03-pandas-ii.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<div style=\"direction:rtl;line-height:300%;\"><font face=\"XB Zar\" size=5>\n",
    "<div style=\"direction:rtl;line-height:300%;\"><font face=\"XB Zar\" size=5>\n",
    "<div align=center>\n",
    "<font face=\"IranNastaliq\" size=30>\n",
    "<p></p>\n",
    "به نام خدا\n",
    "</font>\n",
    "<br>\n",
    "<font color=#FF7500>\n",
    "دانشگاه صنعتی شریف - دانشکده مدیریت و اقتصاد شریف\n",
    "</font>\n",
    "<br>\n",
    "<font color=blue>\n",
    "اقتصاد سنجی ۱\n",
    "</font>\n",
    "<br>\n",
    "ترم پاییز سال تحصیلی ۱۴۰۳-۱۴۰۲\n",
    "<br>\n",
    "دکتر کوثر یوسفی\n",
    "</div>\n",
    "<hr/>\n",
    "<font color=red size=6>\n",
    "<p></p>\n",
    "\n",
    "<div align=center>بخش سوم: ادامه pandas</div>\n",
    "</font>\n",
    "<div align=center>\n",
    "نگین جعفری، محمدمهدی جراحی</div>\n",
    "<hr>\n",
    "</font></div>\n",
    "\n",
    "\n",
    "<style type=\"text/css\" scoped>\n",
    "p{\n",
    "border: 1px solid #a2a9b1;background-color: #f8f9fa;display: inline-block;\n",
    "};\n",
    "</style>\n",
    "\n",
    "\n",
    "<div align=right>\n",
    "منبع: درس یادگیری ماشین دکتر سید عباس حسینی و درس DS 100 تابستان 2020 دانشگاه برکلی</div>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "plt.style.use('fivethirtyeight')\n",
    "sns.set_context(\"notebook\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Let's start by loading the California baby names again.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>271175</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1969</td>\n",
       "      <td>Stephan</td>\n",
       "      <td>49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>257506</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1957</td>\n",
       "      <td>Rich</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>332137</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2000</td>\n",
       "      <td>Esau</td>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>141968</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1998</td>\n",
       "      <td>Marissa</td>\n",
       "      <td>709</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>210123</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>2015</td>\n",
       "      <td>Mina</td>\n",
       "      <td>71</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year     Name  Count\n",
       "271175    CA   M  1969  Stephan     49\n",
       "257506    CA   M  1957     Rich     20\n",
       "332137    CA   M  2000     Esau     26\n",
       "141968    CA   F  1998  Marissa    709\n",
       "210123    CA   F  2015     Mina     71"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import urllib.request\n",
    "import os.path\n",
    "import zipfile\n",
    "\n",
    "data_url = \"https://www.ssa.gov/oact/babynames/state/namesbystate.zip\"\n",
    "local_filename = \"namesbystate.zip\"\n",
    "if not os.path.exists(local_filename): # if the data exists don't download again\n",
    "    with urllib.request.urlopen(data_url) as resp, open(local_filename, 'wb') as f:\n",
    "        f.write(resp.read())\n",
    "\n",
    "zf = zipfile.ZipFile(local_filename, 'r')\n",
    "\n",
    "ca_name = 'CA.TXT'\n",
    "field_names = ['State', 'Sex', 'Year', 'Name', 'Count']\n",
    "with zf.open(ca_name) as fh:\n",
    "    babynames = pd.read_csv(fh, header=None, names=field_names)\n",
    "\n",
    "babynames.sample(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Goal 1: Find the most popular baby name in California in 2018</p>\n"
   ]
  },
  {
   "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</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>221154</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>2018</td>\n",
       "      <td>Emma</td>\n",
       "      <td>2741</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>382082</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2018</td>\n",
       "      <td>Noah</td>\n",
       "      <td>2567</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>221155</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>2018</td>\n",
       "      <td>Mia</td>\n",
       "      <td>2497</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>221156</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>2018</td>\n",
       "      <td>Olivia</td>\n",
       "      <td>2464</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>382083</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2018</td>\n",
       "      <td>Liam</td>\n",
       "      <td>2411</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year    Name  Count\n",
       "221154    CA   F  2018    Emma   2741\n",
       "382082    CA   M  2018    Noah   2567\n",
       "221155    CA   F  2018     Mia   2497\n",
       "221156    CA   F  2018  Olivia   2464\n",
       "382083    CA   M  2018    Liam   2411"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames[babynames[\"Year\"] == 2018].sort_values(by = \"Count\", ascending = False).head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h2 id=\"Goal-2:-Find-baby-names-that-start-with-j.\">Goal 2: Find baby names that start with j.<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Goal-2:-Find-baby-names-that-start-with-j.\">¶</h2>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Approach1: Use Basic Python Syntax"
   ]
  },
  {
   "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</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1910</td>\n",
       "      <td>Josephine</td>\n",
       "      <td>66</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1910</td>\n",
       "      <td>Jean</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1910</td>\n",
       "      <td>Jessie</td>\n",
       "      <td>32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>59</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1910</td>\n",
       "      <td>Julia</td>\n",
       "      <td>28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1910</td>\n",
       "      <td>Juanita</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>387597</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2019</td>\n",
       "      <td>Joseantonio</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>387598</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2019</td>\n",
       "      <td>Jovian</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>387599</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2019</td>\n",
       "      <td>Jujhar</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>387600</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2019</td>\n",
       "      <td>Jullian</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>387601</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2019</td>\n",
       "      <td>June</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>33400 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year         Name  Count\n",
       "16        CA   F  1910    Josephine     66\n",
       "44        CA   F  1910         Jean     35\n",
       "46        CA   F  1910       Jessie     32\n",
       "59        CA   F  1910        Julia     28\n",
       "66        CA   F  1910      Juanita     25\n",
       "...      ...  ..   ...          ...    ...\n",
       "387597    CA   M  2019  Joseantonio      5\n",
       "387598    CA   M  2019       Jovian      5\n",
       "387599    CA   M  2019       Jujhar      5\n",
       "387600    CA   M  2019      Jullian      5\n",
       "387601    CA   M  2019         June      5\n",
       "\n",
       "[33400 rows x 5 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "j_names = babynames[[x[0] == 'J' for x in babynames[\"Name\"]]]\n",
    "j_names"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"Approach-2:-Use-the-Series.str-methods.\">Approach 2: Use the Series.str methods.<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Approach-2:-Use-the-Series.str-methods.\">¶</h3>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    False\n",
       "1    False\n",
       "2    False\n",
       "3    False\n",
       "4    False\n",
       "5    False\n",
       "6    False\n",
       "7    False\n",
       "8    False\n",
       "9    False\n",
       "Name: Name, dtype: bool"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "starts_with_j = babynames[\"Name\"].str.startswith('J')\n",
    "starts_with_j.head(10)"
   ]
  },
  {
   "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>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>49490</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1964</td>\n",
       "      <td>Julia</td>\n",
       "      <td>368</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>378939</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2016</td>\n",
       "      <td>Jailen</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>365027</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2012</td>\n",
       "      <td>Jairo</td>\n",
       "      <td>68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>342967</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2004</td>\n",
       "      <td>Jevon</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>170080</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>2005</td>\n",
       "      <td>Jarely</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year    Name  Count\n",
       "49490     CA   F  1964   Julia    368\n",
       "378939    CA   M  2016  Jailen      5\n",
       "365027    CA   M  2012   Jairo     68\n",
       "342967    CA   M  2004   Jevon     12\n",
       "170080    CA   F  2005  Jarely     15"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames[babynames[\"Name\"].str.startswith('J')].sample(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>158295</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>2002</td>\n",
       "      <td>Madysen</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>188511</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>2009</td>\n",
       "      <td>Cadance</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>216803</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>2016</td>\n",
       "      <td>Sade</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>381123</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2017</td>\n",
       "      <td>Madhav</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>383778</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2018</td>\n",
       "      <td>Konrad</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year     Name  Count\n",
       "158295    CA   F  2002  Madysen     14\n",
       "188511    CA   F  2009  Cadance      6\n",
       "216803    CA   F  2016     Sade      6\n",
       "381123    CA   M  2017   Madhav      8\n",
       "383778    CA   M  2018   Konrad     10"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames[babynames[\"Name\"].str.contains('ad')].sample(5)"
   ]
  },
  {
   "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>Name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>[M, ry]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[Helen]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>[Dorothy]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>[M, rg, ret]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>[Fr, nces]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Name\n",
       "0       [M, ry]\n",
       "1       [Helen]\n",
       "2     [Dorothy]\n",
       "3  [M, rg, ret]\n",
       "4    [Fr, nces]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames[\"Name\"].str.split('a').to_frame().head(5)"
   ]
  },
  {
   "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</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>251270</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1951</td>\n",
       "      <td>Robert</td>\n",
       "      <td>6169</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>235120</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1926</td>\n",
       "      <td>Herbert</td>\n",
       "      <td>136</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>352976</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2008</td>\n",
       "      <td>Robert</td>\n",
       "      <td>1000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>228625</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1911</td>\n",
       "      <td>Robert</td>\n",
       "      <td>153</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>249831</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1949</td>\n",
       "      <td>Delbert</td>\n",
       "      <td>41</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year     Name  Count\n",
       "251270    CA   M  1951   Robert   6169\n",
       "235120    CA   M  1926  Herbert    136\n",
       "352976    CA   M  2008   Robert   1000\n",
       "228625    CA   M  1911   Robert    153\n",
       "249831    CA   M  1949  Delbert     41"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames[babynames[\"Name\"].str.endswith('ert')].sample(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h2 id=\"Goal-3:-Sort-names-by-their-length.\">Goal 3: Sort names by their length.<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Goal-3:-Sort-names-by-their-length.\">¶</h2>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Suppose we want to sort all baby names in California by their length.</p>\n",
    "<p>As before, there are ways to do this using only lecture 5 content. For example, the montrosity below was concocted during the Sp19 version of this class.</p>\n"
   ]
  },
  {
   "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</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>102493</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1986</td>\n",
       "      <td>Mariadelosangel</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>301497</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1987</td>\n",
       "      <td>Franciscojavier</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>302930</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1988</td>\n",
       "      <td>Franciscojavier</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>305837</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1989</td>\n",
       "      <td>Franciscojavier</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>310744</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1991</td>\n",
       "      <td>Ryanchristopher</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year             Name  Count\n",
       "102493    CA   F  1986  Mariadelosangel      5\n",
       "301497    CA   M  1987  Franciscojavier      5\n",
       "302930    CA   M  1988  Franciscojavier     10\n",
       "305837    CA   M  1989  Franciscojavier      6\n",
       "310744    CA   M  1991  Ryanchristopher      7"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames.iloc[[i for i, m in sorted(enumerate(babynames['Name']), key=lambda x: -len(x[1]))]].head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"Approach-1:-Create-a-temporary-column.\">Approach 1: Create a temporary column.<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Approach-1:-Create-a-temporary-column.\">¶</h3>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Create a new series of only the lengths. Then add that series to the dataframe as a column. Then sort by that column. Then drop that column.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "      <th>name_lengths</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1910</td>\n",
       "      <td>Mary</td>\n",
       "      <td>295</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1910</td>\n",
       "      <td>Helen</td>\n",
       "      <td>239</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1910</td>\n",
       "      <td>Dorothy</td>\n",
       "      <td>220</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1910</td>\n",
       "      <td>Margaret</td>\n",
       "      <td>163</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1910</td>\n",
       "      <td>Frances</td>\n",
       "      <td>134</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  State Sex  Year      Name  Count  name_lengths\n",
       "0    CA   F  1910      Mary    295             4\n",
       "1    CA   F  1910     Helen    239             5\n",
       "2    CA   F  1910   Dorothy    220             7\n",
       "3    CA   F  1910  Margaret    163             8\n",
       "4    CA   F  1910   Frances    134             7"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "#create a new series of only the lengths\n",
    "babyname_lengths = babynames[\"Name\"].str.len()\n",
    "\n",
    "#add that series to the dataframe as a column\n",
    "babynames[\"name_lengths\"] = babyname_lengths\n",
    "babynames.head(5)\n",
    "\n"
   ]
  },
  {
   "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</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "      <th>name_lengths</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>310744</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1991</td>\n",
       "      <td>Ryanchristopher</td>\n",
       "      <td>7</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>302930</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1988</td>\n",
       "      <td>Franciscojavier</td>\n",
       "      <td>10</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>333388</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2000</td>\n",
       "      <td>Franciscojavier</td>\n",
       "      <td>6</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>102493</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1986</td>\n",
       "      <td>Mariadelosangel</td>\n",
       "      <td>5</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>316422</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1993</td>\n",
       "      <td>Ryanchristopher</td>\n",
       "      <td>5</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year             Name  Count  name_lengths\n",
       "310744    CA   M  1991  Ryanchristopher      7            15\n",
       "302930    CA   M  1988  Franciscojavier     10            15\n",
       "333388    CA   M  2000  Franciscojavier      6            15\n",
       "102493    CA   F  1986  Mariadelosangel      5            15\n",
       "316422    CA   M  1993  Ryanchristopher      5            15"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "#sort by the temporary column\n",
    "babynames = babynames.sort_values(by = \"name_lengths\", ascending=False)\n",
    "babynames.head(5)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>310744</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1991</td>\n",
       "      <td>Ryanchristopher</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>302930</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1988</td>\n",
       "      <td>Franciscojavier</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>333388</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2000</td>\n",
       "      <td>Franciscojavier</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>102493</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1986</td>\n",
       "      <td>Mariadelosangel</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>316422</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1993</td>\n",
       "      <td>Ryanchristopher</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year             Name  Count\n",
       "310744    CA   M  1991  Ryanchristopher      7\n",
       "302930    CA   M  1988  Franciscojavier     10\n",
       "333388    CA   M  2000  Franciscojavier      6\n",
       "102493    CA   F  1986  Mariadelosangel      5\n",
       "316422    CA   M  1993  Ryanchristopher      5"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#drop the temporary column\n",
    "babynames = babynames.drop(\"name_lengths\", axis = 1)\n",
    "babynames.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>We can also use the Python map function if we want to use an arbitrarily defined function. Suppose we want to sort by the number of occurrences of \"dr\" plus the number of occurences of \"ea\".</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>101964</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1986</td>\n",
       "      <td>Deandrea</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>297086</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1985</td>\n",
       "      <td>Deandrea</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>131014</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1994</td>\n",
       "      <td>Leandrea</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>115943</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1990</td>\n",
       "      <td>Deandrea</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>108718</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1988</td>\n",
       "      <td>Deandrea</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year      Name  Count\n",
       "101964    CA   F  1986  Deandrea      6\n",
       "297086    CA   M  1985  Deandrea      6\n",
       "131014    CA   F  1994  Leandrea      5\n",
       "115943    CA   F  1990  Deandrea      5\n",
       "108718    CA   F  1988  Deandrea      5"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "def dr_ea_count(string):\n",
    "    return string.count('dr') + string.count('ea')\n",
    "\n",
    "#create the temporary column\n",
    "babynames[\"dr_ea_count\"] = babynames[\"Name\"].map(dr_ea_count)\n",
    "\n",
    "#sort by the temporary column\n",
    "babynames = babynames.sort_values(by = \"dr_ea_count\", ascending=False)\n",
    "\n",
    "#drop that column\n",
    "babynames = babynames.drop(columns=\"dr_ea_count\")\n",
    "babynames.head(5)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"Approach-2:-Generate-an-index-sorted-in-the-desired-order.\">Approach 2: Generate an index sorted in the desired order.<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Approach-2:-Generate-an-index-sorted-in-the-desired-order.\">¶</h3>\n"
   ]
  },
  {
   "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</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>30787</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1952</td>\n",
       "      <td>Luann</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>68880</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1973</td>\n",
       "      <td>Dorinda</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>69646</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1974</td>\n",
       "      <td>Graciela</td>\n",
       "      <td>73</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>288408</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1981</td>\n",
       "      <td>Nicolas</td>\n",
       "      <td>190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>124606</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1993</td>\n",
       "      <td>Kourtney</td>\n",
       "      <td>41</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year      Name  Count\n",
       "30787     CA   F  1952     Luann     11\n",
       "68880     CA   F  1973   Dorinda      6\n",
       "69646     CA   F  1974  Graciela     73\n",
       "288408    CA   M  1981   Nicolas    190\n",
       "124606    CA   F  1993  Kourtney     41"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#let's start over by first scrambling the order of babynames\n",
    "babynames = babynames.sample(frac=1)\n",
    "babynames.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Another approach is to take advantage of the fact that .loc can accept an index. That is:</p>\n",
    "<ul>\n",
    "<li>df.loc[idx] returns df with its rows in the same order as the given index.</li>\n",
    "<li>Only works if the index exactly matches the DataFrame.</li>\n",
    "</ul>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>The first step was to create a sequence of the lengths of the names.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "30787     5\n",
       "68880     7\n",
       "69646     8\n",
       "288408    7\n",
       "124606    8\n",
       "Name: Name, dtype: int64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "name_lengths = babynames[\"Name\"].str.len()\n",
    "name_lengths.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>The next step is to sort the new series we just created.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "239912    2\n",
       "81596     2\n",
       "361057    2\n",
       "344551    2\n",
       "115283    2\n",
       "Name: Name, dtype: int64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "name_lengths_sorted_by_length = name_lengths.sort_values()\n",
    "name_lengths_sorted_by_length.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Next, we pass the index of the sorted series to the loc method of the original dataframe.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index([239912,  81596, 361057, 344551, 115283,   6157, 239372, 302824, 240922,\n",
       "       252502,\n",
       "       ...\n",
       "       310744, 301497, 326250, 102493, 302930, 323115, 333388, 310865, 328420,\n",
       "       305837],\n",
       "      dtype='int64', length=387781)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "index_sorted_by_length = name_lengths_sorted_by_length.index\n",
    "index_sorted_by_length"
   ]
  },
  {
   "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</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>239912</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1934</td>\n",
       "      <td>Al</td>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81596</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1979</td>\n",
       "      <td>Jo</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>361057</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2010</td>\n",
       "      <td>Cy</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>344551</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2005</td>\n",
       "      <td>Ty</td>\n",
       "      <td>198</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>115283</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1990</td>\n",
       "      <td>Jo</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year Name  Count\n",
       "239912    CA   M  1934   Al     18\n",
       "81596     CA   F  1979   Jo     20\n",
       "361057    CA   M  2010   Cy      6\n",
       "344551    CA   M  2005   Ty    198\n",
       "115283    CA   F  1990   Jo      7"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames.loc[index_sorted_by_length].head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Note we can also do this all in one line:</p>\n"
   ]
  },
  {
   "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</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Year</th>\n",
       "      <th>Name</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>239912</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>1934</td>\n",
       "      <td>Al</td>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81596</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1979</td>\n",
       "      <td>Jo</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>361057</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2010</td>\n",
       "      <td>Cy</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>344551</th>\n",
       "      <td>CA</td>\n",
       "      <td>M</td>\n",
       "      <td>2005</td>\n",
       "      <td>Ty</td>\n",
       "      <td>198</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>115283</th>\n",
       "      <td>CA</td>\n",
       "      <td>F</td>\n",
       "      <td>1990</td>\n",
       "      <td>Jo</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       State Sex  Year Name  Count\n",
       "239912    CA   M  1934   Al     18\n",
       "81596     CA   F  1979   Jo     20\n",
       "361057    CA   M  2010   Cy      6\n",
       "344551    CA   M  2005   Ty    198\n",
       "115283    CA   F  1990   Jo      7"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames.loc[babynames[\"Name\"].str.len().sort_values().index].head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"Goal-4:-Name-whose-popularity-has-changed-the-most.\">Goal 4: Name whose popularity has changed the most.<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Goal-4:-Name-whose-popularity-has-changed-the-most.\">¶</h3>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>First we need to define change in popularity.</p>\n",
    "<p>For the purposes of lecture, let’s stay simple and use the AMMD (absolute max/min difference): max(count) - min(count).</p>\n",
    "<p>To make sure we understand this quantity, let's consider the name Jennifer.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "65211     6064\n",
       "32821      412\n",
       "30102      350\n",
       "45783     1257\n",
       "275464      16\n",
       "Name: Count, dtype: int64"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "jennifer_counts = babynames.query(\"Name == 'Jennifer'\")[\"Count\"]\n",
    "jennifer_counts.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>The AMMD for Jennifer is 6,059, as seen below:</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6059"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "max(jennifer_counts) - min(jennifer_counts)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "def ammd(series):\n",
    "    return max(series) - min(series)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6059"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ammd(jennifer_counts)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"Approach-1:-Naive-For-Loop\">Approach 1: Naive For Loop<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Approach-1:-Naive-For-Loop\">¶</h3>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>As a first approach, we can try to use a for loop.</p>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Answer below. Note that we only used the first 100 names because otherwise the code takes ages to complete running.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Aadan        2\n",
       "Aadarsh      0\n",
       "Aaden      148\n",
       "Aadhav       2\n",
       "Aadhira      4\n",
       "dtype: int64"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "#build dictionary where entry i is the ammd for the given name\n",
    "#e.g. ammd[\"jennifer\"] should be 6061\n",
    "ammd_of_babyname_counts = {}\n",
    "for name in sorted(babynames[\"Name\"].unique())[0:100]:\n",
    "    counts_of_current_name = babynames[babynames[\"Name\"] == name][\"Count\"]\n",
    "    ammd_of_babyname_counts[name] = ammd(counts_of_current_name)\n",
    "    \n",
    "#convert to series\n",
    "ammd_of_babyname_counts = pd.Series(ammd_of_babyname_counts) \n",
    "ammd_of_babyname_counts.head(5)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"Approach-2:-Use-groupby.agg\">Approach 2: Use groupby.agg<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Approach-2:-Use-groupby.agg\">¶</h3>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Instead, we can use the very powerful groupby.agg operation, which allows us to simply and efficiently compute what we want.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "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>Year</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Name</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Aadan</th>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aadarsh</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aaden</th>\n",
       "      <td>12</td>\n",
       "      <td>148</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aadhav</th>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aadhira</th>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Year  Count\n",
       "Name                \n",
       "Aadan       6      2\n",
       "Aadarsh     0      0\n",
       "Aaden      12    148\n",
       "Aadhav      5      2\n",
       "Aadhira     1      4"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames.drop(columns=['State', 'Sex']).groupby(\"Name\").agg(ammd).head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Note that the result includes both a Year and Count column. The Count column is what we want, namely the AMMD for the name in that row. To check your understanding, try to figure out what the Year column represents.</p>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>To understand how groupby works, consider the visual diagram below. The <code>groupby</code> function clusters rows from the original dataframe into groups (which I call subframes). The <code>agg</code> function then condenses each subframe into a single representative row using the provided function f.</p>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p><img alt=\"groupby_picture.png\" src=\"data:image/png;base64,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\"/></p>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h2 id=\"Some-Additional-Groupby-Puzzles\">Some Additional Groupby Puzzles<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Some-Additional-Groupby-Puzzles\">¶</h2>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Groupby puzzle #1: To test your understanding, try to interpret the result of the code below.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnQAAAHMCAYAAABcGDVKAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAACHYklEQVR4nO3de3zT5fn/8VeSNumJHihQDq1UoK1yVMGiIiBHDwzlpHNfkTkYbk6UbWwehjideJhHZG7+5pQ5wXmogMhEBQWZbgqiE1SUFhEoIAVK03OTJvn8/kgTjOXQYw7t+/l47OFI7nx652qaXLnuk8lutxuIiIiISMQyh7oDIiIiItI8SuhEREREIpwSOhEREZEIp4ROREREJMIpoRMRERGJcEroRERERCKcEjoRERGRCKeETkRERCTCKaGTegzDwO12YxjaczoYFO/gU8yDTzEPPsU8+EIZcyV0Uo/D4WDXrl04HI5Qd6VdULyDTzEPPsU8+BTz4AtlzJXQiYiIiEQ4JXQiIiIiEU4JnYiIiEiEU0InIiIiEuGU0ImIiIhEuKhQd0BERERCw+Px4HK5Qt2NNqO2ttb/X7P51DWzqKioBrVrCCV0IiIi7YxhGJSUlFBZWRnqrrQphmFgsVgoKSnBZDI16DHx8fGkpKQ0uP2JKKETERFpZ3zJXFJSEjabrdnJhHh5PB5qa2uJjo4+ZeXNMAwcDgelpaUAdOzYsVk/WwmdiIhIO+LxePzJXGJiYqi706Z4PB4ArFZrg4ZSbTYbAKWlpSQnJzdr+FWLIkRERNoR35w5XzIhoeX7PTR3LqMSOhERkXZIw6zhoaV+D0roRERERCKcEjoRERGRCKeETkRERCLamjVrmDx5MpmZmXTu3JmBAwfyy1/+kp07d4akP5999hn3338/VVVVQfuZSuhEREQkYt1111383//9H4mJiTz++OO8+uqr3HLLLezYsYOf/OQnIenTZ599xh//+Eeqq6uD9jO1bYmIRIRD1W6uXFeM24CcpChykqPISY5mYMdoTk9sm29ldocHu9NDZoe2+fwixe5yF93jLFgtWkQQbtauXcuiRYv47W9/y/z58/23Dxs2jOnTp/Pmm2+GsHfBpQqdiESE5buq2Vpcy+dHa1n+TTX3/a+cH284ytnLi3irsCbU3Wtx5bUeRr52iLNeKWLa2iO8f9CBYRih7la7s7awhrNeKeKeT8pC3RU5jieeeIIuXbpwyy23HPf+Sy65BICamhp+97vfccYZZ5CWlsaFF17I6tWrA9pOmDCBH/7whwG3bdu2jeTkZN577z3/bcnJyTz++OPcf//9ZGVl0atXL37xi1/4T9148cUXmTNnDgC9e/cmOTmZAQMGtNhzPhF97RORiPDutw4ApmfFkZUUxVd2F+8fdFBY4WbjtzVcnBET4h62rHs+LmNPhRuAt/c7eHu/g3M7RzN3QAcuOy0Gs7acCIpXvvHOgfp33euvraus9YTk58ZHN76+5HK52LRpE5dffjnR0dEnbTt79mzeeecd7rjjDrKzs3nxxReZMWMGzz//PJdddlmjf/bf/vY3zj//fJ588kl27tzJnXfeSZcuXbjzzjsZO3Ys8+bN45FHHmH58uUkJiZitVob/TMaSwmdiIS9Wo/Bfw96P1B/ekY8Z3Xyvjk+l1/Jzf+x82VJ2zpcfMthJ3/70vtt/4kLk/nfkVqWFVTy0eFapq8/yozsOBYPSwlxL9s+wzDYeMD7uisodeExjDafSPdY9m1Ifq79Jz0a/ZijR4/icDhIT08/abvPP/+c1atX89hjj/nn1I0dO5a9e/fyxz/+sUkJXVpaGn/729/819q6dSurVq3izjvvpFOnTpx++ukAnHXWWaSmpjb6+k2hIVcRCXufHHZSXmuQYjMxMPXYN/Ezk73//yt7bai61uJqPQY3/6cEA7i6dyzTs+J55PxkPruyK7POiAfgvwedoe1kO/Gl3UVRtbdiVeUyOFDpDnGP5HhOtTHvBx98AMCkSZMCbp88eTLbtm3zD5U2xqhRowL+fcYZZ3DgwIFGX6clqUInImFvY91w14hutoAKSU6y9y3s2yoPJQ4PKbbI+Y66u9xFQrSJTjGWgNv/9HkF20tcpNrM3Jub5L+9S6yFn54RzzNfVXLUEZphsfZmw4HAYdaCUhfpCW37Y3P/9G6h7kKDdezYkZiYGPbt23fSdna7nejoaFJSAqvaXbp0wTAMSktLiY+Pb9TPTkpKCvh3dHQ0Dkdoh+Xb9itTRNqEd+s+WC/qFjhPLtFqJiPBQmGFmy9Larmga9PPply/vwarxcSFzbhGQ31T5uK8V4sAuC47nl8N7EDXOAtfl7r446feyff3DU0i9XvJXse6hLXE4cHtMbCY2/bwX6i9uz9wsU1+qYtRjR8ZjChNmcsWKlFRUQwdOpSNGzficrmIijp+SpOSkkJtbS12u53k5GT/7YcOHcJkMvmTs5iYGJzOwOq33W5vre63uEb/5tasWcOYMWNIT08nJyeH6667jt27d9dr99xzzzF48GDS0tIYNmzYcZcOl5aWMmfOHDIzM0lPT2fGjBkcPHiwXrtNmzYxbtw4unbtSv/+/Vm0aJFWe4m0IYZhUHKCqlNlrYePDnvfZEd2r59s9a2r0n3ZjGHXT484mbK2mCvePMJnR1t/+Pad/TU43OBww1+/rOSsVw7yu812bv5vCQ43jOpu46pesfUe1zHG+5ZtAKVOVelak8Nt8J8i7+tuXA/v625naduaq9kW3HjjjRQVFfHwww8f9/61a9dy3nnnAfDqq68G3Ldq1SoGDhzor851796dgoKCgPxiw4YNTeqXbxFETU3wVuA3KqF77733mD59Ojk5OSxbtoz777+fzz//nMmTJwdsnrd8+XLmzp3L5MmTycvLIzc3l+nTp/PRRx8FXG/mzJls2LCBxx57jKeeeoqdO3cybdo0XK5jfzS7du1i6tSppKWl8dJLL3HDDTdw33338cQTTzTzqYtIuHjiiwpO/+e3/LOg/lyWD4qc1HogI8HC6R0s9e4/M8U7j66pCyMMw+D3W7xVMbcBv/xPCW5P635h/PCQN1GYlBlLbmcrNW74yxeV/Oegk1iLiccuSD7uvKBos4nEaO/txRp2bVWbDzmpchl0iTVzxene5DpfCV3YGT9+PHPnzuWBBx7gJz/5CatXr+a///0vL7zwAhMmTOCee+6hf//+TJw4kfnz5/Pkk0/y9ttvc/3117Np0yZuu+02/7WuuOIK9u3bxy233MK7777LH//4R1atWtWkfmVnZwPw9NNPs2XLFr744osWeb4n06gh1xUrVpCRkcGf//xn/5tNp06duPzyy/nf//7HBRdcAMD999/P1KlTueOOOwAYMWIEX3zxBQ8++CB5eXkAbN68mXfeeYcVK1YwevRoALKyssjNzWX16tVMnjwZgMWLF5OSksKSJUuwWq2MHDmS4uJiHn74Ya6//npsttYfHhGR1lPl8vDYtgoA7vtfOVf2jiP6O0OJvvlzI7vZjpvknFG3MGJ7SdMqaxsOONj4rQOrGWwWEx8fqeWZryq5vm9Ck653KoZh8EHdooaZZ8QzvKuV9Qcc3PdJGR8fqeXuIYkn3Ui4Y4yZslo3R2s8kHTCZtJM7x7wVlYu6mYjO8n7+ygobTuLb9qSu+++m9zcXP72t78xZ84cqqqq6NatG2PGjOGmm24C4KmnnuIPf/gDixYtoqSkhKysLP7xj39w6aWX+q8zduxY/vCHP/DUU0/xz3/+k3HjxvHYY49xxRVXNLpPAwcO5LbbbmPp0qU8/vjj9OjRg88++6zFnvPxNCqhq62tJSEhIeBNNTExEcBfoty9ezc7d+7krrvuCnjslClTuPPOO3E4HNhsNtatW0dSUlLASpGsrCwGDBjA2rVr/Qnd22+/zQ9+8IOAPVymTJnCo48+yubNmxk+fHjjnrGIhJUXdlb5J/nvq3ST93UV/5d1bIKyb9uIkd2O/+XtzJRjQ66GYZxyxdt3eQyD328pB+CnZ8bTOzGKeR+Ucs8nZUzoGUuP+PoVweYqrHSzv8pNlAmGdI7GZDIxpkcMo7vbKHUaJJ9iYUdHm5nd5W5V6FqZb0HERd1tZCV5vzQcqPJQXuuhQwTNM2svJkyYwIQJE054f2xsLPfffz/333//Sa9z8803c/PNNwfc9v15dMebV/eLX/yCX/ziF3g8x/4ub7vttoAKYGtrVEL3f//3f7z44os8/fTTXHnllZSUlHDPPfcwcOBA/xh1fn4+cKzc6JOTk4PT6WTPnj1kZ2dTUFBAVlZWvTffnJwcCgoKAKisrGTfvn31rpWdnY3JZKKgoOCECd2gQYNO+Dxef/11evToEfIVKeHKNyn0+5NDpXW053h7DIM/f+5NqM5IsvBVqZvHtpUzKd2M2WSi2OFhW92ctvM6Hn8+ymk2A7MJShwGe+3VpMWe+sPWF+uXv67is6O1dIg2MSfHSrLVxAsFUWw54uI3/y3m78MTW/DZer23z/u+M7BjFGaXk5rvjOLFAKeaclNXkKSowkFNTeQsioik13mJw8P/jnhfd+enQqzhpJPNxBGHwReHqjgrNTLWE54o5rW13i8/Ho8nIAGR5vMVt3zxbQiPx4NhGDgcjuM+xmq1Yjaf+n2tUa/KCy64gGXLljF79mx+85vfADBgwACWL1+OxeL9JuvLXL+/pNe3sqSkpMTf7vttfO18bUpLS497LavVSlxcnL9dU3g8HgoLC5v8+PagqKgo1F1oV9pjvDcWW9hVbqODxeDR7Aqu/CSGgjI3z2/9lotS3bx9xALY6B3noebIfk70F5seE8PeajPvFXzL0JSGvYk6PPDHbVWAmWu7O6g8tJ9KYF6GienFMbyxr5alnx7gotQT7z1W64FHv4mmm81gRnrD5let/yYaiObMmGoKCxt/nJTNZQWi+KaohMLoyJvTFQmv83eOWDCwcXqcB1fxAQqLIcNm44jDwubdh0itiqz96I4Xc4vFQm2thpBbS2NiW1tbi8vlOu6iUIDMzMyWT+g2bdrEz372M2bMmMHFF19MSUkJDz74IFdddRVvvPEGsbH1V2WFytatW096v2EYZGRkBKk3kcXpdFJUVERaWlpQjitp79pzvF/ZUQq4uC47lnP6dGJWZRWLt1fzz0PxTB+UyPZvKwEHYzLiyMjofMLrDNhdzt59To5aO5KRcer3IafTyaOfFPOtw0y3WDO/ye1KXJS32pUBzHFU8fj2ah7dHcukfkknHGJ7/IsqXvnWuyDsrPSOTMg49ZzeLz6zA27G9upIRnrjf98ZhyvhcA2e2EQyMhq3d1YoRdLrfPvBCsDBmPRjr7v+31bwvzIHJdHJZGTEhbaDDXSimNfW1lJSUkJ0dHTY/y4ijWEY1NbWEh0d3ajpH1FRUXTu3Pm4R5j5CmanvEaDfxpw6623MmLECO69917/bUOGDKF///689NJLXHfddf5KXFlZGWlpaf52vsqdb2O/5ORk9u/fX+9n2O12fxtfZa6sLPBbrNPppKqqqt4mgY1hMpmIiWlbZz+2NKvVqhgFUXuL9yeHnXx42EW0GX4xMJmYGAs3DYzmqR3V/K/YxUd2M+8f8lagRmfEnTQ2/To5eX2fk4IKGhTDUqeHvxd63zhvPyeRjgmBSeBtg22sLnSyq9zNXVsdPDGs/qrTXWUuHv3i2Or+335UxbAeCXSNO/Gbr93h4atSb3VneHo8MTGNn6PXOc4J1FDqMkfk6yUSXuf/LrIDMPa0Y6+7M1Jd8LWDXZVG2Pf/+74fc7PZjMlkwmw2N6jyIw3nGzL1xbchfL8Pm83WrAS7Ub/JHTt2MGDAgIDbevToQWpqKt988w1wbO6cby6dT35+PlarlczMTMC7AOL7+7342mVlZQEQHx9Penp6vWv5HudrJyKR54kvvCtbp54eS7e6JKhzrIVr6xZE3LbJzjflbiwmGHaKzX771k0sa+hedH/5soZSl4nsRAv/16d+tSU2ysSiYSmYTfB8QRVPfxW4nYphGPzqv3Ycbu9ijYEdoznq8HDT+yUn3SNzU912JVlJUfVOiGgo32bDOi2idewud7G73Lto5buvu6zEupWu9sgb5j4R7ecaHlrq99CohC4jI6PeUObevXspLi7mtNNOA7xjvX369Km3d8vKlSsZOXKkP/scN24cdrudjRs3+tvs3LmTbdu2MX78eP9tY8eOZc2aNQHj0StXriQpKYmhQ4c2pvsiEib2VrhYtdtb3bqxf4eA++b0T8Bigu11+8oN6Ww95apC30rXr0q8B6ifjNtj8M9d3pUHtw6MJeoEpy2M6Gbj7sHeRRG3byrlvW+PLaJ68etqNn7rIMYCiy5I5qmRKdgssG6/gyU7Tnwu5IdF3muc16Xp38JT6zYXVkLXOjbs9/6Ozu0S+LrLrtvAemeZq9X3KWxtvhMVtDAwPPh+Dyc66aKhGvXon/zkJ9x+++3ceuutXHrppRw9epSHH36Yzp07+7cZAe9S3dmzZ5OZmcnw4cNZuXIlW7ZsYc2aNf42ubm5jBkzhjlz5rBw4UJsNhv33HMP/fr1Y+LEif52N998M3l5ecyaNYtZs2axfft2Fi9ezIIFCzT2LxKh/t/2CtyGt7o1oGPgnJGeHaKY2iuWl7/2JnzHOx3i+3olRmE1Q4XLoLDCTc+T7OP2/kEHh2sMkqIMxnU/+XvInP4JfHa0lpd3VXPdhqOsn9iZhGgT8zd7F2zdelYip9dVbu4anMTtm0u5Y3MZI7od2+riu3wbCp+X1vT3Lt95tUdrlNC1hg11+8+N+t7rLiPegs3iPd1jb4Xb/3uPRGazmfj4eP/CQ5vt+Hs8SuN5PB5/AepUQ66+la2+s2SbO/zdqFfkz3/+c2w2G8888wzLli0jISGBc889l2effZaOHTv6202bNo2qqioWLVrEokWL6NOnD8uWLSM3NzfgekuWLGH+/PnMnTsXt9vNqFGjePDBBwOy1F69erFixQrmz5/PVVddRadOnbj99tuZM2dOs564iIRGmdPD0vwqwJswHc8vB3Q4ltCdYP+574o2m8hKiuKLEhdf2mtPmtAt/8Z73VGpbqyWk3+ImUwmHh+Wwo5SF1uLa7lm/VFykqI46vDQNyUqoP8/6xvPW/tqePeAg+v/XcLaCZ0DNkiucRl8XHeE2flpTd8QPbUuodM+dC2vsMLFu3WV2FHdA+fJWcwmeidGsb3ERUGpK6ITOjg2n92X1EnLMAzDf65sQ5Pk+Pj4Zq0J8GnUK9JkMjFz5kxmzpx5yrYzZsxgxowZJ22TlJTEE088ccpjvIYOHcrbb7/dmK6KSJj66LCT8lqD0xIsjO1x/MSmb0o09wxJpLDS3eDhyb4p0d6ErsTFJSdYwO50G7xWN9R7ceeGzYWKjTLx/OiOjFp9mM+P1vL50VpMwOMXpAQkbGaTiT9fmMIFrxbxvyO1PPhpOfPPObaP3afFTpwe6BJrPu4RZg3lO8+1xOHBYxiYVVlpEV+W1DJ17RHKnAa9Ey2c3al+hTU7KZrtJS7yS2sZnxFZCyO+z2Qy0bFjR5KTkwOO25TmcTgcHDx4kM6dOzfoJKuoqKgWW5gS2V8xRCTi7C73fnj0TTn5sv6bBnQ44X3H4z3TtZovT3IE2PoDNdidBl1iTJyd1PAKV3pCFM+N7sjlbx6h1gM/PSOec4+TaPaIt/DY+cnM3FjCI9vKGZduI7eL9039w7qD3s/rYm3W8FbHugqd24Ayp0GyTQldc31Y5OCHbxdT6jTISYpi+fjU486tzPIfAdZ2EiCz2azpSy3It8o1FFvCaL2yiATV7nLvth2ZzahSHc+ZdZPWt59kFeKKXd7q3OWn2TjFaGs956fZePaijsw+M547h5z4BIkpveK4qncsHgOu/3cJ5bXeN/gP/PPnmnf+tM1iIqFuzzwtjGi+N/ZWM+mtI5Q6DXI7W3lzQmfSE45f6/AldPltKKGTtkMJnYgEla9Cd7ID6JvCW6HzHqDuOs4qxCqXhzV7vRPeJ/ds2jfnCT1jeei85FOuun3ovGTS4y3sLndz+6ZSPIbBproVruc3Y0GEj2/YtVgLI5rltd3VTF9/lBo3XJxu49VLUv2LTo4nuw1W6KTtUEInIkHVWhW60xIsxEeZcLjhm/L6H7hrCx1UuLxz985p5bM4k6xm/joiBROwrKCKh7eWY3caxEeZ6q3qbQrfsKsqdE1nGAb3flKG24Af9o5l2ZhU4qJO/pHYpy6hO1LjoUSxlzCjhE5EgsYwDPa0UoXObDKR4xt2Lamf0C3/xruydurpsUHZomFYVxtzB3hXwd73v3LAu6feifa9a4xUf4Uuss4UDSdf2l3sKHVhNcOD5yUHLHA5kYRoMz3qNsEuKNU5qBJelNCJSNCUODyU1XqHQ3ueYJ5Sc/iGXb+/MKLM6WHtPu9w65RewTuH83dnJwZU5Jqz/9x3qULXfCvqtq8Z0yOGJGvDPwqzkjWPTsKTEjoRCRrfcGu3ODOxUS1fJfMtjPj+EWCv763B4fbOgeqfErzF/VaLib+NTMF3ytcFzVwQ4aOErnkMw2BlXcV2yumxp2gdyL/StQ0dASZtg7YtEZGgaa0FET59/RW6wA/bFbvqhlt7BWe49bvOSI7m5XGd+PxoLSO6tVCFLkanRTTHtqO1fF3mJsYCl5zWuP3kfGe6qkIn4UYJnYgEze4Kb4WuZ0LLLojw8Q255pe6yHrhWzI7WMjsEMWGA94Vpo2txrSUEd1sjGjAiRcNpdMimmdl3XDr+PSYU65Y/j7fma5a6SrhRkOuIhI0rV2h6xprZkzd6ROHazx8dLiWvF3VuAwY2DH6uOerRiINuTadYRj++XNTTm/8fErfa2h3uYva42yPIxIqqtCJSNAc27Kkdd56TCYTy8d3wu7wsLvcxZ4KN7vLXRyscnN1n+AthmhtqRpybbJPjtSyt8JNfJSJ8RmNr5p2jzMTH2Wi0mXwTZmL7OS28SVBIp8SOhEJmm/8FbrWGXL1SbaZOctm5axOrfpjQiZFFbom81XnLsmIOeW+c8djMpnokxTF1uJaCkqV0En40JCriASF022wv7J1K3TtRWrdstniGg+GoWG/hvIYBq/WJXSTmzGf8rS6OaD7KrUPoIQPJXQiEhT7Kt14DIixQFqs3nqawzeHzmVAea0SuobafMjJ/io3idEmxvZo3OrW7+oR703o9iuhkzCid1URCYrvLogI9tYhbU1slIm4un382uOwa3GNG4e78Ymsb7j10tNiiGnGPohK6CQcKaETkaDwLYjoqeHWFuFf6dqOFka4PQYLPy6j9wsH+fGGo41+7KrdTV/d+l3pdQndgSoldBI+lNCJSFD4KnSnt/KCiPaiYzvbi+5QtZvJa4t5eJv3XNw3C2v4yt7w81Q3fuugqNpDstXEqO7N2xOwe5zm0En4UUInIkHR2nvQtTf+0yLaQUL3n4MORqw6xL+/dRAfZaJv3ea+/9hR2aDHG4bBvZ+UAXBV7zisluYN+fuGXL+tdOPWXnQSJpTQiUhQHNuDThW6luA/LaKND7ku+aqSy988wsFqD2ckR7F+YmfuPjcJgBd2VlHjOnVC9dqeGj4+Ukt8lInfDOrQ7D51jbNgNnkXpRxu4/GXyKGETkRanWEYqtC1sPZwWkRRlZvbNtlxG3BVr1je+UFncpKjGd3dRnq8BbvT4LU91Se9Rq3H4A8flwIwp38CXWKb/4Uiymyia91KbS2MkHChhE5EWp3daVBWt73Gaa10jmt707EdnBbxzI5KnB7I7WzlryNSiK87d9ViNjEj27uw4dlTDLv+Y0clX5e56RxjZk7/hBbrm2/YVfPoJFwooRORVuerznWNNTdpd36pr61X6GpcBku+8iZrv+iXUG+rm+lZ8ZhN8N8iJ/knWBxRXuvhj596F1HcelYHOkS33GuvR7y30qwKnYQLvbOKSKvTcGvL853nWlzTNhOKvF1VHKnxkB5v4Qc9628C3D3ewsXp3tv/kV913Gs88XkFh2s89E608OOc+BbtX/d4b/wPKKGTMKGETkRa3bE96DTc2lLacoXOMAye3F4BwM/OjCfKfPxVqdfVJWnHWxxRVOXmic+917hzcBLRJ7hGU6lCJ+FGCZ2ItLpvVKFrcW05ofv3tw62l7iIjzJxbfaJK2tje9joEWfhqMPDv/YeWxxR5fKwYEsplS6DwZ2iufw4Fb7mStdpERJmlNCJSKs7tmWJErqW0jHm2LYlhtG29kL7yxfeytr/ZcWRbDvxx5TFbGL6dxZH7K1w8fuPSun70kFe/tqb4N19blKrHDXXQ6dFSJhRQicirU6nRLQ83z50Tg9UNmAvtkixs7SWt/Y5MAE/P/PUq1KnZ8VhNsH7B52c9UoRj39egd1p0DPBwhMXJnNh1+adCnEivtMivq3S5sISHvR1WURaVa3H8G/toApdy4mLMmGzgMPtrdIltOAKzlD6f9u9K1svzoihd9KpXy8ZCVGMS4/hrcIaPAaM7Gbj533jGZ8eg6WF5819V1qsmai6zYUPVnv8FTuRUNG7q4i0qn0VbjwGxFi8H4LSMkwmE6k2MweqPJQ4PPRs/gEIIXe0xs0/d3pXrN7Qt+F7xj1+QTJ5u6oY2yOGM1OiW6t7ASxmE13jLOyrdHOg0q2ETkJOCZ2ItKrvblnSGnOZ2rOUuoSuOAIXRrg8Bvd8XMbWo7UUVbkpqvb4F3j0S4liRDdrg6/VNc7CTf2Dn9H2iPcmdPsr3Zwb9J8uEkgJnYi0qmNblujtpqWlxlgAV0SeFrFqdzWP120r8l3xUSbmn5MYEcn/sdMiXCHuiUgjF0VMmDCB5OTk4/5v+fLl/nbPPfccgwcPJi0tjWHDhvHmm2/Wu1ZpaSlz5swhMzOT9PR0ZsyYwcGDB+u127RpE+PGjaNr167079+fRYsWtbkVXSJtmb9CpyO/Wpxv65JIrND9v7p95q7JimPl+FT+O6kLu37UlcLp3bjstNgQ965hemjrEgkjjfrK/Mgjj1BeXh5w25NPPslrr73GRRddBMDy5cuZO3cu8+bNY8SIEaxcuZLp06fzxhtvcO65x4rSM2fO5KuvvuKxxx7DZrOxcOFCpk2bxrvvvktUlLdbu3btYurUqVx00UXccccdfP7559x9991YLBZuuummZj51EQmG3RXag661+E6LiLS96D4+7OSjw7VEm+H3gxPpEhuZyb5vpau2LpFw0Kh32DPOOKPebT/96U8ZPXo0qampANx///1MnTqVO+64A4ARI0bwxRdf8OCDD5KXlwfA5s2beeedd1ixYgWjR48GICsri9zcXFavXs3kyZMBWLx4MSkpKSxZsgSr1crIkSMpLi7m4Ycf5vrrr8dma53l6CLSco7tQReZH9rhLMW3uXCEDbn+9UtvdW7K6bERm8yBKnQSXpq15GzTpk3s2bOHK6+8EoDdu3ezc+dOJk2aFNBuypQpbNy4EYfDAcC6detISkpi1KhR/jZZWVkMGDCAtWvX+m97++23mTBhAlarNeBapaWlbN68uTldF5Eg2VM35Ko5dC0vNQJPizhU7WHlN95NfxuzkjUc6bQICSfNSuheeeUV4uPjueyyywDIz88HIDs7O6BdTk4OTqeTPXv2AFBQUEBWVla9Sa85OTkUFBQAUFlZyb59++pdKzs7G5PJ5G8nIuGrvNaD3emd85qubR1a3HdPi4gU/9hZQ60Hhnaxclanhq9kDUe+Ct3BKg+12lxYQqzJX5ldLhcrV67k0ksvJT7ee9ae3W4HICkpKaBtcnIyACUlJf5232/ja+drU1paetxrWa1W4uLi/O1OZNCgQSe87/XXX6dHjx7+iqEEcjqdAf+V1tWW4/11qbc6lxRtwupxUlMT4g7VaSsx72Dyxre42kVNuAT3BJxOJ04PPFfg7edP+ljDvs+n0sFkEG2GWg/sKakKuy8tbeV1HklaI+ZWqxWz+dT1tyYndBs2bODIkSNMmzatqZcIKY/HQ2FhYai7EdaKiopC3YV2pS3G+9OjZiCGLlZ3WP69RXrMa8u98T1UVRuW8f2+t49YOOww6Gz1MIhDRECXT6lzdAwHHGY+3X0QIzE8K6WR/jqPRC0Z88zMzNZN6PLy8ujYsSNjxozx3+arxJWVlZGWlua/3Ve5S0lJ8bfbv39/vWva7XZ/G19lrqysLKCN0+mkqqrK3+5Etm7detL7DcMgIyPjpG3aK6fTSVFREWlpaQHzF6V1tOV4O2pqgEpOT7aRkdE51N3xaysx91S4Yaudcrc57N/PHA4HL37qHXmZdUY8p/cMn9dDc5y2o5QDh124EjqRkRFeC/Xayus8krRGzC2WhlV+m5TQVVdXs2bNGq666iqio48ds+Kb75afn09WVpb/9vz8fKxWK5mZmYB3AcS7776LYRgB8+jy8/Pp27cvAPHx8aSnp/vn5fkUFBRgGEbA9ZvCZDIRExPTrGu0dVarVTEKorYY7yKnd1pDz8TwfG6RHvPuFg9gp9oNnigrcVHhe7TaliO1fFlhwWaGn/ZLIiYmvIYnmyq9QxUcdnHYaQ7b11Kkv84jUShi3qS//jfeeIOKiop6w62ZmZn06dOHVatWBdy+cuVKRo4c6c9Wx40bh91uZ+PGjf42O3fuZNu2bYwfP95/29ixY1mzZg21tbUB10pKSmLo0KFN6bqIBFFhhXf1X0aYzS1qKxKiTETXvYuH+9YlT+/wzpeb3NNGpzaSzAH0iPOdFqGVrhJaTarQ5eXlkZ6ezvnnn1/vvttuu43Zs2eTmZnJ8OHDWblyJVu2bGHNmjX+Nrm5uYwZM4Y5c+awcOFCbDYb99xzD/369WPixIn+djfffDN5eXnMmjWLWbNmsX37dhYvXsyCBQtUPhaJAP6ETqdEtAqTyUSqzczBau95rulhugtIRa2HN/d7J4lfl9W2KkXai07CRaMrdHa7nXfeeYepU6ce96y9adOm8fjjj/PKK68wdepUPvzwQ5YtW0Zubm5AuyVLlnDRRRcxd+5cZs+eTe/evcnLy/OfEgHQq1cvVqxYwYEDB7jqqqt44oknuP3225kzZ04TnqqIBJuvapEerz3oWovv+K+SMN6L7u19DmrckB7jYVDHtpXc+xI6nRYhodbod9nk5GQOHTp00jYzZsxgxowZJ22TlJTEE088wRNPPHHSdkOHDuXtt99ubDdFJMRqPYb/Q04VutYTCXvRrdrt3Uh4dCf3cQsBkUwVOgkX4TuDVkQi2rdVbjwGWM3QJVZvNa3FV6E7EqYJXbXLYO0+7/y50altL+nxJXSHqj043dpcWEJH77Ii0ip88+d6xFswt7GqTDjplegdaNleUnuKlqHxzv4aKl0GPeLM9E0Iz6SzOTrFmLGawUDDrhJaSuhEhN3lLg608JCRb/5cRoLmz7WmIZ29C8Q+OhSepwG8tsc73PqDDCttMa83mUx0982j07CrhJASOpF2rqLWw4hVhzj/1SIKK1wtdl1fhS7cjkNqa86tS+i+tLsoc4ZXBczhNnhzr3e4dUJG292ZQPPoJBwooRNp5/ZXuimrNSh1Gtz8HzuG0TLzgPbVJYdaENG60uIsnJZgwQD+dyS8qnQbDzgoqzXoGmtmSKe2W6lVQifhQAmdSDt3+DuT6TcccPDsjqoWuW5hpSp0weKr0n10OLzm0a2qG26d2DO2Tc+j9G0uvF9z6CSElNCJtHO+7S6i6j5v7/iolN3lzR963Vc35HqaKnStzj+P7nD4VOhqPQZr9noTusszY0Pcm9alCp2EAyV0Iu3c4Wrvh9D4jBguSLNS6TKY834JnmYMvRqG8Z0KXdsdagsX53bxJnRbDjlbbMi8ud7/1kGJw6BTjJkL0tru/DlQQifhQQmdSDvnG3JNizXzl+EpxEeZeP+gk799Wdnka5Y4PFS5vIlFDw25troBHaOxmqHY4eGb8vBIKvyrW0+LwWJuu8OtoIROwoMSOpF2zjfkmhpjIbNDFHcPSQTgri1lfF3atKHXvXXDrV1izcREte0P83Bgs5gYlBoNhMewq9tj8K893tWtbX24FY5tzXOkxkOVK7xWGkv7oYROpJ07XONNvjrXHSE184x4RnazUe02uP/TsiZd0zfcmqHqXNB8d9g11N4/6ORwjYdkq4nh3Wyh7k6rS7aaSLR6v7jsCZMKqbQ/SuhE2jnfkVG+hM5sMnHHOd4q3VuFNTiacJyRb0FEuhZEBM25YbIw4tMjTn668SjgXd0a3caHW8G7uXBmXZWuJRYUiTSFEjqRdu5I9bEhV5/BnaPpGmumvNbg3986Gn3Nwsq6Pei0ICJofCtdPz9aG7Jhv/X7a5jwxhEO13gY2DGaOwcnhqQfoZDZwfv3s6dCFToJDSV0Iu2cb1FE59hjbwdmk4nLTvPOfXq9bnJ7Y6hCF3zp8Ra6xppxGfDpkeDvR/fS11Vcta6YSpfByG42/nVpJzrHtp/ff2YHVegktJTQibRjLo9BicOb0HWKCXw7+EHPGADWFNbg9jRu2FVz6ILPZDL5q3Rbgjzs+qfPy/nZv0twGTCtVyx541JJtLavj5eedRW63ZpDJyHSvv7iRCTAUYcHAzABHW2BbwcXdrWRaDVxqNrT6HlZvgqdjv0KLt/CiGDOo3v3QA0LPvIunrmxXwJPjUjBamn78+a+z1eh26MKnYSIEjqRdsy3ICLFZibqe5PXrRYTl6R7q3Sv1x2w3hDVLsM/jOvbzkGCw78wIkgbDNe4DOZ9YAdg1hnx3Jub1KaP+DoZ36KIPRXusNncWdoXJXQi7djh6sAVrt83oad3Ht2/9lQ3+ENqf92CiIQoE8nW9vnhHipndYrGYoKD1Z6gbHK76LNyvi5z0zXWzO/b0QKI48lIsGACqr7zhUYkmJTQibRjxXV70HWKPf5bwZgeNmwW+KbczfaShg0lFX5nQYSpnVZrQiUuykz/jt4Nhrccbt2FEV+Xunh0WzkA9w9Nandz5r7PajH5T4zQwggJhfb9FyjSzvkqCd9fEOGTEG1mVHffsGvDVrtqQURo+YZdNx9u/HYzDWUYBr/50I7T4036J7WD0yAaIlMLIySElNCJtGP+LUtiTpx8TTjNm9D5jnI6lUJtWRJS/pWuh1qvQrfim2o2HHBgs8BD5yWrElunp7YukRBSQifSjvmGXFNPUKEDuPS0GMwm2Ha0tkEr+Pb5KnRaEBESvgrdp8XOJp3ycSqlTg+/21wKwLyBHeiVqN+zT2aCKnQSOkroRNqxUy2KAOgUY+H8NG+SsKYBq10LK7xJX7qGXEOiV6KFjjYzTg98drTlq3R/+LiMomoPfRKjmDugQ4tfP5L5ty6pUIVOgk8JnUg7VuzwnRJx8uRrQt2pEf9qwDy6Qu1BF1Imk8m/H92mQy27H92/9lTzzFeVADxyfhK2drjf3Mkc24tOFToJPiV0Iu3YYf85rid/K/DNo/ugyMmRmhN/WLk9Bgeq6ubQqUIXMkO7HNuPrqXsrXBx4/slANzUP4GRdYtl5Bjfooj9le5WGe4WORkldCLt2OG65OxkQ67gnew9KDUajwEv7Kw6Ybuiag+1HrCYoFucErpQ8a90PdQyK11rPQaz3j1KqdNgSOdoFpzTvvecO5FOMWbio0wYHJt6IBIsSuhE2imn26DU6a0inGjbku+adUY8AH/dXonrBGe77qvbVLhbnKXeyRMSPOfUbTB8oMrDvkYkFuW1Hkqd9TfFXfhxGR8driXRauKZkR3b5dFeDWEymXSmq4SMEjqRdso3f85s8h79dSpX9YqjU4yZfZVuVu85/lw6zZ8LD/HRxzYY3tzAYddvq9wMXl5Er39+y6S3jrDkq0oOVbtZt6+Gxz+vAOCJYSn+rTnk+HomaOsSCQ0ldCLtlO8c11SbuUHnb8ZEmZhZV6X7yxcVx21TUOr9ENOmwqGX28W3wfCpEzrDMLj5/RIOVXtwG/DuAQe//sBOzosHuXZ9MQCzz4zncm0gfEq+eXR7KlShk+BSQifSTh2pbtj8ue/66RnxWM3w0eHaevOz9la4+HNdondemq3lOipNktu54QsjlhZUsW6/d6PgvHGp3D0kkcGdojGAGjcM7BjNPUOSWrnHbUOmNheWEFHtXKSd8h/7dYotS76rS6yFK3vH8XxBFX/5opLcLt7EzWMY3PheCeW1BkO7WPlxdlyr9Fkazleh21pcS7XLIDbq+FXYPeUufrfJu1HwHWcnMi49hnHpMcwd0IHCChcfFDkZ08NGzAkeL4GOJXSq0ElwqUIn0k4dOcU5rifyi74JALy2p9p/csRTX1by3kEncVEmnhyegkULIkLutAQLabFmXIb31Ijj8RgGc94vocJlcF4XK7/olxBwf0ZCFFf1jiP1JEfDSSD/kGu5C8PQ1iUSPE1K6P75z38yfPhw0tLS6NWrF9OmTaO6+tgk6TfeeINhw4aRlpbG4MGDWbZsWb1rOJ1OFixYQHZ2Nt27d2fSpEkUFBTUa5efn8+kSZPo3r072dnZ3HnnnTidLbtZpkh75NtPrrEJXb+O0VzU3YbH8CZy+fZa7trirfDcc26ijoIKEyaT6dg8uhMMu/7tO4n4X5SIt4jT6hZFlNUalDjqrxgWaS2NTugefvhhbr31VqZMmcLy5ct57LHH6NmzJ26398Phgw8+YPr06eTm5pKXl8fkyZO56aabWLVqVcB1br31Vv7xj3+wYMECli5disPh4IorrqC0tNTfxm63c/nll+N0Olm6dCkLFizg2WefZf78+c182iLS1AodwI11lZzn8iu5/t8l1LhhdHcbM3PiW7SP0jy5nU+c0O0sreWuLWUA/GGIEvGWEhtlomus929KCyMkmBr1F1xQUMADDzzACy+8wLhx4/y3X3HFFf7//9BDDzFkyBAee+wxAEaMGMHu3bu57777/O3279/Pc889xyOPPMK1114LwDnnnEP//v159tlnmTt3LgBLliyhvLyc559/npSUFADcbjfz5s3j17/+Nd26dWvGUxdp346d49r44bQxPWxkJ0WRX+ri02Lv/mR/ujAFUwNWy0rwfLdCZxiG//djGAZz/2un2m0wqrvNv8egtIzMDlEcrHayu9zF2Z2soe6OtBON+mr+/PPP07Nnz4Bk7rscDgfvvfdeQIIHMGXKFHbs2MGePXsAWL9+PR6Ph0mTJvnbpKSkMGrUKNauXeu/bd26dYwcOdKfzAFMmjQJj8fD+vXrG9N1Efke35DrqY79Oh6zycQNfY/Nt3rovGR6aKuSsDMo1Uq02bsA5rvVotf21PCfg05iLPD4sGQl4i1MmwtLKDSqQvfRRx/Rt29fHnroIf76179SWlrKOeecw7333suQIUP45ptvqK2tJTs7O+BxOTk5gLfC17NnTwoKCujcuTPJycn12i1dutT/74KCAqZPnx7QJjk5ma5dux53vt13DRo06IT3vf766/To0QOHo2WOxWlrfHMUNVcxOEIV78N125YkWVzU1NQ0+vGT0s28nWGlZ7yZy7ubmnSNUGlPr/GBKVF8XOzi/X2VdD3dRrXLYP5mOwA3nhlLlygXNTWtv8VGe4p5et12fV/bHdTURIesH+0p5uGiNWJutVoxm0/9xbtRCd2hQ4fYunUr27dv55FHHiE2NpZHH32UKVOm8PHHH2O32wFISgrcr8iXuJWUeA92ttvt9dr42vnaNKZdU3g8HgoLC5t1jbauqKgo1F1oV4Id78PVsYCJ2pIiCmuathrvrp7e/+7bd7TlOhZE7eE1nmOL5mOieXdPCUOjanlmbxT7Kq10sXqY1KGYwsLioPanPcS8g8MC2NhxpIrCwuZ9VrWE9hDzcNOSMc/MzGz5hM7j8VBRUcGbb75J//79ATj33HMZOHAgTz31FGPGjGlab1vB1q1bT3q/YRhkZGQEqTeRxel0UlRURFpaGlar5n+0tlDEu8ZtUOn2JmH9M7uTbG1fOxi1p9f4KMPBPw9U8FV1DJbUzvzjAzvgXQiR1bNz0PrRnmJ+dkwtFJRxyB1NRkaXkPWjPcU8XLRGzC2Whk1naVRCl5ycTMeOHf3JHHjnvg0YMICvvvqKqVOnAlBWVhbwOF/lzjcXLjk5uV4bX7vvzpdraLumMJlMxMTENOsabZ3ValWMgiiY8T5Sd2B7lAnSOsS22zlU7eE1PqxHNFDB9lI3C/5XQ7Ubzuti5YfZiSH5vbeHmGenRgNl7Kv0EGW1ERXi7WDaQ8zDTShi3qiv5WecccYJ73M4HJx++ulER0eTn58fcJ/v31lZWf7/Hjp0yJ/ofbedr42v3fevVVpaysGDBwPaiUjjfHfLkvaazLUX3eMtpMdb8Bjw+t4aTMADQ5P0e29FabFmbBZwG7CvUgsjJDgaldBdfPHFHD16lG3btvlv8/170KBB2Gw2hg8fzmuvvRbwuJUrV5KTk0PPnt4JN6NHj8ZsNge0s9vtbNiwgfHjx/tvGzduHBs3bgxI/FatWoXZbGb06NGNeqIicsyRJhz7JZHLt30JwPSsOM7SVhqtymwy0bNug+E9OtNVgqRRCd0PfvADzjnnHH784x+zYsUK1qxZww9/+EOsVis//elPAfjtb3/L5s2bmTdvHu+99x733XcfeXl53H777f7r9OjRgxkzZrBgwQKWLVvG+vXrueaaa0hMTOS6667zt5s5cyYJCQlcc801rF+/nmXLlrFgwQJmzpypPehEmsF3jmvnJmxZIpHHl9B1iDaxYHBiiHvTPmRq6xIJskbNoTObzf7k7Je//CW1tbWcf/75rFmzhrS0NADOP/98li5dysKFC1m6dCnp6eksXrw4YM85gAceeID4+HjuvvtuKioqGDp0KK+++mrAqtbk5GRWrVrFLbfcwjXXXENCQoI/ERSRpmvqsV8Sma7uHceHRU6u7BVLF1Vlg6JnhyjAwZ4KVegkOBp91ktqaipPPfXUSdtcdtllXHbZZSdtY7PZWLhwIQsXLjxpu5ycnHrHholI8xypbvqxXxJ5km1mnh3VMdTdaFd61x2l9pVdCZ0Eh97NRdqhw/5FEarWiLSGAR29GwpvK64NcU+kvVBCJ9IOFdcNuXaO1VuASGvwJXT7Kt0crdE8Oml9ejcXaYd8FbpUm94CRFpDotVMr7qFEduOqkonrU/v5iLtkG/bElXoRFrPoFTv6uKtGnaVINC7uUg75E/oNIdOpNUMTNU8OgkeJXQi7UxlrYcqlwFAqla5irSaQXUJnSp0Egx6NxdpZ3zVOZvFu9GsiLQOX4VuZ5mL8lpPiHsjbZ0SOpF2xn/sl82i8zxFWlGnGAs94rzTGj7XwghpZUroRNqZY+e46s9fpLUN0LCrBIne0UXamcO+Peg0f06k1Q3SwggJEr2ji7Qzxb496JTQibS6gR19FTpniHsibZ3e0UXamcPV2rJEJFh8Fboddhc1davLRVqDEjqRdsY35NpJFTqRVtcj3kJHmxmXAV/aNewqrUfv6CLtjK9CpyFXkdZnMpk0j06CQu/oIu3MV3VVgj5JUSHuiUj7cGwenRI6aT1K6ETakcPVbg5UeTAB/es+ZESkdfkrdEe1MEJajxI6kXZkW93mpr0SLXSI1p+/SDD4Toz4/GgtLo8WRkjr0Du6SDvim8MzKNUa4p6ItB+9EqNIiDJR44aCUleouyNtlBI6kXbEl9AN1HCrSNCYTSadGCGtTgmdSDvim8PjGwISkeDwfYnSPDppLUroRNqJMqeHr8u8e9ApoRMJroGq0EkrU0In0k58XrcgokechU46JUIkqHzzVj8rrsVjaGGEtDwldCLthG+F6wBV50SCLic5CpsFymoNdpe7Q90daYOU0Im0E/4FEUroRIIu2mxiUEdvle6d/TUh7o20RUroRNqJrcV1CyK0wlUkJC7PjAFgxTfVIe6JtEVK6ETaAYfbYIfdu//VIFXoREJiyulxmIAPipwUVmg/OmlZSuhE2oEvS2pxGZBiM5EerwURIqHQPd7CBV29w64rVaWTFqaETqQd8C2IGNjRislkCnFvRNqvaafHAbBcCZ20MCV0Iu2AFkSIhIfLM2OIMnn3o9tZqj3ppOUooRNpB3wLIjR/TiS0UmMsjOpuA+CVXarSSctRQifSxrk9Bl+UeCdga4WrSOhN7eUddl3xTTWGNhmWFtKohO75558nOTm53v/uuuuugHbPPfccgwcPJi0tjWHDhvHmm2/Wu1ZpaSlz5swhMzOT9PR0ZsyYwcGDB+u127RpE+PGjaNr167079+fRYsW6Q9ApBF2lrmochnERZnonRgV6u6ItHuXnRZDjAXyS118dlTDrtIymvTuvnz5chITE/3/7tatW8B9c+fOZd68eYwYMYKVK1cyffp03njjDc4991x/u5kzZ/LVV1/x2GOPYbPZWLhwIdOmTePdd98lKsrbrV27djF16lQuuugi7rjjDj7//HPuvvtuLBYLN910U1Ofs0i74ps/1z8lGotZCyJEQi3RamZ8egyv7alh+a5qBtYdCybSHE1K6M466yxSU1OPe9/999/P1KlTueOOOwAYMWIEX3zxBQ8++CB5eXkAbN68mXfeeYcVK1YwevRoALKyssjNzWX16tVMnjwZgMWLF5OSksKSJUuwWq2MHDmS4uJiHn74Ya6//npsNltTui/SrvgOA9f8OZHwMbVXnDeh+6aau4YkavW5NFuLzqHbvXs3O3fuZNKkSQG3T5kyhY0bN+JwOABYt24dSUlJjBo1yt8mKyuLAQMGsHbtWv9tb7/9NhMmTMBqtQZcq7S0lM2bN7dk10XaLJ3hKhJ+xqfH0CHaxL5KN5sPOUPdHWkDmpTQnXfeeXTs2JFBgwbx6KOP4nZ7DxrOz88HIDs7O6B9Tk4OTqeTPXv2AFBQUEBWVla9byQ5OTkUFBQAUFlZyb59++pdKzs7G5PJ5G8nIidmGAbbdOSXSNiJjTJx2Wneo8Be0Z500gIaNeTatWtXbr/9doYMGYLJZOKNN95g4cKFfPvttzz00EPY7XYAkpKSAh6XnJwMQElJCQB2u71eG187X5vS0tLjXstqtRIXF+dvdyKDBg064X2vv/46PXr08FcMJZDT6Qz4r7Su1ox3YaUbu9MgygSnx7qpqdGh4KDXeCgo5vVdnh7FS1/Dyl1V/H6gjagWnuOqmAdfa8TcarViNp+6/taohG7MmDGMGTPG/+/Ro0cTExPDX/7yF+bNm9f4XoaQx+OhsLAw1N0Ia0VFRaHuQrvSGvFef8QC2OgV5+HQgX0tfv1Ip9d48Cnmx/TyQFJULEcc8OrnBxia4mmVn6OYB19LxjwzM7PlE7rjmTx5Mn/605/47LPP/JW4srIy0tLS/G18lbuUlBTAW4nbv39/vWvZ7XZ/G19lrqysLKCN0+mkqqrK3+5Etm7detL7DcMgIyPjpG3aK6fTSVFREWlpaQHzF6V1tGa8P/+2AnBwQfdYMjI6t+i1I5le48GnmB/fFYcqeG6ng/erkpg2MKFFr62YB19rxNxiadj52y26KZVvvlt+fj5ZWVn+2/Pz87FarWRmZgLeBRDvvvsuhmEEzKPLz8+nb9++AMTHx5Oenu6fl+dTUFCAYRgB128Kk8lETExMs67R1lmtVsUoiFo63h7DYN0B79SEiacn6Hd5HHqNB59iHuiHWSae2+lgzT4ni6JsxES1/GpXxTz4QhHzZq9yXb58ORaLhYEDB5KZmUmfPn1YtWpVQJuVK1cycuRIf7Y6btw47HY7Gzdu9LfZuXMn27ZtY/z48f7bxo4dy5o1a6itrQ24VlJSEkOHDm1u10XatE+P1HKw2kOHaBMXdtUWPyLh6Pw0Kz3iLJTVGqzbrzmu0nSNqtBNmTKFESNG+Ktob7zxBs8++yw///nP/UOst912G7NnzyYzM5Phw4ezcuVKtmzZwpo1a/zXyc3NZcyYMcyZM4eFCxdis9m455576NevHxMnTvS3u/nmm8nLy2PWrFnMmjWL7du3s3jxYhYsWKDyscgprCn0fjiM6RGDzaI9rkTCkdlkYkqvWP70eQXLd1UzsWdsqLskEapRCV1WVhZLly7lwIEDeDweevfuzf3338/PfvYzf5tp06ZRVVXFokWLWLRoEX369GHZsmXk5uYGXGvJkiXMnz+fuXPn4na7GTVqFA8++KD/lAiAXr16sWLFCubPn89VV11Fp06duP3225kzZ04zn7ZI2/fGXu9WCJeepqEWkXA29XRvQvdmYTVlTg+JVh2zLo1nstvtOhhVAtTU1FBYWEhGRobmXQRBa8R7T7mLQa8UYTHBzh91I8WmD4jv0ms8+BTzEzMMg3NXHGJnmYv/NzyFq/vEtch1FfPgC2XM9S4v0ga9UTfcel6aVcmcSJgzmUxM6+Udal2+qyrEvZFIpXd6kTbojb3ehO7SDH0rF4kEvoRu/QEHR2rcIe6NRCIldCJtjN3h4T8HvaegXJqhCdYikaBPUjSDUqNxG7Bqt44Ck8ZTQifSxryzvwaXATlJUfROatGtJkWkFU073fsF7JVdSuik8ZTQibQxvvlzWt0qElmm9IrDBHxQ5KSwwhXq7kiEUUIn0obUegzW7tP8OZFI1CPewvlp3j1Wl6tKJ42khE4kglW5Ag/z/u9BJ2VOg84xZoZ01ubbIpHGt2XJs/mVeAztKiYNp4ROJEI9tq2c7ku/5exXDvLr/9pZtbuaV+q2PLg4IwaLWadDiESaab1iSbSa2F3u5u19jlB3RyKIEjqRCLWm7iSIb8rdLNlRyY83HGVpgTeh03CrSGSKizJzTV2V7umvKkLcG4kkSuhEIpBhGOyweydN/3FoEj87M54zkr0rWrvFmbmouy2U3RORZvjpGQkArNvnYHe5FkdIw2hPA5EIdLDaQ1mtgcUE1+XEY7N4h1eLqtzERJmIj9Z3NZFI1TspitHdbaw/4GDJV5X84dykUHdJIoDe9UUi0A57LQC9EqP8yRxAWpyFJB3sLRLxfnpmPABLCyqpdmlxhJya3vlFItBXdcOt2do4WKRNujg9hvR4CyUOg5Xf6HxXOTUldCIRyFeh882bE5G2xWI2MfMMb5Xu6a8qQ9wbiQRK6EQikK9Cl5McHeKeiEhrmZEdh9UMnxyp5ZPDzlB3R8KcEjqRCJTvT+hUoRNpqzrFWJhUd76rqnRyKkroRCLMkRo3xQ4PJiBLc+hE2rTZdVuYLP+min0631VOQgmdSITxDbeelmAhLkp/wiJt2ZDO0QztYsXhhuvePYrTrRWvcnz6NBCJMFoQIdJ+mEwm/joihSSriS2Ha5m/uTTUXZIwpYROJMJoQYRI+5LZIYqnRnQE4G9fVfLy19rGROrTV3yRCKMFESLtz8UZMfxmUAce3lrOL/9rp3/HaPqmeL/UVbk8rNvnYPMhJ6kxZnrEW+gRb6FzlBuPRmjbDX0iiEQY35CrKnQi7cvtZ3Xg48NONhxwcO36Yu4aksTq3dWs2VtDxQlOk+gVF8O/0jx0jwlyZyXolNCJRBC7w8PBag+gUyJE2huL2cTTI1MY+dphvi5zc+36o/77MhIsXJweQ6XLYH+lm30VLvZVutlVZeaBbVUsHh4Xwp5LMOgTQSSC+KpzPeIsJOrMVpF2JzXGwrOjOjLlrSPERpmYlBnLtF5xDOkcjclkCmi7fm85U94pY+lOB7P6OhmUag1RryUYlNCJRJAdpZo/J9LeDelspeBH3Yg2g/l7Sdx3XdAlmos7u3jrcBS3fFjKm5d1qpf0Sduhr/giEWRH3YKIbCV0Iu2azWI6aTLnc3NmLXFRsOmQk5e+rg5CzyRUlNCJRJBje9BpQYSInFoXm8Gv+nnnz/1+SyllTk+IeyStRQmdSAT5SluWiEgjXZ8TQ+9EC0XVHh78tDzU3ZFWooROJEKU13rYV+kGIEcrXEWkgWwWEw8MTQbg/22v8Ff6G8pjGKzfX0OJQ9W9cKaETiRCFNRV57rEmukYYwlxb0QkkoxLj+GSjBhcBox87RA/eruYZQWVFNe4T/nYu7eUMWVtMTe8VxKEnkpT6Wu+SITwrXDV/nMi0hQPnpfE3nIX2+0u3iis4Y3CGswmGN7VxiPnJ9Enqf7c3Nf3VPP45xUAvFVYw+5yF5kd9B4UjppVoauoqKBv374kJyfzv//9L+C+5557jsGDB5OWlsawYcN488036z2+tLSUOXPmkJmZSXp6OjNmzODgwYP12m3atIlx48bRtWtX+vfvz6JFizAMnWci7YsWRIhIc5yWEMV/JnXh/Su6cNtZHRjQMRqPARu/dXDZG0f4/GjgUOw3ZS5ueN9blYu1mDCAZ3dUhqDn0hDNSugeeughXC5XvduXL1/O3LlzmTx5Mnl5eeTm5jJ9+nQ++uijgHYzZ85kw4YNPPbYYzz11FPs3LmTadOmBVxz165dTJ06lbS0NF566SVuuOEG7rvvPp544onmdF0k4mhBhIg0l8lkon/HaG47O5H3rujC/6amMaBjNIeqPfzgjcNsOewEoNplcO2Go5Q5Dc7rYuUvw5MBWJpfhcOtgko4avInQ35+Pk8//TQLFy7kV7/6VcB9999/P1OnTuWOO+4AYMSIEXzxxRc8+OCD5OXlAbB582beeecdVqxYwejRowHIysoiNzeX1atXM3nyZAAWL15MSkoKS5YswWq1MnLkSIqLi3n44Ye5/vrrsdlsTX0KIhFFZ7iKSEs7PTGK1Zd04qp1xWw+7GTSm0d4YWwqL31dxedHa+kcY2bJRR3pEmume1wpB6o8vLa7mit76yixcNPkCt0tt9zCT37yE/r06RNw++7du9m5cyeTJk0KuH3KlCls3LgRh8MBwLp160hKSmLUqFH+NllZWQwYMIC1a9f6b3v77beZMGECVqs14FqlpaVs3ry5qd0XiSjVLoPd5d7Jy2eoQiciLSjZZmbFxamM7GajwmUw+a0jLCuowmyCp0em0D3eQpTZxI9z4gFYomHXsNSkhG7VqlVs376dW265pd59+fn5AGRnZwfcnpOTg9PpZM+ePQAUFBSQlZVV7xiSnJwcCgoKAKisrGTfvn31rpWdnY3JZPK3E2nrdpa5MIBkq4nOMVqcLiItKyHazEtjU7m0biUswO/OTmRk9xh/mxnZ8VhM8EGRky+ONm7rE2l9jf6qX1VVxfz581mwYAGJiYn17rfb7QAkJSUF3J6cnAxASUmJv9332/ja+dqUlpYe91pWq5W4uDh/u+MZNGjQCe97/fXX6dGjh79aKIGcTmfAf6V1NSTenx/yvlazEi163bYAvcaDTzEPvqbE/KkL4njsC2+h5RfZUdTU1PjvSzHDJelWXi908rftpTwwJKFlO9wGtMbr3Gq1Yjaf+ot8oxO6hx9+mM6dOzN9+vQmdSxceDweCgsLQ92NsFZUVBTqLrQrJ4v3R/uigWh6WGooLCwLXqfaOL3Gg08xD77GxvxHyd7/7t9X/77Lksy8XhhD3q4aftKphDhtiXlcLfk6z8zMbPmEbu/evTzxxBMsW7bMXz2rrPSOpVdUVFBRUeGvxJWVlZGWluZ/rK9yl5KSAngrcfv376/3M+x2u7+NrzJXVhb4AeZ0OqmqqvK3O56tW7ee9LkYhkFGRsZJ27RXTqeToqIi0tLSAuYuSutoSLyL9pQDTs7unkhGRmxwO9gG6TUefIp58LVGzNPTDR7dY+frcg+bXJ2ZkRlz6ge1I60Rc4ulYVlzoxK6PXv24HQ6ueqqq+rdN3HiRIYMGcLTTz8NeOfSZWVl+e/Pz8/HarWSmZkJeBdAvPvuuxiGETCPLj8/n759+wIQHx9Penq6f16eT0FBAYZhBFy/sUwmEzExeiGejNVqVYyC6GTx3lnm/QLVv3OsfictSK/x4FPMg6+lYz7zTDfzN5fy3NdOZvdLqjcXXkLzOm/U7OoBAwawevXqgP/dd999ADz22GM8/PDDZGZm0qdPH1atWhXw2JUrVzJy5Eh/xjpu3DjsdjsbN270t9m5cyfbtm1j/Pjx/tvGjh3LmjVrqK2tDbhWUlISQ4cObfwzFokwtR6Dr8t0SoSIhIf/6xNHjAU+P1qrFa9hpFGfDsnJyQwfPvy495111lmcddZZANx2223Mnj2bzMxMhg8fzsqVK9myZQtr1qzxt8/NzWXMmDHMmTOHhQsXYrPZuOeee+jXrx8TJ070t7v55pvJy8tj1qxZzJo1i+3bt7N48WIWLFigsr20C7vKXLgMSIgykR6vCSsiElopNjOzz0zgT59XMO+DUraXuLg/NwmrpX6lzuUxiDKrghcMrbL/wbRp03j88cd55ZVXmDp1Kh9++CHLli0jNzc3oN2SJUu46KKLmDt3LrNnz6Z3797k5eURFXUsz+zVqxcrVqzgwIEDXHXVVTzxxBPcfvvtzJkzpzW6LhJ2dtSdEJGVHKWhDREJC38Yksgd5yRiAp75qpIr3jrCoWrvXpmVtR5e3FnFFW8eoctzB/j9R6U6rjMITHa7XVGWADU1NRQWFpKRkaG5LkFwqng/9GkZ9/6vnKt7x/L/RnQMQQ/bHr3Gg08xD75gxPytwhpm/9t7RFj3ODMju8ewenc1Fa7A1OL3gxP51cAOrdKHcBLK17l2KBUJcztKfWe46sgvEQkvF2fEsP4HnclJiuJAlYcXdlZR4TLI7GDh9rM7cPvZ3iTu7o/LWJqv+XatSTOsRcKcb8g1R0d+iUgY6pMUzbofdObuj8twewyu6h3H+WlW/xSRapfBos8qmPtfO6kxZi47TVsvtQZ9QoiEMbfHoKDUu8I7J0kVOhEJT4lWM4+cn3zc+34/OJHDNR6eL6hi5rtHWTG+Exd0tQW3g+2AhlxFwlhhpZsaN9gs0LODVriKSOQxmUw8fkEyF2fEUOOGq98p5tsqd6i71eYooRMJY1/ZvdW53olRWvovIhErymzi7xel0C8lijKnwavfVIe6S22OEjqRMJZfN3/uDC2IEJEIFxdl5uo+cQCs21cT4t60PUroRMLYV3adECEibcfF6d6tPN4/6KCy1hPi3rQtSuhEwlh+3YIIVehEpC3ISoqiZ4IFpwc2futo1rU8hqENi79DCZ1ImDIMQ1uWiEibYjKZGF9XpWvqsKthGDyXX8np//yW6949qqSujhI6kTD1bZWH8loDi8m7KEJEpC0Yn+FN6NYWOhqdjJU4PPx4w1Fu/o+dUqfBqt01vLpbCyxACZ1I2NpRt8K1V2LUcQ+9FhGJRBd2tRFrMbG/ys32EleDH/fetw4ufPUQr+2pIcoEF3a1AnDH5jIqNB9PCZ1IuPId+aUFESLSlsRGmRjRzZuMrW3gsOufPivn8jePsL/KTZ/EKN7+QWfyxnWiZ4KF/VVuHt1W3ppdjghK6ETClK9Cd4bmz4lIGzOubh5dQxK6naW13PVxGQYwIzuOjZd35qxOVmKjTNw/NAmAP31ewc66RWTtlRI6kTDl37JEK1xFpI3xJXSbDzmxO04+XHrf/8pxG3BJRgyLh6UQH30sdbk0I4ZxPWzUeuC2TaXteoGEEjqRMOXbVDhHQ64i0sb07BDFGclRuA1Yv//EVbqtxU5WfFONCbjjnMR695tMJh4YmozVDG/vd7Bmb/vdsFgJnUgYOlLjprjuW2uWEjoRaYMaMuy68OMyAKb1iqV/x+OPVvROimJO/wQAbt9cSrWrfVbplNCJhCHf/nOnJVgChhdERNoK3350b+934DnOUOl/DzpYt99BlAluP7t+de675g3sQI84C3sr3DzzVUWr9Dfc6ZNCJAzt0HCriLRx56VZSYw2caTGw/+OBC5oMAyDez7xVueuzY6j1yn24oyPNvObQR0A+GdBVbucS6eETiQM+Va45mhBhIi0UdFmE6N62ID6w67r9jn4oMhJjAV+O+jk1TmfyafHYrPAdruLz462vxWvSuhEwpB/DzptWSIibZhvHt3/217B7I1HefrLCj47Wuuvzs0+M4Hu8ZYGXSvZZubSjFgAXvy6qnU6HMaU0ImEGcMw+KpEe9CJSNt3aUYMqTYzpU6DvF3V/ObDUoavOsRnR2vpEG3ilwMSGnW9H/b2JnSv7KrG5Wlfw676tBAJM+8ddHKw2kN8lIl+KRpyFZG2KzXGwtYr0/jokJNNdf/bcthJea3BLYM6kBrTsOqcz9h0b4J4qNrDhgMOfwWwPVBCJxJmfCu0ftg7TitcRaTNS4g2M6pHDKN6eJMvt8fgUI2HrrGNf/+LNpuY1iuWv35ZyYs7q9pVQqdPC5Ew8m2Vm3/t8U4OnnlGfIh7IyISfBaziW5xFkwmU5Mef3WfOABe31tNmfPkp1C0JUroRMLIc/mVuA04P816wk00RUTkxM5KjSYnKYoaN6zaXR3q7gSNEjqRMFHrMXh2RyUAs1SdExFpEpPJ5K/StafVrkroRMLE2v1Ovq3y0DnGzMSesaHujohIxLqyVywm4D8HneytcIW6O0GhhE4kTDxb4ABgRnYcNkvT5o6IiAikJ0QxvJt30+KXv24fw65K6ETCwO4qE+8V1WI2wY9zNNwqItJcV9ftSffizvZxFJgSOpEwsPygdwehi9NjOC1BuwmJiDTXxMxY4qJM7Cxz8e9vnaHuTqtTQicSYpUug38VeZM4LYYQEWkZHaLNXFO3OGLx5+Uh7k3rU0InEmKr9jiocJvomWBmdN1B1SIi0nw39k/AbIJ39jv47GhtqLvTqhqV0K1du5bLLruM3r1706VLFwYNGsTvfvc7SktLA9q98cYbDBs2jLS0NAYPHsyyZcvqXcvpdLJgwQKys7Pp3r07kyZNoqCgoF67/Px8Jk2aRPfu3cnOzubOO+/E6Wz7pVNpP57b6d1IeEafGMxN3EhTRETqy+wQxeRM71y6xZ+17SpdoxK6kpIShgwZwqOPPsry5cu58cYbefHFF7nuuuv8bT744AOmT59Obm4ueXl5TJ48mZtuuolVq1YFXOvWW2/lH//4BwsWLGDp0qU4HA6uuOKKgOTQbrdz+eWX43Q6Wbp0KQsWLODZZ59l/vz5zXvWImFiW7GTT4+6iTIZ/PB0VedERFrazQMSAFjxTTV7ytvuFiaNmn39wx/+MODfw4cPx2azMXfuXL799lu6devGQw89xJAhQ3jssccAGDFiBLt37+a+++7jiiuuAGD//v0899xzPPLII1x77bUAnHPOOfTv359nn32WuXPnArBkyRLKy8t5/vnnSUlJAcDtdjNv3jx+/etf061bt+Y9e5EQey7fu+nlRaluOsVoBoSISEsblGplVHcbGw44+PMXFTx4XnKou9Qqmv0J4ku0nE4nDoeD9957z5+4+UyZMoUdO3awZ88eANavX4/H42HSpEkB1xk1ahRr167137Zu3TpGjhzp/xkAkyZNwuPxsH79+uZ2XSSkKms9vFy3i/nkrm33W6OISKjNravSLc2vorjGHeLetI4m7Y/gdrupra3lq6++4sEHH+TSSy+lZ8+efPXVV9TW1pKdnR3QPicnB4CCggJ69uxJQUEBnTt3Jjk5uV67pUuX+v9dUFDA9OnTA9okJyfTtWvX4863+65Bgwad8L7XX3+dHj164HA4GvJ02x3fHEXNVWxdL++qoazW4LR4E0OSPIp3EOk1HnyKefAp5scMTTEYmGJhW4mbJz8r5TcD4lrl57RGzK1WK2bzqetvTUroBgwYwIEDBwAYO3YsTz/9NOCd8waQlJQU0N6XuJWUlPjbfb+Nr52vTWPaNYXH46GwsLBZ12jrioqKQt2FNm3JdhtgYWInB2aT4h0KinnwKebBp5h7/bCLhW0lNv72VRVXdCgmxtJ6P6slY56Zmdl6Cd3LL79MVVUVX331FQ899BBXX301r776alMu1Wq2bt160vsNwyAjIyNIvYksTqeToqIi0tLSsFqtoe5Om/Sl3cVn5aVEmeAn/VMwSg8r3kGk13jwKebBp5gH+nEPg6f229lT4eHfzk7Mym75M7NbI+YWS8MyzyYldP379wcgNzeXs88+m+HDh/Ovf/3LP7RaVlYW0N5XufPNhUtOTq7Xxtfuu/PlGtquKUwmEzExMc26RltntVoVo2baU+7C7vQwKDXwD/vF3XYALj0thvTEGApLFe9QUMyDTzEPPsX8mJv6u/nNh6U89kUNV2cnktpKZbpQxLzZiyL69+9PdHQ0u3bt4vTTTyc6Opr8/PyANr5/Z2Vl+f976NAhf6L33Xa+Nr52379WaWkpBw8eDGgnEk5qPQardlcz+a0jDHqliJGvHebm/5RQXusBoNpl8GLdYogfZ+tkCBGRYLk2O56+yVEcqfHw2w9LT/2ACNLshG7Lli3U1taSmZmJzWZj+PDhvPbaawFtVq5cSU5ODj179gRg9OjRmM3mgHZ2u50NGzYwfvx4/23jxo1j48aNAYnfqlWrMJvNjB49urldF2lRDrfBwo/L6PfyQX684SgbDjgwASa825Nc+Ooh/nvQwWt7qil1GmQkWBjVXXvPiYgEi81i4i/DU7CYvPvSrdpdHeoutZhGDblOnz6ds88+m379+hEbG8tnn33Gn/70J/r168eECRMA+O1vf8sPfvAD5s2bx6RJk3jvvffIy8vj73//u/86PXr0YMaMGSxYsACz2Uz37t155JFHSExMDNikeObMmTz11FNcc801zJs3jwMHDrBgwQJmzpypPegk7Pzx0zIe3VYBQFqsmelZcVybHc++Sjc3vFfCngo3E9444t9v7tqsOCxmE237MBoRkfByVicrvxrQgYe3lTPvAzsXdrW22tBrMDUqoRs8eDArVqxg0aJFeDweTjvtNGbMmMFNN93kn/x3/vnns3TpUhYuXMjSpUtJT09n8eLFAXvOATzwwAPEx8dz9913U1FRwdChQ3n11VcDVrUmJyezatUqbrnlFq655hoSEhL8iaBIODEMg5XfeL/p3TU4kRv7JxBt9h7jldkhiv9c0YX5m0tZWlDF4RoPZhNMz9Jwq4hIKPz2rA6s2VvNdruL335YypKLOoa6S81mstvtRqg7IeGlpqaGwsJCMjIyNJG2gb6y13LeykNYzfD1/3WjQ/TxZzO8sbeaez4p4+L0GH4/xPvlRfEOPsU8+BTz4FPMT+7TI07G/OswbgP+MaojV2Q2f9VrKGOus4ZEWsCavTUAjOxmO2EyB3DpabH8d1KaP5kTEZHQ8A29Asz7wM43ZZF9Yo8SOpEW8MZe73Drpae1/L5GIiLSOn57Vgf/qtehK4u486NSSp2eUHerSZTQiTRTUZWbLYe9SxsuPU3DGiIikcJmMfHPsamM6m7D6YHFn1dwzitFPP1lBS7PsRlphmHgMcJ7hlqTNhYWkWPe2leDAZzTKZpucZG/UkpEpD3J7BDFivGprNvn4I6PSskvdfGbD0u5bZN3nzoP4DHAYoIpp8fy4HnJpNjCrx4Wfj0SiTCv182fuzRD1TkRkUhkMpkYnxHDfyZ14eHzkki1mXEZ4DK8yRyA24C8XdUMe7WIdw/UhLbDx6EKnUgzVNZ62Fj3h32Z5s+JiES0aLOJn56ZwLXZ8RyqdmMxmbCYwGyCr8tczHnfzs4yF5PeKubnfeP5/eAkYqNMoe42oAqdSLNsOOCgxg2nJVjom6LvRyIibYHNYiIjIYru8RbS4ix0jrVwXpqNjZd3ZtYZ3j1E/9/2Sm54ryTEPT1GCZ1IM7xR6KvOxWAyhce3NBERaR3x0WYeOT+ZvHGpZCRY+M2gDqHukp9KCiJN5PYYvFXomz+n4VYRkfZiXHoMn0xN858IFA5UoZNWFe7LvJvjo8NOjtR4SLKauKCrNdTdERGRIAqnZA6U0EkrmrG+mDNfOsjre6pD3ZVW4Tsd4uL0mLD7wxYRkfZFCZ20isIKF6/tqaGo2sM164/y2w/t1LjaVrXON39OmwmLiEioKaGTVrF6jzfZSbF5K1d/+7KS0f86xFf22lB2q8XssNdSUOoi2gxjeiihExGR0FJCJ61idd0w6y2DElk+PpXOMWa2l7gY9dph5m8u5bXd1Ryscoe4l0334s4qwJvMJVr1ZyQiIqGlVa7S4oqq3HxY5ARgYs8Y0hOi+M+kLtzwXgnv7Hfw5y8q+PMX3rbp8RYGdIym1mNQXmtQ5vRQ5jQ4IyWKJ4en0CU2/I7ScnsMXv7am7D+qE9ciHsjIiKihE5awZq9x842TU/wvsS6xFrIG5fKqt3V/PtbB5sPOfnS7mJfpZt9lfUrdfur3Fzx5hFWX9qJTjGnTuqKqty8vreGKDNMPj2WDtGtVzV776CD/VVukqwmLtFxXyIiEgaU0EmLe61uuPXynoF7s5lNJiafHsfk071VrfJaD/87Uku+vZbYKBOJVjOJ0SYM4Ib3SvjS7uLyN4+w+pJOpB4nqTta42b1nhqWf1PN+wcd/vP27thcyjVZccw+M4FeiS3/En+hbrh16ulx2Cxa3SoiIqGnhE5aVInDw3vfOgD4Qc+TV686RJsZ0c3GiG62eve9dkknfvDGEbaXeM/Me+2STqTYzDjdBm8W1vDCzirW7avhuwtnh3SOxu4w2Fnm4sntlfy/7ZWMz4jhrsGJnJkS3SLPr6LW41/wcXUfbSYsIiLhQQmdtKg3C71JVt/kKPokNT2JykqKZvUlnfjBm0f47Ggtk946Qm4XK6/sqqLEcSyLG9AxmqmnxzLp9FgyO0ThMQzW73fw1JcVrN3n4K3CGjYfcvDaJZ0Z0LH5Sd1ru6upchn0TrRwbmdtJiwiIuFBCZ20qNd2e4dbJ2Y2v3qVnRztr9RtLa5la7F3y5NucWau6hXHj7LiOCM5MEkzm0yMTY9hbHoMO0trueG9Ej46XMukN4/wr0s7NbtS92LdYoire8fp7FYREQkbSuikxVTUelh/wDscObFnywxHnlGX1P3yP3YyEiz8X1YcF3WzYWnAyQx9kqLJG9eJyWuP8L8jtVzx1hH+dUknspObltQVVrj8w8lX9dbqVhERCR/aQEtazLp9NTjc0KuDhX4pLfddoW9KNGt/0JlnLurImB4xDUrmfJJtZlaM78SAjtEcqvZw+ZtH+LrU1aR+vPx1NQZwYVcrPTvou5CIiIQPJXTSYnyLBSb2jA2r4cgUm5lXL06lb0oUB6s9THzzMN82clNjwzB48Wvv6tartfeciIiEGSV00iJqXAZr6842bYn5cy0tNcbCqos7kZMUxYEqD7dvKm3U4z8+4j3qK9Ziqrcdi4iISKgpoZMWseFADRUugx5xFs7p1DJbhLS0zrEWnr6oI2YTvLq7mnf21zTocbUegye/qAC8J1/oqC8REQk3+mSSZqtxGdzzSRng3XvOHEbDrd83oGM0PzszHoDffmCn5rsb2R3Hh0UORr52iOXfeFe3XpMV3+p9FBERaSwldNJsC7aUsr3ERecYM78e2CHU3Tml289OpGusmV3lbh7/vPy4bYpr3Mx5v4RL1ng3N06xmfjzhcmM7F5/E2QREZFQU0InzbJmbzV/+7ISgCeHp5AWd+pzV0Mt0WrmvtwkAB7dVs43ZcdWvbo9Bn//qpIhK4pYVuBdBHFtVhxbpqSpOiciImFLCZ002YFKNze+XwLAnH4JjE2PnIPqJ58ey0XdbTjccOsmO4Zh8J+DDi5afZhffWCnxGHQNyWKNy/rxJ8uTDnuWbIiIiLhQptpSZO4PQbX//soJQ6Ds1KjuXNwYqi71Cgmk4mHzkviglcPsXafgwlvHOG/RU4Akqwmbj87kVlnxBPdiD3vREREQkUVOmmSxz6r4P2DTuKjTDwzsiNWS+QlPllJ0czt753z998iJybgJzlxfDw1jZ/3TVAyJyIiEaNRCd2rr77Kj370I/r27Uv37t258MILWbp0KYYRuFLwueeeY/DgwaSlpTFs2DDefPPNetcqLS1lzpw5ZGZmkp6ezowZMzh48GC9dps2bWLcuHF07dqV/v37s2jRono/T4KroLSW+//nXdX68PnJ9E6K3ELvrwclMLaHjXE9bGy8vDOPXZBCJw2viohIhGlUQvfnP/+ZuLg4Fi5cyAsvvMC4ceOYO3cuf/zjH/1tli9fzty5c5k8eTJ5eXnk5uYyffp0Pvroo4BrzZw5kw0bNvDYY4/x1FNPsXPnTqZNm4bLdWyC+q5du5g6dSppaWm89NJL3HDDDdx333088cQTzXza0hz/b3slbgPG9bBxde/I3mQ3LsrMK+M7kTe+EwNTraHujoiISJM0qrTy4osvkpqa6v/3yJEjOXr0KH/5y1+45ZZbMJvN3H///UydOpU77rgDgBEjRvDFF1/w4IMPkpeXB8DmzZt55513WLFiBaNHjwYgKyuL3NxcVq9ezeTJkwFYvHgxKSkpLFmyBKvVysiRIykuLubhhx/m+uuvx2bTFhLBZnd4eGGnd/XnTQM6hNURXyIiIu1Voyp0303mfAYOHEhZWRmVlZXs3r2bnTt3MmnSpIA2U6ZMYePGjTgcDgDWrVtHUlISo0aN8rfJyspiwIABrF271n/b22+/zYQJE7BarQHXKi0tZfPmzY3purSQ5/IrqXIZ9EuJYnhXVbRERETCQbMXRXz44Yd0796dDh06kJ+fD0B2dnZAm5ycHJxOJ3v27AGgoKCArKysetWdnJwcCgoKAKisrGTfvn31rpWdnY3JZPK3k+BxeQyeqttz7ud9E1SdExERCRPNms3+wQcfsHz5chYuXAiA3W4HICkpKaBdcnIyACUlJf5232/ja+drU1paetxrWa1W4uLi/O1OZNCgQSe87/XXX6dHjx7+iqEEcjqdAf/1Wb3Xwb5KNx1tJib2MFNT07CzUOXkThRvaT2KefAp5sGnmAdfa8TcarViNp+6/tbkhG7//v3MnDmT4cOH8/Of/7yplwkZj8dDYWFhqLsR1oqKigL+/cRnNsDC5C5ODh/YF5pOtWHfj7e0PsU8+BTz4FPMg68lY56Zmdl6CZ3dbufKK68kJSWF5557zv+DfJW4srIy0tLSAtoDpKSk+Nvt37//uNf1tfFV5srKygLaOJ1Oqqqq/O1OZOvWrSe93zAMMjIyTtqmvXI6nRQVFZGWluafv/hpsYutZaVEm+HmwV1Ii9UWhi3lePGW1qWYB59iHnyKefC1RswtloZtpdXohK66upqrr76asrIy1q5dGzAk6pvvlp+fT1ZWlv/2/Px8rFYrmZmZgHcBxLvvvothGAHzsPLz8+nbty8A8fHxpKen++fl+RQUFGAYRsD1m8JkMhETEzlHVYWC1Wr1x2jJ10cB75FZPVPiQtmtNuu78ZbgUMyDTzEPPsU8+EIR80aVWVwuF9dddx07duzglVdeoXv37gH3Z2Zm0qdPH1atWhVw+8qVKxk5cqQ/Wx03bhx2u52NGzf62+zcuZNt27Yxfvx4/21jx45lzZo11NbWBlwrKSmJoUOHNqbr0gzfVrlZ+U01AL/omxDi3oiIiMj3NapCN2/ePN566y0WLlxIeXl5wGbBAwcOxGazcdtttzF79mwyMzMZPnw4K1euZMuWLaxZs8bfNjc3lzFjxjBnzhwWLlyIzWbjnnvuoV+/fkycONHf7uabbyYvL49Zs2Yxa9Ystm/fzuLFi1mwYIHKx0HiMQwe21ZOrQfO62LlrE6Ku4iISLhpVEK3fv16AP+mwd+1detWevbsybRp06iqqmLRokUsWrSIPn36sGzZMnJzcwPaL1myhPnz5zN37lzcbjejRo3iwQcfJCrqWJd69erFihUrmD9/PldddRWdOnXi9ttvZ86cOU15rtIIhgFrCh08/Hkp2+3e0ztu6KfqnIiISDgy2e12HYwqAdbsKuOej+18WeGdiJloNTFvYAdu7q+951pDTU0NhYWFZGRkaJ5LkCjmwaeYB59iHnyhjHnknqoureJfe6qZvrEcsBAXBb/o24E5/RNItmlVq4iISLhSQicBVu32Ln64qKOLP43sTEayVrSKiIiEO5VdJMBHh727W0/t5qJzjF4eIiIikUCf2OJ3uNrN7nI3JqB/B0+ouyMiIiINpIRO/HzVuaxECwkajBcREYkYSujE76ND3oRuSCdlcyIiIpFECZ34+Sp0g5XQiYiIRBQldAKAy2PwyRHvEWtK6ERERCKLEjoBYHtJLVUug8RoE9mJllB3R0RERBpBCZ0A3xlu7WzFrNMgREREIooSOgFgs29BRGdriHsiIiIijaWETgDYUlehy+2ihE5ERCTSKKETimvcfF3mBlShExERiURK6IQth72rW7OSokix6SUhIiISafTpLf4Nhc9VdU5ERCQiKaET/wpXJXQiIiKRSQldO+f2GHzsS+i0IEJERCQiKaFr576yu6hwGSREmTgzWSdEiIiIRCIldO2cb7j1nM5WLGZtKCwiIhKJlNC1c5v9CyKiQ9wTERERaSoldO3cFs2fExERiXhK6NqxvK+ryC91AdpQWEREJJJpFnw7VOXycNumUp7LrwLgiswYOsVYQtwrERERaSoldO3MDnstP9lwlO12FybgN4M6cOtZHULdLREREWkGJXTtyKrd1dzwXglVLoMusWaeGpHCRd1jQt0tERERaSYldO3ExgMOfrrxKLUeGNHNxt9GpJAWp2FWERGRtkAJXTvwZUkt124optYDkzNjeXpkivacExERaUO0yrWNO1jl5sp1xZQ5Dc5Ps/LkcCVzIiIibY0SujasotbDD98uZl+lmz6JUTw/uiMxUUrmRERE2holdG2U020w892jbC2upVOMmVfGp9JRW5OIiIi0SZpD18YYhsFre2q4a0sp35S7ibWYeHFsKpkd9KsWERFpq/Qp34ZsPuTgjs1lbK47zist1syfL0zRKRAiIiJtXKOHXHft2sWvfvUrLrzwQlJTUzn//POP2+65555j8ODBpKWlMWzYMN588816bUpLS5kzZw6ZmZmkp6czY8YMDh48WK/dpk2bGDduHF27dqV///4sWrQIwzAa2/U265syFz/eUMz414+w+bCTuCgTt53VgY+npjE2XfvMiYiItHWNTui+/PJL1q5dS69evcjJyTlum+XLlzN37lwmT55MXl4eubm5TJ8+nY8++iig3cyZM9mwYQOPPfYYTz31FDt37mTatGm4XC5/m127djF16lTS0tJ46aWXuOGGG7jvvvt44oknGtv1NudojZvbN9nJXVnEqt01mE0wIzuOT6amcdvZiSREa4qkiIhIe9DoIddLL72UCRMmAHDDDTfw6aef1mtz//33M3XqVO644w4ARowYwRdffMGDDz5IXl4eAJs3b+add95hxYoVjB49GoCsrCxyc3NZvXo1kydPBmDx4sWkpKSwZMkSrFYrI0eOpLi4mIcffpjrr78em83WpCceyZxug79+WcHDW8spdXorlWN72Lh7SBL9OkaHuHciIiISbI0u4ZjNJ3/I7t272blzJ5MmTQq4fcqUKWzcuBGHwwHAunXrSEpKYtSoUf42WVlZDBgwgLVr1/pve/vtt5kwYQJWqzXgWqWlpWzevLmx3W8TbvnQzoKPyih1GvRLiWLl+FReGd9JyZyIiEg71eKLIvLz8wHIzs4OuD0nJwen08mePXvIzs6moKCArKwsTCZTvXYFBQUAVFZWsm/fvnrXys7OxmQyUVBQwPDhw4/bj0GDBp2wj6+//jo9evTwJ5eRpNjh4Z87qwB4YEg81/a2YTFDTU1Ni/0Mp9MZ8F9pXYp38CnmwaeYB59iHnytEXOr1XrKYhq0QkJnt9sBSEpKCrg9OTkZgJKSEn+777fxtfO1KS0tPe61rFYrcXFx/nZN4fF4KCwsbPLjQ2XpviicHitnJrgZE3OYA/tb72cVFRW13sWlHsU7+BTz4FPMg08xD76WjHlmZmZoErpwsXXr1pPebxgGGRkZQepNyzAMg39ttQMeZp2ZSEZG66xgdTqdFBUVkZaWFjDULa1D8Q4+xTz4FPPgU8yDrzVibrE07FCAFk/ofJW4srIy0tLS/Lf7KncpKSn+dvv31y8v2e12fxtfZa6srCygjdPppKqqyt+uKUwmEzExkbWlx8YDDnaVe+gQbeLqnERiWnkVq9VqjbgYRTLFO/gU8+BTzINPMQ++UMS8xTMC33w331w6n/z8fKxWK5mZmYB3AURBQUG9/eTy8/PJysoCID4+nvT09HrX8j3O1669eHZHJQBX9orTliQiIiLi1+JZQWZmJn369GHVqlUBt69cuZKRI0f6S5Djxo3DbrezceNGf5udO3eybds2xo8f779t7NixrFmzhtra2oBrJSUlMXTo0Jbuftg6XO3mX3urAbguJy7EvREREZFw0ugh16qqKtatWwdAYWEh5eXl/uRt2LBhdOrUidtuu43Zs2eTmZnJ8OHDWblyJVu2bGHNmjX+6+Tm5jJmzBjmzJnDwoULsdls3HPPPfTr14+JEyf62918883k5eUxa9YsZs2axfbt21m8eDELFixoV3MCni+ootYDgztFMzC1/TxvERERObVGJ3SHDx/mxz/+ccBtvn+vXr2a4cOHM23aNKqqqli0aBGLFi2iT58+LFu2jNzc3IDHLVmyhPnz5zN37lzcbjejRo3iwQcfJCrqWLd69erFihUrmD9/PldddRWdOnXi9ttvZ86cOU15vhHJYxg8m+8dbr0uJz7EvREREZFwY7Lb7ToUNcxt2F/D5LXFJEab+PKHXYlv5flzNTU1FBYWkpGRoYm0QaB4B59iHnyKefAp5sEXyphrZn0E+HvdYogf9o5r9WROREREIo+ygzB3sMrNmr3eUyA03CoiIiLHo4QuzP1+SykuA4Z2seqsVhERETkuJXRh7K3CGl76uhqzCe7NrX9MmoiIiAgooQtbdoeHX/7Xe1btjf0SGNJZW5WIiIjI8SmhC1MLPirl2yoPvRMt/O7sxFB3R0RERMKYErowtGF/DUsLqjABT1yYQmyUKdRdEhERkTCmhC7MlNd6uOk/dgBmnxnP+Wm20HZIREREwp4SujDiMQx+t6mUfZVueiZY+P1gDbWKiIjIqTX66C9pHXaHh5+9V8Jbhd495xYPS9EmwiIiItIgSujCwP+OOPnxhqPsrXBjs8DD5yUzsruGWkVERKRhlNCFkGEY/H1HFbdtsuP0QGYHC/8Y1ZFBqdqiRERERBpOCV0I3fu/ch7eWg7AhNNi+POFKSTbNMwqIiIijaOELkQ27K/xJ3N3D0nk5v4JmEzankREREQaTwldCByudvPz97ynQMzMiWfugA4h7pGIiIhEMo3vBZnHMPjFeyUUVXs4MzlKZ7SKiIhIsymhC7L/t72SdfsdxFjgmYs66hQIERERaTYldEH06REnv99SCsC9uUn0TYkOcY9ERESkLVBCFyR2h4efbiyh1uNd0TozJz7UXRIREZE2QgldEByodHPpmsPsLHPRI87CExemaEWriIiItBitcm1l+fZapqwtZl+lm25xZvLGp5KiveZERESkBSmha0VbDju5al0xRx0espKiWD4+ldMSFHIRERFpWcouWsn7Bx1cta6YKpfB4E7RvDwuldQYS6i7JSIiIm2QErpWkpMURddYM6cnRvGPUR1JiNYwq4iIiLQOJXStpHOshdcv60yqzYzVogUQIiIi0nqU0LWibnEaYhUREZHWp3FAERERkQinhE5EREQkwimhExEREYlwSuhEREREIpwSOhEREZEIFxEJXX5+PpMmTaJ79+5kZ2dz55134nQ6Q90tERERkbAQ9tuW2O12Lr/8cnr16sXSpUs5cOAA8+fPp7q6moceeijU3RMREREJubBP6JYsWUJ5eTnPP/88KSkpALjdbubNm8evf/1runXrFuIeioiIiIRW2A+5rlu3jpEjR/qTOYBJkybh8XhYv359CHsmIiIiEh7CvkJXUFDA9OnTA25LTk6ma9euFBQUnPBxgwYNOuF9r7/+Oj169MDhcLRYP9sS3/xEzVMMDsU7+BTz4FPMg08xD77WiLnVasVsPnX9LewTOrvdTlJSUr3bk5OTKSkpafJ1PR4PhYWFzelam1dUVBTqLrQrinfwKebBp5gHn2IefC0Z88zMzLaR0DXV1q1bT3q/YRhkZGQEqTeRxel0UlRURFpaGlarNdTdafMU7+BTzINPMQ8+xTz4WiPmFkvDzoUP+4QuOTmZsrKyerfb7faAeXWNZTKZiImJaU7X2jyr1aoYBZHiHXyKefAp5sGnmAdfKGIe9osisrKyyM/PD7ittLSUgwcPkpWVFaJeiYiIiISPsE/oxo0bx8aNG7Hb7f7bVq1ahdlsZvTo0aHrWBtmtVrJzMxUiT5IFO/gU8yDTzEPPsU8+EIZ87BP6GbOnElCQgLXXHMN69evZ9myZSxYsICZM2dqD7pWcuDAAYqKiho0CVOaT/EOPsU8+BTz4FPMgy+UMTfZ7XYj6D+1kXbs2MEtt9zC5s2bSUhI4Oqrr2bBggX61tFKfFu+nGphibQMxTv4FPPgU8yDTzEPvlDGPOwXRQDk5OSwatWqUHdDREREJCypDisiIiIS4ZTQiYiIiEQ4JXQiIiIiEU4JnYiIiEiEU0InIiIiEuEiYtsSERERETkxVehEREREIpwSOhEREZEIp4ROREREJMIpoRMRERGJcEroRERERCKcEro2ZteuXfzqV7/iwgsvJDU1lfPPP79eG6fTye9//3vOOOMMunbtyujRo9m4cWNAm4KCAn77298ydOhQunXrxsCBA/n1r39NcXFxvevl5+czadIkunfvTnZ2NnfeeSdOp7PVnmO4aamYf99tt91GcnIyv/3tb+vdp5i3bMzz8/O55ppr6NmzJ927d2f48OFs2LAhoM23337LtddeS3p6OpmZmdx0002UlZW1yvMLRy0Z87179zJr1ixycnJIT09n1KhRxz2vuz2/zl999VV+9KMf0bdvX7p3786FF17I0qVLMYzAjSmee+45Bg8eTFpaGsOGDePNN9+sd63S0lLmzJlDZmYm6enpzJgxg4MHD9Zrt2nTJsaNG0fXrl3p378/ixYtqvfz2rKWivknn3zCjTfeyNlnn023bt0455xzuPvuu6msrKz3M1sy5kro2pgvv/yStWvX0qtXL3Jyco7b5vbbb+fpp59m7ty5LFu2jJ49e3LllVfy6aef+tts2LCB//73v1x33XW8/PLL3Hbbbaxdu5ZLL70Uh8Phb2e327n88stxOp0sXbqUBQsW8OyzzzJ//vzWfqpho6Vi/l1ffPEFzz//PImJifXuU8xbNuZffvklY8eOxWq18tRTT/H8888zdepUqqqq/G1qa2uZOnUqX3/9NX/729949NFHWb9+PbNnz27NpxlWWirmDoeDadOm8dlnn/HAAw+wdOlSsrOzue6663jnnXf87dr76/zPf/4zcXFxLFy4kBdeeIFx48Yxd+5c/vjHP/rbLF++nLlz5zJ58mTy8vLIzc1l+vTpfPTRRwHXmjlzJhs2bOCxxx7jqaeeYufOnUybNg2Xy+Vvs2vXLqZOnUpaWhovvfQSN9xwA/fddx9PPPFE0J5zqLVUzFesWMGuXbuYO3cuL7/8MjfccAPPPvssV199dcDPa+mYax+6Nsbj8WA2e/P0G264gU8//ZQPPvjAf/+BAwcYMGAA9913Hz/72c8AMAyDYcOG0bNnT1544QUAjh49SkpKCiaTyf/YTZs2cfHFF/OPf/yDK664AoBHH32URx55hM8//5yUlBQAnn32WebNm8fnn39Ot27dgvK8Q6mlYv5dl112GRdeeCEvvPACl1xyCQ899JD/PsW8ZWN+6aWX0rVrV/7+97+f8Oe98sorzJ49m82bN5OVlQXA+vXrmTJlCu+88w6DBw9ujacZVloq5h999BHjxo1j9erVDB8+3H/ts846ixEjRvg/zNr767y4uJjU1NSA2+bOncvKlSvZvXs3ZrOZIUOGcNZZZ/H000/724wfP56kpCTy8vIA2Lx5M+PHj2fFihWMHj0a8I7A5ObmsmTJEiZPngzAL3/5S9555x0+/vhjrFYrAH/4wx945plnyM/Px2azBeNph1RLxfzIkSN06tQp4Dp5eXnMnj2bd999l7POOgto+ZirQtfG+N5wT+SLL77A7Xb7/7ABTCYTo0ePZv369f7hjI4dOwYkcwADBw4ECCjVr1u3jpEjR/rfcAEmTZqEx+Nh/fr1zX4+kaClYu7z8ssvs3fvXn75y18e93qKecvFPD8/nw8++MCfgJzIunXr6Nevnz+ZAxg1ahQpKSmsXbu2Gc8kcrRUzGtrawECqs9ms5mEhISAoab2/jr/fmIB3vfgsrIyKisr2b17Nzt37mTSpEkBbaZMmcLGjRv9Iynr1q0jKSmJUaNG+dtkZWUxYMCAgNfu22+/zYQJE/yJhe9apaWlbN68uYWfXXhqqZh/P5nzXQe8Uzd8WjrmSujamZqaGoCAFxCAzWbD4XCwZ8+eEz72ww8/BAgYbikoKCA7OzugXXJyMl27dqWgoKCluh3RGhPz8vJy7rzzTv7whz8QFxd33Osp5qfW0Jj7hkkqKysZMWIEqamp9O/fnz/96U8BjztezE0mE9nZ2Yp5nYbGPDc3lzPPPJOFCxeye/du7HY7f/3rX/n666/58Y9/7H+cXuf1ffjhh3Tv3p0OHTqQn58PUC9GOTk5OJ1Of7wLCgrIysqq9wU9JyfHH8fKykr27dtX71rZ2dmYTKZ2G29oWsxPdJ3vPrY1Yq6Erp3p3bs34J20+V2+D7aSkpLjPq6mpoY77riDgQMHMnLkSP/tdrudpKSkeu2Tk5NPeK32pjExf+CBBzj99NOZMmXKCa+nmJ9aQ2N+6NAhAH76059y+eWXs3LlSqZNm8add94ZMASrmJ9aQ2MeFRXFa6+9RklJCWeddRaZmZncddddPPPMM+Tm5vofp5gH+uCDD1i+fDlz5swBvPEB6sUoOTkZOBbvhsSxtLT0uNeyWq3ExcW1y3hD02P+fcXFxTzwwANcdtll/r+T1oh5VKMfIRGtb9++nH/++fz+97+nR48e9OnTh+eff57//Oc/APW+xfn86le/Yu/evbz11lsnbCPH19CYf/nllzz99NOsW7culN1tExoac4/HA8CPfvQjfvOb3wAwYsQIDhw4wCOPPMJPfvKT0DyBCNTQmFdXVzNjxgwMw2DZsmV06NCBVatWMXv2bPLy8rjwwgtD+TTC0v79+5k5cybDhw/n5z//eai70y60VMxra2uZOXMm4J0X2ppUoWuHnnzySVJTUxk/fjy9evXiqaee4pZbbgEgLS2tXvuFCxeSl5fHs88+S9++fQPuS05OPu7WDXa7PWDuS3vXkJjfcccdXHHFFZx22mnY7XbsdjuGYeB0OrHb7f7kQzFvmIbE3PfNesSIEQGPHTFiBPv27fPHWTFvmIbEfOnSpXzyySe8/PLL/OAHP2DkyJE8+uijDB06lD/84Q/+aynmXna7nSuvvJKUlBSee+45/1xG32v3+zHyVZF8MWpIHH1Vou+3czqdVFVVtat4Q/Nj7mMYBjfeeKP/9d61a1f/fa0RcyV07VBmZiYbNmxg69atfPjhh3z66afExsbStWtXTjvttIC2f/3rX3nkkUf405/+xJgxY+pdKysryz+vwKe0tJSDBw8GTCBv7xoS8/z8fF5++WUyMzP9/9u3bx//+Mc/yMzMZOfOnYBi3lANifkZZ5xx0mv4JvIfL+aGYfjnJ4lXQ2K+Y8cOunXrVm8C+sCBA/nmm2/8/9br3FvNvPrqqykrK+OVV14JGJ7zzb36fozy8/OxWq1kZmYC3jgWFBTU29ssPz/fH8f4+HjS09PrXcv3uPYSb2iZmPvccccdvPrqqyxbtowBAwYE3NcaMVdC14717NmTM844w7/P07XXXhtw/yuvvMJtt93G73//e370ox8d9xrjxo1j48aN/m8oAKtWrcJsNgesdhOvk8V8yZIlrF69OuB/Xbp0YcKECaxevZr09HRAMW+sk8U8NzeXjh078u677wY85t133yU9Pd2/Wm3cuHF8/vnnfP311/42Gzdu5OjRo4wfPz4ozyOSnCzmGRkZHDhwgCNHjgQ85tNPPw34QtneX+cul4vrrruOHTt28Morr9C9e/eA+zMzM+nTp0+9DZlXrlzJyJEj/YtTxo0bh91uD9jgeefOnWzbti3gtTt27FjWrFnjX4Xsu1ZSUhJDhw5tjacYdloq5gCPPfYYf/nLX/jLX/4SMO/8u1o65ppD18ZUVVX552AVFhZSXl7uf/ENGzaMTp068dRTT5GYmEiPHj3Yu3cvf/7zn7HZbAHbZLz//vvccMMNjBgxgmHDhgVsmti9e3d69OgBeDesfOqpp7jmmmuYN28eBw4cYMGCBcycObPN7xPl01IxP/fcc+td22az+U8u8FHMWy7m0dHR3Hbbbfzud78jJSWFoUOH8vbbb7N8+XIef/xxf7srrriCRx99lGuvvZY777yT6upqFixYwMUXX9wu9qCDlov5tGnTePTRR7nyyiv55S9/SYcOHXj11Vf597//zV//+ld/u/b+Op83bx5vvfUWCxcupLy8POA9eODAgdhsNm677TZmz55NZmYmw4cPZ+XKlWzZsoU1a9b42+bm5jJmzBjmzJnDwoULsdls3HPPPfTr14+JEyf62918883k5eUxa9YsZs2axfbt21m8eDELFiyot3K5rWqpmOfl5XH33Xdz1VVX0bNnz4DrnH766f4vii0dc20s3Mbs2bOHQYMGHfc+30aef/rTn3jmmWc4cOAAHTt2ZOLEicyfP98/PwDg/vvvD9gd+7tuvfVWbr/9dv+/d+zYwS233MLmzZtJSEjg6quvbldvAi0V8+MZMGBAvY2FQTFv6Zj/9a9/5cknn2T//v307NmTm2++mRkzZgS0OXDgALfeeisbNmzAYrEwceJE7rvvvuOe5tEWtWTMP/30U+69914+/fRTampq6NWrF7/4xS/44Q9/GNCuPb/OBwwYQGFh4XHv27p1Kz179gS8x1AtWrSIffv20adPH+68804uueSSgPalpaXMnz+f1atX43a7GTVqFA8++GC9xHjTpk3Mnz+fzz77jE6dOvHTn/6UX/7yl+1mIVxLxfyGG2447obx4D2N4pprrvH/uyVjroROREREJMJpDp2IiIhIhFNCJyIiIhLhlNCJiIiIRDgldCIiIiIRTgmdiIiISIRTQiciIiIS4ZTQiYiIiEQ4JXQiIiIiEU4JnYiIiEiEU0InIlJn2rRp9OzZk0OHDtW7r7S0lJycHMaMGYPH4wlB70RETkwJnYhInYcffpja2lp+97vf1bvvnnvuobi4mEWLFmE2661TRMKL3pVEROpkZmZy66238sorr7B+/Xr/7Z988glLlizhxhtvZMCAAa3ah5qaGlUARaTRlNCJiHzHjTfeSL9+/Zg3bx41NTW43W5+9atfkZGRwa233kp+fj4zZswgMzOTtLQ0LrroItasWRNwjZKSEu644w4uuOACevToQUZGBtOmTeOzzz4LaPfee++RnJzM8uXLWbhwIWeeeSbdunWjrKwsmE9ZRNqAqFB3QEQknERFRfH4448zfvx4HnroITp16sTWrVtZvnw5e/bs4eKLL6Z79+786le/Ii4ujpUrV3LNNdfw3HPPMXHiRAB2797N66+/zqRJk/xz8p599lkmTJjApk2b6NatW8DPfOihh4iOjmbOnDk4nU6sVmsonrqIRDCT3W43Qt0JEZFw89vf/pZnn30Wm83GJZdcwtNPP80VV1zB4cOH2bBhAzabDQDDMLjkkks4cuQIH3/8MQAOh4Po6OiAuXZ79uwhNzeXefPmccsttwDeCt3EiRPJzMzkgw8+IDY2NvhPVETaBA25iogcx4IFC+jYsSNms5n77ruPkpIS/v3vfzN58mQqKiooLi6muLiYo0ePMnr0aL7++msOHDgAgM1m8ydzbrebo0ePkpCQQJ8+fdi6dWu9n/WjH/1IyZyINIuGXEVEjiMxMZE+ffpw9OhRunTpwscff4xhGNx7773ce++9x33M4cOH6d69Ox6PhyeffJJnnnmGPXv24Ha7/W06duxY73E9e/ZstechIu2DEjoRkQbwrTy96aabGDNmzHHb9OrVC4BHHnmEe++9l+nTpzN//nxSUlIwm83cfvvtx13BquqciDSXEjoRkQbIzMwEIDo6mosuuuikbVetWsXw4cN54oknAm4vLS09boVORKS5NIdORKQBOnfuzIUXXsjf//53Dh48WO/+I0eO+P+/xWLBMALXm7366qv+OXYiIi1NFToRkQZ6+OGHueSSS7jgggv48Y9/TGZmJocOHeKjjz5i//79/Oc//wHg4osv5sEHH+QXv/gFQ4cO5YsvviAvL89f5RMRaWlK6EREGuiMM87g3Xff5YEHHuCf//wnR48epXPnzgwYMMC/FQnAvHnzqKqq4pVXXmHlypUMGjSIl19+mbvuuit0nReRNk370ImIiIhEOM2hExEREYlwSuhEREREIpwSOhEREZEIp4ROREREJMIpoRMRERGJcEroRERERCKcEjoRERGRCKeETkRERCTCKaETERERiXBK6EREREQinBI6ERERkQinhE5EREQkwv1/MeLE1GfYer4AAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "babynames.drop(columns=['State', 'Sex', 'Name']).groupby(\"Year\").agg(ammd).plot();\n",
    "\n",
    "# max - min is valid only for numbers, so string columns are deleted"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h4 id=\"groupby-Puzzle-#2\">groupby Puzzle #2<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#groupby-Puzzle-#2\">¶</h4>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "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>Candidate</th>\n",
       "      <th>Party</th>\n",
       "      <th>%</th>\n",
       "      <th>Year</th>\n",
       "      <th>Result</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Reagan</td>\n",
       "      <td>Republican</td>\n",
       "      <td>58.8</td>\n",
       "      <td>1984</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Dole</td>\n",
       "      <td>Republican</td>\n",
       "      <td>40.7</td>\n",
       "      <td>1996</td>\n",
       "      <td>loss</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Bush</td>\n",
       "      <td>Republican</td>\n",
       "      <td>47.9</td>\n",
       "      <td>2000</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Dukakis</td>\n",
       "      <td>Democratic</td>\n",
       "      <td>45.6</td>\n",
       "      <td>1988</td>\n",
       "      <td>loss</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Bush</td>\n",
       "      <td>Republican</td>\n",
       "      <td>50.7</td>\n",
       "      <td>2004</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Candidate       Party     %  Year Result\n",
       "3     Reagan  Republican  58.8  1984    win\n",
       "11      Dole  Republican  40.7  1996   loss\n",
       "14      Bush  Republican  47.9  2000    win\n",
       "6    Dukakis  Democratic  45.6  1988   loss\n",
       "16      Bush  Republican  50.7  2004    win"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "elections = pd.read_csv(\"elections.csv\")\n",
    "elections.sample(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>We have to be careful when using aggregation functions. For example, the code below might be misinterpreted to say that Woodrow Wilson ran for election in 2016. Why is this happening?</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "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>Candidate</th>\n",
       "      <th>%</th>\n",
       "      <th>Year</th>\n",
       "      <th>Result</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Party</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Democratic</th>\n",
       "      <td>Obama</td>\n",
       "      <td>52.9</td>\n",
       "      <td>2016</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Independent</th>\n",
       "      <td>Perot</td>\n",
       "      <td>18.9</td>\n",
       "      <td>1996</td>\n",
       "      <td>loss</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Republican</th>\n",
       "      <td>Trump</td>\n",
       "      <td>58.8</td>\n",
       "      <td>2016</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Candidate     %  Year Result\n",
       "Party                                   \n",
       "Democratic      Obama  52.9  2016    win\n",
       "Independent     Perot  18.9  1996   loss\n",
       "Republican      Trump  58.8  2016    win"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "elections.groupby(\"Party\").agg('max').head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"groupby-puzzle-#3\">groupby puzzle #3<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#groupby-puzzle-#3\">¶</h3>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Inspired by above, try to predict the results of the groupby operation shown. The answer is below the image.</p>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p><img alt=\"groupby_puzzle.png\" src=\"data:image/png;base64,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\"/></p>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>The top ?? will be \"hi\", the second ?? will be \"tx\", and the third ?? will be \"sd\".</p>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"groupby-puzzle-#4\">groupby puzzle #4<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#groupby-puzzle-#4\">¶</h3>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Next we'll write code that properly returns the best result by each party. That is, each row should show the Year, Candidate, Popular Vote, Result, and % for the election in which that party saw its best results (rather than mixing them as in the example above).</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "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>Candidate</th>\n",
       "      <th>%</th>\n",
       "      <th>Year</th>\n",
       "      <th>Result</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Party</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Democratic</th>\n",
       "      <td>Obama</td>\n",
       "      <td>52.9</td>\n",
       "      <td>2008</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Independent</th>\n",
       "      <td>Perot</td>\n",
       "      <td>18.9</td>\n",
       "      <td>1992</td>\n",
       "      <td>loss</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Republican</th>\n",
       "      <td>Reagan</td>\n",
       "      <td>58.8</td>\n",
       "      <td>1984</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Candidate     %  Year Result\n",
       "Party                                   \n",
       "Democratic      Obama  52.9  2008    win\n",
       "Independent     Perot  18.9  1992   loss\n",
       "Republican     Reagan  58.8  1984    win"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def get_first(s):\n",
    "   return s.iloc[0]\n",
    "    \n",
    "elections_sorted_by_percent = elections.sort_values(\"%\", ascending=False)\n",
    "elections_sorted_by_percent.groupby(\"Party\").agg(get_first)\n",
    "# elections_sorted_by_percent.groupby(\"Party\").agg(lambda x : x.iloc[0])\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h2 id=\"Other-groupby-Features\">Other groupby Features<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Other-groupby-Features\">¶</h2>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>It is possible to group a DataFrame by multiple features. For example, if we group by Year and Sex we get back a DataFrame with the total number of babies of each sex born in each year.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "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></th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Year</th>\n",
       "      <th>Sex</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">1910</th>\n",
       "      <th>F</th>\n",
       "      <td>5950</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>M</th>\n",
       "      <td>3213</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">1911</th>\n",
       "      <th>F</th>\n",
       "      <td>6602</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>M</th>\n",
       "      <td>3381</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">1912</th>\n",
       "      <th>F</th>\n",
       "      <td>9803</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>M</th>\n",
       "      <td>8142</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Count\n",
       "Year Sex       \n",
       "1910 F     5950\n",
       "     M     3213\n",
       "1911 F     6602\n",
       "     M     3381\n",
       "1912 F     9803\n",
       "     M     8142"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames.drop(columns=['State', 'Name']).groupby([\"Year\", \"Sex\"]).agg('sum').head(6)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>The DataFrame resulting from the aggregation operation is now multi-indexed. That is, it has more than one dimension to its index. We will explore this in next week's exercises.</p>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"groupby.size()\">groupby.size()<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#groupby.size()\">¶</h3>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Party\n",
       "Democratic     10\n",
       "Independent     3\n",
       "Republican     10\n",
       "dtype: int64"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#size returns a Series giving the size of each group\n",
    "elections.groupby(\"Party\").size().head(15)\n",
    "# elections.groupby(\"Party\").agg(len).head(15)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"groupby.filter()\">groupby.filter()<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#groupby.filter()\">¶<</h3>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "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>Candidate</th>\n",
       "      <th>Party</th>\n",
       "      <th>%</th>\n",
       "      <th>Year</th>\n",
       "      <th>Result</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Clinton</td>\n",
       "      <td>Democratic</td>\n",
       "      <td>43.0</td>\n",
       "      <td>1992</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Bush</td>\n",
       "      <td>Republican</td>\n",
       "      <td>37.4</td>\n",
       "      <td>1992</td>\n",
       "      <td>loss</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Perot</td>\n",
       "      <td>Independent</td>\n",
       "      <td>18.9</td>\n",
       "      <td>1992</td>\n",
       "      <td>loss</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Candidate        Party     %  Year Result\n",
       "7   Clinton   Democratic  43.0  1992    win\n",
       "8      Bush   Republican  37.4  1992   loss\n",
       "9     Perot  Independent  18.9  1992   loss"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# elections[elections['%']<45]\n",
    "a = elections.groupby(\"Year\").agg('max')\n",
    "y = a[a['%']<45].index\n",
    "elections[elections['Year'].isin(y)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "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>Candidate</th>\n",
       "      <th>Party</th>\n",
       "      <th>%</th>\n",
       "      <th>Year</th>\n",
       "      <th>Result</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Clinton</td>\n",
       "      <td>Democratic</td>\n",
       "      <td>43.0</td>\n",
       "      <td>1992</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Bush</td>\n",
       "      <td>Republican</td>\n",
       "      <td>37.4</td>\n",
       "      <td>1992</td>\n",
       "      <td>loss</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Perot</td>\n",
       "      <td>Independent</td>\n",
       "      <td>18.9</td>\n",
       "      <td>1992</td>\n",
       "      <td>loss</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Candidate        Party     %  Year Result\n",
       "7   Clinton   Democratic  43.0  1992    win\n",
       "8      Bush   Republican  37.4  1992   loss\n",
       "9     Perot  Independent  18.9  1992   loss"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "# filter gives a copy of the original DataFrame where row r is included\n",
    "# if its group obeys the given condition\n",
    "#\n",
    "# Note: Filtering is done per GROUP, not per ROW.\n",
    "elections.groupby(\"Year\").filter(lambda sf: sf[\"%\"].max() < 45)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"groupby.sum(),-groupby.mean(),-etc.\">groupby.sum(), groupby.mean(), etc.<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#groupby.sum(),-groupby.mean(),-etc.\">¶</h3>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>As an alternative to groupby.agg(sum), we can also simply do groupby.sum().</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "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>%</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Year</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1980</th>\n",
       "      <td>98.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1984</th>\n",
       "      <td>96.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1988</th>\n",
       "      <td>99.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1992</th>\n",
       "      <td>99.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1996</th>\n",
       "      <td>98.3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         %\n",
       "Year      \n",
       "1980  98.3\n",
       "1984  96.4\n",
       "1988  99.0\n",
       "1992  99.3\n",
       "1996  98.3"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# elections.groupby(\"Year\").agg(sum).head()\n",
    "elections.drop(columns=['Candidate', 'Party', 'Result']).groupby(\"Year\").sum().head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>The same applies for many other common operations.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "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>Candidate</th>\n",
       "      <th>Party</th>\n",
       "      <th>%</th>\n",
       "      <th>Result</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1980</th>\n",
       "      <td>Reagan</td>\n",
       "      <td>Republican</td>\n",
       "      <td>50.7</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1984</th>\n",
       "      <td>Reagan</td>\n",
       "      <td>Republican</td>\n",
       "      <td>58.8</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1988</th>\n",
       "      <td>Dukakis</td>\n",
       "      <td>Republican</td>\n",
       "      <td>53.4</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1992</th>\n",
       "      <td>Perot</td>\n",
       "      <td>Republican</td>\n",
       "      <td>43.0</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1996</th>\n",
       "      <td>Perot</td>\n",
       "      <td>Republican</td>\n",
       "      <td>49.2</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Candidate       Party     % Result\n",
       "Year                                   \n",
       "1980    Reagan  Republican  50.7    win\n",
       "1984    Reagan  Republican  58.8    win\n",
       "1988   Dukakis  Republican  53.4    win\n",
       "1992     Perot  Republican  43.0    win\n",
       "1996     Perot  Republican  49.2    win"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# elections.groupby(\"Year\").agg(max).head()\n",
    "elections.groupby(\"Year\").max().head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "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>Candidate</th>\n",
       "      <th>Party</th>\n",
       "      <th>%</th>\n",
       "      <th>Result</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1980</th>\n",
       "      <td>Reagan</td>\n",
       "      <td>Republican</td>\n",
       "      <td>50.7</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1984</th>\n",
       "      <td>Reagan</td>\n",
       "      <td>Republican</td>\n",
       "      <td>58.8</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1988</th>\n",
       "      <td>Dukakis</td>\n",
       "      <td>Republican</td>\n",
       "      <td>53.4</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1992</th>\n",
       "      <td>Perot</td>\n",
       "      <td>Republican</td>\n",
       "      <td>43.0</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1996</th>\n",
       "      <td>Perot</td>\n",
       "      <td>Republican</td>\n",
       "      <td>49.2</td>\n",
       "      <td>win</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Candidate       Party     % Result\n",
       "Year                                   \n",
       "1980    Reagan  Republican  50.7    win\n",
       "1984    Reagan  Republican  58.8    win\n",
       "1988   Dukakis  Republican  53.4    win\n",
       "1992     Perot  Republican  43.0    win\n",
       "1996     Perot  Republican  49.2    win"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#elections.groupby(\"Year\").mean().head()\n",
    "#elections.groupby(\"Year\").median().head()\n",
    "elections.groupby(\"Year\").max().head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h2 id=\"Pivot-Tables\">Pivot Tables<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Pivot-Tables\">¶</h2>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<h3 id=\"Goal-5:-Finding-the-number-of-babies-born-in-each-year-of-each-sex.\">Goal 5: Finding the number of babies born in each year of each sex.<a class=\"anchor-link\" href=\"http://www.ds100.org/su20/resources/assets/lectures/lec06/lec06.html#Goal-5:-Finding-the-number-of-babies-born-in-each-year-of-each-sex.\">¶</h3>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>Suppose we want to build a table showing the total number of babies born of each sex in each year. One way is to groupby using both columns of interest.</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "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></th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Year</th>\n",
       "      <th>Sex</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">1910</th>\n",
       "      <th>F</th>\n",
       "      <td>5950</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>M</th>\n",
       "      <td>3213</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">1911</th>\n",
       "      <th>F</th>\n",
       "      <td>6602</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>M</th>\n",
       "      <td>3381</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">1912</th>\n",
       "      <th>F</th>\n",
       "      <td>9803</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>M</th>\n",
       "      <td>8142</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Count\n",
       "Year Sex       \n",
       "1910 F     5950\n",
       "     M     3213\n",
       "1911 F     6602\n",
       "     M     3381\n",
       "1912 F     9803\n",
       "     M     8142"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames.drop(columns=['State', 'Name']).groupby([\"Year\", \"Sex\"]).agg('sum').head(6)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>A more natural approach is to use a pivot table (like we saw in data 8).</p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "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>Sex</th>\n",
       "      <th>F</th>\n",
       "      <th>M</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1910</th>\n",
       "      <td>5950</td>\n",
       "      <td>3213</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1911</th>\n",
       "      <td>6602</td>\n",
       "      <td>3381</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1912</th>\n",
       "      <td>9803</td>\n",
       "      <td>8142</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1913</th>\n",
       "      <td>11860</td>\n",
       "      <td>10234</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1914</th>\n",
       "      <td>13815</td>\n",
       "      <td>13111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1915</th>\n",
       "      <td>18643</td>\n",
       "      <td>17192</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Sex       F      M\n",
       "Year              \n",
       "1910   5950   3213\n",
       "1911   6602   3381\n",
       "1912   9803   8142\n",
       "1913  11860  10234\n",
       "1914  13815  13111\n",
       "1915  18643  17192"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "babynames_pivot = babynames.pivot_table(\n",
    "    index='Year', # the rows (turned into index)\n",
    "    columns='Sex', # the column values\n",
    "    values='Count', # the field(s) to processed in each group\n",
    "    aggfunc='sum', # group operation\n",
    ")\n",
    "babynames_pivot.head(6)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p>The basic idea behind pivot tables is shown in the image below.</p>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<p><img alt=\"pivot_picture.png\" src=\"data:image/png;base64,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\"/></p>\n"
   ]
  },
  {
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}