Skip to content

TST (string dtype): fix and clean up arrow roundtrip tests #59678

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
merged 3 commits into from
Sep 2, 2024
Merged

TST (string dtype): fix and clean up arrow roundtrip tests #59678

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f6a2a5d
TST (string dtype): fix and clean up arrow roundtrip tests
jorisvandenbossche Aug 31, 2024
af81bb1
Merge remote-tracking branch 'upstream/main' into string-dtype-tests-…
jorisvandenbossche Sep 2, 2024
30c41f3
fix using_infer_string
jorisvandenbossche Sep 2, 2024
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
11 changes: 3 additions & 8 deletions pandas/tests/arrays/masked/test_arrow_compat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,12 @@
import numpy as np
import pytest

from pandas._config import using_string_dtype

import pandas as pd
import pandas._testing as tm

pytestmark = [
pytest.mark.filterwarnings(
"ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
),
pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False),
]
pytestmark = pytest.mark.filterwarnings(
"ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
)


pa = pytest.importorskip("pyarrow")
Expand Down
14 changes: 10 additions & 4 deletions pandas/tests/arrays/string_/test_string.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -522,7 +522,6 @@ def test_arrow_array(dtype):
assert arr.equals(expected)


@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
@pytest.mark.filterwarnings("ignore:Passing a BlockManager:DeprecationWarning")
def test_arrow_roundtrip(dtype, string_storage, using_infer_string):
# roundtrip possible from arrow 1.0.0
Expand All @@ -541,13 +540,16 @@ def test_arrow_roundtrip(dtype, string_storage, using_infer_string):
assert result["a"].dtype == "object"
else:
assert isinstance(result["a"].dtype, pd.StringDtype)
expected = df.astype(f"string[{string_storage}]")
expected = df.astype(pd.StringDtype(string_storage, na_value=dtype.na_value))
if using_infer_string:
expected.columns = expected.columns.astype(
pd.StringDtype(string_storage, na_value=np.nan)
)
tm.assert_frame_equal(result, expected)
# ensure the missing value is represented by NA and not np.nan or None
assert result.loc[2, "a"] is result["a"].dtype.na_value


@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
@pytest.mark.filterwarnings("ignore:Passing a BlockManager:DeprecationWarning")
def test_arrow_load_from_zero_chunks(dtype, string_storage, using_infer_string):
# GH-41040
Expand All @@ -569,7 +571,11 @@ def test_arrow_load_from_zero_chunks(dtype, string_storage, using_infer_string):
assert result["a"].dtype == "object"
else:
assert isinstance(result["a"].dtype, pd.StringDtype)
expected = df.astype(f"string[{string_storage}]")
expected = df.astype(pd.StringDtype(string_storage, na_value=dtype.na_value))
if using_infer_string:
expected.columns = expected.columns.astype(
pd.StringDtype(string_storage, na_value=np.nan)
)
tm.assert_frame_equal(result, expected)


Expand Down
Loading