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
- MVC Controller return 格式
所看到的Action都是return View();我们可以看作这个返回值用于解析一个aspx文件.而它的返回类型是ActionResult如 public ActionResult Index() ...
- 【HDU 2014 Multi-University Training Contest 1 1002】/【HDU 4862】Jump
多校训练就这么华丽丽的到了 ,于是乎各种华丽丽的被虐也開始了. 这是多校的1002; 最小费用最大流. 题目大意: 有n*m个方格,每一个方格都一个的十进制一位的数.你能够操作K次. 对于每一次操作, ...
- iBatis自动生成的主键 (Oracle,MS Sql Server,MySQL)【转】
iBatis的sqlMap配置文件的selectKey元素有个type属性,可以指定pre或者post表示前生成(pre)还是后生成(post). Oracle设置 <!-- Oracle SE ...
- BZOJ 2754([SCOI2012]喵喵叫的星球-统计序列的后缀阵列中子序列出现次数)
2754: [SCOI2012]喵喵叫的星球 Time Limit: 20 Sec Memory Limit: 128 MB Submit: 805 Solved: 380 [id=2754&qu ...
- Android保存设置的PreferenceActivity
界面XML文件:preference_setting.xml <?xml version="1.0" encoding="UTF-8"?> < ...
- GCC扩展(转--对看kernel代码有帮助
http://my.oschina.net/senmole/blog?catalog=153878 Linux Kernel的代码,上次就发现一个结构体的定义形式看不懂,后来才知道它用的不是标准的AN ...
- allocator例子
13.39 编写自己的StrVec,包括自己版本的reserve.capacity和resize. 13.40 为StrVec添加一个构造函数,它接受一个initializer_list<str ...
- myeclipse自动生成可持久化类的映射文件的方法
1.打开DB Browser,新建一个数据库的连接,找到想要持久化操作的数据库表的图标,右键选择hibernate reverse engineering 2.之后出现如下所示: java src f ...
- Flume NG中的Netcat Source
NetCat是一个非常简单的Unix工具,可以读.写TCP或UDP网络连接(network connection)中数据 在Flume中的netcat支持Flume与NetCat整合,flume可以使 ...
- Linux下载jdk ,Linux如何下载jdk
Linux下载jdk Linux如何下载jdk >>>>>>>>>>>>>>>>>>> ...