spark中将字符串生成二元组集合

使用Scala的集合工具包中，使用combinations将字符串生成二元组集合。

spark版本：2.0.2

 

val list1 = List(1,3,2,4,5,7,6,9,8)
/*
list1: List[Int] = List(1, 3, 2, 4, 5, 7, 6, 9, 8)
*/
val list2 = list1.sorted.combinations(2)
/*
list2: Iterator[List[Int]] = non-empty iterator
*/
list2.foreach(println)
/*
List(1, 2)
List(1, 3)
List(1, 4)
List(1, 5)
List(1, 6)
List(1, 7)
List(1, 8)
List(1, 9)
List(2, 3)
List(2, 4)
List(2, 5)
List(2, 6)
List(2, 7)
List(2, 8)
List(2, 9)
List(3, 4)
List(3, 5)
List(3, 6)
List(3, 7)
List(3, 8)
List(3, 9)
List(4, 5)
List(4, 6)
List(4, 7)
List(4, 8)
List(4, 9)
List(5, 6)
List(5, 7)
List(5, 8)
List(5, 9)
List(6, 7)
List(6, 8)
List(6, 9)
List(7, 8)
List(7, 9)
List(8, 9)
*/


val rdd1 = sc.parallelize(Seq(Seq(1,2,3,4,5),Seq(2,1,4,5,6,9),Seq(1,6,3,7,2,4)))
/*
rdd1: org.apache.spark.rdd.RDD[Seq[Int]] = ParallelCollectionRDD[0] at parallelize at :24
*/
rdd1.collect
/*
res1: Array[Seq[Int]] = Array(List(1, 2, 3, 4, 5), List(2, 1, 4, 5, 6, 9), List(1, 6, 3, 7, 2, 4))
*/
val rdd2 = rdd1.flatMap(x => x.sorted.combinations(2))
/*
rdd2: org.apache.spark.rdd.RDD[Seq[Int]] = MapPartitionsRDD[1] at flatMap at :26
*/
rdd2.collect
/*
res2: Array[Seq[Int]] = Array(List(1, 2), List(1, 3), List(1, 4), List(1, 5), List(2, 3), List(2, 4), List(2, 5), 
                             List(3, 4), List(3, 5), List(4, 5), List(1, 2), List(1, 4), List(1, 5), List(1, 6), 
							 List(1, 9), List(2, 4), List(2, 5), List(2, 6), List(2, 9), List(4, 5), List(4, 6), 
							 List(4, 9), List(5, 6), List(5, 9), List(6, 9), List(1, 2), List(1, 3), List(1, 4), 
							 List(1, 6), List(1, 7), List(2, 3), List(2, 4), List(2, 6), List(2, 7), List(3, 4), 
							 List(3, 6), List(3, 7), List(4, 6), List(4, 7), List(6, 7))
*/
rdd2.foreach(println)
/*
List(1, 2)
List(1, 2)
List(1, 3)
List(1, 2)
List(1, 4)
List(1, 3)
List(1, 4)
List(1, 6)
List(1, 7)
List(1, 4)
List(2, 3)
List(1, 5)
List(2, 4)
List(1, 5)
List(2, 6)
List(1, 6)
List(2, 3)
List(2, 7)
List(1, 9)
List(2, 4)
List(3, 4)
List(2, 4)
List(2, 5)
List(3, 6)
List(2, 5)
List(3, 4)
List(3, 7)
List(2, 6)
List(3, 5)
List(4, 6)
List(4, 5)
List(2, 9)
List(4, 7)
List(4, 5)
List(6, 7)
List(4, 6)
List(4, 9)
List(5, 6)
List(5, 9)
List(6, 9)
*/

　　

转载于:https://www.cnblogs.com/Sarah-2017/p/6410080.html