added recommendations and content loader

backend/Predictions.ipynb

@@ -0,0 +1,302 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "0b7b123f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import difflib\n",
+    "import pickle \n",
+    "import json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "4d9e252b",
+   "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>Unnamed: 0</th>\n",
+       "      <th>imdb_title_id</th>\n",
+       "      <th>original_title</th>\n",
+       "      <th>year</th>\n",
+       "      <th>genre</th>\n",
+       "      <th>director</th>\n",
+       "      <th>actors</th>\n",
+       "      <th>avg_vote</th>\n",
+       "      <th>cast_size</th>\n",
+       "      <th>comb</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>tt0035423</td>\n",
+       "      <td>kate &amp; leopold</td>\n",
+       "      <td>2001</td>\n",
+       "      <td>Comedy, Fantasy, Romance</td>\n",
+       "      <td>James Mangold</td>\n",
+       "      <td>Meg Ryan Hugh Jackman Liev Schreiber Breckin M...</td>\n",
+       "      <td>6.4</td>\n",
+       "      <td>15</td>\n",
+       "      <td>James Mangold Meg Ryan Hugh Jackman Liev Schre...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>tt0069049</td>\n",
+       "      <td>the other side of the wind</td>\n",
+       "      <td>2018</td>\n",
+       "      <td>Drama</td>\n",
+       "      <td>Orson Welles</td>\n",
+       "      <td>John Huston Oja Kodar Peter Bogdanovich Susan ...</td>\n",
+       "      <td>6.8</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Orson Welles John Huston Oja Kodar Peter Bogda...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>tt0088751</td>\n",
+       "      <td>the naked monster</td>\n",
+       "      <td>2005</td>\n",
+       "      <td>Comedy, Horror, Sci-Fi</td>\n",
+       "      <td>Wayne Berwick, Ted Newsom</td>\n",
+       "      <td>Kenneth Tobey Brinke Stevens R.G. Wilson John ...</td>\n",
+       "      <td>5.4</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Wayne Berwick, Ted Newsom Kenneth Tobey Brinke...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>tt0096056</td>\n",
+       "      <td>crime and punishment</td>\n",
+       "      <td>2002</td>\n",
+       "      <td>Drama</td>\n",
+       "      <td>Menahem Golan</td>\n",
+       "      <td>Crispin Glover Vanessa Redgrave John Hurt Marg...</td>\n",
+       "      <td>5.8</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Menahem Golan Crispin Glover Vanessa Redgrave ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>4</td>\n",
+       "      <td>tt0113026</td>\n",
+       "      <td>the fantasticks</td>\n",
+       "      <td>2000</td>\n",
+       "      <td>Musical, Romance</td>\n",
+       "      <td>Michael Ritchie</td>\n",
+       "      <td>Joel Grey Barnard Hughes Jean Louisa Kelly Joe...</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Michael Ritchie Joel Grey Barnard Hughes Jean ...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Unnamed: 0 imdb_title_id              original_title  year  \\\n",
+       "0           0     tt0035423              kate & leopold  2001   \n",
+       "1           1     tt0069049  the other side of the wind  2018   \n",
+       "2           2     tt0088751           the naked monster  2005   \n",
+       "3           3     tt0096056        crime and punishment  2002   \n",
+       "4           4     tt0113026             the fantasticks  2000   \n",
+       "\n",
+       "                      genre                   director  \\\n",
+       "0  Comedy, Fantasy, Romance              James Mangold   \n",
+       "1                     Drama               Orson Welles   \n",
+       "2    Comedy, Horror, Sci-Fi  Wayne Berwick, Ted Newsom   \n",
+       "3                     Drama              Menahem Golan   \n",
+       "4          Musical, Romance            Michael Ritchie   \n",
+       "\n",
+       "                                              actors  avg_vote  cast_size  \\\n",
+       "0  Meg Ryan Hugh Jackman Liev Schreiber Breckin M...       6.4         15   \n",
+       "1  John Huston Oja Kodar Peter Bogdanovich Susan ...       6.8         15   \n",
+       "2  Kenneth Tobey Brinke Stevens R.G. Wilson John ...       5.4         15   \n",
+       "3  Crispin Glover Vanessa Redgrave John Hurt Marg...       5.8         15   \n",
+       "4  Joel Grey Barnard Hughes Jean Louisa Kelly Joe...       5.6         15   \n",
+       "\n",
+       "                                                comb  \n",
+       "0  James Mangold Meg Ryan Hugh Jackman Liev Schre...  \n",
+       "1  Orson Welles John Huston Oja Kodar Peter Bogda...  \n",
+       "2  Wayne Berwick, Ted Newsom Kenneth Tobey Brinke...  \n",
+       "3  Menahem Golan Crispin Glover Vanessa Redgrave ...  \n",
+       "4  Michael Ritchie Joel Grey Barnard Hughes Jean ...  "
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "movieslist = pickle.load(open('movieslist.pkl','rb'))\n",
+    "movieslist.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b670471f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\LEGION\\AppData\\Roaming\\Python\\Python39\\site-packages\\IPython\\core\\interactiveshell.py:3441: DtypeWarning: Columns (3) have mixed types.Specify dtype option on import or set low_memory=False.\n",
+      "  exec(code_obj, self.user_global_ns, self.user_ns)\n"
+     ]
+    }
+   ],
+   "source": [
+    "similarity = pickle.load(open('similarity.pkl','rb'))\n",
+    "df = pd.read_csv('final_movies.csv')\n",
+    "movies_titles = df['original_title'].tolist()\n",
+    "big_df = pd.read_csv('IMDb movies.csv')\n",
+    "mt = big_df['original_title'].tolist()\n",
+    "def closest(arr,s):\n",
+    "    l = s.split()\n",
+    "    l = set(l)\n",
+    "    match = arr[0]\n",
+    "    wrd_match = -1\n",
+    "    if(len(s.split())==1):\n",
+    "        for i in arr:\n",
+    "            i1 = set(i.split())\n",
+    "            if wrd_match<len(list(l&i1)):\n",
+    "                wrd_match = max(wrd_match,len(list(l&i1)))\n",
+    "                match = i\n",
+    "    return match"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "253e6beb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "similarity_arr=similarity.tolist()\n",
+    "with open(\"sample.json\", \"w\") as outfile:\n",
+    "    json.dump(similarity_arr, outfile)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "c7e7474d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "the avengers\n",
+      "avengers: age of ultron\n",
+      "avengers: infinity war\n",
+      "iron man 2\n",
+      "avengers: endgame\n",
+      "captain america: civil war\n",
+      "captain america: the winter soldier\n",
+      "iron man\n",
+      "much ado about nothing\n",
+      "thor\n",
+      "iron man three\n"
+     ]
+    }
+   ],
+   "source": [
+    "name = input(\"Enter a movie name: \")\n",
+    "name = name.lower()\n",
+    "close_match = difflib.get_close_matches(name,movies_titles)\n",
+    "# close_match[0]\n",
+    "closest_match = closest(close_match,name).lower()\n",
+    "print(closest_match)\n",
+    "closest_index = df[df['original_title'] == closest_match].index.values[0]\n",
+    "similarity_score = list(enumerate(similarity[closest_index]))\n",
+    "# print(similarity_score)\n",
+    "sorted_score = sorted(similarity_score, key=lambda x: x[1], reverse=True)\n",
+    "# print(sorted_score)\n",
+    "for i in range(1, 11):\n",
+    "    idx = sorted_score[i][0]\n",
+    "    # print(idx)de\n",
+    "    print(df['original_title'][idx])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4d4e9a9e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['finding nemo', 'finding joy', 'finding neighbors']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(difflib.get_close_matches('finding nemo',movies_titles))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "49521031",
+   "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": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}