From dcaa016610ac2c11d7dd01803f3515b02ab32e64 Mon Sep 17 00:00:00 2001
From: Reynold Xin <rxin@databricks.com>
Date: Sat, 19 Mar 2016 11:23:14 -0700
Subject: [SPARK-13897][SQL] RelationalGroupedDataset and
 KeyValueGroupedDataset

## What changes were proposed in this pull request?
Previously, Dataset.groupBy returns a GroupedData, and Dataset.groupByKey returns a GroupedDataset. The naming is very similar, and unfortunately does not convey the real differences between the two.

Assume we are grouping by some keys (K). groupByKey is a key-value style group by, in which the schema of the returned dataset is a tuple of just two fields: key and value. groupBy, on the other hand, is a relational style group by, in which the schema of the returned dataset is flattened and contain |K| + |V| fields.

This pull request also removes the experimental tag from RelationalGroupedDataset. It has been with DataFrame since 1.3, and we have enough confidence now to stabilize it.

## How was this patch tested?
This is a rename to improve API understandability. Should be covered by all existing tests.

Author: Reynold Xin <rxin@databricks.com>

Closes #11841 from rxin/SPARK-13897.
---
 .../src/test/java/test/org/apache/spark/sql/JavaDatasetSuite.java | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'sql/core/src/test/java')

diff --git a/sql/core/src/test/java/test/org/apache/spark/sql/JavaDatasetSuite.java b/sql/core/src/test/java/test/org/apache/spark/sql/JavaDatasetSuite.java
index 79b6e61767..4b8b0d9d4f 100644
--- a/sql/core/src/test/java/test/org/apache/spark/sql/JavaDatasetSuite.java
+++ b/sql/core/src/test/java/test/org/apache/spark/sql/JavaDatasetSuite.java
@@ -169,7 +169,7 @@ public class JavaDatasetSuite implements Serializable {
   public void testGroupBy() {
     List<String> data = Arrays.asList("a", "foo", "bar");
     Dataset<String> ds = context.createDataset(data, Encoders.STRING());
-    GroupedDataset<Integer, String> grouped = ds.groupByKey(new MapFunction<String, Integer>() {
+    KeyValueGroupedDataset<Integer, String> grouped = ds.groupByKey(new MapFunction<String, Integer>() {
       @Override
       public Integer call(String v) throws Exception {
         return v.length();
@@ -217,7 +217,7 @@ public class JavaDatasetSuite implements Serializable {
 
     List<Integer> data2 = Arrays.asList(2, 6, 10);
     Dataset<Integer> ds2 = context.createDataset(data2, Encoders.INT());
-    GroupedDataset<Integer, Integer> grouped2 = ds2.groupByKey(new MapFunction<Integer, Integer>() {
+    KeyValueGroupedDataset<Integer, Integer> grouped2 = ds2.groupByKey(new MapFunction<Integer, Integer>() {
       @Override
       public Integer call(Integer v) throws Exception {
         return v / 2;
@@ -249,7 +249,7 @@ public class JavaDatasetSuite implements Serializable {
   public void testGroupByColumn() {
     List<String> data = Arrays.asList("a", "foo", "bar");
     Dataset<String> ds = context.createDataset(data, Encoders.STRING());
-    GroupedDataset<Integer, String> grouped =
+    KeyValueGroupedDataset<Integer, String> grouped =
       ds.groupByKey(length(col("value"))).keyAs(Encoders.INT());
 
     Dataset<String> mapped = grouped.mapGroups(
@@ -410,7 +410,7 @@ public class JavaDatasetSuite implements Serializable {
       Arrays.asList(tuple2("a", 1), tuple2("a", 2), tuple2("b", 3));
     Dataset<Tuple2<String, Integer>> ds = context.createDataset(data, encoder);
 
-    GroupedDataset<String, Tuple2<String, Integer>> grouped = ds.groupByKey(
+    KeyValueGroupedDataset<String, Tuple2<String, Integer>> grouped = ds.groupByKey(
       new MapFunction<Tuple2<String, Integer>, String>() {
         @Override
         public String call(Tuple2<String, Integer> value) throws Exception {
-- 
cgit v1.2.3