spark--transform算子--parallelized

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

/**
  * Created by liupeng on 2017/6/15.
  */
object T_parallelized {

  System.setProperty("hadoop.home.dir","F:\\hadoop-2.6.5")

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

    //parallelize 操作会将集合并行化为RDD
    val data = Array(1, 2, 3, 4, 5)
    val distDate = sc.parallelize(data)
    distDate.foreach(println)
  }
}

运行结果：

1
2
3
4
5