Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/19884#discussion_r158211101
--- Diff: python/pyspark/sql/functions.py ---
@@ -2141,22 +2141,23 @@ def pandas_udf(f=None, returnType=None,
functionType=None):
>>> from pyspark.sql.functions import pandas_udf, PandasUDFType
>>> from pyspark.sql.types import IntegerType, StringType
- >>> slen = pandas_udf(lambda s: s.str.len(), IntegerType())
- >>> @pandas_udf(StringType())
+ >>> slen = pandas_udf(lambda s: s.str.len(), IntegerType()) #
doctest: +SKIP
+ >>> @pandas_udf(StringType()) # doctest: +SKIP
... def to_upper(s):
... return s.str.upper()
...
- >>> @pandas_udf("integer", PandasUDFType.SCALAR)
+ >>> @pandas_udf("integer", PandasUDFType.SCALAR) # doctest: +SKIP
... def add_one(x):
... return x + 1
...
- >>> df = spark.createDataFrame([(1, "John Doe", 21)], ("id",
"name", "age"))
+ >>> df = spark.createDataFrame([(1, "John Doe", 21)],
+ ... ("id", "name", "age")) # doctest:
+SKIP
>>> df.select(slen("name").alias("slen(name)"), to_upper("name"),
add_one("age")) \\
... .show() # doctest: +SKIP
+----------+--------------+------------+
|slen(name)|to_upper(name)|add_one(age)|
+----------+--------------+------------+
- | 8| JOHN DOE| 22|
+ | 8| JOHN| 22|
--- End diff --
nit: we should revert this too
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
