search

erdogant / bnlearn

Python package for Causal Discovery by learning the graphical structure of Bayesian networks. Structure Learning, Parameter Learning, Inferences, Sampling methods.
https://erdogant.github.io/bnlearn
Other
476 stars 46 forks source link

Integrate new models #2

Closed arita37 closed 4 years ago

arita37 commented 4 years ago

This is great work. What about the design to integrate new models ?

erdogant commented 4 years ago

Good point. I will see how I can refactor the code so that other code can be more easily implemented. Do you have any suggestions for design?

arita37 commented 4 years ago

Similar to sklearn :

fit() predict() transform() get_metrics()

On Jan 26, 2020, at 0:16, Erdogan Taskesen notifications@github.com wrote:

 Good point. I will see how I can refactor the code so that other code can be more easily implemented. Do you have any suggestions for design?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

arita37 commented 4 years ago

Am working on generic API: It can be re-used in some ways.

https://github.com/arita37/mlmodels/tree/dev

Wr can discuss here.

On Jan 26, 2020, at 0:16, Erdogan Taskesen notifications@github.com wrote:

 Good point. I will see how I can refactor the code so that other code can be more easily implemented. Do you have any suggestions for design?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.