Pipeline example
Canonical pipeline
The main paper workflow is:
HARPS-N -> flux spectra -> temperature spectra -> planetary injections + CCF RV -> shell HDF5 -> HO/CV5 experiments
Reference experiment folders:
experiments/cnnShell_HO/experiments/cnnShell_CV/
Experiment scripts
Hold-out scripts (HO):
experiments/cnnShell_HO/cnnShellTemp.pyexperiments/cnnShell_HO/cnnShellFlux.pyexperiments/cnnShell_HO/cnnShellDetection.pyexperiments/cnnShell_hyperparameter_opt/cnnShellOptuna.py
Cross-validation scripts (CV5):
experiments/cnnShell_CV/cv5fold_cnn.pyexperiments/cnnShell_CV/cv_cnn_predict.pyexperiments/cnnShell_CV/cv_cnn_detection.pyexperiments/cnnShell_CV/join_chunks.py
Notebooks and analysis scripts
notebooks/ contains runnable Python analysis scripts:
notebooks/ccf_calculator.pynotebooks/shells_plots_on_the_fly.py
Shell Data
Shell datasets are generated by the scripts in data_generators/.
Detailed instructions for each generator script are available in data_generators/data_generator_README.md.
Full paper-scale shell set: about 17 GB.
One realization with temperature and flux: about 1.7 GB.
Single modality only: about 0.8 GB.
The lighter workflows are usually enough for diagnostics or training a single model.