mapreduce wordcount program

Question

   package com.delhi;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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 org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class UppercaseDriver extends Configured implements Tool {

    public int run(String[] args) throws Exception{
        if(args.length !=2){
            System.out.printf("Two parameters are required- <input dir> <output dir>n");
        return -1;}


    Configuration conf = new Configuration();
    Job job=Job.getInstance(conf); 
    job.setJobName("uppercase");
    job.setJarByClass(UppercaseDriver.class);
    job.setMapperClass(UpperCaseMapper.class);
    job.setReducerClass(UpperCaseReduce.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);
    FileInputFormat.setInputPaths(job,new Path(args[0]));
    FileOutputFormat.setOutputPath(job,new Path(args[1]));
    //job.setNumReduceTasks(1);
    boolean success = job.waitForCompletion(true);
    return success ?0:1;
    }
    public static void main(String[] args) throws Exception {
        int exitcode = ToolRunner.run(new UppercaseDriver(), args);
        System.exit(exitcode);
    }

}

这是驱动程序。

接下来是reducer程序：

package com.delhi;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class UpperCaseReduce extends Reducer< Text,LongWritable, Text, LongWritable>{



    public void reduce(Text key, Iterable<LongWritable> value,
        org.apache.hadoop.mapreduce.Reducer.Context context)
        throws IOException, InterruptedException {

      int sum=0;
      System.out.println("how +++++++++++++++++" + key);
      for(LongWritable st: value){
          sum = (int) (sum + st.get());

      }
      System.out.println("how +++++++++++++++++" + key);
    context.write(key, new LongWritable(sum));
}

}

接下来是mapper程序：

package com.delhi;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class UpperCaseMapper extends Mapper<Object, Text, Text, LongWritable>{

@Override
protected void map(Object key, Text value,
        org.apache.hadoop.mapreduce.Mapper.Context context)
        throws IOException, InterruptedException {
    String line = value.toString();
    String arr[] = line.split(" ");
    System.out.println("hello++++++++++++++++++++++++++++");
    for(String st: arr){
    //context.write(new Text(st.toUpperCase().trim()),new LongWritable(1));
    context.write(new Text(st),new LongWritable(1));
    }
}
}

从已经存在的解决方案中我发现在这种类型的问题中，outputkeyclass和outputvalueclass应该与reducer匹配。我想我正在考虑那部分。我的情况@Override for reduce不起作用。我正在使用hadoop 7.2 0.3。我也尝试使用trim函数。问题是wordcount没有发生。我只给出了“word 1”，对于输出文件中的任何单词。 我从不同的问题开始，我就这样结束了。请帮助我。 感谢。

Answer 1

因此，如果您在@Override方法中添加reduce注释，则会收到错误消息：

  

Method不会覆盖超类

中的方法

因此，您遇到的问题是方法签名与Reducer中的方法签名不匹配。

你有：

public void reduce(Text key, Iterable<LongWritable> value,
                   org.apache.hadoop.mapreduce.Reducer.Context context)

如果您将其更改为：

public void reduce(Text key, Iterable<LongWritable> value, Context context)

错误消失了。由于您的reduce方法并未覆盖任何方法，因此它不会被调用，并且它会使用与您的输出匹配的Identity reduce。