harshmotw-db commented on code in PR #48770:
URL: https://github.com/apache/spark/pull/48770#discussion_r1831626706
##########
python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py:
##########
@@ -752,46 +752,87 @@ def check_vectorized_udf_return_scalar(self):
def test_udf_with_variant_input(self):
df = self.spark.range(0, 10).selectExpr("parse_json(cast(id as
string)) v")
- from pyspark.sql.functions import col
- scalar_f = pandas_udf(lambda u: str(u), StringType())
+ scalar_f = pandas_udf(lambda u: u.apply(str), StringType(),
PandasUDFType.SCALAR)
iter_f = pandas_udf(
- lambda it: map(lambda u: str(u), it), StringType(),
PandasUDFType.SCALAR_ITER
+ lambda it: map(lambda u: u.apply(str), it), StringType(),
PandasUDFType.SCALAR_ITER
)
+ expected = [Row(udf="{0}".format(i)) for i in range(10)]
+
for f in [scalar_f, iter_f]:
- with self.assertRaises(AnalysisException) as ae:
- df.select(f(col("v"))).collect()
-
- self.check_error(
- exception=ae.exception,
- errorClass="DATATYPE_MISMATCH.UNSUPPORTED_UDF_INPUT_TYPE",
- messageParameters={
- "sqlExpr": '"<lambda>(v)"',
- "dataType": "VARIANT",
- },
- )
+ result = df.select(f(col("v")).alias("udf")).collect()
+ self.assertEqual(result, expected)
def test_udf_with_variant_output(self):
- # Corresponds to a JSON string of {"a": "b"}.
- returned_variant = VariantVal(bytes([2, 1, 0, 0, 2, 5, 98]), bytes([1,
1, 0, 1, 97]))
- scalar_f = pandas_udf(lambda x: returned_variant, VariantType())
+ scalar_f = pandas_udf(
+ lambda u: u.apply(lambda i: VariantVal(bytes([12, i]), bytes([1,
0, 0]))), VariantType()
+ )
iter_f = pandas_udf(
- lambda it: map(lambda x: returned_variant, it), VariantType(),
PandasUDFType.SCALAR_ITER
+ lambda it: map(lambda u: u.apply(
+ lambda i: VariantVal(bytes([12, i]), bytes([1, 0, 0]))
+ ), it),
+ VariantType(),
+ PandasUDFType.SCALAR_ITER
)
+ expected = [Row(udf=i) for i in range(10)]
Review Comment:
I did add a [nested variant test with chained pandas
UDFs](https://github.com/apache/spark/blob/876d5cab7ffeb55b86516350af23aca8cae35afe/python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py#L809)
but I should also add tests for isolated UDFs.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
