CLN: enforce the deprecation of exposing blocks in core.internals (pandas-dev#58467)

* CLN: enforce the deprecation of exposing blocks in core.internals

* remove the function __getattr__, and entries from __all__

* fix mypy error

* add a note to v3.0.0

* skip parquet tests for minimum Pyarrow version

* fixup test_basic

* fix pre-commit error

* skip pyarrow=10.0.1 in test_parquet.py

* fix mypy error

* fix pre-commit error

* fixup test_parquet.py

* fix pre-commit error

* fixup test_parquet.py

* replacee pytest.skip with pytest.importorskip

* skip pyarrow '10.0.1'

Author: natmokval

doc/source/whatsnew/v3.0.0.rst

@@ -253,6 +253,7 @@ Removal of prior version deprecations/changes
 - Enforced deprecation of :meth:`Series.interpolate` and :meth:`DataFrame.interpolate` for object-dtype (:issue:`57820`)
 - Enforced deprecation of :meth:`offsets.Tick.delta`, use ``pd.Timedelta(obj)`` instead (:issue:`55498`)
 - Enforced deprecation of ``axis=None`` acting the same as ``axis=0`` in the DataFrame reductions ``sum``, ``prod``, ``std``, ``var``, and ``sem``, passing ``axis=None`` will now reduce over both axes; this is particularly the case when doing e.g. ``numpy.sum(df)`` (:issue:`21597`)
+- Enforced deprecation of ``core.internals`` members ``Block``, ``ExtensionBlock``, and ``DatetimeTZBlock`` (:issue:`58467`)
 - Enforced deprecation of non-standard (``np.ndarray``, :class:`ExtensionArray`, :class:`Index`, or :class:`Series`) argument to :func:`api.extensions.take` (:issue:`52981`)
 - Enforced deprecation of parsing system timezone strings to ``tzlocal``, which depended on system timezone, pass the 'tz' keyword instead (:issue:`50791`)
 - Enforced deprecation of passing a dictionary to :meth:`SeriesGroupBy.agg` (:issue:`52268`)

pandas/core/internals/__init__.py

@@ -6,58 +6,8 @@
 )
 
 __all__ = [
-    "Block",
-    "DatetimeTZBlock",
-    "ExtensionBlock",
     "make_block",
     "BlockManager",
     "SingleBlockManager",
     "concatenate_managers",
 ]
-
-
-def __getattr__(name: str):
-    # GH#55139
-    import warnings
-
-    if name == "create_block_manager_from_blocks":
-        # GH#33892
-        warnings.warn(
-            f"{name} is deprecated and will be removed in a future version. "
-            "Use public APIs instead.",
-            DeprecationWarning,
-            # https://github.com/pandas-dev/pandas/pull/55139#pullrequestreview-1720690758
-            # on hard-coding stacklevel
-            stacklevel=2,
-        )
-        from pandas.core.internals.managers import create_block_manager_from_blocks
-
-        return create_block_manager_from_blocks
-
-    if name in [
-        "Block",
-        "ExtensionBlock",
-        "DatetimeTZBlock",
-    ]:
-        warnings.warn(
-            f"{name} is deprecated and will be removed in a future version. "
-            "Use public APIs instead.",
-            DeprecationWarning,
-            # https://github.com/pandas-dev/pandas/pull/55139#pullrequestreview-1720690758
-            # on hard-coding stacklevel
-            stacklevel=2,
-        )
-        if name == "DatetimeTZBlock":
-            from pandas.core.internals.blocks import DatetimeTZBlock
-
-            return DatetimeTZBlock
-        elif name == "ExtensionBlock":
-            from pandas.core.internals.blocks import ExtensionBlock
-
-            return ExtensionBlock
-        else:
-            from pandas.core.internals.blocks import Block
-
-            return Block
-
-    raise AttributeError(f"module 'pandas.core.internals' has no attribute '{name}'")

pandas/io/pytables.py

@@ -125,7 +125,8 @@
         npt,
     )
 
-    from pandas.core.internals import Block
+    from pandas.core.internals.blocks import Block
+
 
 # versioning attribute
 _version = "0.15.2"

pandas/tests/internals/test_api.py

@@ -41,21 +41,6 @@ def test_namespace():
     assert set(result) == set(expected + modules)
 
 
-@pytest.mark.parametrize(
-    "name",
-    [
-        "Block",
-        "ExtensionBlock",
-        "DatetimeTZBlock",
-    ],
-)
-def test_deprecations(name):
-    # GH#55139
-    msg = f"{name} is deprecated.* Use public APIs instead"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        getattr(internals, name)
-
-
 def test_make_block_2d_with_dti():
     # GH#41168
     dti = pd.date_range("2012", periods=3, tz="UTC")
@@ -65,18 +50,6 @@ def test_make_block_2d_with_dti():
     assert blk.values.shape == (1, 3)
 
 
-def test_create_block_manager_from_blocks_deprecated():
-    # GH#33892
-    # If they must, downstream packages should get this from internals.api,
-    #  not internals.
-    msg = (
-        "create_block_manager_from_blocks is deprecated and will be "
-        "removed in a future version. Use public APIs instead"
-    )
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        internals.create_block_manager_from_blocks
-
-
 def test_create_dataframe_from_blocks(float_frame):
     block = float_frame._mgr.blocks[0]
     index = float_frame.index.copy()

pandas/tests/io/test_parquet.py

@@ -655,6 +655,7 @@ def test_read_empty_array(self, pa, dtype):
                 "value": pd.array([], dtype=dtype),
             }
         )
+        pytest.importorskip("pyarrow", "11.0.0")
         # GH 45694
         expected = None
         if dtype == "float":
@@ -671,6 +672,7 @@ def test_read_empty_array(self, pa, dtype):
 class TestParquetPyArrow(Base):
     def test_basic(self, pa, df_full):
         df = df_full
+        pytest.importorskip("pyarrow", "11.0.0")
 
         # additional supported types for pyarrow
         dti = pd.date_range("20130101", periods=3, tz="Europe/Brussels")
@@ -938,6 +940,8 @@ def test_timestamp_nanoseconds(self, pa):
         check_round_trip(df, pa, write_kwargs={"version": ver})
 
     def test_timezone_aware_index(self, request, pa, timezone_aware_date_list):
+        pytest.importorskip("pyarrow", "11.0.0")
+
         if timezone_aware_date_list.tzinfo != datetime.timezone.utc:
             request.applymarker(
                 pytest.mark.xfail(