Update app.py

app.py

@@ -14,6 +14,7 @@ import torch
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 import re
+from datetime import datetime
 
 # Dataset loading function with caching
 @st.cache_data
@@ -113,19 +114,43 @@ def load_model_and_encodings():
         st.error(f"Error loading model: {str(e)}")
         raise e
 
+def calculate_age(year):
+    current_year = datetime.now().year
+    return current_year - year
+
 def predict_price(model, encoders, categorical_features, user_input):
     encoded_features = {}
+    current_year = datetime.now().year
+    
     for feature, value in user_input.items():
         if feature.lower() in encoders:
-            encoded_features[feature] = encoders[feature.lower()].transform([value])[0]
+            encoded_features[feature.capitalize()] = encoders[feature.lower()].transform([value])[0]
         elif feature in categorical_features:
             # If it's a categorical feature but not in encoders, set to 0 (unknown)
-            encoded_features[feature] = 0
+            encoded_features[feature.capitalize()] = 0
         else:
             # For numerical features, use the value as is
-            encoded_features[feature] = value
+            encoded_features[feature.capitalize()] = value
+    
+    # Calculate additional features
+    encoded_features['Age'] = calculate_age(encoded_features['Year'])
+    encoded_features['Age_squared'] = encoded_features['Age'] ** 2
+    
+    # Assume average mileage per year (you may want to adjust this)
+    avg_mileage_per_year = 12000
+    encoded_features['Mileage_per_year'] = avg_mileage_per_year
+    
+    # Assume odometer reading (you may want to adjust this)
+    encoded_features['Odometer'] = encoded_features['Age'] * avg_mileage_per_year
     
     input_data = pd.DataFrame([encoded_features])
+    
+    # Ensure all expected columns are present
+    expected_columns = ['Make', 'Model', 'Year', 'Condition', 'Fuel', 'Odometer', 'Title_status', 'Transmission', 'Drive', 'Size', 'Type', 'Paint_color', 'Age', 'Age_squared', 'Mileage_per_year']
+    for col in expected_columns:
+        if col not in input_data.columns:
+            input_data[col] = 0  # or some default value
+    
     predicted_price = model.predict(input_data)
     return predicted_price[0]
 
@@ -201,6 +226,7 @@ if image is not None:
                 user_input = {
                     'make': match['Make'],
                     'model': match['Model'],
+                    'year': year,
                     'condition': match.get('Condition', 'unknown'),
                     'fuel': match.get('Fuel', 'unknown'),
                     'title_status': match.get('Title_status', 'unknown'),
@@ -209,7 +235,6 @@ if image is not None:
                     'size': match.get('Size', 'unknown'),
                     'type': match.get('Type', 'unknown'),
                     'paint_color': match.get('Paint_color', 'unknown'),
-                    'year': year
                 }
                 
                 price = predict_price(model, label_encoders, categorical_features, user_input)