static void Main(string[] args)
{
// Get the stop words and stemmer for English.
IStemmer stemmer;
Set <string> .ReadOnly stopWords;
TextMiningUtils.GetLanguageTools(Language.English,
out stopWords, out stemmer);
// Create a tokenizer.
UnicodeTokenizer tokenizer = new UnicodeTokenizer();
tokenizer.MinTokenLen = 2; // Each token must be at least 2
// characters long.
tokenizer.Filter = TokenizerFilter.AlphaStrict; // Tokens
// can consist of alphabetic characters only.
// Load a document corpus from a file. Each line in the file
// represents one document.
string[] docs
= File.ReadAllLines("..\\..\\Data\\YahooFinance.txt");
// Create a bag-of-words space.
BowSpace bowSpc = new BowSpace();
bowSpc.Tokenizer = tokenizer; // Assign the tokenizer.
bowSpc.StopWords = stopWords; // Assign the stop words.
bowSpc.Stemmer = stemmer; // Assign the stemmer.
bowSpc.MinWordFreq = 3; // A term must appear at least 3
// times in the corpus for it to be part of the
// vocabulary.
bowSpc.MaxNGramLen = 3; // Terms consisting of at most 3
// consecutive words will be considered.
bowSpc.WordWeightType = WordWeightType.TfIdf; // Set the
// weighting scheme for the bag-of-words vectors to
// TF-IDF.
bowSpc.NormalizeVectors = true; // The TF-IDF vectors will
// be normalized.
bowSpc.CutLowWeightsPerc = 0.2; // The terms with the lowest
// weights, summing up to 20% of the overall weight sum,
// will be removed from each TF-IDF vector.
bowSpc.Initialize(docs); // Initialize the BOW space.
// Compute 100 clusters of documents.
KMeansFast kMeans = new KMeansFast(100); // Set k to 100.
kMeans.Trials = 3; // Perform 3 repetitions. Take the best
// result.
kMeans.Eps = 0.001; // Stop iterating when the partition
// quality increases for less than 0.001.
ClusteringResult cr = kMeans.Cluster(bowSpc); // Execute.
// Extract the top 5 terms with the highest TF-IDF weights
// from each of the clusters' centroids and output the
// number of documents (companies) in each cluster.
foreach (Cluster cl in cr.Roots)
{
SparseVector <double> .ReadOnly centroid
= cl.ComputeCentroid(bowSpc, CentroidType.NrmL2);
Console.Write(bowSpc.GetKeywordsStr(centroid, 5));
Console.WriteLine(" ({0} companies)", cl.Items.Count);
}
// Output the documents that are contained in the first
// cluster.
foreach (int docIdx in cr.Roots[0].Items)
{
Console.WriteLine(docs[docIdx]);
}
}
public Vector2D[] ComputeLayout(LayoutSettings settings)
{
UnlabeledDataset <SparseVector <double> > dataset = new UnlabeledDataset <SparseVector <double> >(mDataset);
// clustering
mLogger.Info("ComputeLayout", "Clustering ...");
KMeansFast kMeans = new KMeansFast(mKClust);
kMeans.Eps = mKMeansEps;
kMeans.Random = mRandom;
kMeans.Trials = 1;
ClusteringResult clustering = kMeans.Cluster(mDataset); // throws ArgumentValueException
// determine reference instances
UnlabeledDataset <SparseVector <double> > dsRefInst = new UnlabeledDataset <SparseVector <double> >();
foreach (Cluster cluster in clustering.Roots)
{
SparseVector <double> centroid
= cluster.Items.Count > 0 ? cluster.ComputeCentroid(mDataset, CentroidType.NrmL2) : new SparseVector <double>();
dsRefInst.Add(centroid); // dataset of reference instances
dataset.Add(centroid); // add centroids to the main dataset
}
// position reference instances
mLogger.Info("ComputeLayout", "Positioning reference instances ...");
SparseMatrix <double> simMtx = ModelUtils.GetDotProductSimilarity(dsRefInst, mSimThresh, /*fullMatrix=*/ false);
StressMajorizationLayout sm = new StressMajorizationLayout(dsRefInst.Count, new DistFunc(simMtx));
sm.Random = mRandom;
Vector2D[] centrPos = sm.ComputeLayout();
// k-NN
mLogger.Info("ComputeLayout", "Computing similarities ...");
simMtx = ModelUtils.GetDotProductSimilarity(dataset, mSimThresh, /*fullMatrix=*/ true);
mLogger.Info("ComputeLayout", "Constructing system of linear equations ...");
LabeledDataset <double, SparseVector <double> > lsqrDs = new LabeledDataset <double, SparseVector <double> >();
foreach (IdxDat <SparseVector <double> > simMtxRow in simMtx)
{
if (simMtxRow.Dat.Count <= 1)
{
mLogger.Warn("ComputeLayout", "Instance #{0} has no neighborhood.", simMtxRow.Idx);
}
ArrayList <KeyDat <double, int> > knn = new ArrayList <KeyDat <double, int> >(simMtxRow.Dat.Count);
foreach (IdxDat <double> item in simMtxRow.Dat)
{
if (item.Idx != simMtxRow.Idx)
{
knn.Add(new KeyDat <double, int>(item.Dat, item.Idx));
}
}
knn.Sort(DescSort <KeyDat <double, int> > .Instance);
int count = Math.Min(knn.Count, mKNN);
SparseVector <double> eq = new SparseVector <double>();
double wgt = 1.0 / (double)count;
for (int i = 0; i < count; i++)
{
eq.InnerIdx.Add(knn[i].Dat);
eq.InnerDat.Add(-wgt);
}
eq.InnerIdx.Sort(); // *** sort only indices
eq[simMtxRow.Idx] = 1;
lsqrDs.Add(0, eq);
}
Vector2D[] layout = new Vector2D[dataset.Count - mKClust];
for (int i = dataset.Count - mKClust, j = 0; i < dataset.Count; i++, j++)
{
SparseVector <double> eq = new SparseVector <double>(new IdxDat <double>[] { new IdxDat <double>(i, 1) });
lsqrDs.Add(centrPos[j].X, eq);
}
LSqrModel lsqr = new LSqrModel();
lsqr.Train(lsqrDs);
for (int i = 0; i < layout.Length; i++)
{
layout[i].X = lsqr.Solution[i];
}
for (int i = lsqrDs.Count - mKClust, j = 0; i < lsqrDs.Count; i++, j++)
{
lsqrDs[i].Label = centrPos[j].Y;
}
lsqr.Train(lsqrDs);
for (int i = 0; i < layout.Length; i++)
{
layout[i].Y = lsqr.Solution[i];
}
return(settings == null ? layout : settings.AdjustLayout(layout));
}
