Remove use_nullable_dtypes from read_parquet (#57370)

Author: phofl

doc/source/whatsnew/v3.0.0.rst

@@ -122,6 +122,7 @@ Removal of prior version deprecations/changes
 - Removed ``pandas.io.sql.execute`` (:issue:`50185`)
 - 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 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 the ``ArrayManager`` (:issue:`55043`)

pandas/io/parquet.py

@@ -9,7 +9,6 @@
     Any,
     Literal,
 )
-import warnings
 from warnings import catch_warnings
 
 from pandas._config import using_pyarrow_string_dtype
@@ -18,7 +17,6 @@
 from pandas.compat._optional import import_optional_dependency
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import doc
-from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import check_dtype_backend
 
 import pandas as pd
@@ -240,7 +238,6 @@ def read(
         path,
         columns=None,
         filters=None,
-        use_nullable_dtypes: bool = False,
         dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
         storage_options: StorageOptions | None = None,
         filesystem=None,
@@ -357,15 +354,9 @@ def read(
         **kwargs,
     ) -> DataFrame:
         parquet_kwargs: dict[str, Any] = {}
-        use_nullable_dtypes = kwargs.pop("use_nullable_dtypes", False)
         dtype_backend = kwargs.pop("dtype_backend", lib.no_default)
         # We are disabling nullable dtypes for fastparquet pending discussion
         parquet_kwargs["pandas_nulls"] = False
-        if use_nullable_dtypes:
-            raise ValueError(
-                "The 'use_nullable_dtypes' argument is not supported for the "
-                "fastparquet engine"
-            )
         if dtype_backend is not lib.no_default:
             raise ValueError(
                 "The 'dtype_backend' argument is not supported for the "
@@ -493,7 +484,6 @@ def read_parquet(
     engine: str = "auto",
     columns: list[str] | None = None,
     storage_options: StorageOptions | None = None,
-    use_nullable_dtypes: bool | lib.NoDefault = lib.no_default,
     dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
     filesystem: Any = None,
     filters: list[tuple] | list[list[tuple]] | None = None,
@@ -534,17 +524,6 @@ def read_parquet(
 
         .. versionadded:: 1.3.0
 
-    use_nullable_dtypes : bool, default False
-        If True, use dtypes that use ``pd.NA`` as missing value indicator
-        for the resulting DataFrame. (only applicable for the ``pyarrow``
-        engine)
-        As new dtypes are added that support ``pd.NA`` in the future, the
-        output with this option will change to use those dtypes.
-        Note: this is an experimental option, and behaviour (e.g. additional
-        support dtypes) may change without notice.
-
-        .. deprecated:: 2.0
-
     dtype_backend : {{'numpy_nullable', 'pyarrow'}}, default 'numpy_nullable'
         Back-end data type applied to the resultant :class:`DataFrame`
         (still experimental). Behaviour is as follows:
@@ -643,27 +622,13 @@ def read_parquet(
     """
 
     impl = get_engine(engine)
-
-    if use_nullable_dtypes is not lib.no_default:
-        msg = (
-            "The argument 'use_nullable_dtypes' is deprecated and will be removed "
-            "in a future version."
-        )
-        if use_nullable_dtypes is True:
-            msg += (
-                "Use dtype_backend='numpy_nullable' instead of use_nullable_dtype=True."
-            )
-        warnings.warn(msg, FutureWarning, stacklevel=find_stack_level())
-    else:
-        use_nullable_dtypes = False
     check_dtype_backend(dtype_backend)
 
     return impl.read(
         path,
         columns=columns,
         filters=filters,
         storage_options=storage_options,
-        use_nullable_dtypes=use_nullable_dtypes,
         dtype_backend=dtype_backend,
         filesystem=filesystem,
         **kwargs,

pandas/tests/io/test_parquet.py

@@ -1273,17 +1273,6 @@ def test_timezone_aware_index(self, fp, timezone_aware_date_list):
         expected.index.name = "index"
         check_round_trip(df, fp, expected=expected)
 
-    def test_use_nullable_dtypes_not_supported(self, fp):
-        df = pd.DataFrame({"a": [1, 2]})
-
-        with tm.ensure_clean() as path:
-            df.to_parquet(path)
-            with pytest.raises(ValueError, match="not supported for the fastparquet"):
-                with tm.assert_produces_warning(FutureWarning):
-                    read_parquet(path, engine="fastparquet", use_nullable_dtypes=True)
-            with pytest.raises(ValueError, match="not supported for the fastparquet"):
-                read_parquet(path, engine="fastparquet", dtype_backend="pyarrow")
-
     def test_close_file_handle_on_read_error(self):
         with tm.ensure_clean("test.parquet") as path:
             pathlib.Path(path).write_bytes(b"breakit")