基于MapReduce的手机流量统计分析
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 interfaceWritable
-
- 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 interfaceWritable
-
- 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
- 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 ...
- 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( ...
- 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. ...
- 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 ...
- 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 ...
- 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 ...
- 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 ...
- 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: ...
- 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
- POJ 1568 Find the Winning Move
Find the Winning Move 链接 题意: 4*4的棋盘,给出一个初始局面,问先手有没有必胜策略? 有的话输出第一步下在哪里,如果有多个,按(0, 0), (0, 1), (0, 2), ...
- [转]URL传中文参数导致乱码的解决方案之encodeURI
通过URL传中文参数时,在服务端后台获取到的值往往会出现乱码.解决方案有很多种.本文介绍如何通过encodeURI来解决中文乱码问题. 首先,在前端页面准备参数的时候,需要对中文参数进行encode处 ...
- C#异步了解一下
如何让你的代码在“同一时间”干着两件件事呢?比如说,在初始化加载配置的同时,UI界面能够响应用户的各种点击事件.而不置于卡死,特别是出现如下面这种情况的时候,对于用户来说是很崩溃的.
- BZOJ1270[BJWC2008]雷涛的小猫
雷涛同学非常的有爱心,在他的宿舍里,养着一只因为受伤被救助的小猫(当然,这样的行为是违反学生宿舍管理条例的).在他的照顾下,小猫很快恢复了健康,并且愈发的活泼可爱了. 可是有一天,雷涛下课回到寝室,却 ...
- (原) MatEditor部- UmateriaEditor中Texture使用过程(1)
@author: 白袍小道 转载说明原处 插件同步在GITHUB: DaoZhang_XDZ 最后YY需求(手滑)(开黑前弄下,充数,见谅) 1.在理清楚基础套路和细节后,自定义纹理资源,并加 ...
- 阿里云DTS VS MySQLdump
云平台的到来,使得越来越多用户的数据库由云下迁到云上.对于这种情况,阿里对此提出两种方案,一种是MySQL自带的MySQLdump,另外一种就是阿里云的DTS. DTS支持异构数据源之间的数据迁移同步 ...
- 爬取图片过程遇到的ValueError: Missing scheme in request url: h 报错与解决方法
一 .scrapy整体框架 1.1 scrapy框架图 1.2 scrapy框架各结构解析 item:保存抓取的内容 spider:定义抓取内容的规则,也是我们主要编辑的文件 pipelines:管道 ...
- Python第二天 (数据类型,变量 )
1. 把任意数据类型赋值给变量 在Python中,等号=是赋值语句,可以把任意数据类型赋值给变量,同一个变量可以反复赋值,而且可以是不同类型的变量,例如: 例子:a = 123 # a是整数 prin ...
- Spring MVC自动为对象注入枚举数据
一.实现转换工厂,定义转换实现,如下: package com.mafwo; import org.springframework.core.convert.converter.Convert ...
- 关于org.springframework.web.filter.CharacterEncodingFilter的学习
介绍 org.springframework.web.filter.CharacterEncodingFilter 这是一个过滤器,是Spring在web请求中定义request和response的编 ...