JAVA大数据的五十七天——Hadoop中求某个科目的最大值

一、TopScore

package nj.zb.kb15.demo4;

import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

public class TopScore implements WritableComparable {
            private  String subjectName;
            private  int  score;

    public TopScore() {
    }

    public TopScore(String subjectName, int score) {
        this.subjectName = subjectName;
        this.score = score;
    }

    @Override
    public String toString() {
        return "TopScore{" +
                "subjectName='" + subjectName + ''' +
                ", score=" + score +
                '}';
    }

    public String getSubjectName() {
        return subjectName;
    }

    public void setSubjectName(String subjectName) {
        this.subjectName = subjectName;
    }

    public int getScore() {
        return score;
    }

    public void setScore(int score) {
        this.score = score;
    }

    @Override
    public int compareTo(TopScore o) {
       return 0;
    }

    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeUTF(subjectName);
        dataOutput.writeInt(score);
    }

    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.subjectName=dataInput.readUTF();
        this.score=dataInput.readInt();
    }
}

二、TopScoreMapper

package nj.zb.kb15.demo4;


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

import java.io.IOException;

public class TopScoreMapper extends Mapper {

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        System.out.println(key.get()+" "+value);
        String[] split=value.toString().split(",");
        String subjectName=split[2];
        Text text=new Text(subjectName);  //赋值Text
        TopScore topScore=new TopScore(subjectName,Integer.parseInt(split[3]));

        context.write(text,topScore);
    }
}

三、TopScoreReduce

package nj.zb.kb15.demo4;


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

import java.io.IOException;

public class TopScoreReducer extends Reducer {
    TopScore topScore=new TopScore();

    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
        String subjectName="";
        int max=0;

        for(TopScore score:values){
            if(max 
 
四、TopScoreDriver
 
package nj.zb.kb15.demo4;

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

import java.io.IOException;

public class TopScoreDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        job.setJarByClass(TopScoreDriver.class);

        job.setMapperClass(TopScoreMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(TopScore.class);

        job.setReducerClass(TopScoreReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(TopScore.class);

        FileInputFormat.setInputPaths(job, new Path("D:\test_20211026\in\demo3\stuscore.csv"));

        Path path = new Path("D:\test_20211026\in\out5");

        FileOutputFormat.setOutputPath(job, path);
        FileSystem fs = FileSystem.get(path.toUri(), configuration);

        if (fs.exists(path)) {
            fs.delete(path, true);
        }
        job.waitForCompletion(true);
    }

}
 
 
五、运行结果
 
数学  TopScore{subjectName='数学', score=91}
英语 TopScore{subjectName='英语', score=47}
语文 TopScore{subjectName='语文', score=96}