Examples of org.apache.mahout.cf.taste.eval.RecommenderEvaluator.evaluate()

Class org.apache.mahout.cf.taste.eval.RecommenderEvaluator

Examples of org.apache.mahout.cf.taste.eval.RecommenderEvaluator.evaluate()

org.apache.mahout.cf.taste.eval.RecommenderEvaluator.evaluate()

Evaluates the quality of a {@link org.apache.mahout.cf.taste.recommender.Recommender}'s recommendations. The range of values that may be returned depends on the implementation, but lower values must mean better recommendations, with 0 being the lowest / best possible evaluation, meaning a perfect match. This method does not accept a {@link org.apache.mahout.cf.taste.recommender.Recommender} directly, butrather a {@link RecommenderBuilder} which can build the{@link org.apache.mahout.cf.taste.recommender.Recommender} to test on top of a given {@link DataModel}.

Implementations will take a certain percentage of the preferences supplied by the given {@link DataModel}as "training data". This is typically most of the data, like 90%. This data is used to produce recommendations, and the rest of the data is compared against estimated preference values to see how much the {@link org.apache.mahout.cf.taste.recommender.Recommender}'s predicted preferences match the user's real preferences. Specifically, for each user, this percentage of the user's ratings are used to produce recommendatinos, and for each user, the remaining preferences are compared against the user's real preferences.

For large datasets, it may be desirable to only evaluate based on a small percentage of the data. evaluationPercentage controls how many of the {@link DataModel}'s users are used in evaluation.

To be clear, trainingPercentage and evaluationPercentage are not related. They do not need to add up to 1.0, for example.
@param recommenderBuilder object that can build a {@link org.apache.mahout.cf.taste.recommender.Recommender} to test @param dataModelBuilder @param dataModelBuilder {@link DataModelBuilder} to use, or if null, a default {@link DataModel}implementation will be used @param dataModel dataset to test on @param trainingPercentage percentage of each user's preferences to use to produce recommendations; the rest are compared to estimated preference values to evaluate {@link org.apache.mahout.cf.taste.recommender.Recommender} performance @param evaluationPercentage percentage of users to use in evaluation @return a "score" representing how well the {@link org.apache.mahout.cf.taste.recommender.Recommender}'s estimated preferences match real values; lower scores mean a better match and 0 is a perfect match @throws TasteException if an error occurs while accessing the {@link DataModel}

        return new SlopeOneRecommender(dataModel);
      }
    };
    RecommenderEvaluator evaluator =
        new AverageAbsoluteDifferenceRecommenderEvaluator();
    double eval = evaluator.evaluate(builder, null, model, 0.85, 1.0);
    assertEquals(0.3833333055178324, eval, EPSILON);
  }


}

View Full Code Here

  public static void main(String... args) throws IOException, TasteException, OptionException {
    RecommenderEvaluator evaluator = new AverageAbsoluteDifferenceRecommenderEvaluator();
    File ratingsFile = TasteOptionParser.getRatings(args);
    if (ratingsFile != null) {
      DataModel model = new NetflixDataModel(ratingsFile, true);
      double evaluation = evaluator.evaluate(new NetflixRecommenderBuilder(), null, model, 0.9, 0.1);
      log.info(String.valueOf(evaluation));
    } else {
      log.error("Netflix Recommender needs a ratings file to work. Please provide it with the -i command line option.");
    }
  }

View Full Code Here

  }


  public static void main(String... args) throws IOException, TasteException {
    RecommenderEvaluator evaluator = new AverageAbsoluteDifferenceRecommenderEvaluator();
    BookCrossingDataModel model = new BookCrossingDataModel();
    double evaluation = evaluator.evaluate(new BookCrossingRecommenderBuilder(model),
                                                 model,
                                                 0.9,
                                                 0.1);
    log.info(String.valueOf(evaluation));
  }

View Full Code Here

  }


  public static void main(String... args) throws IOException, TasteException {
    RecommenderEvaluator evaluator = new AverageAbsoluteDifferenceRecommenderEvaluator();
    DataModel model = new JesterDataModel();
    double evaluation = evaluator.evaluate(new JesterRecommenderBuilder(),
                                                 model,
                                                 0.9,
                                                 1.0);
    log.info(String.valueOf(evaluation));
  }

View Full Code Here

    // do nothing
  }


  public static void main(String... args) throws IOException, TasteException {
    RecommenderEvaluator evaluator = new AverageAbsoluteDifferenceRecommenderEvaluator();
    double evaluation = evaluator.evaluate(new GroupLensRecommenderBuilder(),
                                                 new GroupLensDataModel(),
                                                 0.9,
                                                 0.1);
    log.info(String.valueOf(evaluation));
  }

View Full Code Here

  }


  public static void main(String... args) throws IOException, TasteException {
    RecommenderEvaluator evaluator = new AverageAbsoluteDifferenceRecommenderEvaluator();
    DataModel model = new NetflixDataModel(new File(args[0]), true);
    double evaluation = evaluator.evaluate(new NetflixRecommenderBuilder(), model, 0.9, 0.1);
    log.info(String.valueOf(evaluation));
  }


}

View Full Code Here

        return new SlopeOneRecommender(dataModel);
      }
    };
    RecommenderEvaluator evaluator =
            new AverageAbsoluteDifferenceRecommenderEvaluator();
    double eval = evaluator.evaluate(builder, model, 0.85, 1.0);
    assertEquals(0.2234257618121795, eval, EPSILON);
  }


}

View Full Code Here

      public Recommender buildRecommender(DataModel dataModel) throws TasteException {
        return new SlopeOneRecommender(dataModel);
      }
    };
    RecommenderEvaluator evaluator = new RMSRecommenderEvaluator();
    double eval = evaluator.evaluate(builder, model, 0.85, 1.0);
    assertEquals(0.3004147161079469, eval, EPSILON);
  }


}

View Full Code Here

  
  public static void main(String... args) throws IOException, TasteException, OptionException {
    RecommenderEvaluator evaluator = new AverageAbsoluteDifferenceRecommenderEvaluator();
    File ratingsFile = TasteOptionParser.getRatings(args);
    DataModel model = ratingsFile == null ? new JesterDataModel() : new JesterDataModel(ratingsFile);
    double evaluation = evaluator.evaluate(new JesterRecommenderBuilder(),
      null,
      model,
      0.9,
      0.3);
    log.info(String.valueOf(evaluation));

View Full Code Here

    RecommenderEvaluator evaluator = new AverageAbsoluteDifferenceRecommenderEvaluator();
    File ratingsFile = TasteOptionParser.getRatings(args);
    DataModel model =
        ratingsFile == null ? new BookCrossingDataModel(false) : new BookCrossingDataModel(ratingsFile, false);


    double evaluation = evaluator.evaluate(new BookCrossingRecommenderBuilder(),
      null,
      model,
      0.9,
      0.3);
    log.info(String.valueOf(evaluation));

View Full Code Here

0 1 2

TOP

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.