Prutor classwork Pandas.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "583827fa",
   "metadata": {},
   "source": [
    "# Introduction to Pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fa67ebe5",
   "metadata": {},
   "source": [
    "## 29/04/2022 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5de34d7f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7befe23a",
   "metadata": {},
   "source": [
    "## Read csv file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6ff8800d",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('movies.csv') #reading csv file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "4a0f3644",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(df)\n",
    "df.ndim"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "742ef868",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>9.3</td>\n",
       "      <td>The Shawshank Redemption</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>142</td>\n",
       "      <td>[u'Tim Robbins', u'Morgan Freeman', u'Bob Gunt...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>9.2</td>\n",
       "      <td>The Godfather</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>175</td>\n",
       "      <td>[u'Marlon Brando', u'Al Pacino', u'James Caan']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>9.1</td>\n",
       "      <td>The Godfather: Part II</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>200</td>\n",
       "      <td>[u'Al Pacino', u'Robert De Niro', u'Robert Duv...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>9.0</td>\n",
       "      <td>The Dark Knight</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Action</td>\n",
       "      <td>152</td>\n",
       "      <td>[u'Christian Bale', u'Heath Ledger', u'Aaron E...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.9</td>\n",
       "      <td>Pulp Fiction</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>154</td>\n",
       "      <td>[u'John Travolta', u'Uma Thurman', u'Samuel L....</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   star_rating                     title content_rating   genre  duration  \\\n",
       "0          9.3  The Shawshank Redemption              R   Crime       142   \n",
       "1          9.2             The Godfather              R   Crime       175   \n",
       "2          9.1    The Godfather: Part II              R   Crime       200   \n",
       "3          9.0           The Dark Knight          PG-13  Action       152   \n",
       "4          8.9              Pulp Fiction              R   Crime       154   \n",
       "\n",
       "                                         actors_list  \n",
       "0  [u'Tim Robbins', u'Morgan Freeman', u'Bob Gunt...  \n",
       "1    [u'Marlon Brando', u'Al Pacino', u'James Caan']  \n",
       "2  [u'Al Pacino', u'Robert De Niro', u'Robert Duv...  \n",
       "3  [u'Christian Bale', u'Heath Ledger', u'Aaron E...  \n",
       "4  [u'John Travolta', u'Uma Thurman', u'Samuel L....  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head() #it returns first five rows of the dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "5741a13d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(979, 6)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "8439b923",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>974</th>\n",
       "      <td>7.4</td>\n",
       "      <td>Tootsie</td>\n",
       "      <td>PG</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>116</td>\n",
       "      <td>[u'Dustin Hoffman', u'Jessica Lange', u'Teri G...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>975</th>\n",
       "      <td>7.4</td>\n",
       "      <td>Back to the Future Part III</td>\n",
       "      <td>PG</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>118</td>\n",
       "      <td>[u'Michael J. Fox', u'Christopher Lloyd', u'Ma...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>976</th>\n",
       "      <td>7.4</td>\n",
       "      <td>Master and Commander: The Far Side of the World</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Action</td>\n",
       "      <td>138</td>\n",
       "      <td>[u'Russell Crowe', u'Paul Bettany', u'Billy Bo...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>977</th>\n",
       "      <td>7.4</td>\n",
       "      <td>Poltergeist</td>\n",
       "      <td>PG</td>\n",
       "      <td>Horror</td>\n",
       "      <td>114</td>\n",
       "      <td>[u'JoBeth Williams', u\"Heather O'Rourke\", u'Cr...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>978</th>\n",
       "      <td>7.4</td>\n",
       "      <td>Wall Street</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>126</td>\n",
       "      <td>[u'Charlie Sheen', u'Michael Douglas', u'Tamar...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating                                            title  \\\n",
       "974          7.4                                          Tootsie   \n",
       "975          7.4                      Back to the Future Part III   \n",
       "976          7.4  Master and Commander: The Far Side of the World   \n",
       "977          7.4                                      Poltergeist   \n",
       "978          7.4                                      Wall Street   \n",
       "\n",
       "    content_rating      genre  duration  \\\n",
       "974             PG     Comedy       116   \n",
       "975             PG  Adventure       118   \n",
       "976          PG-13     Action       138   \n",
       "977             PG     Horror       114   \n",
       "978              R      Crime       126   \n",
       "\n",
       "                                           actors_list  \n",
       "974  [u'Dustin Hoffman', u'Jessica Lange', u'Teri G...  \n",
       "975  [u'Michael J. Fox', u'Christopher Lloyd', u'Ma...  \n",
       "976  [u'Russell Crowe', u'Paul Bettany', u'Billy Bo...  \n",
       "977  [u'JoBeth Williams', u\"Heather O'Rourke\", u'Cr...  \n",
       "978  [u'Charlie Sheen', u'Michael Douglas', u'Tamar...  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail() #it displays last 5 records in a data frame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "6453f5fa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Crime', 'Action', 'Drama', 'Western', 'Adventure', 'Biography',\n",
       "       'Comedy', 'Animation', 'Mystery', 'Horror', 'Film-Noir', 'Sci-Fi',\n",
       "       'History', 'Thriller', 'Family', 'Fantasy'], dtype=object)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.genre.unique() #dataframe_name.column_name.unique() it returns unique values in the genre coumn of the csv file movies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "144eab20",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "16"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.genre.nunique() #dataframe_name.column_name.nunique() it returns the number of unique items in genre column of the movies csv file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "47392c02",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Drama        278\n",
       "Comedy       156\n",
       "Action       136\n",
       "Crime        124\n",
       "Biography     77\n",
       "Adventure     75\n",
       "Animation     62\n",
       "Horror        29\n",
       "Mystery       16\n",
       "Western        9\n",
       "Thriller       5\n",
       "Sci-Fi         5\n",
       "Film-Noir      3\n",
       "Family         2\n",
       "Fantasy        1\n",
       "History        1\n",
       "Name: genre, dtype: int64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.genre.value_counts() #dataframe_name.column_name.value_counts() #it returns the number of movies in each genmre \n",
    "#in genre column of the movies csv file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "c242e03a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "star_rating       float64\n",
       "title              object\n",
       "content_rating     object\n",
       "genre              object\n",
       "duration            int64\n",
       "actors_list        object\n",
       "dtype: object"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes #it returns the type of values stored in each column of the csv file\n",
    "#object = String values , float64 = float values, int64 = integer values"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9a4ac3e5",
   "metadata": {},
   "source": [
    "## How to perform operation on a column title"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "11d9b88a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0                             The Shawshank Redemption\n",
       "1                                        The Godfather\n",
       "2                               The Godfather: Part II\n",
       "3                                      The Dark Knight\n",
       "4                                         Pulp Fiction\n",
       "                            ...                       \n",
       "974                                            Tootsie\n",
       "975                        Back to the Future Part III\n",
       "976    Master and Commander: The Far Side of the World\n",
       "977                                        Poltergeist\n",
       "978                                        Wall Street\n",
       "Name: title, Length: 979, dtype: object"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.title #it returns all the values in the title column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "78b46dae",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([142, 175, 200, 152, 154,  96, 161, 201, 195, 139, 178, 148, 124,\n",
       "       142, 179, 169, 133, 207, 146, 121, 136, 130, 130, 106, 127, 116,\n",
       "       175, 118, 110,  87, 125, 112, 102, 107, 119,  87, 169, 115, 112,\n",
       "       109, 189, 110, 150, 165, 155, 137, 113, 165,  95, 151, 155, 153,\n",
       "       125, 130, 116,  89, 137, 117,  88, 165, 170,  89, 146,  99,  98,\n",
       "       116, 156, 122, 149, 134, 122, 136, 157, 123, 119, 137, 128, 120,\n",
       "       229, 107, 134, 103, 177, 129, 102, 216, 136,  93,  68, 189,  99,\n",
       "       108, 113, 181, 103, 138, 110, 129,  88, 160, 126,  91, 116, 125,\n",
       "       143,  93, 102, 132, 153, 183, 160, 120, 138, 140, 153, 170, 129,\n",
       "        81, 127, 131, 172, 115, 108, 107, 129, 156,  96,  91,  95, 162,\n",
       "       130,  86, 186, 151,  96, 170, 118, 161, 131, 126, 131, 129, 224,\n",
       "       180, 105, 117, 140, 119, 124, 130, 139, 107, 132, 117, 126, 122,\n",
       "       178, 238, 149, 172,  98, 116, 116, 123, 148, 123, 182,  92,  93,\n",
       "       100, 135, 105,  94, 140,  83,  95,  98, 143,  99,  98, 121, 163,\n",
       "       121, 167, 188, 121, 109, 110, 129, 127,  94, 107, 100, 117, 129,\n",
       "       120, 121, 133, 111, 122, 101, 134, 165, 138, 212, 154,  89, 134,\n",
       "        93, 114,  88, 130, 101, 158,  99, 108, 124, 132, 113, 131, 191,\n",
       "       167, 130, 147, 102,  88, 165, 132, 118, 101, 108, 174,  98,  92,\n",
       "        98, 106,  85, 101, 105, 115, 115, 124, 105, 103, 138, 184, 120,\n",
       "        99, 131, 138,  98, 123, 118, 114, 118, 112, 124, 160,  67, 146,\n",
       "       125, 115, 134, 141, 129, 104,  94, 124, 150, 119, 128, 143,  85,\n",
       "       151, 118, 101,  99,  92, 125, 102, 106, 107,  91,  80, 122, 102,\n",
       "       112,  92, 135, 136, 153, 105, 126,  68,  84, 103, 145,  80, 106,\n",
       "       127, 178, 137, 172,  76, 130,  96,  82, 115,  95, 143, 125, 120,\n",
       "       127, 112, 104, 113, 189, 127, 188,  96, 113, 132, 122, 126, 140,\n",
       "       133, 112, 102,  93, 109,  81, 108, 111, 119,  96, 197, 127, 138,\n",
       "        66, 181, 141, 144, 128,  83, 121,  98, 117,  94, 174, 112, 108,\n",
       "        70,  99,  96, 137, 136, 100,  90,  96, 161, 115, 181, 169,  98,\n",
       "       136, 138, 119, 123, 112, 120, 103,  97, 109, 165, 156, 147, 100,\n",
       "       126, 115, 105, 144, 102, 107, 119,  90, 197,  86, 113, 133,  64,\n",
       "       141, 113, 122, 105, 119, 102, 122, 123, 113,  97, 117, 111,  85,\n",
       "        99, 134,  75, 109, 117,  91, 128, 111, 119, 100, 114,  92, 141,\n",
       "       101, 115, 127,  96, 129, 135, 109, 157, 193,  94, 155, 113, 130,\n",
       "       117, 159, 141, 112, 162, 126, 120, 144, 120, 109,  97, 108, 115,\n",
       "       136,  90, 170, 220, 116, 134, 124,  91, 103,  96, 119,  98, 101,\n",
       "        93, 179, 155, 121, 103, 127, 103, 107, 100,  92,  94, 158,  86,\n",
       "       115, 130, 107, 100, 108, 124, 131, 122, 242, 127, 141, 126,  89,\n",
       "       113, 152, 107,  92, 145,  84, 126, 132,  78, 117, 128, 100, 128,\n",
       "       100, 143, 107, 100, 125, 106, 157,  94, 104,  94, 153, 123, 120,\n",
       "       105, 166, 112,  94, 111,  87,  80, 108, 102, 105, 136, 101, 100,\n",
       "       108, 101, 106, 105,  88, 129, 138, 129, 118, 139, 123, 150, 132,\n",
       "        80, 178,  79, 163, 114, 144, 130, 154,  81,  95, 101, 120,  93,\n",
       "       115, 106, 120, 110, 123, 142,  99, 112, 120, 122, 130, 139, 129,\n",
       "       141, 127, 130, 118, 110, 115, 101, 112, 108, 143, 152, 117, 121,\n",
       "       119, 114, 122, 105, 110, 116, 139, 121, 109, 146, 113, 100, 121,\n",
       "       113, 113, 117,  93, 101,  90, 131,  98,  93, 121,  82, 124, 100,\n",
       "       117,  99, 116, 123, 114, 133, 105, 127, 144,  90, 118, 122, 102,\n",
       "       187,  87, 154,  89,  88, 129,  95, 118,  98, 194, 114,  80, 130,\n",
       "       135, 101, 105, 129, 134, 143, 202,  89, 106,  92, 137, 124, 122,\n",
       "       113, 112, 110, 135,  88, 146, 104, 125, 131,  91, 142, 129, 158,\n",
       "       102,  99, 101, 104, 119, 103,  88, 100, 146, 150, 140, 140, 110,\n",
       "        97, 102, 152, 100,  94,  85, 104, 112, 191, 119, 111,  94, 103,\n",
       "       134, 157, 158, 127, 101, 109,  98, 134, 168,  93, 145, 111,  88,\n",
       "       123, 121, 144, 116, 124, 147, 106, 113, 129,  94, 126, 128, 111,\n",
       "       146,  85, 105, 132, 130, 162, 113, 110, 113, 162, 110,  78,  92,\n",
       "        95, 138, 102, 128,  96, 164, 126, 110, 109, 122, 124, 128, 157,\n",
       "       120, 102, 152, 170, 102, 116, 164,  85, 104,  99,  81, 131, 101,\n",
       "       121,  69,  92,  94, 141, 116,  98, 135, 121, 108, 114, 102, 112,\n",
       "       140, 157, 128, 108, 139,  83, 131, 113, 136,  96, 118, 108,  83,\n",
       "       205, 124, 111, 137, 104, 109, 115,  99, 114, 133, 131, 131, 123,\n",
       "       126,  97, 126,  89, 122, 121, 125, 105, 118,  81, 115, 126, 113,\n",
       "       107, 126, 111,  85, 120,  93, 100, 107, 126, 131, 116, 143,  93,\n",
       "        96, 160, 137, 119, 114,  98, 111, 138, 144, 107, 114, 125, 146,\n",
       "       113,  85,  97,  93, 113, 128, 114, 147, 127, 167, 124, 109, 124,\n",
       "       102, 130, 125,  98, 154,  97, 128,  98, 101, 147, 172, 125,  88,\n",
       "       125, 121, 112, 120, 133, 110, 135, 110,  80, 135, 101, 112, 124,\n",
       "       129, 104,  96, 105, 109, 117,  78, 138, 106,  90, 106,  91, 112,\n",
       "       134, 112, 104, 101, 120, 123, 133, 110, 129, 120,  83,  88,  96,\n",
       "       139, 113,  84, 106, 170, 144, 104, 153,  85, 130,  93, 148, 115,\n",
       "       102, 125, 106, 121, 143, 116,  99, 116, 128, 119, 104, 114, 152,\n",
       "       129, 103, 112,  92, 141, 106, 109, 104, 122, 111, 112, 116, 130,\n",
       "       133, 134,  92, 104, 110,  97, 100, 118, 112, 138,  92, 118, 140,\n",
       "       128, 101,  75,  97, 111, 175,  94,  97, 132, 120, 107,  89,  86,\n",
       "       103, 108, 105, 117, 102, 104, 157, 104,  98, 109,  96, 103, 114,\n",
       "        99, 118, 150, 105,  87, 136, 162, 109, 107,  90, 112, 126, 116,\n",
       "       118, 138, 114, 126])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duration.values #it will return the values stored in the duration column of the csv file in form of an array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "6f17b5ef",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[142,\n",
       " 175,\n",
       " 200,\n",
       " 152,\n",
       " 154,\n",
       " 96,\n",
       " 161,\n",
       " 201,\n",
       " 195,\n",
       " 139,\n",
       " 178,\n",
       " 148,\n",
       " 124,\n",
       " 142,\n",
       " 179,\n",
       " 169,\n",
       " 133,\n",
       " 207,\n",
       " 146,\n",
       " 121,\n",
       " 136,\n",
       " 130,\n",
       " 130,\n",
       " 106,\n",
       " 127,\n",
       " 116,\n",
       " 175,\n",
       " 118,\n",
       " 110,\n",
       " 87,\n",
       " 125,\n",
       " 112,\n",
       " 102,\n",
       " 107,\n",
       " 119,\n",
       " 87,\n",
       " 169,\n",
       " 115,\n",
       " 112,\n",
       " 109,\n",
       " 189,\n",
       " 110,\n",
       " 150,\n",
       " 165,\n",
       " 155,\n",
       " 137,\n",
       " 113,\n",
       " 165,\n",
       " 95,\n",
       " 151,\n",
       " 155,\n",
       " 153,\n",
       " 125,\n",
       " 130,\n",
       " 116,\n",
       " 89,\n",
       " 137,\n",
       " 117,\n",
       " 88,\n",
       " 165,\n",
       " 170,\n",
       " 89,\n",
       " 146,\n",
       " 99,\n",
       " 98,\n",
       " 116,\n",
       " 156,\n",
       " 122,\n",
       " 149,\n",
       " 134,\n",
       " 122,\n",
       " 136,\n",
       " 157,\n",
       " 123,\n",
       " 119,\n",
       " 137,\n",
       " 128,\n",
       " 120,\n",
       " 229,\n",
       " 107,\n",
       " 134,\n",
       " 103,\n",
       " 177,\n",
       " 129,\n",
       " 102,\n",
       " 216,\n",
       " 136,\n",
       " 93,\n",
       " 68,\n",
       " 189,\n",
       " 99,\n",
       " 108,\n",
       " 113,\n",
       " 181,\n",
       " 103,\n",
       " 138,\n",
       " 110,\n",
       " 129,\n",
       " 88,\n",
       " 160,\n",
       " 126,\n",
       " 91,\n",
       " 116,\n",
       " 125,\n",
       " 143,\n",
       " 93,\n",
       " 102,\n",
       " 132,\n",
       " 153,\n",
       " 183,\n",
       " 160,\n",
       " 120,\n",
       " 138,\n",
       " 140,\n",
       " 153,\n",
       " 170,\n",
       " 129,\n",
       " 81,\n",
       " 127,\n",
       " 131,\n",
       " 172,\n",
       " 115,\n",
       " 108,\n",
       " 107,\n",
       " 129,\n",
       " 156,\n",
       " 96,\n",
       " 91,\n",
       " 95,\n",
       " 162,\n",
       " 130,\n",
       " 86,\n",
       " 186,\n",
       " 151,\n",
       " 96,\n",
       " 170,\n",
       " 118,\n",
       " 161,\n",
       " 131,\n",
       " 126,\n",
       " 131,\n",
       " 129,\n",
       " 224,\n",
       " 180,\n",
       " 105,\n",
       " 117,\n",
       " 140,\n",
       " 119,\n",
       " 124,\n",
       " 130,\n",
       " 139,\n",
       " 107,\n",
       " 132,\n",
       " 117,\n",
       " 126,\n",
       " 122,\n",
       " 178,\n",
       " 238,\n",
       " 149,\n",
       " 172,\n",
       " 98,\n",
       " 116,\n",
       " 116,\n",
       " 123,\n",
       " 148,\n",
       " 123,\n",
       " 182,\n",
       " 92,\n",
       " 93,\n",
       " 100,\n",
       " 135,\n",
       " 105,\n",
       " 94,\n",
       " 140,\n",
       " 83,\n",
       " 95,\n",
       " 98,\n",
       " 143,\n",
       " 99,\n",
       " 98,\n",
       " 121,\n",
       " 163,\n",
       " 121,\n",
       " 167,\n",
       " 188,\n",
       " 121,\n",
       " 109,\n",
       " 110,\n",
       " 129,\n",
       " 127,\n",
       " 94,\n",
       " 107,\n",
       " 100,\n",
       " 117,\n",
       " 129,\n",
       " 120,\n",
       " 121,\n",
       " 133,\n",
       " 111,\n",
       " 122,\n",
       " 101,\n",
       " 134,\n",
       " 165,\n",
       " 138,\n",
       " 212,\n",
       " 154,\n",
       " 89,\n",
       " 134,\n",
       " 93,\n",
       " 114,\n",
       " 88,\n",
       " 130,\n",
       " 101,\n",
       " 158,\n",
       " 99,\n",
       " 108,\n",
       " 124,\n",
       " 132,\n",
       " 113,\n",
       " 131,\n",
       " 191,\n",
       " 167,\n",
       " 130,\n",
       " 147,\n",
       " 102,\n",
       " 88,\n",
       " 165,\n",
       " 132,\n",
       " 118,\n",
       " 101,\n",
       " 108,\n",
       " 174,\n",
       " 98,\n",
       " 92,\n",
       " 98,\n",
       " 106,\n",
       " 85,\n",
       " 101,\n",
       " 105,\n",
       " 115,\n",
       " 115,\n",
       " 124,\n",
       " 105,\n",
       " 103,\n",
       " 138,\n",
       " 184,\n",
       " 120,\n",
       " 99,\n",
       " 131,\n",
       " 138,\n",
       " 98,\n",
       " 123,\n",
       " 118,\n",
       " 114,\n",
       " 118,\n",
       " 112,\n",
       " 124,\n",
       " 160,\n",
       " 67,\n",
       " 146,\n",
       " 125,\n",
       " 115,\n",
       " 134,\n",
       " 141,\n",
       " 129,\n",
       " 104,\n",
       " 94,\n",
       " 124,\n",
       " 150,\n",
       " 119,\n",
       " 128,\n",
       " 143,\n",
       " 85,\n",
       " 151,\n",
       " 118,\n",
       " 101,\n",
       " 99,\n",
       " 92,\n",
       " 125,\n",
       " 102,\n",
       " 106,\n",
       " 107,\n",
       " 91,\n",
       " 80,\n",
       " 122,\n",
       " 102,\n",
       " 112,\n",
       " 92,\n",
       " 135,\n",
       " 136,\n",
       " 153,\n",
       " 105,\n",
       " 126,\n",
       " 68,\n",
       " 84,\n",
       " 103,\n",
       " 145,\n",
       " 80,\n",
       " 106,\n",
       " 127,\n",
       " 178,\n",
       " 137,\n",
       " 172,\n",
       " 76,\n",
       " 130,\n",
       " 96,\n",
       " 82,\n",
       " 115,\n",
       " 95,\n",
       " 143,\n",
       " 125,\n",
       " 120,\n",
       " 127,\n",
       " 112,\n",
       " 104,\n",
       " 113,\n",
       " 189,\n",
       " 127,\n",
       " 188,\n",
       " 96,\n",
       " 113,\n",
       " 132,\n",
       " 122,\n",
       " 126,\n",
       " 140,\n",
       " 133,\n",
       " 112,\n",
       " 102,\n",
       " 93,\n",
       " 109,\n",
       " 81,\n",
       " 108,\n",
       " 111,\n",
       " 119,\n",
       " 96,\n",
       " 197,\n",
       " 127,\n",
       " 138,\n",
       " 66,\n",
       " 181,\n",
       " 141,\n",
       " 144,\n",
       " 128,\n",
       " 83,\n",
       " 121,\n",
       " 98,\n",
       " 117,\n",
       " 94,\n",
       " 174,\n",
       " 112,\n",
       " 108,\n",
       " 70,\n",
       " 99,\n",
       " 96,\n",
       " 137,\n",
       " 136,\n",
       " 100,\n",
       " 90,\n",
       " 96,\n",
       " 161,\n",
       " 115,\n",
       " 181,\n",
       " 169,\n",
       " 98,\n",
       " 136,\n",
       " 138,\n",
       " 119,\n",
       " 123,\n",
       " 112,\n",
       " 120,\n",
       " 103,\n",
       " 97,\n",
       " 109,\n",
       " 165,\n",
       " 156,\n",
       " 147,\n",
       " 100,\n",
       " 126,\n",
       " 115,\n",
       " 105,\n",
       " 144,\n",
       " 102,\n",
       " 107,\n",
       " 119,\n",
       " 90,\n",
       " 197,\n",
       " 86,\n",
       " 113,\n",
       " 133,\n",
       " 64,\n",
       " 141,\n",
       " 113,\n",
       " 122,\n",
       " 105,\n",
       " 119,\n",
       " 102,\n",
       " 122,\n",
       " 123,\n",
       " 113,\n",
       " 97,\n",
       " 117,\n",
       " 111,\n",
       " 85,\n",
       " 99,\n",
       " 134,\n",
       " 75,\n",
       " 109,\n",
       " 117,\n",
       " 91,\n",
       " 128,\n",
       " 111,\n",
       " 119,\n",
       " 100,\n",
       " 114,\n",
       " 92,\n",
       " 141,\n",
       " 101,\n",
       " 115,\n",
       " 127,\n",
       " 96,\n",
       " 129,\n",
       " 135,\n",
       " 109,\n",
       " 157,\n",
       " 193,\n",
       " 94,\n",
       " 155,\n",
       " 113,\n",
       " 130,\n",
       " 117,\n",
       " 159,\n",
       " 141,\n",
       " 112,\n",
       " 162,\n",
       " 126,\n",
       " 120,\n",
       " 144,\n",
       " 120,\n",
       " 109,\n",
       " 97,\n",
       " 108,\n",
       " 115,\n",
       " 136,\n",
       " 90,\n",
       " 170,\n",
       " 220,\n",
       " 116,\n",
       " 134,\n",
       " 124,\n",
       " 91,\n",
       " 103,\n",
       " 96,\n",
       " 119,\n",
       " 98,\n",
       " 101,\n",
       " 93,\n",
       " 179,\n",
       " 155,\n",
       " 121,\n",
       " 103,\n",
       " 127,\n",
       " 103,\n",
       " 107,\n",
       " 100,\n",
       " 92,\n",
       " 94,\n",
       " 158,\n",
       " 86,\n",
       " 115,\n",
       " 130,\n",
       " 107,\n",
       " 100,\n",
       " 108,\n",
       " 124,\n",
       " 131,\n",
       " 122,\n",
       " 242,\n",
       " 127,\n",
       " 141,\n",
       " 126,\n",
       " 89,\n",
       " 113,\n",
       " 152,\n",
       " 107,\n",
       " 92,\n",
       " 145,\n",
       " 84,\n",
       " 126,\n",
       " 132,\n",
       " 78,\n",
       " 117,\n",
       " 128,\n",
       " 100,\n",
       " 128,\n",
       " 100,\n",
       " 143,\n",
       " 107,\n",
       " 100,\n",
       " 125,\n",
       " 106,\n",
       " 157,\n",
       " 94,\n",
       " 104,\n",
       " 94,\n",
       " 153,\n",
       " 123,\n",
       " 120,\n",
       " 105,\n",
       " 166,\n",
       " 112,\n",
       " 94,\n",
       " 111,\n",
       " 87,\n",
       " 80,\n",
       " 108,\n",
       " 102,\n",
       " 105,\n",
       " 136,\n",
       " 101,\n",
       " 100,\n",
       " 108,\n",
       " 101,\n",
       " 106,\n",
       " 105,\n",
       " 88,\n",
       " 129,\n",
       " 138,\n",
       " 129,\n",
       " 118,\n",
       " 139,\n",
       " 123,\n",
       " 150,\n",
       " 132,\n",
       " 80,\n",
       " 178,\n",
       " 79,\n",
       " 163,\n",
       " 114,\n",
       " 144,\n",
       " 130,\n",
       " 154,\n",
       " 81,\n",
       " 95,\n",
       " 101,\n",
       " 120,\n",
       " 93,\n",
       " 115,\n",
       " 106,\n",
       " 120,\n",
       " 110,\n",
       " 123,\n",
       " 142,\n",
       " 99,\n",
       " 112,\n",
       " 120,\n",
       " 122,\n",
       " 130,\n",
       " 139,\n",
       " 129,\n",
       " 141,\n",
       " 127,\n",
       " 130,\n",
       " 118,\n",
       " 110,\n",
       " 115,\n",
       " 101,\n",
       " 112,\n",
       " 108,\n",
       " 143,\n",
       " 152,\n",
       " 117,\n",
       " 121,\n",
       " 119,\n",
       " 114,\n",
       " 122,\n",
       " 105,\n",
       " 110,\n",
       " 116,\n",
       " 139,\n",
       " 121,\n",
       " 109,\n",
       " 146,\n",
       " 113,\n",
       " 100,\n",
       " 121,\n",
       " 113,\n",
       " 113,\n",
       " 117,\n",
       " 93,\n",
       " 101,\n",
       " 90,\n",
       " 131,\n",
       " 98,\n",
       " 93,\n",
       " 121,\n",
       " 82,\n",
       " 124,\n",
       " 100,\n",
       " 117,\n",
       " 99,\n",
       " 116,\n",
       " 123,\n",
       " 114,\n",
       " 133,\n",
       " 105,\n",
       " 127,\n",
       " 144,\n",
       " 90,\n",
       " 118,\n",
       " 122,\n",
       " 102,\n",
       " 187,\n",
       " 87,\n",
       " 154,\n",
       " 89,\n",
       " 88,\n",
       " 129,\n",
       " 95,\n",
       " 118,\n",
       " 98,\n",
       " 194,\n",
       " 114,\n",
       " 80,\n",
       " 130,\n",
       " 135,\n",
       " 101,\n",
       " 105,\n",
       " 129,\n",
       " 134,\n",
       " 143,\n",
       " 202,\n",
       " 89,\n",
       " 106,\n",
       " 92,\n",
       " 137,\n",
       " 124,\n",
       " 122,\n",
       " 113,\n",
       " 112,\n",
       " 110,\n",
       " 135,\n",
       " 88,\n",
       " 146,\n",
       " 104,\n",
       " 125,\n",
       " 131,\n",
       " 91,\n",
       " 142,\n",
       " 129,\n",
       " 158,\n",
       " 102,\n",
       " 99,\n",
       " 101,\n",
       " 104,\n",
       " 119,\n",
       " 103,\n",
       " 88,\n",
       " 100,\n",
       " 146,\n",
       " 150,\n",
       " 140,\n",
       " 140,\n",
       " 110,\n",
       " 97,\n",
       " 102,\n",
       " 152,\n",
       " 100,\n",
       " 94,\n",
       " 85,\n",
       " 104,\n",
       " 112,\n",
       " 191,\n",
       " 119,\n",
       " 111,\n",
       " 94,\n",
       " 103,\n",
       " 134,\n",
       " 157,\n",
       " 158,\n",
       " 127,\n",
       " 101,\n",
       " 109,\n",
       " 98,\n",
       " 134,\n",
       " 168,\n",
       " 93,\n",
       " 145,\n",
       " 111,\n",
       " 88,\n",
       " 123,\n",
       " 121,\n",
       " 144,\n",
       " 116,\n",
       " 124,\n",
       " 147,\n",
       " 106,\n",
       " 113,\n",
       " 129,\n",
       " 94,\n",
       " 126,\n",
       " 128,\n",
       " 111,\n",
       " 146,\n",
       " 85,\n",
       " 105,\n",
       " 132,\n",
       " 130,\n",
       " 162,\n",
       " 113,\n",
       " 110,\n",
       " 113,\n",
       " 162,\n",
       " 110,\n",
       " 78,\n",
       " 92,\n",
       " 95,\n",
       " 138,\n",
       " 102,\n",
       " 128,\n",
       " 96,\n",
       " 164,\n",
       " 126,\n",
       " 110,\n",
       " 109,\n",
       " 122,\n",
       " 124,\n",
       " 128,\n",
       " 157,\n",
       " 120,\n",
       " 102,\n",
       " 152,\n",
       " 170,\n",
       " 102,\n",
       " 116,\n",
       " 164,\n",
       " 85,\n",
       " 104,\n",
       " 99,\n",
       " 81,\n",
       " 131,\n",
       " 101,\n",
       " 121,\n",
       " 69,\n",
       " 92,\n",
       " 94,\n",
       " 141,\n",
       " 116,\n",
       " 98,\n",
       " 135,\n",
       " 121,\n",
       " 108,\n",
       " 114,\n",
       " 102,\n",
       " 112,\n",
       " 140,\n",
       " 157,\n",
       " 128,\n",
       " 108,\n",
       " 139,\n",
       " 83,\n",
       " 131,\n",
       " 113,\n",
       " 136,\n",
       " 96,\n",
       " 118,\n",
       " 108,\n",
       " 83,\n",
       " 205,\n",
       " 124,\n",
       " 111,\n",
       " 137,\n",
       " 104,\n",
       " 109,\n",
       " 115,\n",
       " 99,\n",
       " 114,\n",
       " 133,\n",
       " 131,\n",
       " 131,\n",
       " 123,\n",
       " 126,\n",
       " 97,\n",
       " 126,\n",
       " 89,\n",
       " 122,\n",
       " 121,\n",
       " 125,\n",
       " 105,\n",
       " 118,\n",
       " 81,\n",
       " 115,\n",
       " 126,\n",
       " 113,\n",
       " 107,\n",
       " 126,\n",
       " 111,\n",
       " 85,\n",
       " 120,\n",
       " 93,\n",
       " 100,\n",
       " 107,\n",
       " 126,\n",
       " 131,\n",
       " 116,\n",
       " 143,\n",
       " 93,\n",
       " 96,\n",
       " 160,\n",
       " 137,\n",
       " 119,\n",
       " 114,\n",
       " 98,\n",
       " 111,\n",
       " 138,\n",
       " 144,\n",
       " 107,\n",
       " 114,\n",
       " 125,\n",
       " 146,\n",
       " 113,\n",
       " 85,\n",
       " 97,\n",
       " 93,\n",
       " 113,\n",
       " 128,\n",
       " 114,\n",
       " 147,\n",
       " 127,\n",
       " 167,\n",
       " 124,\n",
       " 109,\n",
       " 124,\n",
       " 102,\n",
       " 130,\n",
       " 125,\n",
       " 98,\n",
       " 154,\n",
       " 97,\n",
       " 128,\n",
       " 98,\n",
       " 101,\n",
       " 147,\n",
       " 172,\n",
       " 125,\n",
       " 88,\n",
       " 125,\n",
       " 121,\n",
       " 112,\n",
       " 120,\n",
       " 133,\n",
       " 110,\n",
       " 135,\n",
       " 110,\n",
       " 80,\n",
       " 135,\n",
       " 101,\n",
       " 112,\n",
       " 124,\n",
       " 129,\n",
       " 104,\n",
       " 96,\n",
       " 105,\n",
       " 109,\n",
       " 117,\n",
       " 78,\n",
       " 138,\n",
       " 106,\n",
       " 90,\n",
       " 106,\n",
       " 91,\n",
       " 112,\n",
       " 134,\n",
       " 112,\n",
       " 104,\n",
       " 101,\n",
       " 120,\n",
       " 123,\n",
       " 133,\n",
       " 110,\n",
       " 129,\n",
       " 120,\n",
       " 83,\n",
       " 88,\n",
       " 96,\n",
       " 139,\n",
       " 113,\n",
       " 84,\n",
       " 106,\n",
       " 170,\n",
       " 144,\n",
       " 104,\n",
       " 153,\n",
       " 85,\n",
       " 130,\n",
       " 93,\n",
       " 148,\n",
       " 115,\n",
       " 102,\n",
       " 125,\n",
       " 106,\n",
       " 121,\n",
       " 143,\n",
       " 116,\n",
       " 99,\n",
       " 116,\n",
       " 128,\n",
       " 119,\n",
       " 104,\n",
       " 114,\n",
       " 152,\n",
       " 129,\n",
       " 103,\n",
       " 112,\n",
       " 92,\n",
       " 141,\n",
       " 106,\n",
       " 109,\n",
       " 104,\n",
       " 122,\n",
       " 111,\n",
       " 112,\n",
       " 116,\n",
       " 130,\n",
       " 133,\n",
       " 134,\n",
       " 92,\n",
       " 104,\n",
       " 110,\n",
       " 97,\n",
       " 100,\n",
       " 118,\n",
       " 112,\n",
       " 138,\n",
       " 92,\n",
       " 118,\n",
       " 140,\n",
       " 128,\n",
       " 101,\n",
       " 75,\n",
       " 97,\n",
       " 111,\n",
       " 175,\n",
       " 94,\n",
       " 97,\n",
       " 132,\n",
       " 120,\n",
       " 107,\n",
       " 89,\n",
       " 86,\n",
       " 103,\n",
       " 108,\n",
       " 105,\n",
       " 117,\n",
       " 102,\n",
       " 104,\n",
       " 157,\n",
       " 104,\n",
       " 98,\n",
       " 109,\n",
       " 96,\n",
       " 103,\n",
       " 114,\n",
       " 99,\n",
       " 118,\n",
       " 150,\n",
       " 105,\n",
       " 87,\n",
       " 136,\n",
       " 162,\n",
       " 109,\n",
       " 107,\n",
       " 90,\n",
       " 112,\n",
       " 126,\n",
       " 116,\n",
       " 118,\n",
       " 138,\n",
       " 114,\n",
       " 126]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duration.to_list() #it will return the values stored in the duration column of the csv file in form of a list"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "66600b4b",
   "metadata": {},
   "source": [
    "## How to acess more than 1 column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "a1646357",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>title</th>\n",
       "      <th>duration</th>\n",
       "      <th>genre</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>The Shawshank Redemption</td>\n",
       "      <td>142</td>\n",
       "      <td>Crime</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>The Godfather</td>\n",
       "      <td>175</td>\n",
       "      <td>Crime</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>The Godfather: Part II</td>\n",
       "      <td>200</td>\n",
       "      <td>Crime</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>The Dark Knight</td>\n",
       "      <td>152</td>\n",
       "      <td>Action</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Pulp Fiction</td>\n",
       "      <td>154</td>\n",
       "      <td>Crime</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>974</th>\n",
       "      <td>Tootsie</td>\n",
       "      <td>116</td>\n",
       "      <td>Comedy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>975</th>\n",
       "      <td>Back to the Future Part III</td>\n",
       "      <td>118</td>\n",
       "      <td>Adventure</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>976</th>\n",
       "      <td>Master and Commander: The Far Side of the World</td>\n",
       "      <td>138</td>\n",
       "      <td>Action</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>977</th>\n",
       "      <td>Poltergeist</td>\n",
       "      <td>114</td>\n",
       "      <td>Horror</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>978</th>\n",
       "      <td>Wall Street</td>\n",
       "      <td>126</td>\n",
       "      <td>Crime</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>979 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               title  duration      genre\n",
       "0                           The Shawshank Redemption       142      Crime\n",
       "1                                      The Godfather       175      Crime\n",
       "2                             The Godfather: Part II       200      Crime\n",
       "3                                    The Dark Knight       152     Action\n",
       "4                                       Pulp Fiction       154      Crime\n",
       "..                                               ...       ...        ...\n",
       "974                                          Tootsie       116     Comedy\n",
       "975                      Back to the Future Part III       118  Adventure\n",
       "976  Master and Commander: The Far Side of the World       138     Action\n",
       "977                                      Poltergeist       114     Horror\n",
       "978                                      Wall Street       126      Crime\n",
       "\n",
       "[979 rows x 3 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[['title', 'duration', 'genre']]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "98a4e316",
   "metadata": {},
   "source": [
    "## how to get all the movies whoes duration is more than 200 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "b22d0524",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8.9</td>\n",
       "      <td>The Lord of the Rings: The Return of the King</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>201</td>\n",
       "      <td>[u'Elijah Wood', u'Viggo Mortensen', u'Ian McK...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>8.7</td>\n",
       "      <td>Seven Samurai</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>207</td>\n",
       "      <td>[u'Toshir\\xf4 Mifune', u'Takashi Shimura', u'K...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78</th>\n",
       "      <td>8.4</td>\n",
       "      <td>Once Upon a Time in America</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>229</td>\n",
       "      <td>[u'Robert De Niro', u'James Woods', u'Elizabet...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>85</th>\n",
       "      <td>8.4</td>\n",
       "      <td>Lawrence of Arabia</td>\n",
       "      <td>PG</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>216</td>\n",
       "      <td>[u\"Peter O'Toole\", u'Alec Guinness', u'Anthony...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>142</th>\n",
       "      <td>8.3</td>\n",
       "      <td>Lagaan: Once Upon a Time in India</td>\n",
       "      <td>PG</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>224</td>\n",
       "      <td>[u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>157</th>\n",
       "      <td>8.2</td>\n",
       "      <td>Gone with the Wind</td>\n",
       "      <td>G</td>\n",
       "      <td>Drama</td>\n",
       "      <td>238</td>\n",
       "      <td>[u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>204</th>\n",
       "      <td>8.1</td>\n",
       "      <td>Ben-Hur</td>\n",
       "      <td>G</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>212</td>\n",
       "      <td>[u'Charlton Heston', u'Jack Hawkins', u'Stephe...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>445</th>\n",
       "      <td>7.9</td>\n",
       "      <td>The Ten Commandments</td>\n",
       "      <td>APPROVED</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>220</td>\n",
       "      <td>[u'Charlton Heston', u'Yul Brynner', u'Anne Ba...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>476</th>\n",
       "      <td>7.8</td>\n",
       "      <td>Hamlet</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Drama</td>\n",
       "      <td>242</td>\n",
       "      <td>[u'Kenneth Branagh', u'Julie Christie', u'Dere...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>630</th>\n",
       "      <td>7.7</td>\n",
       "      <td>Malcolm X</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Biography</td>\n",
       "      <td>202</td>\n",
       "      <td>[u'Denzel Washington', u'Angela Bassett', u'De...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>767</th>\n",
       "      <td>7.6</td>\n",
       "      <td>It's a Mad, Mad, Mad, Mad World</td>\n",
       "      <td>APPROVED</td>\n",
       "      <td>Action</td>\n",
       "      <td>205</td>\n",
       "      <td>[u'Spencer Tracy', u'Milton Berle', u'Ethel Me...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating                                          title  \\\n",
       "7            8.9  The Lord of the Rings: The Return of the King   \n",
       "17           8.7                                  Seven Samurai   \n",
       "78           8.4                    Once Upon a Time in America   \n",
       "85           8.4                             Lawrence of Arabia   \n",
       "142          8.3              Lagaan: Once Upon a Time in India   \n",
       "157          8.2                             Gone with the Wind   \n",
       "204          8.1                                        Ben-Hur   \n",
       "445          7.9                           The Ten Commandments   \n",
       "476          7.8                                         Hamlet   \n",
       "630          7.7                                      Malcolm X   \n",
       "767          7.6                It's a Mad, Mad, Mad, Mad World   \n",
       "\n",
       "    content_rating      genre  duration  \\\n",
       "7            PG-13  Adventure       201   \n",
       "17         UNRATED      Drama       207   \n",
       "78               R      Crime       229   \n",
       "85              PG  Adventure       216   \n",
       "142             PG  Adventure       224   \n",
       "157              G      Drama       238   \n",
       "204              G  Adventure       212   \n",
       "445       APPROVED  Adventure       220   \n",
       "476          PG-13      Drama       242   \n",
       "630          PG-13  Biography       202   \n",
       "767       APPROVED     Action       205   \n",
       "\n",
       "                                           actors_list  \n",
       "7    [u'Elijah Wood', u'Viggo Mortensen', u'Ian McK...  \n",
       "17   [u'Toshir\\xf4 Mifune', u'Takashi Shimura', u'K...  \n",
       "78   [u'Robert De Niro', u'James Woods', u'Elizabet...  \n",
       "85   [u\"Peter O'Toole\", u'Alec Guinness', u'Anthony...  \n",
       "142  [u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...  \n",
       "157  [u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...  \n",
       "204  [u'Charlton Heston', u'Jack Hawkins', u'Stephe...  \n",
       "445  [u'Charlton Heston', u'Yul Brynner', u'Anne Ba...  \n",
       "476  [u'Kenneth Branagh', u'Julie Christie', u'Dere...  \n",
       "630  [u'Denzel Washington', u'Angela Bassett', u'De...  \n",
       "767  [u'Spencer Tracy', u'Milton Berle', u'Ethel Me...  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.duration>200]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "d983bff2",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.9</td>\n",
       "      <td>Pulp Fiction</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>154</td>\n",
       "      <td>[u'John Travolta', u'Uma Thurman', u'Samuel L....</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>8.9</td>\n",
       "      <td>12 Angry Men</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>96</td>\n",
       "      <td>[u'Henry Fonda', u'Lee J. Cobb', u'Martin Bals...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>8.9</td>\n",
       "      <td>The Good, the Bad and the Ugly</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Western</td>\n",
       "      <td>161</td>\n",
       "      <td>[u'Clint Eastwood', u'Eli Wallach', u'Lee Van ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8.9</td>\n",
       "      <td>The Lord of the Rings: The Return of the King</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>201</td>\n",
       "      <td>[u'Elijah Wood', u'Viggo Mortensen', u'Ian McK...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>8.9</td>\n",
       "      <td>Schindler's List</td>\n",
       "      <td>R</td>\n",
       "      <td>Biography</td>\n",
       "      <td>195</td>\n",
       "      <td>[u'Liam Neeson', u'Ralph Fiennes', u'Ben Kings...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>292</th>\n",
       "      <td>8.1</td>\n",
       "      <td>The Manchurian Candidate</td>\n",
       "      <td>APPROVED</td>\n",
       "      <td>Mystery</td>\n",
       "      <td>126</td>\n",
       "      <td>[u'Frank Sinatra', u'Laurence Harvey', u'Janet...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>293</th>\n",
       "      <td>8.1</td>\n",
       "      <td>Duck Soup</td>\n",
       "      <td>PASSED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Groucho Marx', u'Harpo Marx', u'Chico Marx']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>294</th>\n",
       "      <td>8.1</td>\n",
       "      <td>Beauty and the Beast</td>\n",
       "      <td>G</td>\n",
       "      <td>Animation</td>\n",
       "      <td>84</td>\n",
       "      <td>[u\"Paige O'Hara\", u'Robby Benson', u'Richard W...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>295</th>\n",
       "      <td>8.1</td>\n",
       "      <td>The Truman Show</td>\n",
       "      <td>PG</td>\n",
       "      <td>Drama</td>\n",
       "      <td>103</td>\n",
       "      <td>[u'Jim Carrey', u'Ed Harris', u'Laura Linney']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>8.1</td>\n",
       "      <td>The Wild Bunch</td>\n",
       "      <td>R</td>\n",
       "      <td>Action</td>\n",
       "      <td>145</td>\n",
       "      <td>[u'William Holden', u'Ernest Borgnine', u'Robe...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>293 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating                                          title  \\\n",
       "4            8.9                                   Pulp Fiction   \n",
       "5            8.9                                   12 Angry Men   \n",
       "6            8.9                 The Good, the Bad and the Ugly   \n",
       "7            8.9  The Lord of the Rings: The Return of the King   \n",
       "8            8.9                               Schindler's List   \n",
       "..           ...                                            ...   \n",
       "292          8.1                       The Manchurian Candidate   \n",
       "293          8.1                                      Duck Soup   \n",
       "294          8.1                           Beauty and the Beast   \n",
       "295          8.1                                The Truman Show   \n",
       "296          8.1                                 The Wild Bunch   \n",
       "\n",
       "    content_rating      genre  duration  \\\n",
       "4                R      Crime       154   \n",
       "5        NOT RATED      Drama        96   \n",
       "6        NOT RATED    Western       161   \n",
       "7            PG-13  Adventure       201   \n",
       "8                R  Biography       195   \n",
       "..             ...        ...       ...   \n",
       "292       APPROVED    Mystery       126   \n",
       "293         PASSED     Comedy        68   \n",
       "294              G  Animation        84   \n",
       "295             PG      Drama       103   \n",
       "296              R     Action       145   \n",
       "\n",
       "                                           actors_list  \n",
       "4    [u'John Travolta', u'Uma Thurman', u'Samuel L....  \n",
       "5    [u'Henry Fonda', u'Lee J. Cobb', u'Martin Bals...  \n",
       "6    [u'Clint Eastwood', u'Eli Wallach', u'Lee Van ...  \n",
       "7    [u'Elijah Wood', u'Viggo Mortensen', u'Ian McK...  \n",
       "8    [u'Liam Neeson', u'Ralph Fiennes', u'Ben Kings...  \n",
       "..                                                 ...  \n",
       "292  [u'Frank Sinatra', u'Laurence Harvey', u'Janet...  \n",
       "293    [u'Groucho Marx', u'Harpo Marx', u'Chico Marx']  \n",
       "294  [u\"Paige O'Hara\", u'Robby Benson', u'Richard W...  \n",
       "295     [u'Jim Carrey', u'Ed Harris', u'Laura Linney']  \n",
       "296  [u'William Holden', u'Ernest Borgnine', u'Robe...  \n",
       "\n",
       "[293 rows x 6 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# How to use more than 2 conditions\n",
    "df[(df.star_rating>8.0) & (df.star_rating<9.0)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "bb446ebc",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>8.7</td>\n",
       "      <td>Seven Samurai</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>207</td>\n",
       "      <td>[u'Toshir\\xf4 Mifune', u'Takashi Shimura', u'K...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>157</th>\n",
       "      <td>8.2</td>\n",
       "      <td>Gone with the Wind</td>\n",
       "      <td>G</td>\n",
       "      <td>Drama</td>\n",
       "      <td>238</td>\n",
       "      <td>[u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>476</th>\n",
       "      <td>7.8</td>\n",
       "      <td>Hamlet</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Drama</td>\n",
       "      <td>242</td>\n",
       "      <td>[u'Kenneth Branagh', u'Julie Christie', u'Dere...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating               title content_rating  genre  duration  \\\n",
       "17           8.7       Seven Samurai        UNRATED  Drama       207   \n",
       "157          8.2  Gone with the Wind              G  Drama       238   \n",
       "476          7.8              Hamlet          PG-13  Drama       242   \n",
       "\n",
       "                                           actors_list  \n",
       "17   [u'Toshir\\xf4 Mifune', u'Takashi Shimura', u'K...  \n",
       "157  [u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...  \n",
       "476  [u'Kenneth Branagh', u'Julie Christie', u'Dere...  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[(df.duration>200) & (df.genre == 'Drama')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "c2222ef5",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>9.3</td>\n",
       "      <td>The Shawshank Redemption</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>142</td>\n",
       "      <td>[u'Tim Robbins', u'Morgan Freeman', u'Bob Gunt...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>9.2</td>\n",
       "      <td>The Godfather</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>175</td>\n",
       "      <td>[u'Marlon Brando', u'Al Pacino', u'James Caan']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>9.1</td>\n",
       "      <td>The Godfather: Part II</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>200</td>\n",
       "      <td>[u'Al Pacino', u'Robert De Niro', u'Robert Duv...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   star_rating                     title content_rating  genre  duration  \\\n",
       "0          9.3  The Shawshank Redemption              R  Crime       142   \n",
       "1          9.2             The Godfather              R  Crime       175   \n",
       "2          9.1    The Godfather: Part II              R  Crime       200   \n",
       "\n",
       "                                         actors_list  \n",
       "0  [u'Tim Robbins', u'Morgan Freeman', u'Bob Gunt...  \n",
       "1    [u'Marlon Brando', u'Al Pacino', u'James Caan']  \n",
       "2  [u'Al Pacino', u'Robert De Niro', u'Robert Duv...  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.star_rating>9.0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1d4b7fa0",
   "metadata": {},
   "source": [
    "## how to find max value in the duration column and return the row from the dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "39a595f9",
   "metadata": {},
   "outputs": [],
   "source": [
    "index = df.duration.argmax() #it gives the index number of that movie with the max duraiton value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "24b5fdaa",
   "metadata": {},
   "outputs": [],
   "source": [
    "# iloc: it works on default indexing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "62245d82",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "star_rating                                                     7.8\n",
       "title                                                        Hamlet\n",
       "content_rating                                                PG-13\n",
       "genre                                                         Drama\n",
       "duration                                                        242\n",
       "actors_list       [u'Kenneth Branagh', u'Julie Christie', u'Dere...\n",
       "Name: 476, dtype: object"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.iloc[index]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "14dc9755",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>title</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>50</th>\n",
       "      <td>Cinema Paradiso</td>\n",
       "      <td>[u'Philippe Noiret', u'Enzo Cannavale', u'Anto...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>51</th>\n",
       "      <td>Apocalypse Now</td>\n",
       "      <td>[u'Martin Sheen', u'Marlon Brando', u'Robert D...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>52</th>\n",
       "      <td>The Great Dictator</td>\n",
       "      <td>[u'Charles Chaplin', u'Paulette Goddard', u'Ja...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53</th>\n",
       "      <td>The Prestige</td>\n",
       "      <td>[u'Christian Bale', u'Hugh Jackman', u'Scarlet...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54</th>\n",
       "      <td>Back to the Future</td>\n",
       "      <td>[u'Michael J. Fox', u'Christopher Lloyd', u'Le...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>55</th>\n",
       "      <td>The Lion King</td>\n",
       "      <td>[u'Matthew Broderick', u'Jeremy Irons', u'Jame...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>56</th>\n",
       "      <td>The Lives of Others</td>\n",
       "      <td>[u'Ulrich M\\xfche', u'Martina Gedeck', u'Sebas...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>57</th>\n",
       "      <td>Alien</td>\n",
       "      <td>[u'Sigourney Weaver', u'Tom Skerritt', u'John ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58</th>\n",
       "      <td>Paths of Glory</td>\n",
       "      <td>[u'Kirk Douglas', u'Ralph Meeker', u'Adolphe M...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>59</th>\n",
       "      <td>Django Unchained</td>\n",
       "      <td>[u'Jamie Foxx', u'Christoph Waltz', u'Leonardo...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  title                                        actors_list\n",
       "50      Cinema Paradiso  [u'Philippe Noiret', u'Enzo Cannavale', u'Anto...\n",
       "51       Apocalypse Now  [u'Martin Sheen', u'Marlon Brando', u'Robert D...\n",
       "52   The Great Dictator  [u'Charles Chaplin', u'Paulette Goddard', u'Ja...\n",
       "53         The Prestige  [u'Christian Bale', u'Hugh Jackman', u'Scarlet...\n",
       "54   Back to the Future  [u'Michael J. Fox', u'Christopher Lloyd', u'Le...\n",
       "55        The Lion King  [u'Matthew Broderick', u'Jeremy Irons', u'Jame...\n",
       "56  The Lives of Others  [u'Ulrich M\\xfche', u'Martina Gedeck', u'Sebas...\n",
       "57                Alien  [u'Sigourney Weaver', u'Tom Skerritt', u'John ...\n",
       "58       Paths of Glory  [u'Kirk Douglas', u'Ralph Meeker', u'Adolphe M...\n",
       "59     Django Unchained  [u'Jamie Foxx', u'Christoph Waltz', u'Leonardo..."
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#df.iloc[starting row index:ending row index, [column index 1,column index 2]] \n",
    "#it will give all the rows between 50 and 60 index number of the dataframe  \n",
    "df.iloc[50:60,[1,5]] "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "9948512e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# loc: loc works on labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "d5b7e6c0",
   "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>star_rating</th>\n",
       "      <th>duration</th>\n",
       "      <th>title</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>50</th>\n",
       "      <td>8.5</td>\n",
       "      <td>155</td>\n",
       "      <td>Cinema Paradiso</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>51</th>\n",
       "      <td>8.5</td>\n",
       "      <td>153</td>\n",
       "      <td>Apocalypse Now</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>52</th>\n",
       "      <td>8.5</td>\n",
       "      <td>125</td>\n",
       "      <td>The Great Dictator</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53</th>\n",
       "      <td>8.5</td>\n",
       "      <td>130</td>\n",
       "      <td>The Prestige</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54</th>\n",
       "      <td>8.5</td>\n",
       "      <td>116</td>\n",
       "      <td>Back to the Future</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>55</th>\n",
       "      <td>8.5</td>\n",
       "      <td>89</td>\n",
       "      <td>The Lion King</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>56</th>\n",
       "      <td>8.5</td>\n",
       "      <td>137</td>\n",
       "      <td>The Lives of Others</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>57</th>\n",
       "      <td>8.5</td>\n",
       "      <td>117</td>\n",
       "      <td>Alien</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58</th>\n",
       "      <td>8.5</td>\n",
       "      <td>88</td>\n",
       "      <td>Paths of Glory</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>59</th>\n",
       "      <td>8.5</td>\n",
       "      <td>165</td>\n",
       "      <td>Django Unchained</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>8.5</td>\n",
       "      <td>170</td>\n",
       "      <td>3 Idiots</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    star_rating  duration                title\n",
       "50          8.5       155      Cinema Paradiso\n",
       "51          8.5       153       Apocalypse Now\n",
       "52          8.5       125   The Great Dictator\n",
       "53          8.5       130         The Prestige\n",
       "54          8.5       116   Back to the Future\n",
       "55          8.5        89        The Lion King\n",
       "56          8.5       137  The Lives of Others\n",
       "57          8.5       117                Alien\n",
       "58          8.5        88       Paths of Glory\n",
       "59          8.5       165     Django Unchained\n",
       "60          8.5       170             3 Idiots"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#df.loc[startind row index:ending row index,['column name 1','column name 2','column name 3']]\n",
    "#function is the same as iloc only working is different\n",
    "df.loc[50:60,['star_rating','duration','title']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "6f969a42",
   "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>name</th>\n",
       "      <th>marks</th>\n",
       "      <th>loc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>X</td>\n",
       "      <td>34</td>\n",
       "      <td>d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>y</td>\n",
       "      <td>23</td>\n",
       "      <td>k</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  name  marks loc\n",
       "0    X     34   d\n",
       "1    y     23   k"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1 = pd.DataFrame([['X',34,'d'],['y',23,'k']],columns = ['name','marks','loc'])\n",
    "df1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "f979faa9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "min        64.000000\n",
       "max       242.000000\n",
       "mean      120.979571\n",
       "median    117.000000\n",
       "Name: duration, dtype: float64"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# df.column_name.aggregate(['min','max','mean','median'])\n",
    "df.duration.aggregate(['min','max','mean','median'])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4e6dbeb2",
   "metadata": {},
   "source": [
    "## How to sort values in a dataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "534e3854",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>476</th>\n",
       "      <td>7.8</td>\n",
       "      <td>Hamlet</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Drama</td>\n",
       "      <td>242</td>\n",
       "      <td>[u'Kenneth Branagh', u'Julie Christie', u'Dere...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>157</th>\n",
       "      <td>8.2</td>\n",
       "      <td>Gone with the Wind</td>\n",
       "      <td>G</td>\n",
       "      <td>Drama</td>\n",
       "      <td>238</td>\n",
       "      <td>[u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78</th>\n",
       "      <td>8.4</td>\n",
       "      <td>Once Upon a Time in America</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>229</td>\n",
       "      <td>[u'Robert De Niro', u'James Woods', u'Elizabet...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>142</th>\n",
       "      <td>8.3</td>\n",
       "      <td>Lagaan: Once Upon a Time in India</td>\n",
       "      <td>PG</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>224</td>\n",
       "      <td>[u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>445</th>\n",
       "      <td>7.9</td>\n",
       "      <td>The Ten Commandments</td>\n",
       "      <td>APPROVED</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>220</td>\n",
       "      <td>[u'Charlton Heston', u'Yul Brynner', u'Anne Ba...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>293</th>\n",
       "      <td>8.1</td>\n",
       "      <td>Duck Soup</td>\n",
       "      <td>PASSED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Groucho Marx', u'Harpo Marx', u'Chico Marx']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>88</th>\n",
       "      <td>8.4</td>\n",
       "      <td>The Kid</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Charles Chaplin', u'Edna Purviance', u'Jack...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>258</th>\n",
       "      <td>8.1</td>\n",
       "      <td>The Cabinet of Dr. Caligari</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Crime</td>\n",
       "      <td>67</td>\n",
       "      <td>[u'Werner Krauss', u'Conrad Veidt', u'Friedric...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>338</th>\n",
       "      <td>8.0</td>\n",
       "      <td>Battleship Potemkin</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>History</td>\n",
       "      <td>66</td>\n",
       "      <td>[u'Aleksandr Antonov', u'Vladimir Barsky', u'G...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>389</th>\n",
       "      <td>8.0</td>\n",
       "      <td>Freaks</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>64</td>\n",
       "      <td>[u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>979 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating                              title content_rating      genre  \\\n",
       "476          7.8                             Hamlet          PG-13      Drama   \n",
       "157          8.2                 Gone with the Wind              G      Drama   \n",
       "78           8.4        Once Upon a Time in America              R      Crime   \n",
       "142          8.3  Lagaan: Once Upon a Time in India             PG  Adventure   \n",
       "445          7.9               The Ten Commandments       APPROVED  Adventure   \n",
       "..           ...                                ...            ...        ...   \n",
       "293          8.1                          Duck Soup         PASSED     Comedy   \n",
       "88           8.4                            The Kid      NOT RATED     Comedy   \n",
       "258          8.1        The Cabinet of Dr. Caligari        UNRATED      Crime   \n",
       "338          8.0                Battleship Potemkin        UNRATED    History   \n",
       "389          8.0                             Freaks        UNRATED      Drama   \n",
       "\n",
       "     duration                                        actors_list  \n",
       "476       242  [u'Kenneth Branagh', u'Julie Christie', u'Dere...  \n",
       "157       238  [u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...  \n",
       "78        229  [u'Robert De Niro', u'James Woods', u'Elizabet...  \n",
       "142       224  [u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...  \n",
       "445       220  [u'Charlton Heston', u'Yul Brynner', u'Anne Ba...  \n",
       "..        ...                                                ...  \n",
       "293        68    [u'Groucho Marx', u'Harpo Marx', u'Chico Marx']  \n",
       "88         68  [u'Charles Chaplin', u'Edna Purviance', u'Jack...  \n",
       "258        67  [u'Werner Krauss', u'Conrad Veidt', u'Friedric...  \n",
       "338        66  [u'Aleksandr Antonov', u'Vladimir Barsky', u'G...  \n",
       "389        64  [u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...  \n",
       "\n",
       "[979 rows x 6 columns]"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#df.sort_values('column_name',ascending = False)\n",
    "#ascending = True sorting in ascending order ,ascending = False then sorting is in Descending order\n",
    "df4 = df.sort_values('duration',ascending = False) #inplace is not given so df will be unchanged\n",
    "df4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "e4bde09d",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>389</th>\n",
       "      <td>8.0</td>\n",
       "      <td>Freaks</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>64</td>\n",
       "      <td>[u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>338</th>\n",
       "      <td>8.0</td>\n",
       "      <td>Battleship Potemkin</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>History</td>\n",
       "      <td>66</td>\n",
       "      <td>[u'Aleksandr Antonov', u'Vladimir Barsky', u'G...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>258</th>\n",
       "      <td>8.1</td>\n",
       "      <td>The Cabinet of Dr. Caligari</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Crime</td>\n",
       "      <td>67</td>\n",
       "      <td>[u'Werner Krauss', u'Conrad Veidt', u'Friedric...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>293</th>\n",
       "      <td>8.1</td>\n",
       "      <td>Duck Soup</td>\n",
       "      <td>PASSED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Groucho Marx', u'Harpo Marx', u'Chico Marx']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>88</th>\n",
       "      <td>8.4</td>\n",
       "      <td>The Kid</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Charles Chaplin', u'Edna Purviance', u'Jack...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>445</th>\n",
       "      <td>7.9</td>\n",
       "      <td>The Ten Commandments</td>\n",
       "      <td>APPROVED</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>220</td>\n",
       "      <td>[u'Charlton Heston', u'Yul Brynner', u'Anne Ba...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>142</th>\n",
       "      <td>8.3</td>\n",
       "      <td>Lagaan: Once Upon a Time in India</td>\n",
       "      <td>PG</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>224</td>\n",
       "      <td>[u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78</th>\n",
       "      <td>8.4</td>\n",
       "      <td>Once Upon a Time in America</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>229</td>\n",
       "      <td>[u'Robert De Niro', u'James Woods', u'Elizabet...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>157</th>\n",
       "      <td>8.2</td>\n",
       "      <td>Gone with the Wind</td>\n",
       "      <td>G</td>\n",
       "      <td>Drama</td>\n",
       "      <td>238</td>\n",
       "      <td>[u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>476</th>\n",
       "      <td>7.8</td>\n",
       "      <td>Hamlet</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Drama</td>\n",
       "      <td>242</td>\n",
       "      <td>[u'Kenneth Branagh', u'Julie Christie', u'Dere...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>979 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating                              title content_rating      genre  \\\n",
       "389          8.0                             Freaks        UNRATED      Drama   \n",
       "338          8.0                Battleship Potemkin        UNRATED    History   \n",
       "258          8.1        The Cabinet of Dr. Caligari        UNRATED      Crime   \n",
       "293          8.1                          Duck Soup         PASSED     Comedy   \n",
       "88           8.4                            The Kid      NOT RATED     Comedy   \n",
       "..           ...                                ...            ...        ...   \n",
       "445          7.9               The Ten Commandments       APPROVED  Adventure   \n",
       "142          8.3  Lagaan: Once Upon a Time in India             PG  Adventure   \n",
       "78           8.4        Once Upon a Time in America              R      Crime   \n",
       "157          8.2                 Gone with the Wind              G      Drama   \n",
       "476          7.8                             Hamlet          PG-13      Drama   \n",
       "\n",
       "     duration                                        actors_list  \n",
       "389        64  [u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...  \n",
       "338        66  [u'Aleksandr Antonov', u'Vladimir Barsky', u'G...  \n",
       "258        67  [u'Werner Krauss', u'Conrad Veidt', u'Friedric...  \n",
       "293        68    [u'Groucho Marx', u'Harpo Marx', u'Chico Marx']  \n",
       "88         68  [u'Charles Chaplin', u'Edna Purviance', u'Jack...  \n",
       "..        ...                                                ...  \n",
       "445       220  [u'Charlton Heston', u'Yul Brynner', u'Anne Ba...  \n",
       "142       224  [u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...  \n",
       "78        229  [u'Robert De Niro', u'James Woods', u'Elizabet...  \n",
       "157       238  [u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...  \n",
       "476       242  [u'Kenneth Branagh', u'Julie Christie', u'Dere...  \n",
       "\n",
       "[979 rows x 6 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.sort_values('duration',ascending = True, inplace = True) #this will save the changes in the df dataframe\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1a1e2cf0",
   "metadata": {},
   "source": [
    "## How to change the indexing of the dataframe after sorting the elements in the dataframe in ascending or descending order"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "3f1a9b86",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.0</td>\n",
       "      <td>Freaks</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>64</td>\n",
       "      <td>[u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.0</td>\n",
       "      <td>Battleship Potemkin</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>History</td>\n",
       "      <td>66</td>\n",
       "      <td>[u'Aleksandr Antonov', u'Vladimir Barsky', u'G...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.1</td>\n",
       "      <td>The Cabinet of Dr. Caligari</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Crime</td>\n",
       "      <td>67</td>\n",
       "      <td>[u'Werner Krauss', u'Conrad Veidt', u'Friedric...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8.1</td>\n",
       "      <td>Duck Soup</td>\n",
       "      <td>PASSED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Groucho Marx', u'Harpo Marx', u'Chico Marx']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.4</td>\n",
       "      <td>The Kid</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Charles Chaplin', u'Edna Purviance', u'Jack...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>974</th>\n",
       "      <td>7.9</td>\n",
       "      <td>The Ten Commandments</td>\n",
       "      <td>APPROVED</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>220</td>\n",
       "      <td>[u'Charlton Heston', u'Yul Brynner', u'Anne Ba...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>975</th>\n",
       "      <td>8.3</td>\n",
       "      <td>Lagaan: Once Upon a Time in India</td>\n",
       "      <td>PG</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>224</td>\n",
       "      <td>[u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>976</th>\n",
       "      <td>8.4</td>\n",
       "      <td>Once Upon a Time in America</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>229</td>\n",
       "      <td>[u'Robert De Niro', u'James Woods', u'Elizabet...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>977</th>\n",
       "      <td>8.2</td>\n",
       "      <td>Gone with the Wind</td>\n",
       "      <td>G</td>\n",
       "      <td>Drama</td>\n",
       "      <td>238</td>\n",
       "      <td>[u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>978</th>\n",
       "      <td>7.8</td>\n",
       "      <td>Hamlet</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Drama</td>\n",
       "      <td>242</td>\n",
       "      <td>[u'Kenneth Branagh', u'Julie Christie', u'Dere...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>979 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating                              title content_rating      genre  \\\n",
       "0            8.0                             Freaks        UNRATED      Drama   \n",
       "1            8.0                Battleship Potemkin        UNRATED    History   \n",
       "2            8.1        The Cabinet of Dr. Caligari        UNRATED      Crime   \n",
       "3            8.1                          Duck Soup         PASSED     Comedy   \n",
       "4            8.4                            The Kid      NOT RATED     Comedy   \n",
       "..           ...                                ...            ...        ...   \n",
       "974          7.9               The Ten Commandments       APPROVED  Adventure   \n",
       "975          8.3  Lagaan: Once Upon a Time in India             PG  Adventure   \n",
       "976          8.4        Once Upon a Time in America              R      Crime   \n",
       "977          8.2                 Gone with the Wind              G      Drama   \n",
       "978          7.8                             Hamlet          PG-13      Drama   \n",
       "\n",
       "     duration                                        actors_list  \n",
       "0          64  [u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...  \n",
       "1          66  [u'Aleksandr Antonov', u'Vladimir Barsky', u'G...  \n",
       "2          67  [u'Werner Krauss', u'Conrad Veidt', u'Friedric...  \n",
       "3          68    [u'Groucho Marx', u'Harpo Marx', u'Chico Marx']  \n",
       "4          68  [u'Charles Chaplin', u'Edna Purviance', u'Jack...  \n",
       "..        ...                                                ...  \n",
       "974       220  [u'Charlton Heston', u'Yul Brynner', u'Anne Ba...  \n",
       "975       224  [u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...  \n",
       "976       229  [u'Robert De Niro', u'James Woods', u'Elizabet...  \n",
       "977       238  [u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...  \n",
       "978       242  [u'Kenneth Branagh', u'Julie Christie', u'Dere...  \n",
       "\n",
       "[979 rows x 6 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.reset_index(drop=True,inplace=True)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "e6684421",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['title'] = df.title.str.upper() #this will change all the strings in title column in upper case"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "fce577fa",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.0</td>\n",
       "      <td>FREAKS</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>64</td>\n",
       "      <td>[u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.0</td>\n",
       "      <td>BATTLESHIP POTEMKIN</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>History</td>\n",
       "      <td>66</td>\n",
       "      <td>[u'Aleksandr Antonov', u'Vladimir Barsky', u'G...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.1</td>\n",
       "      <td>THE CABINET OF DR. CALIGARI</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Crime</td>\n",
       "      <td>67</td>\n",
       "      <td>[u'Werner Krauss', u'Conrad Veidt', u'Friedric...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8.1</td>\n",
       "      <td>DUCK SOUP</td>\n",
       "      <td>PASSED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Groucho Marx', u'Harpo Marx', u'Chico Marx']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.4</td>\n",
       "      <td>THE KID</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Charles Chaplin', u'Edna Purviance', u'Jack...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   star_rating                        title content_rating    genre  duration  \\\n",
       "0          8.0                       FREAKS        UNRATED    Drama        64   \n",
       "1          8.0          BATTLESHIP POTEMKIN        UNRATED  History        66   \n",
       "2          8.1  THE CABINET OF DR. CALIGARI        UNRATED    Crime        67   \n",
       "3          8.1                    DUCK SOUP         PASSED   Comedy        68   \n",
       "4          8.4                      THE KID      NOT RATED   Comedy        68   \n",
       "\n",
       "                                         actors_list  \n",
       "0  [u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...  \n",
       "1  [u'Aleksandr Antonov', u'Vladimir Barsky', u'G...  \n",
       "2  [u'Werner Krauss', u'Conrad Veidt', u'Friedric...  \n",
       "3    [u'Groucho Marx', u'Harpo Marx', u'Chico Marx']  \n",
       "4  [u'Charles Chaplin', u'Edna Purviance', u'Jack...  "
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bbffa265",
   "metadata": {},
   "source": [
    "## Searching contents in title"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "eaff4d66",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>7.6</td>\n",
       "      <td>ARMY OF DARKNESS</td>\n",
       "      <td>R</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>81</td>\n",
       "      <td>[u'Bruce Campbell', u'Embeth Davidtz', u'Marcu...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>198</th>\n",
       "      <td>7.8</td>\n",
       "      <td>DARK CITY</td>\n",
       "      <td>R</td>\n",
       "      <td>Mystery</td>\n",
       "      <td>100</td>\n",
       "      <td>[u'Rufus Sewell', u'Kiefer Sutherland', u'Jenn...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>426</th>\n",
       "      <td>8.1</td>\n",
       "      <td>DONNIE DARKO</td>\n",
       "      <td>R</td>\n",
       "      <td>Drama</td>\n",
       "      <td>113</td>\n",
       "      <td>[u'Jake Gyllenhaal', u'Jena Malone', u'Mary Mc...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>717</th>\n",
       "      <td>7.8</td>\n",
       "      <td>STAR TREK INTO DARKNESS</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Action</td>\n",
       "      <td>132</td>\n",
       "      <td>[u'Chris Pine', u'Zachary Quinto', u'Zoe Salda...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>792</th>\n",
       "      <td>8.0</td>\n",
       "      <td>DANCER IN THE DARK</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>140</td>\n",
       "      <td>[u'Bj\\xf6rk', u'Catherine Deneuve', u'David Mo...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>860</th>\n",
       "      <td>9.0</td>\n",
       "      <td>THE DARK KNIGHT</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Action</td>\n",
       "      <td>152</td>\n",
       "      <td>[u'Christian Bale', u'Heath Ledger', u'Aaron E...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>7.4</td>\n",
       "      <td>ZERO DARK THIRTY</td>\n",
       "      <td>R</td>\n",
       "      <td>Drama</td>\n",
       "      <td>157</td>\n",
       "      <td>[u'Jessica Chastain', u'Joel Edgerton', u'Chri...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>910</th>\n",
       "      <td>8.5</td>\n",
       "      <td>THE DARK KNIGHT RISES</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Action</td>\n",
       "      <td>165</td>\n",
       "      <td>[u'Christian Bale', u'Tom Hardy', u'Anne Hatha...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating                    title content_rating    genre  duration  \\\n",
       "22           7.6         ARMY OF DARKNESS              R   Comedy        81   \n",
       "198          7.8                DARK CITY              R  Mystery       100   \n",
       "426          8.1             DONNIE DARKO              R    Drama       113   \n",
       "717          7.8  STAR TREK INTO DARKNESS          PG-13   Action       132   \n",
       "792          8.0       DANCER IN THE DARK              R    Crime       140   \n",
       "860          9.0          THE DARK KNIGHT          PG-13   Action       152   \n",
       "888          7.4         ZERO DARK THIRTY              R    Drama       157   \n",
       "910          8.5    THE DARK KNIGHT RISES          PG-13   Action       165   \n",
       "\n",
       "                                           actors_list  \n",
       "22   [u'Bruce Campbell', u'Embeth Davidtz', u'Marcu...  \n",
       "198  [u'Rufus Sewell', u'Kiefer Sutherland', u'Jenn...  \n",
       "426  [u'Jake Gyllenhaal', u'Jena Malone', u'Mary Mc...  \n",
       "717  [u'Chris Pine', u'Zachary Quinto', u'Zoe Salda...  \n",
       "792  [u'Bj\\xf6rk', u'Catherine Deneuve', u'David Mo...  \n",
       "860  [u'Christian Bale', u'Heath Ledger', u'Aaron E...  \n",
       "888  [u'Jessica Chastain', u'Joel Edgerton', u'Chri...  \n",
       "910  [u'Christian Bale', u'Tom Hardy', u'Anne Hatha...  "
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.title.str.contains('dark',case=False)] #this will find all the strings in title column which contains the dark word"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "ceed57c2",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>144</th>\n",
       "      <td>8.9</td>\n",
       "      <td>12 ANGRY MEN</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>96</td>\n",
       "      <td>[u'Henry Fonda', u'Lee J. Cobb', u'Martin Bals...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating         title content_rating  genre  duration  \\\n",
       "144          8.9  12 ANGRY MEN      NOT RATED  Drama        96   \n",
       "\n",
       "                                           actors_list  \n",
       "144  [u'Henry Fonda', u'Lee J. Cobb', u'Martin Bals...  "
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.iloc[[df[(df.genre=='Drama')].star_rating.idxmax()]] #idxmax return the index of the maximum value  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "5dd13cf7",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>883</th>\n",
       "      <td>8.4</td>\n",
       "      <td>RANG DE BASANTI</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>157</td>\n",
       "      <td>[u'Aamir Khan', u'Soha Ali Khan', u'Siddharth']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>912</th>\n",
       "      <td>8.5</td>\n",
       "      <td>TAARE ZAMEEN PAR</td>\n",
       "      <td>PG</td>\n",
       "      <td>Drama</td>\n",
       "      <td>165</td>\n",
       "      <td>[u'Darsheel Safary', u'Aamir Khan', u'Tanay Ch...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>929</th>\n",
       "      <td>8.5</td>\n",
       "      <td>3 IDIOTS</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>170</td>\n",
       "      <td>[u'Aamir Khan', u'Madhavan', u'Mona Singh']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>951</th>\n",
       "      <td>8.3</td>\n",
       "      <td>DIL CHAHTA HAI</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>183</td>\n",
       "      <td>[u'Aamir Khan', u'Saif Ali Khan', u'Akshaye Kh...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>975</th>\n",
       "      <td>8.3</td>\n",
       "      <td>LAGAAN: ONCE UPON A TIME IN INDIA</td>\n",
       "      <td>PG</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>224</td>\n",
       "      <td>[u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating                              title content_rating      genre  \\\n",
       "883          8.4                    RANG DE BASANTI      NOT RATED      Drama   \n",
       "912          8.5                   TAARE ZAMEEN PAR             PG      Drama   \n",
       "929          8.5                           3 IDIOTS          PG-13     Comedy   \n",
       "951          8.3                     DIL CHAHTA HAI      NOT RATED     Comedy   \n",
       "975          8.3  LAGAAN: ONCE UPON A TIME IN INDIA             PG  Adventure   \n",
       "\n",
       "     duration                                        actors_list  \n",
       "883       157    [u'Aamir Khan', u'Soha Ali Khan', u'Siddharth']  \n",
       "912       165  [u'Darsheel Safary', u'Aamir Khan', u'Tanay Ch...  \n",
       "929       170        [u'Aamir Khan', u'Madhavan', u'Mona Singh']  \n",
       "951       183  [u'Aamir Khan', u'Saif Ali Khan', u'Akshaye Kh...  \n",
       "975       224  [u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...  "
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.actors_list.str.contains('amir khan', case = False)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "b6bb2d5a",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['title'] = df.title.apply(str.lower)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "42424812",
   "metadata": {},
   "source": [
    "## how to save dataframe to csv file "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "29492be6",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_csv('updated_data.csv',index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8618b37c",
   "metadata": {},
   "source": [
    "## display all unique values in a dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "29e62e08",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Drama', 'History', 'Crime', 'Comedy', 'Mystery', 'Horror',\n",
       "       'Animation', 'Action', 'Biography', 'Western', 'Film-Noir',\n",
       "       'Adventure', 'Sci-Fi', 'Family', 'Thriller', 'Fantasy'],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.genre.unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e322c50f",
   "metadata": {},
   "source": [
    " ## how to drop a column or a row"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "e3925805",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "150c88a5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 1, 1, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1,\n",
       "       0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0,\n",
       "       1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 0, 0,\n",
       "       1, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 0, 0, 0,\n",
       "       1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1,\n",
       "       0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 1, 1, 1,\n",
       "       1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 0,\n",
       "       1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0,\n",
       "       0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,\n",
       "       0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0,\n",
       "       0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0,\n",
       "       1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1,\n",
       "       1, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0,\n",
       "       0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0,\n",
       "       0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1,\n",
       "       1, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0,\n",
       "       1, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1,\n",
       "       0, 0, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 1,\n",
       "       1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0,\n",
       "       1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1,\n",
       "       0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1,\n",
       "       1, 0, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1,\n",
       "       0, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0,\n",
       "       1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 1,\n",
       "       0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0,\n",
       "       0, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0,\n",
       "       1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0,\n",
       "       0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1,\n",
       "       0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 1,\n",
       "       0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0,\n",
       "       0, 0, 0, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 1,\n",
       "       0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0,\n",
       "       1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1,\n",
       "       1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1,\n",
       "       1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0,\n",
       "       0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1,\n",
       "       0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 1, 0,\n",
       "       1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 1, 1, 1,\n",
       "       1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1, 1, 0,\n",
       "       0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0,\n",
       "       1, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1,\n",
       "       0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 0,\n",
       "       1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0,\n",
       "       1, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0,\n",
       "       1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0])"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result = np.random.randint(0,2,979)\n",
    "result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "a78bb610",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['review'] = result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "b2ede598",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "      <th>review</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.0</td>\n",
       "      <td>freaks</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>64</td>\n",
       "      <td>[u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.0</td>\n",
       "      <td>battleship potemkin</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>History</td>\n",
       "      <td>66</td>\n",
       "      <td>[u'Aleksandr Antonov', u'Vladimir Barsky', u'G...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.1</td>\n",
       "      <td>the cabinet of dr. caligari</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Crime</td>\n",
       "      <td>67</td>\n",
       "      <td>[u'Werner Krauss', u'Conrad Veidt', u'Friedric...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8.1</td>\n",
       "      <td>duck soup</td>\n",
       "      <td>PASSED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Groucho Marx', u'Harpo Marx', u'Chico Marx']</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.4</td>\n",
       "      <td>the kid</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Charles Chaplin', u'Edna Purviance', u'Jack...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   star_rating                        title content_rating    genre  duration  \\\n",
       "0          8.0                       freaks        UNRATED    Drama        64   \n",
       "1          8.0          battleship potemkin        UNRATED  History        66   \n",
       "2          8.1  the cabinet of dr. caligari        UNRATED    Crime        67   \n",
       "3          8.1                    duck soup         PASSED   Comedy        68   \n",
       "4          8.4                      the kid      NOT RATED   Comedy        68   \n",
       "\n",
       "                                         actors_list  review  \n",
       "0  [u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...       0  \n",
       "1  [u'Aleksandr Antonov', u'Vladimir Barsky', u'G...       0  \n",
       "2  [u'Werner Krauss', u'Conrad Veidt', u'Friedric...       1  \n",
       "3    [u'Groucho Marx', u'Harpo Marx', u'Chico Marx']       1  \n",
       "4  [u'Charles Chaplin', u'Edna Purviance', u'Jack...       1  "
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "762066fa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    507\n",
       "1    472\n",
       "Name: review, dtype: int64"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.review.value_counts() #this will tell the unique values along with their number of occurances in a particular column"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c8b20115",
   "metadata": {},
   "source": [
    "## How to delete a column in the dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "a3a01bd3",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.0</td>\n",
       "      <td>freaks</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>64</td>\n",
       "      <td>[u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.0</td>\n",
       "      <td>battleship potemkin</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>History</td>\n",
       "      <td>66</td>\n",
       "      <td>[u'Aleksandr Antonov', u'Vladimir Barsky', u'G...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.1</td>\n",
       "      <td>the cabinet of dr. caligari</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Crime</td>\n",
       "      <td>67</td>\n",
       "      <td>[u'Werner Krauss', u'Conrad Veidt', u'Friedric...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8.1</td>\n",
       "      <td>duck soup</td>\n",
       "      <td>PASSED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Groucho Marx', u'Harpo Marx', u'Chico Marx']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.4</td>\n",
       "      <td>the kid</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Charles Chaplin', u'Edna Purviance', u'Jack...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>974</th>\n",
       "      <td>7.9</td>\n",
       "      <td>the ten commandments</td>\n",
       "      <td>APPROVED</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>220</td>\n",
       "      <td>[u'Charlton Heston', u'Yul Brynner', u'Anne Ba...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>975</th>\n",
       "      <td>8.3</td>\n",
       "      <td>lagaan: once upon a time in india</td>\n",
       "      <td>PG</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>224</td>\n",
       "      <td>[u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>976</th>\n",
       "      <td>8.4</td>\n",
       "      <td>once upon a time in america</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>229</td>\n",
       "      <td>[u'Robert De Niro', u'James Woods', u'Elizabet...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>977</th>\n",
       "      <td>8.2</td>\n",
       "      <td>gone with the wind</td>\n",
       "      <td>G</td>\n",
       "      <td>Drama</td>\n",
       "      <td>238</td>\n",
       "      <td>[u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>978</th>\n",
       "      <td>7.8</td>\n",
       "      <td>hamlet</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Drama</td>\n",
       "      <td>242</td>\n",
       "      <td>[u'Kenneth Branagh', u'Julie Christie', u'Dere...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>979 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating                              title content_rating      genre  \\\n",
       "0            8.0                             freaks        UNRATED      Drama   \n",
       "1            8.0                battleship potemkin        UNRATED    History   \n",
       "2            8.1        the cabinet of dr. caligari        UNRATED      Crime   \n",
       "3            8.1                          duck soup         PASSED     Comedy   \n",
       "4            8.4                            the kid      NOT RATED     Comedy   \n",
       "..           ...                                ...            ...        ...   \n",
       "974          7.9               the ten commandments       APPROVED  Adventure   \n",
       "975          8.3  lagaan: once upon a time in india             PG  Adventure   \n",
       "976          8.4        once upon a time in america              R      Crime   \n",
       "977          8.2                 gone with the wind              G      Drama   \n",
       "978          7.8                             hamlet          PG-13      Drama   \n",
       "\n",
       "     duration                                        actors_list  \n",
       "0          64  [u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...  \n",
       "1          66  [u'Aleksandr Antonov', u'Vladimir Barsky', u'G...  \n",
       "2          67  [u'Werner Krauss', u'Conrad Veidt', u'Friedric...  \n",
       "3          68    [u'Groucho Marx', u'Harpo Marx', u'Chico Marx']  \n",
       "4          68  [u'Charles Chaplin', u'Edna Purviance', u'Jack...  \n",
       "..        ...                                                ...  \n",
       "974       220  [u'Charlton Heston', u'Yul Brynner', u'Anne Ba...  \n",
       "975       224  [u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...  \n",
       "976       229  [u'Robert De Niro', u'James Woods', u'Elizabet...  \n",
       "977       238  [u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...  \n",
       "978       242  [u'Kenneth Branagh', u'Julie Christie', u'Dere...  \n",
       "\n",
       "[979 rows x 6 columns]"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.drop('review', axis=1,inplace = True) # axis=1 means columns axis=0 means rows [Single column]\n",
    "#review = columne name\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "fac5a15c",
   "metadata": {},
   "outputs": [],
   "source": [
    "#df.drop(['title','duration'],axis=1,inplace = True) It will delete multiple columns from "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "330d8fbd",
   "metadata": {},
   "source": [
    "## How to delete a row in the DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "4c139d1f",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.0</td>\n",
       "      <td>freaks</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>64</td>\n",
       "      <td>[u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.0</td>\n",
       "      <td>battleship potemkin</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>History</td>\n",
       "      <td>66</td>\n",
       "      <td>[u'Aleksandr Antonov', u'Vladimir Barsky', u'G...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.1</td>\n",
       "      <td>the cabinet of dr. caligari</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Crime</td>\n",
       "      <td>67</td>\n",
       "      <td>[u'Werner Krauss', u'Conrad Veidt', u'Friedric...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8.1</td>\n",
       "      <td>duck soup</td>\n",
       "      <td>PASSED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Groucho Marx', u'Harpo Marx', u'Chico Marx']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.4</td>\n",
       "      <td>the kid</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Charles Chaplin', u'Edna Purviance', u'Jack...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>974</th>\n",
       "      <td>7.9</td>\n",
       "      <td>the ten commandments</td>\n",
       "      <td>APPROVED</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>220</td>\n",
       "      <td>[u'Charlton Heston', u'Yul Brynner', u'Anne Ba...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>975</th>\n",
       "      <td>8.3</td>\n",
       "      <td>lagaan: once upon a time in india</td>\n",
       "      <td>PG</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>224</td>\n",
       "      <td>[u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>976</th>\n",
       "      <td>8.4</td>\n",
       "      <td>once upon a time in america</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>229</td>\n",
       "      <td>[u'Robert De Niro', u'James Woods', u'Elizabet...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>977</th>\n",
       "      <td>8.2</td>\n",
       "      <td>gone with the wind</td>\n",
       "      <td>G</td>\n",
       "      <td>Drama</td>\n",
       "      <td>238</td>\n",
       "      <td>[u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>978</th>\n",
       "      <td>7.8</td>\n",
       "      <td>hamlet</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Drama</td>\n",
       "      <td>242</td>\n",
       "      <td>[u'Kenneth Branagh', u'Julie Christie', u'Dere...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>978 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating                              title content_rating      genre  \\\n",
       "0            8.0                             freaks        UNRATED      Drama   \n",
       "1            8.0                battleship potemkin        UNRATED    History   \n",
       "2            8.1        the cabinet of dr. caligari        UNRATED      Crime   \n",
       "3            8.1                          duck soup         PASSED     Comedy   \n",
       "4            8.4                            the kid      NOT RATED     Comedy   \n",
       "..           ...                                ...            ...        ...   \n",
       "974          7.9               the ten commandments       APPROVED  Adventure   \n",
       "975          8.3  lagaan: once upon a time in india             PG  Adventure   \n",
       "976          8.4        once upon a time in america              R      Crime   \n",
       "977          8.2                 gone with the wind              G      Drama   \n",
       "978          7.8                             hamlet          PG-13      Drama   \n",
       "\n",
       "     duration                                        actors_list  \n",
       "0          64  [u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...  \n",
       "1          66  [u'Aleksandr Antonov', u'Vladimir Barsky', u'G...  \n",
       "2          67  [u'Werner Krauss', u'Conrad Veidt', u'Friedric...  \n",
       "3          68    [u'Groucho Marx', u'Harpo Marx', u'Chico Marx']  \n",
       "4          68  [u'Charles Chaplin', u'Edna Purviance', u'Jack...  \n",
       "..        ...                                                ...  \n",
       "974       220  [u'Charlton Heston', u'Yul Brynner', u'Anne Ba...  \n",
       "975       224  [u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...  \n",
       "976       229  [u'Robert De Niro', u'James Woods', u'Elizabet...  \n",
       "977       238  [u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...  \n",
       "978       242  [u'Kenneth Branagh', u'Julie Christie', u'Dere...  \n",
       "\n",
       "[978 rows x 6 columns]"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.drop(5,axis=0) # for deleting single row in a dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "aea63e33",
   "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>star_rating</th>\n",
       "      <th>title</th>\n",
       "      <th>content_rating</th>\n",
       "      <th>genre</th>\n",
       "      <th>duration</th>\n",
       "      <th>actors_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.0</td>\n",
       "      <td>freaks</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Drama</td>\n",
       "      <td>64</td>\n",
       "      <td>[u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.0</td>\n",
       "      <td>battleship potemkin</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>History</td>\n",
       "      <td>66</td>\n",
       "      <td>[u'Aleksandr Antonov', u'Vladimir Barsky', u'G...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.1</td>\n",
       "      <td>the cabinet of dr. caligari</td>\n",
       "      <td>UNRATED</td>\n",
       "      <td>Crime</td>\n",
       "      <td>67</td>\n",
       "      <td>[u'Werner Krauss', u'Conrad Veidt', u'Friedric...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8.1</td>\n",
       "      <td>duck soup</td>\n",
       "      <td>PASSED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Groucho Marx', u'Harpo Marx', u'Chico Marx']</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.4</td>\n",
       "      <td>the kid</td>\n",
       "      <td>NOT RATED</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>68</td>\n",
       "      <td>[u'Charles Chaplin', u'Edna Purviance', u'Jack...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>974</th>\n",
       "      <td>7.9</td>\n",
       "      <td>the ten commandments</td>\n",
       "      <td>APPROVED</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>220</td>\n",
       "      <td>[u'Charlton Heston', u'Yul Brynner', u'Anne Ba...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>975</th>\n",
       "      <td>8.3</td>\n",
       "      <td>lagaan: once upon a time in india</td>\n",
       "      <td>PG</td>\n",
       "      <td>Adventure</td>\n",
       "      <td>224</td>\n",
       "      <td>[u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>976</th>\n",
       "      <td>8.4</td>\n",
       "      <td>once upon a time in america</td>\n",
       "      <td>R</td>\n",
       "      <td>Crime</td>\n",
       "      <td>229</td>\n",
       "      <td>[u'Robert De Niro', u'James Woods', u'Elizabet...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>977</th>\n",
       "      <td>8.2</td>\n",
       "      <td>gone with the wind</td>\n",
       "      <td>G</td>\n",
       "      <td>Drama</td>\n",
       "      <td>238</td>\n",
       "      <td>[u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>978</th>\n",
       "      <td>7.8</td>\n",
       "      <td>hamlet</td>\n",
       "      <td>PG-13</td>\n",
       "      <td>Drama</td>\n",
       "      <td>242</td>\n",
       "      <td>[u'Kenneth Branagh', u'Julie Christie', u'Dere...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>979 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     star_rating                              title content_rating      genre  \\\n",
       "0            8.0                             freaks        UNRATED      Drama   \n",
       "1            8.0                battleship potemkin        UNRATED    History   \n",
       "2            8.1        the cabinet of dr. caligari        UNRATED      Crime   \n",
       "3            8.1                          duck soup         PASSED     Comedy   \n",
       "4            8.4                            the kid      NOT RATED     Comedy   \n",
       "..           ...                                ...            ...        ...   \n",
       "974          7.9               the ten commandments       APPROVED  Adventure   \n",
       "975          8.3  lagaan: once upon a time in india             PG  Adventure   \n",
       "976          8.4        once upon a time in america              R      Crime   \n",
       "977          8.2                 gone with the wind              G      Drama   \n",
       "978          7.8                             hamlet          PG-13      Drama   \n",
       "\n",
       "     duration                                        actors_list  \n",
       "0          64  [u'Wallace Ford', u'Leila Hyams', u'Olga Bacla...  \n",
       "1          66  [u'Aleksandr Antonov', u'Vladimir Barsky', u'G...  \n",
       "2          67  [u'Werner Krauss', u'Conrad Veidt', u'Friedric...  \n",
       "3          68    [u'Groucho Marx', u'Harpo Marx', u'Chico Marx']  \n",
       "4          68  [u'Charles Chaplin', u'Edna Purviance', u'Jack...  \n",
       "..        ...                                                ...  \n",
       "974       220  [u'Charlton Heston', u'Yul Brynner', u'Anne Ba...  \n",
       "975       224  [u'Aamir Khan', u'Gracy Singh', u'Rachel Shell...  \n",
       "976       229  [u'Robert De Niro', u'James Woods', u'Elizabet...  \n",
       "977       238  [u'Clark Gable', u'Vivien Leigh', u'Thomas Mit...  \n",
       "978       242  [u'Kenneth Branagh', u'Julie Christie', u'Dere...  \n",
       "\n",
       "[979 rows x 6 columns]"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# for deleting multiple rows in a dataframe\n",
    "#df.drop([0,1,2,3],axis=0)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "6860fd3d",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('train.csv') #reading csv file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "a4f2811d",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Moran, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>18</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>Williams, Mr. Charles Eugene</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>244373</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>20</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Masselmani, Mrs. Fatima</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2649</td>\n",
       "      <td>7.2250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Emir, Mr. Farred Chehab</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2631</td>\n",
       "      <td>7.2250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>29</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>O'Dwyer, Miss. Ellen \"Nellie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330959</td>\n",
       "      <td>7.8792</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>859</th>\n",
       "      <td>860</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Razi, Mr. Raihed</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2629</td>\n",
       "      <td>7.2292</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>863</th>\n",
       "      <td>864</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Sage, Miss. Dorothy Edith \"Dolly\"</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8</td>\n",
       "      <td>2</td>\n",
       "      <td>CA. 2343</td>\n",
       "      <td>69.5500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>868</th>\n",
       "      <td>869</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>van Melkebeke, Mr. Philemon</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>345777</td>\n",
       "      <td>9.5000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>878</th>\n",
       "      <td>879</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Laleff, Mr. Kristo</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>349217</td>\n",
       "      <td>7.8958</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>W./C. 6607</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>177 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass                                      Name  \\\n",
       "5              6         0       3                          Moran, Mr. James   \n",
       "17            18         1       2              Williams, Mr. Charles Eugene   \n",
       "19            20         1       3                   Masselmani, Mrs. Fatima   \n",
       "26            27         0       3                   Emir, Mr. Farred Chehab   \n",
       "28            29         1       3             O'Dwyer, Miss. Ellen \"Nellie\"   \n",
       "..           ...       ...     ...                                       ...   \n",
       "859          860         0       3                          Razi, Mr. Raihed   \n",
       "863          864         0       3         Sage, Miss. Dorothy Edith \"Dolly\"   \n",
       "868          869         0       3               van Melkebeke, Mr. Philemon   \n",
       "878          879         0       3                        Laleff, Mr. Kristo   \n",
       "888          889         0       3  Johnston, Miss. Catherine Helen \"Carrie\"   \n",
       "\n",
       "        Sex  Age  SibSp  Parch      Ticket     Fare Cabin Embarked  \n",
       "5      male  NaN      0      0      330877   8.4583   NaN        Q  \n",
       "17     male  NaN      0      0      244373  13.0000   NaN        S  \n",
       "19   female  NaN      0      0        2649   7.2250   NaN        C  \n",
       "26     male  NaN      0      0        2631   7.2250   NaN        C  \n",
       "28   female  NaN      0      0      330959   7.8792   NaN        Q  \n",
       "..      ...  ...    ...    ...         ...      ...   ...      ...  \n",
       "859    male  NaN      0      0        2629   7.2292   NaN        C  \n",
       "863  female  NaN      8      2    CA. 2343  69.5500   NaN        S  \n",
       "868    male  NaN      0      0      345777   9.5000   NaN        S  \n",
       "878    male  NaN      0      0      349217   7.8958   NaN        S  \n",
       "888  female  NaN      1      2  W./C. 6607  23.4500   NaN        S  \n",
       "\n",
       "[177 rows x 12 columns]"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.Age.isnull()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "efe3a082",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PassengerId      0\n",
       "Survived         0\n",
       "Pclass           0\n",
       "Name             0\n",
       "Sex              0\n",
       "Age            177\n",
       "SibSp            0\n",
       "Parch            0\n",
       "Ticket           0\n",
       "Fare             0\n",
       "Cabin          687\n",
       "Embarked         2\n",
       "dtype: int64"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum() #this will tell the number of null value in each column of the dataframe"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "678fd484",
   "metadata": {},
   "source": [
    "## How to drop nan values in the dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "89cc3aef",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>McCarthy, Mr. Timothy J</td>\n",
       "      <td>male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>11</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Sandstrom, Miss. Marguerite Rut</td>\n",
       "      <td>female</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>PP 9549</td>\n",
       "      <td>16.7000</td>\n",
       "      <td>G6</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>12</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Bonnell, Miss. Elizabeth</td>\n",
       "      <td>female</td>\n",
       "      <td>58.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>113783</td>\n",
       "      <td>26.5500</td>\n",
       "      <td>C103</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>871</th>\n",
       "      <td>872</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Beckwith, Mrs. Richard Leonard (Sallie Monypeny)</td>\n",
       "      <td>female</td>\n",
       "      <td>47.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>11751</td>\n",
       "      <td>52.5542</td>\n",
       "      <td>D35</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>872</th>\n",
       "      <td>873</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Carlsson, Mr. Frans Olof</td>\n",
       "      <td>male</td>\n",
       "      <td>33.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>695</td>\n",
       "      <td>5.0000</td>\n",
       "      <td>B51 B53 B55</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>879</th>\n",
       "      <td>880</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)</td>\n",
       "      <td>female</td>\n",
       "      <td>56.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>11767</td>\n",
       "      <td>83.1583</td>\n",
       "      <td>C50</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>112053</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>B42</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>111369</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>C148</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>183 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass  \\\n",
       "1              2         1       1   \n",
       "3              4         1       1   \n",
       "6              7         0       1   \n",
       "10            11         1       3   \n",
       "11            12         1       1   \n",
       "..           ...       ...     ...   \n",
       "871          872         1       1   \n",
       "872          873         0       1   \n",
       "879          880         1       1   \n",
       "887          888         1       1   \n",
       "889          890         1       1   \n",
       "\n",
       "                                                  Name     Sex   Age  SibSp  \\\n",
       "1    Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "3         Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "6                              McCarthy, Mr. Timothy J    male  54.0      0   \n",
       "10                     Sandstrom, Miss. Marguerite Rut  female   4.0      1   \n",
       "11                            Bonnell, Miss. Elizabeth  female  58.0      0   \n",
       "..                                                 ...     ...   ...    ...   \n",
       "871   Beckwith, Mrs. Richard Leonard (Sallie Monypeny)  female  47.0      1   \n",
       "872                           Carlsson, Mr. Frans Olof    male  33.0      0   \n",
       "879      Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)  female  56.0      0   \n",
       "887                       Graham, Miss. Margaret Edith  female  19.0      0   \n",
       "889                              Behr, Mr. Karl Howell    male  26.0      0   \n",
       "\n",
       "     Parch    Ticket     Fare        Cabin Embarked  \n",
       "1        0  PC 17599  71.2833          C85        C  \n",
       "3        0    113803  53.1000         C123        S  \n",
       "6        0     17463  51.8625          E46        S  \n",
       "10       1   PP 9549  16.7000           G6        S  \n",
       "11       0    113783  26.5500         C103        S  \n",
       "..     ...       ...      ...          ...      ...  \n",
       "871      1     11751  52.5542          D35        S  \n",
       "872      0       695   5.0000  B51 B53 B55        S  \n",
       "879      1     11767  83.1583          C50        C  \n",
       "887      0    112053  30.0000          B42        S  \n",
       "889      0    111369  30.0000         C148        C  \n",
       "\n",
       "[183 rows x 12 columns]"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dropna() #this will drop rows where the values are missing\n",
    "#here you have 2 options how='any' 'any' -> will drop the row if even one value is missing in a row\n",
    "#how='all' 'all' -> will drop the row if  and only if all the values in the row is null (all value of row is null)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "aaf137c5",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Montvila, Rev. Juozas</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>211536</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>112053</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>B42</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>W./C. 6607</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>111369</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>C148</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Dooley, Mr. Patrick</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>370376</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass  \\\n",
       "0              1         0       3   \n",
       "1              2         1       1   \n",
       "2              3         1       3   \n",
       "3              4         1       1   \n",
       "4              5         0       3   \n",
       "..           ...       ...     ...   \n",
       "886          887         0       2   \n",
       "887          888         1       1   \n",
       "888          889         0       3   \n",
       "889          890         1       1   \n",
       "890          891         0       3   \n",
       "\n",
       "                                                  Name     Sex   Age  SibSp  \\\n",
       "0                              Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1    Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                               Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3         Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                             Allen, Mr. William Henry    male  35.0      0   \n",
       "..                                                 ...     ...   ...    ...   \n",
       "886                              Montvila, Rev. Juozas    male  27.0      0   \n",
       "887                       Graham, Miss. Margaret Edith  female  19.0      0   \n",
       "888           Johnston, Miss. Catherine Helen \"Carrie\"  female   NaN      1   \n",
       "889                              Behr, Mr. Karl Howell    male  26.0      0   \n",
       "890                                Dooley, Mr. Patrick    male  32.0      0   \n",
       "\n",
       "     Parch            Ticket     Fare Cabin Embarked  \n",
       "0        0         A/5 21171   7.2500   NaN        S  \n",
       "1        0          PC 17599  71.2833   C85        C  \n",
       "2        0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "3        0            113803  53.1000  C123        S  \n",
       "4        0            373450   8.0500   NaN        S  \n",
       "..     ...               ...      ...   ...      ...  \n",
       "886      0            211536  13.0000   NaN        S  \n",
       "887      0            112053  30.0000   B42        S  \n",
       "888      2        W./C. 6607  23.4500   NaN        S  \n",
       "889      0            111369  30.0000  C148        C  \n",
       "890      0            370376   7.7500   NaN        Q  \n",
       "\n",
       "[891 rows x 12 columns]"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "79b7395e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PassengerId      0\n",
       "Survived         0\n",
       "Pclass           0\n",
       "Name             0\n",
       "Sex              0\n",
       "Age            177\n",
       "SibSp            0\n",
       "Parch            0\n",
       "Ticket           0\n",
       "Fare             0\n",
       "Cabin          687\n",
       "Embarked         2\n",
       "dtype: int64"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum() #this will tell the number of null value in each column of the dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "d16162c9",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>McCarthy, Mr. Timothy J</td>\n",
       "      <td>male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>11</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Sandstrom, Miss. Marguerite Rut</td>\n",
       "      <td>female</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>PP 9549</td>\n",
       "      <td>16.7000</td>\n",
       "      <td>G6</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>12</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Bonnell, Miss. Elizabeth</td>\n",
       "      <td>female</td>\n",
       "      <td>58.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>113783</td>\n",
       "      <td>26.5500</td>\n",
       "      <td>C103</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>871</th>\n",
       "      <td>872</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Beckwith, Mrs. Richard Leonard (Sallie Monypeny)</td>\n",
       "      <td>female</td>\n",
       "      <td>47.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>11751</td>\n",
       "      <td>52.5542</td>\n",
       "      <td>D35</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>872</th>\n",
       "      <td>873</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Carlsson, Mr. Frans Olof</td>\n",
       "      <td>male</td>\n",
       "      <td>33.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>695</td>\n",
       "      <td>5.0000</td>\n",
       "      <td>B51 B53 B55</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>879</th>\n",
       "      <td>880</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)</td>\n",
       "      <td>female</td>\n",
       "      <td>56.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>11767</td>\n",
       "      <td>83.1583</td>\n",
       "      <td>C50</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>112053</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>B42</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>111369</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>C148</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>183 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass  \\\n",
       "1              2         1       1   \n",
       "3              4         1       1   \n",
       "6              7         0       1   \n",
       "10            11         1       3   \n",
       "11            12         1       1   \n",
       "..           ...       ...     ...   \n",
       "871          872         1       1   \n",
       "872          873         0       1   \n",
       "879          880         1       1   \n",
       "887          888         1       1   \n",
       "889          890         1       1   \n",
       "\n",
       "                                                  Name     Sex   Age  SibSp  \\\n",
       "1    Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "3         Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "6                              McCarthy, Mr. Timothy J    male  54.0      0   \n",
       "10                     Sandstrom, Miss. Marguerite Rut  female   4.0      1   \n",
       "11                            Bonnell, Miss. Elizabeth  female  58.0      0   \n",
       "..                                                 ...     ...   ...    ...   \n",
       "871   Beckwith, Mrs. Richard Leonard (Sallie Monypeny)  female  47.0      1   \n",
       "872                           Carlsson, Mr. Frans Olof    male  33.0      0   \n",
       "879      Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)  female  56.0      0   \n",
       "887                       Graham, Miss. Margaret Edith  female  19.0      0   \n",
       "889                              Behr, Mr. Karl Howell    male  26.0      0   \n",
       "\n",
       "     Parch    Ticket     Fare        Cabin Embarked  \n",
       "1        0  PC 17599  71.2833          C85        C  \n",
       "3        0    113803  53.1000         C123        S  \n",
       "6        0     17463  51.8625          E46        S  \n",
       "10       1   PP 9549  16.7000           G6        S  \n",
       "11       0    113783  26.5500         C103        S  \n",
       "..     ...       ...      ...          ...      ...  \n",
       "871      1     11751  52.5542          D35        S  \n",
       "872      0       695   5.0000  B51 B53 B55        S  \n",
       "879      1     11767  83.1583          C50        C  \n",
       "887      0    112053  30.0000          B42        S  \n",
       "889      0    111369  30.0000         C148        C  \n",
       "\n",
       "[183 rows x 12 columns]"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dropna(how='any')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "f7552628",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Montvila, Rev. Juozas</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>211536</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>112053</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>B42</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>W./C. 6607</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>111369</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>C148</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Dooley, Mr. Patrick</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>370376</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass  \\\n",
       "0              1         0       3   \n",
       "1              2         1       1   \n",
       "2              3         1       3   \n",
       "3              4         1       1   \n",
       "4              5         0       3   \n",
       "..           ...       ...     ...   \n",
       "886          887         0       2   \n",
       "887          888         1       1   \n",
       "888          889         0       3   \n",
       "889          890         1       1   \n",
       "890          891         0       3   \n",
       "\n",
       "                                                  Name     Sex   Age  SibSp  \\\n",
       "0                              Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1    Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                               Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3         Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                             Allen, Mr. William Henry    male  35.0      0   \n",
       "..                                                 ...     ...   ...    ...   \n",
       "886                              Montvila, Rev. Juozas    male  27.0      0   \n",
       "887                       Graham, Miss. Margaret Edith  female  19.0      0   \n",
       "888           Johnston, Miss. Catherine Helen \"Carrie\"  female   NaN      1   \n",
       "889                              Behr, Mr. Karl Howell    male  26.0      0   \n",
       "890                                Dooley, Mr. Patrick    male  32.0      0   \n",
       "\n",
       "     Parch            Ticket     Fare Cabin Embarked  \n",
       "0        0         A/5 21171   7.2500   NaN        S  \n",
       "1        0          PC 17599  71.2833   C85        C  \n",
       "2        0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "3        0            113803  53.1000  C123        S  \n",
       "4        0            373450   8.0500   NaN        S  \n",
       "..     ...               ...      ...   ...      ...  \n",
       "886      0            211536  13.0000   NaN        S  \n",
       "887      0            112053  30.0000   B42        S  \n",
       "888      2        W./C. 6607  23.4500   NaN        S  \n",
       "889      0            111369  30.0000  C148        C  \n",
       "890      0            370376   7.7500   NaN        Q  \n",
       "\n",
       "[891 rows x 12 columns]"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dropna(how='all')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "04283f80",
   "metadata": {},
   "source": [
    "## How to use aggregate to find min,max,mean,median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "b5e57412",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "min        0.420000\n",
       "max       80.000000\n",
       "mean      29.699118\n",
       "median    28.000000\n",
       "Name: Age, dtype: float64"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.Age.aggregate(['min','max','mean','median']) #You don't need to type aggregate you just use agg\n",
    "#Note :-> normally difference bvetween mean and median should be very small\n",
    "#Note -> if that is not the case then outlair elements are present in the dataframe\n",
    "# we should get rid of those elements otherwise our ML model will not train correctly"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "3e241ce2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Mode is used to replace null values in categorical column\n",
    "# Median is used to replace null values in numbers type column if mean is greater than median\n",
    "# if Median is greater than Mean then replace mean with all the null values in the columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "d24945fb",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Montvila, Rev. Juozas</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>211536</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>112053</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>B42</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>W./C. 6607</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>111369</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>C148</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Dooley, Mr. Patrick</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>370376</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass  \\\n",
       "0              1         0       3   \n",
       "1              2         1       1   \n",
       "2              3         1       3   \n",
       "3              4         1       1   \n",
       "4              5         0       3   \n",
       "..           ...       ...     ...   \n",
       "886          887         0       2   \n",
       "887          888         1       1   \n",
       "888          889         0       3   \n",
       "889          890         1       1   \n",
       "890          891         0       3   \n",
       "\n",
       "                                                  Name     Sex   Age  SibSp  \\\n",
       "0                              Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1    Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                               Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3         Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                             Allen, Mr. William Henry    male  35.0      0   \n",
       "..                                                 ...     ...   ...    ...   \n",
       "886                              Montvila, Rev. Juozas    male  27.0      0   \n",
       "887                       Graham, Miss. Margaret Edith  female  19.0      0   \n",
       "888           Johnston, Miss. Catherine Helen \"Carrie\"  female  28.0      1   \n",
       "889                              Behr, Mr. Karl Howell    male  26.0      0   \n",
       "890                                Dooley, Mr. Patrick    male  32.0      0   \n",
       "\n",
       "     Parch            Ticket     Fare Cabin Embarked  \n",
       "0        0         A/5 21171   7.2500   NaN        S  \n",
       "1        0          PC 17599  71.2833   C85        C  \n",
       "2        0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "3        0            113803  53.1000  C123        S  \n",
       "4        0            373450   8.0500   NaN        S  \n",
       "..     ...               ...      ...   ...      ...  \n",
       "886      0            211536  13.0000   NaN        S  \n",
       "887      0            112053  30.0000   B42        S  \n",
       "888      2        W./C. 6607  23.4500   NaN        S  \n",
       "889      0            111369  30.0000  C148        C  \n",
       "890      0            370376   7.7500   NaN        Q  \n",
       "\n",
       "[891 rows x 12 columns]"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.fillna({'Age':df.Age.median()},inplace=True) \n",
    "df\n",
    "#this will replace all the null values in Age column in the dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "ead42303",
   "metadata": {},
   "outputs": [],
   "source": [
    "#df.drop(\"Cabin\",axis=1,inplace=True) #deleting the entire cabin column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "1f8013aa",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Montvila, Rev. Juozas</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>211536</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>112053</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>B42</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>W./C. 6607</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>111369</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>C148</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Dooley, Mr. Patrick</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>370376</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass  \\\n",
       "0              1         0       3   \n",
       "1              2         1       1   \n",
       "2              3         1       3   \n",
       "3              4         1       1   \n",
       "4              5         0       3   \n",
       "..           ...       ...     ...   \n",
       "886          887         0       2   \n",
       "887          888         1       1   \n",
       "888          889         0       3   \n",
       "889          890         1       1   \n",
       "890          891         0       3   \n",
       "\n",
       "                                                  Name     Sex   Age  SibSp  \\\n",
       "0                              Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1    Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                               Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3         Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                             Allen, Mr. William Henry    male  35.0      0   \n",
       "..                                                 ...     ...   ...    ...   \n",
       "886                              Montvila, Rev. Juozas    male  27.0      0   \n",
       "887                       Graham, Miss. Margaret Edith  female  19.0      0   \n",
       "888           Johnston, Miss. Catherine Helen \"Carrie\"  female  28.0      1   \n",
       "889                              Behr, Mr. Karl Howell    male  26.0      0   \n",
       "890                                Dooley, Mr. Patrick    male  32.0      0   \n",
       "\n",
       "     Parch            Ticket     Fare Cabin Embarked  \n",
       "0        0         A/5 21171   7.2500   NaN        S  \n",
       "1        0          PC 17599  71.2833   C85        C  \n",
       "2        0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "3        0            113803  53.1000  C123        S  \n",
       "4        0            373450   8.0500   NaN        S  \n",
       "..     ...               ...      ...   ...      ...  \n",
       "886      0            211536  13.0000   NaN        S  \n",
       "887      0            112053  30.0000   B42        S  \n",
       "888      2        W./C. 6607  23.4500   NaN        S  \n",
       "889      0            111369  30.0000  C148        C  \n",
       "890      0            370376   7.7500   NaN        Q  \n",
       "\n",
       "[891 rows x 12 columns]"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "88d50d9e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "S    644\n",
       "C    168\n",
       "Q     77\n",
       "Name: Embarked, dtype: int64"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.Embarked.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "2d82b6f4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.frame.DataFrame"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x = df.Embarked.aggregate(['mode'])\n",
    "type(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "d0740a8c",
   "metadata": {},
   "outputs": [],
   "source": [
    "mode = x.values[0][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "6f9a16a4",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.fillna({'Embarked':mode},inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "d297b15c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "S    646\n",
       "C    168\n",
       "Q     77\n",
       "Name: Embarked, dtype: int64"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.Embarked.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "ff596400",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_copy = df.copy() #it ois used to copy the original df into another variable to make a copy of the original df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "89205850",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Montvila, Rev. Juozas</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>211536</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>112053</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>B42</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>W./C. 6607</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>111369</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>C148</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Dooley, Mr. Patrick</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>370376</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass  \\\n",
       "0              1         0       3   \n",
       "1              2         1       1   \n",
       "2              3         1       3   \n",
       "3              4         1       1   \n",
       "4              5         0       3   \n",
       "..           ...       ...     ...   \n",
       "886          887         0       2   \n",
       "887          888         1       1   \n",
       "888          889         0       3   \n",
       "889          890         1       1   \n",
       "890          891         0       3   \n",
       "\n",
       "                                                  Name     Sex   Age  SibSp  \\\n",
       "0                              Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1    Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                               Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3         Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                             Allen, Mr. William Henry    male  35.0      0   \n",
       "..                                                 ...     ...   ...    ...   \n",
       "886                              Montvila, Rev. Juozas    male  27.0      0   \n",
       "887                       Graham, Miss. Margaret Edith  female  19.0      0   \n",
       "888           Johnston, Miss. Catherine Helen \"Carrie\"  female  28.0      1   \n",
       "889                              Behr, Mr. Karl Howell    male  26.0      0   \n",
       "890                                Dooley, Mr. Patrick    male  32.0      0   \n",
       "\n",
       "     Parch            Ticket     Fare Cabin Embarked  \n",
       "0        0         A/5 21171   7.2500   NaN        S  \n",
       "1        0          PC 17599  71.2833   C85        C  \n",
       "2        0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "3        0            113803  53.1000  C123        S  \n",
       "4        0            373450   8.0500   NaN        S  \n",
       "..     ...               ...      ...   ...      ...  \n",
       "886      0            211536  13.0000   NaN        S  \n",
       "887      0            112053  30.0000   B42        S  \n",
       "888      2        W./C. 6607  23.4500   NaN        S  \n",
       "889      0            111369  30.0000  C148        C  \n",
       "890      0            370376   7.7500   NaN        Q  \n",
       "\n",
       "[891 rows x 12 columns]"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_copy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "2edd8ff8",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.0000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>23.4500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7500</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass   Age  SibSp  Parch     Fare\n",
       "0              1         0       3  22.0      1      0   7.2500\n",
       "1              2         1       1  38.0      1      0  71.2833\n",
       "2              3         1       3  26.0      0      0   7.9250\n",
       "3              4         1       1  35.0      1      0  53.1000\n",
       "4              5         0       3  35.0      0      0   8.0500\n",
       "..           ...       ...     ...   ...    ...    ...      ...\n",
       "886          887         0       2  27.0      0      0  13.0000\n",
       "887          888         1       1  19.0      0      0  30.0000\n",
       "888          889         0       3  28.0      1      2  23.4500\n",
       "889          890         1       1  26.0      0      0  30.0000\n",
       "890          891         0       3  32.0      0      0   7.7500\n",
       "\n",
       "[891 rows x 7 columns]"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_copy.select_dtypes(exclude=['object']) \n",
    "#it will exclude all the columns which contains object type dtype and print the rest of the columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "4998c1c4",
   "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>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>113803</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>373450</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>Montvila, Rev. Juozas</td>\n",
       "      <td>male</td>\n",
       "      <td>211536</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>112053</td>\n",
       "      <td>B42</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>W./C. 6607</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>111369</td>\n",
       "      <td>C148</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>Dooley, Mr. Patrick</td>\n",
       "      <td>male</td>\n",
       "      <td>370376</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                  Name     Sex  \\\n",
       "0                              Braund, Mr. Owen Harris    male   \n",
       "1    Cumings, Mrs. John Bradley (Florence Briggs Th...  female   \n",
       "2                               Heikkinen, Miss. Laina  female   \n",
       "3         Futrelle, Mrs. Jacques Heath (Lily May Peel)  female   \n",
       "4                             Allen, Mr. William Henry    male   \n",
       "..                                                 ...     ...   \n",
       "886                              Montvila, Rev. Juozas    male   \n",
       "887                       Graham, Miss. Margaret Edith  female   \n",
       "888           Johnston, Miss. Catherine Helen \"Carrie\"  female   \n",
       "889                              Behr, Mr. Karl Howell    male   \n",
       "890                                Dooley, Mr. Patrick    male   \n",
       "\n",
       "               Ticket Cabin Embarked  \n",
       "0           A/5 21171   NaN        S  \n",
       "1            PC 17599   C85        C  \n",
       "2    STON/O2. 3101282   NaN        S  \n",
       "3              113803  C123        S  \n",
       "4              373450   NaN        S  \n",
       "..                ...   ...      ...  \n",
       "886            211536   NaN        S  \n",
       "887            112053   B42        S  \n",
       "888        W./C. 6607   NaN        S  \n",
       "889            111369  C148        C  \n",
       "890            370376   NaN        Q  \n",
       "\n",
       "[891 rows x 5 columns]"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.select_dtypes(include=['object']) #it will only print the columns which have object dtype"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b4c586ed",
   "metadata": {},
   "source": [
    "## How to find question marks values in columns of a dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "6835f70d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# pd.read_csv('missing_data.txt', sep = ',', names=[columns names], na_values=['?'])\n",
    "#it will replace all the values ? with null in the dataframe\n",
    "\n",
    "#how to find ? in columns of dataframe\n",
    "#cols = df.select_dtypes(include=['object']) #select the object type columns in the dataframe\n",
    "# c = cols.columns #checking columns type\n",
    "# for k in c: \n",
    "#     count = df[df[k].isin(['?'])].shape[0] #calculate all the rows which has ? in them\n",
    "#     if count>0: #if count is greater than 0 then print\n",
    "#         print('{}:{}',format(k,count))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "300f91c5",
   "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>Name</th>\n",
       "      <th>Marks</th>\n",
       "      <th>Location</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Aditya</td>\n",
       "      <td>19</td>\n",
       "      <td>Lucknow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Aastha</td>\n",
       "      <td>20</td>\n",
       "      <td>Kanpur</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Tanay</td>\n",
       "      <td>17</td>\n",
       "      <td>?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Vikrant</td>\n",
       "      <td>25</td>\n",
       "      <td>?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Shivangi</td>\n",
       "      <td>22</td>\n",
       "      <td>Lakhimpur</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Shivani</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Ludhiana</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>NaN</td>\n",
       "      <td>21</td>\n",
       "      <td>Pune</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>?</td>\n",
       "      <td>12</td>\n",
       "      <td>?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>?</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Mumbai</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>NaN</td>\n",
       "      <td>?</td>\n",
       "      <td>Hydrabad</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Name Marks   Location\n",
       "0    Aditya    19    Lucknow\n",
       "1    Aastha    20     Kanpur\n",
       "2     Tanay    17          ?\n",
       "3   Vikrant    25          ?\n",
       "4  Shivangi    22  Lakhimpur\n",
       "5   Shivani   NaN   Ludhiana\n",
       "6       NaN    21       Pune\n",
       "7         ?    12          ?\n",
       "8         ?   NaN     Mumbai\n",
       "9       NaN     ?   Hydrabad"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#importing a csv file with txt extension into the \n",
    "df3 = pd.read_csv('marks.txt', sep = ',', names=['Name','Marks','Location'])\n",
    "df3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "b563bc2d",
   "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>Name</th>\n",
       "      <th>Marks</th>\n",
       "      <th>Location</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Aditya</td>\n",
       "      <td>19</td>\n",
       "      <td>Lucknow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Aastha</td>\n",
       "      <td>20</td>\n",
       "      <td>Kanpur</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Tanay</td>\n",
       "      <td>17</td>\n",
       "      <td>?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Vikrant</td>\n",
       "      <td>25</td>\n",
       "      <td>?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Shivangi</td>\n",
       "      <td>22</td>\n",
       "      <td>Lakhimpur</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Shivani</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Ludhiana</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>NaN</td>\n",
       "      <td>21</td>\n",
       "      <td>Pune</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>?</td>\n",
       "      <td>12</td>\n",
       "      <td>?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>?</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Mumbai</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>NaN</td>\n",
       "      <td>?</td>\n",
       "      <td>Hydrabad</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Name Marks   Location\n",
       "0    Aditya    19    Lucknow\n",
       "1    Aastha    20     Kanpur\n",
       "2     Tanay    17          ?\n",
       "3   Vikrant    25          ?\n",
       "4  Shivangi    22  Lakhimpur\n",
       "5   Shivani   NaN   Ludhiana\n",
       "6       NaN    21       Pune\n",
       "7         ?    12          ?\n",
       "8         ?   NaN     Mumbai\n",
       "9       NaN     ?   Hydrabad"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#finding the amount of times ? is present in the dataframe\n",
    "#how to find ? in columns of dataframe\n",
    "cols = df3.select_dtypes(include=['object']) #select the object type columns in the dataframe\n",
    "cols"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "a3132f4e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Name', 'Marks', 'Location'], dtype='object')"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "c = cols.columns #checking columns type\n",
    "c"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "fd1fa427",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Name:2\n",
      "Marks:1\n",
      "Location:3\n"
     ]
    }
   ],
   "source": [
    "for k in c: \n",
    "    count = df3[df3[k].isin(['?'])].shape[0] #calculate all the rows which has ? in them\n",
    "    if count>0: #if count is greater than 0 then print\n",
    "        print(f'{k}:{count}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "797b72e0",
   "metadata": {},
   "outputs": [],
   "source": [
    "df3 = pd.read_csv('marks.txt', sep = ',', names=['Name','Marks','Location'], na_values=['?'])\n",
    "#Now replacing all ? with a null in the entire dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "a3bf50fe",
   "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>Name</th>\n",
       "      <th>Marks</th>\n",
       "      <th>Location</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Aditya</td>\n",
       "      <td>19.0</td>\n",
       "      <td>Lucknow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Aastha</td>\n",
       "      <td>20.0</td>\n",
       "      <td>Kanpur</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Tanay</td>\n",
       "      <td>17.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Vikrant</td>\n",
       "      <td>25.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Shivangi</td>\n",
       "      <td>22.0</td>\n",
       "      <td>Lakhimpur</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Shivani</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Ludhiana</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>NaN</td>\n",
       "      <td>21.0</td>\n",
       "      <td>Pune</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>NaN</td>\n",
       "      <td>12.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Mumbai</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Hydrabad</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Name  Marks   Location\n",
       "0    Aditya   19.0    Lucknow\n",
       "1    Aastha   20.0     Kanpur\n",
       "2     Tanay   17.0        NaN\n",
       "3   Vikrant   25.0        NaN\n",
       "4  Shivangi   22.0  Lakhimpur\n",
       "5   Shivani    NaN   Ludhiana\n",
       "6       NaN   21.0       Pune\n",
       "7       NaN   12.0        NaN\n",
       "8       NaN    NaN     Mumbai\n",
       "9       NaN    NaN   Hydrabad"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b1f9010f",
   "metadata": {},
   "source": [
    "## How to convert categorical coulmns into numeric columns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "25f3d56e",
   "metadata": {},
   "source": [
    "### Nominal categorical column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "8ef404c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# There is no mathematical order or relationships between values in the categories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "81c87f91",
   "metadata": {},
   "outputs": [],
   "source": [
    "#For example colors categories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "927c6476",
   "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>Size</th>\n",
       "      <th>color</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>XL</td>\n",
       "      <td>B</td>\n",
       "      <td>34.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>L</td>\n",
       "      <td>G</td>\n",
       "      <td>45.12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>S</td>\n",
       "      <td>W</td>\n",
       "      <td>56.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>XL</td>\n",
       "      <td>B</td>\n",
       "      <td>26.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Size color  price\n",
       "0   XL     B  34.50\n",
       "1    L     G  45.12\n",
       "2    S     W  56.00\n",
       "3   XL     B  26.00"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df4 = pd.DataFrame([['XL','B',34.5],['L','G',45.12],['S','W',56],['XL','B',26]],columns=['Size','color','price'])\n",
    "df4"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "38fc5824",
   "metadata": {},
   "source": [
    "## ->One-hot-encoding:nominal categorical column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "cd1888d9",
   "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>B</th>\n",
       "      <th>G</th>\n",
       "      <th>W</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   B  G  W\n",
       "0  1  0  0\n",
       "1  0  1  0\n",
       "2  0  0  1\n",
       "3  1  0  0"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#One-hot-encoding:nominal categorical column\n",
    "df_1 = pd.get_dummies(df4.color)\n",
    "df_1"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8cc808af",
   "metadata": {},
   "source": [
    "### Ordinal categorical column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "4c64df24",
   "metadata": {},
   "outputs": [],
   "source": [
    "# There is some mathematical order or relationships between categories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "fca17f16",
   "metadata": {},
   "outputs": [],
   "source": [
    "# For example categories of temperature :->\n",
    "# Possible categories in temperature high, low, medium\n",
    "# high > medium > low"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "2ee77a92",
   "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>Size</th>\n",
       "      <th>color</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>B</td>\n",
       "      <td>34.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>G</td>\n",
       "      <td>45.12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>W</td>\n",
       "      <td>56.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>B</td>\n",
       "      <td>26.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Size color  price\n",
       "0     3     B  34.50\n",
       "1     2     G  45.12\n",
       "2     1     W  56.00\n",
       "3     3     B  26.00"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Label Encoding:ordinal categorical column\n",
    "df4['Size'] = df4.Size.map({'XL':3,'L':2,'S':1})\n",
    "df4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "fb2b3b95",
   "metadata": {},
   "outputs": [],
   "source": [
    "df4.drop('color',axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "8644cffa",
   "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>Size</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>34.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>45.12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>56.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>26.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Size  price\n",
       "0     3  34.50\n",
       "1     2  45.12\n",
       "2     1  56.00\n",
       "3     3  26.00"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "15a85cb6",
   "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>B</th>\n",
       "      <th>G</th>\n",
       "      <th>W</th>\n",
       "      <th>Size</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>34.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>45.12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>56.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>26.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   B  G  W  Size  price\n",
       "0  1  0  0     3  34.50\n",
       "1  0  1  0     2  45.12\n",
       "2  0  0  1     1  56.00\n",
       "3  1  0  0     3  26.00"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## How to concatinate two dataFrames\n",
    "## Here we are concatenating df_1 and df4 dataFrames into one DataFrame\n",
    "final_data = pd.concat((df_1,df4),axis=1)\n",
    "final_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "8daf1a71",
   "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>age</th>\n",
       "      <th>workclass</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>education</th>\n",
       "      <th>educational-num</th>\n",
       "      <th>marital-status</th>\n",
       "      <th>occupation</th>\n",
       "      <th>relationship</th>\n",
       "      <th>race</th>\n",
       "      <th>gender</th>\n",
       "      <th>capital-gain</th>\n",
       "      <th>capital-loss</th>\n",
       "      <th>hours-per-week</th>\n",
       "      <th>native-country</th>\n",
       "      <th>income</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25</td>\n",
       "      <td>Private</td>\n",
       "      <td>226802</td>\n",
       "      <td>11th</td>\n",
       "      <td>7</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>38</td>\n",
       "      <td>Private</td>\n",
       "      <td>89814</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Farming-fishing</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>Local-gov</td>\n",
       "      <td>336951</td>\n",
       "      <td>Assoc-acdm</td>\n",
       "      <td>12</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Protective-serv</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>44</td>\n",
       "      <td>Private</td>\n",
       "      <td>160323</td>\n",
       "      <td>Some-college</td>\n",
       "      <td>10</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Husband</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>7688</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>18</td>\n",
       "      <td>?</td>\n",
       "      <td>103497</td>\n",
       "      <td>Some-college</td>\n",
       "      <td>10</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>?</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48837</th>\n",
       "      <td>27</td>\n",
       "      <td>Private</td>\n",
       "      <td>257302</td>\n",
       "      <td>Assoc-acdm</td>\n",
       "      <td>12</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Tech-support</td>\n",
       "      <td>Wife</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>38</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48838</th>\n",
       "      <td>40</td>\n",
       "      <td>Private</td>\n",
       "      <td>154374</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48839</th>\n",
       "      <td>58</td>\n",
       "      <td>Private</td>\n",
       "      <td>151910</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Widowed</td>\n",
       "      <td>Adm-clerical</td>\n",
       "      <td>Unmarried</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48840</th>\n",
       "      <td>22</td>\n",
       "      <td>Private</td>\n",
       "      <td>201490</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Adm-clerical</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48841</th>\n",
       "      <td>52</td>\n",
       "      <td>Self-emp-inc</td>\n",
       "      <td>287927</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Exec-managerial</td>\n",
       "      <td>Wife</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>15024</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>48842 rows × 15 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       age     workclass  fnlwgt     education  educational-num  \\\n",
       "0       25       Private  226802          11th                7   \n",
       "1       38       Private   89814       HS-grad                9   \n",
       "2       28     Local-gov  336951    Assoc-acdm               12   \n",
       "3       44       Private  160323  Some-college               10   \n",
       "4       18             ?  103497  Some-college               10   \n",
       "...    ...           ...     ...           ...              ...   \n",
       "48837   27       Private  257302    Assoc-acdm               12   \n",
       "48838   40       Private  154374       HS-grad                9   \n",
       "48839   58       Private  151910       HS-grad                9   \n",
       "48840   22       Private  201490       HS-grad                9   \n",
       "48841   52  Self-emp-inc  287927       HS-grad                9   \n",
       "\n",
       "           marital-status         occupation relationship   race  gender  \\\n",
       "0           Never-married  Machine-op-inspct    Own-child  Black    Male   \n",
       "1      Married-civ-spouse    Farming-fishing      Husband  White    Male   \n",
       "2      Married-civ-spouse    Protective-serv      Husband  White    Male   \n",
       "3      Married-civ-spouse  Machine-op-inspct      Husband  Black    Male   \n",
       "4           Never-married                  ?    Own-child  White  Female   \n",
       "...                   ...                ...          ...    ...     ...   \n",
       "48837  Married-civ-spouse       Tech-support         Wife  White  Female   \n",
       "48838  Married-civ-spouse  Machine-op-inspct      Husband  White    Male   \n",
       "48839             Widowed       Adm-clerical    Unmarried  White  Female   \n",
       "48840       Never-married       Adm-clerical    Own-child  White    Male   \n",
       "48841  Married-civ-spouse    Exec-managerial         Wife  White  Female   \n",
       "\n",
       "       capital-gain  capital-loss  hours-per-week native-country income  \n",
       "0                 0             0              40  United-States  <=50K  \n",
       "1                 0             0              50  United-States  <=50K  \n",
       "2                 0             0              40  United-States   >50K  \n",
       "3              7688             0              40  United-States   >50K  \n",
       "4                 0             0              30  United-States  <=50K  \n",
       "...             ...           ...             ...            ...    ...  \n",
       "48837             0             0              38  United-States  <=50K  \n",
       "48838             0             0              40  United-States   >50K  \n",
       "48839             0             0              40  United-States  <=50K  \n",
       "48840             0             0              20  United-States  <=50K  \n",
       "48841         15024             0              40  United-States   >50K  \n",
       "\n",
       "[48842 rows x 15 columns]"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1 = pd.read_csv('income.csv')\n",
    "df1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "1fed569b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age                0\n",
       "workclass          0\n",
       "fnlwgt             0\n",
       "education          0\n",
       "educational-num    0\n",
       "marital-status     0\n",
       "occupation         0\n",
       "relationship       0\n",
       "race               0\n",
       "gender             0\n",
       "capital-gain       0\n",
       "capital-loss       0\n",
       "hours-per-week     0\n",
       "native-country     0\n",
       "income             0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "7336e9e0",
   "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>age</th>\n",
       "      <th>workclass</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>education</th>\n",
       "      <th>educational-num</th>\n",
       "      <th>marital-status</th>\n",
       "      <th>occupation</th>\n",
       "      <th>relationship</th>\n",
       "      <th>race</th>\n",
       "      <th>gender</th>\n",
       "      <th>capital-gain</th>\n",
       "      <th>capital-loss</th>\n",
       "      <th>hours-per-week</th>\n",
       "      <th>native-country</th>\n",
       "      <th>income</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25</td>\n",
       "      <td>Private</td>\n",
       "      <td>226802</td>\n",
       "      <td>11th</td>\n",
       "      <td>7</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>38</td>\n",
       "      <td>Private</td>\n",
       "      <td>89814</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Farming-fishing</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>Local-gov</td>\n",
       "      <td>336951</td>\n",
       "      <td>Assoc-acdm</td>\n",
       "      <td>12</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Protective-serv</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>44</td>\n",
       "      <td>Private</td>\n",
       "      <td>160323</td>\n",
       "      <td>Some-college</td>\n",
       "      <td>10</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Husband</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>7688</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>18</td>\n",
       "      <td>NaN</td>\n",
       "      <td>103497</td>\n",
       "      <td>Some-college</td>\n",
       "      <td>10</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48837</th>\n",
       "      <td>27</td>\n",
       "      <td>Private</td>\n",
       "      <td>257302</td>\n",
       "      <td>Assoc-acdm</td>\n",
       "      <td>12</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Tech-support</td>\n",
       "      <td>Wife</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>38</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48838</th>\n",
       "      <td>40</td>\n",
       "      <td>Private</td>\n",
       "      <td>154374</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48839</th>\n",
       "      <td>58</td>\n",
       "      <td>Private</td>\n",
       "      <td>151910</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Widowed</td>\n",
       "      <td>Adm-clerical</td>\n",
       "      <td>Unmarried</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48840</th>\n",
       "      <td>22</td>\n",
       "      <td>Private</td>\n",
       "      <td>201490</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Adm-clerical</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48841</th>\n",
       "      <td>52</td>\n",
       "      <td>Self-emp-inc</td>\n",
       "      <td>287927</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Exec-managerial</td>\n",
       "      <td>Wife</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>15024</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>48842 rows × 15 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       age     workclass  fnlwgt     education  educational-num  \\\n",
       "0       25       Private  226802          11th                7   \n",
       "1       38       Private   89814       HS-grad                9   \n",
       "2       28     Local-gov  336951    Assoc-acdm               12   \n",
       "3       44       Private  160323  Some-college               10   \n",
       "4       18           NaN  103497  Some-college               10   \n",
       "...    ...           ...     ...           ...              ...   \n",
       "48837   27       Private  257302    Assoc-acdm               12   \n",
       "48838   40       Private  154374       HS-grad                9   \n",
       "48839   58       Private  151910       HS-grad                9   \n",
       "48840   22       Private  201490       HS-grad                9   \n",
       "48841   52  Self-emp-inc  287927       HS-grad                9   \n",
       "\n",
       "           marital-status         occupation relationship   race  gender  \\\n",
       "0           Never-married  Machine-op-inspct    Own-child  Black    Male   \n",
       "1      Married-civ-spouse    Farming-fishing      Husband  White    Male   \n",
       "2      Married-civ-spouse    Protective-serv      Husband  White    Male   \n",
       "3      Married-civ-spouse  Machine-op-inspct      Husband  Black    Male   \n",
       "4           Never-married                NaN    Own-child  White  Female   \n",
       "...                   ...                ...          ...    ...     ...   \n",
       "48837  Married-civ-spouse       Tech-support         Wife  White  Female   \n",
       "48838  Married-civ-spouse  Machine-op-inspct      Husband  White    Male   \n",
       "48839             Widowed       Adm-clerical    Unmarried  White  Female   \n",
       "48840       Never-married       Adm-clerical    Own-child  White    Male   \n",
       "48841  Married-civ-spouse    Exec-managerial         Wife  White  Female   \n",
       "\n",
       "       capital-gain  capital-loss  hours-per-week native-country income  \n",
       "0                 0             0              40  United-States  <=50K  \n",
       "1                 0             0              50  United-States  <=50K  \n",
       "2                 0             0              40  United-States   >50K  \n",
       "3              7688             0              40  United-States   >50K  \n",
       "4                 0             0              30  United-States  <=50K  \n",
       "...             ...           ...             ...            ...    ...  \n",
       "48837             0             0              38  United-States  <=50K  \n",
       "48838             0             0              40  United-States   >50K  \n",
       "48839             0             0              40  United-States  <=50K  \n",
       "48840             0             0              20  United-States  <=50K  \n",
       "48841         15024             0              40  United-States   >50K  \n",
       "\n",
       "[48842 rows x 15 columns]"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#make a copy of original df1\n",
    "df6 = df1.copy()\n",
    "#Replacing ? with null Nan\n",
    "import numpy as np\n",
    "df6.replace({'?':np.nan},inplace=True)\n",
    "df6"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "40f3cf9f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(48842, 15)"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df6.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "865cd08e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age                   0\n",
       "workclass          2799\n",
       "fnlwgt                0\n",
       "education             0\n",
       "educational-num       0\n",
       "marital-status        0\n",
       "occupation         2809\n",
       "relationship          0\n",
       "race                  0\n",
       "gender                0\n",
       "capital-gain          0\n",
       "capital-loss          0\n",
       "hours-per-week        0\n",
       "native-country      857\n",
       "income                0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df6.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0922f6b6",
   "metadata": {},
   "source": [
    "## Dealing with categorical columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "e6a79d59",
   "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>workclass</th>\n",
       "      <th>education</th>\n",
       "      <th>marital-status</th>\n",
       "      <th>occupation</th>\n",
       "      <th>relationship</th>\n",
       "      <th>race</th>\n",
       "      <th>gender</th>\n",
       "      <th>native-country</th>\n",
       "      <th>income</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Private</td>\n",
       "      <td>11th</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Private</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Farming-fishing</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Local-gov</td>\n",
       "      <td>Assoc-acdm</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Protective-serv</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Private</td>\n",
       "      <td>Some-college</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Husband</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Some-college</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48837</th>\n",
       "      <td>Private</td>\n",
       "      <td>Assoc-acdm</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Tech-support</td>\n",
       "      <td>Wife</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48838</th>\n",
       "      <td>Private</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48839</th>\n",
       "      <td>Private</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>Widowed</td>\n",
       "      <td>Adm-clerical</td>\n",
       "      <td>Unmarried</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48840</th>\n",
       "      <td>Private</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Adm-clerical</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48841</th>\n",
       "      <td>Self-emp-inc</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Exec-managerial</td>\n",
       "      <td>Wife</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>48842 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          workclass     education      marital-status         occupation  \\\n",
       "0           Private          11th       Never-married  Machine-op-inspct   \n",
       "1           Private       HS-grad  Married-civ-spouse    Farming-fishing   \n",
       "2         Local-gov    Assoc-acdm  Married-civ-spouse    Protective-serv   \n",
       "3           Private  Some-college  Married-civ-spouse  Machine-op-inspct   \n",
       "4               NaN  Some-college       Never-married                NaN   \n",
       "...             ...           ...                 ...                ...   \n",
       "48837       Private    Assoc-acdm  Married-civ-spouse       Tech-support   \n",
       "48838       Private       HS-grad  Married-civ-spouse  Machine-op-inspct   \n",
       "48839       Private       HS-grad             Widowed       Adm-clerical   \n",
       "48840       Private       HS-grad       Never-married       Adm-clerical   \n",
       "48841  Self-emp-inc       HS-grad  Married-civ-spouse    Exec-managerial   \n",
       "\n",
       "      relationship   race  gender native-country income  \n",
       "0        Own-child  Black    Male  United-States  <=50K  \n",
       "1          Husband  White    Male  United-States  <=50K  \n",
       "2          Husband  White    Male  United-States   >50K  \n",
       "3          Husband  Black    Male  United-States   >50K  \n",
       "4        Own-child  White  Female  United-States  <=50K  \n",
       "...            ...    ...     ...            ...    ...  \n",
       "48837         Wife  White  Female  United-States  <=50K  \n",
       "48838      Husband  White    Male  United-States   >50K  \n",
       "48839    Unmarried  White  Female  United-States  <=50K  \n",
       "48840    Own-child  White    Male  United-States  <=50K  \n",
       "48841         Wife  White  Female  United-States   >50K  \n",
       "\n",
       "[48842 rows x 9 columns]"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "columns = df6.select_dtypes(include=['object']) #selecting object type columns in dataFrame\n",
    "columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "90543c41",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "workclass has 8 categories\n",
      "education has 16 categories\n",
      "marital-status has 7 categories\n",
      "occupation has 14 categories\n",
      "relationship has 6 categories\n",
      "race has 5 categories\n",
      "gender has 2 categories\n",
      "native-country has 41 categories\n",
      "income has 2 categories\n"
     ]
    }
   ],
   "source": [
    "d=[]\n",
    "for i in columns:\n",
    "   s=df6[i].nunique()\n",
    "   if s>0:\n",
    "        d.append(s)\n",
    "        print(f\"{i} has {s} categories\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "9aca8a64",
   "metadata": {},
   "outputs": [],
   "source": [
    "#analyzing native-country categorical column \n",
    "d = df6['native-country'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "11edca46",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "47985"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "3cfa1132",
   "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>age</th>\n",
       "      <th>workclass</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>education</th>\n",
       "      <th>educational-num</th>\n",
       "      <th>marital-status</th>\n",
       "      <th>occupation</th>\n",
       "      <th>relationship</th>\n",
       "      <th>race</th>\n",
       "      <th>gender</th>\n",
       "      <th>capital-gain</th>\n",
       "      <th>capital-loss</th>\n",
       "      <th>hours-per-week</th>\n",
       "      <th>native-country</th>\n",
       "      <th>income</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25</td>\n",
       "      <td>Private</td>\n",
       "      <td>226802</td>\n",
       "      <td>11th</td>\n",
       "      <td>7</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>38</td>\n",
       "      <td>Private</td>\n",
       "      <td>89814</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Farming-fishing</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>Local-gov</td>\n",
       "      <td>336951</td>\n",
       "      <td>Assoc-acdm</td>\n",
       "      <td>12</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Protective-serv</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>44</td>\n",
       "      <td>Private</td>\n",
       "      <td>160323</td>\n",
       "      <td>Some-college</td>\n",
       "      <td>10</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Husband</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>7688</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>18</td>\n",
       "      <td>NaN</td>\n",
       "      <td>103497</td>\n",
       "      <td>Some-college</td>\n",
       "      <td>10</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  workclass  fnlwgt     education  educational-num      marital-status  \\\n",
       "0   25    Private  226802          11th                7       Never-married   \n",
       "1   38    Private   89814       HS-grad                9  Married-civ-spouse   \n",
       "2   28  Local-gov  336951    Assoc-acdm               12  Married-civ-spouse   \n",
       "3   44    Private  160323  Some-college               10  Married-civ-spouse   \n",
       "4   18        NaN  103497  Some-college               10       Never-married   \n",
       "\n",
       "          occupation relationship   race  gender  capital-gain  capital-loss  \\\n",
       "0  Machine-op-inspct    Own-child  Black    Male             0             0   \n",
       "1    Farming-fishing      Husband  White    Male             0             0   \n",
       "2    Protective-serv      Husband  White    Male             0             0   \n",
       "3  Machine-op-inspct      Husband  Black    Male          7688             0   \n",
       "4                NaN    Own-child  White  Female             0             0   \n",
       "\n",
       "   hours-per-week native-country income  \n",
       "0              40  United-States  <=50K  \n",
       "1              50  United-States  <=50K  \n",
       "2              40  United-States   >50K  \n",
       "3              40  United-States   >50K  \n",
       "4              30  United-States  <=50K  "
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df6.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "84c4faae",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "United-States                 43832\n",
       "Mexico                          951\n",
       "Philippines                     295\n",
       "Germany                         206\n",
       "Puerto-Rico                     184\n",
       "Canada                          182\n",
       "El-Salvador                     155\n",
       "India                           151\n",
       "Cuba                            138\n",
       "England                         127\n",
       "China                           122\n",
       "South                           115\n",
       "Jamaica                         106\n",
       "Italy                           105\n",
       "Dominican-Republic              103\n",
       "Japan                            92\n",
       "Guatemala                        88\n",
       "Poland                           87\n",
       "Vietnam                          86\n",
       "Columbia                         85\n",
       "Haiti                            75\n",
       "Portugal                         67\n",
       "Taiwan                           65\n",
       "Iran                             59\n",
       "Nicaragua                        49\n",
       "Greece                           49\n",
       "Peru                             46\n",
       "Ecuador                          45\n",
       "France                           38\n",
       "Ireland                          37\n",
       "Thailand                         30\n",
       "Hong                             30\n",
       "Cambodia                         28\n",
       "Trinadad&Tobago                  27\n",
       "Yugoslavia                       23\n",
       "Outlying-US(Guam-USVI-etc)       23\n",
       "Laos                             23\n",
       "Scotland                         21\n",
       "Honduras                         20\n",
       "Hungary                          19\n",
       "Holand-Netherlands                1\n",
       "Name: native-country, dtype: int64"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df6['native-country'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "bf5c22c2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'India',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'England',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'India',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'England',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'England',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'England',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'others',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " 'Us',\n",
       " ...]"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#creating US, India and Others\n",
    "m = []\n",
    "for i in df6['native-country']:\n",
    "    if i == 'United-States':\n",
    "        m.append(\"Us\")\n",
    "    elif i == 'India':\n",
    "        m.append('India')\n",
    "    elif i == 'England':\n",
    "        m.append('England')\n",
    "    else:\n",
    "        m.append(\"others\")\n",
    "m"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "81638776",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Us         43832\n",
       "others      4732\n",
       "India        151\n",
       "England      127\n",
       "Name: native-country, dtype: int64"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df6['native-country'] = m\n",
    "df6['native-country'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "c5baf9ed",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "age has 74 categories\n",
      "workclass has 8 categories\n",
      "fnlwgt has 28523 categories\n",
      "education has 16 categories\n",
      "educational-num has 16 categories\n",
      "marital-status has 7 categories\n",
      "occupation has 14 categories\n",
      "relationship has 6 categories\n",
      "race has 5 categories\n",
      "gender has 2 categories\n",
      "capital-gain has 123 categories\n",
      "capital-loss has 99 categories\n",
      "hours-per-week has 96 categories\n",
      "native-country has 4 categories\n",
      "income has 2 categories\n"
     ]
    }
   ],
   "source": [
    "d=[]\n",
    "for i in df6:\n",
    "    s = df6[i].nunique()\n",
    "    if s>0:\n",
    "        d.append(s)\n",
    "        print('{} has {} categories'.format(i,s))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "cc8185aa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "28995"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(d)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9e729385",
   "metadata": {},
   "source": [
    "## Now we can see that native country column is a Nominal categorical column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "facab595",
   "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>age</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>educational-num</th>\n",
       "      <th>capital-gain</th>\n",
       "      <th>capital-loss</th>\n",
       "      <th>hours-per-week</th>\n",
       "      <th>workclass_Federal-gov</th>\n",
       "      <th>workclass_Local-gov</th>\n",
       "      <th>workclass_Never-worked</th>\n",
       "      <th>workclass_Private</th>\n",
       "      <th>...</th>\n",
       "      <th>race_Other</th>\n",
       "      <th>race_White</th>\n",
       "      <th>gender_Female</th>\n",
       "      <th>gender_Male</th>\n",
       "      <th>native-country_England</th>\n",
       "      <th>native-country_India</th>\n",
       "      <th>native-country_Us</th>\n",
       "      <th>native-country_others</th>\n",
       "      <th>income_&lt;=50K</th>\n",
       "      <th>income_&gt;50K</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25</td>\n",
       "      <td>226802</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>38</td>\n",
       "      <td>89814</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>336951</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>44</td>\n",
       "      <td>160323</td>\n",
       "      <td>10</td>\n",
       "      <td>7688</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>18</td>\n",
       "      <td>103497</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48837</th>\n",
       "      <td>27</td>\n",
       "      <td>257302</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>38</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48838</th>\n",
       "      <td>40</td>\n",
       "      <td>154374</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48839</th>\n",
       "      <td>58</td>\n",
       "      <td>151910</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48840</th>\n",
       "      <td>22</td>\n",
       "      <td>201490</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48841</th>\n",
       "      <td>52</td>\n",
       "      <td>287927</td>\n",
       "      <td>9</td>\n",
       "      <td>15024</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>48842 rows × 70 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       age  fnlwgt  educational-num  capital-gain  capital-loss  \\\n",
       "0       25  226802                7             0             0   \n",
       "1       38   89814                9             0             0   \n",
       "2       28  336951               12             0             0   \n",
       "3       44  160323               10          7688             0   \n",
       "4       18  103497               10             0             0   \n",
       "...    ...     ...              ...           ...           ...   \n",
       "48837   27  257302               12             0             0   \n",
       "48838   40  154374                9             0             0   \n",
       "48839   58  151910                9             0             0   \n",
       "48840   22  201490                9             0             0   \n",
       "48841   52  287927                9         15024             0   \n",
       "\n",
       "       hours-per-week  workclass_Federal-gov  workclass_Local-gov  \\\n",
       "0                  40                      0                    0   \n",
       "1                  50                      0                    0   \n",
       "2                  40                      0                    1   \n",
       "3                  40                      0                    0   \n",
       "4                  30                      0                    0   \n",
       "...               ...                    ...                  ...   \n",
       "48837              38                      0                    0   \n",
       "48838              40                      0                    0   \n",
       "48839              40                      0                    0   \n",
       "48840              20                      0                    0   \n",
       "48841              40                      0                    0   \n",
       "\n",
       "       workclass_Never-worked  workclass_Private  ...  race_Other  race_White  \\\n",
       "0                           0                  1  ...           0           0   \n",
       "1                           0                  1  ...           0           1   \n",
       "2                           0                  0  ...           0           1   \n",
       "3                           0                  1  ...           0           0   \n",
       "4                           0                  0  ...           0           1   \n",
       "...                       ...                ...  ...         ...         ...   \n",
       "48837                       0                  1  ...           0           1   \n",
       "48838                       0                  1  ...           0           1   \n",
       "48839                       0                  1  ...           0           1   \n",
       "48840                       0                  1  ...           0           1   \n",
       "48841                       0                  0  ...           0           1   \n",
       "\n",
       "       gender_Female  gender_Male  native-country_England  \\\n",
       "0                  0            1                       0   \n",
       "1                  0            1                       0   \n",
       "2                  0            1                       0   \n",
       "3                  0            1                       0   \n",
       "4                  1            0                       0   \n",
       "...              ...          ...                     ...   \n",
       "48837              1            0                       0   \n",
       "48838              0            1                       0   \n",
       "48839              1            0                       0   \n",
       "48840              0            1                       0   \n",
       "48841              1            0                       0   \n",
       "\n",
       "       native-country_India  native-country_Us  native-country_others  \\\n",
       "0                         0                  1                      0   \n",
       "1                         0                  1                      0   \n",
       "2                         0                  1                      0   \n",
       "3                         0                  1                      0   \n",
       "4                         0                  1                      0   \n",
       "...                     ...                ...                    ...   \n",
       "48837                     0                  1                      0   \n",
       "48838                     0                  1                      0   \n",
       "48839                     0                  1                      0   \n",
       "48840                     0                  1                      0   \n",
       "48841                     0                  1                      0   \n",
       "\n",
       "       income_<=50K  income_>50K  \n",
       "0                 1            0  \n",
       "1                 1            0  \n",
       "2                 0            1  \n",
       "3                 0            1  \n",
       "4                 1            0  \n",
       "...             ...          ...  \n",
       "48837             1            0  \n",
       "48838             0            1  \n",
       "48839             1            0  \n",
       "48840             1            0  \n",
       "48841             0            1  \n",
       "\n",
       "[48842 rows x 70 columns]"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# So we will use \n",
    "#One-hot-encoding:nominal categorical column\n",
    "f1 = pd.get_dummies(df6)\n",
    "f1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "87a2bc34",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age                         1887430\n",
       "fnlwgt                   9263575662\n",
       "educational-num              492234\n",
       "capital-gain               52703821\n",
       "capital-loss                4273788\n",
       "                            ...    \n",
       "native-country_India            151\n",
       "native-country_Us             43832\n",
       "native-country_others          4732\n",
       "income_<=50K                  37155\n",
       "income_>50K                   11687\n",
       "Length: 70, dtype: int64"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f1.sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "220c6c05",
   "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>age</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>educational-num</th>\n",
       "      <th>capital-gain</th>\n",
       "      <th>capital-loss</th>\n",
       "      <th>hours-per-week</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25</td>\n",
       "      <td>226802</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>38</td>\n",
       "      <td>89814</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>336951</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>44</td>\n",
       "      <td>160323</td>\n",
       "      <td>10</td>\n",
       "      <td>7688</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>18</td>\n",
       "      <td>103497</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48837</th>\n",
       "      <td>27</td>\n",
       "      <td>257302</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48838</th>\n",
       "      <td>40</td>\n",
       "      <td>154374</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48839</th>\n",
       "      <td>58</td>\n",
       "      <td>151910</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48840</th>\n",
       "      <td>22</td>\n",
       "      <td>201490</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48841</th>\n",
       "      <td>52</td>\n",
       "      <td>287927</td>\n",
       "      <td>9</td>\n",
       "      <td>15024</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>48842 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       age  fnlwgt  educational-num  capital-gain  capital-loss  \\\n",
       "0       25  226802                7             0             0   \n",
       "1       38   89814                9             0             0   \n",
       "2       28  336951               12             0             0   \n",
       "3       44  160323               10          7688             0   \n",
       "4       18  103497               10             0             0   \n",
       "...    ...     ...              ...           ...           ...   \n",
       "48837   27  257302               12             0             0   \n",
       "48838   40  154374                9             0             0   \n",
       "48839   58  151910                9             0             0   \n",
       "48840   22  201490                9             0             0   \n",
       "48841   52  287927                9         15024             0   \n",
       "\n",
       "       hours-per-week  \n",
       "0                  40  \n",
       "1                  50  \n",
       "2                  40  \n",
       "3                  40  \n",
       "4                  30  \n",
       "...               ...  \n",
       "48837              38  \n",
       "48838              40  \n",
       "48839              40  \n",
       "48840              20  \n",
       "48841              40  \n",
       "\n",
       "[48842 rows x 6 columns]"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f2 = df6.select_dtypes(exclude=['object'])\n",
    "f2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "a43c2653",
   "metadata": {},
   "outputs": [],
   "source": [
    "final_data = pd.concat((f2,f1),axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "2cf3670f",
   "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>age</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>educational-num</th>\n",
       "      <th>capital-gain</th>\n",
       "      <th>capital-loss</th>\n",
       "      <th>hours-per-week</th>\n",
       "      <th>age</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>educational-num</th>\n",
       "      <th>capital-gain</th>\n",
       "      <th>...</th>\n",
       "      <th>race_Other</th>\n",
       "      <th>race_White</th>\n",
       "      <th>gender_Female</th>\n",
       "      <th>gender_Male</th>\n",
       "      <th>native-country_England</th>\n",
       "      <th>native-country_India</th>\n",
       "      <th>native-country_Us</th>\n",
       "      <th>native-country_others</th>\n",
       "      <th>income_&lt;=50K</th>\n",
       "      <th>income_&gt;50K</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25</td>\n",
       "      <td>226802</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>25</td>\n",
       "      <td>226802</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>38</td>\n",
       "      <td>89814</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>38</td>\n",
       "      <td>89814</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>336951</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>28</td>\n",
       "      <td>336951</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>44</td>\n",
       "      <td>160323</td>\n",
       "      <td>10</td>\n",
       "      <td>7688</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>44</td>\n",
       "      <td>160323</td>\n",
       "      <td>10</td>\n",
       "      <td>7688</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>18</td>\n",
       "      <td>103497</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>18</td>\n",
       "      <td>103497</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48837</th>\n",
       "      <td>27</td>\n",
       "      <td>257302</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>38</td>\n",
       "      <td>27</td>\n",
       "      <td>257302</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48838</th>\n",
       "      <td>40</td>\n",
       "      <td>154374</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>40</td>\n",
       "      <td>154374</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48839</th>\n",
       "      <td>58</td>\n",
       "      <td>151910</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>58</td>\n",
       "      <td>151910</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48840</th>\n",
       "      <td>22</td>\n",
       "      <td>201490</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20</td>\n",
       "      <td>22</td>\n",
       "      <td>201490</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48841</th>\n",
       "      <td>52</td>\n",
       "      <td>287927</td>\n",
       "      <td>9</td>\n",
       "      <td>15024</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>52</td>\n",
       "      <td>287927</td>\n",
       "      <td>9</td>\n",
       "      <td>15024</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>48842 rows × 76 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       age  fnlwgt  educational-num  capital-gain  capital-loss  \\\n",
       "0       25  226802                7             0             0   \n",
       "1       38   89814                9             0             0   \n",
       "2       28  336951               12             0             0   \n",
       "3       44  160323               10          7688             0   \n",
       "4       18  103497               10             0             0   \n",
       "...    ...     ...              ...           ...           ...   \n",
       "48837   27  257302               12             0             0   \n",
       "48838   40  154374                9             0             0   \n",
       "48839   58  151910                9             0             0   \n",
       "48840   22  201490                9             0             0   \n",
       "48841   52  287927                9         15024             0   \n",
       "\n",
       "       hours-per-week  age  fnlwgt  educational-num  capital-gain  ...  \\\n",
       "0                  40   25  226802                7             0  ...   \n",
       "1                  50   38   89814                9             0  ...   \n",
       "2                  40   28  336951               12             0  ...   \n",
       "3                  40   44  160323               10          7688  ...   \n",
       "4                  30   18  103497               10             0  ...   \n",
       "...               ...  ...     ...              ...           ...  ...   \n",
       "48837              38   27  257302               12             0  ...   \n",
       "48838              40   40  154374                9             0  ...   \n",
       "48839              40   58  151910                9             0  ...   \n",
       "48840              20   22  201490                9             0  ...   \n",
       "48841              40   52  287927                9         15024  ...   \n",
       "\n",
       "       race_Other  race_White  gender_Female  gender_Male  \\\n",
       "0               0           0              0            1   \n",
       "1               0           1              0            1   \n",
       "2               0           1              0            1   \n",
       "3               0           0              0            1   \n",
       "4               0           1              1            0   \n",
       "...           ...         ...            ...          ...   \n",
       "48837           0           1              1            0   \n",
       "48838           0           1              0            1   \n",
       "48839           0           1              1            0   \n",
       "48840           0           1              0            1   \n",
       "48841           0           1              1            0   \n",
       "\n",
       "       native-country_England  native-country_India  native-country_Us  \\\n",
       "0                           0                     0                  1   \n",
       "1                           0                     0                  1   \n",
       "2                           0                     0                  1   \n",
       "3                           0                     0                  1   \n",
       "4                           0                     0                  1   \n",
       "...                       ...                   ...                ...   \n",
       "48837                       0                     0                  1   \n",
       "48838                       0                     0                  1   \n",
       "48839                       0                     0                  1   \n",
       "48840                       0                     0                  1   \n",
       "48841                       0                     0                  1   \n",
       "\n",
       "       native-country_others  income_<=50K  income_>50K  \n",
       "0                          0             1            0  \n",
       "1                          0             1            0  \n",
       "2                          0             0            1  \n",
       "3                          0             0            1  \n",
       "4                          0             1            0  \n",
       "...                      ...           ...          ...  \n",
       "48837                      0             1            0  \n",
       "48838                      0             0            1  \n",
       "48839                      0             1            0  \n",
       "48840                      0             1            0  \n",
       "48841                      0             0            1  \n",
       "\n",
       "[48842 rows x 76 columns]"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "4c5bd11b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age                      int64\n",
       "fnlwgt                   int64\n",
       "educational-num          int64\n",
       "capital-gain             int64\n",
       "capital-loss             int64\n",
       "                         ...  \n",
       "native-country_India     uint8\n",
       "native-country_Us        uint8\n",
       "native-country_others    uint8\n",
       "income_<=50K             uint8\n",
       "income_>50K              uint8\n",
       "Length: 76, dtype: object"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_data.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d0e58de2",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:tensorflow] *",
   "language": "python",
   "name": "conda-env-tensorflow-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}