189 8069 5689
这篇文章主要为大家展示了“hadoop中mapreducez如何自定义分区”，内容简而易懂，条理清晰，希望能够帮助大家解决疑惑，下面让小编带领大家一起研究并学习一下“hadoop中mapreducez如何自定义分区”这篇文章吧。
创新互联是一家集网站建设,南通企业网站建设,南通品牌网站建设,网站定制,南通网站建设报价,网络营销,网络优化,南通网站推广为一体的创新建站企业，帮助传统企业提升企业形象加强企业竞争力。可充分满足这一群体相比中小企业更为丰富、高端、多元的互联网需求。同时我们时刻保持专业、时尚、前沿，时刻以成就客户成长自我，坚持不断学习、思考、沉淀、净化自己，让我们为更多的企业打造出实用型网站。
package hello_hadoop;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class AutoParitionner {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
if(args.length!=2) {
System.err.println("Usage: hadoop jar xxx.jar ");
System.exit(1);
}
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "avg of grades");
job.setJarByClass(AutoParitionner.class);
job.setMapperClass(PartitionInputClass.class);
job.setReducerClass(PartitionOutputClass.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(DoubleWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(DoubleWritable.class);
//声明自定义分区的类，下面有类的声明
job.setPartitionerClass(MyPartitioner.class);
job.setNumReduceTasks(2);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true)?0:1);
}
}
class PartitionInputClass extends Mapper{
@Override
protected void map(LongWritable key, Text value, Mapper.Context context)
throws IOException, InterruptedException {
String line = value.toString();
if(line.length()>0){
String[] array = line.split("\t");
if(array.length==2){
String name=array[0];
int grade = Integer.parseInt(array[1]);
context.write(new Text(name), new DoubleWritable(grade));
}
}
}
}
class PartitionOutputClass extends Reducer{
@Override
protected void reduce(Text text, Iterable iterable,
Reducer.Context context) throws IOException, InterruptedException {
int sum = 0;
int cnt= 0 ;
for(DoubleWritable iw : iterable) {
sum+=iw.get();
cnt++;
}
context.write(text, new DoubleWritable(sum/cnt));
}
}
//自定义分区的类
//Partitioner Text,DoubleWirtable分别为map结果的key,value
class MyPartitioner extends Partitioner{
@Override
public int getPartition(Text text, DoubleWritable value, int numofreuceTask) {
String name = text.toString();
if(name.equals("wd")||name.equals("wzf")||name.equals("xzh")||name.equals("zz")) {
return 0;
}else
return 1;
}
} 以上是“hadoop中mapreducez如何自定义分区”这篇文章的所有内容，感谢各位的阅读！相信大家都有了一定的了解，希望分享的内容对大家有所帮助，如果还想学习更多知识，欢迎关注创新互联行业资讯频道！