MapReduce编程实践之自定义数据类型

57 阅读 0 评论 38 点赞

我是靠谱客的博主合适小伙，最近开发中收集的这篇文章主要介绍MapReduce编程实践之自定义数据类型，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

一：任务描述

自定义数据类型完成手机流量的分析

二：example data

格式为：记录报告时间戳、手机号码、AP mac、AC mac、访问的网址、网址种类、上行数据包数、下行数据包数、上行总流量、下行总流量、HTTP Response的状态。

136315798506613726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82i02.c.aliimg.com 2427 248124681 200
1363157995052 138265441015C-0E-8B-C7-F1-E0:CMCC 120.197.40.44 0 264 0 200
1363157991076 1392643565620-10-7A-28-CC-0A:CMCC 120.196.100.992 4 132 1512 200
1363154400022 139262511065C-0E-8B-8B-B1-50:CMCC 120.197.40.44 0 240 0 200
1363157993044 1821157596194-71-AC-CD-E6-18:CMCC-EASY 120.196.100.99iface.qiyi.com 视频网站15 12 1527 2106 200
1363157995074 841384135C-0E-8B-8C-E8-20:7DaysInn 120.197.40.4122.72.52.12 2016 41161432 200
1363157993055 13560439658C4-17-FE-BA-DE-D9:CMCC 120.196.100.9918 15 1116 954 200
1363157995033 159201332575C-0E-8B-C7-BA-20:CMCC 120.197.40.4sug.so.360.cn 信息安全20 20 3156 2936 200
1363157983019 1371919941968-A1-B7-03-07-B1:CMCC-EASY 120.196.100.824 0 240 0 200
1363157984041 136605779915C-0E-8B-92-5C-20:CMCC-EASY 120.197.40.4s19.cnzz.com 站点统计24 9 6960 690 200
1363157973098 150136858585C-0E-8B-C7-F7-90:CMCC 120.197.40.4rank.ie.sogou.com 搜索引擎28 27 3659 3538 200
1363157986029 15989002119E8-99-C4-4E-93-E0:CMCC-EASY 120.196.100.99www.umeng.com 站点统计3 3 1938 180 200
1363157992093 13560439658C4-17-FE-BA-DE-D9:CMCC 120.196.100.9915 9 918 4938 200
1363157986041 134802531045C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.43 3 180 180 200
1363157984040 136028465655C-0E-8B-8B-B6-00:CMCC 120.197.40.42052.flash2-http.qq.com 综合门户15 12 1938 2910 200
1363157995093 1392231446600-FD-07-A2-EC-BA:CMCC 120.196.100.82img.qfc.cn 1212 30083720 200
1363157982040 135024688235C-0A-5B-6A-0B-D4:CMCC-EASY 120.196.100.99y0.ifengimg.com 综合门户57 102 7335 110349 200
1363157986072 1832017338284-25-DB-4F-10-1A:CMCC-EASY 120.196.100.99input.shouji.sogou.com 搜索引擎21 18 9531 2412 200
1363157990043 1392505741300-1F-64-E1-E6-9A:CMCC 120.196.100.55t3.baidu.com 搜索引擎69 63 11058 48243 200
1363157988072 1376077871000-FD-07-A4-7B-08:CMCC 120.196.100.822 2 120 120 200
1363157985079 1382307000120-7C-8F-70-68-1F:CMCC 120.196.100.996 3 360 180 200
1363157985069 1360021750200-1F-64-E2-E8-B1:CMCC 120.196.100.5518 138 1080 186852 200

三：Code

package mrTest;
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.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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class zidingyishujuleixing {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
// TODO Auto-generated method stub
Job job = new Job(new Configuration(),"自定义数据类型");
job.setJarByClass(zidingyishujuleixing.class);
//一：文件输入路径
FileInputFormat.addInputPath(job, new Path(args[0]));
//二：指定自定义Map类
job.setMapperClass(Map.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(WlanString.class);
//三：分区，指定reduce个数
job.setNumReduceTasks(1);
//四：TODO 排序
分组
//五：规约处理
//六：指定自定义的reduce类
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(WlanString.class);
//七：指定文件输出位置
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//八：提交运行
System.exit(job.waitForCompletion(true)? 0 : 1);
}
public static class Map extends Mapper<Object, Text, Text, WlanString>{
public void map(Object key, Text value, Context context) throws IOException, InterruptedException{
String[] split = value.toString().split("t");
String keyNum = split[1];
WlanString ws = new WlanString(split[6],split[7],split[8],split[9]);
System.out.println(split[6] + "| " + split[7] + "|" + split[8] + "|" + split[9]);
context.write(new Text(keyNum), ws);
}
}
public static class Reduce extends Reducer<Text, WlanString, Text, WlanString>{
public void reduce(Text key, Iterable<WlanString> values, Context context) throws IOException, InterruptedException{
long upData = 0;
long downData = 0;
long upFlow = 0;
long downFlow = 0;
for (WlanString w : values) {
upData += w.upData;
downData += w.downData;
upFlow += w.upFlow;
downFlow += w.downFlow;
}
WlanString newWs = new WlanString(String.valueOf(upData),String.valueOf(downData),String.valueOf(upFlow),String.valueOf(downFlow));
context.write(key, newWs);
}
}
public static class WlanString implements Writable{
long upData;
long downData;
long upFlow;
long downFlow;
public WlanString(){	}
public WlanString(String
upData1, String downData1, String upFlow1, String downFlow1) {
// TODO Auto-generated constructor stub
this.upData =
Long.parseLong(upData1);
this.upData = Long.parseLong(downData1);
this.upFlow =
Long.parseLong(upFlow1);
this.downFlow = Long.parseLong(downFlow1);
}
@Override
public void readFields(DataInput in) throws IOException {
// TODO Auto-generated method stub
this.upData = in.readLong();
this.downData = in.readLong();
this.upFlow = in.readLong();
this.downFlow = in.readLong();
System.out.println("upData:" + upData + "downData:" + downData + "upFlow:" + upFlow + "downFlow:" + downFlow);
}
@Override
public void write(DataOutput out) throws IOException {
// TODO Auto-generated method stub
out.writeLong(upData);
out.writeLong(downData);
out.writeLong(upFlow);
out.writeLong(upFlow);
System.out.println("upData:" + upData + "downData:" + downData + "upFlow:" + upFlow + "downFlow:" + downFlow);
}
@Override
public String toString() {
return upData + "t" + downData + "t" + upFlow +"t" + downFlow;
}
}
}

四：结果展示