Github user holdenk commented on a diff in the pull request:
https://github.com/apache/spark/pull/12135#discussion_r98159741
--- Diff: python/pyspark/sql/tests.py ---
@@ -835,11 +835,20 @@ def test_first_last_ignorenulls(self):
self.assertEqual([Row(a=None, b=1, c=None, d=98)], df3.collect())
def test_approxQuantile(self):
- df = self.sc.parallelize([Row(a=i) for i in range(10)]).toDF()
+ df = self.sc.parallelize([Row(a=i, b=i+10) for i in
range(10)]).toDF()
aq = df.stat.approxQuantile("a", [0.1, 0.5, 0.9], 0.1)
self.assertTrue(isinstance(aq, list))
self.assertEqual(len(aq), 3)
self.assertTrue(all(isinstance(q, float) for q in aq))
+ aqs = df.stat.approxQuantile(["a", "b"], [0.1, 0.5, 0.9], 0.1)
+ self.assertTrue(isinstance(aqs, list))
+ self.assertEqual(len(aqs), 2)
+ self.assertTrue(isinstance(aqs[0], list))
+ self.assertEqual(len(aqs[0]), 3)
+ self.assertTrue(all(isinstance(q, float) for q in aqs[0]))
+ self.assertTrue(isinstance(aqs[1], list))
+ self.assertEqual(len(aqs[1]), 3)
+ self.assertTrue(all(isinstance(q, float) for q in aqs[1]))
--- End diff --
Actually one minor thing on the Python side, since we do check the type and
explicitily throw an error, maybe it would be good to have a test that asserts
we get the error we are expecting ?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
