Spark——排序实例

最新推荐文章于 2024-04-30 07:14:08 发布

wangzhangni

最新推荐文章于 2024-04-30 07:14:08 发布

阅读量223

点赞数

CC 4.0 BY-SA版权

本文链接：https://blog.youkuaiyun.com/wangzhangni/article/details/102916337

本文介绍了如何使用Spark进行排序操作，重点讲解了SortByKey和SortBy两个方法的使用，包括基于Java和Scala的实现方式，以取最大的前三个数字为例进行实战演示。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

取最大的前三个数字

top.txt
在这里插入图片描述

1、SortByKey

1）基于java

package cn.spark.study.core;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.PairFunction;
import scala.Tuple2;

import java.util.List;

public class Top3 {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf()
                .setMaster("local")
                .setAppName("Top3");
        JavaSparkContext sc = new JavaSparkContext(conf);

        JavaRDD<String> lines = sc.textFile("E:\\ziliao\\Spark\\node\\shuju\\top.txt");

        JavaPairRDD<Integer, Integer> numbers = lines.mapToPair(new PairFunction<String, Integer, Integer>() {
            @Override
            public Tuple2<Integer, Integer> call(String s) throws Exception {
                return new Tuple2<Integer, Integer>(Integer.parseInt(s), 1);
            }
        });

        JavaPairRDD<Integer, Integer> sorted = numbers.sortByKey(false);

        JavaRDD<Integer> map = sorted.map(new Function<Tuple2<Integer, Integer>, Integer>() {
            @Override
            public Integer call(Tuple2<Integer, Integer> Tuple2) throws Exception {
                return Tuple2._1;
            }
        });

        List<Integer> take = map.take(3);

        for (Integer e: take){
            System.out.println(e);
        }
    }
}

在这里插入图片描述
1）基于scala

package cn.spark.study.core

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

object Top3 {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf()
      .setMaster("local")
      .setAppName("Top3")
    val sc= new SparkContext(conf)
    val lines: RDD[String] = sc.textFile("E:\\ziliao\\Spark\\node\\shuju\\top.txt")

    //注意numPartitions的设置，注意是全局排序还是每个分区排序
    val numTake3: Array[String] = lines.map((_,1)).sortByKey(false,1).map(_._1).take(3)
    for (e <- numTake3){
      println(e)
    }
  }
}

在这里插入图片描述

2、SortBy

1）基于java

package cn.spark.study.core;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.VoidFunction;

public class Top3_SortBy {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf()
                .setMaster("local")
                .setAppName("Top3_SortBy");
        JavaSparkContext sc = new JavaSparkContext(conf);

        JavaRDD<String> lines = sc.textFile("E:\\ziliao\\Spark\\node\\shuju\\top.txt");

        JavaRDD<Integer> number = lines.map(new Function<String, Integer>() {
            @Override
            public Integer call(String s) throws Exception {
                return Integer.parseInt(s);
            }
        });

        JavaRDD<Integer> sortBy = number.sortBy(new Function<Integer, Integer>() {
            @Override
            public Integer call(Integer integer) throws Exception {
                return integer;
            }
        }, false, 1);

		List<Integer> take = sortBy.take(3);

        for (Integer e: take){
            System.out.println(e);
        }
    }
}

在这里插入图片描述
1）基于scala

package cn.spark.study.core

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

object Top3_SortBy {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf()
      .setMaster("local")
      .setAppName("Top3_SortBy")
    val sc = new SparkContext(conf)
    val lines: RDD[String] = sc.textFile("E:\\ziliao\\Spark\\node\\shuju\\top.txt")
    val sortByTake3: Array[Int] = lines.map(Integer.parseInt(_)).sortBy((t:Int) => t, false, 1).take(3)
    for (e <- sortByTake3){
      println(e)
    }
  }
}

在这里插入图片描述