combine participant info

app.py

@@ -1,3 +1,4 @@
+import json
 import os
 import time
 from collections import defaultdict
@@ -11,6 +12,20 @@ from fastapi import FastAPI
 
 load_dotenv()
 
+# Constants
+DATA_DIR = "data"
+PARTICIPANTS_CSV = os.path.join(DATA_DIR, "participants.csv")
+LEADERBOARD_PERSONAL_CSV = "leaderboard_personal.csv"
+
+# Column mappings for participants info
+COLUMN_MAP = {
+    "gmail": "Dirección de correo electrónico",
+    "discord": "¿Cuál es tu nombre en Discord?",
+    "hf_username": "¿Cuál es tu nombre en el Hub de Hugging Face?",
+    "contact_email": "Email de contacto",
+}
+
+# Initialize Argilla client
 try:
     client = rg.Argilla(
         api_url=os.getenv("ARGILLA_API_URL", ""),
@@ -20,14 +35,7 @@ except Exception as e:
     print(f"Error initializing Argilla client: {e}")
     client = None
 
-
-DATA_DIR = "data"
-INCLUDE_CSV = os.path.join(DATA_DIR, "include.csv")
-STEREOTYPES_CSV = os.path.join(DATA_DIR, "stereotypes.csv")
-ARENA_JSON = os.path.join(DATA_DIR, "arena.json")
-PARTICIPANTS_CSV = os.path.join(DATA_DIR, "participants.csv")
-LEADERBOARD_PERSONAL_CSV = os.path.join(".", "leaderboard_personal.csv")
-
+# Countries data
 countries = {
     "Argentina": {"iso": "ARG", "emoji": "🇦🇷"},
     "Bolivia": {"iso": "BOL", "emoji": "🇧🇴"},
@@ -52,95 +60,104 @@ countries = {
 }
 
 
+@lru_cache(maxsize=1)
 def get_user_mapping():
-    """
-    Get cached mapping of emails and hf_usernames to discord usernames.
-    Returns a tuple of (email_to_discord, hf_username_to_discord) mappings.
-    """
-    email_to_discord = {}
-    hf_username_to_discord = {}
+    """Get cached mapping of emails and hf_usernames to discord usernames."""
+    if not os.path.exists(PARTICIPANTS_CSV):
+        return {}, {}
 
     try:
-        if os.path.exists(PARTICIPANTS_CSV):
-            mapping_df = pd.read_csv(PARTICIPANTS_CSV)
-
-            # Map emails to discord usernames
-            if "gmail" in mapping_df.columns and "discord" in mapping_df.columns:
-                for _, row in mapping_df.iterrows():
-                    mail = row["gmail"]
-                    discord = row["discord"]
-                    if pd.notna(mail) and pd.notna(discord) and discord != "NA":
-                        email_to_discord[mail.lower()] = discord.lower()
-
-            # Map hf_usernames to discord usernames
-            if "hf_username" in mapping_df.columns and "discord" in mapping_df.columns:
-                for _, row in mapping_df.iterrows():
-                    hf_username = row["hf_username"]
-                    discord = row["discord"]
-                    if pd.notna(hf_username) and pd.notna(discord) and discord != "NA":
-                        hf_username_to_discord[hf_username.lower()] = discord.lower()
-
+        df = pd.read_csv(PARTICIPANTS_CSV)
+        email_to_discord = {}
+        hf_to_discord = {}
+
+        for _, row in df.iterrows():
+            discord = row.get(COLUMN_MAP["discord"], "")
+            if pd.notna(discord) and discord != "NA":
+                discord_lower = discord.lower()
+
+                # Map email to discord
+                gmail = row.get(COLUMN_MAP["gmail"], "")
+                if pd.notna(gmail):
+                    email_to_discord[gmail.lower()] = discord_lower
+
+                # Map hf_username to discord
+                hf_username = row.get(COLUMN_MAP["hf_username"], "")
+                if pd.notna(hf_username):
+                    hf_to_discord[hf_username.lower()] = discord_lower
+
+        return email_to_discord, hf_to_discord
     except Exception as e:
         print(f"Error loading {PARTICIPANTS_CSV}: {e}")
-
-    return email_to_discord, hf_username_to_discord
+        return {}, {}
 
 
 def get_discord_username(identifier):
-    """
-    Get discord username from either email or hf_username. Returns the discord username if found, otherwise returns the identifier.
-    """
-    email_to_discord, hf_username_to_discord = get_user_mapping()
+    """Get discord username from email or hf_username."""
+    email_to_discord, hf_to_discord = get_user_mapping()
 
-    # Try to find discord username by email first
     if "@" in identifier:
-        discord_username = email_to_discord.get(identifier.lower())
-        if discord_username:
-            return discord_username
+        return email_to_discord.get(identifier.lower(), identifier.split("@")[0])
 
-    # Try to find discord username by hf_username
-    discord_username = hf_username_to_discord.get(identifier.lower())
-    if discord_username:
-        return discord_username
+    return hf_to_discord.get(identifier.lower(), identifier)
 
-    # Fallback: use identifier as username
-    return identifier.split("@")[0] if "@" in identifier else identifier
 
+def get_participant_info():
+    """Get participant information from CSV."""
+    if not os.path.exists(PARTICIPANTS_CSV):
+        return {}
 
-def get_blend_es_data():
-    data = []
+    try:
+        df = pd.read_csv(PARTICIPANTS_CSV)
+        participant_info = {}
+
+        for _, row in df.iterrows():
+            discord_username = row.get(COLUMN_MAP["discord"], "")
+            if pd.notna(discord_username) and discord_username != "NA":
+                participant_info[discord_username.lower()] = {
+                    "gmail": row.get(COLUMN_MAP["gmail"], ""),
+                    "discord_username": discord_username,
+                    "hf_username": row.get(COLUMN_MAP["hf_username"], ""),
+                    "email": row.get(COLUMN_MAP["contact_email"], ""),
+                }
+
+        return participant_info
+    except Exception as e:
+        print(f"Error loading participant info: {e}")
+        return {}
 
-    for country in countries.keys():
-        iso = countries[country]["iso"]
-        emoji = countries[country]["emoji"]
 
-        dataset_name = f"{emoji} {country} - {iso} - Responder"
+def get_blend_es_data():
+    """Get blend-es data from Argilla."""
+    if not client:
+        return []
+
+    data = []
+    for country, info in countries.items():
+        dataset_name = f"{info['emoji']} {country} - {info['iso']} - Responder"
 
         try:
-            print(f"Processing dataset: {dataset_name}")
             dataset = client.datasets(dataset_name)
             records = list(dataset.records(with_responses=True))
 
-            dataset_contributions = defaultdict(int)
+            user_counts = defaultdict(int)
             user_mapping = {}
 
             for record in records:
-                record_dict = record.to_dict()
-                if "answer_1" in record_dict["responses"]:
-                    for answer in record_dict["responses"]["answer_1"]:
-                        if answer["user_id"]:
-                            user_id = answer["user_id"]
-                            dataset_contributions[user_id] += 1
+                if "answer_1" in record.responses:
+                    for answer in record.responses["answer_1"]:
+                        if answer.user_id:
+                            user_id = answer.user_id
+                            user_counts[user_id] += 1
 
                             if user_id not in user_mapping:
                                 try:
                                     user = client.users(id=user_id)
                                     user_mapping[user_id] = user.username
-                                except Exception as e:
-                                    print(f"Error getting username for {user_id}: {e}")
+                                except:
                                     user_mapping[user_id] = f"User-{user_id[:8]}"
 
-            for user_id, count in dataset_contributions.items():
+            for user_id, count in user_counts.items():
                 hf_username = user_mapping.get(user_id, f"User-{user_id[:8]}")
                 username = get_discord_username(hf_username)
                 data.append(
@@ -148,108 +165,118 @@ def get_blend_es_data():
                 )
 
         except Exception as e:
-            print(f"Error processing dataset {dataset_name}: {e}")
+            print(f"Error processing {dataset_name}: {e}")
 
     return data
 
 
 def get_include_data():
-    data = []
-    try:
-        if os.path.exists(INCLUDE_CSV):
-            include_df = pd.read_csv(INCLUDE_CSV)
-            username_column = "Nombre en Discord / username"
-            questions_column = "Total preguntas hackathon"
-            if (
-                username_column in include_df.columns
-                and questions_column in include_df.columns
-            ):
-                discord_users = defaultdict(int)
-                for _, row in include_df.iterrows():
-                    username = row[username_column][1:]  # Remove the @ symbol
-                    questions = row[questions_column]
-                    if pd.notna(username) and pd.notna(questions):
-                        discord_users[username.lower()] += int(questions)
-
-                for username, count in discord_users.items():
-                    data.append(
-                        {"source": "include", "username": username, "count": count}
-                    )
+    """Get include data from CSV."""
+    csv_path = os.path.join(DATA_DIR, "include.csv")
+    if not os.path.exists(csv_path):
+        return []
 
+    try:
+        df = pd.read_csv(csv_path)
+        username_col = "Nombre en Discord / username"
+        questions_col = "Total preguntas hackathon"
+
+        if username_col not in df.columns or questions_col not in df.columns:
+            return []
+
+        user_counts = defaultdict(int)
+        for _, row in df.iterrows():
+            username = row[username_col][1:] if pd.notna(row[username_col]) else ""
+            questions = row[questions_col] if pd.notna(row[questions_col]) else 0
+            if username and questions:
+                user_counts[username.lower()] += int(questions)
+
+        return [
+            {"source": "include", "username": username, "count": count}
+            for username, count in user_counts.items()
+        ]
     except Exception as e:
-        print(f"Error loading {INCLUDE_CSV}: {e}")
-
-    return data
+        print(f"Error loading include data: {e}")
+        return []
 
 
 def get_estereotipos_data():
-    data = []
+    """Get estereotipos data from CSV."""
+    csv_path = os.path.join(DATA_DIR, "stereotypes.csv")
+    if not os.path.exists(csv_path):
+        return []
 
     try:
-        if os.path.exists(STEREOTYPES_CSV):
-            counts_df = pd.read_csv(STEREOTYPES_CSV)
-            if "token_id" in counts_df.columns and "count" in counts_df.columns:
-                mail_counts = defaultdict(int)
-                for _, row in counts_df.iterrows():
-                    mail = row["token_id"]
-                    count = row["count"]
-                    if pd.notna(mail) and pd.notna(count):
-                        mail_counts[mail.lower()] += int(count)
-
-                for mail, count in mail_counts.items():
-                    username = get_discord_username(mail)
-                    data.append(
-                        {"source": "estereotipos", "username": username, "count": count}
-                    )
+        df = pd.read_csv(csv_path)
+        if "token_id" not in df.columns or "count" not in df.columns:
+            return []
+
+        user_counts = defaultdict(int)
+        for _, row in df.iterrows():
+            mail = row.get("token_id", "")
+            count = row.get("count", 0)
+            if pd.notna(mail) and pd.notna(count):
+                user_counts[mail.lower()] += int(count)
+
+        return [
+            {
+                "source": "include",
+                "username": get_discord_username(mail),
+                "count": count,
+            }
+            for mail, count in user_counts.items()
+        ]
     except Exception as e:
-        print(f"Error loading {STEREOTYPES_CSV}: {e}")
-
-    return data
+        print(f"Error loading estereotipos data: {e}")
+        return []
 
 
 def get_arena_data():
-    data = []
+    """Get arena data from JSON."""
+    json_path = os.path.join(DATA_DIR, "arena.json")
+    if not os.path.exists(json_path):
+        return []
 
     try:
-        if os.path.exists(ARENA_JSON):
-            import json
-
-            with open(ARENA_JSON, "r", encoding="utf-8") as f:
-                arena_data = json.load(f)
-
-            mail_counts = defaultdict(int)
-
-            for country, conversations in arena_data.items():
-                for conversation in conversations:
-                    if "username" in conversation:
-                        mail = conversation["username"]
-                        if mail:
-                            mail_counts[mail.lower()] += 1
-
-            for mail, count in mail_counts.items():
-                username = get_discord_username(mail)
-                data.append({"source": "arena", "username": username, "count": count})
+        with open(json_path, "r", encoding="utf-8") as f:
+            arena_data = json.load(f)
+
+        user_counts = defaultdict(int)
+        for conversations in arena_data.values():
+            for conversation in conversations:
+                if username := conversation.get("username"):
+                    user_counts[username.lower()] += 1
+
+        return [
+            {"source": "arena", "username": get_discord_username(mail), "count": count}
+            for mail, count in user_counts.items()
+        ]
     except Exception as e:
-        print(f"Error loading {ARENA_JSON}: {e}")
-
-    return data
-
-
-@lru_cache(maxsize=32)
-def get_user_contributions_cached(cache_buster: int):
-    return consolidate_all_data()
+        print(f"Error loading arena data: {e}")
+        return []
 
 
 def consolidate_all_data():
-    all_data = []
-    all_data.extend(get_blend_es_data())
-    all_data.extend(get_include_data())
-    all_data.extend(get_estereotipos_data())
-    all_data.extend(get_arena_data())
+    """Consolidate all data sources and create leaderboard."""
+    # Collect all data
+    all_data = (
+        get_blend_es_data()
+        + get_include_data()
+        + get_estereotipos_data()
+        + get_arena_data()
+    )
 
+    # Get participant info
+    participant_info = get_participant_info()
+
+    # Aggregate user contributions
     user_contributions = defaultdict(
         lambda: {
             "username": "",
+            "gmail": "",
+            "discord_username": "",
+            "hf_username": "",
+            "email": "",
             "blend_es": 0,
             "include": 0,
             "estereotipos": 0,
@@ -261,11 +288,20 @@ def consolidate_all_data():
         source = item["source"]
         username = item["username"]
         count = item["count"]
-
         user_key = username.lower()
 
         if not user_contributions[user_key]["username"]:
             user_contributions[user_key]["username"] = username
+            if username.lower() in participant_info:
+                info = participant_info[username.lower()]
+                user_contributions[user_key].update(
+                    {
+                        "gmail": info["gmail"],
+                        "discord_username": info["discord_username"],
+                        "hf_username": info["hf_username"],
+                        "email": info["email"],
+                    }
+                )
 
         if source == "blend-es":
             user_contributions[user_key]["blend_es"] += count
@@ -276,55 +312,79 @@ def consolidate_all_data():
         elif source == "arena":
             user_contributions[user_key]["arena"] += count
 
-    rows = []
-    for _, data in user_contributions.items():
-        row = {
-            "Username": data["username"],
-            "Arena": data["arena"],
-            "Blend-ES": data["blend_es"],
-            "Estereotipos": data["estereotipos"],
-            "INCLUDE": data["include"],
-        }
-        rows.append(row)
-
-    df = pd.DataFrame(rows)
-
-    if not df.empty:
-        df = df.sort_values("Arena", ascending=False)
-
-    with open(LEADERBOARD_PERSONAL_CSV, "w", encoding="utf-8") as f:
-        df.to_csv(f, index=False)
-
-    return df
-
-
+    # Create dataframes
+    full_rows = []
+    display_rows = []
+
+    for data in user_contributions.values():
+        # Full data for CSV
+        full_rows.append(
+            {
+                "Username": data["username"],
+                "Gmail": data["gmail"],
+                "Discord_Username": data["discord_username"],
+                "HF_Username": data["hf_username"],
+                "Email": data["email"],
+                "Arena": data["arena"],
+                "Blend-ES": data["blend_es"],
+                "Estereotipos": data["estereotipos"],
+                "INCLUDE": data["include"],
+            }
+        )
+
+        # Display data for UI (public)
+        display_rows.append(
+            {
+                "Username": data["username"],
+                "Arena": data["arena"],
+                "Blend-ES": data["blend_es"],
+                "Estereotipos": data["estereotipos"],
+                "INCLUDE": data["include"],
+            }
+        )
+
+    # Save full data to CSV
+    full_df = pd.DataFrame(full_rows)
+    if not full_df.empty:
+        full_df.sort_values("Arena", ascending=False, inplace=True)
+        full_df.to_csv(LEADERBOARD_PERSONAL_CSV, index=False, encoding="utf-8")
+
+    # Return display dataframe for UI
+    display_df = pd.DataFrame(display_rows)
+    if not display_df.empty:
+        display_df.sort_values("Arena", ascending=False, inplace=True)
+
+    return display_df
+
+
+# FastAPI app
 app = FastAPI()
 
+# Global variables for caching
 last_update_time = 0
 cached_data = None
 
 
 def create_leaderboard_ui():
+    """Create the leaderboard UI with caching."""
     global cached_data, last_update_time
     current_time = time.time()
 
     if cached_data is not None and current_time - last_update_time < 300:
         df = cached_data
     else:
-        cache_buster = int(current_time)
-        df = get_user_contributions_cached(cache_buster)
+        df = consolidate_all_data()
         cached_data = df
         last_update_time = current_time
 
     if not df.empty:
         df = df.reset_index(drop=True)
         df.index = df.index + 1
-        df = df.rename_axis("Rank")
-        df = df.reset_index()
+        df = df.rename_axis("Rank").reset_index()
 
     df_html = df.to_html(classes="leaderboard-table", border=0, index=False)
 
-    styled_html = f"""
+    return f"""
     <div style="margin: 20px 0;">
         <p>Última Actualización: {time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(last_update_time))}</p>
         <style>
@@ -390,22 +450,21 @@ def create_leaderboard_ui():
         {df_html}
     </div>
     """
-    return styled_html
 
 
 def refresh_data():
+    """Refresh the leaderboard data."""
     global cached_data, last_update_time
     cached_data = None
     last_update_time = 0
     return create_leaderboard_ui()
 
 
+# Gradio interface
 with gr.Blocks(theme=gr.themes.Default()) as demo:
     with gr.Column(scale=1):
-        gr.Markdown("""# 🏆 Hackaton Leaderboard""")
-
+        gr.Markdown("# 🏆 Leaderboard Personal Retos Hackathon 2025")
         leaderboard_html = gr.HTML(create_leaderboard_ui)
-
         refresh_btn = gr.Button("🔄 Actualizar Datos", variant="primary")
         refresh_btn.click(fn=refresh_data, outputs=leaderboard_html)
 

leaderboard_personal.csv

@@ -1,39 +1,54 @@
-Username,Arena,Blend-ES,Estereotipos,INCLUDE
-roverico,140,0,1,0
-steminism,133,0,0,0
-andres_seba,120,0,70,0
-mcdaqc,118,0,0,0
-jj,83,0,85,0
-bea esparcia,80,0,126,0
-angustias22,63,0,0,0
-henry mantilla,58,0,0,0
-fabianpp,50,0,0,0
-alvaro8gb,42,0,2,0
-enpaiva93,40,0,3,0
-ghuerta170,35,0,0,0
-edmenciab,30,0,0,0
-luceldasilva,23,0,0,0
-adriszmar,22,0,20,0
-helenpy,19,0,0,0
-danielcavilla,19,0,0,0
-gonzalo_40146,8,0,0,0
-gonzalo.fuentes,1,0,0,0
-gfuentes2000,1,0,0,0
-alexis_castillo,0,0,68,0
-elena w.,0,0,57,0
-alebravo,0,0,30,0
-jedzill4,0,0,27,0
-gonznm,0,0,24,0
-agumeister,0,0,21,0
-maria isabel ll,0,0,12,0
-dramos7,0,0,5,0
-freddyalfonsoboulton,0,0,1,0
-yee51,0,0,1,0
-valaery,0,0,1,0
-jorge.vallego,0,0,14,0
-neovalleltd,0,0,122,0
-daelsand,0,0,2,0
-jorgeav,0,0,13,0
-lucase#5596,0,0,3,0
-clauvallory,0,0,5,0
-da.qc,0,0,2,0
+Username,Gmail,Discord_Username,HF_Username,Email,Arena,Blend-ES,Estereotipos,INCLUDE
+roverico,[email protected],roverico,rovi27,[email protected],140,0,0,304
+steminism,[email protected],steminism,4nd,[email protected],133,0,0,577
+andres_seba,[email protected],andres_seba,AndresSebad,[email protected],120,0,0,440
+mcdaqc,[email protected],mcdaqc,daqc,[email protected],118,0,0,449
+dreamripper1,[email protected],dreamripper1,JuanJCalderonG,[email protected],83,0,0,987
+bea esparcia,[email protected],Bea Esparcia,BeaEsparcia,[email protected],80,0,0,126
+angustias22,[email protected],angustias22,lauramm,[email protected],63,0,0,0
+henry mantilla,[email protected],Henry Mantilla,HenryM,[email protected],58,0,0,0
+fabianpp,[email protected],fabianpp,Factral,[email protected],50,0,0,372
+alvaro8gb,[email protected],Alvaro8gb,Alvaro8gb,[email protected],42,0,0,2
+enpaiva93,[email protected],enpaiva93,enpaiva,[email protected],40,0,0,505
+ghuerta170,[email protected],ghuerta170,Gerard-1705,[email protected],35,0,0,353
+edmenciab,[email protected],edmenciab,edmenciab ,[email protected],30,0,0,0
+luceldasilva,[email protected],luceldasilva,luceldasilva,[email protected],23,0,0,0
+adriszmar,[email protected],adriszmar,adriszmar,[email protected],22,0,0,247
+helenpy,[email protected],helenpy,LATEiimas,[email protected],19,0,0,0
+danielcavilla,[email protected],DanielCavilla,DanielCavilla,[email protected],19,0,0,0
+gonzalo_40146,[email protected],gonzalo_40146,gonznm,[email protected],8,0,0,0
+gonzalo.fuentes,,,,,1,0,0,0
+gfuentes2000,,,,,1,0,0,0
+valaery,[email protected],valaery,valaery,[email protected],0,0,0,1
+clauvallory,,,,,0,0,0,5
+lucase#5596,[email protected],Lucase#5596,Lucase,[email protected],0,0,0,3
+daelsand,,,,,0,0,0,2
+da.qc,,,,,0,0,0,2
+guidoivetta ,,,,,0,0,0,393
+jorge-neo,,,,,0,0,0,927
+yee51,[email protected],Yee51,cleysi51,[email protected],0,0,0,1
+freddyalfonsoboulton,,,,,0,0,0,1
+mgomez8540,[email protected],mgomez8540,[email protected],[email protected],0,0,0,348
+gpalomeque,[email protected],gpalomeque,GPalomeque,[email protected],0,0,0,120
+conilinguist,constanzapjeldres@gmail.com,conilinguist,conijeldres,[email protected],0,0,0,300
+arri98,,,,,0,0,0,598
+dramos7,[email protected],Dramos7,DRamos,[email protected],0,0,0,5
+maria isabel ll,[email protected],Maria Isabel LL,MariaIsabel,[email protected],0,0,0,12
+jorgeav,[email protected],JorgeAV,JorgeAV,[email protected],0,0,0,13
+jorge.vallego,,,,,0,0,0,14
+oscarcumbicus,oskr2703@gmail.com,oscarcumbicus,oskrmiguel,[email protected],0,0,0,1280
+pablo.ce,[email protected],pablo.ce,pabloce,[email protected],0,0,0,2830
+rasel,,,,,0,0,0,300
+reewos,[email protected],reewos,reewos,[email protected],0,0,0,608
+bel21093_72376,,,,,0,0,0,300
+godswrath97,[email protected],godswrath97,JorgeMTT97,[email protected],0,0,0,561
+susanazhou,[email protected],susanazhou,susanazhou ,[email protected],0,0,0,560
+henrymantilla,,,,,0,0,0,302
+neovalleltd,,,,,0,0,0,122
+amayuelas,,,,,0,0,0,2300
+elena w.,[email protected],Elena W.,hyrka,[email protected],0,0,0,57
+alebravo,[email protected],AleBravo,AleBravo,[email protected],0,0,0,30
+jedzill4,[email protected],jedzill4,jedzill4,[email protected],0,0,0,27
+gonznm,,,,,0,0,0,24
+agumeister,[email protected],agumeister,agustinghent,[email protected],0,0,0,21
+alexis_castillo,[email protected],alexis_castillo,AlexisCastillo,[email protected],0,0,0,68

requirements.txt

@@ -1,3 +1,4 @@
 gradio ~= 4.44.0
 argilla ~= 2.5.0
 python-dotenv ~= 1.0.0
+pandas ~= 2.0.0