diff options
Diffstat (limited to 'python/pyspark/tests.py')
| -rw-r--r-- | python/pyspark/tests.py | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/python/pyspark/tests.py b/python/pyspark/tests.py index 3e7040eade..f1a75cbff5 100644 --- a/python/pyspark/tests.py +++ b/python/pyspark/tests.py @@ -404,6 +404,22 @@ class TestRDDFunctions(PySparkTestCase): 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)) + def test_histogram(self): # empty rdd = self.sc.parallelize([]) |