Abstract
This chapter looks at the question of how to convert a continuous attribute to a categorical one, a process known as discretisation. This is important as many data mining algorithms, including TDIDT, require all attributes to take categorical values.
Two different types of discretisation are distinguished, known as local and global discretisation. The process of extending the TDIDT algorithm by adding local discretisation of continuous attributes is illustrated in detail, followed by a description of the ChiMerge algorithm for global discretisation. The effectiveness of the two methods is compared for the TDIDT algorithm for a number of datasets.
Reference
Kerber, R. (1992). ChiMerge: discretization of numeric attributes. In Proceedings of the 10th national conference on artificial intelligence (pp. 123–128). Menlo Park: AAAI Press.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag London
About this chapter
Cite this chapter
Bramer, M. (2013). Continuous Attributes. In: Principles of Data Mining. Undergraduate Topics in Computer Science. Springer, London. https://doi.org/10.1007/978-1-4471-4884-5_8
Download citation
DOI: https://doi.org/10.1007/978-1-4471-4884-5_8
Publisher Name: Springer, London
Print ISBN: 978-1-4471-4883-8
Online ISBN: 978-1-4471-4884-5
eBook Packages: Computer ScienceComputer Science (R0)