hadoop的伪分布环境下统计不同部门员工工资的总额，使用MapReduce来实现的详细步骤

实验三：要求请按照部门号，统计不同部门员工工资的总额，使用MapReduce来实现该实验。实验数据如下：

在eclipce里面编辑好Hadoop代码打成jar到本地，然后上传到hdfs上，建议上传到[root@WFB ~]# cd /training/hadoop-2.7.3/etc/hadoop/目录下

package com.liusong.MR;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;



public class SalaryTotalMain {

	public static void main(String[] args) throws Exception {
		//1、创建一个任务job =map + reduce
		Job job = Job.getInstance(new Configuration());
		 
		//2、指定任务的入口
		job.setJarByClass(SalaryTotalMain.class);
		
		//3、指定任务的map和输出的数据类型
		job.setMapperClass(SalaryTotalMapper.class);
		job.setMapOutputKeyClass(LongWritable.class);
		job.setMapOutputValueClass(LongWritable.class);
		
		//4、指定任务的reduce和输出的数据类型
		job.setReducerClass(SalaryTotalReducer.class);
		job.setOutputKeyClass(LongWritable.class);
		job.setOutputValueClass(LongWritable.class);
		
		//5、指定输入和输出的HDFS路径

		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		//6、提交任务
		job.waitForCompletion(true);
		

	}

}

package com.liusong.MR;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class SalaryTotalMapper  extends Mapper<LongWritable, Text, LongWritable, LongWritable>{

	@Override
	protected void map(LongWritable k1,Text v1, Context context) throws IOException,InterruptedException{
		
		//数据：7654，MARTIN，SALESMAN，7698,1981/9/28,1250/1400/30
		String data = v1.toString();
		
		//分词
		String[] words = data.split(",");
		
		//输出：k2  部门号，v2：员工薪水
		context.write(new LongWritable(Long.parseLong(words[7])), new LongWritable(Long.parseLong(words[5])));	
	}
}

package com.liusong.MR;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.mapreduce.Reducer;

public class SalaryTotalReducer extends Reducer<LongWritable, LongWritable, LongWritable, LongWritable> {
	
	@Override
	protected void reduce(LongWritable k3,Iterable<LongWritable> v3,Context context) throws IOException,InterruptedException{
		//得到v3，代表一个部门中一个员工的薪水
		long total = 0;
		for (LongWritable v : v3) {
			total = total + v.get();
		}
		
		//输出k4部门v4总额
		context.write(k3, new  LongWritable(total));
	}
	
}

 

上传后吧要上传的工作表上传到web上面去