Package org.apache.uima.collection

Examples of org.apache.uima.collection.CollectionReader

72
73
74
75
76
77
78
79
80
81
82
   
    Options options = new Options();
    options.parseOptions(args);

    List<File> trainFiles = Arrays.asList(options.inputDirectory.listFiles());
    CollectionReader collectionReader = getCollectionReader(trainFiles);
   
    AnalysisEngine relationExtractorPrinter = AnalysisEngineFactory.createPrimitive(
        RelationExtractorPrinter.class);
       
    SimplePipeline.runPipeline(collectionReader, relationExtractorPrinter);
View Full Code Here
229
230
231
232
233
234
235
236
237
238
239
    for(int i = 0; i < files.length; i++){
      paths[i] = files[i].getAbsolutePath();
    }
//    TypeSystemDescription typeSystem = TypeSystemDescriptionFactory.createTypeSystemDescriptionFromPath("../common-type-system/desc/common_type_system.xml");
    try {
      CollectionReader xmiReader = CollectionReaderFactory.createCollectionReader(XMIReader.class, XMIReader.PARAM_FILES, paths);
      AnalysisEngine treeConsumer = AnalysisEngineFactory.createPrimitive(TreeFeatureConsumer.class,
                          TreeFeatureConsumer.PARAM_OUTFILE, args[1],
                          TreeFeatureConsumer.PARAM_CLASSIFY_BOTH_DIRECTIONS, true);
      SimplePipeline.runPipeline(xmiReader, treeConsumer);
    } catch (ResourceInitializationException e) {
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
   
    Options options = new Options();
    options.parseOptions(args);

    List<File> trainFiles = Arrays.asList(options.inputDirectory.listFiles());
    CollectionReader collectionReader = getCollectionReader(trainFiles);
   
    AnalysisEngine goldAnnotationStatsCalculator = AnalysisEngineFactory.createPrimitive(
        GoldAnnotationStatsCalculator.class);
       
    SimplePipeline.runPipeline(collectionReader, goldAnnotationStatsCalculator);
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
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
87
88
89
90
91
92
public class OpenNLPPOSCollectionReaderTests {

  @Test
  public void testReader() throws ResourceInitializationException, IOException, CollectionException {
    CollectionReader collectionReader = TestUtil.getCR(new File("desc/test/OpenNLPPOSCollectionReader.xml"));
    AnalysisEngine analysisEngine = TestUtil.getAE(new File("desc/test/NullAnnotator.xml"));
    JCas jCas = analysisEngine.newJCas();
    collectionReader.getNext(jCas.getCas());
   
    BaseToken baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 0);
    assertEquals(0, baseToken.getBegin());
    assertEquals(1, baseToken.getEnd());
    assertEquals("A", baseToken.getCoveredText());
    assertEquals("A", baseToken.getPartOfSpeech());

    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 1);
    assertEquals("farmer", baseToken.getCoveredText());
    assertEquals("B", baseToken.getPartOfSpeech());
   
    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 2);
    assertEquals("went", baseToken.getCoveredText());
    assertEquals("CC", baseToken.getPartOfSpeech());
   
    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 3);
    assertEquals("trotting", baseToken.getCoveredText());
    assertEquals("DDD", baseToken.getPartOfSpeech());
   
    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 4);
    assertEquals("upon_A", baseToken.getCoveredText());
    assertEquals("E", baseToken.getPartOfSpeech());

    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 5);
    assertEquals("his", baseToken.getCoveredText());
    assertEquals("EE", baseToken.getPartOfSpeech());

    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 6);
    assertEquals(".", baseToken.getCoveredText());
    assertEquals(".", baseToken.getPartOfSpeech());

    CollectionException ce = null;
    jCas = analysisEngine.newJCas();
    try {
      collectionReader.getNext(jCas.getCas());
    } catch(CollectionException e) {
      ce = e;
    }
    assertNotNull(ce);
   
    jCas = analysisEngine.newJCas();
    collectionReader.getNext(jCas.getCas());

    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 0);
    assertEquals("A_", baseToken.getCoveredText());
    assertEquals("A", baseToken.getPartOfSpeech());
View Full Code Here
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
    assertEquals("_", baseToken.getPartOfSpeech());
  }
 
  @Test
  public void testLoadWordsOnly() throws ResourceInitializationException, IOException, CollectionException {
    CollectionReader collectionReader = TestUtil.getCR(new File("desc/test/OpenNLPPOSCollectionReader2.xml"));
    AnalysisEngine analysisEngine = TestUtil.getAE(new File("desc/test/NullAnnotator.xml"));
    JCas jCas = analysisEngine.newJCas();
    collectionReader.getNext(jCas.getCas());
   
    BaseToken baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 0);
    assertEquals(0, baseToken.getBegin());
    assertEquals(1, baseToken.getEnd());
    assertEquals("A", baseToken.getCoveredText());
    assertNull(baseToken.getPartOfSpeech());

    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 1);
    assertEquals("farmer", baseToken.getCoveredText());
    assertNull(baseToken.getPartOfSpeech());
   
    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 2);
    assertEquals("went", baseToken.getCoveredText());
    assertNull(baseToken.getPartOfSpeech());
   
    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 3);
    assertEquals("trotting", baseToken.getCoveredText());
    assertNull(baseToken.getPartOfSpeech());
   
    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 4);
    assertEquals("upon_A", baseToken.getCoveredText());
    assertNull(baseToken.getPartOfSpeech());

    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 5);
    assertEquals("his", baseToken.getCoveredText());
    assertNull(baseToken.getPartOfSpeech());

    baseToken = TestUtil.getFeatureStructureAtIndex(jCas, BaseToken.class, 6);
    assertEquals(".", baseToken.getCoveredText());
    assertNull(baseToken.getPartOfSpeech());

    CollectionException ce = null;
    jCas = analysisEngine.newJCas();
    try {
      collectionReader.getNext(jCas.getCas());
    } catch(CollectionException e) {
      ce = e;
    }
    assertNotNull(ce);
   
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
    throws Exception
  {
    // Run the pipeline with different similarity measures
    for (int i = 1; i <= 3; i++)
    { 
      CollectionReader reader = createReader(PlainTextCombinationReader.class,
          PlainTextCombinationReader.PARAM_INPUT_DIR, "classpath:/datasets/test/plaintext",
          PlainTextCombinationReader.PARAM_LANGUAGE, "en",
          PlainTextCombinationReader.PARAM_COMBINATION_STRATEGY, CombinationStrategy.SAME_ROW_ONLY.toString());
 
      AnalysisEngineDescription seg = createEngineDescription(
View Full Code Here
28
29
30
31
32
33
34
35
36
37
38
public class GoldstandardCreator
{
  public static void outputGoldstandard(Dataset dataset)
    throws Exception
  {         
    CollectionReader reader = createReader(
                RTECorpusReader.class,
                RTECorpusReader.PARAM_COMBINATION_STRATEGY, CombinationStrategy.SAME_ROW_ONLY,
                RTECorpusReader.PARAM_INPUT_FILE, RteUtil.getInputFilePathForDataset(DATASET_DIR, dataset));
       
        AnalysisEngineDescription tagger = createEngineDescription(
View Full Code Here
224
225
226
227
228
229
230
231
232
233
234
    {     
      if (new File(OUTPUT_FEATURE_DIR + "/" + config.getTargetPath() + "/" + config.getMeasureName() + ".txt").exists())
      {
        System.out.println("Skipping: " + config.getMeasureName());
      } else {     
        CollectionReader reader = createReader(SemEvalCorpusReader.class,
            SemEvalCorpusReader.PARAM_INPUT_FILE, "classpath:/datasets/semeval/train/STS.input.ALLcombined.txt",
            SemEvalCorpusReader.PARAM_COMBINATION_STRATEGY, CombinationStrategy.SAME_ROW_ONLY.toString());
   
        AnalysisEngineDescription seg = createEngineDescription(
            BreakIteratorSegmenter.class);
View Full Code Here
256
257
258
259
260
261
262
263
264
265
266
      {
        System.out.println(" - skipped, feature already generated");
      }
      else
      {     
        CollectionReader reader = createReader(SemEvalCorpusReader.class,
            SemEvalCorpusReader.PARAM_INPUT_FILE, DATASET_DIR + "/" + mode.toString().toLowerCase() + "/STS.input." + dataset.toString() + ".txt",
            SemEvalCorpusReader.PARAM_COMBINATION_STRATEGY, CombinationStrategy.SAME_ROW_ONLY.toString(), SemEvalCorpusReader.PARAM_LANGUAGE, "en");
   
        // Tokenization
        AnalysisEngineDescription seg = createEngineDescription(
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
  public static void runLinearRegression(Dataset train, Dataset... test)
    throws UIMAException, IOException
  {
    for (Dataset dataset : test)
    {
      CollectionReader reader = createReader(SemEvalCorpusReader.class,
          SemEvalCorpusReader.PARAM_INPUT_FILE, DATASET_DIR + "/test/STS.input." + dataset.toString() + ".txt",
          SemEvalCorpusReader.PARAM_LANGUAGE, "en",
          SemEvalCorpusReader.PARAM_COMBINATION_STRATEGY, CombinationStrategy.SAME_ROW_ONLY.toString());
     
      AnalysisEngineDescription seg = createEngineDescription(BreakIteratorSegmenter.class);
View Full Code Here
TOP

Related Classes of org.apache.uima.collection.CollectionReader

  • de.tudarmstadt.ukp.similarity.experiments.coling2012.FeatureGeneration
  • de.tudarmstadt.ukp.similarity.experiments.coling2012.util.CharacterNGramIdfValuesGenerator
  • de.tudarmstadt.ukp.similarity.experiments.coling2012.util.ColingUtils
  • de.tudarmstadt.ukp.similarity.experiments.coling2012.util.WordIdfValuesGenerator
  • dkpro.similarity.algorithms.sspace.util.LsaIndexCreatorTest
  • dkpro.similarity.example.ml.LinearRegressionExample
  • dkpro.similarity.example.ml.mm09.FeatureGenerationTest
  • dkpro.similarity.example.ml.mm09.FeatureGenerationTrain
  • dkpro.similarity.example.ml.mm09.OutputGoldstandard
  • dkpro.similarity.example.WithDKPro
    • 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.