/**
* Sets boost of termClaimsDescriptionAbstractTitles. boost = weight = factor(tf*idf)
*
* @param vecsTerms
* @param currentField
* @param factor - adjustment factor ( ex. alpha or beta )
* @param decayFactor
* @return
* @throws java.io.IOException
*/
public Map<String, TermQuery> setBoost(
Map<TermFreqVector, String> vecsTerms, String currentField, float factor, float decayFactor)
throws IOException {
Map<String, TermQuery> terms = new HashMap<>();
// setBoost for each of the terms of each of the docs
int i = 0;
float norm = (float) 1 / vecsTerms.size();
// System.out.println("--------------------------");
for (Map.Entry<TermFreqVector, String> e : vecsTerms.entrySet()) {
// Increase decay
String field = e.getValue();
TermFreqVector docTerms = e.getKey();
float decay = decayFactor * i;
// Populate terms: with TermQuries and set boost
for (String termTxt : docTerms.getTerms()) {
// Create Term
Term term = new Term(currentField, termTxt);
// Calculate weight
float tf = docTerms.getFreq(termTxt);
// float idf = ir.docFreq(termTitle);
int docs;
float idf;
if (sourceField.equals(PatentQuery.all)) {
docs = ir.getDocCount(field);
idf = (float) Math.log10((double) docs / (ir.docFreq(new Term(field, termTxt)) + 1));
} else {
docs = ir.getDocCount(sourceField);
idf =
(float) Math.log10((double) docs / (ir.docFreq(new Term(sourceField, termTxt)) + 1));
}
float weight = tf * idf;
// System.out.println(term.text() + " -> tf= " + tf + " idf= " + idf + "
// tfidf= " + weight);
// Adjust weight by decay factor
weight = weight - (weight * decay);
// Create TermQuery and add it to the collection
TermQuery termQuery = new TermQuery(term);
// Calculate and set boost
float boost;
if (vecsTerms.size() == 1) {
boost = factor * tf;
} else {
boost = factor;
}
if (boost != 0) {
termQuery.setBoost(boost * norm);
if (terms.containsKey(termTxt)) {
TermQuery tq = terms.get(termTxt);
tq.setBoost(tq.getBoost() + termQuery.getBoost());
} else {
terms.put(termTxt, termQuery);
}
}
}
i++;
}
return terms;
}
/*
* listPostings displays the first n postings for a term in a
* field in an index (specified by reader). Set n to MAX_VALUE
* to display all postings.
*/
static void listPostings(IndexReader reader, String termString, String field, Integer n)
throws IOException {
System.out.println("\nPostings: " + termString + " " + field);
/*
* Prepare to access the index.
*/
BytesRef termBytes = new BytesRef(termString);
Term term = new Term(field, termBytes);
Bits liveDocs = MultiFields.getLiveDocs(reader);
/*
* Lookup the collection term frequency (ctf).
*/
long df = reader.docFreq(term);
System.out.println("\tdf: " + df);
long ctf = reader.totalTermFreq(term);
System.out.println("\tctf: " + ctf);
if (df < 1) return;
/*
* Lookup the inverted list.
*/
DocsAndPositionsEnum postings =
MultiFields.getTermPositionsEnum(reader, liveDocs, field, termBytes);
/*
* Iterate through the first n postings.
*/
long count = 0;
while ((count < n) && (postings.nextDoc() != DocIdSetIterator.NO_MORE_DOCS)) {
System.out.println("\tdocid: " + postings.docID());
int tf = postings.freq();
System.out.println("\ttf: " + tf);
System.out.print("\tPositions: ");
for (int j = 0; j < tf; j++) {
int pos = postings.nextPosition();
System.out.print(pos + " ");
}
System.out.println("");
count++;
}
;
return;
}
/**
* Create a PriorityQueue from a word->tf map.
*
* @param words a map of words keyed on the word(String) with Int objects as the values.
* @param fieldNames an array of field names to override defaults.
*/
private PriorityQueue<ScoreTerm> createQueue(Map<String, Int> words, String... fieldNames)
throws IOException {
// have collected all words in doc and their freqs
int numDocs = ir.numDocs();
final int limit = Math.min(maxQueryTerms, words.size());
FreqQ queue = new FreqQ(limit); // will order words by score
for (String word : words.keySet()) { // for every word
int tf = words.get(word).x; // term freq in the source doc
if (minTermFreq > 0 && tf < minTermFreq) {
continue; // filter out words that don't occur enough times in the source
}
// go through all the fields and find the largest document frequency
String topField = fieldNames[0];
int docFreq = 0;
for (String fieldName : fieldNames) {
int freq = ir.docFreq(new Term(fieldName, word));
topField = (freq > docFreq) ? fieldName : topField;
docFreq = (freq > docFreq) ? freq : docFreq;
}
if (minDocFreq > 0 && docFreq < minDocFreq) {
continue; // filter out words that don't occur in enough docs
}
if (docFreq > maxDocFreq) {
continue; // filter out words that occur in too many docs
}
if (docFreq == 0) {
continue; // index update problem?
}
float idf = similarity.idf(docFreq, numDocs);
float score = tf * idf;
if (queue.size() < limit) {
// there is still space in the queue
queue.add(new ScoreTerm(word, topField, score, idf, docFreq, tf));
} else {
ScoreTerm term = queue.top();
if (term.score < score) { // update the smallest in the queue in place and update the queue.
term.update(word, topField, score, idf, docFreq, tf);
queue.updateTop();
}
}
}
return queue;
}