Hadoop 学习笔记 (十) MapReduce实现排序 全局变量
一些疑问:
1 全排序的话,最后的应该sortJob.setNumReduceTasks(1);
2 如果多个reduce task都去修改 一个静态的 IntWritable ,IntWritable会乱序吧~
输入数据:
file1
2
32
654
32
15
756
65223
file2
5956
22
650
92
file3
26
54
6 import java.io.IOException; import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
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; public class MySort { public static class IntSortMapper extends Mapper<Object, Text, IntWritable, NullWritable>{ private IntWritable val = new IntWritable(); public void map(Object key, Text value, Context context) throws IOException, InterruptedException{
String line = value.toString().trim();
val.set(Integer.parseInt(line));
context.write(val, NullWritable.get());
}
} public static class IntSortReducer extends Reducer<IntWritable, NullWritable, IntWritable,IntWritable>{
private IntWritable k = new IntWritable();
public void reduce(IntWritable key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException{
k.set();
for (NullWritable value : values) {
context.write(k, key);
}
}
} public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
String dir_in = "hdfs://localhost:9000/in_sort";
String dir_out = "hdfs://localhost:9000/out_sort"; Path in = new Path(dir_in);
Path out = new Path(dir_out); Configuration conf = new Configuration();
Job sortJob = new Job(conf, "my_sort"); sortJob.setJarByClass(MySort.class); sortJob.setInputFormatClass(TextInputFormat.class);
sortJob.setMapperClass(IntSortMapper.class);
//sortJob.setCombinerClass(SortReducer.class);
//countJob.setPartitionerClass(HashPartitioner.class);
sortJob.setMapOutputKeyClass(IntWritable.class);
sortJob.setMapOutputValueClass(NullWritable.class); FileInputFormat.addInputPath(sortJob, in); sortJob.setReducerClass(IntSortReducer.class);
sortJob.setNumReduceTasks();
sortJob.setOutputKeyClass(IntWritable.class);
sortJob.setOutputValueClass(IntWritable.class);
//countJob.setOutputFormatClass(SequenceFileOutputFormat.class); FileOutputFormat.setOutputPath(sortJob, out); sortJob.waitForCompletion(true); } }
结果:
修改reduce函数(不是用Iterable)
public static class IntSortReducer extends Reducer<IntWritable, NullWritable, IntWritable,IntWritable>{
private IntWritable k = new IntWritable();
public void reduce(IntWritable key, NullWritable value, Context context) throws IOException, InterruptedException{
k.set();
//for (NullWritable value : values) {
context.write(k, key);
//}
}
}
结果:(不是很理解,为啥去掉iterable后就只输出一个value key哪去了呢)
import java.io.IOException; import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
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; public class MySort { public static class IntSortMapper extends Mapper<Object, Text, IntWritable, NullWritable>{ private IntWritable val = new IntWritable(); public void map(Object key, Text value, Context context) throws IOException, InterruptedException{
String line = value.toString().trim();
val.set(Integer.parseInt(line));
context.write(val, NullWritable.get());
}
} public static class IntSortReducer extends Reducer<IntWritable, NullWritable, IntWritable,IntWritable>{
private static IntWritable num = new IntWritable();
public void reduce(IntWritable key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException{ for (NullWritable value : values) {
context.write(num, key);
num = new IntWritable(num.get() + );
}
}
} public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
String dir_in = "hdfs://localhost:9000/in_sort";
String dir_out = "hdfs://localhost:9000/out_sort"; Path in = new Path(dir_in);
Path out = new Path(dir_out); Configuration conf = new Configuration();
Job sortJob = new Job(conf, "my_sort"); sortJob.setJarByClass(MySort.class); sortJob.setInputFormatClass(TextInputFormat.class);
sortJob.setMapperClass(IntSortMapper.class);
//sortJob.setCombinerClass(SortReducer.class);
//countJob.setPartitionerClass(HashPartitioner.class);
sortJob.setMapOutputKeyClass(IntWritable.class);
sortJob.setMapOutputValueClass(NullWritable.class); FileInputFormat.addInputPath(sortJob, in); sortJob.setReducerClass(IntSortReducer.class);
sortJob.setNumReduceTasks();
sortJob.setOutputKeyClass(IntWritable.class);
sortJob.setOutputValueClass(IntWritable.class);
//countJob.setOutputFormatClass(SequenceFileOutputFormat.class); FileOutputFormat.setOutputPath(sortJob, out); sortJob.waitForCompletion(true); } }
1 2
2 6
3 15
4 22
5 26
6 32
7 32
8 54
9 92
10 650
11 654
12 756
13 5956
14 65223
Hadoop 学习笔记 (十) MapReduce实现排序 全局变量的更多相关文章
- Hadoop学习笔记—11.MapReduce中的排序和分组
一.写在之前的 1.1 回顾Map阶段四大步骤 首先,我们回顾一下在MapReduce中,排序和分组在哪里被执行: 从上图中可以清楚地看出,在Step1.4也就是第四步中,需要对不同分区中的数据进行排 ...
- Hadoop学习笔记: MapReduce二次排序
本文给出一个实现MapReduce二次排序的例子 package SortTest; import java.io.DataInput; import java.io.DataOutput; impo ...
- hadoop 学习笔记:mapreduce框架详解
开始聊mapreduce,mapreduce是hadoop的计算框架,我学hadoop是从hive开始入手,再到hdfs,当我学习hdfs时候,就感觉到hdfs和mapreduce关系的紧密.这个可能 ...
- Hadoop学习笔记:MapReduce框架详解
开始聊mapreduce,mapreduce是hadoop的计算框架,我学hadoop是从hive开始入手,再到hdfs,当我学习hdfs时候,就感觉到hdfs和mapreduce关系的紧密.这个可能 ...
- 【Big Data - Hadoop - MapReduce】hadoop 学习笔记:MapReduce框架详解
开始聊MapReduce,MapReduce是Hadoop的计算框架,我学Hadoop是从Hive开始入手,再到hdfs,当我学习hdfs时候,就感觉到hdfs和mapreduce关系的紧密.这个可能 ...
- hadoop 学习笔记:mapreduce框架详解(转)
原文:http://www.cnblogs.com/sharpxiajun/p/3151395.html(有删减) Mapreduce运行机制 下面我贴出几张图,这些图都是我在百度图片里找到的比较好的 ...
- Hadoop学习笔记—12.MapReduce中的常见算法
一.MapReduce中有哪些常见算法 (1)经典之王:单词计数 这个是MapReduce的经典案例,经典的不能再经典了! (2)数据去重 "数据去重"主要是为了掌握和利用并行化思 ...
- Hadoop学习笔记: MapReduce Java编程简介
概述 本文主要基于Hadoop 1.0.0后推出的新Java API为例介绍MapReduce的Java编程模型.新旧API主要区别在于新API(org.apache.hadoop.mapreduce ...
- hadoop 学习笔记 (十) mapreduce2.0
MapReduce的特色---不擅长的方面 >实时计算 像mysql一样,在毫秒级或者秒级内返回结果 >流式计算 Mapreduce的输入数据时静态的,不能动态变化 MapReduce自身 ...
- 三、Hadoop学习笔记————从MapReduce到Yarn
Yarn减轻了JobTracker的负担,对其进行了解耦
随机推荐
- Velocity源码分析
velocity模板渲染的步骤: 1) 首先初始化启动Velocity引擎,可以通过Velocity.init()或者新建VelocityEngine类,并调用其中的init()方法: 2) 创建一个 ...
- oracle3
查看表结构 DESC emp; 查询所有列 SELECT * FROM dept; 切忌动不动就用select * set timing on; 打开显示操作时间的开关,在下面显示查询时间. CREA ...
- oralce11 过程
PL/SQL 块的结构和实例 pl/sql(procedural language(过程化语言)/sql)是oracle在标准的sql语言上的扩展.pl/sql不仅允许嵌入sql语言,还可以定义变量和 ...
- jQuery Validate 插件
>>>>>>>>>>>>>>>>>>>>>>>>> ...
- thinkphp3.2.x版本中图片上传缩略图的解决方案
调用方式很简单 get_sc($cover_id,[$width=180,$height=auto,$cut]) @param $cover_id 图片ID___ @param $width 宽度__ ...
- oracle session 相关优化
导读: 同学们是不是都用遇到过这种情况,一个业务系统开发期业务并发量只是估算一个值,而系统上线后这个并发量可能会出现溢出或是不够的 情况.在这种情况下我们DBA怎么给出合理的性能优化建议呢?本文就 ...
- WPF中TreeView数据结构解析
XAML.CS代码: using System; using System.Collections.Generic; using System.Linq; using System.Text; usi ...
- C++专题 - Qt是什么
Qt是一个1991年由奇趣科技开发的跨平台C++图形用户界面应用程序开发框架.它既可以开发GUI程式,也可用于开发非GUI程式,比如控制台工具和服务器.Qt是面向对象的框架,使用特殊的代码生成扩展(称 ...
- UVA 11825 Hackers’ Crackdown(集合动态规划 子集枚举)
Hackers’ Crackdown Miracle Corporations has a number of system services running in a distributed com ...
- pc110301QWERTYU
水题一道,SOLVED只是次数的问题.map一下,就是很easy啦. #include<iostream> #include<cstdio> #include<cstri ...