Github user ueshin commented on a diff in the pull request:
https://github.com/apache/spark/pull/20217#discussion_r160873545
--- Diff: python/pyspark/sql/context.py ---
@@ -203,18 +203,46 @@ def registerFunction(self, name, f,
returnType=StringType()):
>>> _ = sqlContext.udf.register("stringLengthInt", lambda x:
len(x), IntegerType())
>>> sqlContext.sql("SELECT stringLengthInt('test')").collect()
[Row(stringLengthInt(test)=4)]
+ """
+ return self.sparkSession.catalog.registerFunction(name, f,
returnType)
+
+ @ignore_unicode_prefix
+ @since(2.3)
+ def registerUDF(self, name, f):
+ """Registers a :class:`UserDefinedFunction`. The registered UDF
can be used in SQL
+ statement.
+
+ :param name: name of the UDF
+ :param f: a wrapped/native UserDefinedFunction. The UDF can be
either row-at-a-time or
+ scalar vectorized. Grouped vectorized UDFs are not
supported.
+ :return: a wrapped :class:`UserDefinedFunction`
+
+ >>> from pyspark.sql.types import IntegerType
+ >>> from pyspark.sql.functions import udf
+ >>> slen = udf(lambda s: len(s), IntegerType())
+ >>> _ = sqlContext.udf.registerUDF("slen", slen)
+ >>> sqlContext.sql("SELECT slen('test')").collect()
+ [Row(slen(test)=4)]
>>> import random
>>> from pyspark.sql.functions import udf
- >>> from pyspark.sql.types import IntegerType, StringType
+ >>> from pyspark.sql.types import IntegerType
>>> random_udf = udf(lambda: random.randint(0, 100),
IntegerType()).asNondeterministic()
- >>> newRandom_udf = sqlContext.registerFunction("random_udf",
random_udf, StringType())
+ >>> newRandom_udf = sqlContext.registerUDF("random_udf",
random_udf)
>>> sqlContext.sql("SELECT random_udf()").collect() # doctest:
+SKIP
- [Row(random_udf()=u'82')]
+ [Row(random_udf()=82)]
>>> sqlContext.range(1).select(newRandom_udf()).collect() #
doctest: +SKIP
- [Row(random_udf()=u'62')]
+ [Row(random_udf()=62)]
+
+ >>> from pyspark.sql.functions import pandas_udf, PandasUDFType
+ >>> @pandas_udf("integer", PandasUDFType.SCALAR) # doctest: +SKIP
+ ... def add_one(x):
+ ... return x + 1
+ ...
+ >>> _ = sqlContext.udf.registerUDF("add_one", add_one) # doctest:
+SKIP
+ >>> sqlContext.sql("SELECT add_one(id) FROM range(10)").collect()
# doctest: +SKIP
--- End diff --
ditto.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
