DEPR: NDFrame._data

doc/source/user_guide/io.rst

@@ -5314,6 +5314,7 @@ Read from a parquet file.
 Read only certain columns of a parquet file.
 
 .. ipython:: python
+   :okwarning:
 
    result = pd.read_parquet(
        "example_fp.parquet",

doc/source/whatsnew/v2.1.0.rst

@@ -98,6 +98,7 @@ Other API changes
 Deprecations
 ~~~~~~~~~~~~
 - Deprecated silently dropping unrecognized timezones when parsing strings to datetimes (:issue:`18702`)
+- Deprecated :meth:`DataFrame._data` and :meth:`Series._data`, use public APIs instead (:issue:`33333`)
 - Deprecating pinning ``group.name`` to each group in :meth:`SeriesGroupBy.aggregate` aggregations; if your operation requires utilizing the groupby keys, iterate over the groupby object instead (:issue:`41090`)
 - Deprecated ``axis=1`` in :meth:`DataFrame.groupby` and in :class:`Grouper` constructor, do ``frame.T.groupby(...)`` instead (:issue:`51203`)
 - Deprecated passing a :class:`DataFrame` to :meth:`DataFrame.from_records`, use :meth:`DataFrame.set_index` or :meth:`DataFrame.drop` instead (:issue:`51353`)

pandas/core/generic.py

@@ -486,6 +486,13 @@ def _constructor(self) -> Callable[..., Self]:
     def _data(self):
         # GH#33054 retained because some downstream packages uses this,
         #  e.g. fastparquet
+        # GH#33333
+        warnings.warn(
+            f"{type(self).__name__}._data is deprecated and will be removed in "
+            "a future version. Use public APIs instead.",
+            FutureWarning,
+            stacklevel=find_stack_level(),
+        )
         return self._mgr
 
     # ----------------------------------------------------------------------

pandas/tests/extension/base/casting.py

@@ -26,7 +26,7 @@ def test_astype_object_frame(self, all_data):
 
         result = df.astype(object)
         if hasattr(result._mgr, "blocks"):
-            blk = result._data.blocks[0]
+            blk = result._mgr.blocks[0]
             assert isinstance(blk, ObjectBlock), type(blk)
         assert isinstance(result._mgr.arrays[0], np.ndarray)
         assert result._mgr.arrays[0].dtype == np.dtype(object)

pandas/tests/frame/test_api.py

@@ -377,5 +377,8 @@ def test_constructor_expanddim(self):
     def test_inspect_getmembers(self):
         # GH38740
         df = DataFrame()
-        with tm.assert_produces_warning(None):
+        msg = "DataFrame._data is deprecated"
+        with tm.assert_produces_warning(
+            FutureWarning, match=msg, check_stacklevel=False
+        ):
             inspect.getmembers(df)

pandas/tests/generic/test_generic.py

@@ -301,6 +301,13 @@ def test_copy_and_deepcopy(self, frame_or_series, shape, func):
         assert obj_copy is not obj
         tm.assert_equal(obj_copy, obj)
 
+    def test_data_deprecated(self, frame_or_series):
+        obj = frame_or_series()
+        msg = "(Series|DataFrame)._data is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            mgr = obj._data
+        assert mgr is obj._mgr
+
 
 class TestNDFrame:
     # tests that don't fit elsewhere

pandas/tests/series/test_api.py

@@ -170,7 +170,10 @@ def test_attrs(self):
     def test_inspect_getmembers(self):
         # GH38782
         ser = Series(dtype=object)
-        with tm.assert_produces_warning(None, check_stacklevel=False):
+        msg = "Series._data is deprecated"
+        with tm.assert_produces_warning(
+            FutureWarning, match=msg, check_stacklevel=False
+        ):
             inspect.getmembers(ser)
 
     def test_unknown_attribute(self):