private ClusteringResult CreateSingleCluster(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
ClusteringResult clustering = new ClusteringResult();
Cluster root = new Cluster();
for (int i = 0; i < dataset.Count; i++)
{
root.Items.Add(i);
}
clustering.AddRoot(root);
CentroidData centroid = new CentroidData();
centroid.Items.AddRange(root.Items);
centroid.Update(dataset);
centroid.UpdateCentroidLen();
mCentroids = new ArrayList <CentroidData>();
mCentroids.Add(centroid);
return(clustering);
}
private void GetMostSimilarClusters(out int idx1, out int idx2)
{
double maxSim = 0;
idx1 = 0;
idx2 = 1;
for (int i1 = 0; i1 < mCentroids.Count; i1++)
{
for (int i2 = i1 + 1; i2 < mCentroids.Count; i2++)
{
CentroidData c1 = mCentroids[i1];
CentroidData c2 = mCentroids[i2];
double sim = c1.GetDotProduct(c2.GetSparseVector());
if (sim > maxSim)
{
maxSim = sim;
idx1 = i1;
idx2 = i2;
}
}
}
}
public ClusteringResult Cluster(int numOutdated, IUnlabeledExampleCollection <SparseVector <double> > batch)
{
Utils.ThrowException(batch == null ? new ArgumentNullException("batch") : null);
Utils.ThrowException(numOutdated < 0 ? new ArgumentOutOfRangeException("numOutdated") : null);
if (mDataset == null)
{
// initialize
mLogger.Trace("Cluster", "Initializing ...");
Utils.ThrowException(numOutdated > 0 ? new ArgumentOutOfRangeException("numOutdated") : null);
//Utils.ThrowException(batch.Count == 0 ? new ArgumentValueException("batch") : null);
if (batch.Count == 0)
{
return(new ClusteringResult());
}
kMeans(batch, Math.Min(mK, batch.Count));
mDataset = new UnlabeledDataset <SparseVector <double> >(batch);
foreach (CentroidData centroid in mCentroids)
{
centroid.Tag = mTopicId++;
}
//OutputState();
}
else
{
// update clusters
Utils.ThrowException(numOutdated > mDataset.Count ? new ArgumentOutOfRangeException("numOutdated") : null);
if (numOutdated == 0 && batch.Count == 0)
{
return(GetClusteringResult());
}
mLogger.Trace("Cluster", "Updating clusters ...");
// assign new instances
double dummy;
Assign(mCentroids, ModelUtils.GetTransposedMatrix(batch), batch.Count, /*offs=*/ mDataset.Count, out dummy);
mDataset.AddRange(batch);
// remove outdated instances
foreach (CentroidData centroid in mCentroids)
{
foreach (int item in centroid.CurrentItems)
{
if (item >= numOutdated)
{
centroid.Items.Add(item);
}
}
centroid.Update(mDataset);
centroid.UpdateCentroidLen();
}
mDataset.RemoveRange(0, numOutdated);
ArrayList <CentroidData> centroidsNew = new ArrayList <CentroidData>(mCentroids.Count);
foreach (CentroidData centroid in mCentroids)
{
if (centroid.CurrentItems.Count > 0)
{
centroidsNew.Add(centroid);
Set <int> tmp = new Set <int>();
foreach (int idx in centroid.CurrentItems)
{
tmp.Add(idx - numOutdated);
}
centroid.CurrentItems.Inner.SetItems(tmp);
}
}
if (centroidsNew.Count == 0) // reset
{
mCentroids = null;
mDataset = null;
return(new ClusteringResult());
}
mCentroids = centroidsNew;
// execute main loop
kMeansMainLoop(mDataset, mCentroids);
//OutputState();
}
// adjust k
double minQual; // *** not used at the moment
int minQualIdx;
double qual = GetClustQual(out minQual, out minQualIdx);
if (qual < mQualThresh)
{
while (qual < mQualThresh) // split cluster at minQualIdx
{
mLogger.Trace("Cluster", "Increasing k to {0} ...", mCentroids.Count + 1);
mCentroids.Add(mCentroids[minQualIdx].Clone());
mCentroids.Last.Tag = mTopicId++;
kMeansMainLoop(mDataset, mCentroids);
if (mCentroids.Last.CurrentItems.Count > mCentroids[minQualIdx].CurrentItems.Count)
{
// swap topic identifiers
object tmp = mCentroids.Last.Tag;
mCentroids.Last.Tag = mCentroids[minQualIdx].Tag;
mCentroids[minQualIdx].Tag = tmp;
}
qual = GetClustQual(out minQual, out minQualIdx);
//OutputState();
}
}
else if (numOutdated > 0)
{
while (qual > mQualThresh && mCentroids.Count > 1) // join clusters
{
mLogger.Trace("Cluster", "Decreasing k to {0} ...", mCentroids.Count - 1);
ArrayList <CentroidData> centroidsCopy = mCentroids.DeepClone();
if (mCentroids.Count == 2) // create single cluster
{
object topicId = mCentroids[0].CurrentItems.Count > mCentroids[1].CurrentItems.Count ? mCentroids[0].Tag : mCentroids[1].Tag;
mCentroids = new ArrayList <CentroidData>();
mCentroids.Add(new CentroidData());
for (int i = 0; i < mDataset.Count; i++)
{
mCentroids.Last.Items.Add(i);
}
mCentroids.Last.Tag = topicId;
mCentroids.Last.Update(mDataset);
mCentroids.Last.UpdateCentroidLen();
}
else
{
int idx1, idx2;
GetMostSimilarClusters(out idx1, out idx2);
CentroidData c1 = mCentroids[idx1];
CentroidData c2 = mCentroids[idx2];
object topicId = c1.CurrentItems.Count > c2.CurrentItems.Count ? c1.Tag : c2.Tag;
mCentroids.RemoveAt(idx2);
c1.Items.AddRange(c1.CurrentItems);
c1.Items.AddRange(c2.CurrentItems);
c1.Tag = topicId;
c1.Update(mDataset);
c1.UpdateCentroidLen();
kMeansMainLoop(mDataset, mCentroids);
}
qual = GetClustQual();
if (qual >= mQualThresh)
{
mLogger.Trace("Cluster", "Accepted solution at k = {0}.", mCentroids.Count);
}
else
{
mCentroids = centroidsCopy;
}
//OutputState();
}
}
OutputState();
return(GetClusteringResult());
}
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;
}
}