Question

10001|76884|1995-06-24|1996-06-23
10001|76884|1995-06-24|1996-06-23
10001|75286|1993-06-24|1994-06-24

我的目标是删除dup值，输出就像

10001|76884|1995-06-24|1996-06-23
10001|75286|1993-06-24|1994-06-24

我写了一个代码如下

import java.io.IOException;
import java.util.*;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.conf.*;

import org.apache.hadoop.io.*;

import org.apache.hadoop.mapred.JobClient;

import org.apache.hadoop.mapreduce.*;

import org.apache.hadoop.mapreduce.Mapper.Context;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class charterSelDistRec {

        public static class Map extends Mapper <LongWritable, Text, Text, Text> {
            private String tableKey,tableValue;

            public void map(LongWritable key, Text value, Context context)
 throws IOException, InterruptedException {

                    String line = value.toString();
                    String splitarray[] = line.split("\\|",2);
                    tableKey = splitarray[0].trim();
                    tableValue = splitarray[1].trim();

                    context.write(new Text(tableKey), new Text(tableValue));     
                }
        }               

        public static class Reduce extends Reducer <Text, Text, Text, Text> {                         
            public void reduce(Text key, Iterator<Text> values, Context context) 
                      throws IOException, InterruptedException {
                    String ColumnDelim="";
                    String tableOutValue=ColumnDelim+values;
                    context.write(new Text(key), new Text(tableOutValue));

                }
        }

        public static void main(String[] args) throws Exception {
                Configuration conf = new Configuration();
                Job job = new Job(conf,"charterSelDistRec");
                job.getConfiguration().set("mapreduce.job.queuename", "root.Dev");
                job.getConfiguration().set("mapreduce.output.textoutputformat.separator","|");
                job.setJobName("work_charter_stb.ext_chtr_vod_fyi_mapped");
                job.setOutputKeyClass(Text.class);
                job.setOutputValueClass(Text.class);

                job.setMapperClass(Map.class);

                job.setReducerClass(Reduce.class);

                job.setInputFormatClass(TextInputFormat.class);
                job.setOutputFormatClass(TextOutputFormat.class);


                FileInputFormat.addInputPath(job, new Path(args[0]));
                FileOutputFormat.setOutputPath(job, new Path(args[1]));
                job.setJarByClass(charterSelDistRec.class); 
                job.waitForCompletion(true);
          }
      }

但输出文件仍然有重复。请让我知道我错在哪里。

Answer 1

不一定非常复杂。您所要做的就是：

，将每一行作为键和任何值
，只需发出键并忽略值。

分享代码：

这是输入：

10001|76884|1995-06-24|1996-06-23
10001|76884|1995-06-24|1996-06-23
10001|75286|1993-06-24|1994-06-24

以下是代码：

public class StackRemoveDup {

    public  static class MyMapper extends Mapper<LongWritable,Text, Text, NullWritable> {

        @Override
        public void map(LongWritable ignore, Text value, Context context)
            throws java.io.IOException, InterruptedException {
            context.write(value,NullWritable.get());
        }  
    }

    public static class MyReducer extends Reducer<Text, NullWritable, Text, NullWritable> {

      @Override
      public void reduce(Text key, Iterable<NullWritable> values, Context context)
          throws IOException, InterruptedException {
        context.write(key, NullWritable.get());
      }
    }       

  public static void main(String[] args) 
                  throws IOException, ClassNotFoundException, InterruptedException {

    Job job = new Job();
    job.setJarByClass(StackRemoveDup.class);
    job.setJobName("StackRemoveDup");

    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.class);

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(NullWritable.class);

    job.waitForCompletion(true);
  }
}

这是输出：

10001|75286|1993-06-24|1994-06-24
10001|76884|1995-06-24|1996-06-23

Answer 2

第一行有两条记录，第二行有一条记录。一旦在map中读完，你就会基于|进行拆分，但你的行（实体）是按空格分隔的，正如我所看到的。只需验证实际数据是否如何。传统格式就像是，每行（实体）在一行中，而map reduce会在映射阶段之后过滤唯一键。一旦您的输入采用该格式，您在reducer中获得的只是唯一键。

如果您的输入有所不同（如上面 - 同一行中的2条记录），您需要考虑不同的输入格式，或者以不同的方式处理逻辑。了解map reduce如何工作以及它所采用的格式将对您有所帮助。快乐学习

Answer 3

试试这个。这个想法只发出Iterable的第一个值，因为它们都是相同的，你想删除dup值。

import java.io.IOException;
import java.util.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class charterSelDistRec {

    public  static class MyMapper extends Mapper<LongWritable, Text, Text, Text> {

        @Override
        public void map(LongWritable ignore, Text value, Context context)
            throws IOException, InterruptedException {
            context.write(value, value);
        }  
    }

    public static class MyReducer extends Reducer<Text, Text, Text, NullWritable> {    
      @Override
      public void reduce(Text key, Iterable<Text> values, Context context)
          throws IOException, InterruptedException {
          for (Text value : values){
              context.write(value, NullWritable.get());
              break;
          }
      }
    }       

  /* This is your main. Changed the outputValueClass method only */
  public static void main(String[] args) throws Exception {
      Configuration conf = new Configuration();
      Job job = new Job(conf,"charterSelDistRec");
      job.getConfiguration().set("mapreduce.job.queuename", "root.Dev");
      job.getConfiguration().set("mapreduce.output.textoutputformat.separator","|");
      job.setJobName("work_charter_stb.ext_chtr_vod_fyi_mapped");
      job.setOutputKeyClass(Text.class);
      job.setOutputValueClass(NullWritable.class);

      job.setMapperClass(Map.class);

      job.setReducerClass(Reduce.class);

      job.setInputFormatClass(TextInputFormat.class);
      job.setOutputFormatClass(TextOutputFormat.class);


      FileInputFormat.addInputPath(job, new Path(args[0]));
      FileOutputFormat.setOutputPath(job, new Path(args[1]));
      job.setJarByClass(charterSelDistRec.class); 
      job.waitForCompletion(true);
   }
}

在java map reduce中选择distinct查询

3 个答案: