Merge branch 'main' into issue2

pandas/__init__.py

@@ -1,4 +1,3 @@
-# flake8: noqa
 from __future__ import annotations
 
 __docformat__ = "restructuredtext"
@@ -20,7 +19,7 @@
 del _hard_dependencies, _dependency, _missing_dependencies
 
 # numpy compat
-from pandas.compat import is_numpy_dev as _is_numpy_dev
+from pandas.compat import is_numpy_dev as _is_numpy_dev  # pyright: ignore # noqa:F401
 
 try:
     from pandas._libs import hashtable as _hashtable, lib as _lib, tslib as _tslib
@@ -44,7 +43,7 @@
 )
 
 # let init-time option registration happen
-import pandas.core.config_init
+import pandas.core.config_init  # pyright: ignore # noqa:F401
 
 from pandas.core.api import (
     # dtype
@@ -134,7 +133,8 @@
     qcut,
 )
 
-from pandas import api, arrays, errors, io, plotting, testing, tseries
+from pandas import api, arrays, errors, io, plotting, tseries
+from pandas import testing  # noqa:PDF015
 from pandas.util._print_versions import show_versions
 
 from pandas.io.api import (

pandas/_config/__init__.py

@@ -16,7 +16,7 @@
     "options",
 ]
 from pandas._config import config
-from pandas._config import dates  # noqa:F401
+from pandas._config import dates  # pyright: ignore # noqa:F401
 from pandas._config.config import (
     describe_option,
     get_option,

pandas/_libs/interval.pyi

@@ -12,12 +12,12 @@ import numpy.typing as npt
 
 from pandas._libs import lib
 from pandas._typing import (
-    IntervalClosedType,
+    IntervalInclusiveType,
     Timedelta,
     Timestamp,
 )
 
-VALID_CLOSED: frozenset[str]
+VALID_INCLUSIVE: frozenset[str]
 
 _OrderableScalarT = TypeVar("_OrderableScalarT", int, float)
 _OrderableTimesT = TypeVar("_OrderableTimesT", Timestamp, Timedelta)
@@ -52,29 +52,31 @@ class IntervalMixin:
     def open_right(self) -> bool: ...
     @property
     def is_empty(self) -> bool: ...
-    def _check_closed_matches(self, other: IntervalMixin, name: str = ...) -> None: ...
+    def _check_inclusive_matches(
+        self, other: IntervalMixin, name: str = ...
+    ) -> None: ...
 
 def _warning_interval(
     inclusive, closed
-) -> tuple[IntervalClosedType, lib.NoDefault]: ...
+) -> tuple[IntervalInclusiveType, lib.NoDefault]: ...
 
 class Interval(IntervalMixin, Generic[_OrderableT]):
     @property
     def left(self: Interval[_OrderableT]) -> _OrderableT: ...
     @property
     def right(self: Interval[_OrderableT]) -> _OrderableT: ...
     @property
-    def inclusive(self) -> IntervalClosedType: ...
+    def inclusive(self) -> IntervalInclusiveType: ...
     @property
-    def closed(self) -> IntervalClosedType: ...
+    def closed(self) -> IntervalInclusiveType: ...
     mid: _MidDescriptor
     length: _LengthDescriptor
     def __init__(
         self,
         left: _OrderableT,
         right: _OrderableT,
-        inclusive: IntervalClosedType = ...,
-        closed: IntervalClosedType = ...,
+        inclusive: IntervalInclusiveType = ...,
+        closed: IntervalInclusiveType = ...,
     ) -> None: ...
     def __hash__(self) -> int: ...
     @overload
@@ -150,15 +152,15 @@ class Interval(IntervalMixin, Generic[_OrderableT]):
     def overlaps(self: Interval[_OrderableT], other: Interval[_OrderableT]) -> bool: ...
 
 def intervals_to_interval_bounds(
-    intervals: np.ndarray, validate_closed: bool = ...
-) -> tuple[np.ndarray, np.ndarray, str]: ...
+    intervals: np.ndarray, validate_inclusive: bool = ...
+) -> tuple[np.ndarray, np.ndarray, IntervalInclusiveType]: ...
 
 class IntervalTree(IntervalMixin):
     def __init__(
         self,
         left: np.ndarray,
         right: np.ndarray,
-        inclusive: IntervalClosedType = ...,
+        inclusive: IntervalInclusiveType = ...,
         leaf_size: int = ...,
     ) -> None: ...
     @property

pandas/_libs/interval.pyx

@@ -56,7 +56,7 @@ from pandas._libs.tslibs.util cimport (
     is_timedelta64_object,
 )
 
-VALID_CLOSED = frozenset(['both', 'neither', 'left', 'right'])
+VALID_INCLUSIVE = frozenset(['both', 'neither', 'left', 'right'])
 
 
 cdef class IntervalMixin:
@@ -85,7 +85,7 @@ cdef class IntervalMixin:
         Returns
         -------
         bool
-            True if the Interval is closed on the left-side.
+            True if the Interval is closed on the right-side.
         """
         return self.inclusive in ('right', 'both')
 
@@ -99,7 +99,7 @@ cdef class IntervalMixin:
         Returns
         -------
         bool
-            True if the Interval is closed on the left-side.
+            True if the Interval is not closed on the left-side.
         """
         return not self.closed_left
 
@@ -113,7 +113,7 @@ cdef class IntervalMixin:
         Returns
         -------
         bool
-            True if the Interval is closed on the left-side.
+            True if the Interval is not closed on the right-side.
         """
         return not self.closed_right
 
@@ -188,7 +188,7 @@ cdef class IntervalMixin:
         """
         return (self.right == self.left) & (self.inclusive != 'both')
 
-    def _check_closed_matches(self, other, name='other'):
+    def _check_inclusive_matches(self, other, name='other'):
         """
         Check if the inclusive attribute of `other` matches.
 
@@ -203,7 +203,7 @@ cdef class IntervalMixin:
         Raises
         ------
         ValueError
-            When `other` is not closed exactly the same as self.
+            When `other` is not inclusive exactly the same as self.
         """
         if self.inclusive != other.inclusive:
             raise ValueError(f"'{name}.inclusive' is {repr(other.inclusive)}, "
@@ -259,14 +259,14 @@ cdef class Interval(IntervalMixin):
         .. deprecated:: 1.5.0
 
     inclusive : {'both', 'neither', 'left', 'right'}, default 'both'
-        Whether the interval is closed on the left-side, right-side, both or
+        Whether the interval is inclusive on the left-side, right-side, both or
         neither. See the Notes for more detailed explanation.
 
         .. versionadded:: 1.5.0
 
     See Also
     --------
-    IntervalIndex : An Index of Interval objects that are all closed on the
+    IntervalIndex : An Index of Interval objects that are all inclusive on the
         same side.
     cut : Convert continuous data into discrete bins (Categorical
         of Interval objects).
@@ -279,13 +279,13 @@ cdef class Interval(IntervalMixin):
     The parameters `left` and `right` must be from the same type, you must be
     able to compare them and they must satisfy ``left <= right``.
 
-    A closed interval (in mathematics denoted by square brackets) contains
-    its endpoints, i.e. the closed interval ``[0, 5]`` is characterized by the
+    A inclusive interval (in mathematics denoted by square brackets) contains
+    its endpoints, i.e. the inclusive interval ``[0, 5]`` is characterized by the
     conditions ``0 <= x <= 5``. This is what ``inclusive='both'`` stands for.
     An open interval (in mathematics denoted by parentheses) does not contain
     its endpoints, i.e. the open interval ``(0, 5)`` is characterized by the
     conditions ``0 < x < 5``. This is what ``inclusive='neither'`` stands for.
-    Intervals can also be half-open or half-closed, i.e. ``[0, 5)`` is
+    Intervals can also be half-open or half-inclusive, i.e. ``[0, 5)`` is
     described by ``0 <= x < 5`` (``inclusive='left'``) and ``(0, 5]`` is
     described by ``0 < x <= 5`` (``inclusive='right'``).
 
@@ -352,7 +352,7 @@ cdef class Interval(IntervalMixin):
 
     cdef readonly str inclusive
     """
-    Whether the interval is closed on the left-side, right-side, both or
+    Whether the interval is inclusive on the left-side, right-side, both or
     neither.
     """
 
@@ -368,7 +368,7 @@ cdef class Interval(IntervalMixin):
         if inclusive is None:
             inclusive = "right"
 
-        if inclusive not in VALID_CLOSED:
+        if inclusive not in VALID_INCLUSIVE:
             raise ValueError(f"invalid option for 'inclusive': {inclusive}")
         if not left <= right:
             raise ValueError("left side of interval must be <= right side")
@@ -522,7 +522,7 @@ cdef class Interval(IntervalMixin):
         """
         Check whether two Interval objects overlap.
 
-        Two intervals overlap if they share a common point, including closed
+        Two intervals overlap if they share a common point, including inclusive
         endpoints. Intervals that only have an open endpoint in common do not
         overlap.
 
@@ -551,7 +551,7 @@ cdef class Interval(IntervalMixin):
         >>> i1.overlaps(i3)
         False
 
-        Intervals that share closed endpoints overlap:
+        Intervals that share inclusive endpoints overlap:
 
         >>> i4 = pd.Interval(0, 1, inclusive='both')
         >>> i5 = pd.Interval(1, 2, inclusive='both')
@@ -568,7 +568,7 @@ cdef class Interval(IntervalMixin):
             raise TypeError("`other` must be an Interval, "
                             f"got {type(other).__name__}")
 
-        # equality is okay if both endpoints are closed (overlap at a point)
+        # equality is okay if both endpoints are inclusive (overlap at a point)
         op1 = le if (self.closed_left and other.closed_right) else lt
         op2 = le if (other.closed_left and self.closed_right) else lt
 
@@ -580,16 +580,16 @@ cdef class Interval(IntervalMixin):
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def intervals_to_interval_bounds(ndarray intervals, bint validate_closed=True):
+def intervals_to_interval_bounds(ndarray intervals, bint validate_inclusive=True):
     """
     Parameters
     ----------
     intervals : ndarray
         Object array of Intervals / nulls.
 
-    validate_closed: bool, default True
-        Boolean indicating if all intervals must be closed on the same side.
-        Mismatching closed will raise if True, else return None for closed.
+    validate_inclusive: bool, default True
+        Boolean indicating if all intervals must be inclusive on the same side.
+        Mismatching inclusive will raise if True, else return None for inclusive.
 
     Returns
     -------
@@ -602,7 +602,7 @@ def intervals_to_interval_bounds(ndarray intervals, bint validate_closed=True):
         object inclusive = None, interval
         Py_ssize_t i, n = len(intervals)
         ndarray left, right
-        bint seen_closed = False
+        bint seen_inclusive = False
 
     left = np.empty(n, dtype=intervals.dtype)
     right = np.empty(n, dtype=intervals.dtype)
@@ -620,13 +620,13 @@ def intervals_to_interval_bounds(ndarray intervals, bint validate_closed=True):
 
         left[i] = interval.left
         right[i] = interval.right
-        if not seen_closed:
-            seen_closed = True
+        if not seen_inclusive:
+            seen_inclusive = True
             inclusive = interval.inclusive
         elif inclusive != interval.inclusive:
             inclusive = None
-            if validate_closed:
-                raise ValueError("intervals must all be closed on the same side")
+            if validate_inclusive:
+                raise ValueError("intervals must all be inclusive on the same side")
 
     return left, right, inclusive
 

pandas/_libs/lib.pyx

@@ -17,6 +17,7 @@ from cpython.number cimport PyNumber_Check
 from cpython.object cimport (
     Py_EQ,
     PyObject_RichCompareBool,
+    PyTypeObject,
 )
 from cpython.ref cimport Py_INCREF
 from cpython.sequence cimport PySequence_Check
@@ -54,6 +55,11 @@ from numpy cimport (
 
 cnp.import_array()
 
+cdef extern from "Python.h":
+    # Note: importing extern-style allows us to declare these as nogil
+    # functions, whereas `from cpython cimport` does not.
+    bint PyObject_TypeCheck(object obj, PyTypeObject* type) nogil
+
 cdef extern from "numpy/arrayobject.h":
     # cython's numpy.dtype specification is incorrect, which leads to
     # errors in issubclass(self.dtype.type, np.bool_), so we directly
@@ -71,6 +77,9 @@ cdef extern from "numpy/arrayobject.h":
             object fields
             tuple names
 
+    PyTypeObject PySignedIntegerArrType_Type
+    PyTypeObject PyUnsignedIntegerArrType_Type
+
 cdef extern from "numpy/ndarrayobject.h":
     bint PyArray_CheckScalar(obj) nogil
 
@@ -1283,9 +1292,9 @@ cdef class Seen:
         In addition to setting a flag that an integer was seen, we
         also set two flags depending on the type of integer seen:
 
-        1) sint_ : a negative (signed) number in the
+        1) sint_ : a signed numpy integer type or a negative (signed) number in the
                    range of [-2**63, 0) was encountered
-        2) uint_ : a positive number in the range of
+        2) uint_ : an unsigned numpy integer type or a positive number in the range of
                    [2**63, 2**64) was encountered
 
         Parameters
@@ -1294,8 +1303,18 @@ cdef class Seen:
             Value with which to set the flags.
         """
         self.int_ = True
-        self.sint_ = self.sint_ or (oINT64_MIN <= val < 0)
-        self.uint_ = self.uint_ or (oINT64_MAX < val <= oUINT64_MAX)
+        self.sint_ = (
+            self.sint_
+            or (oINT64_MIN <= val < 0)
+            # Cython equivalent of `isinstance(val, np.signedinteger)`
+            or PyObject_TypeCheck(val, &PySignedIntegerArrType_Type)
+        )
+        self.uint_ = (
+            self.uint_
+            or (oINT64_MAX < val <= oUINT64_MAX)
+            # Cython equivalent of `isinstance(val, np.unsignedinteger)`
+            or PyObject_TypeCheck(val, &PyUnsignedIntegerArrType_Type)
+        )
 
     @property
     def numeric_(self):
@@ -2542,7 +2561,6 @@ def maybe_convert_objects(ndarray[object] objects,
             floats[i] = <float64_t>val
             complexes[i] = <double complex>val
             if not seen.null_:
-                val = int(val)
                 seen.saw_int(val)
 
                 if ((seen.uint_ and seen.sint_) or