{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>userId</th>\n",
       "      <th>movieId</th>\n",
       "      <th>rating</th>\n",
       "      <th>timestamp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>964982703</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>964981247</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>4.0</td>\n",
       "      <td>964982224</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>47</td>\n",
       "      <td>5.0</td>\n",
       "      <td>964983815</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>50</td>\n",
       "      <td>5.0</td>\n",
       "      <td>964982931</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   userId  movieId  rating  timestamp\n",
       "0       1        1     4.0  964982703\n",
       "1       1        3     4.0  964981247\n",
       "2       1        6     4.0  964982224\n",
       "3       1       47     5.0  964983815\n",
       "4       1       50     5.0  964982931"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings = pd.read_csv('../data/reduced/ratings_m10.csv')\n",
    "ratings.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>userId</th>\n",
       "      <th>movieId</th>\n",
       "      <th>rating</th>\n",
       "      <th>timestamp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>964982703</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>964981247</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>4.0</td>\n",
       "      <td>964982224</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>47</td>\n",
       "      <td>5.0</td>\n",
       "      <td>964983815</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>50</td>\n",
       "      <td>5.0</td>\n",
       "      <td>964982931</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81111</th>\n",
       "      <td>610</td>\n",
       "      <td>159093</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1493847704</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81112</th>\n",
       "      <td>610</td>\n",
       "      <td>164179</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1493845631</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81113</th>\n",
       "      <td>610</td>\n",
       "      <td>166528</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1493879365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81114</th>\n",
       "      <td>610</td>\n",
       "      <td>168250</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1494273047</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81115</th>\n",
       "      <td>610</td>\n",
       "      <td>168252</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1493846352</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>81116 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       userId  movieId  rating   timestamp\n",
       "0           1        1     4.0   964982703\n",
       "1           1        3     4.0   964981247\n",
       "2           1        6     4.0   964982224\n",
       "3           1       47     5.0   964983815\n",
       "4           1       50     5.0   964982931\n",
       "...       ...      ...     ...         ...\n",
       "81111     610   159093     3.0  1493847704\n",
       "81112     610   164179     5.0  1493845631\n",
       "81113     610   166528     4.0  1493879365\n",
       "81114     610   168250     5.0  1494273047\n",
       "81115     610   168252     5.0  1493846352\n",
       "\n",
       "[81116 rows x 4 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings.reindex()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>tmdbId</th>\n",
       "      <th>imdbId</th>\n",
       "      <th>cast</th>\n",
       "      <th>director</th>\n",
       "      <th>keywords</th>\n",
       "      <th>overview</th>\n",
       "      <th>title</th>\n",
       "      <th>genres</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>movieId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>117529</th>\n",
       "      <td>135397</td>\n",
       "      <td>369610</td>\n",
       "      <td>['Chris Pratt', 'Bryce Dallas Howard', 'Irrfan...</td>\n",
       "      <td>Colin Trevorrow</td>\n",
       "      <td>['monster', 'dna', 'tyrannosaurus rex', 'veloc...</td>\n",
       "      <td>Twenty-two years after the events of Jurassic ...</td>\n",
       "      <td>Jurassic World</td>\n",
       "      <td>['Action', 'Adventure', 'Drama', 'Sci-Fi', 'Th...</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>122882</th>\n",
       "      <td>76341</td>\n",
       "      <td>1392190</td>\n",
       "      <td>['Tom Hardy', 'Charlize Theron', 'Hugh Keays-B...</td>\n",
       "      <td>George Miller</td>\n",
       "      <td>['future', 'chase', 'post-apocalyptic', 'dysto...</td>\n",
       "      <td>An apocalyptic story set in the furthest reach...</td>\n",
       "      <td>Mad Max: Fury Road</td>\n",
       "      <td>['Action', 'Adventure', 'Sci-Fi', 'Thriller']</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>122886</th>\n",
       "      <td>140607</td>\n",
       "      <td>2488496</td>\n",
       "      <td>['Harrison Ford', 'Mark Hamill', 'Carrie Fishe...</td>\n",
       "      <td>J.J. Abrams</td>\n",
       "      <td>['android', 'spaceship', 'jedi', 'space opera'...</td>\n",
       "      <td>Thirty years after defeating the Galactic Empi...</td>\n",
       "      <td>Star Wars: Episode VII - The Force Awakens</td>\n",
       "      <td>['Action', 'Adventure', 'Fantasy', 'Sci-Fi', '...</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>139385</th>\n",
       "      <td>281957</td>\n",
       "      <td>1663202</td>\n",
       "      <td>['Leonardo DiCaprio', 'Tom Hardy', 'Will Poult...</td>\n",
       "      <td>Alejandro González Iñárritu</td>\n",
       "      <td>['father-son relationship', 'rape', 'based on ...</td>\n",
       "      <td>In the 1820s, a frontiersman, Hugh Glass, sets...</td>\n",
       "      <td>The Revenant</td>\n",
       "      <td>['Adventure', 'Drama']</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>134130</th>\n",
       "      <td>286217</td>\n",
       "      <td>3659388</td>\n",
       "      <td>['Matt Damon', 'Jessica Chastain', 'Kristen Wi...</td>\n",
       "      <td>Ridley Scott</td>\n",
       "      <td>['based on novel', 'mars', 'nasa', 'isolation'...</td>\n",
       "      <td>During a manned mission to Mars, Astronaut Mar...</td>\n",
       "      <td>The Martian</td>\n",
       "      <td>['Adventure', 'Drama', 'Sci-Fi']</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         tmdbId   imdbId                                               cast  \\\n",
       "movieId                                                                       \n",
       "117529   135397   369610  ['Chris Pratt', 'Bryce Dallas Howard', 'Irrfan...   \n",
       "122882    76341  1392190  ['Tom Hardy', 'Charlize Theron', 'Hugh Keays-B...   \n",
       "122886   140607  2488496  ['Harrison Ford', 'Mark Hamill', 'Carrie Fishe...   \n",
       "139385   281957  1663202  ['Leonardo DiCaprio', 'Tom Hardy', 'Will Poult...   \n",
       "134130   286217  3659388  ['Matt Damon', 'Jessica Chastain', 'Kristen Wi...   \n",
       "\n",
       "                               director  \\\n",
       "movieId                                   \n",
       "117529                  Colin Trevorrow   \n",
       "122882                    George Miller   \n",
       "122886                      J.J. Abrams   \n",
       "139385   Alejandro González Iñárritu   \n",
       "134130                     Ridley Scott   \n",
       "\n",
       "                                                  keywords  \\\n",
       "movieId                                                      \n",
       "117529   ['monster', 'dna', 'tyrannosaurus rex', 'veloc...   \n",
       "122882   ['future', 'chase', 'post-apocalyptic', 'dysto...   \n",
       "122886   ['android', 'spaceship', 'jedi', 'space opera'...   \n",
       "139385   ['father-son relationship', 'rape', 'based on ...   \n",
       "134130   ['based on novel', 'mars', 'nasa', 'isolation'...   \n",
       "\n",
       "                                                  overview  \\\n",
       "movieId                                                      \n",
       "117529   Twenty-two years after the events of Jurassic ...   \n",
       "122882   An apocalyptic story set in the furthest reach...   \n",
       "122886   Thirty years after defeating the Galactic Empi...   \n",
       "139385   In the 1820s, a frontiersman, Hugh Glass, sets...   \n",
       "134130   During a manned mission to Mars, Astronaut Mar...   \n",
       "\n",
       "                                               title  \\\n",
       "movieId                                                \n",
       "117529                               Jurassic World    \n",
       "122882                           Mad Max: Fury Road    \n",
       "122886   Star Wars: Episode VII - The Force Awakens    \n",
       "139385                                 The Revenant    \n",
       "134130                                  The Martian    \n",
       "\n",
       "                                                    genres  year  \n",
       "movieId                                                           \n",
       "117529   ['Action', 'Adventure', 'Drama', 'Sci-Fi', 'Th...  2015  \n",
       "122882       ['Action', 'Adventure', 'Sci-Fi', 'Thriller']  2015  \n",
       "122886   ['Action', 'Adventure', 'Fantasy', 'Sci-Fi', '...  2015  \n",
       "139385                              ['Adventure', 'Drama']  2015  \n",
       "134130                    ['Adventure', 'Drama', 'Sci-Fi']  2015  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies = pd.read_csv('../data/reduced/movies_m10_rich_pre.csv', index_col='movieId')\n",
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\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>genres</th>\n",
       "      <th>keywords</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>movieId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>117529</th>\n",
       "      <td>Jurassic World</td>\n",
       "      <td>['Action', 'Adventure', 'Drama', 'Sci-Fi', 'Th...</td>\n",
       "      <td>['monster', 'dna', 'tyrannosaurus rex', 'veloc...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>122882</th>\n",
       "      <td>Mad Max: Fury Road</td>\n",
       "      <td>['Action', 'Adventure', 'Sci-Fi', 'Thriller']</td>\n",
       "      <td>['future', 'chase', 'post-apocalyptic', 'dysto...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>122886</th>\n",
       "      <td>Star Wars: Episode VII - The Force Awakens</td>\n",
       "      <td>['Action', 'Adventure', 'Fantasy', 'Sci-Fi', '...</td>\n",
       "      <td>['android', 'spaceship', 'jedi', 'space opera'...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>139385</th>\n",
       "      <td>The Revenant</td>\n",
       "      <td>['Adventure', 'Drama']</td>\n",
       "      <td>['father-son relationship', 'rape', 'based on ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>134130</th>\n",
       "      <td>The Martian</td>\n",
       "      <td>['Adventure', 'Drama', 'Sci-Fi']</td>\n",
       "      <td>['based on novel', 'mars', 'nasa', 'isolation'...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               title  \\\n",
       "movieId                                                \n",
       "117529                               Jurassic World    \n",
       "122882                           Mad Max: Fury Road    \n",
       "122886   Star Wars: Episode VII - The Force Awakens    \n",
       "139385                                 The Revenant    \n",
       "134130                                  The Martian    \n",
       "\n",
       "                                                    genres  \\\n",
       "movieId                                                      \n",
       "117529   ['Action', 'Adventure', 'Drama', 'Sci-Fi', 'Th...   \n",
       "122882       ['Action', 'Adventure', 'Sci-Fi', 'Thriller']   \n",
       "122886   ['Action', 'Adventure', 'Fantasy', 'Sci-Fi', '...   \n",
       "139385                              ['Adventure', 'Drama']   \n",
       "134130                    ['Adventure', 'Drama', 'Sci-Fi']   \n",
       "\n",
       "                                                  keywords  \n",
       "movieId                                                     \n",
       "117529   ['monster', 'dna', 'tyrannosaurus rex', 'veloc...  \n",
       "122882   ['future', 'chase', 'post-apocalyptic', 'dysto...  \n",
       "122886   ['android', 'spaceship', 'jedi', 'space opera'...  \n",
       "139385   ['father-son relationship', 'rape', 'based on ...  \n",
       "134130   ['based on novel', 'mars', 'nasa', 'isolation'...  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies_redu = movies[['title', 'genres', 'keywords']]\n",
    "movies_redu.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>userId</th>\n",
       "      <th>movieId</th>\n",
       "      <th>rating</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>title</th>\n",
       "      <th>genres</th>\n",
       "      <th>keywords</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>964982703</td>\n",
       "      <td>Toy Story</td>\n",
       "      <td>['Adventure', 'Animation', 'Children', 'Comedy...</td>\n",
       "      <td>['jealousy', 'toy', 'boy', 'friendship', 'frie...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>847434962</td>\n",
       "      <td>Toy Story</td>\n",
       "      <td>['Adventure', 'Animation', 'Children', 'Comedy...</td>\n",
       "      <td>['jealousy', 'toy', 'boy', 'friendship', 'frie...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>4.5</td>\n",
       "      <td>1106635946</td>\n",
       "      <td>Toy Story</td>\n",
       "      <td>['Adventure', 'Animation', 'Children', 'Comedy...</td>\n",
       "      <td>['jealousy', 'toy', 'boy', 'friendship', 'frie...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "      <td>2.5</td>\n",
       "      <td>1510577970</td>\n",
       "      <td>Toy Story</td>\n",
       "      <td>['Adventure', 'Animation', 'Children', 'Comedy...</td>\n",
       "      <td>['jealousy', 'toy', 'boy', 'friendship', 'frie...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>17</td>\n",
       "      <td>1</td>\n",
       "      <td>4.5</td>\n",
       "      <td>1305696483</td>\n",
       "      <td>Toy Story</td>\n",
       "      <td>['Adventure', 'Animation', 'Children', 'Comedy...</td>\n",
       "      <td>['jealousy', 'toy', 'boy', 'friendship', 'frie...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   userId  movieId  rating   timestamp       title  \\\n",
       "0       1        1     4.0   964982703  Toy Story    \n",
       "1       5        1     4.0   847434962  Toy Story    \n",
       "2       7        1     4.5  1106635946  Toy Story    \n",
       "3      15        1     2.5  1510577970  Toy Story    \n",
       "4      17        1     4.5  1305696483  Toy Story    \n",
       "\n",
       "                                              genres  \\\n",
       "0  ['Adventure', 'Animation', 'Children', 'Comedy...   \n",
       "1  ['Adventure', 'Animation', 'Children', 'Comedy...   \n",
       "2  ['Adventure', 'Animation', 'Children', 'Comedy...   \n",
       "3  ['Adventure', 'Animation', 'Children', 'Comedy...   \n",
       "4  ['Adventure', 'Animation', 'Children', 'Comedy...   \n",
       "\n",
       "                                            keywords  \n",
       "0  ['jealousy', 'toy', 'boy', 'friendship', 'frie...  \n",
       "1  ['jealousy', 'toy', 'boy', 'friendship', 'frie...  \n",
       "2  ['jealousy', 'toy', 'boy', 'friendship', 'frie...  \n",
       "3  ['jealousy', 'toy', 'boy', 'friendship', 'frie...  \n",
       "4  ['jealousy', 'toy', 'boy', 'friendship', 'frie...  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies_redu_ratings = ratings.merge(movies_redu, on='movieId')\n",
    "movies_redu_ratings.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>userId</th>\n",
       "      <th>movieId</th>\n",
       "      <th>rating</th>\n",
       "      <th>timestamp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>75043.000000</td>\n",
       "      <td>75043.000000</td>\n",
       "      <td>75043.000000</td>\n",
       "      <td>7.504300e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>318.733153</td>\n",
       "      <td>14432.315313</td>\n",
       "      <td>3.549458</td>\n",
       "      <td>1.195556e+09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>181.675975</td>\n",
       "      <td>28044.968471</td>\n",
       "      <td>1.019971</td>\n",
       "      <td>2.170623e+08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>8.281246e+08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>167.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>9.978116e+08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>314.000000</td>\n",
       "      <td>2502.000000</td>\n",
       "      <td>3.500000</td>\n",
       "      <td>1.180013e+09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>474.000000</td>\n",
       "      <td>6003.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.430507e+09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>610.000000</td>\n",
       "      <td>148626.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>1.537799e+09</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             userId        movieId        rating     timestamp\n",
       "count  75043.000000   75043.000000  75043.000000  7.504300e+04\n",
       "mean     318.733153   14432.315313      3.549458  1.195556e+09\n",
       "std      181.675975   28044.968471      1.019971  2.170623e+08\n",
       "min        1.000000       1.000000      0.500000  8.281246e+08\n",
       "25%      167.000000    1028.000000      3.000000  9.978116e+08\n",
       "50%      314.000000    2502.000000      3.500000  1.180013e+09\n",
       "75%      474.000000    6003.000000      4.000000  1.430507e+09\n",
       "max      610.000000  148626.000000      5.000000  1.537799e+09"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies_redu_ratings.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 75043 entries, 0 to 75042\n",
      "Data columns (total 7 columns):\n",
      " #   Column     Non-Null Count  Dtype  \n",
      "---  ------     --------------  -----  \n",
      " 0   userId     75043 non-null  int64  \n",
      " 1   movieId    75043 non-null  int64  \n",
      " 2   rating     75043 non-null  float64\n",
      " 3   timestamp  75043 non-null  int64  \n",
      " 4   title      75043 non-null  object \n",
      " 5   genres     75043 non-null  object \n",
      " 6   keywords   75043 non-null  object \n",
      "dtypes: float64(1), int64(3), object(3)\n",
      "memory usage: 4.0+ MB\n"
     ]
    }
   ],
   "source": [
    "movies_redu_ratings.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>movieId</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>...</th>\n",
       "      <th>134853</th>\n",
       "      <th>135133</th>\n",
       "      <th>135887</th>\n",
       "      <th>136020</th>\n",
       "      <th>138036</th>\n",
       "      <th>139385</th>\n",
       "      <th>139644</th>\n",
       "      <th>140110</th>\n",
       "      <th>142488</th>\n",
       "      <th>148626</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>userId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>606</th>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>607</th>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>608</th>\n",
       "      <td>2.5</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>609</th>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>610</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>3.5</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.5</td>\n",
       "      <td>3.5</td>\n",
       "      <td>4.5</td>\n",
       "      <td>4.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.5</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>610 rows × 2026 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "movieId  1       2       3       5       6       7       9       10      \\\n",
       "userId                                                                    \n",
       "1           4.0     0.0     4.0     0.0     4.0     0.0     0.0     0.0   \n",
       "2           0.0     0.0     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "3           0.0     0.0     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "4           0.0     0.0     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "5           4.0     0.0     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "...         ...     ...     ...     ...     ...     ...     ...     ...   \n",
       "606         2.5     0.0     0.0     0.0     0.0     2.5     0.0     0.0   \n",
       "607         4.0     0.0     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "608         2.5     2.0     2.0     0.0     0.0     0.0     0.0     4.0   \n",
       "609         3.0     0.0     0.0     0.0     0.0     0.0     0.0     4.0   \n",
       "610         5.0     0.0     0.0     0.0     5.0     0.0     0.0     0.0   \n",
       "\n",
       "movieId  11      12      ...  134853  135133  135887  136020  138036  139385  \\\n",
       "userId                   ...                                                   \n",
       "1           0.0     0.0  ...     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "2           0.0     0.0  ...     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "3           0.0     0.0  ...     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "4           0.0     0.0  ...     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "5           0.0     0.0  ...     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "...         ...     ...  ...     ...     ...     ...     ...     ...     ...   \n",
       "606         2.5     0.0  ...     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "607         3.0     0.0  ...     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "608         0.0     0.0  ...     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "609         0.0     0.0  ...     0.0     0.0     0.0     0.0     0.0     0.0   \n",
       "610         0.0     0.0  ...     3.5     4.0     0.0     3.5     3.5     4.5   \n",
       "\n",
       "movieId  139644  140110  142488  148626  \n",
       "userId                                   \n",
       "1           0.0     0.0     0.0     0.0  \n",
       "2           0.0     0.0     0.0     0.0  \n",
       "3           0.0     0.0     0.0     0.0  \n",
       "4           0.0     0.0     0.0     0.0  \n",
       "5           0.0     0.0     0.0     0.0  \n",
       "...         ...     ...     ...     ...  \n",
       "606         0.0     0.0     0.0     0.0  \n",
       "607         0.0     0.0     0.0     0.0  \n",
       "608         0.0     0.0     0.0     0.0  \n",
       "609         0.0     0.0     0.0     0.0  \n",
       "610         4.5     0.0     3.5     4.0  \n",
       "\n",
       "[610 rows x 2026 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "user_movie_mat = movies_redu_ratings.pivot(index='userId', columns='movieId', values='rating').fillna(0)\n",
    "user_movie_mat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.series.Series'>\n",
      "Index: 2026 entries, 117529 to 6305\n",
      "Series name: title\n",
      "Non-Null Count  Dtype \n",
      "--------------  ----- \n",
      "2026 non-null   object\n",
      "dtypes: object(1)\n",
      "memory usage: 31.7+ KB\n"
     ]
    }
   ],
   "source": [
    "movies['title'].info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "610"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings['userId'].nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>NearestNeighbors(algorithm=&#x27;brute&#x27;, metric=&#x27;cosine&#x27;, n_jobs=-1, n_neighbors=10)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">NearestNeighbors</label><div class=\"sk-toggleable__content\"><pre>NearestNeighbors(algorithm=&#x27;brute&#x27;, metric=&#x27;cosine&#x27;, n_jobs=-1, n_neighbors=10)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "NearestNeighbors(algorithm='brute', metric='cosine', n_jobs=-1, n_neighbors=10)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.neighbors import NearestNeighbors\n",
    "\n",
    "knn = NearestNeighbors(metric='cosine', algorithm='brute', n_neighbors=10, n_jobs=-1)\n",
    "\n",
    "# Fitting the model on our matrix\n",
    "knn.fit(user_movie_mat)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\felma\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\fuzzywuzzy\\fuzz.py:11: UserWarning: Using slow pure-python SequenceMatcher. Install python-Levenshtein to remove this warning\n",
      "  warnings.warn('Using slow pure-python SequenceMatcher. Install python-Levenshtein to remove this warning')\n"
     ]
    }
   ],
   "source": [
    "from fuzzywuzzy import process"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "def movie_recommender_engine(movie_name, matrix, cf_model, n_recs):\n",
    "    # Fit model on matrix\n",
    "    knn.fit(matrix.T)\n",
    "    \n",
    "    # Extract input movie ID\n",
    "    movie_id = process.extractOne(movie_name, movies_redu['title'])[2]\n",
    "\n",
    "    knn_input = np.array(matrix[movie_id]).reshape(1, -1)\n",
    "    #print(len(knn_input[0]))\n",
    "    \n",
    "    # Calculate neighbour distances\n",
    "    distances, indices = knn.kneighbors(knn_input, n_neighbors=n_recs)\n",
    "    movie_rec_ids = sorted(list(indices.squeeze().tolist()))\n",
    "    movie_rec_ids = movie_rec_ids\n",
    "    print(movie_rec_ids)\n",
    "    # List to store recommendations\n",
    "    cf_recs = []\n",
    "    for i in movie_rec_ids:\n",
    "        cf_recs.append({'Title':movies_redu.iloc[i]['title']})\n",
    "    \n",
    "    # Select top number of recommendations needed\n",
    "    df = pd.DataFrame(cf_recs, index = range(1,n_recs+1))\n",
    "     \n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0, 536, 569, 759, 879, 971, 982, 1122, 1211, 1271]\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Jurassic World</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Little Women</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Amazing Spider-Man, The</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Ender's Game</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Borat: Cultural Learnings of America for Make ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Secret Window</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Hotel Rwanda</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Revenge of the Nerds</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>First Knight</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>White Men Can't Jump</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                Title\n",
       "1                                     Jurassic World \n",
       "2                                       Little Women \n",
       "3                            Amazing Spider-Man, The \n",
       "4                                       Ender's Game \n",
       "5   Borat: Cultural Learnings of America for Make ...\n",
       "6                                      Secret Window \n",
       "7                                       Hotel Rwanda \n",
       "8                               Revenge of the Nerds \n",
       "9                                       First Knight \n",
       "10                              White Men Can't Jump "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movie_recommender_engine('toy story 2', user_movie_mat, knn, 10)"
   ]
  }
 ],
 "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}