1.map

一条一条读取

def map(): Unit ={

    val list = List("张无忌", "赵敏", "周芷若")

    val listRDD = sc.parallelize(list)

    val nameRDD = listRDD.map(name => "Hello " + name)

    nameRDD.foreach(name => println(name))

  }

2.flatMap

扁平化

def flatMap(): Unit ={

    val list = List("张无忌 赵敏","宋青书 周芷若")

    val listRDD = sc.parallelize(list)

    val nameRDD = listRDD.flatMap(line => line.split(" ")).map(name => "Hello " + name)

    nameRDD.foreach(name => println(name))

  }

3.mapPartitions

一次读取一个分区数据

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1, 2, 3, 4, 5, 6)

    val rdd = spark.parallelize(list, 2)

    rdd.foreach(println)

    val rdd2 = rdd.mapPartitions(iterator => {

      val newList = new ListBuffer[String]

      while (iterator.hasNext) {

        newList.append("hello" + iterator.next())

      }

      newList.toIterator

    })

    rdd2.foreach(name => println(name))

  }

}

4.mapPartitionsWithIndex

一次读取一个分区数据，并且知道是哪个分区的

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1, 2, 3, 4, 5, 6)

    val rdd = spark.parallelize(list, 2)

    val rdd2 = rdd.mapPartitionsWithIndex((index, iterator) => {

      val newList = new ListBuffer[String]

      while (iterator.hasNext) {

        newList.append(index + "_" + iterator.next())

      }

      newList.toIterator

    })

    rdd2.foreach(name => println(name))

  }

}

5.reduce

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1, 2, 3, 4, 5, 6)

    val rdd = spark.parallelize(list)

    val result = rdd.reduce((x, y) => x + y)

    println(result)

  }

}

6.reduceBykey

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(("武当", 99), ("少林", 97), ("武当", 89), ("少林", 77))

    val rdd = spark.parallelize(list)

    val rdd2 = rdd.reduceByKey(_ + _)

    rdd2.foreach(tuple => println(tuple._1 + ":" + tuple._2))

  }

}

7.union

合并，但不去重

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list1 = List(1,2,3,4)

    val list2 = List(3,4,5,6)

    val rdd1 = spark.parallelize(list1)

    val rdd2 = spark.parallelize(list2)

    rdd1.union(rdd2).foreach(println)

  }

}

8.join

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list1 = List((1, "东方不败"), (2, "令狐冲"), (3, "林平之"))

    val list2 = List((1, 99), (2, 98), (3, 97))

    val rdd1 = spark.parallelize(list1)

    val rdd2 = spark.parallelize(list2)

    val rdd3 = rdd1.join(rdd2)

    rdd3.foreach(tuple => {

      val id = tuple._1

      val new_tuple = tuple._2

      val name = new_tuple._1

      val score = new_tuple._2

      println("学号：" + id + " 姓名：" + name + " 成绩:" + score)

    })

  }

}

9.groupbyKey

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(("武当", "张三丰"), ("峨眉", "灭绝师太"), ("武当", "宋青书"), ("峨眉", "周芷若"))

    val rdd1 = spark.parallelize(list)

    val rdd2 = rdd1.groupByKey()

    rdd2.foreach(t => {

      val menpai = t._1

      val iterator = t._2.iterator

      var people = ""

      while (iterator.hasNext) people = people + iterator.next + " "

      println("门派:" + menpai + "人员:" + people)

    })

  }

}

10.cartesian

笛卡尔积

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list1 = List("A", "B")

    val list2 = List(1, 2, 3)

    val list1RDD = spark.parallelize(list1)

    val list2RDD = spark.parallelize(list2)

    list1RDD.cartesian(list2RDD).foreach(t => println(t._1 + "->" + t._2))

  }

}

11.filter

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1,2,3,4,5,6,7,8,9,10)

    val listRDD = spark.parallelize(list)

    listRDD.filter(num => num % 2 ==0).foreach(print(_))

  }

}

12.distinct

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1,1,2,2,3,3,4,5)

    val rdd = spark.parallelize(list)

    rdd.distinct().foreach(println)

  }

}

13.intersection

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list1 = List(1,2,3,4)

    val list2 = List(3,4,5,6)

    val list1RDD = spark.parallelize(list1)

    val list2RDD = spark.parallelize(list2)

    list1RDD.intersection(list2RDD).foreach(println(_))

  }

}

14.coalesce

分区有多-->少

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1,2,3,4,5)

    spark.parallelize(list,3).coalesce(1).foreach(println(_))

  }

}

15.repartition

进行重分区

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1,2,3,4)

    val listRDD = spark.parallelize(list,1)

    listRDD.repartition(2).foreach(println(_))

  }

}

16.repartitionAndSortWithinPartitions

在给定的partitioner内部进行排序，性能比repartition要高。

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1, 4, 55, 66, 33, 48, 23)

    val listRDD = spark.parallelize(list, 1)

    listRDD.map(num => (num, num))

      .repartitionAndSortWithinPartitions(new HashPartitioner(2))

      .mapPartitionsWithIndex((index, iterator) => {

        val listBuffer: ListBuffer[String] = new ListBuffer

        while (iterator.hasNext) {

          listBuffer.append(index + "_" + iterator.next())

        }

        listBuffer.iterator

      }, false)

      .foreach(println(_))

  }

}

17.cogroup

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list1 = List((1, "www"), (2, "bbs"))

    val list2 = List((1, "cnblog"), (2, "cnblog"), (3, "very"))

    val list3 = List((1, "com"), (2, "com"), (3, "good"))

    val list1RDD = spark.parallelize(list1)

    val list2RDD = spark.parallelize(list2)

    val list3RDD = spark.parallelize(list3)

    list1RDD.cogroup(list2RDD,list3RDD).foreach(tuple =>

      println(tuple._1 + " " + tuple._2._1 + " " + tuple._2._2 + " " + tuple._2._3))

  }

}

18.sortByKey

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List((99, "张三丰"), (96, "东方不败"), (66, "林平之"), (98, "聂风"))

    spark.parallelize(list).sortByKey(false).foreach(tuple => println(tuple._2 + "->" + tuple._1))

  }

}

19.aggregateByKey

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

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List("you,jump", "i,jump")

    spark.parallelize(list)

      .flatMap(_.split(","))

      .map((_, 1))

      .aggregateByKey(0)(_ + _, _ + _)

      .foreach(tuple => println(tuple._1 + "->" + tuple._2))

  }

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

import scala.collection.mutable.ListBuffer

object Demo {
  val conf = new SparkConf().setAppName("Demo").setMaster("local");
//  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()
val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {
    val list = List(("武当", "张三丰"), ("峨眉", "灭绝师太"), ("武当", "宋青书"), ("峨眉", "周芷若"))
    val rdd1 = spark.parallelize(list)
    val rdd2 = rdd1.groupByKey()
    rdd2.foreach(t => {
      val menpai = t._1
      val iterator = t._2.iterator
      var people = ""
while (iterator.hasNext) people = people + iterator.next + " "
println("门派:" + menpai + "人员:" + people)
    })
  }
}

spark算子的更多相关文章

  1. (转)Spark 算子系列文章

    http://lxw1234.com/archives/2015/07/363.htm Spark算子:RDD基本转换操作(1)–map.flagMap.distinct Spark算子:RDD创建操 ...

  2. Spark算子总结及案例

    spark算子大致上可分三大类算子: 1.Value数据类型的Transformation算子,这种变换不触发提交作业,针对处理的数据项是Value型的数据. 2.Key-Value数据类型的Tran ...

  3. UserView--第二种方式（避免第一种方式Set饱和），基于Spark算子的java代码实现

      UserView--第二种方式(避免第一种方式Set饱和),基于Spark算子的java代码实现   测试数据 java代码 package com.hzf.spark.study; import ...

  4. UserView--第一种方式set去重，基于Spark算子的java代码实现

    UserView--第一种方式set去重,基于Spark算子的java代码实现 测试数据 java代码 package com.hzf.spark.study; import java.util.Ha ...

  5. spark算子之DataFrame和DataSet

    前言 传统的RDD相对于mapreduce和storm提供了丰富强大的算子.在spark慢慢步入DataFrame到DataSet的今天,在算子的类型基本不变的情况下,这两个数据集提供了更为强大的的功 ...

  6. Spark算子总结（带案例）

    Spark算子总结(带案例) spark算子大致上可分三大类算子: 1.Value数据类型的Transformation算子,这种变换不触发提交作业,针对处理的数据项是Value型的数据. 2.Key ...

  7. Spark算子---实战应用

    Spark算子实战应用 数据集 :http://grouplens.org/datasets/movielens/ MovieLens 1M Datase 相关数据文件 : users.dat --- ...

  8. spark算子集锦

    Spark 是大数据领域的一大利器,花时间总结了一下 Spark 常用算子,正所谓温故而知新. Spark 算子按照功能分,可以分成两大类:transform 和 action.Transform 不 ...

  9. Spark算子使用

    一.spark的算子分类 转换算子和行动算子 转换算子:在使用的时候,spark是不会真正执行,直到需要行动算子之后才会执行.在spark中每一个算子在计算之后就会产生一个新的RDD. 二.在编写sp ...

  10. Spark：常用transformation及action，spark算子详解

    常用transformation及action介绍,spark算子详解 一.常用transformation介绍 1.1 transformation操作实例 二.常用action介绍 2.1 act ...

随机推荐

  1. Pthread 用法笔记

    什么是线程? 从技术上讲,一个线程被定义为一个独立的指令流. 一个进程可以包含一个或多个线程. 线程操作包括线程创建,终止,同步(连接,阻塞),调度,数据管理和进程交互. 进程内的所有线程共享: 相同 ...

  2. 清北学堂Day2

    算数基本定理: 1.整数及其相关 2.唯一分解定理 对于任意的大于1的正整数N,N一定能够分解成有限个质数的乘积,即 其中P1<P2<...<Pk,a1,a2,...,ak>= ...

  3. Loj #528. 「LibreOJ β Round #4」求和 (莫比乌斯反演)

    题目链接:https://loj.ac/problem/528 题目:给定两个正整数N,M,你需要计算ΣΣu(gcd(i,j))^2 mod 998244353 ,其中i属于[1,N],j属于[1,M ...

  4. Stanford Local 2016 G "Ground Defense"（线段树）

    传送门 题意: 有 n 个城市,编号 1~n: 有两种操作:Update,Query Update: E i s a d 更新区间[ i,i+d-1 ], i 节点降落 s 人, i+1 节点降落 s ...

  5. 礼物（中国剩余定理+拓展gcd求逆元+分治=拓展Lucus）

    礼物 题意: 求\[C(n,m)\ \%\ p\] \(n,m,p\le 10^9\),且若\(p=\prod_{i=1}^{k}{p_i}^{c_i}\),则\(\forall i\in [1..k ...

  6. (二分查找 拓展) leetcode 69. Sqrt(x)

    Implement int sqrt(int x). Compute and return the square root of x, where x is guaranteed to be a no ...

  7. EXCEL（1）级联下拉框

    EXCEL级联下拉框 http://jingyan.baidu.com/article/3c343ff756e0cf0d377963f9.html 在输入一些多级项目时,如果输入前一级内容后,能够自动 ...

  8. 深入剖析Kubernetes学习笔记：深入理解镜像（08）

    一.Python 应用案例环境 [root@k8s-node1 Flask]# pwd /opt/Dockerfile/Flask [root@k8s-node1 Flask]# ll total 1 ...

  9. 2018-2019-2 《Java程序设计》第1周学习总结

    # 20175319 2018-2019-2 <Java程序设计>第1周学习总结 ## 教材学习内容总结 第一周我根据老师提供的博客,下载和设置了各种需要的软件,并对这些软件进行初步的了解 ...

  10. 18、cookies与session学习笔记

    本文记录学习 cookies 和 session 的一些小练习和知识点   知识点1    cookies 和 session 的由来   HTTP协议是无状态的协议,因为一旦浏览器和服务器之间的请求 ...