使用计数器在mapper和reducer之间传递参数

最新推荐文章于 2023-09-27 20:41:26 发布

原创最新推荐文章于 2023-09-27 20:41:26 发布 · 2.4k 阅读

1 ·

CC 4.0 BY-SA版权

hadoop 专栏收录该内容

3 篇文章

订阅专栏

本文介绍了一种利用Hadoop MapReduce框架计算大量数据平均数的方法。通过在Mapper阶段使用计数器记录数据条数，并在Reducer阶段获取该计数器的值来实现。这种方法适用于大数据集的平均数计算。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

假设要用MR来求一堆数据的平均数，我们一方面在MR的过程中要记住和，一方面还需要记住数字的总个数。

总个数在mapper端是无法或者的，因此只能在mapper过程中记住，使用hadoop中的计数器可以完成任务。

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.JobID;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.RunningJob;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;


public class WordCount extends Configured implements Tool{
	public static final String GROUP = "group";
	public static final String KEY = "key";
	public static class MapClass extends MapReduceBase 
				implements Mapper<LongWritable, Text, Text,IntWritable>{
			private final static IntWritable one = new IntWritable(1);
			private Text word = new Text();
			
			public void map(LongWritable key, Text value, 
					OutputCollector<Text,IntWritable> output, Reporter reporter) throws IOException{
				String line = value.toString();
				StringTokenizer itr = new StringTokenizer(line);
				while(itr.hasMoreTokens()) {
					word.set(itr.nextToken());
					output.collect(word, one);
					reporter.getCounter(GROUP, KEY).increment(1);
				}
			}
					
	}
	
	public static class Reduce extends MapReduceBase implements 
			Reducer<Text, IntWritable, Text, DoubleWritable> {
		private long SUMM = 0;
		@Override
		public void configure(JobConf conf) {
			try {
				JobClient client = new JobClient(conf);
				RunningJob parentJob = client.getJob(JobID.forName( conf.get("mapred.job.id") ));
				SUMM = parentJob.getCounters().getGroup(GROUP).getCounter(KEY);
			} catch (IOException e) {
				e.printStackTrace();
			}
			super.configure(conf);
		}

		public void reduce(Text key, Iterator<IntWritable> values,
				OutputCollector<Text, DoubleWritable> output, Reporter report)
				throws IOException {
			double sum = 0;
			while(values.hasNext()) {
				sum += values.next().get();
			}

			output.collect(key, new DoubleWritable(sum/SUMM));
		}
		
	}
	
	static int printUsage() {
		System.out.println("wordcount [-m <maps>] [-r <reduces>] <input> <output>");
		ToolRunner.printGenericCommandUsage(System.out);
		return -1;
	}
	public int run(String[] args) throws Exception {
		JobConf conf = new JobConf(getConf(),WordCount.class);
		conf.setJobName("wordcount.test");
		conf.setMapOutputKeyClass(Text.class);
		conf.setMapOutputValueClass(IntWritable.class);
		conf.setOutputKeyClass(Text.class);
		conf.setOutputValueClass(DoubleWritable.class);
		conf.setMapperClass(MapClass.class);
		//conf.setCombinerClass(Reduce.class);
		conf.setReducerClass(Reduce.class);
		
		List<String> other_args = new ArrayList<String>();
		for(int i=0;i<args.length;i++) {
			try{
				if("-m".equals(args[i])) {
					conf.setNumMapTasks(Integer.parseInt(args[++i]));
				} else if("-r".equals(args[i])) {
					conf.setNumReduceTasks(Integer.parseInt(args[++i]));
				}else{
					other_args.add(args[i]);
				}
			}catch(NumberFormatException except) {
				System.out.println("ERROR: Integer expected instead of "
						+ args[i]);
				return printUsage();
			}catch (ArrayIndexOutOfBoundsException except) {
				System.out.println("ERROR: Required parameter missing from "
						+ args[i - 1]);
				return printUsage();
			}
		}
		if (other_args.size() != 2) {
			System.out.println("ERROR: Wrong number of parameters: "
			+ other_args.size() + " instead of 2.");
			return printUsage();
		}
		FileInputFormat.setInputPaths(conf, other_args.get(0));
		FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));

		JobClient.runJob(conf);
		return 0;
	}
	public static void main(String[] args) throws Exception {
		int res = ToolRunner.run(new Configuration(), new WordCount(), args);
		System.exit(res);
	}

}