public static SparseMatrix <double> GetDotProductSimilarity(IUnlabeledExampleCollection <SparseVector <double> > dataset, double thresh, bool fullMatrix)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(thresh < 0 ? new ArgumentOutOfRangeException("thresh") : null);
SparseMatrix <double> trMtx = GetTransposedMatrix(dataset);
double[] simVec = new double[dataset.Count];
SparseMatrix <double> simMtx = new SparseMatrix <double>();
int rowIdx = 0;
foreach (SparseVector <double> item in dataset)
{
GetDotProductSimilarity(item, simVec, trMtx, /*startIdx=*/ fullMatrix ? 0 : rowIdx); // if fullMatrix is false, upper (right) triangular sparse matrix of dot products is computed
for (int idx = 0; idx < simVec.Length; idx++)
{
double sim = simVec[idx];
if (sim > thresh)
{
if (!simMtx.ContainsRowAt(rowIdx))
{
simMtx[rowIdx] = new SparseVector <double>(new IdxDat <double>[] { new IdxDat <double>(idx, sim) });
}
else
{
simMtx[rowIdx].InnerIdx.Add(idx);
simMtx[rowIdx].InnerDat.Add(sim);
}
}
simVec[idx] = 0;
}
rowIdx++;
}
return(simMtx);
}
// *** Dataset utilities ***
public static SparseMatrix <double> GetTransposedMatrix(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
//if (dataset.Count == 0) { return new SparseMatrix<double>(); }
SparseMatrix <double> trMtx = new SparseMatrix <double>();
int rowIdx = 0;
foreach (SparseVector <double> item in dataset)
{
foreach (IdxDat <double> vecItem in item)
{
if (!trMtx.ContainsRowAt(vecItem.Idx))
{
trMtx[vecItem.Idx] = new SparseVector <double>(new IdxDat <double>[] { new IdxDat <double>(rowIdx, vecItem.Dat) });
}
else
{
trMtx[vecItem.Idx].InnerIdx.Add(rowIdx);
trMtx[vecItem.Idx].InnerDat.Add(vecItem.Dat);
}
}
rowIdx++;
}
return(trMtx);
}
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);
}
internal void Update(IUnlabeledExampleCollection <SparseVector <double> > dataset, ArrayList <CentroidData> centroids)
{
foreach (CentroidData centroid in centroids)
{
centroid.Update(dataset);
centroid.UpdateCentroidLen();
}
}
public LabeledDataset <Cluster, ExT> GetClassificationDataset <ExT>(IUnlabeledExampleCollection <ExT> dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
LabeledDataset <Cluster, ExT> classificationDataset = new LabeledDataset <Cluster, ExT>();
FillClassificationDataset(mRoots, dataset, classificationDataset); // throws ArgumentValueException
return(classificationDataset);
}
private void Update(SparseMatrix <double> simMtx, SparseMatrix <double> clustMtxTr, int numClusters, int idx1, int idx2, ArrayList <Cluster> clusters,
IUnlabeledExampleCollection <SparseVector <double> > dataset, double damping)
{
Debug.Assert(idx1 < idx2);
// create new parent
Cluster c1 = clusters[idx1];
Cluster c2 = clusters[idx2];
Cluster parent = new Cluster();
parent.Items.AddRange(c1.Items);
parent.Items.AddRange(c2.Items);
parent.ClusterInfo = Math.Max((int)c1.ClusterInfo, (int)c2.ClusterInfo) + 1;
c1.Parent = parent;
c2.Parent = parent;
parent.AddChild(c1);
parent.AddChild(c2);
SparseVector <double> centroid = ModelUtils.ComputeCentroid(parent.Items, dataset, CentroidType.NrmL2);
centroid = Trim(centroid, 1000, 0.8);
// remove clusters
clusters.RemoveAt(idx2);
clusters.RemoveAt(idx1);
// add new parent
clusters.Add(parent);
// remove rows at idx1 and idx2
simMtx.PurgeRowAt(idx2);
simMtx.PurgeRowAt(idx1);
// remove cols at idx1 and idx2
simMtx.PurgeColAt(idx2);
simMtx.PurgeColAt(idx1);
clustMtxTr.PurgeColAt(idx2);
clustMtxTr.PurgeColAt(idx1);
// update matrices
numClusters -= 2;
foreach (IdxDat <double> item in centroid)
{
if (clustMtxTr[item.Idx] == null)
{
clustMtxTr[item.Idx] = new SparseVector <double>(new IdxDat <double>[] { new IdxDat <double>(numClusters, item.Dat) });
}
else
{
clustMtxTr[item.Idx].InnerIdx.Add(numClusters);
clustMtxTr[item.Idx].InnerDat.Add(item.Dat);
}
}
double[] simVec = ModelUtils.GetDotProductSimilarity(clustMtxTr, numClusters + 1, centroid);
for (int i = 0; i < simVec.Length; i++)
{
simVec[i] *= Math.Pow(damping, (double)((int)parent.ClusterInfo + (int)clusters[i].ClusterInfo) / 2.0);
}
SparseMatrix <double> col = new SparseMatrix <double>();
col[0] = new SparseVector <double>(simVec);
simMtx.AppendCols(col.GetTransposedCopy(), numClusters);
}
public static double[] GetDotProductSimilarity(IUnlabeledExampleCollection <SparseVector <double> > dataset, SparseVector <double> .ReadOnly vec)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(vec == null ? new ArgumentNullException("vec") : null);
SparseMatrix <double> trMtx = GetTransposedMatrix(dataset);
double[] simVec = new double[dataset.Count];
GetDotProductSimilarity(vec, simVec, trMtx, /*startIdx=*/ 0);
return(simVec);
}
private void FillClassificationDataset <ExT>(IEnumerable <Cluster> clusters, IUnlabeledExampleCollection <ExT> dataset, LabeledDataset <Cluster, ExT> classificationDataset)
{
foreach (Cluster cluster in clusters)
{
foreach (int item in cluster.Items)
{
Utils.ThrowException(item < 0 || item >= dataset.Count ? new ArgumentValueException("clusters") : null);
classificationDataset.Add(cluster, dataset[item]);
}
FillClassificationDataset(cluster.Children, dataset, classificationDataset);
}
}
public void Train(IUnlabeledExampleCollection <SparseVector <double> > dataset, ClusteringResult hierarchy)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(dataset.Count == 0 ? new ArgumentValueException("dataset") : null);
Utils.ThrowException(hierarchy == null ? new ArgumentNullException("hierarchy") : null);
Utils.ThrowException(hierarchy.Roots.Count == 0 ? new ArgumentValueException("hierarchy") : null);
mModel = new Dictionary <Cluster, ClusterInfo>();
mDataset = dataset;
foreach (Cluster root in hierarchy.Roots)
{
ComputeCentroid(root);
}
mDataset = null;
}
private double GetClusterQuality(IUnlabeledExampleCollection <SparseVector <double> > dataset, out SparseVector <double> centroid)
{
// compute centroid
centroid = ModelUtils.ComputeCentroid(dataset, CentroidType.NrmL2);
// compute intra-cluster similarities
double[] simData = ModelUtils.GetDotProductSimilarity(dataset, centroid);
// compute cluster quality
double quality = 0;
for (int i = 0; i < simData.Length; i++)
{
quality += simData[i];
}
quality /= (double)simData.Length;
return(quality);
}
public static SparseVector <double> GetDotProductSimilarity(IUnlabeledExampleCollection <SparseVector <double> > dataset, SparseVector <double> .ReadOnly vec, double thresh)
{
Utils.ThrowException(thresh < 0 ? new ArgumentOutOfRangeException("thresh") : null);
double[] simVec = GetDotProductSimilarity(dataset, vec); // throws ArgumentNullException
SparseVector <double> sparseVec = new SparseVector <double>();
for (int i = 0; i < simVec.Length; i++)
{
if (simVec[i] > thresh)
{
sparseVec.InnerIdx.Add(i);
sparseVec.InnerDat.Add(simVec[i]);
}
}
return(sparseVec);
}
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);
}
public void Update(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
Set <int> addIdx = Set <int> .Difference(mItems, mCurrentItems);
Set <int> rmvIdx = Set <int> .Difference(mCurrentItems, mItems);
foreach (int itemIdx in addIdx)
{
SparseVector <double> vec = dataset[itemIdx];
AddToSum(vec);
}
foreach (int itemIdx in rmvIdx)
{
SparseVector <double> vec = dataset[itemIdx];
AddToDiff(-1, vec);
}
mCurrentItems = mItems;
mItems = new Set <int>();
Update(/*positiveValuesOnly=*/ false);
}
public ClusteringResult Cluster(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(dataset.Count < 2 ? new ArgumentValueException("dataset") : null);
ClusteringResult clusteringResult = new ClusteringResult();
Queue <Cluster> queue = new Queue <Cluster>();
// create root
Cluster root = new Cluster();
for (int i = 0; i < dataset.Count; i++)
{
Utils.ThrowException(dataset[i].Count == 0 ? new ArgumentValueException("dataset") : null);
root.Items.Add(i);
}
clusteringResult.AddRoot(root);
// add root to queue
queue.Enqueue(root);
while (queue.Count > 0)
{
// get next cluster
Cluster cluster = queue.Dequeue();
// compute cluster quality
UnlabeledDataset <SparseVector <double> > localDataset = GetDatasetSubset(cluster.Items, dataset);
SparseVector <double> centroid;
double quality = GetClusterQuality(localDataset, out centroid);
cluster.ClusterInfo = new Pair <SparseVector <double>, double>(centroid, quality);
if (quality < mMinQuality)
{
// split cluster, add children to queue
ClusteringResult localResult = mKMeansClustering.Cluster(localDataset);
for (int i = 0; i < 2; i++)
{
cluster.AddChild(localResult.Roots[i]);
localResult.Roots[i].Parent = cluster;
queue.Enqueue(localResult.Roots[i]);
}
}
}
return(clusteringResult);
}
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.Info("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.Info("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.Info("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.Info("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.Info("Cluster", "Accepted solution at k = {0}.", mCentroids.Count);
}
else
{
mCentroids = centroidsCopy;
}
//OutputState();
}
}
OutputState();
return GetClusteringResult();
}
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;
ClusteringResult bestClustering = null;
double globalBestClustQual = 0;
for (int trial = 1; trial <= mTrials; trial++)
{
mLogger.Trace("Cluster", "Clustering trial {0} of {1} ...", trial, mTrials);
ArrayList <SparseVector <double> > centroids = null;
clustering = new ClusteringResult();
for (int i = 0; i < mK; i++)
{
clustering.AddRoot(new Cluster());
}
// 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(ModelUtils.ComputeCentroid(new SparseVector <double>[] { dataset[tmp[i]] }, mCentroidType));
}
// assess quality of seed items
double simAvg = 0;
foreach (SparseVector <double> seed1 in seeds)
{
foreach (SparseVector <double> seed2 in seeds)
{
if (seed1 != seed2)
{
simAvg += mSimilarity.GetSimilarity(seed1, seed2);
}
}
}
simAvg /= (double)(mK * mK - mK);
if (simAvg < minSim)
{
minSim = simAvg;
centroids = seeds;
}
}
// main loop
int iter = 0;
double bestClustQual = 0;
double clustQual;
while (true)
{
iter++;
mLogger.Trace("Cluster", "Iteration {0} ...", iter);
clustQual = 0;
// assign items to clusters
foreach (Cluster cluster in clustering.Roots)
{
cluster.Items.Clear();
}
for (int i = 0; i < dataset.Count; i++)
{
SparseVector <double> example = dataset[i];
double maxSim = double.MinValue;
ArrayList <int> candidates = new ArrayList <int>();
for (int j = 0; j < mK; j++)
{
SparseVector <double> centroid = centroids[j];
double sim = mSimilarity.GetSimilarity(example, centroid);
if (sim > maxSim)
{
maxSim = sim;
candidates.Clear();
candidates.Add(j);
}
else if (sim == maxSim)
{
candidates.Add(j);
}
}
if (candidates.Count > 1)
{
candidates.Shuffle(mRnd);
}
clustering.Roots[candidates[0]].Items.Add(i);
clustQual += maxSim;
}
clustQual /= (double)dataset.Count;
mLogger.Trace("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] = clustering.Roots[i].ComputeCentroid(dataset, mCentroidType);
}
}
if (trial == 1 || clustQual > globalBestClustQual)
{
globalBestClustQual = clustQual;
bestClustering = clustering;
}
}
return(bestClustering);
}
public static SparseVector <double> ComputeCentroid(IEnumerable <int> vecIdxList, IUnlabeledExampleCollection <SparseVector <double> > dataset, CentroidType type)
{
Utils.ThrowException(vecIdxList == null ? new ArgumentNullException("vecIdxList") : null);
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Dictionary <int, double> tmp = new Dictionary <int, double>();
int vecCount = 0;
foreach (int vecIdx in vecIdxList)
{
Utils.ThrowException((vecIdx < 0 || vecIdx >= dataset.Count) ? new ArgumentValueException("vecIdxList") : null);
SparseVector <double> vec = dataset[vecIdx];
foreach (IdxDat <double> item in vec)
{
if (tmp.ContainsKey(item.Idx))
{
tmp[item.Idx] += item.Dat;
}
else
{
tmp.Add(item.Idx, item.Dat);
}
}
vecCount++;
}
//Utils.ThrowException(vecCount == 0 ? new ArgumentValueException("vecIdxList") : null);
if (vecCount == 0)
{
return(new SparseVector <double>());
}
SparseVector <double> centroid = new SparseVector <double>();
switch (type)
{
case CentroidType.Sum:
foreach (KeyValuePair <int, double> item in tmp)
{
centroid.InnerIdx.Add(item.Key);
centroid.InnerDat.Add(item.Value);
}
break;
case CentroidType.Avg:
foreach (KeyValuePair <int, double> item in tmp)
{
centroid.InnerIdx.Add(item.Key);
centroid.InnerDat.Add(item.Value / (double)vecCount);
}
break;
case CentroidType.NrmL2:
double vecLen = 0;
foreach (KeyValuePair <int, double> item in tmp)
{
vecLen += item.Value * item.Value;
}
//Utils.ThrowException(vecLen == 0 ? new InvalidOperationException() : null);
vecLen = Math.Sqrt(vecLen);
if (vecLen > 0)
{
foreach (KeyValuePair <int, double> item in tmp)
{
centroid.InnerIdx.Add(item.Key);
centroid.InnerDat.Add(item.Value / vecLen);
}
}
break;
}
centroid.Sort();
return(centroid);
}
public SparseVector<double> ComputeCentroid(IUnlabeledExampleCollection<SparseVector<double>> dataset, CentroidType type)
{
return ModelUtils.ComputeCentroid(mItems, dataset, type); // throws ArgumentNullException, ArgumentValueException, InvalidOperationException
}
private void kMeansMainLoop(IUnlabeledExampleCollection <SparseVector <double> > dataset, ArrayList <CentroidData> centroids)
{
double dummy;
kMeansMainLoop(dataset, centroids, out dummy);
}
protected ClusteringResult kMeans(IUnlabeledExampleCollection <SparseVector <double> > dataset, int k)
{
if (k == 1)
{
return(CreateSingleCluster(dataset));
} // border case
double globalBestClustQual = 0;
for (int trial = 1; trial <= mTrials; trial++)
{
mLogger.Trace("Cluster", "Clustering trial {0} of {1} ...", trial, mTrials);
ArrayList <CentroidData> centroids = new ArrayList <CentroidData>(k);
ArrayList <int> bestSeeds = null;
for (int i = 0; i < k; 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 i = 0; i < 3; i++)
{
ArrayList <SparseVector <double> > seeds = new ArrayList <SparseVector <double> >(k);
tmp.Shuffle(mRnd);
for (int j = 0; j < k; j++)
{
seeds.Add(dataset[tmp[j]]);
}
// 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)(k * k - k);
if (simAvg < minSim)
{
minSim = simAvg;
bestSeeds = new ArrayList <int>(k);
for (int j = 0; j < k; j++)
{
bestSeeds.Add(tmp[j]);
}
}
}
for (int i = 0; i < k; i++)
{
centroids[i].Items.Add(bestSeeds[i]);
centroids[i].Update(dataset);
centroids[i].UpdateCentroidLen();
}
// execute main loop
double clustQual;
kMeansMainLoop(dataset, centroids, out clustQual);
if (trial == 1 || clustQual > globalBestClustQual)
{
globalBestClustQual = clustQual;
mCentroids = centroids;
}
}
return(GetClusteringResult());
}
public override ClusteringResult Cluster(IUnlabeledExampleCollection<SparseVector<double>> batch)
{
return Cluster(/*numOutdated=*/0, batch); // throws ArgumentNullException, ArgumentValueException
}
private UnlabeledDataset <SparseVector <double> > GetDatasetSubset(IEnumerable <int> items, IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
UnlabeledDataset <SparseVector <double> > datasetSubset = new UnlabeledDataset <SparseVector <double> >();
foreach (int item in items)
{
datasetSubset.Add(dataset[item]);
}
return(datasetSubset);
}
public SparseVector <double> ComputeCentroid(IUnlabeledExampleCollection <SparseVector <double> > dataset, CentroidType type)
{
return(ModelUtils.ComputeCentroid(mItems, dataset, type)); // throws ArgumentValueException
}
public static SparseMatrix <double> GetDotProductSimilarity(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
return(GetDotProductSimilarity(dataset, /*thresh=*/ 0, /*fullMatrix=*/ false)); // throws ArgumentNullException
}
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 ClusteringResult Cluster(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(dataset.Count < mK ? new ArgumentValueException("dataset") : null);
mDataset = new UnlabeledDataset <SparseVector <double> >(dataset);
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>(mDataset.Count);
for (int i = 0; i < mDataset.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(mDataset[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]);
}
}
}
ArrayList <KeyDat <double, int> > medoids = new ArrayList <KeyDat <double, int> >(mK);
for (int i = 0; i < mK; i++)
{
centroids[i].Items.Add(bestSeeds[i]);
centroids[i].Update(mDataset);
centroids[i].UpdateCentroidLen();
medoids.Add(new KeyDat <double, int>(-1, bestSeeds[i]));
}
double[,] dotProd = new double[mDataset.Count, mK];
SparseMatrix <double> dsMat = ModelUtils.GetTransposedMatrix(mDataset);
// 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
//StopWatch stopWatch = new StopWatch();
int j = 0;
foreach (CentroidData cen in centroids)
{
SparseVector <double> cenVec = cen.GetSparseVector();
double[] dotProdSimVec = ModelUtils.GetDotProductSimilarity(dsMat, mDataset.Count, cenVec);
for (int i = 0; i < dotProdSimVec.Length; i++)
{
if (dotProdSimVec[i] > 0)
{
dotProd[i, j] = dotProdSimVec[i];
}
}
j++;
}
for (int dsInstIdx = 0; dsInstIdx < mDataset.Count; dsInstIdx++)
{
double maxSim = double.MinValue;
ArrayList <int> candidates = new ArrayList <int>();
for (int cenIdx = 0; cenIdx < mK; cenIdx++)
{
double sim = dotProd[dsInstIdx, cenIdx];
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(dsInstIdx);
clustQual += maxSim;
if (medoids[candidates[0]].Key < maxSim)
{
medoids[candidates[0]] = new KeyDat <double, int>(maxSim, dsInstIdx);
}
}
}
//Console.WriteLine(stopWatch.TotalMilliseconds);
clustQual /= (double)mDataset.Count;
mLogger.Info("Cluster", "Quality: {0:0.0000}", clustQual);
// compute new centroids
for (int i = 0; i < mK; i++)
{
centroids[i].Update(mDataset);
centroids[i].UpdateCentroidLen();
}
// check if done
if (iter > 1 && clustQual - bestClustQual <= mEps)
{
break;
}
bestClustQual = clustQual;
for (int i = 0; i < medoids.Count; i++)
{
medoids[i] = new KeyDat <double, int>(-1, medoids[i].Dat);
}
}
if (trial == 1 || clustQual > globalBestClustQual)
{
globalBestClustQual = clustQual;
mCentroids = centroids;
mMedoids = medoids;
// 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);
}
public override ClusteringResult Cluster(IUnlabeledExampleCollection <SparseVector <double> > batch)
{
return(Cluster(/*numOutdated=*/ 0, batch)); // throws ArgumentNullException, ArgumentValueException
}
public virtual ClusteringResult Cluster(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(dataset.Count < mK ? new ArgumentValueException("dataset") : null);
return(kMeans(dataset, mK));
}
ClusteringResult IClustering.Cluster(IUnlabeledExampleCollection dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(!(dataset is IUnlabeledExampleCollection <SparseVector <double> >) ? new ArgumentTypeException("dataset") : null);
return(Cluster((IUnlabeledExampleCollection <SparseVector <double> >)dataset)); // throws ArgumentValueException
}
public SemanticSpaceLayout(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
mDataset = dataset;
}
void IHierarchicalModel.Train(IUnlabeledExampleCollection dataset, ClusteringResult hierarchy)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(!(dataset is IUnlabeledExampleCollection <SparseVector <double> >) ? new ArgumentTypeException("dataset") : null);
Train((IUnlabeledExampleCollection <SparseVector <double> >)dataset, hierarchy); // throws ArgumentNullException, ArgumentValueException
}
private void kMeansMainLoop(IUnlabeledExampleCollection<SparseVector<double>> dataset, ArrayList<CentroidData> centroids)
{
double dummy;
kMeansMainLoop(dataset, centroids, out dummy);
}
