org.grouplens.lenskit.basic

Class SimpleRatingPredictor

java.lang.Object

org.grouplens.lenskit.basic.AbstractRatingPredictor

org.grouplens.lenskit.basic.SimpleRatingPredictor

All Implemented Interfaces:

ItemScorer, RatingPredictor

public final class SimpleRatingPredictor
extends AbstractRatingPredictor

Basic RatingPredictor backed by an ItemScorer. The scores are clamped to the preference domain but otherwise unmodified.

If a baseline predictor is provided, then it is used to supply predictions that the item scorer could not.

This class has a provider SimpleRatingPredictor.Provider that is the default provider for RatingPredictor.

Since:

1.1

Author:

GroupLens Research

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	SimpleRatingPredictor.Provider An intelligent provider for simple rating predictors.

Field Summary

Fields inherited from class org.grouplens.lenskit.basic.AbstractRatingPredictor

dao

Constructor Summary

Constructors

Constructor and Description
SimpleRatingPredictor(DataAccessObject dao, ItemScorer scorer, BaselinePredictor baseline, PreferenceDomain domain)

Method Summary

Methods

Modifier and Type	Method and Description
BaselinePredictor	getBaselinePredictor() Get the baseline predictor.
PreferenceDomain	getPreferenceDomain() Get the preference domain.
ItemScorer	getScorer() Get the backing scorer.
void	predict(long user, MutableSparseVector scores) Predict for items in a vector.
void	predict(UserHistory<? extends Event> profile, MutableSparseVector predictions) Predict for items in a vector.

Methods inherited from class org.grouplens.lenskit.basic.AbstractRatingPredictor

canUseHistory, getUserHistory, predict, predict, predict, predict, score, score, score, score, score, score

Methods inherited from class java.lang.Object

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

Constructor Detail

SimpleRatingPredictor

@Inject
public SimpleRatingPredictor(DataAccessObject dao,
                            ItemScorer scorer,
                            @Nullable
                            BaselinePredictor baseline,
                            @Nullable
                            PreferenceDomain domain)

Method Detail

getScorer

public ItemScorer getScorer()

Get the backing scorer.

Returns:

The item scorer.

getPreferenceDomain

@Nullable
public PreferenceDomain getPreferenceDomain()

Get the preference domain.

Returns:

The preference domain

getBaselinePredictor

@Nullable
public BaselinePredictor getBaselinePredictor()

Get the baseline predictor.

Returns:

The baseline predictor, or null if no baseline is configured.

predict

public void predict(long user,
           @Nonnull
           MutableSparseVector scores)

Description copied from class: AbstractRatingPredictor

Predict for items in a vector. The key domain of the provided vector is the items whose predictions are requested, and the predict method sets the values for each item to its predict (or unsets it, if no prediction can be provided). The previous values are discarded.

Delegates to RatingPredictor.predict(org.grouplens.lenskit.data.UserHistory, MutableSparseVector), with a history retrieved from the DAO.

Specified by:

predict in interface RatingPredictor

Overrides:

predict in class AbstractRatingPredictor

Parameters:

user - The user ID.

scores - The score vector.

See Also:

AbstractRatingPredictor.getUserHistory(long)

predict

public void predict(@Nonnull
           UserHistory<? extends Event> profile,
           @Nonnull
           MutableSparseVector predictions)

Description copied from interface: RatingPredictor

Predict for items in a vector. The key domain of the provided vector is the items whose ratings should be predicted, and the predict method sets the values for each item to its predict (or unsets it, if no prediction can be provided). The previous values are discarded.

If the user has rated any items to be predicted, the algorithm should not just use their rating as the predict — it should compute a predict in the normal fashion. If client code wants to substitute ratings, it is easy to do so as a separate step or wrapper interface.

Parameters:

profile - The user history.

predictions - The prediction output vector.