Hadoop MapReduce的Hello World实验目的

Hadoop MapReduce的Hello World实验目的是为了让用户了解Hadoop MapReduce的基本概念和使用方法。通过这个实验，用户可以学习如何编写一个简单的MapReduce程序，并将其部署到Hadoop集群上运行。这个实验可以帮助用户更好地理解Hadoop MapReduce的工作原理和应用场景。

以下是Hadoop MapReduce的Hello World实验步骤：
1. 编写MapReduce程序，包括Mapper和Reducer。
2. 将程序打包成jar文件。
3. 将输入数据上传到Hadoop分布式文件系统（HDFS）中。
4. 运行MapReduce程序。
5. 查看输出结果。

以下是一个简单的Hadoop MapReduce的Hello World实验程序：

import java.io.IOException;
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 {
      String[] words = value.toString().split(" ");
      for (String w : words) {
        word.set(w);
        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);
  }
}