首先是封装了一个给予用户的推荐,用的相似度算法还是皮尔逊相似度,其他的也可以封装。
package com.liuxinquan.utils;
import java.io.File;
import java.io.IOException;
import java.util.List;
import org.apache.mahout.cf.taste.common.TasteException;
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;
public class UserPersonSim {
public static List<RecommendedItem> userRec(String filePath, int nearCnt, int userId, int recCnt) {
try {
DataModel model = new FileDataModel(new File(filePath));
UserSimilarity similarity = new PearsonCorrelationSimilarity(model);
UserNeighborhood neighborhood = new NearestNUserNeighborhood(nearCnt, similarity, model);
Recommender recommender = new GenericUserBasedRecommender(model, neighborhood, similarity);
List<RecommendedItem> recommendations = recommender.recommend(userId, recCnt);
return recommendations;
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (TasteException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return null;
}
}
4个参数:filePath---------要分析的数据文件.csv
nearcnt---------推荐给用户的最近的一组数据个数
userid------推荐用户id
reccnt-------推荐给用户的个数
具体使用:
package com.liuxinquan.recommmder;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import org.apache.mahout.cf.taste.recommender.RecommendedItem;
import com.liuxinquan.utils.UserPersonSim;
public class UserRecommder {
public static void main(String[] args) {
HashMap<String, String> map = new HashMap<>();
map.put("101", "橘子");
map.put("102", "苹果");
map.put("103", "香蕉");
map.put("104", "梨");
map.put("105", "西瓜");
map.put("106", "哈密瓜");
map.put("107", "葡萄");
String filePath = "xxx/intro.csv";
for (RecommendedItem item : UserPersonSim.userRec(filePath, 2, 1, 1)) {
System.out.println(map.get(item.getItemID() + ""));
}
}
}
结果:梨
和上一篇的104是对应的。这样更贴近实际应用,也给大家提供了一种思路。在实际中不可能都是数据格式的,更常见的是: 张三:梨。这就需要我们制定一种规则,先从现实中抽象出来物体的特征:比方一本书的作者、出版商、出版日期等,用数字把特征对应起来后在还原。