我正在尝试计算 hadoop 独立设置中的平均数字。我无法运行该程序。但是程序编译没有任何错误，并且还创建了 jar 文件。我想我正在使用正确的命令在 hadoop 设置中执行程序。有人请查看我的代码并告诉我是否有任何问题。这是我的代码

import java.io.IOException;
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;
  class sum_count{
    int sum;
    int count;  
  }
public class Average {


  public static class TokenizerMapper
       extends Mapper<Object, Text, Text, Object>{

    private final static IntWritable valueofkey = new IntWritable();
    private Text word = new Text();
    sum_count sc=new sum_count();
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      int sum=0;
      int count=0;
      int v;
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        v=Integer.parseInt(word.toString());
        count=count+1;
        sum=sum+v;       
      }
      //valueofkey.set(sum);
      word.set("average");

      sc.sum=sum;
      sc.count=count;

    // context.write(word, valueofkey);
     // valueofkey.set(count);
      //  word.set("count");
      context.write(word,sc);
    }
  }

  public static class IntSumReducer
       extends Reducer<Text,Object,Text,IntWritable> {
    private IntWritable result = new IntWritable();
    private IntWritable test=new IntWritable();

    public void reduce(Text key, Iterable<sum_count> values,Context context) throws IOException, InterruptedException {
      int sum = 0;
      int count=0;
      int wholesum=0;
      int wholecount=0;
      for (sum_count val : values) {
        //value=val.get();
        wholesum=wholesum+val.sum;
        wholecount=wholecount+val.count;
      }
      int res=wholesum/wholecount;
      result.set(res);
      context.write(key, result );
    }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "");
    job.setJarByClass(Average.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

这是我的输出:

manu@manu-Latitude-E5430-vPro:~/hadoop-2.7.2$ ./bin/hadoop jar av.jar Average bin/user/hduser/input bin/user/hduser/out12
Picked up JAVA_TOOL_OPTIONS: -javaagent:/usr/share/java/jayatanaag.jar 
16/07/01 11:19:05 INFO Configuration.deprecation: session.id is deprecated. Instead, use dfs.metrics.session-id
16/07/01 11:19:05 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId=
16/07/01 11:19:05 WARN mapreduce.JobResourceUploader: Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
16/07/01 11:19:05 INFO input.FileInputFormat: Total input paths to process : 2
16/07/01 11:19:05 INFO mapreduce.JobSubmitter: number of splits:2
16/07/01 11:19:05 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_local276107063_0001
16/07/01 11:19:05 INFO mapreduce.Job: The url to track the job: http://localhost:8080/
16/07/01 11:19:05 INFO mapreduce.Job: Running job: job_local276107063_0001
16/07/01 11:19:05 INFO mapred.LocalJobRunner: OutputCommitter set in config null
16/07/01 11:19:05 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
16/07/01 11:19:05 INFO mapred.LocalJobRunner: OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
16/07/01 11:19:05 INFO mapred.LocalJobRunner: Waiting for map tasks
16/07/01 11:19:05 INFO mapred.LocalJobRunner: Starting task: attempt_local276107063_0001_m_000000_0
16/07/01 11:19:06 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
16/07/01 11:19:06 INFO mapred.Task:  Using ResourceCalculatorProcessTree : [ ]
16/07/01 11:19:06 INFO mapred.LocalJobRunner: Starting task: attempt_local276107063_0001_m_000001_0
16/07/01 11:19:06 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
16/07/01 11:19:06 INFO mapred.Task:  Using ResourceCalculatorProcessTree : [ ]
16/07/01 11:19:06 INFO mapred.LocalJobRunner: map task executor complete.
16/07/01 11:19:06 WARN mapred.LocalJobRunner: job_local276107063_0001
java.lang.Exception: java.lang.RuntimeException: java.lang.reflect.InvocationTargetException
    at org.apache.hadoop.mapred.LocalJobRunner$Job.runTasks(LocalJobRunner.java:462)
    at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:522)
Caused by: java.lang.RuntimeException: java.lang.reflect.InvocationTargetException
    at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:134)
    at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:745)
    at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
    at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:243)
    at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
    at java.util.concurrent.FutureTask.run(FutureTask.java:262)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
    at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.reflect.InvocationTargetException
    at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
    at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:57)
    at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
    at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
    at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:132)
    ... 8 more
Caused by: java.lang.NoClassDefFoundError: sum_count
    at Average$TokenizerMapper.<init>(Average.java:24)
    ... 13 more
Caused by: java.lang.ClassNotFoundException: sum_count
    at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
    at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
    at java.security.AccessController.doPrivileged(Native Method)
    at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:425)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:358)
    ... 14 more
16/07/01 11:19:06 INFO mapreduce.Job: Job job_local276107063_0001 running in uber mode : false
16/07/01 11:19:06 INFO mapreduce.Job:  map 0% reduce 0%
16/07/01 11:19:06 INFO mapreduce.Job: Job job_local276107063_0001 failed with state FAILED due to: NA
16/07/01 11:19:06 INFO mapreduce.Job: Counters: 0

最佳答案

您在 sum_count 上收到了 ClassNotFoundException。在文件的顶层声明两个类并不是构建代码的好方法。看起来当 TokenizerMapper 尝试创建该类时，它无法在类路径中找到它。

我会把那个类放在它自己的文件中。无论如何它都需要更改，因为 sum_count 没有 implement Writable 接口(interface)，所以您的工作将无法正常工作。它应该看起来更像:

public class SumCount implements Writable {

    public int sum;
    public int count;

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(sum);
        out.writeInt(count);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        sum = in.readInt();
        count = in.readInt();
    }  
}

在您的 main() 中，您还需要告诉它它将写出的键/值类型是:

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

注意类名的变化。请参阅 Java 命名约定文档 here .

关于java - 平均 map 减少，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/38137820/