See feature_pipeline.py
and prediction_pipeline.py
for usage.
$ 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.
- Add a Tucker decomposition model
- PoE?
- Manually remove regions from LFPs
- Make some pre-zipped features and labels
- Add random seeds?
- Movie app
from joblib import Parallel, delayed
- mouse-specific intercepts
- SMC for sampling label sequence posterior
- Mouse-specific normalization options
- Group Lasso?
- Early stopping in
GridSearchCV
[b,f,r,r]
vs[b,r,r,f]
shapes- automatic groups?
- Save smoothed labels
- More agressive normalization options