Update app.py

app.py

@@ -95,27 +95,7 @@ countries = {
   }
 }
 
-def load_include_data():
-    try:
-        if os.path.exists("include.csv"):
-            include_df = pd.read_csv("include.csv")
-            if "Nombre en Discord / username" in include_df.columns and "Número de preguntas / number of questions" in include_df.columns:
-                include_dict = defaultdict(int)
-                for _, row in include_df.iterrows():
-                    username = row["Nombre en Discord / username"]
-                    questions = row["Número de preguntas / number of questions"]
-                    if pd.notna(username) and pd.notna(questions):
-                        include_dict[username.lower()] += int(questions)
-                return include_dict
-    except Exception as e:
-        print(f"Error loading include.csv: {e}")
-    return {}
-
-@lru_cache(maxsize=32)
-def get_user_contributions_cached(cache_buster: int):
-    return get_user_contributions()
-
-def get_user_contributions():
+def get_blend_es_data():
     user_contributions = defaultdict(lambda: {"username": "", "contributions": 0, "country_contributions": {}})
     user_id_to_username = {}
     
@@ -157,22 +137,72 @@ def get_user_contributions():
         except Exception as e:
             print(f"Error processing dataset {dataset_name}: {e}")
     
-    include_data = load_include_data()
+    return user_contributions, user_id_to_username
+
+def get_include_data(username_mapping):
+    result = defaultdict(int)
+    try:
+        if os.path.exists("include.csv"):
+            include_df = pd.read_csv("include.csv")
+            if "Nombre en Discord / username" in include_df.columns and "Número de preguntas / number of questions" in include_df.columns:
+                discord_users = defaultdict(int)
+                for _, row in include_df.iterrows():
+                    username = row["Nombre en Discord / username"]
+                    questions = row["Número de preguntas / number of questions"]
+                    if pd.notna(username) and pd.notna(questions):
+                        discord_users[username.lower()] += int(questions)
+                
+                reverse_mapping = {}
+                for user_id, username in username_mapping.items():
+                    reverse_mapping[username.lower()] = user_id
+                
+                for discord_name, questions in discord_users.items():
+                    matched = False
+                    for argilla_name in reverse_mapping:
+                        if discord_name in argilla_name or argilla_name in discord_name:
+                            user_id = reverse_mapping[argilla_name]
+                            result[user_id] += questions
+                            matched = True
+                            break
+                    
+                    if not matched:
+                        result[f"discord_{discord_name}"] = questions
+    except Exception as e:
+        print(f"Error loading include.csv: {e}")
+    
+    return result
+
+@lru_cache(maxsize=32)
+def get_user_contributions_cached(cache_buster: int):
+    return consolidate_all_data()
+
+def consolidate_all_data():
+    user_data = {}
+    
+    blend_es_data, username_mapping = get_blend_es_data()
+    include_data = get_include_data(username_mapping)
+    
+    all_user_ids = set(blend_es_data.keys()) | set(include_data.keys())
     
     rows = []
-    for user_id, data in user_contributions.items():
-        username = data["username"]
-        include_value = 0
+    for user_id in all_user_ids:
+        blend_es_value = 0
+        username = user_id
+        
+        if user_id in blend_es_data:
+            blend_es_value = blend_es_data[user_id]["contributions"]
+            username = blend_es_data[user_id]["username"]
+        
+        include_value = include_data.get(user_id, 0)
         
-        for discord_name, questions in include_data.items():
-            if username.lower() in discord_name.lower() or discord_name.lower() in username.lower():
-                include_value = questions
-                break
+        if isinstance(user_id, str) and user_id.startswith("discord_"):
+            username = user_id.replace("discord_", "")
+            blend_es_value = 0
         
         row = {
             "Username": username,
-            "Total": data["contributions"] + include_value,
-            "Blend-es": data["contributions"],
+            "Total": blend_es_value + include_value,
+            "Blend-es": blend_es_value,
             "INCLUDE": include_value
         }
         rows.append(row)