对文件中的手机号流量进行汇总:
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
实现功能大体分析图:
实现4个个java程序:
4.1.为手机流畅数据创建javaBean
4.2.创建Mapper类
4.3.创建Reducer类
4.4.创建提交运行类
4.1.为手机流畅数据创建javaBean
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;
/**
* hadoop中序列化框架的应用示例
* 反序列化时，反射机制会调用类的无参构造函数
* 所以，如果你在类中定义了有参构造，就一定要记得显式定义一下无参构造函数
* @author
*
*/
public class FlowBean implements Writable {
private long upflow;
private long dflow;
private long sumflow;
/**
* 显式定义无参构造
*/
public FlowBean() {}
public FlowBean(long upflow, long dflow) {
this.upflow = upflow;
this.dflow = dflow;
this.sumflow = upflow + dflow;
}
public long getUpflow() {
return upflow;
}
public void setUpflow(long upflow) {
this.upflow = upflow;
}
public long getDflow() {
return dflow;
}
public void setDflow(long dflow) {
this.dflow = dflow;
}
public long getSumflow() {
return sumflow;
}
public void setSumflow(long sumflow) {
this.sumflow = sumflow;
}
/**
* 反序列化的方法，反序列化时，从流中读取到的各个字段的顺序应该与序列化时写出去的顺序保持一致
*/
@Override
public void readFields(DataInput in) throws IOException {
upflow = in.readLong();
dflow = in.readLong();
sumflow = in.readLong();
}
/**
* 序列化的方法
*/
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(upflow);
out.writeLong(dflow);
//可以考虑不序列化总流量，因为总流量是可以通过上行流量和下行流量计算出来的
out.writeLong(sumflow);
}
@Override
public String toString() {
return upflow + "\t" + dflow + "\t" + sumflow;
}
}
4.2.创建Mapper类
import java.io.IOException;
import org.apache.commons.lang.StringUtils;
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, Context context) throws IOException, InterruptedException {
// 将传进来的这一行数据转为string
String line = value.toString();
// 切分这一行，拿到各个字段
String[] fields = StringUtils.split(line,"\t");
// 拿到手机号
String phone = fields[1];
long upflow = Long.parseLong(fields[fields.length - 3]);
long dflow = Long.parseLong(fields[fields.length - 2]);
FlowBean bean = new FlowBean(upflow, dflow);
context.write(new Text(phone), bean);
}
}
4.3.创建Reducer类
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> beans, Context context) throws IOException, InterruptedException {
//先定义两个计数器
long upAmount = 0;
long dAmount = 0;
//遍历该用户所有的流量bean，进行累加求和
for(FlowBean bean:beans){
upAmount += bean.getUpflow();
dAmount += bean.getDflow();
}
//构造一个用于输出最终结果的flowbean
FlowBean countBean = new FlowBean(upAmount, dAmount);
//输出结果
context.write(key, countBean);
}
}
4.4.创建提交运行类
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 FlowCountDriver {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(FlowCountDriver.class);
job.setMapperClass(FlowCountMapper.class);
job.setReducerClass(FlowCountReducer.class);
/**
* 如果map和reduce的输出kv类型一致，则不用专门设置map的输出kv类型
*/
/*
* job.setMapOutputKeyClass(Text.class);
* job.setMapOutputValueClass(FlowBean.class);
*/
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
/**
* hadoop中默认的输入输出组件就是TextInputformat和textoutputformat，所以，这两句代码也可以省略
*/
/*
* job.setInputFormatClass(TextInputFormat.class);
* job.setOutputFormatClass(TextOutputFormat.class);
*/
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean res = job.waitForCompletion(true);
System.exit(res ? 0 : 1);
}
}
时间： 2024-11-19 06:01:53