1,代码

package mr;

import java.io.IOException;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.ArrayWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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; /**
* 使用ArrayWritable
*/
public class TrafficApp4 { public static void main(String[] args) throws Exception{
Configuration conf = new Configuration();
Job job = Job.getInstance(conf , TrafficApp4.class.getSimpleName());
job.setJarByClass(TrafficApp4.class); FileInputFormat.setInputPaths(job, args[]);
job.setMapperClass(TrafficMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongArrayWritable.class); job.setReducerClass(TrafficReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongArrayWritable.class);
FileOutputFormat.setOutputPath(job, new Path(args[])); job.waitForCompletion(true);
} public static class TrafficMapper extends Mapper<LongWritable, Text, Text, LongArrayWritable>{
@Override
protected void map(LongWritable key, Text value,
Mapper<LongWritable, Text, Text, LongArrayWritable>.Context context)
throws IOException, InterruptedException {
String line = value.toString();
String[] splited = line.split("\t");
String phonenumber = splited[]; String upPackNum = splited[];
String downPackNum = splited[];
String upPayLoad = splited[];
String downPayLoad = splited[]; Text k2 = new Text(phonenumber);
LongArrayWritable v2 = new LongArrayWritable(upPackNum, downPackNum, upPayLoad, downPayLoad);
context.write(k2, v2);
}
} public static class TrafficReducer extends Reducer<Text, LongArrayWritable, Text, LongArrayWritable>{
@Override
protected void reduce(Text k2, Iterable<LongArrayWritable> v2s,
Reducer<Text, LongArrayWritable, Text, LongArrayWritable>.Context context)
throws IOException, InterruptedException { long upPackNum = 0L;
long downPackNum = 0L;
long upPayLoad = 0L;
long downPayLoad = 0L;
for (LongArrayWritable v2 : v2s) {
Writable[] values = v2.get();
upPackNum += ((LongWritable)values[]).get();
downPackNum += ((LongWritable)values[]).get();
upPayLoad += ((LongWritable)values[]).get();
downPayLoad += ((LongWritable)values[]).get();
} LongArrayWritable v3 = new LongArrayWritable(upPackNum, downPackNum, upPayLoad, downPayLoad);
context.write(k2, v3);
}
} public static class LongArrayWritable extends ArrayWritable{
/**
* 在调用的时候,首先调用该方法,然后调用set(Writable[])
*/
public LongArrayWritable() {
super(LongWritable.class);
}
/**
* 直接调用该方法即可
* @param values
*/
public LongArrayWritable(LongWritable[] values) {
super(LongWritable.class, values);
}
/**
* 直接调用该方法即可
* @param upPackNum
* @param downPackNum
* @param upPayLoad
* @param downPayLoad
*/
public LongArrayWritable(Long upPackNum, Long downPackNum, Long upPayLoad, Long downPayLoad) {
super(LongWritable.class);
LongWritable[] values = new LongWritable[];
values[] = new LongWritable(upPackNum);
values[] = new LongWritable(downPackNum);
values[] = new LongWritable(upPayLoad);
values[] = new LongWritable(downPayLoad);
super.set(values);
}
/**
* 直接调用该方法即可
* @param upPackNum
* @param downPackNum
* @param upPayLoad
* @param downPayLoad
*/
public LongArrayWritable(String upPackNum, String downPackNum, String upPayLoad, String downPayLoad) {
super(LongWritable.class);
LongWritable[] values = new LongWritable[];
values[] = new LongWritable(Long.parseLong(upPackNum));
values[] = new LongWritable(Long.parseLong(downPackNum));
values[] = new LongWritable(Long.parseLong(upPayLoad));
values[] = new LongWritable(Long.parseLong(downPayLoad));
super.set(values);
} @Override
public String toString() {
String[] array = super.toStrings();
return StringUtils.join(array, "\t");
}
} }

2,ArrayWritable的API

org.apache.hadoop.io
Class ArrayWritable

java.lang.Object
  

org.apache.hadoop.io.ArrayWritable
已实现的接口:
Writable

public class ArrayWritableextends Objectimplements Writable

A Writable for arrays containing instances of a class. The elements of this writable must all be instances of the same class. If this writable will be the input for a Reducer, you will need to create a subclass that sets the value to be of the proper type. For example: public class IntArrayWritable extends ArrayWritable { public IntArrayWritable() { super(IntWritable.class); } }


构造方法摘要
ArrayWritable(Class<? extends Writable> valueClass) 
           
ArrayWritable(Class<? extends Writable> valueClass, Writable[] values) 
           
ArrayWritable(String[] strings) 
           
方法摘要
 Writable[] get() 
           
 Class getValueClass() 
           
 void readFields(DataInput in) 
          Deserialize the fields of this object from in.
 void set(Writable[] values) 
           
 Object toArray() 
           
 String[] toStrings() 
           
 void write(DataOutput out) 
          Serialize the fields of this object to out.
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
构造方法详细信息

ArrayWritable

public ArrayWritable(Class<? extends Writable> valueClass)

ArrayWritable

public ArrayWritable(Class<? extends Writable> valueClass,
Writable[] values)

ArrayWritable

public ArrayWritable(String[] strings)
方法详细信息

getValueClass

public Class getValueClass()

toStrings

public String[] toStrings()

toArray

public Object toArray()

set

public void set(Writable[] values)

get

public Writable[] get()

readFields

public void readFields(DataInput in)
throws IOException
Description copied from interface: Writable
Deserialize the fields of this object from in.

For efficiency, implementations should attempt to re-use storage in the existing object where possible.

Specified by:
readFields in interface Writable
Parameters:
in - DataInput to deseriablize this object from.
Throws:
IOException

write

public void write(DataOutput out)
throws IOException
Description copied from interface: Writable
Serialize the fields of this object to out.

Specified by:
write in interface Writable
Parameters:
out - DataOuput to serialize this object into.
Throws:
IOException

 

 

基于MapReduce的手机流量统计分析的更多相关文章

  1. MapReduce的手机流量统计的案例

    程序:(另外一个关于单词计数的总结:http://www.cnblogs.com/DreamDrive/p/5492572.html) import java.io.IOException; impo ...

  2. 基于winpcap的以太网流量分析器(java)

    开发工具 IDE:eclipse -neon JDK:1.8 OS:Win10-64bit 主要功能 1.要求完成一个基于Winpcap的网络流量统计分析系统,具有易用.美观的界面. 2.完成局域网( ...

  3. 023_数量类型练习——Hadoop MapReduce手机流量统计

    1) 分析业务需求:用户使用手机上网,存在流量的消耗.流量包括两部分:其一是上行流量(发送消息流量),其二是下行流量(接收消息的流量).每种流量在网络传输过程中,有两种形式说明:包的大小,流量的大小. ...

  4. 第2节 mapreduce深入学习:8、手机流量汇总求和

    第2节 mapreduce深入学习:8.手机流量汇总求和 例子:MapReduce综合练习之上网流量统计. 数据格式参见资料夹 需求一:统计求和 统计每个手机号的上行流量总和,下行流量总和,上行总流量 ...

  5. MapReduce 经典案例手机流量排序的分析

    在进行流量排序之前,先要明白排序是发生在map阶段,排序之后(排序结束后map阶段才会显示100%完成)才会到reduce阶段(事实上reduce也会排序),.此外排序之前要已经完成了手机流量的统计工 ...

  6. 基于mapreduce的大规模连通图寻找算法

    基于mapreduce的大规模连通图寻找算法 当我们想要知道哪些账号是一个人的时候往往可以通过业务得到两个账号之间有联系,但是这种联系如何传播呢? 问题 已知每个账号之间的联系 如: A B B C ...

  7. 字节数转换为b,kb,mb,gb的方法 通用的手机流量计算方法

    //通用的手机流量计算方法 private String byteToMB(long size){ long kb = 1024; long mb = kb*1024; long gb = mb*10 ...

  8. MapReduce教程(一)基于MapReduce框架开发<转>

    1 MapReduce编程 1.1 MapReduce简介 MapReduce是一种编程模型,用于大规模数据集(大于1TB)的并行运算,用于解决海量数据的计算问题. MapReduce分成了两个部分: ...

  9. 基于MapReduce的贝叶斯网络算法研究参考文献

    原文链接(系列):http://blog.csdn.net/XuanZuoNuo/article/details/10472219 论文: 加速贝叶斯网络:Accelerating Bayesian ...

随机推荐

  1. Java技术——I/O知识学习

    个字节,主要用在处理二进制数据,字节用来与文件打交道,所有文件的储存都是通过字节(byte)的方式,在磁盘上保留的并不是文件的字符而是先把字符编码成字节,再储存这些字节到磁盘.在读取文件(特别是文本文 ...

  2. 从C到C++ (2)

    从C到C++ (2) 一.    C++中增加了作用域标示符 :: 1.     用于对局部变量同名的全局变量进行访问. 2.     用于表示类成员. 二.    new.delete运算符 1.  ...

  3. pprof 查看goroutine

    package main import ( "net/http" "runtime/pprof" ) var quit chan struct{} = make ...

  4. SSM框架学习思维导图

    SSM框架学习思维导图 2017年08月11日 20:17:28 阅读数:1141 放上前段时间学习SSM框架以及Spring.SpringMVC.MyBatis的学习结果,输出思维导图一共四幅图.这 ...

  5. 每天一个Linux命令(14):dpkg命令

    dpkg命令是Debian Linux系统用来安装.创建和管理软件包的实用工具. 语法: dpkg (选项) (参数) 选项: -i:安装软件包: -r:删除软件包: -P:删除软件包的同时删除其配置 ...

  6. Qt 加载Leap motion 手势识别软件 二次开发 hello world

    研发需要对收拾是被进行精确定位,实现收拾的识别,和在虚拟现实中精确的显示手势在实际世界中的位置. 开始使用的Qt mingw的版本开发,总是函数没有定义,最后发现是leap sdk中需要代育vs的库文 ...

  7. 第十二篇 Python函数之全局变量&局部变量&递归函数

    全局变量:在定义的时候,顶头写的,没有任何缩进的变量就是全局变量. 全局变量的特点:在当前文件里的任何地方都可以进行调用 局部变量:在子程序里定义的变量,就是局部变量. 子程序:比如.py文件里,写的 ...

  8. Java并发基础--线程安全

    一.线程安全 1.线程安全的概念 线程安全:某个类被单个线程,或者多个线程同时访问,所表现出来的行为是一致,则可以说这个类是线程安全的. 2.什么情况下会出现线程安全问题 在单线程中不会出现线程安全问 ...

  9. Sersync实时备份服务部署实践

  10. 并查集——poj2524(入门)

    传送门:Ubiquitous Religions 许多次WA,贴上错的代码随时警示 简单没多加修饰的并查集 [WA1] #include <iostream> #include <c ...