Merge branch 'main' into modify-function-signature

Author: rsm-23

ci/code_checks.sh

@@ -110,25 +110,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas_object \
         pandas.api.interchange.from_dataframe \
         pandas.DatetimeIndex.snap \
-        pandas.core.window.rolling.Rolling.max \
-        pandas.core.window.rolling.Rolling.cov \
-        pandas.core.window.rolling.Rolling.skew \
-        pandas.core.window.rolling.Rolling.apply \
-        pandas.core.window.rolling.Window.mean \
-        pandas.core.window.rolling.Window.sum \
-        pandas.core.window.rolling.Window.var \
-        pandas.core.window.rolling.Window.std \
-        pandas.core.window.expanding.Expanding.count \
-        pandas.core.window.expanding.Expanding.sum \
-        pandas.core.window.expanding.Expanding.mean \
-        pandas.core.window.expanding.Expanding.median \
-        pandas.core.window.expanding.Expanding.min \
-        pandas.core.window.expanding.Expanding.max \
-        pandas.core.window.expanding.Expanding.corr \
-        pandas.core.window.expanding.Expanding.cov \
-        pandas.core.window.expanding.Expanding.skew \
-        pandas.core.window.expanding.Expanding.apply \
-        pandas.core.window.expanding.Expanding.quantile \
         pandas.core.window.ewm.ExponentialMovingWindow.mean \
         pandas.core.window.ewm.ExponentialMovingWindow.sum \
         pandas.core.window.ewm.ExponentialMovingWindow.std \

doc/source/whatsnew/v2.1.0.rst

@@ -296,6 +296,7 @@ Deprecations
 - Deprecated :meth:`Series.interpolate` and :meth:`DataFrame.interpolate` for object-dtype (:issue:`53631`)
 - Deprecated :meth:`Series.last` and :meth:`DataFrame.last` (please create a mask and filter using ``.loc`` instead) (:issue:`53692`)
 - Deprecated allowing arbitrary ``fill_value`` in :class:`SparseDtype`, in a future version the ``fill_value`` will need to be compatible with the ``dtype.subtype``, either a scalar that can be held by that subtype or ``NaN`` for integer or bool subtypes (:issue:`23124`)
+- Deprecated allowing bool dtype in :meth:`DataFrameGroupBy.quantile` and :meth:`SeriesGroupBy.quantile`, consistent with the :meth:`Series.quantile` and :meth:`DataFrame.quantile` behavior (:issue:`51424`)
 - Deprecated behavior of :func:`assert_series_equal` and :func:`assert_frame_equal` considering NA-like values (e.g. ``NaN`` vs ``None`` as equivalent) (:issue:`52081`)
 - Deprecated bytes input to :func:`read_excel`. To read a file path, use a string or path-like object. (:issue:`53767`)
 - Deprecated constructing :class:`SparseArray` from scalar data, pass a sequence instead (:issue:`53039`)

pandas/core/generic.py

@@ -506,7 +506,7 @@ def _data(self):
         warnings.warn(
             f"{type(self).__name__}._data is deprecated and will be removed in "
             "a future version. Use public APIs instead.",
-            FutureWarning,
+            DeprecationWarning,
             stacklevel=find_stack_level(),
         )
         return self._mgr

pandas/core/groupby/groupby.py

@@ -4165,6 +4165,17 @@ def pre_processor(vals: ArrayLike) -> tuple[np.ndarray, DtypeObj | None]:
                 inference = np.dtype(np.int64)
             elif is_bool_dtype(vals.dtype) and isinstance(vals, ExtensionArray):
                 out = vals.to_numpy(dtype=float, na_value=np.nan)
+            elif is_bool_dtype(vals.dtype):
+                # GH#51424 deprecate to match Series/DataFrame behavior
+                warnings.warn(
+                    f"Allowing bool dtype in {type(self).__name__}.quantile is "
+                    "deprecated and will raise in a future version, matching "
+                    "the Series/DataFrame behavior. Cast to uint8 dtype before "
+                    "calling quantile instead.",
+                    FutureWarning,
+                    stacklevel=find_stack_level(),
+                )
+                out = np.asarray(vals)
             elif needs_i8_conversion(vals.dtype):
                 inference = vals.dtype
                 # In this case we need to delay the casting until after the

pandas/core/window/expanding.py

@@ -183,7 +183,19 @@ def aggregate(self, func, *args, **kwargs):
         create_section_header("Returns"),
         template_returns,
         create_section_header("See Also"),
-        template_see_also[:-1],
+        template_see_also,
+        create_section_header("Examples"),
+        dedent(
+            """\
+        >>> ser = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])
+        >>> ser.expanding().count()
+        a    1.0
+        b    2.0
+        c    3.0
+        d    4.0
+        dtype: float64
+        """
+        ),
         window_method="expanding",
         aggregation_description="count of non NaN observations",
         agg_method="count",
@@ -198,7 +210,19 @@ def count(self, numeric_only: bool = False):
         create_section_header("Returns"),
         template_returns,
         create_section_header("See Also"),
-        template_see_also[:-1],
+        template_see_also,
+        create_section_header("Examples"),
+        dedent(
+            """\
+        >>> ser = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])
+        >>> ser.expanding().apply(lambda s: s.max() - 2 * s.min())
+        a   -1.0
+        b    0.0
+        c    1.0
+        d    2.0
+        dtype: float64
+        """
+        ),
         window_method="expanding",
         aggregation_description="custom aggregation function",
         agg_method="apply",
@@ -231,7 +255,19 @@ def apply(
         create_section_header("See Also"),
         template_see_also,
         create_section_header("Notes"),
-        numba_notes[:-1],
+        numba_notes,
+        create_section_header("Examples"),
+        dedent(
+            """\
+        >>> ser = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])
+        >>> ser.expanding().sum()
+        a     1.0
+        b     3.0
+        c     6.0
+        d    10.0
+        dtype: float64
+        """
+        ),
         window_method="expanding",
         aggregation_description="sum",
         agg_method="sum",
@@ -258,7 +294,19 @@ def sum(
         create_section_header("See Also"),
         template_see_also,
         create_section_header("Notes"),
-        numba_notes[:-1],
+        numba_notes,
+        create_section_header("Examples"),
+        dedent(
+            """\
+        >>> ser = pd.Series([3, 2, 1, 4], index=['a', 'b', 'c', 'd'])
+        >>> ser.expanding().max()
+        a    3.0
+        b    3.0
+        c    3.0
+        d    4.0
+        dtype: float64
+        """
+        ),
         window_method="expanding",
         aggregation_description="maximum",
         agg_method="max",
@@ -285,7 +333,19 @@ def max(
         create_section_header("See Also"),
         template_see_also,
         create_section_header("Notes"),
-        numba_notes[:-1],
+        numba_notes,
+        create_section_header("Examples"),
+        dedent(
+            """\
+        >>> ser = pd.Series([2, 3, 4, 1], index=['a', 'b', 'c', 'd'])
+        >>> ser.expanding().min()
+        a    2.0
+        b    2.0
+        c    2.0
+        d    1.0
+        dtype: float64
+        """
+        ),
         window_method="expanding",
         aggregation_description="minimum",
         agg_method="min",
@@ -312,7 +372,19 @@ def min(
         create_section_header("See Also"),
         template_see_also,
         create_section_header("Notes"),
-        numba_notes[:-1],
+        numba_notes,
+        create_section_header("Examples"),
+        dedent(
+            """\
+        >>> ser = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])
+        >>> ser.expanding().mean()
+        a    1.0
+        b    1.5
+        c    2.0
+        d    2.5
+        dtype: float64
+        """
+        ),
         window_method="expanding",
         aggregation_description="mean",
         agg_method="mean",
@@ -339,7 +411,19 @@ def mean(
         create_section_header("See Also"),
         template_see_also,
         create_section_header("Notes"),
-        numba_notes[:-1],
+        numba_notes,
+        create_section_header("Examples"),
+        dedent(
+            """\
+        >>> ser = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])
+        >>> ser.expanding().median()
+        a    1.0
+        b    1.5
+        c    2.0
+        d    2.5
+        dtype: float64
+        """
+        ),
         window_method="expanding",
         aggregation_description="median",
         agg_method="median",
@@ -523,7 +607,20 @@ def sem(self, ddof: int = 1, numeric_only: bool = False):
         "scipy.stats.skew : Third moment of a probability density.\n",
         template_see_also,
         create_section_header("Notes"),
-        "A minimum of three periods is required for the rolling calculation.\n",
+        "A minimum of three periods is required for the rolling calculation.\n\n",
+        create_section_header("Examples"),
+        dedent(
+            """\
+        >>> ser = pd.Series([-1, 0, 2, -1, 2], index=['a', 'b', 'c', 'd', 'e'])
+        >>> ser.expanding().skew()
+        a         NaN
+        b         NaN
+        c    0.935220
+        d    1.414214
+        e    0.315356
+        dtype: float64
+        """
+        ),
         window_method="expanding",
         aggregation_description="unbiased skewness",
         agg_method="skew",
@@ -597,7 +694,21 @@ def kurt(self, numeric_only: bool = False):
         create_section_header("Returns"),
         template_returns,
         create_section_header("See Also"),
-        template_see_also[:-1],
+        template_see_also,
+        create_section_header("Examples"),
+        dedent(
+            """\
+        >>> ser = pd.Series([1, 2, 3, 4, 5, 6], index=['a', 'b', 'c', 'd', 'e', 'f'])
+        >>> ser.expanding(min_periods=4).quantile(.25)
+        a     NaN
+        b     NaN
+        c     NaN
+        d    1.75
+        e    2.00
+        f    2.25
+        dtype: float64
+        """
+        ),
         window_method="expanding",
         aggregation_description="quantile",
         agg_method="quantile",
@@ -714,7 +825,20 @@ def rank(
         create_section_header("Returns"),
         template_returns,
         create_section_header("See Also"),
-        template_see_also[:-1],
+        template_see_also,
+        create_section_header("Examples"),
+        dedent(
+            """\
+        >>> ser1 = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])
+        >>> ser2 = pd.Series([10, 11, 13, 16], index=['a', 'b', 'c', 'd'])
+        >>> ser1.expanding().cov(ser2)
+        a         NaN
+        b    0.500000
+        c    1.500000
+        d    3.333333
+        dtype: float64
+        """
+        ),
         window_method="expanding",
         aggregation_description="sample covariance",
         agg_method="cov",
@@ -782,9 +906,22 @@ def cov(
         columns on the second level.
 
         In the case of missing elements, only complete pairwise observations
-        will be used.
+        will be used.\n
         """
-        ).replace("\n", "", 1),
+        ),
+        create_section_header("Examples"),
+        dedent(
+            """\
+        >>> ser1 = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])
+        >>> ser2 = pd.Series([10, 11, 13, 16], index=['a', 'b', 'c', 'd'])
+        >>> ser1.expanding().corr(ser2)
+        a         NaN
+        b    1.000000
+        c    0.981981
+        d    0.975900
+        dtype: float64
+        """
+        ),
         window_method="expanding",
         aggregation_description="correlation",
         agg_method="corr",