whygrossman / lpne

LFP feature extraction and prediction pipeline

LPNE feature extraction and classification pipeline

Code for preprocessing and building models with local field potentials

See feature_pipeline.py and prediction_pipeline.py for usage.

Installation

$ git clone https://github.com/carlson-lab/lpne.git
$ cd lpne
$ pip install .
$ pytest test # run tests
$ cd docs
$ make html # build docs

Then see docs/build/html/index.html for the docs.

Dependencies

• Python3 (3.7+)
• PyTorch 1.11+
• Black
• MoviePy (optional)

TO DO

9. Add a Tucker decomposition model
10. PoE?
11. Manually remove regions from LFPs
12. Make some pre-zipped features and labels
13. Add random seeds?
14. Movie app
15. from joblib import Parallel, delayed
16. mouse-specific intercepts
17. SMC for sampling label sequence posterior
18. Mouse-specific normalization options
19. Group Lasso?
20. Early stopping in GridSearchCV
21. [b,f,r,r] vs [b,r,r,f] shapes
22. automatic groups?
23. Save smoothed labels
24. More agressive normalization options