How ayoushmanb/hypergraph_subgraph works
Project type and purpose
• The goal is to run simulation experiments, apply testing routines on real-world hypergraph data, compute summary statistics, and generate publication-ready figures.
File structure
• Top-level artifacts:
• hypergraph_subgraph.Rproj (RStudio project)
• README.md
• .gitignore
• Directories by function:
• real_data: holds input RData files and real-data testing scripts
– data_collection: raw RData splits (train/test/all) for multiple datasets (emi, jasa, jcgs, movie)
– hypergraph_testing: R scripts that test two-star and type-2 clustering on real data
– sparse_graphon_testing: scripts for sparse-graphon based tests
– summary-stat-supp.R: summary statistics on real data
• simulation: scripts to run various simulation experiments (colorless triangles, type-2/3 clustering, two-stars)
• figures: output PDFs of histograms, density plots, hypothesis-test images
• No “frontend/backend”—it’s a data pipeline. Primary architectural choice: modular R scripts organized by stage (data collection, simulation, testing, visualization).