{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "[Errno 2] No such file or directory: './data/movietweetings/movies.dat'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-1-7efaf53b7077>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m movies = pd.read_csv('./data/movietweetings/movies.dat', delimiter='::',\n\u001b[1;32m----> 5\u001b[1;33m                      engine='python', header=None, names=['Movie ID', 'Movie Title', 'Genre'])\n\u001b[0m\u001b[0;32m      6\u001b[0m users = pd.read_csv('./data/movietweetings/users.dat', delimiter='::',\n\u001b[0;32m      7\u001b[0m                     engine='python', header=None, names=['User ID', 'Twitter ID'])\n",
      "\u001b[1;32mD:\\ProgramData\\conda3.05\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36mparser_f\u001b[1;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, skipfooter, skip_footer, doublequote, delim_whitespace, as_recarray, compact_ints, use_unsigned, low_memory, buffer_lines, memory_map, float_precision)\u001b[0m\n\u001b[0;32m    653\u001b[0m                     skip_blank_lines=skip_blank_lines)\n\u001b[0;32m    654\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 655\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0m_read\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    656\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    657\u001b[0m     \u001b[0mparser_f\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__name__\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mD:\\ProgramData\\conda3.05\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36m_read\u001b[1;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[0;32m    403\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    404\u001b[0m     \u001b[1;31m# Create the parser.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 405\u001b[1;33m     \u001b[0mparser\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mTextFileReader\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    406\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    407\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mchunksize\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0miterator\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mD:\\ProgramData\\conda3.05\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[0;32m    762\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0moptions\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'has_index_names'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mkwds\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'has_index_names'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    763\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 764\u001b[1;33m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_make_engine\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    765\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    766\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mclose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mD:\\ProgramData\\conda3.05\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36m_make_engine\u001b[1;34m(self, engine)\u001b[0m\n\u001b[0;32m    993\u001b[0m                                  ' \"c\", \"python\", or' ' \"python-fwf\")'.format(\n\u001b[0;32m    994\u001b[0m                                      engine=engine))\n\u001b[1;32m--> 995\u001b[1;33m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mklass\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0moptions\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    996\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    997\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_failover_to_python\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mD:\\ProgramData\\conda3.05\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, f, **kwds)\u001b[0m\n\u001b[0;32m   1983\u001b[0m         f, handles = _get_handle(f, mode, encoding=self.encoding,\n\u001b[0;32m   1984\u001b[0m                                  \u001b[0mcompression\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcompression\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1985\u001b[1;33m                                  memory_map=self.memory_map)\n\u001b[0m\u001b[0;32m   1986\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhandles\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mhandles\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1987\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mD:\\ProgramData\\conda3.05\\lib\\site-packages\\pandas\\io\\common.py\u001b[0m in \u001b[0;36m_get_handle\u001b[1;34m(path_or_buf, mode, encoding, compression, memory_map, is_text)\u001b[0m\n\u001b[0;32m    383\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0mis_text\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    384\u001b[0m             \u001b[1;31m# Python 3 and no explicit encoding\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 385\u001b[1;33m             \u001b[0mf\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mopen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpath_or_buf\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0merrors\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'replace'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    386\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    387\u001b[0m             \u001b[1;31m# Python 3 and binary mode\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: './data/movietweetings/movies.dat'"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "movies = pd.read_csv('./data/movietweetings/movies.dat', delimiter='::',\n",
    "                     engine='python', header=None, names=['Movie ID', 'Movie Title', 'Genre'])\n",
    "users = pd.read_csv('./data/movietweetings/users.dat', delimiter='::',\n",
    "                    engine='python', header=None, names=['User ID', 'Twitter ID'])\n",
    "ratings = pd.read_csv('./data/movietweetings/ratings.dat', delimiter='::', engine='python',\n",
    "                      header=None, names=['User ID', 'Movie ID', 'Rating', 'Rating Timestamp'])\n",
    "\n",
    "print(movies.head(10))\n",
    "mask = movies.Genre.str.contains('comedy', case=False, na=False)\n",
    "print(mask.head(10))\n",
    "comedy = movies[mask]\n",
    "comedy_ids = comedy['Movie ID']\n",
    "print(comedy_ids.head(10))\n",
    "\n",
    "combine = ratings.join(comedy, on='Movie ID', rsuffix='right')\n",
    "print(combine.head(50))\n",
    "result = combine[combine['Movie IDright'] != np.NaN]\n",
    "print(result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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
}