ERR: Check that dtype_backend is valid (#51871)

Author: phofl

pandas/core/generic.py

@@ -96,6 +96,7 @@
 from pandas.util._decorators import doc
 from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import (
+ check_dtype_backend,
  validate_ascending,
  validate_bool_kwarg,
  validate_fillna_kwargs,
@@ -6590,8 +6591,8 @@ def convert_dtypes(
 
  .. versionadded:: 1.2.0
  dtype_backend : {"numpy_nullable", "pyarrow"}, default "numpy_nullable"
- Which dtype_backend to use, e.g. whether a DataFrame should have NumPy
- arrays, nullable dtypes are used for all dtypes that have a nullable
+ Which dtype_backend to use, e.g. whether a DataFrame should use nullable
+ dtypes for all dtypes that have a nullable
  implementation when "numpy_nullable" is set, pyarrow is used for all
  dtypes if "pyarrow" is set.
 
@@ -6710,6 +6711,7 @@ def convert_dtypes(
  2 <NA>
  dtype: string
  """
+ check_dtype_backend(dtype_backend)
  if self.ndim == 1:
  return self._convert_dtypes(
  infer_objects,

pandas/core/internals/construction.py

@@ -980,7 +980,7 @@ def convert_object_array(
  ----------
  content: List[np.ndarray]
  dtype: np.dtype or ExtensionDtype
- dtype_backend: Controls if nullable dtypes are returned.
+ dtype_backend: Controls if nullable/pyarrow dtypes are returned.
  coerce_float: Cast floats that are integers to int.
 
  Returns

pandas/core/tools/numeric.py

@@ -8,6 +8,7 @@
 import numpy as np
 
 from pandas._libs import lib
+from pandas.util._validators import check_dtype_backend
 
 from pandas.core.dtypes.cast import maybe_downcast_numeric
 from pandas.core.dtypes.common import (
@@ -166,6 +167,8 @@ def to_numeric(
  if errors not in ("ignore", "raise", "coerce"):
  raise ValueError("invalid error value specified")
 
+ check_dtype_backend(dtype_backend)
+
  is_series = False
  is_index = False
  is_scalars = False

pandas/io/clipboards.py

@@ -7,6 +7,7 @@
 
 from pandas._libs import lib
 from pandas.util._exceptions import find_stack_level
+from pandas.util._validators import check_dtype_backend
 
 from pandas.core.dtypes.generic import ABCDataFrame
 
@@ -58,6 +59,8 @@ def read_clipboard(
  if encoding is not None and encoding.lower().replace("-", "") != "utf8":
  raise NotImplementedError("reading from clipboard only supports utf-8 encoding")
 
+ check_dtype_backend(dtype_backend)
+
  from pandas.io.clipboard import clipboard_get
  from pandas.io.parsers import read_csv
 

pandas/io/excel/_base.py

@@ -36,6 +36,7 @@
  Appender,
  doc,
 )
+from pandas.util._validators import check_dtype_backend
 
 from pandas.core.dtypes.common import (
  is_bool,
@@ -472,6 +473,8 @@ def read_excel(
  storage_options: StorageOptions = None,
  dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
 ) -> DataFrame | dict[IntStrT, DataFrame]:
+ check_dtype_backend(dtype_backend)
+
  should_close = False
  if not isinstance(io, ExcelFile):
  should_close = True

pandas/io/feather_format.py

@@ -10,6 +10,7 @@
 from pandas._libs import lib
 from pandas.compat._optional import import_optional_dependency
 from pandas.util._decorators import doc
+from pandas.util._validators import check_dtype_backend
 
 import pandas as pd
 from pandas.core.api import DataFrame
@@ -105,6 +106,8 @@ def read_feather(
  import_optional_dependency("pyarrow")
  from pyarrow import feather
 
+ check_dtype_backend(dtype_backend)
+
  with get_handle(
  path, "rb", storage_options=storage_options, is_text=False
  ) as handles:

pandas/io/html.py

@@ -24,6 +24,7 @@
  AbstractMethodError,
  EmptyDataError,
 )
+from pandas.util._validators import check_dtype_backend
 
 from pandas.core.dtypes.common import is_list_like
 
@@ -1170,6 +1171,7 @@ def read_html(
  f'"{extract_links}"'
  )
  validate_header_arg(header)
+ check_dtype_backend(dtype_backend)
 
  io = stringify_path(io)
 

pandas/io/json/_json.py

@@ -29,6 +29,7 @@
 from pandas.compat._optional import import_optional_dependency
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import doc
+from pandas.util._validators import check_dtype_backend
 
 from pandas.core.dtypes.common import (
  ensure_str,
@@ -747,6 +748,8 @@ def read_json(
  if orient == "table" and convert_axes:
  raise ValueError("cannot pass both convert_axes and orient='table'")
 
+ check_dtype_backend(dtype_backend)
+
  if dtype is None and orient != "table":
  # error: Incompatible types in assignment (expression has type "bool", variable
  # has type "Union[ExtensionDtype, str, dtype[Any], Type[str], Type[float],
@@ -947,14 +950,18 @@ def read(self) -> DataFrame | Series:
  if self.engine == "pyarrow":
  pyarrow_json = import_optional_dependency("pyarrow.json")
  pa_table = pyarrow_json.read_json(self.data)
+
+ mapping: type[ArrowDtype] | None | Callable
  if self.dtype_backend == "pyarrow":
- return pa_table.to_pandas(types_mapper=ArrowDtype)
+ mapping = ArrowDtype
  elif self.dtype_backend == "numpy_nullable":
  from pandas.io._util import _arrow_dtype_mapping
 
- mapping = _arrow_dtype_mapping()
- return pa_table.to_pandas(types_mapper=mapping.get)
- return pa_table.to_pandas()
+ mapping = _arrow_dtype_mapping().get
+ else:
+ mapping = None
+
+ return pa_table.to_pandas(types_mapper=mapping)
  elif self.engine == "ujson":
  if self.lines:
  if self.chunksize:

pandas/io/orc.py

@@ -12,6 +12,7 @@
 from pandas._libs import lib
 from pandas.compat import pa_version_under8p0
 from pandas.compat._optional import import_optional_dependency
+from pandas.util._validators import check_dtype_backend
 
 from pandas.core.dtypes.common import (
  is_categorical_dtype,
@@ -98,6 +99,8 @@ def read_orc(
 
  orc = import_optional_dependency("pyarrow.orc")
 
+ check_dtype_backend(dtype_backend)
+
  with get_handle(path, "rb", is_text=False) as handles:
  source = handles.handle
  if is_fsspec_url(path) and filesystem is None:

pandas/io/parquet.py

@@ -16,6 +16,7 @@
 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
 from pandas import (
@@ -515,6 +516,7 @@ def read_parquet(
  DataFrame
  """
  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 "
@@ -527,6 +529,7 @@ def read_parquet(
  warnings.warn(msg, FutureWarning, stacklevel=find_stack_level())
  else:
  use_nullable_dtypes = False
+ check_dtype_backend(dtype_backend)
 
  return impl.read(
  path,