initial commit

2026-03-02 20:55:36 +09:00
commit f224644b49
86 changed files with 1065250 additions and 0 deletions
@@ -0,0 +1,95 @@
+import os
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import random
+
+
+def read_dimacs(file):
+    idx = 0
+    with open(f"{folder}/{file}", "r") as f:
+        for line in f:
+            line = line.strip()
+            if line.startswith("c"):
+                continue
+            elif line.startswith("p"):
+                _, _, n, e = line.split()
+                edges = int(e)
+                data = [0] * edges
+            elif line.startswith("a"):
+                _, u, v, w = line.split()
+                data[idx] = int(w)
+                idx += 1
+    return data
+
+
+def visualize_weights(file):
+    data = read_dimacs(file)
+    sample = np.array(data)
+
+    save_folder = f"{res_folder}/{file}"
+    os.makedirs(save_folder, exist_ok=True)
+
+    plt.figure(figsize=(8, 5))
+    plt.hist(sample, bins=100)
+    plt.title("Edge Weight Distribution (Original Scale)")
+    plt.xlabel("Weight")
+    plt.ylabel("Frequency")
+    plt.tight_layout()
+    plt.savefig(f"{save_folder}/hist_original.png")
+    plt.close()
+
+    log_sample = np.log(sample[sample > 0])
+
+    plt.figure(figsize=(8, 5))
+    plt.hist(log_sample, bins=100)
+    plt.title("Log(Weight) Distribution")
+    plt.xlabel("log(Weight)")
+    plt.ylabel("Frequency")
+    plt.tight_layout()
+    plt.savefig(f"{save_folder}/hist_log.png")
+    plt.close()
+
+    plt.figure(figsize=(8, 5))
+    plt.hist(log_sample, bins=100, density=True)
+    plt.title("Log(Weight) Density")
+    plt.xlabel("log(Weight)")
+    plt.ylabel("Density")
+    plt.tight_layout()
+    plt.savefig(f"{save_folder}/hist_log_density.png")
+    plt.close()
+
+    return {
+        "file": file,
+        "edges": len(sample),
+        "mean": np.mean(sample),
+        "std": np.std(sample),
+        "min": np.min(sample),
+        "max": np.max(sample)
+    }
+
+folder = "experiments/real_data/data/dimacs_data"
+files = [
+    "USA-road-d.BAY.gr",
+    "USA-road-d.CAL.gr",
+    "USA-road-d.COL.gr",
+    "USA-road-d.CTR.gr",
+    "USA-road-d.E.gr",
+    "USA-road-d.FLA.gr",
+    "USA-road-d.LKS.gr",
+    "USA-road-d.NE.gr",
+    "USA-road-d.NW.gr",
+    "USA-road-d.NY.gr",
+    "USA-road-d.USA.gr",
+    "USA-road-d.W.gr"
+]
+
+res_folder = "results/real_data/derived/dimacs_graph_distribution"
+os.makedirs(res_folder, exist_ok=True)
+
+rows = []
+for file in files:
+    row = visualize_weights(file)
+    rows.append(row)
+df = pd.DataFrame(rows)
+df.to_csv(f"{res_folder}/distribution.csv", index=False)