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());
}