Question

我的输出出错了。输入文件是：

1 2 3 4
5 4 3 2

输出应该是关键：总和值：24

MapReduce产生的输出：key：总和值：34

我在Ubuntu 14.04中使用OpenJDK 7来运行jar文件，而jar文件是在Eclipse Juna中创建的，使用的java版本是Oracle JDK 7来编译它。 NumberDriver.java

包numberum;

import java.io.*;
//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;
import org.apache.hadoop.util.GenericOptionsParser;
public class NumberDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // TODO Auto-generated method stub
            Configuration conf=new Configuration();
            String[] otherArgs=new GenericOptionsParser(conf,args).getRemainingArgs();
            if(otherArgs.length!=2)
            {
                System.err.println("Error");
                System.exit(2);
            }
            Job job=new Job(conf, "number sum");
            job.setJarByClass(NumberDriver.class);
            job.setMapperClass(NumberMapper.class);
            job.setReducerClass(NumberReducer.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(IntWritable.class);
            FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
            FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
            System.exit(job.waitForCompletion(true)?0:1);
    }

}

NumberMapper.java

package numbersum;
import java.io.*;
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.LongWritable;
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;
//import org.hsqldb.Tokenizer;

public class NumberMapper extends Mapper <LongWritable, Text, Text, IntWritable> 
    {
        int sum;
        public void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException
        {
            StringTokenizer itr=new StringTokenizer(value.toString());
            while(itr.hasMoreTokens())
            {
                sum+=Integer.parseInt(itr.nextToken());
            }
            context.write(new Text("sum"),new IntWritable(sum));
        }
    }

NumberReducer.java

package numbersum;
import java.io.*;
//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;
//import org.apache.hadoop.util.GenericOptionsParser;

public class NumberReducer extends Reducer <Text, IntWritable, Text, IntWritable>
    {
        public void reduce(Text key,Iterable<IntWritable> values, Context context)throws IOException, InterruptedException
        {
            int sum=0;
            for(IntWritable value:values)
                {
                    sum+=value.get();
                }
            context.write(key,new IntWritable(sum));
        }
    }

Answer 1

我最好的猜测：

    int sum; // <-- Why a class member?
    public void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException
    {
        int sum = 0; //Why not here?
        StringTokenizer itr=new StringTokenizer(value.toString());

猜测的推理：第一张地图：1 + 2 + 3 + 4 = 10 第二张地图：（10 +）2 + 3 + 4 + 5 = 34

..意思是，保留了之前的值。

Answer 2

我想你忘了在sum函数的开头设置0到map：

public void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException
{
    sum = 0;
...

我试图将所有数字加在一个文件中，该文件包含由空格分隔的数字，并使用MapReduce包含在多行中

2 个答案: