Beispiel #1
0
  @Override
  public AnalysisCollector analyze(CollectionReader cr) throws AnalyzerFailureException {
    svm_problem svmProblem = loadData(cr);
    svm_problem sampled = null;
    if (findBestParameters) {
      if (sample < 1d) {
        logger.debug("Sampling.");
        sampled = do_sample(svmProblem);
      }
      logger.debug("Performing grid search.");
      do_find_best_parameters(sampled != null ? sampled : svmProblem);
    }
    svm_parameter svmParam = getDefaultSvmParameters();
    svmParam.probability = 1;
    svmParam.C = c;
    svmParam.gamma = gamma;
    setWeights(svmParam);

    logger.debug("Training with C=" + c + "  gamma=" + gamma);
    svm_model model = svm.svm_train(svmProblem, svmParam);

    logger.debug("Done!");
    return new SingletonAnalysisCollector(
        new LibSvmTrainerAnalysis(model, scaler, labelList, c, gamma));
  }
Beispiel #2
0
 private void setWeights(svm_parameter svmParam) {
   if (weights != null) {
     svmParam.nr_weight = weights.size();
     svmParam.weight_label = new int[weights.size()];
     svmParam.weight = new double[weights.size()];
     for (int i = 0; i < weights.size(); ++i) {
       svmParam.weight_label[i] = i;
       svmParam.weight[i] = weights.get(i);
     }
     logger.debug("Class weights: " + weights);
   }
 }
Beispiel #3
0
 public svm_parameter getDefaultSvmParameters() {
   svm_parameter param = new svm_parameter();
   // default values
   param.svm_type = svm_parameter.C_SVC;
   param.kernel_type = svm_parameter.RBF;
   param.degree = 3;
   param.gamma = 0; // 1/num_features
   param.coef0 = 0;
   param.nu = 0.5;
   param.cache_size = 100;
   param.C = 1;
   param.eps = 1e-3;
   param.p = 0.1;
   param.shrinking = 1;
   param.probability = 0;
   param.nr_weight = 0;
   param.weight_label = new int[0];
   param.weight = new double[0];
   return param;
 }
Beispiel #4
0
  private void do_find_best_parameters(svm_problem svmProblem) {
    svm_parameter svmParam = getDefaultSvmParameters();
    setWeights(svmParam);

    int maxIter =
        ((int) Math.ceil(Math.abs((log2cEnd - log2cBegin) / log2cStep)) + 1)
            * ((int) Math.ceil(Math.abs((log2gEnd - log2gBegin) / log2gStep)) + 1);

    // Run the grid search in separate CV threads
    ExecutorService executorService = Executors.newFixedThreadPool(numberOfThreads);

    List<CvParams> cvParamsList = new ArrayList<CvParams>();

    for (double log2c = log2cBegin;
        (log2cBegin < log2cEnd && log2c <= log2cEnd)
            || (log2cBegin >= log2cEnd && log2c >= log2cEnd);
        log2c += log2cStep) {

      double c1 = Math.pow(2, log2c);

      for (double log2g = log2gBegin;
          (log2gBegin < log2gEnd && log2g <= log2gEnd)
              || (log2gBegin >= log2gEnd && log2g >= log2gEnd);
          log2g += log2gStep) {

        double gamma1 = Math.pow(2, log2g);

        svm_parameter svmParam1 = (svm_parameter) svmParam.clone();
        svmParam1.C = c1;
        svmParam1.gamma = gamma1;

        executorService.execute(
            new RunnableSvmCrossValidator(svmProblem, svmParam1, nrFold, cvParamsList));
      }
    }

    // now wait for all threads to complete by calling shutdown
    // note that this will NOT terminate the currently running threads, it just signals the thread
    // pool to closeWriter
    // once all work is completed
    executorService.shutdown();

    while (!executorService.isTerminated()) {
      try {
        Thread.sleep(1000);
      } catch (InterruptedException e) {
        // don't care if we get interrupted
      }

      // every second, report statistics
      logger.debug(
          String.format("%% complete: %5.2f", cvParamsList.size() / (double) maxIter * 100));
      CvParams best = getBestCvParams(cvParamsList);
      CvParams worst = getWorstcvParams(cvParamsList);
      if (best != null) {
        logger.debug("Best accuracy: " + best.accuracy);
        logger.debug("Best C:        " + best.c);
        logger.debug("Best Gamma:    " + best.gamma);
      }
      if (worst != null) {
        logger.debug("Worst accuracy: " + worst.accuracy);
      }
    }

    CvParams best = getBestCvParams(cvParamsList);
    CvParams worst = getWorstcvParams(cvParamsList);
    if (best != null) {
      logger.debug("Best accuracy: " + best.accuracy);
      logger.debug("Best C:        " + best.c);
      logger.debug("Best Gamma:    " + best.gamma);

      c = best.c;
      gamma = best.gamma;
    } else {
      logger.error("Best CV parameters is null.");
    }
    if (worst != null) {
      logger.debug("Worst accuracy: " + worst.accuracy);
    }
  }