Update app.py

app.py

@@ -9,6 +9,39 @@ from huggingface_hub import hf_hub_download
 from transformers import AutoFeatureExtractor, AutoModelForImageClassification
 import torch
 from datetime import datetime
+from sklearn.preprocessing import LabelEncoder
+
+# Initialize label encoders for categorical variables
+make_encoder = LabelEncoder()
+model_encoder = LabelEncoder()
+condition_encoder = LabelEncoder()
+fuel_encoder = LabelEncoder()
+title_status_encoder = LabelEncoder()
+transmission_encoder = LabelEncoder()
+drive_encoder = LabelEncoder()
+size_encoder = LabelEncoder()
+type_encoder = LabelEncoder()
+paint_color_encoder = LabelEncoder()
+
+# Fit the encoders with some sample data (you may want to use your actual dataset for this)
+sample_data = {
+    'Make': ['Toyota', 'Honda', 'Ford', 'Chevrolet', 'Nissan'],
+    'model': ['Camry', 'Civic', 'F-150', 'Silverado', 'Altima'],
+    'condition': ['Used', 'New', 'Excellent', 'Good', 'Fair'],
+    'fuel': ['Gasoline', 'Diesel', 'Electric', 'Hybrid', 'CNG'],
+    'title_status': ['Clean', 'Salvage', 'Rebuilt', 'Lien', 'Missing'],
+    'transmission': ['Automatic', 'Manual', 'CVT', 'DCT', 'AMT'],
+    'drive': ['Fwd', 'Rwd', 'Awd', '4wd', 'Other'],
+    'size': ['Mid-Size', 'Full-Size', 'Compact', 'Sub-Compact', 'Crossover'],
+    'type': ['Sedan', 'SUV', 'Truck', 'Coupe', 'Van'],
+    'paint_color': ['White', 'Black', 'Silver', 'Red', 'Blue']
+}
+
+for feature, encoder in [('Make', make_encoder), ('model', model_encoder), ('condition', condition_encoder),
+                         ('fuel', fuel_encoder), ('title_status', title_status_encoder),
+                         ('transmission', transmission_encoder), ('drive', drive_encoder),
+                         ('size', size_encoder), ('type', type_encoder), ('paint_color', paint_color_encoder)]:
+    encoder.fit(sample_data[feature])
 
 # Dataset loading function with caching
 @st.cache_data
@@ -81,16 +114,16 @@ def predict_price(model, brand, model_name, year):
         'age': datetime.now().year - year,
         'age_squared': (datetime.now().year - year) ** 2,
         'mileage_per_year': 12000,
-        'Make': brand,  # Note the capital 'M' in Make
-        'model': model_name,  # lowercase 'model'
-        'condition': 'Used',
-        'fuel': 'Gasoline',
-        'title_status': 'Clean',
-        'transmission': 'Automatic',
-        'drive': 'Fwd',
-        'size': 'Mid-Size',
-        'type': 'Sedan',
-        'paint_color': 'White'
+        'Make': make_encoder.transform([brand])[0],
+        'model': model_encoder.transform([model_name])[0],
+        'condition': condition_encoder.transform(['Used'])[0],
+        'fuel': fuel_encoder.transform(['Gasoline'])[0],
+        'title_status': title_status_encoder.transform(['Clean'])[0],
+        'transmission': transmission_encoder.transform(['Automatic'])[0],
+        'drive': drive_encoder.transform(['Fwd'])[0],
+        'size': size_encoder.transform(['Mid-Size'])[0],
+        'type': type_encoder.transform(['Sedan'])[0],
+        'paint_color': paint_color_encoder.transform(['White'])[0]
     }
     
     # Prepare the input for the model