org.grouplens.lenskit.basic

Class AbstractRatingPredictor

java.lang.Object

org.grouplens.lenskit.basic.AbstractRatingPredictor

All Implemented Interfaces:

RatingPredictor

Direct Known Subclasses:

KnownRatingRatingPredictor, OrdRecRatingPredictor, QuantizedRatingPredictor, SimpleRatingPredictor

public abstract class AbstractRatingPredictor
extends Object
implements RatingPredictor

Base class to make rating predictors easier to implement. Delegates all predict methods to RatingPredictor.predict(long, MutableSparseVector).

Constructor Summary

Constructors

Constructor and Description
AbstractRatingPredictor()

Method Summary

Modifier and Type	Method and Description
SparseVector	predict(long user, Collection<Long> items) Predict the user's preference for a collection of items.
double	predict(long user, long item) Predict a user's rating for a single item.

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.grouplens.lenskit.RatingPredictor

predict

Constructor Detail

AbstractRatingPredictor

public AbstractRatingPredictor()

Method Detail

predict

@Nonnull
public SparseVector predict(long user,
                                     @Nonnull
                                     Collection<Long> items)

Predict the user's preference for a collection of items.

Delegates to RatingPredictor.predict(long, MutableSparseVector).

Specified by:

predict in interface RatingPredictor

Parameters:

user - The user ID for whom to generate predicts.

items - The items to predict for.

Returns:

A mapping from item IDs to predicted preference. This mapping may not contain all requested items.

predict

public double predict(long user,
                      long item)

Predict a user's rating for a single item.

Delegates to predict(long, java.util.Collection).

Specified by:

predict in interface RatingPredictor

Parameters:

user - The user ID for whom to generate a prediction.

item - The item ID whose rating is to be predicted.

Returns:

The predicted preference, or Double.NaN if no preference can be predicted.