MapReduce

1.需求

创建一个文件上传到HDFS，统计每个学生的总成绩，文件内容如下：

使用MapReduce

张三 英语 80 河南省

张三 数学 50 河南省

张三 语文 60 河南省

李四 英语 90 河南省

李四 语文 90 河南省

李四 数学 85 河南省

通过结果：

张三 190

李四 265

2.上传到hdfs

3.IDEA代码

添加依赖

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.4</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-app</artifactId>
            <version>3.1.4</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-server-resourcemanager</artifactId>
            <version>3.1.4</version>
        </dependency>
    </dependencies>

package com.yh;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

import java.io.IOException;

// 测试类

public class ScoreTest {
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","hdfs://hadoop10:8020");

        Job job = Job.getInstance(conf);
        job.setJarByClass(ScoreTest.class);

        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

        TextInputFormat.addInputPath(job,new Path("/score.txt"));
        TextOutputFormat.setOutputPath(job,new Path("/out4"));

        job.setMapperClass(ScoreMapper.class);
        job.setReducerClass(ScoreReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        boolean b = job.waitForCompletion(true);
        System.out.println(b);


    }
    
    // Mapper类

    static class ScoreMapper extends Mapper<LongWritable, Text,Text, IntWritable> {
       private Text student = new Text();
       private IntWritable score = new IntWritable();
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] parts = value.toString().split("\\s+"); // 假设字段由空白字符分隔
            if (parts.length >= 4) {
                student.set(parts[0]);
                score.set(Integer.parseInt(parts[2]));
                context.write(student, score);
            }
        }
    }


//Reducer类

    static class ScoreReducer 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 value : values){
                sum = sum+value.get();
            }
            context.write(key,new IntWritable(sum));

        }
    }
}

 4.maven打包

5.上传

 6.查看