Update app.py

app.py

@@ -75,54 +75,29 @@ def load_model_and_encodings():
         raise e
 
 def predict_price(model, brand, model_name, year):
-    # Create a dictionary with default values
+    # Create a dictionary with default values for the specified categories
     input_data = {
         'year': year,
-        'make': brand,
-        'model': model_name,
-        'trim': 'Base',  # Default trim
-        'condition': 'Used',  # Default condition
-        'fuel': 'Gasoline',  # Default fuel type
         'odometer': year * 12000,  # Estimate based on year and average annual mileage
-        'title_status': 'Clean',  # Default title status
-        'transmission': 'Automatic',  # Default transmission
-        'drive': 'Fwd',  # Default drive
-        'size': 'Mid-Size',  # Default size
-        'type': 'Sedan',  # Default type
-        'paint_color': 'White'  # Default color
+        'age': datetime.now().year - year,
+        'age_squared': (datetime.now().year - year) ** 2,
+        'mileage_per_year': 12000,
+        'model': model_name,
+        'condition': 'Used',
+        'fuel': 'Gasoline',
+        'title_status': 'Clean',
+        'transmission': 'Automatic',
+        'drive': 'Fwd',
+        'size': 'Mid-Size',
+        'type': 'Sedan',
+        'paint_color': 'White'
     }
     
-    # Calculate age and other required fields
-    current_year = datetime.now().year
-    input_data['age'] = current_year - year
-    input_data['age_squared'] = input_data['age'] ** 2
-    input_data['mileage_per_year'] = 12000  # Assuming average annual mileage
-    
     # Prepare the input for the model
     input_df = pd.DataFrame([input_data])
     
-    # Rename columns to match what the model expects
-    input_df = input_df.rename(columns={
-        'make': 'Make',
-        'model': 'Model',
-        'year': 'Year',
-        'trim': 'Trim',
-        'condition': 'Condition',
-        'fuel': 'Fuel',
-        'odometer': 'Odometer',
-        'title_status': 'Title_status',
-        'transmission': 'Transmission',
-        'drive': 'Drive',
-        'size': 'Size',
-        'type': 'Type',
-        'paint_color': 'Paint_color',
-        'age': 'Age',
-        'age_squared': 'Age_squared',
-        'mileage_per_year': 'Mileage_per_year'
-    })
-    
-    # Make sure to only include columns that the model expects
-    model_columns = model.feature_names_in_
+    # Make sure to only include the specified columns
+    model_columns = [col for col in model.feature_names_in_ if col in input_data.keys()]
     input_df = input_df[model_columns]
     
     # Predict the price