initial commit

codes/experiments/synthetic_data/analysis/call_relationship.py

@@ -0,0 +1,50 @@
+import os
+import pandas as pd
+import matplotlib.pyplot as plt
+
+csv_file = "results/synthetic_data/raw/20260302_183202.csv"
+save_folder = f"results/synthetic_data/derived/{os.path.splitext(os.path.basename(csv_file))[0]}"
+os.makedirs(save_folder, exist_ok=True)
+
+df = pd.read_csv(csv_file)
+df = df[df["algorithm"] == "binary"].copy()
+df["relax_success_ratio"] = df["relax_success"] / df["relax_attempts"]
+
+# N vs extract_min_calls
+grouped = df.groupby("nodes")["extract_min_calls"].mean()
+
+plt.figure(figsize=(6,4))
+plt.plot(grouped.index, grouped.values, marker='o')
+plt.xlabel("N (nodes)")
+plt.ylabel("Average extract_min_calls")
+plt.title("Nodes vs Extract-Min Calls")
+plt.grid(True)
+plt.tight_layout()
+plt.savefig(f"{save_folder}/N_vs_extract_min.png", dpi=300)
+plt.close()
+
+# Density vs relax_attempts
+grouped = df.groupby("density")["relax_attempts"].mean()
+
+plt.figure(figsize=(6,4))
+plt.plot(grouped.index, grouped.values, marker='o')
+plt.xlabel("Density")
+plt.ylabel("Average relax_attempts")
+plt.title("Density vs Relax Attempts")
+plt.grid(True)
+plt.tight_layout()
+plt.savefig(f"{save_folder}/density_vs_relax_attempts.png", dpi=300)
+plt.close()
+
+# Sigma vs relax_success_ratio
+grouped = df.groupby("sigma")["relax_success_ratio"].mean()
+
+plt.figure(figsize=(6,4))
+plt.plot(grouped.index, grouped.values, marker='o')
+plt.xlabel("Sigma (lognormal)")
+plt.ylabel("Relax Success Ratio")
+plt.title("Sigma vs Relax Success Ratio")
+plt.grid(True)
+plt.tight_layout()
+plt.savefig(f"{save_folder}/sigma_vs_relax_ratio.png", dpi=300)
+plt.close()

codes/experiments/synthetic_data/analysis/regression.py

@@ -0,0 +1,48 @@
+import numpy as np
+import pandas as pd
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import r2_score
+
+def fit_op_cost_functional(df, algo):
+    sub = df[(df["algorithm"] == algo) & (df["reached"] == True)].copy()
+
+    sub["logN"] = np.log(sub["nodes"])
+    sub = sub.rename(columns={"relax_success":"decrease_key_calls",
+                              "nodes":"add_calls"})
+
+    if algo == "binary":
+        sub["f_extract"] = sub["extract_min_calls"] * sub["logN"]
+        sub["f_decrease"] = sub["decrease_key_calls"] * sub["logN"]
+    else:  # fibonacci
+        sub["f_extract"] = sub["extract_min_calls"] * sub["logN"]
+        sub["f_decrease"] = sub["decrease_key_calls"]
+
+    X = sub[["add_calls", "f_extract", "relax_attempts", "f_decrease"]].to_numpy()
+    y = sub["time"].to_numpy()
+
+    model = LinearRegression()
+    model.fit(X, y)
+
+    y_pred = model.predict(X)
+    r2 = r2_score(y, y_pred)
+
+    return {
+        "algo": algo,
+        "intercept": model.intercept_,
+        "coef_add": model.coef_[0],
+        "coef_extract": model.coef_[1],
+        "coef_relax": model.coef_[2],
+        "coef_decrease": model.coef_[3],
+        "r2": r2,
+        "n_samples": len(sub)
+    }
+
+def op_cost_functional_analysis(df):
+    return pd.DataFrame([
+        fit_op_cost_functional(df, "binary"),
+        fit_op_cost_functional(df, "fibonacci")
+    ])
+
+df = pd.read_csv("results/synthetic_data/raw/20260302_183202.csv")
+summary = op_cost_functional_analysis(df)
+print(summary)

codes/experiments/synthetic_data/analysis/speed_ratio.py

@@ -0,0 +1,38 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import os
+
+csv_file = "results/synthetic_data/raw/20260302_183202.csv"
+save_folder = f"results/synthetic_data/derived/{os.path.splitext(os.path.basename(csv_file))[0]}"
+os.makedirs(save_folder, exist_ok=True)
+
+df = pd.read_csv(csv_file)
+# df = df[df["reached"] == True].copy()
+
+key_cols = ["nodes", "density", "std", "sigma", "trial", "seed"]
+
+pivot_time = (
+    df.pivot_table(index=key_cols, columns="algorithm", values="time", aggfunc="mean")
+    .reset_index()
+)
+pivot_time["speed_ratio"] = pivot_time["binary"] / pivot_time["fibonacci"]
+
+# print((pivot_time["speed_ratio"] > 1).sum())
+# print((pivot_time["speed_ratio"] < 1).sum())
+
+relax = (
+    df[df["algorithm"] == "binary"][key_cols + ["relax_success"]]
+)
+
+merged = pivot_time.merge(relax, on=key_cols, how="left")
+
+plt.figure(figsize=(6, 4))
+plt.scatter(merged["relax_success"], merged["speed_ratio"], marker=".")
+plt.axhline(y=1.0, color='red', linestyle='--')
+plt.xlabel("decrease_key (binary)")
+plt.ylabel("speed_ratio (binary / fibonacci)")
+plt.title("decrease_key vs speed_ratio")
+plt.grid(True)
+plt.tight_layout()
+plt.savefig(f"{save_folder}/decrease_key_vs_speed_ratio.png", dpi=300)
+plt.close()