_warning = cast(
-                        Union[type[Warning], tuple[type[Warning], ...]],
+                        "Union[type[Warning], tuple[type[Warning], ...]]",
                         expected_warning,
                     )
                     match = (
@@ -241,7 +241,7 @@ def _is_unexpected_warning(
     """Check if the actual warning issued is unexpected."""
     if actual_warning and not expected_warning:
         return True
-    expected_warning = cast(type[Warning], expected_warning)
+    expected_warning = cast("type[Warning]", expected_warning)
     return bool(not issubclass(actual_warning.category, expected_warning))
 
 

pandas/_testing/asserters.py

@@ -283,7 +283,7 @@ def _check_types(left, right, obj: str = "Index") -> None:
 
     # MultiIndex special comparison for little-friendly error messages
     if isinstance(left, MultiIndex):
-        right = cast(MultiIndex, right)
+        right = cast("MultiIndex", right)
 
         for level in range(left.nlevels):
             lobj = f"{obj} level [{level}]"
@@ -776,11 +776,11 @@ def assert_extension_array_equal(
         # GH 52449
         if not check_dtype and left.dtype.kind in "mM":
             if not isinstance(left.dtype, np.dtype):
-                l_unit = cast(DatetimeTZDtype, left.dtype).unit
+                l_unit = cast("DatetimeTZDtype", left.dtype).unit
             else:
                 l_unit = np.datetime_data(left.dtype)[0]
             if not isinstance(right.dtype, np.dtype):
-                r_unit = cast(DatetimeTZDtype, right.dtype).unit
+                r_unit = cast("DatetimeTZDtype", right.dtype).unit
             else:
                 r_unit = np.datetime_data(right.dtype)[0]
             if (

pandas/compat/numpy/function.py

@@ -169,7 +169,7 @@ def validate_argsort_with_ascending(ascending: bool | int | None, args, kwargs)
         ascending = True
 
     validate_argsort_kind(args, kwargs, max_fname_arg_count=3)
-    ascending = cast(bool, ascending)
+    ascending = cast("bool", ascending)
     return ascending
 
 

pandas/core/algorithms.py

@@ -172,12 +172,12 @@ def _ensure_data(values: ArrayLike) -> np.ndarray:
         return np.asarray(values)
 
     elif is_complex_dtype(values.dtype):
-        return cast(np.ndarray, values)
+        return cast("np.ndarray", values)
 
     # datetimelike
     elif needs_i8_conversion(values.dtype):
         npvalues = values.view("i8")
-        npvalues = cast(np.ndarray, npvalues)
+        npvalues = cast("np.ndarray", npvalues)
         return npvalues
 
     # we have failed, return object
@@ -1289,9 +1289,9 @@ def searchsorted(
 
         if is_integer(value):
             # We know that value is int
-            value = cast(int, dtype.type(value))
+            value = cast("int", dtype.type(value))
         else:
-            value = pd_array(cast(ArrayLike, value), dtype=dtype)
+            value = pd_array(cast("ArrayLike", value), dtype=dtype)
     else:
         # E.g. if `arr` is an array with dtype='datetime64[ns]'
         # and `value` is a pd.Timestamp, we may need to convert value

pandas/core/apply.py

@@ -322,19 +322,19 @@ def transform(self) -> DataFrame | Series:
             return obj.T.transform(func, 0, *args, **kwargs).T
 
         if is_list_like(func) and not is_dict_like(func):
-            func = cast(list[AggFuncTypeBase], func)
+            func = cast("list[AggFuncTypeBase]", func)
             # Convert func equivalent dict
             if is_series:
                 func = {com.get_callable_name(v) or v: v for v in func}
             else:
-                func = {col: func for col in obj}
+                func = dict.fromkeys(obj, func)
 
         if is_dict_like(func):
-            func = cast(AggFuncTypeDict, func)
+            func = cast("AggFuncTypeDict", func)
             return self.transform_dict_like(func)
 
         # func is either str or callable
-        func = cast(AggFuncTypeBase, func)
+        func = cast("AggFuncTypeBase", func)
         try:
             result = self.transform_str_or_callable(func)
         except TypeError:
@@ -434,7 +434,7 @@ def compute_list_like(
             Data for result. When aggregating with a Series, this can contain any
             Python objects.
         """
-        func = cast(list[AggFuncTypeBase], self.func)
+        func = cast("list[AggFuncTypeBase]", self.func)
         obj = self.obj
 
         results = []
@@ -541,7 +541,7 @@ def compute_dict_like(
 
         obj = self.obj
         is_groupby = isinstance(obj, (DataFrameGroupBy, SeriesGroupBy))
-        func = cast(AggFuncTypeDict, self.func)
+        func = cast("AggFuncTypeDict", self.func)
         func = self.normalize_dictlike_arg(op_name, selected_obj, func)
 
         is_non_unique_col = (
@@ -666,7 +666,7 @@ def apply_str(self) -> DataFrame | Series:
         result: Series or DataFrame
         """
         # Caller is responsible for checking isinstance(self.f, str)
-        func = cast(str, self.func)
+        func = cast("str", self.func)
 
         obj = self.obj
 
@@ -1262,7 +1262,7 @@ def numba_func(values, col_names, df_index, *args):
         return numba_func
 
     def apply_with_numba(self) -> dict[int, Any]:
-        func = cast(Callable, self.func)
+        func = cast("Callable", self.func)
         args, kwargs = prepare_function_arguments(
             func, self.args, self.kwargs, num_required_args=1
         )
@@ -1404,7 +1404,7 @@ def numba_func(values, col_names_index, index, *args):
         return numba_func
 
     def apply_with_numba(self) -> dict[int, Any]:
-        func = cast(Callable, self.func)
+        func = cast("Callable", self.func)
         args, kwargs = prepare_function_arguments(
             func, self.args, self.kwargs, num_required_args=1
         )
@@ -1551,7 +1551,7 @@ def apply_compat(self):
 
     def apply_standard(self) -> DataFrame | Series:
         # caller is responsible for ensuring that f is Callable
-        func = cast(Callable, self.func)
+        func = cast("Callable", self.func)
         obj = self.obj
 
         if isinstance(func, np.ufunc):

pandas/core/arrays/_mixins.py

@@ -85,7 +85,7 @@ def method(self, *args, **kwargs):
         order = "F" if flags.f_contiguous else "C"
         return result.reshape(self.shape, order=order)
 
-    return cast(F, method)
+    return cast("F", method)
 
 
 # error: Definition of "delete/ravel/T/repeat/copy" in base class "NDArrayBacked"

pandas/core/arrays/arrow/accessors.py

@@ -445,7 +445,7 @@ def get_name(
                 while level_name_or_index:
                     # we need the cast, otherwise mypy complains about
                     # getting ints, bytes, or str here, which isn't possible.
-                    level_name_or_index = cast(list, level_name_or_index)
+                    level_name_or_index = cast("list", level_name_or_index)
                     name_or_index = level_name_or_index.pop()
                     name = get_name(name_or_index, selected)
                     selected = selected.type.field(selected.type.get_field_index(name))

pandas/core/arrays/arrow/array.py

@@ -1231,7 +1231,7 @@ def factorize(
             uniques = type(self)(combined.dictionary)
 
         if pa_version_under11p0 and pa.types.is_duration(pa_type):
-            uniques = cast(ArrowExtensionArray, uniques.astype(self.dtype))
+            uniques = cast("ArrowExtensionArray", uniques.astype(self.dtype))
         return indices, uniques
 
     def reshape(self, *args, **kwargs):
@@ -1991,7 +1991,7 @@ def __setitem__(self, key, value) -> None:
 
         elif is_integer(key):
             # fast path
-            key = cast(int, key)
+            key = cast("int", key)
             n = len(self)
             if key < 0:
                 key += n

pandas/core/arrays/base.py

@@ -1509,7 +1509,7 @@ def equals(self, other: object) -> bool:
         """
         if type(self) != type(other):
             return False
-        other = cast(ExtensionArray, other)
+        other = cast("ExtensionArray", other)
         if self.dtype != other.dtype:
             return False
         elif len(self) != len(other):

pandas/core/arrays/categorical.py

@@ -2478,7 +2478,7 @@ def _mode(self, dropna: bool = True) -> Categorical:
             mask = self.isna()
 
         res_codes, _ = algorithms.mode(codes, mask=mask)
-        res_codes = cast(np.ndarray, res_codes)
+        res_codes = cast("np.ndarray", res_codes)
         assert res_codes.dtype == codes.dtype
         res = self._from_backing_data(res_codes)
         return res

pandas/core/arrays/datetimelike.py

@@ -191,7 +191,7 @@ def new_meth(self, *args, **kwargs):
         res_i8 = result.view("i8")
         return self._from_backing_data(res_i8)
 
-    return cast(F, new_meth)
+    return cast("F", new_meth)
 
 
 # error: Definition of "_concat_same_type" in base class "NDArrayBacked" is
@@ -391,7 +391,7 @@ def __getitem__(self, key: PositionalIndexer2D) -> Self | DTScalarOrNaT:
             return result
         else:
             # At this point we know the result is an array.
-            result = cast(Self, result)
+            result = cast("Self", result)
         result._freq = self._get_getitem_freq(key)
         return result
 
@@ -990,7 +990,7 @@ def _cmp_method(self, other, op):
             return result
 
         if not isinstance(self.dtype, PeriodDtype):
-            self = cast(TimelikeOps, self)
+            self = cast("TimelikeOps", self)
             if self._creso != other._creso:
                 if not isinstance(other, type(self)):
                     # i.e. Timedelta/Timestamp, cast to ndarray and let
@@ -1637,7 +1637,7 @@ def _mode(self, dropna: bool = True):
 
         i8modes, _ = algorithms.mode(self.view("i8"), mask=mask)
         npmodes = i8modes.view(self._ndarray.dtype)
-        npmodes = cast(np.ndarray, npmodes)
+        npmodes = cast("np.ndarray", npmodes)
         return self._from_backing_data(npmodes)
 
     # ------------------------------------------------------------------
@@ -2198,7 +2198,7 @@ def _round(self, freq, mode, ambiguous, nonexistent):
             )
 
         values = self.view("i8")
-        values = cast(np.ndarray, values)
+        values = cast("np.ndarray", values)
         nanos = get_unit_for_round(freq, self._creso)
         if nanos == 0:
             # GH 52761

pandas/core/arrays/datetimes.py

@@ -508,7 +508,7 @@ def _generate_range(
             # Nanosecond-granularity timestamps aren't always correctly
             # representable with doubles, so we limit the range that we
             # pass to np.linspace as much as possible
-            periods = cast(int, periods)
+            periods = cast("int", periods)
             i8values = (
                 np.linspace(0, end._value - start._value, periods, dtype="int64")
                 + start._value
@@ -2430,7 +2430,7 @@ def _sequence_to_dt64(
     if data_dtype == object or is_string_dtype(data_dtype):
         # TODO: We do not have tests specific to string-dtypes,
         #  also complex or categorical or other extension
-        data = cast(np.ndarray, data)
+        data = cast("np.ndarray", data)
         copy = False
         if lib.infer_dtype(data, skipna=False) == "integer":
             # Much more performant than going through array_to_datetime
@@ -2475,7 +2475,7 @@ def _sequence_to_dt64(
     # so we need to handle these types.
     if isinstance(data_dtype, DatetimeTZDtype):
         # DatetimeArray -> ndarray
-        data = cast(DatetimeArray, data)
+        data = cast("DatetimeArray", data)
         tz = _maybe_infer_tz(tz, data.tz)
         result = data._ndarray
 
@@ -2484,7 +2484,7 @@ def _sequence_to_dt64(
         if isinstance(data, DatetimeArray):
             data = data._ndarray
 
-        data = cast(np.ndarray, data)
+        data = cast("np.ndarray", data)
         result, copy = _construct_from_dt64_naive(
             data, tz=tz, copy=copy, ambiguous=ambiguous
         )
@@ -2495,7 +2495,7 @@ def _sequence_to_dt64(
         if data.dtype != INT64_DTYPE:
             data = data.astype(np.int64, copy=False)
             copy = False
-        data = cast(np.ndarray, data)
+        data = cast("np.ndarray", data)
         result = data.view(out_dtype)
 
     if copy:
@@ -2760,7 +2760,7 @@ def _validate_dt64_dtype(dtype):
             # Without this, things like adding an array of timedeltas and
             # a  tz-aware Timestamp (with a tz specific to its datetime) will
             # be incorrect(ish?) for the array as a whole
-            dtype = cast(DatetimeTZDtype, dtype)
+            dtype = cast("DatetimeTZDtype", dtype)
             dtype = DatetimeTZDtype(
                 unit=dtype.unit, tz=timezones.tz_standardize(dtype.tz)
             )
@@ -2985,8 +2985,8 @@ def _generate_range(
         # argument type "None"
         start = end - (periods - 1) * offset  # type: ignore[operator]
 
-    start = cast(Timestamp, start)
-    end = cast(Timestamp, end)
+    start = cast("Timestamp", start)
+    end = cast("Timestamp", end)
 
     cur = start
     if offset.n >= 0:

pandas/core/arrays/masked.py

@@ -148,7 +148,7 @@ def _from_sequence(cls, scalars, *, dtype=None, copy: bool = False) -> Self:
     @classmethod
     @doc(ExtensionArray._empty)
     def _empty(cls, shape: Shape, dtype: ExtensionDtype) -> Self:
-        dtype = cast(BaseMaskedDtype, dtype)
+        dtype = cast("BaseMaskedDtype", dtype)
         values: np.ndarray = np.empty(shape, dtype=dtype.type)
         values.fill(dtype._internal_fill_value)
         mask = np.ones(shape, dtype=bool)

pandas/core/arrays/period.py

@@ -245,7 +245,7 @@ def __init__(self, values, dtype: Dtype | None = None, copy: bool = False) -> No
             values = np.array(values, dtype="int64", copy=copy)
         if dtype is None:
             raise ValueError("dtype is not specified and cannot be inferred")
-        dtype = cast(PeriodDtype, dtype)
+        dtype = cast("PeriodDtype", dtype)
         NDArrayBacked.__init__(self, values, dtype)
 
     # error: Signature of "_simple_new" incompatible with supertype "NDArrayBacked"

pandas/core/arrays/sparse/array.py

@@ -1031,7 +1031,7 @@ def __getitem__(
 
             if com.is_bool_indexer(key):
                 # mypy doesn't know we have an array here
-                key = cast(np.ndarray, key)
+                key = cast("np.ndarray", key)
                 return self.take(np.arange(len(key), dtype=np.int32)[key])
             elif hasattr(key, "__len__"):
                 return self.take(key)
@@ -1302,7 +1302,7 @@ def astype(self, dtype: AstypeArg | None = None, copy: bool = True):
 
         dtype = self.dtype.update_dtype(dtype)
         subtype = pandas_dtype(dtype._subtype_with_str)
-        subtype = cast(np.dtype, subtype)  # ensured by update_dtype
+        subtype = cast("np.dtype", subtype)  # ensured by update_dtype
         values = ensure_wrapped_if_datetimelike(self.sp_values)
         sp_values = astype_array(values, subtype, copy=copy)
         sp_values = np.asarray(sp_values)