@Override
protected void reduce(IntWritable row, Iterable<VectorWritable> partialDots, Context ctx)
throws IOException, InterruptedException {
Iterator<VectorWritable> partialDotsIterator = partialDots.iterator();
Vector dots = partialDotsIterator.next().get();
while (partialDotsIterator.hasNext()) {
Vector toAdd = partialDotsIterator.next().get();
Iterator<Vector.Element> nonZeroElements = toAdd.iterateNonZero();
while (nonZeroElements.hasNext()) {
Vector.Element nonZeroElement = nonZeroElements.next();
dots.setQuick(
nonZeroElement.index(), dots.getQuick(nonZeroElement.index()) + nonZeroElement.get());
}
}
Vector similarities = dots.like();
double normA = norms.getQuick(row.get());
Iterator<Vector.Element> dotsWith = dots.iterateNonZero();
while (dotsWith.hasNext()) {
Vector.Element b = dotsWith.next();
double similarityValue =
similarity.similarity(b.get(), normA, norms.getQuick(b.index()), numberOfColumns);
if (similarityValue >= treshold) {
similarities.set(b.index(), similarityValue);
}
}
if (excludeSelfSimilarity) {
similarities.setQuick(row.get(), 0);
}
ctx.write(row, new VectorWritable(similarities));
}
// utility functions
static void denseVectorPlusAbsDenseDiff(
DenseVector denseVector, Vector sparseVector, DenseVector meanVector) {
for (int i = 0; i < denseVector.size(); i++) {
double denseV = denseVector.getQuick(i);
double v = sparseVector.getQuick(i);
double mean = meanVector.getQuick(i);
denseVector.setQuick(i, denseV + Math.abs(v - mean));
}
}
static void denseVectorSubtractSparseSubtractDense(
DenseVector mainVector, Vector subtractor1, DenseVector subtractor2) {
int nCols = mainVector.size();
for (int c = 0; c < nCols; c++) {
double v = mainVector.getQuick(c);
v -= subtractor1.getQuick(c);
v -= subtractor2.getQuick(c);
mainVector.setQuick(c, v);
}
}
public void map(Chunk chks[]) {
int chunkSize = chks[0].len();
Vector x = bx.value();
long start = chks[0].start();
atx = new double[chks.length];
for (int r = 0; r < chunkSize; r++) {
double d = x.getQuick((int) start + r);
for (int c = 0; c < chks.length; c++) {
atx[c] += (chks[c].at0(r) * d);
}
}
}
@Override
protected void map(Writable key, VectorWritable value, Context context)
throws IOException, InterruptedException {
omega.computeYRow(value.get(), yRow);
// compute outer product update for YtY
if (yRow.isDense()) {
for (int i = 0; i < kp; i++) {
double yi;
if ((yi = yRow.getQuick(i)) == 0.0) {
continue; // avoid densing up here unnecessarily
}
for (int j = i; j < kp; j++) {
double yj;
if ((yj = yRow.getQuick(j)) != 0.0) {
mYtY.setQuick(i, j, mYtY.getQuick(i, j) + yi * yj);
}
}
}
} else {
/*
* the disadvantage of using sparse vector (aside from the fact that we
* are creating some short-lived references) here is that we obviously
* do two times more iterations then necessary if y row is pretty dense.
*/
for (Iterator<Vector.Element> iterI = yRow.iterateNonZero(); iterI.hasNext(); ) {
Vector.Element eli = iterI.next();
int i = eli.index();
for (Iterator<Vector.Element> iterJ = yRow.iterateNonZero(); iterJ.hasNext(); ) {
Vector.Element elj = iterJ.next();
int j = elj.index();
if (j < i) {
continue;
}
mYtY.setQuick(i, j, mYtY.getQuick(i, j) + eli.get() * elj.get());
}
}
}
}
/**
* A version to compute yRow as a sparse vector in case of extremely sparse matrices
*
* @param aRow
* @param yRowOut
*/
public void computeYRow(Vector aRow, Vector yRowOut) {
yRowOut.assign(0.0);
if (aRow.isDense()) {
int n = aRow.size();
for (int j = 0; j < n; j++) {
accumDots(j, aRow.getQuick(j), yRowOut);
}
} else {
for (Iterator<Element> iter = aRow.iterateNonZero(); iter.hasNext(); ) {
Element el = iter.next();
accumDots(el.index(), el.get(), yRowOut);
}
}
}
/**
* compute YRow=ARow*Omega.
*
* @param aRow row of matrix A (size n)
* @param yRow row of matrix Y (result) must be pre-allocated to size of (k+p)
*/
@Deprecated
public void computeYRow(Vector aRow, double[] yRow) {
// assert yRow.length == kp;
Arrays.fill(yRow, 0.0);
if (aRow.isDense()) {
int n = aRow.size();
for (int j = 0; j < n; j++) {
accumDots(j, aRow.getQuick(j), yRow);
}
} else {
for (Iterator<Element> iter = aRow.iterateNonZero(); iter.hasNext(); ) {
Element el = iter.next();
accumDots(el.index(), el.get(), yRow);
}
}
}
protected void accumDots(int aIndex, double aElement, Vector yRow) {
for (int i = 0; i < kp; i++) {
yRow.setQuick(i, yRow.getQuick(i) + getQuick(aIndex, i) * aElement);
}
}
public double featureWeight(int feature) {
return weightsPerFeature.getQuick(feature);
}
public double labelWeight(int label) {
return weightsPerLabel.getQuick(label);
}
