#yyds干货盘点# Hadoop之MapReduce入门概述

#yyds干货盘点# Hadoop之MapReduce入门概述

一、MapReduce概述

1.1 MapReduce定义

MapReduce是一个分布式运算程序的编程框架，是用户开发“基于Hadoop的数据分析应用”的核心框架。MapReduce核心功能是将用户编写的业务逻辑代码和自带默认组件整合成一个完整的分布式运算程序，并发运行在一个Hadoop集群上。

1.2 MapReduce优缺点

1.2.1 优点

1.6 MapReduce编程规范

1.7 WordCount案例实操

编写map类

package com.demo.mapreduce.wordcount; 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; /** * @author suitianshuang * @date 2021/12/25 - 00:20 */ /** * KEYIN, map阶段输入的key的类型 * VALUEIN,map阶段输入的value的类型 * KEYOUT, 输出阶段。。。 * VALUEOUT，输出阶段 */ public class WordMapper extends Mapper { // 1.x 即负责资源调度 也负责资源的计算 private Text outKey = new Text(); private IntWritable outValue = new IntWritable(1); @Override protected void map(LongWritable key, Text value, Mapper.Context context) throws IOException, InterruptedException { // super.map(key, value, context); // 1. 获取一行 final String line = value.toString(); // 2. 切割 final String[] words = line.split(" "); // 3. 循环写出 for (String word : words) { outKey.set(word); context.write(outKey,outValue); } } }

编写reduce类

package com.demo.mapreduce.wordcount; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer; import java.io.IOException; /** * @author suitianshuang * @date 2021/12/25 - 00:21 */ /** * KEYIN, Reduce阶段输入的key的类型 Text * VALUEIN,Reduce阶段输入的value的类型 IntWritable * KEYOUT, Reduce输出阶段。。。Text * VALUEOUT，Reduce输出阶段 IntWritable */ public class WordReduce extends Reducer { private IntWritable intWritable = new IntWritable(); @Override protected void reduce(Text key, Iterable values, Reducer.Context context) throws IOException, InterruptedException { // super.reduce(key, values, context); int sum = 0; for (IntWritable value : values) { sum += value.get(); } intWritable.set(sum); context.write(key,intWritable); } }

编写调用类

package com.demo.mapreduce.wordcount; 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.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import java.io.IOException; /** * @author suitianshuang * @date 2021/12/25 - 00:21 */ public class WordDriver { public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { // 1 获取配置信息以及获取job对象 Configuration conf = new Configuration(); Job job = Job.getInstance(conf); // 2 关联本Driver程序的jar job.setJarByClass(WordDriver.class); // 3 关联Mapper和Reducer的jar job.setMapperClass(WordMapper.class); job.setReducerClass(WordReduce.class); // 4 设置Mapper输出的kv类型 job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); // 5 设置最终输出kv类型 job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // 6 设置输入和输出路径 FileInputFormat.setInputPaths(job, new Path("")); FileOutputFormat.setOutputPath(job, new Path(args[1])); // 7 提交job boolean result = job.waitForCompletion(true); System.exit(result ? 0 : 1); } }

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。