25-04-2025, 03:46 AM
(This post was last modified: 25-04-2025, 04:38 AM by RadioFM.
Edit Reason: added edit clause, formatting
)
EDIT: Your deterministic mapping from Lunar_Angle to Phase in generate_lunar_angles_seed.py makes the Lunar_Angle a trivial predictor to Phase - is Lunar_Angle a feature fed into your ML model?
Regardless of the previous EDIT, would you mind answering these questions?
Regardless of the previous EDIT, would you mind answering these questions?
- The sweet spot is 4 phases then - any other number just doesn't yield such good results?
- How's the performance with a single decision tree instead of random forest? Unless I'm doing something wrong, scores seem to be good
- You're splitting the data 75% train vs 25% test on the shuffle/ablation/etc validation step w/ the same seed as you did back on training, correct?


