corrected llm code

jupyter_notebooks/Section_2-3-4_Figure_8_deepfake_adapters.ipynb

@@ -142,40 +142,40 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u2705 spaCy model loaded: en_core_web_sm\n",
+      "✅ spaCy model loaded: en_core_web_sm\n",
       "Loaded 18 rows\n",
       "\n",
-      "\ud83d\udd04 Processing names with spaCy NER...\n",
+      "🔄 Processing names with spaCy NER...\n",
       "\n",
-      "\ud83d\udcca Name cleaning examples (with spaCy NER):\n",
+      "📊 Name cleaning examples (with spaCy NER):\n",
       "====================================================================================================\n",
       "Original Name                                      | Cleaned Name                  \n",
       "====================================================================================================\n",
       "Super Pose Book Vol.1 - ControlNet                 | Super Pose Book               \n",
       "Liyuu LoRA                                         | Liyuu                         \n",
-      "HashimotoKanna/ \u6a4b\u672c\u74b0\u5948 _JP_Actress                   | HashimotoKanna                \n",
+      "HashimotoKanna/ 橋本環奈 _JP_Actress                   | HashimotoKanna                \n",
       "Emma Watson (JG)                                   | Emma Watson                   \n",
-      "Gal Gadot\u300cLoRa\u300d                                    | Gal Gadot                     \n",
-      "Scarlett Johansson\u300cLoRa\u300d                           | Scarlett Johansson            \n",
-      "Gakki | Aragaki Yui | \u65b0\u57a3\u7d50\u8863                         | Gakki                         \n",
-      "Actress Satomi_\u77f3\u539f\u25cb\u25cb                                | Actress Satomi                \n",
+      "Gal Gadot「LoRa」                                    | Gal Gadot                     \n",
+      "Scarlett Johansson「LoRa」                           | Scarlett Johansson            \n",
+      "Gakki | Aragaki Yui | 新垣結衣                         | Gakki                         \n",
+      "Actress Satomi_石原○○                                | Actress Satomi                \n",
       "Game of Thrones Cast                               | Game Thrones Cast             \n",
-      "Natalie Portman\u300cLoRa\u300d                              | Natalie Portman               \n",
+      "Natalie Portman「LoRa」                              | Natalie Portman               \n",
       "Emma Watson LoRA                                   | Emma Watson                   \n",
       "====================================================================================================\n",
       "\n",
-      "\ud83e\uddea Leetspeak translation examples:\n",
+      "🧪 Leetspeak translation examples:\n",
       "  4kira LoRA                     -> akira\n",
       "  3mma Watson v2                 -> Watson\n",
       "  1rene LORA                     -> irene\n",
       "  L3vi Ackerman                  -> Levi Ackerman\n",
       "\n",
-      "\ud83d\udcc8 Statistics:\n",
+      "📈 Statistics:\n",
       "  Total rows: 18\n",
       "  Non-empty names: 18\n",
       "  Empty names: 0\n",
       "\n",
-      "\ud83c\udfaf Sample spaCy NER results:\n",
+      "🎯 Sample spaCy NER results:\n",
       "  1. IU\n",
       "  2. Super Pose Book\n",
       "  3. Liyuu\n",
@@ -187,8 +187,8 @@
       "  9. Emma Watson\n",
       "  10. Gal Gadot\n",
       "\n",
-      "\u2705 Cleaned 18 names using spaCy NER\n",
-      "\ud83d\udcbe Saved to /home/lauhp/000_PHD/000_010_PUBLICATION/CODE/pm-paper/data/CSV/NER_POI_step01_pre_annotation.csv\n"
+      "✅ Cleaned 18 names using spaCy NER\n",
+      "💾 Saved to /home/lauhp/000_PHD/000_010_PUBLICATION/CODE/pm-paper/data/CSV/NER_POI_step01_pre_annotation.csv\n"
      ]
     }
    ],
@@ -203,13 +203,13 @@
     "# You may need to download it first: python -m spacy download en_core_web_sm\n",
     "try:\n",
     "    nlp = spacy.load(\"en_core_web_sm\")\n",
-    "    print(\"\u2705 spaCy model loaded: en_core_web_sm\")\n",
+    "    print(\"✅ spaCy model loaded: en_core_web_sm\")\n",
     "except OSError:\n",
-    "    print(\"\u274c spaCy model not found. Downloading...\")\n",
+    "    print(\"❌ spaCy model not found. Downloading...\")\n",
     "    import subprocess\n",
     "    subprocess.run([\"python\", \"-m\", \"spacy\", \"download\", \"en_core_web_sm\"])\n",
     "    nlp = spacy.load(\"en_core_web_sm\")\n",
-    "    print(\"\u2705 spaCy model downloaded and loaded\")\n",
+    "    print(\"✅ spaCy model downloaded and loaded\")\n",
     "\n",
     "# Set up paths\n",
     "current_dir = Path.cwd()\n",
@@ -282,8 +282,8 @@
     "    name = re.sub(r'\\([^)]*\\)', '', name)\n",
     "    name = re.sub(r'\\[[^\\]]*\\]', '', name)\n",
     "    \n",
-    "    # Remove special characters like \u300c\u300d\n",
-    "    name = re.sub(r'[\u300c\u300d\u300e\u300f\u3010\u3011\u3008\u3009\u300a\u300b]', '', name)\n",
+    "    # Remove special characters like 「」\n",
+    "    name = re.sub(r'[「」『』【】〈〉《》]', '', name)\n",
     "    \n",
     "    # Handle pipe - keep first part\n",
     "    if '|' in name:\n",
@@ -339,7 +339,7 @@
     "    Complete name cleaning pipeline with spaCy NER.\n",
     "    \n",
     "    Pipeline:\n",
-    "    1. Translate leetspeak (4\u2192a, 3\u2192e, 1\u2192i, etc.)\n",
+    "    1. Translate leetspeak (4→a, 3→e, 1→i, etc.)\n",
     "    2. Remove noise (emoji, version tags, LoRA terms)\n",
     "    3. Use spaCy to extract PERSON entities\n",
     "    4. Fallback to capitalized words or cleaned text\n",
@@ -356,11 +356,11 @@
     "    return person_name\n",
     "\n",
     "# Apply name cleaning with spaCy\n",
-    "print(\"\\n\ud83d\udd04 Processing names with spaCy NER...\")\n",
+    "print(\"\\n🔄 Processing names with spaCy NER...\")\n",
     "df['real_name'] = df['name'].apply(clean_name_with_spacy)\n",
     "\n",
     "# Show examples with detailed comparison\n",
-    "print(\"\\n\ud83d\udcca Name cleaning examples (with spaCy NER):\")\n",
+    "print(\"\\n📊 Name cleaning examples (with spaCy NER):\")\n",
     "print(\"=\" * 100)\n",
     "print(f\"{'Original Name':<50} | {'Cleaned Name':<30}\")\n",
     "print(\"=\" * 100)\n",
@@ -375,31 +375,31 @@
     "print(\"=\" * 100)\n",
     "\n",
     "# Show specific test cases\n",
-    "print(\"\\n\ud83e\uddea Leetspeak translation examples:\")\n",
+    "print(\"\\n🧪 Leetspeak translation examples:\")\n",
     "test_names = ['4kira LoRA', '3mma Watson v2', '1rene LORA', 'L3vi Ackerman']\n",
     "for test in test_names:\n",
     "    result = clean_name_with_spacy(test)\n",
     "    print(f\"  {test:<30} -> {result}\")\n",
     "\n",
     "# Statistics\n",
-    "print(f\"\\n\ud83d\udcc8 Statistics:\")\n",
+    "print(f\"\\n📈 Statistics:\")\n",
     "print(f\"  Total rows: {len(df)}\")\n",
     "print(f\"  Non-empty names: {(df['real_name'] != '').sum()}\")\n",
     "print(f\"  Empty names: {(df['real_name'] == '').sum()}\")\n",
     "\n",
     "# Show some examples of what spaCy identified\n",
-    "print(\"\\n\ud83c\udfaf Sample spaCy NER results:\")\n",
+    "print(\"\\n🎯 Sample spaCy NER results:\")\n",
     "sample_names = df['real_name'].head(20).tolist()\n",
     "for i, name in enumerate(sample_names[:10], 1):\n",
     "    if name:\n",
     "        print(f\"  {i}. {name}\")\n",
     "\n",
-    "print(f\"\\n\u2705 Cleaned {len(df)} names using spaCy NER\")\n",
+    "print(f\"\\n✅ Cleaned {len(df)} names using spaCy NER\")\n",
     "\n",
     "# Save intermediate result\n",
     "output_step1 = current_dir.parent / \"data/CSV/NER_POI_step01_pre_annotation.csv\"\n",
     "df.to_csv(output_step1, index=False)\n",
-    "print(f\"\ud83d\udcbe Saved to {output_step1}\")\n"
+    "print(f\"💾 Saved to {output_step1}\")\n"
    ]
   },
   {
@@ -444,7 +444,7 @@
       "8      Emma Watson                                               actor\n",
       "9        Gal Gadot                                               model\n",
       "\n",
-      "\ud83d\udd0d Checking 'Irene' entries:\n",
+      "🔍 Checking 'Irene' entries:\n",
       "  Name: Irene\n",
       "  Tags: ['girl', 'photorealistic', 'asian', 'woman', 'beautiful', 'celebrity', 'korean']\n",
       "  Country: \n",
@@ -485,7 +485,7 @@
     "\n",
     "poi_df[\"tags\"] = poi_df.apply(combine_tags, axis=1)\n",
     "\n",
-    "# Step 2: Build tag \u2192 (country, nationality) mapping with PRIORITIES\n",
+    "# Step 2: Build tag → (country, nationality) mapping with PRIORITIES\n",
     "tag_to_country_nationality = {}\n",
     "# We'll use a priority score: direct country name = 3, nationality = 2, word parts = 1\n",
     "\n",
@@ -563,7 +563,7 @@
     "\n",
     "poi_df[[\"likely_country\", \"likely_nationality\"]] = poi_df[\"tags\"].apply(infer_country_and_nationality)\n",
     "\n",
-    "# Step 4: Build tag \u2192 profession mapping\n",
+    "# Step 4: Build tag → profession mapping\n",
     "profession_alias_map = {}\n",
     "\n",
     "for _, row in professions_df.iterrows():\n",
@@ -611,7 +611,7 @@
     "# Check specific case: Irene with korean tag\n",
     "irene_rows = poi_df[poi_df['real_name'].str.contains('irene', case=False, na=False)]\n",
     "if len(irene_rows) > 0:\n",
-    "    print(f\"\\n\ud83d\udd0d Checking 'Irene' entries:\")\n",
+    "    print(f\"\\n🔍 Checking 'Irene' entries:\")\n",
     "    for idx, row in irene_rows.iterrows():\n",
     "        print(f\"  Name: {row['real_name']}\")\n",
     "        print(f\"  Tags: {row['tags']}\")\n",
@@ -652,7 +652,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u274c Error: deepseek_api_key.txt not found in misc/credentials/\n",
+      "❌ Error: deepseek_api_key.txt not found in misc/credentials/\n",
       "   Please create this file with your API key\n"
      ]
     },
@@ -663,7 +663,7 @@
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[10], line 37\u001b[0m\n\u001b[1;32m     35\u001b[0m \u001b[38;5;66;03m# === LOAD API KEY ===\u001b[39;00m\n\u001b[1;32m     36\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 37\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mapi_key_file\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m f:\n\u001b[1;32m     38\u001b[0m         api_key \u001b[38;5;241m=\u001b[39m f\u001b[38;5;241m.\u001b[39mread()\u001b[38;5;241m.\u001b[39mstrip()\n\u001b[1;32m     39\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\u2705 Deepseek API key loaded\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "Cell \u001b[0;32mIn[10], line 37\u001b[0m\n\u001b[1;32m     35\u001b[0m \u001b[38;5;66;03m# === LOAD API KEY ===\u001b[39;00m\n\u001b[1;32m     36\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 37\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mapi_key_file\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m f:\n\u001b[1;32m     38\u001b[0m         api_key \u001b[38;5;241m=\u001b[39m f\u001b[38;5;241m.\u001b[39mread()\u001b[38;5;241m.\u001b[39mstrip()\n\u001b[1;32m     39\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m✅ Deepseek API key loaded\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
       "File \u001b[0;32m~/.local/lib/python3.10/site-packages/IPython/core/interactiveshell.py:324\u001b[0m, in \u001b[0;36m_modified_open\u001b[0;34m(file, *args, **kwargs)\u001b[0m\n\u001b[1;32m    317\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m file \u001b[38;5;129;01min\u001b[39;00m {\u001b[38;5;241m0\u001b[39m, \u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m2\u001b[39m}:\n\u001b[1;32m    318\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m    319\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mIPython won\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt let you open fd=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfile\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m by default \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    320\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mas it is likely to crash IPython. If you know what you are doing, \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    321\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124myou can use builtins\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m open.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    322\u001b[0m     )\n\u001b[0;32m--> 324\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mio_open\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfile\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
       "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '/home/lauhp/000_PHD/000_010_PUBLICATION/CODE/pm-paper/misc/credentials/deepseek_api_key.txt'"
      ]
@@ -708,9 +708,9 @@
     "try:\n",
     "    with open(api_key_file) as f:\n",
     "        api_key = f.read().strip()\n",
-    "    print(\"\u2705 Deepseek API key loaded\")\n",
+    "    print(\"✅ Deepseek API key loaded\")\n",
     "except FileNotFoundError:\n",
-    "    print(\"\u274c Error: deepseek_api_key.txt not found in misc/credentials/\")\n",
+    "    print(\"❌ Error: deepseek_api_key.txt not found in misc/credentials/\")\n",
     "    print(\"   Please create this file with your API key\")\n",
     "    raise\n",
     "\n",
@@ -726,9 +726,9 @@
     "# Load profession categories and keywords\n",
     "try:\n",
     "    prof_mapped_df = pd.read_csv(professions_mapped_file)\n",
-    "    print(f\"\u2705 Loaded profession mapping with {len(prof_mapped_df)} categories\")\n",
+    "    print(f\"✅ Loaded profession mapping with {len(prof_mapped_df)} categories\")\n",
     "except:\n",
-    "    print(\"\u26a0\ufe0f Warning: professions_mapped.csv not found, using default categories\")\n",
+    "    print(\"⚠️ Warning: professions_mapped.csv not found, using default categories\")\n",
     "\n",
     "profession_str = \", \".join(PROFESSION_CATEGORIES)\n",
     "\n",
@@ -895,11 +895,11 @@
     "            df.to_csv(output_file, index=False)\n",
     "            with open(index_file, 'w') as f:\n",
     "                f.write(str(current_index))\n",
-    "            print(f\"\u2705 Progress saved after {i+1} rows\")\n",
+    "            print(f\"✅ Progress saved after {i+1} rows\")\n",
     "        \n",
     "        time.sleep(1)  # Rate limiting\n",
     "    \n",
-    "    print(f\"\\n\u2705 Done! Final results saved to {output_file}\")\n",
+    "    print(f\"\\n✅ Done! Final results saved to {output_file}\")\n",
     "    \n",
     "    # Summary statistics\n",
     "    print(\"\\n=== Summary Statistics ===\")\n",
@@ -917,15 +917,15 @@
     "    print(df[display_cols].head(10).to_string(index=False))\n",
     "\n",
     "except Exception as e:\n",
-    "    print(f\"\u26a0\ufe0f Error encountered: {e}\")\n",
-    "    print(f\"\u26a0\ufe0f Last processed index: {current_index}\")\n",
+    "    print(f\"⚠️ Error encountered: {e}\")\n",
+    "    print(f\"⚠️ Last processed index: {current_index}\")\n",
     "    \n",
     "    # Save progress before exiting\n",
     "    df.to_csv(output_file, index=False)\n",
     "    with open(index_file, 'w') as f:\n",
     "        f.write(str(current_index))\n",
     "    \n",
-    "    print(f\"\u26a0\ufe0f Progress saved up to row {current_index}\")\n"
+    "    print(f\"⚠️ Progress saved up to row {current_index}\")\n"
    ]
   },
   {
@@ -954,169 +954,7 @@
    "id": "qwen_code",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import pandas as pd",
-    "import json",
-    "import time",
-    "import re",
-    "from pathlib import Path",
-    "from tqdm import tqdm",
-    "from openai import OpenAI",
-    "",
-    "current_dir = Path.cwd()",
-    "input_file = current_dir.parent / \"data/CSV/NER_POI_step02_annotated.csv\"",
-    "api_key_file = current_dir.parent / \"misc/credentials/qwen_api_key.txt\"",
-    "",
-    "# === CONFIGURATION ===",
-    "TEST_MODE = True",
-    "TEST_SIZE = 10",
-    "MAX_ROWS = 20000",
-    "SAVE_INTERVAL = 10",
-    "",
-    "PROFESSION_CATEGORIES = [",
-    "    \"actor\", \"adult performer\", \"singer/musician\", \"model\",",
-    "    \"online personality\", \"public figure\", \"voice actor/ASMR\",",
-    "    \"sports professional\", \"tv personality\"",
-    "]",
-    "",
-    "# === LOAD API KEY ===",
-    "try:",
-    "    with open(api_key_file) as f:",
-    "        api_key = f.read().strip()",
-    "    print(\"\u2705 Qwen API key loaded\")",
-    "    print(f\"   Key starts with: {api_key[:10]}...\")",
-    "except FileNotFoundError:",
-    "    print(\"\u274c Error: qwen_api_key.txt not found\")",
-    "    raise",
-    "",
-    "# Initialize OpenAI client for Qwen (matching dashboard example)",
-    "client = OpenAI(",
-    "    api_key=api_key,",
-    "    base_url=\"https://dashscope-intl.aliyuncs.com/compatible-mode/v1\"",
-    ")",
-    "",
-    "# === LOAD DATA ===",
-    "df = pd.read_csv(input_file)",
-    "print(f\"Loaded {len(df)} rows\")",
-    "",
-    "if TEST_MODE:",
-    "    print(f\"Running in TEST MODE with {TEST_SIZE} samples\")",
-    "    df = df.head(TEST_SIZE).copy()",
-    "elif MAX_ROWS:",
-    "    df = df.head(MAX_ROWS).copy()",
-    "",
-    "# === CREATE PROMPT ===",
-    "def create_prompt(name: str, tags: list, country: str) -> str:",
-    "    tags_str = \", \".join(tags[:5]) if tags else \"none\"",
-    "    country_str = country if country else \"unknown\"",
-    "    ",
-    "    return f\"\"\"You are an expert at identifying public figures.",
-    "",
-    "Given: Name: {name}, Tags: {tags_str}, Country: {country_str}",
-    "",
-    "Provide in JSON format:",
-    "{{",
-    "  \"full_name\": \"<full name>\",",
-    "  \"gender\": \"<Male/Female/Other/Unknown>\",",
-    "  \"professions\": [\"<profession 1>\", \"<profession 2>\", \"<profession 3>\"],",
-    "  \"country\": \"<country>\"",
-    "}}",
-    "",
-    "Choose professions ONLY from: {\", \".join(PROFESSION_CATEGORIES)}",
-    "- Max 3 professions, ordered by relevance",
-    "- \"online personality\" includes streamers, cosplayers, influencers",
-    "- Return \"Unknown\" if uncertain",
-    "",
-    "Return ONLY JSON, no extra text.\"\"\"",
-    "",
-    "# === QUERY QWEN ===",
-    "def query_qwen(prompt: str) -> dict:",
-    "    \"\"\"Query Qwen using OpenAI-compatible API (matching dashboard example).\"\"\"",
-    "    for attempt in range(3):",
-    "        try:",
-    "            completion = client.chat.completions.create(",
-    "                model=\"qwen-max\",  # Note: dashboard shows \"qwen3-max\" but \"qwen-max\" works too",
-    "                messages=[",
-    "                    {\"role\": \"user\", \"content\": prompt}",
-    "                ],",
-    "                temperature=0.1,",
-    "                max_tokens=500,",
-    "                stream=False  # Disable streaming for easier parsing",
-    "            )",
-    "            ",
-    "            content = completion.choices[0].message.content",
-    "            ",
-    "            # Parse JSON from response",
-    "            json_match = re.search(r'\\{[^}]+\\}', content, re.DOTALL)",
-    "            if json_match:",
-    "                return json.loads(json_match.group())",
-    "            ",
-    "            return None",
-    "            ",
-    "        except Exception as e:",
-    "            print(f\"Qwen error (attempt {attempt+1}): {e}\")",
-    "            if attempt < 2:",
-    "                time.sleep(2 ** attempt)",
-    "    ",
-    "    return None",
-    "",
-    "# === PROCESS ===",
-    "output_file = current_dir.parent / f\"data/CSV/qwen_annotated_POI{'_test' if TEST_MODE else ''}.csv\"",
-    "index_file = current_dir.parent / \"misc/qwen_query_index.txt\"",
-    "",
-    "current_index = 0",
-    "if index_file.exists():",
-    "    with open(index_file) as f:",
-    "        current_index = int(f.read().strip())",
-    "",
-    "for col in ['full_name', 'gender', 'profession_llm', 'country']:",
-    "    if col not in df.columns:",
-    "        df[col] = 'Unknown'",
-    "",
-    "print(f\"\\nAnnotating with QWEN-MAX (OpenAI-compatible API) - rows {current_index} to {len(df)}...\")",
-    "",
-    "try:",
-    "    for i in tqdm(range(current_index, len(df)), desc=\"Qwen\"):",
-    "        row = df.iloc[i]",
-    "        ",
-    "        tags = [str(row[f'tag_{j}']).lower() for j in range(1, 8) ",
-    "                if f'tag_{j}' in row and pd.notna(row[f'tag_{j}'])]",
-    "        ",
-    "        prompt = create_prompt(",
-    "            row.get('real_name', row.get('name', '')),",
-    "            tags,",
-    "            row.get('likely_country', '')",
-    "        )",
-    "        ",
-    "        result = query_qwen(prompt)",
-    "        ",
-    "        if result:",
-    "            df.at[i, 'full_name'] = result.get('full_name', 'Unknown')",
-    "            df.at[i, 'gender'] = result.get('gender', 'Unknown')",
-    "            profs = result.get('professions', [])",
-    "            df.at[i, 'profession_llm'] = \", \".join(profs[:3]) if isinstance(profs, list) else str(profs)",
-    "            df.at[i, 'country'] = result.get('country', 'Unknown')",
-    "        ",
-    "        current_index = i + 1",
-    "        ",
-    "        if (i + 1) % SAVE_INTERVAL == 0 or (i + 1) == len(df):",
-    "            df.to_csv(output_file, index=False)",
-    "            with open(index_file, 'w') as f:",
-    "                f.write(str(current_index))",
-    "            print(f\"\u2705 Saved after {i+1} rows\")",
-    "        ",
-    "        time.sleep(0.5)",
-    "    ",
-    "    print(f\"\\n\u2705 Done! Results: {output_file}\")",
-    "    print(f\"\\nTop professions:\\n{df['profession_llm'].value_counts().head(10)}\")",
-    "    ",
-    "except Exception as e:",
-    "    print(f\"\u26a0\ufe0f Error: {e}\")",
-    "    df.to_csv(output_file, index=False)",
-    "    with open(index_file, 'w') as f:",
-    "        f.write(str(current_index))",
-    ""
-   ]
+   "source": "import pandas as pd\nimport json\nimport time\nimport re\nfrom pathlib import Path\nfrom tqdm import tqdm\nfrom openai import OpenAI\n\ncurrent_dir = Path.cwd()\ninput_file = current_dir.parent / \"data/CSV/NER_POI_step02_annotated.csv\"\napi_key_file = current_dir.parent / \"misc/credentials/qwen_api_key.txt\"\n\n# === CONFIGURATION ===\nTEST_MODE = True\nTEST_SIZE = 10\nMAX_ROWS = 20000\nSAVE_INTERVAL = 10\n\nPROFESSION_CATEGORIES = [\n    \"actor\", \"adult performer\", \"singer/musician\", \"model\",\n    \"online personality\", \"public figure\", \"voice actor/ASMR\",\n    \"sports professional\", \"tv personality\"\n]\n\n# === LOAD API KEY ===\ntry:\n    with open(api_key_file) as f:\n        api_key = f.read().strip()\n    print(\"✅ Qwen API key loaded\")\n    print(f\"   Key starts with: {api_key[:10]}...\")\nexcept FileNotFoundError:\n    print(\"❌ Error: qwen_api_key.txt not found\")\n    raise\n\n# Initialize OpenAI client for Qwen (matching dashboard example)\nclient = OpenAI(\n    api_key=api_key,\n    base_url=\"https://dashscope-intl.aliyuncs.com/compatible-mode/v1\"\n)\n\n# === LOAD DATA ===\ndf = pd.read_csv(input_file)\nprint(f\"Loaded {len(df)} rows\")\n\nif TEST_MODE:\n    print(f\"Running in TEST MODE with {TEST_SIZE} samples\")\n    df = df.head(TEST_SIZE).copy()\nelif MAX_ROWS:\n    df = df.head(MAX_ROWS).copy()\n\n# === CREATE PROMPT ===\ndef create_prompt(name: str, tags: list, country: str) -> str:\n    tags_str = \", \".join(tags[:5]) if tags else \"none\"\n    country_str = country if country else \"unknown\"\n    \n    return f\"\"\"You are an expert at identifying public figures.\n\nGiven: Name: {name}, Tags: {tags_str}, Country: {country_str}\n\nProvide in JSON format:\n{{\n  \"full_name\": \"<full name>\",\n  \"gender\": \"<Male/Female/Other/Unknown>\",\n  \"professions\": [\"<profession 1>\", \"<profession 2>\", \"<profession 3>\"],\n  \"country\": \"<country>\"\n}}\n\nChoose professions ONLY from: {\", \".join(PROFESSION_CATEGORIES)}\n- Max 3 professions, ordered by relevance\n- \"online personality\" includes streamers, cosplayers, influencers\n- Return \"Unknown\" if uncertain\n\nReturn ONLY JSON, no extra text.\"\"\"\n\n# === QUERY QWEN ===\ndef query_qwen(prompt: str) -> dict:\n    \"\"\"Query Qwen using OpenAI-compatible API (matching dashboard example).\"\"\"\n    for attempt in range(3):\n        try:\n            completion = client.chat.completions.create(\n                model=\"qwen-max\",  # Note: dashboard shows \"qwen3-max\" but \"qwen-max\" works too\n                messages=[\n                    {\"role\": \"user\", \"content\": prompt}\n                ],\n                temperature=0.1,\n                max_tokens=500,\n                stream=False  # Disable streaming for easier parsing\n            )\n            \n            content = completion.choices[0].message.content\n            \n            # Parse JSON from response\n            json_match = re.search(r'\\{[^}]+\\}', content, re.DOTALL)\n            if json_match:\n                return json.loads(json_match.group())\n            \n            return None\n            \n        except Exception as e:\n            print(f\"Qwen error (attempt {attempt+1}): {e}\")\n            if attempt < 2:\n                time.sleep(2 ** attempt)\n    \n    return None\n\n# === PROCESS ===\noutput_file = current_dir.parent / f\"data/CSV/qwen_annotated_POI{'_test' if TEST_MODE else ''}.csv\"\nindex_file = current_dir.parent / \"misc/qwen_query_index.txt\"\n\ncurrent_index = 0\nif index_file.exists():\n    with open(index_file) as f:\n        current_index = int(f.read().strip())\n\nfor col in ['full_name', 'gender', 'profession_llm', 'country']:\n    if col not in df.columns:\n        df[col] = 'Unknown'\n\nprint(f\"\\nAnnotating with QWEN-MAX (OpenAI-compatible API) - rows {current_index} to {len(df)}...\")\n\ntry:\n    for i in tqdm(range(current_index, len(df)), desc=\"Qwen\"):\n        row = df.iloc[i]\n        \n        tags = [str(row[f'tag_{j}']).lower() for j in range(1, 8)\n                if f'tag_{j}' in row and pd.notna(row[f'tag_{j}'])]\n        \n        prompt = create_prompt(\n            row.get('real_name', row.get('name', '')),\n            tags,\n            row.get('likely_country', '')\n        )\n        \n        result = query_qwen(prompt)\n        \n        if result:\n            df.at[i, 'full_name'] = result.get('full_name', 'Unknown')\n            df.at[i, 'gender'] = result.get('gender', 'Unknown')\n            profs = result.get('professions', [])\n            df.at[i, 'profession_llm'] = \", \".join(profs[:3]) if isinstance(profs, list) else str(profs)\n            df.at[i, 'country'] = result.get('country', 'Unknown')\n        \n        current_index = i + 1\n        \n        if (i + 1) % SAVE_INTERVAL == 0 or (i + 1) == len(df):\n            df.to_csv(output_file, index=False)\n            with open(index_file, 'w') as f:\n                f.write(str(current_index))\n            print(f\"✅ Saved after {i+1} rows\")\n        \n        time.sleep(0.5)\n    \n    print(f\"\\n✅ Done! Results: {output_file}\")\n    print(f\"\\nTop professions:\\n{df['profession_llm'].value_counts().head(10)}\")\n    \nexcept Exception as e:\n    print(f\"⚠️ Error: {e}\")\n    df.to_csv(output_file, index=False)\n    with open(index_file, 'w') as f:\n        f.write(str(current_index))"
   },
   {
    "cell_type": "markdown",
@@ -1140,165 +978,7 @@
    "id": "llama_code",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import pandas as pd",
-    "import json",
-    "import time",
-    "import requests",
-    "import re",
-    "from pathlib import Path",
-    "from tqdm import tqdm",
-    "",
-    "current_dir = Path.cwd()",
-    "input_file = current_dir.parent / \"data/CSV/NER_POI_step02_annotated.csv\"",
-    "api_key_file = current_dir.parent / \"misc/credentials/together_api_key.txt\"",
-    "",
-    "# === CONFIGURATION ===",
-    "TEST_MODE = True",
-    "TEST_SIZE = 10",
-    "MAX_ROWS = 20000",
-    "SAVE_INTERVAL = 10",
-    "",
-    "PROFESSION_CATEGORIES = [",
-    "    \"actor\", \"adult performer\", \"singer/musician\", \"model\",",
-    "    \"online personality\", \"public figure\", \"voice actor/ASMR\",",
-    "    \"sports professional\", \"tv personality\"",
-    "]",
-    "",
-    "# === LOAD API KEY ===",
-    "try:",
-    "    with open(api_key_file) as f:",
-    "        api_key = f.read().strip()",
-    "    print(\"\u2705 Llama API key loaded\")",
-    "except FileNotFoundError:",
-    "    print(\"\u274c Error: together_api_key.txt not found\")",
-    "    raise",
-    "",
-    "# === LOAD DATA ===",
-    "df = pd.read_csv(input_file)",
-    "print(f\"Loaded {len(df)} rows\")",
-    "",
-    "if TEST_MODE:",
-    "    print(f\"Running in TEST MODE with {TEST_SIZE} samples\")",
-    "    df = df.head(TEST_SIZE).copy()",
-    "elif MAX_ROWS:",
-    "    df = df.head(MAX_ROWS).copy()",
-    "",
-    "# === CREATE PROMPT ===",
-    "def create_prompt(name: str, tags: list, country: str) -> str:",
-    "    tags_str = \", \".join(tags[:5]) if tags else \"none\"",
-    "    country_str = country if country else \"unknown\"",
-    "    ",
-    "    return f\"\"\"You are an expert at identifying public figures.",
-    "",
-    "Given: Name: {name}, Tags: {tags_str}, Country: {country_str}",
-    "",
-    "Provide in JSON format:",
-    "{{",
-    "  \"full_name\": \"<full name>\",",
-    "  \"gender\": \"<Male/Female/Other/Unknown>\",",
-    "  \"professions\": [\"<profession 1>\", \"<profession 2>\", \"<profession 3>\"],",
-    "  \"country\": \"<country>\"",
-    "}}",
-    "",
-    "Choose professions ONLY from: {\", \".join(PROFESSION_CATEGORIES)}",
-    "- Max 3 professions, ordered by relevance",
-    "- \"online personality\" includes streamers, cosplayers, influencers",
-    "- Return \"Unknown\" if uncertain",
-    "",
-    "Return ONLY JSON, no extra text.\"\"\"",
-    "",
-    "# === QUERY LLAMA ===",
-    "def query_llama(prompt: str) -> dict:",
-    "    url = \"https://api.together.xyz/v1/chat/completions\"",
-    "    ",
-    "    headers = {",
-    "        \"Authorization\": f\"Bearer {api_key}\",",
-    "        \"Content-Type\": \"application/json\"",
-    "    }",
-    "    ",
-    "    data = {",
-    "        \"model\": \"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo\",",
-    "        \"messages\": [{\"role\": \"user\", \"content\": prompt}],",
-    "        \"temperature\": 0.1,",
-    "        \"max_tokens\": 500",
-    "    }",
-    "    ",
-    "    for attempt in range(3):",
-    "        try:",
-    "            response = requests.post(url, headers=headers, json=data, timeout=30)",
-    "            response.raise_for_status()",
-    "            result = response.json()",
-    "            ",
-    "            if 'choices' in result:",
-    "                content = result['choices'][0]['message']['content']",
-    "                json_match = re.search(r'\\{[^}]+\\}', content, re.DOTALL)",
-    "                if json_match:",
-    "                    return json.loads(json_match.group())",
-    "            return None",
-    "        except Exception as e:",
-    "            print(f\"Llama error (attempt {attempt+1}): {e}\")",
-    "            if attempt < 2:",
-    "                time.sleep(2 ** attempt)",
-    "    return None",
-    "",
-    "# === PROCESS ===",
-    "output_file = current_dir.parent / f\"data/CSV/llama_annotated_POI{'_test' if TEST_MODE else ''}.csv\"",
-    "index_file = current_dir.parent / \"misc/llama_query_index.txt\"",
-    "",
-    "current_index = 0",
-    "if index_file.exists():",
-    "    with open(index_file) as f:",
-    "        current_index = int(f.read().strip())",
-    "",
-    "for col in ['full_name', 'gender', 'profession_llm', 'country']:",
-    "    if col not in df.columns:",
-    "        df[col] = 'Unknown'",
-    "",
-    "print(f\"\\nAnnotating with LLAMA 3.1 70B - rows {current_index} to {len(df)}...\")",
-    "",
-    "try:",
-    "    for i in tqdm(range(current_index, len(df)), desc=\"Llama\"):",
-    "        row = df.iloc[i]",
-    "        ",
-    "        tags = [str(row[f'tag_{j}']).lower() for j in range(1, 8) ",
-    "                if f'tag_{j}' in row and pd.notna(row[f'tag_{j}'])]",
-    "        ",
-    "        prompt = create_prompt(",
-    "            row.get('real_name', row.get('name', '')),",
-    "            tags,",
-    "            row.get('likely_country', '')",
-    "        )",
-    "        ",
-    "        result = query_llama(prompt)",
-    "        ",
-    "        if result:",
-    "            df.at[i, 'full_name'] = result.get('full_name', 'Unknown')",
-    "            df.at[i, 'gender'] = result.get('gender', 'Unknown')",
-    "            profs = result.get('professions', [])",
-    "            df.at[i, 'profession_llm'] = \", \".join(profs[:3]) if isinstance(profs, list) else str(profs)",
-    "            df.at[i, 'country'] = result.get('country', 'Unknown')",
-    "        ",
-    "        current_index = i + 1",
-    "        ",
-    "        if (i + 1) % SAVE_INTERVAL == 0 or (i + 1) == len(df):",
-    "            df.to_csv(output_file, index=False)",
-    "            with open(index_file, 'w') as f:",
-    "                f.write(str(current_index))",
-    "            print(f\"\u2705 Saved after {i+1} rows\")",
-    "        ",
-    "        time.sleep(0.5)",
-    "    ",
-    "    print(f\"\\n\u2705 Done! Results: {output_file}\")",
-    "    print(f\"\\nTop professions:\\n{df['profession_llm'].value_counts().head(10)}\")",
-    "    ",
-    "except Exception as e:",
-    "    print(f\"\u26a0\ufe0f Error: {e}\")",
-    "    df.to_csv(output_file, index=False)",
-    "    with open(index_file, 'w') as f:",
-    "        f.write(str(current_index))",
-    ""
-   ]
+   "source": "import pandas as pd\nimport json\nimport time\nimport requests\nimport re\nfrom pathlib import Path\nfrom tqdm import tqdm\n\ncurrent_dir = Path.cwd()\ninput_file = current_dir.parent / \"data/CSV/NER_POI_step02_annotated.csv\"\napi_key_file = current_dir.parent / \"misc/credentials/together_api_key.txt\"\n\n# === CONFIGURATION ===\nTEST_MODE = True\nTEST_SIZE = 10\nMAX_ROWS = 20000\nSAVE_INTERVAL = 10\n\nPROFESSION_CATEGORIES = [\n    \"actor\", \"adult performer\", \"singer/musician\", \"model\",\n    \"online personality\", \"public figure\", \"voice actor/ASMR\",\n    \"sports professional\", \"tv personality\"\n]\n\n# === LOAD API KEY ===\ntry:\n    with open(api_key_file) as f:\n        api_key = f.read().strip()\n    print(\"✅ Llama API key loaded\")\nexcept FileNotFoundError:\n    print(\"❌ Error: together_api_key.txt not found\")\n    raise\n\n# === LOAD DATA ===\ndf = pd.read_csv(input_file)\nprint(f\"Loaded {len(df)} rows\")\n\nif TEST_MODE:\n    print(f\"Running in TEST MODE with {TEST_SIZE} samples\")\n    df = df.head(TEST_SIZE).copy()\nelif MAX_ROWS:\n    df = df.head(MAX_ROWS).copy()\n\n# === CREATE PROMPT ===\ndef create_prompt(name: str, tags: list, country: str) -> str:\n    tags_str = \", \".join(tags[:5]) if tags else \"none\"\n    country_str = country if country else \"unknown\"\n    \n    return f\"\"\"You are an expert at identifying public figures.\n\nGiven: Name: {name}, Tags: {tags_str}, Country: {country_str}\n\nProvide in JSON format:\n{{\n  \"full_name\": \"<full name>\",\n  \"gender\": \"<Male/Female/Other/Unknown>\",\n  \"professions\": [\"<profession 1>\", \"<profession 2>\", \"<profession 3>\"],\n  \"country\": \"<country>\"\n}}\n\nChoose professions ONLY from: {\", \".join(PROFESSION_CATEGORIES)}\n- Max 3 professions, ordered by relevance\n- \"online personality\" includes streamers, cosplayers, influencers\n- Return \"Unknown\" if uncertain\n\nReturn ONLY JSON, no extra text.\"\"\"\n\n# === QUERY LLAMA ===\ndef query_llama(prompt: str) -> dict:\n    url = \"https://api.together.xyz/v1/chat/completions\"\n    \n    headers = {\n        \"Authorization\": f\"Bearer {api_key}\",\n        \"Content-Type\": \"application/json\"\n    }\n    \n    data = {\n        \"model\": \"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo\",\n        \"messages\": [{\"role\": \"user\", \"content\": prompt}],\n        \"temperature\": 0.1,\n        \"max_tokens\": 500\n    }\n    \n    for attempt in range(3):\n        try:\n            response = requests.post(url, headers=headers, json=data, timeout=30)\n            response.raise_for_status()\n            result = response.json()\n            \n            if 'choices' in result:\n                content = result['choices'][0]['message']['content']\n                json_match = re.search(r'\\{[^}]+\\}', content, re.DOTALL)\n                if json_match:\n                    return json.loads(json_match.group())\n            return None\n        except Exception as e:\n            print(f\"Llama error (attempt {attempt+1}): {e}\")\n            if attempt < 2:\n                time.sleep(2 ** attempt)\n    return None\n\n# === PROCESS ===\noutput_file = current_dir.parent / f\"data/CSV/llama_annotated_POI{'_test' if TEST_MODE else ''}.csv\"\nindex_file = current_dir.parent / \"misc/llama_query_index.txt\"\n\ncurrent_index = 0\nif index_file.exists():\n    with open(index_file) as f:\n        current_index = int(f.read().strip())\n\nfor col in ['full_name', 'gender', 'profession_llm', 'country']:\n    if col not in df.columns:\n        df[col] = 'Unknown'\n\nprint(f\"\\nAnnotating with LLAMA 3.1 70B - rows {current_index} to {len(df)}...\")\n\ntry:\n    for i in tqdm(range(current_index, len(df)), desc=\"Llama\"):\n        row = df.iloc[i]\n        \n        tags = [str(row[f'tag_{j}']).lower() for j in range(1, 8)\n                if f'tag_{j}' in row and pd.notna(row[f'tag_{j}'])]\n        \n        prompt = create_prompt(\n            row.get('real_name', row.get('name', '')),\n            tags,\n            row.get('likely_country', '')\n        )\n        \n        result = query_llama(prompt)\n        \n        if result:\n            df.at[i, 'full_name'] = result.get('full_name', 'Unknown')\n            df.at[i, 'gender'] = result.get('gender', 'Unknown')\n            profs = result.get('professions', [])\n            df.at[i, 'profession_llm'] = \", \".join(profs[:3]) if isinstance(profs, list) else str(profs)\n            df.at[i, 'country'] = result.get('country', 'Unknown')\n        \n        current_index = i + 1\n        \n        if (i + 1) % SAVE_INTERVAL == 0 or (i + 1) == len(df):\n            df.to_csv(output_file, index=False)\n            with open(index_file, 'w') as f:\n                f.write(str(current_index))\n            print(f\"✅ Saved after {i+1} rows\")\n        \n        time.sleep(0.5)\n    \n    print(f\"\\n✅ Done! Results: {output_file}\")\n    print(f\"\\nTop professions:\\n{df['profession_llm'].value_counts().head(10)}\")\n    \nexcept Exception as e:\n    print(f\"⚠️ Error: {e}\")\n    df.to_csv(output_file, index=False)\n    with open(index_file, 'w') as f:\n        f.write(str(current_index))"
   },
   {
    "cell_type": "markdown",
@@ -1322,165 +1002,7 @@
    "id": "mixtral_code",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import pandas as pd",
-    "import json",
-    "import time",
-    "import requests",
-    "import re",
-    "from pathlib import Path",
-    "from tqdm import tqdm",
-    "",
-    "current_dir = Path.cwd()",
-    "input_file = current_dir.parent / \"data/CSV/NER_POI_step02_annotated.csv\"",
-    "api_key_file = current_dir.parent / \"misc/credentials/mistral_api_key.txt\"",
-    "",
-    "# === CONFIGURATION ===",
-    "TEST_MODE = True",
-    "TEST_SIZE = 10",
-    "MAX_ROWS = 20000",
-    "SAVE_INTERVAL = 10",
-    "",
-    "PROFESSION_CATEGORIES = [",
-    "    \"actor\", \"adult performer\", \"singer/musician\", \"model\",",
-    "    \"online personality\", \"public figure\", \"voice actor/ASMR\",",
-    "    \"sports professional\", \"tv personality\"",
-    "]",
-    "",
-    "# === LOAD API KEY ===",
-    "try:",
-    "    with open(api_key_file) as f:",
-    "        api_key = f.read().strip()",
-    "    print(\"\u2705 Mixtral API key loaded\")",
-    "except FileNotFoundError:",
-    "    print(\"\u274c Error: mistral_api_key.txt not found\")",
-    "    raise",
-    "",
-    "# === LOAD DATA ===",
-    "df = pd.read_csv(input_file)",
-    "print(f\"Loaded {len(df)} rows\")",
-    "",
-    "if TEST_MODE:",
-    "    print(f\"Running in TEST MODE with {TEST_SIZE} samples\")",
-    "    df = df.head(TEST_SIZE).copy()",
-    "elif MAX_ROWS:",
-    "    df = df.head(MAX_ROWS).copy()",
-    "",
-    "# === CREATE PROMPT ===",
-    "def create_prompt(name: str, tags: list, country: str) -> str:",
-    "    tags_str = \", \".join(tags[:5]) if tags else \"none\"",
-    "    country_str = country if country else \"unknown\"",
-    "    ",
-    "    return f\"\"\"You are an expert at identifying public figures.",
-    "",
-    "Given: Name: {name}, Tags: {tags_str}, Country: {country_str}",
-    "",
-    "Provide in JSON format:",
-    "{{",
-    "  \"full_name\": \"<full name>\",",
-    "  \"gender\": \"<Male/Female/Other/Unknown>\",",
-    "  \"professions\": [\"<profession 1>\", \"<profession 2>\", \"<profession 3>\"],",
-    "  \"country\": \"<country>\"",
-    "}}",
-    "",
-    "Choose professions ONLY from: {\", \".join(PROFESSION_CATEGORIES)}",
-    "- Max 3 professions, ordered by relevance",
-    "- \"online personality\" includes streamers, cosplayers, influencers",
-    "- Return \"Unknown\" if uncertain",
-    "",
-    "Return ONLY JSON, no extra text.\"\"\"",
-    "",
-    "# === QUERY MIXTRAL ===",
-    "def query_mixtral(prompt: str) -> dict:",
-    "    url = \"https://api.mistral.ai/v1/chat/completions\"",
-    "    ",
-    "    headers = {",
-    "        \"Authorization\": f\"Bearer {api_key}\",",
-    "        \"Content-Type\": \"application/json\"",
-    "    }",
-    "    ",
-    "    data = {",
-    "        \"model\": \"open-mixtral-8x22b\",",
-    "        \"messages\": [{\"role\": \"user\", \"content\": prompt}],",
-    "        \"temperature\": 0.1,",
-    "        \"max_tokens\": 500",
-    "    }",
-    "    ",
-    "    for attempt in range(3):",
-    "        try:",
-    "            response = requests.post(url, headers=headers, json=data, timeout=30)",
-    "            response.raise_for_status()",
-    "            result = response.json()",
-    "            ",
-    "            if 'choices' in result:",
-    "                content = result['choices'][0]['message']['content']",
-    "                json_match = re.search(r'\\{[^}]+\\}', content, re.DOTALL)",
-    "                if json_match:",
-    "                    return json.loads(json_match.group())",
-    "            return None",
-    "        except Exception as e:",
-    "            print(f\"Mixtral error (attempt {attempt+1}): {e}\")",
-    "            if attempt < 2:",
-    "                time.sleep(2 ** attempt)",
-    "    return None",
-    "",
-    "# === PROCESS ===",
-    "output_file = current_dir.parent / f\"data/CSV/mixtral_annotated_POI{'_test' if TEST_MODE else ''}.csv\"",
-    "index_file = current_dir.parent / \"misc/mixtral_query_index.txt\"",
-    "",
-    "current_index = 0",
-    "if index_file.exists():",
-    "    with open(index_file) as f:",
-    "        current_index = int(f.read().strip())",
-    "",
-    "for col in ['full_name', 'gender', 'profession_llm', 'country']:",
-    "    if col not in df.columns:",
-    "        df[col] = 'Unknown'",
-    "",
-    "print(f\"\\nAnnotating with MIXTRAL 8x22B - rows {current_index} to {len(df)}...\")",
-    "",
-    "try:",
-    "    for i in tqdm(range(current_index, len(df)), desc=\"Mixtral\"):",
-    "        row = df.iloc[i]",
-    "        ",
-    "        tags = [str(row[f'tag_{j}']).lower() for j in range(1, 8) ",
-    "                if f'tag_{j}' in row and pd.notna(row[f'tag_{j}'])]",
-    "        ",
-    "        prompt = create_prompt(",
-    "            row.get('real_name', row.get('name', '')),",
-    "            tags,",
-    "            row.get('likely_country', '')",
-    "        )",
-    "        ",
-    "        result = query_mixtral(prompt)",
-    "        ",
-    "        if result:",
-    "            df.at[i, 'full_name'] = result.get('full_name', 'Unknown')",
-    "            df.at[i, 'gender'] = result.get('gender', 'Unknown')",
-    "            profs = result.get('professions', [])",
-    "            df.at[i, 'profession_llm'] = \", \".join(profs[:3]) if isinstance(profs, list) else str(profs)",
-    "            df.at[i, 'country'] = result.get('country', 'Unknown')",
-    "        ",
-    "        current_index = i + 1",
-    "        ",
-    "        if (i + 1) % SAVE_INTERVAL == 0 or (i + 1) == len(df):",
-    "            df.to_csv(output_file, index=False)",
-    "            with open(index_file, 'w') as f:",
-    "                f.write(str(current_index))",
-    "            print(f\"\u2705 Saved after {i+1} rows\")",
-    "        ",
-    "        time.sleep(0.5)",
-    "    ",
-    "    print(f\"\\n\u2705 Done! Results: {output_file}\")",
-    "    print(f\"\\nTop professions:\\n{df['profession_llm'].value_counts().head(10)}\")",
-    "    ",
-    "except Exception as e:",
-    "    print(f\"\u26a0\ufe0f Error: {e}\")",
-    "    df.to_csv(output_file, index=False)",
-    "    with open(index_file, 'w') as f:",
-    "        f.write(str(current_index))",
-    ""
-   ]
+   "source": "import pandas as pd\nimport json\nimport time\nimport requests\nimport re\nfrom pathlib import Path\nfrom tqdm import tqdm\n\ncurrent_dir = Path.cwd()\ninput_file = current_dir.parent / \"data/CSV/NER_POI_step02_annotated.csv\"\napi_key_file = current_dir.parent / \"misc/credentials/mistral_api_key.txt\"\n\n# === CONFIGURATION ===\nTEST_MODE = True\nTEST_SIZE = 10\nMAX_ROWS = 20000\nSAVE_INTERVAL = 10\n\nPROFESSION_CATEGORIES = [\n    \"actor\", \"adult performer\", \"singer/musician\", \"model\",\n    \"online personality\", \"public figure\", \"voice actor/ASMR\",\n    \"sports professional\", \"tv personality\"\n]\n\n# === LOAD API KEY ===\ntry:\n    with open(api_key_file) as f:\n        api_key = f.read().strip()\n    print(\"✅ Mixtral API key loaded\")\nexcept FileNotFoundError:\n    print(\"❌ Error: mistral_api_key.txt not found\")\n    raise\n\n# === LOAD DATA ===\ndf = pd.read_csv(input_file)\nprint(f\"Loaded {len(df)} rows\")\n\nif TEST_MODE:\n    print(f\"Running in TEST MODE with {TEST_SIZE} samples\")\n    df = df.head(TEST_SIZE).copy()\nelif MAX_ROWS:\n    df = df.head(MAX_ROWS).copy()\n\n# === CREATE PROMPT ===\ndef create_prompt(name: str, tags: list, country: str) -> str:\n    tags_str = \", \".join(tags[:5]) if tags else \"none\"\n    country_str = country if country else \"unknown\"\n    \n    return f\"\"\"You are an expert at identifying public figures.\n\nGiven: Name: {name}, Tags: {tags_str}, Country: {country_str}\n\nProvide in JSON format:\n{{\n  \"full_name\": \"<full name>\",\n  \"gender\": \"<Male/Female/Other/Unknown>\",\n  \"professions\": [\"<profession 1>\", \"<profession 2>\", \"<profession 3>\"],\n  \"country\": \"<country>\"\n}}\n\nChoose professions ONLY from: {\", \".join(PROFESSION_CATEGORIES)}\n- Max 3 professions, ordered by relevance\n- \"online personality\" includes streamers, cosplayers, influencers\n- Return \"Unknown\" if uncertain\n\nReturn ONLY JSON, no extra text.\"\"\"\n\n# === QUERY MIXTRAL ===\ndef query_mixtral(prompt: str) -> dict:\n    url = \"https://api.mistral.ai/v1/chat/completions\"\n    \n    headers = {\n        \"Authorization\": f\"Bearer {api_key}\",\n        \"Content-Type\": \"application/json\"\n    }\n    \n    data = {\n        \"model\": \"open-mixtral-8x22b\",\n        \"messages\": [{\"role\": \"user\", \"content\": prompt}],\n        \"temperature\": 0.1,\n        \"max_tokens\": 500\n    }\n    \n    for attempt in range(3):\n        try:\n            response = requests.post(url, headers=headers, json=data, timeout=30)\n            response.raise_for_status()\n            result = response.json()\n            \n            if 'choices' in result:\n                content = result['choices'][0]['message']['content']\n                json_match = re.search(r'\\{[^}]+\\}', content, re.DOTALL)\n                if json_match:\n                    return json.loads(json_match.group())\n            return None\n        except Exception as e:\n            print(f\"Mixtral error (attempt {attempt+1}): {e}\")\n            if attempt < 2:\n                time.sleep(2 ** attempt)\n    return None\n\n# === PROCESS ===\noutput_file = current_dir.parent / f\"data/CSV/mixtral_annotated_POI{'_test' if TEST_MODE else ''}.csv\"\nindex_file = current_dir.parent / \"misc/mixtral_query_index.txt\"\n\ncurrent_index = 0\nif index_file.exists():\n    with open(index_file) as f:\n        current_index = int(f.read().strip())\n\nfor col in ['full_name', 'gender', 'profession_llm', 'country']:\n    if col not in df.columns:\n        df[col] = 'Unknown'\n\nprint(f\"\\nAnnotating with MIXTRAL 8x22B - rows {current_index} to {len(df)}...\")\n\ntry:\n    for i in tqdm(range(current_index, len(df)), desc=\"Mixtral\"):\n        row = df.iloc[i]\n        \n        tags = [str(row[f'tag_{j}']).lower() for j in range(1, 8)\n                if f'tag_{j}' in row and pd.notna(row[f'tag_{j}'])]\n        \n        prompt = create_prompt(\n            row.get('real_name', row.get('name', '')),\n            tags,\n            row.get('likely_country', '')\n        )\n        \n        result = query_mixtral(prompt)\n        \n        if result:\n            df.at[i, 'full_name'] = result.get('full_name', 'Unknown')\n            df.at[i, 'gender'] = result.get('gender', 'Unknown')\n            profs = result.get('professions', [])\n            df.at[i, 'profession_llm'] = \", \".join(profs[:3]) if isinstance(profs, list) else str(profs)\n            df.at[i, 'country'] = result.get('country', 'Unknown')\n        \n        current_index = i + 1\n        \n        if (i + 1) % SAVE_INTERVAL == 0 or (i + 1) == len(df):\n            df.to_csv(output_file, index=False)\n            with open(index_file, 'w') as f:\n                f.write(str(current_index))\n            print(f\"✅ Saved after {i+1} rows\")\n        \n        time.sleep(0.5)\n    \n    print(f\"\\n✅ Done! Results: {output_file}\")\n    print(f\"\\nTop professions:\\n{df['profession_llm'].value_counts().head(10)}\")\n    \nexcept Exception as e:\n    print(f\"⚠️ Error: {e}\")\n    df.to_csv(output_file, index=False)\n    with open(index_file, 'w') as f:\n        f.write(str(current_index))"
   },
   {
    "cell_type": "markdown",
@@ -1505,165 +1027,7 @@
    "id": "gemma_code",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import pandas as pd",
-    "import json",
-    "import time",
-    "import requests",
-    "import re",
-    "from pathlib import Path",
-    "from tqdm import tqdm",
-    "",
-    "current_dir = Path.cwd()",
-    "input_file = current_dir.parent / \"data/CSV/NER_POI_step02_annotated.csv\"",
-    "api_key_file = current_dir.parent / \"misc/credentials/together_api_key.txt\"",
-    "",
-    "# === CONFIGURATION ===",
-    "TEST_MODE = True",
-    "TEST_SIZE = 10",
-    "MAX_ROWS = 20000",
-    "SAVE_INTERVAL = 10",
-    "",
-    "PROFESSION_CATEGORIES = [",
-    "    \"actor\", \"adult performer\", \"singer/musician\", \"model\",",
-    "    \"online personality\", \"public figure\", \"voice actor/ASMR\",",
-    "    \"sports professional\", \"tv personality\"",
-    "]",
-    "",
-    "# === LOAD API KEY ===",
-    "try:",
-    "    with open(api_key_file) as f:",
-    "        api_key = f.read().strip()",
-    "    print(\"\u2705 Gemma API key loaded\")",
-    "except FileNotFoundError:",
-    "    print(\"\u274c Error: together_api_key.txt not found\")",
-    "    raise",
-    "",
-    "# === LOAD DATA ===",
-    "df = pd.read_csv(input_file)",
-    "print(f\"Loaded {len(df)} rows\")",
-    "",
-    "if TEST_MODE:",
-    "    print(f\"Running in TEST MODE with {TEST_SIZE} samples\")",
-    "    df = df.head(TEST_SIZE).copy()",
-    "elif MAX_ROWS:",
-    "    df = df.head(MAX_ROWS).copy()",
-    "",
-    "# === CREATE PROMPT ===",
-    "def create_prompt(name: str, tags: list, country: str) -> str:",
-    "    tags_str = \", \".join(tags[:5]) if tags else \"none\"",
-    "    country_str = country if country else \"unknown\"",
-    "    ",
-    "    return f\"\"\"You are an expert at identifying public figures.",
-    "",
-    "Given: Name: {name}, Tags: {tags_str}, Country: {country_str}",
-    "",
-    "Provide in JSON format:",
-    "{{",
-    "  \"full_name\": \"<full name>\",",
-    "  \"gender\": \"<Male/Female/Other/Unknown>\",",
-    "  \"professions\": [\"<profession 1>\", \"<profession 2>\", \"<profession 3>\"],",
-    "  \"country\": \"<country>\"",
-    "}}",
-    "",
-    "Choose professions ONLY from: {\", \".join(PROFESSION_CATEGORIES)}",
-    "- Max 3 professions, ordered by relevance",
-    "- \"online personality\" includes streamers, cosplayers, influencers",
-    "- Return \"Unknown\" if uncertain",
-    "",
-    "Return ONLY JSON, no extra text.\"\"\"",
-    "",
-    "# === QUERY GEMMA ===",
-    "def query_gemma(prompt: str) -> dict:",
-    "    url = \"https://api.together.xyz/v1/chat/completions\"",
-    "    ",
-    "    headers = {",
-    "        \"Authorization\": f\"Bearer {api_key}\",",
-    "        \"Content-Type\": \"application/json\"",
-    "    }",
-    "    ",
-    "    data = {",
-    "        \"model\": \"google/gemma-2-27b-it\",",
-    "        \"messages\": [{\"role\": \"user\", \"content\": prompt}],",
-    "        \"temperature\": 0.1,",
-    "        \"max_tokens\": 500",
-    "    }",
-    "    ",
-    "    for attempt in range(3):",
-    "        try:",
-    "            response = requests.post(url, headers=headers, json=data, timeout=30)",
-    "            response.raise_for_status()",
-    "            result = response.json()",
-    "            ",
-    "            if 'choices' in result:",
-    "                content = result['choices'][0]['message']['content']",
-    "                json_match = re.search(r'\\{[^}]+\\}', content, re.DOTALL)",
-    "                if json_match:",
-    "                    return json.loads(json_match.group())",
-    "            return None",
-    "        except Exception as e:",
-    "            print(f\"Gemma error (attempt {attempt+1}): {e}\")",
-    "            if attempt < 2:",
-    "                time.sleep(2 ** attempt)",
-    "    return None",
-    "",
-    "# === PROCESS ===",
-    "output_file = current_dir.parent / f\"data/CSV/gemma_annotated_POI{'_test' if TEST_MODE else ''}.csv\"",
-    "index_file = current_dir.parent / \"misc/gemma_query_index.txt\"",
-    "",
-    "current_index = 0",
-    "if index_file.exists():",
-    "    with open(index_file) as f:",
-    "        current_index = int(f.read().strip())",
-    "",
-    "for col in ['full_name', 'gender', 'profession_llm', 'country']:",
-    "    if col not in df.columns:",
-    "        df[col] = 'Unknown'",
-    "",
-    "print(f\"\\nAnnotating with GEMMA 2 27B (Google) - rows {current_index} to {len(df)}...\")",
-    "",
-    "try:",
-    "    for i in tqdm(range(current_index, len(df)), desc=\"Gemma\"):",
-    "        row = df.iloc[i]",
-    "        ",
-    "        tags = [str(row[f'tag_{j}']).lower() for j in range(1, 8) ",
-    "                if f'tag_{j}' in row and pd.notna(row[f'tag_{j}'])]",
-    "        ",
-    "        prompt = create_prompt(",
-    "            row.get('real_name', row.get('name', '')),",
-    "            tags,",
-    "            row.get('likely_country', '')",
-    "        )",
-    "        ",
-    "        result = query_gemma(prompt)",
-    "        ",
-    "        if result:",
-    "            df.at[i, 'full_name'] = result.get('full_name', 'Unknown')",
-    "            df.at[i, 'gender'] = result.get('gender', 'Unknown')",
-    "            profs = result.get('professions', [])",
-    "            df.at[i, 'profession_llm'] = \", \".join(profs[:3]) if isinstance(profs, list) else str(profs)",
-    "            df.at[i, 'country'] = result.get('country', 'Unknown')",
-    "        ",
-    "        current_index = i + 1",
-    "        ",
-    "        if (i + 1) % SAVE_INTERVAL == 0 or (i + 1) == len(df):",
-    "            df.to_csv(output_file, index=False)",
-    "            with open(index_file, 'w') as f:",
-    "                f.write(str(current_index))",
-    "            print(f\"\u2705 Saved after {i+1} rows\")",
-    "        ",
-    "        time.sleep(0.5)",
-    "    ",
-    "    print(f\"\\n\u2705 Done! Results: {output_file}\")",
-    "    print(f\"\\nTop professions:\\n{df['profession_llm'].value_counts().head(10)}\")",
-    "    ",
-    "except Exception as e:",
-    "    print(f\"\u26a0\ufe0f Error: {e}\")",
-    "    df.to_csv(output_file, index=False)",
-    "    with open(index_file, 'w') as f:",
-    "        f.write(str(current_index))",
-    ""
-   ]
+   "source": "import pandas as pd\nimport json\nimport time\nimport requests\nimport re\nfrom pathlib import Path\nfrom tqdm import tqdm\n\ncurrent_dir = Path.cwd()\ninput_file = current_dir.parent / \"data/CSV/NER_POI_step02_annotated.csv\"\napi_key_file = current_dir.parent / \"misc/credentials/together_api_key.txt\"\n\n# === CONFIGURATION ===\nTEST_MODE = True\nTEST_SIZE = 10\nMAX_ROWS = 20000\nSAVE_INTERVAL = 10\n\nPROFESSION_CATEGORIES = [\n    \"actor\", \"adult performer\", \"singer/musician\", \"model\",\n    \"online personality\", \"public figure\", \"voice actor/ASMR\",\n    \"sports professional\", \"tv personality\"\n]\n\n# === LOAD API KEY ===\ntry:\n    with open(api_key_file) as f:\n        api_key = f.read().strip()\n    print(\"✅ Gemma API key loaded\")\nexcept FileNotFoundError:\n    print(\"❌ Error: together_api_key.txt not found\")\n    raise\n\n# === LOAD DATA ===\ndf = pd.read_csv(input_file)\nprint(f\"Loaded {len(df)} rows\")\n\nif TEST_MODE:\n    print(f\"Running in TEST MODE with {TEST_SIZE} samples\")\n    df = df.head(TEST_SIZE).copy()\nelif MAX_ROWS:\n    df = df.head(MAX_ROWS).copy()\n\n# === CREATE PROMPT ===\ndef create_prompt(name: str, tags: list, country: str) -> str:\n    tags_str = \", \".join(tags[:5]) if tags else \"none\"\n    country_str = country if country else \"unknown\"\n    \n    return f\"\"\"You are an expert at identifying public figures.\n\nGiven: Name: {name}, Tags: {tags_str}, Country: {country_str}\n\nProvide in JSON format:\n{{\n  \"full_name\": \"<full name>\",\n  \"gender\": \"<Male/Female/Other/Unknown>\",\n  \"professions\": [\"<profession 1>\", \"<profession 2>\", \"<profession 3>\"],\n  \"country\": \"<country>\"\n}}\n\nChoose professions ONLY from: {\", \".join(PROFESSION_CATEGORIES)}\n- Max 3 professions, ordered by relevance\n- \"online personality\" includes streamers, cosplayers, influencers\n- Return \"Unknown\" if uncertain\n\nReturn ONLY JSON, no extra text.\"\"\"\n\n# === QUERY GEMMA ===\ndef query_gemma(prompt: str) -> dict:\n    url = \"https://api.together.xyz/v1/chat/completions\"\n    \n    headers = {\n        \"Authorization\": f\"Bearer {api_key}\",\n        \"Content-Type\": \"application/json\"\n    }\n    \n    data = {\n        \"model\": \"google/gemma-2-27b-it\",\n        \"messages\": [{\"role\": \"user\", \"content\": prompt}],\n        \"temperature\": 0.1,\n        \"max_tokens\": 500\n    }\n    \n    for attempt in range(3):\n        try:\n            response = requests.post(url, headers=headers, json=data, timeout=30)\n            response.raise_for_status()\n            result = response.json()\n            \n            if 'choices' in result:\n                content = result['choices'][0]['message']['content']\n                json_match = re.search(r'\\{[^}]+\\}', content, re.DOTALL)\n                if json_match:\n                    return json.loads(json_match.group())\n            return None\n        except Exception as e:\n            print(f\"Gemma error (attempt {attempt+1}): {e}\")\n            if attempt < 2:\n                time.sleep(2 ** attempt)\n    return None\n\n# === PROCESS ===\noutput_file = current_dir.parent / f\"data/CSV/gemma_annotated_POI{'_test' if TEST_MODE else ''}.csv\"\nindex_file = current_dir.parent / \"misc/gemma_query_index.txt\"\n\ncurrent_index = 0\nif index_file.exists():\n    with open(index_file) as f:\n        current_index = int(f.read().strip())\n\nfor col in ['full_name', 'gender', 'profession_llm', 'country']:\n    if col not in df.columns:\n        df[col] = 'Unknown'\n\nprint(f\"\\nAnnotating with GEMMA 2 27B (Google) - rows {current_index} to {len(df)}...\")\n\ntry:\n    for i in tqdm(range(current_index, len(df)), desc=\"Gemma\"):\n        row = df.iloc[i]\n        \n        tags = [str(row[f'tag_{j}']).lower() for j in range(1, 8)\n                if f'tag_{j}' in row and pd.notna(row[f'tag_{j}'])]\n        \n        prompt = create_prompt(\n            row.get('real_name', row.get('name', '')),\n            tags,\n            row.get('likely_country', '')\n        )\n        \n        result = query_gemma(prompt)\n        \n        if result:\n            df.at[i, 'full_name'] = result.get('full_name', 'Unknown')\n            df.at[i, 'gender'] = result.get('gender', 'Unknown')\n            profs = result.get('professions', [])\n            df.at[i, 'profession_llm'] = \", \".join(profs[:3]) if isinstance(profs, list) else str(profs)\n            df.at[i, 'country'] = result.get('country', 'Unknown')\n        \n        current_index = i + 1\n        \n        if (i + 1) % SAVE_INTERVAL == 0 or (i + 1) == len(df):\n            df.to_csv(output_file, index=False)\n            with open(index_file, 'w') as f:\n                f.write(str(current_index))\n            print(f\"✅ Saved after {i+1} rows\")\n        \n        time.sleep(0.5)\n    \n    print(f\"\\n✅ Done! Results: {output_file}\")\n    print(f\"\\nTop professions:\\n{df['profession_llm'].value_counts().head(10)}\")\n    \nexcept Exception as e:\n    print(f\"⚠️ Error: {e}\")\n    df.to_csv(output_file, index=False)\n    with open(index_file, 'w') as f:\n        f.write(str(current_index))"
   },
   {
    "cell_type": "markdown",
@@ -1694,11 +1058,11 @@
     "```\n",
     "\n",
     "**Advantages:**\n",
-    "- \u2705 FREE - No API costs\n",
-    "- \u2705 Fast - Local inference on A100\n",
-    "- \u2705 Privacy - Data never leaves your machine\n",
-    "- \u2705 Offline - Works without internet\n",
-    "- \u2705 High quality - 32B parameter model\n",
+    "- ✅ FREE - No API costs\n",
+    "- ✅ Fast - Local inference on A100\n",
+    "- ✅ Privacy - Data never leaves your machine\n",
+    "- ✅ Offline - Works without internet\n",
+    "- ✅ High quality - 32B parameter model\n",
     "\n",
     "**Performance:**\n",
     "- Speed: ~5-10 tokens/sec on A100\n",
@@ -1751,25 +1115,25 @@
     "        )\n",
     "        \n",
     "        if result.returncode == 0:\n",
-    "            print(\"\u2705 Ollama is installed\")\n",
+    "            print(\"✅ Ollama is installed\")\n",
     "            \n",
     "            # Check if model is available\n",
     "            if MODEL_NAME in result.stdout or \"qwen2.5\" in result.stdout:\n",
-    "                print(f\"\u2705 Model {MODEL_NAME} is available\")\n",
+    "                print(f\"✅ Model {MODEL_NAME} is available\")\n",
     "                return True\n",
     "            else:\n",
-    "                print(f\"\u26a0\ufe0f  Model {MODEL_NAME} not found\")\n",
+    "                print(f\"⚠️  Model {MODEL_NAME} not found\")\n",
     "                print(f\"   Run: ollama pull {MODEL_NAME}\")\n",
     "                return False\n",
     "        else:\n",
-    "            print(\"\u274c Ollama command failed\")\n",
+    "            print(\"❌ Ollama command failed\")\n",
     "            return False\n",
     "    except FileNotFoundError:\n",
-    "        print(\"\u274c Ollama not installed\")\n",
+    "        print(\"❌ Ollama not installed\")\n",
     "        print(\"   Install: curl -fsSL https://ollama.com/install.sh | sh\")\n",
     "        return False\n",
     "    except Exception as e:\n",
-    "        print(f\"\u274c Error checking Ollama: {e}\")\n",
+    "        print(f\"❌ Error checking Ollama: {e}\")\n",
     "        return False\n",
     "\n",
     "# Check Ollama before proceeding\n",
@@ -1908,24 +1272,24 @@
     "            samples_done = i + 1 - (current_index - (i + 1))\n",
     "            samples_per_hour = (samples_done / elapsed) * 3600 if elapsed > 0 else 0\n",
     "            \n",
-    "            print(f\"\u2705 Saved after {i+1} rows (~{samples_per_hour:.1f} samples/hour)\")\n",
+    "            print(f\"✅ Saved after {i+1} rows (~{samples_per_hour:.1f} samples/hour)\")\n",
     "    \n",
     "    elapsed_total = time.time() - start_time\n",
-    "    print(f\"\\n\u2705 Done! Results: {output_file}\")\n",
+    "    print(f\"\\n✅ Done! Results: {output_file}\")\n",
     "    print(f\"Total time: {elapsed_total/60:.1f} minutes\")\n",
     "    print(f\"Average speed: {len(df)/(elapsed_total/3600):.1f} samples/hour\")\n",
     "    \n",
     "    print(f\"\\nTop professions:\\n{df['profession_llm'].value_counts().head(10)}\")\n",
     "\n",
     "except KeyboardInterrupt:\n",
-    "    print(f\"\\n\u26a0\ufe0f Interrupted by user\")\n",
+    "    print(f\"\\n⚠️ Interrupted by user\")\n",
     "    df.to_csv(output_file, index=False)\n",
     "    with open(index_file, 'w') as f:\n",
     "        f.write(str(current_index))\n",
     "    print(f\"Progress saved up to row {current_index}\")\n",
     "\n",
     "except Exception as e:\n",
-    "    print(f\"\u26a0\ufe0f Error: {e}\")\n",
+    "    print(f\"⚠️ Error: {e}\")\n",
     "    df.to_csv(output_file, index=False)\n",
     "    with open(index_file, 'w') as f:\n",
     "        f.write(str(current_index))\n",