{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<br></br>\n",
    "# **Konlpy**\n",
    "한글모듈\n",
    "\n",
    "## **1 Tagging**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('파이썬', 'Noun'),\n",
       " ('을', 'Josa'),\n",
       " ('활용한', 'Verb'),\n",
       " ('자연어', 'Noun'),\n",
       " ('수업', 'Noun'),\n",
       " ('자료', 'Noun')]"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from konlpy.tag import Twitter\n",
    "twitter = Twitter()\n",
    "twitter.pos('파이썬을 활용한 자연어 수업자료')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<br></br>\n",
    "## **2 Stemming**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "text = \"워런 버핏은 삼성전자가 아닌 애플주식을 왜 샀을까\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[('워런', 'Noun'), ('버핏', 'Noun'), ('은', 'Josa'), ('삼성', 'Noun'), ('전자', 'Noun'), ('가', 'Josa'), ('아니다', 'Adjective'), ('애플', 'Noun'), ('주식', 'Noun'), ('을', 'Josa'), ('왜', 'Noun'), ('사다', 'Verb')]\n",
      "CPU times: user 821 ms, sys: 34 ms, total: 855 ms\n",
      "Wall time: 564 ms\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "print(twitter.pos(text, stem=True))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[('워런', 'Noun'), ('버핏', 'Noun'), ('은', 'Josa'), ('삼성', 'Noun'), ('전자', 'Noun'), ('가', 'Josa'), ('아닌', 'Adjective'), ('애플', 'Noun'), ('주식', 'Noun'), ('을', 'Josa'), ('왜', 'Noun'), ('샀', 'Verb'), ('을까', 'Eomi')]\n",
      "CPU times: user 48.4 ms, sys: 26 µs, total: 48.4 ms\n",
      "Wall time: 67 ms\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "print(twitter.pos(text))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<br></br>\n",
    "## **3 꼬꼬마, 한나눔**\n",
    "개별 모듈에 따라 다른결과를 출력"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[('워', 'UN'), ('런', 'NNG'), ('버핏', 'UN'), ('은', 'JX'), ('삼성전자', 'NNG'), ('가', 'JKS'), ('아니', 'VV'), ('ㄴ', 'ETD'), ('애플', 'NNP'), ('주식', 'NNG'), ('을', 'JKO'), ('왜', 'MAG'), ('사', 'VV'), ('었', 'EPT'), ('을까', 'EFQ')]\n",
      "CPU times: user 21.6 s, sys: 229 ms, total: 21.8 s\n",
      "Wall time: 16.1 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "from konlpy.tag import Kkma\n",
    "kkma = Kkma()\n",
    "print(kkma.pos(text))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[('워런', 'N'), ('버핏', 'N'), ('은', 'J'), ('삼성전자', 'N'), ('가', 'J'), ('아니', 'P'), ('ㄴ', 'E'), ('애플주식', 'N'), ('을', 'J'), ('왜', 'M'), ('사', 'P'), ('아ㄹ까', 'E')]\n",
      "CPU times: user 8.6 s, sys: 77 ms, total: 8.68 s\n",
      "Wall time: 5.29 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "from konlpy.tag import Hannanum\n",
    "han = Hannanum()\n",
    "print(han.pos(text))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}