我已经使用自定义分区程序编写了一个示例mapreduce程序。 我有一个带有数字和文字的文件。数字可以是偶数和奇数的混合。我想对数字进行分区,并将偶数和一个reducer中的偶数移动到另一个reducer。我将reduce partitioners的数量设置为2,但数据只显示在一个reducer中,而分区器不能正常工作,我猜。如果在任何地方出错,请查找内联程序并纠正我。
package com.mapreduce;
import java.io.IOException;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.util.GenericOptionsParser;
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 FindEvenOddNumber {
/**
* @param args
* @throws IOException
*/
public static class MyMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
Text emitKey = new Text();
IntWritable emitValue = new IntWritable();
public void map(LongWritable key, Text value, Context context) throws InterruptedException, IOException {
String line = value.toString();
String[] data = line.split("\\t");
if (data.length == 2) {
emitValue.set(Integer.valueOf(data[0]));
emitKey.set(data[1]);
context.write(emitKey,emitValue);
}
}
}
public static class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterable<IntWritable> values, Context context)throws IOException, InterruptedException {
for(IntWritable value : values)
{
context.write(key, value);
}
}
}
public static class ReducerPartitioner extends Partitioner<Text, IntWritable>{
@Override
public int getPartition(Text key, IntWritable value, int numReduceTasks) {
int number = value.get();
if( numReduceTasks == 0)
{
return 0;
}
if ( number % 2 == 0 ){
System.out.println("You entered an even number.");
return 1 % numReduceTasks;
}
/*if(number >2){
return 1 % numReduceTasks;
}*/
else
{
return 2 % numReduceTasks;
}
}
}
/**
* @param args
*/
public static void main(String args[]) throws IOException,InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
String userArgs[] = new GenericOptionsParser(conf, args).getRemainingArgs();
if (userArgs.length < 2) {
System.out.println("Usage: hadoop jar jarfilename mainclass input output");
System.exit(1);
}
Job job = new Job(conf, "Partitioning Even Odd Numbers");
job.setJarByClass(FindEvenOddNumber.class);
job.setMapperClass(MyMapper.class);
job.setReducerClass(MyReducer.class);
job.setPartitionerClass(ReducerPartitioner.class);
job.setNumReduceTasks(2);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(userArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(userArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
我的数据是:
0 zero
1 one
2 two
3 three
4 four
5 five
and so on
答案 0 :(得分:0)
那个适合我:
public static class ReducerPartitioner extends Partitioner<Text, IntWritable>{
@Override
public int getPartition(Text key, IntWritable value, int numReduceTasks) {
// assert that numReduceTasks is at least 2...
return value.get() % 2 == 0 ? 0 : 1;
}
}