{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "3fa54d9c",
   "metadata": {},
   "source": [
    "# Pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "3d9572b7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pandas version: 2.3.3\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "print(\"Pandas version:\", pd.__version__)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0cd66908",
   "metadata": {},
   "source": [
    "## 1. Series: one-dimensional data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0637c591",
   "metadata": {},
   "source": [
    "### 1.1. Creating series "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "cad2f689",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    22\n",
       "1    25\n",
       "2    23\n",
       "3    28\n",
       "4    24\n",
       "dtype: int64"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "temp = pd.Series([22, 25, 23, 28, 24])\n",
    "temp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "a6960adb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.series.Series"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(temp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4342cfb8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Mon      22\n",
       "Tues     25\n",
       "Wed      23\n",
       "Thurs    28\n",
       "Fri      24\n",
       "dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "day = ['Mon', 'Tues', 'Wed', 'Thurs', 'Fri']\n",
    "temp = pd.Series([22, 25, 23, 28, 24], index=day)\n",
    "\n",
    "temp"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6b90acd9",
   "metadata": {},
   "source": [
    "### 1.2. Accessing series data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "125c05b0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "23\n"
     ]
    }
   ],
   "source": [
    "print(temp.iloc[2])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9ad7b215",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "23\n"
     ]
    }
   ],
   "source": [
    "print(temp['Wed'])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "263cb857",
   "metadata": {},
   "source": [
    "### 1.3. Series operations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "369720c2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "24.4\n"
     ]
    }
   ],
   "source": [
    "print(temp.mean())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d0cb429f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "28\n"
     ]
    }
   ],
   "source": [
    "print(temp.max())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fb7d3124",
   "metadata": {},
   "source": [
    "## 2. DataFrame: two-dimensional data\n",
    "\n",
    "### 2.1. Creating dataframes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "a546e692",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = {\n",
    "    'name': ['Alice', 'Bob', 'Charlie', 'Diana'],\n",
    "    'age': [25, 30, 35, 28],\n",
    "    'city': ['New York', 'Paris', 'London', 'Tokyo'],\n",
    "    'salary': [50000, 60000, 55000, 58000]\n",
    "}\n",
    "\n",
    "type(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "5f7029c4",
   "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>age</th>\n",
       "      <th>city</th>\n",
       "      <th>salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name  age      city  salary\n",
       "0    Alice   25  New York   50000\n",
       "1      Bob   30     Paris   60000\n",
       "2  Charlie   35    London   55000\n",
       "3    Diana   28     Tokyo   58000"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame(data)\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "911fbe8f",
   "metadata": {},
   "source": [
    "### 2.2. Setting the index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "6ef8a6bf",
   "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>age</th>\n",
       "      <th>city</th>\n",
       "      <th>salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name  age      city  salary\n",
       "1    Alice   25  New York   50000\n",
       "2      Bob   30     Paris   60000\n",
       "3  Charlie   35    London   55000\n",
       "4    Diana   28     Tokyo   58000"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "index = [1, 2, 3, 4]\n",
    "df.set_index(pd.Index(index), inplace=True)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "503d204f",
   "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>age</th>\n",
       "      <th>city</th>\n",
       "      <th>salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name  age      city  salary\n",
       "1    Alice   25  New York   50000\n",
       "2      Bob   30     Paris   60000\n",
       "3  Charlie   35    London   55000\n",
       "4    Diana   28     Tokyo   58000"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "853c70b4",
   "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>age</th>\n",
       "      <th>city</th>\n",
       "      <th>salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name  age      city  salary\n",
       "0    Alice   25  New York   50000\n",
       "1      Bob   30     Paris   60000\n",
       "2  Charlie   35    London   55000\n",
       "3    Diana   28     Tokyo   58000"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remove the index\n",
    "df.reset_index(inplace=True, drop=True)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "aa1c8ed8",
   "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>age</th>\n",
       "      <th>city</th>\n",
       "      <th>salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name  age      city  salary\n",
       "0    Alice   25  New York   50000\n",
       "1      Bob   30     Paris   60000\n",
       "2  Charlie   35    London   55000\n",
       "3    Diana   28     Tokyo   58000"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0fd8e05e",
   "metadata": {},
   "source": [
    "### 2.3. Getting and setting column names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "1de8bdf4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['name', 'age', 'city', 'salary'], dtype='object')"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get column names\n",
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "bcd1d47d",
   "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>age</th>\n",
       "      <th>location</th>\n",
       "      <th>salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name  age  location  salary\n",
       "0    Alice   25  New York   50000\n",
       "1      Bob   30     Paris   60000\n",
       "2  Charlie   35    London   55000\n",
       "3    Diana   28     Tokyo   58000"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Rename specific columns(s)\n",
    "rename_dict = {'city': 'location'}\n",
    "\n",
    "df = df.rename(columns=rename_dict)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "e0e67ada",
   "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>full_name</th>\n",
       "      <th>age_years</th>\n",
       "      <th>location</th>\n",
       "      <th>annual_salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  full_name  age_years  location  annual_salary\n",
       "0     Alice         25  New York          50000\n",
       "1       Bob         30     Paris          60000\n",
       "2   Charlie         35    London          55000\n",
       "3     Diana         28     Tokyo          58000"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Set all column names\n",
    "df.columns = ['full_name', 'age_years', 'location', 'annual_salary']\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e623ed07",
   "metadata": {},
   "source": [
    "### 2.4. Removing rows or columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "7b15b296",
   "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>full_name</th>\n",
       "      <th>age_years</th>\n",
       "      <th>location</th>\n",
       "      <th>annual_salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  full_name  age_years  location  annual_salary\n",
       "0     Alice         25  New York          50000\n",
       "1       Bob         30     Paris          60000\n",
       "2   Charlie         35    London          55000\n",
       "3     Diana         28     Tokyo          58000"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Make a copy of the dataframe so we can experiment without changing the original\n",
    "drop_df = df.copy()\n",
    "drop_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "74053f73",
   "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>full_name</th>\n",
       "      <th>age_years</th>\n",
       "      <th>location</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  full_name  age_years  location\n",
       "0     Alice         25  New York\n",
       "1       Bob         30     Paris\n",
       "2   Charlie         35    London\n",
       "3     Diana         28     Tokyo"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Drop a column\n",
    "drop_df.drop('annual_salary', axis=1, inplace=True)\n",
    "drop_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "0a118ed5",
   "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>full_name</th>\n",
       "      <th>age_years</th>\n",
       "      <th>location</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  full_name  age_years  location\n",
       "0     Alice         25  New York\n",
       "1       Bob         30     Paris\n",
       "3     Diana         28     Tokyo"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Drop a row\n",
    "drop_df.drop(2, axis=0, inplace=True)\n",
    "drop_df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e1c077f8",
   "metadata": {},
   "source": [
    "### 2.5. Getting information about dataFrames"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "425720a6",
   "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>full_name</th>\n",
       "      <th>age_years</th>\n",
       "      <th>location</th>\n",
       "      <th>annual_salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  full_name  age_years  location  annual_salary\n",
       "0     Alice         25  New York          50000\n",
       "1       Bob         30     Paris          60000"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "d6595ff8",
   "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>full_name</th>\n",
       "      <th>age_years</th>\n",
       "      <th>location</th>\n",
       "      <th>annual_salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  full_name  age_years location  annual_salary\n",
       "2   Charlie         35   London          55000\n",
       "3     Diana         28    Tokyo          58000"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "5e34f4c5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 4 entries, 0 to 3\n",
      "Data columns (total 4 columns):\n",
      " #   Column         Non-Null Count  Dtype \n",
      "---  ------         --------------  ----- \n",
      " 0   full_name      4 non-null      object\n",
      " 1   age_years      4 non-null      int64 \n",
      " 2   location       4 non-null      object\n",
      " 3   annual_salary  4 non-null      int64 \n",
      "dtypes: int64(2), object(2)\n",
      "memory usage: 260.0+ bytes\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "13410b85",
   "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_years</th>\n",
       "      <th>annual_salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>4.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>29.500000</td>\n",
       "      <td>55750.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>4.203173</td>\n",
       "      <td>4349.32945</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>25.000000</td>\n",
       "      <td>50000.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>27.250000</td>\n",
       "      <td>53750.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>29.000000</td>\n",
       "      <td>56500.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>31.250000</td>\n",
       "      <td>58500.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>35.000000</td>\n",
       "      <td>60000.00000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       age_years  annual_salary\n",
       "count   4.000000        4.00000\n",
       "mean   29.500000    55750.00000\n",
       "std     4.203173     4349.32945\n",
       "min    25.000000    50000.00000\n",
       "25%    27.250000    53750.00000\n",
       "50%    29.000000    56500.00000\n",
       "75%    31.250000    58500.00000\n",
       "max    35.000000    60000.00000"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7a69a146",
   "metadata": {},
   "source": [
    "### 2.6. Selecting data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "ef7bf442",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0      Alice\n",
       "1        Bob\n",
       "2    Charlie\n",
       "3      Diana\n",
       "Name: full_name, dtype: object"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Select a column\n",
    "df['full_name']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "d7b5c66b",
   "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>full_name</th>\n",
       "      <th>location</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>New York</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>Paris</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>London</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>Tokyo</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  full_name  location\n",
       "0     Alice  New York\n",
       "1       Bob     Paris\n",
       "2   Charlie    London\n",
       "3     Diana     Tokyo"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Select multiple columns\n",
    "df[['full_name', 'location']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "acb8c7f2",
   "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>full_name</th>\n",
       "      <th>age_years</th>\n",
       "      <th>location</th>\n",
       "      <th>annual_salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>second</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>third</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fourth</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       full_name  age_years  location  annual_salary\n",
       "first      Alice         25  New York          50000\n",
       "second       Bob         30     Paris          60000\n",
       "third    Charlie         35    London          55000\n",
       "fourth     Diana         28     Tokyo          58000"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Set a new index\n",
    "index = ['first', 'second', 'third', 'fourth']\n",
    "df = df.set_index(pd.Index(index))\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "70fbba6b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "full_name           Alice\n",
       "age_years              25\n",
       "location         New York\n",
       "annual_salary       50000\n",
       "Name: first, dtype: object"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Select a row by its index label\n",
    "df.loc['first']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "2225c63c",
   "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>full_name</th>\n",
       "      <th>age_years</th>\n",
       "      <th>location</th>\n",
       "      <th>annual_salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25</td>\n",
       "      <td>New York</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>second</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       full_name  age_years  location  annual_salary\n",
       "first      Alice         25  New York          50000\n",
       "second       Bob         30     Paris          60000"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Select multiple rows by their index labels\n",
    "df.loc[['first', 'second']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "3752decf",
   "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>full_name</th>\n",
       "      <th>annual_salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <td>Alice</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>second</th>\n",
       "      <td>Bob</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       full_name  annual_salary\n",
       "first      Alice          50000\n",
       "second       Bob          60000"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Select specific rows and columns\n",
    "df.loc[['first', 'second'], ['full_name', 'annual_salary']]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "17f463d8",
   "metadata": {},
   "source": [
    "### 2.7. Filtering data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "b5b8c5bc",
   "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>full_name</th>\n",
       "      <th>age_years</th>\n",
       "      <th>location</th>\n",
       "      <th>annual_salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>second</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>third</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fourth</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       full_name  age_years location  annual_salary\n",
       "second       Bob         30    Paris          60000\n",
       "third    Charlie         35   London          55000\n",
       "fourth     Diana         28    Tokyo          58000"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Select rows based on a condition\n",
    "df[df['annual_salary'] > 50000]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "a3dc5d5a",
   "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>full_name</th>\n",
       "      <th>age_years</th>\n",
       "      <th>location</th>\n",
       "      <th>annual_salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>fourth</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       full_name  age_years location  annual_salary\n",
       "fourth     Diana         28    Tokyo          58000"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Select rows where city is Tokyo\n",
    "df[df['location'] == 'Tokyo']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "b19ed62e",
   "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>full_name</th>\n",
       "      <th>age_years</th>\n",
       "      <th>location</th>\n",
       "      <th>annual_salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>second</th>\n",
       "      <td>Bob</td>\n",
       "      <td>30</td>\n",
       "      <td>Paris</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>third</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35</td>\n",
       "      <td>London</td>\n",
       "      <td>55000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fourth</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28</td>\n",
       "      <td>Tokyo</td>\n",
       "      <td>58000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       full_name  age_years location  annual_salary\n",
       "second       Bob         30    Paris          60000\n",
       "third    Charlie         35   London          55000\n",
       "fourth     Diana         28    Tokyo          58000"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "salary_thresh = df['annual_salary'] > 50000\n",
    "df[salary_thresh]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cfcea26a",
   "metadata": {},
   "source": [
    "## 3. Handling missing data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "df626c4b",
   "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>age</th>\n",
       "      <th>salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25.0</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>NaN</td>\n",
       "      <td>60000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28.0</td>\n",
       "      <td>58000.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name   age   salary\n",
       "0    Alice  25.0  50000.0\n",
       "1      Bob   NaN  60000.0\n",
       "2  Charlie  35.0      NaN\n",
       "3    Diana  28.0  58000.0"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create data with missing values\n",
    "data_with_missing = pd.DataFrame({\n",
    "    'name': ['Alice', 'Bob', 'Charlie', 'Diana'],\n",
    "    'age': [25, np.nan, 35, 28],\n",
    "    'salary': [50000, 60000, np.nan, 58000]\n",
    "})\n",
    "\n",
    "data_with_missing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "6debb1a3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 4 entries, 0 to 3\n",
      "Data columns (total 3 columns):\n",
      " #   Column  Non-Null Count  Dtype  \n",
      "---  ------  --------------  -----  \n",
      " 0   name    4 non-null      object \n",
      " 1   age     3 non-null      float64\n",
      " 2   salary  3 non-null      float64\n",
      "dtypes: float64(2), object(1)\n",
      "memory usage: 228.0+ bytes\n"
     ]
    }
   ],
   "source": [
    "# Null values in info()\n",
    "data_with_missing.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "877d0d98",
   "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>age</th>\n",
       "      <th>salary</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    name    age  salary\n",
       "0  False  False   False\n",
       "1  False   True   False\n",
       "2  False  False    True\n",
       "3  False  False   False"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Finding null values\n",
    "data_with_missing.isnull()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "5395ec92",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "name      0\n",
       "age       1\n",
       "salary    1\n",
       "dtype: int64"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Finding null value counts by feature\n",
    "data_with_missing.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "954c169f",
   "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>age</th>\n",
       "      <th>salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alice</td>\n",
       "      <td>25.0</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bob</td>\n",
       "      <td>0.0</td>\n",
       "      <td>60000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Charlie</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Diana</td>\n",
       "      <td>28.0</td>\n",
       "      <td>58000.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name   age   salary\n",
       "0    Alice  25.0  50000.0\n",
       "1      Bob   0.0  60000.0\n",
       "2  Charlie  35.0      0.0\n",
       "3    Diana  28.0  58000.0"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Filling null values with a specific value\n",
    "data_with_missing.fillna(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "dab38b78",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    25.000000\n",
       "1    29.333333\n",
       "2    35.000000\n",
       "3    28.000000\n",
       "Name: age, dtype: float64"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Filling null values with the mean of the column\n",
    "data_with_missing['age'].fillna(data_with_missing['age'].mean())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "472dbf29",
   "metadata": {},
   "source": [
    "## 4. Working with data types"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "52232e2f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5 entries, 0 to 4\n",
      "Data columns (total 5 columns):\n",
      " #   Column           Non-Null Count  Dtype \n",
      "---  ------           --------------  ----- \n",
      " 0   numbers_as_text  5 non-null      object\n",
      " 1   prices           5 non-null      object\n",
      " 2   categories       5 non-null      object\n",
      " 3   is_active        5 non-null      object\n",
      " 4   dates_as_text    5 non-null      object\n",
      "dtypes: object(5)\n",
      "memory usage: 332.0+ bytes\n"
     ]
    }
   ],
   "source": [
    "mixed_data = pd.DataFrame({\n",
    "    'numbers_as_text': ['1', '2', '3', '4', '5'],\n",
    "    'prices': ['10.50', '20.75', '15.25', '30.00', '25.50'],\n",
    "    'categories': ['A', 'B', 'A', 'C', 'B'],\n",
    "    'is_active': ['True', 'False', 'True', 'True', 'False'],\n",
    "    'dates_as_text': ['2024-01-01', '2024-01-02', '2024-01-03', '2024-01-04', '2024-01-05']\n",
    "})\n",
    "\n",
    "mixed_data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "eec2dca3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5 entries, 0 to 4\n",
      "Data columns (total 5 columns):\n",
      " #   Column           Non-Null Count  Dtype  \n",
      "---  ------           --------------  -----  \n",
      " 0   numbers_as_text  5 non-null      object \n",
      " 1   prices           5 non-null      float64\n",
      " 2   categories       5 non-null      object \n",
      " 3   is_active        5 non-null      object \n",
      " 4   dates_as_text    5 non-null      object \n",
      "dtypes: float64(1), object(4)\n",
      "memory usage: 332.0+ bytes\n"
     ]
    }
   ],
   "source": [
    "mixed_data['prices'] = mixed_data['prices'].astype(float)\n",
    "mixed_data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "cc1e7c8f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5 entries, 0 to 4\n",
      "Data columns (total 5 columns):\n",
      " #   Column           Non-Null Count  Dtype  \n",
      "---  ------           --------------  -----  \n",
      " 0   numbers_as_text  5 non-null      object \n",
      " 1   prices           5 non-null      float32\n",
      " 2   categories       5 non-null      object \n",
      " 3   is_active        5 non-null      object \n",
      " 4   dates_as_text    5 non-null      object \n",
      "dtypes: float32(1), object(4)\n",
      "memory usage: 312.0+ bytes\n"
     ]
    }
   ],
   "source": [
    "mixed_data['prices'] = mixed_data['prices'].astype(np.float32)\n",
    "mixed_data.info()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}