{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# State Data\n",
    "\n",
    "В этом упражнении мы рассмотрим набор данных \"штаты\", который содержит данные за 1970-е годы по пятидесяти штатам в США. Для каждого штата набор данных включает численность населения, доход на душу населения, уровень неграмотности, уровень убийств, количество выпускников средней школы, среднее количество морозных дней, площадь, регион, к которому принадлежит штат и его аббревиатуру из двух букв."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "statedata (CSV):\n",
    "\n",
    "Этот набор данных содержит 50 наблюдений -по одному для каждого штата США для таких параметров:\n",
    "\n",
    "* Population - оценка численности населения штата в 1975 году \n",
    "* Income - доход на душу населения в 1974 году \n",
    "* Illiteracy - уровень неграмотности в 1970 году, выраженный в процентах от населения\n",
    "* Life_Exp - ожидаемая продолжительность жизни в годах жителей штата в 1970 году \n",
    "* Murder - уровень убийств и непредумышленных убийств по неосторожности на 100 000 человек населения в 1976 году.\n",
    "* HS_Grad - процент выпускников средней школы в 1970 году \n",
    "* Frost - среднее количество дней с минимальной температурой ниже нуля за период 1931-1960 годов в столице штата \n",
    "* Area - площадь суши (в квадратных милях) штата\n",
    "* State_abbr - аббревиатура из 2 букв для каждого штата \n",
    "* Region - регион, к которому относится каждый штат (Северо-восточный, Южный, Центральный или Западный).\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib import style\n",
    "import pandas as pd\n",
    "import math\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "statedata = pd.read_csv('statedata-.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Exploration"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Population</th>\n",
       "      <th>Income</th>\n",
       "      <th>Illiteracy</th>\n",
       "      <th>Life_Exp</th>\n",
       "      <th>Murder</th>\n",
       "      <th>HS_Grad</th>\n",
       "      <th>Frost</th>\n",
       "      <th>Area</th>\n",
       "      <th>State_name</th>\n",
       "      <th>Region</th>\n",
       "      <th>State_Abbr</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3615</td>\n",
       "      <td>3624</td>\n",
       "      <td>2.1</td>\n",
       "      <td>69.05</td>\n",
       "      <td>15.1</td>\n",
       "      <td>41.3</td>\n",
       "      <td>20</td>\n",
       "      <td>50708</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>AL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>365</td>\n",
       "      <td>5315</td>\n",
       "      <td>1.5</td>\n",
       "      <td>69.31</td>\n",
       "      <td>11.3</td>\n",
       "      <td>66.7</td>\n",
       "      <td>162</td>\n",
       "      <td>566432</td>\n",
       "      <td>Alaska</td>\n",
       "      <td>Far West</td>\n",
       "      <td>AK</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2212</td>\n",
       "      <td>4530</td>\n",
       "      <td>1.8</td>\n",
       "      <td>70.55</td>\n",
       "      <td>7.8</td>\n",
       "      <td>58.1</td>\n",
       "      <td>15</td>\n",
       "      <td>113417</td>\n",
       "      <td>Arizona</td>\n",
       "      <td>Southwest</td>\n",
       "      <td>AZ</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2110</td>\n",
       "      <td>3378</td>\n",
       "      <td>1.9</td>\n",
       "      <td>70.66</td>\n",
       "      <td>10.1</td>\n",
       "      <td>39.9</td>\n",
       "      <td>65</td>\n",
       "      <td>51945</td>\n",
       "      <td>Arkansas</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>AR</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>21198</td>\n",
       "      <td>5114</td>\n",
       "      <td>1.1</td>\n",
       "      <td>71.71</td>\n",
       "      <td>10.3</td>\n",
       "      <td>62.6</td>\n",
       "      <td>20</td>\n",
       "      <td>156361</td>\n",
       "      <td>California</td>\n",
       "      <td>Far West</td>\n",
       "      <td>CA</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Population  Income  Illiteracy  Life_Exp  Murder  HS_Grad  Frost    Area  \\\n",
       "0        3615    3624         2.1     69.05    15.1     41.3     20   50708   \n",
       "1         365    5315         1.5     69.31    11.3     66.7    162  566432   \n",
       "2        2212    4530         1.8     70.55     7.8     58.1     15  113417   \n",
       "3        2110    3378         1.9     70.66    10.1     39.9     65   51945   \n",
       "4       21198    5114         1.1     71.71    10.3     62.6     20  156361   \n",
       "\n",
       "   State_name     Region State_Abbr  \n",
       "0     Alabama  Southeast         AL  \n",
       "1      Alaska   Far West         AK  \n",
       "2     Arizona  Southwest         AZ  \n",
       "3    Arkansas  Southeast         AR  \n",
       "4  California   Far West         CA  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "statedata.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "Определим, в каком регионе США самый высокий средний показатель выпускников средней школы из всех штатов:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>Population</th>\n",
       "      <th>Income</th>\n",
       "      <th>Illiteracy</th>\n",
       "      <th>Life_Exp</th>\n",
       "      <th>Murder</th>\n",
       "      <th>HS_Grad</th>\n",
       "      <th>Frost</th>\n",
       "      <th>Area</th>\n",
       "      <th>State_name</th>\n",
       "      <th>Region</th>\n",
       "      <th>State_Abbr</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>1203</td>\n",
       "      <td>4022</td>\n",
       "      <td>0.6</td>\n",
       "      <td>72.9</td>\n",
       "      <td>4.5</td>\n",
       "      <td>67.3</td>\n",
       "      <td>137</td>\n",
       "      <td>82096</td>\n",
       "      <td>Utah</td>\n",
       "      <td>Rocky Mountain</td>\n",
       "      <td>UT</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Population  Income  Illiteracy  Life_Exp  Murder  HS_Grad  Frost   Area  \\\n",
       "43        1203    4022         0.6      72.9     4.5     67.3    137  82096   \n",
       "\n",
       "   State_name          Region State_Abbr  \n",
       "43       Utah  Rocky Mountain         UT  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "statedata[statedata[\"HS_Grad\"] == statedata[\"HS_Grad\"].max()]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Теперь составим диаграмму уровня убийств по штатам и найдем в каком штате самый высокий средний уровень убийств."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# cтроим диаграмму размаха\n",
    "bplot = plt.boxplot(statedata[\"Murder\"],\n",
    "                   patch_artist=True)  # fill with color\n",
    "# подписываем ось X\n",
    "#plt.xlabel(\"Р\")\n",
    "# подписываем ось Y\n",
    "plt.ylabel(\"Убийства\")\n",
    "# задаём заголовок графика\n",
    "plt.title(\"ящик с усами\")\n",
    "# показываем график\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Создадим подмножество Юго-восточного региона."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Population</th>\n",
       "      <th>Income</th>\n",
       "      <th>Illiteracy</th>\n",
       "      <th>Life_Exp</th>\n",
       "      <th>Murder</th>\n",
       "      <th>HS_Grad</th>\n",
       "      <th>Frost</th>\n",
       "      <th>Area</th>\n",
       "      <th>State_name</th>\n",
       "      <th>Region</th>\n",
       "      <th>State_Abbr</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3615</td>\n",
       "      <td>3624</td>\n",
       "      <td>2.1</td>\n",
       "      <td>69.05</td>\n",
       "      <td>15.1</td>\n",
       "      <td>41.3</td>\n",
       "      <td>20</td>\n",
       "      <td>50708</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>AL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2110</td>\n",
       "      <td>3378</td>\n",
       "      <td>1.9</td>\n",
       "      <td>70.66</td>\n",
       "      <td>10.1</td>\n",
       "      <td>39.9</td>\n",
       "      <td>65</td>\n",
       "      <td>51945</td>\n",
       "      <td>Arkansas</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>AR</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>8277</td>\n",
       "      <td>4815</td>\n",
       "      <td>1.3</td>\n",
       "      <td>70.66</td>\n",
       "      <td>10.7</td>\n",
       "      <td>52.6</td>\n",
       "      <td>11</td>\n",
       "      <td>54090</td>\n",
       "      <td>Florida</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>FL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>4931</td>\n",
       "      <td>4091</td>\n",
       "      <td>2.0</td>\n",
       "      <td>68.54</td>\n",
       "      <td>13.9</td>\n",
       "      <td>40.6</td>\n",
       "      <td>60</td>\n",
       "      <td>58073</td>\n",
       "      <td>Georgia</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>GA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>3387</td>\n",
       "      <td>3712</td>\n",
       "      <td>1.6</td>\n",
       "      <td>70.10</td>\n",
       "      <td>10.6</td>\n",
       "      <td>38.5</td>\n",
       "      <td>95</td>\n",
       "      <td>39650</td>\n",
       "      <td>Kentucky</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>KY</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>3806</td>\n",
       "      <td>3545</td>\n",
       "      <td>2.8</td>\n",
       "      <td>68.76</td>\n",
       "      <td>13.2</td>\n",
       "      <td>42.2</td>\n",
       "      <td>12</td>\n",
       "      <td>44930</td>\n",
       "      <td>Louisiana</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>LA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>2341</td>\n",
       "      <td>3098</td>\n",
       "      <td>2.4</td>\n",
       "      <td>68.09</td>\n",
       "      <td>12.5</td>\n",
       "      <td>41.0</td>\n",
       "      <td>50</td>\n",
       "      <td>47296</td>\n",
       "      <td>Mississippi</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>MS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>5441</td>\n",
       "      <td>3875</td>\n",
       "      <td>1.8</td>\n",
       "      <td>69.21</td>\n",
       "      <td>11.1</td>\n",
       "      <td>38.5</td>\n",
       "      <td>80</td>\n",
       "      <td>48798</td>\n",
       "      <td>North Carolina</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>NC</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>2816</td>\n",
       "      <td>3635</td>\n",
       "      <td>2.3</td>\n",
       "      <td>67.96</td>\n",
       "      <td>11.6</td>\n",
       "      <td>37.8</td>\n",
       "      <td>65</td>\n",
       "      <td>30225</td>\n",
       "      <td>South Carolina</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>SC</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41</th>\n",
       "      <td>4173</td>\n",
       "      <td>3821</td>\n",
       "      <td>1.7</td>\n",
       "      <td>70.11</td>\n",
       "      <td>11.0</td>\n",
       "      <td>41.8</td>\n",
       "      <td>70</td>\n",
       "      <td>41328</td>\n",
       "      <td>Tennessee</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>TN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>4981</td>\n",
       "      <td>4701</td>\n",
       "      <td>1.4</td>\n",
       "      <td>70.08</td>\n",
       "      <td>9.5</td>\n",
       "      <td>47.8</td>\n",
       "      <td>85</td>\n",
       "      <td>39780</td>\n",
       "      <td>Virginia</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>VA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>1799</td>\n",
       "      <td>3617</td>\n",
       "      <td>1.4</td>\n",
       "      <td>69.48</td>\n",
       "      <td>6.7</td>\n",
       "      <td>41.6</td>\n",
       "      <td>100</td>\n",
       "      <td>24070</td>\n",
       "      <td>West Virginia</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>WV</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Population  Income  Illiteracy  Life_Exp  Murder  HS_Grad  Frost   Area  \\\n",
       "0         3615    3624         2.1     69.05    15.1     41.3     20  50708   \n",
       "3         2110    3378         1.9     70.66    10.1     39.9     65  51945   \n",
       "8         8277    4815         1.3     70.66    10.7     52.6     11  54090   \n",
       "9         4931    4091         2.0     68.54    13.9     40.6     60  58073   \n",
       "16        3387    3712         1.6     70.10    10.6     38.5     95  39650   \n",
       "17        3806    3545         2.8     68.76    13.2     42.2     12  44930   \n",
       "23        2341    3098         2.4     68.09    12.5     41.0     50  47296   \n",
       "32        5441    3875         1.8     69.21    11.1     38.5     80  48798   \n",
       "39        2816    3635         2.3     67.96    11.6     37.8     65  30225   \n",
       "41        4173    3821         1.7     70.11    11.0     41.8     70  41328   \n",
       "45        4981    4701         1.4     70.08     9.5     47.8     85  39780   \n",
       "47        1799    3617         1.4     69.48     6.7     41.6    100  24070   \n",
       "\n",
       "        State_name     Region State_Abbr  \n",
       "0          Alabama  Southeast         AL  \n",
       "3         Arkansas  Southeast         AR  \n",
       "8          Florida  Southeast         FL  \n",
       "9          Georgia  Southeast         GA  \n",
       "16        Kentucky  Southeast         KY  \n",
       "17       Louisiana  Southeast         LA  \n",
       "23     Mississippi  Southeast         MS  \n",
       "32  North Carolina  Southeast         NC  \n",
       "39  South Carolina  Southeast         SC  \n",
       "41       Tennessee  Southeast         TN  \n",
       "45        Virginia  Southeast         VA  \n",
       "47   West Virginia  Southeast         WV  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Southeast = statedata[statedata[\"Region\"] == 'Southeast']\n",
    "Southeast"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Получим оценку статистики параметров по этому региону"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Population</th>\n",
       "      <td>12.0</td>\n",
       "      <td>3973.083333</td>\n",
       "      <td>1792.708335</td>\n",
       "      <td>1799.00</td>\n",
       "      <td>2697.250</td>\n",
       "      <td>3710.500</td>\n",
       "      <td>4943.5000</td>\n",
       "      <td>8277.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Income</th>\n",
       "      <td>12.0</td>\n",
       "      <td>3826.000000</td>\n",
       "      <td>500.908992</td>\n",
       "      <td>3098.00</td>\n",
       "      <td>3599.000</td>\n",
       "      <td>3673.500</td>\n",
       "      <td>3929.0000</td>\n",
       "      <td>4815.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Illiteracy</th>\n",
       "      <td>12.0</td>\n",
       "      <td>1.891667</td>\n",
       "      <td>0.454189</td>\n",
       "      <td>1.30</td>\n",
       "      <td>1.550</td>\n",
       "      <td>1.850</td>\n",
       "      <td>2.1500</td>\n",
       "      <td>2.80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Life_Exp</th>\n",
       "      <td>12.0</td>\n",
       "      <td>69.391667</td>\n",
       "      <td>0.940733</td>\n",
       "      <td>67.96</td>\n",
       "      <td>68.705</td>\n",
       "      <td>69.345</td>\n",
       "      <td>70.1025</td>\n",
       "      <td>70.66</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Murder</th>\n",
       "      <td>12.0</td>\n",
       "      <td>11.333333</td>\n",
       "      <td>2.198071</td>\n",
       "      <td>6.70</td>\n",
       "      <td>10.475</td>\n",
       "      <td>11.050</td>\n",
       "      <td>12.6750</td>\n",
       "      <td>15.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>HS_Grad</th>\n",
       "      <td>12.0</td>\n",
       "      <td>41.966667</td>\n",
       "      <td>4.223599</td>\n",
       "      <td>37.80</td>\n",
       "      <td>39.550</td>\n",
       "      <td>41.150</td>\n",
       "      <td>41.9000</td>\n",
       "      <td>52.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Frost</th>\n",
       "      <td>12.0</td>\n",
       "      <td>59.416667</td>\n",
       "      <td>30.749600</td>\n",
       "      <td>11.00</td>\n",
       "      <td>42.500</td>\n",
       "      <td>65.000</td>\n",
       "      <td>81.2500</td>\n",
       "      <td>100.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Area</th>\n",
       "      <td>12.0</td>\n",
       "      <td>44241.083333</td>\n",
       "      <td>9875.845616</td>\n",
       "      <td>24070.00</td>\n",
       "      <td>39747.500</td>\n",
       "      <td>46113.000</td>\n",
       "      <td>51017.2500</td>\n",
       "      <td>58073.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            count          mean          std       min        25%        50%  \\\n",
       "Population   12.0   3973.083333  1792.708335   1799.00   2697.250   3710.500   \n",
       "Income       12.0   3826.000000   500.908992   3098.00   3599.000   3673.500   \n",
       "Illiteracy   12.0      1.891667     0.454189      1.30      1.550      1.850   \n",
       "Life_Exp     12.0     69.391667     0.940733     67.96     68.705     69.345   \n",
       "Murder       12.0     11.333333     2.198071      6.70     10.475     11.050   \n",
       "HS_Grad      12.0     41.966667     4.223599     37.80     39.550     41.150   \n",
       "Frost        12.0     59.416667    30.749600     11.00     42.500     65.000   \n",
       "Area         12.0  44241.083333  9875.845616  24070.00  39747.500  46113.000   \n",
       "\n",
       "                   75%       max  \n",
       "Population   4943.5000   8277.00  \n",
       "Income       3929.0000   4815.00  \n",
       "Illiteracy      2.1500      2.80  \n",
       "Life_Exp       70.1025     70.66  \n",
       "Murder         12.6750     15.10  \n",
       "HS_Grad        41.9000     52.60  \n",
       "Frost          81.2500    100.00  \n",
       "Area        51017.2500  58073.00  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Southeast.describe().transpose()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Найдем штат с максимальным уровнем убийств"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Population</th>\n",
       "      <th>Income</th>\n",
       "      <th>Illiteracy</th>\n",
       "      <th>Life_Exp</th>\n",
       "      <th>Murder</th>\n",
       "      <th>HS_Grad</th>\n",
       "      <th>Frost</th>\n",
       "      <th>Area</th>\n",
       "      <th>State_name</th>\n",
       "      <th>Region</th>\n",
       "      <th>State_Abbr</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3615</td>\n",
       "      <td>3624</td>\n",
       "      <td>2.1</td>\n",
       "      <td>69.05</td>\n",
       "      <td>15.1</td>\n",
       "      <td>41.3</td>\n",
       "      <td>20</td>\n",
       "      <td>50708</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Southeast</td>\n",
       "      <td>AL</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Population  Income  Illiteracy  Life_Exp  Murder  HS_Grad  Frost   Area  \\\n",
       "0        3615    3624         2.1     69.05    15.1     41.3     20  50708   \n",
       "\n",
       "  State_name     Region State_Abbr  \n",
       "0    Alabama  Southeast         AL  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Southeast[Southeast[\"Murder\"] == Southeast[\"Murder\"].max()]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Прогнозирование ожидаемой продолжительности жизни - Начальная модель\n",
    "\n",
    "Построим модель для прогнозирования ожидаемой продолжительности жизни по штатам, используя статистику, имеющуюся в нашем наборе данных.\n",
    "Построим нашу первоначальную модель по потенциальным переменным ( доход, неграмотность, количество убийств, грамотность, мороз )."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "LESubset = statedata[['Income', 'Murder', 'HS_Grad', 'Frost', 'Life_Exp']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Income</th>\n",
       "      <th>Murder</th>\n",
       "      <th>HS_Grad</th>\n",
       "      <th>Frost</th>\n",
       "      <th>Life_Exp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3624</td>\n",
       "      <td>15.1</td>\n",
       "      <td>41.3</td>\n",
       "      <td>20</td>\n",
       "      <td>69.05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5315</td>\n",
       "      <td>11.3</td>\n",
       "      <td>66.7</td>\n",
       "      <td>162</td>\n",
       "      <td>69.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4530</td>\n",
       "      <td>7.8</td>\n",
       "      <td>58.1</td>\n",
       "      <td>15</td>\n",
       "      <td>70.55</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3378</td>\n",
       "      <td>10.1</td>\n",
       "      <td>39.9</td>\n",
       "      <td>65</td>\n",
       "      <td>70.66</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5114</td>\n",
       "      <td>10.3</td>\n",
       "      <td>62.6</td>\n",
       "      <td>20</td>\n",
       "      <td>71.71</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Income  Murder  HS_Grad  Frost  Life_Exp\n",
       "0    3624    15.1     41.3     20     69.05\n",
       "1    5315    11.3     66.7    162     69.31\n",
       "2    4530     7.8     58.1     15     70.55\n",
       "3    3378    10.1     39.9     65     70.66\n",
       "4    5114    10.3     62.6     20     71.71"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "LESubset.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Соберем данные по группам - отфильтруем"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "X1 = LESubset['Income'].values\n",
    "X2 = LESubset['Murder'].values\n",
    "X3 = LESubset['HS_Grad'].values\n",
    "X4 = LESubset['Frost'].values\n",
    "y = LESubset.iloc[:, -1].values\n",
    "datasets = {'I': (X1, y),'M': (X2, y),'G': (X3, y),'F': (X4, y) }"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Построим точеченые графики и линии регрессии"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x600 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axs = plt.subplots(2, 2, figsize=(6, 6), gridspec_kw={'wspace': 0.25, 'hspace': 0.25})\n",
    "for ax,(label, (x, y)) in zip(axs.flat, datasets.items()):\n",
    "    ax.text(0.1, 0.9, label, fontsize=20, transform=ax.transAxes, va='bottom')\n",
    "    ax.tick_params(direction='in', top=True, right=True)\n",
    "    ax.plot(x, y, 'o')\n",
    "    # linear regression\n",
    "    p1, p0 = np.polyfit(x, y, deg=1)  # наклон, пересечение\n",
    "    ax.axline(xy1=(0, p0), slope=p1, color='r', lw=2)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "What is the interpretation of the coefficient x? x = -2.1804237825283393e-05\n",
    "{For a one unit increase in income, predicted life expectancy decreases by |x|}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To verify this we plot a graph of life expectancy vs. income.\n",
    "\n",
    "Visually observing the plot, Life expectancy is somewhat positively correlated with income."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "66.57559032984935 0.0009744575547240868\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#sns.regplot(x='Life.Exp', y='Income', data = LESubset)\n",
    "plt.plot(X1,y, 'x')\n",
    "# linear regression\n",
    "p1, p0 = np.polynomial.Polynomial.fit(X1,y, deg=1).convert().coef  # наклон, пересечение\n",
    "plt.axline(xy1=(0, p1), slope=p0, color='r', lw=2)\n",
    "# coefficients of the variables of the polynomial\n",
    "coefficient=np.polyfit(X1,y,deg=2)\n",
    "# complete polynomial\n",
    "polynomial=np.poly1d(coefficient)\n",
    "print(p1,p0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "В виде уравнения P1 - пересечение с Y, P0 - наклон к X. \n",
    "\n",
    "Y= P0 * X + P1\n",
    "\n",
    "The model we built does not display the relationship we saw from the plot of life expectancy vs. income. This is due to Multicollinearity."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "jp-MarkdownHeadingCollapsed": true
   },
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}