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);
}
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);
}
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 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 ArrayList <Pair <LblT, SparseVector <double> .ReadOnly> >();
Dictionary <LblT, ArrayList <SparseVector <double> .ReadOnly> > tmp = new Dictionary <LblT, ArrayList <SparseVector <double> .ReadOnly> >(m_lbl_cmp);
foreach (LabeledExample <LblT, SparseVector <double> .ReadOnly> labeled_example in dataset)
{
if (!tmp.ContainsKey(labeled_example.Label))
{
tmp.Add(labeled_example.Label, new ArrayList <SparseVector <double> .ReadOnly>(new SparseVector <double> .ReadOnly[] { labeled_example.Example }));
}
else
{
tmp[labeled_example.Label].Add(labeled_example.Example);
}
}
foreach (KeyValuePair <LblT, ArrayList <SparseVector <double> .ReadOnly> > centroid_data in tmp)
{
SparseVector <double> centroid = ModelUtils.ComputeCentroid(centroid_data.Value, m_normalize ? CentroidType.NrmL2 : CentroidType.Avg);
m_centroids.Add(new Pair <LblT, SparseVector <double> .ReadOnly>(centroid_data.Key, centroid));
}
}
public ClusteringResult Cluster(IExampleCollection <LblT, SparseVector <double> .ReadOnly> dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(dataset.Count < m_k ? new ArgumentValueException("dataset") : null);
ClusteringResult clustering = null;
ClusteringResult best_clustering = null;
double global_best_clust_qual = 0;
for (int trial = 1; trial <= m_trials; trial++)
{
Utils.VerboseLine("*** CLUSTERING TRIAL {0} OF {1} ***", trial, m_trials);
ArrayList <SparseVector <double> .ReadOnly> centroids = null;
clustering = new ClusteringResult();
for (int i = 0; i < m_k; i++)
{
clustering.Roots.Add(new Cluster());
}
// select seed items
double min_sim = 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> .ReadOnly> seeds = new ArrayList <SparseVector <double> .ReadOnly>(m_k);
tmp.Shuffle(m_rnd);
for (int i = 0; i < m_k; i++)
{
seeds.Add(ModelUtils.ComputeCentroid(new SparseVector <double> .ReadOnly[] { dataset[tmp[i]].Example }, m_centroid_type));
}
// assess quality of seed items
double sim_avg = 0;
foreach (SparseVector <double> .ReadOnly seed_1 in seeds)
{
foreach (SparseVector <double> .ReadOnly seed_2 in seeds)
{
if (seed_1 != seed_2)
{
sim_avg += m_similarity.GetSimilarity(seed_1, seed_2);
}
}
}
sim_avg /= (double)(m_k * m_k - m_k);
//Console.WriteLine(sim_avg);
if (sim_avg < min_sim)
{
min_sim = sim_avg;
centroids = seeds;
}
}
// main loop
int iter = 0;
double best_clust_qual = 0;
double clust_qual;
while (true)
{
iter++;
clust_qual = 0;
// assign items to clusters
foreach (Cluster cluster in clustering.Roots)
{
cluster.Items.Clear();
}
for (int i = 0; i < dataset.Count; i++)
{
SparseVector <double> .ReadOnly example = dataset[i].Example;
double max_sim = double.MinValue;
ArrayList <int> candidates = new ArrayList <int>();
for (int j = 0; j < m_k; j++)
{
SparseVector <double> .ReadOnly centroid = centroids[j];
double sim = m_similarity.GetSimilarity(example, centroid);
if (sim > max_sim)
{
max_sim = sim;
candidates.Clear();
candidates.Add(j);
}
else if (sim == max_sim)
{
candidates.Add(j);
}
}
if (candidates.Count > 1)
{
candidates.Shuffle(m_rnd);
}
if (candidates.Count > 0) // *** is this always true?
{
clustering.Roots[candidates[0]].Items.Add(new Pair <double, int>(1, i));
clust_qual += max_sim;
}
}
clust_qual /= (double)dataset.Count;
Utils.VerboseLine("*** Iteration {0} ***", iter);
Utils.VerboseLine("Quality: {0:0.0000}", clust_qual);
// check if done
if (iter > 1 && clust_qual - best_clust_qual <= m_eps)
{
break;
}
best_clust_qual = clust_qual;
// compute new centroids
for (int i = 0; i < m_k; i++)
{
centroids[i] = clustering.Roots[i].ComputeCentroid(dataset, m_centroid_type);
}
}
if (trial == 1 || clust_qual > global_best_clust_qual)
{
global_best_clust_qual = clust_qual;
best_clustering = clustering;
}
}
return(best_clustering);
}
public SparseVector <double> ComputeCentroid(IUnlabeledExampleCollection <SparseVector <double> > dataset, CentroidType type)
{
return(ModelUtils.ComputeCentroid(mItems, dataset, type)); // throws ArgumentValueException
}
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);
}
