CLN: ._data, PeriodIndex arguments (pandas-dev#57385)

* Remove ._data

* Remove _data from StringArrow

* Remove period arguments

* Bump fastparquet

Author: mroeschke

ci/deps/actions-310.yaml

@@ -26,7 +26,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2022.12.0
+  - fastparquet>=2023.04.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1

ci/deps/actions-311-downstream_compat.yaml

@@ -28,7 +28,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2022.12.0
+  - fastparquet>=2023.04.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1

ci/deps/actions-311.yaml

@@ -26,7 +26,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2022.12.0
+  - fastparquet>=2023.04.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1

ci/deps/actions-312.yaml

@@ -26,7 +26,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2022.12.0
+  - fastparquet>=2023.04.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1

ci/deps/actions-39-minimum_versions.yaml

@@ -29,7 +29,7 @@ dependencies:
   - beautifulsoup4=4.11.2
   - blosc=1.21.3
   - bottleneck=1.3.6
-  - fastparquet=2022.12.0
+  - fastparquet=2023.04.0
   - fsspec=2022.11.0
   - html5lib=1.1
   - hypothesis=6.46.1

ci/deps/actions-39.yaml

@@ -26,7 +26,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2022.12.0
+  - fastparquet>=2023.04.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1

ci/deps/circle-310-arm64.yaml

@@ -27,7 +27,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2022.12.0
+  - fastparquet>=2023.04.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1

doc/source/getting_started/install.rst

@@ -361,7 +361,7 @@ Dependency                Minimum Version    pip extra        Notes
 PyTables                  3.8.0              hdf5             HDF5-based reading / writing
 blosc                     1.21.3             hdf5             Compression for HDF5; only available on ``conda``
 zlib                                         hdf5             Compression for HDF5
-fastparquet               2022.12.0          -                Parquet reading / writing (pyarrow is default)
+fastparquet               2023.04.0          -                Parquet reading / writing (pyarrow is default)
 pyarrow                   10.0.1             parquet, feather Parquet, ORC, and feather reading / writing
 pyreadstat                1.2.0              spss             SPSS files (.sav) reading
 odfpy                     1.4.1              excel            Open document format (.odf, .ods, .odt) reading / writing

doc/source/whatsnew/v3.0.0.rst

@@ -77,7 +77,7 @@ Optional libraries below the lowest tested version may still work, but are not c
 +-----------------+---------------------+
 | Package         | New Minimum Version |
 +=================+=====================+
-|                 |                     |
+| fastparquet     | 2023.04.0           |
 +-----------------+---------------------+
 
 See :ref:`install.dependencies` and :ref:`install.optional_dependencies` for more.
@@ -125,6 +125,7 @@ Removal of prior version deprecations/changes
 - Removed ``Series.ravel`` (:issue:`56053`)
 - Removed ``Series.view`` (:issue:`56054`)
 - Removed ``StataReader.close`` (:issue:`49228`)
+- Removed ``_data`` from :class:`DataFrame`, :class:`Series`, :class:`.arrays.ArrowExtensionArray` (:issue:`52003`)
 - Removed ``axis`` argument from :meth:`DataFrame.groupby`, :meth:`Series.groupby`, :meth:`DataFrame.rolling`, :meth:`Series.rolling`, :meth:`DataFrame.resample`, and :meth:`Series.resample` (:issue:`51203`)
 - Removed ``axis`` argument from all groupby operations (:issue:`50405`)
 - Removed ``convert_dtype`` from :meth:`Series.apply` (:issue:`52257`)
@@ -134,6 +135,7 @@ Removal of prior version deprecations/changes
 - Removed ``pandas.value_counts``, use :meth:`Series.value_counts` instead (:issue:`53493`)
 - Removed ``read_gbq`` and ``DataFrame.to_gbq``. Use ``pandas_gbq.read_gbq`` and ``pandas_gbq.to_gbq`` instead https://pandas-gbq.readthedocs.io/en/latest/api.html (:issue:`55525`)
 - Removed ``use_nullable_dtypes`` from :func:`read_parquet` (:issue:`51853`)
+- Removed ``year``, ``month``, ``quarter``, ``day``, ``hour``, ``minute``, and ``second`` keywords in the :class:`PeriodIndex` constructor, use :meth:`PeriodIndex.from_fields` instead (:issue:`55960`)
 - Removed deprecated argument ``obj`` in :meth:`.DataFrameGroupBy.get_group` and :meth:`.SeriesGroupBy.get_group` (:issue:`53545`)
 - Removed deprecated behavior of :meth:`Series.agg` using :meth:`Series.apply` (:issue:`53325`)
 - Removed support for :class:`DataFrame` in :meth:`DataFrame.from_records`(:issue:`51697`)
@@ -142,6 +144,7 @@ Removal of prior version deprecations/changes
 - Removed the ``ArrayManager`` (:issue:`55043`)
 - Removed the ``fastpath`` argument from the :class:`Series` constructor (:issue:`55466`)
 - Removed the ``is_boolean``, ``is_integer``, ``is_floating``, ``holds_integer``, ``is_numeric``, ``is_categorical``, ``is_object``, and ``is_interval`` attributes of :class:`Index` (:issue:`50042`)
+- Removed the ``ordinal`` keyword in :class:`PeriodIndex`, use :meth:`PeriodIndex.from_ordinals` instead (:issue:`55960`)
 - Removed unused arguments ``*args`` and ``**kwargs`` in :class:`Resampler` methods (:issue:`50977`)
 - Unrecognized timezones when parsing strings to datetimes now raises a ``ValueError`` (:issue:`51477`)
 

environment.yml

@@ -29,7 +29,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc
   - bottleneck>=1.3.6
-  - fastparquet>=2022.12.0
+  - fastparquet>=2023.04.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1

pandas/compat/_optional.py

@@ -25,7 +25,7 @@
     "blosc": "1.21.3",
     "bottleneck": "1.3.6",
     "dataframe-api-compat": "0.1.7",
-    "fastparquet": "2022.12.0",
+    "fastparquet": "2023.04.0",
     "fsspec": "2022.11.0",
     "html5lib": "1.1",
     "hypothesis": "6.46.1",

pandas/core/arrays/string_arrow.py

@@ -9,7 +9,6 @@
     Union,
     cast,
 )
-import warnings
 
 import numpy as np
 
@@ -21,7 +20,6 @@
     pa_version_under10p1,
     pa_version_under13p0,
 )
-from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.common import (
     is_bool_dtype,
@@ -272,17 +270,6 @@ def astype(self, dtype, copy: bool = True):
 
         return super().astype(dtype, copy=copy)
 
-    @property
-    def _data(self):
-        # dask accesses ._data directlys
-        warnings.warn(
-            f"{type(self).__name__}._data is a deprecated and will be removed "
-            "in a future version, use ._pa_array instead",
-            FutureWarning,
-            stacklevel=find_stack_level(),
-        )
-        return self._pa_array
-
     # ------------------------------------------------------------------------
     # String methods interface
 

pandas/core/generic.py

@@ -486,23 +486,6 @@ def _constructor(self) -> Callable[..., Self]:
         """
         raise AbstractMethodError(self)
 
-    # ----------------------------------------------------------------------
-    # Internals
-
-    @final
-    @property
-    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.",
-            DeprecationWarning,
-            stacklevel=find_stack_level(),
-        )
-        return self._mgr
-
     # ----------------------------------------------------------------------
     # Axis
     _AXIS_ORDERS: list[Literal["index", "columns"]]

pandas/core/indexes/period.py

@@ -5,7 +5,6 @@
     timedelta,
 )
 from typing import TYPE_CHECKING
-import warnings
 
 import numpy as np
 
@@ -22,7 +21,6 @@
     cache_readonly,
     doc,
 )
-from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.common import is_integer
 from pandas.core.dtypes.dtypes import PeriodDtype
@@ -94,11 +92,6 @@ class PeriodIndex(DatetimeIndexOpsMixin):
     ----------
     data : array-like (1d int np.ndarray or PeriodArray), optional
         Optional period-like data to construct index with.
-    ordinal : array-like of int, optional
-        The period offsets from the proleptic Gregorian epoch.
-
-        .. deprecated:: 2.2.0
-           Use PeriodIndex.from_ordinals instead.
     freq : str or period object, optional
         One of pandas period strings or corresponding objects.
     dtype : str or PeriodDtype, default None
@@ -107,11 +100,6 @@ class PeriodIndex(DatetimeIndexOpsMixin):
         Make a copy of input ndarray.
     name : str, default None
         Name of the resulting PeriodIndex.
-    **fields : optional
-        Date fields such as year, month, etc.
-
-        .. deprecated:: 2.2.0
-           Use PeriodIndex.from_fields instead.
 
     Attributes
     ----------
@@ -219,84 +207,29 @@ def second(self) -> Index:
     def __new__(
         cls,
         data=None,
-        ordinal=None,
         freq=None,
         dtype: Dtype | None = None,
         copy: bool = False,
         name: Hashable | None = None,
-        **fields,
     ) -> Self:
-        valid_field_set = {
-            "year",
-            "month",
-            "day",
-            "quarter",
-            "hour",
-            "minute",
-            "second",
-        }
-
         refs = None
         if not copy and isinstance(data, (Index, ABCSeries)):
             refs = data._references
 
-        if not set(fields).issubset(valid_field_set):
-            argument = next(iter(set(fields) - valid_field_set))
-            raise TypeError(f"__new__() got an unexpected keyword argument {argument}")
-        elif len(fields):
-            # GH#55960
-            warnings.warn(
-                "Constructing PeriodIndex from fields is deprecated. Use "
-                "PeriodIndex.from_fields instead.",
-                FutureWarning,
-                stacklevel=find_stack_level(),
-            )
-
-        if ordinal is not None:
-            # GH#55960
-            warnings.warn(
-                "The 'ordinal' keyword in PeriodIndex is deprecated and will "
-                "be removed in a future version. Use PeriodIndex.from_ordinals "
-                "instead.",
-                FutureWarning,
-                stacklevel=find_stack_level(),
-            )
-
         name = maybe_extract_name(name, data, cls)
 
-        if data is None and ordinal is None:
-            # range-based.
-            if not fields:
-                # test_pickle_compat_construction
-                cls._raise_scalar_data_error(None)
-            data = cls.from_fields(**fields, freq=freq)._data
-            copy = False
+        freq = validate_dtype_freq(dtype, freq)
 
-        elif fields:
-            if data is not None:
-                raise ValueError("Cannot pass both data and fields")
-            raise ValueError("Cannot pass both ordinal and fields")
+        # PeriodIndex allow PeriodIndex(period_index, freq=different)
+        # Let's not encourage that kind of behavior in PeriodArray.
 
-        else:
-            freq = validate_dtype_freq(dtype, freq)
-
-            # PeriodIndex allow PeriodIndex(period_index, freq=different)
-            # Let's not encourage that kind of behavior in PeriodArray.
-
-            if freq and isinstance(data, cls) and data.freq != freq:
-                # TODO: We can do some of these with no-copy / coercion?
-                # e.g. D -> 2D seems to be OK
-                data = data.asfreq(freq)
-
-            if data is None and ordinal is not None:
-                ordinal = np.asarray(ordinal, dtype=np.int64)
-                dtype = PeriodDtype(freq)
-                data = PeriodArray(ordinal, dtype=dtype)
-            elif data is not None and ordinal is not None:
-                raise ValueError("Cannot pass both data and ordinal")
-            else:
-                # don't pass copy here, since we copy later.
-                data = period_array(data=data, freq=freq)
+        if freq and isinstance(data, cls) and data.freq != freq:
+            # TODO: We can do some of these with no-copy / coercion?
+            # e.g. D -> 2D seems to be OK
+            data = data.asfreq(freq)
+
+        # don't pass copy here, since we copy later.
+        data = period_array(data=data, freq=freq)
 
         if copy:
             data = data.copy()

pandas/tests/frame/test_api.py

@@ -376,8 +376,4 @@ def test_inspect_getmembers(self):
         # GH38740
         pytest.importorskip("jinja2")
         df = DataFrame()
-        msg = "DataFrame._data is deprecated"
-        with tm.assert_produces_warning(
-            DeprecationWarning, match=msg, check_stacklevel=False
-        ):
-            inspect.getmembers(df)
+        inspect.getmembers(df)

pandas/tests/generic/test_generic.py

@@ -303,13 +303,6 @@ 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(DeprecationWarning, match=msg):
-            mgr = obj._data
-        assert mgr is obj._mgr
-
 
 class TestNDFrame:
     # tests that don't fit elsewhere