Merge remote-tracking branch 'upstream/main' into ref/read_csv/cln

Author: mroeschke

.github/workflows/wheels.yml

@@ -140,7 +140,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/[email protected].1
+        uses: pypa/[email protected].2
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

asv_bench/benchmarks/indexing.py

@@ -546,24 +546,17 @@ def time_chained_indexing(self, mode):
 
 
 class Block:
-    params = [
-        (True, "True"),
-        (np.array(True), "np.array(True)"),
-    ]
-
-    def setup(self, true_value, mode):
+    def setup(self):
         self.df = DataFrame(
             False,
             columns=np.arange(500).astype(str),
             index=date_range("2010-01-01", "2011-01-01"),
         )
 
-        self.true_value = true_value
-
-    def time_test(self, true_value, mode):
+    def time_test(self):
         start = datetime(2010, 5, 1)
         end = datetime(2010, 9, 1)
-        self.df.loc[start:end, :] = true_value
+        self.df.loc[start:end, :] = True
 
 
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

ci/code_checks.sh

@@ -95,7 +95,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.freqstr SA01" \
         -i "pandas.Period.month SA01" \
-        -i "pandas.Period.now SA01" \
         -i "pandas.Period.ordinal GL08" \
         -i "pandas.Period.strftime PR01,SA01" \
         -i "pandas.Period.to_timestamp SA01" \

doc/source/user_guide/categorical.rst

@@ -793,7 +793,7 @@ Assigning a ``Categorical`` to parts of a column of other types will use the val
     :okwarning:
 
     df = pd.DataFrame({"a": [1, 1, 1, 1, 1], "b": ["a", "a", "a", "a", "a"]})
-    df.loc[1:2, "a"] = pd.Categorical(["b", "b"], categories=["a", "b"])
+    df.loc[1:2, "a"] = pd.Categorical([2, 2], categories=[2, 3])
     df.loc[2:3, "b"] = pd.Categorical(["b", "b"], categories=["a", "b"])
     df
     df.dtypes

doc/source/whatsnew/v3.0.0.rst

@@ -42,6 +42,7 @@ Other enhancements
 - :func:`DataFrame.to_excel` argument ``merge_cells`` now accepts a value of ``"columns"`` to only merge :class:`MultiIndex` column header header cells (:issue:`35384`)
 - :meth:`DataFrame.corrwith` now accepts ``min_periods`` as optional arguments, as in :meth:`DataFrame.corr` and :meth:`Series.corr` (:issue:`9490`)
 - :meth:`DataFrame.cummin`, :meth:`DataFrame.cummax`, :meth:`DataFrame.cumprod` and :meth:`DataFrame.cumsum` methods now have a ``numeric_only`` parameter (:issue:`53072`)
+- :meth:`DataFrame.ewm` now allows ``adjust=False`` when ``times`` is provided (:issue:`54328`)
 - :meth:`DataFrame.fillna` and :meth:`Series.fillna` can now accept ``value=None``; for non-object dtype the corresponding NA value will be used (:issue:`57723`)
 - :meth:`DataFrame.pivot_table` and :func:`pivot_table` now allow the passing of keyword arguments to ``aggfunc`` through ``**kwargs`` (:issue:`57884`)
 - :meth:`Series.cummin` and :meth:`Series.cummax` now supports :class:`CategoricalDtype` (:issue:`52335`)
@@ -360,6 +361,7 @@ Other Removals
 - Changed the default value of ``na_action`` in :meth:`Categorical.map` to ``None`` (:issue:`51645`)
 - Changed the default value of ``observed`` in :meth:`DataFrame.groupby` and :meth:`Series.groupby` to ``True`` (:issue:`51811`)
 - Enforce deprecation in :func:`testing.assert_series_equal` and :func:`testing.assert_frame_equal` with object dtype and mismatched null-like values, which are now considered not-equal (:issue:`18463`)
+- Enforce banning of upcasting in in-place setitem-like operations (:issue:`59007`) (see `PDEP6 <https://pandas.pydata.org/pdeps/0006-ban-upcasting.html>`_)
 - Enforced deprecation ``all`` and ``any`` reductions with ``datetime64``, :class:`DatetimeTZDtype`, and :class:`PeriodDtype` dtypes (:issue:`58029`)
 - Enforced deprecation disallowing ``float`` "periods" in :func:`date_range`, :func:`period_range`, :func:`timedelta_range`, :func:`interval_range`,  (:issue:`56036`)
 - Enforced deprecation disallowing parsing datetimes with mixed time zones unless user passes ``utc=True`` to :func:`to_datetime` (:issue:`57275`)
@@ -502,6 +504,7 @@ Datetimelike
 - 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` when ``unit`` was non-nanosecond (:issue:`59036`)
+- Bug in :meth:`Series.dt.microsecond` producing incorrect results for pyarrow backed :class:`Series`. (:issue:`59154`)
 - Bug in setting scalar values with mismatched resolution into arrays with non-nanosecond ``datetime64``, ``timedelta64`` or :class:`DatetimeTZDtype` incorrectly truncating those scalars (:issue:`56410`)
 
 Timedelta

pandas/_libs/tslibs/nattype.pyx

@@ -1516,7 +1516,7 @@ default 'raise'
 
         See Also
         --------
-        Timestamp.asm8 : Return numpy datetime64 format in nanoseconds.
+        Timestamp.asm8 : Return numpy datetime64 format with same precision.
         Timestamp.to_pydatetime : Convert Timestamp object to a native
             Python datetime object.
         to_timedelta : Convert argument into timedelta object,

pandas/_libs/tslibs/period.pyx

@@ -2472,11 +2472,24 @@ cdef class _Period(PeriodMixin):
         """
         Return the period of now's date.
 
+        The `now` method provides a convenient way to generate a period
+        object for the current date and time. This can be particularly
+        useful in financial and economic analysis, where data is often
+        collected and analyzed in regular intervals (e.g., hourly, daily,
+        monthly). By specifying the frequency, users can create periods
+        that match the granularity of their data.
+
         Parameters
         ----------
         freq : str, BaseOffset
             Frequency to use for the returned period.
 
+        See Also
+        --------
+        to_datetime : Convert argument to datetime.
+        Period : Represents a period of time.
+        Period.to_timestamp : Return the Timestamp representation of the Period.
+
         Examples
         --------
         >>> pd.Period.now('h')  # doctest: +SKIP

pandas/_libs/tslibs/timestamps.pyx

@@ -1139,7 +1139,7 @@ cdef class _Timestamp(ABCTimestamp):
 
         See Also
         --------
-        Timestamp.asm8 : Return numpy datetime64 format in nanoseconds.
+        Timestamp.asm8 : Return numpy datetime64 format with same precision.
         Timestamp.to_pydatetime : Convert Timestamp object to a native
             Python datetime object.
         to_timedelta : Convert argument into timedelta object,
@@ -1170,7 +1170,7 @@ cdef class _Timestamp(ABCTimestamp):
     @property
     def asm8(self) -> np.datetime64:
         """
-        Return numpy datetime64 format in nanoseconds.
+        Return numpy datetime64 format with same precision.
 
         See Also
         --------

pandas/_libs/window/aggregations.pyx

@@ -1813,6 +1813,9 @@ def ewm(const float64_t[:] vals, const int64_t[:] start, const int64_t[:] end,
                             if normalize:
                                 # avoid numerical errors on constant series
                                 if weighted != cur:
+                                    if not adjust and com == 1:
+                                        # update in case of irregular-interval series
+                                        new_wt = 1. - old_wt
                                     weighted = old_wt * weighted + new_wt * cur
                                     weighted /= (old_wt + new_wt)
                                 if adjust:

pandas/core/arrays/arrow/array.py

@@ -2794,7 +2794,10 @@ def _dt_days_in_month(self) -> Self:
 
     @property
     def _dt_microsecond(self) -> Self:
-        return type(self)(pc.microsecond(self._pa_array))
+        # GH 59154
+        us = pc.microsecond(self._pa_array)
+        ms_to_us = pc.multiply(pc.millisecond(self._pa_array), 1000)
+        return type(self)(pc.add(us, ms_to_us))
 
     @property
     def _dt_minute(self) -> Self: