Mahout基于用户的协同过滤算法的例子

每行测试数据分别标识用户id(uid),物品id(itemid),评分(rating),评分时间(time)
3464,2502,3,973282547
3464,3160,2,973282494
3464,2505,3,967175070
3464,1703,2,967248043
3464,1704,5,967246680
3464,3163,1,967174266
3464,2369,4,973282339
3464,1569,4,967247436
3464,896,3,967247557
3464,3316,3,973282934
3464,2517,3,967174139
3464,3174,4,967174266
3464,3175,2,973282421
3464,3176,3,967174298
3464,1573,3,967247865
3464,3178,4,967247587
3464,105,3,967248019
3464,3325,4,973282547
3464,1721,3,967247042
3464,3327,4,973282892
3464,3185,3,967174298
3464,1727,4,967248268
3464,111,5,967174438
3464,3186,4,967242949
3464,1729,3,967247165
3464,1584,3,967247078
3464,2387,3,967247884
3464,2389,4,967175256
3464,1589,4,967248019
3464,1732,4,967247306
3464,2391,4,967246935
3464,2395,4,973282625
3464,2396,5,967246752
3464,1597,4,967174960
3464,2541,3,967247865

package userBased;

import java.io.File;
import java.util.List;

import org.apache.mahout.cf.taste.impl.model.file.FileDataModel;
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.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;

/**
 * mahout基于用户的协同过滤算法
 *
 */
public class UserBased {

    public static void main(String[] args) throws Exception {

        DataModel model = new FileDataModel(new File("F:/ml-1m/ratings.dat"));
        /**
         * 用户偏好数据包含评分    
                欧氏距离：EuclideanDistanceSimilarity
                         皮尔森距离：PearsonCorrelationSimilarity
                                            余弦距离：UncenteredCosineSimilarity

                                    用户偏好数据不包含评分   
                                        曼哈顿距离：CityBlockSimilarity
                                       对数似然距离： LogLikelihoodSimilarity              
         */
        UserSimilarity similarity = new PearsonCorrelationSimilarity(model);
        // 相邻用户UserNeighborhood
        /**
         * NearestNUserNeighborhood 
                 指定距离最近的N个用户作为邻居。
                示例：UserNeighborhood unb = new NearestNUserNeighborhood(10, us, dm);
                三个参数分别是： 邻居的个数，用户相似度，数据模型 
                邻居个数的大小直接决定了推荐结果的近似程度和计算的复杂度   
           ThresholdUserNeighborhood 
                指定距离最近的一定百分比的用户作为邻居。
                示例：UserNeighborhood unb = new ThresholdUserNeighborhood(0.2, us, dm); 
                三个参数分别是： 阀值（取值范围0到1之间），用户相似度，数据模型
         */
        UserNeighborhood neighborhood = new NearestNUserNeighborhood(500, similarity, model);
        //根据数据模型、用户相似度模型、以及邻近值构建推荐引擎
        Recommender recommender = new GenericUserBasedRecommender(model, neighborhood, similarity);
        // 向用户100推荐2个商品
        List<RecommendedItem> recommendations = recommender.recommend(100, 2);
        for (RecommendedItem recommendation : recommendations) {
            // 输出推荐结果
            System.out.println(recommendation);
        }
    }
}