public static void SimilarityInterfaceTest(ISimilarity distance, string first, string second, double expected)
{
var resultString = distance.GetSimilarity(first, second);
Assert.AreEqual(expected, resultString, ErrorTollerance);
var resultNorm = distance.GetSimilarity(new NormalizedString(first), new NormalizedString(second));
Assert.AreEqual(expected, resultNorm, ErrorTollerance);
var resultToken = distance.GetSimilarity(new Token(first), new Token(second));
Assert.AreEqual(expected, resultToken, ErrorTollerance);
}
public Prediction <LblT> Predict(ExT example)
{
Utils.ThrowException(mExamples == null ? new InvalidOperationException() : null);
Utils.ThrowException(example == null ? new ArgumentNullException("example") : null);
ArrayList <KeyDat <double, LabeledExample <LblT, ExT> > > tmp = new ArrayList <KeyDat <double, LabeledExample <LblT, ExT> > >(mExamples.Count);
foreach (LabeledExample <LblT, ExT> labeledExample in mExamples)
{
double sim = mSimilarity.GetSimilarity(example, labeledExample.Example);
tmp.Add(new KeyDat <double, LabeledExample <LblT, ExT> >(sim, labeledExample));
}
tmp.Sort(DescSort <KeyDat <double, LabeledExample <LblT, ExT> > > .Instance);
Dictionary <LblT, double> voting = new Dictionary <LblT, double>(mLblCmp);
int n = Math.Min(mK, tmp.Count);
double value;
if (mSoftVoting) // "soft" voting
{
for (int i = 0; i < n; i++)
{
KeyDat <double, LabeledExample <LblT, ExT> > item = tmp[i];
if (!voting.TryGetValue(item.Dat.Label, out value))
{
voting.Add(item.Dat.Label, item.Key);
}
else
{
voting[item.Dat.Label] = value + item.Key;
}
}
}
else // normal voting
{
for (int i = 0; i < n; i++)
{
KeyDat <double, LabeledExample <LblT, ExT> > item = tmp[i];
if (!voting.TryGetValue(item.Dat.Label, out value))
{
voting.Add(item.Dat.Label, 1);
}
else
{
voting[item.Dat.Label] = value + 1.0;
}
}
}
Prediction <LblT> classifierResult = new Prediction <LblT>();
foreach (KeyValuePair <LblT, double> item in voting)
{
classifierResult.Inner.Add(new KeyDat <double, LblT>(item.Value, item.Key));
}
classifierResult.Inner.Sort(DescSort <KeyDat <double, LblT> > .Instance);
return(classifierResult);
}
public ClassifierResult <LblT> Classify(SparseVector <double> .ReadOnly example)
{
Utils.ThrowException(m_centroids == null ? new InvalidOperationException() : null);
Utils.ThrowException(example == null ? new ArgumentNullException("example") : null);
ClassifierResult <LblT> result = new ClassifierResult <LblT>();
foreach (Pair <LblT, SparseVector <double> .ReadOnly> labeled_centroid in m_centroids)
{
double sim = m_similarity.GetSimilarity(labeled_centroid.Second, example);
result.Items.Add(new KeyDat <double, LblT>(sim, labeled_centroid.First));
}
result.Items.Sort(new DescSort <KeyDat <double, LblT> >());
return(result);
}
public Prediction <LblT> Predict(SparseVector <double> example)
{
Utils.ThrowException(mCentroids == null ? new InvalidOperationException() : null);
Utils.ThrowException(example == null ? new ArgumentNullException("example") : null);
Prediction <LblT> result = new Prediction <LblT>();
foreach (Pair <LblT, SparseVector <double> > labeledCentroid in mCentroids)
{
double sim = mSimilarity.GetSimilarity(labeledCentroid.Second, example);
result.Inner.Add(new KeyDat <double, LblT>(sim, labeledCentroid.First));
}
result.Inner.Sort(DescSort <KeyDat <double, LblT> > .Instance);
return(result);
}
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 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);
}
