dkesada/dbnR

Does it support missing data in the dataframe?

Closed this issue · 1 comments

I have a dataset with high number of missing values. The function threw an error. I was wondering if there is a documentation on how to handle missing data.

Hi, I'm sorry but the package doesn't support missing data at the moment. You would have to treat the dataset to either impute the missing values or clear them before training. Another alternative would be to try and apply a dynamic structural expectation maximization algorithm if you are familiar with this kind of method, but I haven't implemented it yet.