Java-MapReduce 程序案例

最新推荐文章于 2022-05-13 11:05:21 发布

原创最新推荐文章于 2022-05-13 11:05:21 发布 · 471 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#mapreduce

本文介绍了如何使用Java MapReduce处理数据。首先讲解了如何通过MapReduce程序剔除数据中超过三个空格的行，以此进行缺失值处理，并给出相应代码。接着，文章讨论了数据去重的MapReduce实现，同样提供了相应的程序代码，帮助理解MapReduce在数据处理中的应用。

1.缺失值处理

如果一行数据超过三个空则剔除数据，最终输出剔除记录数

程序代码：

package org.mapreduce;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class qqsz1 {
    public static void main(String[]args)throws IOException,InterruptedException,ClassNotFoundException{
        Job job= Job.getInstance();
        job.setJobName("去点点");
        job.setJarByClass(qqsz1.class);
        job.setMapperClass(domap.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        Path in=new Path("输入文件地址");
        Path out=new Path("输出地址");
        FileInputFormat.addInputPath(job,in);
        FileOutputFormat.setOutputPath(job,out);
        System.exit(job.waitForCompletion(true)?0:1);
    }
    public static class domap extends Mapper<Object, Text,Text,Text>{
        public void map(Object key,Text value,Context context)throws IOException,InterruptedException{
            if(key.toString().equals("0")){
                return;
            }
            String [] line=value.toString().split("\t");
            for(String aa:line ){
                int count=0;
                if(aa.trim().equals("")){
                    count++;
                }
                if(count>1){
                    context.getCounter("剔除数据","条数").increment(1);
                    return;
                }
            }
            context.write(value,new Text(""));
        }
    }
}

2.数据去重

程序代码：

package org.mapreduce;
import org.apache.hadoop.fs.Path;
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;

import java.io.IOException;

public class qcfz {
    public static void main(String[]args)throws IOException,InterruptedException,ClassNotFoundException {
        Job job= Job.getInstance();
        job.setJarByClass(qcfz.class);
        job.setJobName("去重");
        job.setMapperClass(domap.class);
        job.setReducerClass(doreduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        Path in=new Path("输入文件地址");
        Path out=new Path("输出结果地址");
        FileInputFormat.addInputPath(job,in);
        FileOutputFormat.setOutputPath(job,out);
        System.exit(job.waitForCompletion(true)?0:1);
    }
    public static class domap extends Mapper<Object, Text,Text,Text>{
        public void map(Object key,Text value,Context context)throws IOException,InterruptedException{
            Text line=value;
            context.write(line,new Text(""));
        }
    }
    public static class doreduce extends Reducer<Text,Text,Text,Text>{
        public void reduce(Text key,Iterable<Text> value,Context context)throws IOException,InterruptedException{
            context.write(key,new Text(""));
        }
    }
}