public Accumulator_cascade[] rank_cascade() {
// point to next position in keptDocs array that hasn't been filled
int indexCntKeptDocs = 0;
// Clear priority queue.
mSortedAccumulators.clear();
// Cliques associated with the MRF.
List<Clique> cliques = mMRF.getCliques();
if (cliques.size() == 0) {
System.out.println("Shouldn't have size 0");
System.exit(-1);
}
// Current accumulator.
Accumulator_cascade a = mAccumulators[0];
/*
// Initialize the MRF.
try {
mMRF.initialize();
} catch (ConfigurationException e) {
sLogger.error("Error initializing MRF. Aborting ranking!");
return null;
}
*/
// Maximum possible score that this MRF can achieve.
float mrfMaxScore = 0.0f;
for (Clique c : cliques) {
if (!((((Clique_cascade) c).getParamID()).equals("termWt"))) {
System.out.println(
"In this faster cascade implementation, first stage must be term in order to get positions[] values! "
+ ((Clique_cascade) c).getParamID());
System.exit(-1);
}
mrfMaxScore += c.getMaxScore();
}
// Sort cliques according to their max scores.
Collections.sort(cliques, mMaxScoreComparator);
// Score that must be achieved to enter result set.
double scoreThreshold = Double.NEGATIVE_INFINITY;
// Offset into document set we're currently at (if applicable).
int docsetOffset = 0;
int docno = 0;
if (mDocSet != null) {
docno = docsetOffset < mDocSet.length ? mDocSet[docsetOffset++] : Integer.MAX_VALUE;
} else {
if (cascadeStage != 0) {
System.out.println("Shouldn't happen. Cascade stage " + cascadeStage);
System.exit(-1);
}
docno = mMRF.getNextCandidate();
}
boolean firstTime = true;
long startTime = System.currentTimeMillis();
while (docno < Integer.MAX_VALUE) {
for (DocumentNode documentNode : mDocNodes) {
documentNode.setDocno(docno);
}
// Document-at-a-time scoring.
float docMaxScore = mrfMaxScore;
boolean skipped = false;
float score = 0.0f;
// Lidan: accumulate document scores across the cascade stages
if (mDocSet != null && cascadeStage != 0) {
score = accumulated_scores[docsetOffset - 1];
}
// for each query term, its position in a document
int[][] termPositions = new int[cliques.size()][];
int document_length = -1;
for (int i = 0; i < cliques.size(); i++) {
// Current clique that we're scoring.
Clique c = cliques.get(i);
// If there's no way that this document can enter the result set
// then exit.
if (firstTime) {
term_to_cliqueNumber.put(c.getConcept().trim().toLowerCase(), i + "");
term_to_termCollectionFrequency.put(
c.getConcept().trim().toLowerCase(), ((Clique_cascade) c).termCollectionCF() + "");
term_to_termDF.put(
c.getConcept().trim().toLowerCase(), ((Clique_cascade) c).termCollectionDF() + "");
}
if (score + docMaxScore <= scoreThreshold) {
// Advance postings readers (but don't score).
for (int j = i; j < cliques.size(); j++) {
cliques.get(j).setNextCandidate(docno + 1);
}
skipped = true;
break;
}
// Document independent cliques do not affect the ranking.
if (!c.isDocDependent()) {
continue;
}
// Update document score.
float cliqueScore = c.getPotential();
score += c.getWeight() * cliqueScore;
// Update the max score for the rest of the cliques.
docMaxScore -= c.getMaxScore();
// stuff needed for document evaluation in the next stage
int[] p = ((Clique_cascade) c).getPositions();
if (p != null) {
termPositions[i] = Arrays.copyOf(p, p.length);
document_length = ((Clique_cascade) c).getDocLen();
}
}
firstTime = false;
// Keep track of mNumResults best accumulators.
if (!skipped && score > scoreThreshold) {
a.docno = docno;
a.score = score;
a.index_into_keptDocs = indexCntKeptDocs;
keptDocLengths[indexCntKeptDocs] = document_length;
mSortedAccumulators.add(a);
// save positional information for each query term in the document
for (int j = 0; j < termPositions.length; j++) {
if (termPositions[j] != null) {
keptDocs[indexCntKeptDocs][j] =
Arrays.copyOf(termPositions[j], termPositions[j].length);
}
}
if (mSortedAccumulators.size() == mNumResults + 1) {
a = mSortedAccumulators.poll(); // Re-use the accumulator of the removed document
// After maximum # docs been put into queue, each time a new document is added, an old
// document will be ejected, use the spot freed by the ejected document to store the new
// document positional info in keptDocs
indexCntKeptDocs = a.index_into_keptDocs;
keptDocs[indexCntKeptDocs] = new int[numQueryTerms][];
scoreThreshold = mSortedAccumulators.peek().score;
} else {
a =
mAccumulators[
mSortedAccumulators.size()]; // Next non-used accumulator in the accumulator pool
indexCntKeptDocs++;
}
}
if (mDocSet != null) {
docno = docsetOffset < mDocSet.length ? mDocSet[docsetOffset++] : Integer.MAX_VALUE;
} else {
if (cascadeStage != 0) {
System.out.println("Shouldn't happen. Cascade stage " + cascadeStage);
System.exit(-1);
}
docno = mMRF.getNextCandidate();
}
}
// Grab the accumulators off the stack, in (reverse) order.
Accumulator_cascade[] results_tmp =
new Accumulator_cascade[Math.min(mNumResults, mSortedAccumulators.size())];
for (int i = 0; i < results_tmp.length; i++) {
results_tmp[results_tmp.length - 1 - i] = mSortedAccumulators.poll();
meanScore += results_tmp[results_tmp.length - 1 - i].score;
}
meanScore /= results_tmp.length;
Accumulator_cascade[] results = results_tmp;
/* Do the sorting in rank()
//if there are more stages, should sort by docno
if (cnt!=cliques_all.size()){
int [] order = new int[results_tmp.length];
double [] docnos = new double[results_tmp.length];
for (int i=0; i<order.length; i++){
order[i] = i;
docnos[i] = results_tmp[i].docno;
}
ivory.smrf.model.constrained.ConstraintModel.Quicksort(docnos, order, 0, results.length-1);
results = new Accumulator_cascade[results_tmp.length];
for (int i=0; i<order.length; i++){
results[i] = results_tmp[order[i]];
}
}
*/
long endTime = System.currentTimeMillis();
return results;
}
