Benchmarking Open-Source Tree Learners in R/RWeka
The two most popular classification tree algorithms in machine learning and statistics — C4.5 and CART — are compared in a benchmark experiment together with two other more recent constant-fit tree learners from the statistics literature (QUEST, conditional inference trees). The study assesses both misclassification error and model complexity on bootstrap replications of 18 different benchmark datasets. It is carried out in the R system for statistical computing, made possible by means of the RWeka package which interfaces R to the opensource machine learning toolbox Weka. Both algorithms are found to be competitive in terms of misclassification error—with the performance difference clearly varying across data sets. However, C4.5 tends to grow larger and thus more complex trees.
KeywordsPredictive Performance Dominance Relation Recursive Partitioning Tree Learner Breast Cancer Data
Unable to display preview. Download preview PDF.
- HORNIK, K. and MEYER, D. (2007): Deriving Consensus Rankings from Benchmarking Experiments In: Advances in Data Analysis (Proceedings of the 30th Annual Conference of the Gesellschaft für Klassifikation e.V., March 8-10, 2006, Berlin), Decker, R., Lenz, H.-J. (Eds.), Springer-Verlag, 163-170.Google Scholar
- HORNIK, K., ZEILEIS, A., HOTHORN, T. and BUCHTA, C. (2007): RWeka: An R Interface to Weka. R package version 0.3-2. http://CRAN.R-project.org/.
- NEWMAN, D., HETTICH, S., BLAKE, C. and MERZ C. (1998): UCI Repository of Machine Learning Databases. http://www.ics.uci.edu/∼mlearn/MLRepository.html.
- QUINLAN, J. (1993): C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, Inc., San Mateo, CA.Google Scholar
- R DEVELOPMENT CORE TEAM (2006): R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0, http://www.R-project.org/.
- THERNEAU, T. and ATKINSON, E. (1997): An Introduction to Recursive Partitioning Using the rpart Routine. Technical Report. Section of Biostatistics, Mayo Clinic, Rochester, http://www.mayo.edu/hsr/techrpt/61.pdf.