Merge branch 'main' into docs/excel-header-bold-styler

Author: antznette1

doc/source/whatsnew/v3.0.0.rst

@@ -737,6 +737,7 @@ Other Deprecations
 - Deprecated allowing ``fill_value`` that cannot be held in the original dtype (excepting NA values for integer and bool dtypes) in :meth:`Series.shift` and :meth:`DataFrame.shift` (:issue:`53802`)
 - Deprecated backward-compatibility behavior for :meth:`DataFrame.select_dtypes` matching "str" dtype when ``np.object_`` is specified (:issue:`61916`)
 - Deprecated option "future.no_silent_downcasting", as it is no longer used. In a future version accessing this option will raise (:issue:`59502`)
+- Deprecated silent casting of non-datetime 'other' to datetime in :meth:`Series.combine_first` (:issue:`62931`)
 - Deprecated slicing on a :class:`Series` or :class:`DataFrame` with a :class:`DatetimeIndex` using a ``datetime.date`` object, explicitly cast to :class:`Timestamp` instead (:issue:`35830`)
 - Deprecated the 'inplace' keyword from :meth:`Resampler.interpolate`, as passing ``True`` raises ``AttributeError`` (:issue:`58690`)
 
@@ -974,13 +975,15 @@ Datetimelike
 - Bug in :class:`Timestamp` constructor failing to raise when given a ``np.datetime64`` object with non-standard unit (:issue:`25611`)
 - Bug in :func:`date_range` where the last valid timestamp would sometimes not be produced (:issue:`56134`)
 - Bug in :func:`date_range` where using a negative frequency value would not include all points between the start and end values (:issue:`56147`)
+- Bug in :func:`infer_freq` with a :class:`Series` with :class:`ArrowDtype` timestamp dtype incorrectly raising ``TypeError`` (:issue:`58403`)
 - Bug in :func:`to_datetime` where passing an ``lxml.etree._ElementUnicodeResult`` together with ``format`` raised  ``TypeError``. Now subclasses of ``str`` are handled. (:issue:`60933`)
 - Bug in :func:`tseries.api.guess_datetime_format` would fail to infer time format when "%Y" == "%H%M" (:issue:`57452`)
 - Bug in :func:`tseries.frequencies.to_offset` would fail to parse frequency strings starting with "LWOM" (:issue:`59218`)
 - 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.asof` with a string key giving incorrect results (:issue:`50946`)
 - 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`)
@@ -1183,10 +1186,13 @@ 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.combine_first` with non-unique columns incorrectly raising (:issue:`29135`)
+- Bug in :meth:`DataFrame.combine` with non-unique columns incorrectly raising (:issue:`51340`)
 - Bug in :meth:`DataFrame.explode` producing incorrect result for :class:`pyarrow.large_list` type (:issue:`61091`)
 - Bug in :meth:`DataFrame.join` inconsistently setting result index name (:issue:`55815`)
 - Bug in :meth:`DataFrame.join` when a :class:`DataFrame` with a :class:`MultiIndex` would raise an ``AssertionError`` when :attr:`MultiIndex.names` contained ``None``. (:issue:`58721`)
 - Bug in :meth:`DataFrame.merge` where merging on a column containing only ``NaN`` values resulted in an out-of-bounds array access (:issue:`59421`)
+- Bug in :meth:`Series.combine_first` incorrectly replacing ``None`` entries with ``NaN`` (:issue:`58977`)
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when ``sort=False`` (:issue:`54987`, :issue:`55516`)
 - Bug in :meth:`DataFrame.unstack` raising an error with indexes containing ``NaN`` with ``sort=False`` (:issue:`61221`)
 - Bug in :meth:`DataFrame.merge` when merging two :class:`DataFrame` on ``intc`` or ``uintc`` types on Windows (:issue:`60091`, :issue:`58713`)

pandas/core/frame.py

@@ -9038,16 +9038,6 @@ def combine(
         0  0 -5.0
         1  0  4.0
 
-        However, if the same element in both dataframes is None, that None
-        is preserved
-
-        >>> df1 = pd.DataFrame({"A": [0, 0], "B": [None, 4]})
-        >>> df2 = pd.DataFrame({"A": [1, 1], "B": [None, 3]})
-        >>> df1.combine(df2, take_smaller, fill_value=-5)
-            A    B
-        0  0 -5.0
-        1  0  3.0
-
         Example that demonstrates the use of `overwrite` and behavior when
         the axis differ between the dataframes.
 
@@ -9106,11 +9096,14 @@ def combine(
 
         # preserve column order
         new_columns = self.columns.union(other_columns, sort=False)
+        this = this.reindex(new_columns, axis=1)
+        other = other.reindex(new_columns, axis=1)
+
         do_fill = fill_value is not None
         result = {}
-        for col in new_columns:
-            series = this[col]
-            other_series = other[col]
+        for i in range(this.shape[1]):
+            series = this.iloc[:, i]
+            other_series = other.iloc[:, i]
 
             this_dtype = series.dtype
             other_dtype = other_series.dtype
@@ -9121,7 +9114,7 @@ def combine(
             # don't overwrite columns unnecessarily
             # DO propagate if this column is not in the intersection
             if not overwrite and other_mask.all():
-                result[col] = this[col].copy()
+                result[i] = series.copy()
                 continue
 
             if do_fill:
@@ -9130,7 +9123,7 @@ def combine(
                 series[this_mask] = fill_value
                 other_series[other_mask] = fill_value
 
-            if col not in self.columns:
+            if new_columns[i] not in self.columns:
                 # If self DataFrame does not have col in other DataFrame,
                 # try to promote series, which is all NaN, as other_dtype.
                 new_dtype = other_dtype
@@ -9155,10 +9148,10 @@ def combine(
                     arr, new_dtype
                 )
 
-            result[col] = arr
+            result[i] = arr
 
-        # convert_objects just in case
-        frame_result = self._constructor(result, index=new_index, columns=new_columns)
+        frame_result = self._constructor(result, index=new_index)
+        frame_result.columns = new_columns
         return frame_result.__finalize__(self, method="combine")
 
     def combine_first(self, other: DataFrame) -> DataFrame:
@@ -9222,9 +9215,14 @@ def combiner(x: Series, y: Series):
             combined = self.combine(other, combiner, overwrite=False)
 
         dtypes = {
+            # Check for isinstance(..., (np.dtype, ExtensionDtype))
+            #  to prevent raising on non-unique columns see GH#29135.
+            #  Note we will just not-cast in these cases.
             col: find_common_type([self.dtypes[col], other.dtypes[col]])
             for col in self.columns.intersection(other.columns)
-            if combined.dtypes[col] != self.dtypes[col]
+            if isinstance(combined.dtypes[col], (np.dtype, ExtensionDtype))
+            and isinstance(self.dtypes[col], (np.dtype, ExtensionDtype))
+            and combined.dtypes[col] != self.dtypes[col]
         }
 
         if dtypes:
@@ -13820,8 +13818,8 @@ def quantile(
         0.1  1    1
         0.5  3  100
 
-        Specifying `numeric_only=False` will also compute the quantile of
-        datetime and timedelta data.
+        Specifying `numeric_only=False` will compute the quantiles for all
+        columns.
 
         >>> df = pd.DataFrame(
         ...     {

pandas/core/indexes/base.py

@@ -4168,7 +4168,7 @@ def reindex(
         limit : int, optional
             Maximum number of consecutive labels in ``target`` to match for
             inexact matches.
-        tolerance : int or float, optional
+        tolerance : int, float, or list-like, optional
             Maximum distance between original and new labels for inexact
             matches. The values of the index at the matching locations must
             satisfy the equation ``abs(index[indexer] - target) <= tolerance``.
@@ -5675,7 +5675,7 @@ def asof(self, label):
                 return self._na_value
         else:
             if isinstance(loc, slice):
-                loc = loc.indices(len(self))[-1]
+                return self[loc][-1]
 
         return self[loc]
 

pandas/core/series.py

@@ -87,7 +87,6 @@
 )
 from pandas.core.dtypes.dtypes import (
     ExtensionDtype,
-    SparseDtype,
 )
 from pandas.core.dtypes.generic import (
     ABCDataFrame,
@@ -3112,8 +3111,8 @@ def combine(
 
         Combine the Series and `other` using `func` to perform elementwise
         selection for combined Series.
-        `fill_value` is assumed when value is missing at some index
-        from one of the two objects being combined.
+        `fill_value` is assumed when value is not present at some index
+        from one of the two Series being combined.
 
         Parameters
         ----------
@@ -3254,9 +3253,6 @@ def combine_first(self, other) -> Series:
         if self.dtype == other.dtype:
             if self.index.equals(other.index):
                 return self.mask(self.isna(), other)
-            elif self._can_hold_na and not isinstance(self.dtype, SparseDtype):
-                this, other = self.align(other, join="outer")
-                return this.mask(this.isna(), other)
 
         new_index = self.index.union(other.index)
 
@@ -3271,6 +3267,16 @@ def combine_first(self, other) -> Series:
         if this.dtype.kind == "M" and other.dtype.kind != "M":
             # TODO: try to match resos?
             other = to_datetime(other)
+            warnings.warn(
+                # GH#62931
+                "Silently casting non-datetime 'other' to datetime in "
+                "Series.combine_first is deprecated and will be removed "
+                "in a future version. Explicitly cast before calling "
+                "combine_first instead.",
+                Pandas4Warning,
+                stacklevel=find_stack_level(),
+            )
+
         combined = concat([this, other])
         combined = combined.reindex(new_index)
         return combined.__finalize__(self, method="combine_first")

pandas/tests/frame/methods/test_combine.py

@@ -45,3 +45,19 @@ def test_combine_generic(self, float_frame):
         )
         tm.assert_frame_equal(chunk, exp)
         tm.assert_frame_equal(chunk2, exp)
+
+    def test_combine_nonunique_columns(self):
+        # GH#51340
+
+        df = pd.DataFrame({"A": range(5), "B": range(5)})
+        df.columns = ["A", "A"]
+
+        other = df.copy()
+        df.iloc[1, :] = None
+
+        def combiner(a, b):
+            return b
+
+        result = df.combine(other, combiner)
+        expected = other.astype("float64")
+        tm.assert_frame_equal(result, expected)

pandas/tests/frame/methods/test_combine_first.py

@@ -413,6 +413,18 @@ def test_combine_first_preserve_EA_precision(self, wide_val, dtype):
         expected = DataFrame({"A": [wide_val, 5, wide_val]}, dtype=dtype)
         tm.assert_frame_equal(result, expected)
 
+    def test_combine_first_non_unique_columns(self):
+        # GH#29135
+        df1 = DataFrame([[1, np.nan], [3, 4]], columns=["P", "Q"], index=["A", "B"])
+        df2 = DataFrame(
+            [[5, 6, 7], [8, 9, np.nan]], columns=["P", "Q", "Q"], index=["A", "B"]
+        )
+        result = df1.combine_first(df2)
+        expected = DataFrame(
+            [[1, 6.0, 7.0], [3, 4.0, 4.0]], index=["A", "B"], columns=["P", "Q", "Q"]
+        )
+        tm.assert_frame_equal(result, expected)
+
 
 @pytest.mark.parametrize(
     "scalar1, scalar2",

pandas/tests/indexes/datetimes/methods/test_asof.py

@@ -1,6 +1,7 @@
 from datetime import timedelta
 
 from pandas import (
+    DatetimeIndex,
     Index,
     Timestamp,
     date_range,
@@ -28,3 +29,18 @@ def test_asof(self):
 
         dt = index[0].to_pydatetime()
         assert isinstance(index.asof(dt), Timestamp)
+
+    def test_asof_datetime_string(self):
+        # GH#50946
+
+        dti = date_range("2021-08-05", "2021-08-10", freq="1D")
+
+        key = "2021-08-09"
+        res = dti.asof(key)
+        exp = dti[4]
+        assert res == exp
+
+        # add a non-midnight time caused a bug
+        dti2 = DatetimeIndex(list(dti) + ["2021-08-11 00:00:01"])
+        res = dti2.asof(key)
+        assert res == exp

pandas/tests/series/methods/test_combine_first.py

@@ -2,6 +2,8 @@
 
 import numpy as np
 
+from pandas.errors import Pandas4Warning
+
 import pandas as pd
 from pandas import (
     Period,
@@ -75,9 +77,14 @@ def test_combine_first_dt64(self, unit):
         xp = to_datetime(Series(["2010", "2011"])).dt.as_unit(unit)
         tm.assert_series_equal(rs, xp)
 
+    def test_combine_first_dt64_casting_deprecation(self, unit):
+        # GH#62931
         s0 = to_datetime(Series(["2010", np.nan])).dt.as_unit(unit)
         s1 = Series([np.nan, "2011"])
-        rs = s0.combine_first(s1)
+
+        msg = "Silently casting non-datetime 'other' to datetime"
+        with tm.assert_produces_warning(Pandas4Warning, match=msg):
+            rs = s0.combine_first(s1)
 
         xp = Series([datetime(2010, 1, 1), "2011"], dtype=f"datetime64[{unit}]")
 
@@ -144,3 +151,12 @@ def test_combine_mixed_timezone(self):
             ),
         )
         tm.assert_series_equal(result, expected)
+
+    def test_combine_first_none_not_nan(self):
+        # GH#58977
+        s1 = Series([None, None, None], index=["a", "b", "c"])
+        s2 = Series([None, None, None], index=["b", "c", "d"])
+
+        result = s1.combine_first(s2)
+        expected = Series([None] * 4, index=["a", "b", "c", "d"])
+        tm.assert_series_equal(result, expected)

pandas/tests/tseries/frequencies/test_inference.py

@@ -13,6 +13,7 @@
 from pandas._libs.tslibs.offsets import _get_offset
 from pandas._libs.tslibs.period import INVALID_FREQ_ERR_MSG
 from pandas.compat import is_platform_windows
+import pandas.util._test_decorators as td
 
 from pandas import (
     DatetimeIndex,
@@ -542,3 +543,16 @@ def test_infer_freq_non_nano_tzaware(tz_aware_fixture):
 
     res = frequencies.infer_freq(dta)
     assert res == "B"
+
+
+@td.skip_if_no("pyarrow")
+def test_infer_freq_pyarrow():
+    # GH#58403
+    data = ["2022-01-01T10:00:00", "2022-01-01T10:00:30", "2022-01-01T10:01:00"]
+    pd_series = Series(data).astype("timestamp[s][pyarrow]")
+    pd_index = Index(data).astype("timestamp[s][pyarrow]")
+
+    assert frequencies.infer_freq(pd_index.values) == "30s"
+    assert frequencies.infer_freq(pd_series.values) == "30s"
+    assert frequencies.infer_freq(pd_index) == "30s"
+    assert frequencies.infer_freq(pd_series) == "30s"

pandas/tseries/frequencies.py

@@ -37,6 +37,7 @@
 
 from pandas.core.dtypes.common import is_numeric_dtype
 from pandas.core.dtypes.dtypes import (
+    ArrowDtype,
     DatetimeTZDtype,
     PeriodDtype,
 )
@@ -132,6 +133,14 @@ def infer_freq(
 
     if isinstance(index, ABCSeries):
         values = index._values
+
+        if isinstance(index.dtype, ArrowDtype):
+            import pyarrow as pa
+
+            if pa.types.is_timestamp(values.dtype.pyarrow_dtype):
+                # GH#58403
+                values = values._to_datetimearray()
+
         if not (
             lib.is_np_dtype(values.dtype, "mM")
             or isinstance(values.dtype, DatetimeTZDtype)