{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## **goodbooks-10k-the-latest**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:00:53.977640Z",
     "iopub.status.busy": "2025-07-06T13:00:53.977344Z",
     "iopub.status.idle": "2025-07-06T13:00:55.797338Z",
     "shell.execute_reply": "2025-07-06T13:00:55.796558Z",
     "shell.execute_reply.started": "2025-07-06T13:00:53.977615Z"
    },
    "trusted": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:01:20.399323Z",
     "iopub.status.busy": "2025-07-06T13:01:20.398769Z",
     "iopub.status.idle": "2025-07-06T13:01:23.186859Z",
     "shell.execute_reply": "2025-07-06T13:01:23.186291Z",
     "shell.execute_reply.started": "2025-07-06T13:01:20.399297Z"
    },
    "trusted": true
   },
   "outputs": [],
   "source": [
    "book_tags_df = pd.read_csv(\"/kaggle/input/goodbooks-10k-the-latest/book_tags.csv\")\n",
    "books_df = pd.read_csv(\"/kaggle/input/goodbooks-10k-the-latest/books.csv\")\n",
    "ratings_df = pd.read_csv(\"/kaggle/input/goodbooks-10k-the-latest/ratings.csv\")\n",
    "tags_df = pd.read_csv(\"/kaggle/input/goodbooks-10k-the-latest/tags.csv\")\n",
    "to_read_df = pd.read_csv(\"/kaggle/input/goodbooks-10k-the-latest/to_read.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:01:33.994608Z",
     "iopub.status.busy": "2025-07-06T13:01:33.993937Z",
     "iopub.status.idle": "2025-07-06T13:01:34.016081Z",
     "shell.execute_reply": "2025-07-06T13:01:34.015333Z",
     "shell.execute_reply.started": "2025-07-06T13:01:33.994574Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.11/dist-packages/pandas/core/computation/expressions.py:73: RuntimeWarning: invalid value encountered in greater\n",
      "  return op(a, b)\n"
     ]
    }
   ],
   "source": [
    "books_df['original_publication_year'] = books_df[(books_df['original_publication_year'] > 0) & (books_df['original_publication_year'] > 1900)]['original_publication_year']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-05T14:12:43.116998Z",
     "iopub.status.busy": "2025-07-05T14:12:43.116738Z",
     "iopub.status.idle": "2025-07-05T14:12:43.206274Z",
     "shell.execute_reply": "2025-07-05T14:12:43.205745Z",
     "shell.execute_reply.started": "2025-07-05T14:12:43.116979Z"
    },
    "trusted": true
   },
   "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>book_id</th>\n",
       "      <th>goodreads_book_id</th>\n",
       "      <th>best_book_id</th>\n",
       "      <th>work_id</th>\n",
       "      <th>books_count</th>\n",
       "      <th>isbn</th>\n",
       "      <th>isbn13</th>\n",
       "      <th>authors</th>\n",
       "      <th>original_publication_year</th>\n",
       "      <th>original_title</th>\n",
       "      <th>...</th>\n",
       "      <th>ratings_count</th>\n",
       "      <th>work_ratings_count</th>\n",
       "      <th>work_text_reviews_count</th>\n",
       "      <th>ratings_1</th>\n",
       "      <th>ratings_2</th>\n",
       "      <th>ratings_3</th>\n",
       "      <th>ratings_4</th>\n",
       "      <th>ratings_5</th>\n",
       "      <th>image_url</th>\n",
       "      <th>small_image_url</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2792775</td>\n",
       "      <td>272</td>\n",
       "      <td>439023483</td>\n",
       "      <td>9.780439e+12</td>\n",
       "      <td>Suzanne Collins</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>The Hunger Games</td>\n",
       "      <td>...</td>\n",
       "      <td>4780653</td>\n",
       "      <td>4942365</td>\n",
       "      <td>155254</td>\n",
       "      <td>66715</td>\n",
       "      <td>127936</td>\n",
       "      <td>560092</td>\n",
       "      <td>1481305</td>\n",
       "      <td>2706317</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603m...</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603s...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>4640799</td>\n",
       "      <td>491</td>\n",
       "      <td>439554934</td>\n",
       "      <td>9.780440e+12</td>\n",
       "      <td>J.K. Rowling, Mary GrandPré</td>\n",
       "      <td>1997.0</td>\n",
       "      <td>Harry Potter and the Philosopher's Stone</td>\n",
       "      <td>...</td>\n",
       "      <td>4602479</td>\n",
       "      <td>4800065</td>\n",
       "      <td>75867</td>\n",
       "      <td>75504</td>\n",
       "      <td>101676</td>\n",
       "      <td>455024</td>\n",
       "      <td>1156318</td>\n",
       "      <td>3011543</td>\n",
       "      <td>https://images.gr-assets.com/books/1474154022m...</td>\n",
       "      <td>https://images.gr-assets.com/books/1474154022s...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>41865</td>\n",
       "      <td>41865</td>\n",
       "      <td>3212258</td>\n",
       "      <td>226</td>\n",
       "      <td>316015849</td>\n",
       "      <td>9.780316e+12</td>\n",
       "      <td>Stephenie Meyer</td>\n",
       "      <td>2005.0</td>\n",
       "      <td>Twilight</td>\n",
       "      <td>...</td>\n",
       "      <td>3866839</td>\n",
       "      <td>3916824</td>\n",
       "      <td>95009</td>\n",
       "      <td>456191</td>\n",
       "      <td>436802</td>\n",
       "      <td>793319</td>\n",
       "      <td>875073</td>\n",
       "      <td>1355439</td>\n",
       "      <td>https://images.gr-assets.com/books/1361039443m...</td>\n",
       "      <td>https://images.gr-assets.com/books/1361039443s...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>2657</td>\n",
       "      <td>2657</td>\n",
       "      <td>3275794</td>\n",
       "      <td>487</td>\n",
       "      <td>61120081</td>\n",
       "      <td>9.780061e+12</td>\n",
       "      <td>Harper Lee</td>\n",
       "      <td>1960.0</td>\n",
       "      <td>To Kill a Mockingbird</td>\n",
       "      <td>...</td>\n",
       "      <td>3198671</td>\n",
       "      <td>3340896</td>\n",
       "      <td>72586</td>\n",
       "      <td>60427</td>\n",
       "      <td>117415</td>\n",
       "      <td>446835</td>\n",
       "      <td>1001952</td>\n",
       "      <td>1714267</td>\n",
       "      <td>https://images.gr-assets.com/books/1361975680m...</td>\n",
       "      <td>https://images.gr-assets.com/books/1361975680s...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>4671</td>\n",
       "      <td>4671</td>\n",
       "      <td>245494</td>\n",
       "      <td>1356</td>\n",
       "      <td>743273567</td>\n",
       "      <td>9.780743e+12</td>\n",
       "      <td>F. Scott Fitzgerald</td>\n",
       "      <td>1925.0</td>\n",
       "      <td>The Great Gatsby</td>\n",
       "      <td>...</td>\n",
       "      <td>2683664</td>\n",
       "      <td>2773745</td>\n",
       "      <td>51992</td>\n",
       "      <td>86236</td>\n",
       "      <td>197621</td>\n",
       "      <td>606158</td>\n",
       "      <td>936012</td>\n",
       "      <td>947718</td>\n",
       "      <td>https://images.gr-assets.com/books/1490528560m...</td>\n",
       "      <td>https://images.gr-assets.com/books/1490528560s...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   book_id  goodreads_book_id  best_book_id  work_id  books_count       isbn  \\\n",
       "0        1            2767052       2767052  2792775          272  439023483   \n",
       "1        2                  3             3  4640799          491  439554934   \n",
       "2        3              41865         41865  3212258          226  316015849   \n",
       "3        4               2657          2657  3275794          487   61120081   \n",
       "4        5               4671          4671   245494         1356  743273567   \n",
       "\n",
       "         isbn13                      authors  original_publication_year  \\\n",
       "0  9.780439e+12              Suzanne Collins                     2008.0   \n",
       "1  9.780440e+12  J.K. Rowling, Mary GrandPré                     1997.0   \n",
       "2  9.780316e+12              Stephenie Meyer                     2005.0   \n",
       "3  9.780061e+12                   Harper Lee                     1960.0   \n",
       "4  9.780743e+12          F. Scott Fitzgerald                     1925.0   \n",
       "\n",
       "                             original_title  ... ratings_count  \\\n",
       "0                          The Hunger Games  ...       4780653   \n",
       "1  Harry Potter and the Philosopher's Stone  ...       4602479   \n",
       "2                                  Twilight  ...       3866839   \n",
       "3                     To Kill a Mockingbird  ...       3198671   \n",
       "4                          The Great Gatsby  ...       2683664   \n",
       "\n",
       "  work_ratings_count  work_text_reviews_count  ratings_1  ratings_2  \\\n",
       "0            4942365                   155254      66715     127936   \n",
       "1            4800065                    75867      75504     101676   \n",
       "2            3916824                    95009     456191     436802   \n",
       "3            3340896                    72586      60427     117415   \n",
       "4            2773745                    51992      86236     197621   \n",
       "\n",
       "   ratings_3  ratings_4  ratings_5  \\\n",
       "0     560092    1481305    2706317   \n",
       "1     455024    1156318    3011543   \n",
       "2     793319     875073    1355439   \n",
       "3     446835    1001952    1714267   \n",
       "4     606158     936012     947718   \n",
       "\n",
       "                                           image_url  \\\n",
       "0  https://images.gr-assets.com/books/1447303603m...   \n",
       "1  https://images.gr-assets.com/books/1474154022m...   \n",
       "2  https://images.gr-assets.com/books/1361039443m...   \n",
       "3  https://images.gr-assets.com/books/1361975680m...   \n",
       "4  https://images.gr-assets.com/books/1490528560m...   \n",
       "\n",
       "                                     small_image_url  \n",
       "0  https://images.gr-assets.com/books/1447303603s...  \n",
       "1  https://images.gr-assets.com/books/1474154022s...  \n",
       "2  https://images.gr-assets.com/books/1361039443s...  \n",
       "3  https://images.gr-assets.com/books/1361975680s...  \n",
       "4  https://images.gr-assets.com/books/1490528560s...  \n",
       "\n",
       "[5 rows x 23 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "books_df = pd.read_csv(\"/kaggle/input/goodbooks-10k-the-latest/books.csv\")\n",
    "books_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-05T14:12:45.248976Z",
     "iopub.status.busy": "2025-07-05T14:12:45.248695Z",
     "iopub.status.idle": "2025-07-05T14:12:45.298184Z",
     "shell.execute_reply": "2025-07-05T14:12:45.297650Z",
     "shell.execute_reply.started": "2025-07-05T14:12:45.248954Z"
    },
    "trusted": true
   },
   "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>book_id</th>\n",
       "      <th>goodreads_book_id</th>\n",
       "      <th>best_book_id</th>\n",
       "      <th>work_id</th>\n",
       "      <th>books_count</th>\n",
       "      <th>isbn13</th>\n",
       "      <th>original_publication_year</th>\n",
       "      <th>average_rating</th>\n",
       "      <th>ratings_count</th>\n",
       "      <th>work_ratings_count</th>\n",
       "      <th>work_text_reviews_count</th>\n",
       "      <th>ratings_1</th>\n",
       "      <th>ratings_2</th>\n",
       "      <th>ratings_3</th>\n",
       "      <th>ratings_4</th>\n",
       "      <th>ratings_5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>10000.00000</td>\n",
       "      <td>1.000000e+04</td>\n",
       "      <td>1.000000e+04</td>\n",
       "      <td>1.000000e+04</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>9.415000e+03</td>\n",
       "      <td>9979.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>1.000000e+04</td>\n",
       "      <td>1.000000e+04</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>1.000000e+04</td>\n",
       "      <td>1.000000e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>5000.50000</td>\n",
       "      <td>5.264697e+06</td>\n",
       "      <td>5.471214e+06</td>\n",
       "      <td>8.646183e+06</td>\n",
       "      <td>75.712700</td>\n",
       "      <td>9.755044e+12</td>\n",
       "      <td>1981.987674</td>\n",
       "      <td>4.002191</td>\n",
       "      <td>5.400124e+04</td>\n",
       "      <td>5.968732e+04</td>\n",
       "      <td>2919.955300</td>\n",
       "      <td>1345.040600</td>\n",
       "      <td>3110.885000</td>\n",
       "      <td>11475.893800</td>\n",
       "      <td>1.996570e+04</td>\n",
       "      <td>2.378981e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2886.89568</td>\n",
       "      <td>7.575462e+06</td>\n",
       "      <td>7.827330e+06</td>\n",
       "      <td>1.175106e+07</td>\n",
       "      <td>170.470728</td>\n",
       "      <td>4.428619e+11</td>\n",
       "      <td>152.576665</td>\n",
       "      <td>0.254427</td>\n",
       "      <td>1.573700e+05</td>\n",
       "      <td>1.678038e+05</td>\n",
       "      <td>6124.378132</td>\n",
       "      <td>6635.626263</td>\n",
       "      <td>9717.123578</td>\n",
       "      <td>28546.449183</td>\n",
       "      <td>5.144736e+04</td>\n",
       "      <td>7.976889e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.00000</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>8.700000e+01</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.951703e+08</td>\n",
       "      <td>-1750.000000</td>\n",
       "      <td>2.470000</td>\n",
       "      <td>2.716000e+03</td>\n",
       "      <td>5.510000e+03</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>30.000000</td>\n",
       "      <td>323.000000</td>\n",
       "      <td>7.500000e+02</td>\n",
       "      <td>7.540000e+02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2500.75000</td>\n",
       "      <td>4.627575e+04</td>\n",
       "      <td>4.791175e+04</td>\n",
       "      <td>1.008841e+06</td>\n",
       "      <td>23.000000</td>\n",
       "      <td>9.780316e+12</td>\n",
       "      <td>1990.000000</td>\n",
       "      <td>3.850000</td>\n",
       "      <td>1.356875e+04</td>\n",
       "      <td>1.543875e+04</td>\n",
       "      <td>694.000000</td>\n",
       "      <td>196.000000</td>\n",
       "      <td>656.000000</td>\n",
       "      <td>3112.000000</td>\n",
       "      <td>5.405750e+03</td>\n",
       "      <td>5.334000e+03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>5000.50000</td>\n",
       "      <td>3.949655e+05</td>\n",
       "      <td>4.251235e+05</td>\n",
       "      <td>2.719524e+06</td>\n",
       "      <td>40.000000</td>\n",
       "      <td>9.780452e+12</td>\n",
       "      <td>2004.000000</td>\n",
       "      <td>4.020000</td>\n",
       "      <td>2.115550e+04</td>\n",
       "      <td>2.383250e+04</td>\n",
       "      <td>1402.000000</td>\n",
       "      <td>391.000000</td>\n",
       "      <td>1163.000000</td>\n",
       "      <td>4894.000000</td>\n",
       "      <td>8.269500e+03</td>\n",
       "      <td>8.836000e+03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>7500.25000</td>\n",
       "      <td>9.382225e+06</td>\n",
       "      <td>9.636112e+06</td>\n",
       "      <td>1.451775e+07</td>\n",
       "      <td>67.000000</td>\n",
       "      <td>9.780831e+12</td>\n",
       "      <td>2011.000000</td>\n",
       "      <td>4.180000</td>\n",
       "      <td>4.105350e+04</td>\n",
       "      <td>4.591500e+04</td>\n",
       "      <td>2744.250000</td>\n",
       "      <td>885.000000</td>\n",
       "      <td>2353.250000</td>\n",
       "      <td>9287.000000</td>\n",
       "      <td>1.602350e+04</td>\n",
       "      <td>1.730450e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>10000.00000</td>\n",
       "      <td>3.328864e+07</td>\n",
       "      <td>3.553423e+07</td>\n",
       "      <td>5.639960e+07</td>\n",
       "      <td>3455.000000</td>\n",
       "      <td>9.790008e+12</td>\n",
       "      <td>2017.000000</td>\n",
       "      <td>4.820000</td>\n",
       "      <td>4.780653e+06</td>\n",
       "      <td>4.942365e+06</td>\n",
       "      <td>155254.000000</td>\n",
       "      <td>456191.000000</td>\n",
       "      <td>436802.000000</td>\n",
       "      <td>793319.000000</td>\n",
       "      <td>1.481305e+06</td>\n",
       "      <td>3.011543e+06</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           book_id  goodreads_book_id  best_book_id       work_id  \\\n",
       "count  10000.00000       1.000000e+04  1.000000e+04  1.000000e+04   \n",
       "mean    5000.50000       5.264697e+06  5.471214e+06  8.646183e+06   \n",
       "std     2886.89568       7.575462e+06  7.827330e+06  1.175106e+07   \n",
       "min        1.00000       1.000000e+00  1.000000e+00  8.700000e+01   \n",
       "25%     2500.75000       4.627575e+04  4.791175e+04  1.008841e+06   \n",
       "50%     5000.50000       3.949655e+05  4.251235e+05  2.719524e+06   \n",
       "75%     7500.25000       9.382225e+06  9.636112e+06  1.451775e+07   \n",
       "max    10000.00000       3.328864e+07  3.553423e+07  5.639960e+07   \n",
       "\n",
       "        books_count        isbn13  original_publication_year  average_rating  \\\n",
       "count  10000.000000  9.415000e+03                9979.000000    10000.000000   \n",
       "mean      75.712700  9.755044e+12                1981.987674        4.002191   \n",
       "std      170.470728  4.428619e+11                 152.576665        0.254427   \n",
       "min        1.000000  1.951703e+08               -1750.000000        2.470000   \n",
       "25%       23.000000  9.780316e+12                1990.000000        3.850000   \n",
       "50%       40.000000  9.780452e+12                2004.000000        4.020000   \n",
       "75%       67.000000  9.780831e+12                2011.000000        4.180000   \n",
       "max     3455.000000  9.790008e+12                2017.000000        4.820000   \n",
       "\n",
       "       ratings_count  work_ratings_count  work_text_reviews_count  \\\n",
       "count   1.000000e+04        1.000000e+04             10000.000000   \n",
       "mean    5.400124e+04        5.968732e+04              2919.955300   \n",
       "std     1.573700e+05        1.678038e+05              6124.378132   \n",
       "min     2.716000e+03        5.510000e+03                 3.000000   \n",
       "25%     1.356875e+04        1.543875e+04               694.000000   \n",
       "50%     2.115550e+04        2.383250e+04              1402.000000   \n",
       "75%     4.105350e+04        4.591500e+04              2744.250000   \n",
       "max     4.780653e+06        4.942365e+06            155254.000000   \n",
       "\n",
       "           ratings_1      ratings_2      ratings_3     ratings_4     ratings_5  \n",
       "count   10000.000000   10000.000000   10000.000000  1.000000e+04  1.000000e+04  \n",
       "mean     1345.040600    3110.885000   11475.893800  1.996570e+04  2.378981e+04  \n",
       "std      6635.626263    9717.123578   28546.449183  5.144736e+04  7.976889e+04  \n",
       "min        11.000000      30.000000     323.000000  7.500000e+02  7.540000e+02  \n",
       "25%       196.000000     656.000000    3112.000000  5.405750e+03  5.334000e+03  \n",
       "50%       391.000000    1163.000000    4894.000000  8.269500e+03  8.836000e+03  \n",
       "75%       885.000000    2353.250000    9287.000000  1.602350e+04  1.730450e+04  \n",
       "max    456191.000000  436802.000000  793319.000000  1.481305e+06  3.011543e+06  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "books_df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-05T14:12:46.982964Z",
     "iopub.status.busy": "2025-07-05T14:12:46.982180Z",
     "iopub.status.idle": "2025-07-05T14:12:46.991181Z",
     "shell.execute_reply": "2025-07-05T14:12:46.990265Z",
     "shell.execute_reply.started": "2025-07-05T14:12:46.982930Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.11/dist-packages/pandas/core/computation/expressions.py:73: RuntimeWarning: invalid value encountered in greater\n",
      "  return op(a, b)\n"
     ]
    }
   ],
   "source": [
    "books_df['original_publication_year'] = books_df[(books_df['original_publication_year'] > 0) & (books_df['original_publication_year'] > 1900)]['original_publication_year']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-04T14:25:06.895437Z",
     "iopub.status.busy": "2025-07-04T14:25:06.894719Z",
     "iopub.status.idle": "2025-07-04T14:25:06.913897Z",
     "shell.execute_reply": "2025-07-04T14:25:06.913197Z",
     "shell.execute_reply.started": "2025-07-04T14:25:06.895413Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 10000 entries, 0 to 9999\n",
      "Data columns (total 23 columns):\n",
      " #   Column                     Non-Null Count  Dtype  \n",
      "---  ------                     --------------  -----  \n",
      " 0   book_id                    10000 non-null  int64  \n",
      " 1   goodreads_book_id          10000 non-null  int64  \n",
      " 2   best_book_id               10000 non-null  int64  \n",
      " 3   work_id                    10000 non-null  int64  \n",
      " 4   books_count                10000 non-null  int64  \n",
      " 5   isbn                       9300 non-null   object \n",
      " 6   isbn13                     9415 non-null   float64\n",
      " 7   authors                    10000 non-null  object \n",
      " 8   original_publication_year  9594 non-null   float64\n",
      " 9   original_title             9415 non-null   object \n",
      " 10  title                      10000 non-null  object \n",
      " 11  language_code              8916 non-null   object \n",
      " 12  average_rating             10000 non-null  float64\n",
      " 13  ratings_count              10000 non-null  int64  \n",
      " 14  work_ratings_count         10000 non-null  int64  \n",
      " 15  work_text_reviews_count    10000 non-null  int64  \n",
      " 16  ratings_1                  10000 non-null  int64  \n",
      " 17  ratings_2                  10000 non-null  int64  \n",
      " 18  ratings_3                  10000 non-null  int64  \n",
      " 19  ratings_4                  10000 non-null  int64  \n",
      " 20  ratings_5                  10000 non-null  int64  \n",
      " 21  image_url                  10000 non-null  object \n",
      " 22  small_image_url            10000 non-null  object \n",
      "dtypes: float64(3), int64(13), object(7)\n",
      "memory usage: 1.8+ MB\n"
     ]
    }
   ],
   "source": [
    "books_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T09:56:09.306945Z",
     "iopub.status.busy": "2025-07-06T09:56:09.306213Z",
     "iopub.status.idle": "2025-07-06T09:56:09.348119Z",
     "shell.execute_reply": "2025-07-06T09:56:09.347469Z",
     "shell.execute_reply.started": "2025-07-06T09:56:09.306922Z"
    },
    "trusted": true
   },
   "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>ratings_1</th>\n",
       "      <th>ratings_2</th>\n",
       "      <th>ratings_3</th>\n",
       "      <th>ratings_4</th>\n",
       "      <th>ratings_5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>1.000000e+04</td>\n",
       "      <td>1.000000e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1345.040600</td>\n",
       "      <td>3110.885000</td>\n",
       "      <td>11475.893800</td>\n",
       "      <td>1.996570e+04</td>\n",
       "      <td>2.378981e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>6635.626263</td>\n",
       "      <td>9717.123578</td>\n",
       "      <td>28546.449183</td>\n",
       "      <td>5.144736e+04</td>\n",
       "      <td>7.976889e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>11.000000</td>\n",
       "      <td>30.000000</td>\n",
       "      <td>323.000000</td>\n",
       "      <td>7.500000e+02</td>\n",
       "      <td>7.540000e+02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>196.000000</td>\n",
       "      <td>656.000000</td>\n",
       "      <td>3112.000000</td>\n",
       "      <td>5.405750e+03</td>\n",
       "      <td>5.334000e+03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>391.000000</td>\n",
       "      <td>1163.000000</td>\n",
       "      <td>4894.000000</td>\n",
       "      <td>8.269500e+03</td>\n",
       "      <td>8.836000e+03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>885.000000</td>\n",
       "      <td>2353.250000</td>\n",
       "      <td>9287.000000</td>\n",
       "      <td>1.602350e+04</td>\n",
       "      <td>1.730450e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>456191.000000</td>\n",
       "      <td>436802.000000</td>\n",
       "      <td>793319.000000</td>\n",
       "      <td>1.481305e+06</td>\n",
       "      <td>3.011543e+06</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           ratings_1      ratings_2      ratings_3     ratings_4     ratings_5\n",
       "count   10000.000000   10000.000000   10000.000000  1.000000e+04  1.000000e+04\n",
       "mean     1345.040600    3110.885000   11475.893800  1.996570e+04  2.378981e+04\n",
       "std      6635.626263    9717.123578   28546.449183  5.144736e+04  7.976889e+04\n",
       "min        11.000000      30.000000     323.000000  7.500000e+02  7.540000e+02\n",
       "25%       196.000000     656.000000    3112.000000  5.405750e+03  5.334000e+03\n",
       "50%       391.000000    1163.000000    4894.000000  8.269500e+03  8.836000e+03\n",
       "75%       885.000000    2353.250000    9287.000000  1.602350e+04  1.730450e+04\n",
       "max    456191.000000  436802.000000  793319.000000  1.481305e+06  3.011543e+06"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "books_df[['ratings_1', 'ratings_2', 'ratings_3', 'ratings_4', 'ratings_5']].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-04T16:59:31.396853Z",
     "iopub.status.busy": "2025-07-04T16:59:31.396119Z",
     "iopub.status.idle": "2025-07-04T16:59:33.034848Z",
     "shell.execute_reply": "2025-07-04T16:59:33.034146Z",
     "shell.execute_reply.started": "2025-07-04T16:59:31.396819Z"
    },
    "trusted": true
   },
   "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>user_id</th>\n",
       "      <th>book_id</th>\n",
       "      <th>rating</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>258</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>4081</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>260</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>9296</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>2318</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id  book_id  rating\n",
       "0        1      258       5\n",
       "1        2     4081       4\n",
       "2        2      260       5\n",
       "3        2     9296       5\n",
       "4        2     2318       3"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings_df = pd.read_csv(\"/kaggle/input/goodbooks-10k-the-latest/ratings.csv\")\n",
    "ratings_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-04T14:25:15.301368Z",
     "iopub.status.busy": "2025-07-04T14:25:15.301072Z",
     "iopub.status.idle": "2025-07-04T14:25:15.308909Z",
     "shell.execute_reply": "2025-07-04T14:25:15.308252Z",
     "shell.execute_reply.started": "2025-07-04T14:25:15.301346Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5976479 entries, 0 to 5976478\n",
      "Data columns (total 3 columns):\n",
      " #   Column   Dtype\n",
      "---  ------   -----\n",
      " 0   user_id  int64\n",
      " 1   book_id  int64\n",
      " 2   rating   int64\n",
      "dtypes: int64(3)\n",
      "memory usage: 136.8 MB\n"
     ]
    }
   ],
   "source": [
    "ratings_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-04T14:25:17.566224Z",
     "iopub.status.busy": "2025-07-04T14:25:17.565964Z",
     "iopub.status.idle": "2025-07-04T14:25:17.977667Z",
     "shell.execute_reply": "2025-07-04T14:25:17.977046Z",
     "shell.execute_reply.started": "2025-07-04T14:25:17.566206Z"
    },
    "trusted": true
   },
   "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>tag_id</th>\n",
       "      <th>tag_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>--1-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>--10-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>--12-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>--122-</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   tag_id tag_name\n",
       "0       0        -\n",
       "1       1     --1-\n",
       "2       2    --10-\n",
       "3       3    --12-\n",
       "4       4   --122-"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tags_df = pd.read_csv(\"/kaggle/input/goodbooks-10k-the-latest/tags.csv\")\n",
    "book_tags_df = pd.read_csv(\"/kaggle/input/goodbooks-10k-the-latest/book_tags.csv\")\n",
    "\n",
    "tags_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-04T14:25:20.177478Z",
     "iopub.status.busy": "2025-07-04T14:25:20.176912Z",
     "iopub.status.idle": "2025-07-04T14:25:20.184824Z",
     "shell.execute_reply": "2025-07-04T14:25:20.184151Z",
     "shell.execute_reply.started": "2025-07-04T14:25:20.177458Z"
    },
    "trusted": true
   },
   "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>goodreads_book_id</th>\n",
       "      <th>tag_id</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>30574</td>\n",
       "      <td>167697</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>11305</td>\n",
       "      <td>37174</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>11557</td>\n",
       "      <td>34173</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>8717</td>\n",
       "      <td>12986</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>33114</td>\n",
       "      <td>12716</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   goodreads_book_id  tag_id   count\n",
       "0                  1   30574  167697\n",
       "1                  1   11305   37174\n",
       "2                  1   11557   34173\n",
       "3                  1    8717   12986\n",
       "4                  1   33114   12716"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "book_tags_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:03:20.872786Z",
     "iopub.status.busy": "2025-07-06T13:03:20.872009Z",
     "iopub.status.idle": "2025-07-06T13:03:21.007798Z",
     "shell.execute_reply": "2025-07-06T13:03:21.007232Z",
     "shell.execute_reply.started": "2025-07-06T13:03:20.872760Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(999912, 4)\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>goodreads_book_id</th>\n",
       "      <th>tag_id</th>\n",
       "      <th>count</th>\n",
       "      <th>tag_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>30574</td>\n",
       "      <td>167697</td>\n",
       "      <td>to-read</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>11305</td>\n",
       "      <td>37174</td>\n",
       "      <td>fantasy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>11557</td>\n",
       "      <td>34173</td>\n",
       "      <td>favorites</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>8717</td>\n",
       "      <td>12986</td>\n",
       "      <td>currently-reading</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>33114</td>\n",
       "      <td>12716</td>\n",
       "      <td>young-adult</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   goodreads_book_id  tag_id   count           tag_name\n",
       "0                  1   30574  167697            to-read\n",
       "1                  1   11305   37174            fantasy\n",
       "2                  1   11557   34173          favorites\n",
       "3                  1    8717   12986  currently-reading\n",
       "4                  1   33114   12716        young-adult"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "full_tags_df = pd.merge(book_tags_df, tags_df, how = \"left\", on=\"tag_id\")\n",
    "print(full_tags_df.shape)\n",
    "full_tags_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:04:47.656148Z",
     "iopub.status.busy": "2025-07-06T13:04:47.655886Z",
     "iopub.status.idle": "2025-07-06T13:04:48.053850Z",
     "shell.execute_reply": "2025-07-06T13:04:48.053070Z",
     "shell.execute_reply.started": "2025-07-06T13:04:47.656128Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Length: 999912\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>book_id</th>\n",
       "      <th>goodreads_book_id</th>\n",
       "      <th>best_book_id</th>\n",
       "      <th>work_id</th>\n",
       "      <th>books_count</th>\n",
       "      <th>isbn</th>\n",
       "      <th>isbn13</th>\n",
       "      <th>authors</th>\n",
       "      <th>original_publication_year</th>\n",
       "      <th>original_title</th>\n",
       "      <th>...</th>\n",
       "      <th>ratings_1</th>\n",
       "      <th>ratings_2</th>\n",
       "      <th>ratings_3</th>\n",
       "      <th>ratings_4</th>\n",
       "      <th>ratings_5</th>\n",
       "      <th>image_url</th>\n",
       "      <th>small_image_url</th>\n",
       "      <th>tag_id</th>\n",
       "      <th>count</th>\n",
       "      <th>tag_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2792775</td>\n",
       "      <td>272</td>\n",
       "      <td>439023483</td>\n",
       "      <td>9.780439e+12</td>\n",
       "      <td>Suzanne Collins</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>The Hunger Games</td>\n",
       "      <td>...</td>\n",
       "      <td>66715</td>\n",
       "      <td>127936</td>\n",
       "      <td>560092</td>\n",
       "      <td>1481305</td>\n",
       "      <td>2706317</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603m...</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603s...</td>\n",
       "      <td>11557</td>\n",
       "      <td>50755</td>\n",
       "      <td>favorites</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2792775</td>\n",
       "      <td>272</td>\n",
       "      <td>439023483</td>\n",
       "      <td>9.780439e+12</td>\n",
       "      <td>Suzanne Collins</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>The Hunger Games</td>\n",
       "      <td>...</td>\n",
       "      <td>66715</td>\n",
       "      <td>127936</td>\n",
       "      <td>560092</td>\n",
       "      <td>1481305</td>\n",
       "      <td>2706317</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603m...</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603s...</td>\n",
       "      <td>8717</td>\n",
       "      <td>35418</td>\n",
       "      <td>currently-reading</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2792775</td>\n",
       "      <td>272</td>\n",
       "      <td>439023483</td>\n",
       "      <td>9.780439e+12</td>\n",
       "      <td>Suzanne Collins</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>The Hunger Games</td>\n",
       "      <td>...</td>\n",
       "      <td>66715</td>\n",
       "      <td>127936</td>\n",
       "      <td>560092</td>\n",
       "      <td>1481305</td>\n",
       "      <td>2706317</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603m...</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603s...</td>\n",
       "      <td>33114</td>\n",
       "      <td>25968</td>\n",
       "      <td>young-adult</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2792775</td>\n",
       "      <td>272</td>\n",
       "      <td>439023483</td>\n",
       "      <td>9.780439e+12</td>\n",
       "      <td>Suzanne Collins</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>The Hunger Games</td>\n",
       "      <td>...</td>\n",
       "      <td>66715</td>\n",
       "      <td>127936</td>\n",
       "      <td>560092</td>\n",
       "      <td>1481305</td>\n",
       "      <td>2706317</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603m...</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603s...</td>\n",
       "      <td>11743</td>\n",
       "      <td>13819</td>\n",
       "      <td>fiction</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2767052</td>\n",
       "      <td>2792775</td>\n",
       "      <td>272</td>\n",
       "      <td>439023483</td>\n",
       "      <td>9.780439e+12</td>\n",
       "      <td>Suzanne Collins</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>The Hunger Games</td>\n",
       "      <td>...</td>\n",
       "      <td>66715</td>\n",
       "      <td>127936</td>\n",
       "      <td>560092</td>\n",
       "      <td>1481305</td>\n",
       "      <td>2706317</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603m...</td>\n",
       "      <td>https://images.gr-assets.com/books/1447303603s...</td>\n",
       "      <td>10064</td>\n",
       "      <td>12985</td>\n",
       "      <td>dystopian</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   book_id  goodreads_book_id  best_book_id  work_id  books_count       isbn  \\\n",
       "0        1            2767052       2767052  2792775          272  439023483   \n",
       "1        1            2767052       2767052  2792775          272  439023483   \n",
       "2        1            2767052       2767052  2792775          272  439023483   \n",
       "3        1            2767052       2767052  2792775          272  439023483   \n",
       "4        1            2767052       2767052  2792775          272  439023483   \n",
       "\n",
       "         isbn13          authors  original_publication_year    original_title  \\\n",
       "0  9.780439e+12  Suzanne Collins                     2008.0  The Hunger Games   \n",
       "1  9.780439e+12  Suzanne Collins                     2008.0  The Hunger Games   \n",
       "2  9.780439e+12  Suzanne Collins                     2008.0  The Hunger Games   \n",
       "3  9.780439e+12  Suzanne Collins                     2008.0  The Hunger Games   \n",
       "4  9.780439e+12  Suzanne Collins                     2008.0  The Hunger Games   \n",
       "\n",
       "   ... ratings_1 ratings_2  ratings_3  ratings_4  ratings_5  \\\n",
       "0  ...     66715    127936     560092    1481305    2706317   \n",
       "1  ...     66715    127936     560092    1481305    2706317   \n",
       "2  ...     66715    127936     560092    1481305    2706317   \n",
       "3  ...     66715    127936     560092    1481305    2706317   \n",
       "4  ...     66715    127936     560092    1481305    2706317   \n",
       "\n",
       "                                           image_url  \\\n",
       "0  https://images.gr-assets.com/books/1447303603m...   \n",
       "1  https://images.gr-assets.com/books/1447303603m...   \n",
       "2  https://images.gr-assets.com/books/1447303603m...   \n",
       "3  https://images.gr-assets.com/books/1447303603m...   \n",
       "4  https://images.gr-assets.com/books/1447303603m...   \n",
       "\n",
       "                                     small_image_url  tag_id  count  \\\n",
       "0  https://images.gr-assets.com/books/1447303603s...   11557  50755   \n",
       "1  https://images.gr-assets.com/books/1447303603s...    8717  35418   \n",
       "2  https://images.gr-assets.com/books/1447303603s...   33114  25968   \n",
       "3  https://images.gr-assets.com/books/1447303603s...   11743  13819   \n",
       "4  https://images.gr-assets.com/books/1447303603s...   10064  12985   \n",
       "\n",
       "            tag_name  \n",
       "0          favorites  \n",
       "1  currently-reading  \n",
       "2        young-adult  \n",
       "3            fiction  \n",
       "4          dystopian  \n",
       "\n",
       "[5 rows x 26 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Merge on book_id\n",
    "merged_df = pd.merge(books_df, full_tags_df, how = \"left\", on=\"goodreads_book_id\")\n",
    "\n",
    "# Show result\n",
    "print(f\"Length: {len(merged_df)}\")\n",
    "merged_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:04:52.553677Z",
     "iopub.status.busy": "2025-07-06T13:04:52.553010Z",
     "iopub.status.idle": "2025-07-06T13:04:54.677884Z",
     "shell.execute_reply": "2025-07-06T13:04:54.677226Z",
     "shell.execute_reply.started": "2025-07-06T13:04:52.553652Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "book_id                      0\n",
       "goodreads_book_id            0\n",
       "best_book_id                 0\n",
       "work_id                      0\n",
       "books_count                  0\n",
       "isbn                         0\n",
       "isbn13                       0\n",
       "authors                      0\n",
       "original_publication_year    0\n",
       "original_title               0\n",
       "title                        0\n",
       "language_code                0\n",
       "average_rating               0\n",
       "ratings_count                0\n",
       "work_ratings_count           0\n",
       "work_text_reviews_count      0\n",
       "ratings_1                    0\n",
       "ratings_2                    0\n",
       "ratings_3                    0\n",
       "ratings_4                    0\n",
       "ratings_5                    0\n",
       "image_url                    0\n",
       "small_image_url              0\n",
       "tag_id                       0\n",
       "count                        0\n",
       "tag_name                     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merged_df.loc[:, merged_df.select_dtypes(\"O\").columns] = (\n",
    "    merged_df.select_dtypes(\"O\").fillna(\"\")\n",
    ")\n",
    "\n",
    "merged_df.loc[:, merged_df.select_dtypes([\"int64\", \"float64\"]).columns] = (\n",
    "    merged_df.select_dtypes([\"int64\", \"float64\"]).fillna(0)\n",
    ")\n",
    "\n",
    "merged_df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:04:56.877226Z",
     "iopub.status.busy": "2025-07-06T13:04:56.876612Z",
     "iopub.status.idle": "2025-07-06T13:04:56.881105Z",
     "shell.execute_reply": "2025-07-06T13:04:56.880425Z",
     "shell.execute_reply.started": "2025-07-06T13:04:56.877204Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Data Features:\n",
      " Index(['book_id', 'goodreads_book_id', 'best_book_id', 'work_id',\n",
      "       'books_count', 'isbn', 'isbn13', 'authors', 'original_publication_year',\n",
      "       'original_title', 'title', 'language_code', 'average_rating',\n",
      "       'ratings_count', 'work_ratings_count', 'work_text_reviews_count',\n",
      "       'ratings_1', 'ratings_2', 'ratings_3', 'ratings_4', 'ratings_5',\n",
      "       'image_url', 'small_image_url', 'tag_id', 'count', 'tag_name'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(f\"Data Features:\\n {merged_df.columns}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:04:59.979980Z",
     "iopub.status.busy": "2025-07-06T13:04:59.979445Z",
     "iopub.status.idle": "2025-07-06T13:05:00.026275Z",
     "shell.execute_reply": "2025-07-06T13:05:00.025659Z",
     "shell.execute_reply.started": "2025-07-06T13:04:59.979957Z"
    },
    "trusted": true
   },
   "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>book_id</th>\n",
       "      <th>goodreads_book_id</th>\n",
       "      <th>title</th>\n",
       "      <th>authors</th>\n",
       "      <th>language_code</th>\n",
       "      <th>original_publication_year</th>\n",
       "      <th>average_rating</th>\n",
       "      <th>tag_name</th>\n",
       "      <th>ratings_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2767052</td>\n",
       "      <td>The Hunger Games (The Hunger Games, #1)</td>\n",
       "      <td>Suzanne Collins</td>\n",
       "      <td>eng</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>4.34</td>\n",
       "      <td>favorites</td>\n",
       "      <td>4780653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2767052</td>\n",
       "      <td>The Hunger Games (The Hunger Games, #1)</td>\n",
       "      <td>Suzanne Collins</td>\n",
       "      <td>eng</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>4.34</td>\n",
       "      <td>currently-reading</td>\n",
       "      <td>4780653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2767052</td>\n",
       "      <td>The Hunger Games (The Hunger Games, #1)</td>\n",
       "      <td>Suzanne Collins</td>\n",
       "      <td>eng</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>4.34</td>\n",
       "      <td>young-adult</td>\n",
       "      <td>4780653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2767052</td>\n",
       "      <td>The Hunger Games (The Hunger Games, #1)</td>\n",
       "      <td>Suzanne Collins</td>\n",
       "      <td>eng</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>4.34</td>\n",
       "      <td>fiction</td>\n",
       "      <td>4780653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2767052</td>\n",
       "      <td>The Hunger Games (The Hunger Games, #1)</td>\n",
       "      <td>Suzanne Collins</td>\n",
       "      <td>eng</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>4.34</td>\n",
       "      <td>dystopian</td>\n",
       "      <td>4780653</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   book_id  goodreads_book_id                                    title  \\\n",
       "0        1            2767052  The Hunger Games (The Hunger Games, #1)   \n",
       "1        1            2767052  The Hunger Games (The Hunger Games, #1)   \n",
       "2        1            2767052  The Hunger Games (The Hunger Games, #1)   \n",
       "3        1            2767052  The Hunger Games (The Hunger Games, #1)   \n",
       "4        1            2767052  The Hunger Games (The Hunger Games, #1)   \n",
       "\n",
       "           authors language_code  original_publication_year  average_rating  \\\n",
       "0  Suzanne Collins           eng                     2008.0            4.34   \n",
       "1  Suzanne Collins           eng                     2008.0            4.34   \n",
       "2  Suzanne Collins           eng                     2008.0            4.34   \n",
       "3  Suzanne Collins           eng                     2008.0            4.34   \n",
       "4  Suzanne Collins           eng                     2008.0            4.34   \n",
       "\n",
       "            tag_name  ratings_count  \n",
       "0          favorites        4780653  \n",
       "1  currently-reading        4780653  \n",
       "2        young-adult        4780653  \n",
       "3            fiction        4780653  \n",
       "4          dystopian        4780653  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Keep needed columns\n",
    "feature_df = merged_df[['book_id', 'goodreads_book_id', 'title', 'authors', 'language_code', 'original_publication_year', 'average_rating', 'tag_name', 'ratings_count', 'image_url']]\n",
    "feature_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:05:02.575821Z",
     "iopub.status.busy": "2025-07-06T13:05:02.575143Z",
     "iopub.status.idle": "2025-07-06T13:05:02.707131Z",
     "shell.execute_reply": "2025-07-06T13:05:02.706515Z",
     "shell.execute_reply.started": "2025-07-06T13:05:02.575796Z"
    },
    "trusted": true
   },
   "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>book_id</th>\n",
       "      <th>goodreads_book_id</th>\n",
       "      <th>original_publication_year</th>\n",
       "      <th>average_rating</th>\n",
       "      <th>ratings_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>999912.000000</td>\n",
       "      <td>9.999120e+05</td>\n",
       "      <td>999912.000000</td>\n",
       "      <td>999912.000000</td>\n",
       "      <td>9.999120e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>5000.470973</td>\n",
       "      <td>5.263442e+06</td>\n",
       "      <td>1916.446687</td>\n",
       "      <td>4.002216</td>\n",
       "      <td>5.400521e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2886.743854</td>\n",
       "      <td>7.574057e+06</td>\n",
       "      <td>394.769683</td>\n",
       "      <td>0.254408</td>\n",
       "      <td>1.573685e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.470000</td>\n",
       "      <td>2.716000e+03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2501.000000</td>\n",
       "      <td>4.622700e+04</td>\n",
       "      <td>1990.000000</td>\n",
       "      <td>3.850000</td>\n",
       "      <td>1.356900e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>5000.000000</td>\n",
       "      <td>3.948410e+05</td>\n",
       "      <td>2004.000000</td>\n",
       "      <td>4.020000</td>\n",
       "      <td>2.115700e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>7500.000000</td>\n",
       "      <td>9.378297e+06</td>\n",
       "      <td>2011.000000</td>\n",
       "      <td>4.180000</td>\n",
       "      <td>4.105800e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>10000.000000</td>\n",
       "      <td>3.328864e+07</td>\n",
       "      <td>2017.000000</td>\n",
       "      <td>4.820000</td>\n",
       "      <td>4.780653e+06</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             book_id  goodreads_book_id  original_publication_year  \\\n",
       "count  999912.000000       9.999120e+05              999912.000000   \n",
       "mean     5000.470973       5.263442e+06                1916.446687   \n",
       "std      2886.743854       7.574057e+06                 394.769683   \n",
       "min         1.000000       1.000000e+00                   0.000000   \n",
       "25%      2501.000000       4.622700e+04                1990.000000   \n",
       "50%      5000.000000       3.948410e+05                2004.000000   \n",
       "75%      7500.000000       9.378297e+06                2011.000000   \n",
       "max     10000.000000       3.328864e+07                2017.000000   \n",
       "\n",
       "       average_rating  ratings_count  \n",
       "count   999912.000000   9.999120e+05  \n",
       "mean         4.002216   5.400521e+04  \n",
       "std          0.254408   1.573685e+05  \n",
       "min          2.470000   2.716000e+03  \n",
       "25%          3.850000   1.356900e+04  \n",
       "50%          4.020000   2.115700e+04  \n",
       "75%          4.180000   4.105800e+04  \n",
       "max          4.820000   4.780653e+06  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "feature_df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:05:05.103333Z",
     "iopub.status.busy": "2025-07-06T13:05:05.103109Z",
     "iopub.status.idle": "2025-07-06T13:05:05.296121Z",
     "shell.execute_reply": "2025-07-06T13:05:05.295513Z",
     "shell.execute_reply.started": "2025-07-06T13:05:05.103318Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 999912 entries, 0 to 999911\n",
      "Data columns (total 9 columns):\n",
      " #   Column                     Non-Null Count   Dtype  \n",
      "---  ------                     --------------   -----  \n",
      " 0   book_id                    999912 non-null  int64  \n",
      " 1   goodreads_book_id          999912 non-null  int64  \n",
      " 2   title                      999912 non-null  object \n",
      " 3   authors                    999912 non-null  object \n",
      " 4   language_code              999912 non-null  object \n",
      " 5   original_publication_year  999912 non-null  float64\n",
      " 6   average_rating             999912 non-null  float64\n",
      " 7   tag_name                   999912 non-null  object \n",
      " 8   ratings_count              999912 non-null  int64  \n",
      "dtypes: float64(2), int64(3), object(4)\n",
      "memory usage: 68.7+ MB\n"
     ]
    }
   ],
   "source": [
    "feature_df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **SVD Model**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:07:23.464417Z",
     "iopub.status.busy": "2025-07-06T13:07:23.463928Z",
     "iopub.status.idle": "2025-07-06T13:20:35.689464Z",
     "shell.execute_reply": "2025-07-06T13:20:35.688711Z",
     "shell.execute_reply.started": "2025-07-06T13:07:23.464393Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<surprise.prediction_algorithms.matrix_factorization.SVDpp at 0x7c30f9a7d990>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from surprise import Dataset, Reader, SVDpp\n",
    "from surprise.model_selection import train_test_split\n",
    "from surprise import accuracy\n",
    "\n",
    "# Prepare data\n",
    "reader = Reader(rating_scale=(1, 5))\n",
    "data = Dataset.load_from_df(ratings_df[['user_id', 'book_id', 'rating']], reader)\n",
    "\n",
    "trainset, testset = train_test_split(data, test_size=0.2, random_state=42)\n",
    "\n",
    "# Train SVD++\n",
    "svdpp = SVDpp()\n",
    "svdpp.fit(trainset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:26:09.026137Z",
     "iopub.status.busy": "2025-07-06T13:26:09.025198Z",
     "iopub.status.idle": "2025-07-06T13:28:27.249993Z",
     "shell.execute_reply": "2025-07-06T13:28:27.249406Z",
     "shell.execute_reply.started": "2025-07-06T13:26:09.026109Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RMSE: 0.8182\n",
      "RMSE (SVD++): 0.8181912821450508\n",
      "MAE:  0.6286\n",
      "MAE (SVD++): 0.6286450039163989\n"
     ]
    }
   ],
   "source": [
    "# Predict\n",
    "predictions = svdpp.test(testset)\n",
    "\n",
    "# Evaluate collaborative-only\n",
    "print(\"RMSE (SVD++):\", accuracy.rmse(predictions))\n",
    "print(\"MAE (SVD++):\", accuracy.mae(predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:32:00.895881Z",
     "iopub.status.busy": "2025-07-06T13:32:00.895597Z",
     "iopub.status.idle": "2025-07-06T13:32:04.625174Z",
     "shell.execute_reply": "2025-07-06T13:32:04.624591Z",
     "shell.execute_reply.started": "2025-07-06T13:32:00.895859Z"
    },
    "trusted": true
   },
   "outputs": [],
   "source": [
    "# Prepare content features for books\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.preprocessing import OneHotEncoder, StandardScaler\n",
    "from scipy.sparse import hstack\n",
    "\n",
    "# Filter feature_df to books in ratings\n",
    "rated_book_ids = feature_df[feature_df['book_id'].isin(ratings_df['book_id'].unique())]\n",
    "\n",
    "# TF-IDF for tags\n",
    "tfidf = TfidfVectorizer(max_features=500)\n",
    "tags_tfidf = tfidf.fit_transform(rated_book_ids['tag_name'])\n",
    "\n",
    "# One-hot encode language\n",
    "ohe = OneHotEncoder()\n",
    "lang_ohe = ohe.fit_transform(rated_book_ids[['language_code']])\n",
    "\n",
    "# Scale numeric features\n",
    "scaler = StandardScaler()\n",
    "num_features = scaler.fit_transform(rated_book_ids[['average_rating', 'ratings_count']])\n",
    "\n",
    "# Combine\n",
    "content_features = hstack([tags_tfidf, lang_ohe, num_features]).tocsr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:32:09.030197Z",
     "iopub.status.busy": "2025-07-06T13:32:09.029842Z",
     "iopub.status.idle": "2025-07-06T13:32:09.134783Z",
     "shell.execute_reply": "2025-07-06T13:32:09.134079Z",
     "shell.execute_reply.started": "2025-07-06T13:32:09.030176Z"
    },
    "trusted": true
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics.pairwise import cosine_similarity\n",
    "\n",
    "def hybrid_predict(user_id, book_id, alpha=0.7):\n",
    "    # Collaborative prediction\n",
    "    pred = svdpp.predict(user_id, book_id).est\n",
    "\n",
    "    # Content similarity: mean similarity to all books user rated highly\n",
    "    user_books = ratings_df[ratings_df['user_id'] == user_id]\n",
    "    high_rated_books = user_books[user_books['rating'] >= 4]['book_id'].values\n",
    "\n",
    "    if len(high_rated_books) == 0:\n",
    "        content_score = 0\n",
    "    else:\n",
    "        # Get indices\n",
    "        idx_target = rated_book_ids[rated_book_ids['book_id'] == book_id].index[0]\n",
    "        idx_high = [rated_book_ids[rated_book_ids['book_id'] == b].index[0] for b in high_rated_books if b in rated_book_ids['book_id'].values]\n",
    "\n",
    "        # Cosine similarity between target book and user's liked books\n",
    "        similarities = cosine_similarity(content_features[idx_target], content_features[idx_high])\n",
    "        content_score = np.mean(similarities)\n",
    "\n",
    "    # Combine\n",
    "    final_score = alpha * pred + (1 - alpha) * content_score\n",
    "    return final_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:32:17.607773Z",
     "iopub.status.busy": "2025-07-06T13:32:17.607096Z",
     "iopub.status.idle": "2025-07-06T13:36:09.281862Z",
     "shell.execute_reply": "2025-07-06T13:36:09.281187Z",
     "shell.execute_reply.started": "2025-07-06T13:32:17.607749Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RMSE: 1.3263\n",
      "RMSE (Hybrid): 1.3263211074229224\n",
      "MAE:  1.1605\n",
      "MAE (Hybrid): 1.1605183074935617\n"
     ]
    }
   ],
   "source": [
    "from surprise import Prediction\n",
    "\n",
    "# Evaluate RMSE for hybrid\n",
    "hybrid_preds = []\n",
    "for uid, iid, true_r in testset[:2000]:\n",
    "    est = hybrid_predict(uid, iid)\n",
    "    hybrid_preds.append((uid, iid, true_r, est, None))\n",
    "\n",
    "hybrid_preds_surprise = [Prediction(uid, iid, true_r, est, None) for uid, iid, true_r, est, _ in hybrid_preds]\n",
    "\n",
    "print(\"RMSE (Hybrid):\", accuracy.rmse(hybrid_preds_surprise))\n",
    "print(\"MAE (Hybrid):\", accuracy.mae(hybrid_preds_surprise))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "execution_failed": "2025-07-06T12:43:38.385Z",
     "iopub.execute_input": "2025-07-06T12:40:56.563459Z",
     "iopub.status.busy": "2025-07-06T12:40:56.562823Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Precomputing SVD predictions...\n",
      "Computing cosine similarity matrix for books...\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics.pairwise import cosine_similarity\n",
    "from surprise import Prediction, accuracy\n",
    "import numpy as np\n",
    "\n",
    "# --- Step 1: Precompute all SVD predictions (vectorized) ---\n",
    "print(\"Precomputing SVD predictions...\")\n",
    "svd_preds = {}\n",
    "for uid, iid, _ in testset:\n",
    "    svd_preds[(uid, iid)] = svdpp.predict(uid, iid).est\n",
    "\n",
    "# --- Step 2: Precompute cosine similarity matrix between all books ---\n",
    "print(\"Computing cosine similarity matrix for books...\")\n",
    "# Make sure content_features is dense if it's sparse\n",
    "if hasattr(content_features, \"toarray\"):\n",
    "    content_features_dense = content_features.toarray()\n",
    "else:\n",
    "    content_features_dense = content_features\n",
    "\n",
    "book_sim_matrix = cosine_similarity(content_features_dense)\n",
    "\n",
    "# --- Step 3: Precompute user liked books ---\n",
    "print(\"Building user liked books map...\")\n",
    "# Filter for books rated >= 4 as \"liked\"\n",
    "liked_books_by_user = ratings_df[ratings_df['rating'] >= 4].groupby('user_id')['book_id'].apply(list).to_dict()\n",
    "\n",
    "# --- Step 4: Hybrid prediction function ---\n",
    "def hybrid_predict_vectorized(uid, iid, alpha=0.5):\n",
    "    \"\"\"\n",
    "    Combines SVD and content-based similarity into a single prediction.\n",
    "    \"\"\"\n",
    "    # SVD prediction\n",
    "    svd_score = svd_preds.get((uid, iid), 3.0)  # Default to 3.0 if missing\n",
    "\n",
    "    # Content-based score\n",
    "    liked_books = liked_books_by_user.get(uid, [])\n",
    "    if not liked_books:\n",
    "        content_score = 3.0  # Fallback if user has no liked books\n",
    "    else:\n",
    "        # Get similarity of target book to all liked books\n",
    "        try:\n",
    "            similarities = book_sim_matrix[iid, liked_books]\n",
    "            content_score = np.mean(similarities)\n",
    "        except IndexError:\n",
    "            content_score = 3.0  # Fallback if book index out of bounds\n",
    "\n",
    "    # Combine\n",
    "    hybrid_score = alpha * svd_score + (1 - alpha) * content_score\n",
    "    return hybrid_score\n",
    "\n",
    "# --- Step 5: Make predictions for full test set ---\n",
    "print(\"Predicting for full test set...\")\n",
    "hybrid_preds = []\n",
    "for uid, iid, true_r in testset:\n",
    "    est = hybrid_predict_vectorized(uid, iid)\n",
    "    hybrid_preds.append(Prediction(uid, iid, true_r, est, None))\n",
    "\n",
    "# --- Step 6: Evaluate ---\n",
    "print(\"Evaluating hybrid model...\")\n",
    "print(\"RMSE (Hybrid):\", accuracy.rmse(hybrid_preds))\n",
    "print(\"MAE  (Hybrid):\", accuracy.mae(hybrid_preds))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:41:20.931127Z",
     "iopub.status.busy": "2025-07-06T13:41:20.930864Z",
     "iopub.status.idle": "2025-07-06T13:41:26.436330Z",
     "shell.execute_reply": "2025-07-06T13:41:26.435594Z",
     "shell.execute_reply.started": "2025-07-06T13:41:20.931107Z"
    },
    "trusted": true
   },
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "# Save SVD++ model\n",
    "with open(\"svd_model.pkl\", \"wb\") as f:\n",
    "    pickle.dump(svdpp, f)\n",
    "\n",
    "# Save content features matrix\n",
    "with open(\"content_features.pkl\", \"wb\") as f:\n",
    "    pickle.dump(content_features, f)\n",
    "\n",
    "# Save content features matrix\n",
    "with open(\"mappings.pkl\", \"wb\") as f:\n",
    "    pickle.dump(mappings, f)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## **Deployement API**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:46:33.571168Z",
     "iopub.status.busy": "2025-07-06T13:46:33.570692Z",
     "iopub.status.idle": "2025-07-06T13:46:33.576635Z",
     "shell.execute_reply": "2025-07-06T13:46:33.575946Z",
     "shell.execute_reply.started": "2025-07-06T13:46:33.571145Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing main.py\n"
     ]
    }
   ],
   "source": [
    "%%writefile main.py\n",
    "from fastapi import FastAPI, HTTPException\n",
    "from pydantic import BaseModel\n",
    "import pickle\n",
    "import numpy as np\n",
    "from surprise import dump\n",
    "\n",
    "# Load models\n",
    "svdpp_model = pickle.load(open(\"svdpp_model.pkl\", \"rb\"))\n",
    "content_features = pickle.load(open(\"content_features.pkl\", \"rb\"))\n",
    "book_metadata = pickle.load(open(\"book_metadata.pkl\", \"rb\"))\n",
    "\n",
    "# API app\n",
    "app = FastAPI(title=\"Book Recommender API\")\n",
    "\n",
    "# Input schema\n",
    "class RatingRequest(BaseModel):\n",
    "    user_id: int\n",
    "    book_id: int\n",
    "    alpha: float = 0.7  # Default weight for SVD++ in hybrid\n",
    "\n",
    "class RecommendRequest(BaseModel):\n",
    "    user_id: int\n",
    "    top_n: int = 10\n",
    "    alpha: float = 0.7\n",
    "\n",
    "# Hybrid predict function\n",
    "def hybrid_predict(user_id, book_id, alpha=0.7):\n",
    "    try:\n",
    "        # SVD++ prediction\n",
    "        svdpp_pred = svdpp_model.predict(user_id, book_id).est\n",
    "    except:\n",
    "        svdpp_pred = 3.0  # Fallback if user/book unknown\n",
    "    \n",
    "    try:\n",
    "        # Content-based prediction\n",
    "        idx_target = book_metadata.index.get_loc(book_id)\n",
    "        user_books = ratings_df[ratings_df['user_id'] == user_id]['book_id'].values\n",
    "        user_books_idx = [book_metadata.index.get_loc(bid) for bid in user_books if bid in book_metadata.index]\n",
    "        if user_books_idx:\n",
    "            from sklearn.metrics.pairwise import cosine_similarity\n",
    "            similarities = cosine_similarity(content_features[idx_target], content_features[user_books_idx])\n",
    "            content_score = np.mean(similarities)\n",
    "        else:\n",
    "            content_score = 3.0  # Fallback\n",
    "    except:\n",
    "        content_score = 3.0\n",
    "\n",
    "    # Hybrid\n",
    "    return alpha * svdpp_pred + (1 - alpha) * content_score\n",
    "\n",
    "# Predict endpoint\n",
    "@app.post(\"/predict/\")\n",
    "def predict_rating(req: RatingRequest):\n",
    "    try:\n",
    "        pred_rating = hybrid_predict(req.user_id, req.book_id, req.alpha)\n",
    "        return {\"user_id\": req.user_id, \"book_id\": req.book_id, \"predicted_rating\": round(pred_rating, 3)}\n",
    "    except Exception as e:\n",
    "        raise HTTPException(status_code=400, detail=str(e))\n",
    "\n",
    "# Top-N recommendations\n",
    "@app.post(\"/recommend/\")\n",
    "def recommend_books(req: RecommendRequest):\n",
    "    try:\n",
    "        all_book_ids = book_metadata['book_id'].tolist()\n",
    "        preds = []\n",
    "        for bid in all_book_ids:\n",
    "            score = hybrid_predict(req.user_id, bid, req.alpha)\n",
    "            preds.append((bid, score))\n",
    "        preds.sort(key=lambda x: x[1], reverse=True)\n",
    "        top_books = preds[:req.top_n]\n",
    "        return {\"user_id\": req.user_id, \"recommendations\": top_books}\n",
    "    except Exception as e:\n",
    "        raise HTTPException(status_code=400, detail=str(e))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-07-06T13:47:04.833117Z",
     "iopub.status.busy": "2025-07-06T13:47:04.832572Z"
    },
    "trusted": true
   },
   "outputs": [],
   "source": [
    "import kagglehub\n",
    "\n",
    "LOCAL_MODEL_DIR = '/kaggle/working/'  # Directory where your model files are saved\n",
    "MODEL_SLUG = 'book-recommender-svd'  # Use the model slug from your Kaggle model page\n",
    "VARIATION_SLUG = 'v1' \n",
    "\n",
    "\n",
    "kagglehub.model_upload(\n",
    "    handle=f\"khalednabawi/{MODEL_SLUG}/keras/{VARIATION_SLUG}\",\n",
    "    local_model_dir=LOCAL_MODEL_DIR,\n",
    "    version_notes=\"Upload - Book Recommender Model\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "trusted": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kaggle": {
   "accelerator": "nvidiaTeslaT4",
   "dataSources": [
    {
     "datasetId": 2505178,
     "sourceId": 4251459,
     "sourceType": "datasetVersion"
    },
    {
     "datasetId": 2505717,
     "sourceId": 4252354,
     "sourceType": "datasetVersion"
    }
   ],
   "dockerImageVersionId": 31041,
   "isGpuEnabled": true,
   "isInternetEnabled": true,
   "language": "python",
   "sourceType": "notebook"
  },
  "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": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}