实验6：Mapreduce实例——WordCount

1. 启动hadoop。

Start-dfs.sh

 

 

 

 

1. 创建在系统中创建一个的TXT文件，并将上面的数据包复制到文件中

 

 

 

1. 将写好的文件从本地上传到hadoop上

（1）进入hadoop目录

 

 

 

（2）上传文件

 

 

 

1. 在eclipse中创建MapReduce程序命名为count，然后导入相关的jar包

 

 

 

然后还需要导入三个配置文件：其中log4j.properties是一个日志文件，如果没有这个文件程序就不会正常运行

 

 

 代码：WordCount java

package test6;

import java.io.IOException;  
import java.util.StringTokenizer;  
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 void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {  
	        Job job = Job.getInstance();  
	        job.setJobName("WordCount");  
	        job.setJarByClass(WordCount.class);  
	        job.setMapperClass(doMapper.class);  
	        job.setReducerClass(doReducer.class);  
	        job.setOutputKeyClass(Text.class);  
	        job.setOutputValueClass(IntWritable.class);  
	        Path in = new Path("hdfs://192.168.43.102:9000/user/hadoop/input/mapReduceTest2.txt");  
	        Path out = new Path("hdfs://192.168.43.102:9000/user/hadoop/output5");  
	        FileInputFormat.addInputPath(job, in);  
	        FileOutputFormat.setOutputPath(job, out);  
	        System.exit(job.waitForCompletion(true) ? 0 : 1);  
	    }  
	    public static class doMapper extends Mapper<Object, Text, Text, IntWritable>{  
	        public static final IntWritable one = new IntWritable(1);  
	        public static Text word = new Text();  
	        @Override  
	        protected void map(Object key, Text value, Context context)  
	                    throws IOException, InterruptedException {  
	            StringTokenizer tokenizer = new StringTokenizer(value.toString(), " ");  
	                word.set(tokenizer.nextToken());  
	                context.write(word, one);  
	        }  
	    }  
	    public static class doReducer extends Reducer<Text, IntWritable, Text, IntWritable>{  
	        private IntWritable result = new IntWritable();  
	        @Override  
	        protected void reduce(Text key, Iterable<IntWritable> values, Context context)  
	        throws IOException, InterruptedException {  
	        int sum = 0;  
	        for (IntWritable value : values) {  
	        sum += value.get();  
	        }  
	        result.set(sum);  
	        context.write(key, result);  
	        }  
	    }  
	}  

　　

实验结果：