Skip to content

BUG: Fix regression in to_hdf with MultiIndex and StringDtype (GH#63412) #63414

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

Merged
mroeschke merged 6 commits into from
Dec 18, 2025
+13 −19
Merged

BUG: Fix regression in to_hdf with MultiIndex and StringDtype (GH#63412) #63414

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
f75274a
TST: Add regression test for GH#63412
zacharym-collins Dec 18, 2025
c80c8ef
STY: apply ruff formatting
zacharym-collins Dec 18, 2025
d0c02fb
BUG: Fix regression in to_hdf with MultiIndex and StringDtype (GH#63412)
zacharym-collins Dec 18, 2025
2c79460
TST: Enable HDF5 tests for StringDtype
zacharym-collins Dec 18, 2025
37a3e8e
REF: Simplify StringDtype check in write_multi_index (GH#63414)
zacharym-collins Dec 18, 2025
c2b8a26
REF: Simplify StringDtype check to allow fallthrough
zacharym-collins Dec 18, 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
10 changes: 7 additions & 3 deletions pandas/io/pytables.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3148,9 +3148,13 @@ def write_multi_index(self, key: str, index: MultiIndex) -> None:
):
# write the level
if isinstance(lev.dtype, ExtensionDtype):
raise NotImplementedError(
"Saving a MultiIndex with an extension dtype is not supported."
)
# GH 63412
if isinstance(lev.dtype, StringDtype):
lev = lev.astype(object)
Copy link
Member

@mroeschke mroeschke Dec 18, 2025

Choose a reason for hiding this comment

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

If you replace this with pass, does _convert_index below already convert this data correctly without the astype?

Copy link
Contributor Author

@zacharym-collins zacharym-collins Dec 18, 2025

Choose a reason for hiding this comment

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

Yes it does. I'll make the modification.

Copy link
Contributor Author

@zacharym-collins zacharym-collins Dec 18, 2025

Choose a reason for hiding this comment

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

@mroeschke Checks passed. I used a different implementation to avoid the two if blocks, I think this is better style, unless you disagree.

else:
raise NotImplementedError(
"Saving a MultiIndex with an extension dtype is not supported."
)
level_key = f"{key}_level{i}"
conv_level = _convert_index(level_key, lev, self.encoding, self.errors)
self.write_array(level_key, conv_level.values)
Expand Down
6 changes: 0 additions & 6 deletions pandas/tests/io/pytables/test_put.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -314,12 +314,6 @@ def test_column_multiindex(tmp_path, setup_path, using_infer_string):

path = tmp_path / setup_path
with HDFStore(path) as store:
if using_infer_string:
# TODO(infer_string) make this work for string dtype
msg = "Saving a MultiIndex with an extension dtype is not supported."
with pytest.raises(NotImplementedError, match=msg):
store.put("df", df)
return
store.put("df", df)
tm.assert_frame_equal(
store["df"], expected, check_index_type=True, check_column_type=True
Expand Down
6 changes: 0 additions & 6 deletions pandas/tests/io/pytables/test_read.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,12 +181,6 @@ def test_read_hdf_open_store(tmp_path, setup_path, using_infer_string):
df = df.set_index(keys="E", append=True)

path = tmp_path / setup_path
if using_infer_string:
# TODO(infer_string) make this work for string dtype
msg = "Saving a MultiIndex with an extension dtype is not supported."
with pytest.raises(NotImplementedError, match=msg):
df.to_hdf(path, key="df", mode="w")
return
df.to_hdf(path, key="df", mode="w")
direct = read_hdf(path, "df")
with HDFStore(path, mode="r") as store:
Expand Down
6 changes: 0 additions & 6 deletions pandas/tests/io/pytables/test_round_trip.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -434,12 +434,6 @@ def test_store_hierarchical(
):
frame = multiindex_dataframe_random_data

if using_infer_string:
# TODO(infer_string) make this work for string dtype
msg = "Saving a MultiIndex with an extension dtype is not supported."
with pytest.raises(NotImplementedError, match=msg):
_check_roundtrip(frame, tm.assert_frame_equal, path=temp_file)
return
_check_roundtrip(frame, tm.assert_frame_equal, path=temp_file)
_check_roundtrip(frame.T, tm.assert_frame_equal, path=temp_file)
_check_roundtrip(frame["A"], tm.assert_series_equal, path=temp_file)
Expand Down
10 changes: 10 additions & 0 deletions pandas/tests/io/pytables/test_store.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1129,3 +1129,13 @@ def test_select_categorical_string_columns(tmp_path, model):
result = store.select("df", "modelId == model")
expected = df[df["modelId"] == model]
tm.assert_frame_equal(result, expected)


def test_to_hdf_multiindex_string_dtype_crash(tmp_path):
# GH#63412
path = tmp_path / "test.h5"
index = MultiIndex.from_tuples([("a", "x"), ("b", "y")], names=["level1", "level2"])
df = DataFrame({"value": [1, 2]}, index=index)
df.to_hdf(path, key="test")
result = read_hdf(path, key="test")
tm.assert_frame_equal(df, result, check_dtype=False)
Loading