join

 

 

 

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


object joinRDD {
  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 joinRDD: RDD[(Int, (String, Int))] = rdd.join(rdd2)
    joinRDD.collect().foreach(println)

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

    val rdd3: RDD[(Int, String)] = sc.makeRDD(List((3,"a"),(2,"a"),(1,"c"),(4,"e")),3)
    val joinRDD3: RDD[(Int, (String, Int))] = rdd3.join(rdd2)
    joinRDD3.collect().foreach(println)

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


  }

}

//