public void Train(ILabeledExampleCollection <LblT, SparseVector <double> > dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(dataset.Count == 0 ? new ArgumentValueException("dataset") : null);
Dictionary <LblT, CentroidData> centroids = new Dictionary <LblT, CentroidData>(mLblCmp);
foreach (LabeledExample <LblT, SparseVector <double> > labeledExample in dataset)
{
if (!centroids.ContainsKey(labeledExample.Label))
{
CentroidData centroidData = new CentroidData();
centroidData.AddToSum(labeledExample.Example);
centroids.Add(labeledExample.Label, centroidData);
}
else
{
CentroidData centroidData = centroids[labeledExample.Label];
centroidData.AddToSum(labeledExample.Example);
}
}
foreach (CentroidData cenData in centroids.Values)
{
cenData.UpdateCentroidLen();
}
double learnRate = 1;
double[][] dotProd = null;
SparseMatrix <double> dsMtx = null;
if (mIterations > 0)
{
dotProd = new double[centroids.Count][];
dsMtx = ModelUtils.GetTransposedMatrix(ModelUtils.ConvertToUnlabeledDataset(dataset));
}
for (int iter = 1; iter <= mIterations; iter++)
{
mLogger.Info("Train", "Iteration {0} / {1} ...", iter, mIterations);
// compute dot products
mLogger.Info("Train", "Computing dot products ...");
int j = 0;
foreach (KeyValuePair <LblT, CentroidData> labeledCentroid in centroids)
{
mLogger.ProgressNormal(Logger.Level.Info, /*sender=*/ this, "Train", "Centroid {0} / {1} ...", j + 1, centroids.Count);
SparseVector <double> cenVec = labeledCentroid.Value.GetSparseVector();
dotProd[j] = ModelUtils.GetDotProductSimilarity(dsMtx, dataset.Count, cenVec);
j++;
}
// classify training examples
mLogger.Info("Train", "Classifying training examples ...");
int errCount = 0;
for (int instIdx = 0; instIdx < dataset.Count; instIdx++)
{
mLogger.ProgressFast(Logger.Level.Info, /*sender=*/ this, "Train", "Example {0} / {1} ...", instIdx + 1, dataset.Count);
double maxSim = double.MinValue;
CentroidData assignedCentroid = null;
CentroidData actualCentroid = null;
LabeledExample <LblT, SparseVector <double> > labeledExample = dataset[instIdx];
SparseVector <double> vec = labeledExample.Example;
int cenIdx = 0;
foreach (KeyValuePair <LblT, CentroidData> labeledCentroid in centroids)
{
double sim = dotProd[cenIdx][instIdx];
if (sim > maxSim)
{
maxSim = sim; assignedCentroid = labeledCentroid.Value;
}
if (labeledCentroid.Key.Equals(labeledExample.Label))
{
actualCentroid = labeledCentroid.Value;
}
cenIdx++;
}
if (assignedCentroid != actualCentroid)
{
assignedCentroid.AddToDiff(-learnRate, vec);
actualCentroid.AddToDiff(learnRate, vec);
errCount++;
}
}
mLogger.Info("Train", "Training set error rate: {0:0.00}%", (double)errCount / (double)dataset.Count * 100.0);
// update centroids
int k = 0;
foreach (CentroidData centroidData in centroids.Values)
{
mLogger.ProgressNormal(Logger.Level.Info, /*sender=*/ this, "Train", "Centroid {0} / {1} ...", ++k, centroids.Count);
centroidData.Update(mPositiveValuesOnly);
centroidData.UpdateCentroidLen();
}
learnRate *= mDamping;
}
mCentroidMtxTr = new SparseMatrix <double>();
mLabels = new ArrayList <LblT>();
int rowIdx = 0;
foreach (KeyValuePair <LblT, CentroidData> labeledCentroid in centroids)
{
mCentroidMtxTr[rowIdx++] = labeledCentroid.Value.GetSparseVector();
mLabels.Add(labeledCentroid.Key);
}
mCentroidMtxTr = mCentroidMtxTr.GetTransposedCopy();
}
public void Train(IExampleCollection <LblT, SparseVector <double> .ReadOnly> dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(dataset.Count == 0 ? new ArgumentValueException("dataset") : null);
m_centroids = new Dictionary <LblT, CentroidData>();
foreach (LabeledExample <LblT, SparseVector <double> .ReadOnly> labeled_example in dataset)
{
if (!m_centroids.ContainsKey(labeled_example.Label))
{
CentroidData centroid_data = new CentroidData();
centroid_data.AddToSum(labeled_example.Example);
m_centroids.Add(labeled_example.Label, centroid_data);
}
else
{
CentroidData centroid_data = m_centroids[labeled_example.Label];
centroid_data.AddToSum(labeled_example.Example);
}
}
foreach (CentroidData vec_data in m_centroids.Values)
{
vec_data.UpdateCentroidLen();
}
double learn_rate = 1;
for (int iter = 1; iter <= m_iterations; iter++)
{
Utils.VerboseLine("Iteration {0} / {1} ...", iter, m_iterations);
// classify training documents
int i = 0;
int num_miscfy = 0;
foreach (LabeledExample <LblT, SparseVector <double> .ReadOnly> labeled_example in dataset)
{
Utils.Verbose("\rExample {0} / {1} ...", ++i, dataset.Count);
double max_sim = double.MinValue;
CentroidData assigned_centroid = null;
CentroidData actual_centroid = null;
SparseVector <double> .ReadOnly vec = labeled_example.Example;
foreach (KeyValuePair <LblT, CentroidData> labeled_centroid in m_centroids)
{
double sim = labeled_centroid.Value.GetSimilarity(vec);
if (sim > max_sim)
{
max_sim = sim; assigned_centroid = labeled_centroid.Value;
}
if (labeled_centroid.Key.Equals(labeled_example.Label))
{
actual_centroid = labeled_centroid.Value;
}
}
if (assigned_centroid != actual_centroid)
{
assigned_centroid.AddToDiff(-learn_rate, vec);
actual_centroid.AddToDiff(learn_rate, vec);
num_miscfy++;
}
}
Utils.VerboseLine("");
Utils.VerboseLine("Training set error rate: {0:0.00}%", (double)num_miscfy / (double)dataset.Count * 100.0);
// update centroids
i = 0;
foreach (CentroidData centroid_data in m_centroids.Values)
{
Utils.Verbose("\rCentroid {0} / {1} ...", ++i, m_centroids.Count);
centroid_data.UpdateCentroid(m_positive_values_only);
centroid_data.UpdateCentroidLen();
}
Utils.VerboseLine("");
learn_rate *= m_damping;
}
}