DEPR: enforce nested-renaming deprecation (pandas-dev#29608)

Author: jbrockmendel

doc/source/whatsnew/v1.0.0.rst

@@ -279,6 +279,7 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - Removed the previously deprecated ``reduce`` and ``broadcast`` arguments from :meth:`DataFrame.apply` (:issue:`18577`)
 - Removed the previously deprecated ``assert_raises_regex`` function in ``pandas.util.testing`` (:issue:`29174`)
 - Removed :meth:`Index.is_lexsorted_for_tuple` (:issue:`29305`)
+- Removed support for nexted renaming in :meth:`DataFrame.aggregate`, :meth:`Series.aggregate`, :meth:`DataFrameGroupBy.aggregate`, :meth:`SeriesGroupBy.aggregate`, :meth:`Rolling.aggregate` (:issue:`29608`)
 -
 
 .. _whatsnew_1000.performance:

pandas/core/base.py

@@ -283,9 +283,7 @@ def _try_aggregate_string_function(self, arg: str, *args, **kwargs):
             # people may try to aggregate on a non-callable attribute
             # but don't let them think they can pass args to it
             assert len(args) == 0
-            assert (
-                len([kwarg for kwarg in kwargs if kwarg not in ["axis", "_level"]]) == 0
-            )
+            assert len([kwarg for kwarg in kwargs if kwarg not in ["axis"]]) == 0
             return f
 
         f = getattr(np, arg, None)
@@ -324,34 +322,17 @@ def _aggregate(self, arg, *args, **kwargs):
         _axis = kwargs.pop("_axis", None)
         if _axis is None:
             _axis = getattr(self, "axis", 0)
-        _level = kwargs.pop("_level", None)
 
         if isinstance(arg, str):
             return self._try_aggregate_string_function(arg, *args, **kwargs), None
 
         if isinstance(arg, dict):
-
             # aggregate based on the passed dict
             if _axis != 0:  # pragma: no cover
                 raise ValueError("Can only pass dict with axis=0")
 
             obj = self._selected_obj
 
-            def nested_renaming_depr(level: int = 4):
-                # deprecation of nested renaming
-                # GH 15931
-                msg = textwrap.dedent(
-                    """\
-                using a dict with renaming is deprecated and will be removed
-                in a future version.
-
-                For column-specific groupby renaming, use named aggregation
-
-                    >>> df.groupby(...).agg(name=('column', aggfunc))
-                """
-                )
-                warnings.warn(msg, FutureWarning, stacklevel=level)
-
             # if we have a dict of any non-scalars
             # eg. {'A' : ['mean']}, normalize all to
             # be list-likes
@@ -374,18 +355,9 @@ def nested_renaming_depr(level: int = 4):
                     # not ok
                     # {'ra' : { 'A' : 'mean' }}
                     if isinstance(v, dict):
-                        is_nested_renamer = True
-
-                        if k not in obj.columns:
-                            msg = (
-                                "cannot perform renaming for {key} with a "
-                                "nested dictionary"
-                            ).format(key=k)
-                            raise SpecificationError(msg)
-                        nested_renaming_depr(4 + (_level or 0))
-
+                        raise SpecificationError("nested renamer is not supported")
                     elif isinstance(obj, ABCSeries):
-                        nested_renaming_depr()
+                        raise SpecificationError("nested renamer is not supported")
                     elif isinstance(obj, ABCDataFrame) and k not in obj.columns:
                         raise KeyError("Column '{col}' does not exist!".format(col=k))
 
@@ -398,7 +370,7 @@ def nested_renaming_depr(level: int = 4):
                 if isinstance(obj, ABCDataFrame) and len(
                     obj.columns.intersection(keys)
                 ) != len(keys):
-                    nested_renaming_depr()
+                    raise SpecificationError("nested renamer is not supported")
 
             from pandas.core.reshape.concat import concat
 
@@ -411,14 +383,14 @@ def _agg_1dim(name, how, subset=None):
                     raise SpecificationError(
                         "nested dictionary is ambiguous in aggregation"
                     )
-                return colg.aggregate(how, _level=(_level or 0) + 1)
+                return colg.aggregate(how)
 
             def _agg_2dim(name, how):
                 """
                 aggregate a 2-dim with how
                 """
                 colg = self._gotitem(self._selection, ndim=2, subset=obj)
-                return colg.aggregate(how, _level=None)
+                return colg.aggregate(how)
 
             def _agg(arg, func):
                 """
@@ -535,7 +507,7 @@ def is_any_frame() -> bool:
             return result, True
         elif is_list_like(arg):
             # we require a list, but not an 'str'
-            return self._aggregate_multiple_funcs(arg, _level=_level, _axis=_axis), None
+            return self._aggregate_multiple_funcs(arg, _axis=_axis), None
         else:
             result = None
 
@@ -546,7 +518,7 @@ def is_any_frame() -> bool:
         # caller can react
         return result, True
 
-    def _aggregate_multiple_funcs(self, arg, _level, _axis):
+    def _aggregate_multiple_funcs(self, arg, _axis):
         from pandas.core.reshape.concat import concat
 
         if _axis != 0:

pandas/core/groupby/generic.py

@@ -11,7 +11,6 @@
 from textwrap import dedent
 import typing
 from typing import Any, Callable, FrozenSet, Iterable, Sequence, Type, Union, cast
-import warnings
 
 import numpy as np
 
@@ -213,7 +212,6 @@ def apply(self, func, *args, **kwargs):
     )
     @Appender(_shared_docs["aggregate"])
     def aggregate(self, func=None, *args, **kwargs):
-        _level = kwargs.pop("_level", None)
 
         relabeling = func is None
         columns = None
@@ -232,7 +230,7 @@ def aggregate(self, func=None, *args, **kwargs):
             # Catch instances of lists / tuples
             # but not the class list / tuple itself.
             func = _maybe_mangle_lambdas(func)
-            ret = self._aggregate_multiple_funcs(func, (_level or 0) + 1)
+            ret = self._aggregate_multiple_funcs(func)
             if relabeling:
                 ret.columns = columns
         else:
@@ -256,32 +254,22 @@ def aggregate(self, func=None, *args, **kwargs):
         if not self.as_index:  # pragma: no cover
             print("Warning, ignoring as_index=True")
 
-        # _level handled at higher
-        if not _level and isinstance(ret, dict):
+        if isinstance(ret, dict):
             from pandas import concat
 
             ret = concat(ret, axis=1)
         return ret
 
     agg = aggregate
 
-    def _aggregate_multiple_funcs(self, arg, _level):
+    def _aggregate_multiple_funcs(self, arg):
         if isinstance(arg, dict):
 
             # show the deprecation, but only if we
             # have not shown a higher level one
             # GH 15931
-            if isinstance(self._selected_obj, Series) and _level <= 1:
-                msg = dedent(
-                    """\
-                using a dict on a Series for aggregation
-                is deprecated and will be removed in a future version. Use \
-                named aggregation instead.
-
-                    >>> grouper.agg(name_1=func_1, name_2=func_2)
-                """
-                )
-                warnings.warn(msg, FutureWarning, stacklevel=3)
+            if isinstance(self._selected_obj, Series):
+                raise SpecificationError("nested renamer is not supported")
 
             columns = list(arg.keys())
             arg = arg.items()
@@ -317,8 +305,7 @@ def _aggregate_multiple_funcs(self, arg, _level):
 
         if any(isinstance(x, DataFrame) for x in results.values()):
             # let higher level handle
-            if _level:
-                return results
+            return results
 
         return DataFrame(results, columns=columns)
 
@@ -845,7 +832,6 @@ class DataFrameGroupBy(GroupBy):
     )
     @Appender(_shared_docs["aggregate"])
     def aggregate(self, func=None, *args, **kwargs):
-        _level = kwargs.pop("_level", None)
 
         relabeling = func is None and _is_multi_agg_with_relabel(**kwargs)
         if relabeling:
@@ -858,7 +844,7 @@ def aggregate(self, func=None, *args, **kwargs):
 
         func = _maybe_mangle_lambdas(func)
 
-        result, how = self._aggregate(func, _level=_level, *args, **kwargs)
+        result, how = self._aggregate(func, *args, **kwargs)
         if how is None:
             return result
 
@@ -878,9 +864,7 @@ def aggregate(self, func=None, *args, **kwargs):
 
                 # try to treat as if we are passing a list
                 try:
-                    result = self._aggregate_multiple_funcs(
-                        [func], _level=_level, _axis=self.axis
-                    )
+                    result = self._aggregate_multiple_funcs([func], _axis=self.axis)
                 except ValueError as err:
                     if "no results" not in str(err):
                         # raised directly by _aggregate_multiple_funcs

pandas/tests/frame/test_apply.py

@@ -13,6 +13,7 @@
 from pandas import DataFrame, MultiIndex, Series, Timestamp, date_range, notna
 from pandas.conftest import _get_cython_table_params
 from pandas.core.apply import frame_apply
+from pandas.core.base import SpecificationError
 import pandas.util.testing as tm
 
 
@@ -1094,7 +1095,8 @@ def test_agg_dict_nested_renaming_depr(self):
         df = pd.DataFrame({"A": range(5), "B": 5})
 
         # nested renaming
-        with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
+        msg = r"nested renamer is not supported"
+        with pytest.raises(SpecificationError, match=msg):
             df.agg({"A": {"foo": "min"}, "B": {"bar": "max"}})
 
     def test_agg_reduce(self, axis, float_frame):

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -267,16 +267,16 @@ def bar(x):
         return np.std(x, ddof=1)
 
     # this uses column selection & renaming
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
+    msg = r"nested renamer is not supported"
+    with pytest.raises(SpecificationError, match=msg):
         d = OrderedDict(
             [["C", np.mean], ["D", OrderedDict([["foo", np.mean], ["bar", np.std]])]]
         )
-        result = grouped.aggregate(d)
+        grouped.aggregate(d)
 
+    # But without renaming, these functions are OK
     d = OrderedDict([["C", [np.mean]], ["D", [foo, bar]]])
-    expected = grouped.aggregate(d)
-
-    tm.assert_frame_equal(result, expected)
+    grouped.aggregate(d)
 
 
 def test_multi_function_flexible_mix(df):
@@ -288,26 +288,25 @@ def test_multi_function_flexible_mix(df):
         [["C", OrderedDict([["foo", "mean"], ["bar", "std"]])], ["D", {"sum": "sum"}]]
     )
     # this uses column selection & renaming
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
-        expected = grouped.aggregate(d)
+    msg = r"nested renamer is not supported"
+    with pytest.raises(SpecificationError, match=msg):
+        grouped.aggregate(d)
 
     # Test 1
     d = OrderedDict(
         [["C", OrderedDict([["foo", "mean"], ["bar", "std"]])], ["D", "sum"]]
     )
     # this uses column selection & renaming
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
-        result = grouped.aggregate(d)
-    tm.assert_frame_equal(result, expected)
+    with pytest.raises(SpecificationError, match=msg):
+        grouped.aggregate(d)
 
     # Test 2
     d = OrderedDict(
         [["C", OrderedDict([["foo", "mean"], ["bar", "std"]])], ["D", ["sum"]]]
     )
     # this uses column selection & renaming
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
-        result = grouped.aggregate(d)
-    tm.assert_frame_equal(result, expected)
+    with pytest.raises(SpecificationError, match=msg):
+        grouped.aggregate(d)
 
 
 def test_groupby_agg_coercing_bools():

pandas/tests/groupby/aggregate/test_other.py

@@ -211,31 +211,26 @@ def test_aggregate_api_consistency():
     expected = pd.concat([c_mean, c_sum, d_mean, d_sum], axis=1)
     expected.columns = MultiIndex.from_product([["C", "D"], ["mean", "sum"]])
 
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
-        result = grouped[["D", "C"]].agg({"r": np.sum, "r2": np.mean})
-    expected = pd.concat([d_sum, c_sum, d_mean, c_mean], axis=1)
-    expected.columns = MultiIndex.from_product([["r", "r2"], ["D", "C"]])
-    tm.assert_frame_equal(result, expected, check_like=True)
+    msg = r"nested renamer is not supported"
+    with pytest.raises(SpecificationError, match=msg):
+        grouped[["D", "C"]].agg({"r": np.sum, "r2": np.mean})
 
 
 def test_agg_dict_renaming_deprecation():
     # 15931
     df = pd.DataFrame({"A": [1, 1, 1, 2, 2], "B": range(5), "C": range(5)})
 
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False) as w:
+    msg = r"nested renamer is not supported"
+    with pytest.raises(SpecificationError, match=msg):
         df.groupby("A").agg(
             {"B": {"foo": ["sum", "max"]}, "C": {"bar": ["count", "min"]}}
         )
-        assert "using a dict with renaming" in str(w[0].message)
-        assert "named aggregation" in str(w[0].message)
 
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
+    with pytest.raises(SpecificationError, match=msg):
         df.groupby("A")[["B", "C"]].agg({"ma": "max"})
 
-    with tm.assert_produces_warning(FutureWarning) as w:
+    with pytest.raises(SpecificationError, match=msg):
         df.groupby("A").B.agg({"foo": "count"})
-        assert "using a dict on a Series for aggregation" in str(w[0].message)
-        assert "named aggregation instead." in str(w[0].message)
 
 
 def test_agg_compat():
@@ -251,18 +246,12 @@ def test_agg_compat():
 
     g = df.groupby(["A", "B"])
 
-    expected = pd.concat([g["D"].sum(), g["D"].std()], axis=1)
-    expected.columns = MultiIndex.from_tuples([("C", "sum"), ("C", "std")])
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
-        result = g["D"].agg({"C": ["sum", "std"]})
-    tm.assert_frame_equal(result, expected, check_like=True)
-
-    expected = pd.concat([g["D"].sum(), g["D"].std()], axis=1)
-    expected.columns = ["C", "D"]
+    msg = r"nested renamer is not supported"
+    with pytest.raises(SpecificationError, match=msg):
+        g["D"].agg({"C": ["sum", "std"]})
 
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
-        result = g["D"].agg({"C": "sum", "D": "std"})
-    tm.assert_frame_equal(result, expected, check_like=True)
+    with pytest.raises(SpecificationError, match=msg):
+        g["D"].agg({"C": "sum", "D": "std"})
 
 
 def test_agg_nested_dicts():
@@ -278,29 +267,20 @@ def test_agg_nested_dicts():
 
     g = df.groupby(["A", "B"])
 
-    msg = r"cannot perform renaming for r[1-2] with a nested dictionary"
+    msg = r"nested renamer is not supported"
     with pytest.raises(SpecificationError, match=msg):
         g.aggregate({"r1": {"C": ["mean", "sum"]}, "r2": {"D": ["mean", "sum"]}})
 
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
-        result = g.agg({"C": {"ra": ["mean", "std"]}, "D": {"rb": ["mean", "std"]}})
-    expected = pd.concat(
-        [g["C"].mean(), g["C"].std(), g["D"].mean(), g["D"].std()], axis=1
-    )
-    expected.columns = pd.MultiIndex.from_tuples(
-        [("ra", "mean"), ("ra", "std"), ("rb", "mean"), ("rb", "std")]
-    )
-    tm.assert_frame_equal(result, expected, check_like=True)
+    with pytest.raises(SpecificationError, match=msg):
+        g.agg({"C": {"ra": ["mean", "std"]}, "D": {"rb": ["mean", "std"]}})
 
     # same name as the original column
     # GH9052
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
-        expected = g["D"].agg({"result1": np.sum, "result2": np.mean})
-    expected = expected.rename(columns={"result1": "D"})
+    with pytest.raises(SpecificationError, match=msg):
+        g["D"].agg({"result1": np.sum, "result2": np.mean})
 
-    with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
-        result = g["D"].agg({"D": np.sum, "result2": np.mean})
-    tm.assert_frame_equal(result, expected, check_like=True)
+    with pytest.raises(SpecificationError, match=msg):
+        g["D"].agg({"D": np.sum, "result2": np.mean})
 
 
 def test_agg_item_by_item_raise_typeerror():