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/load_data.py | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 74 insertions(+)
 create mode 100644 scripts/load_data.py

(limited to 'scripts/load_data.py')

diff --git a/scripts/load_data.py b/scripts/load_data.py
new file mode 100644
index 0000000..5a0362b
--- /dev/null
+++ b/scripts/load_data.py
@@ -0,0 +1,74 @@
+"""Shared data loading utilities for EC-SBM analysis."""
+
+import pandas as pd
+import numpy as np
+
+
+def load_edge_list(path):
+    """Load a tab-separated edge list (no header, two columns: node1, node2)."""
+    df = pd.read_csv(path, sep="\t", header=None, names=["src", "tgt"],
+                      dtype=str, comment="#")
+    return df
+
+
+def load_communities(path):
+    """Load a tab-separated community file (no header: node, community).
+    Returns dict {node_str: community_str}."""
+    node2com = {}
+    with open(path, "r") as f:
+        for line in f:
+            line = line.strip()
+            if not line or line.startswith("#"):
+                continue
+            parts = line.split("\t")
+            if len(parts) >= 2:
+                node2com[parts[0]] = parts[1]
+    return node2com
+
+
+def build_igraph(edge_df):
+    """Build an igraph Graph from an edge DataFrame.
+    Returns (graph, name_to_idx, idx_to_name)."""
+    import igraph as ig
+
+    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()}
+
+    src_ids = edge_df["src"].map(name_to_idx).values
+    tgt_ids = edge_df["tgt"].map(name_to_idx).values
+
+    n = len(all_nodes)
+    g = ig.Graph(n=n, edges=list(zip(src_ids, tgt_ids)), directed=False)
+    g.simplify()  # remove multi-edges and self-loops
+    return g, name_to_idx, idx_to_name
+
+
+def build_graphtool_graph(edge_df):
+    """Build a graph-tool Graph from an edge DataFrame.
+    Returns (graph, name_to_idx, idx_to_name)."""
+    import graph_tool.all as gt
+
+    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()}
+
+    src_ids = edge_df["src"].map(name_to_idx).values.astype(np.int64)
+    tgt_ids = edge_df["tgt"].map(name_to_idx).values.astype(np.int64)
+
+    n = len(all_nodes)
+    g = gt.Graph(directed=False)
+    g.add_vertex(n)
+    g.add_edge_list(np.column_stack([src_ids, tgt_ids]))
+    gt.remove_parallel_edges(g)
+    gt.remove_self_loops(g)
+    return g, name_to_idx, idx_to_name
+
+
+def save_communities(node2com, path):
+    """Save community assignments as TSV (node\tcommunity)."""
+    import os
+    os.makedirs(os.path.dirname(path), exist_ok=True)
+    with open(path, "w") as f:
+        for node, com in sorted(node2com.items(), key=lambda x: x[0]):
+            f.write(f"{node}\t{com}\n")
-- 
cgit v1.2.3