流量统计（统计每个用户的上行流量和下行流量及其流量总和）
源数据：
1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200
1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200
1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200
1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200
1363157993044 18211575961 94-71-AC-CD-E6-18:CMCC-EASY 120.196.100.99 iface.qiyi.com 视频网站 15 12 1527 2106 200
1363157995074 84138413 5C-0E-8B-8C-E8-20:7DaysInn 120.197.40.4 122.72.52.12 20 16 4116 1432 200
1363157993055 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200
1363157995033 15920133257 5C-0E-8B-C7-BA-20:CMCC 120.197.40.4 sug.so.360.cn 信息安全 20 20 3156 2936 200
1363157983019 13719199419 68-A1-B7-03-07-B1:CMCC-EASY 120.196.100.82 4 0 240 0 200
1363157984041 13660577991 5C-0E-8B-92-5C-20:CMCC-EASY 120.197.40.4 s19.cnzz.com 站点统计 24 9 6960 690 200
1363157973098 15013685858 5C-0E-8B-C7-F7-90:CMCC 120.197.40.4 rank.ie.sogou.com 搜索引擎 28 27 3659 3538 200
1363157986029 15989002119 E8-99-C4-4E-93-E0:CMCC-EASY 120.196.100.99 www.umeng.com 站点统计 3 3 1938 180 200
1363157992093 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 15 9 918 4938 200
1363157986041 13480253104 5C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.4 3 3 180 180 200
1363157984040 13602846565 5C-0E-8B-8B-B6-00:CMCC 120.197.40.4 2052.flash2-http.qq.com 综合门户 15 12 1938 2910 200
1363157995093 13922314466 00-FD-07-A2-EC-BA:CMCC 120.196.100.82 img.qfc.cn 12 12 3008 3720 200
1363157982040 13502468823 5C-0A-5B-6A-0B-D4:CMCC-EASY 120.196.100.99 y0.ifengimg.com 综合门户 57 102 7335 110349 200
1363157986072 18320173382 84-25-DB-4F-10-1A:CMCC-EASY 120.196.100.99 input.shouji.sogou.com 搜索引擎 21 18 9531 2412 200
1363157990043 13925057413 00-1F-64-E1-E6-9A:CMCC 120.196.100.55 t3.baidu.com 搜索引擎 69 63 11058 48243 200
1363157988072 13760778710 00-FD-07-A4-7B-08:CMCC 120.196.100.82 2 2 120 120 200
1363157985066 13726238888 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200
1363157993055 13560436666 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200
1、第一次作业：
①封装FlowBean
package com.it18zhang.flowdemo;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.WritableComparable;
public class FlowBean implements WritableComparable<FlowBean> {
private long upFlow;
private long downFlow;
private long sumFlow;
public FlowBean() {
}
public FlowBean(long upFlow, long downFlow) {
this.upFlow = upFlow;
this.downFlow = downFlow;
this.sumFlow = this.upFlow + this.downFlow;
}
public long getUpFlow() {
return upFlow;
}
public void setUpFlow(long upFlow) {
this.upFlow = upFlow;
}
public long getDownFlow() {
return downFlow;
}
public void setDownFlow(long downFlow) {
this.downFlow = downFlow;
}
public long getSumFlow() {
return sumFlow;
}
@Override
public String toString() {
return upFlow + "\t" + downFlow + "\t" + sumFlow;
}
public void write(DataOutput out) throws IOException {
out.writeLong(upFlow);
out.writeLong(downFlow);
out.writeLong(sumFlow);
}
public void readFields(DataInput in) throws IOException {
upFlow = in.readLong();
downFlow = in.readLong();
sumFlow = in.readLong();
}
public int compareTo(FlowBean o) {
return this.sumFlow - o.getSumFlow() > 0 ? -1 : 1;
}
}
②Mapper
package com.it18zhang.flowdemo;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class FlowCountMapper extends Mapper<LongWritable, Text, Text, FlowBean> {
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, FlowBean>.Context context)
throws IOException, InterruptedException {
String[] splits = value.toString().split("\t");
String tel = splits[1];
long upFlow = Integer.parseInt(splits[splits.length - 2]);
long downFlow = Integer.parseInt(splits[splits.length - 3]);
FlowBean fb = new FlowBean(upFlow, downFlow);
context.write(new Text(tel), fb);
}
}
③Reducer
package com.it18zhang.flowdemo;
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class FlowCountReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
@Override
protected void reduce(Text key, Iterable<FlowBean> values, Context context)
throws IOException, InterruptedException {
long upFlow = 0;
long downFlow = 0;
for(FlowBean value : values){
upFlow = value.getUpFlow();
downFlow = value.getDownFlow();
}
FlowBean fb = new FlowBean(upFlow,downFlow);
context.write(key, fb);
}
}
④App
package com.it18zhang.flowdemo;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class FlowCountApp {
public static void main(String[] args) throws Exception {
//新建Job
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJobName("FlowCountApp");
job.setJarByClass(FlowCountApp.class);
//设置Mapper信息
job.setMapperClass(FlowCountMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
//设置Reducer信息
job.setReducerClass(FlowCountReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
//设置输入输出路径
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//提交作业
System.out.println(job.waitForCompletion(true) ? 0 : 1);
System.out.println("Job Finished");
}
}
结果
13480253104 180 180 360
13502468823 110349 7335 117684
13560436666 954 1116 2070
13560439658 5892 2034 7926
13602846565 2910 1938 4848
13660577991 690 6960 7650
13719199419 0 240 240
13726230503 24681 2481 27162
13726238888 24681 2481 27162
13760778710 120 120 240
13826544101 0 264 264
13922314466 3720 3008 6728
13925057413 48243 11058 59301
13926251106 0 240 240
13926435656 1512 132 1644
15013685858 3538 3659 7197
15920133257 2936 3156 6092
15989002119 180 1938 2118
18211575961 2106 1527 3633
18320173382 2412 9531 11943
84138413 1432 4116 5548
2、第二次作业：
①Mapper
package com.it18zhang.flowdemo;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class SortMapper extends Mapper<LongWritable, Text, FlowBean, Text> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String[] splits = value.toString().split("\t");
String tel = splits[0];
long upFlow = Long.parseLong(splits[1]);
long downFlow = Long.parseLong(splits[2]);
FlowBean fb = new FlowBean(upFlow,downFlow);
context.write(fb, new Text(tel));
}
}
②Reducer
package com.it18zhang.flowdemo;
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class SortReducer extends Reducer<FlowBean, Text, Text, FlowBean> {
@Override
protected void reduce(FlowBean key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
context.write(values.iterator().next(), key);
}
}
③App
package com.it18zhang.flowdemo;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class SortApp {
public static void main(String[] args) throws Exception {
// 新建Job
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJobName("SortApp");
job.setJarByClass(SortApp.class);
// 设置Mapper信息
job.setMapperClass(SortMapper.class);
job.setMapOutputKeyClass(FlowBean.class);
job.setMapOutputValueClass(Text.class);
// 设置Reducer信息
job.setReducerClass(SortReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
// 设置输入输出路径
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 提交作业
System.out.println(job.waitForCompletion(true) ? 0 : 1);
System.out.println("Job Finished");
}
}
结果
13502468823 110349 7335 117684
13925057413 48243 11058 59301
13726238888 24681 2481 27162
13726230503 24681 2481 27162
18320173382 2412 9531 11943
13660577991 690 6960 7650
15013685858 3538 3659 7197
13922314466 3720 3008 6728
15920133257 2936 3156 6092
13560439658 4938 918 5856
84138413 1432 4116 5548
13602846565 2910 1938 4848
18211575961 2106 1527 3633
15989002119 180 1938 2118
13560436666 954 1116 2070
13926435656 1512 132 1644
13480253104 180 180 360
13826544101 0 264 264
13926251106 0 240 240
13760778710 120 120 240
13719199419 0 240 240
