private void LoadModel(BinarySerializer reader)
{
mLogger.Info("LoadModel", "Loading model ...");
mBowSpace = new BowSpace(reader);
mModel = Utils.LoadDictionary <string, IModel <string> >(reader);
mLogger.Info("LoadModel", "Model successfully loaded.");
}
// ReSharper restore InconsistentNaming
static void Main(string[] args)
{
string[] documents = Corpus.Split(new[] { '.' }, StringSplitOptions.RemoveEmptyEntries);
var results = new Dictionary<string, SparseVector<double>>();
foreach (TestCase testCase in Enum.GetValues(typeof(TestCase)).Cast<TestCase>())
{
var bow = new BowSpace
{
Tokenizer = new SimpleTokenizer
{
MinTokenLen = 2,
Type = TokenizerType.AllChars
},
StopWords = null,
Stemmer = null,
MaxNGramLen = 2,
MinWordFreq = 1,
WordWeightType = WordWeightType.TermFreq,
NormalizeVectors = true,
KeepWordForms = false
};
switch (testCase)
{
case TestCase.testWordWeightType_TERM_FREQ:
break;
case TestCase.testWordWeightType_TF_IDF:
bow.WordWeightType = WordWeightType.TfIdf;
break;
case TestCase.testWordWeightType_LOG_DF_TF_IDF:
bow.WordWeightType = WordWeightType.LogDfTfIdf;
break;
case TestCase.testNGramLen:
bow.MaxNGramLen = 5;
break;
case TestCase.testMinWordFreq:
bow.MinWordFreq = 3;
break;
case TestCase.testNormalizeVectors:
bow.NormalizeVectors = false;
break;
case TestCase.testKeepWordForms:
bow.KeepWordForms = true;
break;
case TestCase.testLemmatizer:
bow.Stemmer = new Lemmatizer(Language.English);
break;
case TestCase.testStopWords:
bow.Stemmer = new Lemmatizer(Language.English);
bow.StopWords = StopWords.EnglishStopWords;
break;
}
bow.Initialize(documents, testCase == TestCase.testInitializeLargeScale);
SparseVector<double> vector = bow.ProcessDocument(Document);
results.Add(testCase.ToString(), vector);
}
File.WriteAllText("vec.json", JsonConvert.SerializeObject(results));
Console.WriteLine(results);
}
public Prediction <LblT> Predict(string example)
{
Preconditions.CheckState(IsTrained);
example = FeatureProcessor.Run(example);
SparseVector <double> vector = BowSpace.ProcessDocument(example);
return(Model.Predict(vector));
}
static CategorizerDemo()
{
string fileName = HttpContext.Current.Server.MapPath("App_Data\\model.bin");
BinarySerializer binReader = new BinarySerializer(fileName, FileMode.Open);
mBowSpace = new BowSpace(binReader);
mBowSpace.CutLowWeightsPerc = 0.2;
mCategorizer = Utils.LoadDictionary<string, IModel<string>>(binReader);
binReader.Close();
mReady = true;
}
public Pair <string, double>[] GetTopVectorItems(string vectorName, int n, BowSpace bowSpc)
{
SparseVector <double> vec = mFeatureVectors[vectorName];
return(vec
.OrderByDescending(x => x.Dat)
.Take(n)
.Select(x => new Pair <string, double>(bowSpc.Words[x.Idx].Stem, x.Dat))
.ToArray());
}
static TwitterSentimentDemo()
{
string modelFileName = HttpContext.Current.Server.MapPath("App_Data\\AdCfy.bin");
string bowSpcFileName = HttpContext.Current.Server.MapPath("App_Data\\AdCfyBowSpc.bin");
mClassifier = new SvmBinaryClassifier<int>();
mClassifier.LoadModel(modelFileName);
BinarySerializer bs = new BinarySerializer(bowSpcFileName, FileMode.Open);
mBowSpace = new BowSpace(bs);
bs.Close();
mReady = true;
}
static PumpIndexComponent()
{
Logger.GetLogger(typeof(PumpIndexComponent)).Info("PumpIndexComponent", "Loading model ...");
string fileName = Utils.GetConfigValue("PumpIndexModel", ".\\PumpIndexModel.bin");
using (BinarySerializer reader = new BinarySerializer(fileName, FileMode.Open))
{
mBowSpace = new BowSpace(reader);
mClassifier = new SvmBinaryClassifier<int>(reader);
mAvgDistPos = reader.ReadDouble();
mAvgDistNeg = reader.ReadDouble();
//Console.WriteLine(mAvgDistPos);
//Console.WriteLine(mAvgDistNeg);
}
Logger.GetLogger(typeof(PumpIndexComponent)).Info("PumpIndexComponent", "Done.");
}
static DocumentCategorizerComponent()
{
Logger.GetLogger(typeof(DocumentCategorizerComponent)).Info("CategorizerComponent", "Loading model ...");
string fileName = Utils.GetConfigValue("CategorizationModel", ".\\CategorizationModel.bin");
BinarySerializer binReader = new BinarySerializer(fileName, FileMode.Open);
mBowSpace = new BowSpace(binReader);
mBowSpace.CutLowWeightsPerc = 0.2;
mCategorizer = Utils.LoadDictionary<string, IModel<string>>(binReader);
binReader.Close();
//using (BinarySerializer writer = new BinarySerializer(@"C:\Work\AchimPipe\DocumentCategorizerModel.bin", FileMode.Create))
//{
// mBowSpace.Save(writer);
// Utils.SaveDictionary<string, IModel<string>>(mCategorizer, writer);
//}
Logger.GetLogger(typeof(DocumentCategorizerComponent)).Info("CategorizerComponent", "Done.");
}
static PumpIndexComponent()
{
Logger.GetLogger(typeof(PumpIndexComponent)).Info("PumpIndexComponent", "Loading model ...");
string fileName = Utils.GetConfigValue("PumpIndexModel", ".\\PumpIndexModel.bin");
using (BinarySerializer reader = new BinarySerializer(fileName, FileMode.Open))
{
mBowSpace = new BowSpace(reader);
mClassifier = new SvmBinaryClassifier <int>(reader);
mAvgDistPos = reader.ReadDouble();
mAvgDistNeg = reader.ReadDouble();
//Console.WriteLine(mAvgDistPos);
//Console.WriteLine(mAvgDistNeg);
}
Logger.GetLogger(typeof(PumpIndexComponent)).Info("PumpIndexComponent", "Done.");
}
static DocumentCategorizerComponent()
{
Logger.GetLogger(typeof(DocumentCategorizerComponent)).Info("CategorizerComponent", "Loading model ...");
string fileName = Utils.GetConfigValue("CategorizationModel", ".\\CategorizationModel.bin");
BinarySerializer binReader = new BinarySerializer(fileName, FileMode.Open);
mBowSpace = new BowSpace(binReader);
mBowSpace.CutLowWeightsPerc = 0.2;
mCategorizer = Utils.LoadDictionary <string, IModel <string> >(binReader);
binReader.Close();
//using (BinarySerializer writer = new BinarySerializer(@"C:\Work\AchimPipe\DocumentCategorizerModel.bin", FileMode.Create))
//{
// mBowSpace.Save(writer);
// Utils.SaveDictionary<string, IModel<string>>(mCategorizer, writer);
//}
Logger.GetLogger(typeof(DocumentCategorizerComponent)).Info("CategorizerComponent", "Done.");
}
public void Train(ILabeledExampleCollection <LblT, string> dataset)
{
Preconditions.CheckState(!IsTrained);
Preconditions.CheckNotNull(dataset);
Preconditions.CheckNotNull(BowSpace);
Preconditions.CheckNotNull(FeatureProcessor);
Preconditions.CheckNotNull(Model);
// preprocess the text
foreach (LabeledExample <LblT, string> le in dataset)
{
le.Example = FeatureProcessor.Run(le.Example);
}
// bow vectors
List <SparseVector <double> > bowData = BowSpace is DeltaBowSpace <LblT>
?(BowSpace as DeltaBowSpace <LblT>).Initialize(dataset as ILabeledDataset <LblT, string> ?? new LabeledDataset <LblT, string>(dataset))
: BowSpace.Initialize(dataset.Select(d => d.Example));
var bowDataset = new LabeledDataset <LblT, SparseVector <double> >();
for (int i = 0; i < bowData.Count; i++)
{
bowDataset.Add(dataset[i].Label, bowData[i]);
}
// train
if (OnTrainModel == null)
{
Model.Train(bowDataset);
}
else
{
OnTrainModel(this, bowDataset);
}
IsTrained = true;
}
static void Main(string[] args)
{
// load documents
Utils.VerboseLine("Loading documents ...");
string[] docs = File.ReadAllLines("C:\\newwork\\testclustering\\data\\yahoofinance.txt");
BowSpace bowSpace = new BowSpace();
bowSpace.StopWords = StopWords.EnglishStopWords;
bowSpace.Stemmer = new PorterStemmer();
bowSpace.WordWeightType = WordWeightType.TfIdf;
RegexTokenizer tokenizer = new RegexTokenizer();
tokenizer.IgnoreUnknownTokens = true;
bowSpace.Tokenizer = tokenizer;
bowSpace.Initialize(docs);
// compute layout
SemanticSpaceLayout semSpc = new SemanticSpaceLayout(bowSpace);
Vector2D[] coords = semSpc.ComputeLayout();
// build spatial index
//Utils.VerboseLine("Building spatial index ...");
//SpatialIndex2D spatIdx = new SpatialIndex2D();
//spatIdx.BuildIndex(coords);
//spatIdx.InsertPoint(9000, new Vector2D(1000, 1000));
//ArrayList<IdxDat<Vector2D>> points = spatIdx.GetPoints(new Vector2D(0.5, 0.5), 0.1);
//Utils.VerboseLine("Number of retrieved points: {0}.", points.Count);
ArrayList <Vector2D> tmp = new ArrayList <Vector2D>(coords);
tmp.Shuffle();
//tmp.RemoveRange(1000, tmp.Count - 1000);
// compute elevation
StreamWriter writer = new StreamWriter("c:\\elev.txt");
LayoutSettings ls = new LayoutSettings(800, 600);
ls.AdjustmentType = LayoutAdjustmentType.Soft;
ls.StdDevMult = 2;
ls.FitToBounds = true;
ls.MarginVert = 50;
ls.MarginHoriz = 50;
double[,] zMtx = VisualizationUtils.ComputeLayoutElevation(tmp, ls, 150, 200);
VisualizationUtils.__DrawElevation__(tmp, ls, 300, 400).Save("c:\\elev.bmp");
for (int row = 0; row < zMtx.GetLength(0); row++)
{
for (int col = 0; col < zMtx.GetLength(1); col++)
{
writer.Write("{0}\t", zMtx[row, col]);
}
writer.WriteLine();
}
writer.Close();
// output coordinates
StreamWriter tsvWriter = new StreamWriter("c:\\layout.tsv");
for (int i = 0; i < coords.Length; i++)
{
//if (i < points.Count)
//{
// tsvWriter.WriteLine("{0}\t{1}\t{2}\t{3}", coords[i].X, coords[i].Y, points[i].Dat.X, points[i].Dat.Y);
//}
//else
{
tsvWriter.WriteLine("{0}\t{1}", coords[i].X, coords[i].Y);
}
}
tsvWriter.Close();
//// get document names
//int k = 0;
//ArrayList<Pair<string, Vector2D>> layout = new ArrayList<Pair<string, Vector2D>>();
//foreach (string doc in docs)
//{
// string[] docInfo = doc.Split(' ');
// layout.Add(new Pair<string, Vector2D>(docInfo[0], coords[k++]));
//}
//Console.WriteLine(coords.Length);
//Console.WriteLine(layout.Count);
//StreamWriter writer = new StreamWriter("c:\\vidCoords.txt");
//foreach (Pair<string, Vector2D> docPos in layout)
//{
// writer.WriteLine("{0}\t{1}\t{2}", docPos.First, docPos.Second.X, docPos.Second.Y);
//}
//writer.Close();
}
private void LoadModel(BinarySerializer reader)
{
mLogger.Info("LoadModel", "Loading model ...");
mBowSpace = new BowSpace(reader);
mModel = Utils.LoadDictionary<string, IModel<string>>(reader);
mLogger.Info("LoadModel", "Model successfully loaded.");
}
public override void Run(object[] args)
{
// prepare data
IStemmer stemmer;
Set <string> .ReadOnly stopWords;
TextMiningUtils.GetLanguageTools(Language.English, out stopWords, out stemmer);
// Create a tokenizer.
var tokenizer = new UnicodeTokenizer
{
MinTokenLen = 2, // Each token must be at least 2 characters long.
Filter = TokenizerFilter.AlphaStrict // Tokens can consist of alphabetic characters only.
};
// take data for two classes from cvs file
var data = new List <LabeledTweet>(GetLabeledTweets().Where(lt => lt.Polarity != 2)).ToList();
// Create a bag-of-words space.
var bowSpc = new BowSpace
{
Tokenizer = tokenizer, // Assign the tokenizer.
StopWords = stopWords, // Assign the stop words.
Stemmer = stemmer, // Assign the stemmer.
MinWordFreq = 1, // A term must appear at least n-times in the corpus for it to be part of the vocabulary.
MaxNGramLen = 2, // Terms consisting of at most n-consecutive words will be considered.
WordWeightType = WordWeightType.TermFreq, // Set the weighting scheme for the bag-of-words vectors to TF.
//WordWeightType = WordWeightType.TfIdf, // Set the weighting scheme for the bag-of-words vectors to TF-IDF.
NormalizeVectors = true, // The TF-IDF vectors will be normalized.
CutLowWeightsPerc = 0 // The terms with the lowest weights, summing up to 20% of the overall weight sum, will be removed from each TF-IDF vector.
};
ArrayList <SparseVector <double> > bowData = bowSpc.Initialize(data.Select(d => d.Text));
// label data
var labeledSet = new LabeledDataset <string, SparseVector <double> >();
for (int i = 0; i < data.Count; i++)
{
labeledSet.Add(data[i].Label, bowData[i]);
}
labeledSet.Shuffle();
int testSize = labeledSet.Count / 10;
var trainingSet = new LabeledDataset <string, SparseVector <double> >(labeledSet.Skip(testSize));
var testSet = new LabeledDataset <string, SparseVector <double> >(labeledSet.Take(testSize));
//-------------------- SVM
var svmBinClass = new SvmBinaryClassifier <string> {
VerbosityLevel = SvmLightVerbosityLevel.Off
};
if (args.Any())
{
svmBinClass.C = (int)args[0];
}
//svmBinClass.BiasedHyperplane = true;
//svmBinClass.CustomParams = "-t 3"; // non-linear kernel
//svmBinClass.CustomParams = String.Format("-j {0}",j);
svmBinClass.Train(trainingSet);
int correct = 0;
double avgDist = 0;
foreach (LabeledExample <string, SparseVector <double> > labeledExample in testSet)
{
var prediction = svmBinClass.Predict(labeledExample.Example);
//Output.WriteLine("actual: {0}\tpredicted: {1}\t score: {2:0.0000}", labeledExample.Label, prediction.BestClassLabel, prediction.BestScore);
avgDist += prediction.BestScore;
if (prediction.BestClassLabel == labeledExample.Label)
{
correct++;
}
}
Output.WriteLine("Accuracy: {0:0.00}", 100.0 * correct / testSet.Count);
Output.WriteLine("Avg. distance: {0:0.00}", avgDist / testSet.Count);
Result.Add("accuracy", (double)correct / testSet.Count);
Result.Add("classifier", svmBinClass);
Result.Add("labeled_data", labeledSet);
}
static void Main(string[] args)
{
// load documents
Utils.VerboseLine("Loading documents ...");
string[] docs = File.ReadAllLines("C:\\newwork\\testclustering\\data\\yahoofinance.txt");
BowSpace bowSpace = new BowSpace();
bowSpace.StopWords = StopWords.EnglishStopWords;
bowSpace.Stemmer = new PorterStemmer();
bowSpace.WordWeightType = WordWeightType.TfIdf;
RegexTokenizer tokenizer = new RegexTokenizer();
tokenizer.IgnoreUnknownTokens = true;
bowSpace.Tokenizer = tokenizer;
bowSpace.Initialize(docs);
// compute layout
SemanticSpaceLayout semSpc = new SemanticSpaceLayout(bowSpace);
Vector2D[] coords = semSpc.ComputeLayout();
// build spatial index
//Utils.VerboseLine("Building spatial index ...");
//SpatialIndex2D spatIdx = new SpatialIndex2D();
//spatIdx.BuildIndex(coords);
//spatIdx.InsertPoint(9000, new Vector2D(1000, 1000));
//ArrayList<IdxDat<Vector2D>> points = spatIdx.GetPoints(new Vector2D(0.5, 0.5), 0.1);
//Utils.VerboseLine("Number of retrieved points: {0}.", points.Count);
ArrayList<Vector2D> tmp = new ArrayList<Vector2D>(coords);
tmp.Shuffle();
//tmp.RemoveRange(1000, tmp.Count - 1000);
// compute elevation
StreamWriter writer = new StreamWriter("c:\\elev.txt");
LayoutSettings ls = new LayoutSettings(800, 600);
ls.AdjustmentType = LayoutAdjustmentType.Soft;
ls.StdDevMult = 2;
ls.FitToBounds = true;
ls.MarginVert = 50;
ls.MarginHoriz = 50;
double[,] zMtx = VisualizationUtils.ComputeLayoutElevation(tmp, ls, 150, 200);
VisualizationUtils.__DrawElevation__(tmp, ls, 300, 400).Save("c:\\elev.bmp");
for (int row = 0; row < zMtx.GetLength(0); row++)
{
for (int col = 0; col < zMtx.GetLength(1); col++)
{
writer.Write("{0}\t", zMtx[row, col]);
}
writer.WriteLine();
}
writer.Close();
// output coordinates
StreamWriter tsvWriter = new StreamWriter("c:\\layout.tsv");
for (int i = 0; i < coords.Length; i++)
{
//if (i < points.Count)
//{
// tsvWriter.WriteLine("{0}\t{1}\t{2}\t{3}", coords[i].X, coords[i].Y, points[i].Dat.X, points[i].Dat.Y);
//}
//else
{
tsvWriter.WriteLine("{0}\t{1}", coords[i].X, coords[i].Y);
}
}
tsvWriter.Close();
//// get document names
//int k = 0;
//ArrayList<Pair<string, Vector2D>> layout = new ArrayList<Pair<string, Vector2D>>();
//foreach (string doc in docs)
//{
// string[] docInfo = doc.Split(' ');
// layout.Add(new Pair<string, Vector2D>(docInfo[0], coords[k++]));
//}
//Console.WriteLine(coords.Length);
//Console.WriteLine(layout.Count);
//StreamWriter writer = new StreamWriter("c:\\vidCoords.txt");
//foreach (Pair<string, Vector2D> docPos in layout)
//{
// writer.WriteLine("{0}\t{1}\t{2}", docPos.First, docPos.Second.X, docPos.Second.Y);
//}
//writer.Close();
}
public static LabeledDataset <SentimentLabel, SparseVector <double> > InitBowSpace(BowSpace bowSpace,
IEnumerable <LabeledExample <SentimentLabel, string> > labeledExamples, IEnumerable <string> initExamples = null)
{
LabeledExample <SentimentLabel, string>[] examples = labeledExamples as LabeledExample <SentimentLabel, string>[] ?? labeledExamples.ToArray();
List <SparseVector <double> > bowData;
if (initExamples != null)
{
Preconditions.CheckArgument(!(bowSpace is DeltaBowSpace <SentimentLabel>));
bowSpace.Initialize(initExamples);
bowData = examples.Select(le => bowSpace.ProcessDocument(le.Example)).ToList();
}
else
{
bowData = bowSpace is DeltaBowSpace <SentimentLabel>
?((DeltaBowSpace <SentimentLabel>)bowSpace).Initialize(new LabeledDataset <SentimentLabel, string>(examples))
: bowSpace.Initialize(examples.Select(d => d.Example));
}
var bowDataset = new LabeledDataset <SentimentLabel, SparseVector <double> >();
for (int i = 0; i < bowData.Count; i++)
{
bowDataset.Add(examples[i].Label, bowData[i]);
}
return(bowDataset);
}
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);
// Test the stemmer.
Console.WriteLine(stemmer.GetStem("running"));
// Output: run
// 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.
// Test the tokenizer.
tokenizer.Text = "one 1 two 2 three 3 one_1 two_2 three_3";
foreach (string token in tokenizer)
{
Console.Write("\"{0}\" ", token);
}
Console.WriteLine();
// Output: "one" "two" "three"
// 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.
// Output the vocabulary (the terms, their stems,
// frequencies, and document frequencies) to the console.
StreamWriter stdOut
= new StreamWriter(Console.OpenStandardOutput());
bowSpc.OutputStats(stdOut);
stdOut.Close();
// Output the TF-IDF vector representing the description of
// Google to the console.
SparseVector <double> .ReadOnly googVec
= bowSpc.BowVectors[4192 - 1]; // The description of
// Google can be found at the row 4192 in the corpus.
foreach (IdxDat <double> termInfo in googVec)
{
Console.WriteLine("{0} : {1}",
bowSpc.Words[termInfo.Idx].MostFrequentForm,
termInfo.Dat);
}
// Extract the top 5 terms with the highest TF-IDF weights
// from the vector representing Google.
Console.WriteLine(bowSpc.GetKeywordsStr(googVec, 5));
// Output: google, relevant, targeted advertising, search,
// index
}
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]);
}
}
