Instructions to use Danieltash0/dairydan-yield-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use Danieltash0/dairydan-yield-models with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("Danieltash0/dairydan-yield-models", "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
DairyDan milk yield models
History pathway (โฅ3 records) โ scale-free autoregressive linear regression over the last 7 sessions
(ts_linear_regression.joblib). Test MAPE 3.41% vs moving average 7.98% (monthly series, 1973โ75).
Cold-start pathway (<3 records) โ Keras MLP on the cow profile (coldstart_nn.keras + coldstart_preprocessor.joblib),
anchored to Kenyan breed baselines (breed_baselines.json). Target: knowledge_informed.
Test MAE 1.391 L/day vs breed lookup 8.624 L/day.
- Downloads last month
- -