Free Trial

Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.


Share this Page URL
Help

16.1 An example classifier > makeTree() - Pg. 540

540 CHAPTER16 Writing New Learning Schemes Table16.1 SimpleLearningSchemesinWeka Scheme weka.classifiers.bayes.NaiveBayesSimple weka.classifiers.trees.Id3 weka.classifiers.rules.Prism weka.classifiers.lazy.IB1 Description Probabilistic learner Decision tree learner Rule learner Instance-based learner Book Section 4.2 4.3 4.4 4.7 buildClassifier() The buildClassifier() method constructs a classifier from a training dataset. In this case, it first checks the data's characteristics against Id3's capabilities. Characteris- tics of the training data, such as numeric attributes or missing attribute values, will cause the Capabilities class to raise an exception, because the ID3 algorithm cannot handle these. It then makes a copy of the training set (to avoid changing the original data) and calls a method from weka.core.Instances to delete all instances with