Hadoop MapReduce的一些相关代码Code

MapReduce是一种分布式计算模型（distributed programming model），由Google于2004年左右提出，主要用于搜索领域，解决海量数据的计算问题。

MapReduce由两个阶段组成：即Map阶段和Reduce阶段，用户需要实现map()函数和reduce()函数，用于实现分布式计算。

1、WordCountApp.java

package cmd;

import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCountApp extends Configured implements Tool{
	static String INPUT_PATH = "";
	static String OUT_PATH = "";
	
	@Override
	public int run(String[] arg0) throws Exception {
		INPUT_PATH = arg0[0];
		OUT_PATH = arg0[1];
		
		Configuration conf = new Configuration();
		final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), conf);
		final Path outPath = new Path(OUT_PATH);
		if(fileSystem.exists(outPath)){
			fileSystem.delete(outPath, true);
		}
		
		final Job job = new Job(conf , WordCountApp.class.getSimpleName());
		//打包运行必须执行的秘密方法
		job.setJarByClass(WordCountApp.class);
		
		//1.1指定读取的文件位于哪里
		FileInputFormat.setInputPaths(job, INPUT_PATH);
		//指定如何对输入文件进行格式化，把输入文件每一行解析成键值对
		//job.setInputFormatClass(TextInputFormat.class);
		
		//1.2 指定自定义的map类
		job.setMapperClass(MyMapper.class);
		//map输出的<k,v>类型。如果<k3,v3>的类型与<k2,v2>类型一致，则可以省略
		//job.setMapOutputKeyClass(Text.class);
		//job.setMapOutputValueClass(LongWritable.class);
		
		//1.3 分区
		//job.setPartitionerClass(HashPartitioner.class);
		//有一个reduce任务运行
		//job.setNumReduceTasks(1);
		
		//1.4 TODO 排序、分组
		
		//1.5 TODO 规约
		
		//2.2 指定自定义reduce类
		job.setReducerClass(MyReducer.class);
		//指定reduce的输出类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(LongWritable.class);
		
		//2.3 指定写出到哪里
		FileOutputFormat.setOutputPath(job, outPath);
		//指定输出文件的格式化类
		//job.setOutputFormatClass(TextOutputFormat.class);
		
		//把job提交给JobTracker运行
		job.waitForCompletion(true);
		return 0;
	}
	
	public static void main(String[] args) throws Exception {
		ToolRunner.run(new WordCountApp(), args);
	}
	
	/**
	 * KEYIN	即k1		表示行的偏移量
	 * VALUEIN	即v1		表示行文本内容
	 * KEYOUT	即k2		表示行中出现的单词
	 * VALUEOUT	即v2		表示行中出现的单词的次数，固定值1
	 */
	static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable>{
		protected void map(LongWritable k1, Text v1, Context context) throws java.io.IOException ,InterruptedException {
			final String[] splited = v1.toString().split("\t");
			for (String word : splited) {
				context.write(new Text(word), new LongWritable(1));
			}
		};
	}
	
	/**
	 * KEYIN	即k2		表示行中出现的单词
	 * VALUEIN	即v2		表示行中出现的单词的次数
	 * KEYOUT	即k3		表示文本中出现的不同单词
	 * VALUEOUT	即v3		表示文本中出现的不同单词的总次数
	 *
	 */
	static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable>{
		protected void reduce(Text k2, java.lang.Iterable<LongWritable> v2s, Context ctx) throws java.io.IOException ,InterruptedException {
			long times = 0L;
			for (LongWritable count : v2s) {
				times += count.get();
			}
			ctx.write(k2, new LongWritable(times));
		};
	}

		
}

2、GroupApp.java

package group;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.RawComparator;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;

public class GroupApp {
	static final String INPUT_PATH = "hdfs://cloud4:9000/input";
	static final String OUT_PATH = "hdfs://cloud4:9000/out";
	public static void main(String[] args) throws Exception{
		final Configuration configuration = new Configuration();
		
		final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), configuration);
		if(fileSystem.exists(new Path(OUT_PATH))){
			fileSystem.delete(new Path(OUT_PATH), true);
		}
		
		final Job job = new Job(configuration, GroupApp.class.getSimpleName());
		
		//1.1 指定输入文件路径
		FileInputFormat.setInputPaths(job, INPUT_PATH);
		//指定哪个类用来格式化输入文件
		job.setInputFormatClass(TextInputFormat.class);
		
		//1.2指定自定义的Mapper类
		job.setMapperClass(MyMapper.class);
		//指定输出<k2,v2>的类型
		job.setMapOutputKeyClass(NewK2.class);
		job.setMapOutputValueClass(LongWritable.class);
		
		//1.3 指定分区类
		job.setPartitionerClass(HashPartitioner.class);
		job.setNumReduceTasks(1);
		
		//1.4 TODO 排序、分区
		job.setGroupingComparatorClass(MyGroupingComparator.class);
		//1.5  TODO （可选）合并
		
		//2.2 指定自定义的reduce类
		job.setReducerClass(MyReducer.class);
		//指定输出<k3,v3>的类型
		job.setOutputKeyClass(LongWritable.class);
		job.setOutputValueClass(LongWritable.class);
		
		//2.3 指定输出到哪里
		FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
		//设定输出文件的格式化类
		job.setOutputFormatClass(TextOutputFormat.class);
		
		//把代码提交给JobTracker执行
		job.waitForCompletion(true);
	}

	
	static class MyMapper extends Mapper<LongWritable, Text, NewK2, LongWritable>{
		protected void map(LongWritable key, Text value, org.apache.hadoop.mapreduce.Mapper<LongWritable,Text,NewK2,LongWritable>.Context context) throws java.io.IOException ,InterruptedException {
			final String[] splited = value.toString().split("\t");
			final NewK2 k2 = new NewK2(Long.parseLong(splited[0]), Long.parseLong(splited[1]));
			final LongWritable v2 = new LongWritable(Long.parseLong(splited[1]));
			context.write(k2, v2);
		};
	}
	
	static class MyReducer extends Reducer<NewK2, LongWritable, LongWritable, LongWritable>{
		protected void reduce(NewK2 k2, java.lang.Iterable<LongWritable> v2s, org.apache.hadoop.mapreduce.Reducer<NewK2,LongWritable,LongWritable,LongWritable>.Context context) throws java.io.IOException ,InterruptedException {
			long min = Long.MAX_VALUE;
			for (LongWritable v2 : v2s) {
				if(v2.get()<min){
					min = v2.get();
				}
			}
			
			context.write(new LongWritable(k2.first), new LongWritable(min));
		};
	}
	
	/**
	 * 问：为什么实现该类？
	 * 答：因为原来的v2不能参与排序，把原来的k2和v2封装到一个类中，作为新的k2
	 *
	 */
	static class  NewK2 implements WritableComparable<NewK2>{
		Long first;
		Long second;
		
		public NewK2(){}
		
		public NewK2(long first, long second){
			this.first = first;
			this.second = second;
		}
		
		
		@Override
		public void readFields(DataInput in) throws IOException {
			this.first = in.readLong();
			this.second = in.readLong();
		}

		@Override
		public void write(DataOutput out) throws IOException {
			out.writeLong(first);
			out.writeLong(second);
		}

		/**
		 * 当k2进行排序时，会调用该方法.
		 * 当第一列不同时，升序；当第一列相同时，第二列升序
		 */
		@Override
		public int compareTo(NewK2 o) {
			final long minus = this.first - o.first;
			if(minus !=0){
				return (int)minus;
			}
			return (int)(this.second - o.second);
		}
		
		@Override
		public int hashCode() {
			return this.first.hashCode()+this.second.hashCode();
		}
		
		@Override
		public boolean equals(Object obj) {
			if(!(obj instanceof NewK2)){
				return false;
			}
			NewK2 oK2 = (NewK2)obj;
			return (this.first==oK2.first)&&(this.second==oK2.second);
		}
	}
	
	/**
	 * 问：为什么自定义该类？
	 * 答：业务要求分组是按照第一列分组，但是NewK2的比较规则决定了不能按照第一列分。只能自定义分组比较器。
	 */
	static class MyGroupingComparator implements RawComparator<NewK2>{

		@Override
		public int compare(NewK2 o1, NewK2 o2) {
			return (int)(o1.first - o2.first);
		}
		/**
		 * @param arg0 表示第一个参与比较的字节数组
		 * @param arg1 表示第一个参与比较的字节数组的起始位置
		 * @param arg2 表示第一个参与比较的字节数组的偏移量
		 * 
		 * @param arg3 表示第二个参与比较的字节数组
		 * @param arg4 表示第二个参与比较的字节数组的起始位置
		 * @param arg5 表示第二个参与比较的字节数组的偏移量
		 */
		@Override
		public int compare(byte[] arg0, int arg1, int arg2, byte[] arg3,
				int arg4, int arg5) {
			return WritableComparator.compareBytes(arg0, arg1, 8, arg3, arg4, 8);
		}
		
	}
}

3、data

#当第一列相同时，求出第二列的最小值
3	3
3	2
3	1
2	2
2	1
1	1
-------------------
3	1
2	1
1	1

4、KpiApp.java

package mapreduce;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;

public class KpiApp {
	static final String INPUT_PATH = "hdfs://cloud4:9000/wlan";
	static final String OUT_PATH = "hdfs://cloud4:9000/out";
	public static void main(String[] args) throws Exception{
		final Job job = new Job(new Configuration(), KpiApp.class.getSimpleName());
		//1.1 指定输入文件路径
		FileInputFormat.setInputPaths(job, INPUT_PATH);
		//指定哪个类用来格式化输入文件
		job.setInputFormatClass(TextInputFormat.class);
		
		//1.2指定自定义的Mapper类
		job.setMapperClass(MyMapper.class);
		//指定输出<k2,v2>的类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(KpiWritable.class);
		
		//1.3 指定分区类
		job.setPartitionerClass(HashPartitioner.class);
		job.setNumReduceTasks(1);
		
		//1.4 TODO 排序、分区
		
		//1.5  TODO （可选）合并
		
		//2.2 指定自定义的reduce类
		job.setReducerClass(MyReducer.class);
		//指定输出<k3,v3>的类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(KpiWritable.class);
		
		//2.3 指定输出到哪里
		FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
		//设定输出文件的格式化类
		job.setOutputFormatClass(TextOutputFormat.class);
		
		//把代码提交给JobTracker执行
		job.waitForCompletion(true);
	}

	static class MyMapper extends Mapper<LongWritable, Text, Text, KpiWritable>{
		protected void map(LongWritable key, Text value, org.apache.hadoop.mapreduce.Mapper<LongWritable,Text,Text,KpiWritable>.Context context) throws IOException ,InterruptedException {
			final String[] splited = value.toString().split("\t");
			final String msisdn = splited[1];
			final Text k2 = new Text(msisdn);
			final KpiWritable v2 = new KpiWritable(splited[6],splited[7],splited[8],splited[9]);
			context.write(k2, v2);
		};
	}
	
	static class MyReducer extends Reducer<Text, KpiWritable, Text, KpiWritable>{
		/**
		 * @param	k2	表示整个文件中不同的手机号码	
		 * @param	v2s	表示该手机号在不同时段的流量的集合
		 */
		protected void reduce(Text k2, java.lang.Iterable<KpiWritable> v2s, org.apache.hadoop.mapreduce.Reducer<Text,KpiWritable,Text,KpiWritable>.Context context) throws IOException ,InterruptedException {
			long upPackNum = 0L;
			long downPackNum = 0L;
			long upPayLoad = 0L;
			long downPayLoad = 0L;
			
			for (KpiWritable kpiWritable : v2s) {
				upPackNum += kpiWritable.upPackNum;
				downPackNum += kpiWritable.downPackNum;
				upPayLoad += kpiWritable.upPayLoad;
				downPayLoad += kpiWritable.downPayLoad;
			}
			
			final KpiWritable v3 = new KpiWritable(upPackNum+"", downPackNum+"", upPayLoad+"", downPayLoad+"");
			context.write(k2, v3);
		};
	}
}

class KpiWritable implements Writable{
	long upPackNum;
	long downPackNum;
	long upPayLoad;
	long downPayLoad;
	
	public KpiWritable(){}
	
	public KpiWritable(String upPackNum, String downPackNum, String upPayLoad, String downPayLoad){
		this.upPackNum = Long.parseLong(upPackNum);
		this.downPackNum = Long.parseLong(downPackNum);
		this.upPayLoad = Long.parseLong(upPayLoad);
		this.downPayLoad = Long.parseLong(downPayLoad);
	}
	
	
	@Override
	public void readFields(DataInput in) throws IOException {
		this.upPackNum = in.readLong();
		this.downPackNum = in.readLong();
		this.upPayLoad = in.readLong();
		this.downPayLoad = in.readLong();
	}

	@Override
	public void write(DataOutput out) throws IOException {
		out.writeLong(upPackNum);
		out.writeLong(downPackNum);
		out.writeLong(upPayLoad);
		out.writeLong(downPayLoad);
	}
	
	@Override
	public String toString() {
		return upPackNum + "\t" + downPackNum + "\t" + upPayLoad + "\t" + downPayLoad;
	}
}

5、SortApp.java

package sort;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;

public class SortApp {
	static final String INPUT_PATH = "hdfs://cloud4:9000/input";
	static final String OUT_PATH = "hdfs://cloud4:9000/out";
	public static void main(String[] args) throws Exception{
		final Configuration configuration = new Configuration();
		
		final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), configuration);
		if(fileSystem.exists(new Path(OUT_PATH))){
			fileSystem.delete(new Path(OUT_PATH), true);
		}
		
		final Job job = new Job(configuration, SortApp.class.getSimpleName());
		
		//1.1 指定输入文件路径
		FileInputFormat.setInputPaths(job, INPUT_PATH);
		//指定哪个类用来格式化输入文件
		job.setInputFormatClass(TextInputFormat.class);
		
		//1.2指定自定义的Mapper类
		job.setMapperClass(MyMapper.class);
		//指定输出<k2,v2>的类型
		job.setMapOutputKeyClass(NewK2.class);
		job.setMapOutputValueClass(LongWritable.class);
		
		//1.3 指定分区类
		job.setPartitionerClass(HashPartitioner.class);
		job.setNumReduceTasks(1);
		
		//1.4 TODO 排序、分区
		
		//1.5  TODO （可选）合并
		
		//2.2 指定自定义的reduce类
		job.setReducerClass(MyReducer.class);
		//指定输出<k3,v3>的类型
		job.setOutputKeyClass(LongWritable.class);
		job.setOutputValueClass(LongWritable.class);
		
		//2.3 指定输出到哪里
		FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
		//设定输出文件的格式化类
		job.setOutputFormatClass(TextOutputFormat.class);
		
		//把代码提交给JobTracker执行
		job.waitForCompletion(true);
	}

	
	static class MyMapper extends Mapper<LongWritable, Text, NewK2, LongWritable>{
		protected void map(LongWritable key, Text value, org.apache.hadoop.mapreduce.Mapper<LongWritable,Text,NewK2,LongWritable>.Context context) throws java.io.IOException ,InterruptedException {
			final String[] splited = value.toString().split("\t");
			final NewK2 k2 = new NewK2(Long.parseLong(splited[0]), Long.parseLong(splited[1]));
			final LongWritable v2 = new LongWritable(Long.parseLong(splited[1]));
			context.write(k2, v2);
		};
	}
	
	static class MyReducer extends Reducer<NewK2, LongWritable, LongWritable, LongWritable>{
		protected void reduce(NewK2 k2, java.lang.Iterable<LongWritable> v2s, org.apache.hadoop.mapreduce.Reducer<NewK2,LongWritable,LongWritable,LongWritable>.Context context) throws java.io.IOException ,InterruptedException {
			context.write(new LongWritable(k2.first), new LongWritable(k2.second));
		};
	}
	
	/**
	 * 问：为什么实现该类？
	 * 答：因为原来的v2不能参与排序，把原来的k2和v2封装到一个类中，作为新的k2
	 *
	 */
	static class  NewK2 implements WritableComparable<NewK2>{
		Long first;
		Long second;
		
		public NewK2(){}
		
		public NewK2(long first, long second){
			this.first = first;
			this.second = second;
		}
		
		
		@Override
		public void readFields(DataInput in) throws IOException {
			this.first = in.readLong();
			this.second = in.readLong();
		}

		@Override
		public void write(DataOutput out) throws IOException {
			out.writeLong(first);
			out.writeLong(second);
		}

		/**
		 * 当k2进行排序时，会调用该方法.
		 * 当第一列不同时，升序；当第一列相同时，第二列升序
		 */
		@Override
		public int compareTo(NewK2 o) {
			final long minus = this.first - o.first;
			if(minus !=0){
				return (int)minus;
			}
			return (int)(this.second - o.second);
		}
		
		@Override
		public int hashCode() {
			return this.first.hashCode()+this.second.hashCode();
		}
		
		@Override
		public boolean equals(Object obj) {
			if(!(obj instanceof NewK2)){
				return false;
			}
			NewK2 oK2 = (NewK2)obj;
			return (this.first==oK2.first)&&(this.second==oK2.second);
		}
	}
	
}

6、TopKApp.java

package suanfa;

import java.net.URI;

import mapreduce.WordCountApp;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
 * 作业：求最大的100个值
 */
public class TopKApp {
	static final String INPUT_PATH = "hdfs://cloud4:9000/input";
	static final String OUT_PATH = "hdfs://cloud4:9000/out";
	
	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), conf);
		final Path outPath = new Path(OUT_PATH);
		if(fileSystem.exists(outPath)){
			fileSystem.delete(outPath, true);
		}
		
		final Job job = new Job(conf , WordCountApp.class.getSimpleName());
		FileInputFormat.setInputPaths(job, INPUT_PATH);
		job.setMapperClass(MyMapper.class);
		job.setReducerClass(MyReducer.class);
		job.setOutputKeyClass(LongWritable.class);
		job.setOutputValueClass(NullWritable.class);
		FileOutputFormat.setOutputPath(job, outPath);
		job.waitForCompletion(true);
	}
	static class MyMapper extends Mapper<LongWritable, Text, LongWritable, NullWritable>{
		long max = Long.MIN_VALUE;
		protected void map(LongWritable k1, Text v1, Context context) throws java.io.IOException ,InterruptedException {
			final long temp = Long.parseLong(v1.toString());
			if(temp>max){
				max = temp;
			}
		};
		
		protected void cleanup(org.apache.hadoop.mapreduce.Mapper<LongWritable,Text,LongWritable, NullWritable>.Context context) throws java.io.IOException ,InterruptedException {
			context.write(new LongWritable(max), NullWritable.get());
		};
	}
	
	static class MyReducer extends Reducer<LongWritable, NullWritable, LongWritable, NullWritable>{
		long max = Long.MIN_VALUE;
		protected void reduce(LongWritable k2, java.lang.Iterable<NullWritable> arg1, org.apache.hadoop.mapreduce.Reducer<LongWritable,NullWritable,LongWritable,NullWritable>.Context arg2) throws java.io.IOException ,InterruptedException {
			final long temp = k2.get();
			if(temp>max){
				max = temp;
			}
		};
		
		protected void cleanup(org.apache.hadoop.mapreduce.Reducer<LongWritable,NullWritable,LongWritable,NullWritable>.Context context) throws java.io.IOException ,InterruptedException {
			context.write(new LongWritable(max), NullWritable.get());
		};
	}		
}