Prediction method and on-going maintenance

[jelc53]

Hi Matthijs ! Just watched your PyData talk from Oct 2020 and would love to try using this model package in a production codebase. It appears the main missing element is a robust prediction api. Is this still the case?

If so, would you be willing to invest some time either adding this functionality or guiding me to do it? I would also be happy to pitch in some level of on-going maintenance if so.