.

script/train.py

@@ -0,0 +1,67 @@
+import pandas as pd
+import json, os, sys, joblib
+import numpy as np
+from sklearn.ensemble import GradientBoostingRegressor
+from sklearn.model_selection import train_test_split
+
+def train(script_dir, working_dir, data_dir, train_count, val_count, margin):
+    features = pd.read_json(os.path.join(working_dir, 'features.json'))
+    measures = pd.read_csv(os.path.join(data_dir, 'measure.csv'))
+    
+    features['songno'] = features['songno'].astype(int)
+    measures['songno'] = measures['songno'].astype(int)
+    measures['diff'] = measures['diff'].replace('ura', 'edit')
+    
+    df = pd.merge(features, measures, on=['songno', 'diff'])
+    
+    with open(os.path.join(script_dir, 'factor.json'), 'r') as f:
+        weights = json.load(f)
+    for col in ['physical_density', 'stamina_requirement', 'pattern_complexity', 'rhythmic_complexity', 'reading_gimmick']:
+        df[col] = df[col] * weights.get(col, 1.0)
+
+    X_cols = ['physical_density', 'stamina_requirement', 'pattern_complexity', 'rhythmic_complexity', 'reading_gimmick']
+    model_path = os.path.join(working_dir, 'model.pkl')
+    model = joblib.load(model_path) if os.path.exists(model_path) else GradientBoostingRegressor(n_estimators=200, learning_rate=0.05, max_depth=3)
+
+    iteration = 1
+    while True:
+        # 3. 데이터 샘플링
+        df_sample = df.sample(n=int(train_count) + int(val_count))
+        train_df, val_df = train_test_split(df_sample, test_size=int(val_count))
+
+        X_train, y_train = train_df[X_cols], train_df['상수']
+        X_val, y_val = val_df[X_cols], val_df['상수']
+
+        # 4. 학습 (최대 10회)
+        for attempt in range(1, 11):
+            model.fit(X_train, y_train)
+            train_err = np.max(np.abs(np.clip(model.predict(X_train), 1.0, 12.0) - y_train))
+            print(f"Iteration {iteration} - Attempt {attempt} - Train Error: {train_err:.4f}")
+            if train_err <= float(margin): break
+            model.set_params(n_estimators=model.n_estimators + 50)
+
+        # 5. 검증
+        pred_val = np.clip(model.predict(X_val), 1.0, 12.0)
+        val_errors = np.abs(pred_val - y_val)
+        
+        # 6. 검증 실패 시 재시도
+        if np.any(val_errors > float(margin)):
+            print(f"Validation failed (max error: {np.max(val_errors):.4f}). Retrying...")
+            iteration += 1
+            continue
+            
+        val_result = pd.DataFrame({
+            'songno': val_df['songno'],
+            'difficulty': val_df['diff'],
+            'measure': y_val,
+            'predicted_measure': pred_val,
+            'error': val_errors
+        })
+        val_result.to_csv(os.path.join(working_dir, f'validate_result_{iteration}.csv'), index=False)
+        val_result.to_csv(os.path.join(working_dir, 'validate_result.csv'), index=False)
+        break
+
+    joblib.dump(model, model_path)
+
+if __name__ == "__main__":
+    train(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4], sys.argv[5], sys.argv[6])