bigdata/day2/线性回归.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "bd71a510",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:01.293774Z",
     "start_time": "2024-02-29T02:43:00.530213Z"
    }
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv('women.csv', header=0, index_col=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "42bf78f1",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:01.310328Z",
     "start_time": "2024-02-29T02:43:01.294781Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "           height     weight\ncount   20.000000  20.000000\nmean   142.500000  66.650000\nstd     16.922424   4.901933\nmin    115.000000  58.000000\n25%    128.250000  62.750000\n50%    144.000000  67.500000\n75%    156.750000  70.250000\nmax    165.000000  74.000000",
      "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>height</th>\n      <th>weight</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>count</th>\n      <td>20.000000</td>\n      <td>20.000000</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>142.500000</td>\n      <td>66.650000</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>16.922424</td>\n      <td>4.901933</td>\n    </tr>\n    <tr>\n      <th>min</th>\n      <td>115.000000</td>\n      <td>58.000000</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n      <td>128.250000</td>\n      <td>62.750000</td>\n    </tr>\n    <tr>\n      <th>50%</th>\n      <td>144.000000</td>\n      <td>67.500000</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n      <td>156.750000</td>\n      <td>70.250000</td>\n    </tr>\n    <tr>\n      <th>max</th>\n      <td>165.000000</td>\n      <td>74.000000</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "5d234081",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:01.318895Z",
     "start_time": "2024-02-29T02:43:01.311536Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 20 entries, 1 to 20\n",
      "Data columns (total 2 columns):\n",
      " #   Column  Non-Null Count  Dtype\n",
      "---  ------  --------------  -----\n",
      " 0   height  20 non-null     int64\n",
      " 1   weight  20 non-null     int64\n",
      "dtypes: int64(2)\n",
      "memory usage: 480.0 bytes\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "d89ab65f",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:01.323643Z",
     "start_time": "2024-02-29T02:43:01.320196Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "(20, 2)"
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a2225b04",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:01.896026Z",
     "start_time": "2024-02-29T02:43:01.324669Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "<Figure size 640x480 with 1 Axes>",
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAi0AAAHDCAYAAADoTyodAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAAA77ElEQVR4nO3df1yV9f3/8ecBhKMJB5EUCpKDlX3OzCWVUtpW2yxK2bKt1g/XrI9z6Za3WTY/1Lcbo1q2VlNbKm6tLM3PZ7abSymjVVptfVhkGkrHfqCgoIdhooeDckA51/cPxvlwBBTwcA4XPO6323Vb13W9z8WL60Y7z97v63q/LYZhGAIAAOjjIsJdAAAAQFcQWgAAgCkQWgAAgCkQWgAAgCkQWgAAgCkQWgAAgCkQWgAAgCkQWgAAgCkQWgAEVWNjoyoqKuTz+XT8+HFVVFTo+PHj/vPHjx9Xd+a09Hq9+uSTT+TxeHqjXAAmQmgBEFQ7d+6U3W5XfX29du/eLbvdrn379vnPv/LKKzr33HN14MCBLl2voqJC48ePV3Fx8Wnb+nw+HTlypNvbiRMnevz7AgidqHAXAKD/8Hq9iomJkSRZrVZFR0dLkiIjI9XU1KTo6Gh9+OGHGjNmjM4555wuXbP1eq3XamUYhhobG2WxWPxtqqqqNGrUqG7X/dprr2nq1Knd/hyA0KKnBUDQnH/++Ro3bpyklrAxevRoSZLdbteDDz4oSdq8ebNuueUW/2d8Pp+8Xm+n17RYLJKkb3zjG7JYLP4tIiJCgwcP1qOPPupvGxXV8t9hO3fulGEYMgxDx48f18MPP6zKykr/sbZbZGRku0AEoG+ipwVA0Hz55ZeqqKiQw+HQ8ePHVVVVJbvdroqKCo0cOVJ79uxRaWmp5s6dq7lz5/o/9+1vf1tvv/32Ka/92muvaeLEif59wzB07NgxDR061H9s0KBB7T733HPP6bHHHtNll10W0DY2NlaRkZGS5P9fAH0boQVAUJw4cUIRER133rb2jKxevVqJiYlavHixJGnWrFlauHChJkyYcNrr22w2JSYmnrLNyaFl//79euihh2QYhr73ve/5j48cOVJffvmlYmNjJanTugH0LYQWAEHx9ttv6/rrr/fvtw0Qo0aN0uzZs/X666/LZrNpxowZ8vl8uvPOO3XzzTdr7Nix/rYNDQ3617/+5d+vqqqSJFVXV6uioiLgZ55zzjmdDu00NDTohz/8oWpra/X888/rrrvuUkVFhTIyMrRy5Up/YAFgHoQWAEHxne98Rw0NDYqJifE/h9LK6/VqyZIlOnTokCwWiwzDUG1trQzDkM1mC2j77rvv6oYbbmh3/ZtvvrndsY8++kiXXXZZh/UsXrxYBw8e1Ouvv67bb79d+/fv10svvaQFCxYE9LoAMA/6RAEERVRUlKxWqzIyMpSUlKSUlBSlpKRo5MiRGjNmjDIyMvTSSy+psbFRe/bsUXl5uSwWi5KSkgKu09pzUl5e3uGDs4Zh6Msvvwxo25GcnBx98MEHmjx5sq677jo9/PDDamxs1LXXXtt7NwFAryK0AAiqxsZGPfXUU6qqqlJVVZVycnLU0NCga6+9VjfffLPS09P197//Xdu3b1dSUlK751C68yZPRw/eSi1vJK1bt04PPfSQRo0apcOHD+uDDz7QzTffrKuuukqXXHKJfv7zn6usrOyMflcAocXwEICgio6O1o9//GPNnDlTUstbPsnJyf7zkyZN0rp162S1WnXppZe2+7zP55P0f8+ydGT//v2S1OmkcBEREfrf//1fWSwWvfHGG/rb3/6mmTNnavbs2froo4/09ttv67333lNqampPf00AYUBoARB0L774ombMmCFJWrJkiZ566in/uRtvvFE33XSTIiIi9Jvf/KbdZ1vnbLnqqqtO+3MaGxs7Pbd06VJJLcHG4XAoPj5eS5Ys0RdffKE//OEP+sUvftGdXwlAH0BoARBSU6dO1Xnnnad//etf/t6YtpKSkjpdm8gwjICHfNuuadSZu+++W5988oluvPFGrV+/Xunp6T2uHUB48UwLgKAyDEM/+tGP/DPXzp8/P+D8F198Ia/XK5/Pp1deeSXg3Pbt23XJJZfoz3/+s44cOaJp06b5H7r9xz/+ocsuu8zfu/LKK68oIyNDTU1N/s83Nze3q+fxxx/XT3/6U7311lsaP3685s2b165N65AUgL6N0AIgqJqamrR69WoZhqHq6mrNmTPHP+PsO++8o2uuuUa33367/vCHP+i+++7TtGnT9NFHH0mSli1bpvPOO0833XSTbDabPvvsMz377LOSpDFjxuiLL77QM888I0maMGGCdu/eHTDE1PqMS2VlpcrKylRWViav16vrrrtOq1ev1quvvqrp06f7z7U+iMuCiYBJGAAQROnp6cbq1asNwzCMd955xxgyZIixaNEi409/+pMxatQo49VXX/W3/eKLL4xrr73W+NWvfmV89tlnxqBBg4zf//73/vOPPvqoYbPZjKNHjxqGYRi//OUvjYSEBMPj8RiGYRgPP/ywMXjwYKOiosIwDMPYv3+/Ianb2+uvvx6q2wPgDPBMC4Cg2r17t/+fr7nmGnk8Hv80+TNmzAh4pfmCCy7Qm2++Kamld2TevHmaNWuW//wtt9yi8847z/9q87x58+RwODRkyBBJ0vz589XQ0OCf3ba1x2Tnzp0Bs+yeSlRUFD0tgElYDKOTJ94AwGROnDihiooKnXfeeazcDPRDhBYAAGAKPIgLAABMgdACAABMgdACAABMod+8PeTz+XTgwAHFxsYGzJgJAAD6LsMw5PF4dM455/jfNOxMvwktBw4cYPEzAABMqrKyUikpKads029CS+s8DZWVlYqLiwtzNQAAoCvq6uqUmprq/x4/lX4TWlqHhOLi4ggtAACYTFce7eBBXAAAYAqEFgAAYAqEFgAAYAqEFgAAYAqEFgAAYAqEFgAAYAqEFgAAYAqEFgAAYAqEFgAAYAohDy2rVq2SxWJpt61atcrf5vjx47r44ov17rvvhro8AABwkmafoaLdh7Thk/0q2n1IzT4jLHWEfBr/22+/XTfeeKN/v76+XuPHj9dVV13lP/bkk0+qtLQ01KUBAICTFJa6lFfglMvt9R9LtlmVm+1Q1tjkkNYS8p6W6OhoxcfH+7eXXnpJ06dP1+jRoyVJX375pZ566imlpaWFujQAANBGYalLc9ZsCwgsklTt9mrOmm0qLHWFtJ6wPtPi9Xq1dOlSPfjgg/5jP/3pT/Vf//VfGjVqVBgrAwBgYGv2GcorcKqjgaDWY3kFzpAOFYU1tKxdu1YTJ07096q88MILcrvdWrBgwWk/29jYqLq6uoANAAAER3F5bbselrYMSS63V8XltSGrKayhJT8/X/fcc48k6eDBg8rJydHzzz+vyMjI03520aJFstls/i01NbW3ywUAYMCo8XQeWHrSLhjCFlrKyspUVlamKVOmSJJ+8Ytf6D//8z/19a9/vUufz8nJkdvt9m+VlZW9WS4AAAPKiFhrUNsFQ9hCy7p16zRt2jQNGjRIUstQ0e9//3v/A7r/+Mc/NG3aND3xxBMdfj4mJkZxcXEBGwAACI4J9gQl26yydHLeopa3iCbYE0JWU8hfeW5VWFiomTNn+vfLy8sDzt966636xS9+oaysrBBXBgAAIiMsys12aM6abbJIAQ/ktgaZ3GyHIiM6izXBF5aeloaGBn344Ye68sor/cfS0tICNqvVqqSkJMXHx4ejRAAABryssclaMSNDSbbAIaAkm1UrZmSEfJ4Wi2EY4ZnWLsjq6upks9nkdrsZKgIAIIiafYaKy2tV4/FqRGzLkFCweli68/0dtuEhAABgDpERFl0xeni4y2DBRAAAYA6EFgAAYAqEFgAAYAqEFgAAYAqEFgAAYAqEFgAAYAqEFgAAYAqEFgAAYAqEFgAAYArMiAsAwADWm1P0BxuhBQCAAaqw1KW8Aqdcbq//WLLNqtxsR8gXQ+wKhocAABiACktdmrNmW0BgkaRqt1dz1mxTYakrTJV1jtACAMAA0+wzlFfglNHBudZjeQVONfs6ahE+hBYAAAaY4vLadj0sbRmSXG6vistrQ1dUFxBaAAAYYGo8nQeWnrQLFUILAAADzIhYa1DbhQqhBQCAAWaCPUHJNqs6e7HZopa3iCbYE0JZ1mkRWgAAGGAiIyzKzXZIUrvg0rqfm+3oc/O1EFoAABiAssYma8WMDCXZAoeAkmxWrZiR0SfnaWFyOQAABqisscma4khiRlwAAND3RUZYdMXo4eEuo0sYHgIAAKZAaAEAAKZAaAEAAKZAaAEAAKZAaAEAAKZAaAEAAKZAaAEAAKZAaAEAAKZAaAEAAKYQ8tCyatUqWSyWdtuqVav0hz/8QcnJyRo0aJC++c1vyuVyhbo8AAAGlGafoaLdh7Thk/0q2n1IzT4j3CV1ymIYRkira2pq0rFjx/z79fX1Gj9+vP7yl7/olltu0csvv6yLLrpIt99+u1JTU/Xyyy936bp1dXWy2Wxyu92Ki4vrrfIBAOg3CktdyitwyuX2+o8l26zKzXaEbMHE7nx/h7ynJTo6WvHx8f7tpZde0vTp07Vnzx6tXLlS3/nOd5SSkqK77rpL27dvD3V5AAAMCIWlLs1Zsy0gsEhStdurOWu2qbC07412hHXBRK/Xq6VLl+rDDz9UWlpawLnPP/9cF1xwQXgKAwCgH2v2GcorcKqjoRZDkkVSXoFTUxxJfWrF57CGlrVr12rixIntAkttba1WrlyptWvXdvrZxsZGNTY2+vfr6up6q0wAAPqV4vLadj0sbRmSXG6vistr+9QK0GF9eyg/P1/33HNPu+M/+9nPdOWVV+r666/v9LOLFi2SzWbzb6mpqb1ZKgAA/UaNp/PA0pN2oRK20FJWVqaysjJNmTIl4PiLL76oLVu26Pnnnz/l53NycuR2u/1bZWVlb5YLAEC/MSLWGtR2oRK24aF169Zp2rRpGjRokP/Y1q1bde+992rjxo0aOXLkKT8fExOjmJiY3i4TAIB+Z4I9Qck2q6rd3g6fa7FISrJZNcGeEOrSTilsPS2FhYW6+uqr/fs1NTXKzs7WL3/5S1122WWqr69XfX19uMoDAKDfioywKDfbIakloLTVup+b7ehTD+FKYQotDQ0N+vDDD3XllVf6j/33f/+3qqur9fDDDys2Nta/AQCA4Msam6wVMzKUZAscAkqyWbViRkbI5mnpjpBPLtdbmFwOAIDua/YZKi6vVY3HqxGxLUNCoexh6c73d1hfeQYAAOEVGWHpU681nwoLJgIAAFMgtAAAAFMgtAAAAFMgtAAAAFMgtAAAAFMgtAAAAFMgtAAAAFMgtAAAAFMgtAAAAFNgRlwAAIKk6YRPq4sqtLf2mEYlDNGPrkhTdBT9A8FCaAEAIAgWbXLqj38vl6/Nin6/3rRLP7nKrpwbHOErrB8htAAAcIYWbXJq5fvl7Y77DPmPE1zOHH1WAACcgaYTPv3x7+0DS1t//Hu5mk74QlRR/0VoAQDgDKwuqggYEuqIz2hphzNDaAEA4AzsrT0W1HboHKEFAIAzMCphSFDboXOEFgAAzsCPrkhThOXUbSIsLe1wZggtAACcgeioCP3kKvsp2/zkKjvztQQBrzwDAHCGWl9nPnmelgiLmKcliCyGYZzmmWdzqKurk81mk9vtVlxcXLjLAQAMQMyI233d+f6mpwUAgCCJjorQf16VHu4y+i3iHwAAMAVCCwAAMAVCCwAAMAVCCwAAMAVCCwAAMAVCCwAAMAVCCwAAMAVCCwAAMAVCCwAAMAVmxAUA9EnNPkPF5bWq8Xg1ItaqCfYERZ60nHKw2sAcQh5aVq1apbvuuqvd8RdeeEF2u1333HOPDh48qAcffFD33XdfqMsDAPQBhaUu5RU45XJ7/ceSbVblZjuUNTY5qG1gHiFfMLGpqUnHjh3z79fX12v8+PF67bXXdO211+r+++/XbbfdpltvvVVPPfWUrrnmmi5dlwUTAaB/KCx1ac6abTr5y6m1b2TFjAxJCkobgkv4def7O+yrPD/++OOqqKiQw+HQypUr5XQ6ZbFYtGHDBr3yyitas2ZNl65DaAEA82v2GZr8m80BPSNtWSSNjIuRZFF13Zm1SbJZ9Y+F32KoKMy68/0d1gdxvV6vli5dqgcffFAlJSW65pprZLG0/PFMmDBBH3/8caefbWxsVF1dXcAGADC34vLaTgOLJBmSqusaOw0j3WnjcntVXF7b82IRcmENLWvXrtXEiROVlpamuro62e12/7m4uDgdOHCg088uWrRINpvNv6WmpoaiZABAL6rxdB40+sPPw5kJa2jJz8/XPffcI0mKiopSTEyM/5zVag149uVkOTk5crvd/q2ysrLX6wUA9K4RsdZ+/fNwZsL2ynNZWZnKyso0ZcoUSVJCQoIOHjzoP+/xeBQdHd3p52NiYgJCDgDA/CbYE5Rss6ra7W33AK0U+LzKv+rOrE2SreX1Z5hH2Hpa1q1bp2nTpmnQoEGSpMsvv1xFRUX+89u3b9e5554brvIAAGEQGWFRbrZD0v+95dOqdf9X3/2afvXdM2+Tm+3gIVyTCVtoKSws1NVXX+3f/+53v6sPPvhAb7/9to4fP64nn3xS1113XbjKAwCESdbYZK2YkaEkW+DQTZLN6n9NOVhtYC5heeW5oaFB8fHxKikp0UUXXeQ/np+fr3nz5mno0KGKj49XUVGRRo4c2aVr8sozAPQvzIg7MJhqnpaTlZeX67PPPtNVV12loUOHdvlzhBYAAMynO9/ffW7tIbvdHvDqMwAAgMQqzwAAwCQILQAAwBQILQAAwBQILQAAwBQILQAAwBQILQAAwBQILQAAwBQILQAAwBT63ORyAIDQY6p7mAGhBQAGuMJSl/IKnHK5vf5jyTarcrMdLCqIPoXhIQAYwApLXZqzZltAYJGkardXc9ZsU2GpK0yVAe0RWgBggGr2GcorcKqjVXNbj+UVONXs61Pr6mIAI7QAwABVXF7broelLUOSy+1VcXlt6IoCToHQAgADVI2n88DSk3ZAbyO0AMAANSLWGtR2QG8jtADAADXBnqBkm1WdvdhsUctbRBPsCaEsC+gUoQUABqjICItysx2S1C64tO7nZjuYrwV9BqEFAAawrLHJWjEjQ0m2wCGgJJtVK2ZkME8L+hQmlwOAAS5rbLKmOJKYERd9HqEFAKDICIuuGD083GUAp8TwEAAAMAVCCwAAMAVCCwAAMAVCCwAAMAVCCwAAMAVCCwAAMAVCCwAAMAVCCwAAMAVCCwAAMIWwhpaFCxcqOzvbv//cc88pNTVVQ4YM0dVXX609e/aEsToA6D3NPkNFuw9pwyf7VbT7kJp9RrhLAvo8i2EYYfk3ZceOHZo0aZJKSkqUnp6u3bt365prrtGrr76qxMRE5eXl6csvv9T777/fpevV1dXJZrPJ7XYrLi6ul6sHgJ4rLHUpr8Apl9vrP5Zssyo328EChRhwuvP9HZaeFp/Pp9mzZ2v+/PlKT0+XJG3fvl2ZmZnKyMjQeeedp7vvvltlZWXhKA8Aek1hqUtz1mwLCCySVO32as6abSosdYWpMqDvC0toyc/P186dO5WWlqaNGzeqqalJDodDmzdv1ieffCK3263ly5drypQp4SgPAHpFs89QXoFTHXVvtx7LK3AyVAR0IuSrPNfX1ys3N1fp6enau3evVq9erccee0zvvfeefvCDH2j8+PGSJLvdrg8//LDT6zQ2NqqxsdG/X1dX1+u1A8CZKC6vbdfD0pYhyeX2qri8lhWXgQ6EvKdl/fr1Onr0qLZs2aK8vDy99dZb8ng8+v3vf6+CggL985//1JEjR3TbbbfphhtuUGeP3CxatEg2m82/paamhvg3AYDuqfF0Hlh60g4YaEIeWqqqqpSZmanExERJUlRUlMaNGyeXy6Vbb71VEydOlM1m02OPPabdu3erpKSkw+vk5OTI7Xb7t8rKylD+GgDQbSNirUFtBww0IQ8tKSkpamhoCDi2d+9eLVmyRDU1Nf5jHo9Hx44dU3Nzc4fXiYmJUVxcXMAGAH3ZBHuCkm1WWTo5b1HLW0QT7AmhLAswjZCHlqlTp8rpdCo/P19VVVV65plnVFJSopdeeknr16/X4sWLtXbtWt14441KSkrSuHHjQl0iAPSKyAiLcrMdktQuuLTu52Y7FBnRWawBBraQP4g7fPhwbdq0SQsWLNB9992n5ORkrVu3TtOmTVNFRYWWLFkil8ulsWPH6q9//asGDRoU6hIBoNdkjU3WihkZ7eZpSWKeFuC0wja5XLAxuRwAM2n2GSour1WNx6sRsS1DQvSwYCDqzvd3yHtaAAAtQ0W81gx0DwsmAgAAUyC0AAAAUyC0AAAAUyC0AAAAUyC0AAAAUyC0AAAAUyC0AAAAUyC0AAAAUyC0AAAAU2BGXAADAtPmA+ZHaAHQ7xWWutotUJjMAoWA6TA8BKBfKyx1ac6abQGBRZKq3V7NWbNNhaWuMFUGoLsILQD6rWafobwCpzpayr71WF6BU82+frHYPdDvEVoA9FvF5bXteljaMiS53F4Vl9eGrigAPUZoAdBv1Xg6Dyw9aQcgvAgtAPqtEbHWoLYDEF6EFgD91gR7gpJtVnX2YrNFLW8RTbAnhLIsAD3U7dCybt06NTc3Bxz7+9//rh/96EdBKwoAgiEywqLcbIcktQsurfu52Q7mawFMwmIYRrcem4+MjNThw4cVFxfnP3bgwAGlp6fL6w3fuHBdXZ1sNpvcbndAbQDAPC1A39Wd7+8uTy63b98+SZJhGKqsrFRsbKx/f9OmTUpJSTmDkgGg92SNTdYURxIz4gIm1+XQkpaWJovFIovFoosvvth/3GKx6Pzzz9fKlSt7pUAACIbICIuuGD083GUAOANdDi0+n0+SFBERocOHD8tms/VaUQAAACfr9oO4Y8aMUVQUSxYBAIDQ6nb62LVrV2/UAQAAcErdDi1FRUXKyclRZWWlTn7xaM+ePUErDAAAoK1uh5Y77rhDkyZN0kMPPaTo6OjeqAkAAKCdboeWw4cP67HHHtOoUaN6ox4AAIAOdftB3Pvuu095eXk6ceJEb9QDAADQoS71tNx9993+f26dTC4tLU2ZmZkBs9c9//zzwa8QAABAXQwtJw8FzZ07t1eKAQAA6Ey31x567bXXdPXVV2vo0KFn/MMXLlwop9OpgoKCLh0/FdYeAsyn2WcwtT4wwHXn+7vboWXUqFHavHmzvvrqK51//vkaPrxlWuxf//rXWrJkiZYvX66bb775tNfZsWOHJk2apJKSEqWnp5/2+OkQWgBzYRFDAFL3vr+7/SDuD3/4Q33961/X9OnTNWrUKD3zzDOSpN/+9rdatmyZHnvssdNew+fzafbs2Zo/f35AMOnsOID+pbDUpTlrtgUEFkmqdns1Z802FZa6wlQZgL6s26Hl5Zdf1muvvaYDBw6opKRECxcuVE1Njerr6/Xtb39bn3/++WmvkZ+fr507dyotLU0bN25UU1PTKY8D6D+afYbyCpzqqIu39VhegVPNvm51AgMYALodWmJiYrR//341Nzdr//79ioqK0uHDhzVs2DAdP35cgwYNOuXn6+vrlZubq/T0dO3du1eLFy/W5MmT5fF4Ojze0NDQ4XUaGxtVV1cXsAHo+4rLa9v1sLRlSHK5vSourw1dUQBModuTyz333HO68847deedd2rYsGGaOHGi7rjjDg0ePFgPPfSQxo4de8rPr1+/XkePHtWWLVuUmJioEydO6OKLL9bixYs7PL569WrNnj273XUWLVqkvLy87pYPIMxqPJ0Hlp60AzBwdLun5Vvf+paqqqpUXV2tmpoabdq0Sb/+9a/ldDp17rnn6tlnnz3l56uqqpSZmanExERJUlRUlMaNG6fHHnusw+NlZWUdXicnJ0dut9u/VVZWdvdXARAGI2KtQW0HYODodk9Lq7PPPluSFB0dreuuu06S9Mgjj5z2cykpKe2GfPbu3auHHnpIhYWF7Y5feeWVHV4nJiZGMTExPSkdQBhNsCco2WZVtdvb4XMtFklJtpbXnwGgrW73tJypqVOnyul0Kj8/X1VVVXrmmWdUUlKimTNndnj8pptuCnWJAHpRZIRFudkOSS0Bpa3W/dxsB/O1AGgn5KFl+PDh2rRpk1588UVdeOGFWrp0qdatW6dRo0Z1eDw1NTXUJQLoZVljk7ViRoaSbIFDQEk2q1bMyGCeFgAd6tLkcunp6dqxY4eGDh0qu90ui6Xj/wLas2dP0AvsKiaXA8yHGXEBdOf7u0vPtLzwwgsaMmSIJGnVqlVnXCAASC1DRVeMHh7uMgCYRLen8e+r6GkBAMB8enUafwAAgHA4o9DS1NQkwzDk8/mCVQ8AAECHuh1aPB6PZs+erZEjR2rIkCHauXOnUlJS9PHHH/dGfQAAAJJ6EFruuusuVVRU6MUXX9RZZ50lm82m+fPn62c/+1lv1AcAACCpBw/ixsfHa+fOnUpNTdWwYcNUUlIiq9Wq0aNHy+Px9Fadp8WDuAAAmE+vPoh70UUX+V97tlgsslgsev/99/W1r32tR8UCAAB0Rbd7WrZu3arrr79e0dHRqqmp0WWXXaZ9+/Zp48aNuvTSS3urztOipwUAAPMJ+uRyba1evVoPPfSQ6urqNHjwYKWkpOiGG26QzWbrccEAAACn0+3QEhMTo/fee09ffvmlDhw4oPPPP1/vvfeeMjIyNHv27N6oEUCQMG0+ADPr9vBQY2OjPvvsM3322Wf69NNP9cYbb6isrEwXXnihPvzww96q87QYHgJOrbDUpbwCp1xur/9Yss2q3GwHCxQCCJvufH93O7RERkZq0qRJmjZtmr7xjW/oggsu0PDh4V87hNACdK6w1KU5a7bp5H/ZW/tYWFkZQLj06jMt69ev165du+R0OvXWW2/J5/Np5MiRGjNmjHJzc3tcNIDe0ewzlFfgbBdYJMlQS3DJK3BqiiOJoSIAfVq3Q4vNZtPw4cN19tln68iRI9q1a5fKysrU0NDQG/UBOEPF5bUBQ0InMyS53F4Vl9ey4jKAPq3boWXu3LnKyMjQJZdcoqysLI0fP14JCQm9URuAIKjxdB5YetIOAMKl26HF6XT2Rh0AesmIWGtQ2wFAuJzRKs8A+r4J9gQl26zq7GkVi1reIppgp8cUQN9GaAH6ucgIi3KzHZLULri07udmO3gIF0CfR2gBBoCssclaMSNDSbbAIaAkm5XXnQGYRrefaQFgTlljkzXFkcSMuABMi9ACDCCRERZeawZgWgwPAQAAUyC0AAAAUyC0AAAAUyC0AAAAUyC0AAAAUyC0AAAAUyC0AAAAUyC0AAAAUyC0AAAAUwhraFm4cKGys7M7PJeVlaVVq1aFtiAgDJp9hop2H9KGT/araPchNfuMcJcEAH1S2Kbx37Fjh5YvX66SkpJ2515++WW9+eabuvXWW8NQGRA6haUu5RU45XJ7/ceSbVblZjtYxBAAThKWnhafz6fZs2dr/vz5Sk9PDzhXW1ur+++/X2PGjAlHaUDIFJa6NGfNtoDAIknVbq/mrNmmwlJXmCoDgL4pLKElPz9fO3fuVFpamjZu3Kimpib/ufvvv1/Tp09XZmZmOEoDQqLZZyivwKmOBoJaj+UVOBkqAoA2Qh5a6uvrlZubq/T0dO3du1eLFy/W5MmT1dDQoC1btuidd97Rk08+edrrNDY2qq6uLmADzKK4vLZdD0tbhiSX26vi8trQFQUAfVzIn2lZv369jh49qi1btigxMVEnTpzQxRdfrD/+8Y969tlntWLFCsXGxp72OosWLVJeXl4IKgaCr8bTeWDpSTsAGAhC3tNSVVWlzMxMJSYmSpKioqI0btw4lZeX6/LLL9fUqVO7dJ2cnBy53W7/VllZ2ZtlA0E1ItYa1HYAMBCEvKclJSVFDQ0NAcf27t2rdevW6ayzzlJ8fLwk6dixY1q3bp2Ki4u1fPnydteJiYlRTExMKEoGgm6CPUHJNquq3d4On2uxSEqyWTXBnhDq0gCgzwp5aJk6daruvfde5efna9q0aVq/fr1KSkq0b98+NTc3+9stWLBAmZmZmjlzZqhLBHpdZIRFudkOzVmzTRYpILhY/v2/udkORUZYOvg0AAxMIQ8tw4cP16ZNm7RgwQLdd999Sk5O1rp165SamhrQbujQoUpMTPQPIwH9TdbYZK2YkdFunpYk5mkBgA5ZDMPoF+9U1tXVyWazye12Ky4uLtzlAF3W7DNUXF6rGo9XI2JbhoToYQEwUHTn+ztsM+ICaBEZYdEVo4eHuwwA6PNYMBEAAJgCoQUAAJgCoQUAAJgCoQUAAJgCoQUAAJgCoQUAAJgCoQUAAJgCoQUAAJgCoQUAAJgCM+ICHWBqfQDoewgtwEkKS13tFjFMZhFDAAg7hoeANgpLXZqzZltAYJGkardXc9ZsU2GpK0yVAQAILcC/NfsM5RU41dGy563H8gqcavb1i4XRAcB0CC3AvxWX17brYWnLkORye1VcXhu6ogAAfoQW4N9qPJ0Hlp60AwAEF6EF+LcRsdagtgMABBehBfi3CfYEJdus6uzFZota3iKaYE8IZVkAgH8jtAD/FhlhUW62Q5LaBZfW/dxsB/O1AECYEFqANrLGJmvFjAwl2QKHgJJsVq2YkcE8LQAQRkwuB5wka2yypjiSmBEXAPoYQgvQgcgIi64YPTzcZQAA2mB4CAAAmAKhBQAAmAKhBQAAmAKhBQAAmAKhBQAAmAKhBQAAmAKhBQAAmAKhBQAAmAKhBQAAmEJYQ8vChQuVnZ3t39+wYYPS09MVFRWlSy65RLt27Qpjdehrmn2GinYf0oZP9qto9yE1+4xwlwQACCGLYRhh+X/+HTt2aNKkSSopKVF6erp2796tyy+/XPn5+frmN7+pe++9V/v379cHH3zQpevV1dXJZrPJ7XYrLi6ul6tHqBWWupRX4JTL7fUfS7ZZlZvtYBFDADCx7nx/h6Wnxefzafbs2Zo/f77S09MlSbt27dITTzyhW265RSNHjtScOXO0ffv2cJSHPqaw1KU5a7YFBBZJqnZ7NWfNNhWWusJUGQAglMISWvLz87Vz506lpaVp48aNampq0rRp0zR79mx/m88//1wXXHBBOMpDH9LsM5RX4FRH3YGtx/IKnAwVAcAAEPLQUl9fr9zcXKWnp2vv3r1avHixJk+erIaGBn+bpqYmPf3007rnnns6vU5jY6Pq6uoCNvQ/xeW17XpY2jIkudxeFZfXhq4oAEBYhDy0rF+/XkePHtWWLVuUl5ent956Sx6PR6tXr/a3yc3N1VlnnaVZs2Z1ep1FixbJZrP5t9TU1FCUjxCr8XQeWHrSDgBgXiEPLVVVVcrMzFRiYqIkKSoqSuPGjVNZWZkkafPmzVq2bJnWrl2rQYMGdXqdnJwcud1u/1ZZWRmS+hFaI2KtQW0HADCvqFD/wJSUlIChIEnau3evrrzySpWXl+u2227TsmXL5HA4TnmdmJgYxcTE9Gap6AMm2BOUbLOq2u3t8LkWi6Qkm1UT7AmhLg0AEGIh72mZOnWqnE6n8vPzVVVVpWeeeUYlJSW66aabNG3aNH3ve9/T9OnTVV9fr/r6eoXpjWz0EZERFuVmtwRYy0nnWvdzsx2KjDj5LACgvwnLPC0ffPCBFixYoJKSEiUnJ2vJkiXy+Xy68cYb27UtLy9XWlraaa/JPC39G/O0AED/1J3v77BNLhdshJb+r9lnqLi8VjUer0bEtgwJ0cMCAObWne/vkD/TAvRUZIRFV4weHu4yAABhwoKJAADAFAgtAADAFAgtAADAFAgtAADAFAgtAADAFAgtAADAFAgtAADAFAgtAADAFAgtAADAFJgRF2eEqfUBAKFCaEGPsYghACCUGB5CjxSWujRnzbaAwCJJ1W6v5qzZpsJSV5gqAwD0V4QWdFuzz1BegVMdLQ/eeiyvwKlmX79YQBwA0EcQWtBtxeW17XpY2jIkudxeFZfXhq4oAEC/R2hBt9V4Og8sPWkHAEBXEFrQbSNirUFtBwBAVxBa0G0T7AlKtlnV2YvNFrW8RTTBnhDKsgAA/RyhBd0WGWFRbrZDktoFl9b93GwH87UAAIKK0IIeyRqbrBUzMpRkCxwCSrJZtWJGBvO0AACCjsnl0GNZY5M1xZHEjLgAgJAgtOCMREZYdMXo4eEuAwAwADA8BAAATIHQAgAATIHQAgAATIHQAgAATIHQAgAATIHQAgAATIHQAgAATIHQAgAATIHQAgAATIEZcfuhZp/B1PoAgH4nrKFl4cKFcjqdKigokCSVlpbqrrvuUllZmWbNmqUnn3xSFgtftt1RWOpSXoFTLrfXfyzZZlVutoNFDAEApha24aEdO3Zo+fLlWrp0qSSpsbFR2dnZuvTSS7V161Y5nU6tWrUqXOWZUmGpS3PWbAsILJJU7fZqzpptKix1hakyAADOXFhCi8/n0+zZszV//nylp6dLkt544w253W797ne/0+jRo/X444/rT3/6UzjKM6Vmn6G8AqeMDs61HssrcKrZ11ELAAD6vrCElvz8fO3cuVNpaWnauHGjmpqaVFJSoszMTA0ZMkSSNG7cODmdzk6v0djYqLq6uoBtICsur23Xw9KWIcnl9qq4vDZ0RQEAEEQhDy319fXKzc1Venq69u7dq8WLF2vy5Mmqq6uT3W73t7NYLIqMjNThw4c7vM6iRYtks9n8W2pqaqh+hT6pxtN5YOlJOwAA+pqQh5b169fr6NGj2rJli/Ly8vTWW2/J4/Ho+eefV0xMTEBbq9WqY8eOdXidnJwcud1u/1ZZWRmK8vusEbHWoLYDAKCvCfnbQ1VVVcrMzFRiYmJLAVFRGjdunD777DMdPHgwoK3H41F0dHSH14mJiWkXcgayCfYEJdusqnZ7O3yuxSIpydby+jMAAGYU8p6WlJQUNTQ0BBzbu3evlixZoqKiIv+x8vJyNTY2KiGBL9muiIywKDfbIakloLTVup+b7WC+FgCAaYU8tEydOlVOp1P5+fmqqqrSM888o5KSEt10002qq6vTCy+8IEl6/PHH9Z3vfEeRkZGhLtG0ssYma8WMDCXZAoeAkmxWrZiRwTwtAABTsxiGEfJ3YD/44AMtWLBAJSUlSk5O1pIlS5Sdna2NGzfqtttu0+DBgxUREaF3331XDoejS9esq6uTzWaT2+1WXFxcL/8GfRsz4gIAzKI7399hCS2nUl1drY8//liZmZkaPnx4lz9HaAEAwHy68/3d59YeSkpK0tSpU8NdBgAA6GNY5RkAAJgCoQUAAJgCoQUAAJgCoQUAAJgCoQUAAJgCoQUAAJgCoQUAAJgCoQUAAJhCn5tcrr9ian0AAM4MoSUECktdyitwyuX2+o8l26zKzXawiCEAAF3E8FAvKyx1ac6abQGBRZKq3V7NWbNNhaWuMFUGAIC5EFp6UbPPUF6BUx2tSNl6LK/AqWZfn1qzEgCAPonQ0ouKy2vb9bC0ZUhyub0qLq8NXVEAAJgUoaUX1Xg6Dyw9aQcAwEBGaOlFI2KtQW0HAMBARmjpRRPsCUq2WdXZi80WtbxFNMGeEMqyAAAwJUJLL4qMsCg32yFJ7YJL635utoP5WgAA6AJCSy/LGpusFTMylGQLHAJKslm1YkYG87QAANBFTC4XAlljkzXFkcSMuAAAnAFCS4hERlh0xejh4S4DAADTYngIAACYAqEFAACYAqEFAACYAqEFAACYAqEFAACYAqEFAACYAqEFAACYAqEFAACYAqEFAACYQlhCy7x582SxWPzb+eefL0l67rnnlJqaqiFDhujqq6/Wnj17wlFegGafoaLdh7Thk/0q2n1IzT4j3CUBADAghWUa/61bt+r111/XlVdeKUmKjIzU7t279cgjj2jDhg1KTExUXl6eZs6cqffffz8cJUqSCktdyitwyuX2+o8l26zKzXaw0CEAACEW8p6WEydO6NNPP9U3vvENxcfHKz4+XrGxsdq+fbsyMzOVkZGh8847T3fffbfKyspCXZ5fYalLc9ZsCwgsklTt9mrOmm0qLHWFqTIAAAamkIeWnTt3yufz6ZJLLtHgwYOVlZWlffv2yeFwaPPmzfrkk0/kdru1fPlyTZkyJdTlSWoZEsorcKqjgaDWY3kFToaKAAAIoZCHFqfTqTFjxmj16tXasWOHoqKiNHv2bDkcDv3gBz/Q+PHjFR8fr6KiIj311FOdXqexsVF1dXUBW7AUl9e262Fpy5DkcntVXF4btJ8JAABOLeSh5Y477tDWrVt1xRVX6IILLtDy5cv11ltv6f3331dBQYH++c9/6siRI7rtttt0ww03yDA67s1YtGiRbDabf0tNTQ1ajTWezgNLT9oBAIAzF/ZXnkeMGCGfz6fFixfr1ltv1cSJE2Wz2fTYY49p9+7dKikp6fBzOTk5crvd/q2ysjJ4NcVag9oOAACcuZCHlgceeEBr16717xcVFSkiIkKJiYmqqanxH/d4PDp27Jiam5s7vE5MTIzi4uICtmCZYE9Qss0qSyfnLWp5i2iCPSFoPxMAAJxayF95/vrXv67/9//+n0aOHKnm5mbde++9uvPOO3Xdddfpxz/+sTIyMjRy5Eg999xzSkpK0rhx40JdoiIjLMrNdmjOmm2ySAEP5LYGmdxshyIjOos1AAAg2EIeWmbMmKFPP/1U3//+9xUZGakZM2bo8ccf15AhQ7Rr1y4tWbJELpdLY8eO1V//+lcNGjQo1CVKkrLGJmvFjIx287QkMU8LAABhYTE6e9LVZOrq6mSz2eR2u4M6VNTsM1RcXqsaj1cjYluGhOhhAQAgOLrz/R2WGXHNJDLCoitGDw93GQAADHhhf3sIAACgKwgtAADAFAgtAADAFAgtAADAFAgtAADAFAgtAADAFAgtAADAFAgtAADAFAgtAADAFPrNjLitqxHU1dWFuRIAANBVrd/bXVlVqN+EFo/HI0lKTU0NcyUAAKC7PB6PbDbbKdv0mwUTfT6fDhw4oNjYWFksLGhYV1en1NRUVVZWBnUBSQTiPocG9zk0uM+hw73+P4ZhyOPx6JxzzlFExKmfWuk3PS0RERFKSUkJdxl9Tlxc3ID/FyIUuM+hwX0ODe5z6HCvW5yuh6UVD+ICAABTILQAAABTILT0UzExMcrNzVVMTEy4S+nXuM+hwX0ODe5z6HCve6bfPIgLAAD6N3paAACAKRBaAACAKRBagB46cuSIPvzwQx0+fDjcpQDAgEBoMbGvvvpKdrtdFRUV/mMbNmxQenq6oqKidMkll2jXrl3+c6Wlpbr88ss1bNgwPfDAA12aMhkd3+dXXnlFaWlpmjVrllJSUvTKK6/4z3Gfe6aj+9xWVlaWVq1a5d9/77339B//8R9KTEzU7373u9AU2Q90dJ/nzZsni8Xi384//3z/Of6ee+ZUf88LFy5UdnZ2wDHuc9cQWkzqq6++0rRp0wL+hdi9e7fuuusuPfHEE9q/f78uvPBCzZo1S5LU2Nio7OxsXXrppdq6daucTmfAFwA61tF9drvdmjt3rt5//33t3LlTy5Yt0wMPPCCJ+9xTHd3ntl5++WW9+eab/v2DBw/qu9/9rm677TYVFRXp5Zdf1pYtW0JUrXl1dp+3bt2q119/XYcPH9bhw4e1fft2Sfw999Sp/p537Nih5cuXa+nSpf5j3OduMGBK3/72t42lS5cakozy8nLDMAyjoKDAWLlypb/N5s2bjcGDBxuGYRh//etfjWHDhhlHjx41DMMwPvnkE2PSpEkhr9tsOrrP+/btM9asWeNvU1JSYgwdOtQwDO5zT3V0n1sdOnTIGDlypDFmzBjjhRdeMAzDMBYvXmxcdNFFhs/nMwzDMF599VXjjjvuCHHV5tPRfT5+/LgRFxdneDyedu35e+6Zzv6em5ubjYkTJxoPP/xwQHvuc9fR02JSf/zjHzVv3ryAY9OmTdPs2bP9+59//rkuuOACSVJJSYkyMzM1ZMgQSdK4cePkdDpDV7BJdXSfU1NTdccdd0iSjh8/rsWLF2v69OmSuM891dF9bnX//fdr+vTpyszM9B8rKSnRNddc419nbMKECfr4449DUquZdXSfd+7cKZ/Pp0suuUSDBw9WVlaW9u3bJ4m/557q7O85Pz9fO3fuVFpamjZu3KimpiZJ3OfuILSYlN1uP+X5pqYmPf3007rnnnsktSzO1fYzFotFkZGRPER6Gqe6zyUlJUpKSlJhYaGeeeYZSdznnursPm/ZskXvvPOOnnzyyYDjJ9/nuLg4HThwoFdr7A86us9Op1NjxozR6tWrtWPHDkVFRfn/44e/557p6D7X19crNzdX6enp2rt3rxYvXqzJkyeroaGB+9wN/WbBRATKzc3VWWed5X+mJSoqqt3Mi1arVceOHdOwYcPCUaLpjRs3Tn/72980f/58zZo1S3/5y1+4z0Hk9Xr105/+VCtWrFBsbGzAuZPvc+s9Rvfdcccd/p5DSVq+fLnsdrvq6ur4ew6i9evX6+jRo9qyZYsSExN14sQJXXzxxVq9ejX3uRvoaemHNm/erGXLlmnt2rUaNGiQJCkhIUEHDx4MaOfxeBQdHR2OEvsFi8WiSy+9VC+++KLWr1+vI0eOcJ+D6NFHH9Xll1+uqVOntjt38n3mHgfPiBEj5PP55HK5+HsOoqqqKmVmZioxMVFSS/AeN26cysrKuM/dQGjpZ8rLy3Xbbbdp2bJlcjgc/uOXX365ioqKAto1NjYqISEhHGWa2nvvved/W0iSoqOjZbFYFBERwX0OorVr12rDhg2Kj49XfHy81q5dq7lz52ru3Lnt7vP27dt17rnnhrFa83rggQe0du1a/35RUZEiIiKUmprK33MQpaSkqKGhIeDY3r17de6553KfuyPcTwLjzKjN0+nHjh0zHA6H8ZOf/MTweDz+zefzGcePHzfOPvts4/nnnzcMwzBmzZplTJs2LYyVm0vb+3zgwAEjLi7OWLlypbFv3z7jzjvvNLKysgzDMLjPZ6jtfa6srDTKy8v92/e//33jt7/9rXHw4EHj4MGDhtVqNd566y2jqanJyMrKMn7+85+Ht3gTaXufV69ebdjtduPtt9823nzzTePCCy80Zs6caRgGf89nqu19/uqrr4y4uDhjxYoVRmVlpbF06VLDarUa+/bt4z53A6HF5Nr+S/Hqq68aktptrec3bNhgDBkyxBg+fLhx9tlnG59++mn4CjcZnfTq4t/+9jfD4XAYsbGxxg9+8AOjpqbGf4773HMn3+e2fvzjH/tfeTYMw1ixYoUxaNAgY9iwYYbdbjeqq6tDU2Q/cPJ9/q//+i/DZrMZCQkJxrx584z6+nr/Of6ee+7k+/yPf/zDyMzMNAYPHmykp6cbGzdu9J/jPncNqzwPMNXV1fr444+VmZmp4cOHh7ucfov7HBrl5eX67LPPdNVVV2no0KHhLqff4u85NLjPp0doAQAApsCDuAAAwBQILQAAwBQILQAAwBQILQAAwBQILQAAwBQILQB6xbvvvqu0tLSQfPZXv/qVZs6c2aOfBcA8CC0A+pzJkydrx44dQb2mxWJRRUVFUK8JILQILQD6nKioKMXFxYW7DAB9DKEFQK/auHGjRo0apYSEBD377LOSpI8++kgTJ06UzWbTTTfdJLfbHfCZzoaHNm/eLLvdruTkZD3wwANKTU3Vxo0b/ecfeeQRxcfHy26364MPPpAkXXTRRbJYLJIku90ui8Wi//mf/+ml3xZAbyK0AOg1hw4d0m9+8xtt2rRJjzzyiO6//35VV1fr+uuv1/XXX68dO3aorq5O999//2mvZRiGfvSjHykvL08vv/yyli9frnfeeUfXXHONJGnTpk3as2ePtm/frkmTJiknJ0dSS0A6fPiwJKmkpESHDx/W97///d77pQH0GkILgF5TX1+vFStW6Gtf+5pmz56tpqYmvfnmmxo0aJByc3M1atQoLViwIKC3pDMHDx7UgQMHdOutt+pb3/qW4uLidOjQIcXGxkpqGVJauXKl7Ha77rzzTlVWVkqSYmNjFR8fL0mKi4tTfHy8Bg0a1Gu/M4DeExXuAgD0X8OGDdO4ceMkSdHR0ZJaFoU7ePCghg0bJkny+XzyeDzyer2yWq2dXmv48OEaNmyYioqKlJKSIrfbrfPPP99/PjMzUzExMf6fxbJqQP9DaAHQazp6mPbEiRO69NJL9ec//1lSy7CP2+0+be/HiRMnNH78eN1www06ceKEnnjiCZ199tmn/FltWSwWggxgcgwPAQipqVOnat++fSouLtbgwYP1l7/8RVlZWacNFFu2bNGRI0e0detW7du3T/Pnz+/Wzx09erTeeOMN7d+/X++///6Z/AoAwoTQAiCk4uPjtXHjRj399NNKT0/XK6+8oo0bNyoq6tQdv5MmTVJNTY0mT56s5ORkxcXF6dFHH+3yz12xYoWefvpp2e12rVy58kx/DQBhYDHoLwVgAg8//LCqqqr061//WtHR0XrnnXc0d+5cHTp0KNylAQgRnmkBYArf+9739POf/1wXXnihjh8/rgsvvFDLli0Ld1kAQoieFgAAYAo80wIAAEyB0AIAAEyB0AIAAEyB0AIAAEyB0AIAAEyB0AIAAEyB0AIAAEyB0AIAAEyB0AIAAEzh/wPJJh5lPHpaCQAAAABJRU5ErkJggg=="
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from pylab import mpl\n",
    "mpl.rcParams[\"font.sans-serif\"] = [\"SimHei\"]\n",
    "\n",
    "plt.scatter(df['height'], df['weight'])\n",
    "plt.title('散点图')\n",
    "plt.xlabel('height')\n",
    "plt.ylabel('weight')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                 weight   R-squared:                       0.992\n",
      "Model:                            OLS   Adj. R-squared:                  0.991\n",
      "Method:                 Least Squares   F-statistic:                     2136.\n",
      "Date:                Thu, 29 Feb 2024   Prob (F-statistic):           3.70e-20\n",
      "Time:                        10:43:03   Log-Likelihood:                -11.811\n",
      "No. Observations:                  20   AIC:                             27.62\n",
      "Df Residuals:                      18   BIC:                             29.61\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const         25.5447      0.895     28.531      0.000      23.664      27.426\n",
      "height         0.2885      0.006     46.217      0.000       0.275       0.302\n",
      "==============================================================================\n",
      "Omnibus:                        0.331   Durbin-Watson:                   1.053\n",
      "Prob(Omnibus):                  0.848   Jarque-Bera (JB):                0.490\n",
      "Skew:                          -0.165   Prob(JB):                        0.783\n",
      "Kurtosis:                       2.308   Cond. No.                     1.25e+03\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "[2] The condition number is large, 1.25e+03. This might indicate that there are\n",
      "strong multicollinearity or other numerical problems.\n"
     ]
    }
   ],
   "source": [
    "import statsmodels.api as sm\n",
    "\n",
    "height = df['height']\n",
    "weight = df['weight']\n",
    "X = sm.add_constant(height)\n",
    "model = sm.OLS(weight, X).fit()\n",
    "print(model.summary())"
   ],
   "metadata": {
    "collapsed": false,
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:03.823873Z",
     "start_time": "2024-02-29T02:43:01.897342Z"
    }
   },
   "id": "bd21146fd1ba7b29",
   "execution_count": 6
  },
  {
   "cell_type": "code",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "const     25.544734\n",
      "height     0.288458\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "print(model.params)"
   ],
   "metadata": {
    "collapsed": false,
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:03.828429Z",
     "start_time": "2024-02-29T02:43:03.824882Z"
    }
   },
   "id": "5a17e343441beba7",
   "execution_count": 7
  },
  {
   "cell_type": "code",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9916434943512783\n"
     ]
    }
   ],
   "source": [
    "print(model.rsquared)"
   ],
   "metadata": {
    "collapsed": false,
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:03.833541Z",
     "start_time": "2024-02-29T02:43:03.829428Z"
    }
   },
   "id": "dea0c9e29fb1d0c1",
   "execution_count": 8
  },
  {
   "cell_type": "code",
   "outputs": [
    {
     "data": {
      "text/plain": "<Figure size 640x480 with 1 Axes>",
      "image/png": "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"
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(height, weight)\n",
    "plt.plot(height, model.predict(X), color='red')\n",
    "plt.title('回归图')\n",
    "plt.xlabel('身高')\n",
    "plt.ylabel('体重')\n",
    "plt.show()"
   ],
   "metadata": {
    "collapsed": false,
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:03.919716Z",
     "start_time": "2024-02-29T02:43:03.834547Z"
    }
   },
   "id": "a6c91822a8d5b4df",
   "execution_count": 9
  },
  {
   "cell_type": "code",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                 weight   R-squared:                       0.996\n",
      "Model:                            OLS   Adj. R-squared:                  0.995\n",
      "Method:                 Least Squares   F-statistic:                     1188.\n",
      "Date:                Thu, 29 Feb 2024   Prob (F-statistic):           5.32e-19\n",
      "Time:                        10:43:03   Log-Likelihood:                -5.5571\n",
      "No. Observations:                  20   AIC:                             19.11\n",
      "Df Residuals:                      16   BIC:                             23.10\n",
      "Df Model:                           3                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const       -188.2874     75.653     -2.489      0.024    -348.664     -27.910\n",
      "x1             4.7805      1.636      2.921      0.010       1.312       8.249\n",
      "x2            -0.0312      0.012     -2.661      0.017      -0.056      -0.006\n",
      "x3           7.16e-05   2.78e-05      2.575      0.020    1.26e-05       0.000\n",
      "==============================================================================\n",
      "Omnibus:                        4.772   Durbin-Watson:                   1.673\n",
      "Prob(Omnibus):                  0.092   Jarque-Bera (JB):                3.225\n",
      "Skew:                           0.224   Prob(JB):                        0.199\n",
      "Kurtosis:                       4.916   Cond. No.                     3.00e+09\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "[2] The condition number is large,  3e+09. This might indicate that there are\n",
      "strong multicollinearity or other numerical problems.\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "\n",
    "X_poly = np.column_stack((X, height**2, height**3))\n",
    "model = sm.OLS(weight, X_poly).fit()\n",
    "print(model.summary())"
   ],
   "metadata": {
    "collapsed": false,
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:03.929710Z",
     "start_time": "2024-02-29T02:43:03.920751Z"
    }
   },
   "id": "8ee497b71b245620",
   "execution_count": 10
  },
  {
   "cell_type": "code",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "const   -188.287441\n",
      "x1         4.780461\n",
      "x2        -0.031184\n",
      "x3         0.000072\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "print(model.params)"
   ],
   "metadata": {
    "collapsed": false,
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:03.934420Z",
     "start_time": "2024-02-29T02:43:03.930219Z"
    }
   },
   "id": "ad97edf478c8ded3",
   "execution_count": 11
  },
  {
   "cell_type": "code",
   "outputs": [
    {
     "data": {
      "text/plain": "array([70.10367159])"
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "h=155\n",
    "model.predict((1,h,np.power(h,2),np.power(h,3)))"
   ],
   "metadata": {
    "collapsed": false,
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:03.940216Z",
     "start_time": "2024-02-29T02:43:03.935454Z"
    }
   },
   "id": "72385eef901cef86",
   "execution_count": 12
  },
  {
   "cell_type": "code",
   "outputs": [
    {
     "data": {
      "text/plain": "<Figure size 640x480 with 1 Axes>",
      "image/png": "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"
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(height, weight)\n",
    "plt.plot(height, model.predict(), color='red')\n",
    "plt.title('体重与身高关系')\n",
    "plt.xlabel('身高')\n",
    "plt.ylabel('体重')\n",
    "plt.show()"
   ],
   "metadata": {
    "collapsed": false,
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:04.023651Z",
     "start_time": "2024-02-29T02:43:03.940216Z"
    }
   },
   "id": "a37449f5a9608efc",
   "execution_count": 13
  },
  {
   "cell_type": "code",
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false,
    "ExecuteTime": {
     "end_time": "2024-02-29T02:43:04.027164Z",
     "start_time": "2024-02-29T02:43:04.024655Z"
    }
   },
   "id": "1d59feffd46c285c",
   "execution_count": 13
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}