penyesuaian

services/train_service.py

@@ -7,7 +7,7 @@ import joblib
 from sklearn.svm import SVC
 from sklearn.preprocessing import StandardScaler
 from sklearn.pipeline import Pipeline
-from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.model_selection import train_test_split
 from skimage.feature import local_binary_pattern
 
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
@@ -17,6 +17,9 @@ from utils.lbp_features import (
     augmentasi_lbp, preprocess_face, FACE_SIZE, LBP_SCALES
 )
 
+OPTIMAL_C = 20
+OPTIMAL_GAMMA = 0.1
+
 
 def load_images(dataset_path):
     valid_ext = ('.jpg', '.jpeg', '.png')
@@ -111,26 +114,8 @@ def train_model(base_datasets_path, model_output_path, approved_user_ids=None):
         X, y, test_size=0.2, random_state=42, stratify=y
     )
 
-    param_grid = {
-        'svm__C': [0.1, 1, 10, 20],
-        'svm__gamma': ['scale', 'auto', 0.01, 0.001, 0.1]
-    }
-
-    pipe_search = Pipeline([
-        ('scaler', StandardScaler()),
-        ('svm', SVC(kernel='rbf', probability=False))
-    ])
-
-    grid = GridSearchCV(
-        pipe_search, param_grid,
-        cv=5, scoring='accuracy',
-        refit=False, return_train_score=True, verbose=0
-    )
-    grid.fit(X_train, y_train)
-
-    best_C = grid.best_params_['svm__C']
-    best_gamma = grid.best_params_['svm__gamma']
-    cv_score = grid.best_score_
+    best_C = OPTIMAL_C
+    best_gamma = OPTIMAL_GAMMA
 
     model_final = Pipeline([
         ('scaler', StandardScaler()),
@@ -158,8 +143,8 @@ def train_model(base_datasets_path, model_output_path, approved_user_ids=None):
         "user_ids": list(label_map.keys()),
         "best_C": best_C,
         "best_gamma": str(best_gamma),
-        "cv_score": round(cv_score, 4),
         "test_accuracy": round(test_acc, 4),
+        "source": "Ablasi Jalur 2 (GridSearchCV 5-Fold)",
     }
     with open(temp_labels_file, 'w') as f:
         json.dump(labels_data, f, indent=2)
@@ -177,7 +162,6 @@ def train_model(base_datasets_path, model_output_path, approved_user_ids=None):
         "feature_dimension": int(X.shape[1]),
         "best_C": best_C,
         "best_gamma": str(best_gamma),
-        "cv_score": round(cv_score, 4),
         "test_accuracy": round(test_acc, 4),
         "classes": list(model_final.named_steps['svm'].classes_),
         "model_path": model_file,