Being able to access the points that were used to sample the Sankey data might be useful (or at least interesting), and wouldn't require much work. Just need to refactor to generate the random points outside of the sampling function and pass them in. That change would also make it trivial to allow user-defined points, which could be worth adding in the future.
Being able to access the points that were used to sample the Sankey data might be useful (or at least interesting), and wouldn't require much work. Just need to refactor to generate the random points outside of the sampling function and pass them in. That change would also make it trivial to allow user-defined points, which could be worth adding in the future.