hadoop流行音乐排行榜实例

阅读: 评论:0

hadoop流行音乐排行榜实例

hadoop流行音乐排行榜实例

前言

本实例是本人在课设上的作品,为本人原创,文中有设计思路和核心算法,若本人在理解上有问题或者代码还需优化的地方,欢迎一起讨论。

实例描述

现在在网上听歌的人越来越多,有些人听自己常听的歌,厌倦了想听新歌曲,但是又不知道去哪找,如果有音乐排行榜就可以解决这一问题。所以做一个最受欢迎单曲统计程序很有价值也很实用。普通的音乐处理程序无法解决互联网上的巨量信息,我们所学的hadoop分布式恰恰可以处理大数据,所以用hadoop的mapreduce来解决最受欢迎单曲统计这个问题再好不过了。

业务逻辑

  1. 输入n个文件
  2. 读取n个文件内容
  3. 统计每个单曲的数量
  4. 比较每个单曲数量,得出排名

难点

  1. 是不是要考虑一些几个单词组成的歌曲,要重新设计如何从文件中获取每首歌曲
  2. 对于生成的文件,如何进行排序
/*
*@name class:MusicLine.java
*@function 实现分割文本文件歌曲
*/package musicrank.tiger;import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;public class MusicLine {private String music;private IntWritable one = new IntWritable(1);// the flag represent the data is availableprivate boolean right = true;public MusicLine(String musicLine) {// to test whether a row of data is reasonableif (musicLine == null || "".equals(musicLine)) {this.right = false;return;}String[] strs = musicLine.split("//"); // the music split by //
/*      if (strs.length < 2) {this.right = false;return;}*/this.music = strs[0];}public boolean isRight() {return right;}/** @param return map -- key* * @return* */public Text getMusicCountMapOutKey() {return new Text(this.music);}/** @param return map -- value* * @return* */public IntWritable getMusicCountMapOutValue() {;}
}
/*
*@name class:MusicMapper.java
*@function 将key和value写入map(key,value)
*/package musicrank.tiger;import java.io.IOException;
import java.util.StringTokenizer;import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;// 创建一个 WordMapper类 继承于 Mapper抽象类
public class MusicMapper extends Mapper<Object, Text, Text, IntWritable> {private final static IntWritable one = new IntWritable(1);private Text word = new Text();// Mapper抽象类的核心方法,三个参数public void map(Object key, // 首字符偏移量Text value, // 文件的一行内容Context context) // Mapper端的上下文,与 OutputCollector 和 Reporter 的功能类似throws IOException, InterruptedException {/** StringTokenizer itr = new String()); while* (itr.hasMoreTokens()) { word.Token());* context.write(word, one);*/MusicLine musicLine = new String());if (musicLine.isRight()) {context.MusicCountMapOutKey(), MusicCountMapOutValue());}}
}
/*
*@name class:MusicReducer.java
*@function 通过遍历values,根据key对应的value个数重新计算key的值,然后通过context.write写入
*/package musicrank.tiger;import java.io.IOException;import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;// 创建一个 WordReducer类 继承于 Reducer抽象类
public class MusicReducer extends Reducer<Text, IntWritable, Text, IntWritable> {private IntWritable result = new IntWritable(); // 用于记录 key 的最终的词频数// Reducer抽象类的核心方法,三个参数public void reduce(Text key, // Map端 输出的 key 值Iterable<IntWritable> values, // Map端 输出的 Value 集合(相同key的集合)Context context) // Reduce 端的上下文,与 OutputCollector 和 Reporter 的功能类似throws IOException, InterruptedException {int sum = 0;for (IntWritable val : values) // 遍历 values集合,并把值相加{sum += ();}result.set(sum); // 得到最终词频数context.write(key, result); // 写入结果}
}
/*
*@name class:MusicMapSort.java 
*@function 继承于IntWritable.Comparator,实现对map(key,value)进行排序
*/package musicrank.tiger;import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.WritableComparator;public class MusicMapSort extends IntWritable.Comparator{public int compare(WritableComparator a,WritableComparator b) {return -superpare(a, b);}public int compare(byte[]b1,int s1,int l1,byte[]b2,int s2,int l2) {return -superpare(b1, s1, l1, b2, s2, l2);}
}
/*
*@name class:MusicMain.java
*@function 主函数,对功能的 实现
*/package musicrank.tiger;import java.util.Random;import org.f.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparator;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.map.InverseMapper;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;public class MusicMain {public static void main(String[] args) throws Exception {// Configuration类:读取Hadoop的配置文件,如 ;// 也可用set方法重新设置(会覆盖):conf.set("fs.default.name", "hdfs://xxxx:9000")Configuration conf = new Configuration();// 将命令行中参数自动设置到变量conf中String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();/*** 这里必须有输入输出*/if (otherArgs.length != 2) {println("Usage: wordcount <in> <out>");it(2);}Path tempDir = new Path("wordcount-temp-" + String(new Random().nextInt(Integer.MAX_VALUE)));@SuppressWarnings("deprecation")Job job = new Job(conf, "word count"); // 新建一个 job,传入配置信息job.setJarByClass(MusicMain.class); // 设置 job 的主类try {job.setMapperClass(MusicMapper.class);// 设置 job 的 Mapper 类job.setCombinerClass(MusicReducer.class); // 设置 job 的 作业合成类job.setReducerClass(MusicReducer.class); // 设置 job 的 Reducer 类job.setOutputKeyClass(Text.class); // 设置 job 输出数据的关键类job.setOutputValueClass(IntWritable.class); // 设置 job 输出值类FileInputFormat.addInputPath(job, new Path(otherArgs[0])); // 文件输入FileOutputFormat.setOutputPath(job, tempDir); // temp dir// FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); //// 文件输出job.setOutputFormatClass(SequenceFileOutputFormat.class);if (job.waitForCompletion(true)) {Job sortJob = new Job(conf, "sort");sortJob.setJarByClass(MusicMain.class);FileInputFormat.addInputPath(sortJob, tempDir);sortJob.setInputFormatClass(SequenceFileInputFormat.class);sortJob.setMapperClass(InverseMapper.class);sortJob.setNumReduceTasks(1);FileOutputFormat.setOutputPath(sortJob, new Path(otherArgs[1]));sortJob.setOutputKeyClass(IntWritable.class);sortJob.setOutputValueClass(Text.class);sortJob.setSortComparatorClass(MusicMapSort.class);it(sortJob.waitForCompletion(true) ? 0 : 1); // 等待完成退出}} finally {(conf).deleteOnExit(tempDir);}}
}

测试用例

As long as you love me//
Baby//
Love Yourself//
Sorry//
My Boyfriend Is Gay//
Sugar//
Cold//
Let Me Love You//
Feeling U//
Stronger//Faded//
I Am You//
Time Machine//
What Are Words//
Black Black Heart//
Sketch Plane//
We Are One//
Boyfriend//
Animals//Animals//
Booty Music//
Booty Music//
Booty Music//
Booty Music//
As long as you love me//
As long as you love me//
As long as you love me//
As long as you love me//
Let Her Go//La La La//Walk Away//
Baby//
Baby//
Baby//
Love Yourself//
Love Yourself//
Love Yourself//
Love Yourself//
Love Yourself//
As long as you love me//
As long as you love me//
As long as you love me//
As long as you love me//
As long as you love me//
Baby//
Love Yourself//
Sorry//
My Boyfriend Is Gay//
Sugar//
Cold//
Let Me Love You//
Feeling U//
Stronger//
Faded//
I Am You//
Time Machine//
What Are Words//
Black Black Heart//
Sketch Plane//
We Are One//
Boyfriend//
Animals//
Animals//
Booty Music//
Booty Music//
Booty Music//
Booty Music//
As long as you love me//
As long as you love me//
As long as you love me//
As long as you love me//
Let Her Go//
La La La//
Walk Away//
Baby//
Baby//
Baby//
Love Yourself//
Love Yourself//
Love Yourself//
Love Yourself//
Love Yourself//
As long as you love me//
As long as you love me//
As long as you love me//
As long as you love me//
Free Loop//
Top Of The World//
Solo Dance//
Until You//
Numb//
Numb//
Numb//
Numb//
Numb//
Numb//
Numb//
Numb//
Communication//
I just Wanna Run

As long as you love me//
Baby//
Love Yourself//
Sorry//
My Boyfriend Is Gay//
Sugar//
Cold//
Let Me Love You//
Feeling U//
Stronger//Faded//
I Am You//
Time Machine//
What Are Words//
Black Black Heart//
Sketch Plane//
We Are One//
Boyfriend//
Animals//Animals//
Booty Music//
Booty Music//
Booty Music//
Booty Music//
As long as you love me//
As long as you love me//
As long as you love me//
As long as you love me//
Let Her Go//La La La//Walk Away//
Baby//
Baby//
Baby//
Love Yourself//
Love Yourself//
Love Yourself//
Love Yourself//
Love Yourself//
As long as you love me//
As long as you love me//
As long as you love me//
As long as you love me//
As long as you love me//
Baby//
Love Yourself//
Sorry//
My Boyfriend Is Gay//
Sugar//
Cold//
Let Me Love You//
Feeling U//
Stronger//
Faded//
I Am You//
Time Machine//
What Are Words//
Black Black Heart//
Sketch Plane//
We Are One//
Boyfriend//
Animals//
Animals//
Booty Music//
Booty Music//
Booty Music//
Booty Music//
As long as you love me//
As long as you love me//
As long as you love me//
As long as you love me//
Let Her Go//
La La La//
Walk Away//
Baby//
Baby//
Baby//
Love Yourself//
Love Yourself//
Love Yourself//
Love Yourself//
Love Yourself//
As long as you love me//
As long as you love me//
As long as you love me//
As long as you love me//
Black Black Heart//
Sketch Plane//
We Are One//
Boyfriend//
Animals//
Animals//
Booty Music

结果

本文发布于:2024-01-27 18:01:34,感谢您对本站的认可!

本文链接:https://www.4u4v.net/it/17063496961783.html

版权声明:本站内容均来自互联网,仅供演示用,请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系,我们将在24小时内删除。

标签:音乐排行榜   实例   hadoop
留言与评论(共有 0 条评论)
   
验证码:

Copyright ©2019-2022 Comsenz Inc.Powered by ©

网站地图1 网站地图2 网站地图3 网站地图4 网站地图5 网站地图6 网站地图7 网站地图8 网站地图9 网站地图10 网站地图11 网站地图12 网站地图13 网站地图14 网站地图15 网站地图16 网站地图17 网站地图18 网站地图19 网站地图20 网站地图21 网站地图22/a> 网站地图23