[大数据]MapReduce入门经典案例（Windows环境下）

之前一直都是在linux系统中编写MapReduce程序，最近尝试了在Windows环境下链接本地虚拟机，进行MapReduce的编译运行

关于jar包的导入问题可以看我之前的博客

https://blog.csdn.net/qq_44823756/article/details/119059561?spm=1001.2014.3001.5501.

下面是四个经典案例，分别是
一、词频统计
二、最大值
三、去重
四、总和计算

一、词频统计

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class WordCountMapper extends Mapper<LongWritable, Text,Text, IntWritable> {
    @Override
    protected void map(LongWritable key,Text value,Context context) throws IOException,InterruptedException{
        String datas = value.toString();
        String[] split = datas.split(" ");
        for (String data : split){
            context.write(new Text(data),new IntWritable(1));
        }
    }
}

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class WordCountReducer extends Reducer<Text, IntWritable,Text,IntWritable> {
    @Override
    protected void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException,InterruptedException{
        int sum=0;
        for(IntWritable val:values){
            sum=sum+1;
        }
        context.write(key,new IntWritable(sum));
    }
}

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class WordCountDriver {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        //向yarn申请一个job任务用于执行mapreduce程序
        Job job = Job.getInstance(new Configuration());
        //设置入口类
        job.setJarByClass(WordCountDriver.class);
        //设置mapper类
        job.setMapperClass(WordCountMapper.class);
        //设置reduce类
        job.setReducerClass(WordCountReducer.class);
        //设置Mapper类的输出
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //设置reduce类的输出
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置要处理的文件
        FileInputFormat.addInputPath(job,new Path("hdfs://192.168.21.128:9000/txt/words.txt"));
        //设置输出路径
        FileOutputFormat.setOutputPath(job,new Path("hdfs://192.168.21.128:9000/result/wordcount"));
        //启动
        job.waitForCompletion(true);
    }
}

运行时，选中main函数，右键

二、最大值

package cn.top;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class CharTopMapper extends Mapper<LongWritable,Text,Text,IntWritable> {
    @Override
    protected void map(LongWritable key,Text value,Context context) throws IOException,InterruptedException{
        //拆分这一行中的每一个字符
        String datas = value.toString();
        String[] split = datas.split(" ");
        int x = Integer.parseInt(split[1]);
        //将每一个字符进行遍历
        context.write(new Text(split[0]),new IntWritable(x));



    }
}

package cn.top;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class CharTopReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
    @Override
    protected void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException,InterruptedException{
        int sum=0;
        int sum1=0;
        for(IntWritable val:values){
            sum = Integer.parseInt(String.valueOf(val));
            if(sum1 < sum){
                sum1=sum;
            }
        }
        context.write(key,new IntWritable(sum1));
    }
}

package cn.top;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class CharTop {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        //向yarn申请一个job任务用于执行mapreduce程序
        Job job = Job.getInstance(new Configuration());
        //设置入口类
        job.setJarByClass(CharTop.class);
        //设置mapper类
        job.setMapperClass(CharTopMapper.class);
        //设置reduce类
        job.setReducerClass(CharTopReducer.class);
        //设置Mapper类的输出
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //设置reduce类的输出
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置要处理的文件
        FileInputFormat.addInputPath(job,new Path("hdfs://192.168.21.128:9000/txt/score2.txt"));
        //设置输出路径
        FileOutputFormat.setOutputPath(job,new Path("hdfs://192.168.21.128:9000/result/charcount"));
        //启动
        job.waitForCompletion(true);
    }
}

三、去重

package cn.quchong;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class quchongMapper extends Mapper<LongWritable, Text,Text, NullWritable> {
    @Override
    protected void map(LongWritable key,Text value,Context context) throws IOException,InterruptedException{
        String datas = value.toString();
        context.write(new Text(datas),NullWritable.get());
    }
}

package cn.quchong;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class quchongReducer extends Reducer<Text, IntWritable,Text,NullWritable> {
    @Override
    protected void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException,InterruptedException{
        context.write(new Text(key), NullWritable.get());
    }
}

package cn.quchong;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class quchongDriver {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        //向yarn申请一个job任务用于执行mapreduce程序
        Job job = Job.getInstance(new Configuration());
        //设置入口类
        job.setJarByClass(quchongDriver.class);
        //设置mapper类
        job.setMapperClass(quchongMapper.class);
        //设置reduce类
        job.setReducerClass(quchongReducer.class);
        //设置Mapper类的输出
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        //设置reduce类的输出
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        //设置要处理的文件
        FileInputFormat.addInputPath(job,new Path("hdfs://192.168.21.129:9000/txt/ip.txt"));
        //设置输出路径
        FileOutputFormat.setOutputPath(job,new Path("hdfs://192.168.21.129:9000/result/quchong"));
        //启动
        job.waitForCompletion(true);
    }
}

四、总和计算

package cn.ScoreSum;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class ScoreSumMapper extends Mapper<LongWritable, Text,Text, IntWritable> {
    protected void map(LongWritable key,Text value,Context context) throws IOException,InterruptedException{
        String data = value.toString();
        String[] s = data.split(" ");
        context.write(new Text(s[0]),new IntWritable(Integer.parseInt(s[1])));
    }
}

package cn.ScoreSum;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class ScoreSumReducer extends Reducer<Text, IntWritable,Text,IntWritable> {
    @Override
    protected void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException,InterruptedException{
        int sum=0;
        for(IntWritable val:values){
            sum=sum+val.get();
        }
        context.write(key,new IntWritable(sum));
    }
}

package cn.ScoreSum;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class ScoreSumDriver {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        //向yarn申请一个job任务用于执行mapreduce程序
        Job job = Job.getInstance(new Configuration());
        //设置入口类
        job.setJarByClass(ScoreSumDriver.class);
        //设置mapper类
        job.setMapperClass(ScoreSumMapper.class);
        //设置reduce类
        job.setReducerClass(ScoreSumReducer.class);
        //设置Mapper类的输出
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //设置reduce类的输出
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置要处理的文件
        FileInputFormat.addInputPath(job,new Path("hdfs://192.168.21.129:9000/txt/score2"));
        //设置输出路径
        FileOutputFormat.setOutputPath(job,new Path("hdfs://192.168.21.129:9000/result/ScoreSumcount"));
        //启动
        job.waitForCompletion(true);
    }
}