Merge branch 'main' into cooolheater-issue59965

Author: cooolheater

ci/code_checks.sh

@@ -81,7 +81,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
-        -i "pandas.arrays.IntervalArray.length SA01" \
         -i "pandas.arrays.NumpyExtensionArray SA01" \
         -i "pandas.arrays.TimedeltaArray PR07,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \

doc/source/whatsnew/v3.0.0.rst

@@ -56,6 +56,7 @@ Other enhancements
 - :meth:`DataFrame.plot.scatter` argument ``c`` now accepts a column of strings, where rows with the same string are colored identically (:issue:`16827` and :issue:`16485`)
 - :func:`read_parquet` accepts ``to_pandas_kwargs`` which are forwarded to :meth:`pyarrow.Table.to_pandas` which enables passing additional keywords to customize the conversion to pandas, such as ``maps_as_pydicts`` to read the Parquet map data type as python dictionaries (:issue:`56842`)
 - :meth:`DataFrameGroupBy.transform`, :meth:`SeriesGroupBy.transform`, :meth:`DataFrameGroupBy.agg`, :meth:`SeriesGroupBy.agg`, :meth:`RollingGroupby.apply`, :meth:`ExpandingGroupby.apply`, :meth:`Rolling.apply`, :meth:`Expanding.apply`, :meth:`DataFrame.apply` with ``engine="numba"`` now supports positional arguments passed as kwargs (:issue:`58995`)
+- :meth:`Rolling.agg`, :meth:`Expanding.agg` and :meth:`ExponentialMovingWindow.agg` now accept :class:`NamedAgg` aggregations through ``**kwargs`` (:issue:`28333`)
 - :meth:`Series.map` can now accept kwargs to pass on to func (:issue:`59814`)
 - :meth:`pandas.concat` will raise a ``ValueError`` when ``ignore_index=True`` and ``keys`` is not ``None`` (:issue:`59274`)
 - :meth:`str.get_dummies` now accepts a  ``dtype`` parameter to specify the dtype of the resulting DataFrame (:issue:`47872`)

pandas/core/arrays/interval.py

@@ -1306,6 +1306,20 @@ def length(self) -> Index:
         """
         Return an Index with entries denoting the length of each Interval.
 
+        The length of an interval is calculated as the difference between
+        its `right` and `left` bounds. This property is particularly useful
+        when working with intervals where the size of the interval is an important
+        attribute, such as in time-series analysis or spatial data analysis.
+
+        See Also
+        --------
+        arrays.IntervalArray.left : Return the left endpoints of each Interval in
+            the IntervalArray as an Index.
+        arrays.IntervalArray.right : Return the right endpoints of each Interval in
+            the IntervalArray as an Index.
+        arrays.IntervalArray.mid : Return the midpoint of each Interval in the
+            IntervalArray as an Index.
+
         Examples
         --------
 

pandas/core/window/ewm.py

@@ -490,7 +490,7 @@ def online(
         klass="Series/Dataframe",
         axis="",
     )
-    def aggregate(self, func, *args, **kwargs):
+    def aggregate(self, func=None, *args, **kwargs):
         return super().aggregate(func, *args, **kwargs)
 
     agg = aggregate
@@ -981,7 +981,7 @@ def reset(self) -> None:
         """
         self._mean.reset()
 
-    def aggregate(self, func, *args, **kwargs):
+    def aggregate(self, func=None, *args, **kwargs):
         raise NotImplementedError("aggregate is not implemented.")
 
     def std(self, bias: bool = False, *args, **kwargs):

pandas/core/window/expanding.py

@@ -167,7 +167,7 @@ def _get_window_indexer(self) -> BaseIndexer:
         klass="Series/Dataframe",
         axis="",
     )
-    def aggregate(self, func, *args, **kwargs):
+    def aggregate(self, func=None, *args, **kwargs):
         return super().aggregate(func, *args, **kwargs)
 
     agg = aggregate

pandas/core/window/rolling.py

@@ -44,7 +44,10 @@
 
 from pandas.core._numba import executor
 from pandas.core.algorithms import factorize
-from pandas.core.apply import ResamplerWindowApply
+from pandas.core.apply import (
+    ResamplerWindowApply,
+    reconstruct_func,
+)
 from pandas.core.arrays import ExtensionArray
 from pandas.core.base import SelectionMixin
 import pandas.core.common as com
@@ -646,8 +649,12 @@ def _numba_apply(
             out = obj._constructor(result, index=index, columns=columns)
             return self._resolve_output(out, obj)
 
-    def aggregate(self, func, *args, **kwargs):
+    def aggregate(self, func=None, *args, **kwargs):
+        relabeling, func, columns, order = reconstruct_func(func, **kwargs)
         result = ResamplerWindowApply(self, func, args=args, kwargs=kwargs).agg()
+        if isinstance(result, ABCDataFrame) and relabeling:
+            result = result.iloc[:, order]
+            result.columns = columns  # type: ignore[union-attr]
         if result is None:
             return self.apply(func, raw=False, args=args, kwargs=kwargs)
         return result
@@ -1239,7 +1246,7 @@ def calc(x):
         klass="Series/DataFrame",
         axis="",
     )
-    def aggregate(self, func, *args, **kwargs):
+    def aggregate(self, func=None, *args, **kwargs):
         result = ResamplerWindowApply(self, func, args=args, kwargs=kwargs).agg()
         if result is None:
             # these must apply directly
@@ -1951,7 +1958,7 @@ def _raise_monotonic_error(self, msg: str):
         klass="Series/Dataframe",
         axis="",
     )
-    def aggregate(self, func, *args, **kwargs):
+    def aggregate(self, func=None, *args, **kwargs):
         return super().aggregate(func, *args, **kwargs)
 
     agg = aggregate

pandas/io/sql.py

@@ -241,7 +241,7 @@ def read_sql_table(  # pyright: ignore[reportOverlappingOverload]
     schema=...,
     index_col: str | list[str] | None = ...,
     coerce_float=...,
-    parse_dates: list[str] | dict[str, str] | None = ...,
+    parse_dates: list[str] | dict[str, str] | dict[str, dict[str, Any]] | None = ...,
     columns: list[str] | None = ...,
     chunksize: None = ...,
     dtype_backend: DtypeBackend | lib.NoDefault = ...,
@@ -255,7 +255,7 @@ def read_sql_table(
     schema=...,
     index_col: str | list[str] | None = ...,
     coerce_float=...,
-    parse_dates: list[str] | dict[str, str] | None = ...,
+    parse_dates: list[str] | dict[str, str] | dict[str, dict[str, Any]] | None = ...,
     columns: list[str] | None = ...,
     chunksize: int = ...,
     dtype_backend: DtypeBackend | lib.NoDefault = ...,
@@ -268,7 +268,7 @@ def read_sql_table(
     schema: str | None = None,
     index_col: str | list[str] | None = None,
     coerce_float: bool = True,
-    parse_dates: list[str] | dict[str, str] | None = None,
+    parse_dates: list[str] | dict[str, str] | dict[str, dict[str, Any]] | None = None,
     columns: list[str] | None = None,
     chunksize: int | None = None,
     dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
@@ -372,7 +372,7 @@ def read_sql_query(  # pyright: ignore[reportOverlappingOverload]
     index_col: str | list[str] | None = ...,
     coerce_float=...,
     params: list[Any] | Mapping[str, Any] | None = ...,
-    parse_dates: list[str] | dict[str, str] | None = ...,
+    parse_dates: list[str] | dict[str, str] | dict[str, dict[str, Any]] | None = ...,
     chunksize: None = ...,
     dtype: DtypeArg | None = ...,
     dtype_backend: DtypeBackend | lib.NoDefault = ...,
@@ -386,7 +386,7 @@ def read_sql_query(
     index_col: str | list[str] | None = ...,
     coerce_float=...,
     params: list[Any] | Mapping[str, Any] | None = ...,
-    parse_dates: list[str] | dict[str, str] | None = ...,
+    parse_dates: list[str] | dict[str, str] | dict[str, dict[str, Any]] | None = ...,
     chunksize: int = ...,
     dtype: DtypeArg | None = ...,
     dtype_backend: DtypeBackend | lib.NoDefault = ...,
@@ -399,7 +399,7 @@ def read_sql_query(
     index_col: str | list[str] | None = None,
     coerce_float: bool = True,
     params: list[Any] | Mapping[str, Any] | None = None,
-    parse_dates: list[str] | dict[str, str] | None = None,
+    parse_dates: list[str] | dict[str, str] | dict[str, dict[str, Any]] | None = None,
     chunksize: int | None = None,
     dtype: DtypeArg | None = None,
     dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,

pandas/tests/groupby/__init__.py

@@ -2,7 +2,7 @@ def get_groupby_method_args(name, obj):
     """
     Get required arguments for a groupby method.
 
-    When parametrizing a test over groupby methods (e.g. "sum", "mean", "fillna"),
+    When parametrizing a test over groupby methods (e.g. "sum", "mean"),
     it is often the case that arguments are required for certain methods.
 
     Parameters
@@ -16,7 +16,7 @@ def get_groupby_method_args(name, obj):
     -------
     A tuple of required arguments for the method.
     """
-    if name in ("nth", "fillna", "take"):
+    if name in ("nth", "take"):
         return (0,)
     if name == "quantile":
         return (0.5,)

pandas/tests/groupby/test_categorical.py

@@ -1963,10 +1963,7 @@ def test_category_order_transformer(
         df = df.set_index(keys)
     args = get_groupby_method_args(transformation_func, df)
     gb = df.groupby(keys, as_index=as_index, sort=sort, observed=observed)
-    warn = FutureWarning if transformation_func == "fillna" else None
-    msg = "DataFrameGroupBy.fillna is deprecated"
-    with tm.assert_produces_warning(warn, match=msg):
-        op_result = getattr(gb, transformation_func)(*args)
+    op_result = getattr(gb, transformation_func)(*args)
     result = op_result.index.get_level_values("a").categories
     expected = Index([1, 4, 3, 2])
     tm.assert_index_equal(result, expected)

pandas/tests/groupby/test_groupby.py

@@ -2098,36 +2098,14 @@ def test_group_on_empty_multiindex(transformation_func, request):
     df["col_3"] = df["col_3"].astype(int)
     df["col_4"] = df["col_4"].astype(int)
     df = df.set_index(["col_1", "col_2"])
-    if transformation_func == "fillna":
-        args = ("ffill",)
-    else:
-        args = ()
-    warn = FutureWarning if transformation_func == "fillna" else None
-    warn_msg = "DataFrameGroupBy.fillna is deprecated"
-    with tm.assert_produces_warning(warn, match=warn_msg):
-        result = df.iloc[:0].groupby(["col_1"]).transform(transformation_func, *args)
-    with tm.assert_produces_warning(warn, match=warn_msg):
-        expected = df.groupby(["col_1"]).transform(transformation_func, *args).iloc[:0]
+    result = df.iloc[:0].groupby(["col_1"]).transform(transformation_func)
+    expected = df.groupby(["col_1"]).transform(transformation_func).iloc[:0]
     if transformation_func in ("diff", "shift"):
         expected = expected.astype(int)
     tm.assert_equal(result, expected)
 
-    warn_msg = "SeriesGroupBy.fillna is deprecated"
-    with tm.assert_produces_warning(warn, match=warn_msg):
-        result = (
-            df["col_3"]
-            .iloc[:0]
-            .groupby(["col_1"])
-            .transform(transformation_func, *args)
-        )
-    warn_msg = "SeriesGroupBy.fillna is deprecated"
-    with tm.assert_produces_warning(warn, match=warn_msg):
-        expected = (
-            df["col_3"]
-            .groupby(["col_1"])
-            .transform(transformation_func, *args)
-            .iloc[:0]
-        )
+    result = df["col_3"].iloc[:0].groupby(["col_1"]).transform(transformation_func)
+    expected = df["col_3"].groupby(["col_1"]).transform(transformation_func).iloc[:0]
     if transformation_func in ("diff", "shift"):
         expected = expected.astype(int)
     tm.assert_equal(result, expected)