| Author: | Jesús M. Pérez <txus.perez{[at]}ehu.eus>, Oscar Teixeira (oteixeira001{[at]}ikasle.ehu.eus) | |
| Category: | Classification | |
| Date: | 2022-03-18 | |
| Depends: | weka (>=3.8.5) | |
| Description: | Class for generating a decision tree based on the CHAID* algorithm a modified version of the CHAID decision tree induction algorithm that also handles continuous features and includes the same post-pruning mechanism used by C4.5. Unlike C4.5 algorithm (J48 class), CHAID uses chi-squared, X², to measure the correlation between the attributes and the class and it only handles discrete variables, although distinguishing between nominal and ordinal behaviour. New options are added to the J48 class related to the CHAID algorithm (CH). For more information, see: Igor Ibarguren and Aritz Lasarguren and Jesús M. Pérez and Javier Muguerza and Ibai Gurrutxaga and Olatz Arbelaitz. "BFPART: Best-First PART". Information Sciences (2016), 367-368, pp 927-952. doi:10.1016/j.ins.2016.07.023 G. V. Kass. "An Exploratory Technique for Investigating Large Quantities of Categorical Data". Journal of the Royal Statistical Society. Series C (Applied Statistics) (1980), 29(2), pp 119-127. http://www.jstor.org/stable/2986296 | |
| Enhances: | ||
| License: | GPL 3.0 | |
| Maintainer: | Jesús M. Pérez <txus.perez{[at]}ehu.eus> | |
| PackageURL: | http://www.aldapa.eus/res/weka-jchaidstar/JCHAIDStar-v1.2.zip | |
| Related: | ||
| URL: | http://www.aldapa.eus/res/weka-jchaidstar | |
| Version: | 1.2 |