public virtual void Run(bool pathsAreFiles, bool displayWords, bool displayOOV)
{
if (useSplit)
{
IList <TreebankStats.ObservedCorpusStats> allSplitStats = new List <TreebankStats.ObservedCorpusStats>();
makeVocab = true;
foreach (KeyValuePair <TreebankStats.Split, ICollection <string> > split in splitFileLists)
{
DiskTreebank tb = tlpp.DiskTreebank();
IFileFilter splitFilter = new TreebankStats.SplitFilter(split.Value);
foreach (string path in pathNames)
{
tb.LoadPath(path, splitFilter);
}
TreebankStats.ObservedCorpusStats splitStats = GatherStats(tb, languageName.ToString() + "." + split.Key.ToString());
allSplitStats.Add(splitStats);
makeVocab = false;
}
Display(AggregateStats(allSplitStats), displayWords, displayOOV);
foreach (TreebankStats.ObservedCorpusStats ocs in allSplitStats)
{
Display(ocs, displayWords, displayOOV);
}
}
else
{
if (pathsAreFiles)
{
makeVocab = true;
foreach (string path in pathNames)
{
DiskTreebank tb = tlpp.DiskTreebank();
tb.LoadPath(path, null);
TreebankStats.ObservedCorpusStats stats = GatherStats(tb, languageName.ToString() + " " + path);
Display(stats, displayWords, displayOOV);
makeVocab = false;
}
}
else
{
trainVocab = Generics.NewHashSet();
DiskTreebank tb = tlpp.DiskTreebank();
foreach (string path in pathNames)
{
tb.LoadPath(path, null);
}
TreebankStats.ObservedCorpusStats allStats = GatherStats(tb, languageName.ToString());
Display(allStats, displayWords, displayOOV);
}
}
}
public static void Main(string[] args)
{
if (args.Length < minArgs)
{
System.Console.Out.WriteLine(Usage());
System.Environment.Exit(-1);
}
Properties options = StringUtils.ArgsToProperties(args, ArgDefs());
Language language = PropertiesUtils.Get(options, "l", Language.English, typeof(Language));
ITreebankLangParserParams tlpp = language.@params;
DiskTreebank tb = null;
string encoding = options.GetProperty("l", "UTF-8");
bool removeBracket = PropertiesUtils.GetBool(options, "b", false);
tlpp.SetInputEncoding(encoding);
tlpp.SetOutputEncoding(encoding);
tb = tlpp.DiskTreebank();
string[] files = options.GetProperty(string.Empty, string.Empty).Split("\\s+");
if (files.Length != 0)
{
foreach (string filename in files)
{
tb.LoadPath(filename);
}
}
else
{
log.Info(Usage());
System.Environment.Exit(-1);
}
PrintWriter pwo = tlpp.Pw();
string startSymbol = tlpp.TreebankLanguagePack().StartSymbol();
ITreeFactory tf = new LabeledScoredTreeFactory();
int nTrees = 0;
foreach (Tree t in tb)
{
if (removeBracket)
{
if (t.Value().Equals(startSymbol))
{
t = t.FirstChild();
}
}
else
{
if (!t.Value().Equals(startSymbol))
{
//Add a bracket if it isn't already there
t = tf.NewTreeNode(startSymbol, Java.Util.Collections.SingletonList(t));
}
}
pwo.Println(t.ToString());
nTrees++;
}
pwo.Close();
System.Console.Error.Printf("Processed %d trees.%n", nTrees);
}
// private static String stripTag(String tag) {
// if (tag.startsWith("DT")) {
// String newTag = tag.substring(2, tag.length());
// return newTag.length() > 0 ? newTag : tag;
// }
// return tag;
// }
/// <param name="args"/>
public static void Main(string[] args)
{
if (args.Length != 3)
{
System.Console.Error.Printf("Usage: java %s language filename features%n", typeof(TreebankFactoredLexiconStats).FullName);
System.Environment.Exit(-1);
}
Language language = Language.ValueOf(args[0]);
ITreebankLangParserParams tlpp = language.@params;
if (language.Equals(Language.Arabic))
{
string[] options = new string[] { "-arabicFactored" };
tlpp.SetOptionFlag(options, 0);
}
else
{
string[] options = new string[] { "-frenchFactored" };
tlpp.SetOptionFlag(options, 0);
}
Treebank tb = tlpp.DiskTreebank();
tb.LoadPath(args[1]);
MorphoFeatureSpecification morphoSpec = language.Equals(Language.Arabic) ? new ArabicMorphoFeatureSpecification() : new FrenchMorphoFeatureSpecification();
string[] features = args[2].Trim().Split(",");
foreach (string feature in features)
{
morphoSpec.Activate(MorphoFeatureSpecification.MorphoFeatureType.ValueOf(feature));
}
// Counters
ICounter <string> wordTagCounter = new ClassicCounter <string>(30000);
ICounter <string> morphTagCounter = new ClassicCounter <string>(500);
// Counter<String> signatureTagCounter = new ClassicCounter<String>();
ICounter <string> morphCounter = new ClassicCounter <string>(500);
ICounter <string> wordCounter = new ClassicCounter <string>(30000);
ICounter <string> tagCounter = new ClassicCounter <string>(300);
ICounter <string> lemmaCounter = new ClassicCounter <string>(25000);
ICounter <string> lemmaTagCounter = new ClassicCounter <string>(25000);
ICounter <string> richTagCounter = new ClassicCounter <string>(1000);
ICounter <string> reducedTagCounter = new ClassicCounter <string>(500);
ICounter <string> reducedTagLemmaCounter = new ClassicCounter <string>(500);
IDictionary <string, ICollection <string> > wordLemmaMap = Generics.NewHashMap();
TwoDimensionalIntCounter <string, string> lemmaReducedTagCounter = new TwoDimensionalIntCounter <string, string>(30000);
TwoDimensionalIntCounter <string, string> reducedTagTagCounter = new TwoDimensionalIntCounter <string, string>(500);
TwoDimensionalIntCounter <string, string> tagReducedTagCounter = new TwoDimensionalIntCounter <string, string>(300);
int numTrees = 0;
foreach (Tree tree in tb)
{
foreach (Tree subTree in tree)
{
if (!subTree.IsLeaf())
{
tlpp.TransformTree(subTree, tree);
}
}
IList <ILabel> pretermList = tree.PreTerminalYield();
IList <ILabel> yield = tree.Yield();
System.Diagnostics.Debug.Assert(yield.Count == pretermList.Count);
int yieldLen = yield.Count;
for (int i = 0; i < yieldLen; ++i)
{
string tag = pretermList[i].Value();
string word = yield[i].Value();
string morph = ((CoreLabel)yield[i]).OriginalText();
// Note: if there is no lemma, then we use the surface form.
Pair <string, string> lemmaTag = MorphoFeatureSpecification.SplitMorphString(word, morph);
string lemma = lemmaTag.First();
string richTag = lemmaTag.Second();
// WSGDEBUG
if (tag.Contains("MW"))
{
lemma += "-MWE";
}
lemmaCounter.IncrementCount(lemma);
lemmaTagCounter.IncrementCount(lemma + tag);
richTagCounter.IncrementCount(richTag);
string reducedTag = morphoSpec.StrToFeatures(richTag).ToString();
reducedTagCounter.IncrementCount(reducedTag);
reducedTagLemmaCounter.IncrementCount(reducedTag + lemma);
wordTagCounter.IncrementCount(word + tag);
morphTagCounter.IncrementCount(morph + tag);
morphCounter.IncrementCount(morph);
wordCounter.IncrementCount(word);
tagCounter.IncrementCount(tag);
reducedTag = reducedTag.Equals(string.Empty) ? "NONE" : reducedTag;
if (wordLemmaMap.Contains(word))
{
wordLemmaMap[word].Add(lemma);
}
else
{
ICollection <string> lemmas = Generics.NewHashSet(1);
wordLemmaMap[word] = lemmas;
}
lemmaReducedTagCounter.IncrementCount(lemma, reducedTag);
reducedTagTagCounter.IncrementCount(lemma + reducedTag, tag);
tagReducedTagCounter.IncrementCount(tag, reducedTag);
}
++numTrees;
}
// Barf...
System.Console.Out.WriteLine("Language: " + language.ToString());
System.Console.Out.Printf("#trees:\t%d%n", numTrees);
System.Console.Out.Printf("#tokens:\t%d%n", (int)wordCounter.TotalCount());
System.Console.Out.Printf("#words:\t%d%n", wordCounter.KeySet().Count);
System.Console.Out.Printf("#tags:\t%d%n", tagCounter.KeySet().Count);
System.Console.Out.Printf("#wordTagPairs:\t%d%n", wordTagCounter.KeySet().Count);
System.Console.Out.Printf("#lemmas:\t%d%n", lemmaCounter.KeySet().Count);
System.Console.Out.Printf("#lemmaTagPairs:\t%d%n", lemmaTagCounter.KeySet().Count);
System.Console.Out.Printf("#feattags:\t%d%n", reducedTagCounter.KeySet().Count);
System.Console.Out.Printf("#feattag+lemmas:\t%d%n", reducedTagLemmaCounter.KeySet().Count);
System.Console.Out.Printf("#richtags:\t%d%n", richTagCounter.KeySet().Count);
System.Console.Out.Printf("#richtag+lemma:\t%d%n", morphCounter.KeySet().Count);
System.Console.Out.Printf("#richtag+lemmaTagPairs:\t%d%n", morphTagCounter.KeySet().Count);
// Extra
System.Console.Out.WriteLine("==================");
StringBuilder sbNoLemma = new StringBuilder();
StringBuilder sbMultLemmas = new StringBuilder();
foreach (KeyValuePair <string, ICollection <string> > wordLemmas in wordLemmaMap)
{
string word = wordLemmas.Key;
ICollection <string> lemmas = wordLemmas.Value;
if (lemmas.Count == 0)
{
sbNoLemma.Append("NO LEMMAS FOR WORD: " + word + "\n");
continue;
}
if (lemmas.Count > 1)
{
sbMultLemmas.Append("MULTIPLE LEMMAS: " + word + " " + SetToString(lemmas) + "\n");
continue;
}
string lemma = lemmas.GetEnumerator().Current;
ICollection <string> reducedTags = lemmaReducedTagCounter.GetCounter(lemma).KeySet();
if (reducedTags.Count > 1)
{
System.Console.Out.Printf("%s --> %s%n", word, lemma);
foreach (string reducedTag in reducedTags)
{
int count = lemmaReducedTagCounter.GetCount(lemma, reducedTag);
string posTags = SetToString(reducedTagTagCounter.GetCounter(lemma + reducedTag).KeySet());
System.Console.Out.Printf("\t%s\t%d\t%s%n", reducedTag, count, posTags);
}
System.Console.Out.WriteLine();
}
}
System.Console.Out.WriteLine("==================");
System.Console.Out.WriteLine(sbNoLemma.ToString());
System.Console.Out.WriteLine(sbMultLemmas.ToString());
System.Console.Out.WriteLine("==================");
IList <string> tags = new List <string>(tagReducedTagCounter.FirstKeySet());
tags.Sort();
foreach (string tag_1 in tags)
{
System.Console.Out.WriteLine(tag_1);
ICollection <string> reducedTags = tagReducedTagCounter.GetCounter(tag_1).KeySet();
foreach (string reducedTag in reducedTags)
{
int count = tagReducedTagCounter.GetCount(tag_1, reducedTag);
// reducedTag = reducedTag.equals("") ? "NONE" : reducedTag;
System.Console.Out.Printf("\t%s\t%d%n", reducedTag, count);
}
System.Console.Out.WriteLine();
}
System.Console.Out.WriteLine("==================");
}
/// <param name="args"/>
public static void Main(string[] args)
{
if (args.Length != 4)
{
System.Console.Error.Printf("Usage: java %s language features train_file dev_file%n", typeof(Edu.Stanford.Nlp.Parser.Lexparser.FactoredLexicon).FullName);
System.Environment.Exit(-1);
}
// Command line options
Language language = Language.ValueOf(args[0]);
ITreebankLangParserParams tlpp = language.@params;
Treebank trainTreebank = tlpp.DiskTreebank();
trainTreebank.LoadPath(args[2]);
Treebank devTreebank = tlpp.DiskTreebank();
devTreebank.LoadPath(args[3]);
MorphoFeatureSpecification morphoSpec;
Options options = GetOptions(language);
if (language.Equals(Language.Arabic))
{
morphoSpec = new ArabicMorphoFeatureSpecification();
string[] languageOptions = new string[] { "-arabicFactored" };
tlpp.SetOptionFlag(languageOptions, 0);
}
else
{
if (language.Equals(Language.French))
{
morphoSpec = new FrenchMorphoFeatureSpecification();
string[] languageOptions = new string[] { "-frenchFactored" };
tlpp.SetOptionFlag(languageOptions, 0);
}
else
{
throw new NotSupportedException();
}
}
string featureList = args[1];
string[] features = featureList.Trim().Split(",");
foreach (string feature in features)
{
morphoSpec.Activate(MorphoFeatureSpecification.MorphoFeatureType.ValueOf(feature));
}
System.Console.Out.WriteLine("Language: " + language.ToString());
System.Console.Out.WriteLine("Features: " + args[1]);
// Create word and tag indices
// Save trees in a collection since the interface requires that....
System.Console.Out.Write("Loading training trees...");
IList <Tree> trainTrees = new List <Tree>(19000);
IIndex <string> wordIndex = new HashIndex <string>();
IIndex <string> tagIndex = new HashIndex <string>();
foreach (Tree tree in trainTreebank)
{
foreach (Tree subTree in tree)
{
if (!subTree.IsLeaf())
{
tlpp.TransformTree(subTree, tree);
}
}
trainTrees.Add(tree);
}
System.Console.Out.Printf("Done! (%d trees)%n", trainTrees.Count);
// Setup and train the lexicon.
System.Console.Out.Write("Collecting sufficient statistics for lexicon...");
Edu.Stanford.Nlp.Parser.Lexparser.FactoredLexicon lexicon = new Edu.Stanford.Nlp.Parser.Lexparser.FactoredLexicon(options, morphoSpec, wordIndex, tagIndex);
lexicon.InitializeTraining(trainTrees.Count);
lexicon.Train(trainTrees, null);
lexicon.FinishTraining();
System.Console.Out.WriteLine("Done!");
trainTrees = null;
// Load the tuning set
System.Console.Out.Write("Loading tuning set...");
IList <FactoredLexiconEvent> tuningSet = GetTuningSet(devTreebank, lexicon, tlpp);
System.Console.Out.Printf("...Done! (%d events)%n", tuningSet.Count);
// Print the probabilities that we obtain
// TODO(spenceg): Implement tagging accuracy with FactLex
int nCorrect = 0;
ICounter <string> errors = new ClassicCounter <string>();
foreach (FactoredLexiconEvent @event in tuningSet)
{
IEnumerator <IntTaggedWord> itr = lexicon.RuleIteratorByWord(@event.Word(), @event.GetLoc(), @event.FeatureStr());
ICounter <int> logScores = new ClassicCounter <int>();
bool noRules = true;
int goldTagId = -1;
while (itr.MoveNext())
{
noRules = false;
IntTaggedWord iTW = itr.Current;
if (iTW.Tag() == @event.TagId())
{
log.Info("GOLD-");
goldTagId = iTW.Tag();
}
float tagScore = lexicon.Score(iTW, @event.GetLoc(), @event.Word(), @event.FeatureStr());
logScores.IncrementCount(iTW.Tag(), tagScore);
}
if (noRules)
{
System.Console.Error.Printf("NO TAGGINGS: %s %s%n", @event.Word(), @event.FeatureStr());
}
else
{
// Score the tagging
int hypTagId = Counters.Argmax(logScores);
if (hypTagId == goldTagId)
{
++nCorrect;
}
else
{
string goldTag = goldTagId < 0 ? "UNSEEN" : lexicon.tagIndex.Get(goldTagId);
errors.IncrementCount(goldTag);
}
}
log.Info();
}
// Output accuracy
double acc = (double)nCorrect / (double)tuningSet.Count;
System.Console.Error.Printf("%n%nACCURACY: %.2f%n%n", acc * 100.0);
log.Info("% of errors by type:");
IList <string> biggestKeys = new List <string>(errors.KeySet());
biggestKeys.Sort(Counters.ToComparator(errors, false, true));
Counters.Normalize(errors);
foreach (string key in biggestKeys)
{
System.Console.Error.Printf("%s\t%.2f%n", key, errors.GetCount(key) * 100.0);
}
}
/// <summary>Run the Evalb scoring metric on guess/gold input.</summary>
/// <remarks>Run the Evalb scoring metric on guess/gold input. The default language is English.</remarks>
/// <param name="args"/>
public static void Main(string[] args)
{
if (args.Length < minArgs)
{
log.Info(Usage());
System.Environment.Exit(-1);
}
Properties options = StringUtils.ArgsToProperties(args, OptionArgDefs());
Language language = PropertiesUtils.Get(options, "l", Language.English, typeof(Language));
ITreebankLangParserParams tlpp = language.@params;
int maxGoldYield = PropertiesUtils.GetInt(options, "y", int.MaxValue);
bool Verbose = PropertiesUtils.GetBool(options, "v", false);
bool sortByF1 = PropertiesUtils.HasProperty(options, "s");
int worstKTreesToEmit = PropertiesUtils.GetInt(options, "s", 0);
PriorityQueue <Triple <double, Tree, Tree> > queue = sortByF1 ? new PriorityQueue <Triple <double, Tree, Tree> >(2000, new Evalb.F1Comparator()) : null;
bool doCatLevel = PropertiesUtils.GetBool(options, "c", false);
string labelRegex = options.GetProperty("f", null);
string encoding = options.GetProperty("e", "UTF-8");
string[] parsedArgs = options.GetProperty(string.Empty, string.Empty).Split("\\s+");
if (parsedArgs.Length != minArgs)
{
log.Info(Usage());
System.Environment.Exit(-1);
}
string goldFile = parsedArgs[0];
string guessFile = parsedArgs[1];
// Command-line has been parsed. Configure the metric for evaluation.
tlpp.SetInputEncoding(encoding);
PrintWriter pwOut = tlpp.Pw();
Treebank guessTreebank = tlpp.DiskTreebank();
guessTreebank.LoadPath(guessFile);
pwOut.Println("GUESS TREEBANK:");
pwOut.Println(guessTreebank.TextualSummary());
Treebank goldTreebank = tlpp.DiskTreebank();
goldTreebank.LoadPath(goldFile);
pwOut.Println("GOLD TREEBANK:");
pwOut.Println(goldTreebank.TextualSummary());
Evalb metric = new Evalb("Evalb LP/LR", true);
EvalbByCat evalbCat = (doCatLevel) ? new EvalbByCat("EvalbByCat LP/LR", true, labelRegex) : null;
ITreeTransformer tc = tlpp.Collinizer();
//The evalb ref implementation assigns status for each tree pair as follows:
//
// 0 - Ok (yields match)
// 1 - length mismatch
// 2 - null parse e.g. (()).
//
//In the cases of 1,2, evalb does not include the tree pair in the LP/LR computation.
IEnumerator <Tree> goldItr = goldTreebank.GetEnumerator();
IEnumerator <Tree> guessItr = guessTreebank.GetEnumerator();
int goldLineId = 0;
int guessLineId = 0;
int skippedGuessTrees = 0;
while (guessItr.MoveNext() && goldItr.MoveNext())
{
Tree guessTree = guessItr.Current;
IList <ILabel> guessYield = guessTree.Yield();
guessLineId++;
Tree goldTree = goldItr.Current;
IList <ILabel> goldYield = goldTree.Yield();
goldLineId++;
// Check that we should evaluate this tree
if (goldYield.Count > maxGoldYield)
{
skippedGuessTrees++;
continue;
}
// Only trees with equal yields can be evaluated
if (goldYield.Count != guessYield.Count)
{
pwOut.Printf("Yield mismatch gold: %d tokens vs. guess: %d tokens (lines: gold %d guess %d)%n", goldYield.Count, guessYield.Count, goldLineId, guessLineId);
skippedGuessTrees++;
continue;
}
Tree evalGuess = tc.TransformTree(guessTree);
Tree evalGold = tc.TransformTree(goldTree);
metric.Evaluate(evalGuess, evalGold, ((Verbose) ? pwOut : null));
if (doCatLevel)
{
evalbCat.Evaluate(evalGuess, evalGold, ((Verbose) ? pwOut : null));
}
if (sortByF1)
{
StoreTrees(queue, guessTree, goldTree, metric.GetLastF1());
}
}
if (guessItr.MoveNext() || goldItr.MoveNext())
{
System.Console.Error.Printf("Guess/gold files do not have equal lengths (guess: %d gold: %d)%n.", guessLineId, goldLineId);
}
pwOut.Println("================================================================================");
if (skippedGuessTrees != 0)
{
pwOut.Printf("%s %d guess trees\n", "Unable to evaluate", skippedGuessTrees);
}
metric.Display(true, pwOut);
pwOut.Println();
if (doCatLevel)
{
evalbCat.Display(true, pwOut);
pwOut.Println();
}
if (sortByF1)
{
EmitSortedTrees(queue, worstKTreesToEmit, guessFile);
}
pwOut.Close();
}
public static void Main(string[] args)
{
if (args.Length < minArgs)
{
System.Console.Out.WriteLine(usage);
System.Environment.Exit(-1);
}
// Process command-line options
Properties options = StringUtils.ArgsToProperties(args, optionArgDefinitions);
string fileName = options.GetProperty(string.Empty);
if (fileName == null || fileName.Equals(string.Empty))
{
System.Console.Out.WriteLine(usage);
System.Environment.Exit(-1);
}
Language language = PropertiesUtils.Get(options, "l", Language.English, typeof(Language));
ITreebankLangParserParams tlpp = language.@params;
string encoding = options.GetProperty("e", "UTF-8");
tlpp.SetInputEncoding(encoding);
tlpp.SetOutputEncoding(encoding);
DiskTreebank tb = tlpp.DiskTreebank();
tb.LoadPath(fileName);
// Statistics
ICounter <string> binaryRuleTypes = new ClassicCounter <string>(20000);
IList <int> branchingFactors = new List <int>(20000);
int nTrees = 0;
int nUnaryRules = 0;
int nBinaryRules = 0;
int binaryBranchingFactors = 0;
// Read the treebank
PrintWriter pw = tlpp.Pw();
foreach (Tree tree in tb)
{
if (tree.Value().Equals("ROOT"))
{
tree = tree.FirstChild();
}
++nTrees;
foreach (Tree subTree in tree)
{
if (subTree.IsPhrasal())
{
if (subTree.NumChildren() > 1)
{
++nBinaryRules;
branchingFactors.Add(subTree.NumChildren());
binaryBranchingFactors += subTree.NumChildren();
binaryRuleTypes.IncrementCount(TreeToRuleString(subTree));
}
else
{
++nUnaryRules;
}
}
}
}
double mean = (double)binaryBranchingFactors / (double)nBinaryRules;
System.Console.Out.Printf("#trees:\t%d%n", nTrees);
System.Console.Out.Printf("#binary:\t%d%n", nBinaryRules);
System.Console.Out.Printf("#binary types:\t%d%n", binaryRuleTypes.KeySet().Count);
System.Console.Out.Printf("mean branching:\t%.4f%n", mean);
System.Console.Out.Printf("stddev branching:\t%.4f%n", StandardDeviation(branchingFactors, mean));
System.Console.Out.Printf("rule entropy:\t%.5f%n", Counters.Entropy(binaryRuleTypes));
System.Console.Out.Printf("#unaries:\t%d%n", nUnaryRules);
}
/// <summary>Execute with no arguments for usage.</summary>
public static void Main(string[] args)
{
if (!ValidateCommandLine(args))
{
log.Info(Usage);
System.Environment.Exit(-1);
}
ITreebankLangParserParams tlpp = Language.@params;
PrintWriter pwOut = tlpp.Pw();
Treebank guessTreebank = tlpp.DiskTreebank();
guessTreebank.LoadPath(guessFile);
pwOut.Println("GUESS TREEBANK:");
pwOut.Println(guessTreebank.TextualSummary());
Treebank goldTreebank = tlpp.DiskTreebank();
goldTreebank.LoadPath(goldFile);
pwOut.Println("GOLD TREEBANK:");
pwOut.Println(goldTreebank.TextualSummary());
Edu.Stanford.Nlp.Parser.Metrics.LeafAncestorEval metric = new Edu.Stanford.Nlp.Parser.Metrics.LeafAncestorEval("LeafAncestor");
ITreeTransformer tc = tlpp.Collinizer();
//The evalb ref implementation assigns status for each tree pair as follows:
//
// 0 - Ok (yields match)
// 1 - length mismatch
// 2 - null parse e.g. (()).
//
//In the cases of 1,2, evalb does not include the tree pair in the LP/LR computation.
IEnumerator <Tree> goldItr = goldTreebank.GetEnumerator();
IEnumerator <Tree> guessItr = guessTreebank.GetEnumerator();
int goldLineId = 0;
int guessLineId = 0;
int skippedGuessTrees = 0;
while (guessItr.MoveNext() && goldItr.MoveNext())
{
Tree guessTree = guessItr.Current;
IList <ILabel> guessYield = guessTree.Yield();
guessLineId++;
Tree goldTree = goldItr.Current;
IList <ILabel> goldYield = goldTree.Yield();
goldLineId++;
// Check that we should evaluate this tree
if (goldYield.Count > MaxGoldYield)
{
skippedGuessTrees++;
continue;
}
// Only trees with equal yields can be evaluated
if (goldYield.Count != guessYield.Count)
{
pwOut.Printf("Yield mismatch gold: %d tokens vs. guess: %d tokens (lines: gold %d guess %d)%n", goldYield.Count, guessYield.Count, goldLineId, guessLineId);
skippedGuessTrees++;
continue;
}
Tree evalGuess = tc.TransformTree(guessTree);
Tree evalGold = tc.TransformTree(goldTree);
metric.Evaluate(evalGuess, evalGold, ((Verbose) ? pwOut : null));
}
if (guessItr.MoveNext() || goldItr.MoveNext())
{
System.Console.Error.Printf("Guess/gold files do not have equal lengths (guess: %d gold: %d)%n.", guessLineId, goldLineId);
}
pwOut.Println("================================================================================");
if (skippedGuessTrees != 0)
{
pwOut.Printf("%s %d guess trees%n", "Unable to evaluate", skippedGuessTrees);
}
metric.Display(true, pwOut);
pwOut.Close();
}
/// <param name="args"/>
public static void Main(string[] args)
{
if (args.Length < MinArgs)
{
log.Info(Usage());
System.Environment.Exit(-1);
}
Properties options = StringUtils.ArgsToProperties(args, OptionArgDefs());
bool Verbose = PropertiesUtils.GetBool(options, "v", false);
Language Language = PropertiesUtils.Get(options, "l", Language.English, typeof(Language));
int MaxGoldYield = PropertiesUtils.GetInt(options, "g", int.MaxValue);
int MaxGuessYield = PropertiesUtils.GetInt(options, "y", int.MaxValue);
string[] parsedArgs = options.GetProperty(string.Empty, string.Empty).Split("\\s+");
if (parsedArgs.Length != MinArgs)
{
log.Info(Usage());
System.Environment.Exit(-1);
}
File goldFile = new File(parsedArgs[0]);
File guessFile = new File(parsedArgs[1]);
ITreebankLangParserParams tlpp = Language.@params;
PrintWriter pwOut = tlpp.Pw();
Treebank guessTreebank = tlpp.DiskTreebank();
guessTreebank.LoadPath(guessFile);
pwOut.Println("GUESS TREEBANK:");
pwOut.Println(guessTreebank.TextualSummary());
Treebank goldTreebank = tlpp.DiskTreebank();
goldTreebank.LoadPath(goldFile);
pwOut.Println("GOLD TREEBANK:");
pwOut.Println(goldTreebank.TextualSummary());
Edu.Stanford.Nlp.Parser.Metrics.CollinsDepEval depEval = new Edu.Stanford.Nlp.Parser.Metrics.CollinsDepEval("CollinsDep", true, tlpp.HeadFinder(), tlpp.TreebankLanguagePack().StartSymbol());
ITreeTransformer tc = tlpp.Collinizer();
//PennTreeReader skips over null/malformed parses. So when the yields of the gold/guess trees
//don't match, we need to keep looking for the next gold tree that matches.
//The evalb ref implementation differs slightly as it expects one tree per line. It assigns
//status as follows:
//
// 0 - Ok (yields match)
// 1 - length mismatch
// 2 - null parse e.g. (()).
//
//In the cases of 1,2, evalb does not include the tree pair in the LP/LR computation.
IEnumerator <Tree> goldItr = goldTreebank.GetEnumerator();
int goldLineId = 0;
int skippedGuessTrees = 0;
foreach (Tree guess in guessTreebank)
{
Tree evalGuess = tc.TransformTree(guess);
if (guess.Yield().Count > MaxGuessYield)
{
skippedGuessTrees++;
continue;
}
bool doneEval = false;
while (goldItr.MoveNext() && !doneEval)
{
Tree gold = goldItr.Current;
Tree evalGold = tc.TransformTree(gold);
goldLineId++;
if (gold.Yield().Count > MaxGoldYield)
{
continue;
}
else
{
if (evalGold.Yield().Count != evalGuess.Yield().Count)
{
pwOut.Println("Yield mismatch at gold line " + goldLineId);
skippedGuessTrees++;
break;
}
}
//Default evalb behavior -- skip this guess tree
depEval.Evaluate(evalGuess, evalGold, ((Verbose) ? pwOut : null));
doneEval = true;
}
}
//Move to the next guess parse
pwOut.Println("================================================================================");
if (skippedGuessTrees != 0)
{
pwOut.Printf("%s %d guess trees\n", ((MaxGuessYield < int.MaxValue) ? "Skipped" : "Unable to evaluate"), skippedGuessTrees);
}
depEval.Display(true, pwOut);
pwOut.Close();
}
public static void Main(string[] args)
{
if (args.Length < minArgs)
{
System.Console.Out.WriteLine(usage);
System.Environment.Exit(-1);
}
// Process command-line options
Properties options = StringUtils.ArgsToProperties(args, optionArgDefinitions);
string fileName = options.GetProperty(string.Empty);
if (fileName == null || fileName.Equals(string.Empty))
{
System.Console.Out.WriteLine(usage);
System.Environment.Exit(-1);
}
int maxLen = PropertiesUtils.GetInt(options, "y", int.MaxValue);
bool printTrees = PropertiesUtils.GetBool(options, "p", false);
bool flattenTrees = PropertiesUtils.GetBool(options, "f", false);
bool printPOS = PropertiesUtils.GetBool(options, "a", false);
bool printTnT = PropertiesUtils.GetBool(options, "t", false);
Language language = PropertiesUtils.Get(options, "l", Language.English, typeof(Language));
ITreebankLangParserParams tlpp = language.@params;
string encoding = options.GetProperty("e", "UTF-8");
tlpp.SetInputEncoding(encoding);
tlpp.SetOutputEncoding(encoding);
DiskTreebank tb = tlpp.DiskTreebank();
tb.LoadPath(fileName);
// Read the treebank
PrintWriter pw = tlpp.Pw();
int numTrees = 0;
foreach (Tree tree in tb)
{
if (tree.Yield().Count > maxLen)
{
continue;
}
++numTrees;
if (printTrees)
{
pw.Println(tree.ToString());
}
else
{
if (flattenTrees)
{
pw.Println(SentenceUtils.ListToString(tree.Yield()));
}
else
{
if (printPOS)
{
pw.Println(SentenceUtils.ListToString(tree.PreTerminalYield()));
}
else
{
if (printTnT)
{
IList <CoreLabel> yield = tree.TaggedLabeledYield();
foreach (CoreLabel label in yield)
{
pw.Printf("%s\t%s%n", label.Word(), label.Tag());
}
pw.Println();
}
}
}
}
}
System.Console.Error.Printf("Read %d trees.%n", numTrees);
}
