Merge remote-tracking branch 'upstream/main' into enh_top-level_object_name

Author: jorisvandenbossche

doc/source/whatsnew/v3.0.0.rst

@@ -613,6 +613,7 @@ Categorical
 Datetimelike
 ^^^^^^^^^^^^
 - Bug in :attr:`is_year_start` where a DateTimeIndex constructed via a date_range with frequency 'MS' wouldn't have the correct year or quarter start attributes (:issue:`57377`)
+- Bug in :class:`DataFrame` raising ``ValueError`` when ``dtype`` is ``timedelta64`` and ``data`` is a list containing ``None`` (:issue:`60064`)
 - Bug in :class:`Timestamp` constructor failing to raise when ``tz=None`` is explicitly specified in conjunction with timezone-aware ``tzinfo`` or data (:issue:`48688`)
 - 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`)
@@ -710,6 +711,7 @@ Period
 Plotting
 ^^^^^^^^
 - Bug in :meth:`.DataFrameGroupBy.boxplot` failed when there were multiple groupings (:issue:`14701`)
+- Bug in :meth:`DataFrame.plot.bar` with ``stacked=True`` where labels on stacked bars with zero-height segments were incorrectly positioned at the base instead of the label position of the previous segment (:issue:`59429`)
 - Bug in :meth:`DataFrame.plot.line` raising ``ValueError`` when set both color and a ``dict`` style (:issue:`59461`)
 - Bug in :meth:`DataFrame.plot` that causes a shift to the right when the frequency multiplier is greater than one. (:issue:`57587`)
 - Bug in :meth:`Series.plot` with ``kind="pie"`` with :class:`ArrowDtype` (:issue:`59192`)

pandas/_libs/tslibs/period.pyx

@@ -114,7 +114,6 @@ from pandas._libs.tslibs.offsets import (
     INVALID_FREQ_ERR_MSG,
     BDay,
 )
-
 from pandas.util._decorators import set_module
 
 cdef:

pandas/_libs/tslibs/timedeltas.pyx

@@ -1,8 +1,8 @@
 import collections
 import warnings
 
-from pandas.util._exceptions import find_stack_level
 from pandas.util._decorators import set_module
+from pandas.util._exceptions import find_stack_level
 
 cimport cython
 from cpython.object cimport (
@@ -1855,7 +1855,6 @@ cdef class _Timedelta(timedelta):
 
 # Python front end to C extension type _Timedelta
 # This serves as the box for timedelta64
-
 @set_module("pandas")
 class Timedelta(_Timedelta):
     """
@@ -1918,7 +1917,7 @@ class Timedelta(_Timedelta):
     --------
     Here we initialize Timedelta object with both value and unit
 
-    >>> td = pd.Timedelta(1, "d")
+    >>> td = pd.Timedelta(1, "D")
     >>> td
     Timedelta('1 days 00:00:00')
 

pandas/_libs/tslibs/timestamps.pyx

@@ -50,8 +50,8 @@ import datetime as dt
 from pandas._libs.tslibs cimport ccalendar
 from pandas._libs.tslibs.base cimport ABCTimestamp
 
-from pandas.util._exceptions import find_stack_level
 from pandas.util._decorators import set_module
+from pandas.util._exceptions import find_stack_level
 
 from pandas._libs.tslibs.conversion cimport (
     _TSObject,
@@ -2927,7 +2927,7 @@ timedelta}, default 'raise'
         --------
         >>> ts = pd.Timestamp(1584226800, unit='s', tz='Europe/Stockholm')
         >>> ts.tz
-        <DstTzInfo 'Europe/Stockholm' CET+1:00:00 STD>
+        zoneinfo.ZoneInfo(key='Europe/Stockholm')
         """
         return self.tzinfo
 

pandas/core/construction.py

@@ -807,6 +807,12 @@ def _try_cast(
         )
 
     elif dtype.kind in "mM":
+        if is_ndarray:
+            arr = cast(np.ndarray, arr)
+            if arr.ndim == 2 and arr.shape[1] == 1:
+                # GH#60081: DataFrame Constructor converts 1D data to array of
+                # shape (N, 1), but maybe_cast_to_datetime assumes 1D input
+                return maybe_cast_to_datetime(arr[:, 0], dtype).reshape(arr.shape)
         return maybe_cast_to_datetime(arr, dtype)
 
     # GH#15832: Check if we are requesting a numeric dtype and

pandas/core/dtypes/cast.py

@@ -1205,7 +1205,7 @@ def maybe_infer_to_datetimelike(
 
 def maybe_cast_to_datetime(
     value: np.ndarray | list, dtype: np.dtype
-) -> ExtensionArray | np.ndarray:
+) -> DatetimeArray | TimedeltaArray | np.ndarray:
     """
     try to cast the array/value to a datetimelike dtype, converting float
     nan to iNaT

pandas/plotting/_matplotlib/core.py

@@ -1960,7 +1960,7 @@ def _make_plot(self, fig: Figure) -> None:
                 )
                 ax.set_title(label)
             elif self.stacked:
-                mask = y > 0
+                mask = y >= 0
                 start = np.where(mask, pos_prior, neg_prior) + self._start_base
                 w = self.bar_width / 2
                 rect = self._plot(

pandas/tests/api/test_api.py

@@ -413,7 +413,6 @@ def test_set_module():
     assert pd.PeriodIndex.__module__ == "pandas"
     assert pd.RangeIndex.__module__ == "pandas"
     assert pd.TimedeltaIndex.__module__ == "pandas"
+    assert pd.Period.__module__ == "pandas"
     assert pd.Timestamp.__module__ == "pandas"
     assert pd.Timedelta.__module__ == "pandas"
-    assert pd.Period.__module__ == "pandas"
-

pandas/tests/frame/test_constructors.py

@@ -2772,6 +2772,14 @@ def test_construction_datetime_resolution_inference(self, cons):
         res_dtype2 = tm.get_dtype(obj2)
         assert res_dtype2 == "M8[us, US/Pacific]", res_dtype2
 
+    def test_construction_nan_value_timedelta64_dtype(self):
+        # GH#60064
+        result = DataFrame([None, 1], dtype="timedelta64[ns]")
+        expected = DataFrame(
+            ["NaT", "0 days 00:00:00.000000001"], dtype="timedelta64[ns]"
+        )
+        tm.assert_frame_equal(result, expected)
+
 
 class TestDataFrameConstructorIndexInference:
     def test_frame_from_dict_of_series_overlapping_monthly_period_indexes(self):

pandas/tests/plotting/frame/test_frame.py

@@ -774,6 +774,16 @@ def test_bar_nan_stacked(self):
         expected = [0.0, 0.0, 0.0, 10.0, 0.0, 20.0, 15.0, 10.0, 40.0]
         assert result == expected
 
+    def test_bar_stacked_label_position_with_zero_height(self):
+        # GH 59429
+        df = DataFrame({"A": [3, 0, 1], "B": [0, 2, 4], "C": [5, 0, 2]})
+        ax = df.plot.bar(stacked=True)
+        ax.bar_label(ax.containers[-1])
+        expected = [8.0, 2.0, 7.0]
+        result = [text.xy[1] for text in ax.texts]
+        tm.assert_almost_equal(result, expected)
+        plt.close("all")
+
     @pytest.mark.parametrize("idx", [Index, pd.CategoricalIndex])
     def test_bar_categorical(self, idx):
         # GH 13019