Java Recommender类代码示例

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
public static void main(String[] args) throws IOException, TasteException {
	DataModel model  = 
			new FileDataModel(new File("data/ua.base"));
	
	UserSimilarity similarity = 
			new PearsonCorrelationSimilarity(model);
	
	UserNeighborhood neighborhood = 
			new NearestNUserNeighborhood(2, similarity, model);
	
	Recommender recommender = new GenericUserBasedRecommender(
			model, neighborhood, similarity);
	
	List<RecommendedItem> recommendations = recommender.recommend(2, 1);
	
	for (RecommendedItem recommendation : recommendations) {
		logger.info(recommendation.toString());
	}
	
	logger.info("over");
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
private static void recommend(String ratingsFile, int ... userIds)
    throws TasteException, IOException {
  DataModel model = new FileDataModel(new File(ratingsFile));

  UserSimilarity similarity = new PearsonCorrelationSimilarity(model);

  UserNeighborhood neighborhood =
      new NearestNUserNeighborhood(
          100, similarity, model);

  Recommender recommender =  new GenericUserBasedRecommender(
      model, neighborhood, similarity);

  Recommender cachingRecommender = new CachingRecommender(recommender);

  for(int userId: userIds) {
    System.out.println("UserID " + userId);
    List<RecommendedItem> recommendations =
        cachingRecommender.recommend(userId, 2);
    for(RecommendedItem item: recommendations) {
      System.out.println("  item " + item.getItemID() + " score " + item.getValue());
    }
  }
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
@Test
public void testBuildKNNRecommender() {
    GenericRecommenderBuilder rb = new GenericRecommenderBuilder();
    FastByIDMap<PreferenceArray> userData = new FastByIDMap<PreferenceArray>();
    userData.put(1, new GenericUserPreferenceArray(Arrays.asList(new GenericPreference(1, 1, 1),
            new GenericPreference(1, 2, 1), new GenericPreference(1, 3, 1))));
    userData.put(2, new GenericUserPreferenceArray(Arrays.asList(new GenericPreference(2, 1, 1),
            new GenericPreference(2, 2, 1), new GenericPreference(2, 4, 1))));
    DataModel dm = new GenericDataModel(userData);

    Recommender rec = null;
    String recommenderType = "org.apache.mahout.cf.taste.impl.recommender.GenericUserBasedRecommender";
    String similarityType = "org.apache.mahout.cf.taste.impl.similarity.PearsonCorrelationSimilarity";
    try {
        rec = rb.buildRecommender(dm, recommenderType, similarityType);
    } catch (RecommenderException e) {
        e.printStackTrace();
    }
    assertTrue(rec instanceof GenericUserBasedRecommender);
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
public static void main(String[] args) throws IOException, TasteException {
	RandomUtils.useTestSeed();
	
	final DataModel model = new FileDataModel(new File("data/intro.csv"));
	
	RecommenderIRStatsEvaluator evaluator = 
			new GenericRecommenderIRStatsEvaluator();
	
	RecommenderBuilder recommenderBuilder = new RecommenderBuilder() {
		
		public Recommender buildRecommender(DataModel dataModel) 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);
	
	System.out.println(stats.getPrecision());
	System.out.println(stats.getRecall());
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
@Override
public void run(RecommenderConfiguration configuration,
                Environment environment) {
    
    PGPoolingDataSource pgPoolingDataSource = configuration.getDataSourceFactory().build(environment);
    ReloadFromJDBCDataModel dataModel = null;
    try {
        dataModel = configuration.getDataModelFactory().build(pgPoolingDataSource);
    } catch (TasteException e) {
        System.err.println(e);
        System.exit(-1);
    }
    
    Recommender userBasedRecommender = configuration.getRecommenderFactory().buildUserBasedRecommender(dataModel);
    ItemBasedRecommender itemBasedRecommender = configuration.getRecommenderFactory().buildItemBasedRecommender(dataModel);
    
    final RecommendationResource userRecommendationResource = new RecommendationResource(userBasedRecommender, itemBasedRecommender);
    final DataModelResource dataModelResource = new DataModelResource(dataModel);
    environment.jersey().register(userRecommendationResource);
    environment.jersey().register(dataModelResource);
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
public static void main(String[] args) {
    try {
        MysqlDataSource dataSource = new MysqlDataSource();
        dataSource.setServerName("localhost");
        dataSource.setUser("root");
        dataSource.setPassword("root");
        dataSource.setDatabaseName("rec");
        JDBCDataModel dm = new MySQLJDBCDataModel(dataSource,"ratings","userid","itemid","rating","");
        UserSimilarity similarity = new PearsonCorrelationSimilarity(dm);
        UserNeighborhood neighbor = new NearestNUserNeighborhood(2,similarity, dm);
        Recommender recommender = new GenericUserBasedRecommender(dm, neighbor, similarity);
        List<RecommendedItem> list = recommender.recommend(1, 3);// recommend
                                                                 // one item
                                                                 // to user
                                                                 // 1
        for (RecommendedItem ri : list) {
            System.out.println(ri);
        }
    } catch (Exception e) {
        e.printStackTrace();
    }

}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
@Test
public void testBuildDefaultRecommender() {

    RecommenderBuilder rb = new GenericRecommenderBuilder();
    FastByIDMap<PreferenceArray> userData = new FastByIDMap<PreferenceArray>();
    userData.put(1, new GenericUserPreferenceArray(Arrays.asList(new GenericPreference(1, 1, 1),
            new GenericPreference(1, 2, 1), new GenericPreference(1, 3, 1))));
    userData.put(2, new GenericUserPreferenceArray(Arrays.asList(new GenericPreference(2, 1, 1),
            new GenericPreference(2, 2, 1), new GenericPreference(2, 4, 1))));
    DataModel dm = new GenericDataModel(userData);

    Recommender rec = null;
    try {
        rec = rb.buildRecommender(dm);
    } catch (TasteException e) {
        e.printStackTrace();
    }
    assertTrue(rec instanceof RandomRecommender);
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
public Recommender buildRecommender(DataModel arg0) {
	try {
		return BookRecommender.itemBased();
	} catch (Exception e) {
		// TODO Auto-generated catch block
		e.printStackTrace();
	}
	return null;
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
public static void main(String[] args) throws IOException, TasteException {
	RandomUtils.useTestSeed();
	
	final DataModel model = new FileDataModel(new File("data/ua.base"));
	
	RecommenderEvaluator evaluator = new AverageAbsoluteDifferenceRecommenderEvaluator();
	
	RecommenderBuilder builder = new RecommenderBuilder() {
		
		public Recommender buildRecommender(DataModel dataModel) throws TasteException {
			UserSimilarity similarity = new PearsonCorrelationSimilarity(model);
			UserNeighborhood neighborhood = 
					new NearestNUserNeighborhood(2, similarity, model);
			return new GenericUserBasedRecommender(model, neighborhood, similarity);
		}
	};
	
	double score = evaluator.evaluate(builder, null, model, 0.7, 1.0);
	
	System.out.println(score);
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
@Test
public void mahoutSlopeoneGeneratorTest_testBoolRecommender() throws TasteException {
    EasyrecDataModel easyrecDataModel = new EasyrecDataModel(TENANT_ID, BUY_ACTION_TYPE_ID, false, mahoutDataModelMappingDAO);
    /*TanimotoCoefficientSimilarity is intended for "binary" data sets  where a user either expresses a generic "yes" preference for an item or has no preference.*/
    UserSimilarity userSimilarity = new TanimotoCoefficientSimilarity(easyrecDataModel);

    /*ThresholdUserNeighborhood is preferred in situations where we go in for a  similarity measure between neighbors and not any number*/
    UserNeighborhood neighborhood = new ThresholdUserNeighborhood(0.1d, userSimilarity, easyrecDataModel);

    /*GenericBooleanPrefUserBasedRecommender is appropriate for use when no notion of preference value exists in the data. */
    Recommender recommender = new GenericBooleanPrefUserBasedRecommender(easyrecDataModel, neighborhood, userSimilarity);

    Assert.assertEquals(30, recommender.recommend(3, 1).get(0).getItemID());
    Assert.assertEquals(1,(int) recommender.recommend(3, 1).get(0).getValue());
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
@Test
public void mahoutSlopeoneGeneratorTest_testRecommender() throws TasteException {
    EasyrecDataModel easyrecDataModel = new EasyrecDataModel(TENANT_ID, RATE_ACTION_TYPE_ID, true, mahoutDataModelMappingDAO);
    Recommender recommender = new SlopeOneRecommender(easyrecDataModel);

    Assert.assertEquals(3, recommender.recommend(3, 1).get(0).getItemID());
    Assert.assertEquals(10, (int) recommender.recommend(3, 1).get(0).getValue());
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
@Override
public Recommender buildRecommender(DataModel model)
    throws TasteException {
  UserSimilarity similarity =
      new PearsonCorrelationSimilarity(model);

  UserNeighborhood neighborhood =
      new NearestNUserNeighborhood(
          100,
          similarity, model);

  return new GenericUserBasedRecommender(
      model, neighborhood, similarity);
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
/**
 * レコメンデーションを生成して出力
 * @param datamodel
 * @param similarity
 * @param userId
 * @param howMany
 * @throws TasteException
 */
private void recommend(DataModel datamodel, UserSimilarity similarity, UserAffinityVO dto) throws TasteException {
    super.i("◆ " + similarity.getClass());
    similarity.setPreferenceInferrer(new AveragingPreferenceInferrer(datamodel));
    UserNeighborhood neighbor = new NearestNUserNeighborhood(dto.size, similarity, datamodel);
    Recommender recommender = new GenericUserBasedRecommender(datamodel, neighbor, similarity);
    List<RecommendedItem> items = recommender.recommend(dto.userId, dto.howMany);
    for (RecommendedItem item : items) {
        super.i("◆ " + item);
    }
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
/**
 * <b>[推薦の評価方法]</b><br>
 * cf.)70%のデータを使用してレコメンダーを生成→30%のデータを使用して評価
 * @param dataModel
 * @throws TasteException
 */
@Override
public void analyze() throws TasteException {

    super.i("◆ EVAL ======= Start ======");
    super.i("◆ -------------------------");

    final int size = super.dto.size;
    final Map<EvalName, EvaluationVO> evalMap = super.dto.evalMap;

    RandomUtils.useTestSeed();

    /* 実際の評価値と推定値の誤差 */
    // 絶対値を求める=意味平均誤差(mean average error)
    RecommenderEvaluator maeEval = new AverageAbsoluteDifferenceRecommenderEvaluator();
    // 自乗を足し合わせ平方根を取ったRMS(root mean squared)
    RecommenderEvaluator rmsEval = new RMSRecommenderEvaluator();

    RecommenderBuilder builder = new RecommenderBuilder() {

        @Override
        public Recommender buildRecommender(DataModel dataModel) throws TasteException {
            UserSimilarity similarity = new PearsonCorrelationSimilarity(dataModel);
            UserNeighborhood neighborhood = new NearestNUserNeighborhood(size, similarity, dataModel);
            return new GenericUserBasedRecommender(dataModel, neighborhood, similarity);
        }
    };

    // evaluate(RecommenderBuilder, DataModelBuilder, DataModel, 学習用データの割合, 検証用データの割合)
    EvaluationVO mae = evalMap.get(EvalName.MAE);
    EvaluationVO rms = evalMap.get(EvalName.RMS);
    double maeScore = maeEval.evaluate(builder, null, super.dataModel, mae.trainingPercentage, mae.evaluationPercentage);
    double rmsScore = rmsEval.evaluate(builder, null, super.dataModel, rms.trainingPercentage, rms.evaluationPercentage);

    super.i("◆ " + EvalName.MAE.name + " : " + maeScore);
    super.i("◆ " + EvalName.RMS.name + " : " + rmsScore);
    super.i("◆ -------------------------");
    super.iln("◆ EVAL ======= END ======");
}
 

import org.apache.mahout.cf.taste.recommender.Recommender; //导入依赖的package包/类
public List<RecommendedItem> recommend(int userid,int size) throws TasteException, IOException{
		List<RecommendedItem> list = null;
//		MovieDataModel model = new MovieDataModel();
		String file=ServletActionContext.getServletContext().getRealPath("/u1.base");
		DataModel model = new FileDataModel(new File(file));
		Recommender recommender = new CachingRecommender(new SlopeOneRecommender(model));
		list = recommender.recommend(userid, size);
		return list;
	}