Update app.py

app.py

@@ -8,8 +8,6 @@ from io import BytesIO
 import matplotlib.pyplot as plt
 import numpy as np
 from sklearn.preprocessing import LabelEncoder
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.metrics.pairwise import cosine_similarity
 from huggingface_hub import hf_hub_download
 from transformers import AutoFeatureExtractor, AutoModelForImageClassification
 import torch
@@ -58,32 +56,8 @@ def classify_image(image):
         st.error(f"Classification error: {e}")
         return None
 
-def find_closest_match(df, brand, model):
-    # Combine brand and model names from the dataset
-    df['full_name'] = df['Make'] + ' ' + df['Model']
-    
-    # Create a list of all car names
-    car_names = df['full_name'].tolist()
-    
-    # Add the query car name
-    query_car = f"{brand} {model}"
-    car_names.append(query_car)
-    
-    # Create TF-IDF vectorizer
-    vectorizer = TfidfVectorizer()
-    tfidf_matrix = vectorizer.fit_transform(car_names)
-    
-    # Compute cosine similarity
-    cosine_similarities = cosine_similarity(tfidf_matrix[-1], tfidf_matrix[:-1]).flatten()
-    
-    # Get the index of the most similar car
-    most_similar_index = cosine_similarities.argmax()
-    
-    # Return the most similar car's data
-    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"
+def get_car_overview(brand, model, year):
+    prompt = f"Provide an overview of the following car:\nYear: {year}\nMake: {brand}\nModel: {model}\n"
     response = openai.ChatCompletion.create(
         model="gpt-3.5-turbo",
         messages=[{"role": "user", "content": prompt}]
@@ -100,30 +74,28 @@ def load_model_and_encodings():
         st.error(f"Error loading model: {str(e)}")
         raise e
 
-def predict_price(model, match, year):
-    # Start with the data from the closest match
-    input_data = match.copy()
-    
-    # Update the year
-    input_data['Year'] = year
+def predict_price(model, brand, model_name, year):
+    # Create a dictionary with default values
+    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
+    }
     
     # Calculate age
     current_year = datetime.now().year
-    input_data['Age'] = current_year - year
-    input_data['Age_squared'] = input_data['Age'] ** 2
-    
-    # If odometer is missing, estimate it based on age and average yearly mileage
-    if 'Odometer' not in input_data or pd.isna(input_data['Odometer']):
-        avg_yearly_mileage = 12000  # Adjust this value as needed
-        input_data['Odometer'] = input_data['Age'] * avg_yearly_mileage
-    
-    # Ensure all required columns are present
-    required_columns = ['Make', 'Model', 'Year', 'Condition', 'Fuel', 'Odometer', 'Title_status', 'Transmission', 'Drive', 'Size', 'Type', 'Paint_color', 'Age', 'Age_squared']
-    
-    for col in required_columns:
-        if col not in input_data or pd.isna(input_data[col]):
-            # If a required column is missing, fill it with the most common value from the dataset
-            input_data[col] = df[col].mode().iloc[0]
+    input_data['age'] = current_year - year
+    input_data['age_squared'] = input_data['age'] ** 2
     
     # Prepare the input for the model
     input_df = pd.DataFrame([input_data])
@@ -181,44 +153,33 @@ if image is not None:
         
         st.write(f"Identified Car: {brand} {model_name}")
 
-        # Find the closest match in the CSV
-        df = load_datasets()
-        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: ${match['Price']}")
-
-            # Get additional information using GPT-3.5-turbo
-            overview = get_car_overview(match)
-            st.write("Car Overview:")
-            st.write(overview)
-
-            # Interactive Price Prediction
-            st.subheader("Price Prediction Over Time")
-            selected_years = st.slider("Select range of years for price prediction", 
-                                         min_value=2000, max_value=2023, value=(2010, 2023))
-
-            years = np.arange(selected_years[0], selected_years[1] + 1)
-            predicted_prices = []
-
-            for year in years:
-                price = predict_price(model, match, year)
-                predicted_prices.append(price)
-
-            # Plotting the results
-            plt.figure(figsize=(10, 5))
-            plt.plot(years, predicted_prices, marker='o')
-            plt.title(f"Predicted Price of {match['Make']} {match['Model']} Over Time")
-            plt.xlabel("Year")
-            plt.ylabel("Predicted Price ($)")
-            plt.grid()
-            st.pyplot(plt)
-
-        else:
-            st.write("No match found in the database.")
+        # Get additional information using GPT-3.5-turbo
+        current_year = datetime.now().year
+        overview = get_car_overview(brand, model_name, current_year)
+        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:
+            price = predict_price(model, brand, model_name, year)
+            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.error("Could not classify the image. Please try again with a different image.")
 else: