Mapreduce《案例之数据排序》
数据源：
a.txt 内容：
aaa 120
bbb 100
ccc 130
ddd 150
b.txt内容：
aaa 121
bbb 101
ccc 131
ddd 150
c.txt内容
aaa 119
bbb 99
ccc 129
ddd 150
输出结果：
aaa120
bbb100
ccc130
ddd150
===========================java code==========================
package gq;
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
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.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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
/**
*
* Class Description:求平均分测试类
*
* Author:gaoqi
*
* Date:2015年6月5日 下午2:03:08
*
*/
public class AvgScore {
public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
public void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException{
String line = value.toString().trim();
StringTokenizer stk = new StringTokenizer(line,"/n");
while(stk.hasMoreElements()){
StringTokenizer sk = new StringTokenizer(stk.nextToken());
context.write(new Text(sk.nextToken()), new IntWritable(Integer.parseInt(sk.nextToken())));
}
}
}
public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException{
Iterator<IntWritable> its = values.iterator();
int sum = 0;
int cnt = 0;
while(its.hasNext()){
sum += its.next().get();
cnt++;
}
context.write(key, new IntWritable(sum/cnt));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = new Job(conf, "AvgScore");
job.setJarByClass(AvgScore.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path("hdfs://h0:9000/user/tallqi/in/inputAvgScore"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://h0:9000/user/tallqi/in/outputAvgScore"));
System.exit(job.waitForCompletion(true)?0:1);
}
}