Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/19872#discussion_r161495918
--- Diff: python/pyspark/sql/tests.py ---
@@ -4279,6 +4272,386 @@ def test_unsupported_types(self):
df.groupby('id').apply(f).collect()
+@unittest.skipIf(not _have_pandas or not _have_arrow, "Pandas or Arrow not
installed")
+class GroupbyAggTests(ReusedSQLTestCase):
+
+ @property
+ def data(self):
+ from pyspark.sql.functions import array, explode, col, lit
+ return self.spark.range(10).toDF('id') \
+ .withColumn("vs", array([lit(i * 1.0) + col('id') for i in
range(20, 30)])) \
+ .withColumn("v", explode(col('vs'))) \
+ .drop('vs') \
+ .withColumn('w', lit(1.0))
+
+ @property
+ def plus_one(self):
--- End diff --
Could we add a prefix to note the differences like `udf`, `padnas_udf` and
`functionType`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
