hadoop2.2.0 MapReduce的序列化
package com.my.hadoop.mapreduce.dataformat;
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.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import com.my.hadoop.common.Configs;
/**
* hadoop的序列化
* @author yao
*
*/
public class DataCount {
static class DTMap extends Mapper<LongWritable, Text, Text, DataBean>{
DataBean dataBean = null;
@Override
public void map(LongWritable key, Text value, Context context) throws IOException ,InterruptedException {
String[] fields = value.toString().split("\t");
String telNo = fields[1];
long upPayLoad = Long.parseLong(fields[8]);
long downPayLoad = Long.parseLong(fields[9]);
dataBean = new DataBean(telNo, upPayLoad, downPayLoad);
context.write(new Text(telNo), dataBean);
}
}
static class DTReduce extends Reducer<Text, DataBean, Text, DataBean>{
@Override
public void reduce(Text key, Iterable<DataBean> dataBeans, Context context) throws IOException ,InterruptedException {
long upPayLoad = 0;
long downPayLoad = 0;
for (DataBean dataBean : dataBeans) {
upPayLoad += dataBean.getUpPayLoad();
downPayLoad += dataBean.getDownPayLoad();
}
DataBean dataBean = new DataBean("", upPayLoad, downPayLoad);
context.write(key, dataBean);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = Configs.getConfigInstance();
String[] paths = new GenericOptionsParser(conf, args).getRemainingArgs();
if (paths.length != 2) {
System.err.println("Usage: " + DataCount.class.getName() + " <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, DataCount.class.getSimpleName());
job.setJarByClass(DataCount.class); //设置main函数所在的类
FileInputFormat.setInputPaths(job, new Path(args[0]));
job.setMapperClass(DTMap.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(DataBean.class);
job.setReducerClass(DTReduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(DataBean.class);
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1); //等待MapReduce执行完成并打印作业进度详情
}
}
/**
* 实现Writable接口,重写Write方法和readFields方法,严格按字段顺序进行写入写出
* @author yao
*
*/
class DataBean implements Writable {
private String telNo;
private long upPayLoad;
private long downPayLoad;
private long totalPayLoad;
public DataBean(){
}
public DataBean(String telNo, long upPayLoad, long downPayLoad) {
super();
this.telNo = telNo;
this.upPayLoad = upPayLoad;
this.downPayLoad = downPayLoad;
this.totalPayLoad = upPayLoad + downPayLoad;
}
@Override
public void readFields(DataInput in) throws IOException {
this.telNo = in.readUTF();
this.upPayLoad = in.readLong();
this.downPayLoad = in.readLong();
this.totalPayLoad = in.readLong();
}
@Override
public void write(DataOutput out) throws IOException {
out.writeUTF(telNo);
out.writeLong(upPayLoad);
out.writeLong(downPayLoad);
out.writeLong(totalPayLoad);
}
@Override
public String toString() {
return this.telNo+"\t"+this.upPayLoad+"\t"+this.downPayLoad+"\t"+this.totalPayLoad;
}
public String getTelNo() {
return telNo;
}
public void setTelNo(String telNo) {
this.telNo = telNo;
}
public long getUpPayLoad() {
return upPayLoad;
}
public void setUpPayLoad(long upPayLoad) {
this.upPayLoad = upPayLoad;
}
public long getDownPayLoad() {
return downPayLoad;
}
public void setDownPayLoad(long downPayLoad) {
this.downPayLoad = downPayLoad;
}
public long getTotalPayLoad() {
return totalPayLoad;
}
public void setTotalPayLoad(long totalPayLoad) {
this.totalPayLoad = totalPayLoad;
}
}
hadoop2.2.0 MapReduce的序列化的更多相关文章
- hadoop2.2.0 MapReduce求和并排序
javabean必须实现WritableComparable接口,并实现该接口的序列化,反序列话和比较方法 package com.my.hadoop.mapreduce.sort; import j ...
- hadoop2.2.0 MapReduce分区
package com.my.hadoop.mapreduce.partition; import java.util.HashMap;import java.util.Map; import org ...
- 国内最全最详细的hadoop2.2.0集群的MapReduce的最简单配置
简介 hadoop2的中的MapReduce不再是hadoop1中的结构已经没有了JobTracker,而是分解成ResourceManager和ApplicationMaster.这次大变革被称为M ...
- 编写简单的Mapreduce程序并部署在Hadoop2.2.0上运行
今天主要来说说怎么在Hadoop2.2.0分布式上面运行写好的 Mapreduce 程序. 可以在eclipse写好程序,export或用fatjar打包成jar文件. 先给出这个程序所依赖的Mave ...
- Hadoop2.2.0 第一步完成MapReduce wordcount计算文本数量
1.完成Hadoop2.2.0单机版环境搭建之后需要利用一个例子程序来检验hadoop2 的mapreduce的功能 //启动hdfs和yarn sbin/start-dfs.sh sbin/star ...
- 【hadoop2.6.0】用C++ 编写mapreduce
hadoop通过hadoop streaming 来实现用非Java语言写的mapreduce代码. 对于一个一点Java都不会的我来说,这真是个天大的好消息. 官网上hadoop streaming ...
- 使用命令行编译打包运行自己的MapReduce程序 Hadoop2.6.0
使用命令行编译打包运行自己的MapReduce程序 Hadoop2.6.0 网上的 MapReduce WordCount 教程对于如何编译 WordCount.java 几乎是一笔带过… 而有写到的 ...
- Hadoop-2.2.0 (传 hadoop-2.2.0.tar.gz)
配置hadoop 2.1 上传hadoop包 2.2 解压hadoop包 首先在根目录下创建一个cloud目录 mkdir /cloud tar -zxvf hadoop-2.2.0.tar.gz - ...
- Hadoop2.2.0安装过程记录
1 安装环境1.1 客户端1.2 服务端1.3 安装准备 2 操作系统安装2.1.1 BIOS打开虚拟化支持2.1.2 关闭防火墙2.1.3 安装 ...
随机推荐
- Bottle 中文文档
译者: smallfish (smallfish.xy@gmail.com) 更新日期: 2009-09-25 原文地址: http://bottle.paws.de/page/docs (已失效) ...
- C++中将string类型转换为int, float, double类型 主要通过以下几种方式:
C++中将string类型转换为int, float, double类型 主要通过以下几种方式: # 方法一: 使用stringstream stringstream在int或float类型转换为 ...
- Java基础知识强化26:Object类之hashCode()方法、getClass()方法
1. Object类的hashCode()方法,如下: public int hashCode():返回该对象的哈希码值,这个值和地址值有关,但是不是实际地址值(哈希码值是根据实际地址值转化过来的 ...
- 一个简单的Verilog计数器模型
一个简单的Verilog计数器模型 功能说明: 向上计数 向下计数 预装载值 一.代码 1.counter代码(counter.v) module counter( input clk, input ...
- bootstrap字体图标
bootstrap字体图标 http://v3.bootcss.com/components/ <!DOCTYPE HTML> <html> <head> < ...
- 匹配不含有某个信息的sql语句写法
SELECT id,order_id,flight_info FROM order_flights WHERE mark=0 AND flight_info REGEXP '[^() DAY)]' O ...
- asp.net微信开发第六篇----高级群发(文本)
说到高级群发,微信的参考资料http://mp.weixin.qq.com/wiki/14/0c53fac3bdec3906aaa36987b91d64ea.html 首先我们先来讲解一下群发文本信息 ...
- ReportViewer2010冻结行列
<%@ Page Language="C#" AutoEventWireup="true" CodeBehind="NewTrackingVer ...
- 回传值(代理、通知、block)
回传值问题,一直都是困扰初学者的问题,今写者 代理.通知.block 三者的回传值做了一个小小的总结, Main.storyboard 视图: 通过代码分别创建三个代表 代理.通知.block 的按钮 ...
- 武汉科技大学ACM :1004: 零起点学算法74——Palindromes _easy version
Problem Description “回文串”是一个正读和反读都一样的字符串,比如“level”或者“noon”等等就是回文串.请写一个程序判断读入的字符串是否是“回文”. Input 输入包含多 ...