org.apache.spark.graphx.lib

Class SVDPlusPlus

java.lang.Object

org.apache.spark.graphx.lib.SVDPlusPlus

public class SVDPlusPlus
extends java.lang.Object

Implementation of SVD++ algorithm.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	SVDPlusPlus.Conf Configuration parameters for SVDPlusPlus.

Constructor Summary

Constructors

Constructor and Description
SVDPlusPlus()

Method Summary

Methods

Modifier and Type	Method and Description
static scala.Tuple2<Graph<scala.Tuple4<double[],double[],java.lang.Object,java.lang.Object>,java.lang.Object>,java.lang.Object>	run(RDD<Edge<java.lang.Object>> edges, SVDPlusPlus.Conf conf) Implement SVD++ based on "Factorization Meets the Neighborhood: a Multifaceted Collaborative Filtering Model", available at http://public.research.att.com/~volinsky/netflix/kdd08koren.pdf.
static scala.Tuple2<Graph<scala.Tuple4<double[],double[],java.lang.Object,java.lang.Object>,java.lang.Object>,java.lang.Object>	runSVDPlusPlus(RDD<Edge<java.lang.Object>> edges, SVDPlusPlus.Conf conf) This method is now replaced by the updated version of run() and returns exactly the same result.

Methods inherited from class java.lang.Object

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

Constructor Detail

SVDPlusPlus

public SVDPlusPlus()

Method Detail

runSVDPlusPlus

public static scala.Tuple2<Graph<scala.Tuple4<double[],double[],java.lang.Object,java.lang.Object>,java.lang.Object>,java.lang.Object> runSVDPlusPlus(RDD<Edge<java.lang.Object>> edges,
                                                                                                                                      SVDPlusPlus.Conf conf)

This method is now replaced by the updated version of run() and returns exactly the same result.

Parameters:

edges - (undocumented)

conf - (undocumented)

Returns:

(undocumented)

run

public static scala.Tuple2<Graph<scala.Tuple4<double[],double[],java.lang.Object,java.lang.Object>,java.lang.Object>,java.lang.Object> run(RDD<Edge<java.lang.Object>> edges,
                                                                                                                           SVDPlusPlus.Conf conf)

Implement SVD++ based on "Factorization Meets the Neighborhood: a Multifaceted Collaborative Filtering Model", available at http://public.research.att.com/~volinsky/netflix/kdd08koren.pdf.

The prediction rule is rui = u + bu + bi + qi*(pu + |N(u)|^^-0.5^^*sum(y)), see the details on page 6.

Parameters:

edges - edges for constructing the graph

conf - SVDPlusPlus parameters

Returns:

a graph with vertex attributes containing the trained model