Skip to content
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

Jump to bottom

String dtype: implement object-dtype based StringArray variant with NumPy semantics #58451

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
+242 −76
Open

String dtype: implement object-dtype based StringArray variant with NumPy semantics #58451

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
63a7fc5
String dtype: implement object-dtype based StringArray variant with N…
jorisvandenbossche Apr 27, 2024
0eee625
fix constructor to not convert to NA
jorisvandenbossche Apr 27, 2024
607b95e
fix typing
jorisvandenbossche Apr 27, 2024
bca157d
improve logic in str_map
jorisvandenbossche Apr 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion pandas/_libs/lib.pyx
View file
Open in desktop
Expand Up @@ -2692,7 +2692,7 @@ def maybe_convert_objects(ndarray[object] objects,
if using_pyarrow_string_dtype() and is_string_array(objects, skipna=True):
from pandas.core.arrays.string_ import StringDtype

dtype = StringDtype(storage="pyarrow_numpy")
dtype = StringDtype()
Copy link
Member Author

Choose a reason for hiding this comment

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

There are a bunch more of such changes needed to update the code paths behind if using_pyarrow_string_dtype() (which is essentially future.infer_string = True) to properly handle the case without pyarrow installed. But given that this is not needed to actually get the tests passing (we are not testing with infer_strings enabled), would prefer keeping this for a follow-up PR.

return dtype.construct_array_type()._from_sequence(objects, dtype=dtype)

elif convert_to_nullable_dtype and is_string_array(objects, skipna=True):
Expand Down
10 changes: 10 additions & 0 deletions pandas/_testing/asserters.py
View file
Open in desktop
Expand Up @@ -805,6 +805,16 @@ def assert_extension_array_equal(
left_na, right_na, obj=f"{obj} NA mask", index_values=index_values
)

# Specifically for StringArrayNumpySemantics, validate here we have a valid array
if isinstance(left.dtype, StringDtype) and left.dtype.storage == "python_numpy":
assert np.all(
[np.isnan(val) for val in left._ndarray[left_na]] # type: ignore[attr-defined]
), "wrong missing value sentinels"
Comment on lines +808 to +812
Copy link
Member Author

Choose a reason for hiding this comment

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

This is a bit a custom check (and we don't do anything similarly for other types), but given I initially overlooked a case where we were creating string arrays with the wrong missing value sentinel because the tests don't actually catch that (two arrays with different missing value sentinels still pass as equal in case of EAs), I would prefer keeping this in at least on the short term.

if isinstance(right.dtype, StringDtype) and right.dtype.storage == "python_numpy":
assert np.all(
[np.isnan(val) for val in right._ndarray[right_na]] # type: ignore[attr-defined]
), "wrong missing value sentinels"

left_valid = left[~left_na].to_numpy(dtype=object)
right_valid = right[~right_na].to_numpy(dtype=object)
if check_exact:
Expand Down
2 changes: 2 additions & 0 deletions pandas/compat/__init__.py
View file
Open in desktop
Expand Up @@ -26,6 +26,7 @@
import pandas.compat.compressors
from pandas.compat.numpy import is_numpy_dev
from pandas.compat.pyarrow import (
HAS_PYARROW,
pa_version_under10p1,
pa_version_under11p0,
pa_version_under13p0,
Expand Down Expand Up @@ -189,6 +190,7 @@ def get_bz2_file() -> type[pandas.compat.compressors.BZ2File]:
"pa_version_under14p0",
"pa_version_under14p1",
"pa_version_under16p0",
"HAS_PYARROW",
"IS64",
"ISMUSL",
"PY310",
Expand Down
2 changes: 2 additions & 0 deletions pandas/compat/pyarrow.py
View file
Open in desktop
Expand Up @@ -16,6 +16,7 @@
pa_version_under14p1 = _palv < Version("14.0.1")
pa_version_under15p0 = _palv < Version("15.0.0")
pa_version_under16p0 = _palv < Version("16.0.0")
HAS_PYARROW = True
except ImportError:
pa_version_under10p1 = True
pa_version_under11p0 = True
Expand All @@ -25,3 +26,4 @@
pa_version_under14p1 = True
pa_version_under15p0 = True
pa_version_under16p0 = True
HAS_PYARROW = False
2 changes: 2 additions & 0 deletions pandas/conftest.py
View file
Open in desktop
Expand Up @@ -1292,6 +1292,7 @@ def nullable_string_dtype(request):
@pytest.fixture(
params=[
"python",
"python_numpy",
pytest.param("pyarrow", marks=td.skip_if_no("pyarrow")),
pytest.param("pyarrow_numpy", marks=td.skip_if_no("pyarrow")),
]
Expand Down Expand Up @@ -1353,6 +1354,7 @@ def object_dtype(request):
params=[
"object",
"string[python]",
"string[python_numpy]",
pytest.param("string[pyarrow]", marks=td.skip_if_no("pyarrow")),
pytest.param("string[pyarrow_numpy]", marks=td.skip_if_no("pyarrow")),
]
Expand Down