Merge branch 'main' into gh-62717

Author: heoh

doc/make.py

@@ -105,7 +105,7 @@ def _process_single_doc(self, single_doc):
     @staticmethod
     def _run_os(*args) -> None:
         """
-        Execute a command as a OS terminal.
+        Execute a command as an OS terminal.
 
         Parameters
         ----------

doc/source/whatsnew/v3.0.0.rst

@@ -939,6 +939,7 @@ Performance improvements
 - Performance improvement in :meth:`RangeIndex.reindex` returning a :class:`RangeIndex` instead of a :class:`Index` when possible. (:issue:`57647`, :issue:`57752`)
 - Performance improvement in :meth:`RangeIndex.take` returning a :class:`RangeIndex` instead of a :class:`Index` when possible. (:issue:`57445`, :issue:`57752`)
 - Performance improvement in :func:`merge` if hash-join can be used (:issue:`57970`)
+- Performance improvement in :func:`merge` when join keys have different dtypes and need to be upcast (:issue:`62902`)
 - Performance improvement in :meth:`CategoricalDtype.update_dtype` when ``dtype`` is a :class:`CategoricalDtype` with non ``None`` categories and ordered (:issue:`59647`)
 - Performance improvement in :meth:`DataFrame.__getitem__` when ``key`` is a :class:`DataFrame` with many columns (:issue:`61010`)
 - Performance improvement in :meth:`DataFrame.astype` when converting to extension floating dtypes, e.g. "Float64" (:issue:`60066`)
@@ -979,6 +980,7 @@ Datetimelike
 - Bug in :meth:`DataFrame.fillna` raising an ``AssertionError`` instead of ``OutOfBoundsDatetime`` when filling a ``datetime64[ns]`` column with an out-of-bounds timestamp. Now correctly raises ``OutOfBoundsDatetime``. (:issue:`61208`)
 - Bug in :meth:`DataFrame.min` and :meth:`DataFrame.max` casting ``datetime64`` and ``timedelta64`` columns to ``float64`` and losing precision (:issue:`60850`)
 - Bug in :meth:`Dataframe.agg` with df with missing values resulting in IndexError (:issue:`58810`)
+- Bug in :meth:`DateOffset.rollback` (and subclass methods) with ``normalize=True`` rolling back one offset too long (:issue:`32616`)
 - Bug in :meth:`DatetimeIndex.is_year_start` and :meth:`DatetimeIndex.is_quarter_start` does not raise on Custom business days frequencies bigger then "1C" (:issue:`58664`)
 - Bug in :meth:`DatetimeIndex.is_year_start` and :meth:`DatetimeIndex.is_quarter_start` returning ``False`` on double-digit frequencies (:issue:`58523`)
 - Bug in :meth:`DatetimeIndex.union` and :meth:`DatetimeIndex.intersection` when ``unit`` was non-nanosecond (:issue:`59036`)
@@ -1048,6 +1050,7 @@ Interval
 - Bug in :class:`Index`, :class:`Series`, :class:`DataFrame` constructors when given a sequence of :class:`Interval` subclass objects casting them to :class:`Interval` (:issue:`46945`)
 - Bug in :func:`interval_range` where start and end numeric types were always cast to 64 bit (:issue:`57268`)
 - Bug in :meth:`IntervalIndex.get_indexer` and :meth:`IntervalIndex.drop` when one of the sides of the index is non-unique (:issue:`52245`)
+- Construction of :class:`IntervalArray` and :class:`IntervalIndex` from arrays with mismatched signed/unsigned integer dtypes (e.g., ``int64`` and ``uint64``) now raises a :exc:`TypeError` instead of proceeding silently. (:issue:`55715`)
 
 Indexing
 ^^^^^^^^
@@ -1176,6 +1179,7 @@ Groupby/resample/rolling
 
 Reshaping
 ^^^^^^^^^
+- Bug in :func:`concat` with mixed integer and bool dtypes incorrectly casting the bools to integers (:issue:`45101`)
 - Bug in :func:`qcut` where values at the quantile boundaries could be incorrectly assigned (:issue:`59355`)
 - Bug in :meth:`DataFrame.combine_first` not preserving the column order (:issue:`60427`)
 - Bug in :meth:`DataFrame.explode` producing incorrect result for :class:`pyarrow.large_list` type (:issue:`61091`)
@@ -1234,6 +1238,7 @@ Other
 - Bug in :meth:`DataFrame.query` where using duplicate column names led to a ``TypeError``. (:issue:`59950`)
 - Bug in :meth:`DataFrame.query` which raised an exception or produced incorrect results when expressions contained backtick-quoted column names containing the hash character ``#``, backticks, or characters that fall outside the ASCII range (U+0001..U+007F). (:issue:`59285`) (:issue:`49633`)
 - Bug in :meth:`DataFrame.query` which raised an exception when querying integer column names using backticks. (:issue:`60494`)
+- Bug in :meth:`DataFrame.rename` and :meth:`Series.rename` when passed a ``mapper``, ``index``, or ``columns`` argument that is a :class:`Series` with non-unique ``ser.index`` producing a corrupted result instead of raising ``ValueError`` (:issue:`58621`)
 - Bug in :meth:`DataFrame.sample` with ``replace=False`` and ``(n * max(weights) / sum(weights)) > 1``, the method would return biased results. Now raises ``ValueError``. (:issue:`61516`)
 - Bug in :meth:`DataFrame.shift` where passing a ``freq`` on a DataFrame with no columns did not shift the index correctly. (:issue:`60102`)
 - Bug in :meth:`DataFrame.sort_index` when passing ``axis="columns"`` and ``ignore_index=True`` and ``ascending=False`` not returning a :class:`RangeIndex` columns (:issue:`57293`)

pandas/_config/localization.py

@@ -79,7 +79,7 @@ def can_set_locale(lc: str, lc_var: int = locale.LC_ALL) -> bool:
         with set_locale(lc, lc_var=lc_var):
             pass
     except (ValueError, locale.Error):
-        # horrible name for a Exception subclass
+        # horrible name for an Exception subclass
         return False
     else:
         return True

pandas/_libs/tslibs/offsets.pyx

@@ -692,6 +692,9 @@ cdef class BaseOffset:
             Rolled timestamp if not on offset, otherwise unchanged timestamp.
         """
         dt = Timestamp(dt)
+        if self.normalize and (dt - dt.normalize())._value != 0:
+            # GH#32616
+            dt = dt.normalize()
         if not self.is_on_offset(dt):
             dt = dt - type(self)(1, normalize=self.normalize, **self.kwds)
         return dt

pandas/core/arrays/arrow/array.py

@@ -829,6 +829,14 @@ def __arrow_array__(self, type=None):
         """Convert myself to a pyarrow ChunkedArray."""
         return self._pa_array
 
+    def __array_ufunc__(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
+        # Need to wrap np.array results GH#62800
+        result = super().__array_ufunc__(ufunc, method, *inputs, **kwargs)
+        if type(self) is ArrowExtensionArray:
+            # Exclude ArrowStringArray
+            return type(self)._from_sequence(result)
+        return result
+
     def __array__(
         self, dtype: NpDtype | None = None, copy: bool | None = None
     ) -> np.ndarray:

pandas/core/arrays/categorical.py

@@ -269,7 +269,7 @@ class Categorical(NDArrayBackedExtensionArray, PandasObject, ObjectStringArrayMi
         categories are assumed to be the unique values of `values` (sorted, if
         possible, otherwise in the order in which they appear).
     ordered : bool, default False
-        Whether or not this categorical is treated as a ordered categorical.
+        Whether or not this categorical is treated as an ordered categorical.
         If True, the resulting categorical will be ordered.
         An ordered categorical respects, when sorted, the order of its
         `categories` attribute (which in turn is the `categories` argument, if
@@ -1103,7 +1103,7 @@ def set_categories(
         new_categories : Index-like
            The categories in new order.
         ordered : bool, default None
-           Whether or not the categorical is treated as a ordered categorical.
+           Whether or not the categorical is treated as an ordered categorical.
            If not given, do not change the ordered information.
         rename : bool, default False
            Whether or not the new_categories should be considered as a rename
@@ -1277,7 +1277,7 @@ def reorder_categories(self, new_categories, ordered=None) -> Self:
         new_categories : Index-like
            The categories in new order.
         ordered : bool, optional
-           Whether or not the categorical is treated as a ordered categorical.
+           Whether or not the categorical is treated as an ordered categorical.
            If not given, do not change the ordered information.
 
         Returns

pandas/core/arrays/interval.py

@@ -420,6 +420,18 @@ def _ensure_simple_new_inputs(
 
         dtype = IntervalDtype(left.dtype, closed=closed)
 
+        # Check for mismatched signed/unsigned integer dtypes after casting
+        left_dtype = left.dtype
+        right_dtype = right.dtype
+        if (
+            left_dtype.kind in "iu"
+            and right_dtype.kind in "iu"
+            and left_dtype.kind != right_dtype.kind
+        ):
+            raise TypeError(
+                f"Left and right arrays must have matching signedness. "
+                f"Got {left_dtype} and {right_dtype}."
+            )
         return left, right, dtype
 
     @classmethod

pandas/core/arrays/timedeltas.py

@@ -1212,7 +1212,7 @@ def _objects_to_td64ns(
     data, unit=None, errors: DateTimeErrorChoices = "raise"
 ) -> np.ndarray:
     """
-    Convert a object-dtyped or string-dtyped array into an
+    Convert an object-dtyped or string-dtyped array into a
     timedelta64[ns]-dtyped array.
 
     Parameters

pandas/core/dtypes/base.py

@@ -517,7 +517,7 @@ class Registry:
     """
     Registry for dtype inference.
 
-    The registry allows one to map a string repr of a extension
+    The registry allows one to map a string repr of an extension
     dtype to an extension dtype. The string alias can be used in several
     places, including
 

pandas/core/dtypes/concat.py

@@ -161,6 +161,10 @@ def _get_result_dtype(
                 # coerce to object
                 target_dtype = np.dtype(object)
                 kinds = {"o"}
+    elif "b" in kinds and len(kinds) > 1:
+        # GH#21108, GH#45101
+        target_dtype = np.dtype(object)
+        kinds = {"o"}
     else:
         # error: Argument 1 to "np_find_common_type" has incompatible type
         # "*Set[Union[ExtensionDtype, Any]]"; expected "dtype[Any]"