Example usage for org.apache.lucene.search.similarities BM25Similarity BM25Similarity

List of usage examples for org.apache.lucene.search.similarities BM25Similarity BM25Similarity

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.search.similarities.*
  5. BM25Similarity
  6. BM25Similarity

Introduction

In this page you can find the example usage for org.apache.lucene.search.similarities BM25Similarity BM25Similarity.

Prototype

public BM25Similarity()

Source Link

Document

BM25 with these default values:
  • k1 = 1.2
  • b = 0.75

Usage

From source file:IrqaQuery.java

License:Apache License

public static void makeIndexWriter(String indexPath, String stopPath, String sim) throws IOException {
    System.out.println("[makeIndexWriter] started");
    System.out.println("[makeIndexWriter]" + stopPath);
    Directory dir = FSDirectory.open(Paths.get(indexPath));
    Analyzer analyzer = new EnglishAnalyzer(StopFilter.makeStopSet(mygetStopwords(stopPath)));
    IndexWriterConfig iwc = new IndexWriterConfig(analyzer);

    if (sim.equals("TFIDF"))
        iwc.setSimilarity(new ClassicSimilarity());
    else if (sim.equals("BM25"))
        iwc.setSimilarity(new BM25Similarity());
    else/*www. j  av  a 2  s . co  m*/
        iwc.setSimilarity(new BM25Similarity());

    writer = new IndexWriter(dir, iwc);
}

From source file:IrqaQuery.java

License:Apache License

public static List<Document> query(String index, String stoppath, String question, int numResult, String sim)
        throws Exception {
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
    IndexSearcher searcher = new IndexSearcher(reader);

    Analyzer analyzer = new EnglishAnalyzer(StopFilter.makeStopSet(mygetStopwords(stoppath)));

    if (sim.equals("TFIDF"))
        searcher.setSimilarity(new ClassicSimilarity());
    else if (sim.equals("BM25"))
        searcher.setSimilarity(new BM25Similarity());
    else/*w  ww  .j  a va 2 s . co  m*/
        searcher.setSimilarity(new BM25Similarity());

    String field = "contents";
    QueryParser parser = new QueryParser(field, analyzer);
    Query query = parser.parse(parser.escape(question));

    TopDocs results = searcher.search(query, numResult);
    ScoreDoc[] hits = results.scoreDocs;
    List<Document> docs = new ArrayList<Document>();

    int numTotalHits = results.totalHits;
    //        System.out.println(numTotalHits + " total matching documents");

    int end = Math.min(numTotalHits, numResult);

    String searchResult = "";
    //        System.out.println("Only results 1 - " + hits.length);

    for (int i = 0; i < end; i++) {
        Document doc = searcher.doc(hits[i].doc);
        docs.add(doc);
    }

    return docs;
}

From source file:luceneInterface.java

License:Apache License

public static List<Document> query(String index, String stoppath, String question, int numResult, String sim)
        throws Exception {
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
    IndexSearcher searcher = new IndexSearcher(reader);

    Analyzer analyzer = new EnglishAnalyzer(StopFilter.makeStopSet(mygetStopwords(stoppath)));

    if (sim.equals("TFIDF"))
        searcher.setSimilarity(new ClassicSimilarity());
    else if (sim.equals("BM25"))
        searcher.setSimilarity(new BM25Similarity());
    else/*from   w ww .j  a  va  2 s .  c  o  m*/
        searcher.setSimilarity(new BM25Similarity());

    String field = "contents";
    QueryParser parser = new QueryParser(field, analyzer);
    Query query = parser.parse(parser.escape(question));

    BooleanQuery.Builder bqb = new BooleanQuery.Builder();
    bqb.add(new TermQuery(new Term("contents", parser.escape(question))), BooleanClause.Occur.SHOULD);
    bqb.add(new TermQuery(new Term("sec", parser.escape(question))), BooleanClause.Occur.SHOULD);

    //        Term term = new Term(field, question);
    //        Query query = new TermQuery(term);

    //        TopDocs results = searcher.search(query, numResult);
    TopDocs results = searcher.search(parser.parse(bqb.build().toString()), numResult);

    ScoreDoc[] hits = results.scoreDocs;
    List<Document> docs = new ArrayList<Document>();

    int numTotalHits = results.totalHits;
    //        System.out.println(numTotalHits + " total matching documents");

    int end = Math.min(numTotalHits, numResult);

    String searchResult = "";
    //        System.out.println("Only results 1 - " + hits.length);

    for (int i = 0; i < end; i++) {
        Document doc = searcher.doc(hits[i].doc);
        docs.add(doc);
    }

    return docs;
}

From source file:alix.lucene.Alix.java

License:Open Source License

/**
 * Start to scan the glob of xml files/*from w ww .  jav a  2  s . c o m*/
 * 
 * @param indexDir where the lucene indexes are generated
 * @param anAnalyzer Analyzer to use for analyzed fields
 * @param similarity instance of Similarity to work with the writer
 * @throws TransformerConfigurationException 
 */
static public void walk(String xmlGlob, String xslFile, String indexDir)
        throws IOException, TransformerConfigurationException {

    info("Lucene, src:" + xmlGlob + " parser:" + xslFile + " index:" + indexDir);

    Path srcDir = Paths.get(xmlGlob);
    PathMatcher glob = FileSystems.getDefault().getPathMatcher("glob:*.xml");
    if (!Files.isDirectory(srcDir)) {
        String pattern = srcDir.getFileName().toString();
        glob = FileSystems.getDefault().getPathMatcher("glob:" + pattern);
        srcDir = srcDir.getParent();
    }
    if (!Files.isDirectory(srcDir)) {
        fatal("FATAL " + srcDir + " NOT FOUND");
    }

    Path indexPath = Paths.get(indexDir);
    Files.createDirectories(indexPath);
    Directory dir = FSDirectory.open(indexPath);

    // TODO configure analyzers
    Analyzer analyzer = new XmlAnalyzer();
    IndexWriterConfig conf = new IndexWriterConfig(analyzer);
    conf.setOpenMode(OpenMode.CREATE_OR_APPEND);
    conf.setSimilarity(new BM25Similarity());
    conf.setCodec(new ChapitreCodec());
    // Optional: for better indexing performance, if you
    // are indexing many documents, increase the RAM
    // buffer.  But if you do this, increase the max heap
    // size to the JVM (eg add -Xmx512m or -Xmx1g):
    //
    // conf.setRAMBufferSizeMB(256.0);
    lucwriter = new IndexWriter(dir, conf);

    System.setProperty("javax.xml.transform.TransformerFactory", "net.sf.saxon.TransformerFactoryImpl");
    TransformerFactory tf = TransformerFactory.newInstance();
    tf.setAttribute("http://saxon.sf.net/feature/version-warning", Boolean.FALSE);
    tf.setAttribute("http://saxon.sf.net/feature/recoveryPolicy", new Integer(0));
    parser = tf.newTransformer(new StreamSource(xslFile));

    final PathMatcher matcher = glob; // transmit the matcher by a final variable to the anonymous class
    Files.walkFileTree(srcDir, new SimpleFileVisitor<Path>() {
        @Override
        public FileVisitResult visitFile(Path path, BasicFileAttributes attrs) {
            if (path.getFileName().toString().startsWith("."))
                return FileVisitResult.CONTINUE;
            if (!matcher.matches(path.getFileName()))
                return FileVisitResult.CONTINUE;
            parse(path);
            return FileVisitResult.CONTINUE;
        }

        public FileVisitResult preVisitDirectory(Path path, BasicFileAttributes attrs) {
            // .git, .svn
            if (path.getFileName().toString().startsWith("."))
                return FileVisitResult.SKIP_SUBTREE;
            return FileVisitResult.CONTINUE;
        }
    });

    lucwriter.commit();
    // NOTE: if you want to maximize search performance,
    // you can optionally call forceMerge here.  This can be
    // a terribly costly operation, so generally it's only
    // worth it when your index is relatively static (ie
    // you're done adding documents to it):
    //
    lucwriter.forceMerge(1);
    lucwriter.close();
}

From source file:biospectra.Configuration.java

License:Apache License

@JsonIgnore
public Similarity getScoringAlgorithmObject() {
    if (this.scoringAlgorithm == null || this.scoringAlgorithm.isEmpty()
            || this.scoringAlgorithm.equals(DEFAULT_SCORING_ALGORITHM)
            || this.scoringAlgorithm.equalsIgnoreCase("tfidf")
            || this.scoringAlgorithm.equalsIgnoreCase("vectorspace")) {
        // vector-space model
        return new DefaultSimilarity();
    } else if (this.scoringAlgorithm.equalsIgnoreCase("bm25")) {
        // bm25 probability model
        return new BM25Similarity();
    }/*from  www  . j  a  v  a  2 s  .  co m*/

    return new DefaultSimilarity();
}

From source file:cc.twittertools.search.local.RunQueries.java

License:Apache License

@SuppressWarnings("static-access")
public static void main(String[] args) throws Exception {
    Options options = new Options();

    options.addOption(//from   w w w.  j a v a 2  s. com
            OptionBuilder.withArgName("path").hasArg().withDescription("index location").create(INDEX_OPTION));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of results to return")
            .create(NUM_RESULTS_OPTION));
    options.addOption(OptionBuilder.withArgName("file").hasArg()
            .withDescription("file containing topics in TREC format").create(QUERIES_OPTION));
    options.addOption(OptionBuilder.withArgName("similarity").hasArg()
            .withDescription("similarity to use (BM25, LM)").create(SIMILARITY_OPTION));
    options.addOption(
            OptionBuilder.withArgName("string").hasArg().withDescription("runtag").create(RUNTAG_OPTION));
    options.addOption(new Option(VERBOSE_OPTION, "print out complete document"));

    CommandLine cmdline = null;
    CommandLineParser parser = new GnuParser();
    try {
        cmdline = parser.parse(options, args);
    } catch (ParseException exp) {
        System.err.println("Error parsing command line: " + exp.getMessage());
        System.exit(-1);
    }

    if (!cmdline.hasOption(QUERIES_OPTION) || !cmdline.hasOption(INDEX_OPTION)) {
        HelpFormatter formatter = new HelpFormatter();
        formatter.printHelp(RunQueries.class.getName(), options);
        System.exit(-1);
    }

    File indexLocation = new File(cmdline.getOptionValue(INDEX_OPTION));
    if (!indexLocation.exists()) {
        System.err.println("Error: " + indexLocation + " does not exist!");
        System.exit(-1);
    }

    String runtag = cmdline.hasOption(RUNTAG_OPTION) ? cmdline.getOptionValue(RUNTAG_OPTION) : DEFAULT_RUNTAG;

    String topicsFile = cmdline.getOptionValue(QUERIES_OPTION);

    int numResults = 1000;
    try {
        if (cmdline.hasOption(NUM_RESULTS_OPTION)) {
            numResults = Integer.parseInt(cmdline.getOptionValue(NUM_RESULTS_OPTION));
        }
    } catch (NumberFormatException e) {
        System.err.println("Invalid " + NUM_RESULTS_OPTION + ": " + cmdline.getOptionValue(NUM_RESULTS_OPTION));
        System.exit(-1);
    }

    String similarity = "LM";
    if (cmdline.hasOption(SIMILARITY_OPTION)) {
        similarity = cmdline.getOptionValue(SIMILARITY_OPTION);
    }

    boolean verbose = cmdline.hasOption(VERBOSE_OPTION);

    PrintStream out = new PrintStream(System.out, true, "UTF-8");

    IndexReader reader = DirectoryReader.open(FSDirectory.open(indexLocation));
    IndexSearcher searcher = new IndexSearcher(reader);

    if (similarity.equalsIgnoreCase("BM25")) {
        searcher.setSimilarity(new BM25Similarity());
    } else if (similarity.equalsIgnoreCase("LM")) {
        searcher.setSimilarity(new LMDirichletSimilarity(2500.0f));
    }

    QueryParser p = new QueryParser(Version.LUCENE_43, StatusField.TEXT.name, IndexStatuses.ANALYZER);

    TrecTopicSet topics = TrecTopicSet.fromFile(new File(topicsFile));
    for (TrecTopic topic : topics) {
        Query query = p.parse(topic.getQuery());
        Filter filter = NumericRangeFilter.newLongRange(StatusField.ID.name, 0L, topic.getQueryTweetTime(),
                true, true);

        TopDocs rs = searcher.search(query, filter, numResults);

        int i = 1;
        for (ScoreDoc scoreDoc : rs.scoreDocs) {
            Document hit = searcher.doc(scoreDoc.doc);
            out.println(String.format("%s Q0 %s %d %f %s", topic.getId(),
                    hit.getField(StatusField.ID.name).numericValue(), i, scoreDoc.score, runtag));
            if (verbose) {
                out.println("# " + hit.toString().replaceAll("[\\n\\r]+", " "));
            }
            i++;
        }
    }
    reader.close();
    out.close();
}

From source file:cc.twittertools.search.local.SearchStatuses.java

License:Apache License

@SuppressWarnings("static-access")
public static void main(String[] args) throws Exception {
    Options options = new Options();
    options.addOption(//w ww  .  j a  v  a  2 s  .com
            OptionBuilder.withArgName("path").hasArg().withDescription("index location").create(INDEX_OPTION));
    options.addOption(
            OptionBuilder.withArgName("string").hasArg().withDescription("query id").create(QID_OPTION));
    options.addOption(
            OptionBuilder.withArgName("string").hasArg().withDescription("query text").create(QUERY_OPTION));
    options.addOption(
            OptionBuilder.withArgName("string").hasArg().withDescription("runtag").create(RUNTAG_OPTION));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("maxid").create(MAX_ID_OPTION));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of results to return")
            .create(NUM_RESULTS_OPTION));
    options.addOption(OptionBuilder.withArgName("similarity").hasArg()
            .withDescription("similarity to use (BM25, LM)").create(SIMILARITY_OPTION));
    options.addOption(new Option(VERBOSE_OPTION, "print out complete document"));

    CommandLine cmdline = null;
    CommandLineParser parser = new GnuParser();
    try {
        cmdline = parser.parse(options, args);
    } catch (ParseException exp) {
        System.err.println("Error parsing command line: " + exp.getMessage());
        System.exit(-1);
    }

    if (!cmdline.hasOption(QUERY_OPTION) || !cmdline.hasOption(INDEX_OPTION)) {
        HelpFormatter formatter = new HelpFormatter();
        formatter.printHelp(SearchStatuses.class.getName(), options);
        System.exit(-1);
    }

    File indexLocation = new File(cmdline.getOptionValue(INDEX_OPTION));
    if (!indexLocation.exists()) {
        System.err.println("Error: " + indexLocation + " does not exist!");
        System.exit(-1);
    }

    String qid = cmdline.hasOption(QID_OPTION) ? cmdline.getOptionValue(QID_OPTION) : DEFAULT_QID;
    String queryText = cmdline.hasOption(QUERY_OPTION) ? cmdline.getOptionValue(QUERY_OPTION) : DEFAULT_Q;
    String runtag = cmdline.hasOption(RUNTAG_OPTION) ? cmdline.getOptionValue(RUNTAG_OPTION) : DEFAULT_RUNTAG;
    long maxId = cmdline.hasOption(MAX_ID_OPTION) ? Long.parseLong(cmdline.getOptionValue(MAX_ID_OPTION))
            : DEFAULT_MAX_ID;
    int numResults = cmdline.hasOption(NUM_RESULTS_OPTION)
            ? Integer.parseInt(cmdline.getOptionValue(NUM_RESULTS_OPTION))
            : DEFAULT_NUM_RESULTS;
    boolean verbose = cmdline.hasOption(VERBOSE_OPTION);

    String similarity = "LM";
    if (cmdline.hasOption(SIMILARITY_OPTION)) {
        similarity = cmdline.getOptionValue(SIMILARITY_OPTION);
    }

    PrintStream out = new PrintStream(System.out, true, "UTF-8");

    IndexReader reader = DirectoryReader.open(FSDirectory.open(indexLocation));
    IndexSearcher searcher = new IndexSearcher(reader);

    if (similarity.equalsIgnoreCase("BM25")) {
        searcher.setSimilarity(new BM25Similarity());
    } else if (similarity.equalsIgnoreCase("LM")) {
        searcher.setSimilarity(new LMDirichletSimilarity(2500.0f));
    }

    QueryParser p = new QueryParser(Version.LUCENE_43, IndexStatuses.StatusField.TEXT.name,
            IndexStatuses.ANALYZER);
    Query query = p.parse(queryText);
    Filter filter = NumericRangeFilter.newLongRange(StatusField.ID.name, 0L, maxId, true, true);

    TopDocs rs = searcher.search(query, filter, numResults);

    int i = 1;
    for (ScoreDoc scoreDoc : rs.scoreDocs) {
        Document hit = searcher.doc(scoreDoc.doc);

        out.println(String.format("%s Q0 %s %d %f %s", qid, hit.getField(StatusField.ID.name).numericValue(), i,
                scoreDoc.score, runtag));
        if (verbose) {
            out.println("# " + hit.toString().replaceAll("[\\n\\r]+", " "));
        }
        i++;
    }

    reader.close();
    out.close();
}

From source file:com.github.tteofili.looseen.TestWikipediaClassification.java

License:Apache License

@Test
public void testItalianWikipedia() throws Exception {

    String indexProperty = System.getProperty("index");
    if (indexProperty != null) {
        try {/*from  w  w w .ja va  2s .  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;
    DirectoryReader 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;
    try {
        Collection<String> stopWordsList = Arrays.asList("di", "a", "da", "in", "per", "tra", "fra", "il", "lo",
                "la", "i", "gli", "le");
        CharArraySet stopWords = new CharArraySet(stopWordsList, true);
        Analyzer analyzer = new ItalianAnalyzer(stopWords);
        if (index) {

            System.out.format("Indexing Italian Wikipedia...%n");

            long startIndex = System.currentTimeMillis();
            IndexWriter indexWriter = new IndexWriter(directory, new IndexWriterConfig(analyzer));

            importWikipedia(new File(PREFIX + "/itwiki/itwiki-20150405-pages-meta-current1.xml"), indexWriter);
            importWikipedia(new File(PREFIX + "/itwiki/itwiki-20150405-pages-meta-current2.xml"), indexWriter);
            importWikipedia(new File(PREFIX + "/itwiki/itwiki-20150405-pages-meta-current3.xml"), indexWriter);
            importWikipedia(new File(PREFIX + "/itwiki/itwiki-20150405-pages-meta-current4.xml"), 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);
            for (LeafReaderContext context : reader.leaves()) {
                datasetSplitter.split(context.reader(), train, test, cv, analyzer, false, CATEGORY_FIELD,
                        TEXT_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();

        List<Classifier<BytesRef>> classifiers = new LinkedList<>();
        classifiers.add(new KNearestNeighborClassifier(reader, new ClassicSimilarity(), analyzer, null, 1, 0, 0,
                CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestNeighborClassifier(reader, new BM25Similarity(), analyzer, null, 1, 0, 0,
                CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestNeighborClassifier(reader, null, analyzer, null, 1, 0, 0, CATEGORY_FIELD,
                TEXT_FIELD));
        classifiers.add(new KNearestNeighborClassifier(reader, new LMDirichletSimilarity(), analyzer, null, 3,
                1, 1, CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestNeighborClassifier(reader, new LMJelinekMercerSimilarity(0.3f), analyzer,
                null, 3, 1, 1, CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestNeighborClassifier(reader, new ClassicSimilarity(), analyzer, null, 3, 0, 0,
                CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestNeighborClassifier(reader, new ClassicSimilarity(), analyzer, null, 3, 1, 1,
                CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestNeighborClassifier(reader,
                new DFRSimilarity(new BasicModelG(), new AfterEffectB(), new NormalizationH1()), analyzer, null,
                3, 1, 1, CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestNeighborClassifier(reader,
                new DFRSimilarity(new BasicModelP(), new AfterEffectL(), new NormalizationH3()), analyzer, null,
                3, 1, 1, CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestNeighborClassifier(reader,
                new IBSimilarity(new DistributionSPL(), new LambdaDF(), new Normalization.NoNormalization()),
                analyzer, null, 3, 1, 1, CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestNeighborClassifier(reader,
                new IBSimilarity(new DistributionLL(), new LambdaTTF(), new NormalizationH1()), analyzer, null,
                3, 1, 1, CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 5, 1, 100));
        classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 10, 1, 100));
        classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 15, 1, 100));
        classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 15, 3, 100));
        classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 15, 3, 300));
        classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 5, 3, 100));
        classifiers.add(new KNearestFuzzyClassifier(reader, new ClassicSimilarity(), analyzer, null, 3,
                CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestFuzzyClassifier(reader, new ClassicSimilarity(), analyzer, null, 1,
                CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestFuzzyClassifier(reader, new BM25Similarity(), analyzer, null, 3,
                CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new KNearestFuzzyClassifier(reader, new BM25Similarity(), analyzer, null, 1,
                CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new BM25NBClassifier(reader, analyzer, null, CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new CachingNaiveBayesClassifier(reader, analyzer, null, CATEGORY_FIELD, TEXT_FIELD));
        classifiers.add(new SimpleNaiveBayesClassifier(reader, analyzer, null, CATEGORY_FIELD, TEXT_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) {

            final IndexReader finalReader = reader;
            final DirectoryReader finalTestReader = testReader;
            futures.add(service.submit(() -> {
                ConfusionMatrixGenerator.ConfusionMatrix confusionMatrix;
                if (split) {
                    confusionMatrix = ConfusionMatrixGenerator.getConfusionMatrix(finalTestReader, classifier,
                            CATEGORY_FIELD, TEXT_FIELD, 60000 * 30);
                } else {
                    confusionMatrix = ConfusionMatrixGenerator.getConfusionMatrix(finalReader, classifier,
                            CATEGORY_FIELD, TEXT_FIELD, 60000 * 30);
                }

                final long endTime = System.currentTimeMillis();
                final int elapse = (int) (endTime - startTime) / 1000;

                return " * " + classifier + " \n    * accuracy = " + confusionMatrix.getAccuracy()
                        + "\n    * precision = " + confusionMatrix.getPrecision() + "\n    * recall = "
                        + confusionMatrix.getRecall() + "\n    * f1-measure = " + confusionMatrix.getF1Measure()
                        + "\n    * avgClassificationTime = " + confusionMatrix.getAvgClassificationTime()
                        + "\n    * time = " + elapse + " (sec)\n ";
            }));

        }
        for (Future<String> f : futures) {
            System.out.println(f.get());
        }

        Thread.sleep(10000);
        service.shutdown();

    } finally {
        try {
            if (reader != null) {
                reader.close();
            }
            if (directory != null) {
                directory.close();
            }
            if (test != null) {
                test.close();
            }
            if (train != null) {
                train.close();
            }
            if (cv != null) {
                cv.close();
            }
            if (testReader != null) {
                testReader.close();
            }
        } catch (Throwable e) {
            e.printStackTrace();
        }
    }
}

From source file:com.mycompany.lucenedemo.SearchFiles.java

/** Simple command-line based search demo. */
public static void main(String[] args) throws Exception {
    String usage = "Usage:\tjava org.apache.lucene.demo.SearchFiles [-index dir] [-field f] [-repeat n] [-queries file] [-query string] [-raw] [-paging hitsPerPage] [-sim vsm or bm25]\n\nSee http://lucene.apache.org/core/4_1_0/demo/ for details.";
    if (args.length == 0 || (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0])))) {
        System.out.println(usage);
        System.exit(0);/*w  ww. j  a  v  a 2  s  .  c  o  m*/
    }

    String index = "index";
    String field = "contents";
    String queries = null;
    int repeat = 0;
    boolean raw = false;
    String queryString = null;
    int hitsPerPage = 10;
    SimilarityScore score = SimilarityScore.DEFAULT;

    for (int i = 0; i < args.length; i++) {
        if ("-index".equals(args[i])) {
            index = args[i + 1];
            i++;
        } else if ("-field".equals(args[i])) {
            field = args[i + 1];
            i++;
        } else if ("-queries".equals(args[i])) {
            queries = args[i + 1];
            i++;
        } else if ("-query".equals(args[i])) {
            queryString = args[i + 1];
            i++;
        } else if ("-repeat".equals(args[i])) {
            repeat = Integer.parseInt(args[i + 1]);
            i++;
        } else if ("-raw".equals(args[i])) {
            raw = true;
        } else if ("-paging".equals(args[i])) {
            hitsPerPage = Integer.parseInt(args[i + 1]);
            if (hitsPerPage <= 0) {
                System.err.println("There must be at least 1 hit per page.");
                System.exit(1);
            }
            i++;
        } else if ("-sim".equals(args[i])) {
            if (args[i + 1].equals("vsm")) {
                score = SimilarityScore.VSM;
            } else {
                score = SimilarityScore.BM25;
            }
        }
    }

    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer();

    BufferedReader in = null;
    if (queries != null) {
        in = Files.newBufferedReader(Paths.get(queries), StandardCharsets.UTF_8);
    } else {
        in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));
    }
    QueryParser parser = new QueryParser(field, analyzer);

    while (true) {
        if (queries == null && queryString == null) { // prompt the user
            System.out.println("Enter query: ");
        }

        String line = queryString != null ? queryString : in.readLine();

        if (line == null || line.length() == -1) {
            break;
        }

        line = line.trim();
        if (line.length() == 0) {
            break;
        }

        Query query = parser.parse(line);
        System.out.println("Searching for: " + query.toString(field));

        switch (score) {
        case DEFAULT:
            break;
        case VSM:
            searcher.setSimilarity(new ClassicSimilarity());
            break;
        case BM25:
            searcher.setSimilarity(new BM25Similarity());
            break;
        }

        if (repeat > 0) { // repeat & time as benchmark
            Date start = new Date();
            for (int i = 0; i < repeat; i++) {
                searcher.search(query, 100);
            }
            Date end = new Date();
            System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
        }

        doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);

        if (queryString != null) {
            break;
        }
    }
    reader.close();
}

From source file:com.o19s.es.ltr.query.LtrQueryTests.java

License:Apache License

@Before
public void setupIndex() throws IOException {
    dirUnderTest = newDirectory();//from  w ww  .j a v a 2  s  .c  o m
    List<Similarity> sims = Arrays.asList(new ClassicSimilarity(), new SweetSpotSimilarity(), // extends Classic
            new BM25Similarity(), new LMDirichletSimilarity(), new BooleanSimilarity(),
            new LMJelinekMercerSimilarity(0.2F), new AxiomaticF3LOG(0.5F, 10),
            new DFISimilarity(new IndependenceChiSquared()),
            new DFRSimilarity(new BasicModelBE(), new AfterEffectB(), new NormalizationH1()),
            new IBSimilarity(new DistributionLL(), new LambdaDF(), new NormalizationH3()));
    similarity = sims.get(random().nextInt(sims.size()));

    indexWriterUnderTest = new RandomIndexWriter(random(), dirUnderTest,
            newIndexWriterConfig().setSimilarity(similarity));
    for (int i = 0; i < docs.length; i++) {
        Document doc = new Document();
        doc.add(newStringField("id", "" + i, Field.Store.YES));
        doc.add(newField("field", docs[i], Store.YES));
        indexWriterUnderTest.addDocument(doc);
    }
    indexWriterUnderTest.commit();
    indexWriterUnderTest.forceMerge(1);
    indexWriterUnderTest.flush();

    indexReaderUnderTest = indexWriterUnderTest.getReader();
    searcherUnderTest = newSearcher(indexReaderUnderTest);
    searcherUnderTest.setSimilarity(similarity);
}