diff options
author | Cheng Hao <hao.cheng@intel.com> | 2015-05-20 19:09:47 +0800 |
---|---|---|
committer | Cheng Lian <lian@databricks.com> | 2015-05-20 19:09:47 +0800 |
commit | 09265ad7c85c6de6b568ec329daad632d4a79fa3 (patch) | |
tree | 456111dab186b98723d6c443624ee64a42237ad2 /sql/hive | |
parent | b3abf0b8d9bca13840eb759953d76905c2ba9b8a (diff) | |
download | spark-09265ad7c85c6de6b568ec329daad632d4a79fa3.tar.gz spark-09265ad7c85c6de6b568ec329daad632d4a79fa3.tar.bz2 spark-09265ad7c85c6de6b568ec329daad632d4a79fa3.zip |
[SPARK-7320] [SQL] Add Cube / Rollup for dataframe
Add `cube` & `rollup` for DataFrame
For example:
```scala
testData.rollup($"a" + $"b", $"b").agg(sum($"a" - $"b"))
testData.cube($"a" + $"b", $"b").agg(sum($"a" - $"b"))
```
Author: Cheng Hao <hao.cheng@intel.com>
Closes #6257 from chenghao-intel/rollup and squashes the following commits:
7302319 [Cheng Hao] cancel the implicit keyword
a66e38f [Cheng Hao] remove the unnecessary code changes
a2869d4 [Cheng Hao] update the code as comments
c441777 [Cheng Hao] update the code as suggested
84c9564 [Cheng Hao] Remove the CubedData & RollupedData
279584c [Cheng Hao] hiden the CubedData & RollupedData
ef357e1 [Cheng Hao] Add Cube / Rollup for dataframe
Diffstat (limited to 'sql/hive')
-rw-r--r-- | sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDataFrameAnalyticsSuite.scala | 62 |
1 files changed, 62 insertions, 0 deletions
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDataFrameAnalyticsSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDataFrameAnalyticsSuite.scala new file mode 100644 index 0000000000..3ad05f4825 --- /dev/null +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDataFrameAnalyticsSuite.scala @@ -0,0 +1,62 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.hive + +import org.apache.spark.sql.QueryTest +import org.apache.spark.sql.functions._ +import org.apache.spark.sql.hive.test.TestHive +import org.apache.spark.sql.hive.test.TestHive._ +import org.apache.spark.sql.hive.test.TestHive.implicits._ + +case class TestData2Int(a: Int, b: Int) + +// TODO ideally we should put the test suite into the package `sql`, as +// `hive` package is optional in compiling, however, `SQLContext.sql` doesn't +// support the `cube` or `rollup` yet. +class HiveDataFrameAnalyticsSuite extends QueryTest { + val testData = + TestHive.sparkContext.parallelize( + TestData2Int(1, 2) :: + TestData2Int(2, 4) :: Nil).toDF() + + testData.registerTempTable("mytable") + + test("rollup") { + checkAnswer( + testData.rollup($"a" + $"b", $"b").agg(sum($"a" - $"b")), + sql("select a + b, b, sum(a - b) from mytable group by a + b, b with rollup").collect() + ) + + checkAnswer( + testData.rollup("a", "b").agg(sum("b")), + sql("select a, b, sum(b) from mytable group by a, b with rollup").collect() + ) + } + + test("cube") { + checkAnswer( + testData.cube($"a" + $"b", $"b").agg(sum($"a" - $"b")), + sql("select a + b, b, sum(a - b) from mytable group by a + b, b with cube").collect() + ) + + checkAnswer( + testData.cube("a", "b").agg(sum("b")), + sql("select a, b, sum(b) from mytable group by a, b with cube").collect() + ) + } +} |