{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 119,
   "id": "e3e56e2b-d47e-43a2-9eb5-513a6063c09d",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c8d0e24a-0dbd-4fb7-820f-4e0cc964e341",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "source": [
    "## Data Frames"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "id": "4a7f7a67-59dd-4008-8c48-6374c5decb3b",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>User ID</th>\n",
       "      <th>Username</th>\n",
       "      <th>Age</th>\n",
       "      <th>Joined Date</th>\n",
       "      <th>Total Posts</th>\n",
       "      <th>Reputation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>bogdan_s</td>\n",
       "      <td>18.0</td>\n",
       "      <td>2032-01-01</td>\n",
       "      <td>150</td>\n",
       "      <td>500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>jane_smith</td>\n",
       "      <td>35.0</td>\n",
       "      <td>2032-02-15</td>\n",
       "      <td>230</td>\n",
       "      <td>720</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>alex123</td>\n",
       "      <td>25.0</td>\n",
       "      <td>2032-04-25</td>\n",
       "      <td>80</td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>bob56</td>\n",
       "      <td>38.0</td>\n",
       "      <td>2032-06-21</td>\n",
       "      <td>420</td>\n",
       "      <td>940</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>mark_wilson</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2032-09-15</td>\n",
       "      <td>310</td>\n",
       "      <td>500</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   User ID     Username   Age Joined Date  Total Posts  Reputation\n",
       "0        1     bogdan_s  18.0  2032-01-01          150         500\n",
       "1        2   jane_smith  35.0  2032-02-15          230         720\n",
       "2        3      alex123  25.0  2032-04-25           80         200\n",
       "3        4        bob56  38.0  2032-06-21          420         940\n",
       "4        5  mark_wilson   NaN  2032-09-15          310         500"
      ]
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "forum_users = {\n",
    "    'User ID': np.array([1, 2, 3, 4, 5]),\n",
    "    'Username': ['bogdan_s', 'jane_smith', 'alex123', 'bob56', 'mark_wilson'],\n",
    "    'Age': [18, 35, 25, 38, None],\n",
    "    'Joined Date': pd.to_datetime(['2032-01-01', '2032-02-15', '2032-04-25', '2032-06-21', '2032-09-15']),\n",
    "    'Total Posts': [150, 230, 80, 420, 310],\n",
    "    'Reputation': [500, 720, 200, 940, 500]\n",
    "}\n",
    "\n",
    "df = pd.DataFrame(forum_users)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "id": "433c340e-cf75-4c05-a8e7-e9e518bfc19e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5, 6)"
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "id": "b1841365-e8a1-4b5d-a07d-70250877dde0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.frame.DataFrame"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "id": "72f5fea6-2c02-457f-bcc2-ad97095d6958",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['User ID', 'Username', 'Age', 'Joined Date', 'Total Posts',\n",
       "       'Reputation'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "id": "6ead64b1-240e-4892-ad2c-5d057453a728",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.indexes.base.Index"
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(df.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "id": "7392fd77-964b-4c0f-97e2-51447d7a5fe8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['User ID', 'Username', 'Age', 'Joined Date', 'Total Posts', 'Reputation']"
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns.tolist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "id": "b8c0b85b-e8f9-4e96-8193-cbb68bcd32f0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 1, 2, 3, 4]"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.index.tolist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "id": "7d00b16e-53e1-4329-b45d-f636642804d3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "User ID                 int64\n",
       "Username               object\n",
       "Age                   float64\n",
       "Joined Date    datetime64[ns]\n",
       "Total Posts             int64\n",
       "Reputation              int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 127,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "id": "cf15d198-7729-456c-86e5-1f9116b2f9d6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1, 'bogdan_s', 18.0, Timestamp('2032-01-01 00:00:00'), 150, 500],\n",
       "       [2, 'jane_smith', 35.0, Timestamp('2032-02-15 00:00:00'), 230,\n",
       "        720],\n",
       "       [3, 'alex123', 25.0, Timestamp('2032-04-25 00:00:00'), 80, 200],\n",
       "       [4, 'bob56', 38.0, Timestamp('2032-06-21 00:00:00'), 420, 940],\n",
       "       [5, 'mark_wilson', nan, Timestamp('2032-09-15 00:00:00'), 310,\n",
       "        500]], dtype=object)"
      ]
     },
     "execution_count": 128,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "id": "f5481626-06fc-40be-9884-60481939ddfb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "numpy.ndarray"
      ]
     },
     "execution_count": 129,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(df.values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "id": "76e46bea-717c-40ca-9e96-81df57119e1e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'jane_smith'"
      ]
     },
     "execution_count": 130,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.values[1, 1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "id": "3f4f11cf-3ced-4859-b2de-d963d6ac6ec3",
   "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>User ID</th>\n",
       "      <th>Username</th>\n",
       "      <th>Age</th>\n",
       "      <th>Joined Date</th>\n",
       "      <th>Total Posts</th>\n",
       "      <th>Reputation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>bogdan_s</td>\n",
       "      <td>18.0</td>\n",
       "      <td>2032-01-01</td>\n",
       "      <td>150</td>\n",
       "      <td>500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>jane_smith</td>\n",
       "      <td>35.0</td>\n",
       "      <td>2032-02-15</td>\n",
       "      <td>230</td>\n",
       "      <td>720</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>alex123</td>\n",
       "      <td>25.0</td>\n",
       "      <td>2032-04-25</td>\n",
       "      <td>80</td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   User ID    Username   Age Joined Date  Total Posts  Reputation\n",
       "0        1    bogdan_s  18.0  2032-01-01          150         500\n",
       "1        2  jane_smith  35.0  2032-02-15          230         720\n",
       "2        3     alex123  25.0  2032-04-25           80         200"
      ]
     },
     "execution_count": 131,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "id": "47c79af0-399a-4b6a-95c0-382a10cd0cd4",
   "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>User ID</th>\n",
       "      <th>Username</th>\n",
       "      <th>Age</th>\n",
       "      <th>Joined Date</th>\n",
       "      <th>Total Posts</th>\n",
       "      <th>Reputation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>bob56</td>\n",
       "      <td>38.0</td>\n",
       "      <td>2032-06-21</td>\n",
       "      <td>420</td>\n",
       "      <td>940</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>mark_wilson</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2032-09-15</td>\n",
       "      <td>310</td>\n",
       "      <td>500</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   User ID     Username   Age Joined Date  Total Posts  Reputation\n",
       "3        4        bob56  38.0  2032-06-21          420         940\n",
       "4        5  mark_wilson   NaN  2032-09-15          310         500"
      ]
     },
     "execution_count": 132,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "id": "3e519f5f-ef45-40b6-9d58-6720aee5caac",
   "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>User ID</th>\n",
       "      <th>Age</th>\n",
       "      <th>Joined Date</th>\n",
       "      <th>Total Posts</th>\n",
       "      <th>Reputation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5.00</td>\n",
       "      <td>4.00</td>\n",
       "      <td>5</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3.00</td>\n",
       "      <td>29.00</td>\n",
       "      <td>2032-04-28 00:00:00</td>\n",
       "      <td>238.0</td>\n",
       "      <td>572.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.00</td>\n",
       "      <td>18.00</td>\n",
       "      <td>2032-01-01 00:00:00</td>\n",
       "      <td>80.0</td>\n",
       "      <td>200.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2.00</td>\n",
       "      <td>23.25</td>\n",
       "      <td>2032-02-15 00:00:00</td>\n",
       "      <td>150.0</td>\n",
       "      <td>500.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>3.00</td>\n",
       "      <td>30.00</td>\n",
       "      <td>2032-04-25 00:00:00</td>\n",
       "      <td>230.0</td>\n",
       "      <td>500.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>4.00</td>\n",
       "      <td>35.75</td>\n",
       "      <td>2032-06-21 00:00:00</td>\n",
       "      <td>310.0</td>\n",
       "      <td>720.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>5.00</td>\n",
       "      <td>38.00</td>\n",
       "      <td>2032-09-15 00:00:00</td>\n",
       "      <td>420.0</td>\n",
       "      <td>940.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1.58</td>\n",
       "      <td>9.20</td>\n",
       "      <td>NaN</td>\n",
       "      <td>133.3</td>\n",
       "      <td>276.62</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       User ID    Age          Joined Date  Total Posts  Reputation\n",
       "count     5.00   4.00                    5          5.0        5.00\n",
       "mean      3.00  29.00  2032-04-28 00:00:00        238.0      572.00\n",
       "min       1.00  18.00  2032-01-01 00:00:00         80.0      200.00\n",
       "25%       2.00  23.25  2032-02-15 00:00:00        150.0      500.00\n",
       "50%       3.00  30.00  2032-04-25 00:00:00        230.0      500.00\n",
       "75%       4.00  35.75  2032-06-21 00:00:00        310.0      720.00\n",
       "max       5.00  38.00  2032-09-15 00:00:00        420.0      940.00\n",
       "std       1.58   9.20                  NaN        133.3      276.62"
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe().round(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "id": "023b55d7-f83b-4f6a-9687-37aee4a577f6",
   "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>Joined Date</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>18.0</td>\n",
       "      <td>2032-01-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>35.0</td>\n",
       "      <td>2032-02-15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>25.0</td>\n",
       "      <td>2032-04-25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>38.0</td>\n",
       "      <td>2032-06-21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>2032-09-15</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Age Joined Date\n",
       "0  18.0  2032-01-01\n",
       "1  35.0  2032-02-15\n",
       "2  25.0  2032-04-25\n",
       "3  38.0  2032-06-21\n",
       "4   NaN  2032-09-15"
      ]
     },
     "execution_count": 140,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.select_dtypes(exclude=['object', 'int64'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "id": "210468be-60a9-410d-8c8f-c1573443d9f4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Username'], dtype='object')"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.select_dtypes(include='object').columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "id": "89b946d3-0a98-4b4a-9906-0e296cec1963",
   "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>User ID</th>\n",
       "      <th>Total Posts</th>\n",
       "      <th>Reputation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>150</td>\n",
       "      <td>500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>230</td>\n",
       "      <td>720</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>80</td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>420</td>\n",
       "      <td>940</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>310</td>\n",
       "      <td>500</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   User ID  Total Posts  Reputation\n",
       "0        1          150         500\n",
       "1        2          230         720\n",
       "2        3           80         200\n",
       "3        4          420         940\n",
       "4        5          310         500"
      ]
     },
     "execution_count": 136,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.select_dtypes(include='int64')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "id": "fe65dd76-bd28-4f13-962c-43e6cc803ecf",
   "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>User ID</th>\n",
       "      <th>Username</th>\n",
       "      <th>Age</th>\n",
       "      <th>Joined Date</th>\n",
       "      <th>Total Posts</th>\n",
       "      <th>Reputation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   User ID  Username    Age  Joined Date  Total Posts  Reputation\n",
       "0    False     False  False        False        False       False\n",
       "1    False     False  False        False        False       False\n",
       "2    False     False  False        False        False       False\n",
       "3    False     False  False        False        False       False\n",
       "4    False     False   True        False        False       False"
      ]
     },
     "execution_count": 137,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 142,
   "id": "4c60d120-82ed-4aee-924f-f2e1d3df5e72",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "User ID        0\n",
       "Username       0\n",
       "Age            1\n",
       "Joined Date    0\n",
       "Total Posts    0\n",
       "Reputation     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 142,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "abcdb997-4ac2-4353-affb-dfa1767784da",
   "metadata": {},
   "source": [
    "## Series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "id": "41eb8eeb-e0a1-4d12-9591-7dd7e6f5a737",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       bogdan_s\n",
       "1     jane_smith\n",
       "2        alex123\n",
       "3          bob56\n",
       "4    mark_wilson\n",
       "Name: Username, dtype: object"
      ]
     },
     "execution_count": 146,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "username_series = df['Username']\n",
    "username_series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 147,
   "id": "2a476131-dccd-4886-9d2d-342db8affe5f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.series.Series"
      ]
     },
     "execution_count": 147,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(username_series)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 148,
   "id": "0f829957-8aca-4b62-a664-2a95330570ff",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['bogdan_s', 'jane_smith', 'alex123', 'bob56', 'mark_wilson'],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 148,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "username_series.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 149,
   "id": "40c36b4e-4c1c-4c66-b801-32b7d11e4429",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "numpy.ndarray"
      ]
     },
     "execution_count": 149,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(username_series.values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 150,
   "id": "e04c9d33-e362-45a6-acdd-c3139eb2e819",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RangeIndex(start=0, stop=5, step=1)"
      ]
     },
     "execution_count": 150,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "username_series.index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 155,
   "id": "dcdf9cc3-602e-4187-aa7f-89572fe43b2e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Reputation\n",
       "500    2\n",
       "720    1\n",
       "200    1\n",
       "940    1\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 155,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Reputation'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 156,
   "id": "6dcfbaa9-ab64-4639-ba7d-4bf60cd2b9d5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Reputation\n",
       "720    1\n",
       "200    1\n",
       "940    1\n",
       "500    2\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 156,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Reputation'].value_counts(ascending=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 157,
   "id": "0f570a5e-7dce-4adc-8010-055e3f795e22",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([500, 720, 200, 940])"
      ]
     },
     "execution_count": 157,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Reputation'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 159,
   "id": "91b78beb-7901-4596-b146-2991750d8fe4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4    mark_wilson\n",
       "1     jane_smith\n",
       "0       bogdan_s\n",
       "3          bob56\n",
       "2        alex123\n",
       "Name: Username, dtype: object"
      ]
     },
     "execution_count": 159,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Username'].sort_values(ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 160,
   "id": "4b8961bf-968e-4d0c-9513-8f07475ee7c6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2        alex123\n",
       "3          bob56\n",
       "0       bogdan_s\n",
       "1     jane_smith\n",
       "4    mark_wilson\n",
       "Name: Username, dtype: object"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Username'].sort_values()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}