基于谷本系数计算相似度

标签：

//这段程序写的是忽略偏好值基于谷本系数计算相似度
//这个算法是基于谷本系数。
//这个值也叫做Jaccard系数，由两个用户共同表达过偏好的物品数目除以至少
//一个用户表达过偏好的物品数目而得（就是两者得交集除以两者得并集）
package byuser;

import java.io.File;
import java.io.IOException;

import org.apache.mahout.cf.taste.common.TasteException;
import org.apache.mahout.cf.taste.eval.RecommenderBuilder;
import org.apache.mahout.cf.taste.eval.RecommenderEvaluator;
import org.apache.mahout.cf.taste.impl.eval.AverageAbsoluteDifferenceRecommenderEvaluator;
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.CachingUserSimilarity;
import org.apache.mahout.cf.taste.impl.similarity.PearsonCorrelationSimilarity;
import org.apache.mahout.cf.taste.impl.similarity.SpearmanCorrelationSimilarity;
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.cf.taste.similarity.precompute.example.GroupLensDataModel;
import org.apache.mahout.math.hadoop.similarity.cooccurrence.measures.TanimotoCoefficientSimilarity;

public class TanimotoCoefficientSimilarityTest {

	public TanimotoCoefficientSimilarityTest() throws IOException, TasteException{
		DataModel model = new GroupLensDataModel(new File("E:\\mahout项目\\examples\\ratings.dat"));
		RecommenderEvaluator evaluator = new AverageAbsoluteDifferenceRecommenderEvaluator();
		RecommenderBuilder recommenderBuilder = new RecommenderBuilder() {
			@Override
			public Recommender buildRecommender(DataModel model) throws TasteException {
				UserSimilarity similarity = new org.apache.mahout.cf.taste.impl.similarity.TanimotoCoefficientSimilarity(model);
				UserNeighborhood neighborhood = new NearestNUserNeighborhood(100, similarity, model);
				return new GenericUserBasedRecommender(model, neighborhood, similarity);
			}
		};
		double score = evaluator.evaluate(recommenderBuilder, null, model, 0.95, 0.05);
		System.out.println("采用偏好基于谷本系数计算相似度的推荐引擎的评测得分是： " + score);
	}
	
	public static void main(String[] args) throws TasteException, IOException {
		// TODO Auto-generated method stub
		TanimotoCoefficientSimilarityTest tt = new TanimotoCoefficientSimilarityTest();
	}

}

结果：

基于谷本系数计算相似度

标签：

原文地址：http://blog.csdn.net/u012965373/article/details/46051321