rec-code/Chapter7/Hybrid Recom...

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Hybrid Recommenders"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#Import or compute the cosine_sim matrix\n",
    "cosine_sim = pd.read_csv('../data/cosine_sim.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Import or compute the cosine sim mapping matrix\n",
    "cosine_sim_map = pd.read_csv('../data/cosine_sim_map.csv', header=None)\n",
    "\n",
    "#Convert cosine_sim_map into a Pandas Series\n",
    "cosine_sim_map = cosine_sim_map.set_index(0)\n",
    "cosine_sim_map = cosine_sim_map[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Build the SVD based Collaborative filter\n",
    "from surprise import SVD, Reader, Dataset\n",
    "\n",
    "reader = Reader()\n",
    "ratings = pd.read_csv('../data/ratings_small.csv')\n",
    "data = Dataset.load_from_df(ratings[['userId', 'movieId', 'rating']], reader)\n",
    "data.split(n_folds=5)\n",
    "svd = SVD()\n",
    "trainset = data.build_full_trainset()\n",
    "svd.train(trainset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Build title to ID and ID to title mappings\n",
    "id_map = pd.read_csv('../data/movie_ids.csv')\n",
    "id_to_title = id_map.set_index('id')\n",
    "title_to_id = id_map.set_index('title')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Import or compute relevant metadata of the movies\n",
    "smd = pd.read_csv('../data/metadata_small.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def hybrid(userId, title):\n",
    "    #Extract the cosine_sim index of the movie\n",
    "    idx = cosine_sim_map[title]\n",
    "    \n",
    "    #Extract the TMDB ID of the movie\n",
    "    tmdbId = title_to_id.loc[title]['id']\n",
    "    \n",
    "    #Extract the movie ID internally assigned by the dataset\n",
    "    movie_id = title_to_id.loc[title]['movieId']\n",
    "    \n",
    "    #Extract the similarity scores and their corresponding index for every movie from the cosine_sim matrix\n",
    "    sim_scores = list(enumerate(cosine_sim[str(int(idx))]))\n",
    "    \n",
    "    #Sort the (index, score) tuples in decreasing order of similarity scores\n",
    "    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)\n",
    "    \n",
    "    #Select the top 25 tuples, excluding the first \n",
    "    #(as it is the similarity score of the movie with itself)\n",
    "    sim_scores = sim_scores[1:26]\n",
    "    \n",
    "    #Store the cosine_sim indices of the top 25 movies in a list\n",
    "    movie_indices = [i[0] for i in sim_scores]\n",
    "\n",
    "    #Extract the metadata of the aforementioned movies\n",
    "    movies = smd.iloc[movie_indices][['title', 'vote_count', 'vote_average', 'year', 'id']]\n",
    "    \n",
    "    #Compute the predicted ratings using the SVD filter\n",
    "    movies['est'] = movies['id'].apply(lambda x: svd.predict(userId, id_to_title.loc[x]['movieId']).est)\n",
    "    \n",
    "    #Sort the movies in decreasing order of predicted rating\n",
    "    movies = movies.sort_values('est', ascending=False)\n",
    "    \n",
    "    #Return the top 10 movies as recommendations\n",
    "    return movies.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>title</th>\n",
       "      <th>vote_count</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>year</th>\n",
       "      <th>id</th>\n",
       "      <th>est</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1011</th>\n",
       "      <td>The Terminator</td>\n",
       "      <td>4208.0</td>\n",
       "      <td>7.4</td>\n",
       "      <td>1984</td>\n",
       "      <td>218</td>\n",
       "      <td>3.140748</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>974</th>\n",
       "      <td>Aliens</td>\n",
       "      <td>3282.0</td>\n",
       "      <td>7.7</td>\n",
       "      <td>1986</td>\n",
       "      <td>679</td>\n",
       "      <td>3.126947</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8401</th>\n",
       "      <td>Star Trek Into Darkness</td>\n",
       "      <td>4479.0</td>\n",
       "      <td>7.4</td>\n",
       "      <td>2013</td>\n",
       "      <td>54138</td>\n",
       "      <td>3.079551</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7705</th>\n",
       "      <td>Alice in Wonderland</td>\n",
       "      <td>8.0</td>\n",
       "      <td>5.4</td>\n",
       "      <td>1933</td>\n",
       "      <td>25694</td>\n",
       "      <td>3.054995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3060</th>\n",
       "      <td>Sinbad and the Eye of the Tiger</td>\n",
       "      <td>39.0</td>\n",
       "      <td>6.3</td>\n",
       "      <td>1977</td>\n",
       "      <td>11940</td>\n",
       "      <td>3.028386</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8658</th>\n",
       "      <td>X-Men: Days of Future Past</td>\n",
       "      <td>6155.0</td>\n",
       "      <td>7.5</td>\n",
       "      <td>2014</td>\n",
       "      <td>127585</td>\n",
       "      <td>2.997411</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>Fantastic Planet</td>\n",
       "      <td>140.0</td>\n",
       "      <td>7.6</td>\n",
       "      <td>1973</td>\n",
       "      <td>16306</td>\n",
       "      <td>2.957614</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>522</th>\n",
       "      <td>Terminator 2: Judgment Day</td>\n",
       "      <td>4274.0</td>\n",
       "      <td>7.7</td>\n",
       "      <td>1991</td>\n",
       "      <td>280</td>\n",
       "      <td>2.914548</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1621</th>\n",
       "      <td>Darby O'Gill and the Little People</td>\n",
       "      <td>35.0</td>\n",
       "      <td>6.7</td>\n",
       "      <td>1959</td>\n",
       "      <td>18887</td>\n",
       "      <td>2.844940</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1668</th>\n",
       "      <td>Return from Witch Mountain</td>\n",
       "      <td>38.0</td>\n",
       "      <td>5.6</td>\n",
       "      <td>1978</td>\n",
       "      <td>14822</td>\n",
       "      <td>2.804012</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                   title  vote_count  vote_average  year  \\\n",
       "1011                      The Terminator      4208.0           7.4  1984   \n",
       "974                               Aliens      3282.0           7.7  1986   \n",
       "8401             Star Trek Into Darkness      4479.0           7.4  2013   \n",
       "7705                 Alice in Wonderland         8.0           5.4  1933   \n",
       "3060     Sinbad and the Eye of the Tiger        39.0           6.3  1977   \n",
       "8658          X-Men: Days of Future Past      6155.0           7.5  2014   \n",
       "2014                    Fantastic Planet       140.0           7.6  1973   \n",
       "522           Terminator 2: Judgment Day      4274.0           7.7  1991   \n",
       "1621  Darby O'Gill and the Little People        35.0           6.7  1959   \n",
       "1668          Return from Witch Mountain        38.0           5.6  1978   \n",
       "\n",
       "          id       est  \n",
       "1011     218  3.140748  \n",
       "974      679  3.126947  \n",
       "8401   54138  3.079551  \n",
       "7705   25694  3.054995  \n",
       "3060   11940  3.028386  \n",
       "8658  127585  2.997411  \n",
       "2014   16306  2.957614  \n",
       "522      280  2.914548  \n",
       "1621   18887  2.844940  \n",
       "1668   14822  2.804012  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hybrid(1, 'Avatar')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>title</th>\n",
       "      <th>vote_count</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>year</th>\n",
       "      <th>id</th>\n",
       "      <th>est</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>522</th>\n",
       "      <td>Terminator 2: Judgment Day</td>\n",
       "      <td>4274.0</td>\n",
       "      <td>7.7</td>\n",
       "      <td>1991</td>\n",
       "      <td>280</td>\n",
       "      <td>3.943639</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2834</th>\n",
       "      <td>Predator</td>\n",
       "      <td>2129.0</td>\n",
       "      <td>7.3</td>\n",
       "      <td>1987</td>\n",
       "      <td>106</td>\n",
       "      <td>3.866272</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8401</th>\n",
       "      <td>Star Trek Into Darkness</td>\n",
       "      <td>4479.0</td>\n",
       "      <td>7.4</td>\n",
       "      <td>2013</td>\n",
       "      <td>54138</td>\n",
       "      <td>3.858491</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1011</th>\n",
       "      <td>The Terminator</td>\n",
       "      <td>4208.0</td>\n",
       "      <td>7.4</td>\n",
       "      <td>1984</td>\n",
       "      <td>218</td>\n",
       "      <td>3.856029</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7705</th>\n",
       "      <td>Alice in Wonderland</td>\n",
       "      <td>8.0</td>\n",
       "      <td>5.4</td>\n",
       "      <td>1933</td>\n",
       "      <td>25694</td>\n",
       "      <td>3.701565</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>922</th>\n",
       "      <td>The Abyss</td>\n",
       "      <td>822.0</td>\n",
       "      <td>7.1</td>\n",
       "      <td>1989</td>\n",
       "      <td>2756</td>\n",
       "      <td>3.676465</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>974</th>\n",
       "      <td>Aliens</td>\n",
       "      <td>3282.0</td>\n",
       "      <td>7.7</td>\n",
       "      <td>1986</td>\n",
       "      <td>679</td>\n",
       "      <td>3.672303</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1621</th>\n",
       "      <td>Darby O'Gill and the Little People</td>\n",
       "      <td>35.0</td>\n",
       "      <td>6.7</td>\n",
       "      <td>1959</td>\n",
       "      <td>18887</td>\n",
       "      <td>3.628234</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1668</th>\n",
       "      <td>Return from Witch Mountain</td>\n",
       "      <td>38.0</td>\n",
       "      <td>5.6</td>\n",
       "      <td>1978</td>\n",
       "      <td>14822</td>\n",
       "      <td>3.614118</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>Fantastic Planet</td>\n",
       "      <td>140.0</td>\n",
       "      <td>7.6</td>\n",
       "      <td>1973</td>\n",
       "      <td>16306</td>\n",
       "      <td>3.602051</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                   title  vote_count  vote_average  year  \\\n",
       "522           Terminator 2: Judgment Day      4274.0           7.7  1991   \n",
       "2834                            Predator      2129.0           7.3  1987   \n",
       "8401             Star Trek Into Darkness      4479.0           7.4  2013   \n",
       "1011                      The Terminator      4208.0           7.4  1984   \n",
       "7705                 Alice in Wonderland         8.0           5.4  1933   \n",
       "922                            The Abyss       822.0           7.1  1989   \n",
       "974                               Aliens      3282.0           7.7  1986   \n",
       "1621  Darby O'Gill and the Little People        35.0           6.7  1959   \n",
       "1668          Return from Witch Mountain        38.0           5.6  1978   \n",
       "2014                    Fantastic Planet       140.0           7.6  1973   \n",
       "\n",
       "         id       est  \n",
       "522     280  3.943639  \n",
       "2834    106  3.866272  \n",
       "8401  54138  3.858491  \n",
       "1011    218  3.856029  \n",
       "7705  25694  3.701565  \n",
       "922    2756  3.676465  \n",
       "974     679  3.672303  \n",
       "1621  18887  3.628234  \n",
       "1668  14822  3.614118  \n",
       "2014  16306  3.602051  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hybrid(2, 'Avatar')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}