Package ivory.core.preprocess

Examples of ivory.core.preprocess.BuildTermDocVectors


    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);

    Path mappingFile = env.getDocnoMappingData();
    docnoMappingClass.newInstance().getBuilder().build(new Path(collection), mappingFile, conf);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
View Full Code Here


    conf.setInt(Constants.DocnoOffset, 0);
    conf.setInt(Constants.MinDf, 50);
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);
    conf.setInt(Constants.TermIndexWindow, 8);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
View Full Code Here

    conf.setInt(Constants.DocnoOffset, DocnoOffsets[segment]);
    conf.setInt(Constants.MinDf, 10);
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
View Full Code Here

    conf.setInt("Ivory.DocnoOffset", 0); // docnos start at 1
    conf.setInt("Ivory.MinDf", 2); // toss away singleton terms
    conf.setInt("Ivory.MaxDf", Integer.MAX_VALUE);
    conf.setInt("Ivory.TermIndexWindow", 8);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
View Full Code Here

    conf.setInt(Constants.DocnoOffset, 0); // docnos start at 1
    conf.setInt(Constants.MinDf, 2); // toss away singleton terms
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
View Full Code Here

    // Builds term doc vectors from document collection, and filters the terms that are not included
    // in Ivory.SrcVocab.
    long startTime = System.currentTimeMillis();
    long preprocessStartTime = System.currentTimeMillis();
    LOG.info("Building term doc vectors...");
    int exitCode = new BuildTermDocVectors(conf).run();
    if (exitCode >= 0) {
      LOG.info("Job BuildTermDocVectors finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
    }else {
      LOG.info("Error: BuildTermDocVectors. Terminating...");
      return -1;
View Full Code Here

    conf.setInt(Constants.MinDf, 2); // toss away singleton terms
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);
    conf.setInt(Constants.TermIndexWindow, 8);
    conf.set(Constants.InputFormat, TrecDocumentInputFormat.class.getCanonicalName());

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
View Full Code Here

    // Builds term doc vectors from document collection, and filters the terms that are not included
    // in Ivory.SrcVocab.
    long startTime = System.currentTimeMillis();
    long preprocessStartTime = System.currentTimeMillis();
    LOG.info("Building term doc vectors...");
    int exitCode = new BuildTermDocVectors(conf).run();
    if (exitCode >= 0) {
      LOG.info("Job BuildTermDocVectors finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
    }else {
      LOG.info("Error: BuildTermDocVectors. Terminating...");
      return -1;
View Full Code Here

    conf.setInt(Constants.DocnoOffset, 0); // docnos start at 1
    conf.setInt(Constants.MinDf, 10);
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);
    conf.setInt(Constants.TermIndexWindow, 8);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
View Full Code Here

TOP

Related Classes of ivory.core.preprocess.BuildTermDocVectors

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.