spark--transform算子--distinct

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

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

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

    val list = List(1,2,3,1,4,5,4,7,1)
    var rdd = sc.parallelize(list)

    //distinct方法用于对本身的数据集进行去重处理
    val result = rdd.distinct()
      .foreach(println)
    //如果是键值对的数据，kv都相同，才算是相同的元素
    val list1 = List(("liupeng", 120), ("liupeng", 120), ("liusi", 120))
    val rdd1 = sc.parallelize(list1)
    val result1 = rdd1.distinct()
      .foreach(println)
  }
}

运行结果：

4
1
3
7
5
2

liusi,120)
(liupeng,120)