Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
+38 −25
Open

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

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a0614f3
Add files via upload
Sachi-Parashar Jul 28, 2025
ae5365d
Add files via upload
Sachi-Parashar Jul 28, 2025
2c1b5df
Delete tests/test_excel_converters.py
Sachi-Parashar Jul 29, 2025
288c04d
Move converter test to test_io.py
Sachi-Parashar Jul 29, 2025
19d18ce
Used ensure_clean()
Sachi-Parashar Aug 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions pandas-stubs/io/excel/_base.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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 = ...,
Expand Down Expand Up @@ -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 = ...,
Expand Down Expand Up @@ -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 = ...,
Expand Down Expand Up @@ -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 = ...,
Expand Down Expand Up @@ -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 = ...,
Expand Down Expand Up @@ -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 = ...,
Expand Down
51 changes: 32 additions & 19 deletions tests/test_io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
)

import numpy as np
from functools import partial
import pandas as pd
from pandas import (
DataFrame,
Expand Down Expand Up @@ -304,23 +305,23 @@ def test_sas_bdat() -> None:
path = pathlib.Path(CWD, "data", "airline.sas7bdat")
check(assert_type(read_sas(path), DataFrame), DataFrame)
with check(
assert_type(read_sas(path, iterator=True), Union[SAS7BDATReader, XportReader]),
SAS7BDATReader,
assert_type(read_sas(path, iterator=True), Union[SAS7BDATReader, XportReader]),
SAS7BDATReader,
Comment on lines +308 to +309
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't know why you indented here and elsewhere. Make sure to install the pre-commit and run black

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You can see from the CI that the pre-commit failed because of this

):
pass
with check(
assert_type(read_sas(path, iterator=True, format="sas7bdat"), SAS7BDATReader),
SAS7BDATReader,
assert_type(read_sas(path, iterator=True, format="sas7bdat"), SAS7BDATReader),
SAS7BDATReader,
):
pass
with check(
assert_type(read_sas(path, chunksize=1), Union[SAS7BDATReader, XportReader]),
SAS7BDATReader,
assert_type(read_sas(path, chunksize=1), Union[SAS7BDATReader, XportReader]),
SAS7BDATReader,
):
pass
with check(
assert_type(read_sas(path, chunksize=1, format="sas7bdat"), SAS7BDATReader),
SAS7BDATReader,
assert_type(read_sas(path, chunksize=1, format="sas7bdat"), SAS7BDATReader),
SAS7BDATReader,
):
pass

Expand All @@ -329,23 +330,23 @@ def test_sas_xport() -> None:
path = pathlib.Path(CWD, "data", "SSHSV1_A.xpt")
check(assert_type(read_sas(path), DataFrame), DataFrame)
with check(
assert_type(read_sas(path, iterator=True), Union[SAS7BDATReader, XportReader]),
XportReader,
assert_type(read_sas(path, iterator=True), Union[SAS7BDATReader, XportReader]),
XportReader,
):
pass
with check(
assert_type(read_sas(path, iterator=True, format="xport"), XportReader),
XportReader,
assert_type(read_sas(path, iterator=True, format="xport"), XportReader),
XportReader,
):
pass
with check(
assert_type(read_sas(path, chunksize=1), Union[SAS7BDATReader, XportReader]),
XportReader,
assert_type(read_sas(path, chunksize=1), Union[SAS7BDATReader, XportReader]),
XportReader,
):
pass
with check(
assert_type(read_sas(path, chunksize=1, format="xport"), XportReader),
XportReader,
assert_type(read_sas(path, chunksize=1, format="xport"), XportReader),
XportReader,
):
pass

Expand Down Expand Up @@ -1149,9 +1150,9 @@ def test_excel_reader():
check(assert_type(pd.read_excel(ef), pd.DataFrame), pd.DataFrame)

with pd.ExcelFile(
path_or_buffer=path,
engine="openpyxl",
engine_kwargs={"data_only": True},
path_or_buffer=path,
engine="openpyxl",
engine_kwargs={"data_only": True},
) as ef:
check(assert_type(ef, pd.ExcelFile), pd.ExcelFile)
check(assert_type(pd.read_excel(ef), pd.DataFrame), pd.DataFrame)
Expand Down Expand Up @@ -1792,3 +1793,15 @@ 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)

Loading