20.69 The Original C5.0 Implementation

The (Kuhn and Quinlan 2022) package interfaces the original C code of the C5.0 implementation by Ross Quinlan, the developer of the decision tree induction algorithm.

library(C50)
model <- C5.0(form, ds[tr, vars])
model
## 
## Call:
## C5.0.formula(formula = form, data = ds[tr, vars])
## 
## Classification Tree
## Number of samples: 123722 
## Number of predictors: 20 
## 
## Tree size: 780 
## 
## Non-standard options: attempt to group attributes
C5imp(model)
##                 Overall
## humidity_3pm     100.00
## wind_gust_speed   92.32
## sunshine          91.59
## rain_today        84.34
## pressure_3pm      47.63
## min_temp          29.55
## rainfall          22.49
## wind_dir_3pm      16.85
## humidity_9am      14.23
## cloud_3pm         13.44
## max_temp          11.21
## wind_gust_dir     10.48
## temp_9am          10.37
## wind_speed_9am     9.77
## temp_3pm           9.61
## wind_dir_9am       8.66
## wind_speed_3pm     7.49
## pressure_9am       6.58
## cloud_9am          5.93
## evaporation        2.88

% DONT EVAL YET - SEEMS TO BE TAKING LONG TIME

plot(model)

I am not aware of any converter from a C5.0 tree to an rpart tree and so fancyRpartPlot() will not be useful here.

References

Kuhn, Max, and Ross Quinlan. 2022. C50: C5.0 Decision Trees and Rule-Based Models. https://topepo.github.io/C5.0/.


Your donation will support ongoing availability and give you access to the PDF version of this book. Desktop Survival Guides include Data Science, GNU/Linux, and MLHub. Books available on Amazon include Data Mining with Rattle and Essentials of Data Science. Popular open source software includes rattle, wajig, and mlhub. Hosted by Togaware, a pioneer of free and open source software since 1984. Copyright © 1995-2021 Graham.Williams@togaware.com Creative Commons Attribution-ShareAlike 4.0