mapreduce 统计流量
来源:互联网 发布:千牛是淘宝卖家版么 编辑:程序博客网 时间:2024/05/18 03:01
流量统计,第一列为用户手机号,第二列为上行流量,第三列为下行流量,ok 问题来了 根据用户统计用户上行和下行流量
1363157985066,2481,246811363157995052,264,01363157991076,132,15121363157995052,240,01363157993044,1527,21061363157995074,4116,14321363157993055,1116,9541363157995033,3156,29361363157983019,240,01363157984041,6960,6901363157973098,3659,35381363157986029,1938,1801363157992093,918,49381363157986041,180,1801363157984040,1938,29101363157995093,3008,37201363157982040,7335,1103491363157986072,9531,24121363157990043,11058,48243
package com.demo.mapreduce;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.*;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.input.TextInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;import java.io.DataInput;import java.io.DataOutput;import java.io.IOException;import java.util.HashSet;import java.util.Set;/** * Created by leslie on 17/6/25. */public class MapreduceNet { static class NetFlow implements WritableComparable<NetFlow>{ private String phone=""; private long upLoad=0l; private long dLoad=0l; private long sLoad=0l; public NetFlow(String phone, long upLoad, long dLoad, long sLoad) { this.phone = phone; this.upLoad = upLoad; this.dLoad = dLoad; this.sLoad = sLoad; } public String getPhone() { return phone; } public void setPhone(String phone) { this.phone = phone; } public long getUpLoad() { return upLoad; } public void setUpLoad(long upLoad) { this.upLoad = upLoad; } public long getdLoad() { return dLoad; } public void setdLoad(long dLoad) { this.dLoad = dLoad; } public long getsLoad() { return sLoad; } public void setsLoad(long sLoad) { this.sLoad = sLoad; } @Override public int compareTo(NetFlow o) { this.setsLoad(this.getUpLoad()+this.getdLoad()); o.setsLoad(o.getdLoad()+o.getUpLoad()); return Long.compare(this.getsLoad(),this.getsLoad()); } @Override public void write(DataOutput dataOutput) throws IOException { dataOutput.writeChars(phone); dataOutput.writeLong(upLoad); dataOutput.writeLong(dLoad); dataOutput.writeLong(sLoad); } @Override public void readFields(DataInput dataInput) throws IOException { phone = dataInput.readUTF(); upLoad = dataInput.readLong(); dLoad = dataInput.readLong(); sLoad = dataInput.readLong(); } } static class MyMapper extends Mapper<LongWritable,Text,Text,NetFlow>{ @Override protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String[] strings = value.toString().split(","); if(strings.length==3){ long uload = Long.parseLong(strings[1]); long dLoad = Long.parseLong(strings[2]); long sLoad = uload+dLoad; NetFlow flow = new NetFlow(strings[0],uload,dLoad,sLoad); context.write(new Text(strings[0]),flow); } } } static class MyComparator extends WritableComparator{ public MyComparator(){super(NetFlow.class,true);} @Override public int compare(WritableComparable a, WritableComparable b) { NetFlow n1 = (NetFlow)a; NetFlow n2 = (NetFlow)b; return Long.compare(n1.getsLoad(),n2.getsLoad()); } } static class MyReducer extends Reducer<Text,NetFlow,Text,NullWritable>{ @Override protected void reduce(Text key, Iterable<NetFlow> values, Context context) throws IOException, InterruptedException { long uLoad = 0;long dLoad = 0; for(NetFlow flow:values){ uLoad+=flow.getUpLoad(); dLoad+= flow.getdLoad(); } long sLoad = uLoad+dLoad; context.write(new Text(key.toString()+":"+uLoad+":"+dLoad+":"+sLoad),NullWritable.get()); } } public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { Configuration conf = new Configuration(); Job job = new Job(conf,"mapreduce"); Path mypath = new Path(args[1]); FileSystem hdfs = mypath.getFileSystem(conf); if (hdfs.isDirectory(mypath)) { hdfs.delete(mypath, true); } job.setJarByClass(MapreduceNet.class);// job.setGroupingComparatorClass(MyComparator.class); job.setMapperClass(MyMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(NetFlow.class); job.setReducerClass(MyReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(NullWritable.class); job.setInputFormatClass( TextInputFormat.class ); job.setOutputFormatClass( TextOutputFormat.class ); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath( job,new Path(args[1])); System.exit(job.waitForCompletion(true)?0:1); }}
结果输出
1363157973098:3659:3538:7197
1363157982040:7335:110349:117684
1363157983019:240:0:240
1363157984040:1938:2910:4848
1363157984041:6960:690:7650
1363157985066:2481:24681:27162
1363157986029:1938:180:2118
1363157986041:180:180:360
1363157986072:9531:2412:11943
1363157990043:11058:48243:59301
1363157991076:132:1512:1644
1363157992093:918:4938:5856
1363157993044:1527:2106:3633
1363157993055:1116:954:2070
1363157995033:3156:2936:6092
1363157995052:504:0:504
1363157995074:4116:1432:5548
1363157995093:3008:3720:6728
阅读全文
0 0
- mapreduce 统计流量
- MapReduce实现手机上网流量统计
- mapreduce实现简单的流量统计功能
- MapReduce实战练习一:手机流量统计
- MapReduce 开篇练习之 统计流量
- MapReduce之一——上网流量数据统计
- MapReduce编程--1.统计用户上网流量DataCount
- Hadoop MapReduce统计手机流量案例学习(结合Partitioner)
- 基于Mapreduce的手机流量统计——Mapreduce大型项目书写流程
- 流量统计
- 流量统计
- 流量统计
- 流量统计
- 流量统计
- 流量统计
- 流量统计
- 流量统计
- 流量统计
- notepad++ 配置C/C++环境
- Ss 笔记
- 流程的Python 第三章:字典和集合
- 定义一个ArrayList集合,存储一批书籍,书籍具有书名、作者、价格三个属性, 键盘录入一个书名时,显示该书籍的详细信息。
- Oracle之表的种类(heap,partition table,glable temp table,orgination index table,cluster sort hash table)
- mapreduce 统计流量
- spring之使用表达式定义切入点
- u-boot第二阶段分析(一)
- 判断IP合法性和纯数字合法性
- jqueryeasyui datagrid
- Vue.js学习系列六——Vue单元测试Karma+Mocha学习笔记
- (1) 初识birt(免费开源报表软件)-建立第一个birt report项目
- 日常linux使用笔记
- eclipse提交代码至GitHub