public ClusteringResult Cluster(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(dataset.Count < NumLeaves ? new ArgumentValueException("dataset") : null);
ClusteringResult clusters = mKMeansClustering.Cluster(dataset);
UnlabeledDataset <SparseVector <double> > centroids = new UnlabeledDataset <SparseVector <double> >();
foreach (Cluster cluster in clusters.Roots)
{
SparseVector <double> centroid = ModelUtils.ComputeCentroid(cluster.Items, dataset, CentroidType.NrmL2);
centroids.Add(centroid);
centroid = Trim(centroid, 1000, 0.8);
cluster.ClusterInfo = 1; // cluster level
}
SparseMatrix <double> simMtx = ModelUtils.GetDotProductSimilarity(centroids, /*thresh=*/ 0, /*fullMatrix=*/ false);
SparseMatrix <double> clustMtxTr = ModelUtils.GetTransposedMatrix(centroids);
int iter = 1;
while (clusters.Roots.Count > 1)
{
Console.WriteLine("Iteration {0} ...", iter++);
int idx1, idx2;
FindMaxSim(simMtx, out idx1, out idx2);
Update(simMtx, clustMtxTr, clusters.Roots.Count, idx1, idx2, clusters.Roots.Inner, dataset, /*damping=*/ 0.9);
Console.WriteLine(simMtx.ToString("E0.00"));
Console.WriteLine();
}
return(clusters);
}
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);
mDatasetMtx = ModelUtils.GetTransposedMatrix(ModelUtils.ConvertToUnlabeledDataset(dataset));
mLabels = new ArrayList <LblT>();
foreach (LabeledExample <LblT, SparseVector <double> > labeledExample in dataset)
{
mLabels.Add(labeledExample.Label);
}
}
internal void kMeansMainLoop(IUnlabeledExampleCollection <SparseVector <double> > dataset, ArrayList <CentroidData> centroids, out double clustQual)
{
double[][] dotProd = new double[centroids.Count][];
SparseMatrix <double> dataMtx = ModelUtils.GetTransposedMatrix(dataset);
int iter = 0;
double bestClustQual = 0;
while (true)
{
iter++;
mLogger.Trace("Cluster", "Iteration {0} ...", iter);
// assign items to clusters
Assign(centroids, dataMtx, dataset.Count, /*offs=*/ 0, out clustQual);
mLogger.Trace("Cluster", "Quality: {0:0.0000}", clustQual);
// update centroids
Update(dataset, centroids);
// check if done
if (iter > 1 && clustQual - bestClustQual <= mEps)
{
break;
}
bestClustQual = clustQual;
}
}
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 ClusteringResult Cluster(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(dataset.Count < mK ? new ArgumentValueException("dataset") : null);
ClusteringResult clustering = null;
double globalBestClustQual = 0;
for (int trial = 1; trial <= mTrials; trial++)
{
mLogger.Info("Cluster", "Clustering trial {0} of {1} ...", trial, mTrials);
ArrayList <CentroidData> centroids = new ArrayList <CentroidData>(mK);
ArrayList <int> bestSeeds = null;
for (int i = 0; i < mK; i++)
{
centroids.Add(new CentroidData());
}
// select seed items
double minSim = double.MaxValue;
ArrayList <int> tmp = new ArrayList <int>(dataset.Count);
for (int i = 0; i < dataset.Count; i++)
{
tmp.Add(i);
}
for (int k = 0; k < 3; k++)
{
ArrayList <SparseVector <double> > seeds = new ArrayList <SparseVector <double> >(mK);
tmp.Shuffle(mRnd);
for (int i = 0; i < mK; i++)
{
seeds.Add(dataset[tmp[i]]);
}
// assess quality of seed items
double simAvg = 0;
foreach (SparseVector <double> seed1 in seeds)
{
foreach (SparseVector <double> seed2 in seeds)
{
if (seed1 != seed2)
{
simAvg += DotProductSimilarity.Instance.GetSimilarity(seed1, seed2);
}
}
}
simAvg /= (double)(mK * mK - mK);
//Console.WriteLine(simAvg);
if (simAvg < minSim)
{
minSim = simAvg;
bestSeeds = new ArrayList <int>(mK);
for (int i = 0; i < mK; i++)
{
bestSeeds.Add(tmp[i]);
}
}
}
for (int i = 0; i < mK; i++)
{
centroids[i].Items.Add(bestSeeds[i]);
centroids[i].Update(dataset);
centroids[i].UpdateCentroidLen();
}
double[][] dotProd = new double[mK][];
SparseMatrix <double> dsMtx = ModelUtils.GetTransposedMatrix(dataset);
// main loop
int iter = 0;
double bestClustQual = 0;
double clustQual;
while (true)
{
iter++;
mLogger.Info("Cluster", "Iteration {0} ...", iter);
clustQual = 0;
// assign items to clusters
int j = 0;
foreach (CentroidData cen in centroids)
{
SparseVector <double> cenVec = cen.GetSparseVector();
dotProd[j] = ModelUtils.GetDotProductSimilarity(dsMtx, dataset.Count, cenVec);
j++;
}
for (int instIdx = 0; instIdx < dataset.Count; instIdx++)
{
double maxSim = double.MinValue;
ArrayList <int> candidates = new ArrayList <int>();
for (int cenIdx = 0; cenIdx < mK; cenIdx++)
{
double sim = dotProd[cenIdx][instIdx];
if (sim > maxSim)
{
maxSim = sim;
candidates.Clear();
candidates.Add(cenIdx);
}
else if (sim == maxSim)
{
candidates.Add(cenIdx);
}
}
if (candidates.Count > 1)
{
candidates.Shuffle(mRnd);
}
if (candidates.Count > 0) // *** is this always true?
{
centroids[candidates[0]].Items.Add(instIdx);
clustQual += maxSim;
}
}
clustQual /= (double)dataset.Count;
mLogger.Info("Cluster", "Quality: {0:0.0000}", clustQual);
// check if done
if (iter > 1 && clustQual - bestClustQual <= mEps)
{
break;
}
bestClustQual = clustQual;
// compute new centroids
for (int i = 0; i < mK; i++)
{
centroids[i].Update(dataset);
centroids[i].UpdateCentroidLen();
}
}
if (trial == 1 || clustQual > globalBestClustQual)
{
globalBestClustQual = clustQual;
// save the result
clustering = new ClusteringResult();
for (int i = 0; i < mK; i++)
{
clustering.AddRoot(new Cluster());
clustering.Roots.Last.Items.AddRange(centroids[i].Items);
}
}
}
return(clustering);
}
