mapreduce-reducer给出错误的输出日期

zf9nrax1  于 2021-06-03  发布在  Hadoop
关注(0)|答案(1)|浏览(243)

我已经编写了一个mapreduce程序来解析csv中的值。
数据集如下-
普拉文,40020,婴儿,026A22015年4月12日
普拉文,40020,玩具,0383,1/04/2014
praveen,272,图书,033832013年3月14日
普拉文,22636,自行车,737,2012年12月24日
我的Map函数是从csv读取第一个值(即用户名)作为键,最后一个值(即日期)作为值
我的reduce函数也非常简单,我必须从特定键ie username的值列表中选择最新日期作为值
守则如下—

package com.test.mapreduce;
  import java.io.IOException;
  import java.text.ParseException;
  import java.text.SimpleDateFormat;
  import java.util.ArrayList;
  import java.util.Date;
  import java.util.HashSet;
  import java.util.Iterator;
  import java.util.List;
  import java.util.Set;

  import org.apache.hadoop.conf.Configuration;
  import org.apache.hadoop.conf.Configured;
  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.mapred.FileInputFormat;
  import org.apache.hadoop.mapred.FileOutputFormat;
  import org.apache.hadoop.mapred.JobClient;
  import org.apache.hadoop.mapred.JobConf;
  import org.apache.hadoop.mapred.KeyValueTextInputFormat;
  import org.apache.hadoop.mapred.MapReduceBase;
  import org.apache.hadoop.mapred.Mapper;
  import org.apache.hadoop.mapred.OutputCollector;
  import org.apache.hadoop.mapred.Reducer;
  import org.apache.hadoop.mapred.Reporter;
  import org.apache.hadoop.mapred.TextInputFormat;
  import org.apache.hadoop.mapred.TextOutputFormat;
  import org.apache.hadoop.util.Tool;
  import org.apache.hadoop.util.ToolRunner;

 public class RetailCustomerAnalysis_2 extends Configured implements Tool {
             public static class MapClass extends MapReduceBase
             implements Mapper<LongWritable, Text, Text, Text> {

      private Text key1 = new Text();
      private Text value1 = new Text();
      private int noofFields = 5;

 public void map(LongWritable key, Text value,
                 OutputCollector<Text, Text> output,
                 Reporter reporter) throws IOException {

        String line = value.toString().replaceAll("\\s+","");
        String[] split = line.split(",");

        if(split.length!=noofFields){
        return;
        }

        else {
            key1.set(split[0].toString().trim()); 
            value1.set(split[4].toString().trim());
            System.out.println(split[4].toString().trim());
            output.collect(key1, value1);
     }
    }
  }

 public static class Reduce extends MapReduceBase
 implements Reducer<Text, Text, Text, Text> {

 public void reduce(Text key, Iterator<Text> values,
                    OutputCollector<Text, Text> output,
                    Reporter reporter) throws IOException {

     SimpleDateFormat formatter = new SimpleDateFormat("MM/dd/yyyy");
     Date date = new Date();

     List<Text> dateList = new ArrayList<Text>();

     for(Iterator<Text> it = values; it.hasNext();) {
         // add the values in the arrayList
         dateList.add((Text) it.next());
     }

     if(dateList.size()==1){ //If the mapper output has only one date , then select that date 
                             // as the VALUE
     try  {
            date = formatter.parse(dateList.get(0).toString());
          } catch (ParseException e) {
            e.printStackTrace();
        }
     } //If part ends 

     else {
             try {
               date = formatter.parse(dateList.get(0).toString()); 
                      //select the first date from list
             } catch (ParseException e1) {
               e1.printStackTrace();
             }

             for(int i=0 ; i <dateList.size();++i){
                   try {
                   //compare the selected date with the rest of the dates in the list.
                   if((formatter.parse(dateList.get(i).toString())).compareTo(date)>0){
                       date=formatter.parse(dateList.get(i).toString());
                       // getting the max date from the list
                        }
                   }
                   catch (ParseException e) {
                  e.printStackTrace();
                }
             } //for loops ends
     }  // else part ends    

     Text value = new Text(date.toString());
       output.collect(key, value);
      }
  }

 public int run(String[] args) throws Exception {
 Configuration conf = getConf();

 JobConf job = new JobConf(conf, RetailCustomerAnalysis_2.class);

 Path in = new Path(args[0]);
 Path out = new Path(args[1]);
 FileInputFormat.setInputPaths(job, in);
 FileOutputFormat.setOutputPath(job, out);

 job.setJobName("RetailCustomerAnalysis_2");
 job.setMapperClass(MapClass.class);
 job.setReducerClass(Reduce.class);

 job.setInputFormat(TextInputFormat.class);
 job.setOutputFormat(TextOutputFormat.class);
 job.setOutputKeyClass(Text.class);
 job.setOutputValueClass(Text.class);
 job.set("key.value.separator.in.input.line", ",");

 JobClient.runJob(job);
 return 0;
  }

public static void main(String[] args) throws Exception { 
 int res = ToolRunner.run(new Configuration(), new RetailCustomerAnalysis_2(), args);

 System.exit(res);
 }

 }

但我从名单上随机得到了一个日期。有人能帮忙吗。

mrzz3bfm

mrzz3bfm1#

代码基本正确。reducer的实现需要稍加修改。下面的代码狙击手制造的问题

for(Iterator<Text> it = values; it.hasNext();) {
   // add the values in the arrayList
   dateList.add((Text) it.next());
}

在上面的代码片段中,每个itreation中使用了相同的值对象,只更改了它们的内容。
例如,假设mapreduce使用以下输入运行
普拉文,4002013454,婴儿,026a12,12/04/2015
普拉文,4002013454,玩具,020383,1/04/2014
普拉文,272,书,033832013年3月14日
普拉文,2263637373,自行车,73737,2012年12月24日
在reduce方法“datelist”中,对象elemets在for循环完成后具有值(12/24/2012、12/24/2012、12/24/2012、12/24/2012)。这会导致剩余代码的不正确执行,并且最终输出是错误的。
相反,您更改代码如下

public static class Reduce extends MapReduceBase implements Reducer<Text, Text, Text, Text> {

    public void reduce(Text key, Iterator<Text> values, OutputCollector<Text, Text> output, Reporter reporter) throws IOException {

        SimpleDateFormat formatter = new SimpleDateFormat("MM/dd/yyyy");
        Date date = new Date();
        //-----Modified section START-----------
        List<String> dateList = new ArrayList<String>();

        for(Iterator<Text> it = values; it.hasNext();) {
            // add the values in the arrayList
            dateList.add(((Text)it.next()).toString());
        }
        //----Modified section END--------------
        if(dateList.size()==1){ //If the mapper output has only one date , then select that date 
            // as the VALUE
            try  {
                date = formatter.parse(dateList.get(0).toString());
            } catch (ParseException e) {
                e.printStackTrace();
            }
        } //If part ends 
        else {
            String str = dateList.get(0).toString();
            try {

                date = formatter.parse(dateList.get(0).toString());
                //select the first date from list
            } catch (ParseException e1) {
                e1.printStackTrace();
            }

            for(int i=0 ; i <dateList.size();++i){
                try {
                    //compare the selected date with the rest of the dates in the list.
                    if((formatter.parse(dateList.get(i).toString())).compareTo(date)>0){
                        date=formatter.parse(dateList.get(i).toString());
                        // getting the max date from the list
                    }
                }
                catch (ParseException e) {
                    e.printStackTrace();
                }
            } //for loops ends
        }  // else part ends    

        Text value = new Text(date.toString());
        output.collect(key, value);
    }
}

请参考内存中的hadoop reducer值?有关Map中对象引用的详细信息,请参阅reduce方法。

相关问题