From ce92a9c18f033ac9fa2f12143fab00a90e0f4577 Mon Sep 17 00:00:00 2001 From: Sandy Ryza Date: Thu, 12 Jun 2014 08:14:25 -0700 Subject: SPARK-554. Add aggregateByKey. Author: Sandy Ryza Closes #705 from sryza/sandy-spark-554 and squashes the following commits: 2302b8f [Sandy Ryza] Add MIMA exclude f52e0ad [Sandy Ryza] Fix Python tests for real 2f3afa3 [Sandy Ryza] Fix Python test 0b735e9 [Sandy Ryza] Fix line lengths ae56746 [Sandy Ryza] Fix doc (replace T with V) c2be415 [Sandy Ryza] Java and Python aggregateByKey 23bf400 [Sandy Ryza] SPARK-554. Add aggregateByKey. --- python/pyspark/tests.py | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'python/pyspark/tests.py') diff --git a/python/pyspark/tests.py b/python/pyspark/tests.py index 184ee810b8..c15bb45775 100644 --- a/python/pyspark/tests.py +++ b/python/pyspark/tests.py @@ -188,6 +188,21 @@ class TestRDDFunctions(PySparkTestCase): os.unlink(tempFile.name) self.assertRaises(Exception, lambda: filtered_data.count()) + def testAggregateByKey(self): + data = self.sc.parallelize([(1, 1), (1, 1), (3, 2), (5, 1), (5, 3)], 2) + def seqOp(x, y): + x.add(y) + return x + + def combOp(x, y): + x |= y + return x + + sets = dict(data.aggregateByKey(set(), seqOp, combOp).collect()) + self.assertEqual(3, len(sets)) + self.assertEqual(set([1]), sets[1]) + self.assertEqual(set([2]), sets[3]) + self.assertEqual(set([1, 3]), sets[5]) class TestIO(PySparkTestCase): -- cgit v1.2.3