EDA portfolio.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 161,
   "id": "38718e5e-f2d3-4754-bfb6-b7f914617268",
   "metadata": {},
   "outputs": [],
   "source": [
    "# https://www.kaggle.com/datasets/aiaiaidavid/the-big-dataset-of-ultra-marathon-running/discussion/420633"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "id": "ffd40adc-de38-495d-a6be-5eaf244a8693",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "id": "64cb1b56-52f3-4eaf-a6a8-e572fc9ab2c5",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      
     ]
    },
    {
     "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 of event</th>\n",
       "      <th>Event dates</th>\n",
       "      <th>Event name</th>\n",
       "      <th>Event distance/length</th>\n",
       "      <th>Event number of finishers</th>\n",
       "      <th>Athlete performance</th>\n",
       "      <th>Athlete club</th>\n",
       "      <th>Athlete country</th>\n",
       "      <th>Athlete year of birth</th>\n",
       "      <th>Athlete gender</th>\n",
       "      <th>Athlete age category</th>\n",
       "      <th>Athlete average speed</th>\n",
       "      <th>Athlete ID</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2018</td>\n",
       "      <td>06.01.2018</td>\n",
       "      <td>Selva Costera (CHI)</td>\n",
       "      <td>50km</td>\n",
       "      <td>22</td>\n",
       "      <td>4:51:39 h</td>\n",
       "      <td>Tnfrc</td>\n",
       "      <td>CHI</td>\n",
       "      <td>1978.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M35</td>\n",
       "      <td>10.286</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2018</td>\n",
       "      <td>06.01.2018</td>\n",
       "      <td>Selva Costera (CHI)</td>\n",
       "      <td>50km</td>\n",
       "      <td>22</td>\n",
       "      <td>5:15:45 h</td>\n",
       "      <td>Roberto Echeverría</td>\n",
       "      <td>CHI</td>\n",
       "      <td>1981.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M35</td>\n",
       "      <td>9.501</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2018</td>\n",
       "      <td>06.01.2018</td>\n",
       "      <td>Selva Costera (CHI)</td>\n",
       "      <td>50km</td>\n",
       "      <td>22</td>\n",
       "      <td>5:16:44 h</td>\n",
       "      <td>Puro Trail Osorno</td>\n",
       "      <td>CHI</td>\n",
       "      <td>1987.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M23</td>\n",
       "      <td>9.472</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2018</td>\n",
       "      <td>06.01.2018</td>\n",
       "      <td>Selva Costera (CHI)</td>\n",
       "      <td>50km</td>\n",
       "      <td>22</td>\n",
       "      <td>5:34:13 h</td>\n",
       "      <td>Columbia</td>\n",
       "      <td>ARG</td>\n",
       "      <td>1976.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M40</td>\n",
       "      <td>8.976</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2018</td>\n",
       "      <td>06.01.2018</td>\n",
       "      <td>Selva Costera (CHI)</td>\n",
       "      <td>50km</td>\n",
       "      <td>22</td>\n",
       "      <td>5:54:14 h</td>\n",
       "      <td>Baguales Trail</td>\n",
       "      <td>CHI</td>\n",
       "      <td>1992.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M23</td>\n",
       "      <td>8.469</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Year of event Event dates           Event name Event distance/length  \\\n",
       "0           2018  06.01.2018  Selva Costera (CHI)                  50km   \n",
       "1           2018  06.01.2018  Selva Costera (CHI)                  50km   \n",
       "2           2018  06.01.2018  Selva Costera (CHI)                  50km   \n",
       "3           2018  06.01.2018  Selva Costera (CHI)                  50km   \n",
       "4           2018  06.01.2018  Selva Costera (CHI)                  50km   \n",
       "\n",
       "   Event number of finishers Athlete performance        Athlete club  \\\n",
       "0                         22           4:51:39 h               Tnfrc   \n",
       "1                         22           5:15:45 h  Roberto Echeverría   \n",
       "2                         22           5:16:44 h   Puro Trail Osorno   \n",
       "3                         22           5:34:13 h            Columbia   \n",
       "4                         22           5:54:14 h      Baguales Trail   \n",
       "\n",
       "  Athlete country  Athlete year of birth Athlete gender Athlete age category  \\\n",
       "0             CHI                 1978.0              M                  M35   \n",
       "1             CHI                 1981.0              M                  M35   \n",
       "2             CHI                 1987.0              M                  M23   \n",
       "3             ARG                 1976.0              M                  M40   \n",
       "4             CHI                 1992.0              M                  M23   \n",
       "\n",
       "  Athlete average speed  Athlete ID  \n",
       "0                10.286           0  \n",
       "1                 9.501           1  \n",
       "2                 9.472           2  \n",
       "3                 8.976           3  \n",
       "4                 8.469           4  "
      ]
     },
     "execution_count": 163,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's look at the data\n",
    "df = pd.read_csv('TWO_CENTURIES_OF_UM_RACES.csv')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "id": "3dd5cb08-787d-4fc2-84b5-2765cc828bef",
   "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 of event</th>\n",
       "      <th>event dates</th>\n",
       "      <th>event name</th>\n",
       "      <th>event distance/length</th>\n",
       "      <th>event number of finishers</th>\n",
       "      <th>athlete performance</th>\n",
       "      <th>athlete club</th>\n",
       "      <th>athlete country</th>\n",
       "      <th>athlete year of birth</th>\n",
       "      <th>athlete gender</th>\n",
       "      <th>athlete age category</th>\n",
       "      <th>athlete average speed</th>\n",
       "      <th>athlete id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2018</td>\n",
       "      <td>06.01.2018</td>\n",
       "      <td>Selva Costera (CHI)</td>\n",
       "      <td>50km</td>\n",
       "      <td>22</td>\n",
       "      <td>4:51:39 h</td>\n",
       "      <td>Tnfrc</td>\n",
       "      <td>CHI</td>\n",
       "      <td>1978.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M35</td>\n",
       "      <td>10.286</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2018</td>\n",
       "      <td>06.01.2018</td>\n",
       "      <td>Selva Costera (CHI)</td>\n",
       "      <td>50km</td>\n",
       "      <td>22</td>\n",
       "      <td>5:15:45 h</td>\n",
       "      <td>Roberto Echeverría</td>\n",
       "      <td>CHI</td>\n",
       "      <td>1981.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M35</td>\n",
       "      <td>9.501</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2018</td>\n",
       "      <td>06.01.2018</td>\n",
       "      <td>Selva Costera (CHI)</td>\n",
       "      <td>50km</td>\n",
       "      <td>22</td>\n",
       "      <td>5:16:44 h</td>\n",
       "      <td>Puro Trail Osorno</td>\n",
       "      <td>CHI</td>\n",
       "      <td>1987.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M23</td>\n",
       "      <td>9.472</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2018</td>\n",
       "      <td>06.01.2018</td>\n",
       "      <td>Selva Costera (CHI)</td>\n",
       "      <td>50km</td>\n",
       "      <td>22</td>\n",
       "      <td>5:34:13 h</td>\n",
       "      <td>Columbia</td>\n",
       "      <td>ARG</td>\n",
       "      <td>1976.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M40</td>\n",
       "      <td>8.976</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2018</td>\n",
       "      <td>06.01.2018</td>\n",
       "      <td>Selva Costera (CHI)</td>\n",
       "      <td>50km</td>\n",
       "      <td>22</td>\n",
       "      <td>5:54:14 h</td>\n",
       "      <td>Baguales Trail</td>\n",
       "      <td>CHI</td>\n",
       "      <td>1992.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M23</td>\n",
       "      <td>8.469</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year of event event dates           event name event distance/length  \\\n",
       "0           2018  06.01.2018  Selva Costera (CHI)                  50km   \n",
       "1           2018  06.01.2018  Selva Costera (CHI)                  50km   \n",
       "2           2018  06.01.2018  Selva Costera (CHI)                  50km   \n",
       "3           2018  06.01.2018  Selva Costera (CHI)                  50km   \n",
       "4           2018  06.01.2018  Selva Costera (CHI)                  50km   \n",
       "\n",
       "   event number of finishers athlete performance        athlete club  \\\n",
       "0                         22           4:51:39 h               Tnfrc   \n",
       "1                         22           5:15:45 h  Roberto Echeverría   \n",
       "2                         22           5:16:44 h   Puro Trail Osorno   \n",
       "3                         22           5:34:13 h            Columbia   \n",
       "4                         22           5:54:14 h      Baguales Trail   \n",
       "\n",
       "  athlete country  athlete year of birth athlete gender athlete age category  \\\n",
       "0             CHI                 1978.0              M                  M35   \n",
       "1             CHI                 1981.0              M                  M35   \n",
       "2             CHI                 1987.0              M                  M23   \n",
       "3             ARG                 1976.0              M                  M40   \n",
       "4             CHI                 1992.0              M                  M23   \n",
       "\n",
       "  athlete average speed  athlete id  \n",
       "0                10.286           0  \n",
       "1                 9.501           1  \n",
       "2                 9.472           2  \n",
       "3                 8.976           3  \n",
       "4                 8.469           4  "
      ]
     },
     "execution_count": 164,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's make all columns labels lower case\n",
    "df.columns = df.columns.str.lower()\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "id": "a6183de5-484a-4b3e-8234-a1501ee926e6",
   "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 of event</th>\n",
       "      <th>event dates</th>\n",
       "      <th>event name</th>\n",
       "      <th>event distance/length</th>\n",
       "      <th>event number of finishers</th>\n",
       "      <th>athlete performance</th>\n",
       "      <th>athlete club</th>\n",
       "      <th>athlete country</th>\n",
       "      <th>athlete year of birth</th>\n",
       "      <th>athlete gender</th>\n",
       "      <th>athlete age category</th>\n",
       "      <th>athlete average speed</th>\n",
       "      <th>athlete id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2613471</th>\n",
       "      <td>2020</td>\n",
       "      <td>23.02.2020</td>\n",
       "      <td>Terre di Siena Ultramarathon (ITA)</td>\n",
       "      <td>50km</td>\n",
       "      <td>462</td>\n",
       "      <td>3:23:24 h</td>\n",
       "      <td>POD. Ozzanese</td>\n",
       "      <td>ITA</td>\n",
       "      <td>1981.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M35</td>\n",
       "      <td>14.749</td>\n",
       "      <td>36487</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2613472</th>\n",
       "      <td>2020</td>\n",
       "      <td>23.02.2020</td>\n",
       "      <td>Terre di Siena Ultramarathon (ITA)</td>\n",
       "      <td>50km</td>\n",
       "      <td>462</td>\n",
       "      <td>3:35:03 h</td>\n",
       "      <td>POL. Dil. Santa Lucia</td>\n",
       "      <td>ITA</td>\n",
       "      <td>1981.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M35</td>\n",
       "      <td>13.95</td>\n",
       "      <td>89785</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2613473</th>\n",
       "      <td>2020</td>\n",
       "      <td>23.02.2020</td>\n",
       "      <td>Terre di Siena Ultramarathon (ITA)</td>\n",
       "      <td>50km</td>\n",
       "      <td>462</td>\n",
       "      <td>3:47:58 h</td>\n",
       "      <td>A.S.D. Risubbiani 2008</td>\n",
       "      <td>ITA</td>\n",
       "      <td>1978.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M40</td>\n",
       "      <td>13.16</td>\n",
       "      <td>3564</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2613474</th>\n",
       "      <td>2020</td>\n",
       "      <td>23.02.2020</td>\n",
       "      <td>Terre di Siena Ultramarathon (ITA)</td>\n",
       "      <td>50km</td>\n",
       "      <td>462</td>\n",
       "      <td>3:53:58 h</td>\n",
       "      <td>Marathon Cremona</td>\n",
       "      <td>ITA</td>\n",
       "      <td>1989.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M23</td>\n",
       "      <td>12.822</td>\n",
       "      <td>36509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2613475</th>\n",
       "      <td>2020</td>\n",
       "      <td>23.02.2020</td>\n",
       "      <td>Terre di Siena Ultramarathon (ITA)</td>\n",
       "      <td>50km</td>\n",
       "      <td>462</td>\n",
       "      <td>3:55:08 h</td>\n",
       "      <td>Sevenlife SSD</td>\n",
       "      <td>ITA</td>\n",
       "      <td>1974.0</td>\n",
       "      <td>M</td>\n",
       "      <td>M45</td>\n",
       "      <td>12.759</td>\n",
       "      <td>826011</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         year of event event dates                          event name  \\\n",
       "2613471           2020  23.02.2020  Terre di Siena Ultramarathon (ITA)   \n",
       "2613472           2020  23.02.2020  Terre di Siena Ultramarathon (ITA)   \n",
       "2613473           2020  23.02.2020  Terre di Siena Ultramarathon (ITA)   \n",
       "2613474           2020  23.02.2020  Terre di Siena Ultramarathon (ITA)   \n",
       "2613475           2020  23.02.2020  Terre di Siena Ultramarathon (ITA)   \n",
       "\n",
       "        event distance/length  event number of finishers athlete performance  \\\n",
       "2613471                  50km                        462           3:23:24 h   \n",
       "2613472                  50km                        462           3:35:03 h   \n",
       "2613473                  50km                        462           3:47:58 h   \n",
       "2613474                  50km                        462           3:53:58 h   \n",
       "2613475                  50km                        462           3:55:08 h   \n",
       "\n",
       "                   athlete club athlete country  athlete year of birth  \\\n",
       "2613471           POD. Ozzanese             ITA                 1981.0   \n",
       "2613472   POL. Dil. Santa Lucia             ITA                 1981.0   \n",
       "2613473  A.S.D. Risubbiani 2008             ITA                 1978.0   \n",
       "2613474        Marathon Cremona             ITA                 1989.0   \n",
       "2613475           Sevenlife SSD             ITA                 1974.0   \n",
       "\n",
       "        athlete gender athlete age category athlete average speed  athlete id  \n",
       "2613471              M                  M35                14.749       36487  \n",
       "2613472              M                  M35                 13.95       89785  \n",
       "2613473              M                  M40                 13.16        3564  \n",
       "2613474              M                  M23                12.822       36509  \n",
       "2613475              M                  M45                12.759      826011  "
      ]
     },
     "execution_count": 165,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Only ITA races, 50k km, year 2020\n",
    "df2 = df[(df['event distance/length'] == '50km') & (df['year of event'] == 2020) & (df['event name'].str.contains('ITA'))]\n",
    "df2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "id": "9c6cdb33-6507-4e90-afed-b4090f8fcd43",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['50km']\n",
      "[2020]\n",
      "['Terre di Siena Ultramarathon (ITA)' 'Bettona Crossing (ITA)'\n",
      " '6 Days UMF - 50 K (ITA)' 'Pantelleria Trail (ITA)'\n",
      " 'Ultra Beach 50 Km (ITA)']\n"
     ]
    }
   ],
   "source": [
    "# Let's do a quick check regarding my filtering\n",
    "print(df2['event distance/length'].unique())\n",
    "print(df2['year of event'].unique())\n",
    "print(df2['event name'].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "id": "12fc6d2a-8236-46ca-8949-ad6628f7a8fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Drop NA and duplicates\n",
    "df2 = df2.dropna()\n",
    "df2 = df2.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "id": "247dee43-e166-43ee-964e-473288b66330",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape: (584, 13)\n",
      "year of event                  int64\n",
      "event dates                   object\n",
      "event name                    object\n",
      "event distance/length         object\n",
      "event number of finishers      int64\n",
      "athlete performance           object\n",
      "athlete club                  object\n",
      "athlete country               object\n",
      "athlete year of birth        float64\n",
      "athlete gender                object\n",
      "athlete age category          object\n",
      "athlete average speed         object\n",
      "athlete id                     int64\n",
      "dtype: object\n"
     ]
    }
   ],
   "source": [
    "# Let's check data types since I've been given an error about it\n",
    "print('shape:', df2.shape)\n",
    "print(df2.dtypes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 169,
   "id": "0cdb090e-9e62-496c-9ce2-006b273f61f6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "year of event                         int64\n",
       "event dates                  datetime64[ns]\n",
       "event name                           object\n",
       "event distance/length                 int64\n",
       "event number of finishers             int64\n",
       "athlete performance                  object\n",
       "athlete club                         object\n",
       "athlete country                      object\n",
       "athlete year of birth                 int32\n",
       "athlete gender                       object\n",
       "athlete age category                 object\n",
       "athlete average speed               float64\n",
       "athlete id                            int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 169,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Fixing data types\n",
    "df2['athlete year of birth'] = df2['athlete year of birth'].astype(int)\n",
    "df2['event dates'] = pd.to_datetime(df2['event dates'], dayfirst = True)\n",
    "df2['athlete average speed'] = df2['athlete average speed'].astype(float)\n",
    "\n",
    "df2['event distance/length'] = df2['event distance/length'].str.extract('(\\d+)', expand = False)\n",
    "df2['event distance/length'] = pd.to_numeric(df2['event distance/length'])\n",
    "\n",
    "df2.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "id": "e3894c08-ae80-4a58-9dff-88fa36a3745f",
   "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 of event</th>\n",
       "      <th>event dates</th>\n",
       "      <th>event name</th>\n",
       "      <th>event distance/length</th>\n",
       "      <th>event number of finishers</th>\n",
       "      <th>athlete performance</th>\n",
       "      <th>athlete club</th>\n",
       "      <th>athlete country</th>\n",
       "      <th>athlete year of birth</th>\n",
       "      <th>athlete gender</th>\n",
       "      <th>athlete age category</th>\n",
       "      <th>athlete average speed</th>\n",
       "      <th>athlete id</th>\n",
       "      <th>athlete age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2613471</th>\n",
       "      <td>2020</td>\n",
       "      <td>2020-02-23</td>\n",
       "      <td>Terre di Siena Ultramarathon (ITA)</td>\n",
       "      <td>50</td>\n",
       "      <td>462</td>\n",
       "      <td>3:23:24 h</td>\n",
       "      <td>POD. Ozzanese</td>\n",
       "      <td>ITA</td>\n",
       "      <td>1981</td>\n",
       "      <td>M</td>\n",
       "      <td>M35</td>\n",
       "      <td>14.749</td>\n",
       "      <td>36487</td>\n",
       "      <td>39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2613472</th>\n",
       "      <td>2020</td>\n",
       "      <td>2020-02-23</td>\n",
       "      <td>Terre di Siena Ultramarathon (ITA)</td>\n",
       "      <td>50</td>\n",
       "      <td>462</td>\n",
       "      <td>3:35:03 h</td>\n",
       "      <td>POL. Dil. Santa Lucia</td>\n",
       "      <td>ITA</td>\n",
       "      <td>1981</td>\n",
       "      <td>M</td>\n",
       "      <td>M35</td>\n",
       "      <td>13.950</td>\n",
       "      <td>89785</td>\n",
       "      <td>39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2613473</th>\n",
       "      <td>2020</td>\n",
       "      <td>2020-02-23</td>\n",
       "      <td>Terre di Siena Ultramarathon (ITA)</td>\n",
       "      <td>50</td>\n",
       "      <td>462</td>\n",
       "      <td>3:47:58 h</td>\n",
       "      <td>A.S.D. Risubbiani 2008</td>\n",
       "      <td>ITA</td>\n",
       "      <td>1978</td>\n",
       "      <td>M</td>\n",
       "      <td>M40</td>\n",
       "      <td>13.160</td>\n",
       "      <td>3564</td>\n",
       "      <td>42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2613474</th>\n",
       "      <td>2020</td>\n",
       "      <td>2020-02-23</td>\n",
       "      <td>Terre di Siena Ultramarathon (ITA)</td>\n",
       "      <td>50</td>\n",
       "      <td>462</td>\n",
       "      <td>3:53:58 h</td>\n",
       "      <td>Marathon Cremona</td>\n",
       "      <td>ITA</td>\n",
       "      <td>1989</td>\n",
       "      <td>M</td>\n",
       "      <td>M23</td>\n",
       "      <td>12.822</td>\n",
       "      <td>36509</td>\n",
       "      <td>31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2613475</th>\n",
       "      <td>2020</td>\n",
       "      <td>2020-02-23</td>\n",
       "      <td>Terre di Siena Ultramarathon (ITA)</td>\n",
       "      <td>50</td>\n",
       "      <td>462</td>\n",
       "      <td>3:55:08 h</td>\n",
       "      <td>Sevenlife SSD</td>\n",
       "      <td>ITA</td>\n",
       "      <td>1974</td>\n",
       "      <td>M</td>\n",
       "      <td>M45</td>\n",
       "      <td>12.759</td>\n",
       "      <td>826011</td>\n",
       "      <td>46</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         year of event event dates                          event name  \\\n",
       "2613471           2020  2020-02-23  Terre di Siena Ultramarathon (ITA)   \n",
       "2613472           2020  2020-02-23  Terre di Siena Ultramarathon (ITA)   \n",
       "2613473           2020  2020-02-23  Terre di Siena Ultramarathon (ITA)   \n",
       "2613474           2020  2020-02-23  Terre di Siena Ultramarathon (ITA)   \n",
       "2613475           2020  2020-02-23  Terre di Siena Ultramarathon (ITA)   \n",
       "\n",
       "         event distance/length  event number of finishers athlete performance  \\\n",
       "2613471                     50                        462           3:23:24 h   \n",
       "2613472                     50                        462           3:35:03 h   \n",
       "2613473                     50                        462           3:47:58 h   \n",
       "2613474                     50                        462           3:53:58 h   \n",
       "2613475                     50                        462           3:55:08 h   \n",
       "\n",
       "                   athlete club athlete country  athlete year of birth  \\\n",
       "2613471           POD. Ozzanese             ITA                   1981   \n",
       "2613472   POL. Dil. Santa Lucia             ITA                   1981   \n",
       "2613473  A.S.D. Risubbiani 2008             ITA                   1978   \n",
       "2613474        Marathon Cremona             ITA                   1989   \n",
       "2613475           Sevenlife SSD             ITA                   1974   \n",
       "\n",
       "        athlete gender athlete age category  athlete average speed  \\\n",
       "2613471              M                  M35                 14.749   \n",
       "2613472              M                  M35                 13.950   \n",
       "2613473              M                  M40                 13.160   \n",
       "2613474              M                  M23                 12.822   \n",
       "2613475              M                  M45                 12.759   \n",
       "\n",
       "         athlete id  athlete age  \n",
       "2613471       36487           39  \n",
       "2613472       89785           39  \n",
       "2613473        3564           42  \n",
       "2613474       36509           31  \n",
       "2613475      826011           46  "
      ]
     },
     "execution_count": 170,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Add the 'athlete age' comlumn. We don't have the exact birth date, so it will not be 100% accurate\n",
    "df2['athlete age'] = 2020 - df2['athlete year of birth']\n",
    "df2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 171,
   "id": "057324a6-365c-4898-a446-ebdfaf8e17d4",
   "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 of event</th>\n",
       "      <th>event dates</th>\n",
       "      <th>event distance/length</th>\n",
       "      <th>event number of finishers</th>\n",
       "      <th>athlete year of birth</th>\n",
       "      <th>athlete average speed</th>\n",
       "      <th>athlete id</th>\n",
       "      <th>athlete age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>584.0</td>\n",
       "      <td>584</td>\n",
       "      <td>584.0</td>\n",
       "      <td>584.000000</td>\n",
       "      <td>584.000000</td>\n",
       "      <td>584.000000</td>\n",
       "      <td>584.000000</td>\n",
       "      <td>584.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2020.0</td>\n",
       "      <td>2020-04-23 20:35:20.547945216</td>\n",
       "      <td>50.0</td>\n",
       "      <td>369.551370</td>\n",
       "      <td>1971.849315</td>\n",
       "      <td>8.686914</td>\n",
       "      <td>369919.210616</td>\n",
       "      <td>48.150685</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2020.0</td>\n",
       "      <td>2020-02-23 00:00:00</td>\n",
       "      <td>50.0</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>1945.000000</td>\n",
       "      <td>5.386000</td>\n",
       "      <td>2311.000000</td>\n",
       "      <td>22.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2020.0</td>\n",
       "      <td>2020-02-23 00:00:00</td>\n",
       "      <td>50.0</td>\n",
       "      <td>147.000000</td>\n",
       "      <td>1966.000000</td>\n",
       "      <td>7.602000</td>\n",
       "      <td>36886.000000</td>\n",
       "      <td>42.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2020.0</td>\n",
       "      <td>2020-02-23 00:00:00</td>\n",
       "      <td>50.0</td>\n",
       "      <td>462.000000</td>\n",
       "      <td>1972.000000</td>\n",
       "      <td>8.637500</td>\n",
       "      <td>217128.500000</td>\n",
       "      <td>48.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2020.0</td>\n",
       "      <td>2020-09-26 00:00:00</td>\n",
       "      <td>50.0</td>\n",
       "      <td>462.000000</td>\n",
       "      <td>1978.000000</td>\n",
       "      <td>9.679500</td>\n",
       "      <td>742545.000000</td>\n",
       "      <td>54.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>2020.0</td>\n",
       "      <td>2020-10-17 00:00:00</td>\n",
       "      <td>50.0</td>\n",
       "      <td>462.000000</td>\n",
       "      <td>1998.000000</td>\n",
       "      <td>14.749000</td>\n",
       "      <td>838692.000000</td>\n",
       "      <td>75.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "      <td>149.722548</td>\n",
       "      <td>9.016160</td>\n",
       "      <td>1.555555</td>\n",
       "      <td>338522.316748</td>\n",
       "      <td>9.016160</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       year of event                    event dates  event distance/length  \\\n",
       "count          584.0                            584                  584.0   \n",
       "mean          2020.0  2020-04-23 20:35:20.547945216                   50.0   \n",
       "min           2020.0            2020-02-23 00:00:00                   50.0   \n",
       "25%           2020.0            2020-02-23 00:00:00                   50.0   \n",
       "50%           2020.0            2020-02-23 00:00:00                   50.0   \n",
       "75%           2020.0            2020-09-26 00:00:00                   50.0   \n",
       "max           2020.0            2020-10-17 00:00:00                   50.0   \n",
       "std              0.0                            NaN                    0.0   \n",
       "\n",
       "       event number of finishers  athlete year of birth  \\\n",
       "count                 584.000000             584.000000   \n",
       "mean                  369.551370            1971.849315   \n",
       "min                     5.000000            1945.000000   \n",
       "25%                   147.000000            1966.000000   \n",
       "50%                   462.000000            1972.000000   \n",
       "75%                   462.000000            1978.000000   \n",
       "max                   462.000000            1998.000000   \n",
       "std                   149.722548               9.016160   \n",
       "\n",
       "       athlete average speed     athlete id  athlete age  \n",
       "count             584.000000     584.000000   584.000000  \n",
       "mean                8.686914  369919.210616    48.150685  \n",
       "min                 5.386000    2311.000000    22.000000  \n",
       "25%                 7.602000   36886.000000    42.000000  \n",
       "50%                 8.637500  217128.500000    48.000000  \n",
       "75%                 9.679500  742545.000000    54.000000  \n",
       "max                14.749000  838692.000000    75.000000  \n",
       "std                 1.555555  338522.316748     9.016160  "
      ]
     },
     "execution_count": 171,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Let's gather some statistical information about the dataset\n",
    "df2.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 181,
   "id": "a914d5f1-5bde-4169-af26-4380fd2a5edb",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [

     ]
    },
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x2f6bc4908d0>"
      ]
     },
     "execution_count": 181,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Let's visualize the athlete average speed distribution\n",
    "sns.displot(df2[df2['event distance/length'] == 50]['athlete average speed'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 186,
   "id": "33f47b62-b57a-4b66-853d-feb0161c665a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='event distance/length', ylabel='athlete average speed'>"
      ]
     },
     "execution_count": 186,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjMAAAGwCAYAAABcnuQpAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAAA8iklEQVR4nO3deViVdeL+8fsBlQOyKLgACqKpmUuKqRVZallKZaVToZi5NNZM9c3E1BzTrClN6+syNeOSMy79xGwabVrEJSuXmHIhrSlzC0NUYtQEt4PK+fz+aDzfEEUOHjg88n5d17kuzrPenJPDPc/nWSxjjBEAAIBN+fk6AAAAwOWgzAAAAFujzAAAAFujzAAAAFujzAAAAFujzAAAAFujzAAAAFur5usA5c3lcunAgQMKCQmRZVm+jgMAAErBGKNjx44pOjpafn4lH3u54svMgQMHFBMT4+sYAACgDPbt26eGDRuWuMwVX2ZCQkIk/fJhhIaG+jgNAAAojfz8fMXExLj/jpfkii8z54aWQkNDKTMAANhMaU4R4QRgAABga5QZAABga5QZAABga1f8OTMAgCtbYWGhzpw54+sY8FD16tXl7+/vlW1RZgAAtmSMUU5Ojo4ePerrKCijWrVqKTIy8rLvA0eZAQDY0rkiU69ePQUFBXFjVBsxxujkyZPKzc2VJEVFRV3W9igzAADbKSwsdBeZiIgIX8dBGQQGBkqScnNzVa9evcsacuIEYACA7Zw7RyYoKMjHSXA5zn1/l3vOE2UGAGBbDC3Zm7e+P8oM4KH09HQlJSUpPT3d11EAAKLMAB5xOp2aOnWqfvrpJ02dOlVOp9PXkQCgyqPMAB5YtGiRDh8+LEk6fPiwUlNTfZwIgDcNGjRI9913X4nLxMXFafr06RWSpzKxLEvvvfeer2NcEGUGKKXs7GylpqbKGCPpl0sLU1NTlZ2d7eNkADy1d+9eWZalrVu3lvu+JkyYoHbt2pX7fqoyygxQCsYYzZgx46LTzxUcAMCFnT59uty2TZkBSiErK0ubNm1SYWFhkemFhYXatGmTsrKyfJQMwIWsWLFCnTt3Vq1atRQREaG7775be/bscc9v3LixJCk+Pl6WZalr165F1n/ttdcUFRWliIgIPfHEEyVeOpyXl6dHH31U9erVU2hoqG699VZt27ZNkjR//ny98MIL2rZtmyzLkmVZmj9//iXXu5j09HS1a9dODodDHTp00HvvvVfsCNN3332nO++8U8HBwapfv74GDBigQ4cOued37dpVTz31lEaNGqXw8HBFRkZqwoQJRfaza9cu3XLLLXI4HGrZsqVWr15dLMv+/fuVlJSk2rVrKyIiQvfee6/27t3rnn9uyG7SpEmKjo5W8+bNS/zdLgdlBiiF2NhYdezYsdhNnfz9/dWpUyfFxsb6KBmACzlx4oRSUlK0adMmrVmzRn5+furdu7dcLpckaePGjZKkjz/+WAcPHtTSpUvd63766afas2ePPv30Uy1YsEDz5893F5DzGWN01113KScnR8uXL9eWLVvUvn173XbbbTpy5IiSkpI0YsQItWrVSgcPHtTBgweVlJR0yfUu5NixY+rVq5fatGmjjIwM/fGPf9To0aOLLHPw4EF16dJF7dq10+bNm7VixQr99NNPevDBB4sst2DBAtWsWVNffvmlpkyZohdffNFdWFwul/r06SN/f3998cUXmjVrVrH9nDx5Ut26dVNwcLDWrVunDRs2KDg4WD179ixyBGbNmjXavn27Vq9erQ8//LAU31wZmStcXl6ekWTy8vJ8HQU2t2/fPnPrrbeaLl26uF+33Xabyc7O9nU0oMo5deqU+e6778ypU6dKtXxubq6RZL755htjjDGZmZlGkvnqq6+KLDdw4EDTqFEjc/bsWfe0Bx54wCQlJbnfN2rUyEybNs0YY8yaNWtMaGiocTqdRbZz1VVXmdmzZxtjjHn++edN27Zti8wvzXrnmzlzpomIiCjyO7/55ptFfo9x48aZO+64o8h6+/btM5LMjh07jDHGdOnSxXTu3LnIMh07djSjR482xhizcuVK4+/vb/bt2+een5aWZiSZZcuWGWOM+etf/2quvvpq43K53MsUFBSYwMBAs3LlSmPML59l/fr1TUFBwQV/H2NK/h49+fvNkRmglBo2bKjk5GT3TZ4sy1JycrIaNGjg42QAzrdnzx4lJyerSZMmCg0NdQ8rlWZIuFWrVkWOwkZFRbmfIXS+LVu26Pjx44qIiFBwcLD7lZmZWWRYyxvr7dixQ9dee60cDod7WqdOnYpt99NPPy2yzRYtWrg/k3OuvfbaIuv9+nfcvn27YmNj1bBhQ/f8G2+8sdh+du/erZCQEPd+wsPD5XQ6i+ynTZs2qlGjxkU/B2/h2UyAB/r376+0tDQdOnRIderUUXJysq8jAbiAXr16KSYmRm+++aaio6PlcrnUunXrUp2EWr169SLvLctyD0+dz+VyKSoqSp999lmxebVq1broPsqynjGm2B1zzXkXH7hcLvXq1UuTJ08utv6vH+ZY0u94/jbPzT9/P9ddd50WLVpUbNm6deu6f65Zs+YFfxdvo8wAHnA4HEpJSdGMGTM0bNiwIv8PCUDlcPjwYW3fvl2zZ8/WzTffLEnasGFDkWXOHS04/6R+T7Vv3145OTmqVq2a4uLiLrhMjRo1iu2nNOudr0WLFlq0aJEKCgoUEBAgSdq8eXOx7f7jH/9QXFycqlUr25/4li1bKisrSwcOHFB0dLQk6V//+lex/SxZssR98rKvMcwEeCghIUFLlixRQkKCr6MAuIBzV9fMmTNHu3fv1ieffKKUlJQiy9SrV0+BgYHuE2Tz8vLKtK/u3bvrxhtv1H333aeVK1dq7969Sk9P13PPPecuGnFxccrMzNTWrVt16NAhFRQUlGq98yUnJ8vlcunRRx/V9u3btXLlSr322muS/u/IyRNPPKEjR46oX79+2rhxo3744QetWrVKQ4YMKXVx6969u66++mo9/PDD2rZtm9avX6+xY8cWWaZ///6qU6eO7r33Xq1fv16ZmZlau3athg0b5pN7b1FmAABXFD8/P7399tvasmWLWrdureHDh+vVV18tsky1atX0pz/9SbNnz1Z0dLTuvffeMu3LsiwtX75ct9xyi4YMGaLmzZurb9++2rt3r+rXry9J+s1vfqOePXuqW7duqlu3rhYvXlyq9c4XGhqqDz74QFu3blW7du00duxYjR8/XpLcR4mjo6P1+eefq7CwUD169FDr1q01bNgwhYWFyc+vdH/y/fz8tGzZMhUUFKhTp0767W9/q5dffrnIMkFBQVq3bp1iY2PVp08fXXPNNRoyZIhOnTrlkyM1lrnQ4NgVJD8/X2FhYcrLy6sUh8IAAJfP6XQqMzNTjRs3rtLDvYsWLdLgwYOVl5enwMBAX8fxWEnfoyd/vzlnBgAAm1i4cKGaNGmiBg0aaNu2bRo9erQefPBBWxYZb6LMAABgEzk5ORo/frxycnIUFRWlBx54oNgQUFVEmQEAwCZGjRqlUaNG+TpGpcMJwAAAwNYoMwAAwNYoMwAAwNYoMwAAwNYoMwAAwNa4mgkAgDIoLCy84EMZy4NlWUWe5I2iKDMAAHiosLBQfe5/QHk/H6mQ/YXVDtfSd//uUaEZNGiQFixYoMcee0yzZs0qMu/xxx/XzJkzNXDgQM2fP9/LaSseZQYAAA8ZY5T38xEda/+wZJXzGRvGJWUsLNNRoJiYGL399tuaNm2a+y7BTqdTixcvVmxsrLeT+gznzAAAUFaWn+RXzq/LKEvt27dXbGysli5d6p62dOlSxcTEKD4+3hufQKVAmQEA4Ao2ePBgzZs3z/3+b3/7m4YMGeLDRN5HmQEA4Ao2YMAAbdiwQXv37tWPP/6ozz//XA899JCvY3mVT8vMunXr1KtXL0VHR8uyLL333nsXXfaxxx6TZVmaPn16heUDAMDu6tSpo7vuuksLFizQvHnzdNddd6lOnTq+juVVPi0zJ06cUNu2bfXGG2+UuNx7772nL7/8UtHR0RWUDLi49PR0JSUlKT093ddRAKBUhgwZovnz52vBggVX3BCT5OOrmRITE5WYmFjiMvv379eTTz6plStX6q677qqgZMCFOZ1OTZ06VYcOHdLUqVPVvn17ORwOX8cCgBL17NlTp0+fliT16NHDx2m8r1KfM+NyuTRgwACNHDlSrVq1KtU6BQUFys/PL/ICvGXRokU6fPiwJOnw4cNKTU31cSIAuDR/f39t375d27dvvyJvvlepy8zkyZNVrVo1PfXUU6VeZ9KkSQoLC3O/YmJiyjEhqpLs7Gylpqa67/VgjFFqaqqys7N9nAyAzxiX5Crnl3F5JWpoaKhCQ0O9sq3KptLeNG/Lli2aMWOGMjIyZFlWqdcbM2aMUlJS3O/z8/MpNLhsxhjNmDHjotOnTJni0X+nAOzNsiyF1Q6XMhZWyP7Caod7/L8xl7qzb0kX3dhNpS0z69evV25ubpE7FBYWFmrEiBGaPn269u7de8H1AgICFBAQUEEpUVVkZWVp06ZNxaYXFhZq06ZNysrKUqNGjXyQDIAv+Pv7a+m7f+fZTJVEpS0zAwYMUPfu3YtM69GjhwYMGKDBgwf7KBWqqtjYWHXs2FEZGRkqLCx0T/f399d11113Rd0WHEDpUC4qD5+WmePHj2v37t3u95mZmdq6davCw8MVGxuriIiIIstXr15dkZGRuvrqqys6Kqo4y7I0bNgwDRw48ILTGWICAN/x6QnAmzdvVnx8vPv5ECkpKYqPj9f48eN9GQu4oIYNGyo5OdldXCzLUnJysho0aODjZABQtfn0yEzXrl09Gm+82HkyQEXp37+/0tLSdOjQIdWpU0fJycm+jgQAVV6lvjQbqGwcDodSUlJUv359DR8+nBvmAUAlUGlPAAYqq4SEBCUkJPg6BgDgvzgyAwAAbI0yAwAAbI1hJgAAyqCwsJCb5lUSlBkAADxUWFiopAf66NCRvArZX53wMC35+1KPCs2gQYO0YMGCYtN37dqlpk2bejOez1FmAADwkDFGh47k6c0uh+VfzvfMLDTS0LUq01Ggnj17at68eUWm1a1b11vRKg3KDAAAZeRvSdXK++zTy3hodkBAgCIjI72XpZLiBGAAAGBrlBkAAK5QH374oYKDg92vBx54wNeRygXDTAAAXKG6deummTNnut/XrFnTh2nKD2UGAIArVM2aNa+4K5cuhGEmAABga5QZAABgawwzAQBQRoVGl3XpdKn3gRJRZgAA8JBlWaoTHqahaytmf3XCw2RZnt2db/78+eUTphKizAAA4CF/f38t+ftSns1USVBmAAAoA8pF5cEJwICH0tPTlZSUpPT0dF9HAQCIMgN4xOl0aurUqfrpp580depUOZ1OX0cCgCqPMgN4YNGiRTp8+LAk6fDhw0pNTfVxIqBqq6hzVlA+vPX9UWaAUsrOzlZqaqr7H58xRqmpqcrOzvZxMqDqqV69uiTp5MmTPk6Cy3Hu+zv3fZYVJwADpWCM0YwZMy46fcqUKR5fNgmg7Pz9/VWrVi3l5uZKkoKCgvg3aCPGGJ08eVK5ubmqVavWZZ9MTZkBSiErK0ubNm0qNr2wsFCbNm1SVlaWGjVq5INkQNUVGRkpSe5CA/upVauW+3u8HJQZoBRiY2PVsWNHZWRkqLCw0D3d399f1113nWJjY32YDqiaLMtSVFSU6tWrpzNnzvg6DjxUvXp1r13eTpkBSsGyLA0bNkwDBw684HQObwO+4+/vzz1fqjhOAAZKqWHDhkpOTnYXF8uylJycrAYNGvg4GQBUbZQZwAP9+/dXRESEJKlOnTpKTk72cSIAAGUG8IDD4VBKSorq16+v4cOHy+Fw+DoSAFR5nDMDeCghIUEJCQm+jgEA+C+OzAAAAFujzAAAAFujzAAAAFvjnBlUGGOM7Z8ybYxRQUGBJCkgIMDW95dxOBy2zg8A51BmUGGcTqcSExN9HQP/lZaWpsDAQF/HAIDLxjATAACwNY7MoMI4HA6lpaX5OsZlcTqd6t27tyRp2bJltr7PjJ2zA8CvUWZQYSzLuqKGNRwOxxX1+wCAXTHMBAAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbK1aaRbq06dPqTe4dOnSMocBAADwVKmOzISFhblfoaGhWrNmjTZv3uyev2XLFq1Zs0ZhYWHlFhQAAOBCSnVkZt68ee6fR48erQcffFCzZs2Sv7+/JKmwsFCPP/64QkNDyyclAADARXh8zszf/vY3PfPMM+4iI0n+/v5KSUnR3/72N4+2tW7dOvXq1UvR0dGyLEvvvfeee96ZM2c0evRotWnTRjVr1lR0dLQefvhhHThwwNPIAADgCuZxmTl79qy2b99ebPr27dvlcrk82taJEyfUtm1bvfHGG8XmnTx5UhkZGRo3bpwyMjK0dOlS7dy5U/fcc4+nkQEA5Sw9PV1JSUlKT0/3dRRUQaUaZvq1wYMHa8iQIdq9e7duuOEGSdIXX3yhV155RYMHD/ZoW4mJiUpMTLzgvLCwMK1evbrItNdff12dOnVSVlaWYmNjPY0OACgHTqdTU6dO1aFDhzR16lS1b99eDofD17FQhXhcZl577TVFRkZq2rRpOnjwoCQpKipKo0aN0ogRI7we8Nfy8vJkWZZq1ap10WUKCgpUUFDgfp+fn1+umQCgqlu0aJEOHz4sSTp8+LBSU1M1ZMgQH6dCVeLxMJOfn59GjRql/fv36+jRozp69Kj279+vUaNGFTmPxtucTqeeffZZJScnl3ii8aRJk4pcfRUTE1NumQCgqsvOzlZqaqqMMZIkY4xSU1OVnZ3t42SoSsp007yzZ8/q448/1uLFi2VZliTpwIEDOn78uFfDnXPmzBn17dtXLpdLf/nLX0pcdsyYMcrLy3O/9u3bVy6ZAKCqM8ZoxowZF51+ruAA5c3jYaYff/xRPXv2VFZWlgoKCnT77bcrJCREU6ZMkdPp1KxZs7wa8MyZM3rwwQeVmZmpTz755JKXfwcEBCggIMCrGQAAxWVlZWnTpk3FphcWFmrTpk3KyspSo0aNfJAMVY3HR2aGDRumDh066Oeff1ZgYKB7eu/evbVmzRqvhjtXZHbt2qWPP/5YERERXt0+AKDsYmNj1bFjx2KnGPj7+6tTp05cqIEK4/GRmQ0bNujzzz9XjRo1ikxv1KiR9u/f79G2jh8/rt27d7vfZ2ZmauvWrQoPD1d0dLTuv/9+ZWRk6MMPP1RhYaFycnIkSeHh4cX2DwCoWJZladiwYRo4cOAFp587DQEobx4fmXG5XCosLCw2PTs7WyEhIR5ta/PmzYqPj1d8fLwkKSUlRfHx8Ro/fryys7P1/vvvKzs7W+3atVNUVJT7xX0MAKByaNiwoZKTk93FxbIsJScnq0GDBj5OhqrE4yMzt99+u6ZPn645c+ZI+uU/3OPHj+v555/XnXfe6dG2unbtWuIJYpw8BgCVX//+/ZWWlqZDhw6pTp06Sk5O9nUkVDEeH5mZNm2a1q5dq5YtW8rpdCo5OVlxcXHav3+/Jk+eXB4ZAQCVmMPhUEpKiurXr6/hw4dzwzxUOI+PzERHR2vr1q1avHixMjIy5HK59Mgjj6h///5FTggGAFQdCQkJSkhI8HUMVFEelxlJCgwM1JAhQ7jDIwAA8Lky3TTvrbfeUufOnRUdHa0ff/xR0i/DT//85z+9Gg4AAOBSPC4zM2fOVEpKihITE/Xzzz+7r2yqXbu2pk+f7u18AAAAJfK4zLz++ut68803NXbsWFWr9n+jVB06dNA333zj1XAAAACX4nGZyczMdN8X5tcCAgJ04sQJr4QCAAAoLY/LTOPGjbV169Zi09PS0tSyZUtvZAIAACg1j69mGjlypJ544gk5nU4ZY7Rx40YtXrxYkyZN0ty5c8sjIwAAwEV5XGYGDx6ss2fPatSoUTp58qT7ttUzZsxQ3759yyMjAADARZXpPjNDhw7V0KFDdejQIblcLtWrV8/buQAAAEqlTGVGknJzc7Vjxw5ZliXLslS3bl1v5gIAACgVj08Azs/P14ABAxQdHa0uXbrolltuUXR0tB566CHl5eWVR0YAAICL8rjM/Pa3v9WXX36pjz76SEePHlVeXp4+/PBDbd68WUOHDi2PjAAAABfl8TDTRx99pJUrV6pz587uaT169NCbb76pnj17ejUcAFQFxhg5nU5fxygzY4wKCgok/XLPMcuyfJzo8jgcDtv/DlWNx2UmIiJCYWFhxaaHhYWpdu3aXgkFAFWJ0+lUYmKir2Pgv9LS0hQYGOjrGPCAx8NMzz33nFJSUnTw4EH3tJycHI0cOVLjxo3zajgAAIBL8fjIzMyZM7V79241atRIsbGxkqSsrCwFBAToP//5j2bPnu1eNiMjw3tJAeAK5XA4lJaW5usYZeZ0OtW7d29J0rJly+RwOHyc6PLYPX9V5HGZue+++8ohBgBUXZZlXTHDGg6H44r5XWAfHpeZ559/vjxyAAAAlInH58zs27dP2dnZ7vcbN27U008/rTlz5ng1GAAAQGl4XGaSk5P16aefSvrlxN/u3btr48aN+sMf/qAXX3zR6wEBAABK4nGZ+fe//61OnTpJkt555x21adNG6enpSk1N1fz5872dDwAAoEQel5kzZ84oICBAkvTxxx/rnnvukSS1aNGiyOXaAAAAFcHjMtOqVSvNmjVL69ev1+rVq913/T1w4IAiIiK8HhAAAKAkHpeZyZMna/bs2eratav69euntm3bSpLef/999/ATAABARfH40uyuXbvq0KFDys/PL/L4gkcffVRBQUFeDQcAAHApHpcZSfL39y/2HKa4uDhv5AEAAPCIx8NMAAAAlQllBgAA2BplBgAA2NpllRmn0+mtHAAAAGXicZlxuVz64x//qAYNGig4OFg//PCDJGncuHH661//6vWAAAAAJfG4zLz00kuaP3++pkyZoho1arint2nTRnPnzvVqOAAAgEvxuMwsXLhQc+bMUf/+/eXv7++efu211+r777/3ajgAAIBL8bjM7N+/X02bNi023eVy6cyZM14JBQAAUFplejbT+vXri03/+9//rvj4eK+EAgAAKC2P7wD8/PPPa8CAAdq/f79cLpeWLl2qHTt2aOHChfrwww/LIyMAAMBFeXxkplevXlqyZImWL18uy7I0fvx4bd++XR988IFuv/328sgIAABwUWV6NlOPHj3Uo0cPb2cBAADwGHcABgAAtubxkZnatWvLsqxi0y3LksPhUNOmTTVo0CANHjzYKwEBAABK4nGZGT9+vF5++WUlJiaqU6dOMsZo06ZNWrFihZ544gllZmbq97//vc6ePauhQ4eWR2YAAAA3j8vMhg0b9NJLL+l3v/tdkemzZ8/WqlWr9I9//EPXXnut/vSnP1FmAABAufP4nJmVK1eqe/fuxabfdtttWrlypSTpzjvvdD+zCQAAoDx5XGbCw8P1wQcfFJv+wQcfKDw8XJJ04sQJhYSEXH46AACAS/B4mGncuHH6/e9/r08//VSdOnWSZVnauHGjli9frlmzZkmSVq9erS5dung9LAAAwPk8LjNDhw5Vy5Yt9cYbb2jp0qUyxqhFixZau3atEhISJEkjRozwelAAAIALKdNN82666SbddNNN3s4CAADgsTKVmXNOnTpV7EnZoaGhlxUIAADAEx6fAHzy5Ek9+eSTqlevnoKDg1W7du0iLwAAgIrkcZkZOXKkPvnkE/3lL39RQECA5s6dqxdeeEHR0dFauHBheWQEAAC4KI+HmT744AMtXLhQXbt21ZAhQ3TzzTeradOmatSokRYtWqT+/fuXR04AAIAL8vjIzJEjR9S4cWNJv5wfc+TIEUlS586dtW7dOu+mAwAAuASPy0yTJk20d+9eSVLLli31zjvvSPrliE2tWrW8mQ0AAOCSPC4zgwcP1rZt2yRJY8aMcZ87M3z4cI0cOdLrAQEAAEri8Tkzw4cPd//crVs3ff/999q8ebOuuuoqtW3b1qvhAAAALsWjIzNnzpxRt27dtHPnTve02NhY9enThyIDAAB8wqMyU716df373/+WZVnllQcAAMAjHp8z8/DDD+uvf/1reWQBAADwmMfnzJw+fVpz587V6tWr1aFDB9WsWbPI/KlTp3otHAAAwKV4fGTm3//+t9q3b6/Q0FDt3LlTX331lfu1detWj7a1bt069erVS9HR0bIsS++9916R+cYYTZgwQdHR0QoMDFTXrl317bffehoZAABcwTw+MvPpp596becnTpxQ27ZtNXjwYP3mN78pNn/KlCmaOnWq5s+fr+bNm+ull17S7bffrh07digkJMRrOQAAgH2V+anZu3fv1p49e3TLLbcoMDBQxhiPTwxOTExUYmLiBecZYzR9+nSNHTtWffr0kSQtWLBA9evXV2pqqh577LELrldQUKCCggL3+/z8fI8yAQAAe/F4mOnw4cO67bbb1Lx5c9155506ePCgJOm3v/2tRowY4bVgmZmZysnJ0R133OGeFhAQoC5duig9Pf2i602aNElhYWHuV0xMjNcyAQCAysfjMjN8+HBVr15dWVlZCgoKck9PSkrSihUrvBYsJydHklS/fv0i0+vXr++edyFjxoxRXl6e+7Vv3z6vZQIAAJWPx8NMq1at0sqVK9WwYcMi05s1a6Yff/zRa8HOOX/o6lLDWQEBAQoICPB6DgAAUDl5fGTmxIkTRY7InHPo0CGvlojIyEhJKnYUJjc3t9jRGgAAUHV5XGZuueUWLVy40P3esiy5XC69+uqr6tatm9eCNW7cWJGRkVq9erV72unTp7V27VolJCR4bT8AAMDePB5mevXVV9W1a1dt3rxZp0+f1qhRo/Ttt9/qyJEj+vzzzz3a1vHjx7V79273+8zMTG3dulXh4eGKjY3V008/rYkTJ6pZs2Zq1qyZJk6cqKCgICUnJ3saGwAAXKE8LjMtW7bU119/rZkzZ8rf318nTpxQnz599MQTTygqKsqjbW3evLnI0ZyUlBRJ0sCBAzV//nyNGjVKp06d0uOPP66ff/5Z119/vVatWlVl7zFjjJHT6fR1jCrt158/34XvORwOnhUHQJYxxvg6RHnKz89XWFiY8vLyFBoa6us4l+XUqVMXvS8PUBWlpaUpMDDQ1zGqvF//bxPfCbzFk7/fHp8z07hxY40bN047duwoc0AAAABv8XiY6X/+53+0ePFivfzyy4qPj9eAAQOUlJTk8RATLs/xdv1k/Mp8A2eUlTGS6+wvP/tVkxjiqHCW66yCty72dQwAlYjHfw1TUlKUkpKinTt3atGiRZo5c6ZGjhypbt266aGHHtLDDz9cHjlxHuNXTfKv7usYVVQNXweo0q7ocXEAZeLxMNM5zZs31wsvvKAdO3Zo/fr1+s9//qPBgwd7MxsAAMAlXdY4xcaNG5WamqolS5YoLy9P999/v7dyAQAAlIrHZebc8FJqaqr27t2rbt266ZVXXlGfPn2q7CXTAADAdzwuMy1atFCHDh30xBNPqG/fvu7HDgAAAPiCx2Xm+++/V/PmzcsjCwAAgMc8PgGYIgMAACoTj4/MFBYWatq0aXrnnXeUlZWl06dPF5l/5MgRr4UDAAC4FI+PzLzwwguaOnWqHnzwQeXl5SklJUV9+vSRn5+fJkyYUA4RAQAALs7jMrNo0SK9+eabeuaZZ1StWjX169dPc+fO1fjx4/XFF1+UR0YAAICL8rjM5OTkqE2bNpKk4OBg5eXlSZLuvvtuffTRR95NBwAAcAkel5mGDRvq4MGDkqSmTZtq1apVkqRNmzYpICDAu+kAAAAuweMy07t3b61Zs0aSNGzYMI0bN07NmjXTww8/rCFDhng9IAAAQEk8vprplVdecf98//33KyYmRp9//rmaNm2qe+65x6vhAAAALuWyns0kSddff72uv/56b2QBAADwWJmfmg0AAFAZUGYAAICtUWYAAICtUWYAAICtlekE4KNHj+rdd9/Vnj17NHLkSIWHhysjI0P169dXgwYNvJ0RAC7KGCOn0+nrGFXarz9/vgvfczgcsizL1zEqlMdl5uuvv1b37t0VFhamvXv3aujQoQoPD9eyZcv0448/auHCheWREwAuyOl0KjEx0dcx8F+9e/f2dYQqLy0tTYGBgb6OUaE8HmZKSUnRoEGDtGvXLjkcDvf0xMRErVu3zqvhAAAALsXjIzObNm3S7Nmzi01v0KCBcnJyvBIKAMrijc5HFOBvfB2jyjFGOu365ecaflIVG+GoFAoKLT25IdzXMXzG4zLjcDiUn59fbPqOHTtUt25dr4QCgLII8DcK8Pd1iqrJcelFUK6qdon3eJjp3nvv1YsvvqgzZ85IkizLUlZWlp599ln95je/8XpAAACAknhcZl577TX95z//Ub169XTq1Cl16dJFTZs2VUhIiF5++eXyyAgAAHBRHg8zhYaGasOGDfrkk0+UkZEhl8ul9u3bq3v37uWRDwAAoEQel5mFCxcqKSlJt956q2699Vb39NOnT+vtt9/Www8/7NWAAAAAJfF4mGnw4MHKy8srNv3YsWMaPHiwV0IBAACUlsdlxhhzwTsLZmdnKywszCuhAAAASqvUw0zx8fGyLEuWZem2225TtWr/t2phYaEyMzPVs2fPcgkJAABwMaUuM/fdd58kaevWrerRo4eCg4Pd82rUqKG4uDguzQYAABWu1GXm+eeflyTFxcUpKSmpyKMMAAAAfMXjc2YGDhwop9OpuXPnasyYMTpy5IgkKSMjQ/v37/d6QAAAgJLw1Gy7Kjzj6wSAb/DfPoDzeFxmhg8frkGDBmnKlCkKCQlxT09MTFRycrJXw+HiQra97esIAABUCh6Xmc2bN2vOnDnFpvPUbAAA4As8NdumjrXtK/lX93UMoOIVnuHIJIAiPC4z556a/c4770jiqdk+41+dMgMAgHhqNgAAsDmemg0AAGzN4zJzzvlPzQYAAPCFUpWZP/3pT6Xe4FNPPVXmMAAAAJ4qVZmZNm1aqTZmWRZlBgAAVKhSlZnMzMzyzgEAAFAmZT5nBgAqm4JCXycAfKOq/7fvcZkpLCzU/PnztWbNGuXm5srlchWZ/8knn3gtHAB44skNEb6OAMAHPC4zw4YN0/z583XXXXepdevWsiyrPHIBAACUisdl5u2339Y777yjO++8szzyAECZvdH5sAL8fZ0CqHgFhVX7yKTHZaZGjRpq2rRpeWQBgMsS4C/KDFAFefw4gxEjRmjGjBkyxpRHHgAAAI+U6shMnz59irz/5JNPlJaWplatWql69aIPO1y6dKn30gEAAFxCqcpMWFhYkfe9e/culzAAAACeKlWZmTdvXnnnAAAAKBOPz5m59dZbdfTo0WLT8/PzefAkAACocB6Xmc8++0ynT58uNt3pdGr9+vVeCQUAAFBapb40++uvv3b//N133yknJ8f9vrCwUCtWrFCDBg28mw4AAOASSl1m2rVrJ8uyZFnWBYeTAgMD9frrr3s1HAAAwKWUusxkZmbKGKMmTZpo48aNqlu3rntejRo1VK9ePfn7e/duVWfPntWECRO0aNEi5eTkKCoqSoMGDdJzzz0nPz+PR8gAAMAVqNRlplGjRpJU7MGS5Wny5MmaNWuWFixYoFatWmnz5s0aPHiwwsLCNGzYsArLAQAAKi+PH2dwznfffaesrKxiJwPfc889lx3qnH/961+69957ddddd0mS4uLitHjxYm3evNlr+wAAAPbmcZn54Ycf1Lt3b33zzTeyLMv9WINzT88uLCz0WrjOnTtr1qxZ2rlzp5o3b65t27Zpw4YNmj59+kXXKSgoUEFBgft9fn6+1/IAAIDKx+MTT4YNG6bGjRvrp59+UlBQkL799lutW7dOHTp00GeffebVcKNHj1a/fv3UokULVa9eXfHx8Xr66afVr1+/i64zadIkhYWFuV8xMTFezQQAACoXj8vMv/71L7344ouqW7eu/Pz85Ofnp86dO2vSpEl66qmnvBpuyZIl+n//7/8pNTVVGRkZWrBggV577TUtWLDgouuMGTNGeXl57te+ffu8mgkAAFQuHg8zFRYWKjg4WJJUp04dHThwQFdffbUaNWqkHTt2eDXcyJEj9eyzz6pv376SpDZt2ujHH3/UpEmTNHDgwAuuExAQoICAAK/mAAAAlZfHZaZ169b6+uuv1aRJE11//fWaMmWKatSooTlz5qhJkyZeDXfy5Mlil2D7+/tX6BVVAACgcvO4zDz33HM6ceKEJOmll17S3XffrZtvvlkRERFasmSJV8P16tVLL7/8smJjY9WqVSt99dVXmjp1qoYMGeLV/QAAAPvyuMz06NHD/XOTJk303Xff6ciRI6pdu7b7iiZvef311zVu3Dg9/vjjys3NVXR0tB577DGNHz/eq/sBAAD2Veb7zPxaeHi4NzZTTEhIiKZPn17ipdgAAKBq45kAAADA1igzAADA1igzAADA1igzAADA1igzAADA1rxyNRMqnuU6K+PrEFWRMZLr7C8/+1WTvHw7Alyade7zv4CCQkviX0aFM0Y6/d97mdbw45+FL/zy337VRZmxqeCti30dAah0ntxQPreJAFC5McwEAABszTLGXNHHZPPz8xUWFqa8vDyFhob6Os5lMcbI6XT6OkaV5nQ61bt3b0nSsmXL5HA4fJyoajv3+fPvwrf4d1G5OBwOr9+R3xc8+fvNMJONWJalwMBAX8fAfzkcDr6PSoLvofLg3wV8gWEmAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5QZAABga5W+zOzfv18PPfSQIiIiFBQUpHbt2mnLli2+jgUAACqJar4OUJKff/5ZN910k7p166a0tDTVq1dPe/bsUa1atXwdDQAAVBKVusxMnjxZMTExmjdvnntaXFyc7wIBAIBKp1IPM73//vvq0KGDHnjgAdWrV0/x8fF68803S1ynoKBA+fn5RV4AAODKVanLzA8//KCZM2eqWbNmWrlypX73u9/pqaee0sKFCy+6zqRJkxQWFuZ+xcTEVGBiAABQ0Sp1mXG5XGrfvr0mTpyo+Ph4PfbYYxo6dKhmzpx50XXGjBmjvLw892vfvn0VmBgAAFS0Sl1moqKi1LJlyyLTrrnmGmVlZV10nYCAAIWGhhZ5AQCAK1elLjM33XSTduzYUWTazp071ahRIx8lAgAAlU2lLjPDhw/XF198oYkTJ2r37t1KTU3VnDlz9MQTT/g6GgAAqCQq9aXZHTt21LJlyzRmzBi9+OKLaty4saZPn67+/fv7OhoAeI0xRk6n09cxyuzX2e38e5zjcDhkWZavY8ADlbrMSNLdd9+tu+++29cxAKDcOJ1OJSYm+jqGV/Tu3dvXES5bWlqaAgMDfR0DHqjUw0wAAACXUumPzADAlc7hcCgtLc3XMcrMGKOCggJJv1xRavchGofD4esI8BBlBgB8zLIs2w9rBAUF+ToCqjCGmQAAgK1RZgAAgK1RZgAAgK1RZgAAgK1RZgAAgK1RZgAAgK1RZgAAgK1RZgAAgK1RZgAAgK1RZgAAgK3xOANUGGOMnE6nr2Ncll/nt/vv4nA4bP8MHQCQKDOoQE6nU4mJib6O4TW9e/f2dYTLkpaWZvvnAQGAxDATAACwOY7MoMI4HA6lpaX5OsZlMcaooKBAkhQQEGDrYRqHw+HrCADgFZQZVBjLsq6IYY2goCBfRwAA/ArDTAAAwNYoMwAAwNYoMwAAwNYoMwAAwNYoMwAAwNYoMwAAwNYoMwAAwNYoMwAAwNYoMwAAwNYoMwAAwNYoMwAAwNYoMwAAwNYoMwAAwNau+KdmG2MkSfn5+T5OAgAASuvc3+1zf8dLcsWXmWPHjkmSYmJifJwEAAB46tixYwoLCytxGcuUpvLYmMvl0oEDBxQSEiLLsnwdB4AX5efnKyYmRvv27VNoaKiv4wDwImOMjh07pujoaPn5lXxWzBVfZgBcufLz8xUWFqa8vDzKDFCFcQIwAACwNcoMAACwNcoMANsKCAjQ888/r4CAAF9HAeBDnDMDAABsjSMzAADA1igzAADA1igzAADA1igzAADA1igzACq1CRMmyLKsIq/IyEj3fGOMJkyYoOjoaAUGBqpr16769ttvfZgYQEWjzACo9Fq1aqWDBw+6X99884173pQpUzR16lS98cYb2rRpkyIjI3X77be7n8sG4MpHmQFQ6VWrVk2RkZHuV926dSX9clRm+vTpGjt2rPr06aPWrVtrwYIFOnnypFJTU32cGkBFocwAqPR27dql6OhoNW7cWH379tUPP/wgScrMzFROTo7uuOMO97IBAQHq0qWL0tPTfRUXQAWjzACo1K6//notXLhQK1eu1JtvvqmcnBwlJCTo8OHDysnJkSTVr1+/yDr169d3zwNw5avm6wAAUJLExET3z23atNGNN96oq666SgsWLNANN9wgSbIsq8g6xphi0wBcuTgyA8BWatasqTZt2mjXrl3uq5rOPwqTm5tb7GgNgCsXZQaArRQUFGj79u2KiopS48aNFRkZqdWrV7vnnz59WmvXrlVCQoIPUwKoSAwzAajUnnnmGfXq1UuxsbHKzc3VSy+9pPz8fA0cOFCWZenpp5/WxIkT1axZMzVr1kwTJ05UUFCQkpOTfR0dQAWhzACo1LKzs9WvXz8dOnRIdevW1Q033KAvvvhCjRo1kiSNGjVKp06d0uOPP66ff/5Z119/vVatWqWQkBAfJwdQUSxjjPF1CAAAgLLinBkAAGBrlBkAAGBrlBkAAGBrlBkAAGBrlBkAAGBrlBkAAGBrlBkAAGBrlBkAAGBrlBkA5SIuLk7Tp093v7csS++9957P8pSX+fPnq1atWr6O4Xb+5w5UBZQZABfVtWtXPf30017Z1sGDB5WYmFiqZe1QfBo3bqwVK1b4bP+VrUQBvkSZAVAhIiMjFRAQ4OsYXvH111/r8OHD6tatm6+jABBlBqiUjDGaMmWKmjRposDAQLVt21bvvvuuJMnlcqlhw4aaNWtWkXUyMjJkWZZ++OEHSVJeXp4effRR1atXT6Ghobr11lu1bds29/ITJkxQu3bt9NZbbykuLk5hYWHq27evjh07JkkaNGiQ1q5dqxkzZsiyLFmWpb17914wb25urnr16qXAwEA1btxYixYtKrbMr4+2nD59Wk8++aSioqLkcDgUFxenSZMmSfplmESSevfuLcuy3O/37Nmje++9V/Xr11dwcLA6duyojz/+uMg+4uLiNHHiRA0ZMkQhISGKjY3VnDlziiyTnZ2tvn37Kjw8XDVr1lSHDh305Zdfuud/8MEHuu666+RwONSkSRO98MILOnv2bJFt/POf/1SPHj0uWs4utQ3LsjR37lz17t1bQUFBatasmd5///0i23j//ffVrFkzBQYGqlu3blqwYIEsy9LRo0f12WefafDgwcrLy3N/NxMmTHCve/LkyRI/A+CKYwBUOn/4wx9MixYtzIoVK8yePXvMvHnzTEBAgPnss8+MMcaMGDHCdO7cucg6I0aMMDfeeKMxxhiXy2Vuuukm06tXL7Np0yazc+dOM2LECBMREWEOHz5sjDHm+eefN8HBwaZPnz7mm2++MevWrTORkZHmD3/4gzHGmKNHj5obb7zRDB061Bw8eNAcPHjQnD179oJ5ExMTTevWrU16errZvHmzSUhIMIGBgWbatGnuZSSZZcuWGWOMefXVV01MTIxZt26d2bt3r1m/fr1JTU01xhiTm5trJJl58+aZgwcPmtzcXGOMMVu3bjWzZs0yX3/9tdm5c6cZO3ascTgc5scff3Tvo1GjRiY8PNz8+c9/Nrt27TKTJk0yfn5+Zvv27cYYY44dO2aaNGlibr75ZrN+/Xqza9cus2TJEpOenm6MMWbFihUmNDTUzJ8/3+zZs8esWrXKxMXFmQkTJhT5fTt06GDeeustY4wx8+bNM2FhYe55pdmGJNOwYUOTmppqdu3aZZ566ikTHBzs/m4yMzNN9erVzTPPPGO+//57s3jxYtOgQQMjyfz888+moKDATJ8+3YSGhrq/m2PHjpXqMwCuRJQZoJI5fvy4cTgc7j+w5zzyyCOmX79+xhhjMjIyjGVZZu/evcYYYwoLC02DBg3Mn//8Z2OMMWvWrDGhoaHG6XQW2cZVV11lZs+ebYz5pcwEBQWZ/Px89/yRI0ea66+/3v2+S5cuZtiwYSXm3bFjh5FkvvjiC/e07du3G0kXLTP/8z//Y2699VbjcrkuuM1fL1uSli1bmtdff939vlGjRuahhx5yv3e5XKZevXpm5syZxhhjZs+ebUJCQtyl4Xw333yzmThxYpFpb731lomKinK/z87ONtWrV3dv4/wyU5ptSDLPPfec+/3x48eNZVkmLS3NGGPM6NGjTevWrYtsY+zYse4yc6H9lvYzAK5E1Xx1RAjAhX333XdyOp26/fbbi0w/ffq04uPjJUnx8fFq0aKFFi9erGeffVZr165Vbm6uHnzwQUnSli1bdPz4cUVERBTZxqlTp7Rnzx73+7i4OIWEhLjfR0VFKTc316O827dvV7Vq1dShQwf3tBYtWpR4cuqgQYN0++236+qrr1bPnj11991364477ihxPydOnNALL7ygDz/8UAcOHNDZs2d16tQpZWVlFVnu2muvdf9sWZYiIyPdv9PWrVsVHx+v8PDwC+5jy5Yt2rRpk15++WX3tMLCQjmdTp08eVJBQUF6//33ddNNN13WNs7PWbNmTYWEhLhz7tixQx07diyy3U6dOpX4+ZT2MwCuRJQZoJJxuVySpI8++kgNGjQoMu/X52j0799fqampevbZZ5WamqoePXqoTp067m1ERUXps88+K7b9X5eM6tWrF5lnWZZ7/6VljHGvW1rt27dXZmam0tLS9PHHH+vBBx9U9+7d3ecFXcjIkSO1cuVKvfbaa2ratKkCAwN1//336/Tp00WWK+l3CgwMLDGXy+XSCy+8oD59+hSb53A4JP1yLsu99957Wdu4VE5jTLHP89znXBre+F4BO6HMAJVMy5YtFRAQoKysLHXp0uWiyyUnJ+u5557Tli1b9O6772rmzJnuee3bt1dOTo6qVavmPoG2LGrUqKHCwsISl7nmmmt09uxZbd682X30YMeOHTp69GiJ64WGhiopKUlJSUm6//771bNnTx05ckTh4eGqXr16sf2uX79egwYNUu/evSVJx48fv+gJyRdz7bXXau7cue79nK99+/basWOHmjZtesH1jx8/rk8//VR//vOfL7qPS22jNFq0aKHly5cXmbZ58+Yi70vz3QBVBWUGqGRCQkL0zDPPaPjw4XK5XOrcubPy8/OVnp6u4OBgDRw4UNIv9zlJSEjQI488orNnzxY5WtC9e3fdeOONuu+++zR58mRdffXVOnDggJYvX6777ruvyJBQSeLi4vTll19q7969Cg4OVnh4uPz8il4EeW6oaOjQoZozZ46qVaump59+usSjINOmTVNUVJTatWsnPz8//f3vf1dkZKT7qFFcXJzWrFmjm266SQEBAapdu7aaNm2qpUuXqlevXrIsS+PGjfP4aEO/fv00ceJE3XfffZo0aZKioqL01VdfKTo6WjfeeKPGjx+vu+++WzExMXrggQfk5+enr7/+Wt98841eeuklrVixQs2aNVOTJk0uuo9LbaM0HnvsMU2dOlWjR4/WI488oq1bt2r+/PmS/u8IWFxcnI4fP641a9aobdu2CgoKcg9hAVUNl2YDldAf//hHjR8/XpMmTdI111yjHj166IMPPlDjxo2LLNe/f39t27ZNffr0KVIeLMvS8uXLdcstt2jIkCFq3ry5+vbtq71796p+/fqlzvHMM8/I399fLVu2VN26dYudn3LOvHnzFBMToy5duqhPnz7uS8IvJjg4WJMnT1aHDh3UsWNH7d27V8uXL3cXpf/93//V6tWrFRMT4z5PaNq0aapdu7YSEhLUq1cv9ejRQ+3bty/17yL9cjRj1apVqlevnu688061adNGr7zyivz9/SVJPXr00IcffqjVq1erY8eOuuGGGzR16lQ1atRI0i+XZJc0xFSabZRG48aN9e6772rp0qW69tprNXPmTI0dO1bS/w01JiQk6He/+52SkpJUt25dTZkyxaPPAriSWMaTgVgAqKIKCwtVr149paWleXQyrre8/PLLmjVrlvbt21fh+wYqO4aZAKAUDh8+rOHDhxe7yqi8/OUvf1HHjh0VERGhzz//XK+++qqefPLJCtk3YDccmQGASmj48OFasmSJjhw5otjYWA0YMEBjxoxRtWr8f1DgfJQZAABga5wADAAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbI0yAwAAbO3/A4//juCLxO62AAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# What about differences by athlete gender?\n",
    "sns.boxplot(data = df2, x = 'event distance/length', y = 'athlete average speed', hue = 'athlete gender')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 187,
   "id": "da7a7c2d-1bae-416e-8036-873b86c59c61",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x2f6fb6baf50>"
      ]
     },
     "execution_count": 187,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 613.986x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#What about differences by athlete gender and age?\n",
    "sns.lmplot(data = df2, x = 'athlete age', y = 'athlete average speed', hue = 'athlete gender')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "48bacdc8-866d-490d-be64-7570a1253be2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Qestions about dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 188,
   "id": "6335d247-1bee-4239-9d9c-f7863a1cfbb5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "event distance/length  athlete gender\n",
       "50                     F                 8.421859\n",
       "                       M                 8.766608\n",
       "Name: athlete average speed, dtype: float64"
      ]
     },
     "execution_count": 188,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 1. Is there any difference in speed between males and females?\n",
    "df2.groupby(['event distance/length','athlete gender'])['athlete average speed'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 216,
   "id": "703dd812-835e-4107-b42d-95dbb96101ec",
   "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>mean</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>athlete age</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>10.710000</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>9.685286</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>9.541500</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>9.471929</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>9.354000</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  mean  count\n",
       "athlete age                  \n",
       "25           10.710000      1\n",
       "33            9.685286      7\n",
       "27            9.541500      2\n",
       "37            9.471929     14\n",
       "30            9.354000      3"
      ]
     },
     "execution_count": 216,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 2. What age groups are the best?\n",
    "average_speed_by_age = df2.groupby('athlete age')['athlete average speed'].agg(['mean', 'count']).sort_values('mean', ascending = False)\n",
    "average_speed_by_age.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 210,
   "id": "18e1eaa2-ab1b-4347-842e-52b25d11f900",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      
     ]
    },
    {
     "data": {
      "text/plain": [
       "[Text(0, 0.5, 'average speed')]"
      ]
     },
     "execution_count": 210,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.lineplot(data = average_speed_by_age,  x = 'athlete age', y = 'mean',).set(ylabel = 'average speed')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 218,
   "id": "dcd2152f-f92f-4cc1-895e-a555381a81eb",
   "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>mean</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>athlete age</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>74</th>\n",
       "      <td>5.839</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>71</th>\n",
       "      <td>6.086</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>70</th>\n",
       "      <td>6.912</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75</th>\n",
       "      <td>6.997</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>7.171</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              mean  count\n",
       "athlete age              \n",
       "74           5.839      1\n",
       "71           6.086      1\n",
       "70           6.912      3\n",
       "75           6.997      1\n",
       "26           7.171      1"
      ]
     },
     "execution_count": 218,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 3. What age groups are the worst?\n",
    "average_speed_by_age_reverse = df2.groupby('athlete age')['athlete average speed'].agg(['mean', 'count']).sort_values('mean', ascending = True)\n",
    "average_speed_by_age_reverse.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 259,
   "id": "be2bcf91-6aea-4474-8cf4-d31fe9d5c8fb",
   "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>mean</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>event name</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Ultra Beach 50 Km (ITA)</th>\n",
       "      <td>9.543833</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Terre di Siena Ultramarathon (ITA)</th>\n",
       "      <td>9.111012</td>\n",
       "      <td>420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bettona Crossing (ITA)</th>\n",
       "      <td>7.471150</td>\n",
       "      <td>147</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Pantelleria Trail (ITA)</th>\n",
       "      <td>6.749600</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                        mean  count\n",
       "event name                                         \n",
       "Ultra Beach 50 Km (ITA)             9.543833     12\n",
       "Terre di Siena Ultramarathon (ITA)  9.111012    420\n",
       "Bettona Crossing (ITA)              7.471150    147\n",
       "Pantelleria Trail (ITA)             6.749600      5"
      ]
     },
     "execution_count": 259,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 4. What italian event has the highest average athlete speed?\n",
    "df2.groupby('event name')['athlete average speed'].agg(['mean', 'count']).sort_values('mean', ascending=False)"
   ]
  }
 ],
 "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}