initial commit

codes/experiments/real_data/analysis/graph_distribution.py

@@ -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)

codes/experiments/real_data/graph_converters/dimacs_graph_converter.py

@@ -0,0 +1,21 @@
+def dimacs_convert_graph(filename):
+    with open(filename, 'r') as f:
+        for line in f:
+            line = line.strip()
+
+            if line.startswith('c'):
+                continue
+
+            elif line.startswith('p'):
+                _, _, n, e = line.split()
+                nodes = int(n)
+                edges = int(e)
+                adj = [[] for _ in range(nodes + 1)]
+            
+            elif line.startswith('a'):
+                _, u, v, w = line.split()
+                u, v, w = int(u) - 1, int(v) - 1, int(w)
+                
+                adj[u].append((v, w))
+    
+    return nodes, adj

codes/experiments/real_data/run/dimacs_run.py

@@ -0,0 +1,102 @@
+import os
+import time
+import pandas as pd
+import numpy as np
+
+from experiments.real_data.graph_converters.dimacs_graph_converter import dimacs_convert_graph
+from core.dijkstra.heap_dijkstra import heap_dijkstra
+from core.heaps.binary_heap import BinHeap
+from core.heaps.fibonacci_heap import FiboHeap
+
+def run_test(
+    folder,
+    files,
+    trials,
+    base_seed
+):
+    rows = []
+    timer = time.perf_counter
+    rng = np.random.default_rng(base_seed)
+    INF = float('inf')
+
+    for file in files:
+        nodes, adj = dimacs_convert_graph(f'{folder}/{file}')
+        density = len(adj) / (nodes * (nodes - 1))
+
+        for trial in range(1, trials + 1):
+            start, end = rng.choice(nodes, size=2, replace=False) + 1
+
+            bin_heap = BinHeap(nodes)
+            st = timer()
+            dist, stats = heap_dijkstra(nodes, adj, bin_heap, start, end)
+            et = timer()
+            rows.append(
+                {
+                    "file": file,
+                    "nodes": nodes,
+                    "density": density,
+                    "trial": trial,
+                    "start": start,
+                    "end": end,
+                    "time": et - st,
+                    "algorithm": "binary",
+                    "reached": dist != INF,
+                    "extract_min_calls": stats.extract_min_calls,
+                    "relax_attempts": stats.relax_attempts,
+                    "relax_success": stats.relax_success,
+                }
+            )
+
+            fibo_heap = FiboHeap(nodes)
+            st = timer()
+            dist, stats = heap_dijkstra(nodes, adj, fibo_heap, start, end)
+            et = timer()
+            rows.append(
+                {
+                    "file": file,
+                    "nodes": nodes,
+                    "density": density,
+                    "trial": trial,
+                    "start": start,
+                    "end": end,
+                    "time": et - st,
+                    "algorithm": "fibonacci",
+                    "reached": dist != INF,
+                    "extract_min_calls": stats.extract_min_calls,
+                    "relax_attempts": stats.relax_attempts,
+                    "relax_success": stats.relax_success,
+                }
+            )
+
+    df = pd.DataFrame(rows)
+    return df
+
+# Settings
+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"
+]
+trials = 200
+base_seed = 42
+
+df = run_test(
+    folder=folder,
+    files=files,
+    trials=trials,
+    base_seed=base_seed
+)
+
+save_folder = "results/real_data/raw"
+os.makedirs(save_folder, exist_ok=True)
+df.to_csv(f"{save_folder}/dimacs_t{trials}_s{base_seed}.csv", index=False)