Merge remote-tracking branch 'upstream/main' into np-doc-ts-asunit

Author: tuhinsharma121

ci/code_checks.sh

@@ -403,9 +403,9 @@ are returned:
    s = pd.Series(list('abcde'), index=[0, 3, 2, 5, 4])
    s.loc[3:5]
 
-If at least one of the two is absent, but the index is sorted, and can be
-compared against start and stop labels, then slicing will still work as
-expected, by selecting labels which *rank* between the two:
+If the index is sorted, and can be compared against start and stop labels,
+then slicing will still work as expected, by selecting labels which *rank*
+between the two:
 
 .. ipython:: python
 

doc/source/user_guide/indexing.rst

@@ -276,28 +276,9 @@ parse_dates : boolean or list of ints or names or list of lists or dict, default
 
   .. note::
      A fast-path exists for iso8601-formatted dates.
-infer_datetime_format : boolean, default ``False``
-  If ``True`` and parse_dates is enabled for a column, attempt to infer the
-  datetime format to speed up the processing.
-
-  .. deprecated:: 2.0.0
-   A strict version of this argument is now the default, passing it has no effect.
 keep_date_col : boolean, default ``False``
   If ``True`` and parse_dates specifies combining multiple columns then keep the
   original columns.
-date_parser : function, default ``None``
-  Function to use for converting a sequence of string columns to an array of
-  datetime instances. The default uses ``dateutil.parser.parser`` to do the
-  conversion. pandas will try to call date_parser in three different ways,
-  advancing to the next if an exception occurs: 1) Pass one or more arrays (as
-  defined by parse_dates) as arguments; 2) concatenate (row-wise) the string
-  values from the columns defined by parse_dates into a single array and pass
-  that; and 3) call date_parser once for each row using one or more strings
-  (corresponding to the columns defined by parse_dates) as arguments.
-
-  .. deprecated:: 2.0.0
-   Use ``date_format`` instead, or read in as ``object`` and then apply
-   :func:`to_datetime` as-needed.
 date_format : str or dict of column -> format, default ``None``
    If used in conjunction with ``parse_dates``, will parse dates according to this
    format. For anything more complex,
@@ -1639,7 +1620,6 @@ Options that are unsupported by the pyarrow engine which are not covered by the
 * ``decimal``
 * ``iterator``
 * ``dayfirst``
-* ``infer_datetime_format``
 * ``verbose``
 * ``skipinitialspace``
 * ``low_memory``

doc/source/user_guide/io.rst

@@ -243,6 +243,7 @@ Removal of prior version deprecations/changes
 - Removed the "closed" and "unit" keywords in :meth:`TimedeltaIndex.__new__` (:issue:`52628`, :issue:`55499`)
 - All arguments in :meth:`Index.sort_values` are now keyword only (:issue:`56493`)
 - All arguments in :meth:`Series.to_dict` are now keyword only (:issue:`56493`)
+- 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`)
 - Enforced deprecation ``all`` and ``any`` reductions with ``datetime64``, :class:`DatetimeTZDtype`, and :class:`PeriodDtype` dtypes (:issue:`58029`)
@@ -254,6 +255,9 @@ Removal of prior version deprecations/changes
 - Enforced deprecation of :meth:`offsets.Tick.delta`, use ``pd.Timedelta(obj)`` instead (:issue:`55498`)
 - Enforced deprecation of ``axis=None`` acting the same as ``axis=0`` in the DataFrame reductions ``sum``, ``prod``, ``std``, ``var``, and ``sem``, passing ``axis=None`` will now reduce over both axes; this is particularly the case when doing e.g. ``numpy.sum(df)`` (:issue:`21597`)
 - Enforced deprecation of ``core.internals`` members ``Block``, ``ExtensionBlock``, and ``DatetimeTZBlock`` (:issue:`58467`)
+- Enforced deprecation of ``date_parser`` in :func:`read_csv`, :func:`read_table`, :func:`read_fwf`, and :func:`read_excel` in favour of ``date_format`` (:issue:`50601`)
+- Enforced deprecation of ``quantile`` keyword in :meth:`.Rolling.quantile` and :meth:`.Expanding.quantile`, renamed to ``q`` instead. (:issue:`52550`)
+- Enforced deprecation of argument ``infer_datetime_format`` in :func:`read_csv`, as a strict version of it is now the default (:issue:`48621`)
 - Enforced deprecation of non-standard (``np.ndarray``, :class:`ExtensionArray`, :class:`Index`, or :class:`Series`) argument to :func:`api.extensions.take` (:issue:`52981`)
 - Enforced deprecation of parsing system timezone strings to ``tzlocal``, which depended on system timezone, pass the 'tz' keyword instead (:issue:`50791`)
 - Enforced deprecation of passing a dictionary to :meth:`SeriesGroupBy.agg` (:issue:`52268`)
@@ -465,6 +469,7 @@ Sparse
 
 ExtensionArray
 ^^^^^^^^^^^^^^
+- Bug in :meth:`.arrays.ArrowExtensionArray.__setitem__` which caused wrong behavior when using an integer array with repeated values as a key (:issue:`58530`)
 - Bug in :meth:`api.types.is_datetime64_any_dtype` where a custom :class:`ExtensionDtype` would return ``False`` for array-likes (:issue:`57055`)
 
 Styler

doc/source/whatsnew/v3.0.0.rst

@@ -500,6 +500,13 @@ cdef class BaseOffset:
         """
         Return a copy of the frequency.
 
+        See Also
+        --------
+        tseries.offsets.Week.copy : Return a copy of Week offset.
+        tseries.offsets.DateOffset.copy : Return a copy of date offset.
+        tseries.offsets.MonthEnd.copy : Return a copy of MonthEnd offset.
+        tseries.offsets.YearBegin.copy : Return a copy of YearBegin offset.
+
         Examples
         --------
         >>> freq = pd.DateOffset(1)

pandas/_libs/tslibs/offsets.pyx

@@ -672,47 +672,47 @@ def _create_mi_with_dt64tz_level():
 
 
 indices_dict = {
-    "string": Index([f"pandas_{i}" for i in range(100)]),
-    "datetime": date_range("2020-01-01", periods=100),
-    "datetime-tz": date_range("2020-01-01", periods=100, tz="US/Pacific"),
-    "period": period_range("2020-01-01", periods=100, freq="D"),
-    "timedelta": timedelta_range(start="1 day", periods=100, freq="D"),
-    "range": RangeIndex(100),
-    "int8": Index(np.arange(100), dtype="int8"),
-    "int16": Index(np.arange(100), dtype="int16"),
-    "int32": Index(np.arange(100), dtype="int32"),
-    "int64": Index(np.arange(100), dtype="int64"),
-    "uint8": Index(np.arange(100), dtype="uint8"),
-    "uint16": Index(np.arange(100), dtype="uint16"),
-    "uint32": Index(np.arange(100), dtype="uint32"),
-    "uint64": Index(np.arange(100), dtype="uint64"),
-    "float32": Index(np.arange(100), dtype="float32"),
-    "float64": Index(np.arange(100), dtype="float64"),
+    "string": Index([f"pandas_{i}" for i in range(10)]),
+    "datetime": date_range("2020-01-01", periods=10),
+    "datetime-tz": date_range("2020-01-01", periods=10, tz="US/Pacific"),
+    "period": period_range("2020-01-01", periods=10, freq="D"),
+    "timedelta": timedelta_range(start="1 day", periods=10, freq="D"),
+    "range": RangeIndex(10),
+    "int8": Index(np.arange(10), dtype="int8"),
+    "int16": Index(np.arange(10), dtype="int16"),
+    "int32": Index(np.arange(10), dtype="int32"),
+    "int64": Index(np.arange(10), dtype="int64"),
+    "uint8": Index(np.arange(10), dtype="uint8"),
+    "uint16": Index(np.arange(10), dtype="uint16"),
+    "uint32": Index(np.arange(10), dtype="uint32"),
+    "uint64": Index(np.arange(10), dtype="uint64"),
+    "float32": Index(np.arange(10), dtype="float32"),
+    "float64": Index(np.arange(10), dtype="float64"),
     "bool-object": Index([True, False] * 5, dtype=object),
     "bool-dtype": Index([True, False] * 5, dtype=bool),
     "complex64": Index(
-        np.arange(100, dtype="complex64") + 1.0j * np.arange(100, dtype="complex64")
+        np.arange(10, dtype="complex64") + 1.0j * np.arange(10, dtype="complex64")
     ),
     "complex128": Index(
-        np.arange(100, dtype="complex128") + 1.0j * np.arange(100, dtype="complex128")
+        np.arange(10, dtype="complex128") + 1.0j * np.arange(10, dtype="complex128")
     ),
-    "categorical": CategoricalIndex(list("abcd") * 25),
-    "interval": IntervalIndex.from_breaks(np.linspace(0, 100, num=101)),
+    "categorical": CategoricalIndex(list("abcd") * 2),
+    "interval": IntervalIndex.from_breaks(np.linspace(0, 100, num=11)),
     "empty": Index([]),
     "tuples": MultiIndex.from_tuples(zip(["foo", "bar", "baz"], [1, 2, 3])),
     "mi-with-dt64tz-level": _create_mi_with_dt64tz_level(),
     "multi": _create_multiindex(),
     "repeats": Index([0, 0, 1, 1, 2, 2]),
-    "nullable_int": Index(np.arange(100), dtype="Int64"),
-    "nullable_uint": Index(np.arange(100), dtype="UInt16"),
-    "nullable_float": Index(np.arange(100), dtype="Float32"),
-    "nullable_bool": Index(np.arange(100).astype(bool), dtype="boolean"),
+    "nullable_int": Index(np.arange(10), dtype="Int64"),
+    "nullable_uint": Index(np.arange(10), dtype="UInt16"),
+    "nullable_float": Index(np.arange(10), dtype="Float32"),
+    "nullable_bool": Index(np.arange(10).astype(bool), dtype="boolean"),
     "string-python": Index(
-        pd.array([f"pandas_{i}" for i in range(100)], dtype="string[python]")
+        pd.array([f"pandas_{i}" for i in range(10)], dtype="string[python]")
     ),
 }
 if has_pyarrow:
-    idx = Index(pd.array([f"pandas_{i}" for i in range(100)], dtype="string[pyarrow]"))
+    idx = Index(pd.array([f"pandas_{i}" for i in range(10)], dtype="string[pyarrow]"))
     indices_dict["string-pyarrow"] = idx
 
 

pandas/conftest.py

@@ -1425,7 +1425,7 @@ def to_numpy(
             result[~mask] = data[~mask]._pa_array.to_numpy()
         return result
 
-    def map(self, mapper, na_action=None):
+    def map(self, mapper, na_action: Literal["ignore"] | None = None):
         if is_numeric_dtype(self.dtype):
             return map_array(self.to_numpy(), mapper, na_action=na_action)
         else:
@@ -1880,7 +1880,8 @@ def __setitem__(self, key, value) -> None:
                 raise ValueError("Length of indexer and values mismatch")
             if len(indices) == 0:
                 return
-            argsort = np.argsort(indices)
+            # GH#58530 wrong item assignment by repeated key
+            _, argsort = np.unique(indices, return_index=True)
             indices = indices[argsort]
             value = value.take(argsort)
             mask = np.zeros(len(self), dtype=np.bool_)

pandas/core/arrays/arrow/array.py

@@ -2270,7 +2270,7 @@ def __array_ufunc__(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
 
         return arraylike.default_array_ufunc(self, ufunc, method, *inputs, **kwargs)
 
-    def map(self, mapper, na_action=None):
+    def map(self, mapper, na_action: Literal["ignore"] | None = None):
         """
         Map values using an input mapping or function.
 

pandas/core/arrays/base.py

@@ -1483,7 +1483,7 @@ def remove_unused_categories(self) -> Self:
     def map(
         self,
         mapper,
-        na_action: Literal["ignore"] | None | lib.NoDefault = lib.no_default,
+        na_action: Literal["ignore"] | None = None,
     ):
         """
         Map categories using an input mapping or function.
@@ -1501,15 +1501,10 @@ def map(
         ----------
         mapper : function, dict, or Series
             Mapping correspondence.
-        na_action : {None, 'ignore'}, default 'ignore'
+        na_action : {None, 'ignore'}, default None
             If 'ignore', propagate NaN values, without passing them to the
             mapping correspondence.
 
-            .. deprecated:: 2.1.0
-
-               The default value of 'ignore' has been deprecated and will be changed to
-               None in the future.
-
         Returns
         -------
         pandas.Categorical or pandas.Index
@@ -1561,17 +1556,6 @@ def map(
         >>> cat.map({"a": "first", "b": "second"}, na_action=None)
         Index(['first', 'second', nan], dtype='object')
         """
-        if na_action is lib.no_default:
-            warnings.warn(
-                "The default value of 'ignore' for the `na_action` parameter in "
-                "pandas.Categorical.map is deprecated and will be "
-                "changed to 'None' in a future version. Please set na_action to the "
-                "desired value to avoid seeing this warning",
-                FutureWarning,
-                stacklevel=find_stack_level(),
-            )
-            na_action = "ignore"
-
         assert callable(mapper) or is_dict_like(mapper)
 
         new_categories = self.categories.map(mapper)

pandas/core/arrays/categorical.py

@@ -728,7 +728,7 @@ def _unbox(self, other) -> np.int64 | np.datetime64 | np.timedelta64 | np.ndarra
     #  pandas assumes they're there.
 
     @ravel_compat
-    def map(self, mapper, na_action=None):
+    def map(self, mapper, na_action: Literal["ignore"] | None = None):
         from pandas import Index
 
         result = map_array(self, mapper, na_action=na_action)

pandas/core/arrays/datetimelike.py

@@ -1389,6 +1389,12 @@ def closed(self) -> IntervalClosedType:
 
         Either ``left``, ``right``, ``both`` or ``neither``.
 
+        See Also
+        --------
+        IntervalArray.closed : Returns inclusive side of the IntervalArray.
+        Interval.closed : Returns inclusive side of the Interval.
+        IntervalIndex.closed : Returns inclusive side of the IntervalIndex.
+
         Examples
         --------
 
@@ -1747,22 +1753,40 @@ def repeat(
     """
     )
 
-    @Appender(
-        _interval_shared_docs["contains"]
-        % {
-            "klass": "IntervalArray",
-            "examples": textwrap.dedent(
-                """\
+    def contains(self, other):
+        """
+        Check elementwise if the Intervals contain the value.
+
+        Return a boolean mask whether the value is contained in the Intervals
+        of the IntervalArray.
+
+        Parameters
+        ----------
+        other : scalar
+            The value to check whether it is contained in the Intervals.
+
+        Returns
+        -------
+        boolean array
+            A boolean mask whether the value is contained in the Intervals.
+
+        See Also
+        --------
+        Interval.contains : Check whether Interval object contains value.
+        IntervalArray.overlaps : Check if an Interval overlaps the values in the
+            IntervalArray.
+
+        Examples
+        --------
         >>> intervals = pd.arrays.IntervalArray.from_tuples([(0, 1), (1, 3), (2, 4)])
         >>> intervals
         <IntervalArray>
         [(0, 1], (1, 3], (2, 4]]
         Length: 3, dtype: interval[int64, right]
+
+        >>> intervals.contains(0.5)
+        array([ True, False, False])
         """
-            ),
-        }
-    )
-    def contains(self, other):
         if isinstance(other, Interval):
             raise NotImplementedError("contains not implemented for two intervals")
 

pandas/core/arrays/interval.py

@@ -1318,7 +1318,7 @@ def max(self, *, skipna: bool = True, axis: AxisInt | None = 0, **kwargs):
         )
         return self._wrap_reduction_result("max", result, skipna=skipna, axis=axis)
 
-    def map(self, mapper, na_action=None):
+    def map(self, mapper, na_action: Literal["ignore"] | None = None):
         return map_array(self.to_numpy(), mapper, na_action=na_action)
 
     @overload

pandas/core/arrays/masked.py

@@ -1253,7 +1253,7 @@ def astype(self, dtype: AstypeArg | None = None, copy: bool = True):
 
         return self._simple_new(sp_values, self.sp_index, dtype)
 
-    def map(self, mapper, na_action=None) -> Self:
+    def map(self, mapper, na_action: Literal["ignore"] | None = None) -> Self:
         """
         Map categories using an input mapping or function.
 

pandas/core/arrays/sparse/array.py

@@ -486,6 +486,14 @@ def register_extension_dtype(cls: type_t[ExtensionDtypeT]) -> type_t[ExtensionDt
     callable
         A class decorator.
 
+    See Also
+    --------
+    api.extensions.ExtensionDtype : The base class for creating custom pandas
+        data types.
+    Series : One-dimensional array with axis labels.
+    DataFrame : Two-dimensional, size-mutable, potentially heterogeneous
+        tabular data.
+
     Examples
     --------
     >>> from pandas.api.extensions import register_extension_dtype, ExtensionDtype

pandas/core/dtypes/base.py

@@ -10369,7 +10369,7 @@ def apply(
         return op.apply().__finalize__(self, method="apply")
 
     def map(
-        self, func: PythonFuncType, na_action: str | None = None, **kwargs
+        self, func: PythonFuncType, na_action: Literal["ignore"] | None = None, **kwargs
     ) -> DataFrame:
         """
         Apply a function to a Dataframe elementwise.

pandas/core/frame.py

@@ -48,6 +48,25 @@ class BaseIndexer:
     """
     Base class for window bounds calculations.
 
+    Parameters
+    ----------
+    index_array : np.ndarray, default None
+        Array-like structure representing the indices for the data points.
+        If None, the default indices are assumed. This can be useful for
+        handling non-uniform indices in data, such as in time series
+        with irregular timestamps.
+    window_size : int, default 0
+        Size of the moving window. This is the number of observations used
+        for calculating the statistic. The default is to consider all
+        observations within the window.
+    **kwargs
+        Additional keyword arguments passed to the subclass's methods.
+
+    See Also
+    --------
+    DataFrame.rolling : Provides rolling window calculations on dataframe.
+    Series.rolling : Provides rolling window calculations on series.
+
     Examples
     --------
     >>> from pandas.api.indexers import BaseIndexer