Spark-Core的交并差拉链

Posted 2021-06-27 Mr.zhou_Zxy

Spark-Core的交、并、差、拉链

object num6{
    def main(args: Array[String]): Unit = {
        val sc = new SparkContext(new SparkConf().setMaster("local[*]").setAppName("num5"))
        val rdd1: RDD[Int] = sc.makeRDD(List(1,2,3,4))
        val rdd2: RDD[Int] = sc.makeRDD(List(3,4,5,6))
        
        //交集【3，4】
        val rdd3: RDD[Int] = rdd1.intersection(rdd2)
        println(rdd3.collect().mkString("[",",","]"))
    
        //并集【1，2，3，4，3，4，5，6】
        val rdd4: RDD[Int] = rdd1.union(rdd2)
        println(rdd4.collect().mkString("[",",","]"))
    
        //差集【1,2】
        val rdd5: RDD[Int] = rdd1.subtract(rdd2)
        println(rdd5.collect().mkString("[",",","]"))
        //差集【5,6】
        val rdd6: RDD[Int] = rdd2.subtract(rdd1)
        println(rdd6.collect().mkString("[",",","]"))
        //拉链【（1，3），（2，4），（3，5），（4，6）】
        val rdd7: RDD[(Int, Int)] = rdd1.zip(rdd2)
        println(rdd7.collect().mkString("[",",","]"))
    }
}

• 运行结果

[3,4]
[1,2,3,4,3,4,5,6]
[1,2]
[5,6]
[(1,3),(2,4),(3,5),(4,6)]