Open theonaunheim opened 3 years ago
Kludgy workaround to impute values instead of calculating with NaNs.
Thank you! This is very helpful. I also noticed that when I pass series that have NaNs in some parts, but all series have the same length, get_probabilities() returns a pandas that is larger than any of the initial series. I think this might correct for that as well, but I'll confirm.
Currently returns NaN because it is normalized to "ALLOTHERNAMES".