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
- Binary image
http://www.uio.no/studier/emner/matnat/ifi/INF3300/h06/undervisningsmateriale/week-36-2006-solution. ...
- Makefile 入门与基本语法 分类: C/C++ ubuntu 2015-05-18 11:16 466人阅读 评论(0) 收藏
在我看来,学会写简单的Makefile,阅读较复杂的makefile,是每一个Linux程序员都必须拥有的基本素质.Makefile可以自动识别哪些源文件被更改过,需要重新编译,那些不需要.从而节省大 ...
- Linux下jvm、tomcat、mysql、log4j优化配置笔记[转]
小菜一直对操作系统心存畏惧,以前也很少接触,这次创业购买了Linux云主机,由于木有人帮忙,只能自己动手优化服务器了.... 小菜的云主机配置大致为:centeos6(32位),4核心cpu,4G内存 ...
- [Angular 2] Component relative paths
Oingial aritial --> Link Take away: import { Component, OnInit } from '@angular/core'; @Component ...
- C# DataTable怎么合计字段
DataTable dt = new DataTable(); var age=dt.Compute("avg(age)",""); var height =d ...
- oracle学习----统计信息
1.收集统计信息的方式 for all columns size skewonly BEGIN DBMS_STATS.GATHER_TABLE_STATS(ownname => ...
- View事件分发机制
所谓的事件分发,其实就是对MotionEvent事件的分发过程,即当一个MotionEvent产生后,系统需要把这个事件传递给一个具体的View,而这个传递的过程就是分发过程. 点击事件的分发由3个方 ...
- JDK自带方法实现消息摘要运算
啊,有点小注释,懒得介绍了,就贴个代码吧,大意理解就可以了. package jdbc.pro.lin; import java.security.InvalidKeyException; impor ...
- (转)javascript中的this
JavaScript中的this总是让人迷惑,应该是js众所周知的坑之一. 个人也觉得js中的this不是一个好的设计,由于this晚绑定的特性,它可以是全局对象,当前对象,或者…有人甚至因为坑大而不 ...
- .NET设计模式(9):桥接模式(Bridge Pattern)
.NET设计模式(9):桥接模式(Bridge Pattern) 桥接模式(Bridge Pattern) --.NET设计模式系列之九 年月 实现代码如下:..所谓抽象和实现沿着各自维度的变 ...