Update app.py

app.py

@@ -1,84 +1,30 @@
 import gradio as gr
 import pandas as pd
-import pickle
+import os
 import sklearn
-from sklearn.ensemble import RandomForestRegressor
-
-# Загружаем сохраненную модель и feature names
-# def load_model():
-#     try:
-#         with open('car_price_pipeline.pkl', 'rb') as f:
-#             pipeline = pickle.load(f)
-#         with open('feature_names.pkl', 'rb') as f:
-#             feature_names = pickle.load(f)
-#         return pipeline, feature_names
-#     except Exception as e:
-#         print(f"Error loading model: {e}")
-#         return None, None
-
-# def load_model():
-#     try:
-#         pipeline = joblib.load('car_price_pipeline.pkl')
-#         with open('feature_names.pkl', 'rb') as f:
-#             feature_names = pickle.load(f)
-#         return pipeline, feature_names
-#     except Exception as e:
-#         print(f"Error loading model: {e}")
-#         return None, None
+import pickle
 
-def load_model():
-    try:
-        import joblib
-        
-        model_path = 'car_price_pipeline.pkl'
-        
-        if not os.path.exists(model_path):
-            return None
-        
-        # Загружаем через joblib (лучше для sklearn)
-        pipeline = joblib.load(model_path)
-        
-        if not hasattr(pipeline, 'predict'):
-            return None
-        
-        return pipeline
-        
-    except Exception as e:
-        return None
+print("=== ЗАПУСК ПРИЛОЖЕНИЯ ===")
+print(f"Текущая директория: {os.getcwd()}")
+print(f"Файлы в директории: {os.listdir('.')}")
 
-# Функция для предсказания
+# Простая функция для демонстрации
 def predict_car_price(vehicle_manufacturer, vehicle_category, current_mileage, 
                      vehicle_year, vehicle_gearbox_type, doors_cnt, wheels, 
                      vehicle_color, car_leather_interior):
     
-    try:
-        # Создаем DataFrame из входных данных
-        input_data = pd.DataFrame({
-            'vehicle_manufacturer': [vehicle_manufacturer],
-            'vehicle_category': [vehicle_category],
-            'current_mileage': [int(current_mileage)],
-            'vehicle_year': [int(vehicle_year)],
-            'vehicle_gearbox_type': [vehicle_gearbox_type],
-            'doors_cnt': [doors_cnt],
-            'wheels': [wheels],
-            'vehicle_color': [vehicle_color],
-            'car_leather_interior': [int(car_leather_interior)]
-        })
-        
-        # Загружаем модель
-        pipeline = load_model()
-        
-        if pipeline is None:
-            return "Ошибка: модель не загружена"
-        
-        # Предсказание
-        prediction = pipeline.predict(input_data)[0]
-        return f"Предсказанная цена: ${prediction:,.2f}"
+    # Базовая формула цены для демонстрации
+    base_price = 5000
+    year_bonus = (vehicle_year - 2000) * 200
+    mileage_penalty = current_mileage * 0.01
+    leather_bonus = 1000 if car_leather_interior == 1 else 0
+    
+    estimated_price = base_price + year_bonus - mileage_penalty + leather_bonus
+    estimated_price = max(estimated_price, 500)  # Минимальная цена
     
-    except Exception as e:
-        return f"Ошибка предсказания: {str(e)}"
+    return f"Примерная цена: ${estimated_price:,.2f} (демо-режим)\n\nФайлы в директории: {os.listdir('.')}"
 
-# Создаем интерфейс Gradio
+# Создаем интерфейс
 with gr.Blocks(title="Car Price Predictor", theme=gr.themes.Soft()) as demo:
     gr.Markdown("# 🚗 Car Price Prediction Model")
     gr.Markdown("Введите параметры автомобиля для предсказания цены")
@@ -147,7 +93,8 @@ with gr.Blocks(title="Car Price Predictor", theme=gr.themes.Soft()) as demo:
     
     output = gr.Textbox(
         label="Результат",
-        interactive=False
+        interactive=False,
+        lines=3
     )
     
     predict_btn.click(
@@ -157,11 +104,6 @@ with gr.Blocks(title="Car Price Predictor", theme=gr.themes.Soft()) as demo:
                 vehicle_color, car_leather_interior],
         outputs=output
     )
-    
-    gr.Markdown("---")
-    gr.Markdown("### Примеры параметров:")
-    gr.Markdown("- **TOYOTA, Sedan, 100,000 km, 2015, Automatic** → ~$5,000")
-    gr.Markdown("- **BMW, Sedan, 50,000 km, 2018, Automatic** → ~$15,000")
 
 if __name__ == "__main__":
     demo.launch()