Skip to content

ARROW-9407: [Python] Recognize more pandas null sentinels in sequence type inference when converting to Arrow #7714

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

Closed
wesm wants to merge 1 commit into from
Closed

ARROW-9407: [Python] Recognize more pandas null sentinels in sequence type inference when converting to Arrow #7714

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 7 additions & 1 deletion cpp/src/arrow/python/inference.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -320,7 +320,7 @@ class TypeInferrer {
Status Visit(PyObject* obj, bool* keep_going) {
++total_count_;

if (obj == Py_None || (pandas_null_sentinels_ && internal::PyFloat_IsNaN(obj))) {
if (obj == Py_None || (pandas_null_sentinels_ && internal::PandasObjectIsNull(obj))) {
++none_count_;
} else if (PyBool_Check(obj)) {
++bool_count_;
Expand Down Expand Up @@ -626,6 +626,12 @@ class TypeInferrer {
// Non-exhaustive type inference
Status InferArrowType(PyObject* obj, PyObject* mask, bool pandas_null_sentinels,
std::shared_ptr<DataType>* out_type) {
if (pandas_null_sentinels) {
// ARROW-842: If pandas is not installed then null checks will be less
// comprehensive, but that is okay.
internal::InitPandasStaticData();
}

TypeInferrer inferrer(pandas_null_sentinels);
RETURN_NOT_OK(inferrer.VisitSequence(obj, mask));
RETURN_NOT_OK(inferrer.GetType(out_type));
Expand Down
10 changes: 7 additions & 3 deletions python/pyarrow/tests/test_pandas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1205,17 +1205,21 @@ def test_date_objects_typed(self):
tm.assert_frame_equal(table_pandas_objects,
expected_pandas_objects)

def test_object_null_values(self):
def test_pandas_null_values(self):
# ARROW-842
NA = getattr(pd, 'NA', None)
values = np.array([datetime(2000, 1, 1), pd.NaT, NA], dtype=object)
pd_NA = getattr(pd, 'NA', None)
values = np.array([datetime(2000, 1, 1), pd.NaT, pd_NA], dtype=object)
values_with_none = np.array([datetime(2000, 1, 1), None, None],
dtype=object)
result = pa.array(values, from_pandas=True)
expected = pa.array(values_with_none, from_pandas=True)
assert result.equals(expected)
assert result.null_count == 2

# ARROW-9407
assert pa.array([pd.NaT], from_pandas=True).type == pa.null()
assert pa.array([pd_NA], from_pandas=True).type == pa.null()

def test_dates_from_integers(self):
t1 = pa.date32()
t2 = pa.date64()
Expand Down