Upload app.py

app.py

@@ -136,7 +136,10 @@ def recommend_books(target_book: str, num_recommendations: int = 10) -> str:
 
     if dataset is None or faiss_index is None or normalized_data is None or book_titles is None:
         load_and_prepare_data()
+        dataset['ISBN'] = dataset['ISBN'].str.strip()
+        print("Before dropping duplicates:", len(dataset))
         dataset = dataset.drop_duplicates(subset=['ISBN'])
+        print("After dropping duplicates:", len(dataset))
 
     target_book = target_book.lower()
     # Fuzzy match the input to the closest book title
@@ -147,6 +150,12 @@ def recommend_books(target_book: str, num_recommendations: int = 10) -> str:
 
     recommendations = correlations[correlations['book'] != target_book]
 
+    # Create a mask of unique ISBNs
+    unique_mask = dataset.duplicated(subset=['ISBN'], keep='first') == False
+
+    # Apply the mask
+    dataset = dataset[unique_mask]
+
     recommendations = recommendations.head(num_recommendations)
 
     result = f"Top {num_recommendations} recommendations for '{target_book}':\n\n"