search

vonjd / OneR

This R package implements the One Rule (OneR) Machine Learning classification algorithm with enhancements for sophisticated handling of numeric data and missing values together with extensive diagnostic functions.
Other
40 stars 3 forks source link

How does optbin() function optimize the cut points? #7

Closed HMais closed 5 years ago

HMais commented 5 years ago

Thanks for the great package! I ‘m using your discretization function optbin() in a comparative analysis of different discretization methods. I read the documentation about this function (p. 9 - 11), but I remain confused, especially about the "logreg" and the "naive" methods… Could you please provide more details about the three discretization methods available through the optbin(). Thanks!

vonjd commented 5 years ago

What exactly is it, that you don't understand? I think best would be to have a look at the source code for all the details: https://github.com/vonjd/OneR/blob/master/R/OneR_internal.R

The important function here is optcut: the method naive is done directly there, the method logreg can be found in the function logreg_midpoint.

The source code is documented, if you have any specific questions please do not hesitate to reach out!

HMais commented 5 years ago

Thanks very much for your prompt reply. The code documentation answers my questions.

vonjd commented 5 years ago

Could you perhaps post a link here when your analysis is ready? That would be great!