XitongLiang
commented
4 months ago Hi,
Many thanks for your interest in our work and for bringing these issues to our attention. I am so sorry for any inconvenience caused by the malfunctioning codes. I have made the necessary modifications, and they should be run correctly now.
The file "0_examples.R" provides an example of setting up all necessary parameters for the PARNI-DAG proposal using the "gsim100" dataset from the "BiDAG" package. I have incorporated your suggestion by updating the code to set up the working directory in R, and I've also included the code for sourcing the script of "DAG_heatmap."
The purpose of the code "DAG_heatmap(dataset$W)" is to visualise the true underlying graph used in generating the "gsim100" dataset. This true graph should correspond to "gsimmat." I have made the necessary adjustments to reflect this update.
Please do not hesitate to contact me if you encounter any further issues or have any questions. Thanks again for your help.
Best wishes, Tony
alexjilkin
Hello! I am coming from the "Structure Learning with Adaptive Random Neighborhood Informed MCMC" paper and I am trying to use your sampler as a benchmark.
Is it intended to run 0_examples.R as the main file? If yes, it has some issues.
setwd("codes/algorithms") should be setwd("./algorithms") DAG_heatmap is not imported
DAG_heatmap(dataset$W) refers to a dataset variable not existing. Is it supposed to be skel.dataset?