MapReduce练习(三)

来源:互联网 发布:ubuntu debian 知乎 编辑:程序博客网 时间:2024/06/16 03:46

MapReduce练习(

 

这个很简单,数据去重。

 

1、数据:

 

 

2、要求:

数据去重的最终目标是让原始数据中出现次数超过一次的数据在输出文件中只出现一次。

 

 

3、代码:

上:

 

中:

 

 下:


4、结果:

 



附代码:


import java.io.IOException;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.Path;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 Dedup {// map将输入中的value复制到输出数据的key上,并直接输出public static class Map extends Mapper<Object, Text, Text, Text> {private static Text line = new Text();// 每行数据// 实现map函数public void map(Object key, Text value, Context context)throws IOException, InterruptedException {line = value;context.write(line, new Text(""));}}// reduce将输入中的key复制到输出数据的key上,并直接输出public static class Reduce extends Reducer<Text, Text, Text, Text> {// 实现reduce函数public void reduce(Text key, Iterable<Text> values, Context context)throws IOException, InterruptedException {context.write(key, new Text(""));}}public static void main(String[] args) throws Exception {Configuration conf = new Configuration();String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();if (otherArgs.length != 2) {System.err.println("Usage: Data Deduplication <in> <out>");System.exit(2);}Job job = new Job(conf, "Data Deduplication");job.setJarByClass(Dedup.class);// 设置Map、Combine和Reduce处理类job.setMapperClass(Map.class);job.setCombinerClass(Reduce.class);job.setReducerClass(Reduce.class);// 设置输出类型job.setOutputKeyClass(Text.class);job.setOutputValueClass(Text.class);// 设置输入和输出目录FileInputFormat.addInputPath(job, new Path(otherArgs[0]));FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));System.exit(job.waitForCompletion(true) ? 0 : 1);}}




 

0 0
原创粉丝点击