[mlpack-git] master, mlpack-1.0.x: Patch from Siddharth: make the rank parameterizable, and merge the constructors into one. (ce48c53)
gitdub at big.cc.gt.atl.ga.us
gitdub at big.cc.gt.atl.ga.us
Thu Mar 5 21:44:40 EST 2015
Repository : https://github.com/mlpack/mlpack
On branches: master,mlpack-1.0.x
Link : https://github.com/mlpack/mlpack/compare/904762495c039e345beba14c1142fd719b3bd50e...f94823c800ad6f7266995c700b1b630d5ffdcf40
>---------------------------------------------------------------
commit ce48c53adcbe87512c6d144d52f5fdc46f824e00
Author: Ryan Curtin <ryan at ratml.org>
Date: Sat Feb 22 15:55:19 2014 +0000
Patch from Siddharth: make the rank parameterizable, and merge the constructors
into one.
>---------------------------------------------------------------
ce48c53adcbe87512c6d144d52f5fdc46f824e00
src/mlpack/methods/cf/cf.cpp | 66 +++++++++++++++++---------------------------
src/mlpack/methods/cf/cf.hpp | 56 +++++++++++++++++++------------------
2 files changed, 54 insertions(+), 68 deletions(-)
diff --git a/src/mlpack/methods/cf/cf.cpp b/src/mlpack/methods/cf/cf.cpp
index b9a6ea5..d3248f1 100644
--- a/src/mlpack/methods/cf/cf.cpp
+++ b/src/mlpack/methods/cf/cf.cpp
@@ -21,58 +21,32 @@ namespace cf {
/**
* Construct the CF object.
*/
-CF::CF(arma::mat& data) :
- data(data)
-{
- Log::Info<<"Constructor (param: input data, default: numRecs;neighbourhood)"<<endl;
- this->numRecs = 5;
- this->numUsersForSimilarity = 5;
-
- CleanData();
-}
-
-CF::CF(const size_t numRecs,arma::mat& data) :
- data(data)
+CF::CF(arma::mat& data,
+ const size_t numRecs,
+ const size_t numUsersForSimilarity,
+ const size_t rank) :
+ data(data),
+ numRecs(numRecs),
+ numUsersForSimilarity(numUsersForSimilarity),
+ rank(rank)
{
// Validate number of recommendation factor.
if (numRecs < 1)
{
- Log::Warn << "CF::CF(): number of recommendations shoud be > 0("
+ Log::Warn << "CF::CF(): number of recommendations should be > 0("
<< numRecs << " given). Setting value to 5.\n";
//Setting Default Value of 5
this->numRecs = 5;
}
- else
- this->numRecs = numRecs;
- this->numUsersForSimilarity = 5;
- CleanData();
-}
-
-CF::CF(const size_t numRecs, const size_t numUsersForSimilarity,
- arma::mat& data) :
- data(data)
-{
- // Validate number of recommendation factor.
- if (numRecs < 1)
- {
- Log::Warn << "CF::CF(): number of recommendations shoud be > 0("
- << numRecs << " given). Setting value to 5.\n";
- //Setting Default Value of 5
- this->numRecs = 5;
- }
- else
- this->numRecs = numRecs;
// Validate neighbourhood size.
if (numUsersForSimilarity < 1)
{
- Log::Warn << "CF::CF(): neighbourhood size shoud be > 0("
+ Log::Warn << "CF::CF(): neighbourhood size should be > 0("
<< numUsersForSimilarity << " given). Setting value to 5.\n";
//Setting Default Value of 5
this->numUsersForSimilarity = 5;
}
- else
- this->numUsersForSimilarity = numUsersForSimilarity;
CleanData();
}
@@ -95,13 +69,23 @@ void CF::GetRecommendations(arma::Mat<size_t>& recommendations,
{
// Base function for calculating recommendations.
+ // Check if the user wanted us to choose a rank for them.
+ if (rank == 0)
+ {
+ // This is a simple heuristic that picks a rank based on the density of the
+ // dataset between 5 and 105.
+ const double density = (cleanedData.n_nonzero * 100.0) / cleanedData.n_elem;
+ const size_t rankEstimate = size_t(density) + 5;
+
+ // Set to heuristic value.
+ Log::Info << "No rank given for decomposition; using rank of "
+ << rankEstimate << " calculated by density-based heuristic."
+ << std::endl;
+ rank = rankEstimate;
+ }
+
// Operations independent of the query:
// Decompose the sparse data matrix to user and data matrices.
- // This is a simple heuristic that picks a rank based on the density of the
- // dataset between 5 and 105.
- const double density = (cleanedData.n_nonzero * 100.0) / cleanedData.n_elem;
- size_t rank = size_t(density) + 5;
-
// Presently only ALS (via NMF) is supported as an optimizer. This should be
// converted to a template when more optimizers are available.
NMF<RandomInitialization, WAlternatingLeastSquaresRule,
diff --git a/src/mlpack/methods/cf/cf.hpp b/src/mlpack/methods/cf/cf.hpp
index f244363..798306e 100644
--- a/src/mlpack/methods/cf/cf.hpp
+++ b/src/mlpack/methods/cf/cf.hpp
@@ -55,35 +55,23 @@ class CF
{
public:
/**
- * Create a CF object and (optionally) set the parameters with which
- * collaborative filtering will be run.
+ * Initialize the CF object. Store a reference to the data that we
+ * will be using. There are parameters that can be set; default values
+ * are provided for each of them. If the rank is left unset (or is set to 0),
+ * a simple density-based heuristic will be used to choose a rank.
*
- * @param data Initial (user,item,rating) matrix.
+ * @param data Initial (user, item, rating) matrix.
* @param numRecs Desired number of recommendations for each user.
* @param numUsersForSimilarity Size of the neighborhood.
+ * @param rank Rank parameter for matrix factorization.
*/
- CF(const size_t numRecs,const size_t numUsersForSimilarity,
- arma::mat& data);
-
- /**
- * Create a CF object and (optionally) set the parameters which CF
- * will be run with.
- *
- * @param data Initial User,Item,Rating Matrix
- * @param numRecs Number of Recommendations for each user.
- */
- CF(const size_t numRecs, arma::mat& data);
-
- /**
- * Create a CF object and (optionally) set the parameters which CF
- * will be run with.
- *
- * @param data Initial User,Item,Rating Matrix
- */
- CF(arma::mat& data);
+ CF(arma::mat& data,
+ const size_t numRecs = 5,
+ const size_t numUsersForSimilarity = 5,
+ const size_t rank = 0);
//! Sets number of Recommendations.
- void NumRecs(size_t recs)
+ void NumRecs(const size_t recs)
{
if (recs < 1)
{
@@ -101,7 +89,7 @@ class CF
}
//! Sets number of user for calculating similarity.
- void NumUsersForSimilarity(size_t num)
+ void NumUsersForSimilarity(const size_t num)
{
if (num < 1)
{
@@ -112,12 +100,24 @@ class CF
this->numUsersForSimilarity = num;
}
- //! Gets number of users for calculating similarity/
+ //! Gets number of users for calculating similarity.
size_t NumUsersForSimilarity()
{
return numUsersForSimilarity;
}
+ //! Sets rank parameter for matrix factorization.
+ void Rank(const size_t rankValue)
+ {
+ this->rank = rankValue;
+ }
+
+ //! Gets rank parameter for matrix factorization.
+ size_t Rank()
+ {
+ return rank;
+ }
+
//! Get the User Matrix.
const arma::mat& W() const { return w; }
//! Get the Item Matrix.
@@ -174,18 +174,20 @@ class CF
std::string ToString() const;
private:
+ //! Initial data matrix.
+ arma::mat data;
//! Number of recommendations.
size_t numRecs;
//! Number of users for similarity.
size_t numUsersForSimilarity;
+ //! Rank used for matrix factorization.
+ size_t rank;
//! User matrix.
arma::mat w;
//! Item matrix.
arma::mat h;
//! Rating matrix.
arma::mat rating;
- //! Initial data matrix.
- arma::mat data;
//! Cleaned data matrix.
arma::sp_mat cleanedData;
//! Converts the User, Item, Value Matrix to User-Item Table
More information about the mlpack-git
mailing list