Merge branch 'main' of https://github.com/pandas-dev/pandas into add_numeric_only_gb

� Conflicts:
�	doc/source/whatsnew/v1.5.0.rst

Author: rhshadrach

doc/source/whatsnew/v1.5.0.rst

@@ -95,6 +95,7 @@ Other enhancements
 - :meth:`pd.concat` now raises when ``levels`` is given but ``keys`` is None (:issue:`46653`)
 - :meth:`pd.concat` now raises when ``levels`` contains duplicate values (:issue:`46653`)
 - Added ``numeric_only`` argument to :meth:`DataFrame.corr`, :meth:`DataFrame.corrwith`, :meth:`DataFrame.cov`, :meth:`DataFrame.idxmin`, :meth:`DataFrame.idxmax`, :meth:`.GroupBy.idxmin`, :meth:`.GroupBy.idxmax`, :meth:`.GroupBy.var`, :meth:`.GroupBy.std`, :meth:`.GroupBy.sem`, and :meth:`.GroupBy.quantile` (:issue:`46560`)
+- A :class:`errors.PerformanceWarning` is now thrown when using ``string[pyarrow]`` dtype with methods that don't dispatch to ``pyarrow.compute`` methods (:issue:`42613`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_150.notable_bug_fixes:
@@ -481,7 +482,7 @@ Timedelta
 
 Time Zones
 ^^^^^^^^^^
--
+- Bug in :class:`Timestamp` constructor raising when passed a ``ZoneInfo`` tzinfo object (:issue:`46425`)
 -
 
 Numeric
@@ -569,6 +570,8 @@ I/O
 - Bug in Parquet roundtrip for Interval dtype with ``datetime64[ns]`` subtype (:issue:`45881`)
 - Bug in :func:`read_excel` when reading a ``.ods`` file with newlines between xml elements (:issue:`45598`)
 - Bug in :func:`read_parquet` when ``engine="fastparquet"`` where the file was not closed on error (:issue:`46555`)
+- :meth:`to_html` now excludes the ``border`` attribute from ``<table>`` elements when ``border`` keyword is set to ``False``.
+-
 
 Period
 ^^^^^^
@@ -599,7 +602,9 @@ Groupby/resample/rolling
 - Bug in :meth:`GroupBy.cummax` with ``int64`` dtype with leading value being the smallest possible int64 (:issue:`46382`)
 - Bug in :meth:`GroupBy.max` with empty groups and ``uint64`` dtype incorrectly raising ``RuntimeError`` (:issue:`46408`)
 - Bug in :meth:`.GroupBy.apply` would fail when ``func`` was a string and args or kwargs were supplied (:issue:`46479`)
--
+- Bug in :meth:`SeriesGroupBy.apply` would incorrectly name its result when there was a unique group (:issue:`46369`)
+- Bug in :meth:`.Rolling.var` would segfault calculating weighted variance when window size was larger than data size (:issue:`46760`)
+- Bug in :meth:`Grouper.__repr__` where ``dropna`` was not included. Now it is (:issue:`46754`)
 
 Reshaping
 ^^^^^^^^^

pandas/_libs/algos_common_helper.pxi.in

@@ -65,7 +65,8 @@ def ensure_{{name}}(object arr, copy=True):
         if (<ndarray>arr).descr.type_num == NPY_{{c_type}}:
             return arr
         else:
-            return arr.astype(np.{{dtype}}, copy=copy)
+            # equiv: arr.astype(np.{{dtype}}, copy=copy)
+            return cnp.PyArray_Cast(<ndarray>arr, cnp.NPY_{{c_type}})
     else:
         return np.array(arr, dtype=np.{{dtype}})
 

pandas/_libs/tslib.pyx

@@ -424,7 +424,7 @@ cpdef array_to_datetime(
     """
     cdef:
         Py_ssize_t i, n = len(values)
-        object val, py_dt, tz, tz_out = None
+        object val, tz
         ndarray[int64_t] iresult
         ndarray[object] oresult
         npy_datetimestruct dts
@@ -443,6 +443,8 @@ cpdef array_to_datetime(
         float offset_seconds, tz_offset
         set out_tzoffset_vals = set()
         bint string_to_dts_failed
+        datetime py_dt
+        tzinfo tz_out = None
 
     # specify error conditions
     assert is_raise or is_ignore or is_coerce
@@ -647,6 +649,8 @@ cpdef array_to_datetime(
     return result, tz_out
 
 
+@cython.wraparound(False)
+@cython.boundscheck(False)
 cdef ndarray[object] ignore_errors_out_of_bounds_fallback(ndarray[object] values):
     """
     Fallback for array_to_datetime if an OutOfBoundsDatetime is raised

pandas/_libs/tslibs/conversion.pyx

@@ -56,6 +56,7 @@ from pandas._libs.tslibs.timezones cimport (
     is_fixed_offset,
     is_tzlocal,
     is_utc,
+    is_zoneinfo,
     maybe_get_tz,
     tz_compare,
     utc_pytz as UTC,
@@ -532,7 +533,7 @@ cdef _TSObject _create_tsobject_tz_using_offset(npy_datetimestruct dts,
     # see PEP 495 https://www.python.org/dev/peps/pep-0495/#the-fold-attribute
     if is_utc(tz):
         pass
-    elif is_tzlocal(tz):
+    elif is_tzlocal(tz) or is_zoneinfo(tz):
         localize_tzinfo_api(obj.value, tz, &obj.fold)
     else:
         trans, deltas, typ = get_dst_info(tz)
@@ -581,55 +582,62 @@ cdef _TSObject _convert_str_to_tsobject(object ts, tzinfo tz, str unit,
     """
     cdef:
         npy_datetimestruct dts
-        int out_local = 0, out_tzoffset = 0
-        bint do_parse_datetime_string = False
+        int out_local = 0, out_tzoffset = 0, string_to_dts_failed
+        datetime dt
+        int64_t ival
 
     if len(ts) == 0 or ts in nat_strings:
         ts = NaT
+        obj = _TSObject()
+        obj.value = NPY_NAT
+        obj.tzinfo = tz
+        return obj
     elif ts == 'now':
         # Issue 9000, we short-circuit rather than going
         # into np_datetime_strings which returns utc
-        ts = datetime.now(tz)
+        dt = datetime.now(tz)
     elif ts == 'today':
         # Issue 9000, we short-circuit rather than going
         # into np_datetime_strings which returns a normalized datetime
-        ts = datetime.now(tz)
+        dt = datetime.now(tz)
         # equiv: datetime.today().replace(tzinfo=tz)
     else:
         string_to_dts_failed = _string_to_dts(
             ts, &dts, &out_local,
             &out_tzoffset, False
         )
-        try:
-            if not string_to_dts_failed:
+        if not string_to_dts_failed:
+            try:
                 check_dts_bounds(&dts)
                 if out_local == 1:
                     return _create_tsobject_tz_using_offset(dts,
                                                             out_tzoffset, tz)
                 else:
-                    ts = dtstruct_to_dt64(&dts)
+                    ival = dtstruct_to_dt64(&dts)
                     if tz is not None:
                         # shift for _localize_tso
-                        ts = tz_localize_to_utc_single(ts, tz,
-                                                       ambiguous="raise")
+                        ival = tz_localize_to_utc_single(ival, tz,
+                                                         ambiguous="raise")
 
-        except OutOfBoundsDatetime:
-            # GH#19382 for just-barely-OutOfBounds falling back to dateutil
-            # parser will return incorrect result because it will ignore
-            # nanoseconds
-            raise
+                    return convert_to_tsobject(ival, tz, None, False, False)
 
-        except ValueError:
-            do_parse_datetime_string = True
+            except OutOfBoundsDatetime:
+                # GH#19382 for just-barely-OutOfBounds falling back to dateutil
+                # parser will return incorrect result because it will ignore
+                # nanoseconds
+                raise
 
-        if string_to_dts_failed or do_parse_datetime_string:
-            try:
-                ts = parse_datetime_string(ts, dayfirst=dayfirst,
-                                           yearfirst=yearfirst)
-            except (ValueError, OverflowError):
-                raise ValueError("could not convert string to Timestamp")
+            except ValueError:
+                # Fall through to parse_datetime_string
+                pass
+
+        try:
+            dt = parse_datetime_string(ts, dayfirst=dayfirst,
+                                       yearfirst=yearfirst)
+        except (ValueError, OverflowError):
+            raise ValueError("could not convert string to Timestamp")
 
-    return convert_to_tsobject(ts, tz, unit, dayfirst, yearfirst)
+    return convert_datetime_to_tsobject(dt, tz)
 
 
 cdef inline check_overflows(_TSObject obj):
@@ -688,12 +696,8 @@ cdef inline void _localize_tso(_TSObject obj, tzinfo tz):
     Sets obj.tzinfo inplace, alters obj.dts inplace.
     """
     cdef:
-        ndarray[int64_t] trans
-        int64_t[::1] deltas
         int64_t local_val
-        int64_t* tdata
-        Py_ssize_t pos, ntrans, outpos = -1
-        str typ
+        Py_ssize_t outpos = -1
 
     assert obj.tzinfo is None
 

pandas/_libs/tslibs/timedeltas.pxd

@@ -1,6 +1,8 @@
 from cpython.datetime cimport timedelta
 from numpy cimport int64_t
 
+from .np_datetime cimport NPY_DATETIMEUNIT
+
 
 # Exposed for tslib, not intended for outside use.
 cpdef int64_t delta_to_nanoseconds(delta) except? -1
@@ -13,7 +15,9 @@ cdef class _Timedelta(timedelta):
         int64_t value      # nanoseconds
         bint _is_populated  # are my components populated
         int64_t _d, _h, _m, _s, _ms, _us, _ns
+        NPY_DATETIMEUNIT _reso
 
     cpdef timedelta to_pytimedelta(_Timedelta self)
     cdef bint _has_ns(self)
     cdef _ensure_components(_Timedelta self)
+    cdef inline bint _compare_mismatched_resos(self, _Timedelta other, op)