Update app.py

app.py

@@ -59,22 +59,37 @@ def calcular_fator_avaliacao(titulo, EC, PU):
     return fator_avaliacao
 
 def select_nearest_items(df, query):
-    # Implement a more refined selection process
-    # First, filter by title similarity to ensure relevance
+    # Calculate title similarity for relevance
     df['Title_Similarity'] = df['Title'].apply(lambda x: fuzz.WRatio(query, x))
-    df_filtered_by_similarity = df[df['Title_Similarity'] > 70]  # Adjust similarity threshold
+    # Filter by title similarity threshold
+    df_filtered_by_similarity = df[df['Title_Similarity'] > 70]  # Adjust similarity threshold as needed
     
     if df_filtered_by_similarity.empty:
-        # Fallback to broader criteria if no closely matching titles are found
+        # If no closely matching titles are found, return an empty DataFrame
         return pd.DataFrame()
     
-    # Then, select items based on price, considering only those within a reasonable range
+    # Filter by price, considering only those within a reasonable range
     reasonable_price_df = df_filtered_by_similarity[df_filtered_by_similarity['Price'] <= df_filtered_by_similarity['Price'].quantile(0.75)]
-    
+    # Calculate distance from target price for sorting
     target_price = reasonable_price_df['Price'].mode().min() if not reasonable_price_df['Price'].mode().empty else reasonable_price_df['Price'].median()
     reasonable_price_df['Distance'] = (reasonable_price_df['Price'] - target_price).abs()
-    
-    return reasonable_price_df.sort_values(['Distance', 'Title_Similarity'], ascending=[True, False]).head(5)
+
+    # Initialize container for selected items ensuring different marketplaces
+    selected_items = []
+    included_marketplaces = set()
+
+    # Sort by distance to target price, then by title similarity
+    df_sorted = reasonable_price_df.sort_values(['Distance', 'Title_Similarity'], ascending=[True, False])
+
+    for _, row in df_sorted.iterrows():
+        marketplace = row['Marketplace']
+        if marketplace not in included_marketplaces:
+            selected_items.append(row)
+            included_marketplaces.add(marketplace)
+        if len(selected_items) >= 5:
+            break
+
+    return pd.DataFrame(selected_items)
 
 def search_with_fallback(query, df, limit=15):
     query_parts = query.split()