org.lenskit.eval.traintest.recommend

Class TopNNDPMMetric

java.lang.Object

org.lenskit.eval.traintest.metrics.Metric<X>

org.lenskit.eval.traintest.recommend.TopNMetric<X>

org.lenskit.eval.traintest.recommend.ListOnlyTopNMetric<MeanAccumulator>

org.lenskit.eval.traintest.recommend.TopNNDPMMetric

public class TopNNDPMMetric
extends ListOnlyTopNMetric<MeanAccumulator>

Measure the nDPM of the top-N recommendations, using rankings. This metric is registered with the type name ndpm. The paper used as a reference for this implementation is http://www2.cs.uregina.ca/~yyao/PAPERS/jasis_ndpm.pdf.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	TopNNDPMMetric.Spec Specification for configuring nDPM metrics.

Field Summary

Fields

Modifier and Type	Field and Description
static String	DEFAULT_COLUMN

Constructor Summary

Constructors

Constructor and Description
TopNNDPMMetric(String name) Construct a new nDPM Top-N metric.
TopNNDPMMetric(TopNNDPMMetric.Spec spec) Construct a top-N nDCG metric from a spec.

Method Summary

Modifier and Type	Method and Description
MeanAccumulator	createContext(AlgorithmInstance algorithm, DataSet dataSet, Recommender recommender) Create the context for an experimental condition (algorithm/data set pair).
MetricResult	getAggregateMeasurements(MeanAccumulator context) Get the aggregate results from an accumulator.
MetricResult	measureUser(TestUser user, int targetLength, LongList recommendations, MeanAccumulator context) Measurement method that only uses the recommend list.

Methods inherited from class org.lenskit.eval.traintest.recommend.ListOnlyTopNMetric

measureUser

Methods inherited from class org.lenskit.eval.traintest.metrics.Metric

getAggregateColumnLabels, getColumnLabels, getRequiredRoots

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT_COLUMN

public static final String DEFAULT_COLUMN

See Also:

Constant Field Values

Constructor Detail

TopNNDPMMetric

public TopNNDPMMetric(TopNNDPMMetric.Spec spec)

Construct a top-N nDCG metric from a spec.

Parameters:

spec - The spec.

TopNNDPMMetric

public TopNNDPMMetric(String name)

Construct a new nDPM Top-N metric.

Method Detail

createContext

@Nullable
public MeanAccumulator createContext(AlgorithmInstance algorithm,
                                                DataSet dataSet,
                                                Recommender recommender)

Description copied from class: Metric

Create the context for an experimental condition (algorithm/data set pair). The default implementation returns null.

Overrides:

createContext in class Metric<MeanAccumulator>

Parameters:

algorithm - The algorithm.

dataSet - The data set.

recommender - The LensKit recommender, if applicable. This can be null for an external algorithm that does not provide a LensKit recommender.

Returns:

The accumulator. This will be passed to the individual measurement methods. If the metric does need to accumulate any results, this method can return null.

getAggregateMeasurements

@Nonnull
public MetricResult getAggregateMeasurements(MeanAccumulator context)

Description copied from class: Metric

Get the aggregate results from an accumulator. The default implementation returns MetricResult.empty().

Overrides:

getAggregateMeasurements in class Metric<MeanAccumulator>

Parameters:

context - The context for an experimental condition.

Returns:

The aggregate results from the accumulator.

measureUser

@Nonnull
public MetricResult measureUser(TestUser user,
                                          int targetLength,
                                          LongList recommendations,
                                          MeanAccumulator context)

Description copied from class: ListOnlyTopNMetric

Measurement method that only uses the recommend list.

Specified by:

measureUser in class ListOnlyTopNMetric<MeanAccumulator>

Parameters:

user - The user.

targetLength - The target list length.

recommendations - The list of recommendations.

context - The context.

Returns:

The results of measuring this user.