Tabular Classification
Scikit-learn
survival-analysis
predictive-maintenance
battery
time-series
scheduling
operations-research
nora-batteryswapai-2026
Instructions to use YassY-The-AlchemYst/YassYBS26Sol48 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use YassY-The-AlchemYst/YassYBS26Sol48 with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("YassY-The-AlchemYst/YassYBS26Sol48", "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
YassYBS26 Sol48 โ High-Precision Veto Planner
Submission for the NORA BatterySwapAI 2026 challenge.
Planner.plan() estimates a predictive distribution over each battery's
end-of-life date, prices every candidate swap day (and the option of not
swapping) with the competition's cost model, and searches over work-order
assignments to minimise the expected total.
Layout
script.py submission entry point
batteryswap_example/features.py cut-time feature extraction
batteryswap_example/survival.py end-of-life model
batteryswap_example/tsbp.py trajectory-similarity features
batteryswap_example/costmodel.py cost model and schedule simulator
batteryswap_example/planner.py planner and search
batteryswap_example/planners/best.pickle fitted model
Running
BATTERYSWAP_DATASET_PATH=/path/to/dataset \
BATTERYSWAP_SPLITS=public,private \
python script.py
Writes submission.csv. This tree is inference-only; model fitting lives
outside the published repository.
- Downloads last month
- -