docs

train/train_xgboost.py

@@ -6,6 +6,9 @@ import os
 import random
 import joblib
 import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
 
 from xgboost import XGBRegressor
 from sklearn.preprocessing import StandardScaler
@@ -177,7 +180,9 @@ def train_model(
 
             dataset.append((
                 features,
-                measure
+                measure,
+                songno,
+                diff
             ))
 
     # =====================================================
@@ -205,25 +210,29 @@ def train_model(
     ]
 
     X_train = np.array(
-        [x for x, _ in train_dataset],
+        [x for x, _, _, _ in train_dataset],
         dtype=np.float32
     )
 
     y_train = np.array(
-        [y for _, y in train_dataset],
+        [y for _, y, _, _ in train_dataset],
         dtype=np.float32
     )
 
     X_valid = np.array(
-        [x for x, _ in valid_dataset],
+        [x for x, _, _, _ in valid_dataset],
         dtype=np.float32
     )
 
     y_valid = np.array(
-        [y for _, y in valid_dataset],
+        [y for _, y, _, _ in valid_dataset],
         dtype=np.float32
     )
 
+    valid_info = [
+        (s, d) for _, _, s, d in valid_dataset
+    ]
+
     print(f"Train Size: {len(X_train)}")
     print(f"Valid Size: {len(X_valid)}")
     print(f"Feature Count: {len(feature_names)}")
@@ -314,6 +323,73 @@ def train_model(
     for name, score in pairs:
         print(f"{name:25} {score:.6f}")
 
+    # =====================================================
+    # save validate.json
+    # =====================================================
+
+    validate_details = []
+    for i in range(len(y_valid)):
+        actual = float(y_valid[i])
+        predicted = float(pred[i])
+        songno, diff = valid_info[i]
+        
+        validate_details.append({
+            "songno": songno,
+            "diff": diff,
+            "actual": actual,
+            "predicted": predicted,
+            "error": actual - predicted
+        })
+
+    # 에러 절댓값 기준 정렬
+    validate_details.sort(key=lambda x: abs(x["error"]), reverse=True)
+
+    validate_result = {
+        "summary": {
+            "total_compared": len(y_valid),
+            "average_absolute_error": float(mae),
+            "accuracy": float(accuracy),
+            "timestamp": "now",
+            "script_used": "train/train_xgboost.py"
+        },
+        "details": validate_details
+    }
+
+    validate_path = os.path.join(working_dir, "validate.json")
+    with open(validate_path, "w", encoding="utf-8") as f:
+        json.dump(validate_result, f, indent=2, ensure_ascii=False)
+
+    print(f"Validation result saved: {validate_path}")
+
+    # =====================================================
+    # save validate.png
+    # =====================================================
+    try:
+        plt.switch_backend('Agg') # GUI 없는 환경 대응
+        df_plot = pd.DataFrame(validate_details)
+        df_plot['abs_error'] = df_plot['error'].abs()
+        df_plot = df_plot.sort_values('abs_error', ascending=False).reset_index(drop=True)
+
+        plt.figure(figsize=(12, 6))
+        sns.scatterplot(data=df_plot, x=df_plot.index, y='abs_error', alpha=0.6, s=20, color='darkorange')
+        
+        plt.axhline(0.2, color='green', linestyle='--', linewidth=0.8, alpha=0.5, label='Target (0.2)')
+        plt.axhline(0.5, color='blue', linestyle='--', linewidth=0.8, alpha=0.5)
+        plt.axhline(1.0, color='red', linestyle='--', linewidth=0.8, alpha=0.5)
+        
+        plt.ylim(0, max(3.5, df_plot['abs_error'].max() + 0.5))
+        plt.title(f'Validation Absolute Error - {os.path.basename(working_dir)}', fontsize=14)
+        plt.xlabel('Samples (Sorted by Error Magnitude)', fontsize=12)
+        plt.ylabel('Absolute Error', fontsize=12)
+        plt.grid(True, axis='y', alpha=0.3)
+        
+        plot_path = os.path.join(working_dir, "validate.png")
+        plt.savefig(plot_path)
+        plt.close()
+        print(f"Validation plot saved: {plot_path}")
+    except Exception as e:
+        print(f"[WARN] Failed to create validation plot: {e}")
+
     # =====================================================
     # save
     # =====================================================
@@ -366,4 +442,4 @@ if __name__ == "__main__":
     train_model(
         args.workingDir,
         args.dataDir
-    )
+    )