Package org.uimafit.factory

Examples of org.uimafit.factory.AggregateBuilder

171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
  @Override
  protected Map<String, AnnotationStatistics<String>> test(
      CollectionReader collectionReader,
      File directory) throws Exception {
    AggregateBuilder aggregateBuilder = this.getPreprocessorAggregateBuilder();
    aggregateBuilder.add(CopyFromGold.getDescription(EventMention.class));
    aggregateBuilder.add(CopyFromGold.getDescription(TimeMention.class));
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(ClearEventProperties.class));
    aggregateBuilder.add(DocTimeRelAnnotator.createAnnotatorDescription(new File(directory, DOC_TIME_REL)));
    aggregateBuilder.add(ContextualModalityAnnotator.createAnnotatorDescription(new File(directory, CONTEXTUAL_MODALITY)));

    Function<EventMention, ?> eventMentionToSpan = AnnotationStatistics.annotationToSpan();
    Map<String, Function<EventMention, String>> propertyGetters;
    propertyGetters = new HashMap<String, Function<EventMention, String>>();
    for (String name : PROPERTY_NAMES) {
      propertyGetters.put(name, getPropertyGetter(name));
    }

    Map<String, AnnotationStatistics<String>> statsMap = new HashMap<String, AnnotationStatistics<String>>();

    for(String propertyName : PROPERTY_NAMES){
      statsMap.put(propertyName, new AnnotationStatistics<String>());
    }

    for (JCas jCas : new JCasIterable(collectionReader, aggregateBuilder.createAggregate())) {
      JCas goldView = jCas.getView(GOLD_VIEW_NAME);
      JCas systemView = jCas.getView(CAS.NAME_DEFAULT_SOFA);
      String text = goldView.getDocumentText();
      for (Segment segment : JCasUtil.select(jCas, Segment.class)) {
        if (!THYMEData.SEGMENTS_TO_SKIP.contains(segment.getId())) {
View Full Code Here
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
      files.addAll(getTestTextFiles(options.getBatchesDirectory()));
      CollectionReader reader = UriCollectionReader.getCollectionReaderFromFiles(files);

      // load the text from the URI, run the preprocessor, then run the
      // Knowtator XML reader
      AggregateBuilder builder = new AggregateBuilder();
      builder.add(UriToDocumentTextAnnotator.getDescription());
      File preprocessDescFile = new File("desc/analysis_engine/RelationExtractorPreprocessor.xml");
      XMLParser parser = UIMAFramework.getXMLParser();
      XMLInputSource source = new XMLInputSource(preprocessDescFile);
      builder.add(parser.parseAnalysisEngineDescription(source));
      builder.add(AnalysisEngineFactory.createPrimitiveDescription(
          ViewCreatorAnnotator.class,
          ViewCreatorAnnotator.PARAM_VIEW_NAME,
          GOLD_VIEW_NAME));
      builder.add(AnalysisEngineFactory.createPrimitiveDescription(CopyDocumentTextToGoldView.class));
      builder.add(
          AnalysisEngineFactory.createPrimitiveDescription(DocumentIDAnnotator.class),
          CAS.NAME_DEFAULT_SOFA,
          GOLD_VIEW_NAME);
      builder.add(
          AnalysisEngineFactory.createPrimitiveDescription(SHARPKnowtatorXMLReader.class),
          CAS.NAME_DEFAULT_SOFA,
          GOLD_VIEW_NAME);

      // write out an XMI for each file
      for (JCas jCas : new JCasIterable(reader, builder.createAggregate())) {
        JCas goldView = jCas.getView(GOLD_VIEW_NAME);
        String documentID = DocumentIDAnnotationUtil.getDocumentID(goldView);
        if (documentID == null) {
          throw new IllegalArgumentException("No documentID for CAS:\n" + jCas);
        }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
        + "The patient was well till 6 months ago, when he started having a little blood with stool.";
    JCas jcas = JCasFactory.createJCas();
    jcas.setDocumentText(note);

    // Get the default pipeline with umls dictionary lookup
    AggregateBuilder builder = new AggregateBuilder();
    builder.add(ClinicalPipelineFactory.getTokenProcessingPipeline());
    builder.add(AnalysisEngineFactory
        .createPrimitiveDescription(CopyNPChunksToLookupWindowAnnotations.class));
    builder.add(AnalysisEngineFactory
        .createPrimitiveDescription(RemoveEnclosedLookupWindows.class));
    // Commented out the Dictionary lookup for the test
    // Uncomment and set -Dctakes.umlsuser and -Dctakes.umlspw env params if
    // needed
    //builder.add(UmlsDictionaryLookupAnnotator.createAnnotatorDescription());
    builder.add(ClearNLPDependencyParserAE.createAnnotatorDescription());

    // Add BackwardsTimeAnnotator
    builder.add(BackwardsTimeAnnotator
        .createAnnotatorDescription("/org/apache/ctakes/temporal/ae/timeannotator/model.jar"));
    // Add EventAnnotator
    builder.add(EventAnnotator
        .createAnnotatorDescription("/org/apache/ctakes/temporal/ae/eventannotator/model.jar"));
    // Add ContextualModalityAnnotator
    builder.add(ContextualModalityAnnotator
        .createAnnotatorDescription("/org/apache/ctakes/temporal/ae/contextualmodality/model.jar"));
   
    // Add DocTimeRelAnnotator
    builder.add(DocTimeRelAnnotator
        .createAnnotatorDescription("/org/apache/ctakes/temporal/ae/doctimerel/model.jar"));

    //builder.createAggregateDescription().toXML(new FileWriter("desc/analysis_engine/TemporalAggregateUMLSPipeline.xml"));
   
    SimplePipeline.runPipeline(jcas, builder.createAggregateDescription());

    Collection<EventMention> mentions = JCasUtil.select(jcas,
        EventMention.class);

    ArrayList<String> temp = new ArrayList<>();
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
65
import org.xml.sax.SAXException;

public class ClinicalPipelineFactory {

  public static AnalysisEngineDescription getDefaultPipeline() throws ResourceInitializationException{
    AggregateBuilder builder = new AggregateBuilder();
    builder.add(getTokenProcessingPipeline());
    builder.add(AnalysisEngineFactory.createPrimitiveDescription(CopyNPChunksToLookupWindowAnnotations.class));
    builder.add(AnalysisEngineFactory.createPrimitiveDescription(RemoveEnclosedLookupWindows.class));
    builder.add(UmlsDictionaryLookupAnnotator.createAnnotatorDescription());
    builder.add(ClearNLPDependencyParserAE.createAnnotatorDescription());
    builder.add(PolarityCleartkAnalysisEngine.createAnnotatorDescription());
    return builder.createAggregateDescription();
  }
View Full Code Here
64
65
66
67
68
69
70
71
    return builder.createAggregateDescription();
  }
 
  // TODO
  public static AnalysisEngineDescription getParsingPipeline(){
    AggregateBuilder builder = new AggregateBuilder();
    throw new UnsupportedOperationException("Not yet implemented!");
  }
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
    AggregateBuilder builder = new AggregateBuilder();
    throw new UnsupportedOperationException("Not yet implemented!");
  }
 
  public static AnalysisEngineDescription getTokenProcessingPipeline() throws ResourceInitializationException {
    AggregateBuilder builder = new AggregateBuilder();
    builder.add(SimpleSegmentAnnotator.createAnnotatorDescription());
    builder.add(SentenceDetector.createAnnotatorDescription());
    builder.add(TokenizerAnnotatorPTB.createAnnotatorDescription());
    builder.add(LvgAnnotator.createAnnotatorDescription());
    builder.add(ContextDependentTokenizerAnnotator.createAnnotatorDescription());
    builder.add(POSTagger.createAnnotatorDescription());
    builder.add(Chunker.createAnnotatorDescription());
    builder.add(getStandardChunkAdjusterAnnotator());
   
    return builder.createAggregateDescription();
  }
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
   
    return builder.createAggregateDescription();
  }
 
  public static AnalysisEngineDescription getStandardChunkAdjusterAnnotator() throws ResourceInitializationException{
    AggregateBuilder builder = new AggregateBuilder();
    // adjust NP in NP NP to span both
    builder.add(ChunkAdjuster.createAnnotatorDescription(new String[] { "NP", "NP" },  1));
    // adjust NP in NP PP NP to span all three
    builder.add(ChunkAdjuster.createAnnotatorDescription(new String[] { "NP", "PP", "NP" }, 2));
    return builder.createAggregateDescription();
  }
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
108
109
  }

  @Override
  protected AnalysisEngineDescription getAnnotatorDescription(File directory)
      throws ResourceInitializationException {
    AggregateBuilder aggregateBuilder = new AggregateBuilder();
    aggregateBuilder.add(SentenceAnnotator.getDescription());
    aggregateBuilder.add(TokenAnnotator.getDescription());
    aggregateBuilder.add(PosTaggerAnnotator.getDescription());
    aggregateBuilder.add(DefaultSnowballStemmer.getDescription("English"));
    aggregateBuilder.add(TimeAnnotator.FACTORY.getAnnotatorDescription());
    return aggregateBuilder.createAggregateDescription();
  }
View Full Code Here
96
97
98
99
100
101
102
103
104
105
106
107
108
109
  }

  @Override
  protected AnalysisEngineDescription getAnnotatorDescription(File directory)
      throws ResourceInitializationException {
    AggregateBuilder aggregateBuilder = new AggregateBuilder();
    aggregateBuilder.add(SentenceAnnotator.getDescription());
    aggregateBuilder.add(TokenAnnotator.getDescription());
    aggregateBuilder.add(PosTaggerAnnotator.getDescription());
    aggregateBuilder.add(DefaultSnowballStemmer.getDescription("English"));
    aggregateBuilder.add(ParserAnnotator.getDescription());
    aggregateBuilder.add(EventAnnotator.FACTORY.getAnnotatorDescription());
    return aggregateBuilder.createAggregateDescription();
  }
View Full Code Here
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
    String note = "Hello World!";
      JCas jcas = JCasFactory.createJCas();
      jcas.setDocumentText(note);
     
    AggregateBuilder builder = new AggregateBuilder();
    // Get a simple pre-defined existing pipeline for Tokenization
   
    // You can consider using ClinicalPipelineFactory.getDefaultPipeline();
    // Which will include the UMLS Lookup, but you'll need to set your
    // -Dctakes.umlsuser and -Dctatkes.umlspw in your environment
    builder.add(ClinicalPipelineFactory.getTokenProcessingPipeline());
   
    //Add the new HelloWorld Example:
    builder.add(ExampleHelloWorldAnnotator.createAnnotatorDescription());
   
    //Run the Aggregate Pipeline
      SimplePipeline.runPipeline(jcas, builder.createAggregateDescription());
     
      //Print out the IdentifiedAnnotation objects
      for(IdentifiedAnnotation entity : JCasUtil.select(jcas, IdentifiedAnnotation.class)){
        System.out.println("Entity: " + entity.getCoveredText() + " === Polarity: " + entity.getPolarity());
      }
     
      //Example to save the Aggregate descriptor to an xml file for external
      //use such as the UIMA CVD/CPE
      if(args.length > 0)
        builder.createAggregateDescription().toXML(new FileWriter(args[0]));
    }
View Full Code Here
TOP

Related Classes of org.uimafit.factory.AggregateBuilder

  • de.tudarmstadt.ukp.similarity.experiments.coling2012.FeatureGeneration
  • de.tudarmstadt.ukp.similarity.experiments.coling2012.util.CharacterNGramIdfValuesGenerator
  • de.tudarmstadt.ukp.similarity.experiments.coling2012.util.WordIdfValuesGenerator
  • org.apache.ctakes.assertion.cr.NegExCorpusReader
  • org.apache.ctakes.assertion.eval.AssertionEvalBasedOnModifier
  • org.apache.ctakes.assertion.eval.AssertionEvaluation
  • org.apache.ctakes.assertion.eval.MergeGoldViewFromOneCasIntoInitialViewOfAnotherCas
  • org.apache.ctakes.assertion.medfacts.cleartk.CreateAssertionDescriptor
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.CueWordTest
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.CueWordTest2
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.