Skip to content

renamed groupByRelationKey to groupByKey #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
viirya merged 1 commit into from
Nov 13, 2019
Merged

renamed groupByRelationKey to groupByKey #9

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1733,7 +1733,7 @@ class Dataset[T] private[sql](
* @since 3.0.0
*/
@scala.annotation.varargs
def groupByRelationKey(
def groupByKey(
col1: String,
cols: String*): KeyValueGroupedDataset[Row, T] = {
val colNames: Seq[String] = col1 +: cols
Expand Down
6 changes: 3 additions & 3 deletions sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2204,14 +2204,14 @@ class DataFrameSuite extends QueryTest with SharedSparkSession {
}
}

test("groupByRelationKey") {
test("groupByKey relational") {
val df1 = Seq((1, 2, 3), (2, 3, 4)).toDF("a", "b", "c")
.repartition($"a", $"b").sortWithinPartitions("a", "b")
val df2 = Seq((1, 2, 4), (2, 3, 5)).toDF("a", "b", "c")
.repartition($"a", $"b").sortWithinPartitions("a", "b")

val df3 = df1.groupByRelationKey("a", "b")
.cogroup(df2.groupByRelationKey("a", "b")) { case (key, data1, data2) =>
val df3 = df1.groupByKey("a", "b")
.cogroup(df2.groupByKey("a", "b")) { case (key, data1, data2) =>
data1.zip(data2).map { p =>
p._1.getInt(2) + p._2.getInt(2)
}
Expand Down
6 changes: 3 additions & 3 deletions sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1861,14 +1861,14 @@ class DatasetSuite extends QueryTest with SharedSparkSession {
}
}

test("groupByRelationKey") {
test("groupByKey relational") {
val df1 = Seq(DoubleData(1, "one"), DoubleData(2, "two"), DoubleData( 3, "three")).toDS()
.repartition($"id").sortWithinPartitions("id")
val df2 = Seq(DoubleData(5, "one"), DoubleData(1, "two"), DoubleData( 3, "three")).toDS()
.repartition($"id").sortWithinPartitions("id")

val df3 = df1.groupByRelationKey("id").keyAs[Int]
.cogroup(df2.groupByRelationKey("id").keyAs[Int]) { case (key, data1, data2) =>
val df3 = df1.groupByKey("id").keyAs[Int]
.cogroup(df2.groupByKey("id").keyAs[Int]) { case (key, data1, data2) =>
if (key == 1) {
Iterator(DoubleData(key, (data1 ++ data2).foldLeft("")((cur, next) => cur + next.val1)))
} else Iterator.empty
Expand Down