{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# MovieLens Data Processing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Import packages\n",
    "import os\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Define file directories\n",
    "MOVIELENS_DIR = 'dat'\n",
    "USER_DATA_FILE = 'users.dat'\n",
    "MOVIE_DATA_FILE = 'movies.dat'\n",
    "RATING_DATA_FILE = 'ratings.dat'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Specify User's Age and Occupation Column\n",
    "AGES = { 1: \"Under 18\", 18: \"18-24\", 25: \"25-34\", 35: \"35-44\", 45: \"45-49\", 50: \"50-55\", 56: \"56+\" }\n",
    "OCCUPATIONS = { 0: \"other or not specified\", 1: \"academic/educator\", 2: \"artist\", 3: \"clerical/admin\",\n",
    "                4: \"college/grad student\", 5: \"customer service\", 6: \"doctor/health care\",\n",
    "                7: \"executive/managerial\", 8: \"farmer\", 9: \"homemaker\", 10: \"K-12 student\", 11: \"lawyer\",\n",
    "                12: \"programmer\", 13: \"retired\", 14: \"sales/marketing\", 15: \"scientist\", 16: \"self-employed\",\n",
    "                17: \"technician/engineer\", 18: \"tradesman/craftsman\", 19: \"unemployed\", 20: \"writer\" }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Define csv files to be saved into\n",
    "USERS_CSV_FILE = 'users.csv'\n",
    "MOVIES_CSV_FILE = 'movies.csv'\n",
    "RATINGS_CSV_FILE = 'ratings.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1000209 ratings loaded\n"
     ]
    }
   ],
   "source": [
    "# Read the Ratings File\n",
    "ratings = pd.read_csv(os.path.join(MOVIELENS_DIR, RATING_DATA_FILE), \n",
    "                    sep='::', \n",
    "                    engine='python', \n",
    "                    encoding='latin-1',\n",
    "                    names=['user_id', 'movie_id', 'rating', 'timestamp'])\n",
    "\n",
    "# Set max_userid to the maximum user_id in the ratings\n",
    "max_userid = ratings['user_id'].drop_duplicates().max()\n",
    "# Set max_movieid to the maximum movie_id in the ratings\n",
    "max_movieid = ratings['movie_id'].drop_duplicates().max()\n",
    "\n",
    "# Process ratings dataframe for Keras Deep Learning model\n",
    "# Add user_emb_id column whose values == user_id - 1\n",
    "ratings['user_emb_id'] = ratings['user_id'] - 1\n",
    "# Add movie_emb_id column whose values == movie_id - 1\n",
    "ratings['movie_emb_id'] = ratings['movie_id'] - 1\n",
    "\n",
    "print len(ratings), 'ratings loaded'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saved to ratings.csv\n"
     ]
    }
   ],
   "source": [
    "# Save into ratings.csv\n",
    "ratings.to_csv(RATINGS_CSV_FILE, \n",
    "               sep='\\t', \n",
    "               header=True, \n",
    "               encoding='latin-1', \n",
    "               columns=['user_id', 'movie_id', 'rating', 'timestamp', 'user_emb_id', 'movie_emb_id'])\n",
    "print 'Saved to', RATINGS_CSV_FILE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "6040 descriptions of 6040 users loaded.\n"
     ]
    }
   ],
   "source": [
    "# Read the Users File\n",
    "users = pd.read_csv(os.path.join(MOVIELENS_DIR, USER_DATA_FILE), \n",
    "                    sep='::', \n",
    "                    engine='python', \n",
    "                    encoding='latin-1',\n",
    "                    names=['user_id', 'gender', 'age', 'occupation', 'zipcode'])\n",
    "users['age_desc'] = users['age'].apply(lambda x: AGES[x])\n",
    "users['occ_desc'] = users['occupation'].apply(lambda x: OCCUPATIONS[x])\n",
    "print len(users), 'descriptions of', max_userid, 'users loaded.'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saved to users.csv\n"
     ]
    }
   ],
   "source": [
    "# Save into users.csv\n",
    "users.to_csv(USERS_CSV_FILE, \n",
    "             sep='\\t', \n",
    "             header=True, \n",
    "             encoding='latin-1',\n",
    "             columns=['user_id', 'gender', 'age', 'occupation', 'zipcode', 'age_desc', 'occ_desc'])\n",
    "print 'Saved to', USERS_CSV_FILE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3883 descriptions of 3952 movies loaded.\n"
     ]
    }
   ],
   "source": [
    "# Read the Movies File\n",
    "movies = pd.read_csv(os.path.join(MOVIELENS_DIR, MOVIE_DATA_FILE), \n",
    "                    sep='::', \n",
    "                    engine='python', \n",
    "                    encoding='latin-1',\n",
    "                    names=['movie_id', 'title', 'genres'])\n",
    "print len(movies), 'descriptions of', max_movieid, 'movies loaded.'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saved to movies.csv\n"
     ]
    }
   ],
   "source": [
    "# Save into movies.csv\n",
    "movies.to_csv(MOVIES_CSV_FILE, \n",
    "              sep='\\t', \n",
    "              header=True, \n",
    "              columns=['movie_id', 'title', 'genres'])\n",
    "print 'Saved to', MOVIES_CSV_FILE"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}