云计算-MapReduce

Posted 悉宇馨

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了云计算-MapReduce相关的知识,希望对你有一定的参考价值。

Hadoop示例程序WordCount详解及实例http://blog.csdn.net/xw13106209/article/details/6116323

hadoop中使用MapReduce编程实例(转)http://eric-gcm.iteye.com/blog/1807468

【mapreduce进阶编程二】奇偶行分别求和http://www.aboutyun.com/forum.php?mod=viewthread&tid=9360

hadoop2.2.0 MapReduce求和并排序http://www.cnblogs.com/mengyao/p/4151509.html

 

MapReduce求最大值http://blog.csdn.net/lzm1340458776/article/details/43227759

慢慢看!

求最大值:

package org.apache.hadoop.examples;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
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.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
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;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class Score2 {
private static String SPILT = " ";
private static int max = -10000;

public static class ScoreMapper extends Mapper<LongWritable, Text, Text, Text> {

public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

int num = Integer.valueOf(String.valueOf(value));

if (max < num)
max = num;
context.write(new Text(String.valueOf(max)), new Text(""));
}
}

public static class MaxReducer extends Reducer<Text, Text, Text, Text> {
@Override
public void reduce(Text key, Iterable<Text> value, Context context) throws IOException, InterruptedException {
int num = Integer.valueOf(String.valueOf(key));

if (num == max) {
context.write(new Text("max:"), new Text(String.valueOf(num)));
}
}
}


public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length < 2) {
System.out.println("please input at least 2 arguments");
System.exit(2);
}

Job job = Job.getInstance(conf, "max");
job.setJarByClass(Score2.class);
job.setMapperClass(ScoreMapper.class);
job.setReducerClass(MaxReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setNumReduceTasks(1);

FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));

System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
 
啊啊啊啊啊啊

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.DoubleWritable.Comparator;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.util.GenericOptionsParser;

 

public class max {
  public static class Map1 extends

     Mapper<Object, Text, Text, IntWritable> {

         public void map(Object key, Text value, Context context)

         throws IOException, InterruptedException {
          int count=0;
          String line = value.toString();
          String s[]=line.split(" ");
          for (int i=0;i<s.length;i++)
          {
           //if (Integer.parseInt(s[i])<min)//s[i]bian int
            //min=Integer.parseInt(s[i]);

           char c[] = s[i].toCharArray();
           if (c[c.length-1]==\'h\')
            count++;

          }
          context.write(new Text("1"), new IntWritable(count));
          //context.write(new Text(key.tostring),new IntWritable(max));

         }

     }

  public static class Reduce1 extends
  Reducer<Text, IntWritable, Text, IntWritable> {
      public void reduce(Text key, Iterable<IntWritable> values,
      Context context) throws IOException, InterruptedException {
       //int min=1000000;
       int sum=0;
          Iterator<IntWritable> iterator = values.iterator();  //
          while (iterator.hasNext()) {
           int n=iterator.next().get();

          // if (n<min)
           // min=n;
         sum=sum+n;
          }
      context.write(new Text(" "), new IntWritable(sum));
      }
  }

  public static void main(String[] args) throws Exception {

         Configuration conf = new Configuration();
         FileSystem fs = FileSystem.get(conf);
         conf.set("mapred.job.tracker", "127.0.0.1:9000");
         String[] otherArgs = new GenericOptionsParser(conf, args)
                 .getRemainingArgs();
         if (otherArgs.length != 2) { //input output

             System.err.println("Usage: Data Deduplication <in> <out><out>");
             System.exit(2);
         }
         Job job = Job.getInstance(conf,"min");

         job.setJarByClass(max.class);

         job.setMapperClass(Map1.class);
         job.setMapOutputKeyClass(Text.class);
         job.setMapOutputValueClass(IntWritable.class);

         job.setReducerClass(Reduce1.class);
         job.setOutputKeyClass(Text.class);
         job.setOutputValueClass(IntWritable.class);

         FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
         Path outpath = new Path(otherArgs[1]);
         if (fs.exists(outpath))
         {
          fs.delete(outpath,true);
         }
         FileOutputFormat.setOutputPath(job, outpath);


         if (job.waitForCompletion(true))
         {

           System.exit(0);

         }

 

     }


}

以上是关于云计算-MapReduce的主要内容,如果未能解决你的问题,请参考以下文章

大数据框架之Hadoop:MapReduceMapReduce框架原理——OutputFormat数据输出

大数据框架之Hadoop:MapReduceMapReduce框架原理——数据清洗(ETL)

大数据框架之Hadoop:MapReduceMapReduce框架原理——Join多种应用

大数据离线

大数据技术栈

MapReduce编程模型——在idea里面邂逅CDH MapReduce