Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/20137#discussion_r159582570
--- Diff: python/pyspark/sql/catalog.py ---
@@ -255,9 +255,26 @@ def registerFunction(self, name, f,
returnType=StringType()):
>>> _ = spark.udf.register("stringLengthInt", len, IntegerType())
>>> spark.sql("SELECT stringLengthInt('test')").collect()
[Row(stringLengthInt(test)=4)]
+
+ >>> import random
+ >>> from pyspark.sql.functions import udf
+ >>> from pyspark.sql.types import IntegerType, StringType
+ >>> random_udf = udf(lambda: random.randint(0, 100),
IntegerType()).asNondeterministic()
+ >>> newRandom_udf = spark.catalog.registerFunction("random_udf",
random_udf, StringType())
+ >>> spark.sql("SELECT random_udf()").collect() # doctest: +SKIP
+ [Row(random_udf()=u'82')]
+ >>> spark.range(1).select(newRandom_udf()).collect() # doctest:
+SKIP
+ [Row(random_udf()=u'62')]
"""
- udf = UserDefinedFunction(f, returnType=returnType, name=name,
- evalType=PythonEvalType.SQL_BATCHED_UDF)
+
+ # This is to check whether the input function is a wrapped/native
UserDefinedFunction
+ if hasattr(f, 'asNondeterministic'):
+ udf = UserDefinedFunction(f.func, returnType=returnType,
name=name,
+
evalType=PythonEvalType.SQL_BATCHED_UDF,
--- End diff --
cc @ueshin @icexelloss , shall we support register pandas UDF here too?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
