public Event next() { isVirgin = false; return new Event(sample.getLanguage().getLang(), mContextGenerator.getContext(sample.getContext().toString())); }
@Override public Language[] predictLanguages(CharSequence content) { double[] eval = model.getMaxentModel().eval(mContextGenerator.getContext(content.toString())); Language[] arr = new Language[eval.length]; for (int i = 0; i < eval.length; i++) { arr[i] = new Language(model.getMaxentModel().getOutcome(i), eval[i]); } Arrays.sort(arr, (o1, o2) -> Double.compare(o2.getConfidence(), o1.getConfidence())); return arr; }
@Test public void extractContext() throws Exception { String doc = "abcde fghijk"; LanguageDetectorContextGenerator cg = new DefaultLanguageDetectorContextGenerator(1, 3); Collection<String> features = Arrays.asList(cg.getContext(doc)); Assert.assertEquals(33, features.size()); Assert.assertTrue(features.contains("ab")); Assert.assertTrue(features.contains("abc")); Assert.assertTrue(features.contains("e f")); Assert.assertTrue(features.contains(" fg")); } }
@Test public void testDummyFactoryContextGenerator() throws Exception { LanguageDetectorContextGenerator cg = model.getFactory().getContextGenerator(); String[] context = cg.getContext( "a dummy text phrase to test if the context generator works!!!!!!!!!!!!"); Set<String> set = new HashSet(Arrays.asList(context)); Assert.assertTrue(set.contains("!!!!!")); // default normalizer would remove the repeated ! Assert.assertTrue(set.contains("a dum")); Assert.assertTrue(set.contains("tg=[THE,CONTEXT,GENERATOR]")); }
public Event next() { isVirgin = false; return new Event(sample.getLanguage().getLang(), mContextGenerator.getContext(sample.getContext().toString())); }
public Event next() { isVirgin = false; return new Event(sample.getLanguage().getLang(), mContextGenerator.getContext(sample.getContext().toString())); }
@Override public Language[] predictLanguages(CharSequence content) { double[] eval = model.getMaxentModel().eval(mContextGenerator.getContext(content.toString())); Language[] arr = new Language[eval.length]; for (int i = 0; i < eval.length; i++) { arr[i] = new Language(model.getMaxentModel().getOutcome(i), eval[i]); } Arrays.sort(arr, (o1, o2) -> Double.compare(o2.getConfidence(), o1.getConfidence())); return arr; }
@Override public Language[] predictLanguages(CharSequence content) { double[] eval = model.getMaxentModel().eval(mContextGenerator.getContext(content.toString())); Language[] arr = new Language[eval.length]; for (int i = 0; i < eval.length; i++) { arr[i] = new Language(model.getMaxentModel().getOutcome(i), eval[i]); } Arrays.sort(arr, (o1, o2) -> Double.compare(o2.getConfidence(), o1.getConfidence())); return arr; }