Github user icexelloss commented on a diff in the pull request:
https://github.com/apache/spark/pull/21082#discussion_r190061061
--- Diff: python/pyspark/sql/tests.py ---
@@ -5181,6 +5190,235 @@ def test_invalid_args(self):
'mixture.*aggregate function.*group aggregate pandas
UDF'):
df.groupby(df.id).agg(mean_udf(df.v), mean(df.v)).collect()
+
+@unittest.skipIf(
+ not _have_pandas or not _have_pyarrow,
+ _pandas_requirement_message or _pyarrow_requirement_message)
+class WindowPandasUDFTests(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 python_plus_one(self):
--- End diff --
I agree those should be shared, but let's do it maybe in a separate PR?
Because the refactor will probably touch many test cases and the PR is quite
large already..
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
