DEPR: ArrayManager (pandas-dev#55044)

* DEPR: ArrayManager

* Fixup

* Test fixup

* debug CI

* Test fixup

* warn if PANDAS_DATA_MANAGER is set

* single_cpu

Author: rhshadrach

doc/source/whatsnew/v2.2.0.rst

@@ -199,6 +199,7 @@ Deprecations
 - Deprecated strings ``T``, ``S``, ``L``, ``U``, and ``N`` denoting frequencies in :class:`Minute`, :class:`Second`, :class:`Milli`, :class:`Micro`, :class:`Nano` (:issue:`52536`)
 - Deprecated strings ``T``, ``S``, ``L``, ``U``, and ``N`` denoting units in :class:`Timedelta` (:issue:`52536`)
 - Deprecated the extension test classes ``BaseNoReduceTests``, ``BaseBooleanReduceTests``, and ``BaseNumericReduceTests``, use ``BaseReduceTests`` instead (:issue:`54663`)
+- Deprecated the option ``mode.data_manager`` and the ``ArrayManager``; only the ``BlockManager`` will be available in future versions (:issue:`55043`)
 - Deprecating downcasting the results of :meth:`DataFrame.fillna`, :meth:`Series.fillna`, :meth:`DataFrame.ffill`, :meth:`Series.ffill`, :meth:`DataFrame.bfill`, :meth:`Series.bfill` in object-dtype cases. To opt in to the future version, use ``pd.set_option("future.no_silent_downcasting", True)`` (:issue:`54261`)
 
 .. ---------------------------------------------------------------------------

pandas/__init__.py

@@ -1,5 +1,8 @@
 from __future__ import annotations
 
+import os
+import warnings
+
 __docformat__ = "restructuredtext"
 
 # Let users know if they're missing any of our hard dependencies
@@ -190,6 +193,17 @@
     __git_version__ = v.get("full-revisionid")
     del get_versions, v
 
+# GH#55043 - deprecation of the data_manager option
+if "PANDAS_DATA_MANAGER" in os.environ:
+    warnings.warn(
+        "The env variable PANDAS_DATA_MANAGER is set. The data_manager option is "
+        "deprecated and will be removed in a future version. Only the BlockManager "
+        "will be available. Unset this environment variable to silence this warning.",
+        FutureWarning,
+        stacklevel=2,
+    )
+# Don't allow users to use pandas.os or pandas.warnings
+del os, warnings
 
 # module level doc-string
 __doc__ = """

pandas/conftest.py

@@ -49,6 +49,8 @@
     utc,
 )
 
+from pandas._config.config import _get_option
+
 import pandas.util._test_decorators as td
 
 from pandas.core.dtypes.dtypes import (
@@ -1983,15 +1985,18 @@ def using_array_manager() -> bool:
     """
     Fixture to check if the array manager is being used.
     """
-    return pd.options.mode.data_manager == "array"
+    return _get_option("mode.data_manager", silent=True) == "array"
 
 
 @pytest.fixture
 def using_copy_on_write() -> bool:
     """
     Fixture to check if Copy-on-Write is enabled.
     """
-    return pd.options.mode.copy_on_write and pd.options.mode.data_manager == "block"
+    return (
+        pd.options.mode.copy_on_write
+        and _get_option("mode.data_manager", silent=True) == "block"
+    )
 
 
 warsaws = ["Europe/Warsaw", "dateutil/Europe/Warsaw"]

pandas/core/config_init.py

@@ -454,6 +454,13 @@ def use_inf_as_na_cb(key) -> None:
         validator=is_one_of_factory(["block", "array"]),
     )
 
+cf.deprecate_option(
+    # GH#55043
+    "mode.data_manager",
+    "data_manager option is deprecated and will be removed in a future "
+    "version. Only the BlockManager will be available.",
+)
+
 
 # TODO better name?
 copy_on_write_doc = """

pandas/core/frame.py

@@ -43,6 +43,7 @@
     get_option,
     using_copy_on_write,
 )
+from pandas._config.config import _get_option
 
 from pandas._libs import (
     algos as libalgos,
@@ -694,7 +695,7 @@ def __init__(
                 NDFrame.__init__(self, data)
                 return
 
-        manager = get_option("mode.data_manager")
+        manager = _get_option("mode.data_manager", silent=True)
 
         # GH47215
         if isinstance(index, set):
@@ -2411,7 +2412,7 @@ def maybe_reorder(
 
             columns = columns.drop(exclude)
 
-        manager = get_option("mode.data_manager")
+        manager = _get_option("mode.data_manager", silent=True)
         mgr = arrays_to_mgr(arrays, columns, result_index, typ=manager)
 
         return cls(mgr)
@@ -2612,7 +2613,7 @@ def _from_arrays(
         if dtype is not None:
             dtype = pandas_dtype(dtype)
 
-        manager = get_option("mode.data_manager")
+        manager = _get_option("mode.data_manager", silent=True)
         columns = ensure_index(columns)
         if len(columns) != len(arrays):
             raise ValueError("len(columns) must match len(arrays)")

pandas/core/series.py

@@ -26,10 +26,8 @@
 
 import numpy as np
 
-from pandas._config import (
-    get_option,
-    using_copy_on_write,
-)
+from pandas._config import using_copy_on_write
+from pandas._config.config import _get_option
 
 from pandas._libs import (
     lib,
@@ -404,7 +402,7 @@ def __init__(
         if fastpath:
             # data is a ndarray, index is defined
             if not isinstance(data, (SingleBlockManager, SingleArrayManager)):
-                manager = get_option("mode.data_manager")
+                manager = _get_option("mode.data_manager", silent=True)
                 if manager == "block":
                     data = SingleBlockManager.from_array(data, index)
                 elif manager == "array":
@@ -510,7 +508,7 @@ def __init__(
         else:
             data = sanitize_array(data, index, dtype, copy)
 
-            manager = get_option("mode.data_manager")
+            manager = _get_option("mode.data_manager", silent=True)
             if manager == "block":
                 data = SingleBlockManager.from_array(data, index, refs=refs)
             elif manager == "array":

pandas/io/parquet.py

@@ -13,6 +13,7 @@
 from warnings import catch_warnings
 
 from pandas._config import using_pyarrow_string_dtype
+from pandas._config.config import _get_option
 
 from pandas._libs import lib
 from pandas.compat._optional import import_optional_dependency
@@ -258,7 +259,7 @@ def read(
         elif using_pyarrow_string_dtype():
             to_pandas_kwargs["types_mapper"] = arrow_string_types_mapper()
 
-        manager = get_option("mode.data_manager")
+        manager = _get_option("mode.data_manager", silent=True)
         if manager == "array":
             to_pandas_kwargs["split_blocks"] = True  # type: ignore[assignment]
 

pandas/tests/extension/conftest.py

@@ -2,6 +2,8 @@
 
 import pytest
 
+from pandas._config.config import _get_option
+
 from pandas import (
     Series,
     options,
@@ -212,4 +214,7 @@ def using_copy_on_write() -> bool:
     """
     Fixture to check if Copy-on-Write is enabled.
     """
-    return options.mode.copy_on_write and options.mode.data_manager == "block"
+    return (
+        options.mode.copy_on_write
+        and _get_option("mode.data_manager", silent=True) == "block"
+    )

pandas/tests/internals/test_managers.py

@@ -1,6 +1,12 @@
 """
 Testing interaction between the different managers (BlockManager, ArrayManager)
 """
+import os
+import subprocess
+import sys
+
+import pytest
+
 from pandas.core.dtypes.missing import array_equivalent
 
 import pandas as pd
@@ -14,12 +20,19 @@
 
 
 def test_dataframe_creation():
-    with pd.option_context("mode.data_manager", "block"):
-        df_block = pd.DataFrame({"a": [1, 2, 3], "b": [0.1, 0.2, 0.3], "c": [4, 5, 6]})
+    msg = "data_manager option is deprecated"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        with pd.option_context("mode.data_manager", "block"):
+            df_block = pd.DataFrame(
+                {"a": [1, 2, 3], "b": [0.1, 0.2, 0.3], "c": [4, 5, 6]}
+            )
     assert isinstance(df_block._mgr, BlockManager)
 
-    with pd.option_context("mode.data_manager", "array"):
-        df_array = pd.DataFrame({"a": [1, 2, 3], "b": [0.1, 0.2, 0.3], "c": [4, 5, 6]})
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        with pd.option_context("mode.data_manager", "array"):
+            df_array = pd.DataFrame(
+                {"a": [1, 2, 3], "b": [0.1, 0.2, 0.3], "c": [4, 5, 6]}
+            )
     assert isinstance(df_array._mgr, ArrayManager)
 
     # also ensure both are seen as equal
@@ -45,12 +58,15 @@ def test_dataframe_creation():
 
 
 def test_series_creation():
-    with pd.option_context("mode.data_manager", "block"):
-        s_block = pd.Series([1, 2, 3], name="A", index=["a", "b", "c"])
+    msg = "data_manager option is deprecated"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        with pd.option_context("mode.data_manager", "block"):
+            s_block = pd.Series([1, 2, 3], name="A", index=["a", "b", "c"])
     assert isinstance(s_block._mgr, SingleBlockManager)
 
-    with pd.option_context("mode.data_manager", "array"):
-        s_array = pd.Series([1, 2, 3], name="A", index=["a", "b", "c"])
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        with pd.option_context("mode.data_manager", "array"):
+            s_array = pd.Series([1, 2, 3], name="A", index=["a", "b", "c"])
     assert isinstance(s_array._mgr, SingleArrayManager)
 
     # also ensure both are seen as equal
@@ -68,3 +84,20 @@ def test_series_creation():
     result = s_array._as_manager("block")
     assert isinstance(result._mgr, SingleBlockManager)
     tm.assert_series_equal(result, s_array)
+
+
+@pytest.mark.single_cpu
+@pytest.mark.parametrize("manager", ["block", "array"])
+def test_array_manager_depr_env_var(manager):
+    # GH#55043
+    test_env = os.environ.copy()
+    test_env["PANDAS_DATA_MANAGER"] = manager
+    response = subprocess.run(
+        [sys.executable, "-c", "import pandas"],
+        capture_output=True,
+        env=test_env,
+        check=True,
+    )
+    msg = "FutureWarning: The env variable PANDAS_DATA_MANAGER is set"
+    stderr_msg = response.stderr.decode("utf-8")
+    assert msg in stderr_msg, stderr_msg

pandas/tests/io/test_parquet.py

@@ -8,10 +8,8 @@
 import numpy as np
 import pytest
 
-from pandas._config import (
-    get_option,
-    using_copy_on_write,
-)
+from pandas._config import using_copy_on_write
+from pandas._config.config import _get_option
 
 from pandas.compat import is_platform_windows
 from pandas.compat.pyarrow import (
@@ -61,7 +59,8 @@
         pytest.param(
             "fastparquet",
             marks=pytest.mark.skipif(
-                not _HAVE_FASTPARQUET or get_option("mode.data_manager") == "array",
+                not _HAVE_FASTPARQUET
+                or _get_option("mode.data_manager", silent=True) == "array",
                 reason="fastparquet is not installed or ArrayManager is used",
             ),
         ),
@@ -88,7 +87,7 @@ def pa():
 def fp():
     if not _HAVE_FASTPARQUET:
         pytest.skip("fastparquet is not installed")
-    elif get_option("mode.data_manager") == "array":
+    elif _get_option("mode.data_manager", silent=True) == "array":
         pytest.skip("ArrayManager is not supported with fastparquet")
     return "fastparquet"