{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "4e391b33-ae37-4419-9b95-c0c88ecc9ee6",
   "metadata": {},
   "source": [
    "# Token 을 벡터로 임베딩\n",
    "- [pypi kss](https://github.com/hyunwoongko/kss)\n",
    "- [FastText 단어 유사도 구현하기](https://sunghee2.tistory.com/entry/FastText-%EB%8B%A8%EC%96%B4-%EC%9C%A0%EC%82%AC%EB%8F%84-%EA%B5%AC%ED%98%84%ED%95%98%EA%B8%B0)\n",
    "- [FastText model을 이용한 감정 분석 모델(pytorch)](https://happy-jihye.github.io/nlp/nlp-3/)\n",
    "- [Bag of Word with Bag 한글해설](https://m.blog.naver.com/antler07/221476398640)\n",
    "- [Word2vec from Scratch with NumPy](https://nathanrooy.github.io/posts/2018-03-22/word2vec-from-scratch-with-python-and-numpy/)\n",
    "- [AwesomeKorean Data](https://github.com/songys/AwesomeKorean_Data)\n",
    "```bash\n",
    "! pip install python-mecab-ko -U\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "ac723d00-aab2-4c69-b18e-0cdb5ac7fbcd",
   "metadata": {},
   "outputs": [],
   "source": [
    "%reset -f"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "f69578f0-23ca-4c51-84fb-5bcd41465042",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['회사 동료 분들과 다녀왔는데 분위기도 좋고 음식도 맛있었어요',\n",
       " '다만, 강남 토끼정이 강남 쉑쉑버거 골목길로 쭉 올라가야 하는데 다들 쉑쉑버거의 유혹에 넘어갈 뻔 했답니다',\n",
       " '강남역 맛집 토끼정의 외부 모습.']"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import kss\n",
    "import mecab\n",
    "text = \"회사 동료 분들과 다녀왔는데 분위기도 좋고 음식도 맛있었어요 다만, 강남 토끼정이 강남 쉑쉑버거 골목길로 쭉 올라가야 하는데 다들 쉑쉑버거의 유혹에 넘어갈 뻔 했답니다 강남역 맛집 토끼정의 외부 모습.\"\n",
    "kss.split_morphemes(text, backend=\"mecab\", num_workers=8)\n",
    "# kss.split_sentences(text, backend=\"mecab\", num_workers=8, ignores=[])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "6d123730-a044-4e12-affb-941fb6cd2f5a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('자연주의', 'NNG'),\n",
       " ('쇼핑몰', 'NNG'),\n",
       " ('은', 'JX'),\n",
       " ('어떤', 'MM'),\n",
       " ('곳', 'NNG'),\n",
       " ('인가', 'VCP+EF'),\n",
       " ('?', 'SF')]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from mecab import MeCab\n",
    "mecab = MeCab()\n",
    "mecab.pos('자연주의 쇼핑몰은 어떤 곳인가?')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "575ee639-3618-4574-880c-d10468caa54f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Morpheme(span=Span(start=0, end=3), surface='즐거운', feature=Feature(pos='VA+ETM', semantic=None, has_jongseong=True, reading='즐거운', type='Inflect', start_pos='VA', end_pos='ETM', expression='즐겁/VA/*+ᆫ/ETM/*')),\n",
       " Morpheme(span=Span(start=4, end=6), surface='하루', feature=Feature(pos='NNG', semantic=None, has_jongseong=False, reading='하루', type=None, start_pos=None, end_pos=None, expression=None)),\n",
       " Morpheme(span=Span(start=7, end=9), surface='보내', feature=Feature(pos='VV', semantic=None, has_jongseong=False, reading='보내', type=None, start_pos=None, end_pos=None, expression=None)),\n",
       " Morpheme(span=Span(start=9, end=11), surface='세요', feature=Feature(pos='EP+EF', semantic=None, has_jongseong=False, reading='세요', type='Inflect', start_pos='EP', end_pos='EF', expression='시/EP/*+어요/EF/*')),\n",
       " Morpheme(span=Span(start=11, end=12), surface='!', feature=Feature(pos='SF', semantic=None, has_jongseong=None, reading=None, type=None, start_pos=None, end_pos=None, expression=None))]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mecab.parse('즐거운 하루 보내세요!')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "ce4c99ec-7256-4f0f-9497-8cc84efd3361",
   "metadata": {},
   "outputs": [],
   "source": [
    "from gensim.models import FastText\n",
    "FastText.load_fasttext_format("
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ab3a97a8-c233-45b2-b913-f3a6cd7746ed",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "zsh:1: parse error near `&'\n"
     ]
    }
   ],
   "source": [
    "!curl -c ./cookie -s -L \"https://drive.google.com/uc?export=download&id=1CQT4Sear6NKxGiZIW3WpAGkTanO0azrl\" > /dev/null\n",
    "!curl -Lb ./cookie \\\"https://drive.google.com/uc?export=download&confirm=`awk '/download/ {print $NF}' ./cookie`&id=1CQT4Sear6NKxGiZIW3WpAGkTanO0azrl\\\" -o wiki_20190620_small.txt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "4b68c8db-40b1-4558-a0fb-3a0eb5e6bf27",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "zsh:1: no matches found: \"https://drive.google.com/uc?export=download\n"
     ]
    }
   ],
   "source": [
    "!curl -c ./cookie -s -L \\\"https://drive.google.com/uc?export=download&id=1CQT4Sear6NKxGiZIW3WpAGkTanO0azrl\\\" > /dev/null"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "9238249a-9fd9-490b-826a-94a067da2487",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['영등포구청역', '에', '있', '는', '맛집', '좀', '알려', '주', '세요', '.']"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from mecab import MeCab\n",
    "mecab = MeCab()\n",
    "mecab.morphs('영등포구청역에 있는 맛집 좀 알려주세요.')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a06e19f3-fddd-4a58-a643-ed849a854f08",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}