public string RunNMFbasedOMF(int maxEpoch, double learnRate, double regularization, int factorCount,
List <double> quantizer, int topN = 0)
{
if (!ReadyForNumerical)
{
GetReadyForNumerical();
}
StringBuilder log = new StringBuilder();
log.AppendLine(Utils.PrintHeading("NMF based OMF"));
// NMF Prediction
// Get ratings from scorer, for both train and test
// R_all contains indexes of all ratings both train and test
DataMatrix R_all = new DataMatrix(R_unknown.UserCount, R_unknown.ItemCount);
R_all.MergeNonOverlap(R_unknown);
R_all.MergeNonOverlap(R_train.IndexesOfNonZeroElements());
Utils.StartTimer();
DataMatrix R_predictedByNMF = NMF.PredictRatings(R_train, R_all, maxEpoch,
learnRate, regularization, factorCount);
log.AppendLine(Utils.StopTimer());
// OMF Prediction
log.AppendLine(Utils.PrintHeading("Ordinal Matrix Factorization with NMF as scorer"));
Utils.StartTimer();
Dictionary <Tuple <int, int>, List <double> > OMFDistributionByUserItem;
DataMatrix R_predicted;
log.AppendLine(OMF.PredictRatings(R_train.Matrix, R_unknown.Matrix, R_predictedByNMF.Matrix,
quantizer, out R_predicted, out OMFDistributionByUserItem));
log.AppendLine(Utils.StopTimer());
// Numerical Evaluation
log.AppendLine(Utils.PrintValue("RMSE", RMSE.Evaluate(R_test, R_predicted).ToString("0.0000")));
log.AppendLine(Utils.PrintValue("MAE", MAE.Evaluate(R_test, R_predicted).ToString("0.0000")));
// TopN Evaluation
if (topN != 0)
{
var topNItemsByUser = ItemRecommendationCore.GetTopNItemsByUser(R_predicted, topN);
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("NCDG@" + n, NCDG.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000")));
}
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("MAP@" + n, MAP.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000")));
}
}
// Save OMFDistribution to file
if (!File.Exists(GetDataFileName("RatingOMF_")))
{
Utils.IO <Dictionary <Tuple <int, int>, List <double> > > .SaveObject(OMFDistributionByUserItem, GetDataFileName("RatingOMF_"));
}
return(log.ToString());
}
public string RunPrefKNN(int neighborCount, int topN = 10)
{
if (!ReadyForOrdinal)
{
GetReadyForOrdinal();
}
StringBuilder log = new StringBuilder();
log.AppendLine(Utils.PrintHeading("PrefKNN"));
// Prediction
Utils.StartTimer();
DataMatrix R_predicted = PrefUserKNN.PredictRatings(PR_train, R_unknown, neighborCount, UserSimilaritiesOfPref);
log.AppendLine(Utils.StopTimer());
// TopN Evaluation
var topNItemsByUser = ItemRecommendationCore.GetTopNItemsByUser(R_predicted, topN);
for (int n = 1; n <= topN; n++)
{
Utils.PrintValue("NCDG@" + n, NCDG.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000"));
}
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("MAP@" + n, MAP.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000")));
}
return(log.ToString());
}
public string RunPrefNMF(int maxEpoch, double learnRate, double regularizationOfUser,
double regularizationOfItem, int factorCount, int topN = 10)
{
if (!ReadyForOrdinal)
{
GetReadyForOrdinal();
}
StringBuilder log = new StringBuilder();
log.AppendLine(Utils.PrintHeading("PrefNMF"));
// Prediction
Utils.StartTimer();
DataMatrix R_predicted = PrefNMF.PredictRatings(PR_train, R_unknown,
maxEpoch, learnRate, regularizationOfUser, regularizationOfItem, factorCount);
log.AppendLine(Utils.StopTimer());
// Evaluation
var topNItemsByUser = ItemRecommendationCore.GetTopNItemsByUser(R_predicted, topN);
for (int n = 1; n <= topN; n++)
{
Utils.PrintValue("NCDG@" + n, NCDG.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000"));
}
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("MAP@" + n, MAP.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000")));
}
return(log.ToString());
}
public string RunPrefMRF(double regularization, double learnRate, int maxEpoch, List <double> quantizer,
int topN = 10)
{
// Load OMFDistribution from file
Dictionary <Tuple <int, int>, List <double> > OMFDistributionByUserItem;
if (File.Exists(GetDataFileName("PrefOMF_")))
{
OMFDistributionByUserItem = Utils.IO <Dictionary <Tuple <int, int>, List <double> > > .LoadObject(GetDataFileName("PrefOMF_"));
}
else
{
return("Abort, Run OMF first.");
}
if (!ReadyForOrdinal)
{
GetReadyForOrdinal();
}
StringBuilder log = new StringBuilder();
log.AppendLine(Utils.PrintHeading("PrefMRF: PrefNMF based ORF"));
// Prediction
Utils.StartTimer();
DataMatrix R_predicted_expectations;
DataMatrix R_predicted_mostlikely;
// Convert PR_train into user-wise preferences
DataMatrix R_train_positions = new DataMatrix(PR_train.GetPositionMatrix());
R_train_positions.Quantization(quantizer[0], quantizer[quantizer.Count - 1] - quantizer[0], quantizer);
ORF orf = new ORF();
orf.PredictRatings(R_train_positions, R_unknown, StrongSimilarityIndicatorsByItemPref,
OMFDistributionByUserItem, regularization, learnRate, maxEpoch,
quantizer.Count, out R_predicted_expectations, out R_predicted_mostlikely);
log.AppendLine(Utils.StopTimer());
// Evaluation
var topNItemsByUser_expectations = ItemRecommendationCore.GetTopNItemsByUser(R_predicted_expectations, topN);
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("NCDG@" + n, NCDG.Evaluate(RelevantItemsByUser,
topNItemsByUser_expectations, n).ToString("0.0000")));
}
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("MAP@" + n, MAP.Evaluate(RelevantItemsByUser, topNItemsByUser_expectations, n).ToString("0.0000")));
}
return(log.ToString());
}
public string RunNMFbasedORF(double regularization, double learnRate,
int maxEpoch, List <double> quantizer, int topN = 0)
{
// Load OMFDistribution from file
Dictionary <Tuple <int, int>, List <double> > OMFDistributionByUserItem;
if (File.Exists(GetDataFileName("RatingOMF_")))
{
OMFDistributionByUserItem = Utils.IO <Dictionary <Tuple <int, int>, List <double> > > .LoadObject(GetDataFileName("RatingOMF_"));
}
else
{
return("Abort, Run OMF first.");
}
if (!ReadyForNumerical)
{
GetReadyForNumerical();
}
StringBuilder log = new StringBuilder();
log.AppendLine(Utils.PrintHeading("NMF based ORF"));
// Prediction
Utils.StartTimer();
DataMatrix R_predicted_expectations;
DataMatrix R_predicted_mostlikely;
ORF orf = new ORF();
orf.PredictRatings(R_train, R_unknown, StrongSimilarityIndicatorsByItemRating,
OMFDistributionByUserItem, regularization, learnRate, maxEpoch,
quantizer.Count, out R_predicted_expectations, out R_predicted_mostlikely);
log.AppendLine(Utils.StopTimer());
// Numerical Evaluation
log.AppendLine(Utils.PrintValue("RMSE", RMSE.Evaluate(R_test, R_predicted_expectations).ToString("0.0000")));
log.AppendLine(Utils.PrintValue("MAE", RMSE.Evaluate(R_test, R_predicted_mostlikely).ToString("0.0000")));
// Top-N Evaluation
if (topN != 0)
{
var topNItemsByUser_expectations = ItemRecommendationCore.GetTopNItemsByUser(R_predicted_expectations, topN);
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("NCDG@" + n, NCDG.Evaluate(RelevantItemsByUser, topNItemsByUser_expectations, n).ToString("0.0000")));
}
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("MAP@" + n, MAP.Evaluate(RelevantItemsByUser, topNItemsByUser_expectations, n).ToString("0.0000")));
}
}
return(log.ToString());
}
/// <summary>
/// Rating based Non-negative Matrix Factorization
/// </summary>
public string RunNMF(int maxEpoch, double learnRate, double regularization,
int factorCount, int topN = 0)
{
if (!ReadyForNumerical)
{
GetReadyForNumerical();
}
StringBuilder log = new StringBuilder();
log.AppendLine(Utils.PrintHeading("NMF"));
// Prediction
Utils.StartTimer();
DataMatrix R_predicted = NMF.PredictRatings(R_train, R_unknown, maxEpoch,
learnRate, regularization, factorCount);
log.AppendLine(Utils.StopTimer());
// Numerical Evaluation
log.AppendLine(Utils.PrintValue("RMSE", RMSE.Evaluate(R_test, R_predicted).ToString("0.0000")));
log.AppendLine(Utils.PrintValue("MAE", MAE.Evaluate(R_test, R_predicted).ToString("0.0000")));
// TopN Evaluation
if (topN != 0)
{
var topNItemsByUser = ItemRecommendationCore.GetTopNItemsByUser(R_predicted, topN);
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("NCDG@" + n, NCDG.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000")));
}
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("MAP@" + n, MAP.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000")));
}
}
return(log.ToString());
}
public void GetTopNItemsByUser()
{
/*
* 5 3 0 1
* 4 0 0 1
* 1 1 0 5
* 1 0 0 4
* 0 1 5 4
*/
DataMatrix R = GetSampleRatingMatrix();
// act
Dictionary <int, List <int> > topNItemsByUser = ItemRecommendationCore.GetTopNItemsByUser(R, 2);
// assert
Debug.Assert(topNItemsByUser[0].Count == 2);
Debug.Assert(topNItemsByUser[0][0] == 0);
Debug.Assert(topNItemsByUser[0][1] == 1);
Debug.Assert(topNItemsByUser[1][0] == 0);
Debug.Assert(topNItemsByUser[1][1] == 3);
Debug.Assert(topNItemsByUser[4][0] == 2);
Debug.Assert(topNItemsByUser[4][1] == 3);
}
/// <summary>
/// Recommend the most popular (measured by mean rating) items to all users.
/// </summary>
public string RunMostPopular(int topN)
{
if (!ReadyForNumerical)
{
GetReadyForNumerical();
}
StringBuilder log = new StringBuilder();
log.AppendLine(Utils.PrintHeading("Most popular"));
// Prediction
Utils.StartTimer();
var meanByItem = R_train.GetItemMeans();
DataMatrix R_predicted = new DataMatrix(R_unknown.UserCount, R_unknown.ItemCount);
foreach (var element in R_unknown.Matrix.EnumerateIndexed(Zeros.AllowSkip))
{
int indexOfUser = element.Item1;
int indexOfItem = element.Item2;
R_predicted[indexOfUser, indexOfItem] = meanByItem[indexOfItem];
}
var topNItemsByUser = ItemRecommendationCore.GetTopNItemsByUser(R_predicted, topN);
log.AppendLine(Utils.StopTimer());
// TopN Evaluation
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("NCDG@" + n, NCDG.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000")));
}
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("MAP@" + n, MAP.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000")));
}
return(log.ToString());
}
public string RunUserKNN(int topN = 0)
{
if (!ReadyForNumerical)
{
GetReadyForNumerical();
}
StringBuilder log = new StringBuilder();
log.AppendLine(Utils.PrintHeading("UserKNN"));
// Prediction
Utils.StartTimer();
DataMatrix R_predicted = Numerical.UserKNN.PredictRatings(R_train, R_unknown, UserSimilaritiesOfRating, MaxCountOfNeighbors);
log.AppendLine(Utils.StopTimer());
// Numerical Evaluation
log.AppendLine(Utils.PrintValue("RMSE", RMSE.Evaluate(R_test, R_predicted).ToString("0.0000")));
log.AppendLine(Utils.PrintValue("MAE", MAE.Evaluate(R_test, R_predicted).ToString("0.0000")));
// TopN Evaluation
if (topN != 0)
{
var topNItemsByUser = ItemRecommendationCore.GetTopNItemsByUser(R_predicted, topN);
for (int n = 1; n <= topN; n++)
{
Utils.PrintValue("NCDG@" + n, NCDG.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000"));
}
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("MAP@" + n, MAP.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000")));
}
}
return(log.ToString());
}
public string RunPrefNMFbasedOMF(int maxEpoch, double learnRate, double regularizationOfUser,
double regularizationOfItem, int factorCount, List <double> quantizer, int topN)
{
if (!ReadyForOrdinal)
{
GetReadyForOrdinal();
}
StringBuilder log = new StringBuilder();
log.AppendLine(Utils.PrintHeading("PrefNMF based OMF"));
// =============PrefNMF prediction on Train+Unknown============
// Get ratings from scorer, for both train and test
// R_all contains indexes of all ratings both train and test
// DataMatrix R_all = new DataMatrix(R_unknown.UserCount, R_unknown.ItemCount);
// R_all.MergeNonOverlap(R_unknown);
//R_all.MergeNonOverlap(R_train.IndexesOfNonZeroElements());
//PrefRelations PR_unknown = PrefRelations.CreateDiscrete(R_all);
// R_all is far too slow, change the data structure
//Dictionary<int, List<Tuple<int, int>>> PR_unknown = new Dictionary<int, List<Tuple<int, int>>>();
//Dictionary<int, List<int>> PR_unknown_cache = new Dictionary<int, List<int>>();
Dictionary <int, List <int> > ItemsByUser_train = R_train.GetItemsByUser();
Dictionary <int, List <int> > ItemsByUser_unknown = R_unknown.GetItemsByUser();
Dictionary <int, List <int> > PR_unknown = new Dictionary <int, List <int> >(ItemsByUser_train);
List <int> keys = new List <int>(ItemsByUser_train.Keys);
foreach (var key in keys)
{
PR_unknown[key].AddRange(ItemsByUser_unknown[key]);
}
/*
* foreach (var row in R_unknown.Matrix.EnumerateRowsIndexed())
* {
* int indexOfUser = row.Item1;
* PR_unknown_cache[indexOfUser] = new List<int>();
* Vector<double> itemsOfUser = row.Item2;
* foreach (var item in itemsOfUser.EnumerateIndexed(Zeros.AllowSkip))
* {
* PR_unknown_cache[indexOfUser].Add(item.Item1);
* }
* }
* foreach (var row in R_train.Matrix.EnumerateRowsIndexed())
* {
* int indexOfUser = row.Item1;
* Vector<double> itemsOfUser = row.Item2;
* foreach (var item in itemsOfUser.EnumerateIndexed(Zeros.AllowSkip))
* {
* PR_unknown_cache[indexOfUser].Add(item.Item1);
* }
* }
*/
Utils.StartTimer();
SparseMatrix PR_predicted = PrefNMF.PredictPrefRelations(PR_train, PR_unknown,
maxEpoch, learnRate, regularizationOfUser, regularizationOfItem, factorCount, quantizer);
// Both predicted and train need to be quantized
// otherwise OMF won't accept
//PR_predicted.quantization(0, 1.0,
// new List<double> { Config.Preferences.LessPreferred,
// Config.Preferences.EquallyPreferred, Config.Preferences.Preferred });
DataMatrix R_predictedByPrefNMF = new DataMatrix(PR_predicted);// new DataMatrix(PR_predicted.GetPositionMatrix());
// PR_train itself is already in quantized form!
//PR_train.quantization(0, 1.0, new List<double> { Config.Preferences.LessPreferred, Config.Preferences.EquallyPreferred, Config.Preferences.Preferred });
DataMatrix R_train_positions = new DataMatrix(PR_train.GetPositionMatrix());
R_train_positions.Quantization(quantizer[0], quantizer[quantizer.Count - 1] - quantizer[0], quantizer);
log.AppendLine(Utils.StopTimer());
// =============OMF prediction on Train+Unknown============
log.AppendLine(Utils.PrintHeading("Ordinal Matrix Factorization with PrefNMF as scorer"));
Utils.StartTimer();
Dictionary <Tuple <int, int>, List <double> > OMFDistributionByUserItem;
DataMatrix R_predicted;
log.AppendLine(OMF.PredictRatings(R_train_positions.Matrix, R_unknown.Matrix, R_predictedByPrefNMF.Matrix,
quantizer, out R_predicted, out OMFDistributionByUserItem));
log.AppendLine(Utils.StopTimer());
// TopN Evaluation
var topNItemsByUser = ItemRecommendationCore.GetTopNItemsByUser(R_predicted, topN);
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("NCDG@" + n, NCDG.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000")));
}
for (int n = 1; n <= topN; n++)
{
log.AppendLine(Utils.PrintValue("MAP@" + n, MAP.Evaluate(RelevantItemsByUser, topNItemsByUser, n).ToString("0.0000")));
}
// Save OMFDistribution to file
if (!File.Exists(GetDataFileName("PrefOMF_")))
{
Utils.IO <Dictionary <Tuple <int, int>, List <double> > > .SaveObject(OMFDistributionByUserItem, GetDataFileName("PrefOMF_"));
}
return(log.ToString());
}
public string GetReadyForNumerical(bool saveLoadedData = true)
{
if (ReadyForNumerical)
{
return("Is ready.");
}
StringBuilder log = new StringBuilder();
Utils.StartTimer();
log.AppendLine(Utils.PrintHeading("Create R_train/R_test sets from " + DataSetFile));
Utils.LoadMovieLensSplitByCount(DataSetFile, out R_train,
out R_test, MinCountOfRatings, MaxCountOfRatings, CountOfRatingsForTrain, ShuffleData, Seed);
Console.WriteLine(R_train.DatasetBrief("Train set"));
Console.WriteLine(R_test.DatasetBrief("Test set"));
log.AppendLine(R_train.DatasetBrief("Train set"));
log.AppendLine(R_test.DatasetBrief("Test set"));
R_unknown = R_test.IndexesOfNonZeroElements();
log.AppendLine(Utils.PrintValue("Relevant item criteria", RelevantItemCriteria.ToString("0.0")));
RelevantItemsByUser = ItemRecommendationCore.GetRelevantItemsByUser(R_test, RelevantItemCriteria);
log.AppendLine(Utils.PrintValue("Mean # of relevant items per user",
RelevantItemsByUser.Average(k => k.Value.Count).ToString("0")));
log.AppendLine(Utils.StopTimer());
#region Prepare similarity data
if (File.Exists(GetDataFileName("USR")) &&
File.Exists(GetDataFileName("ISR")) &&
File.Exists(GetDataFileName("SSIIR")))
{
Utils.StartTimer();
Utils.PrintHeading("Load user-user similarities (rating based)");
UserSimilaritiesOfRating = Utils.IO <SimilarityData> .LoadObject(GetDataFileName("USR"));
Utils.StopTimer();
Utils.StartTimer();
Utils.PrintHeading("Load item-item similarities (rating based)");
ItemSimilaritiesOfRating = Utils.IO <SimilarityData> .LoadObject(GetDataFileName("ISR"));
Utils.StopTimer();
Utils.StartTimer();
Utils.PrintHeading("Load item-item strong similarity indicators (rating based)");
StrongSimilarityIndicatorsByItemRating = Utils.IO <HashSet <Tuple <int, int> > > .LoadObject(GetDataFileName("SSIIR"));
Utils.StopTimer();
}
else
{
Utils.StartTimer();
Utils.PrintHeading("Compute user-user similarities (rating based)");
Metric.GetPearsonOfRows(R_train, MaxCountOfNeighbors, StrongSimilarityThreshold,
out UserSimilaritiesOfRating);
if (saveLoadedData)
{
Utils.IO <SimilarityData> .SaveObject(UserSimilaritiesOfRating, GetDataFileName("USR"));
}
Utils.StopTimer();
Utils.StartTimer();
Utils.PrintHeading("Compute item-item similarities (rating based)");
Metric.GetPearsonOfColumns(R_train, MaxCountOfNeighbors, StrongSimilarityThreshold,
out ItemSimilaritiesOfRating, out StrongSimilarityIndicatorsByItemRating);
if (saveLoadedData)
{
Utils.IO <SimilarityData> .SaveObject(ItemSimilaritiesOfRating, GetDataFileName("ISR"));
Utils.IO <HashSet <Tuple <int, int> > >
.SaveObject(StrongSimilarityIndicatorsByItemRating, GetDataFileName("SSIIR"));
}
Utils.StopTimer();
}
#endregion
ReadyForNumerical = true;
return(log.ToString());
}