/// <summary>
/// Test cross validation
/// </summary>
public static void Test_CalcProbability_Xval(int data_set_index)
{
List <MLDataPoint> X = MLDataPointUtil.LoadDataSet(string.Format("X{0}.txt", data_set_index));
List <MLDataPoint> Xval = MLDataPointUtil.LoadDataSet(string.Format("Xval{0}.txt", data_set_index));
MultiVariateGaussianDistributionAD <MLDataPoint> algorithm = new MultiVariateGaussianDistributionAD <MLDataPoint>();
algorithm.ComputeGaussianDistribution(X);
List <MLDataPoint> correct_pval = MLDataPointUtil.LoadDataSet(string.Format("pval{0}.txt", data_set_index));
int row_count = Xval.Count;
double total_error = 0;
for (int i = 0; i < row_count; ++i)
{
double pval = algorithm.CalcProbability(Xval[i]);
double error = System.Math.Abs(correct_pval[i][0] - pval);
total_error += error;
Console.WriteLine("pval={0} correct_pval={1}", pval, correct_pval[i]);
}
Console.WriteLine("Total error: {0}", total_error);
}
public static void Test_FindOutliers(int data_set_index)
{
double threshold, F1Score;
SelectThreshold(data_set_index, out F1Score, out threshold);
List <MLDataPoint> X = MLDataPointUtil.LoadDataSet(string.Format("X{0}.txt", data_set_index));
List <MLDataPoint> correct_outliers = MLDataPointUtil.LoadDataSet(string.Format("outliers{0}.txt", data_set_index));
Console.WriteLine("Correct Outliers:");
for (int i = 0; i < correct_outliers.Count; ++i)
{
Console.WriteLine("{0}", correct_outliers[i][0]);
}
MultiVariateGaussianDistributionAD <MLDataPoint> algorithm = new MultiVariateGaussianDistributionAD <MLDataPoint>();
algorithm.ComputeGaussianDistribution(X);
List <int> outliers = algorithm.FindOutliers(X, threshold);
Console.WriteLine("Predict Outliers:");
for (int i = 0; i < outliers.Count; ++i)
{
Console.WriteLine("{0}", outliers[i] + 1);
}
Console.WriteLine("Point Count: {0}", X.Count);
Console.WriteLine("Threshold: {0}", threshold);
Console.WriteLine("Predict Outliers Count; {0} Correct Outliers Count: {1}", outliers.Count, correct_outliers.Count);
}
public static void Test_LoadDataSet()
{
List <MLDataPoint> X1 = MLDataPointUtil.LoadDataSet("X1.txt");
List <MLDataPoint> Xval1 = MLDataPointUtil.LoadDataSet("Xval1.txt");
List <MLDataPoint> yval1 = MLDataPointUtil.LoadDataSet("yval1.txt");
List <MLDataPoint> X2 = MLDataPointUtil.LoadDataSet("X2.txt");
List <MLDataPoint> Xval2 = MLDataPointUtil.LoadDataSet("Xval2.txt");
List <MLDataPoint> yval2 = MLDataPointUtil.LoadDataSet("yval2.txt");
int row_count, col_count;
MLDataPointUtil.GetSize(X1, out row_count, out col_count);
Console.WriteLine("size(X1)=[{0} {1}]", row_count, col_count);
MLDataPointUtil.GetSize(Xval1, out row_count, out col_count);
Console.WriteLine("size(Xval1)=[{0} {1}]", row_count, col_count);
MLDataPointUtil.GetSize(yval1, out row_count, out col_count);
Console.WriteLine("size(yval1)=[{0} {1}]", row_count, col_count);
MLDataPointUtil.GetSize(X2, out row_count, out col_count);
Console.WriteLine("size(X2)=[{0} {1}]", row_count, col_count);
MLDataPointUtil.GetSize(Xval2, out row_count, out col_count);
Console.WriteLine("size(Xval2)=[{0} {1}]", row_count, col_count);
MLDataPointUtil.GetSize(yval2, out row_count, out col_count);
Console.WriteLine("size(yval2)=[{0} {1}]", row_count, col_count);
}
private void ImportData(string X_filepath, string y_filepath)
{
mTrainingPercent = 100;
mTestingPercent = 0;
mCrossValidationPercent = 0;
lvTabularData.Items.Clear();
lvTabularData.Columns.Clear();
List <MLDataPoint> X_points = MLDataPointUtil.LoadDataSet(X_filepath);
List <List <int> > y_points = IntDataTableUtil.LoadDataSet(y_filepath);
List <CDataRecord> X = new List <CDataRecord>();
for (int i = 0; i < X_points.Count; ++i)
{
CDataRecord X_i = new CDataRecord(X_points[i].Dimension);
for (int j = 0; j < X_points[i].Dimension; ++j)
{
X_i[j + 1] = X_points[i][j];
}
X_i.Label = y_points[i][0].ToString();
X.Add(X_i);
}
lvTabularData.Columns.Add("#");
for (int i = 0; i < X[0].Dimension; ++i)
{
lvTabularData.Columns.Add(string.Format("X[{0}]", i));
}
lvTabularData.Columns.Add("Y");
lvTabularData.Columns.Add("Data Set");
lvTabularData.Columns.Add("Predicted Y");
int m = X.Count;
for (int i = 0; i < m; ++i)
{
CDataRecord X_i = X[i];
ListViewItem item = new ListViewItem();
item.Text = (lvTabularData.Items.Count + 1).ToString();
for (int j = 0; j < X_i.Dimension; ++j)
{
item.SubItems.Add(X_i[j].ToString());
}
item.SubItems.Add(X_i.Label.ToString());
item.SubItems.Add(X_i.DataSetType.ToString());
item.SubItems.Add(X_i.PredictedLabel.ToString());
item.Tag = X_i;
item.ForeColor = Color.Green;
lvTabularData.Items.Add(item);
}
}
protected static void SelectThreshold(int data_set_index, out double F1Score, out double threshold)
{
List <MLDataPoint> X = MLDataPointUtil.LoadDataSet(string.Format("X{0}.txt", data_set_index));
List <MLDataPoint> Xval = MLDataPointUtil.LoadDataSet(string.Format("Xval{0}.txt", data_set_index));
List <MLDataPoint> yval_temp = MLDataPointUtil.LoadDataSet(string.Format("yval{0}.txt", data_set_index));
bool[] yval = new bool[yval_temp.Count];
int row_count = yval_temp.Count;
for (int i = 0; i < row_count; ++i)
{
yval[i] = yval_temp[i][0] > 0.5;
}
MultiVariateGaussianDistributionAD <MLDataPoint> algorithm = new MultiVariateGaussianDistributionAD <MLDataPoint>();
threshold = algorithm.SelectThreshold(X, Xval, yval, out F1Score);
}
public static void Run_Classify2()
{
List <MLDataPoint> X_points = MLDataPointUtil.LoadDataSet("X1.txt");
List <List <int> > y_points = IntDataTableUtil.LoadDataSet("y1.txt");
List <CDataRecord> X = new List <CDataRecord>();
for (int i = 0; i < X_points.Count; ++i)
{
CDataRecord X_i = new CDataRecord(X_points[i].Dimension);
for (int j = 0; j < X_points[i].Dimension; ++j)
{
X_i[i + 1] = X_points[i][j]; //X_i index must start at 1
}
X_i.Label = y_points[i][0].ToString();
X.Add(X_i);
}
LinearSVM <CDataRecord> algorithm = new LinearSVM <CDataRecord>();
algorithm.C = 100;
algorithm.Train(X);
}