//line is a jsonstring of map of label to array of strings; ex: {"name":["Bush","Carter","Obama"]}
/// <exception cref="System.Exception"/>
public virtual string DoNewPhrases(string line)
{
System.Console.Out.WriteLine("adding new phrases");
ConstantsAndVariables constVars = new ConstantsAndVariables(props, humanLabelClasses.Keys, humanLabelClasses);
IJsonReader jsonReader = Javax.Json.Json.CreateReader(new StringReader(line));
IJsonObject objarr = jsonReader.ReadObject();
foreach (KeyValuePair <string, IJsonValue> o in objarr)
{
string label = o.Key;
ICollection <CandidatePhrase> seed = new HashSet <CandidatePhrase>();
IJsonArray arr = objarr.GetJsonArray(o.Key);
for (int i = 0; i < arr.Count; i++)
{
string seedw = arr.GetString(i);
System.Console.Out.WriteLine("adding " + seedw + " to seed ");
seed.Add(CandidatePhrase.CreateOrGet(seedw));
}
Sharpen.Collections.AddAll(seedWords[label], seed);
constVars.AddSeedWords(label, seed);
GetPatternsFromDataMultiClass.RunLabelSeedWords(Data.sents, humanLabelClasses[label], label, seed, constVars, false);
}
//model.labelWords(label, labelclass, Data.sents, seed);
return("SUCCESS added new phrases");
}
/*
* 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);
}
}
}
}
}
public static void ComputeRawFreqIfNull(IDictionary <string, DataInstance> sents, int numWordsCompound)
{
Redwood.Log(Redwood.Dbg, "Computing raw freq for every 1-" + numWordsCompound + " consecutive words");
foreach (DataInstance l in sents.Values)
{
IList <IList <CoreLabel> > ngrams = CollectionUtils.GetNGrams(l.GetTokens(), 1, numWordsCompound);
foreach (IList <CoreLabel> n in ngrams)
{
string s = string.Empty;
foreach (CoreLabel c in n)
{
// if (useWord(c, commonEngWords, ignoreWordRegex)) {
s += " " + c.Word();
}
// }
s = s.Trim();
if (!s.IsEmpty())
{
Data.rawFreq.IncrementCount(CandidatePhrase.CreateOrGet(s));
}
}
}
//if (googleNGram != null && googleNGram.size() > 0)
if (usingGoogleNgram)
{
SetRatioGoogleNgramFreqWithDataFreq();
}
if (domainNGramRawFreq != null && domainNGramRawFreq.Size() > 0)
{
ratioDomainNgramFreqWithDataFreq = domainNGramRawFreq.TotalCount() / Data.rawFreq.TotalCount();
}
}
internal virtual double GetPatTFIDFScore(CandidatePhrase word, ICounter <E> patsThatExtractedThis, ICounter <E> allSelectedPatterns)
{
if (Data.processedDataFreq.GetCount(word) == 0.0)
{
Redwood.Log(Redwood.Warn, "How come the processed corpus freq has count of " + word + " 0. The count in raw freq is " + Data.rawFreq.GetCount(word) + " and the Data.rawFreq size is " + Data.rawFreq.Size());
return(0);
}
else
{
double total = 0;
ICollection <E> rem = new HashSet <E>();
foreach (KeyValuePair <E, double> en2 in patsThatExtractedThis.EntrySet())
{
double weight = 1.0;
if (usePatternWeights)
{
weight = allSelectedPatterns.GetCount(en2.Key);
if (weight == 0)
{
Redwood.Log(Redwood.Force, "Warning: Weight zero for " + en2.Key + ". May be pattern was removed when choosing other patterns (if subsumed by another pattern).");
rem.Add(en2.Key);
}
}
total += weight;
}
Counters.RemoveKeys(patsThatExtractedThis, rem);
double score = total / Data.processedDataFreq.GetCount(word);
return(score);
}
}
public virtual ICounter <CandidatePhrase> ChooseTopWords(ICounter <CandidatePhrase> newdt, TwoDimensionalCounter <CandidatePhrase, E> terms, ICounter <CandidatePhrase> useThresholdNumPatternsForTheseWords, ICollection <CandidatePhrase> ignoreWords
, double thresholdWordExtract)
{
IEnumerator <CandidatePhrase> termIter = Counters.ToPriorityQueue(newdt).GetEnumerator();
ICounter <CandidatePhrase> finalwords = new ClassicCounter <CandidatePhrase>();
while (termIter.MoveNext())
{
if (finalwords.Size() >= constVars.numWordsToAdd)
{
break;
}
CandidatePhrase w = termIter.Current;
if (newdt.GetCount(w) < thresholdWordExtract)
{
Redwood.Log(ConstantsAndVariables.extremedebug, "not adding word " + w + " and any later words because the score " + newdt.GetCount(w) + " is less than the threshold of " + thresholdWordExtract);
break;
}
System.Diagnostics.Debug.Assert((newdt.GetCount(w) != double.PositiveInfinity));
if (useThresholdNumPatternsForTheseWords.ContainsKey(w) && NumNonRedundantPatterns(terms, w) < constVars.thresholdNumPatternsApplied)
{
Redwood.Log("extremePatDebug", "Not adding " + w + " because the number of non redundant patterns are below threshold of " + constVars.thresholdNumPatternsApplied + ":" + terms.GetCounter(w).KeySet());
continue;
}
CandidatePhrase matchedFuzzy = null;
if (constVars.minLen4FuzzyForPattern > 0 && ignoreWords != null)
{
matchedFuzzy = ConstantsAndVariables.ContainsFuzzy(ignoreWords, w, constVars.minLen4FuzzyForPattern);
}
if (matchedFuzzy == null)
{
Redwood.Log("extremePatDebug", "adding word " + w);
finalwords.SetCount(w, newdt.GetCount(w));
}
else
{
Redwood.Log("extremePatDebug", "not adding " + w + " because it matched " + matchedFuzzy + " in common English word");
ignoreWords.Add(w);
}
}
string nextTen = string.Empty;
int n = 0;
while (termIter.MoveNext())
{
n++;
if (n > 10)
{
break;
}
CandidatePhrase w = termIter.Current;
nextTen += ";\t" + w + ":" + newdt.GetCount(w);
}
Redwood.Log(Redwood.Dbg, "Next ten phrases were " + nextTen);
return(finalwords);
}
public virtual double GetDictOddsScore(CandidatePhrase word, string label, double defaultWt)
{
double dscore;
ICounter <CandidatePhrase> dictOddsWordWeights = constVars.dictOddsWeights[label];
System.Diagnostics.Debug.Assert(dictOddsWordWeights != null, "dictOddsWordWeights is null for label " + label);
if (dictOddsWordWeights.ContainsKey(word))
{
dscore = dictOddsWordWeights.GetCount(word);
}
else
{
dscore = GetPhraseWeightFromWords(dictOddsWordWeights, word, defaultWt);
}
return(dscore);
}
public static double GetGoogleNgramScore(CandidatePhrase g)
{
double count = GoogleNGramsSQLBacked.GetCount(g.GetPhrase().ToLower()) + GoogleNGramsSQLBacked.GetCount(g.GetPhrase());
if (count != -1)
{
if (!Data.rawFreq.ContainsKey(g))
{
//returning 1 because usually lower this tf-idf score the better. if we don't have raw freq info, give it a bad score
return(1);
}
else
{
return((1 + Data.rawFreq.GetCount(g) * Math.Sqrt(Data.ratioGoogleNgramFreqWithDataFreq)) / count);
}
}
return(0);
}
public virtual double GetPhraseWeightFromWords(ICounter <CandidatePhrase> weights, CandidatePhrase ph, double defaultWt)
{
string[] t = ph.GetPhrase().Split("\\s+");
if (t.Length < 2)
{
if (weights.ContainsKey(ph))
{
return(weights.GetCount(ph));
}
else
{
return(defaultWt);
}
}
double totalscore = 0;
double minScore = double.MaxValue;
foreach (string w in t)
{
double score = defaultWt;
if (weights.ContainsKey(CandidatePhrase.CreateOrGet(w)))
{
score = weights.GetCount(w);
}
if (score < minScore)
{
minScore = score;
}
totalscore += score;
}
if (useAvgInsteadofMinPhraseScoring)
{
return(totalscore / ph.GetPhrase().Length);
}
else
{
return(minScore);
}
}
/// <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");
}
}
}
private double NumNonRedundantPatterns(TwoDimensionalCounter <CandidatePhrase, E> terms, CandidatePhrase w)
{
object[] pats = Sharpen.Collections.ToArray(terms.GetCounter(w).KeySet());
int numPat = 0;
for (int i = 0; i < pats.Length; i++)
{
//String pati = constVars.getPatternIndex().get(pats[i]).toString();
string pati = pats[i].ToString();
bool contains = false;
for (int j = i + 1; j < pats.Length; j++)
{
//String patj = constVars.getPatternIndex().get(pats[j]).toString();
string patj = pats[j].ToString();
if (patj.Contains(pati) || pati.Contains(patj))
{
contains = true;
break;
}
}
if (!contains)
{
numPat++;
}
}
return(numPat);
}
public static bool DoNotUse(string word, ICollection <CandidatePhrase> stopWords)
{
return(stopWords.Contains(CandidatePhrase.CreateOrGet(word.ToLower())) || ignoreWordRegex.Matcher(word).Matches());
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.TypeLoadException"/>
internal virtual ICounter <E> Convert2OneDim(string label, IToDoubleFunction <Pair <E, CandidatePhrase> > scoringFunction, ICollection <CandidatePhrase> allCandidatePhrases, TwoDimensionalCounter <E, CandidatePhrase> positivePatternsAndWords, bool
sqrtPatScore, bool scorePhrasesInPatSelection, ICounter <CandidatePhrase> dictOddsWordWeights, bool useFreqPhraseExtractedByPat)
{
// if (Data.googleNGram.size() == 0 && Data.googleNGramsFile != null) {
// Data.loadGoogleNGrams();
// }
ICounter <E> patterns = new ClassicCounter <E>();
ICounter <CandidatePhrase> googleNgramNormScores = new ClassicCounter <CandidatePhrase>();
ICounter <CandidatePhrase> domainNgramNormScores = new ClassicCounter <CandidatePhrase>();
ICounter <CandidatePhrase> externalFeatWtsNormalized = new ClassicCounter <CandidatePhrase>();
ICounter <CandidatePhrase> editDistanceFromOtherSemanticBinaryScores = new ClassicCounter <CandidatePhrase>();
ICounter <CandidatePhrase> editDistanceFromAlreadyExtractedBinaryScores = new ClassicCounter <CandidatePhrase>();
double externalWtsDefault = 0.5;
ICounter <string> classifierScores = null;
if ((patternScoring.Equals(GetPatternsFromDataMultiClass.PatternScoring.PhEvalInPat) || patternScoring.Equals(GetPatternsFromDataMultiClass.PatternScoring.PhEvalInPatLogP)) && scorePhrasesInPatSelection)
{
foreach (CandidatePhrase gc in allCandidatePhrases)
{
string g = gc.GetPhrase();
if (constVars.usePatternEvalEditDistOther)
{
editDistanceFromOtherSemanticBinaryScores.SetCount(gc, constVars.GetEditDistanceScoresOtherClassThreshold(label, g));
}
if (constVars.usePatternEvalEditDistSame)
{
editDistanceFromAlreadyExtractedBinaryScores.SetCount(gc, 1 - constVars.GetEditDistanceScoresThisClassThreshold(label, g));
}
if (constVars.usePatternEvalGoogleNgram)
{
googleNgramNormScores.SetCount(gc, PhraseScorer.GetGoogleNgramScore(gc));
}
if (constVars.usePatternEvalDomainNgram)
{
// calculate domain-ngram wts
if (Data.domainNGramRawFreq.ContainsKey(g))
{
System.Diagnostics.Debug.Assert((Data.rawFreq.ContainsKey(gc)));
domainNgramNormScores.SetCount(gc, scorePhrases.phraseScorer.GetDomainNgramScore(g));
}
}
if (constVars.usePatternEvalWordClass)
{
int num = constVars.GetWordClassClusters()[g];
if (num == null)
{
num = constVars.GetWordClassClusters()[g.ToLower()];
}
if (num != null && constVars.distSimWeights[label].ContainsKey(num))
{
externalFeatWtsNormalized.SetCount(gc, constVars.distSimWeights[label].GetCount(num));
}
else
{
externalFeatWtsNormalized.SetCount(gc, externalWtsDefault);
}
}
}
if (constVars.usePatternEvalGoogleNgram)
{
googleNgramNormScores = GetPatternsFromDataMultiClass.NormalizeSoftMaxMinMaxScores(googleNgramNormScores, true, true, false);
}
if (constVars.usePatternEvalDomainNgram)
{
domainNgramNormScores = GetPatternsFromDataMultiClass.NormalizeSoftMaxMinMaxScores(domainNgramNormScores, true, true, false);
}
if (constVars.usePatternEvalWordClass)
{
externalFeatWtsNormalized = GetPatternsFromDataMultiClass.NormalizeSoftMaxMinMaxScores(externalFeatWtsNormalized, true, true, false);
}
}
else
{
if ((patternScoring.Equals(GetPatternsFromDataMultiClass.PatternScoring.Logreg) || patternScoring.Equals(GetPatternsFromDataMultiClass.PatternScoring.LOGREGlogP)) && scorePhrasesInPatSelection)
{
Properties props2 = new Properties();
props2.PutAll(props);
props2.SetProperty("phraseScorerClass", "edu.stanford.nlp.patterns.ScorePhrasesLearnFeatWt");
ScorePhrases scoreclassifier = new ScorePhrases(props2, constVars);
System.Console.Out.WriteLine("file is " + props.GetProperty("domainNGramsFile"));
ArgumentParser.FillOptions(typeof(Data), props2);
classifierScores = scoreclassifier.phraseScorer.ScorePhrases(label, allCandidatePhrases, true);
}
}
ICounter <CandidatePhrase> cachedScoresForThisIter = new ClassicCounter <CandidatePhrase>();
foreach (KeyValuePair <E, ClassicCounter <CandidatePhrase> > en in positivePatternsAndWords.EntrySet())
{
foreach (KeyValuePair <CandidatePhrase, double> en2 in en.Value.EntrySet())
{
CandidatePhrase word = en2.Key;
ICounter <ConstantsAndVariables.ScorePhraseMeasures> scoreslist = new ClassicCounter <ConstantsAndVariables.ScorePhraseMeasures>();
double score = 1;
if ((patternScoring.Equals(GetPatternsFromDataMultiClass.PatternScoring.PhEvalInPat) || patternScoring.Equals(GetPatternsFromDataMultiClass.PatternScoring.PhEvalInPatLogP)) && scorePhrasesInPatSelection)
{
if (cachedScoresForThisIter.ContainsKey(word))
{
score = cachedScoresForThisIter.GetCount(word);
}
else
{
if (constVars.GetOtherSemanticClassesWords().Contains(word) || constVars.GetCommonEngWords().Contains(word))
{
score = 1;
}
else
{
if (constVars.usePatternEvalSemanticOdds)
{
double semanticClassOdds = 1;
if (dictOddsWordWeights.ContainsKey(word))
{
semanticClassOdds = 1 - dictOddsWordWeights.GetCount(word);
}
scoreslist.SetCount(ConstantsAndVariables.ScorePhraseMeasures.Semanticodds, semanticClassOdds);
}
if (constVars.usePatternEvalGoogleNgram)
{
double gscore = 0;
if (googleNgramNormScores.ContainsKey(word))
{
gscore = 1 - googleNgramNormScores.GetCount(word);
}
scoreslist.SetCount(ConstantsAndVariables.ScorePhraseMeasures.Googlengram, gscore);
}
if (constVars.usePatternEvalDomainNgram)
{
double domainscore;
if (domainNgramNormScores.ContainsKey(word))
{
domainscore = 1 - domainNgramNormScores.GetCount(word);
}
else
{
domainscore = 1 - scorePhrases.phraseScorer.GetPhraseWeightFromWords(domainNgramNormScores, word, scorePhrases.phraseScorer.OOVDomainNgramScore);
}
scoreslist.SetCount(ConstantsAndVariables.ScorePhraseMeasures.Domainngram, domainscore);
}
if (constVars.usePatternEvalWordClass)
{
double externalFeatureWt = externalWtsDefault;
if (externalFeatWtsNormalized.ContainsKey(word))
{
externalFeatureWt = 1 - externalFeatWtsNormalized.GetCount(word);
}
scoreslist.SetCount(ConstantsAndVariables.ScorePhraseMeasures.Distsim, externalFeatureWt);
}
if (constVars.usePatternEvalEditDistOther)
{
System.Diagnostics.Debug.Assert(editDistanceFromOtherSemanticBinaryScores.ContainsKey(word), "How come no edit distance info for word " + word + string.Empty);
scoreslist.SetCount(ConstantsAndVariables.ScorePhraseMeasures.Editdistother, editDistanceFromOtherSemanticBinaryScores.GetCount(word));
}
if (constVars.usePatternEvalEditDistSame)
{
scoreslist.SetCount(ConstantsAndVariables.ScorePhraseMeasures.Editdistsame, editDistanceFromAlreadyExtractedBinaryScores.GetCount(word));
}
// taking average
score = Counters.Mean(scoreslist);
phInPatScores.SetCounter(word, scoreslist);
}
cachedScoresForThisIter.SetCount(word, score);
}
}
else
{
if ((patternScoring.Equals(GetPatternsFromDataMultiClass.PatternScoring.Logreg) || patternScoring.Equals(GetPatternsFromDataMultiClass.PatternScoring.LOGREGlogP)) && scorePhrasesInPatSelection)
{
score = 1 - classifierScores.GetCount(word);
}
}
// score = 1 - scorePhrases.scoreUsingClassifer(classifier,
// e.getKey(), label, true, null, null, dictOddsWordWeights);
// throw new RuntimeException("not implemented yet");
if (useFreqPhraseExtractedByPat)
{
score = score * scoringFunction.ApplyAsDouble(new Pair <E, CandidatePhrase>(en.Key, word));
}
if (constVars.sqrtPatScore)
{
patterns.IncrementCount(en.Key, Math.Sqrt(score));
}
else
{
patterns.IncrementCount(en.Key, score);
}
}
}
return(patterns);
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.TypeLoadException"/>
internal virtual void SetUpProperties(string line, bool readFile, bool writeOutputToFile, string additionalSeedWordsFiles)
{
IJsonReader jsonReader = Javax.Json.Json.CreateReader(new StringReader(line));
IJsonObject objarr = jsonReader.ReadObject();
jsonReader.Close();
Properties props = new Properties();
foreach (string o in objarr.Keys)
{
if (o.Equals("seedWords"))
{
IJsonObject obj = objarr.GetJsonObject(o);
foreach (string st in obj.Keys)
{
seedWords[st] = new HashSet <CandidatePhrase>();
IJsonArray arr = obj.GetJsonArray(st);
for (int i = 0; i < arr.Count; i++)
{
string val = arr.GetString(i);
seedWords[st].Add(CandidatePhrase.CreateOrGet(val));
System.Console.Out.WriteLine("adding " + val + " for label " + st);
}
}
}
else
{
props.SetProperty(o, objarr.GetString(o));
}
}
System.Console.Out.WriteLine("seedwords are " + seedWords);
if (additionalSeedWordsFiles != null && !additionalSeedWordsFiles.IsEmpty())
{
IDictionary <string, ICollection <CandidatePhrase> > additionalSeedWords = GetPatternsFromDataMultiClass.ReadSeedWords(additionalSeedWordsFiles);
logger.Info("additional seed words are " + additionalSeedWords);
foreach (string label in seedWords.Keys)
{
if (additionalSeedWords.Contains(label))
{
Sharpen.Collections.AddAll(seedWords[label], additionalSeedWords[label]);
}
}
}
outputFile = null;
if (readFile)
{
System.Console.Out.WriteLine("input value is " + objarr.GetString("input"));
outputFile = props.GetProperty("input") + "_processed";
props.SetProperty("file", objarr.GetString("input"));
if (writeOutputToFile && !props.Contains("columnOutputFile"))
{
props.SetProperty("columnOutputFile", outputFile);
}
}
else
{
string systemdir = Runtime.GetProperty("java.io.tmpdir");
File tempFile = File.CreateTempFile("sents", ".tmp", new File(systemdir));
tempFile.DeleteOnExit();
IOUtils.WriteStringToFile(props.GetProperty("input"), tempFile.GetPath(), "utf8");
props.SetProperty("file", tempFile.GetAbsolutePath());
}
SetProperties(props);
this.props = props;
int i_1 = 1;
foreach (string label_1 in seedWords.Keys)
{
string ansclstr = "edu.stanford.nlp.patterns.PatternsAnnotations$PatternLabel" + i_1;
Type mcCl = (Type)Sharpen.Runtime.GetType(ansclstr);
machineAnswerClasses[label_1] = mcCl;
string humanansclstr = "edu.stanford.nlp.patterns.PatternsAnnotations$PatternHumanLabel" + i_1;
humanLabelClasses[label_1] = (Type)Sharpen.Runtime.GetType(humanansclstr);
i_1++;
}
}
/// <exception cref="System.MemberAccessException"/>
/// <exception cref="System.Exception"/>
/// <exception cref="Java.Util.Concurrent.ExecutionException"/>
/// <exception cref="System.IO.IOException"/>
/// <exception cref="Java.Lang.InstantiationException"/>
/// <exception cref="System.MissingMethodException"/>
/// <exception cref="System.Reflection.TargetInvocationException"/>
/// <exception cref="System.TypeLoadException"/>
/// <exception cref="Java.Sql.SQLException"/>
public virtual string SuggestPhrasesTest(Properties testProps, string modelPropertiesFile, string stopWordsFile)
{
logger.Info("Suggesting phrases in test");
logger.Info("test properties are " + testProps);
Properties runProps = StringUtils.ArgsToPropertiesWithResolve(new string[] { "-props", modelPropertiesFile });
string[] removeProperties = new string[] { "allPatternsDir", "storePatsForEachToken", "invertedIndexClass", "savePatternsWordsDir", "batchProcessSents", "outDir", "saveInvertedIndex", "removeOverLappingLabels", "numThreads" };
foreach (string s in removeProperties)
{
if (runProps.Contains(s))
{
runProps.Remove(s);
}
}
runProps.SetProperty("stopWordsPatternFiles", stopWordsFile);
runProps.SetProperty("englishWordsFiles", stopWordsFile);
runProps.SetProperty("commonWordsPatternFiles", stopWordsFile);
runProps.PutAll(props);
runProps.PutAll(testProps);
props.PutAll(runProps);
ProcessText(false);
GetPatternsFromDataMultiClass <SurfacePattern> model = new GetPatternsFromDataMultiClass <SurfacePattern>(runProps, Data.sents, seedWords, true, humanLabelClasses);
ArgumentParser.FillOptions(model, runProps);
GetPatternsFromDataMultiClass.LoadFromSavedPatternsWordsDir(model, runProps);
IDictionary <string, int> alreadyLearnedIters = new Dictionary <string, int>();
foreach (string label in model.constVars.GetLabels())
{
alreadyLearnedIters[label] = model.constVars.GetLearnedWordsEachIter()[label].LastEntry().Key;
}
if (model.constVars.learn)
{
// Map<String, E> p0 = new HashMap<String, SurfacePattern>();
// Map<String, Counter<CandidatePhrase>> p0Set = new HashMap<String, Counter<CandidatePhrase>>();
// Map<String, Set<E>> ignorePatterns = new HashMap<String, Set<E>>();
model.IterateExtractApply(null, null, null);
}
IDictionary <string, ICounter <CandidatePhrase> > allExtractions = new Dictionary <string, ICounter <CandidatePhrase> >();
//Only for one label right now!
string label_1 = model.constVars.GetLabels().GetEnumerator().Current;
allExtractions[label_1] = new ClassicCounter <CandidatePhrase>();
foreach (KeyValuePair <string, DataInstance> sent in Data.sents)
{
StringBuilder str = new StringBuilder();
foreach (CoreLabel l in sent.Value.GetTokens())
{
if (l.Get(typeof(PatternsAnnotations.MatchedPatterns)) != null && !l.Get(typeof(PatternsAnnotations.MatchedPatterns)).IsEmpty())
{
str.Append(" " + l.Word());
}
else
{
allExtractions[label_1].IncrementCount(CandidatePhrase.CreateOrGet(str.ToString().Trim()));
str.Length = 0;
}
}
}
allExtractions.PutAll(model.matchedSeedWords);
return(model.constVars.GetSetWordsAsJson(allExtractions));
}
