mahout 推荐系统 之 评估查全率与查准率

从更全面的看待推荐系统：通过偏好值来生成推荐结果并非绝对必要。给出一个从优到劣排序的推荐结果在很多场景就够用了，而不用必须包含估计的偏好值；而事实上，有时候精确的列表顺序也不是那么必要，有几个好的结果就可以了。

从这种普遍的视角，可以运用经典的信息检索(information retrieval)度量标准来评估推荐系统：查准率(precision)、查全率(recall)

一个评估查全率与查准率的简单demo：

package com.xh.recommender;import org.apache.mahout.cf.taste.common.TasteException;
import org.apache.mahout.cf.taste.eval.IRStatistics;
import org.apache.mahout.cf.taste.eval.RecommenderBuilder;
import org.apache.mahout.cf.taste.eval.RecommenderIRStatsEvaluator;
import org.apache.mahout.cf.taste.impl.eval.GenericRecommenderIRStatsEvaluator;
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.Recommender;
import org.apache.mahout.cf.taste.similarity.UserSimilarity;
import org.apache.mahout.common.RandomUtils;import java.io.File;
import java.net.URL;/*** @author xiaohe* @version V1.0.0* @Description: 评估 查全率 与 查准率* @date: 2018-8-25 18:52* @Copyright:*/
public class IREvaluatorIntro {public static void main(String[] args) throws Exception {/**** 强制 每次选择相同的随机值* 只是为了获取可重复的结果* 可以用在demo和测试用例，不能用在实际代码中**/RandomUtils.useTestSeed();final String filePath = "intro.csv";URL url = RecommenderIntro.class.getClassLoader().getResource(filePath);File modelFile = new File(url.getFile());if(!modelFile.exists()) {System.err.println("Please, specify name of file, or put file 'input.csv' into current directory!");System.exit(1);}// 装载数据文件DataModel model = new FileDataModel(modelFile);RecommenderIRStatsEvaluator evaluator =new GenericRecommenderIRStatsEvaluator();// 构建  推荐 示例RecommenderBuilder recommenderBuilder = new RecommenderBuilder() {/**** Recommender 是由新的 DataModel 构建的**/@Overridepublic Recommender buildRecommender(DataModel model) throws TasteException {UserSimilarity similarity = new PearsonCorrelationSimilarity(model);UserNeighborhood neighborhood =new NearestNUserNeighborhood(2, similarity, model);return new GenericUserBasedRecommender(model, neighborhood, similarity);}};IRStatistics stats = evaluator.evaluate(recommenderBuilder,null, model, null, 2,GenericRecommenderIRStatsEvaluator.CHOOSE_THRESHOLD,1.0);// 查准率  有多少结果是好的System.out.println(stats.getPrecision());// 查全率  有多少好的推荐包含在里面System.out.println(stats.getRecall());}}

项目结构：