Update app.py

app.py

@@ -10,6 +10,9 @@ import numpy as np
 from sklearn.preprocessing import LabelEncoder
 from huggingface_hub import hf_hub_download
 from transformers import pipeline
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+import re
 
 # Dataset loading function with caching
 @st.cache_data
@@ -42,10 +45,28 @@ def classify_image(image):
         return None
 
 def find_closest_match(df, brand, model):
-    match = df[(df['Make'].str.contains(brand, case=False)) & (df['Model'].str.contains(model, case=False))]
-    if not match.empty:
-        return match.iloc[0]
-    return None
+    # 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"
@@ -124,7 +145,10 @@ if camera_image is not None:
         match = find_closest_match(df, brand, model_name)
         if match is not None:
             st.write("Closest Match Found:")
-            st.write(match)
+            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)
@@ -141,8 +165,8 @@ if camera_image is not None:
 
             for year in years:
                 user_input = {
-                    'Make': brand,
-                    'Model': model_name,
+                    'Make': match['Make'],
+                    'Model': match['Model'],
                     'Condition': match['Condition'],
                     'Fuel': match['Fuel'],
                     'Title_status': match['Title_status'],
@@ -160,7 +184,7 @@ if camera_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 {brand} {model_name} Over Time")
+            plt.title(f"Predicted Price of {match['Make']} {match['Model']} Over Time")
             plt.xlabel("Year")
             plt.ylabel("Predicted Price ($)")
             plt.grid()