Merge remote-tracking branch 'upstream/main' into string-dtype-astype-str

Author: jorisvandenbossche

ci/code_checks.sh

@@ -70,10 +70,8 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         --format=actions \
         -i ES01 `# For now it is ok if docstrings are missing the extended summary` \
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
-        -i "pandas.NA SA01" \
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
-        -i "pandas.PeriodDtype.freq SA01" \
         -i "pandas.RangeIndex.from_range PR01,SA01" \
         -i "pandas.RangeIndex.step SA01" \
         -i "pandas.Series.cat.add_categories PR01,PR02" \
@@ -103,29 +101,24 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.sparse.from_coo PR07,SA01" \
         -i "pandas.Series.sparse.npoints SA01" \
         -i "pandas.Series.sparse.sp_values SA01" \
-        -i "pandas.Timedelta.components SA01" \
         -i "pandas.Timedelta.max PR02" \
         -i "pandas.Timedelta.min PR02" \
         -i "pandas.Timedelta.resolution PR02" \
         -i "pandas.Timedelta.to_timedelta64 SA01" \
-        -i "pandas.Timedelta.total_seconds SA01" \
         -i "pandas.TimedeltaIndex.to_pytimedelta RT03,SA01" \
         -i "pandas.Timestamp.max PR02" \
         -i "pandas.Timestamp.min PR02" \
         -i "pandas.Timestamp.nanosecond GL08" \
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.Timestamp.year GL08" \
-        -i "pandas.api.extensions.ExtensionArray.interpolate PR01,SA01" \
         -i "pandas.api.types.is_dict_like PR07,SA01" \
-        -i "pandas.api.types.is_extension_array_dtype SA01" \
         -i "pandas.api.types.is_file_like PR07,SA01" \
         -i "pandas.api.types.is_float PR01,SA01" \
         -i "pandas.api.types.is_float_dtype SA01" \
         -i "pandas.api.types.is_hashable PR01,RT03,SA01" \
         -i "pandas.api.types.is_int64_dtype SA01" \
         -i "pandas.api.types.is_integer PR01,SA01" \
-        -i "pandas.api.types.is_integer_dtype SA01" \
         -i "pandas.api.types.is_interval_dtype SA01" \
         -i "pandas.api.types.is_iterator PR07,SA01" \
         -i "pandas.api.types.is_list_like SA01" \
@@ -137,7 +130,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
         -i "pandas.arrays.BooleanArray SA01" \
         -i "pandas.arrays.DatetimeArray SA01" \
-        -i "pandas.arrays.FloatingArray SA01" \
         -i "pandas.arrays.IntegerArray SA01" \
         -i "pandas.arrays.IntervalArray.left SA01" \
         -i "pandas.arrays.IntervalArray.length SA01" \
@@ -154,14 +146,11 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.DataFrameGroupBy.groups SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.hist RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.indices SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.max SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.min SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.nth PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.ohlc SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.sem SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.sum SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.__iter__ RT03,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.agg RT03" \
         -i "pandas.core.groupby.SeriesGroupBy.aggregate RT03" \
@@ -170,13 +159,10 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.SeriesGroupBy.indices SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_decreasing SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_increasing SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.max SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.min SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.nth PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.ohlc SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.sem SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.sum SA01" \
         -i "pandas.core.resample.Resampler.__iter__ RT03,SA01" \
         -i "pandas.core.resample.Resampler.ffill RT03" \
         -i "pandas.core.resample.Resampler.get_group RT03,SA01" \
@@ -205,7 +191,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.errors.IntCastingNaNError SA01" \
         -i "pandas.errors.InvalidIndexError SA01" \
         -i "pandas.errors.InvalidVersion SA01" \
-        -i "pandas.errors.MergeError SA01" \
         -i "pandas.errors.NullFrequencyError SA01" \
         -i "pandas.errors.NumExprClobberingError SA01" \
         -i "pandas.errors.NumbaUtilError SA01" \

doc/source/whatsnew/index.rst

@@ -32,6 +32,7 @@ Version 2.2
 .. toctree::
    :maxdepth: 2
 
+   v2.2.3
    v2.2.2
    v2.2.1
    v2.2.0

doc/source/whatsnew/v2.2.3.rst

@@ -0,0 +1,36 @@
+.. _whatsnew_223:
+
+What's new in 2.2.3 (September XX, 2024)
+----------------------------------------
+
+These are the changes in pandas 2.2.3. See :ref:`release` for a full changelog
+including other versions of pandas.
+
+{{ header }}
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_223.regressions:
+
+Fixed regressions
+~~~~~~~~~~~~~~~~~
+-
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_223.bug_fixes:
+
+Bug fixes
+~~~~~~~~~
+-
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_223.other:
+
+Other
+~~~~~
+-
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_223.contributors:
+
+Contributors
+~~~~~~~~~~~~

doc/source/whatsnew/v2.3.0.rst

@@ -102,9 +102,11 @@ Conversion
 
 Strings
 ^^^^^^^
+- Bug in :meth:`Series.rank` for :class:`StringDtype` with ``storage="pyarrow"`` incorrectly returning integer results in case of ``method="average"`` and raising an error if it would truncate results (:issue:`59768`)
 - Bug in :meth:`Series.str.replace` when ``n < 0`` for :class:`StringDtype` with ``storage="pyarrow"`` (:issue:`59628`)
+- Bug in ``ser.str.slice`` with negative ``step`` with :class:`ArrowDtype` and :class:`StringDtype` with ``storage="pyarrow"`` giving incorrect results (:issue:`59710`)
 - Bug in the ``center`` method on :class:`Series` and :class:`Index` object ``str`` accessors with pyarrow-backed dtype not matching the python behavior in corner cases with an odd number of fill characters (:issue:`54792`)
-
+-
 
 Interval
 ^^^^^^^^

doc/source/whatsnew/v3.0.0.rst

@@ -627,6 +627,7 @@ I/O
 - Bug in :meth:`read_csv` causing segmentation fault when ``encoding_errors`` is not a string. (:issue:`59059`)
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``index_col`` is specified and ``na_values`` is a dict containing the key ``None``. (:issue:`57547`)
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``nrows`` and ``iterator`` are specified without specifying a ``chunksize``. (:issue:`59079`)
+- Bug in :meth:`read_csv` where the order of the ``na_values`` makes an inconsistency when ``na_values`` is a list non-string values. (:issue:`59303`)
 - Bug in :meth:`read_excel` raising ``ValueError`` when passing array of boolean values when ``dtype="boolean"``. (:issue:`58159`)
 - Bug in :meth:`read_json` not validating the ``typ`` argument to not be exactly ``"frame"`` or ``"series"`` (:issue:`59124`)
 - Bug in :meth:`read_stata` raising ``KeyError`` when input file is stored in big-endian format and contains strL data. (:issue:`58638`)

pandas/_libs/lib.pyx

@@ -600,6 +600,8 @@ def array_equivalent_object(ndarray left, ndarray right) -> bool:
                     if not array_equivalent(x, y):
                         return False
 
+            elif PyArray_Check(x) or PyArray_Check(y):
+                return False
             elif (x is C_NA) ^ (y is C_NA):
                 return False
             elif not (

pandas/_libs/missing.pyx

@@ -347,6 +347,14 @@ class NAType(C_NAType):
     The NA singleton is a missing value indicator defined by pandas. It is
     used in certain new extension dtypes (currently the "string" dtype).
 
+    See Also
+    --------
+    numpy.nan : Floating point representation of Not a Number (NaN) for numerical data.
+    isna : Detect missing values for an array-like object.
+    notna : Detect non-missing values for an array-like object.
+    DataFrame.fillna : Fill missing values in a DataFrame.
+    Series.fillna : Fill missing values in a Series.
+
     Examples
     --------
     >>> pd.NA

pandas/_libs/tslibs/nattype.pyx

@@ -493,6 +493,14 @@ class NaTType(_NaT):
         """
         Total seconds in the duration.
 
+        This method calculates the total duration in seconds by combining
+        the days, seconds, and microseconds of the `Timedelta` object.
+
+        See Also
+        --------
+        to_timedelta : Convert argument to timedelta.
+        Timedelta : Represents a duration, the difference between two dates or times.
+
         Examples
         --------
         >>> td = pd.Timedelta('1min')

pandas/_libs/tslibs/timedeltas.pyx

@@ -1189,6 +1189,14 @@ cdef class _Timedelta(timedelta):
         """
         Total seconds in the duration.
 
+        This method calculates the total duration in seconds by combining
+        the days, seconds, and microseconds of the `Timedelta` object.
+
+        See Also
+        --------
+        to_timedelta : Convert argument to timedelta.
+        Timedelta : Represents a duration, the difference between two dates or times.
+
         Examples
         --------
         >>> td = pd.Timedelta('1min')
@@ -1493,6 +1501,17 @@ cdef class _Timedelta(timedelta):
         """
         Return a components namedtuple-like.
 
+        Each component represents a different time unit, allowing you to access the
+        breakdown of the total duration in terms of days, hours, minutes, seconds,
+        milliseconds, microseconds, and nanoseconds.
+
+        See Also
+        --------
+        Timedelta.total_seconds : Returns the total duration of the Timedelta in
+            seconds.
+        to_timedelta : Convert argument to Timedelta.
+        Timedelta : Represents a duration, the difference between two dates or times.
+
         Examples
         --------
         >>> td = pd.Timedelta('2 day 4 min 3 us 42 ns')

pandas/conftest.py

@@ -1338,7 +1338,13 @@ def string_storage(request):
         pytest.param(("pyarrow", pd.NA), marks=td.skip_if_no("pyarrow")),
         pytest.param(("pyarrow", np.nan), marks=td.skip_if_no("pyarrow")),
         ("python", np.nan),
-    ]
+    ],
+    ids=[
+        "string=string[python]",
+        "string=string[pyarrow]",
+        "string=str[pyarrow]",
+        "string=str[python]",
+    ],
 )
 def string_dtype_arguments(request):
     """
@@ -1369,6 +1375,7 @@ def dtype_backend(request):
 
 # Alias so we can test with cartesian product of string_storage
 string_storage2 = string_storage
+string_dtype_arguments2 = string_dtype_arguments
 
 
 @pytest.fixture(params=tm.BYTES_DTYPES)