你好，游客 登录
背景：
阅读新闻

hadoop实现购物商城推荐系统

[日期：2014-07-04] 来源：uml.org.cn  作者：潇洒子弦的博客 [字体：大 中 小] 
package xian.zhang.common;
import java.util.regex.Pattern;
public class Util {
	 public static final Pattern DELIMITER = Pattern.compile("[\t,]");
}

 

package xian.zhang.core;
import java.io.IOException;
import java.util.Iterator;
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.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;
/**
 * 将输入数据 userid1，product1  userid1，product2   userid1，product3
 * 合并成 userid1 product1,product2,product3输出
 * @author zx
 *
 */
public class CombinProductInUser {
	
	public static class CombinProductMapper extends Mapper<LongWritable, Text, IntWritable, Text>{
		@Override
		protected void map(LongWritable key, Text value,Context context)
				throws IOException, InterruptedException {
			String[] items = value.toString().split(","); 
			context.write(new IntWritable(Integer.parseInt(items[0])), new Text(items[1]));
		}
	}
	
	public static class CombinProductReducer extends Reducer<IntWritable, Text, IntWritable, Text>{
		@Override
		protected void reduce(IntWritable key, Iterable<Text> values,Context context)
				throws IOException, InterruptedException {
			StringBuffer sb = new StringBuffer();
			Iterator<Text> it = values.iterator();
			sb.append(it.next().toString());
			while(it.hasNext()){
				sb.append(",").append(it.next().toString());
			}
			context.write(key, new Text(sb.toString()));
		}
		
	}
	
	@SuppressWarnings("deprecation")
	public static boolean run(Path inPath,Path outPath) throws IOException, ClassNotFoundException, InterruptedException{
		
		Configuration conf = new Configuration();
		Job job = new Job(conf,"CombinProductInUser");
		
		job.setJarByClass(CombinProductInUser.class);
		job.setMapperClass(CombinProductMapper.class);
		job.setReducerClass(CombinProductReducer.class);
		job.setOutputKeyClass(IntWritable.class);
		job.setOutputValueClass(Text.class);
		
		FileInputFormat.addInputPath(job, inPath);
		FileOutputFormat.setOutputPath(job, outPath);
		
		return job.waitForCompletion(true);
		
	}
	
}

 

package xian.zhang.core;
import java.io.IOException;
import java.util.Iterator;
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.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;
/**
 * 将输入数据 userid1，product1  userid1，product2   userid1，product3
 * 合并成 userid1 product1,product2,product3输出
 * @author zx
 *
 */
public class CombinProductInUser {
	
	public static class CombinProductMapper extends Mapper<LongWritable, Text, IntWritable, Text>{
		@Override
		protected void map(LongWritable key, Text value,Context context)
				throws IOException, InterruptedException {
			String[] items = value.toString().split(","); 
			context.write(new IntWritable(Integer.parseInt(items[0])), new Text(items[1]));
		}
	}
	
	public static class CombinProductReducer extends Reducer<IntWritable, Text, IntWritable, Text>{
		@Override
		protected void reduce(IntWritable key, Iterable<Text> values,Context context)
				throws IOException, InterruptedException {
			StringBuffer sb = new StringBuffer();
			Iterator<Text> it = values.iterator();
			sb.append(it.next().toString());
			while(it.hasNext()){
				sb.append(",").append(it.next().toString());
			}
			context.write(key, new Text(sb.toString()));
		}
		
	}
	
	@SuppressWarnings("deprecation")
	public static boolean run(Path inPath,Path outPath) throws IOException, ClassNotFoundException, InterruptedException{
		
		Configuration conf = new Configuration();
		Job job = new Job(conf,"CombinProductInUser");
		
		job.setJarByClass(CombinProductInUser.class);
		job.setMapperClass(CombinProductMapper.class);
		job.setReducerClass(CombinProductReducer.class);
		job.setOutputKeyClass(IntWritable.class);
		job.setOutputValueClass(Text.class);
		
		FileInputFormat.addInputPath(job, inPath);
		FileOutputFormat.setOutputPath(job, outPath);
		
		return job.waitForCompletion(true);
		
	}
	
}


 

package xian.zhang.core;
import java.io.IOException;
import org.apache.hadoop.fs.Path;
public class Main {
	
	public static void main(String[] args) throws ClassNotFoundException, IOException, InterruptedException {
		
		if(args.length < 2){
			throw new IllegalArgumentException("要有两个参数，数据输入的路径和输出路径");
		}
		
		Path inPath1 = new Path(args[0]);
		Path outPath1 = new Path(inPath1.getParent()+"/CombinProduct");
		
		Path inPath2 = outPath1;
		Path outPath2 = new Path(args[1]);
		
		if(CombinProductInUser.run(inPath1, outPath1)){
			System.exit(ProductCo_occurrenceMatrix.run(inPath2, outPath2)?0:1);
		}
	}
	
}

ShopxxUserRecommend<相同购物喜好的好友推荐>

整个项目分两部，一，以商品对用户进行分组，二，求出用户的同现矩阵。

原理和ShopxxProductRecommend一样

下面附上代码

package xian.zhang.common;
import java.util.regex.Pattern;
public class Util {
	 public static final Pattern DELIMITER = Pattern.compile("[\t,]");
}

 

package xian.zhang.core;
import java.io.IOException;
import java.util.Iterator;
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.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;
/**
 * 将输入数据 userid1，product1  userid1，product2   userid1，product3
 * 合并成 productid1 user1,user2,user3输出
 * @author zx
 *
 */
public class CombinUserInProduct {
	
	public static class CombinUserMapper extends Mapper<LongWritable, Text, IntWritable, Text>{
		@Override
		protected void map(LongWritable key, Text value,Context context)
				throws IOException, InterruptedException {
			String[] items = value.toString().split(","); 
			context.write(new IntWritable(Integer.parseInt(items[1])), new Text(items[0]));
		}
	}
	
	public static class CombinUserReducer extends Reducer<IntWritable, Text, IntWritable, Text>{
		@Override
		protected void reduce(IntWritable key, Iterable<Text> values,Context context)
				throws IOException, InterruptedException {
			StringBuffer sb = new StringBuffer();
			Iterator<Text> it = values.iterator();
			sb.append(it.next().toString());
			while(it.hasNext()){
				sb.append(",").append(it.next().toString());
			}
			context.write(key, new Text(sb.toString()));
		}
		
	}
	
	@SuppressWarnings("deprecation")
	public static boolean run(Path inPath,Path outPath) throws IOException, ClassNotFoundException, InterruptedException{
		Configuration conf = new Configuration();
		Job job = new Job(conf,"CombinUserInProduct");
		
		job.setJarByClass(CombinUserInProduct.class);
		job.setMapperClass(CombinUserMapper.class);
		job.setReducerClass(CombinUserReducer.class);
		job.setOutputKeyClass(IntWritable.class);
		job.setOutputValueClass(Text.class);
		
		FileInputFormat.addInputPath(job, inPath);
		FileOutputFormat.setOutputPath(job, outPath);
		
		return job.waitForCompletion(true);
		
	}
	
}

 

package xian.zhang.core;
import java.io.IOException;
import java.util.Iterator;
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.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import xian.zhang.common.Util;
/**
 * 用户的同先矩阵
 * @author zx
 *
 */
public class UserCo_occurrenceMatrix {
	public static class Co_occurrenceMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
		IntWritable one = new IntWritable(1);
		
		@Override
		protected void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException {
			
			String[] products = Util.DELIMITER.split(value.toString());
			for(int i=1;i<products.length;i++){
				for(int j=1;j<products.length;j++){
					if(i != j){
						context.write(new Text(products[i] + ":" + products[j]), one);
					}
				}
			}
			
		}
		
	}
	
	public static class Co_occurrenceReducer extends Reducer<Text, IntWritable, NullWritable, Text>{
		NullWritable nullKey =NullWritable.get();
		
		@Override
		protected void reduce(Text key, Iterable<IntWritable> values,Context context)
				throws IOException, InterruptedException {
			int sum = 0;
			Iterator<IntWritable> it = values.iterator();
			while(it.hasNext()){
				sum += it.next().get();
			}
			context.write(nullKey, new Text(key.toString().replace(":", ",") + "," + sum));
		}
		
	}
	
	@SuppressWarnings("deprecation")
	public static boolean run(Path inPath,Path outPath) throws IOException, ClassNotFoundException, InterruptedException{
		
		Configuration conf = new Configuration();
		Job job = new Job(conf,"UserCo_occurrenceMatrix");
		
		job.setJarByClass(UserCo_occurrenceMatrix.class);
		job.setMapperClass(Co_occurrenceMapper.class);
		job.setReducerClass(Co_occurrenceReducer.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		job.setOutputKeyClass(NullWritable.class);
		job.setOutputKeyClass(Text.class);
		
		FileInputFormat.addInputPath(job, inPath);
		FileOutputFormat.setOutputPath(job, outPath);
		
		return job.waitForCompletion(true);
	}
	
}

 

package xian.zhang.core;
import java.io.IOException;
import org.apache.hadoop.fs.Path;
public class Main {
	
	public static void main(String[] args) throws ClassNotFoundException, IOException, InterruptedException {
		
		if(args.length < 2){
			throw new IllegalArgumentException("要有两个参数，数据输入的路径和输出路径");
		}
		
		Path inPath1 = new Path(args[0]);
		Path outPath1 = new Path(inPath1.getParent()+"/CombinUser");
		
		Path inPath2 = outPath1;
		Path outPath2 = new Path(args[1]);
		
		if(CombinUserInProduct.run(inPath1, outPath1)){
			System.exit(UserCo_occurrenceMatrix.run(inPath2, outPath2)?0:1);
		}
	}
	
}

代码在github上有

git@github.com:chaoku/ShopxxProductRecommend.git





收藏 推荐 打印 | 录入： | 阅读： 次
云服务新宠儿Spark和Hadoop，谁将是最后的赢家
详解Hadoop核心架构
相关新闻       Hadoop 
本文评论 　　查看全部评论 (0)
表情： 表情 姓名： 字数
点评：
　　　 　　　
评论声明
  • 尊重网上道德，遵守中华人民共和国的各项有关法律法规
  • 承担一切因您的行为而直接或间接导致的民事或刑事法律责任
  • 本站管理人员有权保留或删除其管辖留言中的任意内容
  • 本站有权在网站内转载或引用您的评论
  • 参与本评论即表明您已经阅读并接受上述条款
推荐阅读