es.upm.etsisi.cf4j.recommender.knn

Class ItemKNN

java.lang.Object

es.upm.etsisi.cf4j.recommender.Recommender

es.upm.etsisi.cf4j.recommender.knn.ItemKNN

public class ItemKNN
extends Recommender

Implements item-to-item KNN based collaborative filtering

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	ItemKNN.AggregationApproach Available aggregation approaches to merge k-nearest neighbors ratings

Field Summary

Fields

Modifier and Type	Field and Description
protected ItemKNN.AggregationApproach	aggregationApproach Aggregation approach used to aggregate k-nearest neighbors ratings
protected ItemSimilarityMetric	metric Similarity metric to compute the similarity between two items
protected int[][]	neighbors Contains the neighbors indexes of each item
protected int	numberOfNeighbors Number of neighbors (k)

Fields inherited from class es.upm.etsisi.cf4j.recommender.Recommender

datamodel

Constructor Summary

Constructors

Constructor and Description
ItemKNN(DataModel datamodel, int numberOfNeighbors, ItemSimilarityMetric metric, ItemKNN.AggregationApproach aggregationApproach) Recommender constructor
ItemKNN(DataModel datamodel, Map<String,Object> params) Recommender constructor from a Map containing the recommender's hyper-parameters values.

Method Summary

Modifier and Type	Method and Description
void	fit() Estimates model parameters given the hyper-parameters
double	predict(int userIndex, int itemIndex) Computes a rating prediction
String	toString()

Methods inherited from class es.upm.etsisi.cf4j.recommender.Recommender

getDataModel, predict

Methods inherited from class java.lang.Object

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

Field Detail

numberOfNeighbors

protected int numberOfNeighbors

Number of neighbors (k)

metric

protected ItemSimilarityMetric metric

Similarity metric to compute the similarity between two items

aggregationApproach

protected ItemKNN.AggregationApproach aggregationApproach

Aggregation approach used to aggregate k-nearest neighbors ratings

neighbors

protected int[][] neighbors

Contains the neighbors indexes of each item

Constructor Detail

ItemKNN

public ItemKNN(DataModel datamodel,
               Map<String,Object> params)

Recommender constructor from a Map containing the recommender's hyper-parameters values. Map object must contains the following keys:

• numberOfNeighbors: int value with the number of neighbors.
• metric:: ItemSimilarityMetric instance with the similarity metric to compute the similarity between two items.
• aggregationApproach: ItemKNN.AggregationApproach instance with the aggregation approach used to aggregate k-nearest neighbors ratings.

Parameters:

datamodel - DataModel instance

params - Recommender's hyper-parameters values

ItemKNN

public ItemKNN(DataModel datamodel,
               int numberOfNeighbors,
               ItemSimilarityMetric metric,
               ItemKNN.AggregationApproach aggregationApproach)

Recommender constructor

Parameters:

datamodel - DataModel instance

numberOfNeighbors - Number of neighbors (k)

metric - Similarity metric to compute the similarity between two items

aggregationApproach - Aggregation approach used to aggregate k-nearest neighbors ratings

Method Detail

fit

public void fit()

Description copied from class: Recommender

Estimates model parameters given the hyper-parameters

Specified by:

fit in class Recommender

predict

public double predict(int userIndex,
                      int itemIndex)

Description copied from class: Recommender

Computes a rating prediction

Specified by:

predict in class Recommender

Parameters:

userIndex - Index of the user in the array of Users of the DataModel instance

itemIndex - Index of the item in the array of Items of the DataModel instance

Returns:

Prediction

toString

public String toString()

Overrides:

toString in class Object