Examples of org.apache.mahout.cf.taste.impl.similarity.PearsonCorrelationSimilarity

Package org.apache.mahout.cf.taste.impl.similarity

Examples of org.apache.mahout.cf.taste.impl.similarity.PearsonCorrelationSimilarity

org.apache.mahout.cf.taste.impl.similarity.PearsonCorrelationSimilarity
An implementation of the Pearson correlation. For users X and Y, the following values are calculated:
- sumX2: sum of the square of all X's preference values
- sumY2: sum of the square of all Y's preference values
- sumXY: sum of the product of X and Y's preference value for all items for which both X and Y express a preference
The correlation is then:
sumXY / sqrt(sumX2 * sumY2)

Note that this correlation "centers" its data, shifts the user's preference values so that each of their means is 0. This is necessary to achieve expected behavior on all data sets.

This correlation implementation is equivalent to the cosine measure correlation since the data it receives is assumed to be centered -- mean is 0. The correlation may be interpreted as the cosine of the angle between the two vectors defined by the users' preference values.

  public static class MyRecommendBuilder implements RecommenderBuilder {
    @Override
    public Recommender buildRecommender(DataModel model)
        throws TasteException {
      UserSimilarity similarity =
          new PearsonCorrelationSimilarity(model);


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

View Full Code Here

    assertEquals(0, mostSimilar.length);
  }


  private static UserBasedRecommender buildRecommender() throws TasteException {
    DataModel dataModel = getDataModel();
    UserSimilarity similarity = new PearsonCorrelationSimilarity(dataModel);
    UserNeighborhood neighborhood = new NearestNUserNeighborhood(2, similarity, dataModel);
    return new GenericUserBasedRecommender(dataModel, neighborhood, similarity);
  }

View Full Code Here

                    {0.2, 0.3, 0.3, 0.6},
                    {0.4, 0.4, 0.5, 0.9},
                    {0.1, 0.4, 0.5, 0.8, 0.9, 1.0},
                    {0.2, 0.3, 0.6, 0.7, 0.1, 0.2},
            });
    UserSimilarity similarity = new PearsonCorrelationSimilarity(dataModel);
    UserNeighborhood neighborhood = new NearestNUserNeighborhood(2, similarity, dataModel);
    Recommender recommender = new GenericUserBasedRecommender(dataModel, neighborhood, similarity);
    List<RecommendedItem> fewRecommended = recommender.recommend(1, 2);
    List<RecommendedItem> moreRecommended = recommender.recommend(1, 4);
    for (int i = 0; i < fewRecommended.size(); i++) {

View Full Code Here

            new Double[][] {
                    {0.1, 0.2},
                    {0.2, 0.3, 0.3, 0.6},
                    {0.4, 0.5, 0.5, 0.9},
            });
    UserSimilarity similarity = new PearsonCorrelationSimilarity(dataModel);
    UserNeighborhood neighborhood = new NearestNUserNeighborhood(2, similarity, dataModel);
    Recommender recommender = new GenericUserBasedRecommender(dataModel, neighborhood, similarity);
    List<RecommendedItem> originalRecommended = recommender.recommend(1, 2);
    List<RecommendedItem> rescoredRecommended =
        recommender.recommend(1, 2, new ReversingRescorer<Long>());

View Full Code Here

            new Double[][] {
                    {0.1, 0.2},
                    {0.2, 0.3, 0.3, 0.6},
                    {0.4, 0.5, 0.5, 0.9},
            });
    UserSimilarity similarity = new PearsonCorrelationSimilarity(dataModel);
    UserNeighborhood neighborhood = new NearestNUserNeighborhood(2, similarity, dataModel);
    Recommender recommender = new GenericUserBasedRecommender(dataModel, neighborhood, similarity);
    List<RecommendedItem> originalRecommended = recommender.recommend(1, 4, null, true);
    List<RecommendedItem> rescoredRecommended = recommender.recommend(1, 4, new ReversingRescorer<Long>(), true);
    assertNotNull(originalRecommended);

View Full Code Here

                    {0.1, 0.2},
                    {0.2, 0.3, 0.3, 0.6},
                    {0.4, 0.4, 0.5, 0.9},
                    {null, null, null, null, 1.0},
            });
    UserSimilarity similarity = new PearsonCorrelationSimilarity(dataModel);
    UserNeighborhood neighborhood = new NearestNUserNeighborhood(3, similarity, dataModel);
    UserBasedRecommender recommender = new GenericUserBasedRecommender(dataModel, neighborhood, similarity);
    long[] mostSimilar = recommender.mostSimilarUserIDs(4, 3);
    assertNotNull(mostSimilar);
    assertEquals(0, mostSimilar.length);

View Full Code Here

0 1 2 3 4 5 6 7

TOP

Related Classes of org.apache.mahout.cf.taste.impl.similarity.PearsonCorrelationSimilarity

com.manning.hip.ch9.MovieUserEvaluator$MyRecommendBuilder

com.manning.hip.ch9.MovieUserRecommender

de.apaxo.bedcon.AnimalFoodRecommender

mia.recommender.ch02.EvaluatorIntro

mia.recommender.ch02.IREvaluatorIntro

mia.recommender.ch03.IREvaluatorBooleanPrefIntro1

mia.recommender.ch04.GroupLens10MEvalIntro

mia.recommender.ch04.GroupLensDataModelIntro

org.apache.mahout.cf.taste.example.bookcrossing.BookCrossingRecommender

org.apache.mahout.cf.taste.impl.LoadTest

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.