Statistical Thinking in Python (Part 2).ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "prostate-arizona",
   "metadata": {
    "id": "bA5ajAmk7XH6"
   },
   "source": [
    "# Statistical Thinking in Python (Part 2)\n",
    "\n",
    "👋 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2e25fdd8-4d84-45bc-80f0-949917e00a17",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing course packages; you can add more too!\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from empiricaldist import Cdf\n",
    "\n",
    "# Importing course datasets as DataFrames\n",
    "anscombe = pd.read_csv('datasets/anscombe.csv', header=[0,1])\n",
    "bees = pd.read_csv('datasets/bee_sperm.csv', comment='#')\n",
    "literacy_fertility = pd.read_csv('datasets/female_literacy_fertility.csv')\n",
    "beaks_1975 = pd.read_csv('datasets/finch_beaks_1975.csv')\n",
    "beaks_2012 = pd.read_csv('datasets/finch_beaks_2012.csv')\n",
    "frogs = pd.read_csv('datasets/frog_tongue.csv', comment='#')\n",
    "mlb = pd.read_csv('datasets/mlb_nohitters.csv')\n",
    "weather = pd.read_csv('datasets/sheffield_weather_station.csv', comment='#', delimiter='\\s+', na_values='---')\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "0b514d91-3ffa-44d2-bbfc-2666934422f2",
   "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>Country</th>\n",
       "      <th>Continent</th>\n",
       "      <th>female literacy</th>\n",
       "      <th>fertility</th>\n",
       "      <th>population</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Chine</td>\n",
       "      <td>ASI</td>\n",
       "      <td>90.5</td>\n",
       "      <td>1.769</td>\n",
       "      <td>1,324,655,000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Inde</td>\n",
       "      <td>ASI</td>\n",
       "      <td>50.8</td>\n",
       "      <td>2.682</td>\n",
       "      <td>1,139,964,932</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>USA</td>\n",
       "      <td>NAM</td>\n",
       "      <td>99.0</td>\n",
       "      <td>2.077</td>\n",
       "      <td>304,060,000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Indonésie</td>\n",
       "      <td>ASI</td>\n",
       "      <td>88.8</td>\n",
       "      <td>2.132</td>\n",
       "      <td>227,345,082</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Brésil</td>\n",
       "      <td>LAT</td>\n",
       "      <td>90.2</td>\n",
       "      <td>1.827</td>\n",
       "      <td>191,971,506</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>157</th>\n",
       "      <td>Vanuatu</td>\n",
       "      <td>OCE</td>\n",
       "      <td>79.5</td>\n",
       "      <td>3.883</td>\n",
       "      <td>233,866</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>158</th>\n",
       "      <td>Samoa</td>\n",
       "      <td>OCE</td>\n",
       "      <td>98.5</td>\n",
       "      <td>3.852</td>\n",
       "      <td>178,869</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>159</th>\n",
       "      <td>Sao Tomé-et-Principe</td>\n",
       "      <td>AF</td>\n",
       "      <td>83.3</td>\n",
       "      <td>3.718</td>\n",
       "      <td>160,174</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>160</th>\n",
       "      <td>Aruba</td>\n",
       "      <td>LAT</td>\n",
       "      <td>98.0</td>\n",
       "      <td>1.732</td>\n",
       "      <td>105,455</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>161</th>\n",
       "      <td>Tonga</td>\n",
       "      <td>ASI</td>\n",
       "      <td>99.1</td>\n",
       "      <td>3.928</td>\n",
       "      <td>103,566</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>162 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                 Country  Continent  female literacy  fertility     population\n",
       "0                   Chine       ASI             90.5      1.769  1,324,655,000\n",
       "1                    Inde       ASI             50.8      2.682  1,139,964,932\n",
       "2                     USA       NAM             99.0      2.077    304,060,000\n",
       "3               Indonésie       ASI             88.8      2.132    227,345,082\n",
       "4                  Brésil       LAT             90.2      1.827    191,971,506\n",
       "..                    ...       ...              ...        ...            ...\n",
       "157               Vanuatu       OCE             79.5      3.883        233,866\n",
       "158                 Samoa       OCE             98.5      3.852        178,869\n",
       "159  Sao Tomé-et-Principe        AF             83.3      3.718        160,174\n",
       "160                 Aruba       LAT             98.0      1.732        105,455\n",
       "161                 Tonga       ASI             99.1      3.928        103,566\n",
       "\n",
       "[162 rows x 5 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "literacy_fertility"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "5a1f17ca",
   "metadata": {},
   "outputs": [],
   "source": [
    "literacy_fertility['female literacy'] = (literacy_fertility['female literacy'] - 100) * -1\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e19bfde0",
   "metadata": {},
   "outputs": [],
   "source": [
    "literacy_fertility.rename(columns={'female literacy':'illiteracy'}, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "3dd967fe-5c9d-493c-b953-93354fd5ef7e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.scatterplot(x= 'illiteracy', y= 'fertility', data=literacy_fertility);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f28fe25d-69fa-45f8-b791-8b3f59f6cdc3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(literacy_fertility.corr(), annot=True, cmap='seismic');\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3fb6f7dc",
   "metadata": {},
   "source": [
    "## Linear Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e006551d-cbf7-475a-a524-edb002a2c4fc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope = 0.04979854809063423 children per woman / percent illiterate\n",
      "intercept = 1.888050610636557 children per woman\n"
     ]
    }
   ],
   "source": [
    "# Perform a linear regression using np.polyfit()\n",
    "slope , intercept =  np.polyfit(literacy_fertility['illiteracy'], literacy_fertility['fertility'],1)\n",
    "\n",
    "# Print the results to the screen\n",
    "print('slope =', slope, 'children per woman / percent illiterate')\n",
    "print('intercept =', intercept, 'children per woman')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "060d8863-fc8b-4f99-8132-ea1ba151d1b4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(0.04979854809063423, 1.888050610636557)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "slope , intercept"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "7de236f4-2cbe-408f-b6a1-a663d946ccfe",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Make theoretical line to plot\n",
    "x = np.array([0,100])\n",
    "y = slope * x +  intercept"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "1cb950f0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXsAAAEGCAYAAACEgjUUAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAAA4/ElEQVR4nO3deXyU1dn4/8+ZrCQkbIGwhCREQlhlCxYVUUEF97rivtSWb2sVl7q0fez3+bX28fkKioI7brXWtS61LmWRHQQxqCAKISEkIRCSECD7OnN+f8xMSMJMMknmnrln5nq/XrxIJjP3nHsmue4z51znOkprjRBCiOBm8XcDhBBCGE+CvRBChAAJ9kIIEQIk2AshRAiQYC+EECEg3N8NaC0hIUGnpqb6uxlCCBEwtm/ffkRrPbCz+5kq2KemppKVleXvZgghRMBQShV4cj9TBXshhPAmm02TX15DSWU9ifHRpA6IxWJR/m6WX0iwF0IEJZtNs/zHw9z//vfUN9mIjrCw+NpJzB03OCQDvmETtEqpDKXU963+VSql7jXq+YQQorX88pqWQA9Q32Tj/ve/J7+8xs8t8w/DevZa62xgEoBSKgw4CHxs1PMJIURrJZX1LYHeqb7JRmlVPWkDe/upVf7jq9TL2cA+rbVHEwlCCNFTifHRREe0DXHRERYGxUX7qUX+5atgfx3wjqsfKKXmK6WylFJZZWVlPmqOECLYpQ6IZfG1k1oCvnPMPnVArJ9b5h/K6KqXSqlI4BAwTmtd0tF9MzMztaReCiG8xZmNU1pVz6C44MzGUUpt11pndnY/X2TjXAh821mgF0IIb7NYFGkDe4fkGH17vhjGuR43QzhCCCE6t+tgBd8WHuvRMQwN9kqpGOB84CMjn0cIIYJRXlk1v337Wy55ZhOLlmf36FiGDuNorWuBAUY+hxBCBJviijqWrs7h/awiosItLJg1kl/OTOvRMWUFrRBCmMSxmkZeXL+Pv32Vj01rbp6ewm/PHcnAuKgeH1uCvRBC+FlNQzOvb97PS+vzqG5s5orJw7jvvFEM7x/jteeQYC+EEH7S2GzjnW2FPLMmlyPVDZw/NpEHLsggY3Cc159Lgr0QQviY1ab5946DLF61lwNH6/jZiP68dPNUpqb0M+w5JdgLIYSPaK1ZvbuURSuyyS6pYtzQeN74xQRmpieglLGLvSTYCyGED3ydV87CFdlsLzjGiIRYnrl+MhdPGOKzFb0S7IUQwkA/Hqpg0Yps1mWXkRgfxf9eOYGrpyYREebbLcAl2AshhAHyj9Tw5Kq9fLrjEH16RfCHC0dz6xmpREeE+aU9EuyFECHLiG0LSyrrWbo6h/e+OUBEmIW7zh3Jr2am0adXhJda3T0S7IUQIcnb2xZW1Dbxwvp9/O2r/Vhtmht+lsxds0aapn6+BHshREhyt23h6AVndalKZm1jM69vzufF9fuobmjm55PsC6KSB3hvQZQ3SLAXQoSknm5b2Nhs471vClm6JpeyqgbOGzOIB+ZkMHpwvFFN7hEJ9kKIkOTctrB1wPdk20KbTfPpzkM8uXIvhUdrOS21Py/cOIXM1P5GN7lHJNgLIUKSc9vC9mP27rYt1FqzNruUhcuz2XO4ijFD4nn99mmcM2qg4QuivEGCvRAiJFksirnjBjN6wVmdblv4Tf5RFi7fwzf5x0gZEMOS6yZx6alDA2qLQwn2QoiQ1dm2hbuLK1m0Ips1e0oZGBfFX38+nnnThvt8QZQ3SLAXXmFEvrIQ/lJYXsviVdl8suMQcVHhPDx3NLedkUqvSP8siPIGCfaix7ydryyEv5RW1vPMmlze2VZIeJji12efwq9nnkKfGP8uiPIGCfaix7yVryyEv1TUNfHS+n28vjmfJquN604bzoJZ6QyKN8eCKG+QYC96rKf5ykL4S12jlTe25PPCun1U1DVx+aSh3H/+KFLcZOQEMgn2ose6m68shL80WW28n3WAJV/mUFrVwKzRg3jgggzGDjXngihvkGAveqyr+cpC+IvNpvnsh2IWr8wmv7yWzJR+PHvDFE4bYe4FUd4gwV70WFfylYVwxehsLq016/aWsWh5Nj8VVzJ6cByv3ZbJuRmDAmJBlDdIsBde0Vm+shDuGJ3Ntb3gKI8vz2bb/qMM79+Lp+dN4rKJgbUgyhsk2Ash/MqobK49hyt5YkU2X+4uJaF3FI9ePo5505KJDA+8BVHeYGiwV0r1BV4BxgMa+IXWeouRzymECCzezuY6cLSWp1bt5ePvD9I7KpwH52Rw+5mpxESGdt/W6LNfAizXWl+tlIoEzFXgWQjhd97K5iqrauDZNTm8va0Qi1LMn5nGb84+hb4xkd5uckAyLNgrpeKBmcBtAFrrRqDRqOcTQgSmnmZzVdY3sWx9Hq9t3k9Ds4150+wLogb3kdTf1ozs2acBZcDrSqmJwHbgHq11Tes7KaXmA/MBkpOTDWyOCAVSoyfwdDebq77Jyt+35PP8un0cr23iklOH8LsLMhiRICm/riittTEHVioT2AqcqbX+Wim1BKjUWv/J3WMyMzN1VlaWIe0RwU9q9ISGZquNf24vYsmXORyurOfsUQN5cE4G44f18XfT/EIptV1rndnZ/Yzs2RcBRVrrrx3ffwD83sDnEyFOavQEN5tN859dh3lyZTZ5R2qYktyXp6+bxPS0Af5uWkAwLNhrrQ8rpQ4opTK01tnAbOAno55PCKnRE9jcDcFprdmYc4SFK/aw62AloxJ78/ItmZw3JnQWRHmD0dk4dwNvOTJx8oDbDX4+EcKkRk/gcjcENzg+mkUrstmSV05Sv14svnYil08aRpgMy3WZYWP23SFj9qInZMw+cOWVVXPR0o1tLtQWBTYNCb0juXtWOtedNpyo8MDdPMQoZhizF6JbuptRIzV6AperITibhmszk/jvS8cRGyWhqqfkFRSm0tPeudToCUyR4RbCLGBtFe+jwu07RUmg947QLBIhTMtdRk1+eU0njxSBqKq+icWr9nLLq9vQGsIc1/PoCAtPzZssZbK9SC6ZwlQko6b7AmlBWX2TlX9sLeC5tbkcq23i4glDuO+8dCwWJUNwBpFgL0ylOxk1gRTkjBIok9PNVhsfflvE01/mUFxRz1npCTw0ZzQTkk4siJKLujEk2AtT6WqdlEAJckYz+4IyrTXLdx1m0cps8spqmDi8L09eM5EzRib4u2khQ4K9MJWuZtSYPcj5ipmHvzY5FkTtLKpg5KDevHTzVC4YmygLonxMgr0wna5k1Jg5yPmSGReU7ThwnIUr9rA5t5xhfXux6OpTuXJKkiyI8hMJ9sKrfD1+bsYg5w9m2vQ9t7SKJ1bsZfmPh+kfG8n/vWQsN05PlgVRfibBXniNP8bPzRTk/MkMC8oOHq/j6VV7+fDbImIiw7nvvFHccdYIekuevClIuQThNc4l7/1iIrlyShJK2fOmr5g8jNQE44ZUnJ8mJGXPP8qrG3h+3T7e3FIAwM2np3DnOacwoHeUn1sWGqRcgvC5ksp6+sVEcvP0FJauyWnpaacMiCW5v3EBWFbN+kd1QzOvbMzjlY37qW1s5uqpSdxz3iiG9e3l76YJFyTYC69JjI/mmsyklkAP9snSP378A5OG95VgHCQamq38Y0sBS9fkUlHXxMz0BB65eCyjBsf5rA2ytqLrJNgLr0kdEMuoQXGSHROkrDbNR98W8dSXezl0vB5nbN2Wf5TcsmpGDurtk4Arayu6R4K98BqLRTFuaDwLZo/E5pgK+nB7EcdqG0MuOyaYaK1Z8WMJT67MJqe0mozEOCLCGmiy2t/k1msbUgfEGt7jlrUV3SPBXniNzabZfbiKZRvyWnpc98xOJz2xd8hlxwSLr3KP8PiKbHYcOM4pA2N58aYpxEeHc8Mr29rcr77JRkllPXsOVxne45a1Fd0jVS89ZLNp8sqq2bLvCHll1dhs5sliMgtXPa4lq3MYMcA3H++F9+wsOs7Nr37NDa98TVllPQuvOpUV985k7vghDO7Ti+iItqEjOsJCTGSYTyqWOtdWtH9++fTYMQn2HnCOEV60dCPXv/w1Fy3dyPIfD0vAb8ddj6usut5PLRJdta+smjvf2s5lz25m18EKHrl4DGseOIdrpw0nPMweLpxrG5wB19mDb7Ta3Pa4vcnd88unx47JMI4HZIzQM7KaNXAVV9Sx5Msc/rm9iOhw+/DbL88aQVx0xEn3dbeAK7+8xicVS82wgCwQSbD3gIwReiYUVrMGW8rfsZpGnl+XyxtbCkDDLaen8NtzR5LQyYIoV2sbfFmxVNZWdJ0Eew9Ij9Uzwd7jCqaUv5qGZl7dtJ+XN+RR09jMlVOSuPe8dJL6xXT4uI4udlKx1Nwk2HsgFHqs3hLMPa5gCE4NzVbe+bqQZ9fmcqS6kQvGJvLAnAxGJXa+IMqTi51ULDUvCfYeCPYeq/CMt4OTL4eErDbNv747yOJVezl4vI7paf1ZdstopiT38/gY3r7YySdm35Jg76Fg7rEKz3gzOPlqSEhrzaqfSnhiZTZ7S6oZPyye/71yAmelJ3R58xBvX+zkE7NvSbAXwkPeDE6+GBLamlfO48v38F3hcdISYnnuhilcOL77FxNv98TlE7NvGRrslVL5QBVgBZo9KcMphC/4O+XPyPHqXQcrWLgimw17yxgcH83/u3ICV09NasmT7y4jeuLyidl3fNGzP1drfcQHzyOER8yQ8mfEePX+IzU8uTKbz3YW0zcmgv+6aAw3n55CdIR9h6iezhFITzywyTCOCDlmyKrxtJfsSYA+XFHPktU5vJ91gKhwC3fPGsmvZqYR32pBlLfmCKQnHriMDvYaWKmU0sBLWutl7e+glJoPzAdITk42uDlCmCPlz5NecmcB+nhtIy+s38ffNudj05qbp9sXRA2MO3lBlBkucMK/jA72Z2qtDymlBgGrlFJ7tNYbWt/BcQFYBvZtCQ1ujxCmSfnrrJfsLkCn/OYM1mWX8eL6fVQ3NHPF5GHcd94ohvd3vyDK3QWuIIhWA4uOGRrstdaHHP+XKqU+Bk4DNnT8qNAQbMvuA0mgpPy5C9A3vPw1FXVNnDcmkQfnZJDhwQ5R7i5w3x04ztLVuQG9Glh4xrBgr5SKBSxa6yrH1xcAfzHq+QJJMC27D0SBMtHoKkADpAyI4b8vHcfUFM8XRLm6wN0zO52/OzYJl2Gd4Gdkzz4R+NixcCMceFtrvdzA5wsYMn7qf4Ew0ZjSP4bbzxjBi+v3oQEF3HnuKdx/3ijCuphG2f4Cp1Dc+973FFecKD8spQqCm2HBXmudB0w06viBzAwThMLctu0/yuPL97C94BjD+vbiqqnDuGziUNISur8RTOsLXF5ZNcdqG9v8XEoVBDdJvfQDs0wQCvP58VAFT6zIZm12GYnxUTx2xQSuyUwioocLotoLlHkL4T0S7P1A/tBEe/lHali8ai//3nGIPr0i+P2Fo7n19FR6RYYZ8nyBMm8hvEdpbZ5sx8zMTJ2VleXvZviEMxtH/tBCW0llPUtX5/DeNweICLPwixmp/GpGGkdrGyVTS3hEKbXdk1I00rP3k0CYIBTGqaht4sUN+3h9836arZrrT0vm7ln2HaIkU0sYQYK9MIysJThZXaOV17/az4vr9lHV0MzlE4dy3/mjSHEM4eWVVUumljCEBHthCFlL0FaT1ca73xzgmdU5lFY1MHv0IB6Yk8GYIfFt7ieZWsIoEuyFIWQtgZ3Npvl05yEWr9pLQXkt01L78fyNU8hM7e/y/pKpJYwiwV50W0fDNKHeQ9Vasy67jIUrstldXMnowXG8fts0zskY2OEOUZKpJYwiwV50S2fDNGbqofp67iAr/ygLl2ezLf8oyf1jWHLdJC4eP4TCY7VszSvvsA2SEimMIqmXolvyyqq5aOnGk4L5F45hGrOM2fuyHbuLK3liRTar95QyMC6KBbPTmZc5nHCLMsVrIYKTpF4KQ3U2TOOtHmpPe+W+mDsoLK9l8apsPtlxiLiocB6am8FtZ6QSE2n/85IMG2EGEuxFt3gyTNPTtQTe6JUbOXdQWlXPM6tzeWdbIeFhil+ffQq/nnkKfWIi2twv1OcvhDlIsBfd4ouJRG/0yr01d9D6E0ZsZDjLfzzM65vzabLamDdtOAtmp5MY7/qYZpq/EKGr02CvlPoQeA34j9ba1tn9RWjwxUSiN3rE3rgoOT9h3PfedzQ0n5jjuvTUIfzuggxSEzo+lmTYCDPwpGf/AnA7sFQp9U/gb1rrPcY2SwQCo0s+eKNH7I2LUm5pFQve/Y5m64lAHxmuuO/8UZ0Gem+1QYie6rRuqtb6S631jcAUIB/7XrJfKaVuV0pFdPxoIbrP2SOOjrD/mna3R+y8KE1PS2iZPPaEzab5dMchbnltW5tAD9DYrCmtqnfzSO+1QQhv8WjMXik1ALgJuBn4DngLmAHcCpxjVONEaPNXj1hrzfq9ZSxakc2PhyoZkRBLRFgjTa0Cvoy5i0DjyZj9R8Bo4E3gUq11seNH7ymlJCleGMrX1UG3Fxxj4fI9fL3/KMP79+KpeRO5ZMJQVu0ukTF3EdA86dm/orX+ovUNSqkorXWDJ4n8QniD0atgsw9XsWhFNl/uLiGhdxR/uXwc101LJjLcPoQkY+4i0HkS7P8KfNHuti3Yx/CFMJyRq2APHK3lqS/38vF3B+kdGc6DczK4/cwTC6KcZP8BEejcBnul1GBgGNBLKTUZ++b2APFAjA/aJgTg3VWwzk8I2YerWPlTCZ/tPIRFKebPTOM3Z59C35hII05BCL/rqGc/B7gNSAIWt7q9CvijgW0Sog1vrUC12TQff3eQhz7cgdVxuBkjE1h41akM7dfLm00WwnTcBnut9RvAG0qpq7TWH/qwTUK04Y18+/omK0+t2stLG/La3J5VcJT6ZqvX2iqEWXU0jHOT1vofQKpS6v72P9daL3bxMCG8ricrUJutNj7YXsTTX+ZwuPLkvHipUSNCRUfDOM6/JPkrEH43dkgcb9x+GrWNzST3j2VEQsfZMDab5j+7DvPkymzyjtQwObkvD83N4I8f/yA1akRI6mgY5yXH/3/2XXOE2fl6IxB3mTgj3JQp0FqzMecIC1fsYdfBSpL69eLRy8dxw2nJKKWIjgiTfHkRktxuXqKUWtrRA7XWCzx6AqXCgCzgoNb6ko7uK5uXmJs/NiTpbJOU1r4rPMbC5dlsySunf2wkVfVNNFl1m3aCPbtH8uVFsPB085KOauNs7+Sfp+4Bdnfh/sKEbDbNDwePu0yBzC+vMex5O8rEccopqWL+37O44vmv2FtSxV3njqSmoamlvEHrdkqNGhGqOsvG6RGlVBJwMfA/wEmTvF3h6+EDcYKzR7/ncKXPN+HoKBOn6FgtT3+Zw0ffFhETGc7954/iFzNG8EPRcZ5dm+vTdgphdh1l4zyttb5XKfUpcNJYj9b6Mg+O/zTwEBDXwfPMB+YDJCcnu7yPWfYzDVXORU2/PCvN55twuMrE+fNl4/j7lgLe/roQFNwxYwS/OWck/WPtC6JksxAhTtbRmP1UrfV2pdTZrn6utV7f4YGVugS4SGt9p1LqHOCB7o7Zd2XcNhj5+1PNln1HuP7lrxnSJ5qbp6ewdE0O9U02Ugb04tHLJxARpgxtl/P888urWZd9hA+3F1HXZOXaTPsOUUP79jrp/sHSOfD3ey/Mr8cbjmutnePyk7TWS9od/B6gw2APnAlcppS6CIgG4pVS/9Ba39RZo9pzN25bUF4T9L/8Zghczp5ycUU9b24t4I4ZafSJDmNgXDTz38wyvF2NVhtr9pTy3NpcjtU2cdGEwdx/fgYjB7m+0AfLZiFmeO9F8Oh08xLsNevbu62zB2mt/6C1TtJapwLXAWu6E+jhRLBpLTrCwncHjrP8x8PYbK4/nQQDd3VhjJwUba/1JiLFFfW8uimP0UP68IdWOetGtKvZauP9bw4w64l1/PXz3Ywf1od/33Umz9841W2gdwqGiVgzvPcieHQ0Zn89cAOQppT6d6sfxQHlRjesNVfjtgtmpfPm1gKO1TZ2qyBWoPBWXZiecNVTNrJdWmtW/HiYRSuy2VdWw8ThfXnimomcMTKhR8cNNGZ470Xw6GgF7VdAMZAAPNnq9ipgZ1eeRGu9DljXxba1cAabAbefxsbcI2gNb24toLjCnn4XzL/8ZplsdFXi14h2bc49wsLle9hRVMHIQb158aapzBmXiFKB1zPvKbO89yI4dDRmX6CUKgJqOpuM9QWLRTEwLopXNuYF/C9/VybdelIXxkjebteOA8dZuGIPm3PLGda3F4uuPpUrpyQRFoDDL95i1vdeBCa32Tgtd7AP4dysta4wujGdraANhgmr7pyD8+JgtslGb7Qrt7SaJ1dm859dh+kfG8ld547kxunJRIWHGdTqwGLW916Yh6fZOJ4E+/eB6cAqoGVmyNNyCV3hSbmEQP/lD/U0UqeDx+tY8uVePtheRK+IMH41M41fnpVG7yhPNk8TQjj1OPWylc8d/0wh0LeHC/VJt6M1jTy3Npc3txaAhtvPHMGd55zCgN5R/m6aEEGt02CvtX5DKdULSNZaZ/ugTUEtVCfdqhuaeXXjfl7emEdtYzNXTUni3vNHMayv7BAlhC90GuyVUpcCTwCRwAil1CTgLx6WSxDthNqkW0Ozlbe2FvLc2lzKaxqZO24wD8wZxchBbitoCCEM4Mkwzv8HnIYjdVJr/b1SaoSBbQpqwbK6szNWm+ajb+07RB08XscZpwzgobmjmTS8r7+bJkRI8iTYN2utK9rlOQfvklUfCPR5h45orVn5UwlPrMgmp7SaCcP68PhVpzIjPbQWRAlhNp4E+11KqRuAMKVUOrAA+4IrIdr4at8RFi7P5vsDx0kbGMsLN05h7vjBIbkgSgiz6ahcwpta65uBfcA4oAF4B1gBPOqb5olA8ENRBQtX7GFjzhGG9Inm8asmcNWUJMLDPCm9JITwhY569lOVUinAPOBc2pZMiAHqXT5KhExZ2n1l1SxeuZfPfyimX0wEj1w8hpumpxAdIQuihDCbjoL9i8ByIA37HrJOCvuYfZqB7QpYwbDKtzPFFXUsXZ3D+1lFRIVbWDA7nV+dNYK46AiPHh8qF0MhzMSTFbQvaK1/44vG9GTDcbMEkH2l1Vz8THCukD1W08gL6/fxt6/yQcON05P57bkjSejCgqhQuBgK4UteW0Hrq0Dfkc4Cua8CiCft2F3s+31ajVbT0Mxrm/azbEMeNY3NXDE5iXvPS2d4/5guH8tdjfZgLlMthBmYvhCJJ4HcFwHE03bklFYFzQrZhmYr73xdyLNrczlS3cgFYxN5YE4GoxK7vyAq1MtFCOEvpg/2ngRyXwQQV+14fPluhvWNprbRSmJ8NOU1DbyfVcSCWekt+7RGR1h47IoJAbVC1mrTfPL9QRav2kvRsTqmp/Vn2S2jmZLcr8fHDtVyEUL4m+mDvSeB3F0AGdg7mryyaq+M47dvx5A+0czLTGbesq0tQf3xq04lMly17NOqFFgUTEnuGxDj0VprvtxdyqIVe9hbUs34YfE8dsUEzkpP8FqufKiVixDCLEwf7D3pCboLIPvLq7nr7e+8Mo7fvh1XTklq6b2D/QL08Ic7WXZzJvPfzOK5tbktz5ncv20gM8tkcmtb88pZuHwP3xYeZ0RCLM/eMJmLxg/xertCpVyEEGbTaTaOL7nKxvF08rV9nXuLgrlLvJcV074dC2aPZOnq3JPu986vfkZifLTbQNbcbOPzXcU8/OFOU2Sj7DpYwaIV2azfW0ZifBT3njeKq6cmESELooQICN6sZ+9XnvYE29eb2bLviFfH8du3o1dEOMs2nLxFYmJ8tNu6Nzab5qu88pZA72xTTyaTu/spYf+RGp5cmc1nO4vp0yuCP140mltOT5UFUUIEKdMHe+he4TAjJgJbt8Nm010ee84vryGr4KjXLkLdSTktqaxnyeoc3vvmAJFhFu46dyS/mplGn16eLYgSQgSmgAj23WH0RGB3xp5LKuuxabx2EepKyunxWseCqM352LTmpp8l89tZIyULRogQEbTB3hcTgV39xJEYH82nOw6elJr5+FWndusi5EmmUm1jM69vzufF9fuobmjmiknDuO/8Ud1aECWECFxBG+zBfHXjUwfE8vDcMTy+fDd3zEgjzAKZKf05I22AVzKE4MSnhMZmG+99U8iS1bkcqW7gvDGDeGBOBqMHx3vzlIQQAcL02Tje1NOUR2+kTLbPGuroGN0pE/HENRNpbLbx9Jc5FB6t5bQR/Xl4bgZTU/p3qZ1CiMDgaTaOYcFeKRUNbACisH+C+EBr/d8dPcbIYN/T+jm+LuDV1ZTTkso69h+p5e9bCthzuIqxQ+J5aG4GZ48aKJuHCBHEzBDsFRCrta5WSkUAm4B7tNZb3T3GyGCfV1bNRUs30i8mkiunJKEUhCm4YvIwUhM6H+ZxPt4X1SxtNs0PB4+zek8pNg0fbi+iuKLe7fN9k3+Ux/+zh6yCY6QOiOH+CzK4ZIL3F0QJIczH73n22n4VqXZ8G+H457cxo5LKevrFRHLz9JQ2k6MpA2JJ7t/5cIyvCni56tEvmJXOm1sLKK6ob/N8Px2qZNGKPazNLmNQXBT/c8V4rs0cLguihBAnMXSCVikVBmwHRgLPaa2/dnGf+cB8gOTkZMPakhgfzTWZJ5c4+OPHPzBpeN9OA7avCni5SqdcuiaHO2ak8eqmPAbFRVNQXsPiVXv55PtDxEeH8/sLR3Pr6an0ipQFUUII1wztAmqtrVrrSUAScJpSaryL+yzTWmdqrTMHDhxoWFtSB8QyalCc2965J49ffO0koiPsL5lRBbzcfYIIs8B/XzqOVzftZ/aT61nx42HuPOcUNj40i1+ffYoEeiFEh3ySeqm1Pq6UWgfMBXb54jnbs1gUY4bEd7t37qsCXq4+QUSFKw4eq2PZhjyarZrrT0vm7lkjGRRvzIIoMxZqE0L0jJETtAOBJkeg7wWsBB7XWn/m7jG+SL3095Z4XU2nDLcoIsIt1DdZuXziUO47fxQpBpYDNsNr5CmzX5TM3j4RHMyQjXMq8AYQhn246H2t9V86eozRwR66luduxHN7Ekgbmqy8sH4fb3yVz7HaJs7NGMiDc0YzdqjxC6J8mXXUE2a/KJm9fSJ4mCEbZycw2ajju9NZb8qfq2o7q2Vjs2k+3XmIxav2UlBeS2ZKPx6+cDTTUn23ICpQtg00+162Zm+fCD1BVS7B7L0pd4G0pLKOgqO1LFyeze7iSkYPjuO12zI5N2OQzxdEBcq2gWa/KJm9fSL0BFVCtrveVH55jZ9bZucMpK1Fhike+yKb21//hpqGZpZcN4kvFpzFrNGJfln56quso55y9Vqa6aJk9vaJ0BNUPXuz96bal122KGi0ag5X1vPo5eOYNy2ZyHDX19/2w1PJ/WIoPFbr9cm/QNk20MgS1t6YWJW9doXZBFWwN/sQhMWiGDsknhkjE1i9u5RekWH85uxT+MWMEcREhmOzaZcbpLsanvrrz8fzzJocCsrrvD5cZbZqoa4YdVHy1lBgoFw0RegIqqqXvhqz707Pr6yqgWfX5PD2tkIsSnH7mSP49dlp9I2J7LTt+eU1LjNk7piRxnNrc1u+N1vGTCAKlGwkIZz8no3jD77oTXX1glJZ38Sy9Xm8umk/jVYb100bzoLZ6SS2WxDVUfaGu+Gp1kP6ZhquCmRmHwoUoruCKtiD8UMQnqbU1TdZeeOrfJ5ft4+KuiYunTiU+88fxYgE12O2HQUZd8NTrT+UmWm4KpCZfShQFmqJ7gqYYG+WX/LOen5NVhv/zCpiyeq9lFQ2cE7GQH53/ihio8I5XFGH1tpl2zsKMq4m+5xj9s77yeSfd5h5YtXsqcXC3AJizL67v+QdXSA8vXi0v5/WcPEzJ4/pfnb3DHYXV7F41V72H6lhako/HpqTwbTU/h61vbnZxue7inn4w50u79d+5a8zG0cm/7zPn6usOyLzCcIVv5dL6A53wb47v+QdXSAAj3eBan+/Z2+YzPHaJh751y7qm2xEhStuOT2Vzbnl/FRcSUZiHA/OyWD2GPuCKE/a7nyex5fv5pJTh7XZmzbcTSqmCD1b9h3h+pdPqhLOu/N/xvS0BD+0SJhBUE3Qltc0cMeMtJYJSefOTR1NmnU0tg54NO7u6hh3vf0d95+Xzh0z0iiprGfLvnJe3rifwfHRPDVvIpdNHEZYqwuGJxN+rZ9HsmuEO2afTxDmZvpgb7NpDh2v59VNeW12bnovq7DDX3L3pQnqqWuyepRx4e4Y+8treWfbgTa3P3HNBGakDzqpHZ78gUoGiPCEmecThPmZPtjnl9e0jGPDiZ2blt2c2eEvubsg22TV7Dhw3KMekqtjxEaF8e62A0SGWZiS0pf9R2qoqGtiaN8Yl+3w5A9UemzCE7JQS/SE6YO9u15vRJjq8JfcVZB9/KpT+dMnP9DYrFkwK73NXrStA7DNpik8WkNZVQNPXTuJnw5V8OrmfGobrTQ02bBYoNFq4/sDx7lndjrpib3dXng8+QMNlR6bWTKqAlkgrG4W5mT6YO+u19t+UVJ7roJseU0DBeV1ALy5taBlHuCskQlMS+3fkvWyJruEnJJqnv5yLw3N9glsi4ILxiayfm8pDc3256hvsrFkdQ6f331Wh0Grsz/QUOixSdqgXOyEf5k+1aMnVRidQXZ6WgJpA3szIDaq5TjFFfU8tzaXVzbmMTAuquWPLr+8hm8LjvHkyhOBHiA8THFNZlKb28Ae8MuqO9/D1pO2pg6IZVBcNCWV9eSX12CzmSdTqqfMXpG0I86aRVv2HSGvrLpb74vzYnfR0o1c//LXXLR0I8t/PBxU77EwN9P37AEiwxXzZ6Zh0/YedmR493pDnQ2XNFttvLutkLe3HaC53R9hY7Omodlm2Nh6sPd8A3US2lvvi2xmIvzN9ME+v7yGu97+7qQA+9786UwY1tcrlQiVgi9+KOaJldnkldUwOD6KhmYrTVZ7wB/SJ5prMpOwWm386ZKxPPrZT14fWw/2YBCok9Deel8C9WIngofpg727P5LVe0rJL69laN9oBsRGeTz+2X78fFPOERau2MPOogrSB/XmpZumYrFocktrWLI6h34xkdxyegpLVtsnc1MG9GLxtZPILa1makpfTk9L8ErPO9iDQaBOQnvrfQnUi50IHqYP9u7+SKw2ePjDndwxI41XN+V1+aP19weOs3D5Hr7aV86wvr144pqJXDHZviDKZtOkD6phSnI/mm027ngjq+X5C8rruP/975k/M41wi8VrQyzBHgwCdRLaW+9LoF7sRPAwfbB3/pG0LiUwZnA8L6zLbSnz25WP1jklVSxakc3Kn0qIjw7nrnNP4bfnjiQqPOykTInUhN5s2XfEZc8uuX8MifFRXj/PYA4GgZg26K33JVAvdiJ4mD7YWyyKC8Yk0tBk5Q8f/9BmFW1FfVNLmd/OPloXHavl6S9z+OjbIiLDLIRbFJX1zbyyaT9jh/YhMly1zA20noTrKPUzyc1Cqu6epwQD8/Hm+xKIFzsRPEyfeglQeKyWp1fv5Y4Zadx//igWXT2RcAv89fIJbNxbCrj/aF1e3cBfPv2JWU+s5987DnHVlCQ0uiXbxvmpYGdRhcu0QFepn3+6ZCxLvsxm5e4SQ1LnTFSbTnByCq9cgEUgMn3PHuyF0OZlJrdZ8bpgVjqPfPID8zKTqahv4uG5Y9p8tK6qb+KVjft5ZWMedU1Wrpk6nHvOS6egvIZNuUe4ckpSm8Jq7WN2608Kc8cNZtj86azeU4rVBs+uyaW4op5dh7yXLRPsqZdCCP8KiGAfabG0BHo4UR/njhlpLF2T0yYNs77JyltfF/Lc2lyO1jRy0YTB3H9+BiMH2QNyY7O1TXZNdISFe2anE9YunkZHWBgcH92yAbhFKf6ZZa+26eTNbJlgT70UQviXYcFeKTUc+DswGLABy7TWS7pzrKO1jS1BcEif6JZeeUZiHP1iIqlrsmLTmg+yinh61V4OVdQzY2QCD87JYOLwvm2OZbXREujhRMmDV27NbBmbd9at/6m4qk1P+57Z6fx9S0FLwPdmtkywp14KIfzLyJ59M/A7rfW3Sqk4YLtSapXW+qeuHig2KpzoCAv9YiK5eXpKm+GcRy4ew84DFTzy8Y/kllUzMakPi66ZyJkjXW/mUFrlOqiGKcUXrSbh2u9I5bwozJ+ZxtLVuV7Plgn21EshhH8ZFuy11sVAsePrKqXUbmAY0OVg39BsZcGsdOqbrScN5/zpkx/RGhLjo3ju+smMHhJHaVUDeWXVXdrrNTE+uk2mhLuUy8nD+/Lu/J95PVsmFFIvhRD+45Mxe6VUKjAZOGlPNaXUfGA+QHJyssvHD43vxSNZu7jz7JEnBWCtYdboQWzOLSOuVwQXP7OpwwlOT4Oqu4tCyoBYQ4ZVJPVSCGEkw4O9Uqo38CFwr9a6sv3PtdbLgGVg34O29c+cJWGP1zVx3bRkdh2qwKJokzkTFa4YMySeNXtKySo42ukEp7ugCrRMxibG2zf09nVPW/KwhRBGMTTYK6UisAf6t7TWH3Xlsa1TEedNG8773xRR32QlMtyC1WbPk3emYL65taClhEJr7iY42wdVd2mPF4xJbDOOLz1tIUSgMjIbRwGvAru11ou7+vj9R06kIv5jayFWm2ZqSj9KKuu4bloyg/tEU3i0lje3FnCstpHHrzqVxauy2xzD0wlOd2mPn999Fkp1bZFToG9QEejtF0K4ZmTP/kzgZuAHpdT3jtv+qLX+wpMHFx6taQm+kWEW/njpaP7ni93UN9l4YuXelrLDf7l8HKcM7E1yvxgiwizdGnZxl/a4p6SS372/w+NFTq4+ITx7w2RGDOhNaZX5g6cs7BIieBmZjbMJ6HaEcKZb1jfZqGuycqy2qU1ALq6oZ+nqXN751c9ahmO6O8EZExnucjJW2+jSIqf2nxD6xUSSU1LtsuaOt4KnN3visrBLiOBl2hW0znTLpWvsNeXTEmJZMHskNg0bsks5a9Qgwiz2QG2zaSwW1e0Jzkar9aQNyBfMSqfoeG2b+3W2yKn9J4QrpySdtIDLm8HT2z1xWdglRPAybbAf2ieGR/61i3tmpxPfK4IHPtjRsnnIr2eO5M+f/Uh9k41lG7pey769AbFRvJdV2LIBudbwXlYhl08a1uZ+nc0BtE/XdJZfbs3MJRZkYZcQwcu0VS9HJMTy8NwxhCl7j/OXZ6Vx16yRXDN1eEugB+9sXJ06wP5cr27K49k1uby6KY8bTkthQExkm2qXj10xocM5gPYVMsMULV87+arEQnf0ZHN3IYS5mbZn76xj/68dh1j8rxN17B+9fLzXe8vtc+97RYSx4N3vaGzWLb19i4IpyR3vedv+OIPjo8kYHG9Yrr63e+KysEuI4GXaYA/2OvaPOAI92IN6eXWDywA3sHd0jyYrW4/322yah+eO4f73v+e5tSfq4CT37zxIt583SO4fa1jwNKLEgizsEiI4mTrYuxqm0MA9s9NPKlFsUXhtsjJQdieSnrgQwlOmDvauhinqmqz8M6uozWTq37cUMHpwnFcnKwOlhxso7RRC+JdpJ2gBkvvF8Nefj28zYTgxqS/Haht5bm0uz67J5bm1uRyrbSQmMtyrk5VCCBFMTN2zLzxWyzOOHamcvfgX1uXwp0vG8uhnP7UM1zx+1akM6RvVkocP9q0Gj9U2StqgEEJg8mBfUllPQXkdz63NbXP7VVOSWHztJPYcrsRqgze37KexOYVlG/LajOOnJ/aWtEEhhMDkwd5dGYNTBsZxy+vbWm7/7bkj+dMnu07aVerzu8+SyUohhMDkwb7RauUPc0dTXtuITdsXKSX0jqLoeF2bC4C7laqFR2sCogCZEEIYzdQTtAN7RxEW1jZA944O50hVvcuVqe2//+7Aca5/+WsuWrqR5T8exmbrQq1iIYQIIqYO9lpDVX0zyzbYyxi8tCGPwxX1RITZC5U5A/ynOw7y58vGtcnauWd2Ov/MKgJcl1Sw2TR5ZdVs2XeEvLJquRAIIYKaqYdxSqoaTqoauWR1Douvmcijn+9uU8qgocnKSzdPZXvBMdIHxfHYF7sprjiRdtm6pILUbRdChBpT9+wr65pcjsVbLKol1/6VjXlEh4fx6ub9VNY1s3R1LtklVRyrbWzzuNY1Y9xVi+xJMTUhhDAzU/fse0eHuczGiYkM46lrJ7HbkXr5XlYh8zKTOXi8lugICx9uLzqpPn3rmjGuyjD0i4mkrKpBtuMTQgQlUwf7Pr0iuP/8USxetbclaN9//ij2lVazbON+rslMYvzQeADe3FoA0BLk39xawPyZaYxKjGPM4HhGJNiDt82miYkMa1mA9eF2+7j+LaencKsjnVOGdYQQwcbUwT4mIpzocAvzZ6Zh0/ax+ehwCzWNVo7VNpI6IJbRg+O4r9WQzPJdxTxx9UQsFhjWN4ZxQ+IJD7ePVrkaq18wK51wCyz+0rgdpYQQwt9MPWZ/uLKeF9bnYXWMuFht8ML6PPrHRvLCjVNIS4ghpdWGG0P6RHPhhCE88MEO7nzrO+Yt28LK3SUtmTauxuqXrslh3LA+UldHCBHUTN2zT4yPbpmIdYqOsHDweB1HaxqZ4xhmGTskjvkz00gfFMeDju0L4eQeurudnRqbbbIdnxAiqJm6Z+9qm7x7ZqeTEBvZpu5NcUV9SxZORz10Z8nk1qIjLCT3l+34hBDBzdQ9e+fmHBl3n0Xh0Roiwy1Eh4cxoHckyf1PZMu0DuId9dDd7ew0IiGWEQnG7SglhBD+prQ2z8rRzMxMnZWV1eXHOSdeH1++m3mZySelXLbOqnFuXShBXQgRDJRS27XWmZ3eLxiCPZwI4kdrGogIs1DbaJV8eSFE0PM02Bs2jKOUeg24BCjVWo836nmcZHs+IYRwz8gJ2r8Bcw08vhBCCA8Z1rPXWm9QSqUadXwjOYeEpHSCECJY+D0bRyk1H5gPkJyc7OfWuF5lK6UThBCBzu959lrrZVrrTK115sCBA/3dHKmIKYQISn4P9mbjbpWtlE4QQgQyCfbtuFtlK6UThBCBzLBgr5R6B9gCZCilipRSdxj1XN7kqkSDlE4QQgQ6I7Nxrjfq2EZylmiQ0glCiGBiqhW0SqkyoMDFjxKAIz5ujpmE+vmDvAahfv4gr4G780/RWnea3WKqYO+OUirLk+XAwSrUzx/kNQj18wd5DXp6/jJBK4QQIUCCvRBChIBACfbL/N0APwv18wd5DUL9/EFegx6df0CM2QshhOiZQOnZCyGE6AEJ9kIIEQJMHeyVUnOVUtlKqVyl1O/93R5fUEoNV0qtVUrtVkr9qJS6x3F7f6XUKqVUjuP/fv5uq5GUUmFKqe+UUp85vg+18++rlPpAKbXH8btweii9Bkqp+xy//7uUUu8opaKD+fyVUq8ppUqVUrta3eb2fJVSf3DExWyl1BxPnsO0wV4pFQY8B1wIjAWuV0qN9W+rfKIZ+J3WegwwHfit47x/D6zWWqcDqx3fB7N7gN2tvg+1818CLNdajwYmYn8tQuI1UEoNAxYAmY5d7sKA6wju8/8bJ2/25PJ8HfHgOmCc4zHPO+Jlh0wb7IHTgFytdZ7WuhF4F7jcz20ynNa6WGv9rePrKux/5MOwn/sbjru9AfzcLw30AaVUEnAx8Eqrm0Pp/OOBmcCrAFrrRq31cULoNcBeyqWXUiociAEOEcTnr7XeABxtd7O7870ceFdr3aC13g/kYo+XHTJzsB8GHGj1fZHjtpDh2OlrMvA1kKi1Lgb7BQEY5MemGe1p4CGgda3pUDr/NKAMeN0xlPWKUiqWEHkNtNYHgSeAQqAYqNBaryREzr8Vd+fbrdho5mDvqvJYyOSJKqV6Ax8C92qtK/3dHl9RSjk3qd/u77b4UTgwBXhBaz0ZqCG4hiw65BibvhwYAQwFYpVSN/m3VabSrdho5mBfBAxv9X0S9o9yQU8pFYE90L+ltf7IcXOJUmqI4+dDgFJ/tc9gZwKXKaXysQ/dzVJK/YPQOX+w/+4Xaa2/dnz/AfbgHyqvwXnAfq11mda6CfgIOIPQOX8nd+fbrdho5mD/DZCulBqhlIrEPiHxbz+3yXBKKYV9rHa31npxqx/9G7jV8fWtwCe+bpsvaK3/oLVO0lqnYn/P12itbyJEzh9Aa30YOKCUynDcNBv4idB5DQqB6UqpGMffw2zsc1ehcv5O7s7338B1SqkopdQIIB3Y1unRtNam/QdcBOwF9gH/5e/2+OicZ2D/SLYT+N7x7yJgAPYZ+RzH//393VYfvBbnAJ85vg6p8wcmAVmO34N/Af1C6TUA/gzsAXYBbwJRwXz+wDvY5yeasPfc7+jofIH/csTFbOBCT55DyiUIIUQIMPMwjhBCCC+RYC+EECFAgr0QQoQACfZCCBECJNgLIUQIkGAvhINS6l6lVIybn73iLMSnlMpXSiU4vq52/D9UKfWB4+tJSqmLvNiuvkqpO711PBGaJNiLgOYolOUt92IvunUSrfUvtdY/uXug1vqQ1vpqx7eTsK+N8Fgn59EXkGAvekSCvfArpVSqo2b7G0qpnY4a7jGOn01VSq1XSm1XSq1otXR8nVLqMaXUeuAepdQ0pdRXSqkdSqltSqk4Rz38RUqpbxzH/T+Ox57jeLyzVvxbym4B9josa5VSa120c51SKrOT89jlWO39F2CeUup7pdQ8pVSso175N47CZpc7HnObUuqfSqlPgZVKqd5KqdVKqW+VUj847wf8P+AUx/EWOR77YKtz+7O33g8RxPy9ckz+hfY/IBX7iuEzHd+/BjwARABfAQMdt88DXnN8vQ543vF1JJAHTHN8H4+9kNh84BHHbVHYV6OOwL4qtwJ7PRELsAWY4bhfPpDgpp3rsNdXb3M/oLrVeexyfH0b8Gyrxz4G3OT4ui/2VeGxjvsV4VgZ6Wh3vOPrBOyla1XrYzt+dgH2zaeV4xw+A2b6+72Uf+b+582PwEJ01wGt9WbH1//AvnHFcmA8sMpeHoUw7MvJnd5z/J8BFGutvwHQjgqhSqkLgFOVUs6hlT7Ya4g0Atu01kWO+32PPZhuMuLEHC7AXtztAcf30UCy4+tVWmtnHXMFPKaUmom9vPMwINHN8S4AvnN83xv7uW0woO0iSEiwF2bQvmaHxh74ftRan+7mMTWO/5WLxztvv1trvaLNjUqdAzS0usmK8X8HCrhKa53dri0/48R5ANwIDASmaq2bHJU/o90c73+11i8Z1F4RhGTMXphBslLKGdSvx97LzgYGOm9XSkUopca5eOweYKhSaprjfnGOyc4VwG8c5aJRSo1ybADSkSogruenc9JxVgB3Oyo4opSa7OZxfbDX8m9SSp0LpHRwvF8o+54HKKWGKaWCfSMP0UMS7IUZ7AZuVUrtBPpj37SjEbgaeFwptQN79c8z2j/Qcb95wDOO+63C3ht+BXtZ4G+VfRPnl+i8B78M+I+rCdouWguMdU7QAo9in4PY6WjLo24e9xaQqZTKwt7L3wOgtS4HNjsmgBdp+65NbwNblFI/YK93742LlAhiUvVS+JWyb734mbZvLC2EMIj07IUQIgRIz14IIUKA9OyFECIESLAXQogQIMFeCCFCgAR7IYQIARLshRAiBPz/OJkPOUgwHQYAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot the illiteracy rate versus fertility\n",
    "sns.scatterplot(x= 'illiteracy', y= 'fertility', data=literacy_fertility)\n",
    "plt.plot(x,y);\n",
    "plt.margins(0.02)\n",
    "_ = plt.xlabel('percent illiterate')\n",
    "_ = plt.ylabel('fertility')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "2c9887a1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Specify slopes to consider: a_vals\n",
    "a_vals = np.linspace(0,.1,200)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "f9171c09",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Initialize sum of square of residuals: rss\n",
    "rss = np.empty_like(a_vals)\n",
    "\n",
    "# Compute sum of square of residuals for each value of a_vals\n",
    "for i, a in enumerate(a_vals):\n",
    "    rss[i] = np.sum((literacy_fertility['fertility'] - a*literacy_fertility['illiteracy'] - intercept)**2)\n",
    "    \n",
    "# Plot the RSS\n",
    "plt.plot(a_vals,rss, '-')\n",
    "plt.xlabel('slope (children per woman / percent illiterate)')\n",
    "plt.ylabel('sum of square of residuals')\n",
    "\n",
    "plt.show()    "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "afda8e03",
   "metadata": {},
   "source": [
    "## Linear regression on appropriate Anscombe data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "9e6421a3",
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"2\" halign=\"left\">0</th>\n",
       "      <th colspan=\"2\" halign=\"left\">1</th>\n",
       "      <th colspan=\"2\" halign=\"left\">2</th>\n",
       "      <th colspan=\"2\" halign=\"left\">3</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>10.0</td>\n",
       "      <td>8.04</td>\n",
       "      <td>10.0</td>\n",
       "      <td>9.14</td>\n",
       "      <td>10.0</td>\n",
       "      <td>7.46</td>\n",
       "      <td>8.0</td>\n",
       "      <td>6.58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.0</td>\n",
       "      <td>6.95</td>\n",
       "      <td>8.0</td>\n",
       "      <td>8.14</td>\n",
       "      <td>8.0</td>\n",
       "      <td>6.77</td>\n",
       "      <td>8.0</td>\n",
       "      <td>5.76</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>13.0</td>\n",
       "      <td>7.58</td>\n",
       "      <td>13.0</td>\n",
       "      <td>8.74</td>\n",
       "      <td>13.0</td>\n",
       "      <td>12.74</td>\n",
       "      <td>8.0</td>\n",
       "      <td>7.71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>9.0</td>\n",
       "      <td>8.81</td>\n",
       "      <td>9.0</td>\n",
       "      <td>8.77</td>\n",
       "      <td>9.0</td>\n",
       "      <td>7.11</td>\n",
       "      <td>8.0</td>\n",
       "      <td>8.84</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>11.0</td>\n",
       "      <td>8.33</td>\n",
       "      <td>11.0</td>\n",
       "      <td>9.26</td>\n",
       "      <td>11.0</td>\n",
       "      <td>7.81</td>\n",
       "      <td>8.0</td>\n",
       "      <td>8.47</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      0           1           2           3      \n",
       "      x     y     x     y     x      y    x     y\n",
       "0  10.0  8.04  10.0  9.14  10.0   7.46  8.0  6.58\n",
       "1   8.0  6.95   8.0  8.14   8.0   6.77  8.0  5.76\n",
       "2  13.0  7.58  13.0  8.74  13.0  12.74  8.0  7.71\n",
       "3   9.0  8.81   9.0  8.77   9.0   7.11  8.0  8.84\n",
       "4  11.0  8.33  11.0  9.26  11.0   7.81  8.0  8.47"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "anscombe.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "c0515226",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#for i in range(0,4)\n",
    "sns.scatterplot(x= 'x', y= 'y', data=anscombe['0']);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "fbc50187",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.scatterplot(x= 'x', y= 'y', data=anscombe['1']);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "ce9f7812",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.scatterplot(x= 'x', y= 'y', data=anscombe['2']);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "8b47dd8c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.scatterplot(x= 'x', y= 'y', data=anscombe['3']);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "6b4ac343",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5000909090909091 3.000090909090908\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "x = anscombe['0']['x']\n",
    "y = anscombe['0']['y']\n",
    "\n",
    "# Perform linear regression: a, b\n",
    "a, b = np.polyfit(x,y,1)\n",
    "# Print the slope and intercept\n",
    "print(a, b)\n",
    "\n",
    "# Generate theoretical x and y data: x_theor, y_theor\n",
    "x_theor = np.array([3, 15])\n",
    "y_theor = a * x_theor + b\n",
    "\n",
    "# Plot the Anscombe data and theoretical line\n",
    "_ = plt.plot(x,y, marker='.', linestyle='none')\n",
    "_ = plt.plot(x_theor,y_theor)\n",
    "\n",
    "# Label the axes\n",
    "plt.xlabel('x')\n",
    "plt.ylabel('y')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "20df32e9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.4997272727272729 3.002454545454545\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "x = anscombe['2']['x']\n",
    "y = anscombe['2']['y']\n",
    "\n",
    "# Perform linear regression: a, b\n",
    "a, b = np.polyfit(x,y,1)\n",
    "# Print the slope and intercept\n",
    "print(a, b)\n",
    "\n",
    "# Generate theoretical x and y data: x_theor, y_theor\n",
    "x_theor = np.array([3, 15])\n",
    "y_theor = a * x_theor + b\n",
    "\n",
    "# Plot the Anscombe data and theoretical line\n",
    "_ = plt.plot(x,y, marker='.', linestyle='none')\n",
    "_ = plt.plot(x_theor,y_theor)\n",
    "\n",
    "# Label the axes\n",
    "plt.xlabel('x')\n",
    "plt.ylabel('y')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "f51283d0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: 0.5000909090909091 intercept: 3.000090909090908\n",
      "slope: 0.4999999999999999 intercept: 3.000909090909089\n",
      "slope: 0.4997272727272729 intercept: 3.002454545454545\n",
      "slope: 0.49990909090909097 intercept: 3.0017272727272717\n"
     ]
    }
   ],
   "source": [
    "anscombe_x = []\n",
    "anscombe_y = []\n",
    "for i in range(0,4):\n",
    "    anscombe_x.append(anscombe[str(i)]['x'])\n",
    "    anscombe_y.append(anscombe[str(i)]['y'])\n",
    "    \n",
    "# Iterate through x,y pairs\n",
    "for x, y in zip(anscombe_x, anscombe_y):\n",
    "    # Compute the slope and intercept: a, b\n",
    "    a, b = np.polyfit(x,y,1)\n",
    "\n",
    "    # Print the result\n",
    "    print('slope:', a, 'intercept:', b)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "49564e31",
   "metadata": {},
   "source": [
    "## Visualizing bootstrap samples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "ac1eebb8",
   "metadata": {},
   "outputs": [],
   "source": [
    "def ecdf(data):\n",
    "    \"\"\"Compute ECDF for a one-dimensional array of measurements.\"\"\"\n",
    "    # Number of data points: n\n",
    "    n = len(data)\n",
    "\n",
    "    # x-data for the ECDF: x\n",
    "    x = np.sort(data)\n",
    "\n",
    "    # y-data for the ECDF: y\n",
    "    y = np.arange(1, n+1) / n\n",
    "\n",
    "    return x, y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "3119c080",
   "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>yyyy</th>\n",
       "      <th>mm</th>\n",
       "      <th>tmax</th>\n",
       "      <th>tmin</th>\n",
       "      <th>af</th>\n",
       "      <th>rain</th>\n",
       "      <th>sun</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1883</td>\n",
       "      <td>1</td>\n",
       "      <td>6.3</td>\n",
       "      <td>1.7</td>\n",
       "      <td>6.0</td>\n",
       "      <td>122.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1883</td>\n",
       "      <td>2</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.8</td>\n",
       "      <td>2.0</td>\n",
       "      <td>69.8</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1883</td>\n",
       "      <td>3</td>\n",
       "      <td>4.8</td>\n",
       "      <td>-1.6</td>\n",
       "      <td>23.0</td>\n",
       "      <td>29.6</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1883</td>\n",
       "      <td>4</td>\n",
       "      <td>12.2</td>\n",
       "      <td>3.8</td>\n",
       "      <td>2.0</td>\n",
       "      <td>74.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1883</td>\n",
       "      <td>5</td>\n",
       "      <td>14.7</td>\n",
       "      <td>6.2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>31.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   yyyy  mm  tmax  tmin    af   rain  sun\n",
       "0  1883   1   6.3   1.7   6.0  122.1  NaN\n",
       "1  1883   2   8.0   2.8   2.0   69.8  NaN\n",
       "2  1883   3   4.8  -1.6  23.0   29.6  NaN\n",
       "3  1883   4  12.2   3.8   2.0   74.0  NaN\n",
       "4  1883   5  14.7   6.2   0.0   31.2  NaN"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weather.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "5876480e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 864x1152 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for _ in range(50):\n",
    "    # Generate bootstrap sample: bs_sample\n",
    "    bs_sample = np.random.choice(weather['rain'], size=len(weather['rain']))\n",
    "      # Compute and plot ECDF from bootstrap sample\n",
    "    x, y = ecdf(bs_sample)\n",
    "    _ = plt.plot(x, y, marker='.', linestyle='none',\n",
    "                 color='gray', alpha=0.2);\n",
    "\n",
    "    \n",
    "  \n",
    "#Compute and plot ECDF from original data\n",
    "x, y = ecdf(weather['rain'])\n",
    "_ = plt.plot(x, y, marker='.')\n",
    "\n",
    "# Make margins and label axes\n",
    "plt.margins(0.02)\n",
    "_ = plt.xlabel('yearly rain')\n",
    "_ = plt.ylabel('ECDF')\n",
    "plt.figure(figsize=(12,16));\n",
    "# Show the plot\n",
    "plt.show()    \n",
    "    \n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "877525bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 864x1152 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#from empiricaldist import Cdf\n",
    "\n",
    "for _ in range(50):\n",
    "    # Generate bootstrap sample: bs_sample\n",
    "    bs_sample = np.random.choice(weather['rain'], size=len(weather['rain']))\n",
    "    # Compute and plot ECDF from bootstrap sample\n",
    "    Cdf.from_seq(bs_sample).plot(color='gold')\n",
    "\n",
    "    \n",
    "#Compute and plot ECDF from original data\n",
    "\n",
    "Cdf.from_seq(weather['rain']).plot()\n",
    "\n",
    "# Make margins and label axes\n",
    "plt.margins(0.02)\n",
    "_ = plt.xlabel('yearly rain')\n",
    "_ = plt.ylabel('ECDF')\n",
    "plt.figure(figsize=(12,16));\n",
    "# Show the plot\n",
    "plt.show() "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "da320135",
   "metadata": {},
   "source": [
    "## Generating many bootstrap replicates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "2fa824aa",
   "metadata": {},
   "outputs": [],
   "source": [
    "def bootstrap_replicate_1d(data, func):\n",
    "    \"\"\"Generate bootstrap replicate of 1D data.\"\"\"\n",
    "    bs_sample = np.random.choice(data, len(data))\n",
    "    return func(bs_sample)\n",
    "\n",
    "def draw_bs_reps(data, func, size=1):\n",
    "    \"\"\"Draw bootstrap replicates.\"\"\"\n",
    "\n",
    "    # Initialize array of replicates: bs_replicates\n",
    "    bs_replicates = np.empty(shape=size)\n",
    "\n",
    "    # Generate replicates\n",
    "    for i in range(size):\n",
    "        bs_replicates[i] = bootstrap_replicate_1d(data,func)\n",
    "\n",
    "    return bs_replicates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "9d625837",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "37.244473630243405"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bootstrap_replicate_1d(weather['rain'], np.std)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "02709b80",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "66.75024968788998"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weather['rain'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "5eeef47e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9488593574676786\n",
      "0.9603926629107423\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Take 10,000 bootstrap replicates of the mean: bs_replicates\n",
    "rain = np.array(weather['rain'])\n",
    "bs_replicates = draw_bs_reps(rain, np.mean, 10000)\n",
    "\n",
    "# Compute and print SEM\n",
    "sem = np.std(rain) / np.sqrt(len(rain))\n",
    "print(sem)\n",
    "\n",
    "# Compute and print standard deviation of bootstrap replicates\n",
    "bs_std = np.std(bs_replicates)\n",
    "print(bs_std)\n",
    "\n",
    "# Make a histogram of the results\n",
    "_ = sns.histplot(bs_replicates, bins=50, stat = \"probability\")\n",
    "_ = plt.xlabel('mean annual rain')\n",
    "_ = plt.ylabel('PDF')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f06a71e5",
   "metadata": {},
   "source": [
    "## Confidence intervals of rainfall data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "defdbef2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([64.89475499, 68.66045724])"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.percentile(bs_replicates, [2.5, 97.5])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4ee87b20",
   "metadata": {},
   "source": [
    "## Bootstrap replicates of other statistics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "568c35ac",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Generate 10,000 bootstrap replicates of the variance: bs_replicates\n",
    "bs_replicates = draw_bs_reps(rain,np.var,10000)\n",
    "\n",
    "# Put the variance in units of square centimeters\n",
    "bs_replicates = bs_replicates/10\n",
    "\n",
    "# Make a histogram of the results\n",
    "_ = sns.histplot(bs_replicates, stat = \"probability\", bins=50)\n",
    "_ = plt.xlabel('variance of annual rain (sq. cm)')\n",
    "_ = plt.ylabel('PDF')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "63c6ba74",
   "metadata": {},
   "source": [
    "## A function to do pairs bootstrap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "e3236d91",
   "metadata": {},
   "outputs": [],
   "source": [
    "def draw_bs_pairs_linreg(x, y, size=1):\n",
    "    \"\"\"Perform pairs bootstrap for linear regression.\"\"\"\n",
    "\n",
    "    # Set up array of indices to sample from: inds\n",
    "    inds = np.arange(len(x))\n",
    "\n",
    "    # Initialize replicates: bs_slope_reps, bs_intercept_reps\n",
    "    bs_slope_reps = np.empty(shape=size)\n",
    "    bs_intercept_reps = np.empty(shape=size)\n",
    "\n",
    "    # Generate replicates\n",
    "    for i in range(size):\n",
    "        bs_inds = np.random.choice(inds, len(inds))\n",
    "        bs_x, bs_y = x[bs_inds], y[bs_inds]\n",
    "        bs_slope_reps[i], bs_intercept_reps[i] = np.polyfit(bs_x, bs_y,1)\n",
    "\n",
    "    return bs_slope_reps, bs_intercept_reps"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "7c3bfeb9",
   "metadata": {},
   "outputs": [],
   "source": [
    "fertility = literacy_fertility['fertility']\n",
    "illiteracy = literacy_fertility['illiteracy']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "bf5857d5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.0442861  0.05533117]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Generate replicates of slope and intercept using pairs bootstrap\n",
    "bs_slope_reps, bs_intercept_reps = draw_bs_pairs_linreg(illiteracy,fertility,1000)\n",
    "\n",
    "# Compute and print 95% CI for slope\n",
    "print(np.percentile(bs_slope_reps, [2.5, 97.5]))\n",
    "\n",
    "# Plot the histogram\n",
    "_ = sns.histplot(bs_slope_reps, bins=50, stat='probability')\n",
    "_ = plt.xlabel('slope')\n",
    "_ = plt.ylabel('PDF')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "0fbae928",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Generate array of x-values for bootstrap lines: x\n",
    "x = np.array([0, 100])\n",
    "\n",
    "# Plot the bootstrap lines\n",
    "for i in range(100):\n",
    "    _ = plt.plot(x, \n",
    "                 bs_slope_reps[i] * x + bs_intercept_reps[i],\n",
    "                 linewidth=0.5, alpha=0.2, color='red')\n",
    "\n",
    "# Plot the data\n",
    "_ = plt.plot(illiteracy, fertility, marker='.', linestyle='none')\n",
    "\n",
    "# Label axes, set the margins, and show the plot\n",
    "_ = plt.xlabel('illiteracy')\n",
    "_ = plt.ylabel('fertility')\n",
    "plt.margins(0.02)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "29d033a5",
   "metadata": {},
   "source": [
    " ## Generating a permutation sample"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "07871ef0",
   "metadata": {},
   "outputs": [],
   "source": [
    "def permutation_sample(data1, data2):\n",
    "    \"\"\"Generate a permutation sample from two data sets.\"\"\"\n",
    "\n",
    "    # Concatenate the data sets: data\n",
    "    data = np.concatenate((data1,data2))\n",
    "\n",
    "    # Permute the concatenated array: permuted_data\n",
    "    permuted_data = np.random.permutation(data)\n",
    "\n",
    "    # Split the permuted array into two: perm_sample_1, perm_sample_2\n",
    "    perm_sample_1 = permuted_data[:len(data1)]\n",
    "    perm_sample_2 = permuted_data[len(data1):]\n",
    "\n",
    "    return perm_sample_1, perm_sample_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "d07279a5",
   "metadata": {},
   "outputs": [],
   "source": [
    "rain_june = weather[weather['mm'] == 6]['rain']\n",
    "rain_november = weather[weather['mm'] == 11]['rain']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "34ae4cfc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "for i in range(50):\n",
    "    # Generate permutation samples\n",
    "    perm_sample_1, perm_sample_2 = permutation_sample(rain_june,rain_november)\n",
    "\n",
    "\n",
    "    # Compute ECDFs\n",
    "    x_1, y_1 = ecdf(perm_sample_1)\n",
    "    x_2, y_2 = ecdf(perm_sample_2)\n",
    "\n",
    "    # Plot ECDFs of permutation sample\n",
    "    _ = plt.plot(x_1, y_1, marker='.', linestyle='none',\n",
    "                 color='red', alpha=0.02)\n",
    "    _ = plt.plot(x_2, y_2, marker='.', linestyle='none',\n",
    "                 color='blue', alpha=0.02)\n",
    "\n",
    "# Create and plot ECDFs from original data\n",
    "x_1, y_1 = ecdf(rain_june)\n",
    "x_2, y_2 = ecdf(rain_november)\n",
    "_ = plt.plot(x_1, y_1, marker='.', linestyle='none', color='red')\n",
    "_ = plt.plot(x_2, y_2, marker='.', linestyle='none', color='blue')\n",
    "\n",
    "# Label axes, set margin, and show plot\n",
    "plt.margins(0.02)\n",
    "_ = plt.xlabel('monthly rain (mm)')\n",
    "_ = plt.ylabel('ECDF')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e1b0712f",
   "metadata": {},
   "source": [
    "## Generating permutation replicates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "91681254",
   "metadata": {},
   "outputs": [],
   "source": [
    "def draw_perm_reps(data_1, data_2, func, size=1):\n",
    "    \"\"\"Generate multiple permutation replicates.\"\"\"\n",
    "\n",
    "    # Initialize array of replicates: perm_replicates\n",
    "    perm_replicates = np.empty(size)\n",
    "\n",
    "    for i in range(size):\n",
    "        # Generate permutation sample\n",
    "        perm_sample_1, perm_sample_2 = permutation_sample(data_1,data_2)\n",
    "\n",
    "        # Compute the test statistic\n",
    "        perm_replicates[i] = func(perm_sample_1,perm_sample_2)\n",
    "\n",
    "    return perm_replicates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "f98312a9",
   "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>date</th>\n",
       "      <th>ID</th>\n",
       "      <th>trial number</th>\n",
       "      <th>impact force (mN)</th>\n",
       "      <th>impact time (ms)</th>\n",
       "      <th>impact force / body weight</th>\n",
       "      <th>adhesive force (mN)</th>\n",
       "      <th>time frog pulls on target (ms)</th>\n",
       "      <th>adhesive force / body weight</th>\n",
       "      <th>adhesive impulse (N-s)</th>\n",
       "      <th>total contact area (mm2)</th>\n",
       "      <th>contact area without mucus (mm2)</th>\n",
       "      <th>contact area with mucus / contact area without mucus</th>\n",
       "      <th>contact pressure (Pa)</th>\n",
       "      <th>adhesive strength (Pa)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2013_02_26</td>\n",
       "      <td>I</td>\n",
       "      <td>3</td>\n",
       "      <td>1205</td>\n",
       "      <td>46</td>\n",
       "      <td>1.95</td>\n",
       "      <td>-785</td>\n",
       "      <td>884</td>\n",
       "      <td>1.27</td>\n",
       "      <td>-0.290</td>\n",
       "      <td>387</td>\n",
       "      <td>70</td>\n",
       "      <td>0.82</td>\n",
       "      <td>3117</td>\n",
       "      <td>-2030</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2013_02_26</td>\n",
       "      <td>I</td>\n",
       "      <td>4</td>\n",
       "      <td>2527</td>\n",
       "      <td>44</td>\n",
       "      <td>4.08</td>\n",
       "      <td>-983</td>\n",
       "      <td>248</td>\n",
       "      <td>1.59</td>\n",
       "      <td>-0.181</td>\n",
       "      <td>101</td>\n",
       "      <td>94</td>\n",
       "      <td>0.07</td>\n",
       "      <td>24923</td>\n",
       "      <td>-9695</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2013_03_01</td>\n",
       "      <td>I</td>\n",
       "      <td>1</td>\n",
       "      <td>1745</td>\n",
       "      <td>34</td>\n",
       "      <td>2.82</td>\n",
       "      <td>-850</td>\n",
       "      <td>211</td>\n",
       "      <td>1.37</td>\n",
       "      <td>-0.157</td>\n",
       "      <td>83</td>\n",
       "      <td>79</td>\n",
       "      <td>0.05</td>\n",
       "      <td>21020</td>\n",
       "      <td>-10239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2013_03_01</td>\n",
       "      <td>I</td>\n",
       "      <td>2</td>\n",
       "      <td>1556</td>\n",
       "      <td>41</td>\n",
       "      <td>2.51</td>\n",
       "      <td>-455</td>\n",
       "      <td>1025</td>\n",
       "      <td>0.74</td>\n",
       "      <td>-0.170</td>\n",
       "      <td>330</td>\n",
       "      <td>158</td>\n",
       "      <td>0.52</td>\n",
       "      <td>4718</td>\n",
       "      <td>-1381</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2013_03_01</td>\n",
       "      <td>I</td>\n",
       "      <td>3</td>\n",
       "      <td>493</td>\n",
       "      <td>36</td>\n",
       "      <td>0.80</td>\n",
       "      <td>-974</td>\n",
       "      <td>499</td>\n",
       "      <td>1.57</td>\n",
       "      <td>-0.423</td>\n",
       "      <td>245</td>\n",
       "      <td>216</td>\n",
       "      <td>0.12</td>\n",
       "      <td>2012</td>\n",
       "      <td>-3975</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         date ID  trial number  impact force (mN)  impact time (ms)  \\\n",
       "0  2013_02_26  I             3               1205                46   \n",
       "1  2013_02_26  I             4               2527                44   \n",
       "2  2013_03_01  I             1               1745                34   \n",
       "3  2013_03_01  I             2               1556                41   \n",
       "4  2013_03_01  I             3                493                36   \n",
       "\n",
       "   impact force / body weight  adhesive force (mN)  \\\n",
       "0                        1.95                 -785   \n",
       "1                        4.08                 -983   \n",
       "2                        2.82                 -850   \n",
       "3                        2.51                 -455   \n",
       "4                        0.80                 -974   \n",
       "\n",
       "   time frog pulls on target (ms)  adhesive force / body weight  \\\n",
       "0                             884                          1.27   \n",
       "1                             248                          1.59   \n",
       "2                             211                          1.37   \n",
       "3                            1025                          0.74   \n",
       "4                             499                          1.57   \n",
       "\n",
       "   adhesive impulse (N-s)  total contact area (mm2)  \\\n",
       "0                  -0.290                       387   \n",
       "1                  -0.181                       101   \n",
       "2                  -0.157                        83   \n",
       "3                  -0.170                       330   \n",
       "4                  -0.423                       245   \n",
       "\n",
       "   contact area without mucus (mm2)  \\\n",
       "0                                70   \n",
       "1                                94   \n",
       "2                                79   \n",
       "3                               158   \n",
       "4                               216   \n",
       "\n",
       "   contact area with mucus / contact area without mucus  \\\n",
       "0                                               0.82      \n",
       "1                                               0.07      \n",
       "2                                               0.05      \n",
       "3                                               0.52      \n",
       "4                                               0.12      \n",
       "\n",
       "   contact pressure (Pa)  adhesive strength (Pa)  \n",
       "0                   3117                   -2030  \n",
       "1                  24923                   -9695  \n",
       "2                  21020                  -10239  \n",
       "3                   4718                   -1381  \n",
       "4                   2012                   -3975  "
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frogs.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "e4923031",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['I', 'II', 'III', 'IV'], dtype=object)"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frogs['ID'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "5eab2315",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Make bee swarm plot\n",
    "_ = sns.swarmplot(x='ID', y='impact force (mN)', data=frogs)\n",
    "\n",
    "# Label axes\n",
    "_ = plt.xlabel('frog')\n",
    "_ = plt.ylabel('impact force (N)')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5b3e783f",
   "metadata": {},
   "source": [
    "## Permutation test on frog data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "8a69c60e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.5301999999999998"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.array(frogs[frogs['ID'] == 'I']['impact force (mN)']/1000).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "656dc3c4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7073500000000001"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.array(frogs[frogs['ID'] == 'II']['impact force (mN)']/1000).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "5ebf023d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5500999999999999"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.array(frogs[frogs['ID'] == 'III']['impact force (mN)']/1000).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "b3b7ef33",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.4191000000000001"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.array(frogs[frogs['ID'] == 'IV']['impact force (mN)']/1000).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "d2c15ebd",
   "metadata": {},
   "outputs": [],
   "source": [
    "force_a = np.array(frogs[frogs['ID'] == 'II']['impact force (mN)']/1000)\n",
    "force_b = np.array(frogs[frogs['ID'] == 'IV']['impact force (mN)']/1000)\n",
    "force_c = np.array(frogs[frogs['ID'] == 'III']['impact force (mN)']/1000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "2f1849ad",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "p-value = 0.0054\n"
     ]
    }
   ],
   "source": [
    "def diff_of_means(data_1, data_2):\n",
    "    \"\"\"Difference in means of two arrays.\"\"\"\n",
    "\n",
    "    # The difference of means of data_1, data_2: diff\n",
    "    diff = np.mean(data_1) - np.mean(data_2)\n",
    "\n",
    "    return diff\n",
    "\n",
    "# Compute difference of mean impact force from experiment: empirical_diff_means\n",
    "empirical_diff_means = diff_of_means(force_a,force_b)\n",
    "\n",
    "# Draw 10,000 permutation replicates: perm_replicates\n",
    "perm_replicates = draw_perm_reps(force_a, force_b,\n",
    "                                 diff_of_means, size=10000)\n",
    "\n",
    "# Compute p-value: p\n",
    "p = np.sum(perm_replicates >= empirical_diff_means) / len(perm_replicates)\n",
    "\n",
    "# Print the result\n",
    "print('p-value =', p)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1407508d",
   "metadata": {},
   "source": [
    "## A one-sample bootstrap hypothesis test"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7578fe75",
   "metadata": {},
   "source": [
    "Another juvenile frog was studied, Frog III, and you want to see if Frog II and Frog III have similar impact forces. Unfortunately, you do not have Frog III's impact forces available, but you know they have a mean of 0.55 N."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "45e8251c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "p =  0.0065\n"
     ]
    }
   ],
   "source": [
    "# Make an array of translated impact forces: translated_force_b\n",
    "translated_force_b = force_b - np.mean(force_b) + 0.55\n",
    "\n",
    "# Take bootstrap replicates of Frog B's translated impact forces: bs_replicates\n",
    "bs_replicates = draw_bs_reps(translated_force_b, np.mean, 10000)\n",
    "\n",
    "# Compute fraction of replicates that are less than the observed Frog B force: p\n",
    "p = np.sum(bs_replicates <= np.mean(force_b)) / 10000\n",
    "\n",
    "# Print the p-value\n",
    "print('p = ', p)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6d15a4f0",
   "metadata": {},
   "source": [
    "## A two-sample bootstrap hypothesis test for difference of means"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "05939180",
   "metadata": {},
   "outputs": [],
   "source": [
    "def diff_of_means(data_1, data_2):\n",
    "    \"\"\"Difference in means of two arrays.\"\"\"\n",
    "\n",
    "    # The difference of means of data_1, data_2: diff\n",
    "    diff = np.mean(data_1) - np.mean(data_2)\n",
    "\n",
    "    return diff"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "82dbfc0f",
   "metadata": {},
   "outputs": [],
   "source": [
    "empirical_diff_means = diff_of_means(force_a,force_b)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "1e6b8e8b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "p-value = 0.0054\n"
     ]
    }
   ],
   "source": [
    "# Compute mean of all forces: mean_force\n",
    "forces_concat = np.concatenate((force_a,force_b))\n",
    "\n",
    "\n",
    "mean_force = np.mean(forces_concat)\n",
    "\n",
    "# Generate shifted arrays\n",
    "force_a_shifted = force_a - np.mean(force_a) + mean_force\n",
    "force_b_shifted = force_b - np.mean(force_b) + mean_force\n",
    "\n",
    "# Compute 10,000 bootstrap replicates from shifted arrays\n",
    "bs_replicates_a = draw_bs_reps(force_a_shifted, np.mean, 10000)\n",
    "bs_replicates_b = draw_bs_reps(force_b_shifted, np.mean, 10000)\n",
    "\n",
    "# Get replicates of difference of means: bs_replicates\n",
    "bs_replicates = bs_replicates_a - bs_replicates_b\n",
    "\n",
    "# Compute and print p-value: p\n",
    "p = np.sum(bs_replicates > (np.mean(force_a) - np.mean(force_b)))/ 10000\n",
    "print('p-value =', p)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c1d55eaf",
   "metadata": {},
   "source": [
    "## The vote for the Civil Rights Act in 1964"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6d078c12",
   "metadata": {},
   "source": [
    "The Civil Rights Act of 1964 was one of the most important pieces of legislation ever passed in the USA. Excluding \"present\" and \"abstain\" votes, 153 House Democrats and 136 Republicans voted yea. However, 91 Democrats and 35 Republicans voted nay. Did party affiliation make a difference in the vote?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "9b0b2f16",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "p-value = 0.0001\n"
     ]
    }
   ],
   "source": [
    "# Construct arrays of data: dems, reps\n",
    "dems = np.array([True] * 153 + [False] * 91)\n",
    "reps = np.array([True] * 136 + [False] * 35)\n",
    "\n",
    "def frac_yea_dems(dems, reps):\n",
    "    \"\"\"Compute fraction of Democrat yea votes.\"\"\"\n",
    "    frac = np.sum(dems) / len(dems)\n",
    "    return frac\n",
    "\n",
    "# Acquire permutation samples: perm_replicates\n",
    "perm_replicates = draw_perm_reps(dems, reps, frac_yea_dems, 10000)\n",
    "\n",
    "# Compute and print p-value: p\n",
    "p = np.sum(perm_replicates <= 153/244) / len(perm_replicates)\n",
    "print('p-value =', p)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9e84da3f",
   "metadata": {},
   "source": [
    "This small p-value suggests that party identity had a lot to do with the voting. Importantly, the South had a higher fraction of Democrat representatives, and consequently also a more racist bias."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d0838597",
   "metadata": {},
   "source": [
    "## Hypothesis test on Pearson correlation\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "50f4e48b",
   "metadata": {},
   "source": [
    "The observed correlation between female illiteracy and fertility may just be by chance; the fertility of a given country may actually be totally independent of its illiteracy. You will test this hypothesis."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "5b1fd149",
   "metadata": {},
   "outputs": [],
   "source": [
    "def pearson_r(x, y):\n",
    "    \"\"\"Compute Pearson correlation coefficient between two arrays.\"\"\"\n",
    "    # Compute correlation matrix: corr_mat\n",
    "    corr_mat = np.corrcoef(x,y)\n",
    "\n",
    "    # Return entry [0,1]\n",
    "    return corr_mat[0,1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "aff12732",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "p-val = 0.0\n"
     ]
    }
   ],
   "source": [
    "# Compute observed correlation: r_obs\n",
    "r_obs = pearson_r(illiteracy,fertility)\n",
    "\n",
    "# Initialize permutation replicates: perm_replicates\n",
    "perm_replicates = np.empty(10000)\n",
    "\n",
    "# Draw replicates\n",
    "for i in range(10000):\n",
    "    # Permute illiteracy measurments: illiteracy_permuted\n",
    "    illiteracy_permuted = np.random.permutation(illiteracy)\n",
    "\n",
    "    # Compute Pearson correlation\n",
    "    perm_replicates[i] = pearson_r(illiteracy_permuted, fertility)\n",
    "\n",
    "# Compute p-value: p\n",
    "p = np.sum(perm_replicates >= r_obs) / 10000\n",
    "print('p-val =', p)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "22c5e744",
   "metadata": {},
   "source": [
    "We got a p-value of zero. In hacker statistics, this means that your p-value is very low, since we never got a single replicate in the 10,000 we took that had a Pearson correlation greater than the observed one."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dca0307a",
   "metadata": {},
   "source": [
    "## Do neonicotinoid insecticides have unintended consequences?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "63ad9ee6",
   "metadata": {
    "scrolled": true
   },
   "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>Specimen</th>\n",
       "      <th>Treatment</th>\n",
       "      <th>Environment</th>\n",
       "      <th>TreatmentNCSS</th>\n",
       "      <th>Sample ID</th>\n",
       "      <th>Colony</th>\n",
       "      <th>Cage</th>\n",
       "      <th>Sample</th>\n",
       "      <th>Sperm Volume per 500 ul</th>\n",
       "      <th>Quantity</th>\n",
       "      <th>ViabilityRaw (%)</th>\n",
       "      <th>Quality</th>\n",
       "      <th>Age (d)</th>\n",
       "      <th>Infertil</th>\n",
       "      <th>AliveSperm</th>\n",
       "      <th>Quantity Millions</th>\n",
       "      <th>Alive Sperm Millions</th>\n",
       "      <th>Dead Sperm Millions</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>227</td>\n",
       "      <td>Control</td>\n",
       "      <td>Cage</td>\n",
       "      <td>1</td>\n",
       "      <td>C2-1-1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2150000</td>\n",
       "      <td>2150000</td>\n",
       "      <td>96.7263814616756</td>\n",
       "      <td>96.726381</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "      <td>2079617</td>\n",
       "      <td>2.1500</td>\n",
       "      <td>2.079617</td>\n",
       "      <td>0.070383</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>228</td>\n",
       "      <td>Control</td>\n",
       "      <td>Cage</td>\n",
       "      <td>1</td>\n",
       "      <td>C2-1-2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2287500</td>\n",
       "      <td>2287500</td>\n",
       "      <td>96.3498079760595</td>\n",
       "      <td>96.349808</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "      <td>2204001</td>\n",
       "      <td>2.2875</td>\n",
       "      <td>2.204001</td>\n",
       "      <td>0.083499</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>229</td>\n",
       "      <td>Control</td>\n",
       "      <td>Cage</td>\n",
       "      <td>1</td>\n",
       "      <td>C2-1-3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>87500</td>\n",
       "      <td>87500</td>\n",
       "      <td>98.75</td>\n",
       "      <td>98.750000</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "      <td>86406</td>\n",
       "      <td>0.0875</td>\n",
       "      <td>0.086406</td>\n",
       "      <td>0.001094</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>230</td>\n",
       "      <td>Control</td>\n",
       "      <td>Cage</td>\n",
       "      <td>1</td>\n",
       "      <td>C2-1-4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>1875000</td>\n",
       "      <td>1875000</td>\n",
       "      <td>93.2874208336941</td>\n",
       "      <td>93.287421</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "      <td>1749139</td>\n",
       "      <td>1.8750</td>\n",
       "      <td>1.749139</td>\n",
       "      <td>0.125861</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>231</td>\n",
       "      <td>Control</td>\n",
       "      <td>Cage</td>\n",
       "      <td>1</td>\n",
       "      <td>C2-1-5</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>1587500</td>\n",
       "      <td>1587500</td>\n",
       "      <td>97.7925061050061</td>\n",
       "      <td>97.792506</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "      <td>1552456</td>\n",
       "      <td>1.5875</td>\n",
       "      <td>1.552456</td>\n",
       "      <td>0.035044</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Specimen Treatment Environment  TreatmentNCSS Sample ID  Colony  Cage  \\\n",
       "0       227   Control        Cage              1    C2-1-1       2     1   \n",
       "1       228   Control        Cage              1    C2-1-2       2     1   \n",
       "2       229   Control        Cage              1    C2-1-3       2     1   \n",
       "3       230   Control        Cage              1    C2-1-4       2     1   \n",
       "4       231   Control        Cage              1    C2-1-5       2     1   \n",
       "\n",
       "   Sample  Sperm Volume per 500 ul  Quantity  ViabilityRaw (%)    Quality  \\\n",
       "0       1                  2150000   2150000  96.7263814616756  96.726381   \n",
       "1       2                  2287500   2287500  96.3498079760595  96.349808   \n",
       "2       3                    87500     87500             98.75  98.750000   \n",
       "3       4                  1875000   1875000  93.2874208336941  93.287421   \n",
       "4       5                  1587500   1587500  97.7925061050061  97.792506   \n",
       "\n",
       "   Age (d)  Infertil  AliveSperm  Quantity Millions  Alive Sperm Millions  \\\n",
       "0       14         0     2079617             2.1500              2.079617   \n",
       "1       14         0     2204001             2.2875              2.204001   \n",
       "2       14         0       86406             0.0875              0.086406   \n",
       "3       14         0     1749139             1.8750              1.749139   \n",
       "4       14         0     1552456             1.5875              1.552456   \n",
       "\n",
       "   Dead Sperm Millions  \n",
       "0             0.070383  \n",
       "1             0.083499  \n",
       "2             0.001094  \n",
       "3             0.125861  \n",
       "4             0.035044  "
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bees.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "0c713ca0",
   "metadata": {},
   "outputs": [],
   "source": [
    "control = bees[bees['Treatment'] == 'Control']['AliveSperm']\n",
    "treated = bees[bees['Treatment'] == 'Pesticide']['AliveSperm']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "1deaa475",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Compute x,y values for ECDFs\n",
    "x_control, y_control = ecdf(control)\n",
    "x_treated, y_treated = ecdf(treated)\n",
    "\n",
    "# Plot the ECDFs\n",
    "plt.plot(x_control, y_control, marker='.', linestyle='none')\n",
    "plt.plot(x_treated, y_treated, marker='.', linestyle='none')\n",
    "\n",
    "# Set the margins\n",
    "plt.margins(0.02)\n",
    "\n",
    "# Add a legend\n",
    "plt.legend(('control', 'treated'), loc='lower right')\n",
    "\n",
    "# Label axes and show plot\n",
    "plt.xlabel('millions of alive sperm per mL')\n",
    "plt.ylabel('ECDF')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2af5e715",
   "metadata": {},
   "source": [
    "## Bootstrap hypothesis test on bee sperm counts\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "f06162ca",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "p-value = 0.0\n"
     ]
    }
   ],
   "source": [
    "# Compute the difference in mean sperm count: diff_means\n",
    "diff_means =np.mean(control) - np.mean(treated)\n",
    "\n",
    "# Compute mean of pooled data: mean_count\n",
    "mean_count = np.mean(np.concatenate([control, treated]))\n",
    "\n",
    "# Generate shifted data sets\n",
    "control_shifted = control - np.mean(control) + mean_count\n",
    "treated_shifted = treated - np.mean(treated) + mean_count\n",
    "\n",
    "# Generate bootstrap replicates\n",
    "bs_reps_control = draw_bs_reps(control_shifted,\n",
    "                       np.mean, size=10000)\n",
    "bs_reps_treated = draw_bs_reps(treated_shifted,\n",
    "                       np.mean, size=10000)\n",
    "\n",
    "# Get replicates of difference of means: bs_replicates\n",
    "bs_replicates = bs_reps_control - bs_reps_treated\n",
    "\n",
    "# Compute and print p-value: p\n",
    "p = np.sum(bs_replicates >= np.mean(control) - np.mean(treated)) \\\n",
    "            / len(bs_replicates)\n",
    "print('p-value =', p)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "68fce427",
   "metadata": {},
   "source": [
    "The p-value is small, most likely less than 0.0001, since we never saw a bootstrap replicated with a difference of means at least as extreme as what was observed"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b46b4de3",
   "metadata": {},
   "source": [
    "## EDA of beak depths of Darwin's finches\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "cc9edd6a",
   "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>band</th>\n",
       "      <th>species</th>\n",
       "      <th>Beak length, mm</th>\n",
       "      <th>Beak depth, mm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>fortis</td>\n",
       "      <td>9.4</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>9</td>\n",
       "      <td>fortis</td>\n",
       "      <td>9.2</td>\n",
       "      <td>8.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>12</td>\n",
       "      <td>fortis</td>\n",
       "      <td>9.5</td>\n",
       "      <td>7.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>15</td>\n",
       "      <td>fortis</td>\n",
       "      <td>9.5</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>305</td>\n",
       "      <td>fortis</td>\n",
       "      <td>11.5</td>\n",
       "      <td>9.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   band species  Beak length, mm  Beak depth, mm\n",
       "0     2  fortis              9.4             8.0\n",
       "1     9  fortis              9.2             8.3\n",
       "2    12  fortis              9.5             7.5\n",
       "3    15  fortis              9.5             8.0\n",
       "4   305  fortis             11.5             9.9"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "beaks_1975.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "e3228379",
   "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>band</th>\n",
       "      <th>species</th>\n",
       "      <th>blength</th>\n",
       "      <th>bdepth</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19022</td>\n",
       "      <td>fortis</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>19028</td>\n",
       "      <td>fortis</td>\n",
       "      <td>12.5</td>\n",
       "      <td>8.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>19032</td>\n",
       "      <td>fortis</td>\n",
       "      <td>9.3</td>\n",
       "      <td>7.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>19041</td>\n",
       "      <td>fortis</td>\n",
       "      <td>10.3</td>\n",
       "      <td>9.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>19044</td>\n",
       "      <td>fortis</td>\n",
       "      <td>11.0</td>\n",
       "      <td>9.2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    band species  blength  bdepth\n",
       "0  19022  fortis     10.0     8.5\n",
       "1  19028  fortis     12.5     8.9\n",
       "2  19032  fortis      9.3     7.5\n",
       "3  19041  fortis     10.3     9.6\n",
       "4  19044  fortis     11.0     9.2"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "beaks_2012.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "9b6e603d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['fortis', 'scandens'], dtype=object)"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "beaks_2012['species'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "47c30481",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['fortis', 'scandens'], dtype=object)"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "beaks_1975['species'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "b1581a3c",
   "metadata": {},
   "outputs": [],
   "source": [
    "beaks_1975['year'] = ['1975']*403"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "45141c37",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 248 entries, 0 to 247\n",
      "Data columns (total 4 columns):\n",
      " #   Column   Non-Null Count  Dtype  \n",
      "---  ------   --------------  -----  \n",
      " 0   band     248 non-null    int64  \n",
      " 1   species  248 non-null    object \n",
      " 2   blength  248 non-null    float64\n",
      " 3   bdepth   248 non-null    float64\n",
      "dtypes: float64(2), int64(1), object(1)\n",
      "memory usage: 7.9+ KB\n"
     ]
    }
   ],
   "source": [
    "beaks_2012.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "a40da844",
   "metadata": {},
   "outputs": [],
   "source": [
    "beaks_2012['year'] = ['2012']*248"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "1f6ed6d1",
   "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>band</th>\n",
       "      <th>species</th>\n",
       "      <th>blength</th>\n",
       "      <th>bdepth</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19022</td>\n",
       "      <td>fortis</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.5</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>19028</td>\n",
       "      <td>fortis</td>\n",
       "      <td>12.5</td>\n",
       "      <td>8.9</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>19032</td>\n",
       "      <td>fortis</td>\n",
       "      <td>9.3</td>\n",
       "      <td>7.5</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>19041</td>\n",
       "      <td>fortis</td>\n",
       "      <td>10.3</td>\n",
       "      <td>9.6</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>19044</td>\n",
       "      <td>fortis</td>\n",
       "      <td>11.0</td>\n",
       "      <td>9.2</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    band species  blength  bdepth  year\n",
       "0  19022  fortis     10.0     8.5  2012\n",
       "1  19028  fortis     12.5     8.9  2012\n",
       "2  19032  fortis      9.3     7.5  2012\n",
       "3  19041  fortis     10.3     9.6  2012\n",
       "4  19044  fortis     11.0     9.2  2012"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = beaks_2012.merge(beaks_1975.rename(columns={'Beak length, mm':'blength', 'Beak depth, mm':'bdepth'}),how='outer')\n",
    "df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "6010f12e",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.rename(columns={'blength': 'beak_length', 'bdepth': 'beak_depth'}, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "cb520237",
   "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>band</th>\n",
       "      <th>species</th>\n",
       "      <th>beak_length</th>\n",
       "      <th>beak_depth</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19022</td>\n",
       "      <td>fortis</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.5</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>19028</td>\n",
       "      <td>fortis</td>\n",
       "      <td>12.5</td>\n",
       "      <td>8.9</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>19032</td>\n",
       "      <td>fortis</td>\n",
       "      <td>9.3</td>\n",
       "      <td>7.5</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>19041</td>\n",
       "      <td>fortis</td>\n",
       "      <td>10.3</td>\n",
       "      <td>9.6</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>19044</td>\n",
       "      <td>fortis</td>\n",
       "      <td>11.0</td>\n",
       "      <td>9.2</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    band species  beak_length  beak_depth  year\n",
       "0  19022  fortis         10.0         8.5  2012\n",
       "1  19028  fortis         12.5         8.9  2012\n",
       "2  19032  fortis          9.3         7.5  2012\n",
       "3  19041  fortis         10.3         9.6  2012\n",
       "4  19044  fortis         11.0         9.2  2012"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "fc5df9a9",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df[df['species']=='scandens']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "2f0eb597",
   "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>band</th>\n",
       "      <th>species</th>\n",
       "      <th>beak_length</th>\n",
       "      <th>beak_depth</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>121</th>\n",
       "      <td>19026</td>\n",
       "      <td>scandens</td>\n",
       "      <td>14.30</td>\n",
       "      <td>9.40</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>122</th>\n",
       "      <td>19028</td>\n",
       "      <td>scandens</td>\n",
       "      <td>12.50</td>\n",
       "      <td>8.90</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>123</th>\n",
       "      <td>19029</td>\n",
       "      <td>scandens</td>\n",
       "      <td>13.70</td>\n",
       "      <td>9.50</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>124</th>\n",
       "      <td>19094</td>\n",
       "      <td>scandens</td>\n",
       "      <td>13.80</td>\n",
       "      <td>11.00</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>125</th>\n",
       "      <td>19122</td>\n",
       "      <td>scandens</td>\n",
       "      <td>12.00</td>\n",
       "      <td>8.70</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>646</th>\n",
       "      <td>20225</td>\n",
       "      <td>scandens</td>\n",
       "      <td>14.55</td>\n",
       "      <td>9.45</td>\n",
       "      <td>1975</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>647</th>\n",
       "      <td>20252</td>\n",
       "      <td>scandens</td>\n",
       "      <td>14.05</td>\n",
       "      <td>9.05</td>\n",
       "      <td>1975</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>648</th>\n",
       "      <td>20255</td>\n",
       "      <td>scandens</td>\n",
       "      <td>14.45</td>\n",
       "      <td>8.75</td>\n",
       "      <td>1975</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>649</th>\n",
       "      <td>20266</td>\n",
       "      <td>scandens</td>\n",
       "      <td>15.05</td>\n",
       "      <td>9.45</td>\n",
       "      <td>1975</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>650</th>\n",
       "      <td>20279</td>\n",
       "      <td>scandens</td>\n",
       "      <td>13.25</td>\n",
       "      <td>8.35</td>\n",
       "      <td>1975</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>214 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      band   species  beak_length  beak_depth  year\n",
       "121  19026  scandens        14.30        9.40  2012\n",
       "122  19028  scandens        12.50        8.90  2012\n",
       "123  19029  scandens        13.70        9.50  2012\n",
       "124  19094  scandens        13.80       11.00  2012\n",
       "125  19122  scandens        12.00        8.70  2012\n",
       "..     ...       ...          ...         ...   ...\n",
       "646  20225  scandens        14.55        9.45  1975\n",
       "647  20252  scandens        14.05        9.05  1975\n",
       "648  20255  scandens        14.45        8.75  1975\n",
       "649  20266  scandens        15.05        9.45  1975\n",
       "650  20279  scandens        13.25        8.35  1975\n",
       "\n",
       "[214 rows x 5 columns]"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "bbec006b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Create bee swarm plot\n",
    "plt.figure(figsize=(10, 6))\n",
    "_ = sns.swarmplot(x='year', y='beak_depth', data=df)\n",
    "\n",
    "# Label the axes\n",
    "_ = plt.xlabel('year')\n",
    "_ = plt.ylabel('beak depth (mm)')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "8646297d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Compute ECDFs\n",
    "x_1975, y_1975 = ecdf(df[df['year']== '1975']['beak_depth'])\n",
    "x_2012, y_2012 = ecdf(df[df['year']== '2012']['beak_depth'])\n",
    "\n",
    "# Plot the ECDFs\n",
    "_ = plt.plot(x_1975, y_1975, marker='.', linestyle='none')\n",
    "_ = plt.plot(x_2012, y_2012, marker='.', linestyle='none')\n",
    "\n",
    "# Set margins\n",
    "plt.margins(.02)\n",
    "\n",
    "# Add axis labels and legend\n",
    "_ = plt.xlabel('beak depth (mm)')\n",
    "_ = plt.ylabel('ECDF')\n",
    "_ = plt.legend(('1975', '2012'), loc='lower right')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "cb740b9e",
   "metadata": {},
   "outputs": [],
   "source": [
    "bd_1975 = df[df['year']== '1975']['beak_depth']\n",
    "bd_2012 = df[df['year']== '2012']['beak_depth']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "6fa7a2b4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "difference of means = 0.2262204724409429 mm\n",
      "95% confidence interval = [0.06085435 0.39035128] mm\n"
     ]
    }
   ],
   "source": [
    "# Compute the difference of the sample means: mean_diff\n",
    "mean_diff = np.mean(bd_2012) - np.mean(bd_1975)\n",
    "\n",
    "# Get bootstrap replicates of means\n",
    "bs_replicates_1975 = draw_bs_reps(bd_1975, np.mean, 10000 )\n",
    "bs_replicates_2012 = draw_bs_reps(bd_2012, np.mean, 10000)\n",
    "\n",
    "# Compute samples of difference of means: bs_diff_replicates\n",
    "bs_diff_replicates = bs_replicates_2012 - bs_replicates_1975\n",
    "\n",
    "# Compute 95% confidence interval: conf_int\n",
    "conf_int = np.percentile(bs_diff_replicates, [2.5, 97.5])\n",
    "\n",
    "# Print the results\n",
    "print('difference of means =', mean_diff, 'mm')\n",
    "print('95% confidence interval =', conf_int, 'mm')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "0d0292f2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "p = 0.0035\n"
     ]
    }
   ],
   "source": [
    "# Compute mean of combined data set: combined_mean\n",
    "combined_mean = np.mean(np.concatenate((bd_1975, bd_2012)))\n",
    "\n",
    "# Shift the samples\n",
    "bd_1975_shifted = bd_1975 - np.mean(bd_1975) + combined_mean\n",
    "bd_2012_shifted = bd_2012 - np.mean(bd_2012) + combined_mean\n",
    "\n",
    "# Get bootstrap replicates of shifted data sets\n",
    "bs_replicates_1975 = draw_bs_reps(bd_1975_shifted,np.mean, 10000)\n",
    "bs_replicates_2012 = draw_bs_reps(bd_2012_shifted, np.mean, 10000)\n",
    "\n",
    "# Compute replicates of difference of means: bs_diff_replicates\n",
    "bs_diff_replicates = bs_replicates_2012 - bs_replicates_1975\n",
    "\n",
    "# Compute the p-value\n",
    "p = np.sum(bs_diff_replicates >= mean_diff) / len(bs_diff_replicates)\n",
    "\n",
    "# Print p-value\n",
    "print('p =', p)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ccd499b4",
   "metadata": {},
   "source": [
    "We get a p-value of 0.0034, which suggests that there is a statistically significant difference"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "883a970e",
   "metadata": {},
   "source": [
    "## EDA of beak length and depth"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "40eb4adf",
   "metadata": {},
   "outputs": [],
   "source": [
    "bl_1975 = df[df['year']== '1975']['beak_length']\n",
    "bl_2012 = df[df['year']== '2012']['beak_length']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "2f6b77e3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Make scatter plot of 1975 data\n",
    "_ = plt.scatter(bl_1975, bd_1975, marker='.',\n",
    "             linestyle='None', alpha=.5, color='blue')\n",
    "\n",
    "# Make scatter plot of 2012 data\n",
    "_ = plt.scatter(bl_2012, bd_2012, marker='.',\n",
    "            linestyle='None', alpha=.5, color='red')\n",
    "\n",
    "# Label axes and make legend\n",
    "_ = plt.xlabel('beak length (mm)')\n",
    "_ = plt.ylabel('beak depth (mm)')\n",
    "_ = plt.legend(('1975', '2012'), loc='upper left')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "0c67399f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1975: slope = 0.4652051691605937 conf int = [0.32232798 0.58972743]\n",
      "1975: intercept = 2.390875236584227 conf int = [0.67060569 4.35821159]\n",
      "2012: slope = 0.462630358835313 conf int = [0.32422576 0.59610645]\n",
      "2012: intercept = 2.977247498236017 conf int = [1.18701496 4.81066994]\n"
     ]
    }
   ],
   "source": [
    "# Compute the linear regressions\n",
    "slope_1975, intercept_1975 = np.polyfit(np.array(bl_1975), np.array(bd_1975), 1)\n",
    "slope_2012, intercept_2012 = np.polyfit(np.array(bl_2012), np.array(bd_2012), 1)\n",
    "\n",
    "# Perform pairs bootstrap for the linear regressions\n",
    "bs_slope_reps_1975, bs_intercept_reps_1975 = draw_bs_pairs_linreg(np.array(bl_1975), np.array(bd_1975), 1000)\n",
    "bs_slope_reps_2012, bs_intercept_reps_2012 = draw_bs_pairs_linreg(np.array(bl_2012), np.array(bd_2012), 1000)\n",
    "\n",
    "# Compute confidence intervals of slopes\n",
    "slope_conf_int_1975 = np.percentile(bs_slope_reps_1975, [2.5, 97.5])\n",
    "slope_conf_int_2012 = np.percentile(bs_slope_reps_2012, [2.5, 97.5])\n",
    "intercept_conf_int_1975 = np.percentile(\n",
    "                            bs_intercept_reps_1975, [2.5, 97.5])\n",
    "intercept_conf_int_2012 = np.percentile(\n",
    "                            bs_intercept_reps_2012, [2.5, 97.5])\n",
    "\n",
    "# Print the results\n",
    "print('1975: slope =', slope_1975,\n",
    "      'conf int =', slope_conf_int_1975)\n",
    "print('1975: intercept =', intercept_1975,\n",
    "      'conf int =', intercept_conf_int_1975)\n",
    "print('2012: slope =', slope_2012,\n",
    "      'conf int =', slope_conf_int_2012)\n",
    "print('2012: intercept =', intercept_2012,\n",
    "      'conf int =', intercept_conf_int_2012)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "e13332eb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Make scatter plot of 1975 data\n",
    "_ = plt.plot(bl_1975, bd_1975, marker='.',\n",
    "             linestyle='none', color='blue', alpha=0.5)\n",
    "\n",
    "# Make scatter plot of 2012 data\n",
    "_ = plt.plot(bl_2012, bd_2012, marker='.',\n",
    "             linestyle='none', color='red', alpha=0.5)\n",
    "\n",
    "# Label axes and make legend\n",
    "_ = plt.xlabel('beak length (mm)')\n",
    "_ = plt.ylabel('beak depth (mm)')\n",
    "_ = plt.legend(('1975', '2012'), loc='upper left')\n",
    "\n",
    "# Generate x-values for bootstrap lines: x\n",
    "x = np.array([10, 17])\n",
    "\n",
    "# Plot the bootstrap lines\n",
    "for i in range(100):\n",
    "    plt.plot(x, bs_slope_reps_1975[i]*x +bs_intercept_reps_1975[i],\n",
    "             linewidth=0.5, alpha=0.2, color='blue')\n",
    "    plt.plot(x, bs_slope_reps_2012[i] * x + bs_intercept_reps_2012[i],\n",
    "             linewidth=0.5, alpha=0.2, color='red')\n",
    "\n",
    "# Draw the plot again\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8030d0c4",
   "metadata": {},
   "source": [
    "## Beak length to depth ratio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "d213926b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1975: mean ratio = 1.5788823771858533 conf int = [1.55692462 1.60039081]\n",
      "2012: mean ratio = 1.4658342276847767 conf int = [1.44444756 1.48729348]\n"
     ]
    }
   ],
   "source": [
    "# Compute length-to-depth ratios\n",
    "ratio_1975 = np.array(bl_1975/bd_1975)\n",
    "ratio_2012 = np.array(bl_2012/bd_2012)\n",
    "\n",
    "# Compute means\n",
    "mean_ratio_1975 = np.mean(ratio_1975)\n",
    "mean_ratio_2012 = np.mean(ratio_2012)\n",
    "\n",
    "# Generate bootstrap replicates of the means\n",
    "bs_replicates_1975 = draw_bs_reps(ratio_1975,np.mean,10000)\n",
    "bs_replicates_2012 = draw_bs_reps(ratio_2012,np.mean,10000)\n",
    "\n",
    "# Compute the 99% confidence intervals\n",
    "conf_int_1975 = np.percentile(bs_replicates_1975,[.5,99.5])\n",
    "conf_int_2012 = np.percentile(bs_replicates_2012,[.5,99.5])\n",
    "\n",
    "# Print the results\n",
    "print('1975: mean ratio =', mean_ratio_1975,\n",
    "      'conf int =', conf_int_1975)\n",
    "print('2012: mean ratio =', mean_ratio_2012,\n",
    "      'conf int =', conf_int_2012)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1bcbe302",
   "metadata": {},
   "source": [
    "The mean beak length-to-depth ratio decreased by about 0.1, or 7%, from 1975 to 2012. The 99% confidence intervals are not even close to overlapping, so this is a real change. The beak shape changed."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6d49e11e",
   "metadata": {},
   "source": [
    "## EDA of heritability\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "23092faf",
   "metadata": {},
   "source": [
    "The array bd_parent_scandens contains the average beak depth (in mm) of two parents of the species G. scandens. The array bd_offspring_scandens contains the average beak depth of the offspring of the respective parents. The arrays bd_parent_fortis and bd_offspring_fortis contain the same information about measurements from G. fortis birds."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "a096218f",
   "metadata": {},
   "outputs": [],
   "source": [
    "bd_parent_scandens = [8.3318, 8.4035, 8.5317, 8.7202, 8.7089, 8.7541, 8.773, 8.8107, 8.7919, 8.8069, 8.6523, 8.6146, 8.6938, 8.7127, 8.7466, 8.7504, 8.7805, 8.7428, 8.7164, 8.8032, 8.8258, 8.856, 8.9012, 8.9125, 8.8635, 8.8258, 8.8522, 8.8974, 8.9427, 8.9879, 8.9615, 8.9238, 8.9351, 9.0143, 9.0558, 9.0596, 8.9917, 8.905, 8.9314, 8.9465, 8.9879, 8.9804, 9.0219, 9.052, 9.0407, 9.0407, 8.9955, 8.9992, 8.9992, 9.0747, 9.0747, 9.5385, 9.4781, 9.4517, 9.3537, 9.2707, 9.1199, 9.1689, 9.1425, 9.135, 9.1011, 9.1727, 9.2217, 9.2255, 9.2821, 9.3235, 9.3198, 9.3198, 9.3198, 9.3273, 9.3725, 9.3989, 9.4253, 9.4593, 9.4442, 9.4291, 9.2632, 9.2293, 9.1878, 9.1425, 9.1275, 9.1802, 9.1765, 9.2481, 9.2481, 9.1991, 9.1689, 9.1765, 9.2406, 9.3198, 9.3235, 9.1991, 9.2971, 9.2443, 9.316, 9.2934, 9.3914, 9.3989, 9.5121, 9.6176, 9.5535, 9.4668, 9.3725, 9.3348, 9.3763, 9.3839, 9.4216, 9.4065, 9.3348, 9.4442, 9.4367, 9.5083, 9.448, 9.4781, 9.595, 9.6101, 9.5686, 9.6365, 9.7119, 9.8213, 9.825, 9.7609, 9.6516, 9.5988, 9.546, 9.6516, 9.7572, 9.8854, 10.0023, 9.3914]\n",
    "bd_offspring_scandens = [8.419, 9.2468, 8.1532, 8.0089, 8.2215, 8.3734, 8.5025, 8.6392, 8.7684, 8.8139, 8.7911, 8.9051, 8.9203, 8.8747, 8.943, 9.0038, 8.981, 9.0949, 9.2696, 9.1633, 9.1785, 9.1937, 9.2772, 9.0722, 8.9658, 8.9658, 8.5025, 8.4949, 8.4949, 8.5633, 8.6013, 8.6468, 8.1532, 8.3734, 8.662, 8.6924, 8.7456, 8.8367, 8.8595, 8.9658, 8.9582, 8.8671, 8.8671, 8.943, 9.0646, 9.1405, 9.2089, 9.2848, 9.3759, 9.4899, 9.4519, 8.1228, 8.2595, 8.3127, 8.4949, 8.6013, 8.4646, 8.5329, 8.7532, 8.8823, 9.0342, 8.6392, 8.6772, 8.6316, 8.7532, 8.8291, 8.8975, 8.9734, 9.0494, 9.1253, 9.1253, 9.1253, 9.1785, 9.2848, 9.4595, 9.3608, 9.2089, 9.2544, 9.3684, 9.3684, 9.2316, 9.1709, 9.2316, 9.0342, 8.8899, 8.8291, 8.981, 8.8975, 10.4089, 10.1886, 9.7633, 9.7329, 9.6114, 9.5051, 9.5127, 9.3684, 9.6266, 9.5354, 10.0215, 10.0215, 9.6266, 9.6038, 9.4063, 9.2316, 9.338, 9.262, 9.262, 9.4063, 9.4367, 9.0342, 8.943, 8.9203, 8.7835, 8.7835, 9.057, 8.9354, 8.8975, 8.8139, 8.8671, 9.0873, 9.2848, 9.2392, 9.2924, 9.4063, 9.3152, 9.4899, 9.5962, 9.6873, 9.5203, 9.6646]\n",
    "\n",
    "bd_parent_fortis = [10.100000000000001, 9.55, 9.399999999999999, 10.25, 10.125, 9.7, 9.05, 7.4, 9.0, 8.65, 9.625, 9.899999999999999, 9.55, 9.05, 8.35, 10.1, 10.1, 9.899999999999999, 10.225, 10.0, 10.55, 10.45, 9.2, 10.2, 8.95, 10.05, 10.2, 9.5, 9.925, 9.95, 10.05, 8.75, 9.2, 10.15, 9.8, 10.7, 10.5, 9.55, 10.55, 10.475, 8.649999999999999, 10.7, 9.1, 9.4, 10.3, 9.65, 9.5, 9.7, 10.525, 9.95, 10.1, 9.75, 10.05, 9.9, 10.0, 9.1, 9.45, 9.25, 9.5, 10.0, 10.524999999999999, 9.899999999999999, 10.399999999999999, 8.95, 9.4, 10.95, 10.75, 10.100000000000001, 8.05, 9.1, 9.55, 9.05, 10.2, 10.0, 10.55, 10.75, 8.175, 9.7, 8.8, 10.75, 9.3, 9.7, 9.600000000000001, 9.75, 9.600000000000001, 10.45, 11.0, 10.85, 10.149999999999999, 10.350000000000001, 10.4, 9.95, 9.1, 10.1, 9.85, 9.625, 9.475, 9.0, 9.25, 9.100000000000001, 9.25, 9.2, 9.95, 8.65, 9.8, 9.4, 9.0, 8.55, 8.75, 9.65, 8.95, 9.15, 9.85, 10.225, 9.825, 10.0, 9.425, 10.4, 9.875, 8.95, 8.9, 9.350000000000001, 10.425, 10.0, 10.175, 9.875, 9.875, 9.15, 9.45, 9.025, 9.7, 9.7, 10.05, 10.3, 9.6, 10.0, 9.8, 10.05, 8.75, 10.55, 9.7, 10.0, 9.85, 9.8, 9.175, 9.649999999999999, 9.55, 9.9, 11.55, 11.3, 10.4, 10.8, 9.8, 10.45, 10.0, 10.75, 9.350000000000001, 10.75, 9.175, 9.65, 8.8, 10.55, 10.675, 9.95, 9.55, 8.825, 9.7, 9.850000000000001, 9.8, 9.55, 9.274999999999999, 10.325, 9.15, 9.35, 9.149999999999999, 9.65, 10.575, 9.975000000000001, 9.55, 9.2, 9.925, 9.2, 9.3, 8.775, 9.325, 9.175, 9.325, 8.975000000000001, 9.7, 9.5, 10.225000000000001, 10.025, 8.2, 8.2, 9.55, 9.05, 9.600000000000001, 9.600000000000001, 10.15, 9.875, 10.485, 11.485, 10.985, 9.7, 9.65, 9.35, 10.05, 10.100000000000001, 9.9, 8.95, 9.3, 9.95, 9.45, 9.5, 8.45, 8.8, 8.525, 9.375, 10.2, 7.625, 8.375, 9.25, 9.4, 10.55, 8.9, 8.8, 9.0, 8.575, 8.575, 9.600000000000001, 9.375, 9.600000000000001, 9.95, 9.6, 10.2, 9.850000000000001, 9.625, 9.025, 10.375, 10.25, 9.3, 9.5, 9.55, 8.55, 9.05, 9.9, 9.8, 9.75, 10.25, 9.1, 9.65, 10.3, 8.9, 9.95, 9.5, 9.774999999999999, 9.425, 7.75, 7.550000000000001, 9.1, 9.6, 9.575, 8.95, 9.649999999999999, 9.65, 9.65, 9.525, 9.85, 9.05, 9.3, 8.899999999999999, 9.45, 10.0, 9.85, 9.25, 10.1, 9.125, 9.65, 9.100000000000001, 8.05, 7.4, 8.85, 9.075, 9.0, 9.7, 8.7, 9.45, 9.7, 8.35, 8.85, 9.7, 9.45, 10.3, 10.0, 10.45, 9.45, 8.5, 8.3, 10.0, 9.225, 9.75, 9.149999999999999, 9.55, 9.0, 9.274999999999999, 9.35, 8.95, 9.875, 8.45, 8.600000000000001, 9.7, 8.55, 9.05, 9.600000000000001, 8.65, 9.2, 8.95, 9.6, 9.15, 9.399999999999999, 8.95, 9.95, 10.55, 9.7, 8.850000000000001, 8.8, 10.0, 9.05, 8.2, 8.1, 7.25, 8.3, 9.15, 8.600000000000001, 9.5, 8.05, 9.425, 9.3, 9.8, 9.3, 9.85, 9.5, 8.65, 9.825, 9.0, 10.45, 9.1, 9.55, 9.05, 10.0, 9.350000000000001, 8.375, 8.3, 8.8, 10.100000000000001, 9.5, 9.75, 10.100000000000001, 9.575, 9.425, 9.65, 8.725, 9.025, 8.5, 8.95, 9.3, 8.85, 8.95, 9.8, 9.5, 8.65, 9.100000000000001, 9.399999999999999, 8.475, 9.35, 7.95, 9.350000000000001, 8.575, 9.05, 8.175, 9.850000000000001, 7.85, 9.850000000000001, 10.1, 9.350000000000001, 8.850000000000001, 8.75, 9.625, 9.25, 9.55, 10.325, 8.55, 9.675, 9.15, 9.0, 9.649999999999999, 8.6, 8.8, 9.0, 9.95, 8.4, 9.35, 10.3, 9.05, 9.975, 9.975000000000001, 8.65, 8.725000000000001, 8.2, 7.8500000000000005, 8.774999999999999, 8.5, 9.4]\n",
    "\n",
    "bd_offspring_fortis = [10.7, 9.78, 9.48, 9.6, 10.27, 9.5, 9.0, 7.46, 7.65, 8.63, 9.81, 9.4, 9.48, 8.75, 7.6, 10.0, 10.09, 9.74, 9.64, 8.49, 10.15, 10.28, 9.2, 10.01, 9.03, 9.94, 10.5, 9.7, 10.02, 10.04, 9.43, 8.1, 9.5, 9.9, 9.48, 10.18, 10.16, 9.08, 10.39, 9.9, 8.4, 10.6, 8.75, 9.46, 9.6, 9.6, 9.95, 10.05, 10.16, 10.1, 9.83, 9.46, 9.7, 9.82, 10.34, 8.02, 9.65, 9.87, 9.0, 11.14, 9.25, 8.14, 10.23, 8.7, 9.8, 10.54, 11.19, 9.85, 8.1, 9.3, 9.34, 9.19, 9.52, 9.36, 8.8, 8.6, 8.0, 8.5, 8.3, 10.38, 8.54, 8.94, 10.0, 9.76, 9.45, 9.89, 10.9, 9.91, 9.39, 9.86, 9.74, 9.9, 9.09, 9.69, 10.24, 8.9, 9.67, 8.93, 9.3, 8.67, 9.15, 9.23, 9.59, 9.03, 9.58, 8.97, 8.57, 8.47, 8.71, 9.21, 9.13, 8.5, 9.58, 9.21, 9.6, 9.32, 8.7, 10.46, 9.29, 9.24, 9.45, 9.35, 10.19, 9.91, 9.18, 9.89, 9.6, 10.3, 9.45, 8.79, 9.2, 8.8, 9.69, 10.61, 9.6, 9.9, 9.26, 10.2, 8.79, 9.28, 8.83, 9.76, 10.2, 9.43, 9.4, 9.9, 9.5, 8.95, 9.98, 9.72, 9.86, 11.1, 9.14, 10.49, 9.75, 10.35, 9.73, 9.83, 8.69, 9.58, 8.42, 9.25, 10.12, 9.31, 9.99, 8.59, 8.74, 8.79, 9.6, 9.52, 8.93, 10.23, 9.35, 9.35, 9.09, 9.04, 9.75, 10.5, 9.09, 9.05, 9.54, 9.3, 9.06, 8.7, 9.32, 8.4, 8.67, 8.6, 9.53, 9.77, 9.65, 9.43, 8.35, 8.26, 9.5, 8.6, 9.57, 9.14, 10.79, 8.91, 9.93, 10.7, 9.3, 9.93, 9.51, 9.44, 10.05, 10.13, 9.24, 8.21, 8.9, 9.34, 8.77, 9.4, 8.82, 8.83, 8.6, 9.5, 10.2, 8.09, 9.07, 9.29, 9.1, 10.19, 9.25, 8.98, 9.02, 8.6, 8.25, 8.7, 9.9, 9.65, 9.45, 9.38, 10.4, 9.96, 9.46, 8.26, 10.05, 8.92, 9.5, 9.43, 8.97, 8.44, 8.92, 10.3, 8.4, 9.37, 9.91, 10.0, 9.21, 9.95, 8.84, 9.82, 9.5, 10.29, 8.4, 8.31, 9.29, 8.86, 9.4, 9.62, 8.62, 8.3, 9.8, 8.48, 9.61, 9.5, 9.37, 8.74, 9.31, 9.5, 9.49, 9.74, 9.2, 9.24, 9.7, 9.64, 9.2, 7.5, 7.5, 8.7, 8.31, 9.0, 9.74, 9.31, 10.5, 9.3, 8.12, 9.34, 9.72, 9.0, 9.65, 9.9, 10.0, 10.1, 8.0, 9.07, 9.75, 9.33, 8.11, 9.36, 9.74, 9.9, 9.23, 9.7, 8.2, 9.35, 9.49, 9.34, 8.87, 9.03, 9.07, 9.43, 8.2, 9.19, 9.0, 9.2, 9.06, 9.81, 8.89, 9.4, 10.45, 9.64, 9.03, 8.71, 9.91, 8.33, 8.2, 7.83, 7.14, 8.91, 9.18, 8.8, 9.9, 7.73, 9.25, 8.7, 9.5, 9.3, 9.05, 10.18, 8.85, 9.24, 9.15, 9.98, 8.77, 9.8, 8.65, 10.0, 8.81, 8.01, 7.9, 9.41, 10.18, 9.55, 9.08, 8.4, 9.75, 8.9, 9.07, 9.35, 8.9, 8.19, 8.65, 9.19, 8.9, 9.28, 10.58, 9.0, 9.4, 8.91, 9.93, 10.0, 9.37, 7.4, 9.0, 8.8, 9.18, 8.3, 10.08, 7.9, 9.96, 10.4, 9.65, 8.8, 8.65, 9.7, 9.23, 9.43, 9.93, 8.47, 9.55, 9.28, 8.85, 8.9, 8.75, 8.63, 9.0, 9.43, 8.28, 9.23, 10.4, 9.0, 9.8, 9.77, 8.97, 8.37, 7.7, 7.9, 9.5, 8.2, 8.8]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "6d20c7f5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Make scatter plots\n",
    "_ = plt.plot(bd_parent_fortis, bd_offspring_fortis,\n",
    "             marker='.', linestyle='none', color='blue', alpha=.5)\n",
    "_ = plt.plot(bd_parent_scandens, bd_offspring_scandens,\n",
    "             marker='.', linestyle='none', color='red', alpha=.5)\n",
    "\n",
    "# Label axes\n",
    "_ = plt.xlabel('parental beak depth (mm)')\n",
    "_ = plt.ylabel('offspring beak depth (mm)')\n",
    "\n",
    "# Add legend\n",
    "_ = plt.legend(('G. fortis', 'G. scandens'), loc='lower right')\n",
    "\n",
    "# Show plot\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Welcome to DataCamp Workspaces.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}