Hey. We currently support only pandas dataframes, so you'd need to load it into memory. You could build a lightgbm dataset after the preprocessing and train using that, not sure if it that'd help a lot though.
m
Mike C
08/29/2023, 7:09 PM
Makes sense. Thanks for the quick response!
j
José Morales
08/29/2023, 7:18 PM
We try to keep the types where possible, so if you define the id as categorical and the target as float32 you could reduce the memory usage