Download YouTube Spam Comments with R

Download YouTube Spam Comments with R.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# https://docs.anaconda.com/anaconda/packages/r-language-pkg-docs/\n",
    "# conda install rpy2\n",
    "# conda install -c r r-essentials\n",
    "# conda install -c r r-base\n",
    "# conda search -f r-EXACTNAME to search for existing packages and conda install EXACTNAME\n",
    "# If any issue happens, remove /anaconda3/lib/R and install everything again\n",
    "\n",
    "import rpy2.ipython\n",
    "\n",
    "%reload_ext rpy2.ipython"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%R\n",
    "\n",
    "# Snippet from\n",
    "# https://github.com/christophM/interpretable-ml-book/blob/master/R/get-SpamTube-dataset.R\n",
    "\n",
    "# Data from\n",
    "# http://www.dt.fee.unicamp.br/~tiago//youtubespamcollection/\n",
    "\n",
    "data_dir = \"youtube_data\"\n",
    "\n",
    "# Download the youtube datasets \n",
    "download.spam.data = function(){\n",
    "  urls = sprintf('http://lasid.sor.ufscar.br/labeling/datasets/%i/download/', 9:13)\n",
    "  ycomments = lapply(urls, read.csv, stringsAsFactors=FALSE)\n",
    "  ycomments = do.call('rbind', ycomments)\n",
    "  cleanFun <- function(htmlString) {\n",
    "    return(gsub(\"<.*?>\", \"\", htmlString))\n",
    "  }\n",
    "  ycomments$CONTENT = cleanFun(ycomments$CONTENT)\n",
    "  # Convert to ASCII\n",
    "  ycomments$CONTENT = iconv(ycomments$CONTENT, \"UTF-8\", \"ASCII\", sub=\"\")\n",
    "  write.csv( x = ycomments, file = sprintf('%s/TubeSpam.csv', data_dir),row.names=FALSE)\n",
    "}\n",
    "download.spam.data()"
   ]
  }
 ],
 "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": "3.7.3"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}