Backport PR #54922 on branch 2.1.x (REGR: Restore _constructor_from_mgr to pass manager object to constructor) (#55704)

Backport PR #54922: REGR: Restore _constructor_from_mgr to pass manager object to constructor

Author: jorisvandenbossche

doc/source/whatsnew/v2.1.2.rst

@@ -29,6 +29,7 @@ Fixed regressions
 - Fixed performance regression with wide DataFrames, typically involving methods where all columns were accessed individually (:issue:`55256`, :issue:`55245`)
 - Fixed regression in :func:`merge_asof` raising ``TypeError`` for ``by`` with datetime and timedelta dtypes (:issue:`55453`)
 - Fixed regression in :meth:`DataFrame.to_sql` not roundtripping datetime columns correctly for sqlite when using ``detect_types`` (:issue:`55554`)
+- Fixed regression in construction of certain DataFrame or Series subclasses (:issue:`54922`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_212.bug_fixes:

pandas/core/frame.py

@@ -639,28 +639,25 @@ def _constructor(self) -> Callable[..., DataFrame]:
         return DataFrame
 
     def _constructor_from_mgr(self, mgr, axes):
-        df = self._from_mgr(mgr, axes=axes)
-
-        if type(self) is DataFrame:
-            # fastpath avoiding constructor call
-            return df
+        if self._constructor is DataFrame:
+            # we are pandas.DataFrame (or a subclass that doesn't override _constructor)
+            return self._from_mgr(mgr, axes=axes)
         else:
             assert axes is mgr.axes
-            return self._constructor(df, copy=False)
+            return self._constructor(mgr)
 
     _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):
-        ser = self._sliced_from_mgr(mgr, axes=axes)
-        ser._name = None  # caller is responsible for setting real name
-        if type(self) is DataFrame:
-            # fastpath avoiding constructor call
+        if self._constructor_sliced is Series:
+            ser = self._sliced_from_mgr(mgr, axes)
+            ser._name = None  # caller is responsible for setting real name
             return ser
         assert axes is mgr.axes
-        return self._constructor_sliced(ser, copy=False)
+        return self._constructor_sliced(mgr)
 
     # ----------------------------------------------------------------------
     # Constructors

pandas/core/series.py

@@ -579,14 +579,14 @@ def _constructor(self) -> Callable[..., Series]:
         return Series
 
     def _constructor_from_mgr(self, mgr, axes):
-        ser = self._from_mgr(mgr, axes=axes)
-        ser._name = None  # caller is responsible for setting real name
-        if type(self) is Series:
-            # fastpath avoiding constructor call
+        if self._constructor is Series:
+            # we are pandas.Series (or a subclass that doesn't override _constructor)
+            ser = self._from_mgr(mgr, axes=axes)
+            ser._name = None  # caller is responsible for setting real name
             return ser
         else:
             assert axes is mgr.axes
-            return self._constructor(ser, copy=False)
+            return self._constructor(mgr)
 
     @property
     def _constructor_expanddim(self) -> Callable[..., DataFrame]:
@@ -610,12 +610,12 @@ def _expanddim_from_mgr(self, mgr, axes) -> DataFrame:
         return DataFrame._from_mgr(mgr, axes=mgr.axes)
 
     def _constructor_expanddim_from_mgr(self, mgr, axes):
-        df = self._expanddim_from_mgr(mgr, axes)
-        if type(self) is Series:
-            # fastpath avoiding constructor
-            return df
+        from pandas.core.frame import DataFrame
+
+        if self._constructor_expanddim is DataFrame:
+            return self._expanddim_from_mgr(mgr, axes)
         assert axes is mgr.axes
-        return self._constructor_expanddim(df, copy=False)
+        return self._constructor_expanddim(mgr)
 
     # types
     @property

pandas/tests/frame/test_arithmetic.py

@@ -2078,6 +2078,9 @@ def test_frame_sub_nullable_int(any_int_ea_dtype):
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager|Passing a SingleBlockManager:DeprecationWarning"
+)
 def test_frame_op_subclass_nonclass_constructor():
     # GH#43201 subclass._constructor is a function, not the subclass itself
 

pandas/tests/frame/test_subclass.py

@@ -10,6 +10,10 @@
 )
 import pandas._testing as tm
 
+pytestmark = pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager|Passing a SingleBlockManager:DeprecationWarning"
+)
+
 
 @pytest.fixture()
 def gpd_style_subclass_df():
@@ -734,8 +738,36 @@ def test_replace_list_method(self):
         # https://github.com/pandas-dev/pandas/pull/46018
         df = tm.SubclassedDataFrame({"A": [0, 1, 2]})
         msg = "The 'method' keyword in SubclassedDataFrame.replace is deprecated"
-        with tm.assert_produces_warning(FutureWarning, match=msg):
+        with tm.assert_produces_warning(
+            FutureWarning, match=msg, raise_on_extra_warnings=False
+        ):
             result = df.replace([1, 2], method="ffill")
         expected = tm.SubclassedDataFrame({"A": [0, 0, 0]})
         assert isinstance(result, tm.SubclassedDataFrame)
         tm.assert_frame_equal(result, expected)
+
+
+class MySubclassWithMetadata(DataFrame):
+    _metadata = ["my_metadata"]
+
+    def __init__(self, *args, **kwargs) -> None:
+        super().__init__(*args, **kwargs)
+
+        my_metadata = kwargs.pop("my_metadata", None)
+        if args and isinstance(args[0], MySubclassWithMetadata):
+            my_metadata = args[0].my_metadata  # type: ignore[has-type]
+        self.my_metadata = my_metadata
+
+    @property
+    def _constructor(self):
+        return MySubclassWithMetadata
+
+
+def test_constructor_with_metadata():
+    # https://github.com/pandas-dev/pandas/pull/54922
+    # https://github.com/pandas-dev/pandas/issues/55120
+    df = MySubclassWithMetadata(
+        np.random.default_rng(2).random((5, 3)), columns=["A", "B", "C"]
+    )
+    subset = df[["A", "B"]]
+    assert isinstance(subset, MySubclassWithMetadata)

pandas/tests/groupby/test_groupby_subclass.py

@@ -11,6 +11,10 @@
 import pandas._testing as tm
 from pandas.tests.groupby import get_groupby_method_args
 
+pytestmark = pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager|Passing a SingleBlockManager:DeprecationWarning"
+)
+
 
 @pytest.mark.parametrize(
     "obj",

pandas/tests/reshape/concat/test_concat.py

@@ -591,6 +591,9 @@ def test_duplicate_keys_same_frame():
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager|Passing a SingleBlockManager:DeprecationWarning"
+)
 @pytest.mark.parametrize(
     "obj",
     [

pandas/tests/reshape/merge/test_merge.py

@@ -689,6 +689,9 @@ def test_merge_nan_right2(self):
         )[["i1", "i2", "i1_", "i3"]]
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.filterwarnings(
+        "ignore:Passing a BlockManager|Passing a SingleBlockManager:DeprecationWarning"
+    )
     def test_merge_type(self, df, df2):
         class NotADataFrame(DataFrame):
             @property

pandas/tests/reshape/merge/test_merge_ordered.py

@@ -70,6 +70,9 @@ def test_multigroup(self, left, right):
         result = merge_ordered(left, right, on="key", left_by="group")
         assert result["group"].notna().all()
 
+    @pytest.mark.filterwarnings(
+        "ignore:Passing a BlockManager|Passing a SingleBlockManager:DeprecationWarning"
+    )
     def test_merge_type(self, left, right):
         class NotADataFrame(DataFrame):
             @property

pandas/tests/series/methods/test_to_frame.py

@@ -1,3 +1,5 @@
+import pytest
+
 from pandas import (
     DataFrame,
     Index,
@@ -40,6 +42,9 @@ def test_to_frame(self, datetime_series):
         )
         tm.assert_frame_equal(rs, xp)
 
+    @pytest.mark.filterwarnings(
+        "ignore:Passing a BlockManager|Passing a SingleBlockManager:DeprecationWarning"
+    )
     def test_to_frame_expanddim(self):
         # GH#9762
 

pandas/tests/series/test_subclass.py

@@ -4,6 +4,10 @@
 import pandas as pd
 import pandas._testing as tm
 
+pytestmark = pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager|Passing a SingleBlockManager:DeprecationWarning"
+)
+
 
 class TestSeriesSubclassing:
     @pytest.mark.parametrize(