/// <exception cref="System.IO.IOException"/>
public NERClassifierCombiner(bool applyNumericClassifiers, NERClassifierCombiner.Language nerLanguage, bool useSUTime, bool augmentRegexNER, Properties nscProps, params string[] loadPaths)
: base(nscProps, ClassifierCombiner.ExtractCombinationModeSafe(nscProps), loadPaths)
{
// NOTE: nscProps may contains sutime props which will not be recognized by the SeqClassifierFlags
this.applyNumericClassifiers = applyNumericClassifiers;
this.nerLanguage = nerLanguage;
this.useSUTime = useSUTime;
// check for which language to use for number sequence classifier
if (nerLanguage == NERClassifierCombiner.Language.Chinese)
{
this.nsc = new ChineseNumberSequenceClassifier(new Properties(), useSUTime, nscProps);
}
else
{
this.nsc = new NumberSequenceClassifier(new Properties(), useSUTime, nscProps);
}
if (augmentRegexNER)
{
this.gazetteMapping = ReadRegexnerGazette(DefaultPaths.DefaultNerGazetteMapping);
}
else
{
this.gazetteMapping = Java.Util.Collections.EmptyMap();
}
}
/// <summary>Method for displaying info about an NERClassifierCombiner.</summary>
public static void ShowNCCInfo(NERClassifierCombiner ncc)
{
log.Info(string.Empty);
log.Info("info for this NERClassifierCombiner: ");
ClassifierCombiner.ShowCCInfo(ncc);
log.Info("useSUTime: " + ncc.useSUTime);
log.Info("applyNumericClassifier: " + ncc.applyNumericClassifiers);
log.Info(string.Empty);
}
public virtual void RunTest(string[] firstInput, string[] secondInput, string[] expectedOutput, params string[] labels)
{
IList <CoreLabel> input1 = CoreUtilities.ToCoreLabelList(words, tags, firstInput);
IList <CoreLabel> input2 = CoreUtilities.ToCoreLabelList(words, tags, secondInput);
IList <CoreLabel> result = CoreUtilities.ToCoreLabelList(words, tags, expectedOutput);
ICollection <string> auxLabels = new HashSet <string>();
foreach (string label in labels)
{
auxLabels.Add(label);
}
ClassifierCombiner.MergeTwoDocuments(input1, input2, auxLabels, "O");
NUnit.Framework.Assert.AreEqual(result, input1);
}
public virtual void OutputResults(string[] firstInput, string[] secondInput, string[] expectedOutput, params string[] labels)
{
IList <CoreLabel> input1 = CoreUtilities.ToCoreLabelList(words, tags, firstInput);
IList <CoreLabel> input2 = CoreUtilities.ToCoreLabelList(words, tags, secondInput);
IList <CoreLabel> result = CoreUtilities.ToCoreLabelList(words, tags, expectedOutput);
ICollection <string> auxLabels = new HashSet <string>();
foreach (string label in labels)
{
auxLabels.Add(label);
}
ClassifierCombiner.MergeTwoDocuments(input1, input2, auxLabels, "O");
foreach (CoreLabel word in input1)
{
System.Console.Out.WriteLine(word.Word() + " " + word.Tag() + " " + word.Get(typeof(CoreAnnotations.AnswerAnnotation)));
}
}
/// <summary>The main method.</summary>
/// <exception cref="System.Exception"/>
public static void Main(string[] args)
{
StringUtils.LogInvocationString(log, args);
Properties props = StringUtils.ArgsToProperties(args);
SeqClassifierFlags flags = new SeqClassifierFlags(props, false);
// false for print probs as printed in next code block
string loadPath = props.GetProperty("loadClassifier");
NERClassifierCombiner ncc;
if (loadPath != null)
{
// note that when loading a serialized classifier, the philosophy is override
// any settings in props with those given in the commandline
// so if you dumped it with useSUTime = false, and you say -useSUTime at
// the commandline, the commandline takes precedence
ncc = ((NERClassifierCombiner)GetClassifier(loadPath, props));
}
else
{
// pass null for passDownProperties to let all props go through
ncc = CreateNERClassifierCombiner("ner", null, props);
}
// write the NERClassifierCombiner to the given path on disk
string serializeTo = props.GetProperty("serializeTo");
if (serializeTo != null)
{
ncc.SerializeClassifier(serializeTo);
}
string textFile = props.GetProperty("textFile");
if (textFile != null)
{
ncc.ClassifyAndWriteAnswers(textFile);
}
// run on multiple textFiles , based off CRFClassifier code
string textFiles = props.GetProperty("textFiles");
if (textFiles != null)
{
IList <File> files = new List <File>();
foreach (string filename in textFiles.Split(","))
{
files.Add(new File(filename));
}
ncc.ClassifyFilesAndWriteAnswers(files);
}
// options for run the NERClassifierCombiner on a testFile or testFiles
string testFile = props.GetProperty("testFile");
string testFiles = props.GetProperty("testFiles");
string crfToExamine = props.GetProperty("crfToExamine");
IDocumentReaderAndWriter <CoreLabel> readerAndWriter = ncc.DefaultReaderAndWriter();
if (testFile != null || testFiles != null)
{
// check if there is not a crf specific request
if (crfToExamine == null)
{
// in this case there is no crfToExamine
if (testFile != null)
{
ncc.ClassifyAndWriteAnswers(testFile, readerAndWriter, true);
}
else
{
IList <File> files = Arrays.Stream(testFiles.Split(",")).Map(null).Collect(Collectors.ToList());
ncc.ClassifyFilesAndWriteAnswers(files, ncc.DefaultReaderAndWriter(), true);
}
}
else
{
ClassifierCombiner.ExamineCRF(ncc, crfToExamine, flags, testFile, testFiles, readerAndWriter);
}
}
// option for showing info about the NERClassifierCombiner
string showNCCInfo = props.GetProperty("showNCCInfo");
if (showNCCInfo != null)
{
ShowNCCInfo(ncc);
}
// option for reading in from stdin
if (flags.readStdin)
{
ncc.ClassifyStdin();
}
}
