Improve methods for exploring graphs

itsrainingdata / sparsebn

Software for learning sparse Bayesian networks

43 stars 8 forks source link

Improve methods for exploring graphs #13

Open itsrainingdata opened 7 years ago

itsrainingdata commented 7 years ago

Extend and improve the existing show.parents method to filter by richer criteria such as minimum number of parents, number of children, v-structures, etc.

Write a method for filtering: filter.nodes that returns a list of filtered nodes
Write a wrapper that calls show.parents on the output of filter.nodes

s0810110 commented 3 years ago

Hi, first of all, thank you so much for this wonderful tool for R. I am a new to this library so I have a very strange questions.

When I obtain the coefficients from the estimate

cyto.param$coefs

This returns a matrix of edge weights.

I wonder how I should interpret the edge weights in the sparsebn context for directed edges; do these represent the posterior probability of the child given the parent or are these the marginal likelihood of the parent?