spark学习02之app流量统计并排序(JAVA)

关注

转载最新推荐文章于 2026-08-12 13:58:19 发布 1.2k 阅读 AI 写同款· GEO 优化 ›

计算出用户上网流量总流量（上行+下行）最高的网站Top3 分析用户访问网站日志，计算出上网总流量前3名的网站名及总流量日志部分如下（电话号，URL，上行量，下行量） 13026230503 http://v.baidu.com/tv 20 5000 13826544101 http://www.weibo.com/?category=7 20 5000 13926435656 http://v.baidu.com/tv 20 ... 阅读详情

转载自龙果学院的视频http://www.roncoo.com/course/view/1af3e9867cb84263a2a1873880205ae1。

有这样一份log日志记录了某时间戳下某个设备访问网站时产生的上行流量、下行流量。

时间戳/设备号/上行流量/下行流量

现在想统计出每个设备号的最早访问时间及总的上行流量、下行流量，最后打印出10个按上行流量、下行流量排序的最多的10个记录。

创建个普通的maven项目。

pom.xml

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.fei</groupId>
  <artifactId>spark-appTrafficCount</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  
  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
  </properties>

  <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>3.8.1</version>
      <scope>test</scope>
    </dependency>
     <dependency>
	  <groupId>org.apache.spark</groupId>
	  <artifactId>spark-core_2.10</artifactId>
	  <version>1.3.0</version>
	</dependency>
	
	
	
  </dependencies>
  
</project>

写个DataFileGenerator.java模拟日志数据，并写入文件，便于后面spark读取文件

package com.fei;

import java.io.FileOutputStream;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
import java.util.ArrayList;
import java.util.List;
import java.util.Random;
import java.util.UUID;

/**
 * 模拟生成数据，并把数据写到文件中
 * 文件内容：
 * 时间戳 \t设备号\t上行流量\t下行流量
 * @author Jfei
 *
 */
public class DataFileGenerator {

	public static void main(String[] args) {
		//1.生成100个设备号
		List<String> deviceIds = new ArrayList<String>();
		for(int i=0;i<100;i++){
			deviceIds.add(getDeviceId());
		}
		
		//2.生成1000个时间戳，该时间戳对应的设备号及上行流量、下行流量
		Random random = new Random();
		StringBuffer sb = new StringBuffer();
		for(int i=0;i<1000;i++){
			long timestamp = System.currentTimeMillis() - random.nextInt(10000);
			//随机获取一个设备号
			String deviceId = deviceIds.get(random.nextInt(100));
			//上行流量
			long upTraffic = random.nextInt(10000);
			//下行流量
			long downTraffic = random.nextInt(10000);
			
			sb.append(timestamp).append("\t").append(deviceId).append("\t").append(upTraffic)
			    .append("\t").append(downTraffic).append("\n");
		}
		
		//将数据写到文件
		PrintWriter pw = null;
		try {
			pw = new PrintWriter(new OutputStreamWriter(new FileOutputStream("e:\\app-log.txt")));
			pw.write(sb.toString());
		} catch (Exception e) {
			e.printStackTrace();
		}finally{
			if(pw != null){
				pw.close();
			}
		}
		
	}
	
	private static String getDeviceId(){
		return UUID.randomUUID().toString().replace("-", "");
	}
}

写个AccessLogInfo.java对应文件中的时间戳/上行流量/下行流量

package com.fei;

import java.io.Serializable;

/**
 * 设备(deviceId)访问日志信息对象，对应app-log.txt里面的内容
 * 
 * 因为后面是要将这对象放到spark中处理的，所以必须序列化
 * @author Jfei
 *
 */
public class AccessLogInfo implements Serializable{

	private static final long serialVersionUID = 1L;
    //没有设备号，是因为这对象是站在设备角度看的，k-v形式<设备号,AccessLogInfo>
	
	private long timestamp;//时间戳
	private long upTraffic;//上行流量
	private long downTraffic;//下行流量
	
	public AccessLogInfo(){
		
	}
	
	public AccessLogInfo(long timestamp, long upTraffic, long downTraffic) {
		this.timestamp = timestamp;
		this.upTraffic = upTraffic;
		this.downTraffic = downTraffic;
	}
	
	public long getTimestamp() {
		return timestamp;
	}
	public void setTimestamp(long timestamp) {
		this.timestamp = timestamp;
	}
	public long getUpTraffic() {
		return upTraffic;
	}
	public void setUpTraffic(long upTraffic) {
		this.upTraffic = upTraffic;
	}
	public long getDownTraffic() {
		return downTraffic;
	}
	public void setDownTraffic(long downTraffic) {
		this.downTraffic = downTraffic;
	}
	public static long getSerialversionuid() {
		return serialVersionUID;
	}
	
	
	
}

因为有排序要求，而上面的AccessLogInfo.java是没有定义排序比较的，所以定义个AccessLogSortKey.java

package com.fei;

import java.io.Serializable;

import scala.math.Ordered;
/**
 * 可排序的对象,上行流量、下行流量、时间戳来排序，降序
 * @author Jfei
 *
 */
public class AccessLogSortKey implements Ordered<AccessLogSortKey>,Serializable{

	private static final long serialVersionUID = 1L;

	private long timestamp;//时间戳
	private long upTraffic;//上行流量
	private long downTraffic;//下行流量
	
	public AccessLogSortKey(){
		
	}
	
	public AccessLogSortKey(long timestamp, long upTraffic, long downTraffic) {
		this.timestamp = timestamp;
		this.upTraffic = upTraffic;
		this.downTraffic = downTraffic;
	}

	public boolean $greater(AccessLogSortKey other) {
		if(upTraffic > other.upTraffic){
			return true;
		}else if(upTraffic == other.upTraffic && downTraffic > other.downTraffic	){
			return true;
		}else if(upTraffic == other.upTraffic && downTraffic == other.downTraffic && timestamp > other.timestamp	){
			return true;
		}
		
		return false;
	}

	public boolean $greater$eq(AccessLogSortKey other) {
		if($greater(other)){
			return true;
		}else if(upTraffic == other.upTraffic && downTraffic == other.downTraffic && timestamp == other.timestamp){
			return true;
		}
		return false;
	}
	public boolean $less(AccessLogSortKey other) {
		
		if(upTraffic < other.upTraffic){
			return true;
		}else if(upTraffic == other.upTraffic && downTraffic < other.downTraffic	){
			return true;
		}else if(upTraffic == other.upTraffic && downTraffic == other.downTraffic && timestamp < other.timestamp	){
			return true;
		}
		
		return false;
	}

	public boolean $less$eq(AccessLogSortKey other) {
		if($less(other)){
			return true;
		}else if(upTraffic == other.upTraffic && downTraffic == other.downTraffic && timestamp == other.timestamp){
			return true;
		}
		return false;
	}

	public int compare(AccessLogSortKey other) {
		if(upTraffic - other.upTraffic != 0){
			return (int)(upTraffic - other.upTraffic);
		}
		if(downTraffic - other.downTraffic != 0){
			return (int)(downTraffic - other.downTraffic);
		}
		if(timestamp - other.timestamp != 0){
			return (int)(timestamp - other.timestamp);
		}
		return 0;
	}
	public int compareTo(AccessLogSortKey other) {
		if(upTraffic - other.upTraffic != 0){
			return (int)(upTraffic - other.upTraffic);
		}
		if(downTraffic - other.downTraffic != 0){
			return (int)(downTraffic - other.downTraffic);
		}
		if(timestamp - other.timestamp != 0){
			return (int)(timestamp - other.timestamp);
		}
		return 0;
	}

	@Override
	public int hashCode() {
		final int prime = 31;
		int result = 1;
		result = prime * result + (int) (downTraffic ^ (downTraffic >>> 32));
		result = prime * result + (int) (timestamp ^ (timestamp >>> 32));
		result = prime * result + (int) (upTraffic ^ (upTraffic >>> 32));
		return result;
	}

	@Override
	public boolean equals(Object obj) {
		if (this == obj)
			return true;
		if (obj == null)
			return false;
		if (getClass() != obj.getClass())
			return false;
		AccessLogSortKey other = (AccessLogSortKey) obj;
		if (downTraffic != other.downTraffic)
			return false;
		if (timestamp != other.timestamp)
			return false;
		if (upTraffic != other.upTraffic)
			return false;
		return true;
	}

	
	public long getTimestamp() {
		return timestamp;
	}

	public void setTimestamp(long timestamp) {
		this.timestamp = timestamp;
	}

	public long getUpTraffic() {
		return upTraffic;
	}

	public void setUpTraffic(long upTraffic) {
		this.upTraffic = upTraffic;
	}

	public long getDownTraffic() {
		return downTraffic;
	}

	public void setDownTraffic(long downTraffic) {
		this.downTraffic = downTraffic;
	}

	public static long getSerialversionuid() {
		return serialVersionUID;
	}

	
	

}

好了，可以使用spark了

AppLogSpark.java

package com.fei;

import java.util.List;

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.Function2;
import org.apache.spark.api.java.function.PairFunction;

import scala.Tuple2;

/**
 * 读取app-log.txt中的内容，然后按设备号统计出每个设备号总的上行流量/总的下行流量，
 * 然后挑出前10个上行流量最大的设备号,打印出来
 * @author Jfei
 *
 */
public class AppLogSpark {

	public static void main(String[] args) {
		//1.创建spark配置文件及上下文对象
		SparkConf conf = new SparkConf().setAppName("appLogSpark").setMaster("local");
		JavaSparkContext sc = new JavaSparkContext(conf);
		
		//2.读取日志文件，并创建一个RDD，使用sparkContext方法textFile()可以读取本地文件或
		//HDFS文件，创建的RDD会包含文件中的所有内容数据
		JavaRDD<String> appLogRDD = sc.textFile("e:\\app-log.txt");
		
		//3.将appLogRDD映射成k-v形式<设备号,AccessLogInfo>的RDD
		//可以这样理解为List<deviceId,AccessLogInfo>，deviceId是可以对应多个AcessLogInfo的 
		JavaPairRDD<String, AccessLogInfo> appLogPairRDD = mapAppLogRDD2Pair(appLogRDD);
		
		//4.将appLogPairRDD根据key进行聚合，并统计
		//可以这样理解List<deviceId,AccessLogInfo>聚合后,deviceId只有对应一个AccessLogInfo了,
		//AccessLogInfo里面的数据就是某个deviceId的总上行流量/总下行流量了
		JavaPairRDD<String, AccessLogInfo> aggregateLogPairRDD =  aggregateByDevice(appLogPairRDD);
		
		//5.排序，按上行流量、上行流量、时间戳排序
		//因为JavaPairRDD中排序只有sortByKey(XX),而我们这是根据value排序的，所以需要
		//将JavaPairRDD<String, AccessLogInfo>转为JavaPairRDD<AccessLogInfo, String>的RDD,
		//而AccessLogInfo只是个普通的POJO，为了便于比较排序，定义个AccessLogSortKey对象
		JavaPairRDD<AccessLogSortKey, String > logSortRDD =  mapRDDKey2SortKey(aggregateLogPairRDD);
		
		//6.实现排序
		JavaPairRDD<AccessLogSortKey, String >  sortRDD = logSortRDD.sortByKey(false);//降序
		//7.取前10个
		List<Tuple2<AccessLogSortKey, String>>  list = sortRDD.take(10);
		
		//打印
		for(Tuple2<AccessLogSortKey, String> t : list){
			System.out.println(t._2 + "\t" + t._1.getTimestamp() + "\t" + t._1.getUpTraffic()+ "\t" + t._1.getDownTraffic());
		}
		
		//关闭
		sc.close();
	}
	/**
	 * 将appLogRDD映射成key-value形式的JavaPairRDD<String, AccessLogInfo>的RDD
	 * @param appLogRDD
	 * @return
	 */
	private static JavaPairRDD<String, AccessLogInfo> mapAppLogRDD2Pair(JavaRDD<String> appLogRDD){
		return appLogRDD.mapToPair(new PairFunction<String, String, AccessLogInfo>() {

			private static final long serialVersionUID = 1L;

			//accessLog是对应文件中的一行数据
			public Tuple2<String, AccessLogInfo> call(String accessLog) throws Exception {
				//根据\t对一行的数据进行分割
				String[] data = accessLog.split("\t");
				long timestamp = Long.parseLong(data[0]);
				String deviceId = data[1];
				long upTraffic = Long.parseLong(data[2]);
				long downTraffic = Long.parseLong(data[3]);
				
				AccessLogInfo info = new AccessLogInfo(timestamp,upTraffic,downTraffic);
				return new Tuple2<String, AccessLogInfo>(deviceId,info);
			}
		});
	}
	/**
	 * 将JavaPairRDD<String, AccessLogInfo>进行聚合
	 * @param appLogPairRDD
	 * @return
	 */
	private static JavaPairRDD<String, AccessLogInfo> aggregateByDevice(JavaPairRDD<String, AccessLogInfo> appLogPairRDD){
		return appLogPairRDD.reduceByKey(new Function2<AccessLogInfo, AccessLogInfo, AccessLogInfo>() {
			
			private static final long serialVersionUID = 1L;

			public AccessLogInfo call(AccessLogInfo v1, AccessLogInfo v2) throws Exception {
				//最早的访问时间
				long timestamp = v1.getTimestamp() < v2.getTimestamp() ? v1.getTimestamp() : v2.getTimestamp();
				long upTraffic = v1.getUpTraffic() + v2.getUpTraffic();//总上行流量
				long downTraffic = v1.getDownTraffic() + v2.getDownTraffic();//总下行流量
				return new AccessLogInfo(timestamp,upTraffic,downTraffic);
			}
		});
	}
	
	/**
	 * 将JavaPairRDD<String, AccessLogInfo>转为JavaPairRDD<AccessLogSortKey, String >便于后面的排序
	 */
	private static JavaPairRDD<AccessLogSortKey, String > mapRDDKey2SortKey(JavaPairRDD<String, AccessLogInfo> aggregateRDD){
		return aggregateRDD.mapToPair(new PairFunction<Tuple2<String,AccessLogInfo>,AccessLogSortKey, String >() {
			private static final long serialVersionUID = 1L;
			public Tuple2<AccessLogSortKey, String> call(Tuple2<String, AccessLogInfo> t) throws Exception {
				String deviceId = t._1;
				AccessLogInfo info = t._2;
				AccessLogSortKey sortKey = new AccessLogSortKey(info.getTimestamp(),info.getUpTraffic(),info.getDownTraffic()	);
				return new Tuple2<AccessLogSortKey, String>(sortKey,deviceId);
			}
		});
	}
}

执行后，打印出的日志