prea.recommender.baseline
Class Average

java.lang.Object
  prea.recommender.baseline.BaselineRecommender
      prea.recommender.baseline.Average

All Implemented Interfaces:

Recommender

public class Average
extends BaselineRecommender

The class implementing a baseline, predicting by overall average of training set ratings.

Since:

2012. 4. 20

Version:

1.1

Author:

Joonseok Lee

Field Summary

private double

constantValue The value which will be used for predicting all ratings.

Fields inherited from class prea.recommender.baseline.BaselineRecommender

itemCount, maxValue, minValue, rateMatrix, userCount

Constructor Summary

Average(int uc, int ic, double max, double min)
Construct a constant model with the given data.

Method Summary

void	buildModel(SparseMatrix rm) Build a model with given training set.
double	predict(int userId, int itemId) Predict a rating for the given user and item.

Methods inherited from class prea.recommender.baseline.BaselineRecommender

evaluate

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

constantValue

private double constantValue

The value which will be used for predicting all ratings.

Constructor Detail

Average

public Average(int uc,
               int ic,
               double max,
               double min)

Construct a constant model with the given data.

Parameters:

uc - The number of users in the dataset.

ic - The number of items in the dataset.

max - The maximum rating value in the dataset.

min - The minimum rating value in the dataset.

Method Detail

buildModel

public void buildModel(SparseMatrix rm)

Build a model with given training set.

Specified by:

buildModel in interface Recommender

Overrides:

buildModel in class BaselineRecommender

Parameters:

rm - Training data set.

predict

public double predict(int userId,
                      int itemId)

Predict a rating for the given user and item.

Specified by:

predict in class BaselineRecommender

Parameters:

userId - The target user.

itemId - The target item.

Returns:

predicted rating.