Github user davies commented on a diff in the pull request: https://github.com/apache/spark/pull/2274#discussion_r17199169 --- Diff: python/pyspark/tests.py --- @@ -405,22 +404,6 @@ def test_zip_with_different_number_of_items(self): self.assertEquals(a.count(), b.count()) self.assertRaises(Exception, lambda: a.zip(b).count()) - def test_count_approx_distinct(self): - rdd = self.sc.parallelize(range(1000)) - self.assertTrue(950 < rdd.countApproxDistinct(0.04) < 1050) - self.assertTrue(950 < rdd.map(float).countApproxDistinct(0.04) < 1050) - self.assertTrue(950 < rdd.map(str).countApproxDistinct(0.04) < 1050) - self.assertTrue(950 < rdd.map(lambda x: (x, -x)).countApproxDistinct(0.04) < 1050) - - rdd = self.sc.parallelize([i % 20 for i in range(1000)], 7) - self.assertTrue(18 < rdd.countApproxDistinct() < 22) - self.assertTrue(18 < rdd.map(float).countApproxDistinct() < 22) - self.assertTrue(18 < rdd.map(str).countApproxDistinct() < 22) - self.assertTrue(18 < rdd.map(lambda x: (x, -x)).countApproxDistinct() < 22) - - self.assertRaises(ValueError, lambda: rdd.countApproxDistinct(0.00000001)) - self.assertRaises(ValueError, lambda: rdd.countApproxDistinct(0.5)) - --- End diff -- These are removed by accident during merging?
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org