{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example on Data Preparation: US States Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
      "                                 Dload  Upload   Total   Spent    Left  Speed\n",
      "100 57935  100 57935    0     0   115k      0 --:--:-- --:--:-- --:--:--  115k\n"
     ]
    }
   ],
   "source": [
    "!curl -O https://raw.githubusercontent.com/jakevdp/data-USstates/master/state-population.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>state/region</th>\n",
       "      <th>ages</th>\n",
       "      <th>year</th>\n",
       "      <th>population</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2012</td>\n",
       "      <td>1117489.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2012</td>\n",
       "      <td>4817528.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2010</td>\n",
       "      <td>1130966.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2010</td>\n",
       "      <td>4785570.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2011</td>\n",
       "      <td>1125763.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  state/region     ages  year  population\n",
       "0           AL  under18  2012   1117489.0\n",
       "1           AL    total  2012   4817528.0\n",
       "2           AL  under18  2010   1130966.0\n",
       "3           AL    total  2010   4785570.0\n",
       "4           AL  under18  2011   1125763.0"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop = pd.read_csv('state-population.csv')\n",
    "pop.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>state/region</th>\n",
       "      <th>ages</th>\n",
       "      <th>year</th>\n",
       "      <th>population</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>500</th>\n",
       "      <td>GA</td>\n",
       "      <td>total</td>\n",
       "      <td>2004</td>\n",
       "      <td>8769252.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>501</th>\n",
       "      <td>GA</td>\n",
       "      <td>under18</td>\n",
       "      <td>2004</td>\n",
       "      <td>2308855.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>502</th>\n",
       "      <td>GA</td>\n",
       "      <td>total</td>\n",
       "      <td>2001</td>\n",
       "      <td>8377038.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>503</th>\n",
       "      <td>GA</td>\n",
       "      <td>under18</td>\n",
       "      <td>2001</td>\n",
       "      <td>2215390.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>504</th>\n",
       "      <td>GA</td>\n",
       "      <td>total</td>\n",
       "      <td>2002</td>\n",
       "      <td>8508256.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>695</th>\n",
       "      <td>IN</td>\n",
       "      <td>under18</td>\n",
       "      <td>2001</td>\n",
       "      <td>1579527.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>696</th>\n",
       "      <td>IN</td>\n",
       "      <td>total</td>\n",
       "      <td>2002</td>\n",
       "      <td>6155967.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>697</th>\n",
       "      <td>IN</td>\n",
       "      <td>under18</td>\n",
       "      <td>2002</td>\n",
       "      <td>1580814.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>698</th>\n",
       "      <td>IN</td>\n",
       "      <td>total</td>\n",
       "      <td>1999</td>\n",
       "      <td>6044970.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699</th>\n",
       "      <td>IN</td>\n",
       "      <td>under18</td>\n",
       "      <td>1999</td>\n",
       "      <td>1566079.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>200 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    state/region     ages  year  population\n",
       "500           GA    total  2004   8769252.0\n",
       "501           GA  under18  2004   2308855.0\n",
       "502           GA    total  2001   8377038.0\n",
       "503           GA  under18  2001   2215390.0\n",
       "504           GA    total  2002   8508256.0\n",
       "..           ...      ...   ...         ...\n",
       "695           IN  under18  2001   1579527.0\n",
       "696           IN    total  2002   6155967.0\n",
       "697           IN  under18  2002   1580814.0\n",
       "698           IN    total  1999   6044970.0\n",
       "699           IN  under18  1999   1566079.0\n",
       "\n",
       "[200 rows x 4 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop[500:700]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
      "                                 Dload  Upload   Total   Spent    Left  Speed\n",
      "100   835  100   835    0     0   2221      0 --:--:-- --:--:-- --:--:--  2220\n"
     ]
    }
   ],
   "source": [
    "!curl -O https://raw.githubusercontent.com/jakevdp/data-USstates/master/state-areas.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>state</th>\n",
       "      <th>area (sq. mi)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Alaska</td>\n",
       "      <td>656425</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Arizona</td>\n",
       "      <td>114006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Arkansas</td>\n",
       "      <td>53182</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>California</td>\n",
       "      <td>163707</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        state  area (sq. mi)\n",
       "0     Alabama          52423\n",
       "1      Alaska         656425\n",
       "2     Arizona         114006\n",
       "3    Arkansas          53182\n",
       "4  California         163707"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "areas = pd.read_csv('state-areas.csv')\n",
    "areas.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
      "                                 Dload  Upload   Total   Spent    Left  Speed\n",
      "100   872  100   872    0     0   2273      0 --:--:-- --:--:-- --:--:--  2276\n"
     ]
    }
   ],
   "source": [
    "!curl -O https://raw.githubusercontent.com/jakevdp/data-USstates/master/state-abbrevs.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>state</th>\n",
       "      <th>abbreviation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alabama</td>\n",
       "      <td>AL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Alaska</td>\n",
       "      <td>AK</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Arizona</td>\n",
       "      <td>AZ</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Arkansas</td>\n",
       "      <td>AR</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>California</td>\n",
       "      <td>CA</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        state abbreviation\n",
       "0     Alabama           AL\n",
       "1      Alaska           AK\n",
       "2     Arizona           AZ\n",
       "3    Arkansas           AR\n",
       "4  California           CA"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "abbrevs = pd.read_csv('state-abbrevs.csv')\n",
    "abbrevs.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Merge Data Sets of States Abbreviation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>state/region</th>\n",
       "      <th>ages</th>\n",
       "      <th>year</th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "      <th>abbreviation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2012</td>\n",
       "      <td>1117489.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>AL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2012</td>\n",
       "      <td>4817528.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>AL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2010</td>\n",
       "      <td>1130966.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>AL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2010</td>\n",
       "      <td>4785570.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>AL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2011</td>\n",
       "      <td>1125763.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>AL</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  state/region     ages  year  population    state abbreviation\n",
       "0           AL  under18  2012   1117489.0  Alabama           AL\n",
       "1           AL    total  2012   4817528.0  Alabama           AL\n",
       "2           AL  under18  2010   1130966.0  Alabama           AL\n",
       "3           AL    total  2010   4785570.0  Alabama           AL\n",
       "4           AL  under18  2011   1125763.0  Alabama           AL"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop_ab = pd.merge(pop, abbrevs, how='outer',\n",
    "                  left_on='state/region', \n",
    "                  right_on='abbreviation')\n",
    "pop_ab.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>state/region</th>\n",
       "      <th>ages</th>\n",
       "      <th>year</th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2012</td>\n",
       "      <td>1117489.0</td>\n",
       "      <td>Alabama</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2012</td>\n",
       "      <td>4817528.0</td>\n",
       "      <td>Alabama</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2010</td>\n",
       "      <td>1130966.0</td>\n",
       "      <td>Alabama</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2010</td>\n",
       "      <td>4785570.0</td>\n",
       "      <td>Alabama</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2011</td>\n",
       "      <td>1125763.0</td>\n",
       "      <td>Alabama</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  state/region     ages  year  population    state\n",
       "0           AL  under18  2012   1117489.0  Alabama\n",
       "1           AL    total  2012   4817528.0  Alabama\n",
       "2           AL  under18  2010   1130966.0  Alabama\n",
       "3           AL    total  2010   4785570.0  Alabama\n",
       "4           AL  under18  2011   1125763.0  Alabama"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop_ab = pop_ab.drop('abbreviation',axis=1) \n",
    "pop_ab.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fill in Missing Values for States"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "state/region    False\n",
       "ages            False\n",
       "year            False\n",
       "population       True\n",
       "state            True\n",
       "dtype: bool"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop_ab.isnull().any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>state/region</th>\n",
       "      <th>ages</th>\n",
       "      <th>year</th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2448</th>\n",
       "      <td>PR</td>\n",
       "      <td>under18</td>\n",
       "      <td>1990</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2449</th>\n",
       "      <td>PR</td>\n",
       "      <td>total</td>\n",
       "      <td>1990</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2450</th>\n",
       "      <td>PR</td>\n",
       "      <td>total</td>\n",
       "      <td>1991</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2451</th>\n",
       "      <td>PR</td>\n",
       "      <td>under18</td>\n",
       "      <td>1991</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2452</th>\n",
       "      <td>PR</td>\n",
       "      <td>total</td>\n",
       "      <td>1993</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     state/region     ages  year  population state\n",
       "2448           PR  under18  1990         NaN   NaN\n",
       "2449           PR    total  1990         NaN   NaN\n",
       "2450           PR    total  1991         NaN   NaN\n",
       "2451           PR  under18  1991         NaN   NaN\n",
       "2452           PR    total  1993         NaN   NaN"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop_ab[pop_ab['state'].isnull()].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['PR', 'USA'], dtype=object)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Choose ALL null rows, and column 'state/region'. Read its unique values.\n",
    "pop_ab.loc[pop_ab['state'].isnull(), 'state/region'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "state/region    False\n",
       "ages            False\n",
       "year            False\n",
       "population       True\n",
       "state           False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# data.loc[row condition, variable_to_be_updated] = 'new value'\n",
    "\n",
    "pop_ab.loc[pop_ab['state/region'] == 'PR', 'state'] = 'Puerto Rico'\n",
    "pop_ab.loc[pop_ab['state/region'] == 'USA', 'state'] = 'United States'\n",
    "\n",
    "pop_ab.isnull().any()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Merge the 3rd Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>state/region</th>\n",
       "      <th>ages</th>\n",
       "      <th>year</th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "      <th>area (sq. mi)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2012</td>\n",
       "      <td>1117489.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2012</td>\n",
       "      <td>4817528.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2010</td>\n",
       "      <td>1130966.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2010</td>\n",
       "      <td>4785570.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2011</td>\n",
       "      <td>1125763.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  state/region     ages  year  population    state  area (sq. mi)\n",
       "0           AL  under18  2012   1117489.0  Alabama        52423.0\n",
       "1           AL    total  2012   4817528.0  Alabama        52423.0\n",
       "2           AL  under18  2010   1130966.0  Alabama        52423.0\n",
       "3           AL    total  2010   4785570.0  Alabama        52423.0\n",
       "4           AL  under18  2011   1125763.0  Alabama        52423.0"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final = pd.merge(pop_ab, areas, on='state', how='left')\n",
    "final.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "state/region     False\n",
       "ages             False\n",
       "year             False\n",
       "population        True\n",
       "state            False\n",
       "area (sq. mi)     True\n",
       "dtype: bool"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final.isnull().any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>state/region</th>\n",
       "      <th>ages</th>\n",
       "      <th>year</th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "      <th>area (sq. mi)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2012</td>\n",
       "      <td>1117489.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2012</td>\n",
       "      <td>4817528.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2010</td>\n",
       "      <td>1130966.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2010</td>\n",
       "      <td>4785570.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2011</td>\n",
       "      <td>1125763.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  state/region     ages  year  population    state  area (sq. mi)\n",
       "0           AL  under18  2012   1117489.0  Alabama        52423.0\n",
       "1           AL    total  2012   4817528.0  Alabama        52423.0\n",
       "2           AL  under18  2010   1130966.0  Alabama        52423.0\n",
       "3           AL    total  2010   4785570.0  Alabama        52423.0\n",
       "4           AL  under18  2011   1125763.0  Alabama        52423.0"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final.dropna(inplace=True)\n",
    "final.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Creating New Variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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>state/region</th>\n",
       "      <th>ages</th>\n",
       "      <th>year</th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "      <th>area (sq. mi)</th>\n",
       "      <th>density</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2012</td>\n",
       "      <td>1117489.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "      <td>21.316769</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2012</td>\n",
       "      <td>4817528.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "      <td>91.897221</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2010</td>\n",
       "      <td>1130966.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "      <td>21.573851</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2010</td>\n",
       "      <td>4785570.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "      <td>91.287603</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AL</td>\n",
       "      <td>under18</td>\n",
       "      <td>2011</td>\n",
       "      <td>1125763.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "      <td>21.474601</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  state/region     ages  year  population    state  area (sq. mi)    density\n",
       "0           AL  under18  2012   1117489.0  Alabama        52423.0  21.316769\n",
       "1           AL    total  2012   4817528.0  Alabama        52423.0  91.897221\n",
       "2           AL  under18  2010   1130966.0  Alabama        52423.0  21.573851\n",
       "3           AL    total  2010   4785570.0  Alabama        52423.0  91.287603\n",
       "4           AL  under18  2011   1125763.0  Alabama        52423.0  21.474601"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final['density'] = final['population'] / final['area (sq. mi)']\n",
    "final.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Subsetting the Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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>state/region</th>\n",
       "      <th>ages</th>\n",
       "      <th>year</th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "      <th>area (sq. mi)</th>\n",
       "      <th>density</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AL</td>\n",
       "      <td>total</td>\n",
       "      <td>2010</td>\n",
       "      <td>4785570.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>52423.0</td>\n",
       "      <td>91.287603</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>91</th>\n",
       "      <td>AK</td>\n",
       "      <td>total</td>\n",
       "      <td>2010</td>\n",
       "      <td>713868.0</td>\n",
       "      <td>Alaska</td>\n",
       "      <td>656425.0</td>\n",
       "      <td>1.087509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>101</th>\n",
       "      <td>AZ</td>\n",
       "      <td>total</td>\n",
       "      <td>2010</td>\n",
       "      <td>6408790.0</td>\n",
       "      <td>Arizona</td>\n",
       "      <td>114006.0</td>\n",
       "      <td>56.214497</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>189</th>\n",
       "      <td>AR</td>\n",
       "      <td>total</td>\n",
       "      <td>2010</td>\n",
       "      <td>2922280.0</td>\n",
       "      <td>Arkansas</td>\n",
       "      <td>53182.0</td>\n",
       "      <td>54.948667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>197</th>\n",
       "      <td>CA</td>\n",
       "      <td>total</td>\n",
       "      <td>2010</td>\n",
       "      <td>37333601.0</td>\n",
       "      <td>California</td>\n",
       "      <td>163707.0</td>\n",
       "      <td>228.051342</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    state/region   ages  year  population       state  area (sq. mi)  \\\n",
       "3             AL  total  2010   4785570.0     Alabama        52423.0   \n",
       "91            AK  total  2010    713868.0      Alaska       656425.0   \n",
       "101           AZ  total  2010   6408790.0     Arizona       114006.0   \n",
       "189           AR  total  2010   2922280.0    Arkansas        53182.0   \n",
       "197           CA  total  2010  37333601.0  California       163707.0   \n",
       "\n",
       "        density  \n",
       "3     91.287603  \n",
       "91     1.087509  \n",
       "101   56.214497  \n",
       "189   54.948667  \n",
       "197  228.051342  "
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data2010 = final.query(\" year == 2010 & ages == 'total' \")\n",
    "data2010.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "data2010.set_index('state', inplace=True) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'data2010' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn [13], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mdata2010\u001b[49m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'data2010' is not defined"
     ]
    }
   ],
   "source": [
    "data2010"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.11.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}