/**
* Builds the classifier
*
* @param train the training data to be used for generating the
* boosted classifier.
* @throws Exception if the classifier could not be built successfully
*/
public void buildClassifier()
{
Console.ForegroundColor = ConsoleColor.White;
Console.WriteLine("Extracting Data");
for (int i = 2; i >= 0; i--)
{
Console.Write(".");
Thread.Sleep(330);
Console.Write(".");
Thread.Sleep(330);
Console.Write(".");
Thread.Sleep(330);
Console.Write("\b\b\b \b\b\b");
Thread.Sleep(330);
}
char[] delimiters = new char[] { '\r', '\n' };
/* Load Labeled Data */
StreamReader s = new StreamReader("traindata.txt");
/* Read the data in the file */
string AllData = s.ReadToEnd();
/* Split off each row at the Carriage Return/Line Feed
This will work for Excel, Access, etc. default exports */
string[] rows = AllData.Split(delimiters, StringSplitOptions.RemoveEmptyEntries);
int i_1 = 0, j_1 = 0;
double[,] Data = new double[rows.Length, 20];
/* Add each row to the matrix */
foreach (string r in rows)
{
/* Split the row at the delimiter */
string[] items = r.Split('\t');
foreach (string ite in items)
{
Data[i_1, j_1] = Convert.ToDouble(ite);
j_1++;
}
j_1 = 0;
i_1++;
}
s.Close();
//const int m_ClassIndex = 19;
//const int m_NumClasses = 6;
int nK = m_NumClasses - 1; // Only K-1 class labels needed
int nR = Data.GetLength(1) - 1; // Parameters
int nC = Data.GetLength(0); // Trained Instances
double[,] m_Data = new double[nC, nR + 1]; // Data in new format
int[] Y = new int[nC]; // Class labels
double[] xMean = new double[nR + 1]; // Attribute means
double[] xSD = new double[nR + 1]; // Attribute stddev's
double[] sY = new double[nK + 1]; // Number of classes
double[,] m_Par = new double[nR + 1, nK]; // Optimized parameter values
for (int i = 0; i < nC; i++)
{
// initialize X[][]
Y[i] = (int)(Data[i, 19] - 1);
m_Data[i, 0] = 1;
int j = 1;
for (int k = 0; k <= nR; k++)
{
if (k != m_ClassIndex)
{
double z = Data[i, k];
m_Data[i, j] = z;
xMean[j] += z;
xSD[j] += z * z;
j++;
}
}
// Class count
sY[Y[i]]++;
}
xMean[0] = 0; xSD[0] = 1;
for (int j = 1; j <= nR; j++)
{
xMean[j] = xMean[j] / nC;
xSD[j] = Math.Sqrt(Math.Abs(xSD[j] - nC * xMean[j] * xMean[j]) / (nC - 1));
}
if (m_Debug)
{
// Output stats about input data
Console.WriteLine("Descriptives...");
for (int m = 0; m <= nK; m++)
Console.WriteLine("{0} cases have class {1}", sY[m], m);
Console.WriteLine("\n Variable Avg SD ");
for (int j = 1; j <= nR; j++)
Console.WriteLine(" {0} {1} {2}", j, xMean[j], xSD[j]);
}
// Normalise input data
for (int i = 0; i < nC; i++)
{
for (int j = 0; j <= nR; j++)
{
if (xSD[j] != 0)
m_Data[i, j] = (m_Data[i, j] - xMean[j]) / xSD[j];
}
}
Console.WriteLine("\nBuilding Model(This may take a while)");
double[] x = new double[(nR + 1) * nK];
double[,] b = new double[2, x.Length];// Boundary constraints, N/A here
// Initialize
for (int p = 0; p < nK; p++)
{
int offset = p * (nR + 1);
x[offset] = Math.Log(sY[p] + 1.0) - Math.Log(sY[nK] + 1.0); // Null model
b[0, offset] = Double.NaN;
b[1, offset] = Double.NaN;
for (int q = 1; q <= nR; q++)
{
x[offset + q] = 0.0;
b[0, offset + q] = Double.NaN;
b[1, offset + q] = Double.NaN;
}
}
setVar(m_Data, m_Par, xMean, xSD);
LogicOpt opt = new LogicOpt();
opt.setClassLabels(Y);
if (m_MaxIts == -1) // Search until convergence
{
x = opt.findArgMin(x, b);
while (x == null)
{
x = opt.getVarbValues();
Console.WriteLine("200 iterations finished, not enough!");
x = opt.findArgMin(x, b);
}
Console.WriteLine(" -------------<Converged>--------------");
}
else
{
opt.setMaxIteration(m_MaxIts);
x = opt.findArgMin(x, b);
if (x == null) // Not enough, but use the current value
x = opt.getVarbValues();
}
m_LL = -opt.getMinFunction(); // Log-likelihood
// Convert coefficients back to non-normalized attribute units
for (int i = 0; i < nK; i++)
{
m_Par[0, i] = x[i * (nR + 1)];
for (int j = 1; j <= nR; j++)
{
m_Par[j, i] = x[i * (nR + 1) + j];
if (xSD[j] != 0)
{
m_Par[j, i] /= xSD[j];
m_Par[0, i] -= m_Par[j, i] * xMean[j];
}
}
}
// Copy for global Parameters
setVar(m_Data, m_Par, xMean, xSD);
// Don't need data matrix anymore
m_Data = null;
}
public WhereSegmentNode(WhereNode left, LogicOpt opt, WhereNode right)
{
this.left = left;
this.opt = opt;
this.right = right;
}
