Package org.uimafit.factory

Examples of org.uimafit.factory.AggregateBuilder

59
60
61
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
        + "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 Document Time Relative Annotator
    builder.add(DocTimeRelAnnotator
        .createAnnotatorDescription("/org/apache/ctakes/temporal/ae/doctimerel/model.jar"));

    SimplePipeline.runPipeline(jcas, builder.createAggregateDescription());

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

    ArrayList<String> temp = new ArrayList<>();
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
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
  }
 
  public void execute() throws Exception
  {
    AggregateBuilder builder = new AggregateBuilder();

//    AnalysisEngineDescription documentIdPrinter =
//        AnalysisEngineFactory.createPrimitiveDescription(DocumentIdPrinterAnalysisEngine.class);
//    builder.add(documentIdPrinter);
 
    URI generalSectionRegexFileUri =
      this.getClass().getClassLoader().getResource("org/mitre/medfacts/uima/section_regex.xml").toURI();
//    ExternalResourceDescription generalSectionRegexDescription = ExternalResourceFactory.createExternalResourceDescription(
//        SectionRegexConfigurationResource.class, new File(generalSectionRegexFileUri));
    AnalysisEngineDescription zonerAnnotator =
        AnalysisEngineFactory.createPrimitiveDescription(ZoneAnnotator.class,
            ZoneAnnotator.PARAM_SECTION_REGEX_FILE_URI,
            generalSectionRegexFileUri
            );
    builder.add(zonerAnnotator);

    URI mayoSectionRegexFileUri =
        this.getClass().getClassLoader().getResource("org/mitre/medfacts/uima/mayo_sections.xml").toURI();
//      ExternalResourceDescription mayoSectionRegexDescription = ExternalResourceFactory.createExternalResourceDescription(
//          SectionRegexConfigurationResource.class, new File(mayoSectionRegexFileUri));
    AnalysisEngineDescription mayoZonerAnnotator =
        AnalysisEngineFactory.createPrimitiveDescription(ZoneAnnotator.class,
            ZoneAnnotator.PARAM_SECTION_REGEX_FILE_URI,
            mayoSectionRegexFileUri
            );
    builder.add(mayoZonerAnnotator);
   
    FileOutputStream outputStream = new FileOutputStream("desc/aggregateAssertionZoner.xml");
   
    AnalysisEngineDescription description = builder.createAggregateDescription();
   
    description.toXML(outputStream);
  }
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
   */
  @Test
  public void testSentenceDetection() throws UIMAException, IOException {
//      JCas jCas = JCasFactory.createJCasFromPath("src/main/resources/org/apache/ctakes/ytex/types/TypeSystem.xml");
      String text = "Dr. Doolitle asked patient\nto take a deep breath\nand exhale slowly.  Patient coughed.";
      AggregateBuilder builder = new AggregateBuilder();
      File directoryCtakes = new File("../ctakes-core/desc/analysis_engine");
      File fileCtakes = new File(directoryCtakes, "TokenizerAnnotator.xml");
      XMLParser parser = UIMAFramework.getXMLParser();
      XMLInputSource source = new XMLInputSource(fileCtakes);
      builder.add(parser.parseAnalysisEngineDescription(source));
      File directory = new File("desc/analysis_engine");
      File file = new File(directory, "SentenceDetectorAnnotator.xml");
      source = new XMLInputSource(file);
      builder.add(parser.parseAnalysisEngineDescription(source));
      AnalysisEngine engine = builder.createAggregate();
      JCas jCas = engine.newJCas();
      jCas.setDocumentText(text);
      Segment s = new Segment(jCas);
      s.setBegin(0);
      s.setEnd(text.length());
View Full Code Here
309
310
311
312
313
314
315
316
317
318
319
320
321
        ? this.getXMIReadingPreprocessorAggregateBuilder()
        : this.getXMIWritingPreprocessorAggregateBuilder();
  }

  protected AggregateBuilder getXMIReadingPreprocessorAggregateBuilder() throws UIMAException {
    AggregateBuilder aggregateBuilder = new AggregateBuilder();
    aggregateBuilder.add(UriToDocumentTextAnnotator.getDescription());
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
        XMIReader.class,
        XMIReader.PARAM_XMI_DIRECTORY,
        this.xmiDirectory));
    return aggregateBuilder;
  }
View Full Code Here
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
    return aggregateBuilder;
  }

  protected AggregateBuilder getXMIWritingPreprocessorAggregateBuilder()
      throws Exception {
    AggregateBuilder aggregateBuilder = new AggregateBuilder();
    aggregateBuilder.add(UriToDocumentTextAnnotator.getDescription());

    // read manual annotations into gold view
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
        ViewCreatorAnnotator.class,
        ViewCreatorAnnotator.PARAM_VIEW_NAME,
        GOLD_VIEW_NAME));
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
        ViewTextCopierAnnotator.class,
        ViewTextCopierAnnotator.PARAM_SOURCE_VIEW_NAME,
        CAS.NAME_DEFAULT_SOFA,
        ViewTextCopierAnnotator.PARAM_DESTINATION_VIEW_NAME,
        GOLD_VIEW_NAME));
    switch (this.xmlFormat) {
    case Anafora:
      aggregateBuilder.add(
          THYMEAnaforaXMLReader.getDescription(this.xmlDirectory),
          CAS.NAME_DEFAULT_SOFA,
          GOLD_VIEW_NAME);
      break;
    case Knowtator:
      aggregateBuilder.add(
          THYMEKnowtatorXMLReader.getDescription(this.xmlDirectory),
          CAS.NAME_DEFAULT_SOFA,
          GOLD_VIEW_NAME);
      break;
    case I2B2:
      aggregateBuilder.add(
          I2B2TemporalXMLReader.getDescription(this.xmlDirectory),
          CAS.NAME_DEFAULT_SOFA,
          GOLD_VIEW_NAME);
      break;
    }

    // identify segments
    if(this.xmlFormat == XMLFormat.I2B2){
      aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(SimpleSegmentAnnotator.class));
    }else{
      aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(SegmentsFromBracketedSectionTagsAnnotator.class));
    }
    // identify sentences
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
        SentenceDetector.class,
        SentenceDetector.SD_MODEL_FILE_PARAM,
        "org/apache/ctakes/core/sentdetect/sd-med-model.zip"));
    // identify tokens
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(TokenizerAnnotatorPTB.class));
    // merge some tokens
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(ContextDependentTokenizerAnnotator.class));

    // identify part-of-speech tags
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
        POSTagger.class,
        TypeSystemDescriptionFactory.createTypeSystemDescription(),
        TypePrioritiesFactory.createTypePriorities(Segment.class, Sentence.class, BaseToken.class),
        POSTagger.POS_MODEL_FILE_PARAM,
        "org/apache/ctakes/postagger/models/mayo-pos.zip"));

    // identify chunks
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
        Chunker.class,
        Chunker.CHUNKER_MODEL_FILE_PARAM,
        FileLocator.locateFile("org/apache/ctakes/chunker/models/chunker-model.zip"),
        Chunker.CHUNKER_CREATOR_CLASS_PARAM,
        DefaultChunkCreator.class));

    // identify UMLS named entities

    // adjust NP in NP NP to span both
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
        ChunkAdjuster.class,
        ChunkAdjuster.PARAM_CHUNK_PATTERN,
        new String[] { "NP", "NP" },
        ChunkAdjuster.PARAM_EXTEND_TO_INCLUDE_TOKEN,
        1));
    // adjust NP in NP PP NP to span all three
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
        ChunkAdjuster.class,
        ChunkAdjuster.PARAM_CHUNK_PATTERN,
        new String[] { "NP", "PP", "NP" },
        ChunkAdjuster.PARAM_EXTEND_TO_INCLUDE_TOKEN,
        2));
    // add lookup windows for each NP
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(CopyNPChunksToLookupWindowAnnotations.class));
    // maximize lookup windows
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
        OverlapAnnotator.class,
        "A_ObjectClass",
        LookupWindowAnnotation.class,
        "B_ObjectClass",
        LookupWindowAnnotation.class,
        "OverlapType",
        "A_ENV_B",
        "ActionType",
        "DELETE",
        "DeleteAction",
        new String[] { "selector=B" }));
    // add UMLS on top of lookup windows
    aggregateBuilder.add(
        UmlsDictionaryLookupAnnotator.createAnnotatorDescription()
        );

    // add lvg annotator
    String[] XeroxTreebankMap = {
        "adj|JJ",
        "adv|RB",
        "aux|AUX",
        "compl|CS",
        "conj|CC",
        "det|DET",
        "modal|MD",
        "noun|NN",
        "prep|IN",
        "pron|PRP",
        "verb|VB" };
    String[] ExclusionSet = {
        "and",
        "And",
        "by",
        "By",
        "for",
        "For",
        "in",
        "In",
        "of",
        "Of",
        "on",
        "On",
        "the",
        "The",
        "to",
        "To",
        "with",
        "With" };
    AnalysisEngineDescription lvgAnnotator = AnalysisEngineFactory.createPrimitiveDescription(
        LvgAnnotator.class,
        "UseSegments",
        false,
        "SegmentsToSkip",
        new String[0],
        "UseCmdCache",
        false,
        "CmdCacheFileLocation",
        "/org/apache/ctakes/lvg/2005_norm.voc",
        "CmdCacheFrequencyCutoff",
        20,
        "ExclusionSet",
        ExclusionSet,
        "XeroxTreebankMap",
        XeroxTreebankMap,
        "LemmaCacheFileLocation",
        "/org/apache/ctakes/lvg/2005_lemma.voc",
        "UseLemmaCache",
        false,
        "LemmaCacheFrequencyCutoff",
        20,
        "PostLemmas",
        false,
        "LvgCmdApi",
        ExternalResourceFactory.createExternalResourceDescription(
            LvgCmdApiResourceImpl.class,
            new File(LvgCmdApiResourceImpl.class.getResource(
                "/org/apache/ctakes/lvg/data/config/lvg.properties").toURI())));
    aggregateBuilder.add(lvgAnnotator);

    // add dependency parser
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(ClearNLPDependencyParserAE.class));

    // add semantic role labeler
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(ClearNLPSemanticRoleLabelerAE.class));

    // add gold standard parses to gold view, and adjust gold view to correct a few annotation mis-steps
    if(this.treebankDirectory != null){
      aggregateBuilder.add(THYMETreebankReader.getDescription(this.treebankDirectory));
      aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(TimexAnnotationCorrector.class));
    }else{
      // add ctakes constituency parses to system view
      aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(ConstituencyParser.class,
          ConstituencyParser.PARAM_MODEL_FILENAME,
          "org/apache/ctakes/constituency/parser/models/sharpacq-3.1.bin"));
//      aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(BerkeleyParserWrapper.class,
//          BerkeleyParserWrapper.PARAM_MODEL_FILENAME,
//         
//        "org/apache/ctakes/constituency/parser/models/thyme.gcg.4sm.bin"));
//          "org/apache/ctakes/constituency/parser/models/thyme.4sm.bin"));
    }
    // write out the CAS after all the above annotations
    aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
        XMIWriter.class,
        XMIWriter.PARAM_XMI_DIRECTORY,
        this.xmiDirectory));

    return aggregateBuilder;
View Full Code Here
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
    return fileList;
  }

  public void execute() throws UIMAException, IOException, URISyntaxException
  {
    AggregateBuilder builder = new AggregateBuilder();
   
    TypeSystemDescription typeSystemDescription = TypeSystemDescriptionFactory.createTypeSystemDescriptionFromPath();
   
//    CollectionReader reader =
//        CollectionReaderFactory.createCollectionReader(
//          XMIReader.class,
//          typeSystemDescription,
//          XMIReader.PARAM_FILES,
//          inputFiles);

    CollectionReader reader =
    CollectionReaderFactory.createCollectionReader(
      TextReader.class,
      typeSystemDescription,
      TextReader.PARAM_FILES,
      inputFiles);

   
      AnalysisEngineDescription documentIdPrinter =
          AnalysisEngineFactory.createPrimitiveDescription(DocumentIdPrinterAnalysisEngine.class);
      builder.add(documentIdPrinter);
   
      String generalSectionRegexFileUri =
        "org/mitre/medfacts/uima/section_regex.xml";
      //URI generalSectionRegexFileUri =
      //  this.getClass().getClassLoader().getResource("org/mitre/medfacts/zoner/section_regex.xml").toURI();
//      ExternalResourceDescription generalSectionRegexDescription = ExternalResourceFactory.createExternalResourceDescription(
//          SectionRegexConfigurationResource.class, new File(generalSectionRegexFileUri));
      AnalysisEngineDescription zonerAnnotator =
          AnalysisEngineFactory.createPrimitiveDescription(ZoneAnnotator.class,
              ZoneAnnotator.PARAM_SECTION_REGEX_FILE_URI,
              generalSectionRegexFileUri
              );
      builder.add(zonerAnnotator);

      String mayoSectionRegexFileUri =
          "org/mitre/medfacts/uima/mayo_sections.xml";
//      URI mayoSectionRegexFileUri =
//          this.getClass().getClassLoader().getResource("org/mitre/medfacts/zoner/mayo_sections.xml").toURI();
//        ExternalResourceDescription mayoSectionRegexDescription = ExternalResourceFactory.createExternalResourceDescription(
//            SectionRegexConfigurationResource.class, new File(mayoSectionRegexFileUri));
      AnalysisEngineDescription mayoZonerAnnotator =
          AnalysisEngineFactory.createPrimitiveDescription(ZoneAnnotator.class,
              ZoneAnnotator.PARAM_SECTION_REGEX_FILE_URI,
              mayoSectionRegexFileUri
              );
      builder.add(mayoZonerAnnotator);

      AnalysisEngineDescription xWriter = AnalysisEngineFactory.createPrimitiveDescription(
          XWriter.class,
          typeSystemDescription,
          XWriter.PARAM_OUTPUT_DIRECTORY_NAME,
          outputDirectory.toString(),
          XWriter.PARAM_FILE_NAMER_CLASS_NAME,
          CtakesFileNamer.class.getName()
          );
     
      builder.add(xWriter);

    logger.info("BEFORE RUNNING PIPELINE...");
    SimplePipeline.runPipeline(reader,  builder.createAggregateDescription());
    logger.info("AFTER RUNNING PIPELINE...COMPLETED");
  }
View Full Code Here
54
55
56
57
58
59
60
61
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
    createZonerMayoDescriptor();
  }
 
  public void createZonerAggregateDescriptor() throws Exception
  {
    AggregateBuilder builder = new AggregateBuilder();

////
    String generalSectionRegexFileUri =
      "org/mitre/medfacts/zoner/section_regex.xml";
    AnalysisEngineDescription zonerAnnotator =
        AnalysisEngineFactory.createPrimitiveDescription(ZoneAnnotator.class,
            ZoneAnnotator.PARAM_SECTION_REGEX_FILE_URI,
            generalSectionRegexFileUri
            );
    builder.add(zonerAnnotator);

    String mayoSectionRegexFileUri =
      "org/mitre/medfacts/uima/mayo_sections.xml";
    AnalysisEngineDescription mayoZonerAnnotator =
        AnalysisEngineFactory.createPrimitiveDescription(ZoneAnnotator.class,
            ZoneAnnotator.PARAM_SECTION_REGEX_FILE_URI,
            mayoSectionRegexFileUri
            );
    builder.add(mayoZonerAnnotator);
   
////
   
    File outputFile = new File("desc/analysis_engine/assertion_zoner__both_regular_and_mayo.xml");
    FileOutputStream outputStream = new FileOutputStream(outputFile);
    String outputFilePath = outputFile.getAbsolutePath();
    System.out.println("output descriptor file: " + outputFilePath);
   
    AnalysisEngineDescription description = builder.createAggregateDescription();
   
    description.toXML(outputStream);
  }
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
    description.toXML(outputStream);
  }
 
  public void createZonerNormalDescriptor() throws Exception
  {
    AggregateBuilder builder = new AggregateBuilder();

    String generalSectionRegexFileUri =
      "org/mitre/medfacts/zoner/section_regex.xml";
    AnalysisEngineDescription zonerAnnotator =
        AnalysisEngineFactory.createPrimitiveDescription(ZoneAnnotator.class,
            ZoneAnnotator.PARAM_SECTION_REGEX_FILE_URI,
            generalSectionRegexFileUri
            );
    builder.add(zonerAnnotator);

    File outputFile = new File("desc/analysis_engine/assertion_zoner__normal.xml");
    FileOutputStream outputStream = new FileOutputStream(outputFile);
    String outputFilePath = outputFile.getAbsolutePath();
    System.out.println("output descriptor file: " + outputFilePath);
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
    zonerAnnotator.toXML(outputStream);
  }
 
  public void createZonerMayoDescriptor() throws Exception
  {
    AggregateBuilder builder = new AggregateBuilder();

    String generalSectionRegexFileUri =
      "org/mitre/medfacts/uima/mayo_sections.xml";
    AnalysisEngineDescription zonerAnnotator =
        AnalysisEngineFactory.createPrimitiveDescription(ZoneAnnotator.class,
            ZoneAnnotator.PARAM_SECTION_REGEX_FILE_URI,
            generalSectionRegexFileUri
            );
    builder.add(zonerAnnotator);

    File outputFile = new File("desc/analysis_engine/assertion_zoner__mayo.xml");
    FileOutputStream outputStream = new FileOutputStream(outputFile);
    String outputFilePath = outputFile.getAbsolutePath();
    System.out.println("output descriptor file: " + outputFilePath);
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
 
  public void execute() throws UIMAException, IOException
  {
    logger.info("starting");

    AggregateBuilder builder = new AggregateBuilder();
   
    TypeSystemDescription typeSystemDescription = TypeSystemDescriptionFactory.createTypeSystemDescription();
    String filename = "/work/medfacts/sharp/data/2013-01-11_cue_phrase_feature_test/ON03FP00037D00207__merged.txt.xmi";
   
    JCas jcas = JCasFactory.createJCas(filename, typeSystemDescription);
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.