Skip to content

[SPARK-58464][PS] Use native functions for NumPy bitwise shifts #57667

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
zhengruifeng wants to merge 2 commits into
base: master
Choose a base branch
from
+25 −6
Open

[SPARK-58464][PS] Use native functions for NumPy bitwise shifts #57667

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3932838
[SPARK-58249][PS][FOLLOWUP] Use native functions for NumPy bitwise sh…
zhengruifeng Jul 31, 2026
1debcd7
[SPARK-58464][PS] Fix bitwise shift formatting
zhengruifeng Jul 31, 2026
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
16 changes: 10 additions & 6 deletions python/pyspark/pandas/numpy_compat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@

from pyspark.sql import functions as F
from pyspark.sql.pandas.functions import pandas_udf
from pyspark.sql.types import DoubleType, LongType, BooleanType
from pyspark.sql.types import DoubleType, BooleanType
from pyspark.pandas.base import IndexOpsMixin

unary_np_spark_mappings = {
Expand Down Expand Up @@ -107,8 +107,10 @@
"ldexp": pandas_udf( # type: ignore[call-overload]
lambda s1, s2: np.ldexp(s1, s2), DoubleType()
),
"left_shift": pandas_udf( # type: ignore[call-overload]
lambda s1, s2: np.left_shift(s1, s2), LongType()
# F.shiftleft accepts literal counts only; call_function also accepts a column.
# NumPy returns zero for counts outside an int64's bit width, unlike JVM shifts.
"left_shift": lambda c1, c2: F.when((c2 < 0) | (c2 >= 64), F.lit(0)).otherwise(
F.call_function("shiftleft", c1, c2)
),
"logaddexp": pandas_udf( # type: ignore[call-overload]
lambda s1, s2: np.logaddexp(s1, s2), DoubleType()
Expand All @@ -129,9 +131,11 @@
"nextafter": pandas_udf( # type: ignore[call-overload]
lambda s1, s2: np.nextafter(s1, s2), DoubleType()
),
"right_shift": pandas_udf( # type: ignore[call-overload]
lambda s1, s2: np.right_shift(s1, s2), LongType()
),
# F.shiftright accepts literal counts only; call_function also accepts a column.
# NumPy sign-extends counts outside an int64's bit width, unlike JVM shifts.
"right_shift": lambda c1, c2: F.when(
(c2 < 0) | (c2 >= 64), F.call_function("shiftright", c1, F.lit(63))
).otherwise(F.call_function("shiftright", c1, c2)),
}


Expand Down
15 changes: 15 additions & 0 deletions python/pyspark/pandas/tests/test_numpy_compat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,6 +115,21 @@ def test_np_math_functions(self):

self.assert_eq(np_func(psdf.a), np_func(pdf.a), almost=True)

def test_np_bitwise_shift_functions(self):
pdf = pd.DataFrame(
{
"value": [np.iinfo(np.int64).min, -2, -1, 0, 1, 2, np.iinfo(np.int64).max],
"bits": [-1, 0, 1, 63, 64, 65, 2],
}
)
psdf = ps.from_pandas(pdf)

for np_func in (np.left_shift, np.right_shift):
with self.subTest(name=np_func.__name__):
self.assert_eq(
np_func(psdf.value, psdf.bits), np_func(pdf.value, pdf.bits), almost=True
)

def test_np_spark_compat_series(self):
from pyspark.pandas.numpy_compat import unary_np_spark_mappings, binary_np_spark_mappings

Expand Down