{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **Chapter 2 Visulaizaion**\n",
    "## **Word Cloud - 말뭉치 응용**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# ! apt-get update\n",
    "# ! apt-get install g++ openjdk-8-jdk \n",
    "# ! pip3  install  nltk konlpy wordcloud matplotlib gensim \n",
    "\n",
    "# ! apt-get install fonts-nanum*\n",
    "# ! apt-get install fontconfig\n",
    "# ! fc-cache -fv\n",
    "# ! cp /usr/share/fonts/truetype/nanum/Nanum* /usr/local/lib/python3.6/dist-packages/matplotlib/mpl-data/fonts/ttf/\n",
    "# ! rm -rf /content/.cache/matplotlib/*\n",
    "\n",
    "# speech_text = \"https://raw.githubusercontent.com/YongBeomKim/nltk_rnd/master/data/pyongyang_fin.txt\"\n",
    "# font_file   = \"/usr/local/lib/python3.6/dist-packages/matplotlib/mpl-data/fonts/ttf/NanumGothicCoding.ttf\"\n",
    "speech_text = \"../data/pyongyang_fin.txt\"\n",
    "font_file   = \"../data/D2Coding.ttf\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# import nltk\n",
    "# nltk.download('punkt')\n",
    "\n",
    "import pandas as pd\n",
    "from nltk import FreqDist\n",
    "from nltk.tokenize import word_tokenize\n",
    "\n",
    "# for Colab\n",
    "# import requests\n",
    "# texts = requests.get(speech_text).text\n",
    "# texts[:100]\n",
    "\n",
    "# for LocalHost\n",
    "with open(speech_text, 'r') as f:\n",
    "    texts = f.read()\n",
    "texts[:100]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "from wordcloud import WordCloud\n",
    "wcloud = WordCloud(font_file).generate(texts)\n",
    "plt.figure(figsize=(12,12))\n",
    "plt.imshow(wcloud)\n",
    "plt.axis(\"off\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from collections import Counter\n",
    "dictionary = Counter(texts.split())\n",
    "dictionary.most_common()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<br/>\n",
    "## **명사만 추출하여 Wordcloud 만들기**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Twitter 모듈을 활용하여 명사만 추출\n",
    "from konlpy.tag import Okt \n",
    "twitter     = Okt()\n",
    "tokens      = twitter.pos(texts, stem=True)\n",
    "tokens_noun = [token[0]   for token in tokens  \n",
    "                          if token[1] == \"Noun\"]\n",
    "\n",
    "texts_noun  = \" \".join(tokens_noun)\n",
    "texts_noun[:300]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "plt.figure(figsize=(12,12))\n",
    "wcloud = WordCloud(font_file).generate(texts_noun)\n",
    "plt.imshow(wcloud)\n",
    "plt.axis(\"off\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Token 빈도결과값\n",
    "from collections import Counter\n",
    "dictionary = Counter(texts_noun.split())\n",
    "dictionary.most_common()[:10]"
   ]
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}