// check the accuracy so far
private double GetAccuracy(int instance, VMatrix features, VMatrix labels)
{
var eCount = 0;
for (var row = 0; row < features.Rows(); row++)
{
double net = 0;
for (var col = 0; col < features.Cols(); col++)
{
net += m_weights[instance][col] * features.Row(row)[col];
}
// add the bias
net += m_weights[instance][m_weights[instance].Length - 1];
var z = (net > 0 ? 1.0 : 0);
var t = labels.Row(row)[0];
if (m_count > 2)
{
t = (t == instance) ? 1.0 : 0;
}
if (t != z)
{
eCount++;
}
}
return(1.0 - (1.0 * eCount / features.Rows()));
}
private double TrainK()
{
if (_outputFile != null)
{
_outputFile.WriteLine("Assigning each row to the cluster of the nearest centroid...");
_outputFile.WriteLine("The cluster assignments are:");
}
// add the training set elements to the clusters
for (var row = 0; row < _features.Rows(); row++)
{
var cluster = GetNearestCluster(_features.Row(row));
cluster.AddInstance(row);
if (_outputFile != null)
{
if (row % 10 == 0)
{
_outputFile.WriteLine();
_outputFile.Write("\t");
}
else
{
_outputFile.Write(", ");
}
_outputFile.Write(string.Format("{0}={1}", row, cluster.Number));
}
}
if (_outputFile != null)
{
_outputFile.WriteLine();
}
double sse = 0;
foreach (var cluster in _clusters)
{
sse += cluster.GetSSE();
}
return(sse);
}
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();
}
}
// Move the inputs down one slot
private void SetInputs(VMatrix features, int row)
{
SetInputs(features.Row(row));
}
public double VMeasureAccuracy(VMatrix features, VMatrix labels, Matrix confusion)
{
if (features.Rows() != labels.Rows())
{
throw (new Exception("Expected the features and labels to have the same number of rows"));
}
if (labels.Cols() != 1)
{
throw (new Exception("Sorry, this method currently only supports one-dimensional labels"));
}
if (features.Rows() == 0)
{
throw (new Exception("Expected at least one row"));
}
var cl = 0;
if (Parameters.Verbose)
{
Console.Write("VMeasureAccuracy ");
cl = Console.CursorLeft;
}
var count = features.Rows();
var begRow = 0;
if (this is BPTT)
{
var learner = this as BPTT;
begRow = learner.m_k - 1;
count -= begRow;
}
var labelValues = labels.ValueCount(0);
if (labelValues == 0) // If the label is continuous...
{
// The label is continuous, so measure root mean squared error
var pred = new double[1];
var sse = 0.0;
for (var i = 0; i < features.Rows(); i++)
{
if (Parameters.Verbose)
{
Console.SetCursorPosition(cl, Console.CursorTop);
Console.Write(i);
}
var feat = features.Row(i);
var targ = labels.Row(i);
pred[0] = 0.0; // make sure the prediction is not biased by a previous prediction
Predict(feat, pred);
if (i >= begRow)
{
var delta = targ[0] - pred[0];
sse += (delta * delta);
}
}
if (Parameters.Verbose)
{
Console.WriteLine();
}
return(Math.Sqrt(sse / count));
}
else
{
// The label is nominal, so measure predictive accuracy
if (confusion != null)
{
confusion.SetSize(labelValues, labelValues);
for (var i = 0; i < labelValues; i++)
{
confusion.SetAttrName(i, labels.AttrValue(0, i));
}
}
var correctCount = 0;
var prediction = new double[1];
for (var i = 0; i < features.Rows(); i++)
{
if (Parameters.Verbose)
{
Console.SetCursorPosition(cl, Console.CursorTop);
Console.Write(i);
}
var feat = features.Row(i);
var lab = labels.Get(i, 0);
if (lab != Matrix.MISSING)
{
var targ = (int)lab;
if (targ >= labelValues)
{
throw new Exception("The label is out of range");
}
Predict(feat, prediction);
if (i >= begRow)
{
var pred = (int)prediction[0];
if (confusion != null)
{
confusion.Set(targ, pred, confusion.Get(targ, pred) + 1);
}
if (pred == targ)
{
correctCount++;
}
}
}
else
{
count--;
}
}
if (Parameters.Verbose)
{
Console.WriteLine();
}
return((double)correctCount / count);
}
}
private double TrainEpoch(int instance, int epoch, VMatrix features, VMatrix labels)
{
if (m_outputFile == null)
{
Console.WriteLine(epoch);
}
var eCount = 0;
for (var row = 0; row < features.Rows(); row++)
{
double net = 0;
// calculate the net value
for (var col = 0; col < features.Cols(); col++)
{
net += m_weights[instance][col] * features.Row(row)[col];
}
// add the bias
net += m_weights[instance][m_weights[instance].Length - 1];
var z = (net > 0 ? 1.0 : 0);
var t = labels.Row(row)[0];
if (m_count > 2)
{
t = (t == instance) ? 1.0 : 0;
}
// check to see if the predicted matches the actual
if (z != t)
{
eCount++;
double delta;
// adjust the weights
for (var i = 0; i < m_weights[instance].Length - 1; i++)
{
delta = (t - z) * m_rate * features.Row(row)[i];
//Console.Write(string.Format("{0}\t", delta));
m_weights[instance][i] += delta;
}
// adjust the bias weight
delta = (t - z) * m_rate;
//Console.WriteLine(delta);
m_weights[instance][m_weights[instance].Length - 1] += delta;
}
}
// print the new weights
if (m_outputFile == null)
{
for (var i = 0; i < m_weights[instance].Length - 1; i++)
{
Console.Write(string.Format("{0}\t", m_weights[instance][i]));
}
Console.WriteLine(m_weights[instance][m_weights[instance].Length - 1]);
}
var error = 1.0 * eCount / features.Rows();
if (m_outputFile == null)
{
Console.WriteLine(error);
Console.WriteLine();
}
else
{
m_outputFile.WriteLine(string.Format("{0}\t{1}", epoch, error));
}
return(error);
}