initial commit

2026-03-02 20:55:36 +09:00
commit f224644b49
86 changed files with 1065250 additions and 0 deletions
@@ -0,0 +1,149 @@
+import time
+import pandas as pd
+import numpy as np
+from tqdm import tqdm
+import datetime
+import json
+import os
+
+from experiments.synthetic_data.graph_generators.outdegree_graph_generator import outdegree_generate_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(
+    nodes_li,
+    densities,
+    stds,
+    trials,
+    mean_dist,
+    start,
+    end,
+    base_seed
+):
+    timer = time.perf_counter
+    file_exists = False
+    INF = float('inf')
+
+    total_jobs = (
+        len(nodes_li) *
+        len(densities) *
+        len(stds) *
+        trials
+    )
+
+    with tqdm(total=total_jobs) as pbar:
+        for nodes in nodes_li:
+            rows = []
+
+            for density in densities:
+                for std in stds:
+                    sigma = np.sqrt(np.log((std / mean_dist)**2 + 1))
+                    mu = np.log(mean_dist) - (sigma**2) / 2
+                    distribution = ('lognormal', (mu, sigma))
+
+                    for trial in range(1, trials + 1):
+                        seed = (base_seed * 1_000_003) ^ (nodes * 9176) ^ int(density * 1e9) ^ int(sigma * 1e6) ^ trial
+                        seed &= 0xFFFFFFFF
+
+                        adj = outdegree_generate_graph(
+                            NODES=nodes,
+                            DENSITY=density,
+                            DISTRIBUTION=distribution,
+                            SEED=seed
+                        )
+
+                        bin_heap = BinHeap(nodes)
+                        st = timer()
+                        dist, stats = heap_dijkstra(nodes, adj, bin_heap, start, end)
+                        et = timer()
+                        rows.append(
+                            {
+                                "nodes": nodes,
+                                "density": density,
+                                "std": std,
+                                "sigma": sigma,
+                                "trial": trial,
+                                "seed": seed,
+                                "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(
+                            {
+                                "nodes": nodes,
+                                "density": density,
+                                "std": std,
+                                "sigma": sigma,
+                                "trial": trial,
+                                "seed": seed,
+                                "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,
+                            }
+                        )
+
+                        pbar.update(1)
+
+            df_nodes = pd.DataFrame(rows)
+            df_nodes.to_csv(
+                csv_file,
+                mode='a',
+                header=not file_exists,
+                index=False
+            )
+            file_exists = True
+            print(f"=== SAVED nodes = {nodes} ({len(df_nodes)} rows) ===")
+    return
+
+# Settings
+nodes_li = [2000, 4000, 8000, 16000]
+densities = [0.00015, 0.0003, 0.0006, 0.0012, 0.0024, 0.0048, 0.0096, 0.0192, 0.0384]
+stds = [1000, 1500, 2000, 3000, 4000, 6000, 8000, 12000, 16000]
+trials = 400
+mean_dist = 3000
+start = 0
+end = 1
+base_seed = 42
+
+save_folder = "results/synthetic_data/raw"
+os.makedirs(save_folder, exist_ok=True)
+timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
+csv_file = f"{save_folder}/{timestamp}.csv"
+config_file = f"{save_folder}/{timestamp}.json"
+
+config = {
+    "nodes_li": nodes_li,
+    "densities": densities,
+    "stds": stds,
+    "trials": trials,
+    "mean_dist": mean_dist,
+    "start": start,
+    "end": end,
+    "base_seed": base_seed,
+}
+with open(config_file, "w") as f:
+    json.dump(config, f, indent=4)
+
+df = run_test(
+    nodes_li = nodes_li,
+    densities = densities,
+    stds = stds,
+    trials = trials,
+    mean_dist = mean_dist,
+    start = start,
+    end = end,
+    base_seed = base_seed
+)