Upload 6 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+movies_df.csv filter=lfs diff=lfs merge=lfs -text
+my_index.ann filter=lfs diff=lfs merge=lfs -text
+TMDB.csv filter=lfs diff=lfs merge=lfs -text

TMDB.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb74d9630803fa76200511ee5fed3f23193b9ffdcb5999578f735962bcbcb57
+size 570252856

feature_array.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4211dd1420c9a800b52de53d7e82417c2fe223def70ef57b1624a024f7f9fe21
+size 88777756

meow.ipynb

@@ -0,0 +1,102 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3afa097a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Time and Space\n",
+      "A Monster From Space\n",
+      "Budhayaan\n",
+      "Manhunt in Space\n",
+      "Journey to Space\n"
+     ]
+    }
+   ],
+   "source": [
+    "from annoy import AnnoyIndex\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "\n",
+    "# Load your movie data and feature shape\n",
+    "new_movies = pd.read_csv('movies_df.csv')\n",
+    "feature_array = np.load('feature_array.npz')['arr_0']\n",
+    "f = feature_array.shape[1]  # Feature dimension\n",
+    "\n",
+    "# Create Annoy index and load from file\n",
+    "annoy_index = AnnoyIndex(f, 'angular')\n",
+    "annoy_index.load('my_index.ann')\n",
+    "\n",
+    "def get_movie_title(movie_id):\n",
+    "    return new_movies.iloc[movie_id]['title']\n",
+    "\n",
+    "def recommend_fast(movie_id, top_k=5):\n",
+    "    idxs = annoy_index.get_nns_by_item(movie_id, top_k+1)[1:] # skip itself\n",
+    "    return idxs\n",
+    "\n",
+    "# Example: Get recommendations for any movie\n",
+    "recommended_movies = recommend_fast(1)\n",
+    "for mv in recommended_movies:\n",
+    "    print(get_movie_title(mv))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "39068f98",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Time and Space\n",
+      "A Monster From Space\n",
+      "Budhayaan\n",
+      "Manhunt in Space\n",
+      "Journey to Space\n"
+     ]
+    }
+   ],
+   "source": [
+    "recommended_movies = recommend_fast(1)\n",
+    "for mv in recommended_movies:\n",
+    "    print(get_movie_title(mv))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f22a4417",
+   "metadata": {},
+   "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": "3.13.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

movie.ipynb

@@ -0,0 +1,1674 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c9c09288",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Defaulting to user installation because normal site-packages is not writeable\n",
+      "Requirement already satisfied: pandas in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (2.3.2)\n",
+      "Requirement already satisfied: numpy in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (2.2.4)\n",
+      "Requirement already satisfied: python-dateutil>=2.8.2 in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from pandas) (2.9.0.post0)\n",
+      "Requirement already satisfied: pytz>=2020.1 in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from pandas) (2025.2)\n",
+      "Requirement already satisfied: tzdata>=2022.7 in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from pandas) (2025.2)\n",
+      "Requirement already satisfied: six>=1.5 in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from python-dateutil>=2.8.2->pandas) (1.17.0)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "[notice] A new release of pip is available: 25.0.1 -> 25.2\n",
+      "[notice] To update, run: C:\\Users\\unkno\\AppData\\Local\\Microsoft\\WindowsApps\\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\\python.exe -m pip install --upgrade pip\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install pandas numpy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "0f6a3484",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "ae7debab",
+   "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>id</th>\n",
+       "      <th>title</th>\n",
+       "      <th>vote_average</th>\n",
+       "      <th>vote_count</th>\n",
+       "      <th>status</th>\n",
+       "      <th>release_date</th>\n",
+       "      <th>revenue</th>\n",
+       "      <th>runtime</th>\n",
+       "      <th>adult</th>\n",
+       "      <th>backdrop_path</th>\n",
+       "      <th>...</th>\n",
+       "      <th>original_title</th>\n",
+       "      <th>overview</th>\n",
+       "      <th>popularity</th>\n",
+       "      <th>poster_path</th>\n",
+       "      <th>tagline</th>\n",
+       "      <th>genres</th>\n",
+       "      <th>production_companies</th>\n",
+       "      <th>production_countries</th>\n",
+       "      <th>spoken_languages</th>\n",
+       "      <th>keywords</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>27205</td>\n",
+       "      <td>Inception</td>\n",
+       "      <td>8.364</td>\n",
+       "      <td>34495</td>\n",
+       "      <td>Released</td>\n",
+       "      <td>2010-07-15</td>\n",
+       "      <td>825532764</td>\n",
+       "      <td>148</td>\n",
+       "      <td>False</td>\n",
+       "      <td>/8ZTVqvKDQ8emSGUEMjsS4yHAwrp.jpg</td>\n",
+       "      <td>...</td>\n",
+       "      <td>Inception</td>\n",
+       "      <td>Cobb, a skilled thief who commits corporate es...</td>\n",
+       "      <td>83.952</td>\n",
+       "      <td>/oYuLEt3zVCKq57qu2F8dT7NIa6f.jpg</td>\n",
+       "      <td>Your mind is the scene of the crime.</td>\n",
+       "      <td>Action, Science Fiction, Adventure</td>\n",
+       "      <td>Legendary Pictures, Syncopy, Warner Bros. Pict...</td>\n",
+       "      <td>United Kingdom, United States of America</td>\n",
+       "      <td>English, French, Japanese, Swahili</td>\n",
+       "      <td>rescue, mission, dream, airplane, paris, franc...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1 rows × 24 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      id      title  vote_average  vote_count    status release_date  \\\n",
+       "0  27205  Inception         8.364       34495  Released   2010-07-15   \n",
+       "\n",
+       "     revenue  runtime  adult                     backdrop_path  ...  \\\n",
+       "0  825532764      148  False  /8ZTVqvKDQ8emSGUEMjsS4yHAwrp.jpg  ...   \n",
+       "\n",
+       "   original_title                                           overview  \\\n",
+       "0       Inception  Cobb, a skilled thief who commits corporate es...   \n",
+       "\n",
+       "  popularity                       poster_path  \\\n",
+       "0     83.952  /oYuLEt3zVCKq57qu2F8dT7NIa6f.jpg   \n",
+       "\n",
+       "                                tagline                              genres  \\\n",
+       "0  Your mind is the scene of the crime.  Action, Science Fiction, Adventure   \n",
+       "\n",
+       "                                production_companies  \\\n",
+       "0  Legendary Pictures, Syncopy, Warner Bros. Pict...   \n",
+       "\n",
+       "                       production_countries  \\\n",
+       "0  United Kingdom, United States of America   \n",
+       "\n",
+       "                     spoken_languages  \\\n",
+       "0  English, French, Japanese, Swahili   \n",
+       "\n",
+       "                                            keywords  \n",
+       "0  rescue, mission, dream, airplane, paris, franc...  \n",
+       "\n",
+       "[1 rows x 24 columns]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "movies = pd.read_csv(\"TMDB.csv\")\n",
+    "movies.head(1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "0fece246",
+   "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>id</th>\n",
+       "      <th>title</th>\n",
+       "      <th>overview</th>\n",
+       "      <th>poster_path</th>\n",
+       "      <th>backdrop_path</th>\n",
+       "      <th>tagline</th>\n",
+       "      <th>genres</th>\n",
+       "      <th>keywords</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>27205</td>\n",
+       "      <td>Inception</td>\n",
+       "      <td>Cobb, a skilled thief who commits corporate es...</td>\n",
+       "      <td>/oYuLEt3zVCKq57qu2F8dT7NIa6f.jpg</td>\n",
+       "      <td>/8ZTVqvKDQ8emSGUEMjsS4yHAwrp.jpg</td>\n",
+       "      <td>Your mind is the scene of the crime.</td>\n",
+       "      <td>Action, Science Fiction, Adventure</td>\n",
+       "      <td>rescue, mission, dream, airplane, paris, franc...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>157336</td>\n",
+       "      <td>Interstellar</td>\n",
+       "      <td>The adventures of a group of explorers who mak...</td>\n",
+       "      <td>/gEU2QniE6E77NI6lCU6MxlNBvIx.jpg</td>\n",
+       "      <td>/pbrkL804c8yAv3zBZR4QPEafpAR.jpg</td>\n",
+       "      <td>Mankind was born on Earth. It was never meant ...</td>\n",
+       "      <td>Adventure, Drama, Science Fiction</td>\n",
+       "      <td>rescue, future, spacecraft, race against time,...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>155</td>\n",
+       "      <td>The Dark Knight</td>\n",
+       "      <td>Batman raises the stakes in his war on crime. ...</td>\n",
+       "      <td>/qJ2tW6WMUDux911r6m7haRef0WH.jpg</td>\n",
+       "      <td>/nMKdUUepR0i5zn0y1T4CsSB5chy.jpg</td>\n",
+       "      <td>Welcome to a world without rules.</td>\n",
+       "      <td>Drama, Action, Crime, Thriller</td>\n",
+       "      <td>joker, sadism, chaos, secret identity, crime f...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>19995</td>\n",
+       "      <td>Avatar</td>\n",
+       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
+       "      <td>/kyeqWdyUXW608qlYkRqosgbbJyK.jpg</td>\n",
+       "      <td>/vL5LR6WdxWPjLPFRLe133jXWsh5.jpg</td>\n",
+       "      <td>Enter the world of Pandora.</td>\n",
+       "      <td>Action, Adventure, Fantasy, Science Fiction</td>\n",
+       "      <td>future, society, culture clash, space travel, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>24428</td>\n",
+       "      <td>The Avengers</td>\n",
+       "      <td>When an unexpected enemy emerges and threatens...</td>\n",
+       "      <td>/RYMX2wcKCBAr24UyPD7xwmjaTn.jpg</td>\n",
+       "      <td>/9BBTo63ANSmhC4e6r62OJFuK2GL.jpg</td>\n",
+       "      <td>Some assembly required.</td>\n",
+       "      <td>Science Fiction, Action, Adventure</td>\n",
+       "      <td>new york city, superhero, shield, based on com...</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266860</th>\n",
+       "      <td>796654</td>\n",
+       "      <td>Numéro Complémentaire</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>/xR5oBqeGUHszPSuzhf6Xqb74UT2.jpg</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Comedy</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266861</th>\n",
+       "      <td>796656</td>\n",
+       "      <td>Heimat Tansania - Unter dem Kilimandscharo</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Documentary</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266862</th>\n",
+       "      <td>796657</td>\n",
+       "      <td>Car Crash: Who's Lying?</td>\n",
+       "      <td>Documentary exploring the aftermath of a car c...</td>\n",
+       "      <td>/yatOGyk6OZKtfZQlRIBnHYwfSHD.jpg</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Documentary</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266863</th>\n",
+       "      <td>796658</td>\n",
+       "      <td>Cowboy</td>\n",
+       "      <td>Having grown up in a home with an abusive fath...</td>\n",
+       "      <td>/fhPUn11H9wU0cGWLpo6WMcMXb9a.jpg</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Documentary, Animation</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266864</th>\n",
+       "      <td>1525030</td>\n",
+       "      <td>Detective Kibbles: Part 2 | Remastered</td>\n",
+       "      <td>After a brutal attack in his own home, Detecti...</td>\n",
+       "      <td>/74SKZslJiJrO1nK4LnFa7ztesxZ.jpg</td>\n",
+       "      <td>/q436vhtfFMJzaqkSgiy9wDhZ3FI.jpg</td>\n",
+       "      <td>Every hero must have an end.</td>\n",
+       "      <td>Crime, Comedy, Drama</td>\n",
+       "      <td>police, detective, drama, kibbles</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1266865 rows × 8 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "              id                                       title  \\\n",
+       "0          27205                                   Inception   \n",
+       "1         157336                                Interstellar   \n",
+       "2            155                             The Dark Knight   \n",
+       "3          19995                                      Avatar   \n",
+       "4          24428                                The Avengers   \n",
+       "...          ...                                         ...   \n",
+       "1266860   796654                       Numéro Complémentaire   \n",
+       "1266861   796656  Heimat Tansania - Unter dem Kilimandscharo   \n",
+       "1266862   796657                     Car Crash: Who's Lying?   \n",
+       "1266863   796658                                      Cowboy   \n",
+       "1266864  1525030      Detective Kibbles: Part 2 | Remastered   \n",
+       "\n",
+       "                                                  overview  \\\n",
+       "0        Cobb, a skilled thief who commits corporate es...   \n",
+       "1        The adventures of a group of explorers who mak...   \n",
+       "2        Batman raises the stakes in his war on crime. ...   \n",
+       "3        In the 22nd century, a paraplegic Marine is di...   \n",
+       "4        When an unexpected enemy emerges and threatens...   \n",
+       "...                                                    ...   \n",
+       "1266860                                                NaN   \n",
+       "1266861                                                NaN   \n",
+       "1266862  Documentary exploring the aftermath of a car c...   \n",
+       "1266863  Having grown up in a home with an abusive fath...   \n",
+       "1266864  After a brutal attack in his own home, Detecti...   \n",
+       "\n",
+       "                              poster_path                     backdrop_path  \\\n",
+       "0        /oYuLEt3zVCKq57qu2F8dT7NIa6f.jpg  /8ZTVqvKDQ8emSGUEMjsS4yHAwrp.jpg   \n",
+       "1        /gEU2QniE6E77NI6lCU6MxlNBvIx.jpg  /pbrkL804c8yAv3zBZR4QPEafpAR.jpg   \n",
+       "2        /qJ2tW6WMUDux911r6m7haRef0WH.jpg  /nMKdUUepR0i5zn0y1T4CsSB5chy.jpg   \n",
+       "3        /kyeqWdyUXW608qlYkRqosgbbJyK.jpg  /vL5LR6WdxWPjLPFRLe133jXWsh5.jpg   \n",
+       "4         /RYMX2wcKCBAr24UyPD7xwmjaTn.jpg  /9BBTo63ANSmhC4e6r62OJFuK2GL.jpg   \n",
+       "...                                   ...                               ...   \n",
+       "1266860  /xR5oBqeGUHszPSuzhf6Xqb74UT2.jpg                               NaN   \n",
+       "1266861                               NaN                               NaN   \n",
+       "1266862  /yatOGyk6OZKtfZQlRIBnHYwfSHD.jpg                               NaN   \n",
+       "1266863  /fhPUn11H9wU0cGWLpo6WMcMXb9a.jpg                               NaN   \n",
+       "1266864  /74SKZslJiJrO1nK4LnFa7ztesxZ.jpg  /q436vhtfFMJzaqkSgiy9wDhZ3FI.jpg   \n",
+       "\n",
+       "                                                   tagline  \\\n",
+       "0                     Your mind is the scene of the crime.   \n",
+       "1        Mankind was born on Earth. It was never meant ...   \n",
+       "2                        Welcome to a world without rules.   \n",
+       "3                              Enter the world of Pandora.   \n",
+       "4                                  Some assembly required.   \n",
+       "...                                                    ...   \n",
+       "1266860                                                NaN   \n",
+       "1266861                                                NaN   \n",
+       "1266862                                                NaN   \n",
+       "1266863                                                NaN   \n",
+       "1266864                       Every hero must have an end.   \n",
+       "\n",
+       "                                              genres  \\\n",
+       "0                 Action, Science Fiction, Adventure   \n",
+       "1                  Adventure, Drama, Science Fiction   \n",
+       "2                     Drama, Action, Crime, Thriller   \n",
+       "3        Action, Adventure, Fantasy, Science Fiction   \n",
+       "4                 Science Fiction, Action, Adventure   \n",
+       "...                                              ...   \n",
+       "1266860                                       Comedy   \n",
+       "1266861                                  Documentary   \n",
+       "1266862                                  Documentary   \n",
+       "1266863                       Documentary, Animation   \n",
+       "1266864                         Crime, Comedy, Drama   \n",
+       "\n",
+       "                                                  keywords  \n",
+       "0        rescue, mission, dream, airplane, paris, franc...  \n",
+       "1        rescue, future, spacecraft, race against time,...  \n",
+       "2        joker, sadism, chaos, secret identity, crime f...  \n",
+       "3        future, society, culture clash, space travel, ...  \n",
+       "4        new york city, superhero, shield, based on com...  \n",
+       "...                                                    ...  \n",
+       "1266860                                                NaN  \n",
+       "1266861                                                NaN  \n",
+       "1266862                                                NaN  \n",
+       "1266863                                                NaN  \n",
+       "1266864                  police, detective, drama, kibbles  \n",
+       "\n",
+       "[1266865 rows x 8 columns]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "movies = movies[[\"id\",\"title\",\"overview\",\"poster_path\",\"backdrop_path\",\"tagline\",\"genres\",\"keywords\"]]\n",
+    "movies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4217a767",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "\n",
+    "\n",
+    "def convert_string_list(value):\n",
+    "    value = re.sub(r\"[^\\w\\s]\", \"\", value)\n",
+    "    return \",\".join(value.split())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8be31676",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "movies = movies[movies['overview'].notna()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "ea71ec24",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0          Cobb, a skilled thief who commits corporate es...\n",
+       "1          The adventures of a group of explorers who mak...\n",
+       "2          Batman raises the stakes in his war on crime. ...\n",
+       "3          In the 22nd century, a paraplegic Marine is di...\n",
+       "4          When an unexpected enemy emerges and threatens...\n",
+       "                                 ...                        \n",
+       "1266856    A warrior is transported 1,000 years into the ...\n",
+       "1266857    The utilization of numerical oscillation model...\n",
+       "1266862    Documentary exploring the aftermath of a car c...\n",
+       "1266863    Having grown up in a home with an abusive fath...\n",
+       "1266864    After a brutal attack in his own home, Detecti...\n",
+       "Name: overview, Length: 991491, dtype: object"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "movies['overview']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "cc7e4bc4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\unkno\\AppData\\Local\\Temp\\ipykernel_5356\\1915643281.py:1: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  movies['overview']=movies['overview'].apply(convert_string_list)\n"
+     ]
+    }
+   ],
+   "source": [
+    "movies['overview']=movies['overview'].apply(convert_string_list)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "2428a165",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\unkno\\AppData\\Local\\Temp\\ipykernel_5356\\42895326.py:1: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  movies.drop(columns=[\"backdrop_path\"], inplace=True)\n"
+     ]
+    }
+   ],
+   "source": [
+    "movies.drop(columns=[\"backdrop_path\"], inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "e7e4288e",
+   "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>id</th>\n",
+       "      <th>title</th>\n",
+       "      <th>overview</th>\n",
+       "      <th>poster_path</th>\n",
+       "      <th>tagline</th>\n",
+       "      <th>genres</th>\n",
+       "      <th>keywords</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>27205</td>\n",
+       "      <td>Inception</td>\n",
+       "      <td>Cobb,a,skilled,thief,who,commits,corporate,esp...</td>\n",
+       "      <td>/oYuLEt3zVCKq57qu2F8dT7NIa6f.jpg</td>\n",
+       "      <td>Your mind is the scene of the crime.</td>\n",
+       "      <td>Action, Science Fiction, Adventure</td>\n",
+       "      <td>rescue, mission, dream, airplane, paris, franc...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>157336</td>\n",
+       "      <td>Interstellar</td>\n",
+       "      <td>The,adventures,of,a,group,of,explorers,who,mak...</td>\n",
+       "      <td>/gEU2QniE6E77NI6lCU6MxlNBvIx.jpg</td>\n",
+       "      <td>Mankind was born on Earth. It was never meant ...</td>\n",
+       "      <td>Adventure, Drama, Science Fiction</td>\n",
+       "      <td>rescue, future, spacecraft, race against time,...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>155</td>\n",
+       "      <td>The Dark Knight</td>\n",
+       "      <td>Batman,raises,the,stakes,in,his,war,on,crime,W...</td>\n",
+       "      <td>/qJ2tW6WMUDux911r6m7haRef0WH.jpg</td>\n",
+       "      <td>Welcome to a world without rules.</td>\n",
+       "      <td>Drama, Action, Crime, Thriller</td>\n",
+       "      <td>joker, sadism, chaos, secret identity, crime f...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>19995</td>\n",
+       "      <td>Avatar</td>\n",
+       "      <td>In,the,22nd,century,a,paraplegic,Marine,is,dis...</td>\n",
+       "      <td>/kyeqWdyUXW608qlYkRqosgbbJyK.jpg</td>\n",
+       "      <td>Enter the world of Pandora.</td>\n",
+       "      <td>Action, Adventure, Fantasy, Science Fiction</td>\n",
+       "      <td>future, society, culture clash, space travel, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>24428</td>\n",
+       "      <td>The Avengers</td>\n",
+       "      <td>When,an,unexpected,enemy,emerges,and,threatens...</td>\n",
+       "      <td>/RYMX2wcKCBAr24UyPD7xwmjaTn.jpg</td>\n",
+       "      <td>Some assembly required.</td>\n",
+       "      <td>Science Fiction, Action, Adventure</td>\n",
+       "      <td>new york city, superhero, shield, based on com...</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266856</th>\n",
+       "      <td>796650</td>\n",
+       "      <td>Survival of a Dragon</td>\n",
+       "      <td>A,warrior,is,transported,1000,years,into,the,p...</td>\n",
+       "      <td>/qX69cmtnyc9EfE3WN2UF3UI5Ta8.jpg</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Adventure, Action, Fantasy</td>\n",
+       "      <td>time travel</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266857</th>\n",
+       "      <td>796651</td>\n",
+       "      <td>A Model for the Motion of a Spring</td>\n",
+       "      <td>The,utilization,of,numerical,oscillation,model...</td>\n",
+       "      <td>/3s2vSewmxpdnzrWwPamkBbAM7mo.jpg</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Fantasy</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266862</th>\n",
+       "      <td>796657</td>\n",
+       "      <td>Car Crash: Who's Lying?</td>\n",
+       "      <td>Documentary,exploring,the,aftermath,of,a,car,c...</td>\n",
+       "      <td>/yatOGyk6OZKtfZQlRIBnHYwfSHD.jpg</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Documentary</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266863</th>\n",
+       "      <td>796658</td>\n",
+       "      <td>Cowboy</td>\n",
+       "      <td>Having,grown,up,in,a,home,with,an,abusive,fath...</td>\n",
+       "      <td>/fhPUn11H9wU0cGWLpo6WMcMXb9a.jpg</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Documentary, Animation</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266864</th>\n",
+       "      <td>1525030</td>\n",
+       "      <td>Detective Kibbles: Part 2 | Remastered</td>\n",
+       "      <td>After,a,brutal,attack,in,his,own,home,Detectiv...</td>\n",
+       "      <td>/74SKZslJiJrO1nK4LnFa7ztesxZ.jpg</td>\n",
+       "      <td>Every hero must have an end.</td>\n",
+       "      <td>Crime, Comedy, Drama</td>\n",
+       "      <td>police, detective, drama, kibbles</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>991491 rows × 7 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "              id                                   title  \\\n",
+       "0          27205                               Inception   \n",
+       "1         157336                            Interstellar   \n",
+       "2            155                         The Dark Knight   \n",
+       "3          19995                                  Avatar   \n",
+       "4          24428                            The Avengers   \n",
+       "...          ...                                     ...   \n",
+       "1266856   796650                    Survival of a Dragon   \n",
+       "1266857   796651      A Model for the Motion of a Spring   \n",
+       "1266862   796657                 Car Crash: Who's Lying?   \n",
+       "1266863   796658                                  Cowboy   \n",
+       "1266864  1525030  Detective Kibbles: Part 2 | Remastered   \n",
+       "\n",
+       "                                                  overview  \\\n",
+       "0        Cobb,a,skilled,thief,who,commits,corporate,esp...   \n",
+       "1        The,adventures,of,a,group,of,explorers,who,mak...   \n",
+       "2        Batman,raises,the,stakes,in,his,war,on,crime,W...   \n",
+       "3        In,the,22nd,century,a,paraplegic,Marine,is,dis...   \n",
+       "4        When,an,unexpected,enemy,emerges,and,threatens...   \n",
+       "...                                                    ...   \n",
+       "1266856  A,warrior,is,transported,1000,years,into,the,p...   \n",
+       "1266857  The,utilization,of,numerical,oscillation,model...   \n",
+       "1266862  Documentary,exploring,the,aftermath,of,a,car,c...   \n",
+       "1266863  Having,grown,up,in,a,home,with,an,abusive,fath...   \n",
+       "1266864  After,a,brutal,attack,in,his,own,home,Detectiv...   \n",
+       "\n",
+       "                              poster_path  \\\n",
+       "0        /oYuLEt3zVCKq57qu2F8dT7NIa6f.jpg   \n",
+       "1        /gEU2QniE6E77NI6lCU6MxlNBvIx.jpg   \n",
+       "2        /qJ2tW6WMUDux911r6m7haRef0WH.jpg   \n",
+       "3        /kyeqWdyUXW608qlYkRqosgbbJyK.jpg   \n",
+       "4         /RYMX2wcKCBAr24UyPD7xwmjaTn.jpg   \n",
+       "...                                   ...   \n",
+       "1266856  /qX69cmtnyc9EfE3WN2UF3UI5Ta8.jpg   \n",
+       "1266857  /3s2vSewmxpdnzrWwPamkBbAM7mo.jpg   \n",
+       "1266862  /yatOGyk6OZKtfZQlRIBnHYwfSHD.jpg   \n",
+       "1266863  /fhPUn11H9wU0cGWLpo6WMcMXb9a.jpg   \n",
+       "1266864  /74SKZslJiJrO1nK4LnFa7ztesxZ.jpg   \n",
+       "\n",
+       "                                                   tagline  \\\n",
+       "0                     Your mind is the scene of the crime.   \n",
+       "1        Mankind was born on Earth. It was never meant ...   \n",
+       "2                        Welcome to a world without rules.   \n",
+       "3                              Enter the world of Pandora.   \n",
+       "4                                  Some assembly required.   \n",
+       "...                                                    ...   \n",
+       "1266856                                                NaN   \n",
+       "1266857                                                NaN   \n",
+       "1266862                                                NaN   \n",
+       "1266863                                                NaN   \n",
+       "1266864                       Every hero must have an end.   \n",
+       "\n",
+       "                                              genres  \\\n",
+       "0                 Action, Science Fiction, Adventure   \n",
+       "1                  Adventure, Drama, Science Fiction   \n",
+       "2                     Drama, Action, Crime, Thriller   \n",
+       "3        Action, Adventure, Fantasy, Science Fiction   \n",
+       "4                 Science Fiction, Action, Adventure   \n",
+       "...                                              ...   \n",
+       "1266856                   Adventure, Action, Fantasy   \n",
+       "1266857                                      Fantasy   \n",
+       "1266862                                  Documentary   \n",
+       "1266863                       Documentary, Animation   \n",
+       "1266864                         Crime, Comedy, Drama   \n",
+       "\n",
+       "                                                  keywords  \n",
+       "0        rescue, mission, dream, airplane, paris, franc...  \n",
+       "1        rescue, future, spacecraft, race against time,...  \n",
+       "2        joker, sadism, chaos, secret identity, crime f...  \n",
+       "3        future, society, culture clash, space travel, ...  \n",
+       "4        new york city, superhero, shield, based on com...  \n",
+       "...                                                    ...  \n",
+       "1266856                                        time travel  \n",
+       "1266857                                                NaN  \n",
+       "1266862                                                NaN  \n",
+       "1266863                                                NaN  \n",
+       "1266864                  police, detective, drama, kibbles  \n",
+       "\n",
+       "[991491 rows x 7 columns]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "movies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d9704c70",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\unkno\\AppData\\Local\\Temp\\ipykernel_5356\\1367133233.py:1: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  movies['tagline'] = movies['tagline'].fillna(\"\")\n",
+      "C:\\Users\\unkno\\AppData\\Local\\Temp\\ipykernel_5356\\1367133233.py:2: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  movies['keywords'] = movies['keywords'].fillna(\"\")\n"
+     ]
+    }
+   ],
+   "source": [
+    "movies['tagline'] = movies['tagline'].fillna(\"\") \n",
+    "movies['keywords'] = movies['keywords'].fillna(\"\") "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "c4b3977b",
+   "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>id</th>\n",
+       "      <th>title</th>\n",
+       "      <th>overview</th>\n",
+       "      <th>poster_path</th>\n",
+       "      <th>tagline</th>\n",
+       "      <th>genres</th>\n",
+       "      <th>keywords</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>27205</td>\n",
+       "      <td>Inception</td>\n",
+       "      <td>Cobb,a,skilled,thief,who,commits,corporate,esp...</td>\n",
+       "      <td>/oYuLEt3zVCKq57qu2F8dT7NIa6f.jpg</td>\n",
+       "      <td>Your mind is the scene of the crime.</td>\n",
+       "      <td>Action, Science Fiction, Adventure</td>\n",
+       "      <td>rescue, mission, dream, airplane, paris, franc...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>157336</td>\n",
+       "      <td>Interstellar</td>\n",
+       "      <td>The,adventures,of,a,group,of,explorers,who,mak...</td>\n",
+       "      <td>/gEU2QniE6E77NI6lCU6MxlNBvIx.jpg</td>\n",
+       "      <td>Mankind was born on Earth. It was never meant ...</td>\n",
+       "      <td>Adventure, Drama, Science Fiction</td>\n",
+       "      <td>rescue, future, spacecraft, race against time,...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>155</td>\n",
+       "      <td>The Dark Knight</td>\n",
+       "      <td>Batman,raises,the,stakes,in,his,war,on,crime,W...</td>\n",
+       "      <td>/qJ2tW6WMUDux911r6m7haRef0WH.jpg</td>\n",
+       "      <td>Welcome to a world without rules.</td>\n",
+       "      <td>Drama, Action, Crime, Thriller</td>\n",
+       "      <td>joker, sadism, chaos, secret identity, crime f...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>19995</td>\n",
+       "      <td>Avatar</td>\n",
+       "      <td>In,the,22nd,century,a,paraplegic,Marine,is,dis...</td>\n",
+       "      <td>/kyeqWdyUXW608qlYkRqosgbbJyK.jpg</td>\n",
+       "      <td>Enter the world of Pandora.</td>\n",
+       "      <td>Action, Adventure, Fantasy, Science Fiction</td>\n",
+       "      <td>future, society, culture clash, space travel, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>24428</td>\n",
+       "      <td>The Avengers</td>\n",
+       "      <td>When,an,unexpected,enemy,emerges,and,threatens...</td>\n",
+       "      <td>/RYMX2wcKCBAr24UyPD7xwmjaTn.jpg</td>\n",
+       "      <td>Some assembly required.</td>\n",
+       "      <td>Science Fiction, Action, Adventure</td>\n",
+       "      <td>new york city, superhero, shield, based on com...</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266856</th>\n",
+       "      <td>796650</td>\n",
+       "      <td>Survival of a Dragon</td>\n",
+       "      <td>A,warrior,is,transported,1000,years,into,the,p...</td>\n",
+       "      <td>/qX69cmtnyc9EfE3WN2UF3UI5Ta8.jpg</td>\n",
+       "      <td></td>\n",
+       "      <td>Adventure, Action, Fantasy</td>\n",
+       "      <td>time travel</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266857</th>\n",
+       "      <td>796651</td>\n",
+       "      <td>A Model for the Motion of a Spring</td>\n",
+       "      <td>The,utilization,of,numerical,oscillation,model...</td>\n",
+       "      <td>/3s2vSewmxpdnzrWwPamkBbAM7mo.jpg</td>\n",
+       "      <td></td>\n",
+       "      <td>Fantasy</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266862</th>\n",
+       "      <td>796657</td>\n",
+       "      <td>Car Crash: Who's Lying?</td>\n",
+       "      <td>Documentary,exploring,the,aftermath,of,a,car,c...</td>\n",
+       "      <td>/yatOGyk6OZKtfZQlRIBnHYwfSHD.jpg</td>\n",
+       "      <td></td>\n",
+       "      <td>Documentary</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266863</th>\n",
+       "      <td>796658</td>\n",
+       "      <td>Cowboy</td>\n",
+       "      <td>Having,grown,up,in,a,home,with,an,abusive,fath...</td>\n",
+       "      <td>/fhPUn11H9wU0cGWLpo6WMcMXb9a.jpg</td>\n",
+       "      <td></td>\n",
+       "      <td>Documentary, Animation</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266864</th>\n",
+       "      <td>1525030</td>\n",
+       "      <td>Detective Kibbles: Part 2 | Remastered</td>\n",
+       "      <td>After,a,brutal,attack,in,his,own,home,Detectiv...</td>\n",
+       "      <td>/74SKZslJiJrO1nK4LnFa7ztesxZ.jpg</td>\n",
+       "      <td>Every hero must have an end.</td>\n",
+       "      <td>Crime, Comedy, Drama</td>\n",
+       "      <td>police, detective, drama, kibbles</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>991491 rows × 7 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "              id                                   title  \\\n",
+       "0          27205                               Inception   \n",
+       "1         157336                            Interstellar   \n",
+       "2            155                         The Dark Knight   \n",
+       "3          19995                                  Avatar   \n",
+       "4          24428                            The Avengers   \n",
+       "...          ...                                     ...   \n",
+       "1266856   796650                    Survival of a Dragon   \n",
+       "1266857   796651      A Model for the Motion of a Spring   \n",
+       "1266862   796657                 Car Crash: Who's Lying?   \n",
+       "1266863   796658                                  Cowboy   \n",
+       "1266864  1525030  Detective Kibbles: Part 2 | Remastered   \n",
+       "\n",
+       "                                                  overview  \\\n",
+       "0        Cobb,a,skilled,thief,who,commits,corporate,esp...   \n",
+       "1        The,adventures,of,a,group,of,explorers,who,mak...   \n",
+       "2        Batman,raises,the,stakes,in,his,war,on,crime,W...   \n",
+       "3        In,the,22nd,century,a,paraplegic,Marine,is,dis...   \n",
+       "4        When,an,unexpected,enemy,emerges,and,threatens...   \n",
+       "...                                                    ...   \n",
+       "1266856  A,warrior,is,transported,1000,years,into,the,p...   \n",
+       "1266857  The,utilization,of,numerical,oscillation,model...   \n",
+       "1266862  Documentary,exploring,the,aftermath,of,a,car,c...   \n",
+       "1266863  Having,grown,up,in,a,home,with,an,abusive,fath...   \n",
+       "1266864  After,a,brutal,attack,in,his,own,home,Detectiv...   \n",
+       "\n",
+       "                              poster_path  \\\n",
+       "0        /oYuLEt3zVCKq57qu2F8dT7NIa6f.jpg   \n",
+       "1        /gEU2QniE6E77NI6lCU6MxlNBvIx.jpg   \n",
+       "2        /qJ2tW6WMUDux911r6m7haRef0WH.jpg   \n",
+       "3        /kyeqWdyUXW608qlYkRqosgbbJyK.jpg   \n",
+       "4         /RYMX2wcKCBAr24UyPD7xwmjaTn.jpg   \n",
+       "...                                   ...   \n",
+       "1266856  /qX69cmtnyc9EfE3WN2UF3UI5Ta8.jpg   \n",
+       "1266857  /3s2vSewmxpdnzrWwPamkBbAM7mo.jpg   \n",
+       "1266862  /yatOGyk6OZKtfZQlRIBnHYwfSHD.jpg   \n",
+       "1266863  /fhPUn11H9wU0cGWLpo6WMcMXb9a.jpg   \n",
+       "1266864  /74SKZslJiJrO1nK4LnFa7ztesxZ.jpg   \n",
+       "\n",
+       "                                                   tagline  \\\n",
+       "0                     Your mind is the scene of the crime.   \n",
+       "1        Mankind was born on Earth. It was never meant ...   \n",
+       "2                        Welcome to a world without rules.   \n",
+       "3                              Enter the world of Pandora.   \n",
+       "4                                  Some assembly required.   \n",
+       "...                                                    ...   \n",
+       "1266856                                                      \n",
+       "1266857                                                      \n",
+       "1266862                                                      \n",
+       "1266863                                                      \n",
+       "1266864                       Every hero must have an end.   \n",
+       "\n",
+       "                                              genres  \\\n",
+       "0                 Action, Science Fiction, Adventure   \n",
+       "1                  Adventure, Drama, Science Fiction   \n",
+       "2                     Drama, Action, Crime, Thriller   \n",
+       "3        Action, Adventure, Fantasy, Science Fiction   \n",
+       "4                 Science Fiction, Action, Adventure   \n",
+       "...                                              ...   \n",
+       "1266856                   Adventure, Action, Fantasy   \n",
+       "1266857                                      Fantasy   \n",
+       "1266862                                  Documentary   \n",
+       "1266863                       Documentary, Animation   \n",
+       "1266864                         Crime, Comedy, Drama   \n",
+       "\n",
+       "                                                  keywords  \n",
+       "0        rescue, mission, dream, airplane, paris, franc...  \n",
+       "1        rescue, future, spacecraft, race against time,...  \n",
+       "2        joker, sadism, chaos, secret identity, crime f...  \n",
+       "3        future, society, culture clash, space travel, ...  \n",
+       "4        new york city, superhero, shield, based on com...  \n",
+       "...                                                    ...  \n",
+       "1266856                                        time travel  \n",
+       "1266857                                                     \n",
+       "1266862                                                     \n",
+       "1266863                                                     \n",
+       "1266864                  police, detective, drama, kibbles  \n",
+       "\n",
+       "[991491 rows x 7 columns]"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "movies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "d68c1ec7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\unkno\\AppData\\Local\\Temp\\ipykernel_5356\\3940781081.py:1: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  movies['encode_list'] = (\n"
+     ]
+    }
+   ],
+   "source": [
+    "movies['encode_list'] = (\n",
+    "    movies['overview'].fillna('') + \" \" +\n",
+    "    movies['genres'].fillna('') + \" \" +\n",
+    "    movies['keywords'].fillna('')\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "fa8d3290",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0          Cobb,a,skilled,thief,who,commits,corporate,esp...\n",
+       "1          The,adventures,of,a,group,of,explorers,who,mak...\n",
+       "2          Batman,raises,the,stakes,in,his,war,on,crime,W...\n",
+       "3          In,the,22nd,century,a,paraplegic,Marine,is,dis...\n",
+       "4          When,an,unexpected,enemy,emerges,and,threatens...\n",
+       "                                 ...                        \n",
+       "1266856    A,warrior,is,transported,1000,years,into,the,p...\n",
+       "1266857    The,utilization,of,numerical,oscillation,model...\n",
+       "1266862    Documentary,exploring,the,aftermath,of,a,car,c...\n",
+       "1266863    Having,grown,up,in,a,home,with,an,abusive,fath...\n",
+       "1266864    After,a,brutal,attack,in,his,own,home,Detectiv...\n",
+       "Name: encode_list, Length: 991491, dtype: object"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "movies['encode_list']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "3c2cc44f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    Cobb,a,skilled,thief,who,commits,corporate,esp...\n",
+       "Name: encode_list, dtype: object"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "movies['encode_list'].head(1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "5685e307",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Defaulting to user installation because normal site-packages is not writeable\n",
+      "Requirement already satisfied: nltk in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (3.9.1)\n",
+      "Requirement already satisfied: click in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from nltk) (8.3.0)\n",
+      "Requirement already satisfied: joblib in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from nltk) (1.5.2)\n",
+      "Requirement already satisfied: regex>=2021.8.3 in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from nltk) (2024.11.6)\n",
+      "Requirement already satisfied: tqdm in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from nltk) (4.67.1)\n",
+      "Requirement already satisfied: colorama in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from click->nltk) (0.4.6)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "[notice] A new release of pip is available: 25.0.1 -> 25.2\n",
+      "[notice] To update, run: C:\\Users\\unkno\\AppData\\Local\\Microsoft\\WindowsApps\\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\\python.exe -m pip install --upgrade pip\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install nltk"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "e7182aa4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\unkno\\AppData\\Local\\Temp\\ipykernel_5356\\3196361095.py:9: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  movies['encode_list'] = movies['encode_list'].map(stem)\n"
+     ]
+    }
+   ],
+   "source": [
+    "from nltk.stem.porter import PorterStemmer\n",
+    "\n",
+    "ps = PorterStemmer()\n",
+    "\n",
+    "def stem(text):\n",
+    "    return \" \".join(ps.stem(word) for word in text.split(\",\"))\n",
+    "    \n",
+    "# Use 'map' instead of 'apply' for faster operation\n",
+    "movies['encode_list'] = movies['encode_list'].map(stem)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "eeca71ce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "new_movies = movies[['id', 'title', 'poster_path', 'encode_list']]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "82157fde",
+   "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>id</th>\n",
+       "      <th>title</th>\n",
+       "      <th>poster_path</th>\n",
+       "      <th>encode_list</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>27205</td>\n",
+       "      <td>Inception</td>\n",
+       "      <td>/oYuLEt3zVCKq57qu2F8dT7NIa6f.jpg</td>\n",
+       "      <td>cobb a skill thief who commit corpor espionag ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>157336</td>\n",
+       "      <td>Interstellar</td>\n",
+       "      <td>/gEU2QniE6E77NI6lCU6MxlNBvIx.jpg</td>\n",
+       "      <td>the adventur of a group of explor who make use...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>155</td>\n",
+       "      <td>The Dark Knight</td>\n",
+       "      <td>/qJ2tW6WMUDux911r6m7haRef0WH.jpg</td>\n",
+       "      <td>batman rais the stake in hi war on crime with ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>19995</td>\n",
+       "      <td>Avatar</td>\n",
+       "      <td>/kyeqWdyUXW608qlYkRqosgbbJyK.jpg</td>\n",
+       "      <td>in the 22nd centuri a parapleg marin is dispat...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>24428</td>\n",
+       "      <td>The Avengers</td>\n",
+       "      <td>/RYMX2wcKCBAr24UyPD7xwmjaTn.jpg</td>\n",
+       "      <td>when an unexpect enemi emerg and threaten glob...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       id            title                       poster_path  \\\n",
+       "0   27205        Inception  /oYuLEt3zVCKq57qu2F8dT7NIa6f.jpg   \n",
+       "1  157336     Interstellar  /gEU2QniE6E77NI6lCU6MxlNBvIx.jpg   \n",
+       "2     155  The Dark Knight  /qJ2tW6WMUDux911r6m7haRef0WH.jpg   \n",
+       "3   19995           Avatar  /kyeqWdyUXW608qlYkRqosgbbJyK.jpg   \n",
+       "4   24428     The Avengers   /RYMX2wcKCBAr24UyPD7xwmjaTn.jpg   \n",
+       "\n",
+       "                                         encode_list  \n",
+       "0  cobb a skill thief who commit corpor espionag ...  \n",
+       "1  the adventur of a group of explor who make use...  \n",
+       "2  batman rais the stake in hi war on crime with ...  \n",
+       "3  in the 22nd centuri a parapleg marin is dispat...  \n",
+       "4  when an unexpect enemi emerg and threaten glob...  "
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "new_movies.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "e15ed18b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Defaulting to user installation because normal site-packages is not writeable\n",
+      "Requirement already satisfied: scikit-learn in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (1.7.2)\n",
+      "Requirement already satisfied: numpy>=1.22.0 in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from scikit-learn) (2.2.4)\n",
+      "Requirement already satisfied: scipy>=1.8.0 in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from scikit-learn) (1.16.2)\n",
+      "Requirement already satisfied: joblib>=1.2.0 in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from scikit-learn) (1.5.2)\n",
+      "Requirement already satisfied: threadpoolctl>=3.1.0 in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (from scikit-learn) (3.6.0)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "[notice] A new release of pip is available: 25.0.1 -> 25.2\n",
+      "[notice] To update, run: C:\\Users\\unkno\\AppData\\Local\\Microsoft\\WindowsApps\\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\\python.exe -m pip install --upgrade pip\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install scikit-learn\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "vectorizer = TfidfVectorizer(max_features=1000, stop_words='english')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "634f446d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "features  = vectorizer.fit_transform(new_movies['encode_list']).toarray()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "d1f0fdac",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[0., 0., 0., ..., 0., 0., 0.],\n",
+       "       [0., 0., 0., ..., 0., 0., 0.],\n",
+       "       [0., 0., 0., ..., 0., 0., 0.],\n",
+       "       ...,\n",
+       "       [0., 0., 0., ..., 0., 0., 0.],\n",
+       "       [0., 0., 0., ..., 0., 0., 0.],\n",
+       "       [0., 0., 0., ..., 0., 0., 0.]], shape=(991491, 1000))"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "features"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "1ca6a500",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Skip FAISS - use sklearn only with limited data\n",
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
+    "\n",
+    "# Your features is already a numpy array - use it directly\n",
+    "feature_array = features.astype('float32')\n",
+    "\n",
+    "def get_movie_title(movie_id):\n",
+    "    return new_movies.iloc[movie_id]['title']\n",
+    "\n",
+    "def recommend(movie_id, top_k=5):\n",
+    "    # Get the feature vector for the input movie\n",
+    "    movie_vector = feature_array[movie_id].reshape(1, -1)\n",
+    "    \n",
+    "    # Calculate similarity only for this movie vs all others\n",
+    "    similarity_scores = cosine_similarity(movie_vector, feature_array).flatten()\n",
+    "    \n",
+    "    # Get top similar movies (exclude the movie itself)\n",
+    "    similar_indices = similarity_scores.argsort()[-top_k-1:-1][::-1]\n",
+    "    \n",
+    "    return similar_indices\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "c425f84f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Interstellar\n",
+      "Time and Space\n",
+      "A Monster From Space\n",
+      "Budhayaan\n",
+      "Manhunt in Space\n",
+      "Journey to Space\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(get_movie_title(1))\n",
+    "\n",
+    "recommended_movies = recommend(1)  # Get recommendations for movie at index 0\n",
+    "for mv in recommended_movies:\n",
+    "    print(get_movie_title(mv))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "65432cd8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "\n",
+    "# Save compressed numpy array\n",
+    "np.savez_compressed('feature_array.npz', feature_array)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "2139293d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "# Remove any extension type columns\n",
+    "safe_new_movies = new_movies.select_dtypes(include=['int64', 'float64', 'object']).copy()\n",
+    "\n",
+    "# Convert all columns to string as a fallback if extension issues persist\n",
+    "for col in safe_new_movies.columns:\n",
+    "    safe_new_movies[col] = safe_new_movies[col].astype(str)\n",
+    "\n",
+    "safe_new_movies.reset_index(drop=True, inplace=True)\n",
+    "\n",
+    "# Now save as parquet\n",
+    "safe_new_movies.to_csv('movies_df.csv', index=False)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "d0eb30ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
+    "\n",
+    "# Load compressed numpy feature array and movie data\n",
+    "feature_array = np.load('feature_array.npz')['arr_0']\n",
+    "new_movies = pd.read_csv('movies_df.csv')\n",
+    "\n",
+    "def get_movie_title(movie_id):\n",
+    "    return new_movies.iloc[movie_id]['title']\n",
+    "\n",
+    "def recommend(movie_id, top_k=5):\n",
+    "    movie_vector = feature_array[movie_id].reshape(1, -1)\n",
+    "    similarity_scores = cosine_similarity(movie_vector, feature_array).flatten()\n",
+    "    similar_indices = similarity_scores.argsort()[-top_k-1:-1][::-1]  # Exclude itself\n",
+    "    return similar_indices\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "c6e82e65",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Time and Space\n",
+      "A Monster From Space\n",
+      "Budhayaan\n",
+      "Manhunt in Space\n",
+      "Journey to Space\n"
+     ]
+    }
+   ],
+   "source": [
+    "recommended_movies = recommend(1)\n",
+    "for mv in recommended_movies:\n",
+    "    print(get_movie_title(mv))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a1aa9f21",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Defaulting to user installation because normal site-packages is not writeable\n",
+      "Requirement already satisfied: annoy in c:\\users\\unkno\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.13_qbz5n2kfra8p0\\localcache\\local-packages\\python313\\site-packages (1.17.3)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "[notice] A new release of pip is available: 25.0.1 -> 25.2\n",
+      "[notice] To update, run: C:\\Users\\unkno\\AppData\\Local\\Microsoft\\WindowsApps\\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\\python.exe -m pip install --upgrade pip\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Time and Space\n",
+      "A Monster From Space\n",
+      "Budhayaan\n",
+      "Manhunt in Space\n",
+      "Journey to Space\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install annoy\n",
+    "\n",
+    "from annoy import AnnoyIndex\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "\n",
+    "# Load data\n",
+    "feature_array = np.load('feature_array.npz')['arr_0']\n",
+    "new_movies = pd.read_csv('movies_df.csv')\n",
+    "f = feature_array.shape[1]\n",
+    "annoy_index = AnnoyIndex(f, 'angular')\n",
+    "\n",
+    "# Build Annoy index (run this only once, it takes some time—then it's super fast)\n",
+    "for i in range(feature_array.shape[0]):\n",
+    "    annoy_index.add_item(i, feature_array[i])\n",
+    "annoy_index.build(10)\n",
+    "\n",
+    "def get_movie_title(movie_id):\n",
+    "    return new_movies.iloc[movie_id]['title']\n",
+    "\n",
+    "def recommend_fast(movie_id, top_k=5):\n",
+    "    idxs = annoy_index.get_nns_by_item(movie_id, top_k+1)[1:] # skip itself\n",
+    "    return idxs\n",
+    "\n",
+    "# Example usage\n",
+    "recommended_movies = recommend_fast(1)\n",
+    "for mv in recommended_movies:\n",
+    "    print(get_movie_title(mv))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "26664759",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Time and Space\n",
+      "A Monster From Space\n",
+      "Budhayaan\n",
+      "Manhunt in Space\n",
+      "Journey to Space\n"
+     ]
+    }
+   ],
+   "source": [
+    "recommended_movies = recommend_fast(1)\n",
+    "for mv in recommended_movies:\n",
+    "    print(get_movie_title(mv))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "f7be3f08",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Hunger Games: Katniss & Rue\n",
+      "Offside - an Unequal Game\n",
+      "bottomofthe9th\n",
+      "Ádám Wilds - The Movie\n",
+      "Pi Pong\n"
+     ]
+    }
+   ],
+   "source": [
+    "recommended_movies = recommend_fast(200)\n",
+    "for mv in recommended_movies:\n",
+    "    print(get_movie_title(mv))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "adda9d00",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "3.851896818727255 GB\n"
+     ]
+    }
+   ],
+   "source": [
+    "annoy_index.save('my_index.ann')\n",
+    "\n",
+    "import os\n",
+    "print(os.path.getsize('my_index.ann') / (1024**3), \"GB\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1f34ea24",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n"
+   ]
+  }
+ ],
+ "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": "3.13.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

movies_df.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ed8378723b509ba7c779ce6c495a32a3d6605a12d51fb9a1821c55aea2a808
+size 309075548

my_index.ann

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51716a2ec84add79327be429a40daed697255f555ec3e1b1193c959dfbdf214f
+size 4135942716