python-libmf
python-libmf copied to clipboard
Python bindings to the libmf c++ repo for Matrix Factorization. libmf is fast, highly parallel, and can support factoring large matrices without holding them all in memory.
When receiving IDs for users and items, they get casted to float32. For values above 2^23 (around 8.3 million), the conversion might be imprecise, since not all integers higher than...
Fixes https://github.com/PorkShoulderHolder/python-libmf/issues/9#issuecomment-1207489893
For some reason I keep getting extremely unreasonable results when fitting a model, regardless of the data or parameters. I am not sure why this is, but I suspect it...
Hi I installed libmf successfully, but I have the following error to importing it when I write: from libmf import mf The error is: cannot import name 'mf' from 'libmf'
Even after I fix all the print statements, the unit tests all failed and prompted: OSError: [WinError 127] The specified procedure could not be found
add python3 support and auto autodetect so file
there should be an interface to expose the latent factor matrices for use in python
We should remove the `mf_` prefix from all methods to make it match the signature of sklearn
Hi, Your use of libmf violates the licensing terms, specifically > 1. Redistributions of source code **must retain the above copyright notice**, this list of conditions and the following disclaimer....
Is there a way to add random seed control to ensure reproducibility?