spark算子

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

(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 ...
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 ...
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 ...
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 ...
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 ...
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 ...
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 --- ...
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 ...
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 ...
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

Assignment HDU - 2853（求最小改变边数）
Assignment Time Limit: 2000/1000 MS (Java/Others) Memory Limit: 32768/32768 K (Java/Others)Total ...
如何取消Paypal自动付款功能
在国外在线服务消费肯定会常遇到PayPal的支付方式,有些人可能PayPal有些余额可能会用这个工具来支付,但付款后,可能服务因为不满意而退掉,但第二年却自动续约了?但明明服务已退掉,这该怎么处理呢? ...
maven 使用 log4j
Log4j是Apache的一个开源项目,通过使用Log4j,我们可以控制日志信息输送的目的地是控制台.文件.GUI组件,甚至是套接口服务器.NT的事件记录器.UNIX Syslog守护进程等:我们也可 ...
Python判断自定义的参数格式是否正确
import argparse def args_validation(valid_list, valid_value): assert valid_value in valid_list, 'inv ...
mtd-utils 安装
title: mkdosfs 安装 tags: linux date: 2018/12/26/ 17:08:54 --- mtd-utils安装 for 主机在制作根文件系统中需要使用它制作jffs ...
Pandas系列（五）-分类数据处理
内容目录 1. 创建对象 2. 常用操作 3. 内存使用量的陷阱一.创建对象 1.基本概念:分类数据直白来说就是取值为有限的,或者说是固定数量的可能值.例如:性别.血型. 2.创建分类数据:这里以血 ...
win10添加右键打开命令窗口
新建文件cmd.reg,将下面代码贴入 Windows Registry Editor Version 5.00 [HKEY_CLASSES_ROOT\Directory\Background\she ...
Word中页眉、页码设置
本篇博文简单介绍一下文档中页眉.页码设置的问题一个项目中,封面一般不需要页眉,要关闭首页的页眉,可以在"页眉和页脚工具->选项->首页不同"可以如下设置: 图 1关闭 ...
.NET面试题系列（十七）前端面试
JavaScript js如何实现继承 CSS 行内元素和块状元素的区别 CSS让2个DIV在同一行显示的解决方法在CSS中,div属于块级元素,每个块级元素默认占一行高度,一行内添加一个块级 ...
end to end testing
概念 https://www.softwaretestinghelp.com/what-is-end-to-end-testing/ What is “End to End Testing”? Ter ...

spark算子

1.map

2.flatMap

3.mapPartitions

4.mapPartitionsWithIndex

5.reduce

6.reduceBykey

7.union

8.join

9.groupbyKey

10.cartesian

11.filter

12.distinct

13.intersection

14.coalesce

15.repartition

16.repartitionAndSortWithinPartitions

17.cogroup

18.sortByKey

19.aggregateByKey

spark算子的更多相关文章

随机推荐

热门专题