首页 > 代码库 > hadoop2.2.0 MapReduce分区
hadoop2.2.0 MapReduce分区
package com.my.hadoop.mapreduce.partition;
import java.util.HashMap;
import java.util.Map;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 ParCount {
public static class ParMap extends Mapper<LongWritable, Text, Text, InfoBean>{
private Text key = new Text();
@Override
public void map(LongWritable key, Text value, Context context) throws java.io.IOException ,InterruptedException {
String[] fields = value.toString().split("\t");
String telNo = fields[1];
long upPayLoad = Long.parseLong(fields[8]);
long downPayLoad = Long.parseLong(fields[9]);
InfoBean bean = new InfoBean(telNo, upPayLoad, downPayLoad);
this.key.set(telNo);
context.write(this.key, bean);
}
}
public static class ParReduce extends Reducer<Text, InfoBean, Text, InfoBean>{
@Override
public void reduce(Text key, java.lang.Iterable<InfoBean> value, org.apache.hadoop.mapreduce.Reducer<Text,InfoBean,Text,InfoBean>.Context context) throws java.io.IOException ,InterruptedException {
long up_sum = 0;
long down_sum = 0;
for (InfoBean bean : value) {
up_sum += bean.getUpPayLoad();
down_sum += bean.getDownPayLoad();
}
InfoBean bean = new InfoBean("", up_sum, down_sum);
context.write(key, bean);
}
}
/**
* 分区,参数为Map的输出
* @author yao
*
*/
public static class MyPar extends Partitioner<Text, InfoBean>{
private static Map<String, Integer> parFlag = new HashMap<String, Integer>();
static {
parFlag.put("135", 1);
parFlag.put("136", 1);
parFlag.put("137", 1);
parFlag.put("138", 1);
parFlag.put("139", 1);
parFlag.put("150", 2);
parFlag.put("159", 2);
parFlag.put("182", 3);
parFlag.put("183", 3);
}
@Override
public int getPartition(Text key, InfoBean value, int arg2) {
String telNo = key.toString().substring(0, 3);
Integer code = parFlag.get(telNo);
if (code == null) {
code = 0;
}
return code;
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, ParCount.class.getSimpleName());;
job.setJarByClass(ParCount.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
job.setMapperClass(ParMap.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(InfoBean.class);
job.setPartitionerClass(MyPar.class); //指定自定义的分区类
job.setNumReduceTasks(4); //需要根据分区的数量设置Reducer数量,多了会出现空文件,少了会报错
job.setReducerClass(ParReduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(InfoBean.class);
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
hadoop2.2.0 MapReduce分区