public virtual void TestSetCount()
{
NUnit.Framework.Assert.AreEqual(c.TotalCount(), 21.0);
c.SetCount("p", "q", 1.0);
NUnit.Framework.Assert.AreEqual(c.TotalCount(), 22.0);
NUnit.Framework.Assert.AreEqual(c.TotalCount("p"), 1.0);
NUnit.Framework.Assert.AreEqual(c.GetCount("p", "q"), 1.0);
c.Remove("p", "q");
}
public static void PrintCounter(TwoDimensionalCounter <string, string> cnt, string fname)
{
try
{
PrintWriter pw = new PrintWriter(new TextWriter(new FileOutputStream(new File(fname)), false, "UTF-8"));
foreach (string key in cnt.FirstKeySet())
{
foreach (string val in cnt.GetCounter(key).KeySet())
{
pw.Printf("%s\t%s\t%d%n", key, val, (int)cnt.GetCount(key, val));
}
}
pw.Close();
}
catch (UnsupportedEncodingException e)
{
Sharpen.Runtime.PrintStackTrace(e);
}
catch (FileNotFoundException e)
{
Sharpen.Runtime.PrintStackTrace(e);
}
}
/// <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 virtual double[] GetInformationGains()
{
// assert size > 0;
// data = trimToSize(data); // Don't need to trim to size, and trimming is dangerous the dataset is empty (you can't add to it thereafter)
labels = TrimToSize(labels);
// counts the number of times word X is present
ClassicCounter <F> featureCounter = new ClassicCounter <F>();
// counts the number of time a document has label Y
ClassicCounter <L> labelCounter = new ClassicCounter <L>();
// counts the number of times the document has label Y given word X is present
TwoDimensionalCounter <F, L> condCounter = new TwoDimensionalCounter <F, L>();
for (int i = 0; i < labels.Length; i++)
{
labelCounter.IncrementCount(labelIndex.Get(labels[i]));
// convert the document to binary feature representation
bool[] doc = new bool[featureIndex.Size()];
//logger.info(i);
for (int j = 0; j < data[i].Length; j++)
{
doc[data[i][j]] = true;
}
for (int j_1 = 0; j_1 < doc.Length; j_1++)
{
if (doc[j_1])
{
featureCounter.IncrementCount(featureIndex.Get(j_1));
condCounter.IncrementCount(featureIndex.Get(j_1), labelIndex.Get(labels[i]), 1.0);
}
}
}
double entropy = 0.0;
for (int i_1 = 0; i_1 < labelIndex.Size(); i_1++)
{
double labelCount = labelCounter.GetCount(labelIndex.Get(i_1));
double p = labelCount / Size();
entropy -= p * (Math.Log(p) / Math.Log(2));
}
double[] ig = new double[featureIndex.Size()];
Arrays.Fill(ig, entropy);
for (int i_2 = 0; i_2 < featureIndex.Size(); i_2++)
{
F feature = featureIndex.Get(i_2);
double featureCount = featureCounter.GetCount(feature);
double notFeatureCount = Size() - featureCount;
double pFeature = featureCount / Size();
double pNotFeature = (1.0 - pFeature);
if (featureCount == 0)
{
ig[i_2] = 0;
continue;
}
if (notFeatureCount == 0)
{
ig[i_2] = 0;
continue;
}
double sumFeature = 0.0;
double sumNotFeature = 0.0;
for (int j = 0; j < labelIndex.Size(); j++)
{
L label = labelIndex.Get(j);
double featureLabelCount = condCounter.GetCount(feature, label);
double notFeatureLabelCount = Size() - featureLabelCount;
// yes, these dont sum to 1. that is correct.
// one is the prob of the label, given that the
// feature is present, and the other is the prob
// of the label given that the feature is absent
double p = featureLabelCount / featureCount;
double pNot = notFeatureLabelCount / notFeatureCount;
if (featureLabelCount != 0)
{
sumFeature += p * (Math.Log(p) / Math.Log(2));
}
if (notFeatureLabelCount != 0)
{
sumNotFeature += pNot * (Math.Log(pNot) / Math.Log(2));
}
}
//System.out.println(pNot+" "+(Math.log(pNot)/Math.log(2)));
//logger.info(pFeature+" * "+sumFeature+" = +"+);
//logger.info("^ "+pNotFeature+" "+sumNotFeature);
ig[i_2] += pFeature * sumFeature + pNotFeature * sumNotFeature;
}
/* earlier the line above used to be: ig[i] = pFeature*sumFeature + pNotFeature*sumNotFeature;
* This completely ignored the entropy term computed above. So added the "+=" to take that into account.
* -Ramesh ([email protected])
*/
return(ig);
}
