opennlp.tools.doccat.DocumentCategorizerME Java Examples

The following examples show how to use opennlp.tools.doccat.DocumentCategorizerME. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: Chapter6.java    From Natural-Language-Processing-with-Java-Second-Edition with MIT License 6 votes vote down vote up 
private static void usingOpenNLP() {
    try (InputStream modelIn = new FileInputStream(
            new File("en-animal.model"));) {
        DoccatModel model = new DoccatModel(modelIn);
        DocumentCategorizerME categorizer = new DocumentCategorizerME(model);
        double[] outcomes = categorizer.categorize(inputText);
        for (int i = 0; i < categorizer.getNumberOfCategories(); i++) {
            String category = categorizer.getCategory(i);
            System.out.println(category + " - " + outcomes[i]);
        }
        System.out.println(categorizer.getBestCategory(outcomes));
        System.out.println(categorizer.getAllResults(outcomes));
    } catch (IOException ex) {
        ex.printStackTrace();
    }
}
Example #2
Source File: OpenNlpDoccatRecommender.java    From inception with Apache License 2.0 5 votes vote down vote up 
@Override
public void predict(RecommenderContext aContext, CAS aCas) throws RecommendationException
{
    DoccatModel model = aContext.get(KEY_MODEL).orElseThrow(() -> 
            new RecommendationException("Key [" + KEY_MODEL + "] not found in context"));
    
    DocumentCategorizerME finder = new DocumentCategorizerME(model);

    Type sentenceType = getType(aCas, Sentence.class);
    Type predictedType = getPredictedType(aCas);
    Type tokenType = getType(aCas, Token.class);
    Feature scoreFeature = getScoreFeature(aCas);
    Feature predictedFeature = getPredictedFeature(aCas);
    Feature isPredictionFeature = getIsPredictionFeature(aCas);

    int predictionCount = 0;
    for (AnnotationFS sentence : select(aCas, sentenceType)) {
        if (predictionCount >= traits.getPredictionLimit()) {
            break;
        }
        predictionCount++;
        
        List<AnnotationFS> tokenAnnotations = selectCovered(tokenType, sentence);
        String[] tokens = tokenAnnotations.stream()
            .map(AnnotationFS::getCoveredText)
            .toArray(String[]::new);

        double[] outcome = finder.categorize(tokens);
        String label = finder.getBestCategory(outcome);
        
        AnnotationFS annotation = aCas.createAnnotation(predictedType, sentence.getBegin(),
                sentence.getEnd());
        annotation.setStringValue(predictedFeature, label);
        annotation.setDoubleValue(scoreFeature, NumberUtils.max(outcome));
        annotation.setBooleanValue(isPredictionFeature, true);
        aCas.addFsToIndexes(annotation);
    }
}
Example #3
Source File: OpenNlpDoccatRecommender.java    From inception with Apache License 2.0 5 votes vote down vote up 
private DoccatModel train(List<DocumentSample> aSamples, TrainingParameters aParameters)
    throws RecommendationException
{
    try (DocumentSampleStream stream = new DocumentSampleStream(aSamples)) {
        DoccatFactory factory = new DoccatFactory();
        return DocumentCategorizerME.train("unknown", stream, aParameters, factory);
    }
    catch (IOException e) {
        throw new RecommendationException(
                "Exception during training the OpenNLP Document Categorizer model.", e);
    }
}
Example #4
Source File: OpenNLPIntentMatcher.java    From Mutters with Apache License 2.0 5 votes vote down vote up 
@Override
protected SortedMap<Double, SortedSet<String>> generateSortedScoreMap(String[] utteranceTokens)
{
  DocumentCategorizerME intentCategorizer = new DocumentCategorizerME(model);
  SortedMap<Double, Set<String>> scores = intentCategorizer.sortedScoreMap(utteranceTokens);

  // convert to sorted set of intents
  SortedMap<Double, SortedSet<String>> sortedScores = new TreeMap<>();
  scores.forEach((score, intents) -> sortedScores.put(score, new TreeSet<>(intents)));

  return sortedScores;
}
Example #5
Source File: TestCategorization.java    From Mutters with Apache License 2.0 5 votes vote down vote up 
@Test
public void testCategorization() throws Exception
{
  URL modelUrl = Thread.currentThread().getContextClassLoader().getResource("models/en-cat-taxi-intents.bin");
  assertThat(modelUrl, is(notNullValue()));

  DoccatModel model = new DoccatModel(modelUrl);
  assertThat(model, is(notNullValue()));

  DocumentCategorizerME myCategorizer = new DocumentCategorizerME(model);
  // model was built with OpenNLP whitespace tokenizer
  OpenNLPTokenizer tokenizer = new OpenNLPTokenizer(WhitespaceTokenizer.INSTANCE);

  String category = myCategorizer.getBestCategory(myCategorizer.categorize(tokenizer.tokenize("Order me a taxi")));
  assertThat(category, is(notNullValue()));
  assertThat(category, is("OrderTaxi"));

  category = myCategorizer.getBestCategory(myCategorizer.categorize(tokenizer.tokenize("Send me a taxi")));
  assertThat(category, is(notNullValue()));
  assertThat(category, is("OrderTaxi"));

  category = myCategorizer
      .getBestCategory(myCategorizer.categorize(tokenizer.tokenize("Send a taxi to 12 Pleasent Street")));
  assertThat(category, is(notNullValue()));
  assertThat(category, is("OrderTaxi"));

  category = myCategorizer.getBestCategory(myCategorizer.categorize(tokenizer.tokenize("Cancel my cab")));
  assertThat(category, is(notNullValue()));
  assertThat(category, is("CancelTaxi"));

  category = myCategorizer.getBestCategory(myCategorizer.categorize(tokenizer.tokenize("Where is my taxi ?")));
  assertThat(category, is(notNullValue()));
  assertThat(category, is("WhereTaxi"));

  category = myCategorizer
      .getBestCategory(myCategorizer.categorize(tokenizer.tokenize("The address is 136 River Road")));
  assertThat(category, is(notNullValue()));
  assertThat(category, is("GaveAddress"));
}