From 8f63cf9f41bbdb8d55cd4679872d2b4ae2129324 Mon Sep 17 00:00:00 2001
From: YurenHao0426 <blackhao0426@gmail.com>
Date: Tue, 24 Feb 2026 08:40:49 +0000
Subject: 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.
---
 scripts/run_leiden.py | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)
 create mode 100644 scripts/run_leiden.py

(limited to 'scripts/run_leiden.py')

diff --git a/scripts/run_leiden.py b/scripts/run_leiden.py
new file mode 100644
index 0000000..375b6bb
--- /dev/null
+++ b/scripts/run_leiden.py
@@ -0,0 +1,62 @@
+"""Run Leiden community detection (modularity or CPM)."""
+
+import argparse
+import sys
+import os
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+
+import igraph as ig
+import leidenalg
+
+from config import NETWORKS, RESULTS_DIR, SEED
+from load_data import load_edge_list, build_igraph, save_communities
+
+
+def run_leiden(network_name, method_name, quality, resolution=None):
+    net = NETWORKS[network_name]
+    edge_df = load_edge_list(net["edge_tsv"])
+    g, name_to_idx, idx_to_name = build_igraph(edge_df)
+
+    print(f"  Graph: {g.vcount()} nodes, {g.ecount()} edges")
+
+    if quality == "modularity":
+        partition = leidenalg.find_partition(
+            g, leidenalg.ModularityVertexPartition, seed=SEED
+        )
+    elif quality == "cpm":
+        partition = leidenalg.find_partition(
+            g, leidenalg.CPMVertexPartition,
+            resolution_parameter=resolution, seed=SEED
+        )
+    else:
+        raise ValueError(f"Unknown quality function: {quality}")
+
+    print(f"  Found {len(partition)} communities, modularity={partition.modularity:.4f}")
+
+    # Convert partition to node2com dict
+    node2com = {}
+    for comm_id, members in enumerate(partition):
+        for idx in members:
+            node2com[idx_to_name[idx]] = str(comm_id)
+
+    out_path = os.path.join(RESULTS_DIR, network_name, method_name, "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)
+    parser.add_argument("--method", required=True,
+                        choices=["leiden_mod", "leiden_cpm_01", "leiden_cpm_001"])
+    args = parser.parse_args()
+
+    method_configs = {
+        "leiden_mod": {"quality": "modularity"},
+        "leiden_cpm_01": {"quality": "cpm", "resolution": 0.1},
+        "leiden_cpm_001": {"quality": "cpm", "resolution": 0.01},
+    }
+    cfg = method_configs[args.method]
+    print(f"Running {args.method} on {args.network}...")
+    run_leiden(args.network, args.method, **cfg)
-- 
cgit v1.2.3