Mahout实现基于用户的协同过滤算法

package com.mahout.helloworlddemo;

import java.sql.Connection;
import java.sql.DatabaseMetaData;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.sql.Statement;
import java.util.HashSet;
import java.util.List;

import org.apache.mahout.cf.taste.impl.model.jdbc.MySQLJDBCDataModel;
import org.apache.mahout.cf.taste.impl.neighborhood.NearestNUserNeighborhood;
import org.apache.mahout.cf.taste.impl.recommender.GenericUserBasedRecommender;
import org.apache.mahout.cf.taste.impl.similarity.PearsonCorrelationSimilarity;
import org.apache.mahout.cf.taste.model.DataModel;
import org.apache.mahout.cf.taste.model.JDBCDataModel;
import org.apache.mahout.cf.taste.neighborhood.UserNeighborhood;
import org.apache.mahout.cf.taste.recommender.RecommendedItem;
import org.apache.mahout.cf.taste.recommender.Recommender;
import org.apache.mahout.cf.taste.similarity.UserSimilarity;

import com.mahout.util.DBUtil;
import com.mysql.jdbc.jdbc2.optional.MysqlDataSource;



/**
 *
 *@author wxisme
 *@time 2015-9-13 下午6:25:26
 */
public class RecommenderIntroFromMySQL {
    
    public static void main(String[] args) throws Exception {
        
        //连接MySQL
        MysqlDataSource dataSource = new MysqlDataSource();
        dataSource.setServerName("localhost");
        dataSource.setUser("root");
        dataSource.setPassword("1234");
        dataSource.setDatabaseName("mahoutdemo");
        
        
        //获取数据模型
        JDBCDataModel dataModel = new MySQLJDBCDataModel(dataSource, "taste_preferences", "user_id", "item_id", "preference","time");
                                       
        DataModel model = dataModel;
        
        //计算相似度
        UserSimilarity similarity = new PearsonCorrelationSimilarity(model);
        //计算阈值
        UserNeighborhood neighborhood = new NearestNUserNeighborhood(2,similarity,model);
        
        //推荐
        Recommender recommender = new GenericUserBasedRecommender(model,neighborhood,similarity);
        
        Connection con = DBUtil.getConnection();
        Statement stmt = con.createStatement();
        
        //获取每个用户的推荐数据并存入数据库
        
        for(int i=0; i<5; i++) {
            List<RecommendedItem> recommendations = recommender.recommend(i, 3);
            
            String tableName = "user_" + i;
            
            for (RecommendedItem recommendation : recommendations) {
                
                //如果是第一次推荐就创建该用户的数据表
                if(!doesTableExist(tableName)) {
                    
                    String createSQL = "create table " + tableName
                            + " (item_id bigint primary key,value float);";
                    stmt.execute(createSQL);
                }
                
                String insertSQL = "insert into " + tableName + " values ("
                        + recommendation.getItemID() + "," + recommendation.getValue() + " );";
                
                //插入用户的推荐数据
                stmt.execute(insertSQL);
                
                
                System.out.println(recommendation);
            }
        }
        
        
        
        
        
    }
    
    
    /**
     * 是否存在这个数据表
     * @param tablename
     * @return
     * @throws SQLException
     */
    public static Boolean doesTableExist(String tablename) throws SQLException {
        HashSet<String> set = new HashSet<String>();
        Connection con = DBUtil.getConnection();
        DatabaseMetaData meta = con.getMetaData();
        ResultSet res = meta.getTables(null, null, null,
                new String[]{"TABLE"});
        while (res.next()) {
            set.add(res.getString("TABLE_NAME"));
        }
        DBUtil.close(res, con);
        return set.contains(tablename);
    }

}