protected void btnGenerate_Click(Object Sender, EventArgs e)
{
int intSQL = (radYes.Checked ? 1 : (radNo.Checked ? 0 : -1));
intInstance = oCluster.AddInstance(intCluster, txtName.Text, intSQL);
double dblSize = double.Parse(txtSize.Text);
double dblQA = double.Parse(txtQA.Text);
double dblTest = double.Parse(txtTest.Text);
int intNon = (radNonYes.Checked ? 1 : 0);
double dblNon = 0.00;
double dblNonQA = 0.00;
double dblNonTest = 0.00;
if (intNon == 1)
{
dblNon = double.Parse(txtNon.Text);
dblNonQA = double.Parse(txtNonQA.Text);
dblNonTest = double.Parse(txtNonTest.Text);
}
oStorage.AddLunSQL(intAnswer, intInstance, intCluster, 0, 0, dblSize, dblQA, dblTest, dblNon, dblNonQA, dblNonTest);
Response.Redirect(Request.Path + "?aid=" + intAnswer + "&cid=" + intCluster + "&save=true");
}
public override void VTrain(VMatrix features, VMatrix labels)
{
_features = new VMatrix(features, 0, 0, features.Rows(), features.Cols());
if (labels.Data != null)
{
_labels = new VMatrix(labels, 0, 0, labels.Rows(), labels.Cols());
}
_clusters = new List <Cluster>();
Console.Write("Algorithm: ");
if (_algorithm == "k")
{
Console.WriteLine("k-means (k = " + _k + ")");
// Features.Shuffle(Rand, Labels);
// create the initial clusters
for (var k = 0; k < _k; k++)
{
var cluster = new Cluster(k, _features, k, _ignore);
_clusters.Add(cluster);
if (_outputFile != null)
{
cluster.PrintCentroid(_outputFile);
}
}
double lastSsd = double.MinValue;
for (;;)
{
var ssd = TrainK();
if (_outputFile != null)
{
_outputFile.WriteLine(string.Format("Sum squared-distance of each row with its centroid={0}", ssd));
}
if (ssd != lastSsd)
{
lastSsd = ssd;
if (_outputFile != null)
{
_outputFile.WriteLine("Recomputing the centroids of each cluster...");
}
foreach (var cluster in _clusters)
{
cluster.Recalculate();
cluster.ClearInstances();
if (_outputFile != null)
{
cluster.PrintCentroid(_outputFile);
}
}
}
else
{
break;
}
}
}
else if (_algorithm == "single")
{
if (_outputFile != null)
{
_outputFile.WriteLine("HAC single (k = " + _k + ")");
}
// create the initial clusters
for (var row = 0; row < _features.Rows(); row++)
{
var cluster = new Cluster(0, _features, row, _ignore);
cluster.AddInstance(row);
_clusters.Add(cluster);
}
// create the distance matrix
_distances = new double[_features.Rows(), _features.Rows()];
for (var row = 0; row < _features.Rows(); row++)
{
for (var row2 = row; row2 < _features.Rows(); row2++)
{
double distance = 0;
if (row2 > row)
{
distance = _clusters[row].GetDistance(_features.Row(row2));
}
_distances[row, row2] = distance;
if (row != row2)
{
_distances[row2, row] = distance;
}
}
}
int iteration = 0;
do
{
TrainSingle(iteration++);
} while (_clusters.Count > _k);
}
else if (_algorithm == "complete")
{
if (_outputFile != null)
{
_outputFile.WriteLine("HAC complete (k = " + _k + ")");
}
// create the initial clusters
for (var row = 0; row < _features.Rows(); row++)
{
var cluster = new Cluster(0, _features, row, _ignore);
cluster.AddInstance(row);
_clusters.Add(cluster);
}
// create the distance matrix
_distances = new double[_features.Rows(), _features.Rows()];
for (var row = 0; row < _features.Rows(); row++)
{
for (var row2 = row; row2 < _features.Rows(); row2++)
{
double distance = 0;
if (row2 > row)
{
distance = _clusters[row].GetDistance(_features.Row(row2));
}
_distances[row, row2] = distance;
if (row != row2)
{
_distances[row2, row] = distance;
}
}
}
int iteration = 0;
do
{
TrainComplete(iteration++);
} while (_clusters.Count > _k);
}
else if (_algorithm == "average")
{
if (_outputFile != null)
{
_outputFile.WriteLine("HAC average (k = " + _k + ")");
}
// create the initial clusters
for (var row = 0; row < _features.Rows(); row++)
{
var cluster = new Cluster(0, _features, row, _ignore);
cluster.AddInstance(row);
_clusters.Add(cluster);
}
// create the distance matrix
_distances = new double[_features.Rows(), _features.Rows()];
for (var row = 0; row < _features.Rows(); row++)
{
for (var row2 = row; row2 < _features.Rows(); row2++)
{
double distance = 0;
if (row2 > row)
{
distance = _clusters[row].GetDistance(_features.Row(row2));
}
_distances[row, row2] = distance;
if (row != row2)
{
_distances[row2, row] = distance;
}
}
}
int iteration = 0;
do
{
TrainAverage(iteration++);
} while (_clusters.Count > _k);
}
else
{
throw new Exception("Inavlid Algorithm - " + _algorithm);
}
if (_outputFile != null)
{
_outputFile.WriteLine();
_outputFile.WriteLine("Cluster centroids:");
_outputFile.Write("Cluster#\t\t\t");
for (var c = 0; c < _clusters.Count; c++)
{
_outputFile.Write("\t\t" + c);
}
_outputFile.WriteLine();
_outputFile.Write("# of instances:\t\t\t");
for (var c = 0; c < _clusters.Count; c++)
{
_outputFile.Write("\t\t" + _clusters[c].Instances.Count);
}
_outputFile.WriteLine();
_outputFile.WriteLine("==========================================================================================================");
for (var col = 0; col < _features.Cols(); col++)
{
if (!_ignore.Contains(col))
{
_outputFile.Write(_features.AttrName(col));
foreach (var cluster in _clusters)
{
if (cluster.Centroid[col] == Matrix.MISSING)
{
_outputFile.Write("\t?");
}
else if (_features.ValueCount(col) < 2)
{
// continuous
_outputFile.Write(string.Format("\t{0:0.#####}", cluster.Centroid[col]));
}
else
{
_outputFile.Write("\t" + _features.AttrValue(col, (int)cluster.Centroid[col]));
}
}
_outputFile.WriteLine();
}
}
double sse = 0;
_outputFile.Write("Sum squared error:\t");
foreach (var cluster in _clusters)
{
var error = cluster.GetSSE();
sse += error;
_outputFile.Write(string.Format("\t{0:0.#####}", error));
}
_outputFile.WriteLine();
_outputFile.WriteLine("Number of clusters: " + _clusters.Count);
_outputFile.WriteLine(string.Format("Total sum squared error: {0:0.#####}", sse));
_outputFile.WriteLine(string.Format("DBI: {0}", GetDBI()));
}
if (_outputFile != null)
{
_outputFile.Close();
}
}
