spark--transform算子--cartesian

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

/**
  * Created by lp on 2017/6/16.
  */
object T_cartesian {
  System.setProperty("hadoop.home.dir","F:\\hadoop-2.6.5")

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("cartesian_test").setMaster("local")
    val sc = new SparkContext(conf)

    val rdd = sc.parallelize(List(1,2,3))
    val rdd1 = sc.parallelize(List("A", "B"))
    //这个方法用于计算两个(K,V)数据集之间的笛卡尔积
    val sum = rdd.cartesian(rdd1)
      .foreach(println)
  }
}

运行结果：

(1,A)
(1,B)
(2,A)
(2,B)
(3,A)
(3,B)