Question

有人可以帮助我找出为什么我在运行MapReduce代码后没有得到平均工资问题：计算永久雇员和合同雇员的平均工资

示例输入：
    1 user1永久100
    2 user2合同500
    3 user3永久200
    4 user4合同300

预期产出：
永久285
合同187

我得到的输出：
    永久的100
    永久200
    合同500
    合同300

运行工作： $ hadoop jar partition.jar com.hadoop.PartitionExample input / partition_example.txt输出

package com.hadoop;
import java.io.IOException;
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;


public class PartitionExample {
        public static class MapClass extends Mapper<LongWritable, Text, 
        Text, IntWritable>{

        Text outKey = new Text(); ;
        IntWritable outValue = new IntWritable();

        public void map(LongWritable key, Text value, Context context) 
        throws IOException, InterruptedException{
            String[] colmn = value.toString().split(" ");
            outKey.set(colmn[2]);           
            outValue.set(Integer.parseInt(colmn[3])); 
            context.write(outKey, outValue);
     }
}
// permanent      [100,300,200,400]
public static class ReduceClass extends Reducer<Text,IntWritable,Text, 
IntWritable>{
        IntWritable outValue = new IntWritable();
        public void Reduce(Text key, Iterable<IntWritable> value, Context 
        context) throws IOException, InterruptedException{
            int sum = 0; int count = 0; int avg ;
            //outKey.set(key);
            for (IntWritable sal:value){
                sum = sum + sal.get(); 
                count++;
            }
            avg = sum/count ;
            outValue.set(avg);
            context.write(key, outValue);
     }
 }

public static void main(String[] args) throws IOException, 
    ClassNotFoundException, InterruptedException{
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if(otherArgs.length != 2){
        System.err.println("Number of argument passed is not 2");
        System.exit(1);
    }
    Job job = new Job(conf, "My regular MapReduce job");

    job.setJarByClass(PartitionExample.class);
    job.setMapperClass(MapClass.class);
//  job.setCombinerClass(ReduceClass.class);
    job.setReducerClass(ReduceClass.class);

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

}
}

Answer 1

我在代码中发现了我的错误。我可以说这是非常愚蠢的错误:( 它是在ovirridden中减少函数名称。我将它从“减少”更改为“减少”。

通过MapReduce代码获得的平均工资

1 个答案: