Pipeline Scripts

data_preprocess.py

Loading networks, generating sub-samples, exporting all to uniform dataset.

Datasets are saved in /data/processed/networks: subsamples_edge_lists.csv subsamples_metadata.csv

topology_features.py + topology_features.R

Extract topological features for each network (and subsample) from previous step.

results are saved in /data/processed/features: features_R.csv features_py.csv

results.py

Running predictive models needed for the paper and exporting the results to /results/ for further processing with R.

results_preprocessing.Rmd

Loading results from previous step and generating minimalistic datasets, so each plot/table will have its own dataset.

results_figs.Rmd

Takes the processed results from last step and generate plots for the paper.