我正在尝试使用Hadoop mapReduce对输入的数据进行排序。问题是我只能按键对键值对进行排序,而我试图按值对它们进行排序。每个值的键都是用一个计数器创建的,所以第一个值(234)具有键1,第二个值(944)具有键2,依此类推。关于如何操作并按值对输入进行排序的任何想法吗? >
import java.io.IOException;
import java.util.StringTokenizer;
import java.util.ArrayList;
import java.util.List;
import java.util.Collections;
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;
public class Sortt {
public static class TokenizerMapper
extends Mapper<Object, Text, Text ,IntWritable >{
int k=0;
int v=0;
int va=0;
public Text ke = new Text();
private final static IntWritable val = new IntWritable();
public void map(Object key, Text value, Context context) throws
IOException, InterruptedException
{
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens())
{
val.set(Integer.parseInt(itr.nextToken()));
v=val.get();
k=k+1;
ke.set(Integer.toString(k));
context.write(ke, new IntWritable(v));}
}
}
public static class SortReducer
extends Reducer<Text,IntWritable,Text,IntWritable> {
int a=0;
int v=0;
private IntWritable va = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values,
Context context
) throws IOException, InterruptedException {
List<Integer> sorted = new ArrayList<Integer>();
for (IntWritable val : values) {
a= val.get();
sorted.add(a);
}
Collections.sort(sorted);
for(int i=0;i<sorted.size();i++) {
v=sorted.get(i);
va.set(v);
context.write(key, va);
}
}
}
public static void main(String[] args) throws Exception {
long startTime=0;
long Time=0;
long duration=0;
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "sort");
job.setJarByClass(Sortt.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(SortReducer.class);
job.setReducerClass(SortReducer.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);
Time = System.currentTimeMillis();
//duration = (endTime-startTime)/1000000;
System.out.println("time="+Time+"MS");
}
}
输入:
234
944
241
130
369
470
250
100
250
735
856
659
425
756
123
756
459
754
654
951
753
254
698
741
预期输出:
8100
15 123
4130
1 234
3 241
24 241
7 250
9250
22 254
5 369
13425
17 459
6 470
19 654
12 659
23698
10 735
21 753
18 754
14 756
16 756
11 856
2 944
20 951
当前输出:
1 234
10 735
11 856
12 659
13425
14 757
15 123
16 756
17 459
18 754
19 654
2 944
20 951
21 753
22 254
23698
24 741
3 241
4130
5 369
6 470
7 250
8100
9250
答案 0 :(得分:0)
MapReduce默认情况下按键对输出进行排序,而要对值进行排序,则可以使用辅助排序。 次级排序是对根据值对化简器输出进行排序的最佳技术之一,here是一个完整的示例。