hadoop编程之mapreduce，计算总数和平均数

最新推荐文章于 2024-05-17 16:48:52 发布

lcjmsr

最新推荐文章于 2024-05-17 16:48:52 发布

阅读量2k

点赞数 1

分类专栏： hadoop

本文链接：https://blog.csdn.net/a7980718/article/details/71305413

版权

hadoop 专栏收录该内容

4 篇文章 0 订阅

订阅专栏

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.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;
import org.apache.hadoop.util.GenericOptionsParser;
 
public class Test {
 
  public static class TokenizerMapper 
       extends Mapper<Object, Text, Text, Text>{
    private Text record = new Text();
    private Text time = new Text();
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString(), "\n");
      while (itr.hasMoreTokens()) {
    	 String[] strs = itr.nextToken().split("\\s+");
    	 if(strs.length == 3) {
    		 record.set(strs[0] + " " + strs[1]);
    		 time.set(strs[2]);
             context.write(record, time);
    	 }
      }
    }
  }
 
  public static class AverageReducer 
       extends Reducer<Text, Text, Text, Text> {
    private Text result = new Text();
    private Text record = new Text();
    public void reduce(Text key, Iterable<Text> values, 
                       Context context
                       ) throws IOException, InterruptedException {
      int count = 0;
      float aveScore = 0;
      for (Text val : values) {
    	aveScore += Float.parseFloat(val.toString());
        count++;
      }
      aveScore = aveScore / count;
      record.set(key + " " + String.valueOf(count));
      result.set(String .format("%.3f",aveScore));
      context.write(record, result);
      System.out.println(record.toString() + " " + String .format("%.3f",aveScore));
    }
  }
 
  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if(otherArgs.length < 2) {
        System.err.println("Usage: wordcount <in> [<in>...] <out>");
        System.exit(2);
    }
    Job job = new Job(conf, new Test().getClass().getName());
    job.setJarByClass(Test.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setMapOutputKeyClass(Text.class); 
    job.setMapOutputValueClass(Text.class);
    job.setReducerClass(AverageReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    for (int i = 0; i < otherArgs.length - 1; ++i) {
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    FileOutputFormat.setOutputPath(job,
      new Path(otherArgs[otherArgs.length - 1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
  
}