EC-SBM community detection analysis: full pipeline and writeup

Implement community detection on 3 EC-SBM networks (polblogs, topology,
internet_as) using 5 methods (Leiden-Mod, Leiden-CPM at 0.1 and 0.01,
Infomap, graph-tool SBM). Compute AMI/ARI/NMI accuracy, cluster statistics,
and generate figures and LaTeX report.

1 files changed, 61 insertions, 0 deletions

diff --git a/scripts/run_infomap.py b/scripts/run_infomap.py
new file mode 100644
index 0000000..e53c77d
--- /dev/null
+++ b/scripts/run_infomap.py
@@ -0,0 +1,61 @@
+"""Run Infomap community detection."""
+
+import argparse
+import sys
+import os
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+
+import infomap
+
+from config import NETWORKS, RESULTS_DIR, SEED
+from load_data import load_edge_list, save_communities
+
+
+def run_infomap(network_name):
+    net = NETWORKS[network_name]
+    edge_df = load_edge_list(net["edge_tsv"])
+
+    # Build node mapping
+    import pandas as pd
+    all_nodes = pd.unique(edge_df[["src", "tgt"]].values.ravel("K"))
+    name_to_idx = {name: i for i, name in enumerate(all_nodes)}
+    idx_to_name = {i: name for name, i in name_to_idx.items()}
+
+    n = len(all_nodes)
+    print(f"  Network: {n} nodes, {len(edge_df)} edges")
+
+    im = infomap.Infomap("--two-level --flow-model undirected --seed {}".format(SEED))
+
+    for _, row in edge_df.iterrows():
+        im.add_link(name_to_idx[row["src"]], name_to_idx[row["tgt"]])
+
+    im.run()
+
+    print(f"  Found {im.num_top_modules} top modules, codelength={im.codelength:.4f}")
+
+    # Extract communities
+    node2com = {}
+    for node_id in im.tree:
+        if node_id.is_leaf:
+            node2com[idx_to_name[node_id.node_id]] = str(node_id.module_id)
+
+    # Assign singleton communities to any nodes not in infomap output
+    max_com = max(int(c) for c in node2com.values()) + 1
+    for idx in range(n):
+        name = idx_to_name[idx]
+        if name not in node2com:
+            node2com[name] = str(max_com)
+            max_com += 1
+
+    out_path = os.path.join(RESULTS_DIR, network_name, "infomap", "com.tsv")
+    save_communities(node2com, out_path)
+    print(f"  Saved to {out_path}")
+    return node2com
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--network", required=True)
+    args = parser.parse_args()
+    print(f"Running Infomap on {args.network}...")
+    run_infomap(args.network)