MapReduce 求取学生成绩平均值

最新推荐文章于 2024-05-11 14:39:48 发布

star5610

最新推荐文章于 2024-05-11 14:39:48 发布

阅读量3k

点赞数 3

分类专栏： Hadoop 文章标签： mapreduce hadoop 大数据

本文链接：https://blog.youkuaiyun.com/star5610/article/details/106070271

版权

Hadoop 专栏收录该内容

11 篇文章

订阅专栏

本文介绍了一个使用MapReduce算法计算学生成绩平均值的Hadoop应用实例。通过自定义Mapper和Reducer类，该应用能从大量学生数据中计算每个学生的平均成绩，展示了MapReduce在处理大规模数据集时的高效性和实用性。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

MapReduce 求取学生成绩平均值

学生数据：

Tom 80 
Tom 80
Tom 80
jack 90
Lili  88
Lili  90
jack  86 
jack  84

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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.reduce.IntSumReducer;

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;

public class StuAvg {

    public static class MyMapper extends Mapper<LongWritable,Text,Text,IntWritable>{

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            // 将输入的纯文本文件的数据转化成String
            String line = value.toString();
            // 将输入的数据首先按行进行分割
            StringTokenizer tokenizerArticle = new StringTokenizer(line, "\\s");
            // 分别对每一行进行处理
            while (tokenizerArticle.hasMoreElements()) {
                // 每行按空格划分
                StringTokenizer tokenizerLine = new StringTokenizer(tokenizerArticle.nextToken());
                String strName = tokenizerLine.nextToken();// 学生姓名部分
                String strScore = tokenizerLine.nextToken();// 成绩部分
                Text name = new Text(strName);
                int scoreInt = Integer.parseInt(strScore);
                // 输出姓名和成绩
                context.write(name, new IntWritable(scoreInt));
            }

        }
    }
    public static class MyReducer extends Reducer<Text,IntWritable,Text,IntWritable>{

        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

            int sum = 0;
            int count = 0;
            Iterator<IntWritable> iterator = values.iterator();
            while (iterator.hasNext()) {
                sum += iterator.next().get();// 计算总分
                count++;// 统计总的科目数
            }
            int average = (int) sum / count;// 计算平均成绩
            context.write(key, new IntWritable(average));

        }
    }


    public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "StuAvg");

        job.setJarByClass(StuAvg.class);

        FileInputFormat.addInputPath(job,new Path(args[0]));

        job.setMapperClass(MyMapper.class);
        job.setCombinerClass(MyReducer.class);
        job.setReducerClass(MyReducer.class);

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


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

        boolean b = job.waitForCompletion(true);
        System.out.println(b?1:0);

    }

}