hadoop期末考试题

Hadoop期末考试题

简介

Hadoop是一种分布式计算框架，用于处理大规模数据集。它提供了可靠的存储和高效的处理能力，可以运行在由成百上千台服务器组成的集群上。Hadoop的核心是由两个部分组成：Hadoop分布式文件系统（HDFS）和Hadoop分布式计算框架（MapReduce）。在本文中，我们将探讨一些关于Hadoop的期末考试题，并提供相应的代码示例。

Hadoop期末考试题

题目一：Word Count

实现一个简单的Word Count程序，统计给定文本中单词的出现次数。

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);
  }
}

题目二：TopK

实现一个TopK程序，找到给定文本中出现次数最多的前K个单词。

import java.io.IOException;
import java.util.Map;
import java.util.TreeMap;
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 TopK {
 
  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 TreeMap<Integer, String> topKMap = new TreeMap<>();
    private int k;
 
    protected void setup(Context context) throws IOException, InterruptedException {
      k = context.getConfiguration().getInt("topk.k", 10);
    }
 
    public void reduce(Text key, Iterable<IntWritable> values,
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      topKMap.put(sum, key.toString());
      if (topKMap.size() > k) {
        topKMap.remove(topKMap.firstKey());
      }
    }
 
    protected void cleanup(Context context) throws IOException, InterruptedException {
      for (Map.Entry<Integer, String> entry : topKMap.descendingMap().entrySet()) {
        context.write(new Text(entry.getValue()), new IntWritable(entry