Merge remote-tracking branch 'upstream/main' into 59717-from-records-columns-reorder

VibavariG · VibavariG · commit a3d353f2bb63 · 2024-09-16T20:17:21.000-04:00
diff --git a/ci/code_checks.sh b/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" \
@@ -103,12 +101,10 @@ 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" \
@@ -117,14 +113,12 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.Timestamp.year GL08" \
         -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" \
@@ -136,7 +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" \
@@ -198,7 +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" \
diff --git a/doc/source/whatsnew/index.rst b/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
diff --git a/doc/source/whatsnew/v2.2.3.rst b/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
+~~~~~~~~~~~~
diff --git a/pandas/_libs/missing.pyx b/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
diff --git a/pandas/_libs/tslibs/nattype.pyx b/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')
diff --git a/pandas/_libs/tslibs/timedeltas.pyx b/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')
diff --git a/pandas/core/arrays/base.py b/pandas/core/arrays/base.py
@@ -1010,7 +1010,6 @@ def interpolate(
             * 'time': Works on daily and higher resolution data to interpolate
             given length of interval.
             * 'index', 'values': use the actual numerical values of the index.
-            * 'pad': Fill in NaNs using existing values.
             * 'nearest', 'zero', 'slinear', 'quadratic', 'cubic', 'barycentric',
             'polynomial': Passed to scipy.interpolate.interp1d, whereas 'spline'
             is passed to scipy.interpolate.UnivariateSpline. These methods use
diff --git a/pandas/core/arrays/floating.py b/pandas/core/arrays/floating.py
@@ -96,6 +96,14 @@ class FloatingArray(NumericArray):
     -------
     FloatingArray
 
+    See Also
+    --------
+    array : Create an array.
+    Float32Dtype : Float32 dtype for FloatingArray.
+    Float64Dtype : Float64 dtype for FloatingArray.
+    Series : One-dimensional labeled array capable of holding data.
+    DataFrame : Two-dimensional, size-mutable, potentially heterogeneous tabular data.
+
     Examples
     --------
     Create an FloatingArray with :func:`pandas.array`:
diff --git a/pandas/core/computation/eval.py b/pandas/core/computation/eval.py
@@ -14,7 +14,10 @@
 from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import validate_bool_kwarg
 
-from pandas.core.dtypes.common import is_extension_array_dtype
+from pandas.core.dtypes.common import (
+    is_extension_array_dtype,
+    is_string_dtype,
+)
 
 from pandas.core.computation.engines import ENGINES
 from pandas.core.computation.expr import (
@@ -345,10 +348,13 @@ def eval(
         parsed_expr = Expr(expr, engine=engine, parser=parser, env=env)
 
         if engine == "numexpr" and (
-            is_extension_array_dtype(parsed_expr.terms.return_type)
+            (
+                is_extension_array_dtype(parsed_expr.terms.return_type)
+                and not is_string_dtype(parsed_expr.terms.return_type)
+            )
             or getattr(parsed_expr.terms, "operand_types", None) is not None
             and any(
-                is_extension_array_dtype(elem)
+                (is_extension_array_dtype(elem) and not is_string_dtype(elem))
                 for elem in parsed_expr.terms.operand_types
             )
         ):
diff --git a/pandas/core/computation/expr.py b/pandas/core/computation/expr.py
@@ -21,6 +21,8 @@
 
 from pandas.errors import UndefinedVariableError
 
+from pandas.core.dtypes.common import is_string_dtype
+
 import pandas.core.common as com
 from pandas.core.computation.ops import (
     ARITH_OPS_SYMS,
@@ -524,10 +526,12 @@ def _maybe_evaluate_binop(
         elif self.engine != "pytables":
             if (
                 getattr(lhs, "return_type", None) == object
+                or is_string_dtype(getattr(lhs, "return_type", None))
                 or getattr(rhs, "return_type", None) == object
+                or is_string_dtype(getattr(rhs, "return_type", None))
             ):
                 # evaluate "==" and "!=" in python if either of our operands
-                # has an object return type
+                # has an object or string return type
                 return self._maybe_eval(res, eval_in_python + maybe_eval_in_python)
         return res
 
diff --git a/pandas/core/dtypes/common.py b/pandas/core/dtypes/common.py
@@ -694,6 +694,15 @@ def is_integer_dtype(arr_or_dtype) -> bool:
         Whether or not the array or dtype is of an integer dtype and
         not an instance of timedelta64.
 
+    See Also
+    --------
+    api.types.is_integer : Return True if given object is integer.
+    api.types.is_numeric_dtype : Check whether the provided array or dtype is of a
+        numeric dtype.
+    api.types.is_float_dtype : Check whether the provided array or dtype is of a
+        float dtype.
+    Int64Dtype : An ExtensionDtype for Int64Dtype integer data.
+
     Examples
     --------
     >>> from pandas.api.types import is_integer_dtype
@@ -1401,6 +1410,10 @@ def is_extension_array_dtype(arr_or_dtype) -> bool:
     bool
         Whether the `arr_or_dtype` is an extension array type.
 
+    See Also
+    --------
+    api.extensions.ExtensionArray : Abstract base class for pandas extension arrays.
+
     Notes
     -----
     This checks whether an object implements the pandas extension
diff --git a/pandas/core/dtypes/dtypes.py b/pandas/core/dtypes/dtypes.py
@@ -1065,6 +1065,20 @@ def freq(self) -> BaseOffset:
         """
         The frequency object of this PeriodDtype.
 
+        The `freq` property returns the `BaseOffset` object that represents the
+        frequency of the PeriodDtype. This frequency specifies the interval (e.g.,
+        daily, monthly, yearly) associated with the Period type. It is essential
+        for operations that depend on time-based calculations within a period index
+        or series.
+
+        See Also
+        --------
+        Period : Represents a period of time.
+        PeriodIndex : Immutable ndarray holding ordinal values indicating
+            regular periods.
+        PeriodDtype : An ExtensionDtype for Period data.
+        date_range : Return a fixed frequency range of dates.
+
         Examples
         --------
         >>> dtype = pd.PeriodDtype(freq="D")
diff --git a/pandas/core/internals/blocks.py b/pandas/core/internals/blocks.py
@@ -915,7 +915,7 @@ def _replace_coerce(
                         nb = nb.copy()
                     putmask_inplace(nb.values, mask, value)
                     return [nb]
-                return [self]
+                return [self.copy(deep=False)]
             return self.replace(
                 to_replace=to_replace,
                 value=value,
diff --git a/pandas/errors/__init__.py b/pandas/errors/__init__.py
@@ -261,6 +261,11 @@ class MergeError(ValueError):
 
     Subclass of ``ValueError``.
 
+    See Also
+    --------
+    DataFrame.join : For joining DataFrames on their indexes.
+    merge : For merging two DataFrames on a common set of keys.
+
     Examples
     --------
     >>> left = pd.DataFrame(
diff --git a/pandas/tests/copy_view/test_replace.py b/pandas/tests/copy_view/test_replace.py
@@ -286,6 +286,12 @@ def test_replace_list_none():
 
     assert not np.shares_memory(get_array(df, "a"), get_array(df2, "a"))
 
+    # replace multiple values that don't actually replace anything with None
+    # https://github.com/pandas-dev/pandas/issues/59770
+    df3 = df.replace(["d", "e", "f"], value=None)
+    tm.assert_frame_equal(df3, df_orig)
+    assert tm.shares_memory(get_array(df, "a"), get_array(df3, "a"))
+
 
 def test_replace_list_none_inplace_refs():
     df = DataFrame({"a": ["a", "b", "c"]})
diff --git a/pandas/tests/frame/test_query_eval.py b/pandas/tests/frame/test_query_eval.py
diff --git a/pandas/tests/series/indexing/test_setitem.py b/pandas/tests/series/indexing/test_setitem.py
diff --git a/web/pandas/config.yml b/web/pandas/config.yml
