cogroup

 

 

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}


object cogroupRDD {
  def main(args: Array[String]): Unit = {

    val conf: SparkConf = new SparkConf().setAppName("My scala word count").setMaster("local")
    val sc = new SparkContext(conf)

    //join;根据key关联
    val rdd: RDD[(Int, String)] = sc.makeRDD(List((3,"a"),(2,"a"),(1,"c")),3)
    val rdd2: RDD[(Int, Int)] = sc.makeRDD(Array((1,3),(2,6),(3,9)))
    val cogroupRDD: RDD[(Int, (Iterable[String], Iterable[Int]))] = rdd.cogroup(rdd2)
    cogroupRDD.collect().foreach(println)


//    (3,(CompactBuffer(a),CompactBuffer(9)))
//    (1,(CompactBuffer(c),CompactBuffer(3)))
//    (2,(CompactBuffer(a),CompactBuffer(6)))


    val rdd3: RDD[(Int, String)] = sc.makeRDD(List((3,"a"),(2,"a"),(1,"c"),(4,"e")),3)
    val cogroupRDD3: RDD[(Int, (Iterable[String], Iterable[Int]))] = rdd3.cogroup(rdd2)
    cogroupRDD3.collect().foreach(println)

//    (3,(CompactBuffer(a),CompactBuffer(9)))
//    (4,(CompactBuffer(e),CompactBuffer()))
//    (1,(CompactBuffer(c),CompactBuffer(3)))
//    (2,(CompactBuffer(a),CompactBuffer(6)))







  }

}

//