{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\Jose\\Desktop\\Nuanced_Recommendation_System\\.venv\\Lib\\site-packages\\sentence_transformers\\cross_encoder\\CrossEncoder.py:13: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from tqdm.autonotebook import tqdm, trange\n",
      "c:\\Users\\Jose\\Desktop\\Nuanced_Recommendation_System\\.venv\\Lib\\site-packages\\transformers\\tokenization_utils_base.py:1617: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be deprecated in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import json\n",
    "\n",
    "from sentence_transformers import SentenceTransformer\n",
    "\n",
    "model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def update_filters(filters, data):\n",
    "    for key, value in filters.items():\n",
    "        dont_add = ['Boys Love', 'Erotica', 'Girls Love', 'Hentai', 'Ecchi', 'Gore', 'Crossdressing', 'Magical Sex Shift', 'Rx - Hentai', 'R+ - Mild Nudity']\n",
    "        if data[key] and key == 'rating':\n",
    "            if data[key] not in dont_add:\n",
    "                value.add(data[key])\n",
    "        else:\n",
    "            for val in data[key]:\n",
    "                if val and val not in dont_add:\n",
    "                    value.add(val)\n",
    "    return filters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def clean_filters(filters):\n",
    "    for key, val in filters.items():\n",
    "        val.add('ALL')\n",
    "        filters[key] = list(val)\n",
    "    return filters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print('Embedding Started')\n",
    "\n",
    "filters = {\n",
    "'genres': set(),\n",
    "'themes': set(),\n",
    "'rating': set()\n",
    "}\n",
    "\n",
    "embeddings = {}\n",
    "for name in os.listdir('./anime'):\n",
    "    with open(f\"./anime/{name}\", 'r') as file:\n",
    "        data = json.load(file)\n",
    "\n",
    "    if not data:\n",
    "        continue\n",
    "\n",
    "    filters = update_filters(filters, data)\n",
    "\n",
    "    name = name.replace('.json', '')\n",
    "    \n",
    "    data['image'] = f\"./images/{name}.jpg\"\n",
    "\n",
    "    text = f'''Episodes: {data['episodes']} \n",
    "            Premiered: {data['premiered']} \n",
    "            Broadcast: {data['broadcast']} \n",
    "            Producers: {' '.join(data['producers'])} \n",
    "            Licensors: {' '.join(data['licensors'])} \n",
    "            Studios: {' '.join(data['studios'])} \n",
    "            Source: {' '.join(data['source'])}  \n",
    "            Genres: {' '.join(data['genres'])} \n",
    "            Themes: {' '.join(data['themes'])} \n",
    "            Demographic: {data['demographic']} \n",
    "            Duration: {data['duration']} \n",
    "            Rating: {data['rating']} \n",
    "            Description: {data['description']}'''\n",
    "    \n",
    "    embeddings[name] = data.copy()\n",
    "    \n",
    "    embeddings[name]['objective_embedding'] = [model.encode(text).tolist()]\n",
    "    subjective_embeddings = []\n",
    "    for review in embeddings[name]['reviews']:\n",
    "        text = review['text']\n",
    "        subjective_embeddings.append(model.encode(text).tolist())\n",
    "        data['review'] = text\n",
    "    embeddings[name]['subjective_embeddings'] = subjective_embeddings\n",
    "\n",
    "filters = clean_filters(filters)\n",
    "\n",
    "with open('./embeddings/data.json', 'w') as f:\n",
    "    json.dump({'embeddings':embeddings, 'filters': filters}, f)\n",
    "\n",
    "print('Embedding Complete')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}