static void TitanicDemo()
{
WriteH1("Testing");
#region Dummy data importer
//WriteH2("Dummy Data");
//DataImporterDummy di = new DataImporterDummy();
//DataFrame df = new DataFrame(di);
//df.Load(String.Empty, true, true);
//Console.WriteLine(df.TotalColumns);
//foreach(string h in df.Headers)
//{
// Console.WriteLine(h);
//}
#endregion
#region CSV data importer
WriteH2("CSV Data (Titanic)");
DataImporterCSV di_csv = new DataImporterCSV();
DataExporterCSV de_csv = new DataExporterCSV();
DataFrame df_train = new DataFrame(di_csv, de_csv);
DataFrame df_test = new DataFrame(di_csv, de_csv);
df_train.Load(@"c:\temp\titanic.csv", true, "Survived");
df_test.Load(@"c:\temp\titanic_test.csv", true);
Console.WriteLine($"Total Columns (training data): {df_train.TotalColumns}");
Console.WriteLine($"Total Columns (testing data): {df_test.TotalColumns}");
// Change the type of some of the training columns
df_train.SetColumnType("pclass", DataFrameColumnType.Factors);
df_train.SetColumnType("sex", DataFrameColumnType.Factors);
df_train.SetColumnType("age", DataFrameColumnType.Bins);
//df_train["age"].SetBins(new double[] { 0.0, 18.0, 100.0 });
df_train["age"].SetBins(new double[] { 0.0, 15.0, 25.0, 30.0, 40.0, 50.0, 55.0, 65.0, 75.0, 100.0 });
df_train["age"].EmptyValue = 30.27; // Average value of known ages
df_train.SetColumnType("fare", DataFrameColumnType.Double);
df_train.SetColumnType("sibsp", DataFrameColumnType.Double);
df_train.SetColumnType("parch", DataFrameColumnType.Double);
df_train.CreateDataColumn("CabinLetter", GetCabinLetter);
df_test.CreateDataColumn("CabinLetter", GetCabinLetter); // For now, we have to explicitly set both training set
// and test set separately.
df_train.SetColumnType("CabinLetter", DataFrameColumnType.Factors);
df_train.SetColumnType("survived", DataFrameColumnType.Double);
// Try and match the types in the testing set
df_test.MatchColumns(df_train);
Console.WriteLine($"df_train hasResults? {df_train.HasResults}. df_test hasResults? {df_test.HasResults}");
// Start calculations
Matrix Xtrain = df_train.ExportFeatures();
Matrix ytrain = df_train.ExportResults();
Matrix Xtest = df_test.ExportFeatures();
// Try Logistic Regression
double[] labels = new double[] { 0.0, 1.0 };
Matrix lr_theta = LogisticRegression.OneVsAll(Xtrain, ytrain, labels, 0.1, 1000);
Matrix lr_prediction = LogisticRegression.PredictOneVsAll(lr_theta, Xtest);
int input_layer_size = Xtrain.Columns;
int output_layer_size = labels.Length;
int hidden_layer_size = (input_layer_size + output_layer_size) / 2;
Matrix[] nn_theta = NeuralNetwork.Train(Xtrain, ytrain, input_layer_size, hidden_layer_size, labels, 0.1, 1000);
Matrix nn_prediction = NeuralNetwork.Predict(nn_theta[0], nn_theta[1], Xtest);
// Exporting
DataFrame df_lr_export = df_test;
DataFrame df_nn_export = df_test;
DataFrameColumn col_lr_results = new DataFrameColumn(df_lr_export, lr_prediction, 0);
DataFrameColumn col_nn_results = new DataFrameColumn(df_nn_export, nn_prediction, 0);
col_lr_results.Header = col_nn_results.Header = "Survived";
df_lr_export.Save(@"c:\temp\lr_results.csv");
df_nn_export.Save(@"c:\temp\nn_results.csv");
#endregion
}
static void LogisticRegressionDemo()
{
WriteH1("Logistic Regression");
#region Sigmoid Function
WriteH2("Sigmoid Function");
Matrix m1 = new Matrix(new double[, ] {
{ 1200000 }
});
Matrix sigmoid1 = LogisticRegression.Sigmoid(m1);
Console.Write("Target: 1.0 Actual: {0}", sigmoid1);
m1[0, 0] = -25000;
sigmoid1 = LogisticRegression.Sigmoid(m1);
Console.Write("Target: 0.0 Actual: {0}", sigmoid1);
m1[0, 0] = 0;
sigmoid1 = LogisticRegression.Sigmoid(m1);
Console.Write("Target: 0.5 Actual: {0}", sigmoid1);
m1 = new Matrix(new double[, ] {
{ 4, 5, 6 }
});
sigmoid1 = LogisticRegression.Sigmoid(m1);
Console.Write("Target: 0.98 0.99 0.997 Actual: {0}", sigmoid1);
#endregion
#region Predict
WriteH2("Prediction");
m1 = new Matrix(new double[, ] {
{ 1, 1 }, { 1, 2.5 }, { 1, 3 }, { 1, 4 }
});
Matrix theta = new Matrix(new double[, ] {
{ -3.5 }, { 1.3 }
});
Matrix prediction = LogisticRegression.Predict(m1, theta);
Console.WriteLine("Target: 0.0 ; 0.0 ; 1.0 ; 1.0 ; Actual: {0}", prediction.ToString().Replace("\n", "; "));
m1 = Matrix.Magic(3);
theta = new Matrix(new double[, ] {
{ 4 }, { 3 }, { -8 }
});
prediction = LogisticRegression.Predict(m1, theta);
Console.WriteLine("Target: 0.0 ; 0.0 ; 1.0 ; Actual: {0}", prediction.ToString().Replace("\n", "; "));
#endregion
#region Cost Function
WriteH2("Cost Function");
Matrix X = Matrix.AddIdentityColumn(Matrix.Magic(3));
Matrix y = new Matrix(new double[, ] {
{ 1 }, { 0 }, { 1 }
});
theta = new Matrix(new double[, ] {
{ -2 }, { -1 }, { 1 }, { 2 }
});
Tuple <double, Matrix> cost = LogisticRegression.CostFunction(X, y, theta);
Console.WriteLine("Target: 4.6832 ; Actual: {0}", cost.Item1);
#endregion
#region Regularized Cost Function
WriteH2("Regularized Cost Function");
MinimizeOptions options = new MinimizeOptions();
options.RegularizationParameter = 3;
cost = LogisticRegression.CostFunction(X, y, theta, options);
Console.WriteLine("Target: 7.6832 ; Actual: {0}", cost.Item1);
X = new Matrix(new double[, ] {
{ 1.0, 0.1, 0.6, 1.1 },
{ 1.0, 0.2, 0.7, 1.2 },
{ 1.0, 0.3, 0.8, 1.3 },
{ 1.0, 0.4, 0.9, 1.4 },
{ 1.0, 0.5, 1.0, 1.5 }
});
y = new Matrix(new double[, ] {
{ 1.0 },
{ 0.0 },
{ 1.0 },
{ 0.0 },
{ 1.0 }
});
theta = new Matrix(new double[, ] {
{ -2 }, { -1 }, { 1 }, { 2 }
});
cost = LogisticRegression.CostFunction(X, y, theta, options);
Console.WriteLine("Target: 2.5348 ; Actual: {0}", cost.Item1);
#endregion
#region OneVsAll
WriteH2("One vs All");
X = new Matrix(new double[, ] {
{ 8.0, 1.0, 6.0 },
{ 3.0, 5.0, 7.0 },
{ 4.0, 9.0, 2.0 },
{ 0.84147, 0.90930, 0.14112 },
{ 0.54030, -0.41615, -0.98999 }
});
y = new Matrix(new double[, ] {
{ 1.0 },
{ 2.0 },
{ 2.0 },
{ 1.0 },
{ 3.0 }
});
//Matrix testTheta = new Matrix(4, 1);
//Matrix X0 = Matrix.Join(Matrix.Ones(5, 1), X, MatrixDimensions.Columns);
//cost = LogisticRegression.CostFunction(X0, y==1, testTheta, 0.1);
//Console.WriteLine(cost.Item1);
//Console.WriteLine(cost.Item2);
double[] labels = new double[] { 1.0, 2.0, 3.0 };
Matrix all_theta = LogisticRegression.OneVsAll(X, y, labels, 0.1);
Console.WriteLine(all_theta);
#endregion
#region PredictOneVsAll
WriteH2("Predict One vs All");
X = new Matrix(new double[, ] {
{ 1.0, 7.0 },
{ 4.0, 5.0 },
{ 7.0, 8.0 },
{ 1.0, 4.0 }
});
all_theta = new Matrix(new double[, ] {
{ 1.0, -6.0, 3.0 },
{ -2.0, 4.0, -3.0 }
});
prediction = LogisticRegression.PredictOneVsAll(all_theta, X);
Console.WriteLine("Target: 0; 1; 1; 0; Actual: {0}", prediction.ToString().Replace("\n", "; "));
#endregion
}
