public void GetPositionMatrix()
{
/*
* 5 3 0 1
* 4 0 0 1
* 1 1 0 5
* 1 0 0 4
* 0 1 5 4
*/
DataMatrix R = GetSampleRatingMatrix();
PrefRelations PR = PrefRelations.CreateDiscrete(R);
// act
SparseMatrix positionMatrix = PR.GetPositionMatrix();
// assert
// How many ratings we have then how many positions we have
Debug.Assert(positionMatrix.NonZerosCount == R.AsSparseMatrix.NonZerosCount);
// Check if each rating has a corresponding position
// we have check the count so don't need to check the oppsite
foreach (Tuple <int, int, double> element in R.AsSparseMatrix.EnumerateIndexed(Zeros.AllowSkip))
{
int indexOfUser = element.Item1;
int indexOfItem = element.Item2;
double rating = element.Item3;
Debug.Assert(positionMatrix[indexOfUser, indexOfItem] != SparseMatrix.Zero);
}
}
public static void GetCosineOfPrefRelations(PrefRelations PR, int maxCountOfNeighbors,
double strongSimilarityThreshold, out SimilarityData neighborsByObject)
{
HashSet <Tuple <int, int> > foo;
ComputeSimilarities(PR, SimilarityMetric.CosinePrefRelations, maxCountOfNeighbors,
strongSimilarityThreshold, out neighborsByObject, out foo);
}
public void CreateDiscrete()
{
/*
* 5 3 0 1
* 4 0 0 1
* 1 1 0 5
* 1 0 0 4
* 0 1 5 4
*/
DataMatrix R = GetSampleRatingMatrix();
// act
PrefRelations PR = PrefRelations.CreateDiscrete(R);
// assert
foreach (KeyValuePair <int, SparseMatrix> user in PR.PreferenceRelationsByUser)
{
int indexOfUser = user.Key;
SparseMatrix preferencesOfUser = user.Value;
// Note that the diagonal (item compares to itsself) is elft empty
Debug.Assert(preferencesOfUser.Trace() == 0);
// Check if the correct number of preference relations have been created
Debug.Assert((Math.Pow(R.GetNonZerosCountOfRow(indexOfUser), 2)
- R.GetNonZerosCountOfRow(indexOfUser))
== preferencesOfUser.NonZerosCount);
}
// Check if the first user's preferences are correct
Debug.WriteLine("PR[0][0, 0]=" + PR[0][0, 0]);
Debug.Assert(PR[0][0, 0] == SparseMatrix.Zero);
Debug.Assert(PR[0][0, 1] == Config.Preferences.Preferred);
Debug.Assert(PR[0][1, 0] == Config.Preferences.LessPreferred);
Debug.Assert(PR[0][0, 2] == SparseMatrix.Zero);
Debug.Assert(PR[0][2, 0] == SparseMatrix.Zero);
Debug.Assert(PR[0][1, 2] == SparseMatrix.Zero);
Debug.Assert(PR[0][2, 1] == SparseMatrix.Zero);
Debug.Assert(PR[0][1, 3] == Config.Preferences.Preferred);
Debug.Assert(PR[0][3, 1] == Config.Preferences.LessPreferred);
// Check if the last user's preferences are correct
Debug.Assert(PR[4][1, 1] == SparseMatrix.Zero);
Debug.Assert(PR[4][0, 1] == SparseMatrix.Zero);
Debug.Assert(PR[4][1, 0] == SparseMatrix.Zero);
Debug.Assert(PR[4][0, 2] == SparseMatrix.Zero);
Debug.Assert(PR[4][2, 0] == SparseMatrix.Zero);
Debug.Assert(PR[4][1, 2] == Config.Preferences.LessPreferred);
Debug.Assert(PR[4][2, 1] == Config.Preferences.Preferred);
Debug.Assert(PR[4][1, 3] == Config.Preferences.LessPreferred);
Debug.Assert(PR[4][3, 1] == Config.Preferences.Preferred);
}
public void PreferencesToPositions()
{
/*
* 5 3 0 1
* 4 0 0 1
* 1 1 0 5
* 1 0 0 4
* 0 1 5 4
*/
DataMatrix R = GetSampleRatingMatrix();
PrefRelations PR = PrefRelations.CreateDiscrete(R);
// act
// Convert first, Third, and last users' preferences to positions
Vector <double> positionsOfUserFirst = PR.PreferencesToPositions(PR[0]);
Vector <double> positionsOfUserThird = PR.PreferencesToPositions(PR[2]);
Vector <double> positionsOfUserLast = PR.PreferencesToPositions(PR[4]);
// assert
// Check first user
Debug.Assert(positionsOfUserFirst[0] == 1 + Config.Preferences.PositionShift);
Debug.Assert(positionsOfUserFirst[1] == 0 + Config.Preferences.PositionShift);
Debug.Assert(positionsOfUserFirst[2] == SparseMatrix.Zero);
Debug.Assert(positionsOfUserFirst[3] == -1 + Config.Preferences.PositionShift);
// Check third user
Debug.Assert(positionsOfUserThird[0] == -0.5 + Config.Preferences.PositionShift);
Debug.Assert(positionsOfUserThird[1] == -0.5 + Config.Preferences.PositionShift);
Debug.Assert(positionsOfUserThird[2] == SparseMatrix.Zero);
Debug.Assert(positionsOfUserThird[3] == 1 + Config.Preferences.PositionShift);
// Check second last user
Debug.Assert(positionsOfUserLast[0] == SparseMatrix.Zero);
Debug.Assert(positionsOfUserLast[1] == -1 + Config.Preferences.PositionShift);
Debug.Assert(positionsOfUserLast[2] == 1 + Config.Preferences.PositionShift);
Debug.Assert(positionsOfUserLast[3] == 0 + Config.Preferences.PositionShift);
// The number of positions should match the number of ratings by each user
Debug.Assert(positionsOfUserFirst.GetNonZerosCount()
== R.GetNonZerosCountOfRow(0), String.Format("{0}=={1}",
positionsOfUserFirst.GetNonZerosCount(), R.GetNonZerosCountOfRow(0)));
Debug.Assert(positionsOfUserThird.GetNonZerosCount()
== R.GetNonZerosCountOfRow(2), String.Format("{0}=={1}",
positionsOfUserThird.GetNonZerosCount(), R.GetNonZerosCountOfRow(2)));
Debug.Assert(positionsOfUserLast.GetNonZerosCount()
== R.GetNonZerosCountOfRow(4), String.Format("{0}=={1}",
positionsOfUserLast.GetNonZerosCount(), R.GetNonZerosCountOfRow(4)));
}
/// <summary>
/// Switch between different metrics.
/// </summary>
/// <param name="PR"></param>
/// <param name="similarityMetric"></param>
/// <returns></returns>
private static void ComputeSimilarities(PrefRelations PR,
Metric.SimilarityMetric similarityMetric, int maxCountOfNeighbors,
double minSimilarityThreshold, out SimilarityData neighborsByObject,
out HashSet <Tuple <int, int> > strongSimilarityIndicators)
{
int dimension = PR.UserCount;
HashSet <Tuple <int, int> > strongSimilarityIndicators_out = new HashSet <Tuple <int, int> >();
SimilarityData neighborsByObject_out = new SimilarityData(maxCountOfNeighbors);
// Compute similarity for the lower triangular
Object lockMe = new Object();
Parallel.For(0, dimension, i =>
{
Utils.PrintEpoch("Progress current/total", i, dimension);
for (int j = 0; j < dimension; j++)
{
if (i == j)
{
continue;
} // Skip self similarity
else if (i > j)
{
switch (similarityMetric)
{
case SimilarityMetric.CosinePrefRelations:
double cosinePR = Metric.cosinePR(PR, i, j);
lock (lockMe)
{
if (cosinePR > minSimilarityThreshold)
{
strongSimilarityIndicators_out.Add(new Tuple <int, int>(i, j));
}
neighborsByObject_out.AddSimilarityData(i, j, cosinePR);
neighborsByObject_out.AddSimilarityData(j, i, cosinePR);
}
break;
// More metrics to be added here.
}
}
}
});
neighborsByObject = neighborsByObject_out;
strongSimilarityIndicators = strongSimilarityIndicators_out;
}
private static double cosinePR(PrefRelations PR, int u_a, int u_b)
{
SparseMatrix pr_a = PR[u_a];
SparseMatrix pr_b = PR[u_b];
//Debug.Assert(pr_a.Trace() == SparseMatrix.Zero, "The diagonal of user preference relation matrix should be left empty.");
//Debug.Assert(pr_b.Trace() == SparseMatrix.Zero, "The diagonal of user preference relation matrix should be left empty.");
// The number of preference relations agreed between users a and b
int agreedCount = pr_a.Fold2((count, prefOfA, prefOfB) =>
count + (prefOfA == prefOfB ? 1 : 0), 0, pr_b, Zeros.AllowSkip);
#region Obsolate naive implementation
/*
* // TODO: there should be a faster lambda way of doing this
* // Loop through all non-zero elements
* foreach (Tuple<int, int, double> element in pr_a.EnumerateIndexed(Zeros.AllowSkip))
* {
* int item_i = element.Item1;
* int item_j = element.Item2;
* double preference_a = element.Item3;
* // Because pr_ij is just the reverse of pr_ji,
* // we count only i-j to avoid double counting
* // and also reduce the number of calling pr_b[]
* if (item_i > item_j)
* {
* if (preference_a == pr_b[item_i, item_j])
* {
++agreedCount;
* }
* }
* }
*/
#endregion
// Multiplicaiton result can be too large and cause overflow,
// therefore we do Sqrt() first and then multiply
double normalization = checked (Math.Sqrt((double)pr_a.NonZerosCount) * Math.Sqrt((double)pr_b.NonZerosCount));
// Very small value
return(agreedCount / normalization);
}
public string GetReadyForOrdinal(bool saveLoadedData = true)
{
if (!ReadyForNumerical)
{
GetReadyForNumerical();
}
if (ReadyForOrdinal)
{
return("Is ready.");
}
StringBuilder log = new StringBuilder();
Utils.StartTimer();
log.AppendLine(Utils.PrintHeading("Prepare preferecen relation data"));
Console.WriteLine("Converting R_train into PR_train");
log.AppendLine("Converting R_train into PR_train");
PR_train = PrefRelations.CreateDiscrete(R_train);
//Console.WriteLine("Converting R_test into PR_test");
//log.AppendLine("Converting R_test into PR_test");
//PR_test = PrefRelations.CreateDiscrete(R_test);
log.AppendLine(Utils.StopTimer());
#region Prepare similarity data
if (File.Exists(GetDataFileName("USP")) &&
File.Exists(GetDataFileName("ISP")) &&
File.Exists(GetDataFileName("SSIIP")))
{
Utils.StartTimer();
Utils.PrintHeading("Load user, item, indicators variables (Pref based)");
UserSimilaritiesOfPref = Utils.IO <SimilarityData> .LoadObject(GetDataFileName("USP"));
ItemSimilaritiesOfPref = Utils.IO <SimilarityData> .LoadObject(GetDataFileName("ISP"));
StrongSimilarityIndicatorsByItemPref = Utils.IO <HashSet <Tuple <int, int> > > .LoadObject(GetDataFileName("SSIIP"));
Utils.StopTimer();
}
else
{
Utils.StartTimer();
Utils.PrintHeading("Compute user-user similarities (Pref based)");
Metric.GetCosineOfPrefRelations(PR_train, MaxCountOfNeighbors,
StrongSimilarityThreshold, out UserSimilaritiesOfPref);
Utils.StopTimer();
// For the moment, we use user-wise preferences to compute
// item-item similarities, it is not the same as user-user pref similarities
Utils.StartTimer();
Utils.PrintHeading("Compute item-item similarities (Pref based)");
DataMatrix PR_userwise_preferences = new DataMatrix(PR_train.GetPositionMatrix());
Metric.GetPearsonOfColumns(PR_userwise_preferences, MaxCountOfNeighbors, StrongSimilarityThreshold,
out ItemSimilaritiesOfPref, out StrongSimilarityIndicatorsByItemPref);
Utils.StopTimer();
if (saveLoadedData)
{
Utils.IO <SimilarityData> .SaveObject(UserSimilaritiesOfPref, GetDataFileName("USP"));
Utils.IO <SimilarityData> .SaveObject(ItemSimilaritiesOfPref, GetDataFileName("ISP"));
Utils.IO <HashSet <Tuple <int, int> > >
.SaveObject(StrongSimilarityIndicatorsByItemPref, GetDataFileName("SSIIP"));
}
Utils.StopTimer();
}
#endregion
ReadyForOrdinal = true;
return(log.ToString());
}
