public void assignLabels( LingoProcessingContext context, DoubleMatrix2D stemCos, IntIntOpenHashMap filteredRowToStemIndex, DoubleMatrix2D phraseCos )
{
PreprocessingContext preprocessingContext = context.preprocessingContext;
int firstPhraseIndex = preprocessingContext.allLabels.firstPhraseIndex;
int [] labelsFeatureIndex = preprocessingContext.allLabels.featureIndex;
int [] mostFrequentOriginalWordIndex = preprocessingContext.allStems.mostFrequentOriginalWordIndex;
int desiredClusterCount = stemCos.columns();
IntArrayList clusterLabelFeatureIndex = new IntArrayList(
desiredClusterCount);
DoubleArrayList clusterLabelScore = new DoubleArrayList(desiredClusterCount);
for (int label = 0; label < desiredClusterCount; label++)
{
Pair<int, int> stemMax = max(stemCos);
Pair<int, int> phraseMax = max(phraseCos);
if (stemMax == null && phraseMax == null)
{
break;
}
double stemScore = stemMax != null ? stemCos.getQuick(stemMax.objectA,
stemMax.objectB) : -1;
double phraseScore = phraseMax != null ? phraseCos.getQuick(
phraseMax.objectA, phraseMax.objectB) : -1;
if (phraseScore > stemScore)
{
phraseCos.viewRow(phraseMax.objectA).assign(0);
phraseCos.viewColumn(phraseMax.objectB).assign(0);
stemCos.viewColumn(phraseMax.objectB).assign(0);
clusterLabelFeatureIndex.add(labelsFeatureIndex[phraseMax.objectA
+ firstPhraseIndex]);
clusterLabelScore.add(phraseScore);
}
else
{
stemCos.viewRow(stemMax.objectA).assign(0);
stemCos.viewColumn(stemMax.objectB).assign(0);
if (phraseCos != null)
{
phraseCos.viewColumn(stemMax.objectB).assign(0);
}
clusterLabelFeatureIndex
.add(mostFrequentOriginalWordIndex[filteredRowToStemIndex
.get(stemMax.objectA)]);
clusterLabelScore.add(stemScore);
}
}
context.clusterLabelFeatureIndex = clusterLabelFeatureIndex.toArray();
context.clusterLabelScore = clusterLabelScore.toArray();
}
public void assignLabels( LingoProcessingContext context, DoubleMatrix2D stemCos, IntIntOpenHashMap filteredRowToStemIndex, DoubleMatrix2D phraseCos )
{
PreprocessingContext preprocessingContext = context.preprocessingContext;
int firstPhraseIndex = preprocessingContext.allLabels.firstPhraseIndex;
int[] labelsFeatureIndex = preprocessingContext.allLabels.featureIndex;
int[] mostFrequentOriginalWordIndex = preprocessingContext.allStems.mostFrequentOriginalWordIndex;
int desiredClusterCount = stemCos.columns();
int[] candidateStemIndices = new int[desiredClusterCount];
double[] candidateStemScores = new double[desiredClusterCount];
int[] candidatePhraseIndices = new int[desiredClusterCount];
for ( int i = 0; i < desiredClusterCount; i++ )
{
candidatePhraseIndices[i] = -1;
}
double[] candidatePhraseScores = new double[desiredClusterCount];
MatrixUtils.maxInColumns( stemCos, candidateStemIndices, candidateStemScores,
Functions.ABS );
if ( phraseCos != null )
{
MatrixUtils.maxInColumns( phraseCos, candidatePhraseIndices,
candidatePhraseScores, Functions.ABS );
}
int[] clusterLabelFeatureIndex = new int[desiredClusterCount];
double [] clusterLabelScore = new double [desiredClusterCount];
for (int i = 0; i < desiredClusterCount; i++)
{
int phraseFeatureIndex = candidatePhraseIndices[i];
int stemIndex = filteredRowToStemIndex.get(candidateStemIndices[i]);
double phraseScore = candidatePhraseScores[i];
if (phraseFeatureIndex >= 0 && phraseScore > candidateStemScores[i])
{
clusterLabelFeatureIndex[i] = labelsFeatureIndex[phraseFeatureIndex
+ firstPhraseIndex];
clusterLabelScore[i] = phraseScore;
}
else
{
clusterLabelFeatureIndex[i] = mostFrequentOriginalWordIndex[stemIndex];
clusterLabelScore[i] = candidateStemScores[i];
}
}
context.clusterLabelFeatureIndex = clusterLabelFeatureIndex;
context.clusterLabelScore = clusterLabelScore;
}
