Merge branch 'main' into ref-gpr_index

Author: jbrockmendel

Diff for: doc/source/whatsnew/v2.0.0.rst

@@ -780,7 +780,11 @@ Deprecations
 - :meth:`Index.is_object` has been deprecated. Use :func:`pandas.api.types.is_object_dtype` instead (:issue:`50042`)
 - :meth:`Index.is_interval` has been deprecated. Use :func:`pandas.api.types.is_intterval_dtype` instead (:issue:`50042`)
 - Deprecated ``all`` and ``any`` reductions with ``datetime64`` and :class:`DatetimeTZDtype` dtypes, use e.g. ``(obj != pd.Timestamp(0), tz=obj.tz).all()`` instead (:issue:`34479`)
+- Deprecated unused arguments ``*args`` and ``**kwargs`` in :class:`Resampler` (:issue:`50977`)
 - Deprecated calling ``float`` or ``int`` on a single element :class:`Series` to return a ``float`` or ``int`` respectively. Extract the element before calling ``float`` or ``int`` instead (:issue:`51101`)
+- Deprecated :meth:`Grouper.groups`, use :meth:`Groupby.groups` instead (:issue:`51182`)
+- Deprecated :meth:`Grouper.grouper`, use :meth:`Groupby.grouper` instead (:issue:`51182`)
+-
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_200.prior_deprecations:
@@ -1196,6 +1200,7 @@ Indexing
 - Bug in :meth:`Series.loc` raising error for out of bounds end of slice indexer (:issue:`50161`)
 - Bug in :meth:`DataFrame.loc` raising ``ValueError`` with ``bool`` indexer and :class:`MultiIndex` (:issue:`47687`)
 - Bug in :meth:`DataFrame.loc` raising ``IndexError`` when setting values for a pyarrow-backed column with a non-scalar indexer (:issue:`50085`)
+- Bug in :meth:`DataFrame.loc` modifying object when setting incompatible value with an empty indexer (:issue:`45981`)
 - Bug in :meth:`DataFrame.__setitem__` raising ``ValueError`` when right hand side is :class:`DataFrame` with :class:`MultiIndex` columns (:issue:`49121`)
 - Bug in :meth:`DataFrame.reindex` casting dtype to ``object`` when :class:`DataFrame` has single extension array column when re-indexing ``columns`` and ``index`` (:issue:`48190`)
 - Bug in :meth:`DataFrame.iloc` raising ``IndexError`` when indexer is a :class:`Series` with numeric extension array dtype (:issue:`49521`)

Diff for: pandas/core/common.py

@@ -316,6 +316,18 @@ def is_null_slice(obj) -> bool:
     )
 
 
+def is_empty_slice(obj) -> bool:
+    """
+    We have an empty slice, e.g. no values are selected.
+    """
+    return (
+        isinstance(obj, slice)
+        and obj.start is not None
+        and obj.stop is not None
+        and obj.start == obj.stop
+    )
+
+
 def is_true_slices(line) -> list[bool]:
     """
     Find non-trivial slices in "line": return a list of booleans with same length.

Diff for: pandas/core/generic.py

@@ -8783,7 +8783,7 @@ def resample(
 
         axis = self._get_axis_number(axis)
         return get_resampler(
-            self,
+            cast("Series | DataFrame", self),
             freq=rule,
             label=label,
             closed=closed,

Diff for: pandas/core/groupby/generic.py

@@ -58,6 +58,7 @@
     is_dict_like,
     is_integer_dtype,
     is_interval_dtype,
+    is_numeric_dtype,
     is_scalar,
 )
 from pandas.core.dtypes.missing import (
@@ -172,9 +173,18 @@ def _wrap_agged_manager(self, mgr: Manager) -> Series:
         # NB: caller is responsible for setting ser.index
         return ser
 
-    def _get_data_to_aggregate(self) -> SingleManager:
+    def _get_data_to_aggregate(
+        self, *, numeric_only: bool = False, name: str | None = None
+    ) -> SingleManager:
         ser = self._selected_obj
         single = ser._mgr
+        if numeric_only and not is_numeric_dtype(ser.dtype):
+            # GH#41291 match Series behavior
+            kwd_name = "numeric_only"
+            raise TypeError(
+                f"Cannot use {kwd_name}=True with "
+                f"{type(self).__name__}.{name} and non-numeric dtypes."
+            )
         return single
 
     def _iterate_slices(self) -> Iterable[Series]:
@@ -380,10 +390,16 @@ def _wrap_applied_output(
         """
         if len(values) == 0:
             # GH #6265
+            if is_transform:
+                # GH#47787 see test_group_on_empty_multiindex
+                res_index = data.index
+            else:
+                res_index = self.grouper.result_index
+
             return self.obj._constructor(
                 [],
                 name=self.obj.name,
-                index=self.grouper.result_index,
+                index=res_index,
                 dtype=data.dtype,
             )
         assert values is not None
@@ -1136,14 +1152,12 @@ def cov(
     @property
     @doc(Series.is_monotonic_increasing.__doc__)
     def is_monotonic_increasing(self) -> Series:
-        result = self._op_via_apply("is_monotonic_increasing")
-        return result
+        return self.apply(lambda ser: ser.is_monotonic_increasing)
 
     @property
     @doc(Series.is_monotonic_decreasing.__doc__)
     def is_monotonic_decreasing(self) -> Series:
-        result = self._op_via_apply("is_monotonic_decreasing")
-        return result
+        return self.apply(lambda ser: ser.is_monotonic_decreasing)
 
     @doc(Series.hist.__doc__)
     def hist(
@@ -1181,8 +1195,7 @@ def hist(
     @property
     @doc(Series.dtype.__doc__)
     def dtype(self) -> Series:
-        result = self._op_via_apply("dtype")
-        return result
+        return self.apply(lambda ser: ser.dtype)
 
     @doc(Series.unique.__doc__)
     def unique(self) -> Series:
@@ -1428,9 +1441,13 @@ def _wrap_applied_output(
     ):
 
         if len(values) == 0:
-            result = self.obj._constructor(
-                index=self.grouper.result_index, columns=data.columns
-            )
+            if is_transform:
+                # GH#47787 see test_group_on_empty_multiindex
+                res_index = data.index
+            else:
+                res_index = self.grouper.result_index
+
+            result = self.obj._constructor(index=res_index, columns=data.columns)
             result = result.astype(data.dtypes, copy=False)
             return result
 
@@ -1542,9 +1559,9 @@ def _cython_transform(
         #  test_transform_numeric_ret
         # With self.axis == 1, _get_data_to_aggregate does a transpose
         #  so we always have a single block.
-        mgr: Manager2D = self._get_data_to_aggregate()
-        if numeric_only:
-            mgr = mgr.get_numeric_data(copy=False)
+        mgr: Manager2D = self._get_data_to_aggregate(
+            numeric_only=numeric_only, name=how
+        )
 
         def arr_func(bvalues: ArrayLike) -> ArrayLike:
             return self.grouper._cython_operation(
@@ -1719,18 +1736,11 @@ def _transform_item_by_item(self, obj: DataFrame, wrapper) -> DataFrame:
         # iterate through columns, see test_transform_exclude_nuisance
         #  gets here with non-unique columns
         output = {}
-        inds = []
         for i, (colname, sgb) in enumerate(self._iterate_column_groupbys(obj)):
             output[i] = sgb.transform(wrapper)
-            inds.append(i)
-
-        if not output:
-            raise TypeError("Transform function invalid for data types")
-
-        columns = obj.columns.take(inds)
 
         result = self.obj._constructor(output, index=obj.index)
-        result.columns = columns
+        result.columns = obj.columns
         return result
 
     def filter(self, func, dropna: bool = True, *args, **kwargs):
@@ -1864,12 +1874,18 @@ def _gotitem(self, key, ndim: int, subset=None):
 
         raise AssertionError("invalid ndim for _gotitem")
 
-    def _get_data_to_aggregate(self) -> Manager2D:
+    def _get_data_to_aggregate(
+        self, *, numeric_only: bool = False, name: str | None = None
+    ) -> Manager2D:
         obj = self._obj_with_exclusions
         if self.axis == 1:
-            return obj.T._mgr
+            mgr = obj.T._mgr
         else:
-            return obj._mgr
+            mgr = obj._mgr
+
+        if numeric_only:
+            mgr = mgr.get_numeric_data(copy=False)
+        return mgr
 
     def _indexed_output_to_ndframe(
         self, output: Mapping[base.OutputKey, ArrayLike]
@@ -2677,8 +2693,8 @@ def hist(
     @property
     @doc(DataFrame.dtypes.__doc__)
     def dtypes(self) -> Series:
-        result = self._op_via_apply("dtypes")
-        return result
+        # error: Incompatible return value type (got "DataFrame", expected "Series")
+        return self.apply(lambda df: df.dtypes)  # type: ignore[return-value]
 
     @doc(DataFrame.corrwith.__doc__)
     def corrwith(