ENH: set __module__ on remaining io.* (pandas-dev#62597)

dkane01 · dkane01 · Justine Wezenaar · commit dc91d9f799e4 · 2025-10-08T14:52:18.000-04:00
Co-authored-by: dkane01 &lt;dk1284@nyu.edu&gt;
diff --git a/pandas/io/clipboards.py b/pandas/io/clipboards.py
@@ -7,6 +7,7 @@
 import warnings
 
 from pandas._libs import lib
+from pandas.util._decorators import set_module
 from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import check_dtype_backend
 
@@ -21,6 +22,7 @@
     from pandas._typing import DtypeBackend
 
 
+@set_module("pandas")
 def read_clipboard(
     sep: str = r"\s+",
     dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
diff --git a/pandas/io/excel/_base.py b/pandas/io/excel/_base.py
@@ -39,6 +39,7 @@
 from pandas.util._decorators import (
     Appender,
     doc,
+    set_module,
 )
 from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import check_dtype_backend
@@ -434,6 +435,7 @@ def read_excel(
 ) -> dict[IntStrT, DataFrame]: ...
 
 
+@set_module("pandas")
 @doc(storage_options=_shared_docs["storage_options"])
 @Appender(_read_excel_doc)
 def read_excel(
@@ -951,6 +953,7 @@ def _parse_sheet(
         return output
 
 
+@set_module("pandas")
 @doc(storage_options=_shared_docs["storage_options"])
 class ExcelWriter(Generic[_WorkbookT]):
     """
@@ -1471,6 +1474,7 @@ def inspect_excel_format(
         return "zip"
 
 
+@set_module("pandas")
 @doc(storage_options=_shared_docs["storage_options"])
 class ExcelFile:
     """
diff --git a/pandas/io/feather_format.py b/pandas/io/feather_format.py
@@ -13,7 +13,10 @@
 from pandas._libs import lib
 from pandas.compat._optional import import_optional_dependency
 from pandas.errors import Pandas4Warning
-from pandas.util._decorators import doc
+from pandas.util._decorators import (
+    doc,
+    set_module,
+)
 from pandas.util._validators import check_dtype_backend
 
 from pandas.core.api import DataFrame
@@ -68,6 +71,7 @@ def to_feather(
         feather.write_feather(df, handles.handle, **kwargs)
 
 
+@set_module("pandas")
 @doc(storage_options=_shared_docs["storage_options"])
 def read_feather(
     path: FilePath | ReadBuffer[bytes],
diff --git a/pandas/io/formats/format.py b/pandas/io/formats/format.py
@@ -42,6 +42,7 @@
     Timestamp,
 )
 from pandas._libs.tslibs.nattype import NaTType
+from pandas.util._decorators import set_module
 
 from pandas.core.dtypes.common import (
     is_complex_dtype,
@@ -1955,6 +1956,7 @@ def __call__(self, num: float) -> str:
         return formatted
 
 
+@set_module("pandas")
 def set_eng_float_format(accuracy: int = 3, use_eng_prefix: bool = False) -> None:
     """
     Format float representation in DataFrame with SI notation.
diff --git a/pandas/io/html.py b/pandas/io/html.py
@@ -24,7 +24,10 @@
     AbstractMethodError,
     EmptyDataError,
 )
-from pandas.util._decorators import doc
+from pandas.util._decorators import (
+    doc,
+    set_module,
+)
 from pandas.util._validators import check_dtype_backend
 
 from pandas.core.dtypes.common import is_list_like
@@ -1024,6 +1027,7 @@ def _parse(
     return ret
 
 
+@set_module("pandas")
 @doc(storage_options=_shared_docs["storage_options"])
 def read_html(
     io: FilePath | ReadBuffer[str],
diff --git a/pandas/io/iceberg.py b/pandas/io/iceberg.py
@@ -3,10 +3,12 @@
 )
 
 from pandas.compat._optional import import_optional_dependency
+from pandas.util._decorators import set_module
 
 from pandas import DataFrame
 
 
+@set_module("pandas")
 def read_iceberg(
     table_identifier: str,
     catalog_name: str | None = None,
diff --git a/pandas/io/json/_json.py b/pandas/io/json/_json.py
@@ -29,7 +29,10 @@
 from pandas._libs.tslibs import iNaT
 from pandas.compat._optional import import_optional_dependency
 from pandas.errors import AbstractMethodError
-from pandas.util._decorators import doc
+from pandas.util._decorators import (
+    doc,
+    set_module,
+)
 from pandas.util._validators import check_dtype_backend
 
 from pandas.core.dtypes.common import (
@@ -496,6 +499,7 @@ def read_json(
 ) -> DataFrame: ...
 
 
+@set_module("pandas")
 @doc(
     storage_options=_shared_docs["storage_options"],
     decompression_options=_shared_docs["decompression_options"] % "path_or_buf",
diff --git a/pandas/io/json/_normalize.py b/pandas/io/json/_normalize.py
@@ -17,6 +17,7 @@
 import numpy as np
 
 from pandas._libs.writers import convert_json_to_lines
+from pandas.util._decorators import set_module
 
 import pandas as pd
 from pandas import (
@@ -266,6 +267,7 @@ def _simple_json_normalize(
     return normalized_json_object
 
 
+@set_module("pandas")
 def json_normalize(
     data: dict | list[dict] | Series,
     record_path: str | list | None = None,
diff --git a/pandas/io/orc.py b/pandas/io/orc.py
@@ -11,6 +11,7 @@
 
 from pandas._libs import lib
 from pandas.compat._optional import import_optional_dependency
+from pandas.util._decorators import set_module
 from pandas.util._validators import check_dtype_backend
 
 from pandas.core.indexes.api import default_index
@@ -35,6 +36,7 @@
     from pandas.core.frame import DataFrame
 
 
+@set_module("pandas")
 def read_orc(
     path: FilePath | ReadBuffer[bytes],
     columns: list[str] | None = None,
diff --git a/pandas/io/parquet.py b/pandas/io/parquet.py
@@ -21,7 +21,10 @@
     AbstractMethodError,
     Pandas4Warning,
 )
-from pandas.util._decorators import doc
+from pandas.util._decorators import (
+    doc,
+    set_module,
+)
 from pandas.util._validators import check_dtype_backend
 
 from pandas import (
@@ -500,6 +503,7 @@ def to_parquet(
         return None
 
 
+@set_module("pandas")
 @doc(storage_options=_shared_docs["storage_options"])
 def read_parquet(
     path: FilePath | ReadBuffer[bytes],
diff --git a/pandas/io/pickle.py b/pandas/io/pickle.py
@@ -10,7 +10,10 @@
 import warnings
 
 from pandas.compat import pickle_compat
-from pandas.util._decorators import doc
+from pandas.util._decorators import (
+    doc,
+    set_module,
+)
 
 from pandas.core.shared_docs import _shared_docs
 
@@ -31,6 +34,7 @@
     )
 
 
+@set_module("pandas")
 @doc(
     storage_options=_shared_docs["storage_options"],
     compression_options=_shared_docs["compression_options"] % "filepath_or_buffer",
@@ -114,6 +118,7 @@ def to_pickle(
         pickle.dump(obj, handles.handle, protocol=protocol)
 
 
+@set_module("pandas")
 @doc(
     storage_options=_shared_docs["storage_options"],
     decompression_options=_shared_docs["decompression_options"] % "filepath_or_buffer",
diff --git a/pandas/io/pytables.py b/pandas/io/pytables.py
@@ -51,7 +51,10 @@
     PerformanceWarning,
     PossibleDataLossError,
 )
-from pandas.util._decorators import cache_readonly
+from pandas.util._decorators import (
+    cache_readonly,
+    set_module,
+)
 from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.common import (
@@ -312,6 +315,7 @@ def to_hdf(
             f(store)
 
 
+@set_module("pandas")
 def read_hdf(
     path_or_buf: FilePath | HDFStore,
     key=None,
@@ -488,6 +492,7 @@ def _is_metadata_of(group: Node, parent_group: Node) -> bool:
     return False
 
 
+@set_module("pandas")
 class HDFStore:
     """
     Dict-like IO interface for storing pandas objects in PyTables.
diff --git a/pandas/io/sas/sasreader.py b/pandas/io/sas/sasreader.py
@@ -15,7 +15,10 @@
     overload,
 )
 
-from pandas.util._decorators import doc
+from pandas.util._decorators import (
+    doc,
+    set_module,
+)
 
 from pandas.core.shared_docs import _shared_docs
 
@@ -83,6 +86,7 @@ def read_sas(
 ) -> DataFrame | SASReader: ...
 
 
+@set_module("pandas")
 @doc(decompression_options=_shared_docs["decompression_options"] % "filepath_or_buffer")
 def read_sas(
     filepath_or_buffer: FilePath | ReadBuffer[bytes],
diff --git a/pandas/io/spss.py b/pandas/io/spss.py
@@ -7,6 +7,7 @@
 
 from pandas._libs import lib
 from pandas.compat._optional import import_optional_dependency
+from pandas.util._decorators import set_module
 from pandas.util._validators import check_dtype_backend
 
 from pandas.core.dtypes.inference import is_list_like
@@ -22,6 +23,7 @@
     from pandas import DataFrame
 
 
+@set_module("pandas")
 def read_spss(
     path: str | Path,
     usecols: Sequence[str] | None = None,
diff --git a/pandas/io/sql.py b/pandas/io/sql.py
@@ -40,6 +40,7 @@
     AbstractMethodError,
     DatabaseError,
 )
+from pandas.util._decorators import set_module
 from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import check_dtype_backend
 
@@ -263,6 +264,7 @@ def read_sql_table(
 ) -> Iterator[DataFrame]: ...
 
 
+@set_module("pandas")
 def read_sql_table(
     table_name: str,
     con,
@@ -394,6 +396,7 @@ def read_sql_query(
 ) -> Iterator[DataFrame]: ...
 
 
+@set_module("pandas")
 def read_sql_query(
     sql,
     con,
@@ -532,6 +535,7 @@ def read_sql(
 ) -> Iterator[DataFrame]: ...
 
 
+@set_module("pandas")
 def read_sql(
     sql,
     con,
diff --git a/pandas/io/stata.py b/pandas/io/stata.py
@@ -46,6 +46,7 @@
 from pandas.util._decorators import (
     Appender,
     doc,
+    set_module,
 )
 from pandas.util._exceptions import find_stack_level
 
@@ -2133,6 +2134,7 @@ def value_labels(self) -> dict[str, dict[int, str]]:
         return self._value_label_dict
 
 
+@set_module("pandas")
 @Appender(_read_stata_doc)
 def read_stata(
     filepath_or_buffer: FilePath | ReadBuffer[bytes],
diff --git a/pandas/io/xml.py b/pandas/io/xml.py
@@ -17,7 +17,10 @@
     AbstractMethodError,
     ParserError,
 )
-from pandas.util._decorators import doc
+from pandas.util._decorators import (
+    doc,
+    set_module,
+)
 from pandas.util._validators import check_dtype_backend
 
 from pandas.core.dtypes.common import is_list_like
@@ -829,6 +832,7 @@ def _parse(
     )
 
 
+@set_module("pandas")
 @doc(
     storage_options=_shared_docs["storage_options"],
     decompression_options=_shared_docs["decompression_options"] % "path_or_buffer",
diff --git a/pandas/tests/api/test_api.py b/pandas/tests/api/test_api.py
@@ -538,5 +538,28 @@ def test_set_module():
     assert pd.pivot.__module__ == "pandas"
     assert pd.cut.__module__ == "pandas"
     assert pd.qcut.__module__ == "pandas"
+    assert pd.read_clipboard.__module__ == "pandas"
+    assert pd.ExcelFile.__module__ == "pandas"
+    assert pd.ExcelWriter.__module__ == "pandas"
+    assert pd.read_excel.__module__ == "pandas"
+    assert pd.read_feather.__module__ == "pandas"
+    assert pd.set_eng_float_format.__module__ == "pandas"
+    assert pd.read_html.__module__ == "pandas"
+    assert pd.read_iceberg.__module__ == "pandas"
+    assert pd.read_json.__module__ == "pandas"
+    assert pd.json_normalize.__module__ == "pandas"
+    assert pd.read_orc.__module__ == "pandas"
+    assert pd.read_parquet.__module__ == "pandas"
+    assert pd.read_pickle.__module__ == "pandas"
+    assert pd.to_pickle.__module__ == "pandas"
+    assert pd.HDFStore.__module__ == "pandas"
+    assert pd.read_hdf.__module__ == "pandas"
+    assert pd.read_sas.__module__ == "pandas"
+    assert pd.read_spss.__module__ == "pandas"
+    assert pd.read_sql.__module__ == "pandas"
+    assert pd.read_sql_query.__module__ == "pandas"
+    assert pd.read_sql_table.__module__ == "pandas"
+    assert pd.read_stata.__module__ == "pandas"
+    assert pd.read_xml.__module__ == "pandas"
     assert api.typing.SeriesGroupBy.__module__ == "pandas.api.typing"
     assert api.typing.DataFrameGroupBy.__module__ == "pandas.api.typing"

Original file line number	Diff line number	Diff line change
`@@ -3,10 +3,12 @@`
`3`	`3`	`)`
`4`	`4`
`5`	`5`	`from pandas.compat._optional import import_optional_dependency`
	`6`	`+from pandas.util._decorators import set_module`
`6`	`7`
`7`	`8`	`from pandas import DataFrame`
`8`	`9`
`9`	`10`
	`11`	`+@set_module("pandas")`
`10`	`12`	`def read_iceberg(`
`11`	`13`	`table_identifier: str,`
`12`	`14`	`catalog_name: str \| None = None,`