Hadoop教程：MapReduce

package hadoop; 

import java.util.*; 

import java.io.IOException; 
import java.io.IOException; 

import org.apache.hadoop.fs.Path; 
import org.apache.hadoop.conf.*; 
import org.apache.hadoop.io.*; 
import org.apache.hadoop.mapred.*; 
import org.apache.hadoop.util.*; 

public class ProcessUnits 
{ 
   //Mapper class 
   public static class E_EMapper extends MapReduceBase implements 
   Mapper<LongWritable ,/*Input key Type */ 
   Text,                /*Input value Type*/ 
   Text,                /*Output key Type*/ 
   IntWritable>        /*Output value Type*/ 
   { 
      
      //Map function 
      public void map(LongWritable key, Text value, 
      OutputCollector<Text, IntWritable> output,   
      Reporter reporter) throws IOException 
      { 
         String line = value.toString(); 
         String lasttoken = null; 
         StringTokenizer s = new StringTokenizer(line,"\t"); 
         String year = s.nextToken(); 
         
         while(s.hasMoreTokens())
            {
               lasttoken=s.nextToken();
            } 
            
         int avgprice = Integer.parseInt(lasttoken); 
         output.collect(new Text(year), new IntWritable(avgprice)); 
      } 
   } 
   
   
   //Reducer class 
   public static class E_EReduce extends MapReduceBase implements 
   Reducer< Text, IntWritable, Text, IntWritable > 
   {  
   
      //Reduce function 
      public void reduce( Text key, Iterator <IntWritable> values, 
         OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException 
         { 
            int maxavg=30; 
            int val=Integer.MIN_VALUE; 
            
            while (values.hasNext()) 
            { 
               if((val=values.next().get())>maxavg) 
               { 
                  output.collect(key, new IntWritable(val)); 
               } 
            } 
 
         } 
   }  
   
   
   //Main function 
   public static void main(String args[])throws Exception 
   { 
      JobConf conf = new JobConf(ProcessUnits.class); 
      
      conf.setJobName("max_eletricityunits"); 
      conf.setOutputKeyClass(Text.class);
      conf.setOutputValueClass(IntWritable.class); 
      conf.setMapperClass(E_EMapper.class); 
      conf.setCombinerClass(E_EReduce.class); 
      conf.setReducerClass(E_EReduce.class); 
      conf.setInputFormat(TextInputFormat.class); 
      conf.setOutputFormat(TextOutputFormat.class); 
      
      FileInputFormat.setInputPaths(conf, new Path(args[0])); 
      FileOutputFormat.setOutputPath(conf, new Path(args[1])); 
      
      JobClient.runJob(conf); 
   } 
}

$ mkdir units

$ javac -classpath hadoop-core-1.2.1.jar -d units ProcessUnits.java 
$ jar -cvf units.jar -C units/ .

$HADOOP_HOME/bin/hadoop fs -mkdir input_dir

$HADOOP_HOME/bin/hadoop jar units.jar hadoop.ProcessUnits input_dir output_dir

INFO mapreduce.Job: Job job_1414748220717_0002 
completed successfully 
14/10/31 06:02:52 
INFO mapreduce.Job: Counters: 49 
File System Counters 
 
FILE: Number of bytes read=61 
FILE: Number of bytes written=279400 
FILE: Number of read operations=0 
FILE: Number of large read operations=0   
FILE: Number of write operations=0 
HDFS: Number of bytes read=546 
HDFS: Number of bytes written=40 
HDFS: Number of read operations=9 
HDFS: Number of large read operations=0 
HDFS: Number of write operations=2 Job Counters 


   Launched map tasks=2  
   Launched reduce tasks=1 
   Data-local map tasks=2  
   Total time spent by all maps in occupied slots (ms)=146137 
   Total time spent by all reduces in occupied slots (ms)=441   
   Total time spent by all map tasks (ms)=14613 
   Total time spent by all reduce tasks (ms)=44120 
   Total vcore-seconds taken by all map tasks=146137 
   
   Total vcore-seconds taken by all reduce tasks=44120 
   Total megabyte-seconds taken by all map tasks=149644288 
   Total megabyte-seconds taken by all reduce tasks=45178880 
   
Map-Reduce Framework 
 
Map input records=5  
   Map output records=5   
   Map output bytes=45  
   Map output materialized bytes=67  
   Input split bytes=208 
   Combine input records=5  
   Combine output records=5 
   Reduce input groups=5  
   Reduce shuffle bytes=6  
   Reduce input records=5  
   Reduce output records=5  
   Spilled Records=10  
   Shuffled Maps =2  
   Failed Shuffles=0  
   Merged Map outputs=2  
   GC time elapsed (ms)=948  
   CPU time spent (ms)=5160  
   Physical memory (bytes) snapshot=47749120  
   Virtual memory (bytes) snapshot=2899349504  
   Total committed heap usage (bytes)=277684224
     
File Output Format Counters 
 
   Bytes Written=40

$HADOOP_HOME/bin/hadoop fs -ls output_dir/

$HADOOP_HOME/bin/hadoop fs -cat output_dir/part-00000

$HADOOP_HOME/bin/hadoop fs -cat output_dir/part-00000/bin/hadoop dfs get output_dir /home/hadoop

$ $HADOOP_HOME/bin/hadoop job -status <JOB-ID> 
e.g. 
$ $HADOOP_HOME/bin/hadoop job -status job_201310191043_0004

$ $HADOOP_HOME/bin/hadoop job -history <DIR-NAME> 
e.g. 
$ $HADOOP_HOME/bin/hadoop job -history /user/expert/output

$ $HADOOP_HOME/bin/hadoop job -kill <JOB-ID> 
e.g. 
$ $HADOOP_HOME/bin/hadoop job -kill job_201310191043_0004