Workflow 1

  • read data
  • create new class attribute
  • fill in value for new class attribute based on existing attribute values (such as object, flag, etc)
  • discard all attributes except magnitudes, new class attribute
  • sample dataset using a combination of oversampling the minority class, undersampling the majority class to create 10 training and 10 test sets
  • apply Decision tree algorithm, using 10-fold cross validation
  • compute overall result
  • display result
  • save model
  • discard training and test sets