Instructions to use wwood/aerobicity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use wwood/aerobicity with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("wwood/aerobicity", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
probability question
#1
by michoug - opened
Hi,
Very nice model,
I'm not sure that I understand well how is the probability value calculated.
It tends to be 1 if it's aerobic and 0 for anaerobic, do you apply a threshold at which point you consider the prediction to not be "acceptable"?
I have some probability values of 0.6, 0.3, or 0.2 for example and I gather if the values are above or below 0.5 is when the program choose to categorize the aerobicity.
Cheers
Greg
Hi Greg,
Thanks. Yes, 0.5 is the threshold, though I find in most cases the values are quite close to 0 or 1.
HTH