Implementation of the NMF policy to act as a wrapper when accessing NMF from within CFType. More...

#include <nmf_method.hpp>

Public Member Functions
template<typename MatType >
void	Apply (const MatType &, const arma::sp_mat &cleanedData, const size_t rank, const size_t maxIterations, const double minResidue, const bool mit)
	Apply Collaborative Filtering to the provided dataset using NMF method. More...

double	GetRating (const size_t user, const size_t item) const
	Return predicted rating given user ID and item ID. More...

void	GetRatingOfUser (const size_t user, arma::vec &rating) const
	Get predicted ratings for a user. More...

template<typename NeighborSearchPolicy >
void	GetNeighborhood (const arma::Col< size_t > &users, const size_t numUsersForSimilarity, arma::Mat< size_t > &neighborhood, arma::mat &similarities) const
	Get the neighborhood and corresponding similarities for a set of users. More...

const arma::mat &	W () const
	Get the Item Matrix.

const arma::mat &	H () const
	Get the User Matrix.

template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialization.

Detailed Description

Implementation of the NMF policy to act as a wrapper when accessing NMF from within CFType.

An example of how to use NMFPolicy in CF is shown below:

extern arma::mat data; // data is a (user, item, rating) table.
// Users for whom recommendations are generated.
extern arma::Col<size_t> users;
arma::Mat<size_t> recommendations; // Resulting recommendations.
CFType<NMFPolicy> cf(data);
// Generate 10 recommendations for all users.
cf.GetRecommendations(10, recommendations);

Member Function Documentation

◆ Apply()

template<typename MatType >

void mlpack::cf::NMFPolicy::Apply	(	const MatType &	,
		const arma::sp_mat &	cleanedData,
		const size_t	rank,
		const size_t	maxIterations,
		const double	minResidue,
		const bool	mit
	)

inline

Apply Collaborative Filtering to the provided dataset using NMF method.

Parameters

*	(data) Data matrix: dense matrix (coordinate lists) or sparse matrix (cleaned).
cleanedData	item user table in form of sparse matrix.
rank	Rank parameter for matrix factorization.
maxIterations	Maximum number of iterations.
minResidue	Residue required to terminate.
mit	Whether to terminate only when maxIterations is reached.

◆ GetNeighborhood()

template<typename NeighborSearchPolicy >

void mlpack::cf::NMFPolicy::GetNeighborhood	(	const arma::Col< size_t > &	users,
		const size_t	numUsersForSimilarity,
		arma::Mat< size_t > &	neighborhood,
		arma::mat &	similarities
	)		const

inline

Get the neighborhood and corresponding similarities for a set of users.

Template Parameters

NeighborSearchPolicy The policy to perform neighbor search.

Parameters

users	Users whose neighborhood is to be computed.
numUsersForSimilarity	The number of neighbors returned for each user.
neighborhood	Neighbors represented by user IDs.
similarities	Similarity between each user and each of its neighbors.

◆ GetRating()

double mlpack::cf::NMFPolicy::GetRating	(	const size_t	user,
		const size_t	item
	)		const

inline

Return predicted rating given user ID and item ID.

Parameters

user	User ID.
item	Item ID.

◆ GetRatingOfUser()

void mlpack::cf::NMFPolicy::GetRatingOfUser	(	const size_t	user,
		arma::vec &	rating
	)		const

inline

Get predicted ratings for a user.

Parameters

user	User ID.
rating	Resulting rating vector.

The documentation for this class was generated from the following file:

src/mlpack/methods/cf/decomposition_policies/nmf_method.hpp

Public Member Functions

Detailed Description

Member Function Documentation

◆ Apply()

◆ GetNeighborhood()

◆ GetRating()

◆ GetRatingOfUser()