头歌Hadoop WordCount词频统计

好的，以下是一个简单的 Hadoop WordCount 词频统计程序示例：

Mapper 类：

import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
  
  @Override
  public void map(LongWritable key, Text value, Context context)
      throws IOException, InterruptedException {
    
    String line = value.toString();
    
    // 将每一行按空格分隔成多个单词
    String[] words = line.split(" ");
    
    // 遍历每个单词，发送到 Reducer 进行统计
    for (String word : words) {
      context.write(new Text(word), new LongWritable(1));
    }
  }
  
}

Reducer 类：

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

public class WordCountReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
  
  @Override
  public void reduce(Text key, Iterable<LongWritable> values, Context context)
      throws IOException, InterruptedException {
    
    long sum = 0;
    
    // 遍历同一个单词的所有出现次数，求和
    for (LongWritable value : values) {
      sum += value.get();
    }
    
    // 将单词和出现次数发送到输出
    context.write(key, new LongWritable(sum));
  }
  
}

Main 方法：

import org.apache.hadoop.conf.Configuration;
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;

public class WordCount {
  
  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(WordCountMapper.class);
    job.setCombinerClass(WordCountReducer.class);
    job.setReducerClass(WordCountReducer.class);
    
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);
    
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
  
}

在执行该程序时，需要在命令行中输入以下命令：

hadoop jar WordCount.jar WordCount /input /output

其中，第一个参数 WordCount.jar 是打包好的程序文件，第二个参数 WordCount 表示程序的类名，后面的 /input 和 /output 分别是输入和输出的路径。