I have a dataset x, y, and errors on y over which I want to perform a weighted LOWESS interpolation. Unfortunately, I am stuck working in Python 3.7. I have tried the package lowess from statsmodels.api.nonparametric, but this doesn't support weighting. I have tried the package loess from skmisc.loess, which does support weighting but straight up doesn't exist in skmisc-0.1.4 as far as I can tell. That is, skmisc.loess seems to exist but not the loess function inside of that? I get a missing DLL error. Is there another option out there that I'm missing, or am I stuck trying to create my own weighted LOWESS regression algorithm by hand? Or perhaps I'm just missing something when it comes to skmisc? Traceback (most recent call last): File "c:/Users/atomg/OneDrive - Thermochron Systems LLC/heman_code/Pro/misc_tools/asdf.py", line 2, in <module> from skmisc.loess import loess File "C:\Users\atomg\OneDrive - Thermochron Systems LLC\heman_code\Pro\.venv\lib\site-packages\skmisc\loess\__init__.py", line 51, in <module> from ._loess import (loess, loess_model, loess_inputs, loess_control, ImportError: DLL load failed: The specified module could not be found. Continue reading...
