直接使用hadoop中的wordcount中的jar包进行使用

JAVA实现WordCount

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.output.FileOutputFormat; public class Demo1 { // map类
// 第一对kv,是决定数据输入的格式
// 第二队kv 是决定数据输出的格式
public static class map extends Mapper<LongWritable,Text,Text,LongWritable>{
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//一行一行的读,先LongWrtable再value是因为第一个LongWritable是偏移量
String line=value.toString();
//需要读出内容和行数1,所以要对结果进行类型转换
context.write(new Text(line),new LongWritable(1));
}
} // reduce类
// 用来接收map端输出的数据
public static class reduce extends Reducer<Text,LongWritable,Text,LongWritable>{
/**
* reduce 聚合程序 每一个k都会调用一次
* 默认是一个节点
* key:每一个单词
* values:map端 当前k所对应的所有的v
*/
@Override
protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
long sum=0; //进行整合后values值变成(key,1,1,1,1),values需要遍历
for (LongWritable value : values) {
//这里同理需要将value转换类型,LongWritable是一个接口可以用get方法转为long型整数
sum+=value.get();
}
//同理long类型sum转换为LongWritable类型
context.write(key,new LongWritable(sum));
}
} //mapreduce的程序入口
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
//创造一个job任务
Job job = Job.getInstance();
//命名job名称
job.setJobName("第一次通过自己的jar包连接"); //指定当前main坐在类端口
job.setJarByClass(Demo1.class); //指定map类端口
job.setMapperClass(map.class);
//指定map输出的kv类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class); //指定reduce类端口
job.setReducerClass(reduce.class);
//指定reduce输出的kv类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class); //指定输入路径 hdfs路径
Path in = new Path("/wordcount");
FileInputFormat.addInputPath(job,in); //指定输出路径
Path out = new Path("/output1");
//如果路径存在,进行删除操作
FileSystem fs = FileSystem.get(new Configuration());
if (fs.exists(out)){
fs.delete(out,true); //true可以删除多级目录
}
FileOutputFormat.setOutputPath(job,out); //启动任务
job.waitForCompletion(true); /**
* 提交任务
* 1.通过maven中package将项目打包上传服务器然后执行
* 2.执行任务 hadoop jar hadoop-mapreduce-examples-2.7.6.jar com.shujia.hadoop.Demo01WordCount /word /output
*
*/ System.out.println("wordcount实现成功"); }
}

实现玩代码后进行打包,打完后的包xftp上传到

/usr/local/soft/hadoop-2.7.6/share/hadoop/mapreduce

开始正式对包进行解析(jar)

路径在idea中查看,是mian函数的路径

对数据进行逗号分隔代码

只需对map阶段进行操作即可

public static class map extends Mapper<LongWritable,Text,Text,LongWritable>{
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String s = value.toString();
String[] split = s.split(",");
for (String s1 : split) {
context.write(new Text(s1),new LongWritable(1));
} }
}

对students中clazz中年龄的总和

public static class map extends Mapper<LongWritable,Text,Text,LongWritable>{
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String s = value.toString();
String[] split = s.split(","); String s1 = split[2];
LongWritable age = new LongWritable(Integer.valueOf(s1));
String s2 = split[4];
Text clazz = new Text(s2);
context.write(clazz, age);
}
}

对students.txt中进行男女性别人数的统计

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.output.FileOutputFormat; import java.io.IOException; public class Demo4 {
public static class map extends Mapper<LongWritable,Text,Text,LongWritable>{
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String s = value.toString().split(",")[3];
context.write(new Text(s),new LongWritable(1));
}
} public static class reduce extends Reducer<Text,LongWritable,Text,LongWritable>{
@Override
protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
long sum=0l;
for (LongWritable value : values) {
sum+=value.get();
}
context.write(key,new LongWritable(sum));
}
} public static void main(String[] args) throws Exception{ Job job = Job.getInstance();
job.setJobName("男女性别人数的统计");
job.setJarByClass(Demo4.class); job.setMapperClass(map.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class); job.setReducerClass(reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class); Path in = new Path("/data/students.txt");
FileInputFormat.addInputPath(job,in); Path out = new Path("/output4");
FileSystem fs = FileSystem.get(new Configuration());
if (fs.exists(out)){
fs.delete(out,true);
}
FileOutputFormat.setOutputPath(job,out); job.waitForCompletion(true);
System.out.println("第四个了"); }
}

Students.txt中筛选出男生的所有信息,无reduce阶段,因为无需计算

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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 java.io.IOException; public class Demo5 { public static class map extends Mapper<LongWritable,Text,Text,NullWritable> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String s = value.toString().split(",")[3];
if (s.equals("男")){
context.write(value,NullWritable.get());
}
}
} public static void main(String[] args) throws Exception {
Job job = Job.getInstance();
job.setJobName("students中只筛选出男生,无reduce操作");
job.setJarByClass(Demo5.class); job.setMapperClass(map.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(NullWritable.class); Path in = new Path("/data/students.txt");
FileInputFormat.addInputPath(job,in); Path out = new Path("/output5");
FileSystem fs = FileSystem.get(new Configuration());
if (fs.exists(out)){
fs.delete(out,true);
}
FileOutputFormat.setOutputPath(job,out); job.waitForCompletion(true); }
}

对两张表进行拼接操作:

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
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.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import java.io.IOException;
import java.util.ArrayList; public class Demo6 { public static class map extends Mapper<LongWritable,Text,Text,Text>{
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//context获取切片,上面是hdfs就从hdfs,下面是reduce
//获取路径InputSplit
InputSplit is = context.getInputSplit(); //InputSplit获取切片,然后从hdfs中获取文件名或者路径
FileSplit fileSplit= (FileSplit) is; //InputSplit是抽象类,不能使用自己的方法,所以用FileSplit来实现
String s = fileSplit.getPath().toString(); //获取切片的文件路径,是path不是name if (s.contains("students")){
//打上标签
String s1 = "*"+value.toString();
String id = value.toString().split(",")[0];
context.write(new Text(id),new Text(s1));
}else {
String s1 = "#"+value.toString();
String id = value.toString().split(",")[0];
context.write(new Text(id),new Text(s1));
} }
} public static class reduce extends Reducer<Text,Text,Text,NullWritable> {
@Override
protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
//此时进行了一个reducetask任务,key是学号,而values是相同key所对应的所有的数据,包括学生信息和分数信息,
//此时里面有七个,六个是score信息,对其进行集合存储 String st="";
ArrayList<String> sc = new ArrayList<String>();
//分数弄成一个集合是因为一个学生对应六个分数,可以通过对集合的遍历将六个成绩逐一算到学生中去 for (Text value : values) {
String s = value.toString();
if (s.startsWith("*")){
st = s.substring(1); //此时注意s是包含标签的,记得索引0是标签
}else {
sc.add(s.substring(1));
}
} //两张表进行拼接
for (String s : sc) {
String s1 = s.split(",")[2];
String end=st+","+s1;
context.write(new Text(end),NullWritable.get());
}
}
} public static void main(String[] args) throws Exception{
Job job = Job.getInstance();
job.setJobName("两个文件进行拼接");
job.setJarByClass(Demo6.class); job.setMapperClass(map.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class); job.setReducerClass(reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class); Path in = new Path("/datajava");
FileInputFormat.addInputPath(job,in); Path out = new Path("/output6");
FileOutputFormat.setOutputPath(job,out); job.waitForCompletion(true);
System.out.println("可以了第六次"); }
}

combine对数据进行性别进行计数

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.output.FileOutputFormat; import java.io.IOException; public class Demo8 { public static class map extends Mapper<LongWritable,Text,Text,LongWritable>{
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String sex = value.toString().split(",")[3];
context.write(new Text(sex),new LongWritable(1)); }
} public static class combine extends Reducer<Text,LongWritable,Text,LongWritable>{
@Override
protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
long sum=0l;
for (LongWritable value : values) {
sum+=value.get();
}
context.write(key,new LongWritable(sum));
}
} public static class reduce extends Reducer<Text,LongWritable,Text,LongWritable>{
@Override
protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
long sum=0l;
for (LongWritable value : values) {
sum+=value.get();
}
context.write(key,new LongWritable(sum));
}
} public static void main(String[] args) throws Exception{ Job job = Job.getInstance();
job.setJobName("combine对性别进行计数");
job.setJarByClass(Demo8.class); job.setMapperClass(map.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class); job.setCombinerClass(combine.class); job.setReducerClass(reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class); Path in = new Path("/data/students.txt");
FileInputFormat.addInputPath(job,in); Path out = new Path("/output8");
FileSystem fs = FileSystem.get(new Configuration());
if (fs.exists(out)){
fs.delete(out,true);
}
FileOutputFormat.setOutputPath(job,out); job.waitForCompletion(true);
System.out.println("你又可以了"); }
}

WordCount基于本地和java的使用的更多相关文章

  1. Terrocotta - 基于JVM的Java应用集群解决方案

    前言 越来越多的企业关键应用都必须采用集群技术,实现负载均衡(Load Balancing).容错(Fault Tolerance)和灾难恢复(Failover).以达到系统可用性(High Avai ...

  2. [How to]基于本地镜像的yum镜像源搭建

    1.简介 本文介绍如何在封闭环境(无外网)下安装离线安装本地镜像与基于本地镜像的yum镜像源. 2.环境版本交代: OS:CentOS-6.7-x86_64-minimal yum: yum-3.2. ...

  3. 基于JavaMail的Java邮件发送:复杂邮件发送

    参考:http://blog.csdn.net/xietansheng/article/details/51722660package com.bfd.ftp.utils;import java.ut ...

  4. 基于本地存储的kvm虚拟机在线迁移

    基于本地存储的kvm虚拟机在线迁移 kvm虚拟机迁移分为4种(1)热迁移基于共享存储(2)热迁移基于本地存储(3)冷迁移基于共享存储(4)冷迁移基于本地存储 这里介绍的是基于本地存储的热迁移 动态块迁 ...

  5. 基于本地文件系统的LocalDB

    零.前言 之前写一些小工具的时候,需要用到数据存储方面的技术,但是用数据库又觉得太大了,本地文件存储txt文件存储又不是很规范,于是乎想到了去编写一个简单的基于本地文件系统的数据存储库,暂且叫它loc ...

  6. 基于类(Java)和基于原理(JavaScript)的对象系统的比较

    Java:面向对象编程语言,吸收了C++语言的各种优点,丢掉了C++让人头疼的多继承.指针等概念.具有功能强大和简单易用的两大特征.Java具有简单性.面向对象.分布式.健壮性.安全性.平台独立与可移 ...

  7. 基于Mapxtreme for JAVA的电子地图设计与实现

    基于Mapxtreme for JAVA的电子地图设计与实现学生毕业设计,适合测绘类专业研究目标:        开发一个基于MapXtreme for JAVA的校园电子地图项目,使用MapInfo ...

  8. Linux -- 基于zookeeper的java api(二)

    Linux -- 基于zookeeper的java api(二) 写一个关于基于集群的zookeeper的自定义实现HA 基于客户端和监控器:使用监控的方法查看每个注册过的节点的状态来做出操作. Wa ...

  9. Linux -- 基于zookeeper的java api(一)

    Linux -- 基于zookeeper的java api 首先启动你所有的 zkService.sh 查看状态:检查是否启动正确 [root@hu-hadoop2 ~]# zkServer.sh s ...

随机推荐

  1. CSS Modules 的六种用法

    一.局部作用域 二.全局作用域 三.定制哈希类名 四. Class 的组合 五.输入其他模块 六.输入变量

  2. vivo 评论中台的流量及数据隔离实践

    一.背景 vivo评论中台通过提供评论发表.点赞.举报.自定义评论排序等通用能力,帮助前台业务快速搭建评论功能并提供评论运营能力,避免了前台业务的重复建设和数据孤岛问题.目前已有vivo短视频.viv ...

  3. SharePoint Online 为Modern Page添加脚本

    前言 众所周知,如果我们想向SharePoint 页面添加脚本,最方便的便是经典页面,添加方式主要有内容编辑器Web部件或者直接使用SharePoint Designer. 但是,如果页面是Moder ...

  4. CentOS 7中的系统语言包及UTF-8、en_US.UTF-8和zh_CN.UTF-8的区别

    UTF-8.en_US.UTF-8和zh_CN.UTF-8的区别 en_US.UTF-8.zh_CN.UTF-8叫做字符集,就是说'A'.'B'.'中'.'国'等对应的整数值,en_US.UTF-8只 ...

  5. ARC下的内存管理

    1.ARC下单对象内存管理 局部变量释放对象随之被释放 int main(int argc, const char * argv[]) { @autoreleasepool { Person *p = ...

  6. MySQL语法命令之约束篇

    文章目录 1.约束概述 1.1约束的分类 1.2添加约束 2.查看表中的约束 3. `not null` 非空约束 3.1 在 `create table` 时创建 3.2 在`alter table ...

  7. 手把手教你在命令行(静默)部署oracle 11gR2

    文章目录 环境介绍 linux发行版 cpu.内存以及磁盘空间 敲黑板 关闭防火墙以及selinux 操作系统配置 使用阿里的yum源提速 安装依赖软件 设置用户最大进程数以及最大文件打开数 内核参数 ...

  8. MySQL架构原理之存储引擎InnoDB数据文件

    MySQL架构原理之体系架构 - 池塘里洗澡的鸭子 - 博客园 (cnblogs.com)中简单介绍了MySQL的系统文件层,其中包含了数据文件.那么InnoDB的数据文件是如何分类并存储的呢? 一. ...

  9. 日行一算(Consecutive Integer-连续整数)

    题目 题目描述 2005年的百度之星初赛有这么一道题,一个正整数有可能可以被表示为 m(m>1) 个连续正整数之和,如: 15=1+2+3+4+5 15=4+5+6 15=7+8 但现在你的任务 ...

  10. IDEA使用JDBC链接MySql(java编程)

    1.在Maven的pom.xml文件中引入MySql的驱动 <dependency> <groupId>mysql</groupId> <artifactId ...