Update app.py

app.py

@@ -10,6 +10,21 @@ import numpy as np
 from sklearn.preprocessing import LabelEncoder
 from huggingface_hub import hf_hub_download
 
+# Dataset loading function with caching
+@st.cache_data
+def load_datasets():
+    try:
+        with st.spinner('Loading dataset...'):
+            # Load the CSV content
+            original_data = pd.read_csv('CTP_Model1.csv', low_memory=False)
+            
+            # Ensure column names match the model's expectations
+            original_data.columns = original_data.columns.str.strip().str.capitalize()
+            return original_data
+    except Exception as e:
+        st.error(f"Error loading dataset: {str(e)}")
+        raise e
+
 # Function definitions
 
 def load_image(image_file):
@@ -33,29 +48,14 @@ def classify_image(image):
         st.error("Image classification failed. Please try again.")
         return None
 
-@st.cache_data
-def load_datasets():
-    try:
-        with st.spinner('Loading dataset...'):
-            # Use BytesIO to read the CSV content
-            original_data = pd.read_csv('CTP_Model1.csv', low_memory=False)
-            
-            
-            # Ensure column names match the model's expectations
-            original_data.columns = original_data.columns.str.strip().str.capitalize()
-            return original_data
-    except Exception as e:
-        st.error(f"Error loading dataset: {str(e)}")
-        raise e
-
 def find_closest_match(df, brand, model):
-    match = df[(df['make'].str.contains(brand, case=False)) & (df['model'].str.contains(model, case=False))]
+    match = df[(df['Make'].str.contains(brand, case=False)) & (df['Model'].str.contains(model, case=False))]
     if not match.empty:
         return match.iloc[0]
     return None
 
 def get_car_overview(car_data):
-    prompt = f"Provide an overview of the following car:\nYear: {car_data['year']}\nMake: {car_data['make']}\nModel: {car_data['model']}\nTrim: {car_data['trim']}\nPrice: ${car_data['price']}\nCondition: {car_data['condition']}\n"
+    prompt = f"Provide an overview of the following car:\nYear: {car_data['Year']}\nMake: {car_data['Make']}\nModel: {car_data['Model']}\nTrim: {car_data['Trim']}\nPrice: ${car_data['Price']}\nCondition: {car_data['Condition']}\n"
     response = openai.ChatCompletion.create(
         model="gpt-3.5-turbo",
         messages=[{"role": "user", "content": prompt}]
@@ -68,11 +68,12 @@ def load_model_and_encodings():
             model_content = hf_hub_download(repo_id="EdBoy2202/car_prediction_model", filename="car_price_modelv3.pkl")
             model = joblib.load(model_content)
 
-        original_data = load_datasets()  # Ensure this function loads your CSV data
+        # Load datasets
+        original_data = load_datasets()
         
         label_encoders = {}
-        categorical_features = ['Make', 'model', 'condition', 'fuel', 'title_status', 
-                                'transmission', 'drive', 'size', 'type', 'paint_color']
+        categorical_features = ['Make', 'Model', 'Condition', 'Fuel', 'Title_status', 
+                                'Transmission', 'Drive', 'Size', 'Type', 'Paint_color']
         
         for feature in categorical_features:
             if feature in original_data.columns:
@@ -103,9 +104,6 @@ def predict_price(model, encoders, user_input):
 st.title("Auto Appraise")
 st.write("Capture a car image using your camera or upload an image to get its brand, model, overview, and expected price!")
 
-# Load the CSV file
-df = pd.read_csv('CTP_Model1.csv')
-
 # Load model and encoders
 model, label_encoders = load_model_and_encodings()
 
@@ -118,62 +116,66 @@ camera_image = st.camera_input("Take a picture of the car!")
 
 if camera_image is not None:
     image = load_image(camera_image)
-    st.image(image, caption='Captured Image.', use_column_width=True)
+    st.image(image, caption='Captured Image.', use_container_width=True)  # Updated parameter
 
     # Classify the car image
     car_info = classify_image(image)
     if car_info:
-        brand = car_info['brand']  # Adjust according to response structure
-        model_name = car_info['model']
-        st.write(f"Identified Car: {brand} {model_name}")
-
-        # Find the closest match in the CSV
-        match = find_closest_match(df, brand, model_name)
-        if match is not None:
-            st.write("Closest Match Found:")
-            st.write(match)
-
-            # Get additional information using GPT-3.5-turbo
-            overview = get_car_overview(match)
-            st.write("Car Overview:")
-            st.write(overview)
-
-            # Interactive Price Prediction
-            st.subheader("Price Prediction Over Time")
-            selected_years = st.slider("Select range of years for price prediction", 
-                                         min_value=2000, max_value=2023, value=(2010, 2023))
-
-            years = np.arange(selected_years[0], selected_years[1] + 1)
-            predicted_prices = []
-
-            for year in years:
-                user_input = {
-                    'Make': brand,
-                    'model': model_name,
-                    'condition': match['condition'],
-                    'fuel': match['fuel'],
-                    'title_status': match['title_status'],
-                    'transmission': match['transmission'],
-                    'drive': match['drive'],
-                    'size': match['size'],
-                    'type': match['type'],
-                    'paint_color': match['paint_color'],
-                    'year': year
-                }
-                
-                price = predict_price(model, label_encoders, user_input)
-                predicted_prices.append(price)
-
-            # Plotting the results
-            plt.figure(figsize=(10, 5))
-            plt.plot(years, predicted_prices, marker='o')
-            plt.title(f"Predicted Price of {brand} {model_name} Over Time")
-            plt.xlabel("Year")
-            plt.ylabel("Predicted Price ($)")
-            plt.grid()
-            st.pyplot(plt)
-
+        brand = car_info.get('brand', None)  # Adjust according to the response structure
+        model_name = car_info.get('model', None)
+        
+        if brand and model_name:
+            st.write(f"Identified Car: {brand} {model_name}")
+
+            # Find the closest match in the CSV
+            match = find_closest_match(df, brand, model_name)
+            if match is not None:
+                st.write("Closest Match Found:")
+                st.write(match)
+
+                # Get additional information using GPT-3.5-turbo
+                overview = get_car_overview(match)
+                st.write("Car Overview:")
+                st.write(overview)
+
+                # Interactive Price Prediction
+                st.subheader("Price Prediction Over Time")
+                selected_years = st.slider("Select range of years for price prediction", 
+                                             min_value=2000, max_value=2023, value=(2010, 2023))
+
+                years = np.arange(selected_years[0], selected_years[1] + 1)
+                predicted_prices = []
+
+                for year in years:
+                    user_input = {
+                        'Make': brand,
+                        'Model': model_name,
+                        'Condition': match['Condition'],
+                        'Fuel': match['Fuel'],
+                        'Title_status': match['Title_status'],
+                        'Transmission': match['Transmission'],
+                        'Drive': match['Drive'],
+                        'Size': match['Size'],
+                        'Type': match['Type'],
+                        'Paint_color': match['Paint_color'],
+                        'Year': year
+                    }
+                    
+                    price = predict_price(model, label_encoders, user_input)
+                    predicted_prices.append(price)
+
+                # Plotting the results
+                plt.figure(figsize=(10, 5))
+                plt.plot(years, predicted_prices, marker='o')
+                plt.title(f"Predicted Price of {brand} {model_name} Over Time")
+                plt.xlabel("Year")
+                plt.ylabel("Predicted Price ($)")
+                plt.grid()
+                st.pyplot(plt)
+
+            else:
+                st.write("No match found in the database.")
         else:
-            st.write("No match found in the database.")
+            st.error("Could not identify the brand or model. Please try again.")
 else:
     st.write("Please take a picture of the car to proceed.")