List of usage examples for org.apache.lucene.search.similarities AxiomaticF1LOG AxiomaticF1LOG
public AxiomaticF1LOG()
From source file:com.github.tteofili.looseen.Test20NewsgroupsClassification.java
License:Apache License
@Test public void test20Newsgroups() throws Exception { String indexProperty = System.getProperty("index"); if (indexProperty != null) { try {// ww w . java 2 s. co m index = Boolean.valueOf(indexProperty); } catch (Exception e) { // ignore } } String splitProperty = System.getProperty("split"); if (splitProperty != null) { try { split = Boolean.valueOf(splitProperty); } catch (Exception e) { // ignore } } Path mainIndexPath = Paths.get(INDEX + "/original"); Directory directory = FSDirectory.open(mainIndexPath); Path trainPath = Paths.get(INDEX + "/train"); Path testPath = Paths.get(INDEX + "/test"); Path cvPath = Paths.get(INDEX + "/cv"); FSDirectory cv = null; FSDirectory test = null; FSDirectory train = null; IndexReader testReader = null; if (split) { cv = FSDirectory.open(cvPath); test = FSDirectory.open(testPath); train = FSDirectory.open(trainPath); } if (index) { delete(mainIndexPath); if (split) { delete(trainPath, testPath, cvPath); } } IndexReader reader = null; List<Classifier<BytesRef>> classifiers = new LinkedList<>(); try { Analyzer analyzer = new StandardAnalyzer(); if (index) { System.out.format("Indexing 20 Newsgroups...%n"); long startIndex = System.currentTimeMillis(); IndexWriter indexWriter = new IndexWriter(directory, new IndexWriterConfig(analyzer)); buildIndex(new File(PREFIX + "/20n/20_newsgroups"), indexWriter); long endIndex = System.currentTimeMillis(); System.out.format("Indexed %d pages in %ds %n", indexWriter.maxDoc(), (endIndex - startIndex) / 1000); indexWriter.close(); } if (split && !index) { reader = DirectoryReader.open(train); } else { reader = DirectoryReader.open(directory); } if (index && split) { // split the index System.out.format("Splitting the index...%n"); long startSplit = System.currentTimeMillis(); DatasetSplitter datasetSplitter = new DatasetSplitter(0.1, 0); datasetSplitter.split(reader, train, test, cv, analyzer, false, CATEGORY_FIELD, BODY_FIELD, SUBJECT_FIELD, CATEGORY_FIELD); reader.close(); reader = DirectoryReader.open(train); // using the train index from now on long endSplit = System.currentTimeMillis(); System.out.format("Splitting done in %ds %n", (endSplit - startSplit) / 1000); } final long startTime = System.currentTimeMillis(); classifiers.add(new KNearestNeighborClassifier(reader, new ClassicSimilarity(), analyzer, null, 1, 0, 0, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, null, analyzer, null, 1, 0, 0, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new ClassicSimilarity(), analyzer, null, 3, 0, 0, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new AxiomaticF1EXP(), analyzer, null, 3, 0, 0, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new AxiomaticF1LOG(), analyzer, null, 3, 0, 0, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new LMDirichletSimilarity(), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new LMJelinekMercerSimilarity(0.3f), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, null, analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new DFRSimilarity(new BasicModelG(), new AfterEffectB(), new NormalizationH1()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new DFRSimilarity(new BasicModelP(), new AfterEffectL(), new NormalizationH3()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new IBSimilarity(new DistributionSPL(), new LambdaDF(), new Normalization.NoNormalization()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new IBSimilarity(new DistributionLL(), new LambdaTTF(), new NormalizationH1()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new MinHashClassifier(reader, BODY_FIELD, CATEGORY_FIELD, 15, 1, 100)); classifiers.add(new MinHashClassifier(reader, BODY_FIELD, CATEGORY_FIELD, 30, 3, 300)); classifiers.add(new MinHashClassifier(reader, BODY_FIELD, CATEGORY_FIELD, 10, 1, 100)); classifiers.add(new KNearestFuzzyClassifier(reader, new LMJelinekMercerSimilarity(0.3f), analyzer, null, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new IBSimilarity(new DistributionLL(), new LambdaTTF(), new NormalizationH1()), analyzer, null, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new ClassicSimilarity(), analyzer, null, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new ClassicSimilarity(), analyzer, null, 3, CATEGORY_FIELD, BODY_FIELD)); classifiers .add(new KNearestFuzzyClassifier(reader, null, analyzer, null, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers .add(new KNearestFuzzyClassifier(reader, null, analyzer, null, 3, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new AxiomaticF1EXP(), analyzer, null, 3, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new AxiomaticF1LOG(), analyzer, null, 3, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new BM25NBClassifier(reader, analyzer, null, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new CachingNaiveBayesClassifier(reader, analyzer, null, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new SimpleNaiveBayesClassifier(reader, analyzer, null, CATEGORY_FIELD, BODY_FIELD)); int maxdoc; if (split) { testReader = DirectoryReader.open(test); maxdoc = testReader.maxDoc(); } else { maxdoc = reader.maxDoc(); } System.out.format("Starting evaluation on %d docs...%n", maxdoc); ExecutorService service = Executors.newCachedThreadPool(); List<Future<String>> futures = new LinkedList<>(); for (Classifier<BytesRef> classifier : classifiers) { testClassifier(reader, startTime, testReader, service, futures, classifier); } for (Future<String> f : futures) { System.out.println(f.get()); } Thread.sleep(10000); service.shutdown(); } finally { if (reader != null) { reader.close(); } directory.close(); if (test != null) { test.close(); } if (train != null) { train.close(); } if (cv != null) { cv.close(); } if (testReader != null) { testReader.close(); } for (Classifier c : classifiers) { if (c instanceof Closeable) { ((Closeable) c).close(); } } } }