Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implement some transformation operators for valued networks. #595

Open
krivit opened this issue Jan 29, 2025 · 1 comment
Open

Implement some transformation operators for valued networks. #595

krivit opened this issue Jan 29, 2025 · 1 comment

Comments

@krivit
Copy link
Member

krivit commented Jan 29, 2025

Ideally, there would be a way to evaluate some function on each dyad's value and then evaluate the terms of interest on the valued network with new dyad values.

In practice, a good starting point might be a Pow(formula, pow) operator that takes the dyad values to the specified positive power. This could work well with in combination with Project() to model various forms of bipartite mixing while reducing the risk of degeneracy, e.g.,

y ~ Proj1(~Pow(~absdiff("x"), 1/2))

Any other ideas?

@krivit
Copy link
Member Author

krivit commented Jan 31, 2025

On further thought, using a formula-within-a-formula is more elegant:

y ~ Proj1(~(sqrt~absdiff("x")))

The LHS can have some presets for now, but, eventually, perhaps a stack-based language-within-a-language akin to the one that implements layer logic in ergm.multi could be used.

krivit added a commit that referenced this issue Jan 31, 2025
…ming them by EXPR added and "sqrt" transformation implemented.

references #595
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant