diff --git a/script.ipynb b/script.ipynb
index c647a1e..0b30f73 100644
--- a/script.ipynb
+++ b/script.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "municipal-plumbing",
+   "id": "academic-calvin",
    "metadata": {},
    "source": [
     "### Skrypt do ściagnięcia zbiory danych"
@@ -11,7 +11,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "colored-lesbian",
+   "id": "compound-politics",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -24,20 +24,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "id": "previous-oracle",
+   "execution_count": null,
+   "id": "hundred-limitation",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Downloading dataset from Kaggle...\n",
-      "/bin/bash: kaggle: command not found\n",
-      "Done.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "!echo \"Downloading dataset from Kaggle...\"\n",
     "!kaggle datasets download -d harshitshankhdhar/imdb-dataset-of-top-1000-movies-and-tv-shows\n",
@@ -46,19 +36,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "desperate-amazon",
+   "execution_count": null,
+   "id": "provincial-circuit",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Unzipping archive\n",
-      "Done.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "!echo \"Unzipping archive\"\n",
     "!files=$(unzip imdb-dataset-of-top-1000-movies-and-tv-shows.zip | tail -n +2 | cut -d ' ' -f 4)\n",
@@ -67,8 +48,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
-   "id": "fixed-accessory",
+   "execution_count": 81,
+   "id": "armed-brisbane",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -80,8 +61,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
-   "id": "otherwise-atlas",
+   "execution_count": 82,
+   "id": "nominated-grenada",
    "metadata": {},
    "outputs": [
     {
@@ -99,7 +80,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "strategic-brooks",
+   "id": "generic-success",
    "metadata": {},
    "source": [
     "## Usuwanie kolumn\n",
@@ -109,8 +90,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
-   "id": "alternative-genealogy",
+   "execution_count": 83,
+   "id": "compliant-synthesis",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -122,8 +103,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
-   "id": "antique-nowhere",
+   "execution_count": 84,
+   "id": "reserved-whole",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -146,102 +127,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
-   "id": "furnished-dating",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "(831, 16)"
-      ]
-     },
-     "execution_count": 60,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "data.describe(include='all')\n",
-    "data.shape"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 61,
-   "id": "political-pension",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "IMDB_Rating           7.9\n",
-       "No_of_Votes      186734.0\n",
-       "Gross          23530892.0\n",
-       "dtype: float64"
-      ]
-     },
-     "execution_count": 61,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "data.median()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 64,
-   "id": "fitting-houston",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "(601, 16)\n",
-      "(115, 16)\n",
-      "(115, 16)\n"
-     ]
-    }
-   ],
-   "source": [
-    "from sklearn.model_selection import train_test_split\n",
-    "import sklearn\n",
-    "\n",
-    "data_train, data_test = train_test_split(data, test_size=230, random_state=1)\n",
-    "data_test, data_dev = train_test_split(data_test, test_size=115, random_state=1)\n",
-    "print(data_train.shape)\n",
-    "print(data_test.shape)\n",
-    "print(data_dev.shape)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 65,
-   "id": "white-livestock",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "0.1913477537437604"
-      ]
-     },
-     "execution_count": 65,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "data_test.size/data_train.size"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 66,
-   "id": "sharp-criterion",
+   "execution_count": 86,
+   "id": "given-sodium",
    "metadata": {},
    "outputs": [
     {
@@ -265,14 +152,12 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>Poster_Link</th>\n",
        "      <th>Series_Title</th>\n",
        "      <th>Released_Year</th>\n",
        "      <th>Certificate</th>\n",
        "      <th>Runtime</th>\n",
        "      <th>Genre</th>\n",
        "      <th>IMDB_Rating</th>\n",
-       "      <th>Overview</th>\n",
        "      <th>Meta_score</th>\n",
        "      <th>Director</th>\n",
        "      <th>Star1</th>\n",
@@ -286,57 +171,51 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>count</th>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>601.000000</td>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>6.010000e+02</td>\n",
-       "      <td>6.010000e+02</td>\n",
+       "      <td>831</td>\n",
+       "      <td>831</td>\n",
+       "      <td>831</td>\n",
+       "      <td>831</td>\n",
+       "      <td>831</td>\n",
+       "      <td>831.000000</td>\n",
+       "      <td>831</td>\n",
+       "      <td>831</td>\n",
+       "      <td>831</td>\n",
+       "      <td>831</td>\n",
+       "      <td>831</td>\n",
+       "      <td>831</td>\n",
+       "      <td>8.310000e+02</td>\n",
+       "      <td>8.310000e+02</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>unique</th>\n",
-       "      <td>601</td>\n",
-       "      <td>601</td>\n",
-       "      <td>90</td>\n",
-       "      <td>13</td>\n",
-       "      <td>121</td>\n",
-       "      <td>162</td>\n",
+       "      <td>831</td>\n",
+       "      <td>95</td>\n",
+       "      <td>14</td>\n",
+       "      <td>133</td>\n",
+       "      <td>182</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>601</td>\n",
-       "      <td>59</td>\n",
-       "      <td>378</td>\n",
-       "      <td>438</td>\n",
-       "      <td>530</td>\n",
+       "      <td>64</td>\n",
+       "      <td>472</td>\n",
        "      <td>556</td>\n",
-       "      <td>577</td>\n",
+       "      <td>704</td>\n",
+       "      <td>737</td>\n",
+       "      <td>782</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>top</th>\n",
-       "      <td>https://m.media-amazon.com/images/M/MV5BNGYyZG...</td>\n",
-       "      <td>what ever happened to baby jane?</td>\n",
+       "      <td>a streetcar named desire</td>\n",
        "      <td>2014</td>\n",
        "      <td>U</td>\n",
        "      <td>101 min</td>\n",
        "      <td>drama</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>A few friends have a weekly fools' dinner, whe...</td>\n",
        "      <td></td>\n",
-       "      <td>martin scorsese</td>\n",
-       "      <td>clint eastwood</td>\n",
+       "      <td>steven spielberg</td>\n",
+       "      <td>tom hanks</td>\n",
        "      <td>emma watson</td>\n",
-       "      <td>joe pesci</td>\n",
+       "      <td>rupert grint</td>\n",
        "      <td>michael caine</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
@@ -344,19 +223,17 @@
        "    <tr>\n",
        "      <th>freq</th>\n",
        "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>22</td>\n",
-       "      <td>143</td>\n",
-       "      <td>17</td>\n",
-       "      <td>53</td>\n",
+       "      <td>31</td>\n",
+       "      <td>200</td>\n",
+       "      <td>21</td>\n",
+       "      <td>75</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>1</td>\n",
-       "      <td>53</td>\n",
-       "      <td>10</td>\n",
-       "      <td>10</td>\n",
+       "      <td>81</td>\n",
+       "      <td>13</td>\n",
+       "      <td>12</td>\n",
+       "      <td>7</td>\n",
        "      <td>5</td>\n",
        "      <td>4</td>\n",
-       "      <td>4</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
@@ -367,17 +244,15 @@
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>7.947920</td>\n",
+       "      <td>7.946931</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>3.174649e+05</td>\n",
-       "      <td>6.775699e+07</td>\n",
+       "      <td>3.152499e+05</td>\n",
+       "      <td>6.803475e+07</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>std</th>\n",
@@ -386,17 +261,15 @@
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.280238</td>\n",
+       "      <td>0.283204</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>3.407094e+05</td>\n",
-       "      <td>1.095511e+08</td>\n",
+       "      <td>3.436443e+05</td>\n",
+       "      <td>1.097500e+08</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>min</th>\n",
@@ -405,7 +278,6 @@
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
        "      <td>7.600000</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
@@ -413,7 +285,6 @@
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
        "      <td>2.508800e+04</td>\n",
        "      <td>1.305000e+03</td>\n",
        "    </tr>\n",
@@ -424,7 +295,6 @@
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
        "      <td>7.700000</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
@@ -432,326 +302,8 @@
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>6.846300e+04</td>\n",
-       "      <td>3.151130e+06</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>50%</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>7.900000</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>1.897160e+05</td>\n",
-       "      <td>2.365000e+07</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>75%</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>8.100000</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>4.622520e+05</td>\n",
-       "      <td>7.891296e+07</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>max</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>9.200000</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.303232e+06</td>\n",
-       "      <td>8.583730e+08</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                                              Poster_Link  \\\n",
-       "count                                                 601   \n",
-       "unique                                                601   \n",
-       "top     https://m.media-amazon.com/images/M/MV5BNGYyZG...   \n",
-       "freq                                                    1   \n",
-       "mean                                                  NaN   \n",
-       "std                                                   NaN   \n",
-       "min                                                   NaN   \n",
-       "25%                                                   NaN   \n",
-       "50%                                                   NaN   \n",
-       "75%                                                   NaN   \n",
-       "max                                                   NaN   \n",
-       "\n",
-       "                            Series_Title Released_Year Certificate  Runtime  \\\n",
-       "count                                601           601         601      601   \n",
-       "unique                               601            90          13      121   \n",
-       "top     what ever happened to baby jane?          2014           U  101 min   \n",
-       "freq                                   1            22         143       17   \n",
-       "mean                                 NaN           NaN         NaN      NaN   \n",
-       "std                                  NaN           NaN         NaN      NaN   \n",
-       "min                                  NaN           NaN         NaN      NaN   \n",
-       "25%                                  NaN           NaN         NaN      NaN   \n",
-       "50%                                  NaN           NaN         NaN      NaN   \n",
-       "75%                                  NaN           NaN         NaN      NaN   \n",
-       "max                                  NaN           NaN         NaN      NaN   \n",
-       "\n",
-       "        Genre  IMDB_Rating                                           Overview  \\\n",
-       "count     601   601.000000                                                601   \n",
-       "unique    162          NaN                                                601   \n",
-       "top     drama          NaN  A few friends have a weekly fools' dinner, whe...   \n",
-       "freq       53          NaN                                                  1   \n",
-       "mean      NaN     7.947920                                                NaN   \n",
-       "std       NaN     0.280238                                                NaN   \n",
-       "min       NaN     7.600000                                                NaN   \n",
-       "25%       NaN     7.700000                                                NaN   \n",
-       "50%       NaN     7.900000                                                NaN   \n",
-       "75%       NaN     8.100000                                                NaN   \n",
-       "max       NaN     9.200000                                                NaN   \n",
-       "\n",
-       "       Meta_score         Director           Star1        Star2      Star3  \\\n",
-       "count         601              601             601          601        601   \n",
-       "unique         59              378             438          530        556   \n",
-       "top                martin scorsese  clint eastwood  emma watson  joe pesci   \n",
-       "freq           53               10              10            5          4   \n",
-       "mean          NaN              NaN             NaN          NaN        NaN   \n",
-       "std           NaN              NaN             NaN          NaN        NaN   \n",
-       "min           NaN              NaN             NaN          NaN        NaN   \n",
-       "25%           NaN              NaN             NaN          NaN        NaN   \n",
-       "50%           NaN              NaN             NaN          NaN        NaN   \n",
-       "75%           NaN              NaN             NaN          NaN        NaN   \n",
-       "max           NaN              NaN             NaN          NaN        NaN   \n",
-       "\n",
-       "                Star4   No_of_Votes         Gross  \n",
-       "count             601  6.010000e+02  6.010000e+02  \n",
-       "unique            577           NaN           NaN  \n",
-       "top     michael caine           NaN           NaN  \n",
-       "freq                4           NaN           NaN  \n",
-       "mean              NaN  3.174649e+05  6.775699e+07  \n",
-       "std               NaN  3.407094e+05  1.095511e+08  \n",
-       "min               NaN  2.508800e+04  1.305000e+03  \n",
-       "25%               NaN  6.846300e+04  3.151130e+06  \n",
-       "50%               NaN  1.897160e+05  2.365000e+07  \n",
-       "75%               NaN  4.622520e+05  7.891296e+07  \n",
-       "max               NaN  2.303232e+06  8.583730e+08  "
-      ]
-     },
-     "execution_count": 66,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "data_train.describe(include=\"all\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 102,
-   "id": "excessive-congress",
-   "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>Series_Title</th>\n",
-       "      <th>Released_Year</th>\n",
-       "      <th>Certificate</th>\n",
-       "      <th>Runtime</th>\n",
-       "      <th>Genre</th>\n",
-       "      <th>IMDB_Rating</th>\n",
-       "      <th>Meta_score</th>\n",
-       "      <th>Director</th>\n",
-       "      <th>Star1</th>\n",
-       "      <th>Star2</th>\n",
-       "      <th>Star3</th>\n",
-       "      <th>Star4</th>\n",
-       "      <th>No_of_Votes</th>\n",
-       "      <th>Gross</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>count</th>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200.000000</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>2.000000e+02</td>\n",
-       "      <td>1.600000e+02</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>unique</th>\n",
-       "      <td>200</td>\n",
-       "      <td>75</td>\n",
-       "      <td>10</td>\n",
-       "      <td>88</td>\n",
-       "      <td>98</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>49</td>\n",
-       "      <td>162</td>\n",
-       "      <td>172</td>\n",
-       "      <td>192</td>\n",
-       "      <td>197</td>\n",
-       "      <td>198</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>top</th>\n",
-       "      <td>in america</td>\n",
-       "      <td>2003</td>\n",
-       "      <td>A</td>\n",
-       "      <td>118 min</td>\n",
-       "      <td>drama</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td></td>\n",
-       "      <td>woody allen</td>\n",
-       "      <td>humphrey bogart</td>\n",
-       "      <td>robert downey jr.</td>\n",
-       "      <td>lea thompson</td>\n",
-       "      <td>mark ruffalo</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>freq</th>\n",
-       "      <td>1</td>\n",
-       "      <td>6</td>\n",
-       "      <td>48</td>\n",
-       "      <td>7</td>\n",
-       "      <td>23</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>30</td>\n",
-       "      <td>5</td>\n",
-       "      <td>4</td>\n",
-       "      <td>2</td>\n",
-       "      <td>2</td>\n",
-       "      <td>2</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>mean</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>7.949500</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.826230e+05</td>\n",
-       "      <td>7.249570e+07</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>std</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.290381</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>3.501372e+05</td>\n",
-       "      <td>1.224538e+08</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>min</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>7.600000</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.519800e+04</td>\n",
-       "      <td>6.013000e+03</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>25%</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>7.700000</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>5.038950e+04</td>\n",
-       "      <td>3.786699e+06</td>\n",
+       "      <td>7.143000e+04</td>\n",
+       "      <td>3.253559e+06</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>50%</th>\n",
@@ -767,8 +319,8 @@
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>1.354640e+05</td>\n",
-       "      <td>2.325044e+07</td>\n",
+       "      <td>1.867340e+05</td>\n",
+       "      <td>2.353089e+07</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>75%</th>\n",
@@ -784,293 +336,8 @@
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>3.851505e+05</td>\n",
-       "      <td>7.603522e+07</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>max</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>9.000000</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.303232e+06</td>\n",
-       "      <td>8.583730e+08</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "       Series_Title Released_Year Certificate  Runtime  Genre  IMDB_Rating  \\\n",
-       "count           200           200         200      200    200   200.000000   \n",
-       "unique          200            75          10       88     98          NaN   \n",
-       "top      in america          2003           A  118 min  drama          NaN   \n",
-       "freq              1             6          48        7     23          NaN   \n",
-       "mean            NaN           NaN         NaN      NaN    NaN     7.949500   \n",
-       "std             NaN           NaN         NaN      NaN    NaN     0.290381   \n",
-       "min             NaN           NaN         NaN      NaN    NaN     7.600000   \n",
-       "25%             NaN           NaN         NaN      NaN    NaN     7.700000   \n",
-       "50%             NaN           NaN         NaN      NaN    NaN     7.900000   \n",
-       "75%             NaN           NaN         NaN      NaN    NaN     8.100000   \n",
-       "max             NaN           NaN         NaN      NaN    NaN     9.000000   \n",
-       "\n",
-       "       Meta_score     Director            Star1              Star2  \\\n",
-       "count         200          200              200                200   \n",
-       "unique         49          162              172                192   \n",
-       "top                woody allen  humphrey bogart  robert downey jr.   \n",
-       "freq           30            5                4                  2   \n",
-       "mean          NaN          NaN              NaN                NaN   \n",
-       "std           NaN          NaN              NaN                NaN   \n",
-       "min           NaN          NaN              NaN                NaN   \n",
-       "25%           NaN          NaN              NaN                NaN   \n",
-       "50%           NaN          NaN              NaN                NaN   \n",
-       "75%           NaN          NaN              NaN                NaN   \n",
-       "max           NaN          NaN              NaN                NaN   \n",
-       "\n",
-       "               Star3         Star4   No_of_Votes         Gross  \n",
-       "count            200           200  2.000000e+02  1.600000e+02  \n",
-       "unique           197           198           NaN           NaN  \n",
-       "top     lea thompson  mark ruffalo           NaN           NaN  \n",
-       "freq               2             2           NaN           NaN  \n",
-       "mean             NaN           NaN  2.826230e+05  7.249570e+07  \n",
-       "std              NaN           NaN  3.501372e+05  1.224538e+08  \n",
-       "min              NaN           NaN  2.519800e+04  6.013000e+03  \n",
-       "25%              NaN           NaN  5.038950e+04  3.786699e+06  \n",
-       "50%              NaN           NaN  1.354640e+05  2.325044e+07  \n",
-       "75%              NaN           NaN  3.851505e+05  7.603522e+07  \n",
-       "max              NaN           NaN  2.303232e+06  8.583730e+08  "
-      ]
-     },
-     "execution_count": 102,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "data_test.describe(include=\"all\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 103,
-   "id": "exact-prince",
-   "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>Series_Title</th>\n",
-       "      <th>Released_Year</th>\n",
-       "      <th>Certificate</th>\n",
-       "      <th>Runtime</th>\n",
-       "      <th>Genre</th>\n",
-       "      <th>IMDB_Rating</th>\n",
-       "      <th>Meta_score</th>\n",
-       "      <th>Director</th>\n",
-       "      <th>Star1</th>\n",
-       "      <th>Star2</th>\n",
-       "      <th>Star3</th>\n",
-       "      <th>Star4</th>\n",
-       "      <th>No_of_Votes</th>\n",
-       "      <th>Gross</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>count</th>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200.000000</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>200</td>\n",
-       "      <td>2.000000e+02</td>\n",
-       "      <td>1.660000e+02</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>unique</th>\n",
-       "      <td>200</td>\n",
-       "      <td>70</td>\n",
-       "      <td>10</td>\n",
-       "      <td>89</td>\n",
-       "      <td>91</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>47</td>\n",
-       "      <td>162</td>\n",
-       "      <td>176</td>\n",
-       "      <td>191</td>\n",
-       "      <td>195</td>\n",
-       "      <td>199</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>top</th>\n",
-       "      <td>clerks</td>\n",
-       "      <td>2014</td>\n",
-       "      <td>U</td>\n",
-       "      <td>106 min</td>\n",
-       "      <td>drama</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td></td>\n",
-       "      <td>steven spielberg</td>\n",
-       "      <td>toshirô mifune</td>\n",
-       "      <td>ed harris</td>\n",
-       "      <td>frances mcdormand</td>\n",
-       "      <td>lucy liu</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>freq</th>\n",
-       "      <td>1</td>\n",
-       "      <td>11</td>\n",
-       "      <td>57</td>\n",
-       "      <td>6</td>\n",
-       "      <td>17</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>39</td>\n",
-       "      <td>6</td>\n",
-       "      <td>4</td>\n",
-       "      <td>3</td>\n",
-       "      <td>3</td>\n",
-       "      <td>2</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>mean</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>7.955500</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.563293e+05</td>\n",
-       "      <td>6.607024e+07</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>std</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.279931</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>3.208478e+05</td>\n",
-       "      <td>1.035885e+08</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>min</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>7.600000</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.593800e+04</td>\n",
-       "      <td>6.460000e+03</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>25%</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>7.700000</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>5.946375e+04</td>\n",
-       "      <td>3.392077e+06</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>50%</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>7.900000</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>1.256995e+05</td>\n",
-       "      <td>2.249226e+07</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>75%</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>8.100000</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>3.365100e+05</td>\n",
-       "      <td>7.597351e+07</td>\n",
+       "      <td>4.457210e+05</td>\n",
+       "      <td>8.075089e+07</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>max</th>\n",
@@ -1087,7 +354,670 @@
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>2.343110e+06</td>\n",
-       "      <td>6.085817e+08</td>\n",
+       "      <td>9.366622e+08</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                    Series_Title Released_Year Certificate  Runtime  Genre  \\\n",
+       "count                        831           831         831      831    831   \n",
+       "unique                       831            95          14      133    182   \n",
+       "top     a streetcar named desire          2014           U  101 min  drama   \n",
+       "freq                           1            31         200       21     75   \n",
+       "mean                         NaN           NaN         NaN      NaN    NaN   \n",
+       "std                          NaN           NaN         NaN      NaN    NaN   \n",
+       "min                          NaN           NaN         NaN      NaN    NaN   \n",
+       "25%                          NaN           NaN         NaN      NaN    NaN   \n",
+       "50%                          NaN           NaN         NaN      NaN    NaN   \n",
+       "75%                          NaN           NaN         NaN      NaN    NaN   \n",
+       "max                          NaN           NaN         NaN      NaN    NaN   \n",
+       "\n",
+       "        IMDB_Rating Meta_score          Director      Star1        Star2  \\\n",
+       "count    831.000000        831               831        831          831   \n",
+       "unique          NaN         64               472        556          704   \n",
+       "top             NaN             steven spielberg  tom hanks  emma watson   \n",
+       "freq            NaN         81                13         12            7   \n",
+       "mean       7.946931        NaN               NaN        NaN          NaN   \n",
+       "std        0.283204        NaN               NaN        NaN          NaN   \n",
+       "min        7.600000        NaN               NaN        NaN          NaN   \n",
+       "25%        7.700000        NaN               NaN        NaN          NaN   \n",
+       "50%        7.900000        NaN               NaN        NaN          NaN   \n",
+       "75%        8.100000        NaN               NaN        NaN          NaN   \n",
+       "max        9.300000        NaN               NaN        NaN          NaN   \n",
+       "\n",
+       "               Star3          Star4   No_of_Votes         Gross  \n",
+       "count            831            831  8.310000e+02  8.310000e+02  \n",
+       "unique           737            782           NaN           NaN  \n",
+       "top     rupert grint  michael caine           NaN           NaN  \n",
+       "freq               5              4           NaN           NaN  \n",
+       "mean             NaN            NaN  3.152499e+05  6.803475e+07  \n",
+       "std              NaN            NaN  3.436443e+05  1.097500e+08  \n",
+       "min              NaN            NaN  2.508800e+04  1.305000e+03  \n",
+       "25%              NaN            NaN  7.143000e+04  3.253559e+06  \n",
+       "50%              NaN            NaN  1.867340e+05  2.353089e+07  \n",
+       "75%              NaN            NaN  4.457210e+05  8.075089e+07  \n",
+       "max              NaN            NaN  2.343110e+06  9.366622e+08  "
+      ]
+     },
+     "execution_count": 86,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.describe(include='all')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "id": "effective-treasury",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "IMDB_Rating           7.9\n",
+       "No_of_Votes      186734.0\n",
+       "Gross          23530892.0\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 74,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.median()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 87,
+   "id": "egyptian-sacramento",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(831, 14)"
+      ]
+     },
+     "execution_count": 87,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 88,
+   "id": "intended-christmas",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(601, 14)\n",
+      "(115, 14)\n",
+      "(115, 14)\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "import sklearn\n",
+    "\n",
+    "data_train, data_test = train_test_split(data, test_size=230, random_state=1)\n",
+    "data_test, data_dev = train_test_split(data_test, test_size=115, random_state=1)\n",
+    "print(data_train.shape)\n",
+    "print(data_test.shape)\n",
+    "print(data_dev.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "id": "little-gravity",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.1913477537437604"
+      ]
+     },
+     "execution_count": 76,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data_test.size/data_train.size"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "id": "executive-canada",
+   "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>Series_Title</th>\n",
+       "      <th>Released_Year</th>\n",
+       "      <th>Certificate</th>\n",
+       "      <th>Runtime</th>\n",
+       "      <th>Genre</th>\n",
+       "      <th>IMDB_Rating</th>\n",
+       "      <th>Meta_score</th>\n",
+       "      <th>Director</th>\n",
+       "      <th>Star1</th>\n",
+       "      <th>Star2</th>\n",
+       "      <th>Star3</th>\n",
+       "      <th>Star4</th>\n",
+       "      <th>No_of_Votes</th>\n",
+       "      <th>Gross</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>601</td>\n",
+       "      <td>601</td>\n",
+       "      <td>601</td>\n",
+       "      <td>601</td>\n",
+       "      <td>601</td>\n",
+       "      <td>601.000000</td>\n",
+       "      <td>601</td>\n",
+       "      <td>601</td>\n",
+       "      <td>601</td>\n",
+       "      <td>601</td>\n",
+       "      <td>601</td>\n",
+       "      <td>601</td>\n",
+       "      <td>6.010000e+02</td>\n",
+       "      <td>6.010000e+02</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>unique</th>\n",
+       "      <td>601</td>\n",
+       "      <td>90</td>\n",
+       "      <td>13</td>\n",
+       "      <td>121</td>\n",
+       "      <td>162</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>59</td>\n",
+       "      <td>378</td>\n",
+       "      <td>438</td>\n",
+       "      <td>530</td>\n",
+       "      <td>556</td>\n",
+       "      <td>577</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>top</th>\n",
+       "      <td>what ever happened to baby jane?</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>U</td>\n",
+       "      <td>101 min</td>\n",
+       "      <td>drama</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td></td>\n",
+       "      <td>martin scorsese</td>\n",
+       "      <td>clint eastwood</td>\n",
+       "      <td>emma watson</td>\n",
+       "      <td>joe pesci</td>\n",
+       "      <td>michael caine</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>freq</th>\n",
+       "      <td>1</td>\n",
+       "      <td>22</td>\n",
+       "      <td>143</td>\n",
+       "      <td>17</td>\n",
+       "      <td>53</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>53</td>\n",
+       "      <td>10</td>\n",
+       "      <td>10</td>\n",
+       "      <td>5</td>\n",
+       "      <td>4</td>\n",
+       "      <td>4</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.947920</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3.174649e+05</td>\n",
+       "      <td>6.775699e+07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.280238</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3.407094e+05</td>\n",
+       "      <td>1.095511e+08</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.600000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.508800e+04</td>\n",
+       "      <td>1.305000e+03</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.700000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>6.846300e+04</td>\n",
+       "      <td>3.151130e+06</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.900000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.897160e+05</td>\n",
+       "      <td>2.365000e+07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>8.100000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.622520e+05</td>\n",
+       "      <td>7.891296e+07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>9.200000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.303232e+06</td>\n",
+       "      <td>8.583730e+08</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                            Series_Title Released_Year Certificate  Runtime  \\\n",
+       "count                                601           601         601      601   \n",
+       "unique                               601            90          13      121   \n",
+       "top     what ever happened to baby jane?          2014           U  101 min   \n",
+       "freq                                   1            22         143       17   \n",
+       "mean                                 NaN           NaN         NaN      NaN   \n",
+       "std                                  NaN           NaN         NaN      NaN   \n",
+       "min                                  NaN           NaN         NaN      NaN   \n",
+       "25%                                  NaN           NaN         NaN      NaN   \n",
+       "50%                                  NaN           NaN         NaN      NaN   \n",
+       "75%                                  NaN           NaN         NaN      NaN   \n",
+       "max                                  NaN           NaN         NaN      NaN   \n",
+       "\n",
+       "        Genre  IMDB_Rating Meta_score         Director           Star1  \\\n",
+       "count     601   601.000000        601              601             601   \n",
+       "unique    162          NaN         59              378             438   \n",
+       "top     drama          NaN             martin scorsese  clint eastwood   \n",
+       "freq       53          NaN         53               10              10   \n",
+       "mean      NaN     7.947920        NaN              NaN             NaN   \n",
+       "std       NaN     0.280238        NaN              NaN             NaN   \n",
+       "min       NaN     7.600000        NaN              NaN             NaN   \n",
+       "25%       NaN     7.700000        NaN              NaN             NaN   \n",
+       "50%       NaN     7.900000        NaN              NaN             NaN   \n",
+       "75%       NaN     8.100000        NaN              NaN             NaN   \n",
+       "max       NaN     9.200000        NaN              NaN             NaN   \n",
+       "\n",
+       "              Star2      Star3          Star4   No_of_Votes         Gross  \n",
+       "count           601        601            601  6.010000e+02  6.010000e+02  \n",
+       "unique          530        556            577           NaN           NaN  \n",
+       "top     emma watson  joe pesci  michael caine           NaN           NaN  \n",
+       "freq              5          4              4           NaN           NaN  \n",
+       "mean            NaN        NaN            NaN  3.174649e+05  6.775699e+07  \n",
+       "std             NaN        NaN            NaN  3.407094e+05  1.095511e+08  \n",
+       "min             NaN        NaN            NaN  2.508800e+04  1.305000e+03  \n",
+       "25%             NaN        NaN            NaN  6.846300e+04  3.151130e+06  \n",
+       "50%             NaN        NaN            NaN  1.897160e+05  2.365000e+07  \n",
+       "75%             NaN        NaN            NaN  4.622520e+05  7.891296e+07  \n",
+       "max             NaN        NaN            NaN  2.303232e+06  8.583730e+08  "
+      ]
+     },
+     "execution_count": 89,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data_train.describe(include=\"all\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 78,
+   "id": "alert-campus",
+   "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>Series_Title</th>\n",
+       "      <th>Released_Year</th>\n",
+       "      <th>Certificate</th>\n",
+       "      <th>Runtime</th>\n",
+       "      <th>Genre</th>\n",
+       "      <th>IMDB_Rating</th>\n",
+       "      <th>Meta_score</th>\n",
+       "      <th>Director</th>\n",
+       "      <th>Star1</th>\n",
+       "      <th>Star2</th>\n",
+       "      <th>Star3</th>\n",
+       "      <th>Star4</th>\n",
+       "      <th>No_of_Votes</th>\n",
+       "      <th>Gross</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115.000000</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>1.150000e+02</td>\n",
+       "      <td>1.150000e+02</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>unique</th>\n",
+       "      <td>115</td>\n",
+       "      <td>57</td>\n",
+       "      <td>10</td>\n",
+       "      <td>64</td>\n",
+       "      <td>59</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>44</td>\n",
+       "      <td>105</td>\n",
+       "      <td>100</td>\n",
+       "      <td>113</td>\n",
+       "      <td>109</td>\n",
+       "      <td>114</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>top</th>\n",
+       "      <td>queen</td>\n",
+       "      <td>2013</td>\n",
+       "      <td>U</td>\n",
+       "      <td>102 min</td>\n",
+       "      <td>drama</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td></td>\n",
+       "      <td>frank darabont</td>\n",
+       "      <td>al pacino</td>\n",
+       "      <td>emma watson</td>\n",
+       "      <td>carrie fisher</td>\n",
+       "      <td>lucy liu</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>freq</th>\n",
+       "      <td>1</td>\n",
+       "      <td>7</td>\n",
+       "      <td>30</td>\n",
+       "      <td>7</td>\n",
+       "      <td>14</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>16</td>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.947826</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3.140691e+05</td>\n",
+       "      <td>6.622925e+07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.313259</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3.647432e+05</td>\n",
+       "      <td>9.085320e+07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.600000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.669700e+04</td>\n",
+       "      <td>1.095000e+04</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.700000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.206000e+04</td>\n",
+       "      <td>4.232562e+06</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.900000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.654650e+05</td>\n",
+       "      <td>2.602096e+07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>8.100000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.268040e+05</td>\n",
+       "      <td>7.556908e+07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>9.300000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.343110e+06</td>\n",
+       "      <td>3.808433e+08</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -1095,46 +1025,344 @@
       ],
       "text/plain": [
        "       Series_Title Released_Year Certificate  Runtime  Genre  IMDB_Rating  \\\n",
-       "count           200           200         200      200    200   200.000000   \n",
-       "unique          200            70          10       89     91          NaN   \n",
-       "top          clerks          2014           U  106 min  drama          NaN   \n",
-       "freq              1            11          57        6     17          NaN   \n",
-       "mean            NaN           NaN         NaN      NaN    NaN     7.955500   \n",
-       "std             NaN           NaN         NaN      NaN    NaN     0.279931   \n",
+       "count           115           115         115      115    115   115.000000   \n",
+       "unique          115            57          10       64     59          NaN   \n",
+       "top           queen          2013           U  102 min  drama          NaN   \n",
+       "freq              1             7          30        7     14          NaN   \n",
+       "mean            NaN           NaN         NaN      NaN    NaN     7.947826   \n",
+       "std             NaN           NaN         NaN      NaN    NaN     0.313259   \n",
        "min             NaN           NaN         NaN      NaN    NaN     7.600000   \n",
        "25%             NaN           NaN         NaN      NaN    NaN     7.700000   \n",
        "50%             NaN           NaN         NaN      NaN    NaN     7.900000   \n",
        "75%             NaN           NaN         NaN      NaN    NaN     8.100000   \n",
        "max             NaN           NaN         NaN      NaN    NaN     9.300000   \n",
        "\n",
-       "       Meta_score          Director           Star1      Star2  \\\n",
-       "count         200               200             200        200   \n",
-       "unique         47               162             176        191   \n",
-       "top                steven spielberg  toshirô mifune  ed harris   \n",
-       "freq           39                 6               4          3   \n",
-       "mean          NaN               NaN             NaN        NaN   \n",
-       "std           NaN               NaN             NaN        NaN   \n",
-       "min           NaN               NaN             NaN        NaN   \n",
-       "25%           NaN               NaN             NaN        NaN   \n",
-       "50%           NaN               NaN             NaN        NaN   \n",
-       "75%           NaN               NaN             NaN        NaN   \n",
-       "max           NaN               NaN             NaN        NaN   \n",
+       "       Meta_score        Director      Star1        Star2          Star3  \\\n",
+       "count         115             115        115          115            115   \n",
+       "unique         44             105        100          113            109   \n",
+       "top                frank darabont  al pacino  emma watson  carrie fisher   \n",
+       "freq           16               2          4            2              2   \n",
+       "mean          NaN             NaN        NaN          NaN            NaN   \n",
+       "std           NaN             NaN        NaN          NaN            NaN   \n",
+       "min           NaN             NaN        NaN          NaN            NaN   \n",
+       "25%           NaN             NaN        NaN          NaN            NaN   \n",
+       "50%           NaN             NaN        NaN          NaN            NaN   \n",
+       "75%           NaN             NaN        NaN          NaN            NaN   \n",
+       "max           NaN             NaN        NaN          NaN            NaN   \n",
        "\n",
-       "                    Star3     Star4   No_of_Votes         Gross  \n",
-       "count                 200       200  2.000000e+02  1.660000e+02  \n",
-       "unique                195       199           NaN           NaN  \n",
-       "top     frances mcdormand  lucy liu           NaN           NaN  \n",
-       "freq                    3         2           NaN           NaN  \n",
-       "mean                  NaN       NaN  2.563293e+05  6.607024e+07  \n",
-       "std                   NaN       NaN  3.208478e+05  1.035885e+08  \n",
-       "min                   NaN       NaN  2.593800e+04  6.460000e+03  \n",
-       "25%                   NaN       NaN  5.946375e+04  3.392077e+06  \n",
-       "50%                   NaN       NaN  1.256995e+05  2.249226e+07  \n",
-       "75%                   NaN       NaN  3.365100e+05  7.597351e+07  \n",
-       "max                   NaN       NaN  2.343110e+06  6.085817e+08  "
+       "           Star4   No_of_Votes         Gross  \n",
+       "count        115  1.150000e+02  1.150000e+02  \n",
+       "unique       114           NaN           NaN  \n",
+       "top     lucy liu           NaN           NaN  \n",
+       "freq           2           NaN           NaN  \n",
+       "mean         NaN  3.140691e+05  6.622925e+07  \n",
+       "std          NaN  3.647432e+05  9.085320e+07  \n",
+       "min          NaN  2.669700e+04  1.095000e+04  \n",
+       "25%          NaN  7.206000e+04  4.232562e+06  \n",
+       "50%          NaN  1.654650e+05  2.602096e+07  \n",
+       "75%          NaN  4.268040e+05  7.556908e+07  \n",
+       "max          NaN  2.343110e+06  3.808433e+08  "
       ]
      },
-     "execution_count": 103,
+     "execution_count": 78,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data_test.describe(include=\"all\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 79,
+   "id": "little-mathematics",
+   "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>Series_Title</th>\n",
+       "      <th>Released_Year</th>\n",
+       "      <th>Certificate</th>\n",
+       "      <th>Runtime</th>\n",
+       "      <th>Genre</th>\n",
+       "      <th>IMDB_Rating</th>\n",
+       "      <th>Meta_score</th>\n",
+       "      <th>Director</th>\n",
+       "      <th>Star1</th>\n",
+       "      <th>Star2</th>\n",
+       "      <th>Star3</th>\n",
+       "      <th>Star4</th>\n",
+       "      <th>No_of_Votes</th>\n",
+       "      <th>Gross</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115.000000</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>1.150000e+02</td>\n",
+       "      <td>1.150000e+02</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>unique</th>\n",
+       "      <td>115</td>\n",
+       "      <td>56</td>\n",
+       "      <td>8</td>\n",
+       "      <td>72</td>\n",
+       "      <td>71</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>42</td>\n",
+       "      <td>101</td>\n",
+       "      <td>104</td>\n",
+       "      <td>115</td>\n",
+       "      <td>115</td>\n",
+       "      <td>112</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>top</th>\n",
+       "      <td>mr. smith goes to washington</td>\n",
+       "      <td>2004</td>\n",
+       "      <td>UA</td>\n",
+       "      <td>120 min</td>\n",
+       "      <td>drama</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td></td>\n",
+       "      <td>billy wilder</td>\n",
+       "      <td>johnny depp</td>\n",
+       "      <td>charlize theron</td>\n",
+       "      <td>joel edgerton</td>\n",
+       "      <td>kevin bacon</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>freq</th>\n",
+       "      <td>1</td>\n",
+       "      <td>6</td>\n",
+       "      <td>28</td>\n",
+       "      <td>5</td>\n",
+       "      <td>8</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>12</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.940870</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3.048547e+05</td>\n",
+       "      <td>7.129188e+07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.269143</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3.400764e+05</td>\n",
+       "      <td>1.275242e+08</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.600000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.522900e+04</td>\n",
+       "      <td>3.600000e+03</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.700000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>8.123350e+04</td>\n",
+       "      <td>3.425538e+06</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>7.900000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.820090e+05</td>\n",
+       "      <td>2.018666e+07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>8.100000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.148195e+05</td>\n",
+       "      <td>8.406197e+07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>8.800000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.067042e+06</td>\n",
+       "      <td>9.366622e+08</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                        Series_Title Released_Year Certificate  Runtime  \\\n",
+       "count                            115           115         115      115   \n",
+       "unique                           115            56           8       72   \n",
+       "top     mr. smith goes to washington          2004          UA  120 min   \n",
+       "freq                               1             6          28        5   \n",
+       "mean                             NaN           NaN         NaN      NaN   \n",
+       "std                              NaN           NaN         NaN      NaN   \n",
+       "min                              NaN           NaN         NaN      NaN   \n",
+       "25%                              NaN           NaN         NaN      NaN   \n",
+       "50%                              NaN           NaN         NaN      NaN   \n",
+       "75%                              NaN           NaN         NaN      NaN   \n",
+       "max                              NaN           NaN         NaN      NaN   \n",
+       "\n",
+       "        Genre  IMDB_Rating Meta_score      Director        Star1  \\\n",
+       "count     115   115.000000        115           115          115   \n",
+       "unique     71          NaN         42           101          104   \n",
+       "top     drama          NaN             billy wilder  johnny depp   \n",
+       "freq        8          NaN         12             3            3   \n",
+       "mean      NaN     7.940870        NaN           NaN          NaN   \n",
+       "std       NaN     0.269143        NaN           NaN          NaN   \n",
+       "min       NaN     7.600000        NaN           NaN          NaN   \n",
+       "25%       NaN     7.700000        NaN           NaN          NaN   \n",
+       "50%       NaN     7.900000        NaN           NaN          NaN   \n",
+       "75%       NaN     8.100000        NaN           NaN          NaN   \n",
+       "max       NaN     8.800000        NaN           NaN          NaN   \n",
+       "\n",
+       "                  Star2          Star3        Star4   No_of_Votes  \\\n",
+       "count               115            115          115  1.150000e+02   \n",
+       "unique              115            115          112           NaN   \n",
+       "top     charlize theron  joel edgerton  kevin bacon           NaN   \n",
+       "freq                  1              1            2           NaN   \n",
+       "mean                NaN            NaN          NaN  3.048547e+05   \n",
+       "std                 NaN            NaN          NaN  3.400764e+05   \n",
+       "min                 NaN            NaN          NaN  2.522900e+04   \n",
+       "25%                 NaN            NaN          NaN  8.123350e+04   \n",
+       "50%                 NaN            NaN          NaN  1.820090e+05   \n",
+       "75%                 NaN            NaN          NaN  4.148195e+05   \n",
+       "max                 NaN            NaN          NaN  2.067042e+06   \n",
+       "\n",
+       "               Gross  \n",
+       "count   1.150000e+02  \n",
+       "unique           NaN  \n",
+       "top              NaN  \n",
+       "freq             NaN  \n",
+       "mean    7.129188e+07  \n",
+       "std     1.275242e+08  \n",
+       "min     3.600000e+03  \n",
+       "25%     3.425538e+06  \n",
+       "50%     2.018666e+07  \n",
+       "75%     8.406197e+07  \n",
+       "max     9.366622e+08  "
+      ]
+     },
+     "execution_count": 79,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1145,8 +1373,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 105,
-   "id": "modified-potential",
+   "execution_count": 80,
+   "id": "sufficient-parade",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1158,7 +1386,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "finnish-burning",
+   "id": "accompanied-virtue",
    "metadata": {},
    "outputs": [],
    "source": []