{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "worldwide-blood",
   "metadata": {},
   "source": [
    "# A Data Science Investigation About Fatal Car Crashes in America "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "understanding-numbers",
   "metadata": {},
   "source": [
    "It's a collection of data on the reasons fatal car crashes occur in every state of America, and it will be used to determine which region of America is the deadliest. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "greater-circular",
   "metadata": {},
   "source": [
    "## Overarching Question: What is the deadliest region in America to drive in?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "appreciated-testimony",
   "metadata": {},
   "source": [
    "I am interested in this because I live on the Northeast Coast and we have a lot of car \n",
    "accidents. People drive very fast here. The roads are not always paved properly and maintained. I want to know if it's just bad luck when people get into accidents or if it's their own fault. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "permanent-pollution",
   "metadata": {},
   "source": [
    "# Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "technical-evans",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Include any import statements you will need\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "overhead-sigma",
   "metadata": {},
   "outputs": [],
   "source": [
    "### 💻 FILL IN YOUR DATASET FILE NAME BELOW 💻 ###\n",
    "\n",
    "file_name = \"B_D2 - bad-drivers.csv\"\n",
    "dataset_path = \"data/\" + file_name\n",
    "\n",
    "df = pd.read_csv(dataset_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "heated-blade",
   "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>number_drivers_fatal_billion_miles</th>\n",
       "      <th>percentage_drivers_fatal_speeding</th>\n",
       "      <th>percentage_drivers_fatal_alcohol_impaired</th>\n",
       "      <th>percentage_drivers_fatal_not_distracted</th>\n",
       "      <th>percentage_drivers_fatal_no_previous_accidents</th>\n",
       "      <th>car_insurance_premiums</th>\n",
       "      <th>region</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Alabama</td>\n",
       "      <td>18.8</td>\n",
       "      <td>39</td>\n",
       "      <td>30</td>\n",
       "      <td>96</td>\n",
       "      <td>80</td>\n",
       "      <td>784.55</td>\n",
       "      <td>Southeast</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Alaska</td>\n",
       "      <td>18.1</td>\n",
       "      <td>41</td>\n",
       "      <td>25</td>\n",
       "      <td>90</td>\n",
       "      <td>94</td>\n",
       "      <td>1053.48</td>\n",
       "      <td>West</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Arizona</td>\n",
       "      <td>18.6</td>\n",
       "      <td>35</td>\n",
       "      <td>28</td>\n",
       "      <td>84</td>\n",
       "      <td>96</td>\n",
       "      <td>899.47</td>\n",
       "      <td>Southeast</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Arkansas</td>\n",
       "      <td>22.4</td>\n",
       "      <td>18</td>\n",
       "      <td>26</td>\n",
       "      <td>94</td>\n",
       "      <td>95</td>\n",
       "      <td>827.34</td>\n",
       "      <td>Southeast</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>California</td>\n",
       "      <td>12.0</td>\n",
       "      <td>35</td>\n",
       "      <td>28</td>\n",
       "      <td>91</td>\n",
       "      <td>89</td>\n",
       "      <td>878.41</td>\n",
       "      <td>West</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        State  number_drivers_fatal_billion_miles  \\\n",
       "0     Alabama                                18.8   \n",
       "1      Alaska                                18.1   \n",
       "2     Arizona                                18.6   \n",
       "3    Arkansas                                22.4   \n",
       "4  California                                12.0   \n",
       "\n",
       "   percentage_drivers_fatal_speeding  \\\n",
       "0                                 39   \n",
       "1                                 41   \n",
       "2                                 35   \n",
       "3                                 18   \n",
       "4                                 35   \n",
       "\n",
       "   percentage_drivers_fatal_alcohol_impaired  \\\n",
       "0                                         30   \n",
       "1                                         25   \n",
       "2                                         28   \n",
       "3                                         26   \n",
       "4                                         28   \n",
       "\n",
       "   percentage_drivers_fatal_not_distracted  \\\n",
       "0                                       96   \n",
       "1                                       90   \n",
       "2                                       84   \n",
       "3                                       94   \n",
       "4                                       91   \n",
       "\n",
       "   percentage_drivers_fatal_no_previous_accidents  car_insurance_premiums  \\\n",
       "0                                              80                  784.55   \n",
       "1                                              94                 1053.48   \n",
       "2                                              96                  899.47   \n",
       "3                                              95                  827.34   \n",
       "4                                              89                  878.41   \n",
       "\n",
       "      region  \n",
       "0  Southeast  \n",
       "1       West  \n",
       "2  Southeast  \n",
       "3  Southeast  \n",
       "4       West  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "continental-franklin",
   "metadata": {},
   "source": [
    "**Data Overview**\n",
    "\n",
    "### When is this data set from?\n",
    "\n",
    "I got the data set from FiveThirtyEight. It was used for an article called\n",
    "\"Dear Mona, Which state has the worst drivers?\" in October 2014. The data they used for this article were gathered over different years between 2009 and 2012. The person who wrote the article is Mona Chalabi, they are a data editor at the Guardian US, a columnist at New York Magazine, and a lead news writer for FiveThirtyEight. \n",
    "\n",
    "The date is about fatal collisions in each state. There are 8 rows:\n",
    "\n",
    "1. State\n",
    "2. Number of drivers involved in fatal collisions per billion miles\n",
    "3. Percentage Of Drivers Involved In Fatal Collisions Who Were Speeding\n",
    "4. Percentage Of Drivers Involved In Fatal Collisions Who Were Alcohol-Impaired\n",
    "5. Percentage Of Drivers Involved In Fatal Collisions Who Were Not Distracted\n",
    "6. Percentage Of Drivers Involved In Fatal Collisions Who Had Not Been Involved In Any Previous Accidents\n",
    "7. Car Insurance Premiums ($)\n",
    "8. Region\n",
    "\n",
    "### How did this data set get clean?\n",
    "\n",
    "I did not need to do much data cleaning myself, but I did add a \"Region\" column to split the states into 4 regions: Midwest, Southeast, West, and Northeast. I also excluded data on Losses incurred by insurance companies for collisions per insured driver because insurance companies are well known for finding ways to avoid paying customers for collisions, so this is not an accurate representation of fatal car crashes.    \n",
    "\n",
    "## What specific research questions will you investigate?\n",
    "\n",
    "1. What region has the highest drinking and driving cause of fatal collisions?\n",
    "\n",
    "2. What region has the highest car insurance premiums?\n",
    "\n",
    "3. What region is the most unlucky state for fatal collisions?\n",
    "\n",
    "4. Is there a connection between the average Percentage Of Drivers Involved In Fatal Collisions Who Were Speeding and the Number of drivers involved in fatal collisions per billion miles?\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "f7bba5f3-5911-4a76-ad43-f6ce78cd4fb3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['State', 'number_drivers_fatal_billion_miles',\n",
       "       'percentage_drivers_fatal_speeding',\n",
       "       'percentage_drivers_fatal_alcohol_impaired',\n",
       "       'percentage_drivers_fatal_not_distracted',\n",
       "       'percentage_drivers_fatal_no_previous_accidents',\n",
       "       'car_insurance_premiums', 'region'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "infinite-instrument",
   "metadata": {},
   "source": [
    "# Methods and Results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "basic-canadian",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<function seaborn.rcmod.set_theme(context='notebook', style='darkgrid', palette='deep', font='sans-serif', font_scale=1, color_codes=True, rc=None)>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import seaborn as sns\n",
    "sns.set_theme"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "recognized-positive",
   "metadata": {},
   "source": [
    "## First Research Question: What region has the highest drinking and driving cause of fatal collisions?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "graduate-palmer",
   "metadata": {},
   "source": [
    "### Methods"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "endless-variation",
   "metadata": {},
   "source": [
    "*Explain how you will approach this research question below. Consider the following:* \n",
    "  - *Which aspects of the dataset will you use?* \n",
    "  - *How will you reorganize/store the data?* \n",
    "  - *What data science tools/functions will you use and why?* \n",
    "  \n",
    "✏️ *Write your answer below:*\n",
    "\n",
    "To answer this question, I will organize the data for each state by the region it is in. Then, calculate the average percentage of drivers involved in fatal collisions who were alcohol-impaired. Finally, I will make a bar plot to compare the average number of fatal collisions that involved drinking and driving for each of the regions\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "portuguese-japan",
   "metadata": {},
   "source": [
    "### Results "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "negative-highlight",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "region\n",
       "Southeast    29.687500\n",
       "West         30.363636\n",
       "Northeast    31.333333\n",
       "Midwest      31.666667\n",
       "Name: percentage_drivers_fatal_alcohol_impaired, dtype: float64"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#######################################################################\n",
    "### 💻 YOUR WORK GOES HERE TO ANSWER THE FIRST RESEARCH QUESTION 💻 \n",
    "### \n",
    "### Your data analysis may include a statistic and/or a data visualization\n",
    "#######################################################################\n",
    "\n",
    "region = df.groupby(\"region\").percentage_drivers_fatal_alcohol_impaired.mean().sort_values()\n",
    "region\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "victorian-burning",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='region', ylabel='percentage_drivers_fatal_alcohol_impaired'>"
      ]
     },
     "execution_count": 16,
     "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.barplot(data=df, x=\"region\", y=\"percentage_drivers_fatal_alcohol_impaired\", errorbar=\"sd\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a4159a11-dde7-4756-949b-e12407d56af9",
   "metadata": {},
   "source": [
    "This graph shows that the Midwest region has the highest percentage of drivers involved in fatal collisions who were alcohol-impaired in 2012"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "collectible-puppy",
   "metadata": {},
   "source": [
    "## Second Research Question: What region has the highest car insurance premiums?\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "demographic-future",
   "metadata": {},
   "source": [
    "### Methods"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "incorporate-roller",
   "metadata": {},
   "source": [
    "*Explain how you will approach this research question below. Consider the following:* \n",
    "  - *Which aspects of the dataset will you use?* \n",
    "  - *How will you reorganize/store the data?* \n",
    "  - *What data science tools/functions will you use and why?* \n",
    "\n",
    "✏️ *Write your answer below:*\n",
    "\n",
    "To answer this question, I will organize the data for each state by the region it is in. Then, compare the average cost of car insurance and see which region is the highest.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "juvenile-creation",
   "metadata": {},
   "source": [
    "### Results "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "pursuant-surrey",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "region\n",
       "Midwest       756.630833\n",
       "West          855.624545\n",
       "Southeast     905.472500\n",
       "Northeast    1021.320000\n",
       "Name: car_insurance_premiums, dtype: float64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#######################################################################\n",
    "### 💻 YOUR WORK GOES HERE TO ANSWER THE SECOND RESEARCH QUESTION 💻 \n",
    "###\n",
    "### Your data analysis may include a statistic and/or a data visualization\n",
    "#######################################################################\n",
    "\n",
    "df.groupby(\"region\").car_insurance_premiums.mean().sort_values()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "located-night",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='region', ylabel='car_insurance_premiums'>"
      ]
     },
     "execution_count": 31,
     "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.barplot(data=df, x=\"region\", y=\"car_insurance_premiums\", errorbar=\"sd\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8e330a3f-3da7-4a1a-ab73-f7c528dfb809",
   "metadata": {},
   "source": [
    "The graph shows that the region with the highest premium car insurance is the Northwest "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e998c4c9-6d26-45fc-86f9-1362761c2b46",
   "metadata": {},
   "source": [
    "## Third Research Question: What region is the most unlucky for fatal collisions? "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "810dc600-da04-437d-a546-4d6c5bec01c6",
   "metadata": {},
   "source": [
    "### Methods"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "be64d030-0f40-4c32-ac3e-be494e64b3a7",
   "metadata": {},
   "source": [
    "*Explain how you will approach this research question below. Consider the following:* \n",
    "  - *Which aspects of the dataset will you use?* \n",
    "  - *How will you reorganize/store the data?* \n",
    "  - *What data science tools/functions will you use and why?* \n",
    "\n",
    "✏️ *Write your answer below:*\n",
    "\n",
    "To answer this question, I will organize the data for each state by the region it is in. Then, compare the average percentage of Drivers Involved In Fatal Collisions Who Were Not Distracted and the average percentage of Drivers Involved In Fatal Collisions Who Had Not Been Involved In Any Previous Accidents."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "096fe314-2953-4644-86e0-cd717f77eb8f",
   "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>percentage_drivers_fatal_not_distracted</th>\n",
       "      <th>percentage_drivers_fatal_no_previous_accidents</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>region</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Midwest</th>\n",
       "      <td>88.833333</td>\n",
       "      <td>86.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Northeast</th>\n",
       "      <td>88.666667</td>\n",
       "      <td>87.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Southeast</th>\n",
       "      <td>83.000000</td>\n",
       "      <td>89.312500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>West</th>\n",
       "      <td>84.000000</td>\n",
       "      <td>91.727273</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           percentage_drivers_fatal_not_distracted  \\\n",
       "region                                               \n",
       "Midwest                                  88.833333   \n",
       "Northeast                                88.666667   \n",
       "Southeast                                83.000000   \n",
       "West                                     84.000000   \n",
       "\n",
       "           percentage_drivers_fatal_no_previous_accidents  \n",
       "region                                                     \n",
       "Midwest                                         86.666667  \n",
       "Northeast                                       87.250000  \n",
       "Southeast                                       89.312500  \n",
       "West                                            91.727273  "
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "region = df.groupby(\"region\")\n",
    "region_mean = region[[\"percentage_drivers_fatal_not_distracted\", \"percentage_drivers_fatal_no_previous_accidents\"]].mean().sort_values(\"region\")\n",
    "region_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "3777e6d1-08a5-4747-9100-9af86f88e90a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='region', ylabel='percentage_drivers_fatal_not_distracted'>"
      ]
     },
     "execution_count": 33,
     "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.barplot(data=region_mean, x=\"region\", y=\"percentage_drivers_fatal_not_distracted\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "21d5122b-9973-43f9-b4f0-7db7a6c936d9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='region', ylabel='percentage_drivers_fatal_no_previous_accidents'>"
      ]
     },
     "execution_count": 34,
     "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.barplot(data=region_mean, x=\"region\", y=\"percentage_drivers_fatal_no_previous_accidents\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8f0aafcf-d9d4-4840-be7f-6e84d97efbcf",
   "metadata": {},
   "source": [
    "After looking at the two bar graphs about the percentage of drivers involved in fatal collisions who were not distracted and the percentage of drivers involved in fatal collisions who had not been involved in any previous accidents, it seems that the Midwest region has the highest percentage in Fatal Collisions Who Were Not Distracted and the West region had more drivers in Fatal Collisions Who Had Not Been Involved In Any Previous Accidents both categories."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d66967db-fe78-4889-824e-f7bce4e02cc8",
   "metadata": {},
   "source": [
    "## Fourth Research Question: Is there a connection between the average Percentage Of Drivers Involved In Fatal Collisions Who Were Speeding and the Number of drivers involved in fatal collisions per billion miles?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9661b6d4-3c4f-42a2-8916-b9df38375760",
   "metadata": {},
   "source": [
    "### Methods"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cc44ade7-3ae9-44a0-b821-29ecb1b66385",
   "metadata": {},
   "source": [
    "Explain how you will approach this research question below. Consider the following:\n",
    "\n",
    "Which aspects of the dataset will you use?\n",
    "How will you reorganize/store the data?\n",
    "What data science tools/functions will you use and why?\n",
    "✏️ Write your answer below:\n",
    "\n",
    "To answer this question, I will organize the data for each state by the region it is in. Then, compare the average Percentage Of Drivers Involved In Fatal Collisions Who Were Speeding to see if there is a connection with the region with the highest car insurance."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "b921b74c-951a-4f30-a42e-292f011fd61a",
   "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>percentage_drivers_fatal_speeding</th>\n",
       "      <th>number_drivers_fatal_billion_miles</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>region</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Midwest</th>\n",
       "      <td>27.166667</td>\n",
       "      <td>15.558333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Northeast</th>\n",
       "      <td>34.166667</td>\n",
       "      <td>12.225000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Southeast</th>\n",
       "      <td>27.687500</td>\n",
       "      <td>19.200000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>West</th>\n",
       "      <td>39.909091</td>\n",
       "      <td>14.972727</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           percentage_drivers_fatal_speeding  \\\n",
       "region                                         \n",
       "Midwest                            27.166667   \n",
       "Northeast                          34.166667   \n",
       "Southeast                          27.687500   \n",
       "West                               39.909091   \n",
       "\n",
       "           number_drivers_fatal_billion_miles  \n",
       "region                                         \n",
       "Midwest                             15.558333  \n",
       "Northeast                           12.225000  \n",
       "Southeast                           19.200000  \n",
       "West                                14.972727  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "region = df.groupby(\"region\")\n",
    "region_speed_insur = region[[\"percentage_drivers_fatal_speeding\", \"number_drivers_fatal_billion_miles\"]].mean().sort_values(\"region\")\n",
    "region_speed_insur"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "c242ede2-9440-4d49-8967-e6dfce650ec1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='region', ylabel='percentage_drivers_fatal_speeding'>"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjMAAAGwCAYAAABcnuQpAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAO2BJREFUeJzt3Qd0VNX69/En9N6lh44U6aFLB4mA9EsTBRFRuYB0AQFRuiDVi3hFCKAiSlW8SouAUoJAQGmCQCQBKQqGUEObdz37v868GUggDJPMnOT7WevIzDmTk23OlN/s6udwOBwCAABgUym8XQAAAIDHQZgBAAC2RpgBAAC2RpgBAAC2RpgBAAC2RpgBAAC2RpgBAAC2lkqSuLt378qff/4pmTNnFj8/P28XBwAAxINOg3f58mXJnz+/pEiRInmHGQ0y/v7+3i4GAABwQ0REhBQsWDB5hxmtkbH+GFmyZPF2cQAAQDxERUWZygjrczxZhxmraUmDDGEGAAB7iU8XEToAAwAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAW/OpMDN58mQzbfGAAQOc+27cuCF9+vSRnDlzSqZMmaR9+/Zy7tw5r5YTAAD4Dp8JM7t27ZL//ve/UqFCBZf9AwcOlDVr1siyZctky5YtZhXsdu3aea2cAADAt/hEmLly5Yp07dpV5s2bJ9mzZ3fuv3TpksyfP1+mT58ujRo1koCAAAkKCpLt27dLSEiIV8sMAAB8g0+EGW1GatGihTRp0sRl/549e+TWrVsu+0uXLi2FChWSHTt2xHqu6Ohos2x4zA0AACRdqbxdgKVLl0poaKhpZrrX2bNnJU2aNJItWzaX/Xny5DHHYjNp0iR59913E6y8AADAt3g1zEREREj//v1lw4YNki5dOo+cc8SIETJo0CDnfa2Z8ff398i5AQD2EjB0sbeLgBj2TO0mSa6ZSZuRzp8/L1WqVJFUqVKZTTv5zp4929zWGpibN29KZGSky8/paKa8efPGes60adNKlixZXDYAAJB0ebVmpnHjxrJ//36XfT169DD9YoYNG2ZqVFKnTi3BwcFmSLY6cuSIhIeHS61atbxUagAA4Eu8GmYyZ84s5cqVc9mXMWNGM6eMtb9nz56m2ShHjhymlqVfv34myNSsWdNLpQYAAL7E6x2AH2bGjBmSIkUKUzOjI5UCAwPlww8/9HaxAACAj/C5MLN582aX+9oxeM6cOWYDAADwyXlmAAAA3EWYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtkaYAQAAtubVMDN37lypUKGCZMmSxWy1atWS77//3nm8QYMG4ufn57K9/vrr3iwyAADwMam8+csLFiwokydPlpIlS4rD4ZBFixZJ69atZe/evfLUU0+Zx/Tq1UvGjh3r/JkMGTJ4scQAAMDXeDXMtGzZ0uX+hAkTTG1NSEiIM8xoeMmbN6+XSggAAHydz/SZuXPnjixdulSuXr1qmpssn3/+ueTKlUvKlSsnI0aMkGvXrj3wPNHR0RIVFeWyAQCApMurNTNq//79JrzcuHFDMmXKJKtWrZKyZcuaY88//7wULlxY8ufPL7/++qsMGzZMjhw5IitXrozzfJMmTZJ33303Ef8PAACAN/k5tLOKF928eVPCw8Pl0qVLsnz5cvnkk09ky5YtzkAT0w8//CCNGzeWY8eOSfHixeOsmdHNojUz/v7+5vzayRgAkHwEDF3s7SIghj1Tu0l86ed31qxZ4/X57fWamTRp0kiJEiXM7YCAANm1a5fMmjVL/vvf/9732Bo1aph/HxRm0qZNazYAAJA8+EyfGcvdu3ddalZi2rdvn/k3X758iVwqAADgq7xaM6Mdeps1ayaFChWSy5cvy5IlS2Tz5s2ybt06OX78uLnfvHlzyZkzp+kzM3DgQKlXr56ZmwYAAMDrYeb8+fPSrVs3OXPmjGkX05CiQeaZZ56RiIgI2bhxo8ycOdOMcNJ+L+3bt5dRo0Zx5QAAwOOFmbiGO+sMvdpfRfvBxMf8+fPjPKbhRTsCAwAAeDzMZMuWzQSXB83s+9JLL8mYMWMkRQqf65YDuGC0g31HOwCA22Fm4cKFMnLkSBNYqlevbvb9/PPPZjkCbQb666+/5P333ze1NG+99RZ/aQAA4FthRkPLtGnTpGPHji5LE5QvX94MqQ4ODjadenV5AsIMAABISG61AW3fvl0qV658337dt2PHDnO7Tp06ZjI8AAAAnwsz2jk3ts67uk+PqQsXLkj27Nkfv4QAAACebmbS/jAdOnSQ77//XqpVq2b27d69W3777TezJIHSmXw7derkzukBAAASNsy0atXKBBftH3P06FGzTye/W716tRQpUsTc7927tzunBgAASJxJ84oWLSqTJ09298cBAAC8G2YiIyPNcGydxVfXU4pJZ/UFAADw2TCzZs0a6dq1q1y5csUsyx1zAj29TZgBAAA+PZpp8ODB8vLLL5swozU0//zzj3O7ePGi50sJAADgyTBz+vRpeeONNyRDhgzu/DgAAIB3w0xgYKAZig0AAGDLPjMtWrSQoUOHyqFDh8wSBqlTp75v6DYAAIDPhplevXqZf8eOHXvfMe0AfOfOnccvGQAAQEKFmXuHYgMAANiqzwwAAIDtamZmz54tr776qqRLl87cfhAd6QQAAOBTYWbGjBlmojwNM3o7LtpnhjADAAB8LsyEhYXFehsAAMCb6DMDAACSR83MoEGD4n3S6dOnu1seAACAhAkze/fudbkfGhoqt2/fllKlSpn7R48elZQpU0pAQMCjlQAAACAxwsymTZtcal4yZ84sixYtkuzZs5t9ushkjx49pG7duo9THgAAgITvMzNt2jSZNGmSM8govT1+/HhzDAAAwKfDTFRUlPz111/37dd9ly9f9kS5AAAAEi7MtG3b1jQprVy5Uk6dOmW2FStWSM+ePaVdu3bunBIAACDx1mb66KOPZMiQIfL888/LrVu3/u9EqVKZMDN16lT3SgIAAJBYYSZDhgzy4YcfmuBy/Phxs6948eKSMWNGd04HAADgnUnzzpw5Y7aSJUuaIONwOB7ndAAAAIkTZi5cuCCNGzeWJ598Upo3b24CjdJmpsGDB7tzSgAAgMQLMwMHDpTUqVNLeHi4aXKydOrUSdauXeteSQAAABKrz8z69etl3bp1UrBgQZf92tx08uRJd04JAACQeDUzV69edamRsVy8eFHSpk0b7/PMnTtXKlSoIFmyZDFbrVq15Pvvv3cev3HjhvTp00dy5swpmTJlkvbt28u5c+fcKTIAAEii3AozumTB4sWLnff9/Pzk7t27MmXKFGnYsGG8z6M1O5MnT5Y9e/bI7t27pVGjRtK6dWs5ePCgszlrzZo1smzZMtmyZYv8+eefzGMDAAAev5lJQ4t2ANYAcvPmTXnzzTdNANGamW3btsX7PC1btnS5P2HCBFNbExISYoLO/PnzZcmSJSbkqKCgIClTpow5XrNmTXeKDgAAkhi3ambKlStnVsl++umnTU2KNjtpjYmurK3zzbjjzp07snTpUnMubW7S2hqdkK9JkybOx5QuXVoKFSokO3bsiPM80dHRZrmFmBsAAEi63KqZUVmzZpVRo0Y9dgH2799vwov2j9F+MatWrZKyZcvKvn37JE2aNJItWzaXx+fJk0fOnj0b5/l0Acx33333scsFAACS+KR5P/30k7zwwgtSu3ZtOX36tNn36aefytatWx/pPKVKlTLBZefOndK7d2/p3r27HDp0yN1iyYgRI+TSpUvOLSIiwu1zAQCAJBpmdFHJwMBASZ8+vYSGhpqmHaXhYeLEiY90Lq19KVGihAQEBJhalYoVK8qsWbMkb968pj9OZGSky+N1NJMei4uOprJGR1kbAABIutwKM+PHjzeLTc6bN89MnmfRPjQabh6HjorScKThRs8dHBzsPHbkyBEzUZ82SwEAALjdZ0ZDRb169WLtR3NvTcrDmoSaNWtmOvVevnzZjFzavHmzmZBPz6XLIwwaNEhy5Mhhalj69etnggwjmQAAwGOFGW3mOXbsmBQpUsRlv/aXKVasWLzPc/78eenWrZtZ20nDi06gp0HmmWeeMcdnzJghKVKkMJPlaW2NNm3pat0AAACPFWZ69eol/fv3lwULFpgJ83QyOx0uPWTIEBk9enS8z6PzyDxIunTpZM6cOWYDAADwWJgZPny46duiE+ddu3bNNDlpx1sNM9oUBAAA4NNhRmtjRo4cKUOHDjXNTVeuXDFzw+g8MQAAALaYNM8aVp05c2azEWQAAIBthmbfvn3b9I3RTrvaCVg3a0ZgXYIAAADAp2tmtF/MypUrzYKT1pwv2gH4nXfekQsXLpjFIgEAAHw2zOh8MLoopM4RY9Fh1f7+/tKlSxfCDAAA8O1mJh25dO8cM6po0aKmHw0AAIBPh5m+ffvKuHHjnGsyKb09YcIEcwwAAMCnm5n27t1r1kwqWLCgWRhS/fLLL2ZhSJ17pl27ds7Hat8aAAAAnwoz2bJlM0sMxKT9ZQAAAGwRZoKCgjxfEgAAgMTqM3P9+nWzjIHl5MmTMnPmTFm/fr07pwMAAEjcMNO6dWtZvHixuR0ZGSnVq1eXadOmmf0MywYAAD4fZkJDQ6Vu3brm9vLlyyVv3rymdkYDzuzZsz1dRgAAAM/2mdEmJl2PSWnTko5eSpEihdSsWdOEGgDwVQFD/69WGb5hz9Ru3i4CkmvNTIkSJWT16tUSEREh69atk6ZNm5r958+flyxZsni6jAAAAJ4NM2+//bYMGTLEzAJco0YN5/pMWktTuXJld04JAACQeM1M//rXv6ROnTpy5swZ56R5SifMa9u2rfP+qVOnJH/+/KYJCgAAwGfCjNJOv7rFpKOaYipbtqzs27dPihUrJnZCm7pvoU0dAPAgCVpl4nA4EvL0AAAACRtmAAAAEhphBgAA2BphBgAA2FqChhk/P7+EPD0AAAAdgAEAQDIdmh0fhw4dMvPMAAAAeD3M6PpL8bVy5Urzr7+/v3ulAgAA8HSYyZo1a3wfCgAA4HthJigoKGFLAgAA4AaGZgMAgOTZAXj58uXy1VdfSXh4uNy8edPlWGhoqCfKBgAAkDA1M7Nnz5YePXpInjx5ZO/evWaByZw5c8qJEyekWbNm7pwSAAAg8cLMhx9+KB9//LF88MEHkiZNGnnzzTdlw4YN8sYbb8ilS5fcKwkAAEBihRltWqpdu7a5nT59erl8+bK5/eKLL8oXX3zhzikBAAASL8zkzZtXLl68aG4XKlRIQkJCzO2wsLBHmvV30qRJUq1aNcmcObPkzp1b2rRpI0eOHHF5TIMGDcyyCDG3119/3Z1iAwCAJMitMNOoUSP55ptvzG3tOzNw4EB55plnpFOnTtK2bdt4n2fLli3Sp08fE4a0merWrVvStGlTuXr1qsvjevXqJWfOnHFuU6ZMcafYAAAgCXJrNJP2l7l79665rWFEO/9u375dWrVqJa+99lq8z7N27VqX+wsXLjQ1NHv27JF69eo592fIkMHUBsVHdHS02SxRUVHxLg8AAEgmNTOnTp2SlClTOu937tzZjHDq27evnD171u3CWJ2Hc+TI4bL/888/l1y5ckm5cuVkxIgRcu3atQc2XelsxdbGkgoAACRtbtXMFC1a1DT3aC1KTNqPRo/duXPnkc+pNT0DBgyQp59+2oQWy/PPPy+FCxc2C1b++uuvMmzYMNOvxlr/6V4adgYNGuRSM0OgAQAg6XIrzGgnX+2Ie68rV65IunTp3CqINlcdOHBAtm7d6rL/1Vdfdd4uX7685MuXTxo3bizHjx+X4sWL33eetGnTmg0AACQPjxRmrBoPDTKjR482fVksWhuzc+dOqVSp0iMXQpunvv32W/nxxx+lYMGCD3xsjRo1zL/Hjh2LNcwAAIDk5ZHCjM72a9XM7N+/30yYZ9HbFStWlCFDhsT7fHqefv36yapVq2Tz5s2mieph9u3bZ/7VGhoAAIBHCjObNm1yDseeNWuWZMmS5bF+uTYtLVmyRL7++msz14zVeVg77upkfNqUpMebN29uRkxpnxkdBq4jnSpUqPBYvxsAACTjPjNBQUEe+eVz5851Tox37/lfeuklU9uzceNGmTlzppl7Rjvytm/fXkaNGuWR3w8AAJLxqtm7d++Oc9XsuEYa3ethswVreNGJ9QAAADw6z8zSpUvN2kyHDx82/V105t6DBw/KDz/8YJqIAAAAfDrMTJw4UWbMmCFr1qwxTUHaf+a3336Tjh07mrWaAAAAfDrMaMfcFi1amNsaZrQ/iw7X1s65utQBAACAT4eZ7Nmzy+XLl83tAgUKmMnuVGRk5AOXGgAAAPCJDsA6NFpXudYZeTt06CD9+/c3/WV0n87OCwAA4NNh5j//+Y/cuHHD3B45cqSkTp3arJrNsGkAAOCzYUaXMhg3bpxkzJjRNCvpaCaVIkUKGT58eEKWEQAA4PH7zHzwwQdmIUnVsGFDs0I2AACAbWpmihQpIrNnz5amTZuaye527NhhOgLH1acGAADAp8LM1KlT5fXXX5dJkyaZYdht27aN9XF6TFfQBgAA8Kkw06ZNG7NpU5MuMHnkyBHJnTt3wpYOAADA0/PMZMqUyayeXbRoUbN0QWybZfLkyWbuGQAAAJ+aNK9+/fqSKlWqeC17QEdhAADgc2Emvh62KjYAAIBPhxkAAICERpgBAAC2RpgBAAC2RpgBAAC2lqBhpm7dupI+ffqE/BUAACCZcyvMhIaGyv79+533v/76azOh3ltvvSU3b9507v/uu+8kX758nikpAACAp8LMa6+9JkePHjW3T5w4IZ07d5YMGTLIsmXL5M0333TnlAAAAIkXZjTIVKpUydzWAKMLSy5ZskQWLlwoK1ascK8kAAAAiRVmdDK8u3fvmtsbN26U5s2bm9v+/v7y999/u3NKAACAxAszVatWlfHjx8unn34qW7ZskRYtWpj9YWFhkidPHk+XEQAAwLNhZubMmaYTcN++fWXkyJFSokQJs3/58uVSu3Ztd04JAADgloevFnmPO3fumJWwf/zxR8mePbvLsalTp0rKlCndKwkAAEBi1MxoWGnatKkJNPdKly6dpE6d2p1yAAAAJF4zU7ly5cyQbAAAAFuGGe38O2TIEPn222/lzJkzEhUV5bIBAAD4bJ8ZZQ3FbtWqlfj5+bkM2db72q8GAADAZ8PMpk2bPF8SAACAxAoz9evXd+fHAAAAfGfV7J9++kleeOEFM6/M6dOnzT6dRG/r1q2eLB8AAIDnw4yuvxQYGCjp06c3k+dFR0eb/ZcuXZKJEyfG+zyTJk2SatWqSebMmSV37txm5e0jR464PObGjRvSp08fyZkzp2TKlEnat28v586dc6fYAAAgCXJ7NNNHH30k8+bNc5lX5umnnzbhJr50KQQNKiEhIbJhwwa5deuWmcPm6tWrzscMHDhQ1qxZYxa01Mf/+eef0q5dO3eKDQAAkiC3+sxo7YmulH2vrFmzxjqZXlzWrl3rcl9X3dYamj179pjza03P/PnzzYrcjRo1Mo8JCgqSMmXKmABUs2bN+86ptURWTZFiqDgAAEmbWzUzefPmlWPHjt23X/vLFCtWzO3CaHhROXLkMP9qqNHamiZNmjgfU7p0aSlUqJDs2LEjzqYrDVXWpit5AwCApMutMNOrVy/p37+/7Ny508wro00/n3/+uZlIr3fv3m4V5O7duzJgwADTVKUzDKuzZ89KmjRpJFu2bC6P1ZW59VhsRowYYUKRtUVERLhVHgAAkISbmYYPH27CR+PGjeXatWumSSht2rQmzPTr18+tgmjfmQMHDjz2aCgth24AACB5cCvMaG3MyJEjZejQoaa56cqVK1K2bFkz2sgdffv2NUsj6ErcBQsWdGnOunnzpumHE7N2Rkcz6TEAAAC3mpk+++wzUyOjTUAaYqpXr+5WkNHlDzTIrFq1Sn744QcpWrSoy/GAgAAzWio4ONil83F4eLjUqlXLnaIDAIAkxq0wo8OlddTR888/L999953bazFp05IGIx2tpHPNaD8Y3a5fv26Oawfenj17yqBBg8wSCtohuEePHibIxDaSCQAAJD9uhRldKXvp0qWmualjx46SL18+E0y2b9/+SOeZO3eu6aTboEEDcw5r+/LLL52PmTFjhjz33HNmsjztm6PNSytXrnSn2AAAIAlyq89MqlSpTMDQTZubtJlIa1caNmxo+rwcP3483s1MD5MuXTqZM2eO2QAAADwSZmLKkCGDWdrgn3/+kZMnT8rhw4cf95QAAAAJv9Ck1sjo3DLNmzeXAgUKyMyZM6Vt27Zy8OBBd08JAACQODUznTt3NkOptVZG+8yMHj2a0UUAAMA+YSZlypTy1VdfmeYlvQ0AAGCrMKPNSwAAALYKM7Nnz5ZXX33VjC7S2w/yxhtveKJsAAAAngszOt9L165dTZiZPn26mWMmNrqfMAMAAHwuzISFhTlv//HHHwlVHgAAgIQdmn3r1i0pXrw488kAAAB7hhld+PHGjRsJUxoAAIDEmDRP12F677335Pbt2+78OAAAgHeHZu/atUuCg4Nl/fr1Ur58ecmYMaPLcRaCBAAAPh1msmXLZlaxBgAAsGWYCQoK8nxJAAAAEnOhSQAAAFvVzFSuXDnOifLuFRoa+jhlAgAA8HyYadOmjfO2Ds3+8MMPpWzZss7VskNCQuTgwYPy73//O/6/HQAAILHCzJgxY5y3X3nlFbNkwbhx4+57TERExOOWCQAAIGH7zCxbtky6det23/4XXnhBVqxY4c4pAQAAEi/MpE+fXrZt23bfft2nC1ECAAD49NDsAQMGSO/evU1H3+rVq5t9O3fulAULFsjo0aM9XUYAAADPhpnhw4dLsWLFZNasWfLZZ5+ZfWXKlDHzz3Ts2NGdUwIAACRemFEaWh4WXL744gtp1arVfcsdAAAA2GLSvNdee03OnTuXkL8CAAAkcwkaZhwOR0KeHgAAgOUMAACAvRFmAACArRFmAACArRFmAACArSVomClcuLCkTp06IX8FAABI5twOM5GRkfLJJ5/IiBEj5OLFi2afzgh8+vRp52MOHDgg/v7+nikpAACApybN+/XXX6VJkyaSNWtW+eOPP6RXr16SI0cOWblypYSHh8vixYvdOS0AAEDi1MwMGjRIXnrpJfn9999dFpZs3ry5/Pjjj+6cEgAAIPHCzK5du8zsvvcqUKCAnD17Nt7n0eDTsmVLyZ8/v/j5+cnq1atdjmtg0v0xt2effdadIgMAgCTKrTCTNm1aiYqKum//0aNH5Yknnoj3ea5evSoVK1aUOXPmxPkYDS9nzpxxbrreEwAAwGP1mdHFI8eOHStfffWVua81JtpXZtiwYdK+fft4n6dZs2Zme1hwyps3b7zPGR0dbTZLbKELAAAk85qZadOmyZUrVyR37txy/fp1qV+/vpQoUUIyZ84sEyZM8GgBN2/ebH5PqVKlpHfv3nLhwoUHPn7SpEmmY7K1MZoKAICkza2aGQ0JGzZskK1bt5qRTRpsqlSpYkY4eZI2MbVr106KFi0qx48fl7feesvU5OzYsUNSpkwZ68/oUHHtoByzZoZAAwBA0uVWmLHUqVPHbAmlc+fOztvly5eXChUqSPHixU1tTePGjeNsltINAAAkD26FmdmzZ8e6X/vO6FBtbXKqV69enLUn7ipWrJjkypVLjh07FmeYAQAAyYtbYWbGjBny119/ybVr1yR79uxm3z///CMZMmSQTJkyyfnz503w2LRpk0ebeE6dOmX6zOTLl89j5wQAAMmwA/DEiROlWrVqZtI8DRe66bDsGjVqyKxZs8zIJh2BNHDgwAeeR/va7Nu3z2wqLCzM3Naf12NDhw6VkJAQM8twcHCwtG7d2tT6BAYGuvd/CwAAkhy3amZGjRolK1asMP1XLBoy3n//fTM0+8SJEzJlypSHDtPevXu3NGzY0Hnf6rjbvXt3mTt3rulcvGjRIrMOlE6s17RpUxk3bhx9YgAAwOOFGZ287vbt2/ft133WDMAaPi5fvvzA8zRo0EAcDkecx9etW+dO8QAAQDLiVjOT1qbocgZ79+517tPbOg9Mo0aNzP39+/ebIdUAAAA+F2bmz59vVskOCAhwDoWuWrWq2afHlHYE1sn1AAAAfK6ZSTv36qR5v/32m+n4q3SGXt0sMfvCAAAA+OSkeaVLlzYbAACA7cKMzvnyzTffmGHUN2/edDk2ffp0T5QNAAAgYcKMzvmiK2frxHja1FSuXDkzF4yOTNI1mgAAAHy6A7Au5jhkyBAzYkmXL9A5ZyIiIszq2R06dPB8KQEAADwZZg4fPizdunUzt1OlSiXXr183o5fGjh0r7733njunBAAASLwwkzFjRmc/GV0n6fjx485jf//9t3slAQAASKw+MzVr1pStW7dKmTJlpHnz5jJ48GDT5LRy5UpzDAAAwKfDjI5W0oUg1bvvvmtuf/nll1KyZElGMgEAAN8PMzqKKWaT00cffeTJMgEAACRsnxkNMxcuXLhvv65uHTPoAAAA+GSY0Tll7ty5c9/+6OhoOX36tCfKBQAA4PlmJp3x17Ju3TrJmjWr876GG51Mr0iRIo9ySgAAgMQLM23atDH/+vn5Sffu3V2OpU6d2gQZVsoGAAA+G2bu3r1r/i1atKjs2rVLcuXKlVDlAgAASLjRTGFhYe78GAAAgO+smq39Y3Q7f/68s8bGsmDBAk+UDQAAIGHCjE6Up+swVa1a1SxnoH1oAAAAbBNmdJK8hQsXyosvvuj5EgEAACT0PDO6yGTt2rXd+VEAAADvh5lXXnlFlixZ4tmSAAAAJFYz040bN+Tjjz+WjRs3SoUKFcwcMzGx2CQAAPDpMPPrr79KpUqVzO0DBw64HKMzMAAA8Pkws2nTJs+XBAAAILH6zFiOHTtm1mi6fv26ue9wOB7ndAAAAIkTZi5cuCCNGzeWJ598Upo3by5nzpwx+3v27CmDBw9255QAAACJF2YGDhxoOv2Gh4dLhgwZnPs7deoka9euda8kAAAAidVnZv369aZ5qWDBgi77S5YsKSdPnnTnlAAAAIlXM3P16lWXGhnLxYsXJW3atO6VBAAAILHCTN26dWXx4sUuw7F1sckpU6ZIw4YN3TklAABA4jUzaWjRDsC7d+82Sxu8+eabcvDgQVMzs23bNvdKAgAAkFg1M+XKlZOjR49KnTp1pHXr1qbZqV27drJ3714pXrx4vM/z448/SsuWLSV//vymdmf16tUux3Wo99tvv21W5k6fPr00adJEfv/9d3eKDAAAkii3amZU1qxZZeTIkY/1yzUEVaxYUV5++WUThmKrAZo9e7YsWrRIihYtKqNHj5bAwEA5dOiQpEuX7rF+NwAASMZhJigoSDJlyiQdOnRw2b9s2TK5du2adO/ePV7nadasmdlio7UyM2fOlFGjRpnaH6X9dPLkyWNqcDp37uxO0QEAQBLjVjPTpEmTJFeuXPftz507t0ycONET5ZKwsDA5e/asaVqKWRtUo0YN2bFjR5w/Fx0dLVFRUS4bAABIutwKMzpZnjb73Ktw4cLmmCdokFFaExOT3reOxRW0NPRYm7+/v0fKAwAAklCY0RoYXTn7Xr/88ovkzJlTvGnEiBFy6dIl5xYREeHV8gAAAB8MM126dJE33njDrJ59584ds/3www/Sv39/j/VlyZs3r/n33LlzLvv1vnUsNjppX5YsWVw2AACQdLkVZsaNG2f6ruhcMzpkWremTZtKo0aNPNZnRpuxNLQEBwc792n/l507d0qtWrU88jsAAEAyHM2ko4y0z8rChQtl/Pjxsm/fPhNmypcvb/rMPIorV67IsWPHXDr96vly5MghhQoVkgEDBpjfoWs+WUOzdU6aNm3aPGqxAQBAEuVWmClRooSZ8VdDhm7u0hmEYy5/MGjQIPOvDu3WsKQzC+tcNK+++qpERkaaSfp0VW7mmAEAAG6HmRQpUpgAc+HChccKMqpBgwYmHMVFZwUeO3as2QAAADzWZ2by5MkydOhQOXDggDs/DgAA4N0ZgLt162Zm+tWlCNKkSWP6zMSkC04CAAD4bJjRZQYAAABsG2biu/YSAACAT/aZUcePHzeLQOoEeufPnzf7vv/+ezPKCQAAwKfDzJYtW8y8MjqB3cqVK818MdZyBmPGjPF0GQEAADwbZoYPH24ms9uwYYPpAGzRGYBDQkLcOSUAAEDihZn9+/dL27ZtY12A8u+//3avJAAAAIkVZrJlyyZnzpy5b//evXulQIEC7pwSAAAg8cKMrow9bNgws0aTztJ79+5d2bZtmwwZMsTMQQMAAODTYUZXxi5durT4+/ubzr9ly5aVunXrSu3atc0IJwAAAJ+eZ0Y7/c6bN0/efvtt039GF4OsXLmyWYASAADA58OMmj9/vsyYMUN+//13c18XnRwwYIC88sorniwfAACA58OM1shMnz5d+vXrJ7Vq1TL7duzYIQMHDpTw8HBWuQYAAL4dZubOnWuamXT2X0urVq2kQoUKJuAQZgAAgE93AL5165ZUrVr1vv0BAQFy+/ZtT5QLAAAg4cLMiy++aGpn7vXxxx9L165d3TklAABA4ncAXr9+vdSsWdPc13WatL+MzjMzaNAg5+O0bw0AAIBPhZkDBw5IlSpVnKtnq1y5cplNj1l0Qj0AAACfCzObNm3yfEkAAAASq88MAACAryDMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAWyPMAAAAW/P5MPPOO++In5+fy1a6dGlvFwsAAPiIVGIDTz31lGzcuNF5P1UqWxQbAAAkAlukAg0vefPm9XYxAACAD/L5Zib1+++/S/78+aVYsWLStWtXCQ8Pj/Ox0dHREhUV5bIBAICky+fDTI0aNWThwoWydu1amTt3roSFhUndunXl8uXLsT5+0qRJkjVrVufm7++f6GUGAACJx+fDTLNmzaRDhw5SoUIFCQwMlO+++04iIyPlq6++ivXxI0aMkEuXLjm3iIiIRC8zAABIPLboMxNTtmzZ5Mknn5Rjx47Fejxt2rRmAwAAyYPP18zc68qVK3L8+HHJly+ft4sCAAB8gM+HmSFDhsiWLVvkjz/+kO3bt0vbtm0lZcqU0qVLF28XDQAA+ACfb2Y6deqUCS4XLlyQJ554QurUqSMhISHmNgAAgM+HmaVLl3q7CAAAwIf5fDMTAADAgxBmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArRFmAACArdkizMyZM0eKFCki6dKlkxo1asjPP//s7SIBAAAf4fNh5ssvv5RBgwbJmDFjJDQ0VCpWrCiBgYFy/vx5bxcNAAD4AJ8PM9OnT5devXpJjx49pGzZsvLRRx9JhgwZZMGCBd4uGgAA8AGpvF2AB7l586bs2bNHRowY4dyXIkUKadKkiezYsSPWn4mOjjab5dKlS+bfqKioeP/eO9HXH6vc8KxHuXbu4Hr7Fq538sL1Tl6iHuF6W491OBwPf7DDh50+fVr/Dxzbt2932T906FBH9erVY/2ZMWPGmJ9hY2NjY2NjE9tvERERD80LPl0z4w6txdE+Npa7d+/KxYsXJWfOnOLn5yfJhSZaf39/iYiIkCxZsni7OEhgXO/kheudvCTX6+1wOOTy5cuSP3/+hz7Wp8NMrly5JGXKlHLu3DmX/Xo/b968sf5M2rRpzRZTtmzZJLnSJ35yevInd1zv5IXrnbwkx+udNWtW+3cATpMmjQQEBEhwcLBLTYver1WrllfLBgAAfINP18wobTLq3r27VK1aVapXry4zZ86Uq1evmtFNAAAAPh9mOnXqJH/99Ze8/fbbcvbsWalUqZKsXbtW8uTJ4+2i+TRtatO5ee5tckPSxPVOXrjeyQvX++H8tBdwPB4HAADgk3y6zwwAAMDDEGYAAICtEWYAAICtEWZ8WIMGDWTAgAEPfIyuJq4jvJD8vPTSS9KmTRtvFwOJaPPmzWbyz8jISG8XBfAphBkvfADpm9Hrr79+37E+ffqYY/oYtXLlShk3bpz4Ki3r6tWrvV0Mn7qukydPdtmvf5/HnXn6jz/+MOfYt2+f+JrkGqh0hGXv3r2lUKFCZoSJTuIZGBgo27ZtS9QvM95AoHp0ukBy5syZ5fbt2859V65ckdSpU5vrHNvf9/jx40nyPSOhEGa8QKelXrp0qVy//v8XQLtx44YsWbLEvDlacuTIYV4AsId06dLJe++9J//8849HF1uF72nfvr3s3btXFi1aJEePHpVvvvnGfChduHDB20WDD2rYsKEJL7t373bu++mnn0wI3rlzp3n/t2zatMl8DhQvXtxLpbUnwowXVKlSxQQarXmx6G19AleuXDnOb2bnz5+Xli1bSvr06aVo0aLy+eefu5x3yJAh8txzzznva/OTpnOdl8dSokQJ+eSTT5z39XaZMmXMB3Hp0qXlww8/dPkg7du3r+TLl88cL1y4sEyaNMnZvKXatm1rfod1PznT1dz1zcn6G8VmxYoV8tRTT5lv8/o3mzZtmstx3ae1cd26dTPTlr/66qvmWit9bujf+t5vcu+//765Rrr+mNbu3bp1y3lMV5DX50WBAgUkY8aMUqNGDfPNz6Ifvl26dDHHM2TIIOXLl5cvvvjC5fzLly83+/V5p79D/z914sp33nnHfJh//fXXply6xTx3UqU1EvpBpMFVP6T0daETeuq6cK1atTKPCQ8Pl9atW0umTJnMdezYsaPLsiyx1Wjpa926tnp8y5YtMmvWLOffVr9tW/bs2WMmEtVrVrt2bTly5IjLufSa6PuMvm6LFSsm7777rkutwPTp08011eeEvhf9+9//Nh+2lpMnT5r3muzZs5vH6HP2u+++M2XQ/2elx2LWJCNupUqVMq/RmK8Pva3PEX19h4SEuOzXv7HOdq/vJXpcX3sVK1Y0r0WLfmnq2rWrPPHEE+Z4yZIlJSgoyBx72HtGkuSpFa4RP927d3e0bt3aMX36dEfjxo2d+/X2jBkzzDF9jKpfv76jf//+zsc0a9bMUbFiRceOHTscu3fvdtSuXduRPn1683Pqm2++cWTNmtVx+/Ztc79NmzaOXLlyOYYNG2bunzp1yqxA+vvvv5v7n332mSNfvnyOFStWOE6cOGH+zZEjh2PhwoXm+NSpUx3+/v6OH3/80fHHH384fvrpJ8eSJUvMsfPnz5tzBQUFOc6cOWPuJ2fWdV25cqUjXbp0zlVeV61aZf5OSq9ZihQpHGPHjnUcOXLE/O30+um/lsKFCzuyZMnieP/99x3Hjh0z288//2zOsXHjRvO3vnDhgvN36mNff/11x+HDhx1r1qxxZMiQwfHxxx87z/fKK6+Y54leQz2XXtO0adM6jh496nxO6L69e/c6jh8/7pg9e7YjZcqUjp07d5rjf/75pyNVqlTm+RoWFub49ddfHXPmzHFcvnzZbB07dnQ8++yzply6RUdHO5K6W7duOTJlyuQYMGCA48aNG/cdv3PnjqNSpUqOOnXqmGseEhLiCAgIMK/ne58vMelr3XpMZGSko1atWo5evXo5/7b6ut60aZN5LtSoUcOxefNmx8GDBx1169Y119ii11qfF/o61mu6fv16R5EiRRzvvPOO8zH6nvHDDz+YaxocHOwoVaqUo3fv3s7jLVq0cDzzzDPmeus59Lm1ZcsWUwZ9n9Ay6HNYy6VlxcM9//zzjqZNmzrvV6tWzbFs2TLz+n377bfNvmvXrpnXp1678ePHO0qXLu1Yu3atuQb6PqHH9LqrPn36mOfZrl27zHXcsGGD+QxQcb1nJGWEmURmvYnph78+MTUk6KYfgH/99VecYUbfOPTJqU9Si36A6T4rzPzzzz/mw1Kf3Hfv3jXBZNKkSeaNzwovBQoUcP588eLFneHEMm7cOPMmqvr16+do1KiROVds9HfrhzVcP5xq1qzpePnll+8LM/pmph8QMQ0dOtRRtmxZlzCjITQmfaPSc2jguPd36uOt8Ko6dOjg6NSpk7l98uRJE0xOnz7t8nManEeMGBHn/4t+kA0ePNjc3rNnj/nd+hx92P93crJ8+XJH9uzZzetWg4T+PX/55RdzTMOD/t3Dw8Odj9fQEfP1+7AwE9uXGWWFGf2Qsvzvf/8z+65fv+68vhMnTnT5uU8//dR8cYmLfqjmzJnTeb98+fIu4Se2Muj7DeJv3rx5jowZM5owHBUVZb4k6OeAvgfXq1fPPEaDpfV60y8m27dvdzlHz549HV26dDG3W7Zs6ejRo0esvyssjveMpMznlzNIqrRqsEWLFrJw4UKzzLne1lXC43L48GFJlSqVWXjTos1CMVcE19taFanVlLpIp27aTKHTYGsVslZb169f3zxWmwm0g1nPnj2lV69eznNoVbS1SqlWHz/zzDOmivTZZ581TVhNmzZNoL9I0qHND40aNTLNO/deQ61Wjunpp582zYF37twxK8QrbT6IL63+t35OaVX2/v37zW39V8/75JNPuvyMNj1pc5HS4xMnTpSvvvpKTp8+bZoW9bg2Xyh9PjVu3Ng0SWgHV73+//rXv0wTQ3LvM6OvWW1u0iaC77//XqZMmWKabaOiokzTjW6WsmXLmtenPgeqVav22L+/QoUKLtfcaobWpupffvnFdESeMGGC8zF6nbVfxrVr18y13bhxo2nC+O2330x59XUf8/gbb7xhOjivX7/eNCvq/2/M34lHp009+r67a9cu00Skr0v9HND3ZF1rUP/++t6tzYL6fq3XQt9/Y9LXp9UVQa+PXpfQ0FDzutRmS21yTK4IM1708ssvmz4pas6cOR57wegLQvtk6ItEOxFrn5itW7eaMDN48GDzOKt9fN68eaYfRUzWh6O2uYeFhZk3an3z03Z/fWOL2W6L+9WrV8988GsfCnf6E2gfhfjS0RAxafu4trVb11ivpfaviBl4lPblUFOnTjX9MjRQWX0otO+G1fFYf27Dhg2yfft288H2wQcfyMiRI02nRatdPrnS/ij6YaPb6NGj5ZVXXjFfHKzX2IOkSJHCfImJKWZfp0e57tZouZjXXfvItGvXLtYya78X/WKiH4YaePQ9Qt8f9IuNXncNM/r/os/h//3vf+a6a/DR/l39+vWLdxnhSvsrFixY0HTw1TBjfbHMnz+/Cb76GtNj+kXIen/Wv7/2Z4vJWp+pWbNmpm+T9mXasGGD+dKhfea0D11yRJjxIq3t0DcPfTPSN44H0VoY/fakH0zWNzvt9Hfv8Eh9gSxYsMDU4uj5rYCjnTp11IXVEUwX6tQX0YkTJ0wnsrho50Vd7FM3/Uau57x48aJ5A9Q3VP3Gh/vpEG1dFFVrtSwaKu8duqv39RvavWEjJq1hU4/6t9ZvcPoz+o29bt26sT5Gf7/WFr3wwgvOD0R9nmhNgkWfn1qDpJsu+KodXletWmVWtNey8Rz4P/o306H4ep0jIiLMZtXOHDp0yLxWrb+rfiM/cOCAy8/rMNqYIcXdv61+CdH3Bv3wjI2+h+h11nCioUppzdy9tOw6hYRuGsz1i4+GGXefj/i/UU36ZVPDzNChQ12+AOmXxp9//tmETH2eaGjRjuRW6ImNPo+6d+9uNn2N6zk1zCTHa0SY8SL9ANNqZ+v2g1hNPa+99prMnTvXhBX9Bq292GPSF8Xly5fl22+/dc55ogFGg4hWR8dsctBvb1qdrM1Kem5tXtChg/pC0w8qHfGgP6Mfivqmt2zZMjNax2ra0pE3wcHB5kNOX3jJvekhJq3l0JA4e/Zs5z79xq5BVEcraTjcsWOH/Oc//3EZQRab3Llzm+uso9L0m51+u7aaAh9Er7WWQUdG6QeXXkedH0WvmTYZaDOJjoDQmjb9VqjXT6+5jrqxPnS1BkYfr9XYWg69r+fQD2zrObBu3Trz4alNV1que2uLkhodAdahQwdTs6p/R50+QV832sykwVBrL63rrzVe+iVERwvph5LVhKjfvrVWbPHixVKrVi357LPPTLiJOZpR/7b699aaFK1J0y8Q8aGBU2tetMlJX/f62tWmJz3/+PHjTcjRWiCtZdMRSxpodR6UmPS9Rb/563NI3w+0xsC65hpmNeDqe0zz5s3Nc9Oq6cPDw4w14jBmSNHbWkuvX271Mfqc0mbqgQMHmuBZp04duXTpkrlW+gVTw4teZ+12oE3N0dHR5npY18jd9wxb83anneTmYR0mHzSaSXula+dM7ThcqFAhx+LFi00HUKsDsEVHPOXNm9d5X3uy+/n5OTp37nzf7/v8889Nj/g0adKYDo3aEU1H5CgdFaPHtNOajo7QjoWhoaHOn9We8yVKlDAd2bQcyVls11U74enfNebLTDuOaoff1KlTm2uoI4liiu16Wp0HdWSZdvC2OonGpxPpzZs3zUgJHc2iv1M7gbZt29aMUrGeG3oOHZ2TO3dux6hRoxzdunVznvfQoUOOwMBAxxNPPGGed08++aTjgw8+cJ5fOzBqp2b9ef3/1M6hSZ2OYBo+fLijSpUqZvSgdtTU0UD6t9PRKFbn61atWpnXTubMmU3H7LNnz7qcR69Lnjx5zDkGDhzo6Nu3r8u1007/2plcR7zp31afT7F1vtVOntZxi46AsUY76mu3evXqLqPcdHSaPhf0uF5ffS+JeV4tiw4Q0Guu1/7FF190/P33386f1xF5+h6j7yvW+xUezuqYq6OUYtIOv7pfn0cWHXgxc+ZMs09fu3od9FrpqDJrsEaZMmXMNcyRI4d5zeqo1Ae9ZyRlfvofbwcqAAAAdzFpHgAAsDXCDAAAsDXCDAAAsDXCDAAAsDXCDAAAsDXCDAAAsDXCDAAAsDXCDAAAsDXCDADb06n/dekAAMkTMwADsD1dL0pX/NYVnwEkP4QZAF6jC+tZK/wCgLtoZgKQaHQFd10dWFdlzpUrlwQGBprVnHWFZl15OU+ePPLiiy/K33//7fwZXQVeV6DWmhddxX3GjBnmPHqOuJqZwsPDzQrWek5dZbhjx45mNXDLO++8I5UqVZJPP/3U/KyuKNy5c2fzuwDYD2EGQKJatGiRqY3Ztm2bTJ48WRo1aiSVK1eW3bt3y9q1a03o0PBhGTRokHnsN998Ixs2bJCffvpJQkND4zz/3bt3TZC5ePGibNmyxfzMiRMnpFOnTi6PO378uKxevVq+/fZbs+ljtTwA7CeVtwsAIHkpWbKkTJkyxdweP368CTITJ050Hl+wYIH4+/vL0aNHTU2Mhp8lS5ZI48aNzfGgoCDJnz9/nOcPDg6W/fv3S1hYmDmPWrx4sTz11FOya9cuqVatmjP0LFy4UDJnzmzua42Q/uyECRMS9P8fgOcRZgAkqoCAAOftX375RTZt2mSag+6lNSfXr1+XW7duSfXq1Z37tUmoVKlScZ7/8OHDJsRYQUaVLVtWsmXLZo5ZYUabl6wgozQ4nT9/3iP/jwASF2EGQKLSvi+WK1euSMuWLeW9996773EaLo4dO5Zg5UidOrXLfT8/P1NbA8B+6DMDwGuqVKkiBw8eNLUkJUqUcNk09BQrVsyEDm0esly6dMk0QcWlTJkyEhERYTbLoUOHJDIy0tTQAEh6CDMAvKZPnz6mo26XLl1MYNGmpXXr1kmPHj3kzp07phmoe/fuMnToUNMcpcGnZ8+ekiJFClOTEpsmTZpI+fLlzQgo7Sj8888/S7du3aR+/fpStWrVRP9/BJDwCDMAvEY78upIJQ0uTZs2NSFEh1xr/xYNLGr69OlSq1Ytee6550xQefrpp03tS7p06WI9p4acr7/+WrJnzy716tUzP6M1PF9++WUi/98BSCxMmgfAVq5evSoFChSQadOmmVoaAKADMACftnfvXvntt9/MiCbtLzN27FizX+eSAQBFmAHg895//305cuSImWxPh3brxHk6gzAAKJqZAACArdEBGAAA2BphBgAA2BphBgAA2BphBgAA2BphBgAA2BphBgAA2BphBgAA2BphBgAAiJ39P2TTFyFXfNaLAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.barplot(data=region_speed_insur, y=\"percentage_drivers_fatal_speeding\", x=\"region\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "c8079c91-3eb2-4dfd-88c0-53f8a81c9892",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='region', ylabel='number_drivers_fatal_billion_miles'>"
      ]
     },
     "execution_count": 20,
     "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.barplot(data=region_speed_insur, x=\"region\", y=\"number_drivers_fatal_billion_miles\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "98b34885-aa61-4950-a951-6fb131fc2b99",
   "metadata": {},
   "source": [
    "Comparing these two plots, it seems that there is no connection between the average Percentage Of Drivers Involved In Fatal Collisions Who Were Speeding and the Number of drivers involved in fatal collisions per billion miles. What we did learn is that the West region has the highest speeding-related fatal collisions, and the Southeast has the highest number of fatal collisions per billion miles."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "infectious-symbol",
   "metadata": {},
   "source": [
    "# Discussion"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "furnished-camping",
   "metadata": {
    "code_folding": []
   },
   "source": [
    "## Considerations"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bearing-stadium",
   "metadata": {},
   "source": [
    "*It's important to recognize the limitations of our research.\n",
    "Consider the following:*\n",
    "\n",
    "- *Do the results give an accurate depiction of your research question? Why or why not?*\n",
    "- *What were the limitations of your dataset?*\n",
    "- *Are there any known biases in the data?*\n",
    "\n",
    "✏️ *Write your answer below:*\n",
    "\n",
    "I believe that the results do give an accurate depiction of my research question because it takes 6 different causes of fatal collisions and averages them between the 5 regions of the USA. The limitations of the dataset are that it isn't up to date. The data was collected between 2009 and 2012, and some of the collisions are from different years in that time frame. Some biases that could be in this data are how they determined if someone was Alcohol-Impaired, the weather in each region, the maintenance of the roads, and the population."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "beneficial-invasion",
   "metadata": {},
   "source": [
    "## Summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "dc9fd133-418b-4f32-b1f6-0efd3578051b",
   "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>number_drivers_fatal_billion_miles</th>\n",
       "      <th>percentage_drivers_fatal_speeding</th>\n",
       "      <th>percentage_drivers_fatal_alcohol_impaired</th>\n",
       "      <th>percentage_drivers_fatal_not_distracted</th>\n",
       "      <th>percentage_drivers_fatal_no_previous_accidents</th>\n",
       "      <th>car_insurance_premiums</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>region</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Midwest</th>\n",
       "      <td>15.558333</td>\n",
       "      <td>27.166667</td>\n",
       "      <td>31.666667</td>\n",
       "      <td>88.833333</td>\n",
       "      <td>86.666667</td>\n",
       "      <td>756.630833</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Northeast</th>\n",
       "      <td>12.225000</td>\n",
       "      <td>34.166667</td>\n",
       "      <td>31.333333</td>\n",
       "      <td>88.666667</td>\n",
       "      <td>87.250000</td>\n",
       "      <td>1021.320000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Southeast</th>\n",
       "      <td>19.200000</td>\n",
       "      <td>27.687500</td>\n",
       "      <td>29.687500</td>\n",
       "      <td>83.000000</td>\n",
       "      <td>89.312500</td>\n",
       "      <td>905.472500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>West</th>\n",
       "      <td>14.972727</td>\n",
       "      <td>39.909091</td>\n",
       "      <td>30.363636</td>\n",
       "      <td>84.000000</td>\n",
       "      <td>91.727273</td>\n",
       "      <td>855.624545</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           number_drivers_fatal_billion_miles  \\\n",
       "region                                          \n",
       "Midwest                             15.558333   \n",
       "Northeast                           12.225000   \n",
       "Southeast                           19.200000   \n",
       "West                                14.972727   \n",
       "\n",
       "           percentage_drivers_fatal_speeding  \\\n",
       "region                                         \n",
       "Midwest                            27.166667   \n",
       "Northeast                          34.166667   \n",
       "Southeast                          27.687500   \n",
       "West                               39.909091   \n",
       "\n",
       "           percentage_drivers_fatal_alcohol_impaired  \\\n",
       "region                                                 \n",
       "Midwest                                    31.666667   \n",
       "Northeast                                  31.333333   \n",
       "Southeast                                  29.687500   \n",
       "West                                       30.363636   \n",
       "\n",
       "           percentage_drivers_fatal_not_distracted  \\\n",
       "region                                               \n",
       "Midwest                                  88.833333   \n",
       "Northeast                                88.666667   \n",
       "Southeast                                83.000000   \n",
       "West                                     84.000000   \n",
       "\n",
       "           percentage_drivers_fatal_no_previous_accidents  \\\n",
       "region                                                      \n",
       "Midwest                                         86.666667   \n",
       "Northeast                                       87.250000   \n",
       "Southeast                                       89.312500   \n",
       "West                                            91.727273   \n",
       "\n",
       "           car_insurance_premiums  \n",
       "region                             \n",
       "Midwest                756.630833  \n",
       "Northeast             1021.320000  \n",
       "Southeast              905.472500  \n",
       "West                   855.624545  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "region = df.groupby(\"region\")\n",
    "region_collision = region[[\"number_drivers_fatal_billion_miles\", \"percentage_drivers_fatal_speeding\", \"percentage_drivers_fatal_alcohol_impaired\", \"percentage_drivers_fatal_not_distracted\", \"percentage_drivers_fatal_no_previous_accidents\", \"car_insurance_premiums\"]].mean().sort_values(\"region\")\n",
    "region_collision"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "about-raise",
   "metadata": {},
   "source": [
    "*Summarize what you discovered through the research. Consider the following:*\n",
    "\n",
    "- *What did you learn about your media consumption/digital habits?*\n",
    "- *Did the results make sense?*\n",
    "- *What was most surprising?*\n",
    "- *How will this project impact you going forward?*\n",
    "\n",
    "✏️ *Write your answer below:*\n",
    "\n",
    "Through my research on the deadliest regions to drive in across America, I discovered how much my media consumption shapes what I believe about road safety. I realized that I tend to rely on quick social media clips or headlines that focus on shocking accidents instead of looking at real data or credible reports. Once I analyzed official statistics and news articles, I noticed how different the reality was from what I often see online.\n",
    "\n",
    "It was surprising to find that the West and Midwest regions both were the highest for 2 out of the six fatal collision categories. Especially since the Midwest is a less populated area than the other regions. \n",
    "\n",
    "This project made me more aware of how easily digital content can oversimplify serious issues. Going forward, I’ll be more intentional about checking sources, looking at data before forming opinions, and being more cautious when driving or traveling in high-risk regions. It reminded me that media can influence not just what we think, but how safely we act in real life."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "16df71b2-5dc7-4602-9c08-3236dcd4c06f",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "jupytext": {
   "cell_metadata_json": true,
   "text_representation": {
    "extension": ".Rmd",
    "format_name": "rmarkdown",
    "format_version": "1.2",
    "jupytext_version": "1.9.1"
   }
  },
  "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": "3.13.7"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": false,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}