org.lenskit.knn.item

Class ItemItemScorer

java.lang.Object

org.lenskit.basic.AbstractItemScorer

org.lenskit.knn.item.ItemItemScorer

All Implemented Interfaces:

ItemScorer

public class ItemItemScorer
extends AbstractItemScorer

Score items using an item-item CF model. User ratings are not supplied as default preferences.

Field Summary

Fields

Modifier and Type	Field and Description
protected ItemItemModel	model
protected UserVectorNormalizer	normalizer
protected NeighborhoodScorer	scorer

Constructor Summary

Constructors

Constructor and Description
ItemItemScorer(RatingVectorPDAO dao, ItemItemModel m, NeighborhoodScorer scorer, UserVectorNormalizer norm, int nnbrs, int min) Construct a new item-item scorer.

Method Summary

Modifier and Type	Method and Description
UserVectorNormalizer	getNormalizer()
java.util.Map<java.lang.Long,java.lang.Double>	score(long user, java.util.Collection<java.lang.Long> items) Score a collection of items.
protected void	scoreItem(Long2DoubleMap userData, long item, ItemItemScoreAccumulator accum)
ResultMap	scoreWithDetails(long user, java.util.Collection<java.lang.Long> items) Score items by computing predicted ratings.

Methods inherited from class org.lenskit.basic.AbstractItemScorer

score

Methods inherited from class java.lang.Object

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

Field Detail

model

protected final ItemItemModel model

normalizer

@Nonnull
protected final UserVectorNormalizer normalizer

scorer

@Nonnull
protected final NeighborhoodScorer scorer

Constructor Detail

ItemItemScorer

@Inject
public ItemItemScorer(RatingVectorPDAO dao,
                              ItemItemModel m,
                              NeighborhoodScorer scorer,
                              UserVectorNormalizer norm,
                              @NeighborhoodSize
                              int nnbrs,
                              @MinNeighbors
                              int min)

Construct a new item-item scorer.

Parameters:

dao - The rating vector DAO.

m - The model

scorer - The neighborhood scorer.

nnbrs - The number of neighbors.

min - The minimum number of neighbors.

Method Detail

getNormalizer

@Nonnull
public UserVectorNormalizer getNormalizer()

score

@Nonnull
public java.util.Map<java.lang.Long,java.lang.Double> score(long user,
                                                                     @Nonnull
                                                                     java.util.Collection<java.lang.Long> items)

Description copied from class: AbstractItemScorer

Score a collection of items.

This implementation delegates to ItemScorer.scoreWithDetails(long, Collection).

Specified by:

score in interface ItemScorer

Overrides:

score in class AbstractItemScorer

Parameters:

user - The user ID for whom to generate scores.

items - The item to score.

Returns:

The scores for the items. This result set may not contain all requested items.

scoreWithDetails

@Nonnull
public ResultMap scoreWithDetails(long user,
                                           @Nonnull
                                           java.util.Collection<java.lang.Long> items)

Score items by computing predicted ratings.

Parameters:

user - The user ID for whom to generate scores.

items - The item to score.

Returns:

The scores for the items. This result set may not contain all requested items. Implementations that support additional details will return a subclass of ResultMap that provides access to those details.

scoreItem

protected void scoreItem(Long2DoubleMap userData,
                         long item,
                         ItemItemScoreAccumulator accum)