Fix #849: Update converters type in read_excel for better Pyright compatibility (#1297)

* Add files via upload

* Add files via upload

* Delete tests/test_excel_converters.py

Remove redundant test_excel_converters.py after moving test to test_io.py

* Move converter test to test_io.py

Add test_converters_partial() to test_io.py for read_excel converters

* Used ensure_clean()

* Update test_io.py black formatting

* Update test_io.py

* Update test_io.py

---------

Co-authored-by: Loic Diridollou <[email protected]>

Author: Sachi-Parashar

pandas-stubs/io/excel/_base.pyi

@@ -54,7 +54,7 @@ def read_excel(
     usecols: str | UsecolsArgType = ...,
     dtype: str | Dtype | Mapping[str, str | Dtype] | None = ...,
     engine: ExcelReadEngine | None = ...,
-    converters: Mapping[int | str, Callable[[object], object]] | None = ...,
+    converters: Mapping[int | str, Callable[[Any], Any]] | None = ...,
     true_values: Iterable[Hashable] | None = ...,
     false_values: Iterable[Hashable] | None = ...,
     skiprows: int | Sequence[int] | Callable[[object], bool] | None = ...,
@@ -97,7 +97,7 @@ def read_excel(
     usecols: str | UsecolsArgType = ...,
     dtype: str | Dtype | Mapping[str, str | Dtype] | None = ...,
     engine: ExcelReadEngine | None = ...,
-    converters: Mapping[int | str, Callable[[object], object]] | None = ...,
+    converters: Mapping[int | str, Callable[[Any], Any]] | None = ...,
     true_values: Iterable[Hashable] | None = ...,
     false_values: Iterable[Hashable] | None = ...,
     skiprows: int | Sequence[int] | Callable[[object], bool] | None = ...,
@@ -141,7 +141,7 @@ def read_excel(  # type: ignore[overload-cannot-match]
     usecols: str | UsecolsArgType = ...,
     dtype: str | Dtype | Mapping[str, str | Dtype] | None = ...,
     engine: ExcelReadEngine | None = ...,
-    converters: Mapping[int | str, Callable[[object], object]] | None = ...,
+    converters: Mapping[int | str, Callable[[Any], Any]] | None = ...,
     true_values: Iterable[Hashable] | None = ...,
     false_values: Iterable[Hashable] | None = ...,
     skiprows: int | Sequence[int] | Callable[[object], bool] | None = ...,
@@ -184,7 +184,7 @@ def read_excel(
     usecols: str | UsecolsArgType = ...,
     dtype: str | Dtype | Mapping[str, str | Dtype] | None = ...,
     engine: ExcelReadEngine | None = ...,
-    converters: Mapping[int | str, Callable[[object], object]] | None = ...,
+    converters: Mapping[int | str, Callable[[Any], Any]] | None = ...,
     true_values: Iterable[Hashable] | None = ...,
     false_values: Iterable[Hashable] | None = ...,
     skiprows: int | Sequence[int] | Callable[[object], bool] | None = ...,
@@ -264,7 +264,7 @@ class ExcelFile:
         names: ListLikeHashable | None = ...,
         index_col: int | Sequence[int] | None = ...,
         usecols: str | UsecolsArgType = ...,
-        converters: dict[int | str, Callable[[object], object]] | None = ...,
+        converters: dict[int | str, Callable[[Any], Any]] | None = ...,
         true_values: Iterable[Hashable] | None = ...,
         false_values: Iterable[Hashable] | None = ...,
         skiprows: int | Sequence[int] | Callable[[object], bool] | None = ...,
@@ -292,7 +292,7 @@ class ExcelFile:
         names: ListLikeHashable | None = ...,
         index_col: int | Sequence[int] | None = ...,
         usecols: str | UsecolsArgType = ...,
-        converters: dict[int | str, Callable[[object], object]] | None = ...,
+        converters: dict[int | str, Callable[[Any], Any]] | None = ...,
         true_values: Iterable[Hashable] | None = ...,
         false_values: Iterable[Hashable] | None = ...,
         skiprows: int | Sequence[int] | Callable[[object], bool] | None = ...,

tests/test_io.py

@@ -1,6 +1,7 @@
 from collections import defaultdict
 from collections.abc import Generator
 import csv
+from functools import partial
 import io
 import os.path
 import pathlib
@@ -1787,3 +1788,14 @@ def test_read_json_engine() -> None:
         pd.read_json(dd, lines=False, engine="pyarrow")  # type: ignore[call-overload] # pyright: ignore[reportArgumentType, reportCallIssue]
         pd.read_json(io.StringIO(data), engine="pyarrow")  # type: ignore[call-overload] # pyright: ignore[reportArgumentType]
         pd.read_json(io.StringIO(data), lines=True, engine="pyarrow")  # type: ignore[call-overload] # pyright: ignore[reportArgumentType, reportCallIssue]
+
+
+def test_converters_partial() -> None:
+    df = pd.DataFrame({"field_1": ["2020-01-01", "not a date"]})
+    partial_func = partial(pd.to_datetime, errors="coerce")
+
+    with ensure_clean(".xlsx") as path:
+        check(assert_type(df.to_excel(path, index=False), None), type(None))
+
+        result = pd.read_excel(path, converters={"field_1": partial_func})
+        check(assert_type(result, pd.DataFrame), pd.DataFrame)