Mapreduce字数Hadoop最高频率词

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)上，我了解了如何使用map reduce方法实现单词计数，并且输出的单词都是出现频率的。

我想做的是只有输出是最高频率的字从输入文件我有。

我希望输出只是

Jim 4

Word count的当前输出是每个单词及其频率。有没有人编辑单词计数，使它只是打印最高频率的单词和它的频率？

有没有人对如何实现这一点有什么提示呢？

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减速器的数量设置为“1”。然后，让一个减速器记住频率最高的单词，并在清理中将其写入输出。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));
    }
}