Skip to content

[SPARK-58553][PS] Use native Spark functions for NumPy fmax and fmin #57758

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 1 commit into
base: master
Choose a base branch
from
+21 −2
Open

[SPARK-58553][PS] Use native Spark functions for NumPy fmax and fmin #57758

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
7 changes: 5 additions & 2 deletions python/pyspark/pandas/numpy_compat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,8 +111,11 @@
"floor_divide": pandas_udf( # type: ignore[call-overload]
lambda s1, s2: np.floor_divide(s1, s2), DoubleType()
),
"fmax": pandas_udf(lambda s1, s2: np.fmax(s1, s2), DoubleType()), # type: ignore[call-overload]
"fmin": pandas_udf(lambda s1, s2: np.fmin(s1, s2), DoubleType()), # type: ignore[call-overload]
"fmax": lambda c1, c2: F.when(F.isnan(c1.cast("double")), c2)
.when(F.isnan(c2.cast("double")), c1)
.otherwise(F.greatest(c1, c2))
.cast("double"),
"fmin": lambda c1, c2: F.least(c1, c2).cast("double"),
"fmod": pandas_udf(lambda s1, s2: np.fmod(s1, s2), DoubleType()), # type: ignore[call-overload]
"gcd": pandas_udf(lambda s1, s2: np.gcd(s1, s2), DoubleType()), # type: ignore[call-overload]
"heaviside": pandas_udf( # type: ignore[call-overload]
Expand Down
16 changes: 16 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 @@ -171,6 +171,22 @@ def test_np_float_power(self):
almost=True,
)

def test_np_fmax_fmin(self):
for pdf in (
pd.DataFrame({"x1": [-2, -1, 0, 1, 2], "x2": [2, 1, 0, -1, -2]}),
pd.DataFrame(
{
"x1": [np.nan, 2.0, np.nan, -np.inf, -2.0, -0.0, 0.0, 2.0, np.inf],
"x2": [2.0, np.nan, np.nan, np.inf, -np.inf, 0.0, -0.0, np.inf, -np.inf],
}
),
):
psdf = ps.from_pandas(pdf)
for np_func in (np.fmax, np.fmin):
result = np_func(psdf.x1, psdf.x2)
expected = np_func(pdf.x1, pdf.x2)
self.assert_eq(result, expected, 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