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
- OD: DEP - Ret2Libc via VirtualProtect() & VirtualAlloc()
一,通过 VirutalProtect() 修改内存属性绕过 DEP DEP 的四种工作模式中,OptOut 和 AlwaysOn 下所有进程默认都开启 DEP 保护,这里如果一个程序自身需要从堆栈中 ...
- java图片缩放
package com.rubekid.springmvc.utils; import java.awt.AlphaComposite; import java.awt.Graphics2D; imp ...
- (转)JQuery中$.ajax()方法参数详解
url: 要求为String类型的参数,(默认为当前页地址)发送请求的地址. type: 要求为String类型的参数,请求方式(post或get)默认为get.注意其他http请求方法,例如put和 ...
- Andoid源码 BUG修改集合--不断更新
BUG001:很抱歉,***已停止运行 网上查找问题原因很多,有人说事缓存不够,作为一个开发者,需要从代码解决问题 比如,这次遇到一个"很抱歉,instant已停止运行",inst ...
- linux学习笔记<命令介绍>
主要介绍日常工作中一些常用的命令,内容均整理自慕课网 命令提示符 [root@hgs ~]# 其中: root : 当前登录用户 hgs : 主机名 ~ : 当前所在目录(家目录),对于root用户, ...
- win8发布 wcf问题
WCF services don’t run on IIS 8 with the default configuration, because the webserver doesn’t know, ...
- Calling a C++ dll with unsigned char* parameters
unsigned char* 等价 BYTE* 例1: C++: int __stdcall LIVESCAN_GetFPRawData(int nChannel, unsigned char *p ...
- C#数组的使用
//计算数组中最大值,最小值,平均值和总和 //类中main最先执行 static void Main(string[] args) { //声明一个数组,数组长度一定固定就不能更改了 , , , , ...
- 【转】解读Qt 事件处理机制(上篇)
[转自]:http://mobile.51cto.com/symbian-272812.htm 在Qt中,事件被封装成一个个对象,所有的事件均继承自抽象类QEvent. 接下来依次谈谈Qt中有谁来产生 ...
- uva 755 - 487--3279
#include <iostream> #include <string> #include <map> #include <algorithm> #i ...