Grasshopper

algorithmic modeling for Rhino

I intend to use Grasshopper  to do parametric simulations using DIVA.  However, my universe of models is too large, I was wondering if there is any way to use Latin Hypercube Sampling instead of use genetic algorithm to do my sample. Since my goal is not to obtain the model with the best performance, but to obtain a universe of models that represent my entirely set Latin Hypercube is more suitable for my study.

 

Does anybody know if it is possible, or if there is any plugin that is able to do that?

 

Thanks

Views: 354

Reply to This

Replies to This Discussion

Hello, Raphaela, have you found the way to use LHS in GH? I also come across this problem now.

Hello, Raphaela and Shenghuan. I am in a similar situation and would like to use a sampling method. Did you manage to solve this? I was considering generating the distributions externally and then feeding the variables for each sample in as a list. This could work but it would be great if there was something integrated in Grasshopper.

HI, Ryan

I generated them in Grasshopper and imported in GH.

Hello Shenghuan, 

Thanks for the quick reply. Could you explain this a bit more for me? How did you generate the samples? Also what method of sampling and which components? Thanks!

Sorry, it was a typo. I generated them in Matlab, not grasshopper. then imported them in grasshopper

Okay that's great thanks. I will do something similar.

RSS

About

Translate

Search

Photos

  • Add Photos
  • View All

© 2019   Created by Scott Davidson.   Powered by

Badges  |  Report an Issue  |  Terms of Service