seung6lee/dijkstra-runtime-analysis
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

finish all analysis and upload data and results

Browse Source
This commit is contained in:
seung6lee
2026-04-26 10:33:02 +09:00
parent 9d76d82f5e
commit fc1386e572
376 changed files with 1059309 additions and 246 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codes/experiments/real_data/analysis/comparison.py
+92
View File
@@ -0,0 +1,92 @@
import pandas as pd
import os
import matplotlib.pyplot as plt
from sklearn.metrics import mean_squared_error, mean_absolute_error
raw_path = "results/real_data/raw/dimacs_s42.csv"
pred_path = "results/real_data/derived/distribution/dimacs_prediction_result/prediction.csv"
save_folder = "results/real_data/derived/comparison"
os.makedirs(save_folder, exist_ok=True)
raw = pd.read_csv(raw_path)
pred = pd.read_csv(pred_path)
# real: trial 평균
agg = (
raw.groupby("file")
.agg(
nodes = ("nodes", "first"),
density = ("density", "first"),
real_time = ("time", "mean"),
real_relax = ("relax_success","mean"),
)
.reset_index()
)
# prediction: file 기준으로 merge
pred_cols = pred[["file", "predict_time", "relax_success"]].rename(
columns={"relax_success": "pred_relax"}
)
merged = agg.merge(pred_cols, on="file", how="inner")
# 오차 계산
for real_col, pred_col, prefix in [
("real_time", "predict_time", "time"),
("real_relax", "pred_relax", "relax"),
]:
merged[f"{prefix}_abs_err"] = (merged[pred_col] - merged[real_col]).abs()
merged[f"{prefix}_rel_err"] = merged[f"{prefix}_abs_err"] / merged[real_col]
cols = [
"file", "nodes", "density",
"real_time", "predict_time", "time_abs_err", "time_rel_err",
"real_relax", "pred_relax", "relax_abs_err", "relax_rel_err",
]
merged[cols].to_csv(os.path.join(save_folder, "comparison.csv"), index=False)
print(merged[cols].to_string(index=False))
print(f"\nSaved → {save_folder}/comparison.csv")
for real_col, pred_col, label in [
("real_time", "predict_time", "time"),
("real_relax", "pred_relax", "relax_success"),
]:
y = merged[real_col].to_numpy()
y_hat = merged[pred_col].to_numpy()
ss_res = ((y - y_hat) ** 2).sum()
ss_tot = ((y - y.mean()) ** 2).sum()
r2 = 1 - ss_res / ss_tot
rmse = mean_squared_error(y, y_hat) ** 0.5
mae = mean_absolute_error(y, y_hat)
print(f"\n[{label}] R²={r2:.4f} RMSE={rmse:.4g} MAE={mae:.4g}")
# ── Plot ───────────────────────────────────────────────────────────────────────
fig, axes = plt.subplots(1, 2, figsize=(12, 5))
for ax, real_col, pred_col, label in [
(axes[0], "real_time", "predict_time", "Runtime [s]"),
(axes[1], "real_relax", "pred_relax", "Relax Success"),
]:
x = merged[real_col].to_numpy()
y = merged[pred_col].to_numpy()
mn, mx = min(x.min(), y.min()), max(x.max(), y.max())
ax.scatter(x, y, s=60, zorder=3)
for _, row in merged.iterrows():
ax.annotate(
row["file"].replace("USA-road-d.", "").replace(".gr", ""),
(row[real_col], row[pred_col]),
fontsize=6, textcoords="offset points", xytext=(4, 2)
)
ax.plot([mn, mx], [mn, mx], color="red", linestyle="--", linewidth=1.2, label="y = x")
ax.set_xlabel(f"Real {label}")
ax.set_ylabel(f"Predicted {label}")
ax.set_title(f"Predicted vs Real — {label}")
ax.legend(fontsize=8)
ax.grid(True, alpha=0.4)
fig.tight_layout()
fig.savefig(os.path.join(save_folder, "comparison_plot.png"), dpi=300)
plt.close(fig)
print(f"Saved → {save_folder}/comparison_plot.png")
codes/experiments/real_data/analysis/dimacs_prediction.py
+78
View File
@@ -0,0 +1,78 @@
from experiments.synthetic_data.analysis.processing_time_analysis import mean_l
from experiments.synthetic_data.analysis.processing_time_analysis import regression_k3
from experiments.synthetic_data.analysis.processing_time_analysis import regression_m
from experiments.synthetic_data.analysis.call_number_analysis import (
nonlinear_regression,
)
import numpy as np
import pandas as pd
import os
def k3(V):
return k3_a * np.exp(-k3_b * V) + k3_c
def m(V):
return m_a * np.log2(V) + m_b
def relax_success(E, S, AVG_DEG):
relax_attempts = E
relax_success_ratio = (rs_a * np.log(S) + rs_b) * AVG_DEG**rs_c
return relax_attempts * relax_success_ratio
def runtime_predict(V, D, S):
E = V * (V - 1) * D
AVG_DEG = (V - 1) * D
if AVG_DEG < 1:
return False, False
runtime = V * l + E * k3(V) + relax_success(E, S, AVG_DEG) * m(V)
print(relax_success(E, S, AVG_DEG))
# runtime_eq = f"[V * {l}] + [E * {k3_a} * exp(-{k3_b} * V) + {k3_c}] + [E * ({rs_a} * log(S) + {rs_b}) * AVG_DEG ** {rs_c} * {m_a} * log_2(V) + {m_b}]"
return runtime, relax_success(E, S, AVG_DEG)
l = mean_l()
k3_a, k3_b, k3_c = regression_k3()
m_a, m_b = regression_m()
rs_a, rs_b, rs_c = nonlinear_regression()
csv_file = "results/real_data/derived/dimacs_graph_distribution/distribution.csv"
save_folder = f"results/real_data/derived/{os.path.splitext(os.path.basename(csv_file))[0]}/dimacs_prediction_result"
os.makedirs(save_folder, exist_ok=True)
df = pd.read_csv(csv_file)
records = []
for row in df.itertuples():
nodes = row.nodes
density = row.density
sigma = np.sqrt(np.log((row.std / row.mean) ** 2 + 1))
pred_time, pred_relax_success = runtime_predict(nodes, density, sigma)
if pred_time is False:
continue
records.append(
{
"file": row.file,
"nodes": nodes,
"density": density,
"sigma": sigma,
"predict_time": pred_time,
"relax_success": pred_relax_success,
}
)
print(f"finished {row.file}")
result = pd.DataFrame(records)
out_path = os.path.join(save_folder, "prediction.csv")
result.to_csv(out_path, index=False)
print(f"Saved {len(result)} rows → {out_path}")
codes/experiments/real_data/analysis/graph_distribution.py
+11 -11
View File
@@ -102,18 +102,18 @@ def visualize_weights(file):
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.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"
"USA-road-d.W.gr"
]
res_folder = "results/real_data/derived/dimacs_graph_distribution"
codes/experiments/real_data/run/dimacs_run.py
+54 -57
View File
@@ -1,75 +1,73 @@
import os
import gc
import time
import pandas as pd
import numpy as np
import random
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 done_trials(out_path, file):
if not os.path.exists(out_path):
return set()
df = pd.read_csv(out_path, usecols=["file", "trial"])
return set(df[df["file"] == file]["trial"].tolist())
def run_test(
folder,
files,
trials,
base_seed
base_seed,
out_path,
trials=10,
):
rows = []
timer = time.perf_counter
rng = np.random.default_rng(base_seed)
INF = float('inf')
write_header = not os.path.exists(out_path)
for file in files:
completed = done_trials(out_path, file)
remaining = [t for t in range(1, trials + 1) if t not in completed]
if not remaining:
print(f"[SKIP] {file} (all {trials} trials done)")
continue
print(f"[LOAD] {file} (completed: {sorted(completed)}, remaining: {remaining})")
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
for trial in remaining:
print(f" trial {trial}/{trials}")
random.seed(base_seed + trial)
start = random.randint(1, nodes)
bin_heap = BinHeap(nodes)
st = timer()
dist, stats = heap_dijkstra(nodes, adj, bin_heap, start, end)
stats = heap_dijkstra(nodes, adj, bin_heap, start)
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,
}
)
row = pd.DataFrame([{
"file": file,
"nodes": nodes,
"density": density,
"start": start,
"time": et - st,
"trial": trial,
"extract_min_calls": stats.extract_min_calls,
"relax_attempts": stats.relax_attempts,
"relax_success": stats.relax_success,
}])
row.to_csv(out_path, mode="a", header=write_header, index=False)
write_header = False
del bin_heap
gc.collect()
del adj
gc.collect()
print(f"[DONE] {file}")
df = pd.DataFrame(rows)
return df
# Settings
folder = "experiments/real_data/data/dimacs_data"
@@ -87,16 +85,15 @@ files = [
"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)
out_path = f"{save_folder}/dimacs_s{base_seed}.csv"
run_test(
folder=folder,
files=files,
base_seed=base_seed,
out_path=out_path,
)