java - Mapreduce 字数统计 Hadoop 最高频词

Question

因此，从 Hadoop 教程网站 ( http://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html#Source_Code ) 关于如何使用映射缩减方法实现字数统计，我了解它是如何工作的，并且输出将是具有该频率的所有单词。

我想做的只是让输出成为我输入文件中出现频率最高的单词。

示例: 吉姆 吉姆 吉姆 吉姆 汤姆 丹麦人

我希望输出是

Jim 4

字数统计的当前输出是每个单词及其频率。有没有人编辑过字数统计，以便只打印出现频率最高的单词及其频率？

有人对如何实现这一目标有任何建议吗？

我如何编写另一个 MapReducer 来从 WordCount 的输出中找到出现频率最高的单词？

或者还有其他方法吗？

任何帮助将不胜感激。

谢谢!

WordCount.jave:

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;

public class WordCount {

  public static class TokenizerMapper
       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 IntSumReducer
       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();
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

Answer 1

一种可能的方法是将reducer的数量设置为“1”。然后让一个reducer记住出现频率最高的单词，并在清理时将其写入输出。像这样:

public static class IntSumReducer
       extends Reducer<Text,IntWritable,Text,IntWritable> {

    private Text tmpWord = new Text("");
    private int tmpFrequency = 0;

    @Override
    public void reduce(Text key, Iterable<IntWritable> values,
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      if(sum > tmpFrequency) {
         tmpFrequency = sum;
         tmpWord = key;
      }
    }

    @Override
    public void cleanup(Context context) {
    // write the word with the highest frequency
        context.write(tmpWord, new IntWritable(tmpFrequency));
    }
}