/**
* Builds a term-phrase matrix in the same space as the main term-document matrix. If the
* processing context contains no phrases, {@link VectorSpaceModelContext#termPhraseMatrix} will
* remain <code>null</code>.
*/
public void buildTermPhraseMatrix(VectorSpaceModelContext context) {
final PreprocessingContext preprocessingContext = context.preprocessingContext;
final IntIntHashMap stemToRowIndex = context.stemToRowIndex;
final int[] labelsFeatureIndex = preprocessingContext.allLabels.featureIndex;
final int firstPhraseIndex = preprocessingContext.allLabels.firstPhraseIndex;
if (firstPhraseIndex >= 0 && stemToRowIndex.size() > 0) {
// Build phrase matrix
int[] phraseFeatureIndices = new int[labelsFeatureIndex.length - firstPhraseIndex];
for (int featureIndex = 0; featureIndex < phraseFeatureIndices.length; featureIndex++) {
phraseFeatureIndices[featureIndex] = labelsFeatureIndex[featureIndex + firstPhraseIndex];
}
final DoubleMatrix2D phraseMatrix =
TermDocumentMatrixBuilder.buildAlignedMatrix(
context, phraseFeatureIndices, termWeighting);
MatrixUtils.normalizeColumnL2(phraseMatrix, null);
context.termPhraseMatrix = phraseMatrix.viewDice();
}
}
