a_data_selection.py
- reads the full MC data
- drops some rows
- replaces NaNs with an extreme value
- selects columns according to
a_data_selection_features.csv
- 90% reduction in file size
- → subsequent analysis is faster
- outputs to
build_large/data.csv
b_prepare_data.py
- drops energies outside of a certain range
- discretizes the energies
- applies
StandardScaler
- does not write to disk; instead, it's intended to be invoked by other Python files
c_corn.py
- provides the CORN classifier as a sklearn classifier
ca_corn_functions.py
- provides helper functions like
loss
andproba_from_logits
- provides helper functions like
c_dsea.py
- …
d_evaluate.py
- evaluates the classifier's performance
da_evaluate_plots.py
- outputs plots to
build/plots
- outputs plots to
x_config.py
- defines the configuration for the experiment
x_run.py
- runs the experiment
- MAE → EMD (Wasserstein distance)?
- hyperparameter search?
- plotly
- for passing interactive plots wandb.ai
AttributeError: module 'setuptools._distutils' has no attribute 'version'
pip install setuptools==59.5.0