{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "b3vIWjxfy4uB"
   },
   "source": [
    "<img src=\"https://github.com/YongBeomKim/nltk_basic/raw/master/data/cosin.png\" width=800>\n",
    "<br/>\n",
    "# **Chapter 4 | 추천시스템**\n",
    "참고사이트 : https://www.machinelearningplus.com/nlp/cosine-similarity/\n",
    "## **1 데이터 불러오기**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "_-fO8fCqy4uD"
   },
   "outputs": [],
   "source": [
    "! apt-get update\n",
    "! apt-get install g++ openjdk-8-jdk \n",
    "! pip3  install  nltk konlpy matplotlib gensim \n",
    "\n",
    "! apt-get install fonts-nanum-eco\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/*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 72
    },
    "colab_type": "code",
    "id": "nBagMLpZzEyD",
    "outputId": "57224cf2-c10e-4148-e7d7-3f5bf539d896"
   },
   "outputs": [],
   "source": [
    "import nltk\n",
    "nltk.download('wordnet')\n",
    "\n",
    "import pandas as pd\n",
    "import io, requests\n",
    "url = \"https://raw.githubusercontent.com/YongBeomKim/nltk_basic/master/data/movies_metadata.csv\"\n",
    "response = requests.get(url).content\n",
    "movies = pd.read_csv(io.StringIO(response.decode('utf-8')),\n",
    "                    usecols=['original_title', 'overview', 'title'], low_memory=False)\n",
    "movies = movies.dropna(axis=0)\n",
    "movies.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 138
    },
    "colab_type": "code",
    "id": "anzxC1Kxy4uH",
    "outputId": "c9d4aee2-a4eb-4e43-bae1-7abe04e80f8f"
   },
   "outputs": [],
   "source": [
    "movie_plot_li = movies['overview']\n",
    "movie_info_li = movies['title']\n",
    "movies.head(3)"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "04-Recommand.ipynb",
   "provenance": [],
   "version": "0.3.2"
  },
  "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
}