package com.cakin.hadoop.mr;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.WritableComparable;
public class UserWritable implements WritableComparable<UserWritable> {
private Integer id;
private Integer income;
private Integer expenses;
private Integer sum;
public void write(DataOutput out) throws IOException {
// TODO Auto-generated method stub
out.writeInt(id);
out.writeInt(income);
out.writeInt(expenses);
out.writeInt(sum);
}
public void readFields(DataInput in) throws IOException {
// TODO Auto-generated method stub
this.id=in.readInt();
this.income=in.readInt();
this.expenses=in.readInt();
this.sum=in.readInt();
}
public Integer getId() {
return id;
}
public UserWritable setId(Integer id) {
this.id = id;
return this;
}
public Integer getIncome() {
return income;
}
public UserWritable setIncome(Integer income) {
this.income = income;
return this;
}
public Integer getExpenses() {
return expenses;
}
public UserWritable setExpenses(Integer expenses) {
this.expenses = expenses;
return this;
}
public Integer getSum() {
return sum;
}
public UserWritable setSum(Integer sum) {
this.sum = sum;
return this;
}
public int compareTo(UserWritable o) {
// TODO Auto-generated method stub
return this.id>o.getId()?1:-1;
}
@Override
public String toString() {
return id + "\t"+income+"\t"+expenses+"\t"+sum;
}
}
package com.cakin.hadoop.mr;
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.LongWritable;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Reducer;
/*
* 测试数据
* 用户id 收入 支出
* 1 1000 0
* 2 500 300
* 1 2000 1000
* 2 500 200
*
* 需求:
* 用户id 总收入 总支出 总的余额
* 1 3000 1000 2000
* 2 1000 500 500
* */
public class CountMapReduce {
public static class CountMapper extends Mapper<LongWritable,Text,IntWritable,UserWritable>
{
private UserWritable userWritable =new UserWritable();
private IntWritable id =new IntWritable();
@Override
protected void map(LongWritable key,Text value,
Mapper<LongWritable,Text,IntWritable,UserWritable>.Context context) throws IOException, InterruptedException{
String line = value.toString();
String[] words = line.split("\t");
if(words.length ==3)
{
userWritable.setId(Integer.parseInt(words[0]))
.setIncome(Integer.parseInt(words[1]))
.setExpenses(Integer.parseInt(words[2]))
.setSum(Integer.parseInt(words[1])-Integer.parseInt(words[2]));
id.set(Integer.parseInt(words[0]));
}
context.write(id, userWritable);
}
}
public static class CountReducer extends Reducer<IntWritable,UserWritable,UserWritable,NullWritable>
{
/*
* 输入数据
* <1,{[1,1000,0,1000],[1,2000,1000,1000]}>
* <2,[2,500,300,200],[2,500,200,300]>
*
* */
private UserWritable userWritable = new UserWritable();
private NullWritable n = NullWritable.get();
protected void reduce(IntWritable key,Iterable<UserWritable> values,
Reducer<IntWritable,UserWritable,UserWritable,NullWritable>.Context context) throws IOException, InterruptedException{
Integer income=0;
Integer expenses = 0;
Integer sum =0;
for(UserWritable u:values)
{
income += u.getIncome();
expenses+=u.getExpenses();
}
sum = income - expenses;
userWritable.setId(key.get())
.setIncome(income)
.setExpenses(expenses)
.setSum(sum);
context.write(userWritable, n);
}
}
public static void main(String[] args) throws IllegalArgumentException, IOException, ClassNotFoundException, InterruptedException {
Configuration conf=new Configuration();
/*
* 集群中节点都有配置文件
conf.set("mapreduce.framework.name.", "yarn");
conf.set("yarn.resourcemanager.hostname", "mini1");
*/
Job job=Job.getInstance(conf,"countMR");
//jar包在哪里,现在在客户端,传递参数
//任意运行,类加载器知道这个类的路径,就可以知道jar包所在的本地路径
job.setJarByClass(CountMapReduce.class);
//指定本业务job要使用的mapper/Reducer业务类
job.setMapperClass(CountMapper.class);
job.setReducerClass(CountReducer.class);
//指定mapper输出数据的kv类型
job.setMapOutputKeyClass(IntWritable.class);
job.setMapOutputValueClass(UserWritable.class);
//指定最终输出的数据kv类型
job.setOutputKeyClass(UserWritable.class);
job.setOutputKeyClass(NullWritable.class);
//指定job的输入原始文件所在目录
FileInputFormat.setInputPaths(job, new Path(args[0]));
//指定job的输出结果所在目录
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//将job中配置的相关参数及job所用的java类在的jar包,提交给yarn去运行
//提交之后,此时客户端代码就执行完毕,退出
//job.submit();
//等集群返回结果在退出
boolean res=job.waitForCompletion(true);
System.exit(res?0:1);
//类似于shell中的$?
}
}
[root@centos hadoop-2.7.4]# bin/hdfs dfs -cat /input/data
1 1000 0
2 500 300
1 2000 1000
2 500 200
[root@centos hadoop-2.7.4]# bin/yarn jar /root/jar/mapreduce.jar /input/data /output3
17/12/20 21:24:45 INFO client.RMProxy: Connecting to ResourceManager at /0.0.0.0:8032
17/12/20 21:24:46 WARN mapreduce.JobResourceUploader: Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
17/12/20 21:24:47 INFO input.FileInputFormat: Total input paths to process : 1
17/12/20 21:24:47 INFO mapreduce.JobSubmitter: number of splits:1
17/12/20 21:24:47 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1513775596077_0001
17/12/20 21:24:49 INFO impl.YarnClientImpl: Submitted application application_1513775596077_0001
17/12/20 21:24:49 INFO mapreduce.Job: The url to track the job: http://centos:8088/proxy/application_1513775596077_0001/
17/12/20 21:24:49 INFO mapreduce.Job: Running job: job_1513775596077_0001
17/12/20 21:25:13 INFO mapreduce.Job: Job job_1513775596077_0001 running in uber mode : false
17/12/20 21:25:13 INFO mapreduce.Job: map 0% reduce 0%
17/12/20 21:25:38 INFO mapreduce.Job: map 100% reduce 0%
17/12/20 21:25:54 INFO mapreduce.Job: map 100% reduce 100%
17/12/20 21:25:56 INFO mapreduce.Job: Job job_1513775596077_0001 completed successfully
17/12/20 21:25:57 INFO mapreduce.Job: Counters: 49
File System Counters
FILE: Number of bytes read=94
FILE: Number of bytes written=241391
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=135
HDFS: Number of bytes written=32
HDFS: Number of read operations=6
HDFS: Number of large read operations=0
HDFS: Number of write operations=2
Job Counters
Launched map tasks=1
Launched reduce tasks=1
Data-local map tasks=1
Total time spent by all maps in occupied slots (ms)=23672
Total time spent by all reduces in occupied slots (ms)=11815
Total time spent by all map tasks (ms)=23672
Total time spent by all reduce tasks (ms)=11815
Total vcore-milliseconds taken by all map tasks=23672
Total vcore-milliseconds taken by all reduce tasks=11815
Total megabyte-milliseconds taken by all map tasks=24240128
Total megabyte-milliseconds taken by all reduce tasks=12098560
Map-Reduce Framework
Map input records=4
Map output records=4
Map output bytes=80
Map output materialized bytes=94
Input split bytes=94
Combine input records=0
Combine output records=0
Reduce input groups=2
Reduce shuffle bytes=94
Reduce input records=4
Reduce output records=2
Spilled Records=8
Shuffled Maps =1
Failed Shuffles=0
Merged Map outputs=1
GC time elapsed (ms)=157
CPU time spent (ms)=1090
Physical memory (bytes) snapshot=275660800
Virtual memory (bytes) snapshot=4160692224
Total committed heap usage (bytes)=139264000
Shuffle Errors
BAD_ID=0
CONNECTION=0
IO_ERROR=0
WRONG_LENGTH=0
WRONG_MAP=0
WRONG_REDUCE=0
File Input Format Counters
Bytes Read=41
File Output Format Counters
Bytes Written=32
[root@centos hadoop-2.7.4]# bin/hdfs dfs -cat /output3/part-r-00000
1 3000 1000 2000
2 1000 500 500
文章浏览阅读331次。第一部分:准备工作1 安装虚拟机2 安装centos73 安装JDK以上三步是准备工作,至此已经完成一台已安装JDK的主机第二部分:准备3台虚拟机以下所有工作最好都在root权限下操作1 克隆上面已经有一台虚拟机了,现在对master进行克隆,克隆出另外2台子机;1.1 进行克隆21.2 下一步1.3 下一步1.4 下一步1.5 根据子机需要,命名和安装路径1.6 ..._创建一个hadoop项目
文章浏览阅读1.7k次。心脏滴血漏洞HeartBleed CVE-2014-0160 是由heartbeat功能引入的,本文从深入码层面的分析该漏洞产生的原因_heartbleed代码分析
文章浏览阅读1.4k次。前言ofd是国家文档标准,其对标的文档格式是pdf。ofd文档是容器格式文件,ofd其实就是压缩包。将ofd文件后缀改为.zip,解压后可看到文件包含的内容。ofd文件分析工具下载:点我下载。ofd文件解压后,可以看到如下内容: 对于xml文件,可以用文本工具查看。但是对于印章文件(Seal.esl)、签名文件(SignedValue.dat)就无法查看其内容了。本人开发一款ofd内容查看器,..._signedvalue.dat
文章浏览阅读1.8w次,点赞29次,收藏313次。整体系统设计本设计主要是对ADC和DAC的使用,主要实现功能流程为:首先通过串口向FPGA发送控制信号,控制DAC芯片tlv5618进行DA装换,转换的数据存在ROM中,转换开始时读取ROM中数据进行读取转换。其次用按键控制adc128s052进行模数转换100次,模数转换数据存储到FIFO中,再从FIFO中读取数据通过串口输出显示在pc上。其整体系统框图如下:图1:FPGA数据采集系统框图从图中可以看出,该系统主要包括9个模块:串口接收模块、按键消抖模块、按键控制模块、ROM模块、D.._基于fpga的信息采集
文章浏览阅读2.5w次。1.背景错误信息:-- [http-nio-9904-exec-5] o.s.c.n.z.filters.post.SendErrorFilter : Error during filteringcom.netflix.zuul.exception.ZuulException: Forwarding error at org.springframework.cloud..._com.netflix.zuul.exception.zuulexception
文章浏览阅读358次。1.介绍图的相关概念 图是由顶点的有穷非空集和一个描述顶点之间关系-边(或者弧)的集合组成。通常,图中的数据元素被称为顶点,顶点间的关系用边表示,图通常用字母G表示,图的顶点通常用字母V表示,所以图可以定义为: G=(V,E)其中,V(G)是图中顶点的有穷非空集合,E(G)是V(G)中顶点的边的有穷集合1.1 无向图:图中任意两个顶点构成的边是没有方向的1.2 有向图:图中..._给定一个邻接矩阵未必能够造出一个图
文章浏览阅读321次。(十二)、WDS服务器安装通过前面的测试我们会发现,每次安装的时候需要加域光盘映像,这是一个比较麻烦的事情,试想一个上万个的公司,你天天带着一个光盘与光驱去给别人装系统,这将是一个多么痛苦的事情啊,有什么方法可以解决这个问题了?答案是肯定的,下面我们就来简单说一下。WDS服务器,它是Windows自带的一个免费的基于系统本身角色的一个功能,它主要提供一种简单、安全的通过网络快速、远程将Window..._doc server2012上通过wds+mdt无人值守部署win11系统.doc
文章浏览阅读219次。python–xlrd/xlwt/xlutilsxlrd只能读取,不能改,支持 xlsx和xls 格式xlwt只能改,不能读xlwt只能保存为.xls格式xlutils能将xlrd.Book转为xlwt.Workbook,从而得以在现有xls的基础上修改数据,并创建一个新的xls,实现修改xlrd打开文件import xlrdexcel=xlrd.open_workbook('E:/test.xlsx') 返回值为xlrd.book.Book对象,不能修改获取sheett_xlutils模块可以读xlsx吗
文章浏览阅读8.2w次,点赞267次,收藏656次。运行Selenium出现'WebDriver' object has no attribute 'find_element_by_id'或AttributeError: 'WebDriver' object has no attribute 'find_element_by_xpath'等定位元素代码错误,是因为selenium更新到了新的版本,以前的一些语法经过改动。..............._unresolved attribute reference 'find_element_by_id' for class 'webdriver
文章浏览阅读198次。一:模态窗口//父页面JSwindow.showModalDialog(ifrmehref, window, 'dialogWidth:550px;dialogHeight:150px;help:no;resizable:no;status:no');//子页面获取父页面DOM对象//window.showModalDialog的DOM对象var v=parentWin..._jquery获取父window下的dom对象
文章浏览阅读1.7w次,点赞15次,收藏129次。算法(algorithm)是解决一系列问题的清晰指令,也就是,能对一定规范的输入,在有限的时间内获得所要求的输出。 简单来说,算法就是解决一个问题的具体方法和步骤。算法是程序的灵 魂。二、算法的特征1.可行性 算法中执行的任何计算步骤都可以分解为基本可执行的操作步,即每个计算步都可以在有限时间里完成(也称之为有效性) 算法的每一步都要有确切的意义,不能有二义性。例如“增加x的值”,并没有说增加多少,计算机就无法执行明确的运算。 _算法
文章浏览阅读1.5k次,点赞18次,收藏26次。网络安全的标准和规范是网络安全领域的重要组成部分。它们为网络安全提供了技术依据,规定了网络安全的技术要求和操作方式,帮助我们构建安全的网络环境。下面,我们将详细介绍一些主要的网络安全标准和规范,以及它们在实际操作中的应用。_网络安全标准规范