public void getReport()
{
if (lm == null)
{
getMnlModel();
}
Forms.RunningProcess.frmRunningProcessDialog rd = new Forms.RunningProcess.frmRunningProcessDialog(false);
rd.Text = "Soft Max Nnet Results";
rd.TopLevel = true;
rd.pgbProcess.Visible = false;
rd.FormBorderStyle = System.Windows.Forms.FormBorderStyle.Sizable;
rd.addMessage("Sample size = " + n.ToString());
rd.addMessage("Number of Classes = " + NumberOfClasses.ToString());
rd.addMessage("Number of Parameters = " + nvars.ToString());
rd.addMessage("RMSE = " + RMSE.ToString());
rd.addMessage("Average Error = " + AverageError.ToString());
rd.addMessage("Average Relative Error = " + AverageRelativeError.ToString());
rd.addMessage("Average Cross Entropy Error = " + AverageCrossEntropyError.ToString());
rd.addMessage("Classification Error = " + ClassificationError.ToString());
rd.addMessage("Relative Classification Error = " + RelativeClassificationError.ToString());
try
{
if (ModelHelper.chartingAvailable() && System.Windows.Forms.MessageBox.Show("Do you want to build probability graphs?", "Graphs", System.Windows.Forms.MessageBoxButtons.YesNo) == System.Windows.Forms.DialogResult.Yes)
{
createRegChart();
}
}
catch
{
System.Windows.Forms.MessageBox.Show("Cannot create charts");
}
rd.Show();
rd.enableClose();
}
public void getReport(double alpha)
{
Forms.RunningProcess.frmRunningProcessDialog rd = new Forms.RunningProcess.frmRunningProcessDialog(false);
rd.Text = "Regression Results";
rd.TopLevel = true;
rd.pgbProcess.Visible = false;
rd.FormBorderStyle = System.Windows.Forms.FormBorderStyle.Sizable;
rd.addMessage("Dependent field = " + DependentFieldNames[0]);
rd.addMessage("Independent fields = " + String.Join(", ", IndependentFieldNames));
rd.addMessage("Sample size = " + SampleSize.ToString());
rd.addMessage("Intercept Through Origin = " + InterceptThroughOrigin.ToString());
rd.addMessage("F-statistic = " + FValue.ToString() + " p-value = " + PValue.ToString());
rd.addMessage("RMSE = " + RMSE.ToString());
rd.addMessage("R2 = " + Rsquared.ToString());
rd.addMessage("Adj-R2 = " + AdjustedRsquared.ToString() + "\n\nCoefficents and standard errors:\n");
rd.addMessage("Param: Intercept, " + String.Join(", ", IndependentFieldNames));
rd.addMessage("Coef: " + string.Join(", ", (from double d in Coefficients select d.ToString()).ToArray()));
rd.addMessage("STE: " + string.Join(", ", (from double d in StandardErrors select d.ToString()).ToArray()) + "\n");
try
{
if (ModelHelper.chartingAvailable())
{
regChart();
}
}
catch
{
System.Windows.Forms.MessageBox.Show("Cannot create charts");
}
rd.Show();
rd.enableClose();
}
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 void RMSETest()
{
/*
* 5 3 0 1
* 4 0 0 1
* 1 1 0 5
* 1 0 0 4
* 0 1 5 4
*/
DataMatrix R = GetSampleRatingMatrix();
/*
* 3 3 0 1
* 4 0 0 5
* 1 2 0 5
* 1 0 0 4
* 0 1 5 4
*/
DataMatrix R_predicted = GetSampleRatingMatrix();
R_predicted[0, 0] = 3; // was 5
R_predicted[2, 1] = 2; // was 1
R_predicted[1, 3] = 5; // was 1
double debug1 = RMSE.Evaluate(R, R_predicted);
double debug2 = Math.Sqrt(21.0 / 13.0);
Debug.Assert(debug1 == debug2);
}
private ResultModel item_predict(string pathFile)
{
ResultModel result = new ResultModel();
// load data
Matrix <double> data = DelimitedReader.Read <double>(pathFile, false, "\t", false, System.Globalization.CultureInfo.InvariantCulture.NumberFormat);
result.raw_data = data;
int n_users = data.Column(0).Distinct().Count();
int n_items = data.Column(1).Distinct().Count();
double test_split = 0.1;
double train_split = 1 - test_split;
int train_row = (int)(data.RowCount * train_split);
int train_col = data.ColumnCount;
int test_row = data.RowCount - train_row;
int test_col = train_col;
Matrix <double> train_data = DenseMatrix.Create(train_row, train_col, 0);
Matrix <double> test_data = DenseMatrix.Create(test_row, test_col, 0);
train_data = data.SubMatrix(0, train_row, 0, train_col);
test_data = data.SubMatrix(train_row, test_row, 0, test_col);
// Create two user-item matrices, one for training and another for testing
Matrix <double> train_data_matrix = DenseMatrix.Create(n_users, n_items, 0);
for (int line = 0; line < train_data.RowCount; line++)
{
int userId = (int)(train_data[line, 0]);
int itemId = (int)(train_data[line, 1] - 1);
train_data_matrix[userId, itemId] = train_data[line, 2];
}
Matrix <double> test_data_matrix = DenseMatrix.Create(n_users, n_items, 0);
for (int line = 0; line < test_data.RowCount; line++)
{
int userId = (int)(test_data[line, 0]);
int itemId = (int)(test_data[line, 1] - 1);
test_data_matrix[userId, itemId] = test_data[line, 2];
}
result.train_data = train_data_matrix;
result.test_data = test_data_matrix;
// consine similarity calculate
Matrix <double> item_similarity = Recommender_System.cosin(train_data_matrix.Transpose());
// predict
Matrix <double> item_prediction = Recommender_System.predict(train_data_matrix, item_similarity, "item");
result.predic_data = item_prediction;
// rmse error
double item_rmse = RMSE.calRMSE(item_prediction, test_data_matrix);
result.rmse = item_rmse;
return(result);
}
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());
}
public void RMSETest()
{
var actual = new Matrix(100, 1);
var expected = new Matrix(100, 1);
actual.InRandomize(0.25, 0.75);
expected.InRandomize(0.25, 0.75);
var metric = new RMSE();
var e = metric.Evaluate(actual, expected);
var val = Math.Sqrt(new MSE().Evaluate(actual, expected));
Assert.IsTrue(Math.Abs(e - val) < 0.01, metric.Type().ToString() + " Evaluate.");
}
public string writeModel(string outModelPath)
{
if (lm == null)
{
getMnlModel();
}
outPath = outModelPath;
double[,] coef = null;
alglib.mnlunpack(lm, out coef, out nvars, out nclasses);
using (System.IO.StreamWriter sw = new System.IO.StreamWriter(outPath))
{
sw.WriteLine(modelTypes.SoftMax.ToString());
sw.WriteLine(InTablePath);
sw.WriteLine(SampleSize.ToString());
sw.WriteLine(String.Join(",", IndependentFieldNames));
sw.WriteLine(String.Join(",", DependentFieldNames));
sw.WriteLine(String.Join(",", ClassFieldNames));
sw.WriteLine(string.Join(",", Categories));
sw.WriteLine(NumberOfVariables.ToString());
sw.WriteLine(NumberOfClasses.ToString());
sw.WriteLine(RMSE.ToString());
sw.WriteLine(AverageCrossEntropyError.ToString());
sw.WriteLine(AverageError.ToString());
sw.WriteLine(AverageRelativeError.ToString());
sw.WriteLine(ClassificationError.ToString());
sw.WriteLine(RelativeClassificationError.ToString());
sw.WriteLine(String.Join(",", (from double d in minValues select d.ToString()).ToArray()));
sw.WriteLine(String.Join(",", (from double d in maxValues select d.ToString()).ToArray()));
sw.WriteLine(String.Join(",", (from double d in sumValues select d.ToString()).ToArray()));
int rws = coef.GetUpperBound(1);
int clms = coef.GetUpperBound(0);
for (int r = 0; r <= rws; r++)
{
string[] ln = new string[clms + 1];
for (int c = 0; c <= clms; c++)
{
ln[c] = coef[c, r].ToString();
}
sw.WriteLine(String.Join(" ", ln));
}
sw.Close();
}
return(outPath);
}
/// <summary>
/// Add to result
/// </summary>
/// <param name="weights">double[] - weights</param>
/// <param name="sse">double[] - sum square errors</param>
/// <param name="rmse">double[] - rmse's</param>
public void Add(double[] weights, double[] sse, double[] rmse)
{
if (ResultWeights == null)
{
ResultWeights = new List <double[]>();
}
ResultWeights.Add(weights);
if (SSE == null)
{
SSE = new List <double[]>();
}
SSE.Add(sse);
if (RMSE == null)
{
RMSE = new List <double[]>();
}
RMSE.Add(rmse);
}
/// <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());
}
/// <summary>
/// Predict all unknown values as global mean rating.
/// </summary>
public string RunGlobalMean()
{
if (!ReadyForNumerical)
{
GetReadyForNumerical();
}
StringBuilder log = new StringBuilder();
log.AppendLine(Utils.PrintHeading("Global Mean"));
// Prediction
Utils.StartTimer();
double globalMean = R_train.GetGlobalMean();
DataMatrix R_predicted = R_unknown.Multiply(globalMean);
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")));
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());
}
