{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "from os import walk\n",
    "from datetime import datetime\n",
    "import pandas as pd\n",
    "from subprocess import check_call\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "# output_dict = {'speaker': [],\n",
    "#               'date': [],\n",
    "#               'start_size': [],\n",
    "#               'end_size': [],\n",
    "#               'change_size': [], \n",
    "#               'change_size_perc': []}\n",
    "\n",
    "text_dir = './Corpus_of_Presential_Speeches/'\n",
    "for _, _, filenames in walk('./Corpus_of_Presential_Speeches/'):\n",
    "    for file in filenames:\n",
    "        president = file.split(\"_\")[0]\n",
    "        entire_filename = text_dir + president + '/' + file\n",
    "        #check_call(['gzip', entire_filename])\n",
    "        with open(entire_filename+'.infgen', 'w') as outfile:\n",
    "            check_call([\"./infgen\", entire_filename], stdout=outfile)\n",
    "        \n",
    "#         with open(entire_filename) as f:\n",
    "#             file_contents = [line.split() for line in f]\n",
    "            \n",
    "#         text = [item for sublist in file_contents[2:] for item in sublist]\n",
    "#         text = ' '.join(text)\n",
    "        \n",
    "#         output_dict['speaker'].append(president)\n",
    "#         output_dict['date'].append(pd.to_datetime(' '.join(file_contents[1]).split('\"')[1]).strftime('%m-%d-%Y'))\n",
    "#         output_dict['start_size'].append(getsizeof(text))\n",
    "        \n",
    "#         compressed_text = compress(text)\n",
    "#         output_dict['end_size'].append(getsizeof(compressed_text))\n",
    "#         output_dict['change_size'].append(output_dict['start_size'][-1] - output_dict['end_size'][-1])\n",
    "#         output_dict['change_size_perc'].append(output_dict['end_size'][-1]*1.0 / output_dict['start_size'][-1])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda root]",
   "language": "python",
   "name": "conda-root-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}