? 另外一个hadoop的入门demo，求平均数。是对wordcount这个demo的一个小小的修改。输入一堆成绩单（人名，成绩），然后求每个人成绩平均数，比如： //? subject1.txt ? a 90 ? b 80 ? c 70 ?// subject2.txt ? a 100 ? b 90 ? c 80 ? 求a,b,c这三个人的平均
? 另外一个hadoop的入门demo，求平均数。是对wordcount这个demo的一个小小的修改。输入一堆成绩单（人名，成绩），然后求每个人成绩平均数，比如：
//? subject1.txt
? a 90
? b 80
? c 70
?// subject2.txt
? a 100
? b 90
? c 80
? 求a,b,c这三个人的平均分。解决思路很简单，在map阶段key是名字，value是成绩，直接output。reduce阶段得到了map输出的key名字，values是该名字对应的一系列的成绩，那么对其求平均数即可。
? 这里我们实现了两个版本的代码，分别用textinputformat和 keyvaluetextinputformat来作为输入格式。
? textinputformat版本：
?
import java.util.*;import java.io.*;import org.apache.hadoop.conf.configuration;import org.apache.hadoop.fs.path;import org.apache.hadoop.io.text;import org.apache.hadoop.io.intwritable;import org.apache.hadoop.mapreduce.mapper;import org.apache.hadoop.mapreduce.reducer;import org.apache.hadoop.mapreduce.job;import org.apache.hadoop.mapreduce.lib.input.fileinputformat;import org.apache.hadoop.mapreduce.lib.output.fileoutputformat;public class avescore { public static class avemapper extends mapper { @override public void map(object key, text value, context context) throws ioexception, interruptedexception { string line = value.tostring(); string[] strs = line.split( ); string name = strs[0]; int score = integer.parseint(strs[1]); context.write(new text(name), new intwritable(score)); } } public static class avereducer extends reducer { @override public void reduce(text key, iterable values, context context) throws ioexception, interruptedexception { int sum = 0; int count = 0; for(intwritable val : values) { sum += val.get(); count++; } int avescore = sum / count; context.write(key, new intwritable(avescore)); } } public static void main(string[] args) throws exception { configuration conf = new configuration(); job job = new job(conf,averagescore); job.setjarbyclass(avescore.class); job.setmapperclass(avemapper.class); job.setreducerclass(avereducer.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); }}
keyvaluetextinputformat版本；
import java.util.*;import java.io.*;import org.apache.hadoop.conf.configuration;import org.apache.hadoop.fs.path;import org.apache.hadoop.io.text;import org.apache.hadoop.io.intwritable;import org.apache.hadoop.mapreduce.mapper;import org.apache.hadoop.mapreduce.reducer;import org.apache.hadoop.mapreduce.job;import org.apache.hadoop.mapreduce.lib.input.fileinputformat;import org.apache.hadoop.mapreduce.lib.output.fileoutputformat;import org.apache.hadoop.mapreduce.lib.input.keyvaluetextinputformat;import org.apache.hadoop.mapreduce.lib.output.textoutputformat;public class avescore_keyvalue { public static class avemapper extends mapper { @override public void map(text key, text value, context context) throws ioexception, interruptedexception { int score = integer.parseint(value.tostring()); context.write(key, new intwritable(score) ); } } public static class avereducer extends reducer { @override public void reduce(text key, iterable values, context context) throws ioexception, interruptedexception { int sum = 0; int count = 0; for(intwritable val : values) { sum += val.get(); count++; } int avescore = sum / count; context.write(key, new intwritable(avescore)); } } public static void main(string[] args) throws exception { configuration conf = new configuration(); conf.set(mapreduce.input.keyvaluelinerecordreader.key.value.separator, ); job job = new job(conf,averagescore); job.setjarbyclass(avescore_keyvalue.class); job.setmapperclass(avemapper.class); job.setreducerclass(avereducer.class); job.setoutputkeyclass(text.class); job.setoutputvalueclass(intwritable.class); job.setinputformatclass(keyvaluetextinputformat.class); job.setoutputformatclass(textoutputformat.class) ; fileinputformat.addinputpath(job, new path(args[0])); fileoutputformat.setoutputpath(job, new path(args[1])); system.exit( job.waitforcompletion(true) ? 0 : 1); }}
输出结果为：
? a 95
? b 85
? c 75
?
作者：qiul12345 发表于2013-8-23 21:51:03 原文链接
阅读：113 评论：0 查看评论
原文地址：hadoop helloword examples- 求平均数, 感谢原作者分享。