求相同号码一天内的上网流量——mapreduce_reduce将相同号码加起来-优快云博客

本文链接：https://blog.youkuaiyun.com/qq_21000833/article/details/48222315

本文介绍了一个使用Hadoop MapReduce框架处理交通数据的应用案例。该程序通过对输入数据进行映射和归约操作，实现了对特定字段的汇总统计。具体而言，Mapper将原始记录分解并重组为新的键值对，Reducer则负责对相同键的数据进行聚合计算。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

按照老师要求，不用自定义序列化类来实现业务需求，代码如下（已自己通过测试）

package mapreduce;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
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;

public class TrafficHomeWork {

public static class MyMapper extends Mapper<LongWritable, Text, Text, Text>{
@Override
protected void map(LongWritable k1, Text v1,
org.apache.hadoop.mapreduce.Mapper
<LongWritable, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
Text k2=new Text();
Text v2=new Text();
String[] splited = v1.toString().split("\t");
String value=splited[6]+","+splited[7]+","+splited[8]+","+splited[9];
k2.set(splited[1]);
v2.set(value);
context.write(k2, v2);
}
}

public static class MyReducer extends Reducer<Text, Text, Text, Text>{
@Override
protected void reduce(Text k2, Iterable<Text> v2s,
org.apache.hadoop.mapreduce.Reducer<Text, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
long s1=0,s2=0,s3=0,s4=0;
Text v3=new Text();
for (Text v2 : v2s) {
String[] splited = v2.toString().split(",");
s1+=Long.parseLong(splited[0]);
s2+=Long.parseLong(splited[1]);
s3+=Long.parseLong(splited[2]);
s4+=Long.parseLong(splited[3]);
}
String value=Long.toString(s1)+","+Long.toString(s2)
+","+Long.toString(s3)+","+Long.toString(s4);
v3.set(value);
context.write(k2, v3);
}
}

public static void main(String[] args) throws Exception {
Job job = Job.getInstance(new Configuration(), TrafficHomeWork.class.getSimpleName());
job.setJarByClass(TrafficHomeWork.class);

FileInputFormat.setInputPaths(job, args[0]);

job.setMapperClass(MyMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);

job.setReducerClass(MyReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);

FileOutputFormat.setOutputPath(job, new Path(args[1]));

job.waitForCompletion(true);
}

}