Update app.py

app.py

@@ -11,9 +11,6 @@ from sklearn.preprocessing import LabelEncoder
 from huggingface_hub import hf_hub_download
 from transformers import AutoFeatureExtractor, AutoModelForImageClassification
 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
@@ -22,7 +19,7 @@ def load_datasets():
     try:
         with st.spinner('Loading dataset...'):
             original_data = pd.read_csv('CTP_Model1.csv', low_memory=False)
-            original_data.columns = original_data.columns.str.strip().str.capitalize()
+            original_data.columns = original_data.columns.str.strip().str.lower()
             return original_data
     except Exception as e:
         st.error(f"Error loading dataset: {str(e)}")
@@ -62,7 +59,7 @@ def classify_image(image):
 
 def find_closest_match(df, brand, model):
     # Combine brand and model names from the dataset
-    df['full_name'] = df['Make'] + ' ' + df['Model']
+    df['full_name'] = df['make'] + ' ' + df['model']
     
     # Create a list of all car names
     car_names = df['full_name'].tolist()
@@ -85,7 +82,7 @@ def find_closest_match(df, brand, model):
     return df.iloc[most_similar_index]
 
 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}]
@@ -123,30 +120,31 @@ def predict_price(model, encoders, categorical_features, user_input):
     current_year = datetime.now().year
     
     for feature, value in user_input.items():
-        if feature.lower() in encoders:
-            encoded_features[feature.capitalize()] = encoders[feature.lower()].transform([value])[0]
-        elif feature in categorical_features:
+        feature_lower = feature.lower()
+        if feature_lower in encoders:
+            encoded_features[feature_lower] = encoders[feature_lower].transform([value])[0]
+        elif feature_lower in categorical_features:
             # If it's a categorical feature but not in encoders, set to 0 (unknown)
-            encoded_features[feature.capitalize()] = 0
+            encoded_features[feature_lower] = 0
         else:
             # For numerical features, use the value as is
-            encoded_features[feature.capitalize()] = value
+            encoded_features[feature_lower] = value
     
     # Calculate additional features
-    encoded_features['Age'] = calculate_age(encoded_features['Year'])
-    encoded_features['Age_squared'] = encoded_features['Age'] ** 2
+    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
+    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
+    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']
+    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
@@ -204,10 +202,10 @@ if image is not None:
         match = find_closest_match(df, brand, model_name)
         if match is not None:
             st.write("Closest Match Found:")
-            st.write(f"Make: {match['Make']}")
-            st.write(f"Model: {match['Model']}")
-            st.write(f"Year: {match['Year']}")
-            st.write(f"Price: ${match['Price']}")
+            st.write(f"Make: {match['make']}")
+            st.write(f"Model: {match['model']}")
+            st.write(f"Year: {match['year']}")
+            st.write(f"Price: ${match['price']}")
 
             # Get additional information using GPT-3.5-turbo
             overview = get_car_overview(match)
@@ -224,17 +222,17 @@ if image is not None:
 
             for year in years:
                 user_input = {
-                    'make': match['Make'],
-                    'model': match['Model'],
+                    'make': match['make'].lower(),
+                    'model': match['model'].lower(),
                     'year': year,
-                    'condition': match.get('Condition', 'unknown'),
-                    'fuel': match.get('Fuel', 'unknown'),
-                    'title_status': match.get('Title_status', 'unknown'),
-                    'transmission': match.get('Transmission', 'unknown'),
-                    'drive': match.get('Drive', 'unknown'),
-                    'size': match.get('Size', 'unknown'),
-                    'type': match.get('Type', 'unknown'),
-                    'paint_color': match.get('Paint_color', 'unknown'),
+                    'condition': match.get('condition', 'unknown').lower(),
+                    'fuel': match.get('fuel', 'unknown').lower(),
+                    'title_status': match.get('title_status', 'unknown').lower(),
+                    'transmission': match.get('transmission', 'unknown').lower(),
+                    'drive': match.get('drive', 'unknown').lower(),
+                    'size': match.get('size', 'unknown').lower(),
+                    'type': match.get('type', 'unknown').lower(),
+                    'paint_color': match.get('paint_color', 'unknown').lower(),
                 }
                 
                 price = predict_price(model, label_encoders, categorical_features, user_input)
@@ -243,7 +241,7 @@ if image is not None:
             # Plotting the results
             plt.figure(figsize=(10, 5))
             plt.plot(years, predicted_prices, marker='o')
-            plt.title(f"Predicted Price of {match['Make']} {match['Model']} Over Time")
+            plt.title(f"Predicted Price of {match['make']} {match['model']} Over Time")
             plt.xlabel("Year")
             plt.ylabel("Predicted Price ($)")
             plt.grid()