DEPS: Bump cython 3.0

asv_bench/asv.conf.json

@@ -41,7 +41,7 @@
     // pip (with all the conda available packages installed first,
     // followed by the pip installed packages).
     "matrix": {
-        "Cython": ["0.29.33"],
+        "Cython": ["3.0.0"],
         "matplotlib": [],
         "sqlalchemy": [],
         "scipy": [],

ci/deps/actions-310.yaml

@@ -6,7 +6,7 @@ dependencies:
 
   # build dependencies
   - versioneer[toml]
-  - cython>=0.29.33
+  - cython>=3.0.0
   - meson[ninja]=1.0.1
   - meson-python=0.13.1
 

ci/deps/actions-311-downstream_compat.yaml

@@ -7,7 +7,7 @@ dependencies:
 
   # build dependencies
   - versioneer[toml]
-  - cython>=0.29.33
+  - cython>=3.0.0
   - meson[ninja]=1.0.1
   - meson-python=0.13.1
 

ci/deps/actions-311-pyarrownightly.yaml

@@ -7,7 +7,7 @@ dependencies:
   # build dependencies
   - versioneer[toml]
   - meson[ninja]=1.0.1
-  - cython>=0.29.33
+  - cython>=3.0.0
   - meson-python=0.13.1
 
   # test dependencies

ci/deps/actions-311.yaml

@@ -6,7 +6,7 @@ dependencies:
 
   # build dependencies
   - versioneer[toml]
-  - cython>=0.29.33
+  - cython>=3.0.0
   - meson[ninja]=1.0.1
   - meson-python=0.13.1
 

ci/deps/actions-39-minimum_versions.yaml

@@ -8,7 +8,7 @@ dependencies:
 
   # build dependencies
   - versioneer[toml]
-  - cython>=0.29.33
+  - cython>=3.0.0
   - meson[ninja]=1.0.1
   - meson-python=0.13.1
 

ci/deps/actions-39.yaml

@@ -6,7 +6,7 @@ dependencies:
 
   # build dependencies
   - versioneer[toml]
-  - cython>=0.29.33
+  - cython>=3.0.0
   - meson[ninja]=1.0.1
   - meson-python=0.13.1
 

ci/deps/actions-pypy-39.yaml

@@ -9,7 +9,7 @@ dependencies:
 
   # build dependencies
   - versioneer[toml]
-  - cython>=0.29.33
+  - cython>=3.0.0
   - meson[ninja]=1.0.1
   - meson-python=0.13.1
 

ci/deps/circle-310-arm64.yaml

@@ -6,7 +6,7 @@ dependencies:
 
   # build dependencies
   - versioneer[toml]
-  - cython>=0.29.33
+  - cython>=3.0.0
   - meson[ninja]=1.0.1
   - meson-python=0.13.1
 

doc/source/whatsnew/v2.1.0.rst

@@ -799,6 +799,7 @@ Other
 - Bug in :meth:`Series.memory_usage` when ``deep=True`` throw an error with Series of objects and the returned value is incorrect, as it does not take into account GC corrections (:issue:`51858`)
 - Bug in :meth:`period_range` the default behavior when freq was not passed as an argument was incorrect(:issue:`53687`)
 - Fixed incorrect ``__name__`` attribute of ``pandas._libs.json`` (:issue:`52898`)
+- The minimum version of Cython needed to compile pandas is now ``3.0.0`` (:issue:`54335`)
 
 .. ***DO NOT USE THIS SECTION***
 

environment.yml

@@ -8,7 +8,7 @@ dependencies:
 
   # build dependencies
   - versioneer[toml]
-  - cython=0.29.33
+  - cython=3.0.0
   - meson[ninja]=1.0.1
   - meson-python=0.13.1
 

pandas/_libs/arrays.pyi

@@ -26,7 +26,7 @@ class NDArrayBacked:
     def size(self) -> int: ...
     @property
     def nbytes(self) -> int: ...
-    def copy(self): ...
+    def copy(self, order: str = "C"): ...
     def delete(self, loc, axis=...): ...
     def swapaxes(self, axis1, axis2): ...
     def repeat(self, repeats: int | Sequence[int], axis: int | None = ...): ...

pandas/_libs/groupby.pyi

@@ -44,7 +44,6 @@ def group_fillna_indexer(
     labels: np.ndarray,  # ndarray[int64_t]
     sorted_labels: npt.NDArray[np.intp],
     mask: npt.NDArray[np.uint8],
-    direction: Literal["ffill", "bfill"],
     limit: int,  # int64_t
     dropna: bool,
 ) -> None: ...
@@ -55,7 +54,7 @@ def group_any_all(
     mask: np.ndarray,  # const uint8_t[::1]
     val_test: Literal["any", "all"],
     skipna: bool,
-    nullable: bool,
+    result_mask: np.ndarray | None,
 ) -> None: ...
 def group_sum(
     out: np.ndarray,  # complexfloatingintuint_t[:, ::1]

pandas/_libs/hashtable.pyi

@@ -20,7 +20,6 @@ class Factorizer:
     def factorize(
         self,
         values: np.ndarray,
-        sort: bool = ...,
         na_sentinel=...,
         na_value=...,
         mask=...,
@@ -157,9 +156,9 @@ class HashTable:
     def __contains__(self, key: Hashable) -> bool: ...
     def sizeof(self, deep: bool = ...) -> int: ...
     def get_state(self) -> dict[str, int]: ...
-    # TODO: `item` type is subclass-specific
-    def get_item(self, item): ...  # TODO: return type?
-    def set_item(self, item, val) -> None: ...
+    # TODO: `val/key` type is subclass-specific
+    def get_item(self, val): ...  # TODO: return type?
+    def set_item(self, key, val) -> None: ...
     def get_na(self): ...  # TODO: return type?
     def set_na(self, val) -> None: ...
     def map_locations(
@@ -185,6 +184,7 @@ class HashTable:
         self,
         values: np.ndarray,  # np.ndarray[subclass-specific]
         return_inverse: bool = ...,
+        mask=...,
     ) -> (
         tuple[
             np.ndarray,  # np.ndarray[subclass-specific]
@@ -198,6 +198,7 @@ class HashTable:
         na_sentinel: int = ...,
         na_value: object = ...,
         mask=...,
+        ignore_na: bool = True,
     ) -> tuple[np.ndarray, npt.NDArray[np.intp]]: ...  # np.ndarray[subclass-specific]
 
 class Complex128HashTable(HashTable): ...

pandas/_libs/hashtable_class_helper.pxi.in

@@ -1239,9 +1239,10 @@ cdef class StringHashTable(HashTable):
                             na_value=na_value, ignore_na=ignore_na,
                             return_inverse=True)
 
+    # Add unused mask parameter for compat with other signatures
     def get_labels(self, ndarray[object] values, ObjectVector uniques,
                    Py_ssize_t count_prior=0, Py_ssize_t na_sentinel=-1,
-                   object na_value=None):
+                   object na_value=None, object mask=None):
         # -> np.ndarray[np.intp]
         _, labels = self._unique(values, uniques, count_prior=count_prior,
                                  na_sentinel=na_sentinel, na_value=na_value,
@@ -1496,9 +1497,10 @@ cdef class PyObjectHashTable(HashTable):
                             na_value=na_value, ignore_na=ignore_na,
                             return_inverse=True)
 
+    # Add unused mask parameter for compat with other signatures
     def get_labels(self, ndarray[object] values, ObjectVector uniques,
                    Py_ssize_t count_prior=0, Py_ssize_t na_sentinel=-1,
-                   object na_value=None):
+                   object na_value=None, object mask=None):
         # -> np.ndarray[np.intp]
         _, labels = self._unique(values, uniques, count_prior=count_prior,
                                  na_sentinel=na_sentinel, na_value=na_value,

pandas/_libs/lib.pyi

@@ -44,22 +44,24 @@ def is_scalar(val: object) -> bool: ...
 def is_list_like(obj: object, allow_sets: bool = ...) -> bool: ...
 def is_pyarrow_array(obj: object) -> bool: ...
 def is_period(val: object) -> TypeGuard[Period]: ...
-def is_interval(val: object) -> TypeGuard[Interval]: ...
-def is_decimal(val: object) -> TypeGuard[Decimal]: ...
-def is_complex(val: object) -> TypeGuard[complex]: ...
-def is_bool(val: object) -> TypeGuard[bool | np.bool_]: ...
-def is_integer(val: object) -> TypeGuard[int | np.integer]: ...
+def is_interval(obj: object) -> TypeGuard[Interval]: ...
+def is_decimal(obj: object) -> TypeGuard[Decimal]: ...
+def is_complex(obj: object) -> TypeGuard[complex]: ...
+def is_bool(obj: object) -> TypeGuard[bool | np.bool_]: ...
+def is_integer(obj: object) -> TypeGuard[int | np.integer]: ...
 def is_int_or_none(obj) -> bool: ...
-def is_float(val: object) -> TypeGuard[float]: ...
+def is_float(obj: object) -> TypeGuard[float]: ...
 def is_interval_array(values: np.ndarray) -> bool: ...
-def is_datetime64_array(values: np.ndarray) -> bool: ...
-def is_timedelta_or_timedelta64_array(values: np.ndarray) -> bool: ...
+def is_datetime64_array(values: np.ndarray, skipna: bool = True) -> bool: ...
+def is_timedelta_or_timedelta64_array(
+    values: np.ndarray, skipna: bool = True
+) -> bool: ...
 def is_datetime_with_singletz_array(values: np.ndarray) -> bool: ...
 def is_time_array(values: np.ndarray, skipna: bool = ...): ...
 def is_date_array(values: np.ndarray, skipna: bool = ...): ...
 def is_datetime_array(values: np.ndarray, skipna: bool = ...): ...
 def is_string_array(values: np.ndarray, skipna: bool = ...): ...
-def is_float_array(values: np.ndarray, skipna: bool = ...): ...
+def is_float_array(values: np.ndarray): ...
 def is_integer_array(values: np.ndarray, skipna: bool = ...): ...
 def is_bool_array(values: np.ndarray, skipna: bool = ...): ...
 def fast_multiget(mapping: dict, keys: np.ndarray, default=...) -> np.ndarray: ...
@@ -180,7 +182,7 @@ def count_level_2d(
     max_bin: int,
 ) -> np.ndarray: ...  # np.ndarray[np.int64, ndim=2]
 def get_level_sorter(
-    label: np.ndarray,  # const int64_t[:]
+    codes: np.ndarray,  # const int64_t[:]
     starts: np.ndarray,  # const intp_t[:]
 ) -> np.ndarray: ...  # np.ndarray[np.intp, ndim=1]
 def generate_bins_dt64(

pandas/_libs/ops.pyi

@@ -36,8 +36,8 @@ def vec_binop(
 @overload
 def maybe_convert_bool(
     arr: npt.NDArray[np.object_],
-    true_values: Iterable = ...,
-    false_values: Iterable = ...,
+    true_values: Iterable | None = None,
+    false_values: Iterable | None = None,
     convert_to_masked_nullable: Literal[False] = ...,
 ) -> tuple[np.ndarray, None]: ...
 @overload

pandas/_libs/sparse.pyi

@@ -39,6 +39,10 @@ class BlockIndex(SparseIndex):
         self, length: int, blocs: np.ndarray, blengths: np.ndarray
     ) -> None: ...
 
+    # Override to have correct parameters
+    def intersect(self, other: SparseIndex) -> Self: ...
+    def make_union(self, y: SparseIndex) -> Self: ...
+
 def make_mask_object_ndarray(
     arr: npt.NDArray[np.object_], fill_value
 ) -> npt.NDArray[np.bool_]: ...

pandas/_libs/sparse.pyx

@@ -726,7 +726,7 @@ def make_mask_object_ndarray(ndarray[object, ndim=1] arr, object fill_value):
 
     for i in range(new_length):
         value = arr[i]
-        if value == fill_value and type(value) == type(fill_value):
+        if value == fill_value and type(value) is type(fill_value):
             mask[i] = 0
 
     return mask.view(dtype=bool)

pandas/_libs/tslibs/conversion.pyi

@@ -10,5 +10,6 @@ TD64NS_DTYPE: np.dtype
 
 def precision_from_unit(
     unit: str,
+    out_reso: int = ...,
 ) -> tuple[int, int]: ...  # (int64_t, _)
 def localize_pydatetime(dt: datetime, tz: tzinfo | None) -> datetime: ...

pandas/_libs/tslibs/dtypes.pyi

@@ -5,10 +5,10 @@ from enum import Enum
 _attrname_to_abbrevs: dict[str, str]
 _period_code_map: dict[str, int]
 
-def periods_per_day(reso: int) -> int: ...
+def periods_per_day(reso: int = ...) -> int: ...
 def periods_per_second(reso: int) -> int: ...
 def is_supported_unit(reso: int) -> bool: ...
-def npy_unit_to_abbrev(reso: int) -> str: ...
+def npy_unit_to_abbrev(unit: int) -> str: ...
 def get_supported_reso(reso: int) -> int: ...
 def abbrev_to_npy_unit(abbrev: str) -> int: ...
 

pandas/_libs/tslibs/np_datetime.pyi

@@ -9,7 +9,7 @@ class OutOfBoundsTimedelta(ValueError): ...
 def py_get_unit_from_dtype(dtype: np.dtype): ...
 def py_td64_to_tdstruct(td64: int, unit: int) -> dict: ...
 def astype_overflowsafe(
-    arr: np.ndarray,
+    values: np.ndarray,
     dtype: np.dtype,
     copy: bool = ...,
     round_ok: bool = ...,

pandas/_libs/tslibs/offsets.pyi

@@ -275,7 +275,10 @@ def roll_qtrday(
 INVALID_FREQ_ERR_MSG: Literal["Invalid frequency: {0}"]
 
 def shift_months(
-    dtindex: npt.NDArray[np.int64], months: int, day_opt: str | None = ...
+    dtindex: npt.NDArray[np.int64],
+    months: int,
+    day_opt: str | None = ...,
+    reso: int = ...,
 ) -> npt.NDArray[np.int64]: ...
 
 _offset_map: dict[str, BaseOffset]

pandas/_libs/tslibs/offsets.pyx

@@ -498,7 +498,7 @@ cdef class BaseOffset:
     def __sub__(self, other):
         if PyDateTime_Check(other):
             raise TypeError("Cannot subtract datetime from offset.")
-        elif type(other) == type(self):
+        elif type(other) is type(self):
             return type(self)(self.n - other.n, normalize=self.normalize,
                               **self.kwds)
         elif not isinstance(self, BaseOffset):
@@ -1047,7 +1047,7 @@ cdef class Tick(SingleConstructorOffset):
             return other.__add__(self)
 
         if isinstance(other, Tick):
-            if type(self) == type(other):
+            if type(self) is type(other):
                 return type(self)(self.n + other.n)
             else:
                 return delta_to_tick(self.delta + other.delta)

pandas/_libs/tslibs/period.pyi

@@ -89,7 +89,7 @@ class Period(PeriodMixin):
     @classmethod
     def _from_ordinal(cls, ordinal: int, freq) -> Period: ...
     @classmethod
-    def now(cls, freq: BaseOffset = ...) -> Period: ...
+    def now(cls, freq: BaseOffset) -> Period: ...
     def strftime(self, fmt: str) -> str: ...
     def to_timestamp(
         self,

pandas/_libs/tslibs/period.pyx

@@ -2511,7 +2511,7 @@ cdef class _Period(PeriodMixin):
         object_state = None, self.freq, self.ordinal
         return (Period, object_state)
 
-    def strftime(self, fmt: str) -> str:
+    def strftime(self, fmt: str | None) -> str:
         r"""
         Returns a formatted string representation of the :class:`Period`.
 

pandas/_libs/tslibs/timedeltas.pyi

@@ -67,7 +67,7 @@ UnitChoices = Literal[
 _S = TypeVar("_S", bound=timedelta)
 
 def ints_to_pytimedelta(
-    arr: npt.NDArray[np.timedelta64],
+    m8values: npt.NDArray[np.timedelta64],
     box: bool = ...,
 ) -> npt.NDArray[np.object_]: ...
 def array_to_timedelta64(
@@ -161,8 +161,10 @@ class Timedelta(timedelta):
     def __gt__(self, other: timedelta) -> bool: ...
     def __hash__(self) -> int: ...
     def isoformat(self) -> str: ...
-    def to_numpy(self) -> np.timedelta64: ...
-    def view(self, dtype: npt.DTypeLike = ...) -> object: ...
+    def to_numpy(
+        self, dtype: npt.DTypeLike = ..., copy: bool = False
+    ) -> np.timedelta64: ...
+    def view(self, dtype: npt.DTypeLike) -> object: ...
     @property
     def unit(self) -> str: ...
     def as_unit(self, unit: str, round_ok: bool = ...) -> Timedelta: ...

pandas/_libs/tslibs/timestamps.pyi

@@ -177,7 +177,7 @@ class Timestamp(datetime):
     def is_year_end(self) -> bool: ...
     def to_pydatetime(self, warn: bool = ...) -> datetime: ...
     def to_datetime64(self) -> np.datetime64: ...
-    def to_period(self, freq: BaseOffset | str = ...) -> Period: ...
+    def to_period(self, freq: BaseOffset | str | None = None) -> Period: ...
     def to_julian_date(self) -> np.float64: ...
     @property
     def asm8(self) -> np.datetime64: ...

pandas/_libs/tslibs/tzconversion.pyi

@@ -10,7 +10,7 @@ from pandas._typing import npt
 
 # tz_convert_from_utc_single exposed for testing
 def tz_convert_from_utc_single(
-    val: np.int64, tz: tzinfo, creso: int = ...
+    utc_val: np.int64, tz: tzinfo, creso: int = ...
 ) -> np.int64: ...
 def tz_localize_to_utc(
     vals: npt.NDArray[np.int64],

pandas/_libs/tslibs/vectorized.pyi

@@ -31,7 +31,7 @@ def get_resolution(
     reso: int = ...,  # NPY_DATETIMEUNIT
 ) -> Resolution: ...
 def ints_to_pydatetime(
-    arr: npt.NDArray[np.int64],
+    stamps: npt.NDArray[np.int64],
     tz: tzinfo | None = ...,
     box: str = ...,
     reso: int = ...,  # NPY_DATETIMEUNIT

pandas/_libs/window/aggregations.pyi

@@ -111,8 +111,8 @@ def ewm(
     com: float,  # float64_t
     adjust: bool,
     ignore_na: bool,
-    deltas: np.ndarray,  # const float64_t[:]
-    normalize: bool,
+    deltas: np.ndarray | None = None,  # const float64_t[:]
+    normalize: bool = True,
 ) -> np.ndarray: ...  # np.ndarray[np.float64]
 def ewmcov(
     input_x: np.ndarray,  # const float64_t[:]