From 3b0babad1f0856ee16f9d58e1ead30779a4a6310 Mon Sep 17 00:00:00 2001 From: Takuya UESHIN Date: Tue, 27 May 2014 14:55:23 -0700 Subject: [SPARK-1915] [SQL] AverageFunction should not count if the evaluated value is null. Average values are difference between the calculation is done partially or not partially. Because `AverageFunction` (in not-partially calculation) counts even if the evaluated value is null. Author: Takuya UESHIN Closes #862 from ueshin/issues/SPARK-1915 and squashes the following commits: b1ff3c0 [Takuya UESHIN] Modify AverageFunction not to count if the evaluated value is null. --- .../src/test/scala/org/apache/spark/sql/DslQuerySuite.scala | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'sql/core') diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DslQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DslQuerySuite.scala index 8197e8a18d..fb599e1e01 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DslQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DslQuerySuite.scala @@ -115,6 +115,16 @@ class DslQuerySuite extends QueryTest { 2.0) } + test("null average") { + checkAnswer( + testData3.groupBy()(Average('b)), + 2.0) + + checkAnswer( + testData3.groupBy()(Average('b), CountDistinct('b :: Nil)), + (2.0, 1) :: Nil) + } + test("count") { assert(testData2.count() === testData2.map(_ => 1).count()) } -- cgit v1.2.3