使用eclipse开发MapReduce项目更加方便(使用hadoop插件)
1.把插件jar包放到eclipse目录的plugins下面
2.将Window编译后的hadoop文件放到hadoop的bin目录下
3.添加环境变量支持
4.修改hdfs-site.xml的配置
5.eclipse上配置
需要先打开虚拟机上的hadoop服务
然后才能连上去
6.准备要分析的数据并且上传到hdfs 会在D盘的tmp文件下生成1-300.txt 里面就是要分析的数据
package com.blb.core;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.util.ArrayList;
import java.util.List;
import java.util.Random;
/**
* 300户 每户都会有一个清单文件
* 商品是随机 数量也是随机
* 洗漱用品 脸盆、杯子、牙刷和牙膏、毛巾、肥皂(洗衣服的)以及皂盒、洗发水和护发素、沐浴液 [1-5之间]
* 床上用品 比如枕头、枕套、枕巾、被子、被套、棉被、毯子、床垫、凉席 [0 1之间]
* 家用电器 比如电磁炉、电饭煲、吹风机、电水壶、豆浆机、台灯等 [1-3之间]
* 厨房用品 比如锅、碗、瓢、盆、灶 [1-2 之间]
* 柴、米、油、盐、酱、醋 [1-6之间]
* 要生成300个文件 命名规则 1-300来表示
* @author Administrator
*
*/
public class BuildBill {
private static Random random=new Random(); //要还是不要
private static List<String> washList=new ArrayList<>();
private static List<String> bedList=new ArrayList<>();
private static List<String> homeList=new ArrayList<>();
private static List<String> kitchenList=new ArrayList<>();
private static List<String> useList=new ArrayList<>();
static{
washList.add("脸盆");
washList.add("杯子");
washList.add("牙刷");
washList.add("牙膏");
washList.add("毛巾");
washList.add("肥皂");
washList.add("皂盒");
washList.add("洗发水");
washList.add("护发素");
washList.add("沐浴液");
///////////////////////////////
bedList.add("枕头");
bedList.add("枕套");
bedList.add("枕巾");
bedList.add("被子");
bedList.add("被套");
bedList.add("棉被");
bedList.add("毯子");
bedList.add("床垫");
bedList.add("凉席");
//////////////////////////////
homeList.add("电磁炉");
homeList.add("电饭煲");
homeList.add("吹风机");
homeList.add("电水壶");
homeList.add("豆浆机");
homeList.add("电磁炉");
homeList.add("台灯");
//////////////////////////
kitchenList.add("锅");
kitchenList.add("碗");
kitchenList.add("瓢");
kitchenList.add("盆");
kitchenList.add("灶 ");
////////////////////////
useList.add("米");
useList.add("油");
useList.add("盐");
useList.add("酱");
useList.add("醋");
}
//确定要还是不要 1/2
private static boolean iswant()
{
int num=random.nextInt(1000);
if(num%2==0)
{
return true;
}
else
{
return false;
}
}
/**
* 表示我要几个
* @param sum
* @return
*/
private static int wantNum(int sum)
{
return random.nextInt(sum);
}
//生成300个清单文件 格式如下
//输出的文件的格式 一定要是UTF-8
//油 2
public static void main(String[] args) {
for(int i=1;i<=300;i++)
{
System.out.println(i);
try {
//字节流
FileOutputStream out=new FileOutputStream(new File("D:\\tmp\\"+i+".txt"));
//转换流 可以将字节流转换字符流 设定编码格式
//字符流
BufferedWriter writer=new BufferedWriter(new OutputStreamWriter(out,"UTF-8"));
//随机一下 我要不要 随机一下 要几个 再从我们的清单里面 随机拿出几个来 数量
boolean iswant1=iswant();
if(iswant1)
{
//我要几个 不能超过该类商品的总数目
int wantNum = wantNum(washList.size()+1);
//3
for(int j=0;j<wantNum;j++)
{
String product=washList.get(random.nextInt(washList.size()));
writer.write(product+"\t"+(random.nextInt(5)+1));
writer.newLine();
}
}
boolean iswant2=iswant();
if(iswant2)
{
//我要几个 不能超过该类商品的总数目
int wantNum = wantNum(bedList.size()+1);
//3
for(int j=0;j<wantNum;j++)
{
String product=bedList.get(random.nextInt(bedList.size()));
writer.write(product+"\t"+(random.nextInt(1)+1));
writer.newLine();
}
}
boolean iswant3=iswant();
if(iswant3)
{
//我要几个 不能超过该类商品的总数目
int wantNum = wantNum(homeList.size()+1);
//3
for(int j=0;j<wantNum;j++)
{
String product=homeList.get(random.nextInt(homeList.size()));
writer.write(product+"\t"+(random.nextInt(3)+1));
writer.newLine();
}
}
boolean iswant4=iswant();
if(iswant4)
{
//我要几个 不能超过该类商品的总数目
int wantNum = wantNum(kitchenList.size()+1);
//3
for(int j=0;j<wantNum;j++)
{
String product=kitchenList.get(random.nextInt(kitchenList.size()));
writer.write(product+"\t"+(random.nextInt(2)+1));
writer.newLine();
}
}
boolean iswant5=iswant();
if(iswant5)
{
//我要几个 不能超过该类商品的总数目
int wantNum = wantNum(useList.size()+1);
//3
for(int j=0;j<wantNum;j++)
{
String product=useList.get(random.nextInt(useList.size()));
writer.write(product+"\t"+(random.nextInt(6)+1));
writer.newLine();
}
}
writer.flush();
writer.close();
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}生成的文件上传到hdfs
7.开始写MapReduce程序
创建一个MapReduce项目
map阶段
package com.blb.lyx;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class GoodCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
public void map(LongWritable ikey, Text ivalue, Context context) throws IOException, InterruptedException {
//读取一行的文件
String line = ivalue.toString();
//进行字符串的切分
String[] split = line.split("\t");
//写入
context.write(new Text(split[0]), new IntWritable(Integer.parseInt(split[1])));
}
}
reduce阶段
package com.blb.lyx;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class GoodCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text _key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
//将IntWritable转换为Int类型
int i = val.get();
sum += i;
}
context.write(_key, new IntWritable(sum));
}
}
job阶段
package com.blb.lyx;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class GoodCountDriver {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
//配置服务器的端口和地址
conf.set("fs.defaultFS", "hdfs://192.168.43.61:9000");
Job job = Job.getInstance(conf, "CountDriver");
job.setJarByClass(GoodCountDriver.class);
// TODO: specify a mapper
job.setMapperClass(GoodCountMapper.class);
// TODO: specify a reducer
job.setReducerClass(GoodCountReducer.class);
//如果reducer的key类型和map的key类型一样，可以不写map的key类型
//如果reduce的value类型和map的value类型一样，可以不写map的value类型
// TODO: specify output types
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
// TODO: specify input and output DIRECTORIES (not files)
FileInputFormat.setInputPaths(job, new Path("/tmp/"));
FileOutputFormat.setOutputPath(job, new Path("/out2/"));
if (!job.waitForCompletion(true))
return;
}
}
8.运行项目 主要运行在hadoop上 Run on Hadoop
运行成功
查看结果
