samoa-api/src/main/java/org/apache/samoa/learners/classifiers/rules/centralized/AMRulesRegressorProcessor.java [276:305]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
      if (rule.getInstancesSeen() >= this.anomalyNumInstThreshold) {
        isAnomaly = rule.isAnomaly(instance,
            this.univariateAnomalyprobabilityThreshold,
            this.multivariateAnomalyProbabilityThreshold,
            this.anomalyNumInstThreshold);
      }
    }
    return isAnomaly;
  }

  /*
   * Create new rules
   */
  // TODO check this after finish rule, LN
  private ActiveRule newRule(int ID, RuleActiveRegressionNode node, double[] statistics) {
    ActiveRule r = newRule(ID);

    if (node != null)
    {
      if (node.getPerceptron() != null)
      {
        r.getLearningNode().setPerceptron(new Perceptron(node.getPerceptron()));
        r.getLearningNode().getPerceptron().setLearningRatio(this.learningRatio);
      }
      if (statistics == null)
      {
        double mean;
        if (node.getNodeStatistics().getValue(0) > 0) {
          mean = node.getNodeStatistics().getValue(1) / node.getNodeStatistics().getValue(0);
          r.getLearningNode().getTargetMean().reset(mean, 1);
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



samoa-api/src/main/java/org/apache/samoa/learners/classifiers/rules/distributed/AMRulesAggregatorProcessor.java [248:276]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
      if (rule.getInstancesSeen() >= this.anomalyNumInstThreshold) {
        isAnomaly = rule.isAnomaly(instance,
            this.univariateAnomalyprobabilityThreshold,
            this.multivariateAnomalyProbabilityThreshold,
            this.anomalyNumInstThreshold);
      }
    }
    return isAnomaly;
  }

  /*
   * Create new rules
   */
  private ActiveRule newRule(int ID, RuleActiveRegressionNode node, double[] statistics) {
    ActiveRule r = newRule(ID);

    if (node != null)
    {
      if (node.getPerceptron() != null)
      {
        r.getLearningNode().setPerceptron(new Perceptron(node.getPerceptron()));
        r.getLearningNode().getPerceptron().setLearningRatio(this.learningRatio);
      }
      if (statistics == null)
      {
        double mean;
        if (node.getNodeStatistics().getValue(0) > 0) {
          mean = node.getNodeStatistics().getValue(1) / node.getNodeStatistics().getValue(0);
          r.getLearningNode().getTargetMean().reset(mean, 1);
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -