4、MapReduce编程实践

最新推荐文章于 2024-09-29 19:30:50 发布

༺ Dorothy ༻

最新推荐文章于 2024-09-29 19:30:50 发布

阅读量234

点赞数 2

分类专栏： HDFS Hadoop 文章标签： mapreduce 大数据 hdfs ubuntu

本文链接：https://blog.csdn.net/2301_78696436/article/details/142637112

版权

HDFS Hadoop 专栏收录该内容

4 篇文章 0 订阅

订阅专栏

1、创建文件

在这里插入图片描述

2、启动HDFS

在这里插入图片描述

3、启动eclipse 创建项目并导入jar包

file->new->java project

导入jar包

在这里插入图片描述

finish

4、编写Java应用程序

在WordCount项目下 new class
在这里插入图片描述

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.util.GenericOptionsParser;

public class WordCount {
    public static class MyMapper extends Mapper<Object, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration(); // 程序运行时参数
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); // 解析相关参数

        if (otherArgs.length != 2) {
            System.err.println("Usage: wordcount <in> <out>");
            System.exit(2);
        }

        Job job = new Job(conf, "word count"); // 设置环境参数
        job.setJarByClass(WordCount.class); // 设置整个程序的类名
        job.setMapperClass(MyMapper.class); // 添加 MyMapper 类
        job.setReducerClass(MyReducer.class); // 添加 MyReducer 类
        job.setOutputKeyClass(Text.class); // 设置输出键类型
        job.setOutputValueClass(IntWritable.class); // 设置输出值类型
        FileInputFormat.addInputPath(job, new Path(otherArgs[0])); // 设置输入文件路径
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); // 设置输出文件路径
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}