finish all analysis and upload data and results

codes/experiments/synthetic_data/analysis/prediction.py

@@ -0,0 +1,123 @@
+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
+import matplotlib.pyplot as plt
+from sklearn.metrics import mean_squared_error, mean_absolute_error
+
+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
+    
+    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
+    
+
+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/synthetic_data/raw/20260421_031740.csv"
+save_folder = f"results/synthetic_data/derived/{os.path.splitext(os.path.basename(csv_file))[0]}/prediction_result"
+os.makedirs(save_folder, exist_ok=True)
+
+df = pd.read_csv(csv_file)
+df = df[df["algorithm"] == "binary"].copy()
+
+records = []
+for row in df.itertuples():
+    predicted = runtime_predict(row.nodes, row.density, row.sigma)
+    if predicted is False:
+        continue
+    records.append({
+        "nodes":        row.nodes,
+        "density":      row.density,
+        "sigma":        row.sigma,
+        "trial":        row.trial,
+        "real_time":    row.time,
+        "predict_time": predicted,
+        "abs_error": abs(row.time - predicted),
+        "rel_error": abs(row.time - predicted) / row.time,
+    })
+
+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}")
+
+real = result["real_time"].to_numpy()
+pred = result["predict_time"].to_numpy()
+
+ss_res = np.sum((real - pred) ** 2)
+ss_tot = np.sum((real - real.mean()) ** 2)
+r2 = 1 - ss_res / ss_tot
+print(f"R² = {r2:.4f}")
+
+rmse = np.sqrt(mean_squared_error(real, pred))
+mae  = mean_absolute_error(real, pred)
+
+print(f"RMSE: {rmse:.4f} s")  # 평균 제곱 오차의 제곱근
+print(f"MAE:  {mae:.4f} s")   # 평균 절대 오차
+
+mn, mx = min(real.min(), pred.min()), max(real.max(), pred.max())
+
+fig, ax = plt.subplots(figsize=(6, 6))
+ax.scatter(real, pred, s=5, alpha=0.3, color="steelblue")
+ax.plot([mn, mx], [mn, mx], color="red", linewidth=1.5, linestyle="--", label="y = x")
+ax.set_xlabel("real_time [s]")
+ax.set_ylabel("predict_time [s]")
+ax.set_title(f"Predicted vs Real Runtime  R²={r2:.4f}")
+ax.legend(fontsize=9)
+ax.grid(True, alpha=0.4)
+fig.tight_layout()
+fig.savefig(os.path.join(save_folder, "predicted_vs_real.png"), dpi=300)
+plt.close(fig)
+print(f"Saved: {save_folder}/predicted_vs_real.png")
+
+# rel_error distribution
+rel_err = result["rel_error"].to_numpy()
+
+fig, axes = plt.subplots(1, 2, figsize=(12, 5))
+
+# histogram
+axes[0].hist(rel_err, bins=50, color="steelblue", edgecolor="none", alpha=0.8)
+axes[0].axvline(np.median(rel_err), color="red",    linestyle="--", linewidth=1.5, label=f"median={np.median(rel_err):.3f}")
+axes[0].axvline(np.mean(rel_err),   color="orange", linestyle="--", linewidth=1.5, label=f"mean={np.mean(rel_err):.3f}")
+axes[0].set_xlabel("rel_error")
+axes[0].set_ylabel("count")
+axes[0].set_title("Relative Error Distribution")
+axes[0].legend(fontsize=9)
+axes[0].grid(True, alpha=0.4)
+
+# rel_error vs real_time
+axes[1].scatter(real, rel_err, s=5, alpha=0.3, color="steelblue")
+axes[1].set_xlabel("real_time [s]")
+axes[1].set_ylabel("rel_error")
+axes[1].set_title("Relative Error vs Real Time")
+axes[1].grid(True, alpha=0.4)
+
+fig.tight_layout()
+fig.savefig(os.path.join(save_folder, "rel_error_dist.png"), dpi=300)
+plt.close(fig)
+print(f"Saved: {save_folder}/rel_error_dist.png")