Backport PR #57553 on branch 2.2.x (API: avoid passing Manager to subclass init) (#58008)

* Backport PR #57553: API: avoid passing Manager to subclass __init__

* whatsnew, type ignores

* merge 2.2.2 file from main

* rebase on 2.2.x whatsnew

Author: jbrockmendel

pandas/core/frame.py

@@ -656,26 +656,37 @@ class DataFrame(NDFrame, OpsMixin):
     def _constructor(self) -> Callable[..., DataFrame]:
         return DataFrame
 
-    def _constructor_from_mgr(self, mgr, axes):
-        if self._constructor is DataFrame:
-            # we are pandas.DataFrame (or a subclass that doesn't override _constructor)
-            return DataFrame._from_mgr(mgr, axes=axes)
-        else:
-            assert axes is mgr.axes
+    def _constructor_from_mgr(self, mgr, axes) -> DataFrame:
+        df = DataFrame._from_mgr(mgr, axes=axes)
+
+        if type(self) is DataFrame:
+            # This would also work `if self._constructor is DataFrame`, but
+            #  this check is slightly faster, benefiting the most-common case.
+            return df
+
+        elif type(self).__name__ == "GeoDataFrame":
+            # Shim until geopandas can override their _constructor_from_mgr
+            #  bc they have different behavior for Managers than for DataFrames
             return self._constructor(mgr)
 
+        # We assume that the subclass __init__ knows how to handle a
+        #  pd.DataFrame object.
+        return self._constructor(df)
+
     _constructor_sliced: Callable[..., Series] = Series
 
-    def _sliced_from_mgr(self, mgr, axes) -> Series:
-        return Series._from_mgr(mgr, axes)
+    def _constructor_sliced_from_mgr(self, mgr, axes) -> Series:
+        ser = Series._from_mgr(mgr, axes)
+        ser._name = None  # caller is responsible for setting real name
 
-    def _constructor_sliced_from_mgr(self, mgr, axes):
-        if self._constructor_sliced is Series:
-            ser = self._sliced_from_mgr(mgr, axes)
-            ser._name = None  # caller is responsible for setting real name
+        if type(self) is DataFrame:
+            # This would also work `if self._constructor_sliced is Series`, but
+            #  this check is slightly faster, benefiting the most-common case.
             return ser
-        assert axes is mgr.axes
-        return self._constructor_sliced(mgr)
+
+        # We assume that the subclass __init__ knows how to handle a
+        #  pd.Series object.
+        return self._constructor_sliced(ser)
 
     # ----------------------------------------------------------------------
     # Constructors
@@ -1403,7 +1414,8 @@ def _get_values_for_csv(
             na_rep=na_rep,
             quoting=quoting,
         )
-        return self._constructor_from_mgr(mgr, axes=mgr.axes)
+        # error: Incompatible return value type (got "DataFrame", expected "Self")
+        return self._constructor_from_mgr(mgr, axes=mgr.axes)  # type: ignore[return-value]
 
     # ----------------------------------------------------------------------
 
@@ -5077,7 +5089,8 @@ def predicate(arr: ArrayLike) -> bool:
             return True
 
         mgr = self._mgr._get_data_subset(predicate).copy(deep=None)
-        return self._constructor_from_mgr(mgr, axes=mgr.axes).__finalize__(self)
+        # error: Incompatible return value type (got "DataFrame", expected "Self")
+        return self._constructor_from_mgr(mgr, axes=mgr.axes).__finalize__(self)  # type: ignore[return-value]
 
     def insert(
         self,

pandas/core/generic.py

@@ -336,6 +336,7 @@ def _as_manager(self, typ: str, copy: bool_t = True) -> Self:
         # fastpath of passing a manager doesn't check the option/manager class
         return self._constructor_from_mgr(new_mgr, axes=new_mgr.axes).__finalize__(self)
 
+    @final
     @classmethod
     def _from_mgr(cls, mgr: Manager, axes: list[Index]) -> Self:
         """

pandas/core/resample.py

@@ -2548,7 +2548,8 @@ def _take_new_index(
         if axis == 1:
             raise NotImplementedError("axis 1 is not supported")
         new_mgr = obj._mgr.reindex_indexer(new_axis=new_index, indexer=indexer, axis=1)
-        return obj._constructor_from_mgr(new_mgr, axes=new_mgr.axes)
+        # error: Incompatible return value type (got "DataFrame", expected "NDFrameT")
+        return obj._constructor_from_mgr(new_mgr, axes=new_mgr.axes)  # type: ignore[return-value]
     else:
         raise ValueError("'obj' should be either a Series or a DataFrame")
 

pandas/core/series.py

@@ -662,14 +662,17 @@ def _constructor(self) -> Callable[..., Series]:
         return Series
 
     def _constructor_from_mgr(self, mgr, axes):
-        if self._constructor is Series:
-            # we are pandas.Series (or a subclass that doesn't override _constructor)
-            ser = Series._from_mgr(mgr, axes=axes)
-            ser._name = None  # caller is responsible for setting real name
+        ser = Series._from_mgr(mgr, axes=axes)
+        ser._name = None  # caller is responsible for setting real name
+
+        if type(self) is Series:
+            # This would also work `if self._constructor is Series`, but
+            #  this check is slightly faster, benefiting the most-common case.
             return ser
-        else:
-            assert axes is mgr.axes
-            return self._constructor(mgr)
+
+        # We assume that the subclass __init__ knows how to handle a
+        #  pd.Series object.
+        return self._constructor(ser)
 
     @property
     def _constructor_expanddim(self) -> Callable[..., DataFrame]:
@@ -681,18 +684,19 @@ def _constructor_expanddim(self) -> Callable[..., DataFrame]:
 
         return DataFrame
 
-    def _expanddim_from_mgr(self, mgr, axes) -> DataFrame:
+    def _constructor_expanddim_from_mgr(self, mgr, axes):
         from pandas.core.frame import DataFrame
 
-        return DataFrame._from_mgr(mgr, axes=mgr.axes)
+        df = DataFrame._from_mgr(mgr, axes=mgr.axes)
 
-    def _constructor_expanddim_from_mgr(self, mgr, axes):
-        from pandas.core.frame import DataFrame
+        if type(self) is Series:
+            # This would also work `if self._constructor_expanddim is DataFrame`,
+            #  but this check is slightly faster, benefiting the most-common case.
+            return df
 
-        if self._constructor_expanddim is DataFrame:
-            return self._expanddim_from_mgr(mgr, axes)
-        assert axes is mgr.axes
-        return self._constructor_expanddim(mgr)
+        # We assume that the subclass __init__ knows how to handle a
+        #  pd.DataFrame object.
+        return self._constructor_expanddim(df)
 
     # types
     @property

pandas/tests/frame/test_subclass.py

@@ -26,6 +26,17 @@ def _constructor(self):
 
 
 class TestDataFrameSubclassing:
+    def test_no_warning_on_mgr(self):
+        # GH#57032
+        df = tm.SubclassedDataFrame(
+            {"X": [1, 2, 3], "Y": [1, 2, 3]}, index=["a", "b", "c"]
+        )
+        with tm.assert_produces_warning(None):
+            # df.isna() goes through _constructor_from_mgr, which we want to
+            #  *not* pass a Manager do __init__
+            df.isna()
+            df["X"].isna()
+
     def test_frame_subclassing_and_slicing(self):
         # Subclass frame and ensure it returns the right class on slicing it
         # In reference to PR 9632