/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.TypeLoadException"/>
public virtual ICounter <CandidatePhrase> LearnNewPhrases(string label, PatternsForEachToken patternsForEachToken, ICounter <E> patternsLearnedThisIter, ICounter <E> allSelectedPatterns, CollectionValuedMap <E, Triple <string, int, int> > tokensMatchedPatterns
, ICounter <CandidatePhrase> scoreForAllWordsThisIteration, TwoDimensionalCounter <CandidatePhrase, E> terms, TwoDimensionalCounter <CandidatePhrase, E> wordsPatExtracted, TwoDimensionalCounter <E, CandidatePhrase> patternsAndWords4Label, string
identifier, ICollection <CandidatePhrase> ignoreWords)
{
bool computeProcDataFreq = false;
if (Data.processedDataFreq == null)
{
computeProcDataFreq = true;
Data.processedDataFreq = new ClassicCounter <CandidatePhrase>();
System.Diagnostics.Debug.Assert(Data.rawFreq != null);
}
ICollection <CandidatePhrase> alreadyIdentifiedWords = new HashSet <CandidatePhrase>(constVars.GetLearnedWords(label).KeySet());
Sharpen.Collections.AddAll(alreadyIdentifiedWords, constVars.GetSeedLabelDictionary()[label]);
ICounter <CandidatePhrase> words = LearnNewPhrasesPrivate(label, patternsForEachToken, patternsLearnedThisIter, allSelectedPatterns, alreadyIdentifiedWords, tokensMatchedPatterns, scoreForAllWordsThisIteration, terms, wordsPatExtracted, patternsAndWords4Label
, identifier, ignoreWords, computeProcDataFreq);
//constVars.addLabelDictionary(label, words.keySet());
return(words);
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.TypeLoadException"/>
private ICounter <CandidatePhrase> LearnNewPhrasesPrivate(string label, PatternsForEachToken patternsForEachToken, ICounter <E> patternsLearnedThisIter, ICounter <E> allSelectedPatterns, ICollection <CandidatePhrase> alreadyIdentifiedWords, CollectionValuedMap
<E, Triple <string, int, int> > matchedTokensByPat, ICounter <CandidatePhrase> scoreForAllWordsThisIteration, TwoDimensionalCounter <CandidatePhrase, E> terms, TwoDimensionalCounter <CandidatePhrase, E> wordsPatExtracted, TwoDimensionalCounter <E
, CandidatePhrase> patternsAndWords4Label, string identifier, ICollection <CandidatePhrase> ignoreWords, bool computeProcDataFreq)
{
ICollection <CandidatePhrase> alreadyLabeledWords = new HashSet <CandidatePhrase>();
if (constVars.doNotApplyPatterns)
{
// if want to get the stats by the lossy way of just counting without
// applying the patterns
ConstantsAndVariables.DataSentsIterator sentsIter = new ConstantsAndVariables.DataSentsIterator(constVars.batchProcessSents);
while (sentsIter.MoveNext())
{
Pair <IDictionary <string, DataInstance>, File> sentsf = sentsIter.Current;
this.StatsWithoutApplyingPatterns(sentsf.First(), patternsForEachToken, patternsLearnedThisIter, wordsPatExtracted);
}
}
else
{
if (patternsLearnedThisIter.Size() > 0)
{
this.ApplyPats(patternsLearnedThisIter, label, wordsPatExtracted, matchedTokensByPat, alreadyLabeledWords);
}
}
if (computeProcDataFreq)
{
if (!phraseScorer.wordFreqNorm.Equals(PhraseScorer.Normalization.None))
{
Redwood.Log(Redwood.Dbg, "computing processed freq");
foreach (KeyValuePair <CandidatePhrase, double> fq in Data.rawFreq.EntrySet())
{
double @in = fq.Value;
if (phraseScorer.wordFreqNorm.Equals(PhraseScorer.Normalization.Sqrt))
{
@in = Math.Sqrt(@in);
}
else
{
if (phraseScorer.wordFreqNorm.Equals(PhraseScorer.Normalization.Log))
{
@in = 1 + Math.Log(@in);
}
else
{
throw new Exception("can't understand the normalization");
}
}
System.Diagnostics.Debug.Assert(!double.IsNaN(@in), "Why is processed freq nan when rawfreq is " + @in);
Data.processedDataFreq.SetCount(fq.Key, @in);
}
}
else
{
Data.processedDataFreq = Data.rawFreq;
}
}
if (constVars.wordScoring.Equals(GetPatternsFromDataMultiClass.WordScoring.Weightednorm))
{
foreach (CandidatePhrase en in wordsPatExtracted.FirstKeySet())
{
if (!constVars.GetOtherSemanticClassesWords().Contains(en) && (en.GetPhraseLemma() == null || !constVars.GetOtherSemanticClassesWords().Contains(CandidatePhrase.CreateOrGet(en.GetPhraseLemma()))) && !alreadyLabeledWords.Contains(en))
{
terms.AddAll(en, wordsPatExtracted.GetCounter(en));
}
}
RemoveKeys(terms, ConstantsAndVariables.GetStopWords());
ICounter <CandidatePhrase> phraseScores = phraseScorer.ScorePhrases(label, terms, wordsPatExtracted, allSelectedPatterns, alreadyIdentifiedWords, false);
System.Console.Out.WriteLine("count for word U.S. is " + phraseScores.GetCount(CandidatePhrase.CreateOrGet("U.S.")));
ICollection <CandidatePhrase> ignoreWordsAll;
if (ignoreWords != null && !ignoreWords.IsEmpty())
{
ignoreWordsAll = CollectionUtils.UnionAsSet(ignoreWords, constVars.GetOtherSemanticClassesWords());
}
else
{
ignoreWordsAll = new HashSet <CandidatePhrase>(constVars.GetOtherSemanticClassesWords());
}
Sharpen.Collections.AddAll(ignoreWordsAll, constVars.GetSeedLabelDictionary()[label]);
Sharpen.Collections.AddAll(ignoreWordsAll, constVars.GetLearnedWords(label).KeySet());
System.Console.Out.WriteLine("ignoreWordsAll contains word U.S. is " + ignoreWordsAll.Contains(CandidatePhrase.CreateOrGet("U.S.")));
ICounter <CandidatePhrase> finalwords = ChooseTopWords(phraseScores, terms, phraseScores, ignoreWordsAll, constVars.thresholdWordExtract);
phraseScorer.PrintReasonForChoosing(finalwords);
scoreForAllWordsThisIteration.Clear();
Counters.AddInPlace(scoreForAllWordsThisIteration, phraseScores);
Redwood.Log(ConstantsAndVariables.minimaldebug, "\n\n## Selected Words for " + label + " : " + Counters.ToSortedString(finalwords, finalwords.Size(), "%1$s:%2$.2f", "\t"));
if (constVars.goldEntities != null)
{
IDictionary <string, bool> goldEntities4Label = constVars.goldEntities[label];
if (goldEntities4Label != null)
{
StringBuilder s = new StringBuilder();
finalwords.KeySet().Stream().ForEach(null);
Redwood.Log(ConstantsAndVariables.minimaldebug, "\n\n## Gold labels for selected words for label " + label + " : " + s.ToString());
}
else
{
Redwood.Log(Redwood.Dbg, "No gold entities provided for label " + label);
}
}
if (constVars.outDir != null && !constVars.outDir.IsEmpty())
{
string outputdir = constVars.outDir + "/" + identifier + "/" + label;
IOUtils.EnsureDir(new File(outputdir));
TwoDimensionalCounter <CandidatePhrase, CandidatePhrase> reasonForWords = new TwoDimensionalCounter <CandidatePhrase, CandidatePhrase>();
foreach (CandidatePhrase word in finalwords.KeySet())
{
foreach (E l in wordsPatExtracted.GetCounter(word).KeySet())
{
foreach (CandidatePhrase w2 in patternsAndWords4Label.GetCounter(l))
{
reasonForWords.IncrementCount(word, w2);
}
}
}
Redwood.Log(ConstantsAndVariables.minimaldebug, "Saving output in " + outputdir);
string filename = outputdir + "/words.json";
// the json object is an array corresponding to each iteration - of list
// of objects,
// each of which is a bean of entity and reasons
IJsonArrayBuilder obj = Javax.Json.Json.CreateArrayBuilder();
if (writtenInJustification.Contains(label) && writtenInJustification[label])
{
IJsonReader jsonReader = Javax.Json.Json.CreateReader(new BufferedInputStream(new FileInputStream(filename)));
IJsonArray objarr = jsonReader.ReadArray();
foreach (IJsonValue o in objarr)
{
obj.Add(o);
}
jsonReader.Close();
}
IJsonArrayBuilder objThisIter = Javax.Json.Json.CreateArrayBuilder();
foreach (CandidatePhrase w in reasonForWords.FirstKeySet())
{
IJsonObjectBuilder objinner = Javax.Json.Json.CreateObjectBuilder();
IJsonArrayBuilder l = Javax.Json.Json.CreateArrayBuilder();
foreach (CandidatePhrase w2 in reasonForWords.GetCounter(w).KeySet())
{
l.Add(w2.GetPhrase());
}
IJsonArrayBuilder pats = Javax.Json.Json.CreateArrayBuilder();
foreach (E p in wordsPatExtracted.GetCounter(w))
{
pats.Add(p.ToStringSimple());
}
objinner.Add("reasonwords", l);
objinner.Add("patterns", pats);
objinner.Add("score", finalwords.GetCount(w));
objinner.Add("entity", w.GetPhrase());
objThisIter.Add(objinner.Build());
}
obj.Add(objThisIter);
// Redwood.log(ConstantsAndVariables.minimaldebug, channelNameLogger,
// "Writing justification at " + filename);
IOUtils.WriteStringToFile(StringUtils.Normalize(StringUtils.ToAscii(obj.Build().ToString())), filename, "ASCII");
writtenInJustification[label] = true;
}
if (constVars.justify)
{
Redwood.Log(Redwood.Dbg, "\nJustification for phrases:\n");
foreach (CandidatePhrase word in finalwords.KeySet())
{
Redwood.Log(Redwood.Dbg, "Phrase " + word + " extracted because of patterns: \t" + Counters.ToSortedString(wordsPatExtracted.GetCounter(word), wordsPatExtracted.GetCounter(word).Size(), "%1$s:%2$f", "\n"));
}
}
// if (usePatternResultAsLabel)
// if (answerLabel != null)
// labelWords(sents, commonEngWords, finalwords.keySet(),
// patterns.keySet(), outFile);
// else
// throw new RuntimeException("why is the answer label null?");
return(finalwords);
}
else
{
if (constVars.wordScoring.Equals(GetPatternsFromDataMultiClass.WordScoring.Bpb))
{
Counters.AddInPlace(terms, wordsPatExtracted);
ICounter <CandidatePhrase> maxPatWeightTerms = new ClassicCounter <CandidatePhrase>();
IDictionary <CandidatePhrase, E> wordMaxPat = new Dictionary <CandidatePhrase, E>();
foreach (KeyValuePair <CandidatePhrase, ClassicCounter <E> > en in terms.EntrySet())
{
ICounter <E> weights = new ClassicCounter <E>();
foreach (E k in en.Value.KeySet())
{
weights.SetCount(k, patternsLearnedThisIter.GetCount(k));
}
maxPatWeightTerms.SetCount(en.Key, Counters.Max(weights));
wordMaxPat[en.Key] = Counters.Argmax(weights);
}
Counters.RemoveKeys(maxPatWeightTerms, alreadyIdentifiedWords);
double maxvalue = Counters.Max(maxPatWeightTerms);
ICollection <CandidatePhrase> words = Counters.KeysAbove(maxPatWeightTerms, maxvalue - 1e-10);
CandidatePhrase bestw = null;
if (words.Count > 1)
{
double max = double.NegativeInfinity;
foreach (CandidatePhrase w in words)
{
if (terms.GetCount(w, wordMaxPat[w]) > max)
{
max = terms.GetCount(w, wordMaxPat[w]);
bestw = w;
}
}
}
else
{
if (words.Count == 1)
{
bestw = words.GetEnumerator().Current;
}
else
{
return(new ClassicCounter <CandidatePhrase>());
}
}
Redwood.Log(ConstantsAndVariables.minimaldebug, "Selected Words: " + bestw);
return(Counters.AsCounter(Arrays.AsList(bestw)));
}
else
{
throw new Exception("wordscoring " + constVars.wordScoring + " not identified");
}
}
}
/*
* public void applyPats(Counter<E> patterns, String label, boolean computeDataFreq, TwoDimensionalCounter<Pair<String, String>, Integer> wordsandLemmaPatExtracted,
* CollectionValuedMap<Integer, Triple<String, Integer, Integer>> matchedTokensByPat) throws ClassNotFoundException, IOException, InterruptedException, ExecutionException{
* Counter<E> patternsLearnedThisIterConsistsOnlyGeneralized = new ClassicCounter<E>();
* Counter<E> patternsLearnedThisIterRest = new ClassicCounter<E>();
* Set<String> specialWords = constVars.invertedIndex.getSpecialWordsList();
* List<String> extremelySmallStopWordsList = Arrays.asList(".",",","in","on","of","a","the","an");
*
* for(Entry<Integer, Double> en: patterns.entrySet()){
* Integer pindex = en.getKey();
* SurfacePattern p = constVars.getPatternIndex().get(pindex);
* String[] n = p.getSimplerTokensNext();
* String[] pr = p.getSimplerTokensPrev();
* boolean rest = false;
* if(n!=null){
* for(String e: n){
* if(!specialWords.contains(e)){
* rest = true;
* break;
* }
* }
* }
* if(rest == false && pr!=null){
* for(String e: pr){
* if(!specialWords.contains(e) && !extremelySmallStopWordsList.contains(e)){
* rest = true;
* break;
* }
* }
* }
* if(rest)
* patternsLearnedThisIterRest.setCount(en.getKey(), en.getValue());
* else
* patternsLearnedThisIterConsistsOnlyGeneralized.setCount(en.getKey(), en.getValue());
* }
*
*
*
* Map<String, Set<String>> sentidswithfilerest = constVars.invertedIndex.getFileSentIdsFromPats(patternsLearnedThisIterRest.keySet(), constVars.getPatternIndex());
*
* if (constVars.batchProcessSents) {
* List<File> filesToLoad;
* if(patternsLearnedThisIterConsistsOnlyGeneralized.size() > 0)
* filesToLoad = Data.sentsFiles;
* else{
* filesToLoad = new ArrayList<File>();
* for (String fname : sentidswithfilerest.keySet()) {
* String filename;
* // if(!constVars.usingDirForSentsInIndex)
* // filename = constVars.saveSentencesSerDir+"/"+fname;
* // else
* filename = fname;
* filesToLoad.add(new File(filename));
* }
* }
*
* for (File fname : filesToLoad) {
* Redwood.log(Redwood.DBG, "Applying patterns to sents from " + fname);
* Map<String, List<CoreLabel>> sents = IOUtils.readObjectFromFile(fname);
*
* if(sentidswithfilerest != null && !sentidswithfilerest.isEmpty()){
*
* String filename;
* // if(constVars.usingDirForSentsInIndex)
* // filename = constVars.saveSentencesSerDir+"/"+fname.getName();
* // else
* filename = fname.getAbsolutePath();
*
* Set<String> sentIDs = sentidswithfilerest.get(filename);
* if (sentIDs != null){
* this.runParallelApplyPats(sents, sentIDs, label, patternsLearnedThisIterRest, wordsandLemmaPatExtracted, matchedTokensByPat);
* } else
* Redwood.log(Redwood.DBG, "No sentIds for " + filename + " in the index for the keywords from the patterns! The index came up with these files: " + sentidswithfilerest.keySet());
* }
* if(patternsLearnedThisIterConsistsOnlyGeneralized.size() > 0){
* this.runParallelApplyPats(sents, sents.keySet(), label, patternsLearnedThisIterConsistsOnlyGeneralized, wordsandLemmaPatExtracted, matchedTokensByPat);
* }
*
* if (computeDataFreq){
* Data.computeRawFreqIfNull(sents, constVars.numWordsCompound);
* Data.fileNamesUsedToComputeRawFreq.add(fname.getName());
* }
* }
*
* //Compute Frequency from the files not loaded using the invertedindex query. otherwise, later on there is an error.
* if(computeDataFreq){
* for(File f: Data.sentsFiles){
* if(!Data.fileNamesUsedToComputeRawFreq.contains(f.getName())){
* Map<String, List<CoreLabel>> sents = IOUtils.readObjectFromFile(f);
* Data.computeRawFreqIfNull(sents, constVars.numWordsCompound);
* Data.fileNamesUsedToComputeRawFreq.add(f.getName());
* }
* }
* }
*
* } else {
*
* if (sentidswithfilerest != null && !sentidswithfilerest.isEmpty()) {
* String filename = CollectionUtils.toList(sentidswithfilerest.keySet()).get(0);
* Set<String> sentids = sentidswithfilerest.get(filename);
* if (sentids != null) {
* this.runParallelApplyPats(Data.sents, sentids, label, patternsLearnedThisIterRest, wordsandLemmaPatExtracted, matchedTokensByPat);
* } else
* throw new RuntimeException("How come no sentIds for " + filename + ". Index keyset is " + constVars.invertedIndex.getKeySet());
* }
* if(patternsLearnedThisIterConsistsOnlyGeneralized.size() > 0){
* this.runParallelApplyPats(Data.sents, Data.sents.keySet(), label, patternsLearnedThisIterConsistsOnlyGeneralized, wordsandLemmaPatExtracted, matchedTokensByPat);
* }
* Data.computeRawFreqIfNull(Data.sents, constVars.numWordsCompound);
* }
* Redwood.log(Redwood.DBG, "# words/lemma and pattern pairs are " + wordsandLemmaPatExtracted.size());
* }
*/
private void StatsWithoutApplyingPatterns(IDictionary <string, DataInstance> sents, PatternsForEachToken patternsForEachToken, ICounter <E> patternsLearnedThisIter, TwoDimensionalCounter <CandidatePhrase, E> wordsandLemmaPatExtracted)
{
foreach (KeyValuePair <string, DataInstance> sentEn in sents)
{
IDictionary <int, ICollection <E> > pat4Sent = patternsForEachToken.GetPatternsForAllTokens(sentEn.Key);
if (pat4Sent == null)
{
throw new Exception("How come there are no patterns for " + sentEn.Key);
}
foreach (KeyValuePair <int, ICollection <E> > en in pat4Sent)
{
CoreLabel token = null;
ICollection <E> p1 = en.Value;
// Set<Integer> p1 = en.getValue().first();
// Set<Integer> p2 = en.getValue().second();
// Set<Integer> p3 = en.getValue().third();
foreach (E index in patternsLearnedThisIter.KeySet())
{
if (p1.Contains(index))
{
if (token == null)
{
token = sentEn.Value.GetTokens()[en.Key];
}
wordsandLemmaPatExtracted.IncrementCount(CandidatePhrase.CreateOrGet(token.Word(), token.Lemma()), index);
}
}
}
}
}
