Update initialize_system.py

initialize_system.py

@@ -188,90 +188,11 @@ def create_minimal_dataset():
         return False
 
 
-def run_initial_training():
-    """Run enhanced ensemble model training with LightGBM"""
-    log_step("Starting initial model training...")
-
-    try:
-        # Get all the paths
-        model_path = path_manager.get_model_file_path()
-        vectorizer_path = path_manager.get_vectorizer_path()
-        pipeline_path = path_manager.get_pipeline_path()
-
-        log_step(f"Model path: {model_path}")
-        log_step(f"Vectorizer path: {vectorizer_path}")
-        log_step(f"Pipeline path: {pipeline_path}")
 
-        # Check if model already exists
-        if pipeline_path.exists() or (model_path.exists() and vectorizer_path.exists()):
-            log_step("✅ Model files already exist, skipping training")
-            return True
-
-        # Import enhanced training components
-        import sys
-        sys.path.append('/app')
-        from model.train import EnhancedModelTrainer
-        
-        log_step("Using Enhanced Model Trainer with ensemble voting...")
-
-        # Create enhanced trainer with full ensemble configuration
-        trainer = EnhancedModelTrainer(
-            use_enhanced_features=True,  # Enable sentiment, readability, entities, linguistic features
-            enable_ensemble=True         # Enable LightGBM + Random Forest + Logistic Regression ensemble
-        )
-        
-        # Override paths to use the initialization system paths
-        trainer.data_path = path_manager.get_combined_dataset_path()
-        trainer.pipeline_path = pipeline_path
-        trainer.model_path = model_path
-        trainer.vectorizer_path = vectorizer_path
-        trainer.metadata_path = path_manager.get_metadata_path()
-        
-        log_step("Starting enhanced ensemble training (this may take several minutes)...")
-        
-        # Run the full enhanced training
-        success, message = trainer.train_model()
-        
-        if success:
-            log_step(f"✅ Enhanced ensemble training completed: {message}")
-            
-            # Verify pipeline was created
-            if pipeline_path.exists():
-                log_step(f"✅ Enhanced pipeline saved successfully to {pipeline_path}")
-                
-                # Test loading the pipeline
-                try:
-                    import joblib
-                    test_pipeline = joblib.load(pipeline_path)
-                    test_pred = test_pipeline.predict(["This is a test article"])
-                    log_step(f"✅ Enhanced pipeline verification successful: {test_pred}")
-                except Exception as e:
-                    log_step(f"⚠️ Enhanced pipeline verification failed: {e}")
-            else:
-                log_step(f"❌ Enhanced pipeline was not saved to {pipeline_path}")
-                return False
-                
-            return True
-        else:
-            log_step(f"❌ Enhanced ensemble training failed: {message}")
-            # Fall back to basic training if enhanced training fails
-            log_step("Falling back to basic training...")
-            return run_initial_training()
-            
-    except ImportError as e:
-        log_step(f"⚠️ Enhanced training components not available: {e}")
-        log_step("Falling back to basic training...")
-        return run_basic_training_fallback()
-    except Exception as e:
-        log_step(f"❌ Enhanced training failed: {str(e)}")
-        import traceback
-        log_step(f"❌ Traceback: {traceback.format_exc()}")
-        log_step("Falling back to basic training...")
-        return run_basic_training_fallback()
 
 
-def run_basic_training_fallback():
-    """Fallback to basic training if enhanced training fails"""
+def run_initial_training():
+    """Run basic model training"""
     log_step("Running basic training fallback...")
     
     try: