diff --git a/2、幸福感数据分析/第5组-杜佳璐/第5组实战/horse analysis.ipynb b/2、幸福感数据分析/第5组-杜佳璐/第5组实战/horse analysis.ipynb
deleted file mode 100644
index ff503fc..0000000
--- a/2、幸福感数据分析/第5组-杜佳璐/第5组实战/horse analysis.ipynb	
+++ /dev/null
@@ -1,807 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "collapsed": true,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns\n",
-    "from sklearn import preprocessing\n",
-    "from sklearn.preprocessing import StandardScaler\n",
-    "from sklearn.model_selection import train_test_split\n",
-    "from sklearn.metrics import accuracy_score,confusion_matrix,roc_curve,roc_auc_score\n",
-    "from sklearn.ensemble import RandomForestClassifier,BaggingClassifier,AdaBoostClassifier\n",
-    "from sklearn.naive_bayes import GaussianNB\n",
-    "from sklearn.tree import DecisionTreeClassifier\n",
-    "from sklearn.svm import SVC\n",
-    "from sklearn.linear_model import LogisticRegression\n",
-    "from sklearn.neighbors import KNeighborsClassifier\n",
-    "# 中文正常显示\n",
-    "plt.rcParams['font.sans-serif'] = ['SimHei']\n",
-    "plt.rcParams['axes.unicode_minus'] = False"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 数据处理"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "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>直肠温度</th>\n",
-       "      <th>脉搏</th>\n",
-       "      <th>呼吸频率</th>\n",
-       "      <th>红细胞体积</th>\n",
-       "      <th>总蛋白值</th>\n",
-       "      <th>y</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>38.5</td>\n",
-       "      <td>66</td>\n",
-       "      <td>28</td>\n",
-       "      <td>45.0</td>\n",
-       "      <td>8.4</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>39.2</td>\n",
-       "      <td>88</td>\n",
-       "      <td>20</td>\n",
-       "      <td>50.0</td>\n",
-       "      <td>85.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>38.3</td>\n",
-       "      <td>40</td>\n",
-       "      <td>24</td>\n",
-       "      <td>33.0</td>\n",
-       "      <td>6.7</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>39.1</td>\n",
-       "      <td>164</td>\n",
-       "      <td>84</td>\n",
-       "      <td>48.0</td>\n",
-       "      <td>7.2</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>37.3</td>\n",
-       "      <td>104</td>\n",
-       "      <td>35</td>\n",
-       "      <td>74.0</td>\n",
-       "      <td>7.4</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "   直肠温度   脉搏  呼吸频率  红细胞体积  总蛋白值    y\n",
-       "0  38.5   66    28   45.0   8.4  0.0\n",
-       "1  39.2   88    20   50.0  85.0  0.0\n",
-       "2  38.3   40    24   33.0   6.7  1.0\n",
-       "3  39.1  164    84   48.0   7.2  0.0\n",
-       "4  37.3  104    35   74.0   7.4  0.0"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df = pd.read_csv(\"data_horse.csv\",encoding=\"gbk\")\n",
-    "df.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "y        1.000000\n",
-       "直肠温度     0.172629\n",
-       "总蛋白值     0.114651\n",
-       "呼吸频率    -0.036938\n",
-       "红细胞体积   -0.152119\n",
-       "脉搏      -0.276255\n",
-       "Name: y, dtype: float64"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "## 可视化列的缺失值、唯一值、类型\n",
-    "df.corr()\n",
-    "# 可视化变量y与其他的相关性曲线\n",
-    "df.corr()['y'].sort_values(ascending=False)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "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>直肠温度</th>\n",
-       "      <th>脉搏</th>\n",
-       "      <th>红细胞体积</th>\n",
-       "      <th>总蛋白值</th>\n",
-       "      <th>y</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>38.5</td>\n",
-       "      <td>66</td>\n",
-       "      <td>45.0</td>\n",
-       "      <td>8.4</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>39.2</td>\n",
-       "      <td>88</td>\n",
-       "      <td>50.0</td>\n",
-       "      <td>85.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>38.3</td>\n",
-       "      <td>40</td>\n",
-       "      <td>33.0</td>\n",
-       "      <td>6.7</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>39.1</td>\n",
-       "      <td>164</td>\n",
-       "      <td>48.0</td>\n",
-       "      <td>7.2</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>37.3</td>\n",
-       "      <td>104</td>\n",
-       "      <td>74.0</td>\n",
-       "      <td>7.4</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "   直肠温度   脉搏  红细胞体积  总蛋白值    y\n",
-       "0  38.5   66   45.0   8.4  0.0\n",
-       "1  39.2   88   50.0  85.0  0.0\n",
-       "2  38.3   40   33.0   6.7  1.0\n",
-       "3  39.1  164   48.0   7.2  0.0\n",
-       "4  37.3  104   74.0   7.4  0.0"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 剔除相关性绝对值小于0.1的变量\n",
-    "df = df[df.columns[df.corr()['y'].abs()>0.1]]\n",
-    "df.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "直肠温度     0\n",
-       "脉搏       0\n",
-       "红细胞体积    0\n",
-       "总蛋白值     0\n",
-       "y        9\n",
-       "dtype: int64"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df.isnull().sum()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 720x360 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlkAAAFQCAYAAACMH2sSAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAAgX0lEQVR4nO3debxcVZXo8d8igU8jNALmEkWJNMiT50BaOiAo5AGCTJExggM4oB1BRZ+2LYros31O7QC2KMFAsBEalBkEkUFEEFEICqjd9nsOiNIMUVHUbgdw9R/nRCqVunVPJbWr6lZ+38+nPrdunVV7rzNU3XX32XUqMhNJkiT11zrDTkCSJGkcWWRJkiQVYJElSZJUgEWWJElSARZZklSLiBh2DpLGh0WWpLETEQsj4uyIeHLD+O9FxAzgLAstSf1ikSVpWouId0TE9+vb++qHLwG+DnwjInZvi/9hRKwfEZtHxNYRsSXwMLAFEMCzI2KjAa6CpDE1c9gJSNIaehg4ob7/PyNiV+DA+vF3AzcDRMQGwKbAn4DZwHOBzYE/AhsBBwG3As8B/hO4c1ArIGk8WWRJmu4eabmfwM+AO4BnAE/JzN9FxPx62bHABPBB4G7ggDp+E2AhsB7wg8w8cXDpSxpXni6UNN2tA7yvvgHcB3ye6nThehGxLXAqQGYeBtybmS8CbqhjrwV+Xf+8BVh/oNlLGluOZEma7mYC76jvbwscAbwBuBR4GfBEYI/MvG/FEyLi7fXdu4DrgRfXP+cATxpAzpLWAo5kSZruNqA6/fdBgMw8GXgMsAy4HfivzLwvIraPiKuAv6Kar/VTYA/gvVRzs94LvBFYd9ArIGk8WWRJmu62ABYAbwOIiHnAj4HfUBVam0bEYcAPgEXAjzLzw1SnBhdk5i7Ay6nmZ90MvDAiLLQkrTFPF0qa7rYCvk810X1d4EPAkpbli6jmZ701M89puQzWWcCMiMj693cBW1N9uvBE4OzyqUsaZ45kSZq2ImIW1eUXNqcaiZpBVVCdQ3WZht9n5k+Bg6mumfV0YGOAzNyR6nTiEmAH4HDgtszcPjMtsCStMUeyJE1nTwA+R3Vq8NvAJzPzoYjYm2oy/OEAmXkrQERcACxuef7xVO+Ds4CvsfIImCStkcjMqaMkSZLUE08XSpIkFWCRJUmSVIBFliRJUgEjN/F91qxZueWWWw47DUmSpCnddtttP8vMiU7LRq7I2nLLLVm2bNmw05AkSZpSRPx4smVFThdGxKYRsVd9DRtJkqS1Tt+LrIjYBLgc2BH4ckRMRMTdEXF9fXtmv/uUJEkaNSVOF24HvDkzv14XXEcB52bmcQX6kiRJGkl9H8nKzK/UBdZ8qtGs/wIWRMQtEbE0IkZuHpgkSVK/lZqTFVRfZ/Eg8C1gz/p7wtYF9usQvygilkXEsuXLl5dISZIkaaCKFFlZeR1wJ7B5Zt5bL1oGbNMhfklmzsvMeRMTHT8FKUmSNK2UmPh+XES8rP51Y+DUiJgbETOAg4A7+t2nJEnSqCkxkrUEODIibgBmAPOBs4DbgZsz89oCfUqSJI2Uvk9Cz8wHgb3aHt6u3/1IkiSNMr+7UJIkqQCLLEmSpAK8ZpUau/yMfbsuX3DUlQPKRJKk0edIliRJUgEWWZIkSQVYZEmSJBVgkSVJklSARZYkSVIBFlmSJEkFWGRJkiQV4HWypD44/vx9ui5//wu/OKBMJEmjwpEsSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSqgSJEVEZtGxF4RMatE+5IkSaOu70VWRGwCXA7sCHw5IiYiYmlE3BwRJ/S7P0mSpFE0s0Cb2wFvzsyv1wXXHsCMzNw5Is6IiG0y8/8X6FeSJGlk9L3IysyvAETEfKrRrE2B8+rFVwO7ACsVWRGxCFgEMGfOnH6nJEmSNHCl5mQFcDjwIJDAPfWiXwCz2+Mzc0lmzsvMeRMTEyVSkiRJGqgiRVZWXgfcCTwHWL9etGGpPiVJkkZJiYnvx0XEy+pfNwY+SHWKEGAucFe/+5QkSRo1JSa+LwHOi4hXA98BLgFuiIjNgX2BnQr0KUmSNFJKTHx/ENir9bGI2K1+7EOZ+at+9ylJkjRqSoxkraIuvM6bMlCSJGlMOAldkiSpAIssSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKmDnsBDpZvvjsrssnjjliQJlIkiStHkeyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAL6PvE9Ih4LfBaYAfwWOBz4PvDDOuTYzPx2v/uVJEkaJSVGsl4KnJiZzwfuA94GnJuZu9U3CyxJkjT2+l5kZeYpmXlN/esE8DCwICJuiYilETGSl42QJEnqp2JzsiJiZ2AT4Bpgz8zcEVgX2K9D7KKIWBYRy5YvX14qJUmSpIEpUmRFxKbAycBRwJ2ZeW+9aBmwTXt8Zi7JzHmZOW9iYqJESpIkSQPV9yIrItYDzgfenpk/Bs6KiLkRMQM4CLij331KkiSNmhIjWa8CtgfeERHXA98FzgJuB27OzGsL9ClJkjRS+j4JPTMXA4vbHv6HfvcjSZI0yrwYqSRJUgEWWZIkSQVYZEmSJBVgkSVJklSARZYkSVIBFlmSJEkFWGRJkiQVYJElSZJUgEWWJElSARZZkiRJBVhkSZIkFWCRJUmSVIBFliRJUgEWWZIkSQVYZEmSJBVgkSVJklSARZYkSVIBFlmSJEkFWGRJkiQVYJElSZJUgEWWJElSARZZkiRJBVhkSZIkFWCRJUmSVIBFliRJUgEzh53AuPvByQd2Xb71sZcOKBNJkjRIjmRJkiQVYJElSZJUgEWWJElSARZZkiRJBVhkSZIkFdD3IisiHhsRV0bE1RFxcUSsFxFLI+LmiDih3/1JkiSNohIjWS8FTszM5wP3AS8CZmTmzsBWEbFNgT4lSZJGSt+LrMw8JTOvqX+dAI4Azqt/vxrYpf05EbEoIpZFxLLly5f3OyVJkqSBKzYnKyJ2BjYBfgLcUz/8C2B2e2xmLsnMeZk5b2JiolRKkiRJA1OkyIqITYGTgaOA3wDr14s2LNWnJEnSKCkx8X094Hzg7Zn5Y+A2Hj1FOBe4q999SpIkjZoSo0qvArYH3hER1wMBHBkRJwKHAVcU6FOSJGmk9P0LojNzMbC49bGIuAzYC/hQZv6q331KkiSNmr4XWZ1k5oM8+glDSZKksbdapwsjYpXLMEiSJOlRjYqsiLim7aEPFMhFkiRpbHQ9XRgR2wHPAp4YES+rH94A+F3pxCRJkqazqUayosPPn1N9SlCSJEmT6DqSlZl3AHdExFMz8zMDykmSJGnaa/rpwo9FxIuA9VY8YNElSZI0uaafLvwi8BSq04UrbpIkSZpE05GsX2fme4tmIkmSNEaaFlk3RsS5wGeA3wJk5g3FspIkSZrmmhZZfwS+B+xAdaowAYssSZKkSTQtsu6iKqxWFFiSJEnqopev1QlgfeAQYH6ZdCRJksZDo5GszDyz5ddTI+KUQvlIkiSNhUZFVkS0jlxtBjytTDqSJEnjoemcrN15dC7WH4DXlUlHkiRpPDSdk/V+4H5gU+BnwL8Xy0iSJGkMNC2yzgBmA1cCTwQ+XSwjSZKkMdD0dOEWmXlkff+qiPhKqYQkSZLGQdMi6z8i4u3AN4CdgXvKpSRJkjT9NT1deDRVQbYQeAh4TbGMJEmSxkDTIuts4O7MfC3wl1RztCRJkjSJpkXWJisuSJqZ7wdmlUtJkiRp+ms6J+unEXEccAvVl0Q/UC4lSZKk6a9pkfUKYBHVnKzvAS8vlZC6u+VTL+i6fMfXfH5AmUiSpG6afnfh74GTC+ciSZI0NprOyZIkSVIPLLIkSZIKsMiSJEkqoEiRFRGzI+LG+v7MiLg7Iq6vb88s0ackSdIoafrpwsYiYhPgTGCD+qHtgHMz87h+9yVJkjSqSoxkPQIcTvX1OwA7AQsi4paIWBoRfS/sJEmSRk3fC57MfAggIlY8dCuwZ2beGxGfAfYDLmt9TkQsoroOF3PmzOl3StPCt085oOvyZ772sq7LJU0/B15wZdflly7cd0CZSCphEBPf78zMe+v7y4Bt2gMyc0lmzsvMeRMTEwNISZIkqaxBFFlnRcTciJgBHATcMYA+JUmShmoQ86PeA5wDBHBZZl47gD4lSZKGqliRlZm71T+/Q/UJQ0mSpLWGFyOVJEkqwCJLkiSpAIssSZKkArwwqEbeGWc+v+vyo15+9YAykSSpOUeyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSrASzhIWi37X/SRrsuvOOQtA8pEw/aii340ZcxnD/mrAWQijRZHsiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAK+TJUlSj647Z3nX5Xu8ZGJAmWiUOZIlSZJUgEWWJElSARZZkiRJBVhkSZIkFWCRJUmSVIBFliRJUgFewkHSWFpwwVldl1++8Mge27tgypjLFy7sqU1J482RLEmSpAIssiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCihRZETE7Im5s+X1pRNwcESeU6E+SJGnU9L3IiohNgDOBDerfDwFmZObOwFYRsU2/+5QkSRo1JUayHgEOBx6qf98NOK++fzWwS/sTImJRRCyLiGXLly8vkJIkSdJg9b3IysyHMvNXLQ9tANxT3/8FMLvDc5Zk5rzMnDcxMdHvlCRJkgZuEBPffwOsX9/fcEB9SpIkDdUgCp7bePQU4VzgrgH0KUmSNFSD+O7CS4AbI2JzYF9gpwH0KUmSNFTFRrIyc7f650NUk9+/DuzeNl9LkiRpLA1iJIvMfJBHP2EoSZI09pyELkmSVMBARrKkQVh89t5dlx9zxFU9t/n+z3Zv8/gX9d6mJGnt4EiWJElSARZZkiRJBVhkSZIkFWCRJUmSVIBFliRJUgEWWZIkSQV4CQdpgI65aJ+uyxcf8sUBZaK12aEX3tp1+YWH7jCgTKTx5kiWJElSARZZkiRJBVhkSZIkFWCRJUmSVIBFliRJUgEWWZIkSQVYZEmSJBXgdbKkaWzfS4/uuvzKA08dUCaSpHaOZEmSJBVgkSVJklSARZYkSVIBFlmSJEkFWGRJkiQVYJElSZJUgJdw0ND8yz/v3XX5S19x1YAykSSp/xzJkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSqgeJEVETMj4u6IuL6+PbN0n5IkScM2iEs4bAecm5nHDaAvSZKkkTCIImsnYEFE7A58G3hNZj7cGhARi4BFAHPmzBlAStLaZb9L3tZ1+RcO+uCAMpnc/hd+quvyKw59DQALLjyja9zlhx7Vt5ymm4Mv/GrX5RcfusuAMpnccRff03X5Px78xAFlIpU3iDlZtwJ7ZuaOwLrAfu0BmbkkM+dl5ryJiYkBpCRJklTWIEay7szM39f3lwHbDKBPSZKkoRrESNZZETE3ImYABwF3DKBPSZKkoRrESNZ7gHOAAC7LzGsH0KckSdJQFS+yMvM7VJ8wlCRJWmt4MVJJkqQCLLIkSZIKGMScrGnlvlPe3XX541/bffmouOG0/bsun/+3VwwoE00n+1383iljvnDwCQPIRK0OuuBLXZdfsvB5A8pEUi8cyZIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAC/hIEl9dsAFl3ZdftnCAweUyfT1kYvv67r8LQc/vqf2zrvwZ12XH3boLACuOK973P6Hzeqp37XR/Sd1/4ri2W+a23ubH7+xe5tv2LXnNgfBkSxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKmBaXydr+amndV0+cfTfDigTSZPZ/6KTuy6/4pBjB5RJZwsuOLfr8ssXvnhAmWgcfe3M5VPGPOflE0X6/vFJ3a819uQ39XatMfXOkSxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKmBaXyerFw+celLX5Zsd/aae2rvnE8d0Xf7E1y/uqb1huub0/bou3+vVX+ipvQs+vU/X5Qtf+cWe2uu3k87Ze8qYN73kqgFkMrl9L+u+Da88YLjbUGuHF174na7Lzz/0GQPKZHJLL3qg6/JXHbLZgDJZc986vfu6POvV1bp875T7u8Zt+9rZPfV774d+0nX5E966BQD3ffTfu8Y9/u+e2lO/93/sliljZv/vHXtq84GTr+26fLNj96ziPnFF97jX71/FnXJh97jXHtp1uSNZkiRJBVhkSZIkFWCRJUmSVIBFliRJUgEDK7IiYmlE3BwRJwyqT0mSpGEZSJEVEYcAMzJzZ2CriNhmEP1KkiQNS2Rm+U4iPg58MTO/EBEvAtbPzE+3LF8ELKp/fSrQ/jnRWcDPGnTVNK5Em+MSN8y+Rz1umH2Petww+x71uGH27TqPXtww+x71uGH2vSZxT87MiY7RmVn8BiwF5tb3nw+8rcfnL+tnXIk2xyVuOuTothm9uOmQo9vGdR6FuOmQo9umP+uSmQObk/UbYP36/oY44V6SJI25QRU7twG71PfnAncNqF9JkqShGNTX6lwC3BgRmwP7Ajv1+PwlfY4r0ea4xA2z71GPG2bfox43zL5HPW6YfbvOoxc3zL5HPW6YfZdYl8FMfAeIiE2AvYAbMvO+gXQqSZI0JAMrsiRJktYmTkCXJEkqwCJLkiSpgEFNfO9ZRGxN9YnE2VTF4F3AFZn562HmJUmS1MRIzsmKiOOBrYGrgV9QXVtrLvBCYPfMfKAldrWKsYhYkpmLuix/PbAb8GPgI5l5b9vy7YGf1Pm9Ekjg3Mz8zw5tdc0xImYC+wAPZOYtLc97YWaevzrrERFPz8zvRsQ6wH7ANsAdmXld6XWOiPnAY4EvddoebbFjsW2arEvTHFcnvyY59rD/plyPpvul4LYe+LpMkuu0fh/pZ35NcpxMl9fqyO/nfr3uV2OdG73Plto2/X5P7Gd7peqCXuNgdIusmzLzuR0e/yhwc2ZeUP/eqBiLiG8CfwGs+FRjAH8NfCsz92hpf//MvCIiDgB2BM4GdgCObs0nIhYDGwFbAP9K9TVAzwY2zsx92nKeMseIuBC4H5gANgZemZk/jYjr2vJrtB517HWZuUdEnE41YnkbcBBwU2a+q9Q6R8SH65gHgL2BfwZOyszf0WZctk0P69L0OGyUXy859rD/mr6mmu6XEtt6WOsyLu8jfc+vx+3ddDuO9H7uYb/00l5f32cLbJt+vyf2tb0e45oeh433X0fZw+XhB3UDTgfOoKqsn1lv/L8DvgU8tiXupkme/1FgYcvvs4GzgMXARvVjX+7wvE8CFwAfATZrefwrbXG31D8fC5xQ358BPNShzSlzpPpexxWP7wzcAjwPuK7tOY3Wo378uvrn11sem0E1ilBsnVufByygukbabcBLV3PbXDXq26aHdWl6HDbKbw323zu77L+mr6mm+6XEtm56LDZdl76+/lZznwzyfaTv+fW4vZtux5Hezz3sl17a6+v7bIFt0+/3xL62V+g4bLz/Ot1Gck5WZr46Ig6munDpBlRfy3MbMD9XHu77t4g4AzgPuIfqq3t2pTo43tPS3v3AkRGxO3BxRJxCNQTb3u/rImIX4DRgy4hYQlUR398WujwiXkxVAM6JiA2A7YC7O6zO9zrkuEtbjn+KiOdl5pcy8+aI2KeOn9uWX6P1qG0dER8ANoyI2fVznz7JOu9KdYG1Feu8VYN13nCSdf51ROxAVRA/G/gwcDvw9x1ybLL/HmnbNnsD5xfYNk9ruG06HQ+TrcsuwB4r1qWHHBvtuy45dtt/zwCe3GX/TbZP/rwetfb90vGYbbouPW7rpsdip9feKu8PrPr6W6NjrId1WdP3kfb90vR9ZHXf5ybbzis0OnZ6eB007b/pMVvifXbKvntsr+nrtOn7bL+3zZq+J7Zvm76210tcD6/nXvbfqppWY6N4Ax4HHEY18nUa8F3gSOpqsy1uL6phw42Ad9Gh2m2J2wh4bd3e3wMbtMXNAt5Q9zUH+CHwc2CHSfI8GPhYneNJwPeBDVuWb0Q1PNr6nKXAa7qs+7rAO4HvT7J8BvAs4Bjgb+r4a4GnTRI/EzgKOBn4Q4d13hh4PfDiep1PB74EzGuL2xL4HPBN4Pj6sSWT9PmMett8EvgB8CvgCOAvW2K2q9dhHar/2N5U76P27fX0+uc6wAvqffzVLv0+Czi23oZvpfpW9adN0ubMen//Fnhz+7Zp28//BPwRuK5epy0miX0D8AjVPw9P6LLv3gFcBFwI7NrleFiR45fqdrdoW75xvb4vqbfNlzq1CZwKvKU+Xk+vfx7Zuk/quDOo/9NuOybb98vpwLyW43C9+vh4elvcYmD7tuPwjbS8TtpyPKHlWFxar8sqrz+q1+8n6zx+W+/vDdtiNqrbm6i3/auBRcDrOrS3fR23Xt3WPcBjJonbrG7nN1Qj8Z1eU+/k0feRR6jeR3bpcnz9gEffR1baL/V6HE11/D9msn1SPz4fOKA+Zj7eaVu3HDNHUp2amnQ7d3gNrMhxpddzl/ex6zssW9F/k/28ot9ux+xGwDFTHbOT5LfKyEovfTdtj5Vfp63rPOX7bMP8Ou6TXrcNK79O39B+7HTZNh2Ph9Vor+vx1c/jcHXiWm8jOSeriYh4HNUfsqupTif+Avg21UG6Tma+viXuy8BVVOd6H+xD3JT9tuTZej436of/mpbzuZPEzAVuz9WfKzBlv2sQN2nfLXGt/4lMlmPrfJ11gWW0zdeJyef0fC0z3zlJW1PNY5qy37a40+q4NZob1XT+QY/zFFbEvoDqP9o1ajMivgXcSDVEfkpmfoUOWuI2AxZPEXdD3d4ax/XYd9P5LZPFbZKZe69Be08C/q3HfneimhLRPierdQ7OPlRzcE7Mljk40XyezpRtTdLemZ3i2p6zNdWowYoJxz9i6onJM7rEPaWO26xb3LBEgwnjTWJ6aa8lbl/g/iniHkdV8N8MPExVWD+Ymde09dsa98c67pcN4g7s1F6X7TXlhPHJYuLRD9HM4NEP0dyeU3+IZneqie8dJ9PXca+jGunqGBcrfxjhKOBPdPkAyEqaVmOjdgP2BN5e358PfKJl2fXDjmt5bMX53FOY5HxuHfMZ+nhuuEm/vbTZkmOT9qaMqx+fcr5Ok5he4lazzW80aHPKuQVNYnqJK9Hmin0FbA68D7gJOBE4qHDcdU3iemyz6fyWkY7rcBx1nIPTJKZEXEvM8VQjFodRjTYfDLyb6ozAZm1xS4HDG8SdPlXcMG9Uo0ynUJ1evgZ4Uuvx3DSm19iG/T4OuJPqVOL1wMVUp8s+zsp/t1Yn7iuTxbXEf5Pqn4fr6tuXqQYvruslpsN7xGlU/xgcSzUi/562uP3rnwcA7wW2pRpdvKlB3BEd4hYD/0L1T+CpVGdTPkvLPLaux8iwD9I1OLg3oXpz3bHt8SOBq4cd1yHf3esD4tBOB1DTmF7iSrTZzziqj+p+gGokcHb92HasXGRNGdNLXKk262W7Uo1cXAA8n+oU2Xm9xvQS1+82WfUfgKD6Z+J9oxDXY5tXUJ1qeh/VyN2GwHOA70ynuDr2cqqRx5nA/wWeSzVf9d29xJSIa4nv98TkpnE3UI1Gr/gj/eefbc9rjbtuTePq2CknjDeJ6TW2Yb+jMsAw6T/wTWJaYvv9Ya4iHwBZJe8mQaN6ozpFN7/tsbdSDcsPPa5Dvk3O708Z00tciTb7Fceq88ZWma/TJKaXuFJttjxnyrkFTWJ6ietnm3SZnzIKcT22uTGd57fsMJ3i6tgtmWIOTpOYEnEt8U0/Fd7vuNnAlbTNxe2QX1/j6tgvAM9r+X1TqrmvP+8lptfYhv2O1QADvf0j3c9/PBv/M9TpNm3nZEmSRktUnwrfjZU/FX5JrjrXqt9xGwMPZ+Zvpsiv33EbUZ0+Xdzy2LrAqzLz1KYxvbTXY9zGwHaZeUPLY2+l+jDSL0vFddhO6wJvA/bMzP+1OjH1XKztqOYt3kJVbJ1Fdbrwux3iZwIvo/pH+fvA0k77c6q4ep2PpPpQyleB/0P1D9IHM/PWydb5z8+3yJIkSeq/kbxOliRpeomIG4DHAA+1PgxkrvwJ5LGIaxrb7/amQ1yH2KDl2lKTbJuOMVP0vUrsgNa5Y44dNTmn6M2bN2/evHW7MaS5UcOKaxrb7/amQ9zauG0mu3m6UJLUF0OcGzWUuKax/W5vOsQ1jR2nbdPxuRZZkiRJ/bfOsBOQJEkaRxZZkiRJBVhkSRpLEbFTRGzVMHbd0vlIWvtYZEkaCxHx4Yi4NiJOrh96BPhcRLy9JWbniHh/RKwTETMiYoOI+AywR0Q8r74woST1hW8oksbFlpm5Z0RcERFPBban+iLZ77XE/BH4A9UXDr8T+BPwP6i+1gbgyVRf5SJJa8wiS9K4eKT+2fqR6ZcAB0bEU6i+f/IFwFbAA8D/A/4D2Ai4HnhCZlpgSeobTxdKGhcbRMS1wF8Av6X6wtkfUn157ieBnwEfA64GPg3sB8wHHk/1/XhTX71ZknpgkSVpXPwxM/cEfgdsC3yB6msyLgHeBNwKPAc4HHglcDdwWf3zEuCXg05Y0njzdKGkcfG4iLie6rTh14B7gIeB71DNxfobqrlXnwPOBJ4EXApsTjU368LBpyxpnHnFd0ljISIuzMxDI+Jy4BxgS6pJ7f8EnEw1P2szYAHVvK1dW57+VOCnwFmZecog85Y0vjxdKGnai4htgeURsTnVCP0rgE8BM6hOB/4jsC/wWCAz8x+Aa4GP16cYLwdebIElqZ8cyZI07UXE4VQF1ZOBfwU+DxwBvBGYl5kZEbOoTgken5k3RcQEMJtqtOvdwK6Z+ath5C9pPFlkSRoLERHZ8oYWEetl5h+GmZOktZtFliRJUgHOyZIkSSrAIkuSJKkAiyxJkqQCLLIkSZIK+G9UIdVorEaotgAAAABJRU5ErkJggg==",
-      "text/plain": [
-       "<Figure size 720x360 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 720x360 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 720x360 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 720x360 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "#可视化每一个变量\n",
-    "import warnings\n",
-    "warnings.filterwarnings(\"ignore\")\n",
-    "for i in df.columns:\n",
-    "    plt.figure(figsize=(10,5))\n",
-    "    plt.title(i)\n",
-    "    # 设置字体旋转角度\n",
-    "    plt.xticks(rotation=90)\n",
-    "    sns.countplot(df[i])\n",
-    "    plt.show()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "直肠温度     69\n",
-       "脉搏       26\n",
-       "红细胞体积    36\n",
-       "总蛋白值     42\n",
-       "y         9\n",
-       "dtype: int64"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 我们认为这些变量中的0值都是不合理的，所以我们将除了y(最后一列)以外的变量中的0值都替换为np.nan\n",
-    "df[df.columns[:-1]] = df[df.columns[:-1]].replace(0,np.nan)\n",
-    "df.isnull().sum()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "直肠温度     0\n",
-       "脉搏       0\n",
-       "红细胞体积    0\n",
-       "总蛋白值     0\n",
-       "y        9\n",
-       "dtype: int64"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 用众数填充缺失值\n",
-    "# 观察发现直肠温度列是正太分布的，因此可以用均值填充缺失值，其他使用中位数\n",
-    "df['直肠温度'] = df['直肠温度'].fillna(df['直肠温度'].mean())\n",
-    "df[['脉搏','红细胞体积','总蛋白值']]  = df[['脉搏','红细胞体积','总蛋白值']].fillna(df[['脉搏','红细胞体积','总蛋白值']].median())\n",
-    "df.isnull().sum()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "## 删除缺失值\n",
-    "df = df.dropna()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 720x360 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 720x360 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlkAAAFWCAYAAABaRogPAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAAi10lEQVR4nO3debxkVXXo8d+iGxBBBOxBiYyGF+NAK7YEtJFuwiiIzIKC4oQIiKIiimCcYvKcQFQgaCuiCYI0IILQiAwSAbVRccBnNC8QIQKt8kCNGIb1/jjn2mV1Vd0q+uy6dat/38+nPreqzrpn7Tq7Tt1199nnVGQmkiRJatYaU90ASZKkcWSRJUmSVIBFliRJUgEWWZIkSQVYZEmaFiIiproNkjQIiyxJUyYiNoqIOX2GfzgijlyFXHtGxPE9lh8bEce0PF4QEedPss4nR8QrLQAldTJzqhsgabV2BDAXOC4iZgJk5kPwp5GrtTLzjxHxWOAA4Dn1sjOA53ZY3w6Z+YeIOAXYGXgAuDsz9wIOAc7r0ZbdgM+1PP4f4MH2oIj4a+ATwGb1U/8C7BoRHwb+WD83A7g6M98yyeuXNMYssiRNiYh4DHAQsCgiHgfsD7w+ItYFZgM/BwJ4HvAa4Cxgy3q0aXPgYGA+8NTMfHdE3AY8VK/+QeC4eh0fjYgnArsDT42Iv6tjNgOelpnLI+IJwI7AoRGxZmY+CDwC/OlCgi3P/xvwSmBL4ODMfFdEbAvckpmH1rE7A4c1u8UkTTcWWZKmyvHAqcDvgR8Au2fm2XWBcmhmHg4QEVsAbwNeAZwAXEJVXHWSLT/3AO6hKpbeB5yQmYsnAiPiO8Af6oeHAXcA21AVZY8A86qwWAjcBcyMiB3q3/kvqiKLiJhBVQx2a4uk1ZRFlqShi4gdqUaaPks1gnVFZv5nl/AnAP8BvIXq0OI5wIGTpJgJ3AfcC6xLVRD9TUS8Eng8sKCOeSAi1gbeADyYmV8H5tWF3gepCqU7M3Pvlra/GngzsBGwJvB8qsJPkv6ME98lTYWfUB0CvBZ4MnBit8DMXJaZO1CNFh2TK74L7IvAu4FXRcS/Ak9s+bWZwA3AlVQjZfsB383MBcCvgYeBGfX8r5eycpF0LHB+3c6NImJeS3sWZ+bTge8AFwGLgK90aPqM3ptA0rhzJEvS0GXmPRFxOXAZ1aHBByIissuXqUbEh6gO/f0uIp5WP91pTtaExwDvoSqw7u+0ypb7n6f6LNyjznUo1WjXVcAzqA5VnhMRu2TmPXXMNlQjWHcBF1ONyj0jIr7fst6lfWwKSWPMIkvS0NVnEn6NavTpzIhYh+rswZUOGdaxO1Id+nsTcGEfKWYDR1FNgH9v/dzuEXFtff9w6s+/ejTroYggIl4HnAxsT3Voksy8ISJOB74dEQdTzR9bTHU4cYu6XcupDmf+qL6/XWbe0N/WkDSuLLIkDV1mPhQRpwG3Aj/NzAcnLuHQKRbYFiAi1gK26iPF/wJ+THUocsIVLZPpdwbar7m1BjCL6tIPlwDrUR0q/D7wEeC19Tp3oTpM+C1gi8x8R3324meAF1JdNuJTEXFCZl7aR1sljSmLLElDV18D6xaq4umNEfF84K31IcTWuDWpCqY3As8CnkR1eC6oCp3HAGtHxF71soiIpwD31YXcLKr5V48AcyJijcx8BLga+HJEPD4zvxIRawCZmX9fp352fVmG4zLzkLbmf7n+3Z3qNq5DNX/rrZn54/q5A4GrImLHzPxZIxtN0rRjkSVpKmwEfJWqYDoXOBpYAryfqiAiIpYBa1Gd+XcbcGpm3lovWwrsm5k/n1hhPSdrbWA74HMR8QzgG/Xv30k1f+q6usBL4JdUxRZUn4XtFx5dq751s16d7yDgosz80sSCzLw1Ik4ANgEssqTVVHSZZypJIysiNgTuz8yHuyyPzMyWC4hK0tBZZEmSJBXgdbIkSZIKsMiSJEkqwCJLkiSpgJE7u3DWrFm5+eabT3UzJEmSJnXzzTf/KjNnd1o2ckXW5ptvzrJly6a6GZIkSZOKiNu7LfNwoSRJUgEWWZIkSQVYZEmSJBVgkSVJklSARZYkSVIBFlmSJEkFWGRJkiQVYJElSZJUgEWWJElSARZZkiRJBVhkSZIkFTBy310oaXra88JTei6/bL/jhtQSSRoNjmRJkiQV0GiRFREzI+I/I+La+vbMiFgcETdGxElN5pIkSRplTY9kbQ2cm5kLM3MhsBUwIzO3B7aMiK0azidJkjSSmp6TtR2wV0QsAn4I/BE4v152JbAA+FnDOSVJkkZO0yNZ3wF2zsxtgTWBPYA762W/AeZ2+qWIOCIilkXEsuXLlzfcJEmSpOFrusj6QWb+sr6/DJgFrFM/Xq9bvsw8KzPnZ+b82bNnN9wkSZKk4Wu6yPp8RMyLiBnAPsDRVIcIAeYBtzWcT5IkaSQ1PSfrvcC/AAFcAlwMXB8RG1MdOtyu4XySJEkjqdEiKzN/RHWG4Z9ExEJgF+CDmXlfk/kkSZJGVfErvmfmvaw4w1CSJGm14BXfJUmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSqgSJEVEXMj4nv1/cURcWNEnFQilyRJ0igqNZL1YWCdiNgPmJGZ2wNbRsRWhfJJkiSNlMaLrIjYCfg9cBewEDi/XnQlsKDpfJIkSaOo0SIrItYCTgbeXj+1LnBnff83wNwuv3dERCyLiGXLly9vskmSJElToumRrLcDp2fm/6sf/w5Yp76/Xrd8mXlWZs7PzPmzZ89uuEmSJEnDN7Ph9e0M7BQRRwPPAjYFfgHcBMwDftpwPkmSpJHUaJGVmS+YuB8R1wJ7A9dHxMbAHsB2TeaTJEkaVcWuk5WZCzPzfqrJ7zcBizLzvlL5JEmSRknThwtXkpn3suIMQ0mSpNWCV3yXJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKqBIkRURG0XELhExq8T6JUmSRl3jRVZEbAhcCmwLXBMRsyNicUTcGBEnNZ1PkiRpFM0ssM6tgTdn5k11wbUTMCMzt4+Iz0TEVpn5swJ5JUmSRkbjRVZmXgcQES+gGs3aCDi/XnwlsACwyJIkSWOt1JysAF4C3AskcGe96DfA3A7xR0TEsohYtnz58hJNkiRJGqoiRVZWjgZ+ADwPWKdetF6nnJl5VmbOz8z5s2fPLtEkSZKkoSox8f2EiHh5/XAD4B+pDhECzANuazqnJEnSqCkx8f0s4PyIeA3wI+Bi4BsRsTGwB7BdgZySJEkjpcTE93uBXVqfi4iF9XMfzMz7ms4pSZI0akqMZK2kLrzOnzRQkiRpTDyqOVkRsWDyKEmSpNVXX0VWRHyt7al/KNAWSZKksdHzcGFEbA08G/iLljMG1wUeKN0wSZKk6Wyykazo8PPXwEHFWiRJkjQGeo5kZeYtwC0R8VeZec6Q2iRJkjTt9Xt24akRcTCw1sQTFl2SJEnd9Xt24RXAX1IdLpy4SZIkqYt+R7J+m5nvL9oSSZKkMdJvkXV9RJwLnAP8HiAzv1GsVZIkSdNcv0XWg8D/AZ5LdagwAYssSZKkLvotsm6jKqwmCixJkiT1MMjX6gSwDrAf8IIyzZEkSRoPfY1kZebnWh6eGRGnF2qPJEnSWOiryIqI1pGrOcDTyjRHkiRpPPQ7J2sRK+Zi/Q9wdJnmSJIkjYd+52R9ALgb2Aj4FfDTYi2SJEkaA/0WWZ8B5gKXA38BfLZYiyRJksZAv4cLN8nMw+r7SyPiulINkiRJGgf9Fln/FRHvAL4FbA/cWa5JkiRJ01+/hwuPpCrIDgDuB15XrEWSJEljoN8i6wvAf2bmUcDjqOZoSZIkqYt+i6wNJy5ImpkfAGaVa5IkSdL01++crDsi4gTg21RfEn1PuSZJkiRNf/2OZB0O/DfVnKw/AK8o1SBJkqRx0O93F/4R+HjhtkiSJI2NfkeyJEmSNACLLEmSpAIssiRJkgqwyJIkSSrAIkuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAJmTnUDpKn0kXN3mzTmLYcsHUJLJEnjxpEsSZKkAiyyJEmSCmi8yIqIx0fE5RFxZURcFBFrRcTiiLgxIk5qOp8kSdIoKjGS9TLgo5m5K3AXcDAwIzO3B7aMiK0K5JQkSRopjRdZmXl6Zn6tfjgbOBQ4v358JbCg/Xci4oiIWBYRy5YvX950kyRJkoau2JysiNge2BD4BXBn/fRvgLntsZl5VmbOz8z5s2fPLtUkSZKkoSlSZEXERsDHgVcBvwPWqRetVyqnJEnSKCkx8X0t4EvAOzLzduBmVhwinAfc1nROSZKkUVNiVOnVwDbAOyPiWiCAwyLio8BBwGUFckqSJI2Uxq/4nplnAGe0PhcRlwC7AB/MzPuazilJkjRqhvK1Opl5LyvOMJQkSRp7TkKXJEkqwCJLkiSpAIssSZKkAiyyJEmSCrDIkiRJKsAiS5IkqQCLLEmSpAIssiRJkgqwyJIkSSpgKFd8l6QJe154es/ll+131JBaIkllOZIlSZJUgEWWJElSARZZkiRJBVhkSZIkFeDEd0k9vfCif+i5/Kv7vmNILRlNL7rgop7Lv3LAvkNqiaRR40iWJElSARZZkiRJBVhkSZIkFWCRJUmSVIAT3zWtfPqc3Xouf83Llw6pJZIk9eZIliRJUgEWWZIkSQVYZEmSJBVgkSVJklSARZYkSVIBFlmSJEkFWGRJkiQVYJElSZJUgEWWJElSAV7xXZoG9vjyS3ouv/zF5w2pJZKkfjmSJUmSVIBFliRJUgEWWZIkSQVYZEmSJBXgxHeNpU9+Ybeey48+dOmQWqJh2GvJ2T2XX7r/4UNphyS1ciRLkiSpAIssSZKkAiyyJEmSCrDIkiRJKsCJ79Jq6IUXnzxpzFf3ed8QWjJce13wz5PGXHrAy4bQEkmrA0eyJEmSCihSZEXE3Ii4vuXx4oi4MSJOKpFPkiRp1DReZEXEhsDngHXrx/sBMzJze2DLiNiq6ZySJEmjpsRI1sPAS4D768cLgfPr+1cCCwrklCRJGimNT3zPzPsBImLiqXWBO+v7vwG2af+diDgCOAJg0003bbpJmiJf+uzuPZcf+MorhtSS4Tr+gt6v+0MHlHvde1z8xp7LL9/nY8VyS5L+3DAmvv8OWKe+v16nnJl5VmbOz8z5s2fPHkKTJEmSyhpGkXUzKw4RzgNuG0JOSZKkKTWM62RdDFwfERsDewDbDSGnJEnSlCo2kpWZC+uf91NNfr8JWJSZ95XKKUmSNCqGcsX3zLyXFWcYSgJeeVHvCfIAn913PE8O6NeeSz7Vc/ll+792SC3RdHTukuU9lx+yv3OAVZZXfJckSSrAIkuSJKkAiyxJkqQCLLIkSZIKGMrEd0nS1NlvyU09l1+4v1fWkUpwJEuSJKkAiyxJkqQCLLIkSZIKsMiSJEkqwInvktTBXhf0/pKKSw84qFjuF19wZc/lXz5g12K5JTXHkSxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpACe+S9I0te+S63ouv2j/HQde5wFLbum5/IL95w20vmMv+kXP5aftu8lA6xtHNy++p+fy57x6zpBaoqY5kiVJklSARZYkSVIBFlmSJEkFWGRJkiQVYJElSZJUgGcXasp9/uzdJo057PClQ2iJJDXjm+cs77n8+S+fPaSWaCo5kiVJklSARZYkSVIBFlmSJEkFWGRJkiQV4MR3DeySz+zRc/ner7p8SC2RJK2KX37wjp7Ln/S2Jw+pJePJkSxJkqQCLLIkSZIKsMiSJEkqwCJLkiSpACe+T1Pf+qe9ei7/m9ddOqSWSNJwnXnh3T2XH7nf3CG1ZLhuPaP3637a68fzdU9njmRJkiQVYJElSZJUgEWWJElSARZZkiRJBTjxfcxd96k9ey7f8bWXDakl0upt7wsmPxnlkgN6n9AySl6y5Gc9l5+3/1YDr/MDF/2y5/IT933SwOts2lXnLu+5fOdDZg+pJcN110d69/cT3zJ4fzftno9fNWnMnDfsXMV+ovffvjnHVH877/nkkt5xR+/fc7kjWZIkSQVYZEmSJBVgkSVJklSARZYkSVIBIznxffkZX5g0ZvbrD61iz/xU77gjXwvAPWee0jNuzpHHAXDX6X83ae4nHvUeAO74xOt6xj35mH8C4OefeHHPuL885ssA/OCMvXvGbf36SyZt26O1dPELJ43Z7dVfLZZ/Onjfebv1XH7yS5YOqSWSmnbJl37Vc/neB84aUktW3W2n3tVz+eZvemKx3Hef8oOey+cet/WK2FO/3Tv2TdtWcadd3zvu2B36bN3wOZIlSZJUwNCKrIhYHBE3RsRJw8opSZI0VYZSZEXEfsCMzNwe2DIipv6CGpIkSQUNayRrIXB+ff9KYMGQ8kqSJE2JyMzySSIWA6dl5i0RsSuwTWb+Y8vyI4Aj6od/Bfy0bRWzgN6zEgePbTrO3OY2t7nNbW5zr365N8vMzpf6z8ziN+BjwHb1/f2AEwf8/WVNxzYdZ25zm9vc5ja3uc3dehvW4cKbWXGIcB5w25DySpIkTYlhXSfrYuD6iNgY2APYbkh5JUmSpsRQRrIy836qye83AYsy874BV3FWgdim48xtbnOb29zmNre5/2QoE98lSZJWN17xXZIkqQCLLEmSpAIssiRJkgoY1tmFA4uIp1Bd9mEuVTF4G3BZZv52kt87KzOP6LKsr3UOkrvpdU5V7oh4emb+OCLWAF4IbAXckplXt+cdp9ft9jG3uc09jq/H3FPzHmo3kiNZEXEicCLwAPA9qivAPxW4KSLmtMR9NyJujYir69s1wIERsdIfvgHW2VdciXVOZW7g4/XPs4ADgIeAd0bEe0tvy2myzd0+5jb3mOYet9dj7ql5D3U0yJVLh3UDvtnl+Y8AB7Q8ngt8HjgDWL9+7ppVXGdfcSXWOcW5r65/3tTy3Ayq0Zqi23I6bHO3j7nNPb65x+31mHtq3kOdbiN5CYeI+DTVKNv5wJ3AOsAOwKHAwmy7zlZELAJOAk4Hjs7MnR7tOgfJ3fQ6pzj37cC/AHsBO2fm3RGxNfD5zJxXcltOh23u9jG3ucc397i9HnNPzXuok5EssgAiYl+qC5iuC/yO6qt5Ls4ux0AjYk3g7VR/AHdclXUOkrvpdU5V7oiYAWxNdTX+bwM/pBolfG9m/nhcX7fbx9zmNvc4vh5zT817aKUco1pkSZIkTWcjOfFdkiRpurPIkiRJKmBaFVnR4XT5VYmbLus09+jmng5tNLe5zT066zT36pW756mHo3Sjuj7RU3ssPwa4gOq0yu0HWO9fNxlXYp3mHt3c06GN5ja3uUdnneZezXL3m3iYN+C7wK3A1fXtGuBe6msVtcTtWf/cG3g/1QXCDqPDdS2AJwC7AOsBawMHArv02Z6z+ohpLfKe1LbsDGCbPnNtA8ymugbTa4BXA4/tEvsU4BXA26jOrDwYeNwQ+mcm1aUMtm17/sDS2xx4ev1zjboNxwE7le6bQfpwkH4EXgC8qFsfl+rrYfRht35sug8H7Z+m+6bp/um3b1a1f5rqm8n6p0TfDNI//fbNMPaJTtu8xD4xyDYvsU80uT8Mq2+a3icmbiN5dmFEzAU+THWq5AmZeX9EXJOZi9riPkl1QdLbgA9m5j3189dly2UcIuIJVIXaUuC5VAXbD4ENgDUy85iW2O8CjwHumngKeBbwvWy7/lZE7JmZl0XE3sC2wBfq9R+Zmc9vifsecD0wBzgjM6/r8rrPANYHNqEqMn8K/A2wQWbu3hZ7ItUb+UrgN1RvqnlUb6pFE9uihIhYAtxNtVNuALwyM++IiKsntlHBbX51Zu5UX7tkJtWptPtQFdbvaolrum/6iqtj++rHiPhQHXMPsBtwNnBKZj7Qtr7G+7rpPqzj++rHpvuwjm10H+u3b+rYRvunn76p4xrfx/rtmzp2Kj//Gt93VsfPtTrWz6v6KVZxn+jo0VaWw7gBi4CvA/vTNorVErMD8BOqin5X4PXA+W0xOwPvyBWV+Cdall3bFjvIVeQ/Wef9MDCn5fnr2uImrha+MfD3wDeBjwL7tMV9u/75eOCk+v4M4P4Oufu9Wu03gGWsGBWcGBlsHxXsK66OXdpyf3uq60b9bWtswW3e15XXV6FvbujSN33FDdKPrW2h+g/pYqod+GWPpq8H7O8rmuzDQfqx6T4ssY/12zersC9e03Jr75tJ969S+1i/fVNoH2vtm5O79U3BfafRfaLfbV5in+h3mw+y3Qtt834/rxr9m1Nqn+j4uvsJmsobsCZwcvubqC1mJvAqqu+XOxZYr235hlQfuu1DjYcBV3ZZ56QFXh23gJWLvPPaYq5pexz1m+D9bc9fBhxS7xRfoPoP4HnAjzrk/TTwGWB34JlU/9W8Bfg+8Pi2N9LlE2+iHq+jr7g69qvA37Zt36uAX5fe5sDtwD8APwLm1s89s9MbvkvftBfg3frm7x9NXFs/fqDux3WpPhh+1BZ3KdV/XDOB99V9vS7w7ra4xR36+s3tfT1gf7f34UYD9OGh3fqwn37s0odbd+nD9n+ijmzvwwH7sb1vOu5jHfrm+Z36ptC+OOn+VWof69I3HfevLv2zKvtYX/vNgPtOp755M9V30LXvO6vyudZ1n5hsm5fYJ/rd5m3bveffnVXc5m/pss3n0Ozn1b926Juu+8Mq7BMd+6bj+vsJGodb3Zknt3YA1fHi9mO6fzr2S0uB1x7XFruAFUXeG4HD2uKOpb/jyXOANwDvADal+uN6IXB8h9xPAA6q39CfAn5cv5nW7xB3IJMco+43ro7dtG5na+yuVEPWrXGz6u3XGnd8hx2t9Tj6+sC76P7f0Ky6346h+sN3EPBr6uPmHda5PnBUvX2OB9ZtizuJPo7h9xvX0sZj6/7YFPi/dRuf2xY3n2o4/efAOydZ577AqXVfn1L/znpdYh/fuozO8wzW79Bfi4HXtT23AbBD23MPt/dhh/VP7Ds/77BsBvBsqj/Iz6ljrwKe1mVdrf9E/U97H9Yxr+vwXKfXvUH93jmk7ptPU33Azm+L2xw4j2p+6Ind1lc//4y6fz4J/DtwH9Uf3ce1xT29zr8eK+Z2LOqwvq3rbdM6B2SX9v6qYxdQ/dFtje20j7XOK3kR1T72r11ey7Op9u+Tqfa1X3Xqm5Z1zqR6v/+eqoBp38eOacnddU5L/VreQLXfvBx4hGq/md+lnecBP6DaN7vOk6n75mPAg1QjJf8ObNJln3j9RJupipiPUo+OtL2HXlDfPxpYQrVPrDRXsOV3jq1jbu4Ux5/vE++k+txfQtu+17ZPHFu/dx9ufz2t75W6jb3mM25Qb/eX1u+Lr3fKzZ/vE++sYzrNBzsTeCvV59Wn65+H0Xke3BlUnwEdP8ta4j5DPfLc9hnT/hl2Zod2v43q0Gen3Nu0rKvjYE79Guaz4vNqrXo7PL1XmyduIzknq4QB5jm0x70qM3/RHjdIbERcSHXct5Hc9bHnq6mOeW9L9Yd6pWPPbceoVzmuQ+6ux70fZRsnm+PQ6DqbjnsUbZw0ro5tnTsQ9dPPovPcjr5iu8TNA77fR1w/uaH7HIdVaWOTr7ufNt7dkqZb7tY5G2tSHf7Yh5Xn0zyauNY5IDdk5skN5O4156ev9bXFfqqOXaV1Fnrdg8zr6xQ7n6rwev6g62wgd691vohq3tRU5O53Pthc4PTsPR/se1SHDOfSwJzYAeeiDbLOSdvYVT+V2Djc6H+ew6TH5QeNHSCu0bkYTcetrrmH0MYdJlnnxNyB05l8bkdfsXXcOUw+H2GQeSX9znEYpI395p4zQO5zBtg+/WzzfufTNBo3Qrm/NcKve5B5ff3Od2o0bgxzX1P/7Dk/sq0fJ5tL2dc6pzJ3t9ukAeNyo49juoPElVjnAHF9zcVoOm51zT2VbWxb1tc8wUFim45bHXOzYs7GD+kxZ6PpOHP3HTvpvLFBY5uOG6fcDDYfrK/YpuNKrbPjtu0naBxutBxvb3mu0zHdvuJKrHPA3BtQzwtoeW6lY89Nx62uuaeyjR3eDz1PBBk0tum41S03K88x6zhno+k4c/cXW8f3PDnq0cQ2HTcuuenw96pHzr5im44rtc5Ot9VmTpYkSdIwTavvLpQkSZouLLIkSZIKsMiStFqIiIURsWsD69kiItZuok2SxptFlqSREhFfjIgNeyzfICKuiYien18RcUVEXBsR99RF0cuAP3SJvSoiZtT3D46I17Yt3zYizouIH1N9Gf229e9M3L446OuUNP5mTnUDJGlCRDyD6gKgv4+IhVRX816f6mrij1BdvXofqqvTPzYiPgo8DdiM6rT+jYEjMvMqqu9e270ugALYG3hKRDxSp3tXZt4QEdtRXQV8DaqrZz8MPFS3Z6KQ+2Gd++zMfFlEzAHuyMzD67jBLlAoabXgSJakUXI88F6q70ZbKzN3prp+3Hsy82+BB4CdqK6WfxVVMXQo8OX65zn1cwAzI+JwYAvgNcCHM3Onep1fAR5bxx0F3AhcEBHXAl8EPh0R3wC+RvV1OM+luobZFhFxHNUVr1t5mraklTiSJWkkRMSBVMXM6cBjMvOEDmF/BSwHvkP1/Xb79ljlDKrvePwt8CTgkIjYi+p7LH8O/HdEPB14IdWFRl8cEbtRFV8PAadl5gV127ag+qf0KcBNVN+hKEk9OZIlaVRcTHXV7qC6yORKMnMp1ZdkL83Mr9dPf5Gq2PoicHhL+JpUxVJm5jupvn9sooham6pQ+muqK4dPHBp8O/DPwLnAsRHx2Drvf1AVamtQfRnxvcDu9Zyva4FNVvXFSxo/FlmSRkUCp1CNVL00IrZpD4iIJwIXAg9GxPvrpw8GLqp/nt32K7OoCiqA3am+kHtt4C+B39YjVbdTjeqfVS+/k2r0638DX42Izepi6yjgOuAG4MnAjlTfLbof1QibJP0ZDxdKGhVrU/3j9x2q70f7SYeYu6m+XPt24D7gYz3W90BmXhoRh9aPr8jMwyNifaozBH/WEruIanRqM+CldTu+R/VFsJtSHVI8HXhZZp5an634TeDFwEFU3zN68sCvWNJYs8iSNCr+AHwSeB7VIbkrI+KzEwvrw3nPpJqA/iyqz69bgS9QFUfPojq78NqI2Bq4PSJmUp2dCNWXcpOZ90fEjcAxwGn1sq9l5tl18bQfsA5wTmZOTKK/vm7DRMH2IeAjmXlnRJwGXB8Rl2fmDQ1uD0nTnIcLJY2KzYFPUF2q4Y1Uh+S+DiygupTD1VSXYfg34KDM3KGOPTQzN8nMBVRnF86k+vLgJVSH/B6s139HyxyqV1AdGpwQAJn5x/r+Wi0FVqvH1gXcA5l5bv07D1MdStyygW0gaYz4BdGSpq2IWA/478x8ZNJgSRoyiyxJkqQCPFwoSZJUgEWWJElSARZZkiRJBVhkSZIkFWCRJUmSVMD/B00aITvl2Y6LAAAAAElFTkSuQmCC",
-      "text/plain": [
-       "<Figure size 720x360 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 720x360 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 720x360 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "# 再查看一下每个变量的分布\n",
-    "for i in df.columns:\n",
-    "    plt.figure(figsize=(10,5))\n",
-    "    plt.title(i)\n",
-    "    # 设置字体旋转角度\n",
-    "    plt.xticks(rotation=90)\n",
-    "    sns.countplot(df[i])\n",
-    "    plt.show()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "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>accuracy_score</th>\n",
-       "      <th>confusion_matrix</th>\n",
-       "      <th>time</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>GaussianNB</th>\n",
-       "      <td>0.768519</td>\n",
-       "      <td>[[23, 18], [7, 60]]</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>LogisticRegression</th>\n",
-       "      <td>0.75</td>\n",
-       "      <td>[[22, 19], [8, 59]]</td>\n",
-       "      <td>0.002009</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>AdaBoostClassifier</th>\n",
-       "      <td>0.740741</td>\n",
-       "      <td>[[24, 17], [11, 56]]</td>\n",
-       "      <td>0.062897</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>RandomForestClassifier</th>\n",
-       "      <td>0.731481</td>\n",
-       "      <td>[[27, 14], [15, 52]]</td>\n",
-       "      <td>0.159735</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>SVC</th>\n",
-       "      <td>0.722222</td>\n",
-       "      <td>[[20, 21], [9, 58]]</td>\n",
-       "      <td>0.004007</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>KNeighborsClassifier</th>\n",
-       "      <td>0.712963</td>\n",
-       "      <td>[[21, 20], [11, 56]]</td>\n",
-       "      <td>0.003</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>BaggingClassifier</th>\n",
-       "      <td>0.657407</td>\n",
-       "      <td>[[27, 14], [23, 44]]</td>\n",
-       "      <td>0.017781</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>DecisionTreeClassifier</th>\n",
-       "      <td>0.546296</td>\n",
-       "      <td>[[15, 26], [23, 44]]</td>\n",
-       "      <td>0.002382</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                       accuracy_score      confusion_matrix      time\n",
-       "GaussianNB                   0.768519   [[23, 18], [7, 60]]       0.0\n",
-       "LogisticRegression               0.75   [[22, 19], [8, 59]]  0.002009\n",
-       "AdaBoostClassifier           0.740741  [[24, 17], [11, 56]]  0.062897\n",
-       "RandomForestClassifier       0.731481  [[27, 14], [15, 52]]  0.159735\n",
-       "SVC                          0.722222   [[20, 21], [9, 58]]  0.004007\n",
-       "KNeighborsClassifier         0.712963  [[21, 20], [11, 56]]     0.003\n",
-       "BaggingClassifier            0.657407  [[27, 14], [23, 44]]  0.017781\n",
-       "DecisionTreeClassifier       0.546296  [[15, 26], [23, 44]]  0.002382"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 由于变量的取值范围不一样，因此需要对数据进行标准化\n",
-    "import time\n",
-    "X_train,X_test,y_train,y_test = train_test_split(df[df.columns[:-1]],df['y'],test_size=0.3,random_state=0)\n",
-    "X_train = StandardScaler().fit_transform(X_train)\n",
-    "X_test = StandardScaler().fit_transform(X_test)\n",
-    "\n",
-    "model_result = {}\n",
-    "\n",
-    "models = [RandomForestClassifier(),BaggingClassifier(),AdaBoostClassifier(),GaussianNB(),LogisticRegression(),DecisionTreeClassifier(),SVC(),KNeighborsClassifier()]\n",
-    "for model in models:\n",
-    "    try:\n",
-    "        model_name = str(model).split('(')[0]\n",
-    "        start = time.time()\n",
-    "        model.fit(X_train,y_train)\n",
-    "        y_pred = model.predict(X_test)\n",
-    "        end = time.time()\n",
-    "        # 存储准确率和混淆矩阵\n",
-    "        model_result[model_name] = [accuracy_score(y_test,y_pred),confusion_matrix(y_test,y_pred),end-start]\n",
-    "    except Exception as e:\n",
-    "        print(model_name,e)\n",
-    "\n",
-    "## 使用df保存模型的结果\n",
-    "df_result = pd.DataFrame(model_result).T\n",
-    "df_result.columns = ['accuracy_score','confusion_matrix','time']\n",
-    "\n",
-    "df_result.sort_values(by='accuracy_score',ascending=False)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 对数几率回归"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "0.75"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "#第1步：导入算法\n",
-    "from sklearn.linear_model import LogisticRegression\n",
-    "#第2步：创建模型：逻辑回归（logistic regression）\n",
-    "model = LogisticRegression()\n",
-    "#第3步：训练模型\n",
-    "model.fit( X_train , y_train )\n",
-    "#查看模型的正确率\n",
-    "model.score(X_test , y_test )"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## SVC"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Accuracy: 0.72\n"
-     ]
-    }
-   ],
-   "source": [
-    "clf = SVC(kernel='rbf', C=1.0, random_state=0)\n",
-    "clf.fit(X_train, y_train)\n",
-    "y_test_pred = clf.predict(X_test)\n",
-    "print('Accuracy: %.2f' % accuracy_score(y_test, y_test_pred))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 432x288 with 2 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "cm = confusion_matrix(y_test, y_test_pred)\n",
-    "sns.heatmap(cm, annot=True, fmt='d')\n",
-    "plt.xlabel('Predicted Label')\n",
-    "plt.ylabel('True Label')\n",
-    "plt.title('Confusion Matrix')\n",
-    "plt.show()"
-   ]
-  }
- ],
- "metadata": {
-  "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": "3.9.12"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 0
-}