{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "b933782e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: openpyxl in c:\\users\\cnaem\\anaconda3\\lib\\site-packages (3.0.10)\n",
      "Requirement already satisfied: et_xmlfile in c:\\users\\cnaem\\anaconda3\\lib\\site-packages (from openpyxl) (1.1.0)\n"
     ]
    }
   ],
   "source": [
    "!pip install openpyxl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "1442730e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "70648419",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     Case_no   Gender   Age    BW  Height        BMI            VCM_처방일자  \\\n",
      "0           1        0   71  52.0   150.0  23.111111 2020-11-11 00:00:00   \n",
      "1           2        1   77  60.0   160.0  23.437500 2020-11-18 08:23:58   \n",
      "2           3        1   78  50.0   151.0  21.928863 2020-11-23 00:00:00   \n",
      "3           4        1   58  63.0   168.0  22.321429 2020-11-23 00:00:00   \n",
      "4           5        1   78  50.0   151.0  21.928863 2020-11-23 00:00:00   \n",
      "..        ...      ...  ...   ...     ...        ...                 ...   \n",
      "447       448        1   61  70.0   170.0  24.221453 2023-06-21 00:00:00   \n",
      "448       449        0   81  70.0   167.0  25.099502 2023-06-21 00:00:00   \n",
      "449       450        0  101  43.0   140.0  21.938776 2023-06-21 00:00:00   \n",
      "450       451        1   52  66.0   172.0  22.309356 2023-06-16 00:00:00   \n",
      "451       452        1   72  80.7   176.5  25.905031 2023-06-22 00:00:00   \n",
      "\n",
      "               TDM_실시일자  Days_to_TDM  Loading  ...  ARB  ACEi  Fusosemide  \\\n",
      "0   2020-11-15 00:00:00            4        0  ...    0     0           0   \n",
      "1   2020-11-22 00:00:00            4        0  ...    0     0           0   \n",
      "2   2020-11-25 16:30:26            2        0  ...    0     0           0   \n",
      "3   2020-11-25 11:50:13            2        0  ...    0     0           0   \n",
      "4   2020-11-27 15:29:12            4        0  ...    1     0           0   \n",
      "..                  ...          ...      ...  ...  ...   ...         ...   \n",
      "447 2023-06-22 09:15:56            1        0  ...    0     0           0   \n",
      "448 2023-06-23 09:15:59            2        0  ...    1     0           0   \n",
      "449 2023-06-22 09:15:48            1        0  ...    0     0           0   \n",
      "450 2023-06-18 08:45:08            2        0  ...    0     0           0   \n",
      "451 2023-06-24 11:00:03            2        0  ...    0     0           0   \n",
      "\n",
      "     Diuretics  Vasopressors  LAB AG  TZP FLC FQ  \n",
      "0            0             0    0  0    0   0  0  \n",
      "1            0             0    0  0    0   0  0  \n",
      "2            0             0    0  0    0   0  0  \n",
      "3            0             0    0  0    0   0  0  \n",
      "4            0             0    0  0    0   0  0  \n",
      "..         ...           ...  ... ..  ...  .. ..  \n",
      "447          0             0    0  0    0   0  0  \n",
      "448          0             0    0  0    0   0  0  \n",
      "449          0             0    0  0    0   0  0  \n",
      "450          0             0    0  0    0   0  0  \n",
      "451          0             0    0  0    0   0  0  \n",
      "\n",
      "[452 rows x 49 columns]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\cnaem\\AppData\\Local\\Temp\\ipykernel_18428\\1302059992.py:2: FutureWarning: Inferring datetime64[ns] from data containing strings is deprecated and will be removed in a future version. To retain the old behavior explicitly pass Series(data, dtype=datetime64[ns])\n",
      "  dfVanco = pd.read_excel(file_name)\n"
     ]
    }
   ],
   "source": [
    "file_name = 'Vancomycin AUC_최종 (1).xlsx'\n",
    "dfVanco = pd.read_excel(file_name)\n",
    "\n",
    "print(dfVanco)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "2743d963",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "({'Initial VCM_daily_dose': True, 'TDM_AUC': True},\n",
       "    Case_no   Gender   Age    BW  Height        BMI            VCM_처방일자  \\\n",
       " 0         1        0   71  52.0   150.0  23.111111 2020-11-11 00:00:00   \n",
       " 1         2        1   77  60.0   160.0  23.437500 2020-11-18 08:23:58   \n",
       " 2         3        1   78  50.0   151.0  21.928863 2020-11-23 00:00:00   \n",
       " 3         4        1   58  63.0   168.0  22.321429 2020-11-23 00:00:00   \n",
       " 4         5        1   78  50.0   151.0  21.928863 2020-11-23 00:00:00   \n",
       " \n",
       "              TDM_실시일자  Days_to_TDM  Loading  ...  ARB  ACEi  Fusosemide  \\\n",
       " 0 2020-11-15 00:00:00            4        0  ...    0     0           0   \n",
       " 1 2020-11-22 00:00:00            4        0  ...    0     0           0   \n",
       " 2 2020-11-25 16:30:26            2        0  ...    0     0           0   \n",
       " 3 2020-11-25 11:50:13            2        0  ...    0     0           0   \n",
       " 4 2020-11-27 15:29:12            4        0  ...    1     0           0   \n",
       " \n",
       "    Diuretics  Vasopressors  LAB AG  TZP FLC FQ  \n",
       " 0          0             0    0  0    0   0  0  \n",
       " 1          0             0    0  0    0   0  0  \n",
       " 2          0             0    0  0    0   0  0  \n",
       " 3          0             0    0  0    0   0  0  \n",
       " 4          0             0    0  0    0   0  0  \n",
       " \n",
       " [5 rows x 49 columns])"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "df = dfVanco\n",
    "\n",
    "# Check if the columns 'Initial VCM_daily_dose' and 'TDM_AUC' exist\n",
    "col_exists = {'Initial VCM_daily_dose': False, 'TDM_AUC': False}\n",
    "\n",
    "for col in df.columns:\n",
    "    if col == 'Initial VCM_daily_dose':\n",
    "        col_exists['Initial VCM_daily_dose'] = True\n",
    "    if col == 'TDM_AUC':\n",
    "        col_exists['TDM_AUC'] = True\n",
    "\n",
    "col_exists, df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "bc2dad2d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Visualize the data distribution of 'Initial VCM_daily_dose' and 'TDM_AUC'\n",
    "plt.figure(figsize=(12, 6))\n",
    "\n",
    "# Plot for 'Initial VCM_daily_dose'\n",
    "plt.subplot(1, 2, 1)\n",
    "plt.hist(df['Initial VCM_daily_dose'], color='blue', bins=20, edgecolor='black')\n",
    "plt.xlabel('Initial VCM_daily_dose')\n",
    "plt.ylabel('Frequency')\n",
    "plt.title('Distribution of Initial VCM_daily_dose')\n",
    "\n",
    "# Plot for 'TDM_AUC'\n",
    "plt.subplot(1, 2, 2)\n",
    "plt.hist(df['TDM_AUC'], color='blue', bins=20, edgecolor='black')\n",
    "plt.xlabel('TDM_AUC')\n",
    "plt.ylabel('Frequency')\n",
    "plt.title('Distribution of TDM_AUC')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "210af76f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "\n",
    "# Apply log transformation to 'Initial VCM_daily_dose' and 'TDM_AUC' to handle skewness\n",
    "# Adding a small constant to avoid log(0)\n",
    "log_initial_vcm = np.log1p(df['Initial VCM_daily_dose'])\n",
    "log_tdm_auc = np.log1p(df['TDM_AUC'])\n",
    "\n",
    "# Visualize the log-transformed data\n",
    "plt.figure(figsize=(12, 6))\n",
    "\n",
    "# Plot for log-transformed 'Initial VCM_daily_dose'\n",
    "plt.subplot(1, 2, 1)\n",
    "plt.hist(log_initial_vcm, color='blue', bins=20, edgecolor='black')\n",
    "plt.xlabel('Log(Initial VCM_daily_dose)', fontsize=12)\n",
    "plt.ylabel('Frequency', fontsize=12)\n",
    "plt.title('Log-Transformed Distribution of Initial VCM_daily_dose')\n",
    "\n",
    "# Plot for log-transformed 'TDM_AUC'\n",
    "plt.subplot(1, 2, 2)\n",
    "plt.hist(log_tdm_auc, color='blue', bins=20, edgecolor='black')\n",
    "plt.xlabel('Log(TDM_AUC)', fontsize=12)\n",
    "plt.ylabel('Frequency', fontsize=12)\n",
    "plt.title('Log-Transformed Distribution of TDM_AUC')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "27ff1dd9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1sAAAIhCAYAAAC48qAWAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAABzD0lEQVR4nO3deXxTVf7/8Xe6UkobKdCWQll0AFEQFRAB0SKLqGWxMopVQEBEUaSCqIw6os6AoiKMiAuyKzAuBdzYlEUYFgFFQXEvAqUVvlBa1hbS8/sjv0bSNYWkTdLX8/HIo+bcT27OxdvbfHLO/RyLMcYIAAAAAOBWAZXdAQAAAADwRyRbAAAAAOABJFsAAAAA4AEkWwAAAADgASRbAAAAAOABJFsAAAAA4AEkWwAAAADgASRbAAAAAOABJFsAAAAA4AEkW4AXmz17tiwWi+MRFBSk+vXra9CgQUpPT6+QPjRq1Eh333234/maNWtksVi0Zs2acu1nw4YNGjdunI4cOVJkW0JCghISEs6rn562e/du3XzzzYqKipLFYlFKSkqRmHHjxjn9/yrpUXCsd999t1N7eHi4GjVqpF69emnWrFnKzc0t8h4JCQmyWCy68MILZYwpsv3LL7907G/27NnndKz/93//p9DQUFksFm3durXYmISEBLVo0aLE11ssFo0bN67Itu+++06DBg1S48aNVa1aNdWoUUNXXnmlJk6cqMOHD5far7vvvls1atQo9/FUNm87vy0Wix588MFzeu3dd9+tRo0aObWNHz9eixcvLhJ7rtcKV1/78MMPy2Kx6Mcffywx5oknnpDFYtHXX3/taMvNzdXUqVN1zTXXqGbNmgoJCVG9evV02223ae3atUX6UNrv0vXXXy+LxVLk3+RcFffv66rizrOSfg89Zffu3ed17QH8UVBldwBA2WbNmqWLL75YJ0+e1JdffqkJEyZo7dq12rFjh8LDwyu0L1deeaU2btyoSy65pFyv27Bhg5555hndfffduuCCC5y2TZs2zY099IyHH35Ymzdv1syZMxUbG6u6desWibnnnnvUo0cPx/OMjAwlJSVpxIgRSk5OdrRHRkY6/jssLEyrVq2SJJ08eVJ79+7V0qVLNXToUL388statmyZ6tev7/Q+ERERSktL06pVq9SlSxenbTNnzlRkZKRycnLO+VjnzZunvLw8SdKMGTPUpk2bc97X2aZPn67hw4erWbNmGjNmjC655BKdPn1aW7du1RtvvKGNGzdq0aJFbnkveMZTTz2lkSNHOrWNHz9effv2VZ8+fZzaz/Va4aohQ4Zo8uTJmjlzpiZOnFhke35+vubOnavLL79cV155pST7FwE9evTQd999p8GDB2vMmDGKiopSenq6lixZoi5dumjbtm1q1aqVYz8RERGaMWOG05dOkpSWlqY1a9Y4/T5XJl+4jgJVEckW4ANatGjh+MDbuXNn2Ww2Pffcc1q8eLHuvPPOYl9z4sQJVa9e3e19iYyM1NVXX+3WfXrqw5g77dy5U1dddVWRD5Rnq1+/vlNitHv3bklSgwYNSvw3CwgIKLJtwIABGjRokBITE9W3b19t2rTJaXuDBg0UERGhmTNnOiVbR48e1fvvv68777xT06dPL+cR/mXmzJmKjo5Ww4YNtWDBAk2aNElhYWHnvD9J2rhxo+6//35169ZNixcvVmhoqGNbt27dNHr0aC1btuy83gOed9FFF7kc64lrxdlatGihq666SvPmzdP48eMVFOT8kWbFihXat2+fHnvsMUfbgAED9O2332r58uW6/vrrneL79eunUaNGqWbNmk7tt99+u95++2398ssvatKkiaN95syZqlevnlq2bKkffvjBA0dYPr5wHQWqIqYRAj6o4APMH3/8Iemv6VU7duxQ9+7dFRER4fgQnpeXp3/961+6+OKLFRoaqjp16mjQoEE6ePCg0z5Pnz6tRx99VLGxsapevbquueYaffXVV0Xeu6TpPZs3b1bPnj1Vq1YtVatWTRdddJFjqt24ceM0ZswYSVLjxo0dU3MK9lHc9JfDhw9r+PDhqlevnkJCQnThhRfqiSeeKDK1rmBK1Lx589S8eXNVr15drVq10ieffOLSv+WePXt01113KTo6WqGhoWrevLlefvll5efnOx3vr7/+qqVLlzr6XpBIeUr37t01dOhQbd68WV9++WWR7YMHD1ZqaqrTtMyFCxdKsn9oPFebN2/Wzp071b9/fw0dOlTZ2dn68MMPz3l/BcaPHy+LxaK33nrLKdEqEBISol69erm0r++//15dunRReHi46tSpowcffFAnTpxwinnttdd07bXXKjo6WuHh4WrZsqUmTpyo06dPO8V98803SkxMdPz/j4uL080336x9+/Y5YowxmjZtmi6//HKFhYWpZs2a6tu3r37//XenfRljNHHiRDVs2FDVqlXTlVdeqaVLl7r6T6RTp05p7Nixaty4sWNq2wMPPFBk6m2jRo2UmJioZcuW6corr1RYWJguvvhizZw50+X3OlvBOb5gwQI98cQTiouLU2RkpLp27aqffvrJKbbwNDeLxaLjx49rzpw5RabJFnet2Lp1q/r166dGjRopLCxMjRo10h133OG4lpXXkCFDlJmZWey/86xZsxQaGur4Qmrbtm1aunSphgwZUiTRKtC2bVs1aNDAqa1bt26Kj493+vfNz8/XnDlzNHDgQAUEnNtHqdmzZ6tZs2aO687cuXOLjXvmmWfUrl07RUVFKTIyUldeeaVmzJhRZBpxWdNVd+/eraCgIE2YMKHItoLpx++//77L/d+/f79uu+02RUREyGq16vbbb1dmZmaxsR999JHat2+v6tWrKyIiQt26ddPGjRudYg4ePKh7771X8fHxjr9VHTt21Oeff+4U9/nnn6tLly6KjIxU9erV1bFjR33xxRcu9xuoaCRbgA/69ddfJUl16tRxtOXl5alXr166/vrrtWTJEj3zzDPKz89X79699fzzzys5OVmffvqpnn/+ea1cuVIJCQk6efKk4/VDhw7VSy+9pAEDBmjJkiW69dZblZSUpKysrDL7s3z5cnXq1El79uzRpEmTtHTpUj355JP6888/Jdmn140YMUKSlJqaqo0bN2rjxo2OqT2FnTp1Sp07d9bcuXM1atQoffrpp7rrrrs0ceJEJSUlFYn/9NNPNXXqVD377LP68MMPFRUVpVtuuaXIh+HCDh48qA4dOmjFihV67rnn9NFHH6lr16565JFHHPe0FEyFio2NVceOHR19L24aobsVJB/FJVv9+vVTYGCgFixY4GibMWOG+vbte17TmmbMmCHJnsz169dP1atXd7SdK5vNplWrVql169aKj48/r32dPn1aN910k7p06aLFixfrwQcf1Jtvvqnbb7/dKe63335TcnKy5s2bp08++URDhgzRiy++qGHDhjlijh8/rm7duunPP//Ua6+9ppUrV2ry5Mlq0KCBjh496ogbNmyYUlJS1LVrVy1evFjTpk3T999/rw4dOjjOccn+ofixxx5zjN7df//9Gjp0aJGEpTjGGPXp00cvvfSS+vfvr08//VSjRo3SnDlzdP311xf5kuHbb7/V6NGj9fDDD2vJkiW67LLLNGTIkGLPFVf94x//0B9//KG3335bb731ln755Rf17NlTNputxNds3LhRYWFhuummmxy/G6VNZ9u9e7eaNWumyZMna/ny5XrhhReUkZGhtm3b6v/+7//K3ec77rhD1atXL5JoZmVlacmSJbrlllscI1UrVqyQpFJHp4sTEBCgu+++W3PnznX8WxSMmg0aNKjcfZbsidagQYPUvHlzffjhh3ryySf13HPPOaYUn2337t0aNmyY3nvvPaWmpjqmJj/33HPles+C+0HfeOONIv9Pp06dqri4ON1yyy0u7evkyZPq2rWrVqxYoQkTJuj9999XbGxskd9DSZo/f7569+6tyMhILViwQDNmzFBWVpYSEhK0fv16R1z//v21ePFi/fOf/9SKFSv09ttvq2vXrjp06JAj5p133lH37t0VGRmpOXPm6L333lNUVJRuuOEGEi54LwPAa82aNctIMps2bTKnT582R48eNZ988ompU6eOiYiIMJmZmcYYYwYOHGgkmZkzZzq9fsGCBUaS+fDDD53at2zZYiSZadOmGWOM2bVrl5FkHn74Yae4d99910gyAwcOdLStXr3aSDKrV692tF100UXmoosuMidPnizxWF588UUjyaSlpRXZdt1115nrrrvO8fyNN94wksx7773nFPfCCy8YSWbFihWONkkmJibG5OTkONoyMzNNQECAmTBhQon9McaYxx9/3Egymzdvdmq///77jcViMT/99JOjrWHDhubmm28udX+FpaWlGUnmxRdfLHb7wIEDTXh4eImvL/j/cv/99zvarrvuOnPppZc6Xt+mTRtjjDHff/+9kWTWrFnj+P87a9ascvX3+PHjJjIy0lx99dVOfbRYLObXX391ij27H4UdPHjQSDJPP/20Mcb+/0OS6devX7n6U1jBeT5lyhSn9n//+99Gklm/fn2xr7PZbOb06dNm7ty5JjAw0Bw+fNgYY8zWrVuNJLN48eIS33Pjxo1Gknn55Zed2vfu3WvCwsLMo48+aowxJisry1SrVs3ccsstTnH/+9//jCSn87s4y5YtM5LMxIkTndr/+9//GknmrbfecrQ1bNjQVKtWzfzxxx+OtpMnT5qoqCgzbNiwUt/HGPvvzAMPPOB4XvA7fdNNNznFvffee0aS2bhxo6Nt4MCBpmHDhk5x4eHhTteIwvs9+1pR2JkzZ8yxY8dMeHi40/9XV157dp+Cg4PNn3/+6Wh79dVXjSSzcuVKR9t9991nJJkff/yxzH2e3Yf333/f/P7778ZisZhPPvnEGGPM3//+d5OQkGCMMebmm28u8m9SGpvNZuLi4syVV15p8vPzHe27d+82wcHBpe6r4Fx+9tlnTa1atZxeX/g6aoxx+j08+5gWLVrkaEtPTzdBQUHmmWeecfkYXn/9dSPJLFmyxKl96NChTteegmNt2bKlsdlsjrijR4+a6Oho06FDB0dbjRo1TEpKSonvefz4cRMVFWV69uzp1G6z2UyrVq3MVVdd5XL/gYrEyBbgA66++moFBwcrIiJCiYmJio2N1dKlSxUTE+MUd+uttzo9/+STT3TBBReoZ8+eOnPmjONx+eWXKzY21jG9Z/Xq1ZJU5P6v2267rch9EIX9/PPP+u233zRkyBBVq1btPI/UbtWqVQoPD1ffvn2d2gtuUC/8DWbnzp0VERHheB4TE6Po6OgypyatWrVKl1xyia666qoi72OMKfZb5opkiqk2eLbBgwdr69at2rFjh2bMmKGLLrpI11577Tm/33vvvaecnBwNHjzY6T2MMZo1a9Y579fdCp+nBcVHCs5jyT49sFevXqpVq5YCAwMVHBysAQMGyGaz6eeff5Yk/e1vf1PNmjX12GOP6Y033ij2vptPPvlEFotFd911l9PvUGxsrFq1auX4Hdq4caNOnTpVpG8dOnRQw4YNyzymgnOtcBGGv//97woPDy9yzl9++eVO092qVaumpk2bnvN0PElFpnFedtllknRe+yzs2LFjeuyxx/S3v/1NQUFBCgoKUo0aNXT8+HHt2rXrnPY5ZMgQnT59WvPmzXO0zZo1Sw0bNixSQOZcNW7cWAkJCZo5c6YOHTqkJUuWOP2elMdPP/2k/fv3Kzk5WRaLxdHesGFDdejQoUj8qlWr1LVrV1mtVse5/M9//lOHDh3SgQMHyvXeCQkJatWqlV577TVH2xtvvCGLxaJ7773X5f2sXr1aERERRc6ZswsBSX8da//+/Z2mW9aoUUO33nqrNm3a5JgCfNVVV2n27Nn617/+pU2bNhWZ8rthwwYdPnxYAwcOdPpdzM/PV48ePbRlyxYdP37c5WMAKgrJFuAD5s6dqy1btuibb77R/v379d1336ljx45OMdWrVy8yfezPP//UkSNHFBISouDgYKdHZmamY9pOwTSN2NhYp9cHBQWpVq1apfat4N6vwhXzzsehQ4cUGxvr9EFEkqKjoxUUFOQ0rURSsX0MDQ11miZZ0vsUNx0wLi7Osb0yFXzILehPYddee62aNGmiN998U/PmzdPgwYOL/JuVx4wZM1StWjX16NFDR44c0ZEjR3TZZZepUaNGmj17ttPUo6CgoBKnl505c0aSFBwcLEmqXbu2qlevrrS0tHPu29nvW/j/d8F5W/D/a8+ePerUqZPS09M1ZcoUrVu3Tlu2bHF8wCw4L6xWq9auXavLL79c//jHP3TppZcqLi5OTz/9tOOD3p9//iljjGJiYor8Dm3atKnM36GS2go7dOiQgoKCnKYGS/Z7omJjY912zpem8D4L7q07n30WlpycrKlTp+qee+7R8uXL9dVXX2nLli2qU6fOOb9Pp06d1LRpU8cXAt99952+/vprDRo0yOn3oSA5PdfzcMiQIfr4448dBWMKfxnkqvKcK1999ZW6d+8uyV7N83//+5+2bNmiJ554QtK5/b956KGH9MUXX+inn37S6dOnNX36dPXt29el8/TsYyj8ZV9x/S841pKus/n5+Y6p6v/97381cOBAvf3222rfvr2ioqI0YMAAx31gBVN2+/btW+R38YUXXpAxpszlI4DKQDVCwAc0b968zPLbxX3Irl27tmrVqlVilbeC0aCCD1mZmZmqV6+eY/uZM2fKTDgKPhyeXVDgfNWqVUubN2+WMcbpuA4cOKAzZ86odu3abnufjIyMIu379++XJLe9z7n66KOPJKnUm94HDRqkJ598UhaLRQMHDjzn9/r5558d908ULhBQYPny5brpppsk2UcPt2zZUuT/kSTHGnAFH8YCAwPVpUsXLV26VPv27TuvxLzgnDw7MSj4MFbQtnjxYh0/flypqalOo0rbt28vsr+WLVtq4cKFMsbou+++0+zZs/Xss88qLCxMjz/+uGrXri2LxaJ169YVW9ijoO3s36HCMjMzy1w7qVatWjpz5owOHjzolHAZY5SZmam2bduW+npfkJ2drU8++URPP/20Hn/8cUd7bm7ueX9IHjx4sB5//HF99dVXmj9/vuM+q7PdcMMN+sc//qHFixc7LdHgqqSkJD3wwAN6/vnnNXTo0HOu0FnWuXK2hQsXKjg4WJ988onTzIHi1jVzVXJysh577DG99tpruvrqq5WZmakHHnigXPuoVatWsQWUCve/4FhLus4GBAQ47qmrXbu2Jk+erMmTJ2vPnj366KOP9Pjjj+vAgQNatmyZ43r86quvlljlsrgEEKhsjGwBfiwxMVGHDh2SzWZTmzZtijyaNWsm6a8P8++++67T69977z3HKEVJmjZtqosuukgzZ84sdhHeAuX5lrxLly46duxYkQ8UBdW63DU1qEuXLvrhhx+cFjwteB+LxaLOnTu75X3OxcqVK/X222+rQ4cOuuaaa0qMGzhwoHr27KkxY8Y4JcrlVVAEY/r06Vq9erXT47PPPlNwcLBTEYKuXbsqJyen2ET+vffeU0BAgFPFt7Fjx8oYo6FDhzrW8Drb6dOn9fHHH7vU18Ln6fz58yX9dR4XJH9nJ0fGmFLL4VssFrVq1UqvvPKKLrjgAsc5kZiYKGOM0tPTi/0datmypST7VN9q1aoV6duGDRtcmoZXcE6/8847Tu0ffvihjh8/7rZz3hNcHVGzWCwyxhRJWt9+++1Si3C4YuDAgQoKCtKbb76pd999V126dCkyffPKK6/UjTfeqBkzZpQ4RXjr1q3as2dPsdvCwsL0z3/+Uz179tT9999/zn1t1qyZ6tatqwULFjhNFf7jjz+0YcMGp9iCxewDAwMdbSdPnnSaMlle1apV07333qs5c+Zo0qRJuvzyy4vMlChL586ddfToUccXQgUKfhcLNGvWTPXq1dP8+fOdjvX48eP68MMPHRUKC2vQoIEefPBBdevWzfG72LFjR11wwQX64Ycfiv1dbNOmjUJCQsp1HEBFYGQL8GP9+vXTu+++q5tuukkjR47UVVddpeDgYO3bt0+rV69W7969dcstt6h58+a66667NHnyZAUHB6tr167auXOnXnrpJZcq27322mvq2bOnrr76aj388MNq0KCB9uzZo+XLlzs+fBZ8KJ0yZYoGDhyo4OBgNWvWzOleqwIDBgzQa6+9poEDB2r37t1q2bKl1q9fr/Hjx+umm25S165d3fLv8/DDD2vu3Lm6+eab9eyzz6phw4b69NNPNW3aNN1///1q2rSpW96nNPn5+Y51tHJzc7Vnzx4tXbpU7733npo3b6733nuv1NfHxcWd17fckn20aO7cuWrevLnuueeeYmN69uypjz76yDHycuedd2ratGm67bbb9Pjjj6tt27Y6efKkPvvsM02fPl0jRozQhRde6Hh9+/bt9frrr2v48OFq3bq17r//fl166aU6ffq0vvnmG7311ltq0aKFevbsWWpfQ0JC9PLLL+vYsWNq27atNmzYoH/961+68cYbHUlpt27dFBISojvuuEOPPvqoTp06pddff71IZc1PPvlE06ZNU58+fXThhRfKGOMop9+tWzdJ9g949957rwYNGqStW7fq2muvVXh4uDIyMrR+/Xq1bNlS999/v2rWrKlHHnlE//rXv3TPPffo73//u/bu3atx48a5ND2rW7duuuGGG/TYY48pJydHHTt21Hfffaenn35aV1xxhfr371/mPipLy5YttWbNGn388ceqW7euIiIiHF/knC0yMlLXXnutXnzxRdWuXVuNGjXS2rVrNWPGjCILnZdXbGysbrrpJs2aNUvGGA0ZMqTYuLlz56pHjx668cYbNXjwYN14442qWbOmMjIy9PHHH2vBggXatm1biaO7o0aN0qhRo86rrwEBAXruued0zz336JZbbtHQoUN15MiRYs+Vm2++WZMmTVJycrLuvfdeHTp0SC+99FKxo6zlMXz4cE2cOFHbtm3T22+/Xe7XDxgwQK+88ooGDBigf//732rSpIk+++wzLV++vMixTpw4UXfeeacSExM1bNgw5ebm6sUXX9SRI0f0/PPPS7KPenbu3FnJycm6+OKLFRERoS1btmjZsmWOCrQ1atTQq6++qoEDB+rw4cPq27evoqOjdfDgQX377bc6ePCgXn/99fP6dwE8osJLcgBwWUE1wi1btpQaV1pVu9OnT5uXXnrJtGrVylSrVs3UqFHDXHzxxWbYsGHml19+ccTl5uaa0aNHm+joaFOtWjVz9dVXm40bN5qGDRuWWY3QGHvVthtvvNFYrVYTGhpqLrrooiLVDceOHWvi4uJMQECA0z6Kq6J16NAhc99995m6deuaoKAg07BhQzN27Fhz6tQppzgVqqxWoHC/S/LHH3+Y5ORkU6tWLRMcHGyaNWtmXnzxRafKWQX780Q1QkmOR1hYmGnQoIHp2bOnmTlzpsnNzS3ymtKqABYobzXCxYsXG0lm8uTJJcYUVMs7uypfTk6OefTRR02TJk1MSEiIqV69umnTpo154403nKqknW379u1m4MCBpkGDBiYkJMSEh4ebK664wvzzn/80Bw4cKLWfBef5d999ZxISEkxYWJiJiooy999/vzl27JhT7Mcff+w45+vVq2fGjBljli5d6nTe/fjjj+aOO+4wF110kQkLCzNWq9VcddVVZvbs2UXee+bMmaZdu3YmPDzchIWFmYsuusgMGDDAbN261RGTn59vJkyYYOLj401ISIi57LLLzMcff1zs+V2ckydPmscee8w0bNjQBAcHm7p165r777/fZGVlOcWVdC66+j6Ff2fOrrp3toLz9+zzqLhqhNu3bzcdO3Y01atXd6q8WNy1Yt++febWW281NWvWNBEREaZHjx5m586dLl9nSrNkyRIjyURFRRW5Tpzt5MmT5j//+Y9p3769iYyMNEFBQSYuLs4kJSWZTz/9tMx/l8LKW42wwNtvv+343WnatKmZOXNmsf++M2fONM2aNTOhoaHmwgsvNBMmTDAzZswoUt3VlWqEZ0tISDBRUVHmxIkT5e67MX/9v6xRo4aJiIgwt956q9mwYUOx157Fixebdu3amWrVqpnw8HDTpUsX87///c+x/dSpU+a+++4zl112mYmMjDRhYWGmWbNm5umnnzbHjx932tfatWvNzTffbKKiokxwcLCpV6+eufnmm8v8/wRUFosxZZS7AgAAgN84cOCAGjZsqBEjRmjixImV3R3ArzGNEAAAoArYt2+ffv/9d7344osKCAjQyJEjK7tLgN8j2QIAP1dWkZOAgACnNXAAnJv8/Hzl5+eXGlPW2oWe9Pbbb+vZZ59Vo0aN9O677xZbVIfrBeBe/LYAgB/bvXt3kTVpCj+effbZyu4m4BcGDx5c5u9bZRo3bpzy8/P1+++/q0+fPkW2c70A3I97tgDAj+Xl5em7774rNSYuLq7EhZMBuG737t2Oha5LUtaaiZWJ6wXgfiRbAAAAAOABTCMEAAAAAA+gQIaL8vPztX//fkVERMhisVR2dwAAAABUEmOMjh49qri4uFKLxpBsuWj//v2Kj4+v7G4AAAAA8BJ79+5V/fr1S9xOsuWiiIgISfZ/0MjIyEruDQAAAIDKkpOTo/j4eEeOUBKSLRcVTB2MjIwk2QIAAABQ5u1FFMgAAAAAAA8g2QIAAAAADyDZAgAAAAAPqNRk68svv1TPnj0VFxcni8WixYsXF4nZtWuXevXqJavVqoiICF199dXas2ePY3tubq5GjBih2rVrKzw8XL169dK+ffuc9pGVlaX+/fvLarXKarWqf//+OnLkiIePDgAAAEBVVqnJ1vHjx9WqVStNnTq12O2//fabrrnmGl188cVas2aNvv32Wz311FOqVq2aIyYlJUWLFi3SwoULtX79eh07dkyJiYmy2WyOmOTkZG3fvl3Lli3TsmXLtH37dvXv39/jxwcAAACg6rIYY0xld0KyV/JYtGiR+vTp42jr16+fgoODNW/evGJfk52drTp16mjevHm6/fbbJf21HtZnn32mG264Qbt27dIll1yiTZs2qV27dpKkTZs2qX379vrxxx/VrFkzl/qXk5Mjq9Wq7OxsqhECAAAAVZiruYHX3rOVn5+vTz/9VE2bNtUNN9yg6OhotWvXzmmq4bZt23T69Gl1797d0RYXF6cWLVpow4YNkqSNGzfKarU6Ei1Juvrqq2W1Wh0xxcnNzVVOTo7TAwAAAABc5bXJ1oEDB3Ts2DE9//zz6tGjh1asWKFbbrlFSUlJWrt2rSQpMzNTISEhqlmzptNrY2JilJmZ6YiJjo4usv/o6GhHTHEmTJjguMfLarUqPj7ejUcHAAAAwN95bbKVn58vSerdu7cefvhhXX755Xr88ceVmJioN954o9TXGmOcFhgrbrGxwjGFjR07VtnZ2Y7H3r17z/FIAAAAAFRFXpts1a5dW0FBQbrkkkuc2ps3b+6oRhgbG6u8vDxlZWU5xRw4cEAxMTGOmD///LPI/g8ePOiIKU5oaKgiIyOdHgAAAADgKq9NtkJCQtS2bVv99NNPTu0///yzGjZsKElq3bq1goODtXLlSsf2jIwM7dy5Ux06dJAktW/fXtnZ2frqq68cMZs3b1Z2drYjBgAAAADcLagy3/zYsWP69ddfHc/T0tK0fft2RUVFqUGDBhozZoxuv/12XXvttercubOWLVumjz/+WGvWrJEkWa1WDRkyRKNHj1atWrUUFRWlRx55RC1btlTXrl0l2UfCevTooaFDh+rNN9+UJN17771KTEx0uRIhAAAAAJRXpZZ+X7NmjTp37lykfeDAgZo9e7YkaebMmZowYYL27dunZs2a6ZlnnlHv3r0dsadOndKYMWM0f/58nTx5Ul26dNG0adOcClocPnxYDz30kD766CNJUq9evTR16lRdcMEFLveV0u8AAAAAJNdzA69ZZ8vbkWwBAFA8m01at07KyJDq1pU6dZICAyu7VwDgOa7mBpU6jRAAAPi21FRp5Ehp376/2urXl6ZMkZKSKq9fAOANvLZABgAA8G6pqVLfvs6JliSlp9vbU1Mrp18A4C1ItgAAQLnZbPYRreJuRihoS0mxxwFAVUWyBQAAym3duqIjWmczRtq71x4HAFUVyRYAACi3jAz3xgGAPyLZAgAA5Va3rnvjAMAfkWwBAIBy69TJXnXQYil+u8Uixcfb4wCgqiLZAgAA5RYYaC/vLhVNuAqeT57MelsAqjaSLQAAcE6SkqQPPpDq1XNur1/f3s46WwCqOhY1BgAA5ywpSerd2151MCPDfo9Wp06MaAGARLIFAADOU2CglJBQ2b0AAO/DNEIAAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPCASk22vvzyS/Xs2VNxcXGyWCxavHhxibHDhg2TxWLR5MmTndpzc3M1YsQI1a5dW+Hh4erVq5f27dvnFJOVlaX+/fvLarXKarWqf//+OnLkiPsPCAAAAAD+v0pNto4fP65WrVpp6tSppcYtXrxYmzdvVlxcXJFtKSkpWrRokRYuXKj169fr2LFjSkxMlM1mc8QkJydr+/btWrZsmZYtW6bt27erf//+bj8eAAAAACgQVJlvfuONN+rGG28sNSY9PV0PPvigli9frptvvtlpW3Z2tmbMmKF58+apa9eukqR33nlH8fHx+vzzz3XDDTdo165dWrZsmTZt2qR27dpJkqZPn6727dvrp59+UrNmzTxzcAAAAACqNK++Zys/P1/9+/fXmDFjdOmllxbZvm3bNp0+fVrdu3d3tMXFxalFixbasGGDJGnjxo2yWq2OREuSrr76almtVkdMcXJzc5WTk+P0AAAAAABXeXWy9cILLygoKEgPPfRQsdszMzMVEhKimjVrOrXHxMQoMzPTERMdHV3ktdHR0Y6Y4kyYMMFxj5fValV8fPx5HAkAAACAqsZrk61t27ZpypQpmj17tiwWS7lea4xxek1xry8cU9jYsWOVnZ3teOzdu7dcfQAAAABQtXltsrVu3TodOHBADRo0UFBQkIKCgvTHH39o9OjRatSokSQpNjZWeXl5ysrKcnrtgQMHFBMT44j5888/i+z/4MGDjpjihIaGKjIy0ukBAAAAAK7y2mSrf//++u6777R9+3bHIy4uTmPGjNHy5cslSa1bt1ZwcLBWrlzpeF1GRoZ27typDh06SJLat2+v7OxsffXVV46YzZs3Kzs72xEDAAAAAO5WqdUIjx07pl9//dXxPC0tTdu3b1dUVJQaNGigWrVqOcUHBwcrNjbWUUHQarVqyJAhGj16tGrVqqWoqCg98sgjatmypaM6YfPmzdWjRw8NHTpUb775piTp3nvvVWJiIpUIAQAAAHhMpSZbW7duVefOnR3PR40aJUkaOHCgZs+e7dI+XnnlFQUFBem2227TyZMn1aVLF82ePVuBgYGOmHfffVcPPfSQo2phr169ylzbCwAAAADOh8UYYyq7E74gJydHVqtV2dnZ3L8FAAAAVGGu5gZee88WAAAAAPgyki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwAJItAAAAAPAAki0AAAAA8ACSLQAAAADwgEpNtr788kv17NlTcXFxslgsWrx4sWPb6dOn9dhjj6lly5YKDw9XXFycBgwYoP379zvtIzc3VyNGjFDt2rUVHh6uXr16ad++fU4xWVlZ6t+/v6xWq6xWq/r3768jR45UwBECAAAAqKoqNdk6fvy4WrVqpalTpxbZduLECX399dd66qmn9PXXXys1NVU///yzevXq5RSXkpKiRYsWaeHChVq/fr2OHTumxMRE2Ww2R0xycrK2b9+uZcuWadmyZdq+fbv69+/v8eMDAAAAUHVZjDGmsjshSRaLRYsWLVKfPn1KjNmyZYuuuuoq/fHHH2rQoIGys7NVp04dzZs3T7fffrskaf/+/YqPj9dnn32mG264Qbt27dIll1yiTZs2qV27dpKkTZs2qX379vrxxx/VrFmzYt8rNzdXubm5juc5OTmKj49Xdna2IiMj3XfgAAAAAHxKTk6OrFZrmbmBT92zlZ2dLYvFogsuuECStG3bNp0+fVrdu3d3xMTFxalFixbasGGDJGnjxo2yWq2OREuSrr76almtVkdMcSZMmOCYdmi1WhUfH++ZgwIAAADgl3wm2Tp16pQef/xxJScnO7LHzMxMhYSEqGbNmk6xMTExyszMdMRER0cX2V90dLQjpjhjx45Vdna247F37143Hg0AAAAAfxdU2R1wxenTp9WvXz/l5+dr2rRpZcYbY2SxWBzPz/7vkmIKCw0NVWho6Ll1GAAAAECV5/UjW6dPn9Ztt92mtLQ0rVy50mlOZGxsrPLy8pSVleX0mgMHDigmJsYR8+effxbZ78GDBx0xAAAAAOBuXp1sFSRav/zyiz7//HPVqlXLaXvr1q0VHByslStXOtoyMjK0c+dOdejQQZLUvn17ZWdn66uvvnLEbN68WdnZ2Y4YAAAAAHC3Sp1GeOzYMf3666+O52lpadq+fbuioqIUFxenvn376uuvv9Ynn3wim83muMcqKipKISEhslqtGjJkiEaPHq1atWopKipKjzzyiFq2bKmuXbtKkpo3b64ePXpo6NChevPNNyVJ9957rxITE0usRAgAAAAA56tSS7+vWbNGnTt3LtI+cOBAjRs3To0bNy72datXr1ZCQoIke+GMMWPGaP78+Tp58qS6dOmiadOmOVUPPHz4sB566CF99NFHkqRevXpp6tSpjqqGrnC1vCMAAAAA/+ZqbuA162x5O5ItAAAAAJKfrrMFAAAAAL6CZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPKBSk60vv/xSPXv2VFxcnCwWixYvXuy03RijcePGKS4uTmFhYUpISND333/vFJObm6sRI0aodu3aCg8PV69evbRv3z6nmKysLPXv319Wq1VWq1X9+/fXkSNHPHx0AAAAAKqySk22jh8/rlatWmnq1KnFbp84caImTZqkqVOnasuWLYqNjVW3bt109OhRR0xKSooWLVqkhQsXav369Tp27JgSExNls9kcMcnJydq+fbuWLVumZcuWafv27erfv7/Hjw8AAABA1WUxxpjK7oQkWSwWLVq0SH369JFkH9WKi4tTSkqKHnvsMUn2UayYmBi98MILGjZsmLKzs1WnTh3NmzdPt99+uyRp//79io+P12effaYbbrhBu3bt0iWXXKJNmzapXbt2kqRNmzapffv2+vHHH9WsWTOX+peTkyOr1ars7GxFRka6/x8AAAAAgE9wNTfw2nu20tLSlJmZqe7duzvaQkNDdd1112nDhg2SpG3btun06dNOMXFxcWrRooUjZuPGjbJarY5ES5KuvvpqWa1WR0xxcnNzlZOT4/QAAAAAAFd5bbKVmZkpSYqJiXFqj4mJcWzLzMxUSEiIatasWWpMdHR0kf1HR0c7YoozYcIExz1eVqtV8fHx53U8AAAAAKoWr022ClgsFqfnxpgibYUVjikuvqz9jB07VtnZ2Y7H3r17y9lzAAAAAFWZ1yZbsbGxklRk9OnAgQOO0a7Y2Fjl5eUpKyur1Jg///yzyP4PHjxYZNTsbKGhoYqMjHR6AAAAAICrvDbZaty4sWJjY7Vy5UpHW15entauXasOHTpIklq3bq3g4GCnmIyMDO3cudMR0759e2VnZ+urr75yxGzevFnZ2dmOGAAAAABwt6DyBOfk5KhGjRoKCHDO0Ww2m44fP17u0Z9jx47p119/dTxPS0vT9u3bFRUVpQYNGiglJUXjx49XkyZN1KRJE40fP17Vq1dXcnKyJMlqtWrIkCEaPXq0atWqpaioKD3yyCNq2bKlunbtKklq3ry5evTooaFDh+rNN9+UJN17771KTEx0uRIhAACAv7LZpHXrpIwMqW5dqVMnKTCwsnsF+AeXR7YWLVqkNm3a6NSpU0W25ebmqm3btvr444/L9eZbt27VFVdcoSuuuEKSNGrUKF1xxRX65z//KUl69NFHlZKSouHDh6tNmzZKT0/XihUrFBER4djHK6+8oj59+ui2225Tx44dVb16dX388ccKPOsq8e6776ply5bq3r27unfvrssuu0zz5s0rV18BAAD8TWqq1KiR1LmzlJxs/9mokb0dwPlzeZ2t7t2767bbbtM999xT7PaZM2fqv//9r5YvX+7WDnoL1tkCAAD+JDVV6ttXKvxJsKB+2AcfSElJFd8vwBe4fZ2tnTt3KiEhocTt1157rXbs2FGuTgIAAKDi2WzSyJFFEy3pr7aUFHscgHPncrKVlZWlM2fOlLj99OnTRaoCAgAAwPusWyft21fydmOkvXvtcQDOncvJVqNGjbR169YSt2/dulUNGzZ0S6cAAADgORkZ7o0DUDyXk62kpCQ98cQTxa5ZlZmZqSeffFK33nqrWzsHAAAA96tb171xAIrncoGMo0ePqn379tqzZ4/uuusuNWvWTBaLRbt27dK7776r+Ph4bdq0yalSoD+hQAYAAPAXNpu96mB6evH3bVksUv36UloaZeCB4riaG7i8zlZERIT+97//aezYsfrvf//ruD+rZs2auuuuuzR+/Hi/TbQAAAD8SWCgNGWKvRqhxeKccBVUI5w8mUQLOF8uj2ydzRij//u//5MxRnXq1JGl4LfSjzGyBQAA/E1qqr0q4dnFMuLj7YkWZd+BkrmaG5xTslUVkWwBAAB/ZLPZqw5mZNjv0erUiREtoCxun0bYuHHjYkewrFarmjVrpkceeURt2rQ5t94CAACgUgQGSqUspQrgPLicbKWkpBTbfuTIEW3ZskXt27fXihUr1LlzZ3f1DQAAAAB8ltumET733HP6/PPPtXbtWnfszuswjRAAAACA5Hpu4PI6W2Xp27evvv/+e3ftDgAAAAB8msvTCAEAAIpDgQUAKJ7bkq0PPvhALVq0cNfuAACADyiudHj9+vY1nCgdDqCqcznZ+s9//lNse3Z2trZs2aKlS5dq+fLlbusYAADwbqmp9kVxC9/9nZ5ub//gAxIuAFWbywUyGjduXGx7ZGSkLr74Yo0aNUrt2rVza+e8CQUyAAD4i80mNWrkPKJ1NovFPsKVlsaUQgD+x+3rbKWlpbmlYwAAwPetW1dyoiXZR7v27rXHsYYTgKrKbdUId+zYUeJaXAAAwL9kZLg3DgD80XklWzk5OXrzzTd11VVXqVWrVlqzZo2bugUAALxZ3brujQMAf3ROydbatWs1YMAA1a1bV8OHD9f111+vn3/+Wdu3b3dz9wAAgDfq1Ml+T5bFUvx2i0WKj7fHAUBV5XKylZGRofHjx+tvf/ub+vXrp9q1a2vt2rUKCAjQgAED9Le//c2T/QQAAF4kMNBe3r2kMlvGSJMnUxwDQNXmcoGMxo0b6+9//7tee+01devWTQEBbrvdCwAAAAD8jssZU8OGDbV+/Xp9+eWX+vnnnz3ZJwAA4OVsNvtixiWxWKSUFHscAFRVLidbP/30k9555x1lZGSobdu2at26tV555RVJkqWkCdsAAMAvlaf0OwBUVeWaC9ixY0fNnDlTGRkZuu+++/Tee+/JZrNp+PDhmj59ug4ePOipfgIAAC9C6XcAKNs53XhVo0YNDR06VBs3btT333+v1q1b68knn1RcXJy7+wcAALwQpd8BoGznXeWiefPmeumll5Senq7//ve/jvbnn39eR44cOd/dAwAAL0TpdwAom9tKCgYFBSkpKcnxfPz48Tp8+LC7dg8AALxIQel3qWjCVfCc0u8AqjqP1W83JS28AQAA/EJSkvTBB1K9es7t9evb28/6DhYAqiSX19kCAAAoLClJ6t3bXnUwI8N+j1anToxoAYBEsgUAAM5TYKCUkFDZvQAA7+OxaYQAAAAAUJWRbAEAAACAB3gs2erUqZPCwsI8tXsAAAAA8Goeu2frs88+89SuAQAAAMDruZxsBbpYVshms51zZwAAgO+x2ahGCADFcTnZMsaoYcOGGjhwoK644gpP9gkAAPiI1FRp5Ehp376/2urXty94zDpbAKo6l5OtzZs3a+bMmZoyZYoaN26swYMH684771TNmjU92T8AAOClUlOlvn0lY5zb09Pt7SxsDKCqsxhT+BJZulOnTumDDz7QrFmztGnTJvXs2VNDhgxRt27dPNVHr5CTkyOr1ars7GxFRkZWdncAAKhUNpvUqJHziNbZLBb7CFdaGlMKAfgfV3ODclcjrFatmu666y598cUX2rlzpw4cOKAePXro8OHD59VhAADgO9atKznRkuyjXXv32uMAoKo6p2qE+/bt0+zZszV79mydPHlSY8aMYbQHAIAqJCPDvXEA4I9cTrby8vK0aNEizZgxQ+vWrdONN96oyZMn66abblJAAGsjAwBQldSt6944APBHLidbdevWVUREhAYOHKhp06YpOjpaknTs2DGnOEa4AADwf5062e/JSk8vWiBD+uuerU6dKr5vAOAtXC6QcfbolcViKbLdGCOLxeK362xRIAMAAGcF1Qgl54Sr4GMC1QgB+CtXcwOXR7ZWr17tlo4BqFgsNgrAU5KS7AlVcetsTZ5MogUA5S79XlUxsgVfxGKjACoCX+oAqGpczQ3KnWxlZ2dr5cqV2r17tywWixo3bqyuXbv6fQJCsgVfU9Jio0zvAQAAOD8eSbbeeecdPfjgg8rJyXFqt1qteuONN3T77befe4+9HMkWfAmLjQIAAHiO2xc1/vrrrzVo0CD16dNH33zzjU6ePKkTJ05o69at6tmzp/r3769vv/3WLZ0HcH5YbBQAAKDyuVwg49VXX1WfPn00e/Zsp/Yrr7xSc+fO1YkTJzRlyhTNnDnT3X0EUE4sNgoAAFD5XB7Z+t///qdhw4aVuP2+++7T+vXr3dIpAOeHxUYBAAAqn8vJ1v79+9W0adMStzdt2lTp6elu6VSBM2fO6Mknn1Tjxo0VFhamCy+8UM8++6zy8/MdMcYYjRs3TnFxcQoLC1NCQoK+//57p/3k5uZqxIgRql27tsLDw9WrVy/tK22OFeDjChYbLWZJPEn29vh4FhsFAADwJJeTrRMnTqhatWolbg8NDdWpU6fc0qkCL7zwgt544w1NnTpVu3bt0sSJE/Xiiy/q1VdfdcRMnDhRkyZN0tSpU7VlyxbFxsaqW7duOnr0qCMmJSVFixYt0sKFC7V+/XodO3ZMiYmJfrsAMxAYaC/vLhVNuAqeT55McQwAAABPcrkaYUBAgObMmSOr1Vrs9iNHjmjQoEFuTWASExMVExOjGTNmONpuvfVWVa9eXfPmzZMxRnFxcUpJSdFjjz0myT6KFRMToxdeeEHDhg1Tdna26tSpo3nz5jmqJe7fv1/x8fH67LPPdMMNNxT73rm5ucrNzXU8z8nJUXx8PNUI4VOKW2crPp7FRgEAAM6Hq9UIXS6QIUkDBw4sdbulpDlL5+iaa67RG2+8oZ9//llNmzbVt99+q/Xr12vy5MmSpLS0NGVmZqp79+6O14SGhuq6667Thg0bNGzYMG3btk2nT592iomLi1OLFi20YcOGEpOtCRMm6JlnnnHr8QAVLSlJ6t2bxUYBAAAqg8vJ1tn3SVWUxx57TNnZ2br44osVGBgom82mf//737rjjjskSZmZmZKkmJgYp9fFxMTojz/+cMSEhISoZs2aRWIKXl+csWPHatSoUY7nBSNbgK8JDJQSEiq7FwAAAFWPy/dsDR482Ok+qIrw3//+V++8847mz5+vr7/+WnPmzNFLL72kOXPmOMUVHlEzxpQ5ylZWTGhoqCIjI50eAAAAAOAql5OtOXPm6OTJk57sSxFjxozR448/rn79+qlly5bq37+/Hn74YU2YMEGSFBsbK0lFRqgOHDjgGO2KjY1VXl6esrKySowBAAAAAHdzOdlysY6GW504cUIBAc5dDAwMdExpbNy4sWJjY7Vy5UrH9ry8PK1du1YdOnSQJLVu3VrBwcFOMRkZGdq5c6cjBgAAAADcrVwFMtxdAKMsPXv21L///W81aNBAl156qb755htNmjRJgwcPdvQnJSVF48ePV5MmTdSkSRONHz9e1atXV3JysiTJarVqyJAhGj16tGrVqqWoqCg98sgjatmypbp27VqhxwMAAACg6ihXstW0adMyE67Dhw+fV4fO9uqrr+qpp57S8OHDdeDAAcXFxWnYsGH65z//6Yh59NFHdfLkSQ0fPlxZWVlq166dVqxYoYiICEfMK6+8oqCgIN122206efKkunTpotmzZyuQkmwAAAAAPKRc62xNnjy5xHW2CpRVHt5XuVpLHwAAAIB/88g6W/369VN0dPR5dw4A4L1sNtZmAwDAHVxOtir6fi0AQMVLTZVGjpT27furrX59acoU+yLZAADAdV5djRAAUHFSU6W+fZ0TLUlKT7e3p6ZWTr8AAPBVLidb+fn5TCEEAD9ls9lHtIr7Xq2gLSXFHgcAAFzjcrIFAPBf69YVHdE6mzHS3r32OAAA4BqSLQCAMjLcGwcAAEi2AACyVx10ZxwAACDZAgDIXt69fn2ppMKzFosUH2+PAwAAriHZAgAoMNBe3l0qmnAVPJ88mfW2AAAoD5ItAIAk+zpaH3wg1avn3F6/vr2ddbYAACgflxc1BgD4v6QkqXdve9XBjAz7PVqdOjGihdLZbJwzAFAcki0AgJPAQCkhobJ7AV+Rmmpfo+3spQPq17dPS2U0FEBVxzRCAABwTlJTpb59i67Rlp5ub09NrZx+AYC3INkCAADlZrPZR7SMKbqtoC0lxR4HVDabTVqzRlqwwP6T8xIVhWQLAACU27p1RUe0zmaMtHevPQ6oTKmpUqNGUufOUnKy/WejRoy8omKQbAEAgHLLyHBvHOAJTHVFZSPZAgAA5Va3rnvjAHdjqiu8AckWAAAot06d7FUHCy+CXcBikeLj7XFAZWCqK7wByRYAACi3wEB7eXepaMJV8HzyZNbbQuVhqiu8AckWAAA4J0lJ0gcfSPXqObfXr29vZ50t3+CvlfqY6gpvYDGmuJmsKCwnJ0dWq1XZ2dmKjIys7O4AqEJsNvs0l4wM+4eCTp0YLYB34Rz1Xf68KLXNZq86mJ5e/H1bFov9WNPSOF9Rfq7mBkEV2CcAQDn58wch+I/AQCkhobJ7gfIqqNRXOBEpqNTn66OTBVNd+/a1J1ZnHydTXVFRmEYIAF6KksUAPKWqVOpjqisqG9MIXcQ0QgAVqWD6S0mVtJj+AuB8rFljX9y3LKtX+8eoJVNd4W5MIwQAH1aeksX+8EEIQMWqapX6mOqKykKyBcCt+PbQParaByEAFYtKfUDF4J4tAG6Tmmqf+ta5s5ScbP/ZqBH3Fp0LPggB8CQWpQYqBskWALegmIN78UEIgCexKDVQMUi2AJy3qlLVqiLxQQiAp1GpD/A8ki0A5608xRzgOj4IAfC0pCRp92571cH58+0/09K4vgDuQoEMAOeNYg6ek5Qk9e5N0RF4t7w8ado06bffpIsukoYPl0JCKrtXcBWV+gDPIdkCcN4o5uBZfBCCN3v0Uenll6X8/L/aRo+2PyZOrLx+AYA3YBohgPNGMQeganr0UenFF50TLcn+/MUX7dsBoCoj2QJw3ijmAFQ9eXn2Ea3SvPyyPQ4AqiqSLQBuQTEHoGqZOrXoiFZh+fn2OACoqki2ALgNVa2AqsPV6qJUIQVQlVEgA4BbUcwBqBoiItwbBwD+iJEtAABQbv37uzcOAPwRyRYAACi366+XatQoPSYiwh4HAFUVyRYAACi3wEBpzpzSY2bPpgopgKqNZAsAAJyTpCTpww+Lr0L64YcUxwEACmQAAIBzlpQk9e5trzqYkSHVrWtfwJwRLQAg2QIAAOeJKqQAUDymEQIAAACABzCyBcCn2WxMXwIAAN6JZAuAz0pNlUaOlPbt+6utfn1pyhRuzAcAAJWPZAuAT0pNlfr2lYxxbk9Pt7d/8AEJF1BRGGEG4Gm+ep3hni0APsdms49oFU60pL/aUlLscQA8KzVVatBA6txZSk62/2zQwN4OAO6Qmio1auR8nWnUyDeuMyRbAHzOunXOUwcLM0bau9ceB8BzUlOlW2+V9u93bt+/397uCx+EAHi3gpkshf/uF8xk8fbrDMkWAJ+TkeHeOADlZ7NJAweWHjNwICPMAM6dP8xk8fpkKz09XXfddZdq1aql6tWr6/LLL9e2bdsc240xGjdunOLi4hQWFqaEhAR9//33TvvIzc3ViBEjVLt2bYWHh6tXr17aV9rX4gC8Wt267o1D5bLZpDVrpAUL7D+9+Y/mufDX4/viC+nYsdJjjh2zxwHAufCHmSxenWxlZWWpY8eOCg4O1tKlS/XDDz/o5Zdf1gUXXOCImThxoiZNmqSpU6dqy5Ytio2NVbdu3XT06FFHTEpKihYtWqSFCxdq/fr1OnbsmBITE2Xzl794QBXTqZO96qDFUvx2i0WKj7fHwbv58jx8V/jz8c2b5944ACjMH2ayeHWy9cILLyg+Pl6zZs3SVVddpUaNGqlLly666KKLJNlHtSZPnqwnnnhCSUlJatGihebMmaMTJ05o/vz5kqTs7GzNmDFDL7/8srp27aorrrhC77zzjnbs2KHPP/+8Mg8PwDkKDLSXd5eKJlwFzydP9o0qRVWZr8/DL4u/H19Zo1rljQOAwvxhJotXJ1sfffSR2rRpo7///e+Kjo7WFVdcoenTpzu2p6WlKTMzU927d3e0hYaG6rrrrtOGDRskSdu2bdPp06edYuLi4tSiRQtHTHFyc3OVk5Pj9ADgPZKS7OXd69Vzbq9fn7LvvsAf5uGXxt+PT5I6dnRvHAAU5g8zWbw62fr999/1+uuvq0mTJlq+fLnuu+8+PfTQQ5o7d64kKTMzU5IUExPj9LqYmBjHtszMTIWEhKhmzZolxhRnwoQJslqtjkd8fLw7Dw2AGyQlSbt3S6tXS/Pn23+mpZFo+QJ/mIdfGn8/Pkm69FL3xgFAYf4wk8Wrk638/HxdeeWVGj9+vK644goNGzZMQ4cO1euvv+4UZyn0r2+MKdJWWFkxY8eOVXZ2tuOxd+/ecz8QAB4TGCglJEh33GH/6c0XXPzFH+bhl8bfj0+SSpkcck5xAFAcX5/J4tXJVt26dXXJJZc4tTVv3lx79uyRJMXGxkpSkRGqAwcOOEa7YmNjlZeXp6ysrBJjihMaGqrIyEinBwDAPfxhHn5p/P34AKAi+fJMFq9Otjp27KiffvrJqe3nn39Ww4YNJUmNGzdWbGysVq5c6diel5entWvXqkOHDpKk1q1bKzg42CkmIyNDO3fudMQAFclfy0AD5VEwD7803j4PvzT+cJ9BWRIS3BsHAKXx1ZksXp1sPfzww9q0aZPGjx+vX3/9VfPnz9dbb72lBx54QJJ9+mBKSorGjx+vRYsWaefOnbr77rtVvXp1JScnS5KsVquGDBmi0aNH64svvtA333yju+66Sy1btlTXrl0r8/BQBflzGWigPAID7X8wS9Ovn+/8MS3MH+4zKEtCglSrVukxtWqRbAGo2rw62Wrbtq0WLVqkBQsWqEWLFnruuec0efJk3XnnnY6YRx99VCkpKRo+fLjatGmj9PR0rVixQhEREY6YV155RX369NFtt92mjh07qnr16vr4448V6Mt/5eBz/L0MNFAeNpt9dLc0Cxf69sivr99nUJbAQOmtt0qPeest304oAeB8WYwprjAtCsvJyZHValV2djb3b6HcbDb7CFZJ1cksFvsHsLQ0Ppigalizxj6yW5bVq31/ZMRms1cdzMiw36PVqZN//Z6npkoPPWT/4qhA/fr2kT1fTygBoCSu5gZBFdgnoMoqTxloX/9gCbiiKlTrK1Bwn4G/SkqSEhOladOk336TLrpIGj5cCgmp7J4BQOUj2QIqQFX6YAm4gmp9/iM11b6A89lfKL38MiNbACB5+T1bgL/ggyXgrCpU66sKuBcVAEpHsgVUAD5YAs6qQrU+f2ez2Ue0irvzu6AtJcW3i5wAwPki2QIqAB8sgaL8vVqfvyvPvagAUFWRbAEVhA+WQFFJSdLu3faqg/Pn23+mpfH74Au4FxUAykaBDKACJSVJvXv7dxlooLz8vVqfv+JeVAAoG8kWUMH4YAnAH3TqJNWqJR06VHJMrVrciwqgamMaIQAAAAB4AMkWAAAot3XrSh/VkuzbKZABoCoj2QIAAOVGgQwAKBv3bAEAKpXNRtEYXxQd7d44APBHJFsAgEqTmmpfGPfs9Zrq17evS0f5d++Wn+/eOADwR0wj9DE2m7RmjbRggf2nzVbZPQKAc5OaKvXtW3Rh3PR0e3tqauX0C6758kv3xgGAPyLZ8iGpqVKjRlLnzlJysv1no0Z8IAHge2w2+4iWMUW3FbSlpPCFEgDAt5Fs+Qi+AQbgT9atK3o9O5sx0t69VLLzZq6uF8i6ggCqMpItH8A3wAD8DZXsfF+nTlJAGZ8iAgJY1BhA1Uay5QP4BhiAv6lb171xqHgbNpRd/CI/3x4HAFUV1Qh9AN8AAyWjbLhv6tTJXnUwPb34UXuLxb6dURHvlZ7u3jgA8EeMbPkAvgEGikfRGN8VGGgv7y7ZE6uzFTyfPJnE2ZsdPOjeOADwRyRbPqDgG+DCH0gKWCxSfDzfAKNqoWiM70tKkj74QKpXz7m9fn17O+tsebc6ddwbBwD+iGTLB/ANMOCMojH+IylJ2r1bWr1amj/f/jMtjUTLFxROks83DgD8EcmWj+AbYOAvFI3xL4GB9vLgd9xh/8kXR76hYNZFaZh1AaCqI9nyIXwDDNhRNAaofIGB9gS5NP36kTwDqNqoRuhjCr4BBqoyisYAlc9mkxYsKD1m4UJpwgQSLqDKMEY6elQ6cEDKzPzrceCAc1vB8+PHy/8ey5ZJN9zg/r57CMkWAJ9D2XCg8pU1nVf6azovXxIC5+j0aenHH6UdO6Rvv/3rkZlZ2T2rPD16FP/H30uRbAHwOQVFY/r2tSdWZ19zKRoDVAym88InZWdL330n7dxpT1q2b7f/PHWqsnsGVy1ZUtk9KBeSLQA+qaBozMiRzt+u169vT7S4lxHwrOho98bBBxkjff21tHix/bFzZ2X3CBUlJsb+iI62/4yNtT+io+2Pgue1a0tBVTvdqNpHD8CnJSVJvXvbpyllZNjv0erUiREtAD7q+HFp7lzprbfsIy6o2po0kVq2tD9atbI/GjWSAqhv50tItgD4NIrGAJXD1VtGKvXWkrQ06bXXpOnTpZycSuwIvEJgoDRggHTZZfbEpUULVt2Gx1mM8aE7zCpRTk6OrFarsrOzFRkZWdndAQCgYuXnSw8+KL3+emX3BN4kONg+zeCWW+wV4i64oLJ7hHKw2Zgdcq5czQ0Y2QIAoDIcOCB16cJ9Lijq5pulBx6QunWr8ve7wHNSU4u/73nKFO57did+gwEA/mHNGqlz58ruBbxNaKh0333S0KHSpZdWdm8Ar5Caaq/oW3h+W3q6vf2DD0i43IU77AAAReXnS//5j72Wvq88SLQqTr162jD3V1lkynx88bmxf6KrrMepU/YSpSRagCT71MGRI4tfqqqgLSXFHofzR7IFABUhO1t68snKT0hcfQQG2v8ao2I89JCUm1u5SUl5Hvv2qc3tF5VZFC0ggMXFAW9T1oLkxvy1IDnOH9MIAfimzExp2TJp+XJp1Sr7/S9AgUWLpD59KrsXfm3DBvsAaGny8+1xVAwFvAcLklcski0A9q+xNm+2T9JOTbWXSwYK3H67NGmSFBdX2T2BF+EDG+Cb6tZ1bxxKR7IFeILNJh08aB99OXDA/sjMLP75n39Wdm9RkZo3l556SrrtNurrwqdFR7s3DkDF6NTJXnUwPb34+7YsFvt2pgC7B8kWfMOZM9KxY9Lx4/bHsWN/PQrajh611yv97bfK7i0qQr16Uvfu0vXX2wsj1KtX2T0CAMDrBQbaPy717WtPrM5OuCwW+8/Jk/k+0F1ItqoiY+w3YheXvJSWzLgSc/p0ZR8dzlXNmvZFKXv2lLp2lWrUqOweAfBimZnujQNQcZKS7HcOFLfO1uTJlH13J5ItX/T22/b1QlC5qlWTYmKk2Fj7Izra/ih4HhNjfx4TI1mtf31dBAB+4OBB98YBqFhJSVLv3vaqgxkZ9nu0OnViRMvdSLZ8jTHSo49Wdi9cFxYmhYfbHzVq/PUo3FbW87PbwsOl4ODKPjIAcInN5p8fZmrVcm8cgIoXGEi1UE8j2fI1Fou0dKnUv79UvXrZiYkryUv16ipzsRQAQLmlphY/TWfKFN+fpnPokHvjAMAfkWz5onbtpJ9/ruxeAABKkZpqvwG9cLWv9HR7+wcf+HbCxcgWAJSN4QwAANzMZrOPaBVXVrmgLSXFHuerXF1HnPXGAVRlJFsAALjZunXOUwcLM0bau9ce56sOH3ZvHAD4I5ItAADcLCPDvXHeyNVbfbklGEBVxiUQAAA3q1vXvXHeyNUKZlQ6A1CVkWwBAOBmnTrZqw6WtLyexSLFx9vjfFVCQtlrn9eoQbIFoGoj2QIAwM0CA+3l3aWiCVfB88mTfX+9rTNnzm87ALjKZpPWrJEWLLD/9JUCQyRbgJ/z1YsT4OuSkuzl3evVc26vX9/3y75L0hdfSKdOlR5z6pQ9DgDOR2qq1KiR1LmzlJxs/9mokb3d2/lUsjVhwgRZLBalpKQ42owxGjdunOLi4hQWFqaEhAR9//33Tq/Lzc3ViBEjVLt2bYWHh6tXr17aV1qZKMBP+PLFCfAHSUnS7t3S6tXS/Pn2n2lpvp9oSdK8ee6NA4DiFKxZWPije8Gahd7+mcZnkq0tW7borbfe0mWXXebUPnHiRE2aNElTp07Vli1bFBsbq27duuno0aOOmJSUFC1atEgLFy7U+vXrdezYMSUmJsrGV/zwY75+cfJWjBSivAID7fct3XGH/aevTx0scOyYe+MAoDB/WLPQJ5KtY8eO6c4779T06dNVs2ZNR7sxRpMnT9YTTzyhpKQktWjRQnPmzNGJEyc0f/58SVJ2drZmzJihl19+WV27dtUVV1yhd955Rzt27NDnn39e4nvm5uYqJyfH6QH4Cn+4OHmjyhopJMGDN7rmGvfGAUBh/rBmoU8kWw888IBuvvlmde3a1ak9LS1NmZmZ6t69u6MtNDRU1113nTZs2CBJ2rZtm06fPu0UExcXpxYtWjhiijNhwgRZrVbHIz4+3s1HBXiOP1ycvE1ljRQyFRTeasQI98YBQGH+sGah1ydbCxcu1Ndff60JEyYU2ZaZmSlJiomJcWqPiYlxbMvMzFRISIjTiFjhmOKMHTtW2dnZjsfevXvP91CACuMPFydvUlkjhUwFhbcrqbS9q9sBoDT+sGahVydbe/fu1ciRI/XOO++oWrVqJcZZCl3NjTFF2gorKyY0NFSRkZFOD8BX+MPFyZtUxkghU0Hh7aZNK/78PJsx9jgAOBf+sGahVydb27Zt04EDB9S6dWsFBQUpKChIa9eu1X/+8x8FBQU5RrQKj1AdOHDAsS02NlZ5eXnKysoqMQbwN/5wcfImlTFSyFRQeLuff3ZvHAAU5g9rFnp1stWlSxft2LFD27dvdzzatGmjO++8U9u3b9eFF16o2NhYrVy50vGavLw8rV27Vh06dJAktW7dWsHBwU4xGRkZ2rlzpyMG8Df+cHHyJpUxUshUUHi79HT3xgFAcXx9zcKgyu5AaSIiItSiRQuntvDwcNWqVcvRnpKSovHjx6tJkyZq0qSJxo8fr+rVqys5OVmSZLVaNWTIEI0ePVq1atVSVFSUHnnkEbVs2bJIwQ3AnxRcnEaOdB4hqV/fnmh5+8XJmxSMFKanFz9tymKxb3fnSCFTQeHtyppCWN44AOfOZrPPdMjIsP9d6NTJv75QTUqSevf2zWP06mTLFY8++qhOnjyp4cOHKysrS+3atdOKFSsUERHhiHnllVcUFBSk2267TSdPnlSXLl00e/ZsBfrC/yHgPPjyxcmbFIwU9u1rT6zO/vDoqZHCykjwgPI4edK9cQDOTWpq8V+sTpniX1+sFqxZ6GssxvCdkytycnJktVqVnZ1NsQygiiruD1p8vOdGCguqEUrFJ3i+MH0C/mvsWOn558uOe/xxqZiCwgDcoODvROFP8/yd8DxXcwOSLReRbAGQKn6qRkUneICrvvhCcmU2/uefS126eL4/QFVjs9nXXSypmFLBDIi0NGa0eALJlpuRbAGoLP4+F9/fj89f5eVJYWFSfn7JMQEB9mmEISEV1y+gqlizxr7QfVlWr/bN6XfeztXcwOfv2QIAf+er89RdUVXuNfBHGzaUnmhJ9u0bNvjv+QtUJqrW+gavLv0OAPBfBfcaFJ4Ck55ub09NrZx+wTWUfgcqF1VrfQPJFgCfZrPZp1IsWGD/abNVdo/gCpvNPqJV3ET2graUFP5/erPMTPfGASifgqq1hdfTLGCx2O/xpWpt5SLZAuCzUlPtNwd37iwlJ9t/NmrEiIgvWLeu5Ju6JXvCtXevPQ7e6f/+z71xAMqnYFkSqWjC5allSVB+JFsAfBJT0Hwb9xr4vtKS5XOJA1B+SUn28u716jm3169P2XdvQYEMAD6nrCloFot9Clrv3nyj562418D3NWjg3jgA5yYpyf73jqqu3omRLQA+hylovo97DXyfqxUGqUQIeF5B1do77rD/JNHyHiRbAHwOU9B8H/ca+L4AFz9BuBoHAP6ISyAAn8MUNP/AvQaeUxFVOg8ccG8cAPgj7tkC4HM6dLCPeJT2ATIw0B6H8rPZKm7uP/cauF9FLRTNlx4AUDaLMcXdYo7CcnJyZLValZ2drcjIyMruDlClrVljL/NeltWruV+kvCrqgzo8o6BKZ+G/7AVTM905Ymiz2ZdaSE8vvliNxWI/d9LSSJ4B+B9XcwOmEQLwOdyz5RmU0/dtFb1Q9Nn33ZWE++4AVHUkWwB8DtOX3K+iP6jD/SqjSmdSktSrV/HbevViNBQASLYA+BzKhrsf5fR9X2WM+D76qLRkSfHbliyxbweAqoxkC36hIipvwXtQNtz9mJrp+yp6xDcvT5o0qfSYSZPscQBQVZFsweelptpv0u7cWUpOtv9s1Ij7S/wdZcPdi6mZvq+iR3ynTSv7iy2bzR4HAFUVyRZ8Gjf0V21JSdLu3faqg/Pn23+mpZFonQumZvq+ih7x/e0398YBgD8i2YLP4oZ+1/j7FMvAQHt59zvusP9k6uC5YWqmf6jIEd+LLnJvHKoWf//bBBRgnS0Xsc6W92GtpbKxZhLKq7hzJj7enmhxzviOiliYOi9Pqlat+C+8Clgs0qlTUkiIe98bvo2/TfAHruYGQRXYJ8CtuKG/dCUtblowxZL7mlCcpCSpd2/Pf1CHZxWM+ALehr9NqGqYRgifxQ39JWOKJc4HUzPhimnTSh/VkuzbKZCBAvxtQlVEsgWfxQ39JWPNJACeRoEMlBd/m1AVkWzBZ3FDf8mYYgnA0yiQgfLibxOqIpIt+DTWWioeUywBeNqwYe6Ng//jbxOqIqoRuohqhN6tIipv+RKbzb6wc3p68XPjLRZ7QpqWVrX/nQCcOyrCorz42wR/4mpuwMgW/AI39DtjiiUAT2NKGMqLv02oiki2AD/FFEsAnsSUMJwL/jahqmEaoYuYRghfxRRLAJ6QlyeFhUn5+SXHBARIJ0+yqDGK4m8TfB2LGgOQxOKmADxj3brSEy3Jvn3dOqlLl4rpE3wHf5tQVTCNEAAAD7LZ7MUkFiyw//SXBVtXrXJvHAD4I0a2AADwkNRUaeRI54Vc69e3Fwnw9XtT9uxxbxwA+CNGtgAA8IDUVKlvX+dES7KXve7b177dlzVo4N44APBHJFsAALiZzWYf0SquBFVBW0qKb08pvP5698YBgD8i2QIAwM3WrSs6onU2Y6S9e+1xvqpTJ3u1wdIEBNjjAKCqItkC/Jy/3pwPeLOqsODvhg2uVSPcsKFi+gMA3ogCGYAf8+eb8wFvVhUW/K0KCSUAnC9GtgA/5e835wPerFMn+xcbFkvx2y0WKT7et6fYRUe7Nw4A/BHJFuCHqsLN+YA3Cwy0jyBLRROugueTJ9vjAAD+i2QL8ENV4eZ8wNslJUkffCDVq+fcXr++vd3Xp/IeOODeOADwR9yzBfgh7qUAvENSktS7t/2LjYwM+z1anTr5x4hWVbgvDQDOF8kW4If4EAR4j8BAKSGhsnvhfh062I+ttOnIgYH2OACoqphGCPihqnBzPoDKtWFD2fd92myUfgdQtZFsAX6o4Ob84gpkSPZ2bs4HcD6YrgwAZSPZAgAA5cZ0ZQAom8WYkr77xtlycnJktVqVnZ2tyMjIyu4OUCqbTWrUqOSKhBaLfZphWhqjWwDOTV6eVL162fdsnTghhYRUXL8AoCK4mhswsgX4IUq/A/A07tkCgLJRjRDwQ9xLAcDTuM7gfNhs/rkkAlAYyRbgh7iXAoCncZ3BuUpNlUaOdJ6BUb++vbCTry/2DRTm1dMIJ0yYoLZt2yoiIkLR0dHq06ePfvrpJ6cYY4zGjRunuLg4hYWFKSEhQd9//71TTG5urkaMGKHatWsrPDxcvXr10r7S5lgBPo7S7wA8jesMzkVqqtS3b9Gp7unp9vbU1MrpF+ApXp1srV27Vg888IA2bdqklStX6syZM+revbuOHz/uiJk4caImTZqkqVOnasuWLYqNjVW3bt109OhRR0xKSooWLVqkhQsXav369Tp27JgSExNlK2uyOeCjCkq/S0U/CBU8p/Q7gPPBEhMoL5vNPqJV3DlT0JaSUva9gIAv8alqhAcPHlR0dLTWrl2ra6+9VsYYxcXFKSUlRY899pgk+yhWTEyMXnjhBQ0bNkzZ2dmqU6eO5s2bp9tvv12StH//fsXHx+uzzz7TDTfc4NJ7U40Qvqi4qRrx8fYPQEzVAHC+UlOlW28tefuHH3KtwV/WrJE6dy47bvVqKSHB070Bzo9fViPMzs6WJEVFRUmS0tLSlJmZqe7duztiQkNDdd1112nD/y9/tG3bNp0+fdopJi4uTi1atHDEFCc3N1c5OTlOD8DXJCVJu3fb/3DNn2//mZbGhx8A569glKIkFgujFHBGURVURT5TIMMYo1GjRumaa65RixYtJEmZmZmSpJiYGKfYmJgY/fHHH46YkJAQ1axZs0hMweuLM2HCBD3zzDPuPASgUgQG8g0hAPcrzxITXIMgUVQFVZPPjGw9+OCD+u6777RgwYIi2yyFbkoxxhRpK6ysmLFjxyo7O9vx2Lt377l1HAAAP8QoBcqLoiqoinwi2RoxYoQ++ugjrV69WvXr13e0x8bGSlKREaoDBw44RrtiY2OVl5enrKysEmOKExoaqsjISKcHAACwY5QC5UXxJlRFXp1sGWP04IMPKjU1VatWrVLjxo2dtjdu3FixsbFauXKloy0vL09r165Vhw4dJEmtW7dWcHCwU0xGRoZ27tzpiAEAAOXDKAXORVKS9MEHUr16zu3169vbuacY/sar79l64IEHNH/+fC1ZskQRERGOESyr1aqwsDBZLBalpKRo/PjxatKkiZo0aaLx48erevXqSk5OdsQOGTJEo0ePVq1atRQVFaVHHnlELVu2VNeuXSvz8AAA8FkFoxR9+9oTq7NrGzNKgdIkJUm9e9vv58vIsI9+durEuQL/5NWl30u6p2rWrFm6++67JdlHv5555hm9+eabysrKUrt27fTaa685imhI0qlTpzRmzBjNnz9fJ0+eVJcuXTRt2jTFx8e73BdKvwMAUBRLTACoilzNDbw62fImJFsAABTPZmOUAkDV4mpu4NXTCAEAgPdjiQkAKJ5XF8gAAAAAAF9FsgUAAAAAHkCyBQAAAAAeQLIFAAAAAB5AsgUAAAAAHkCyBQAAAAAeQLIFAAAAAB5AsgUAAAAAHkCyBQAAAAAeQLIFAAAAAB5AsgUAAAAAHkCyBQAAAAAeQLIFAAAAAB4QVNkd8BXGGElSTk5OJfcEAAAAQGUqyAkKcoSSkGy56OjRo5Kk+Pj4Su4JAAAAAG9w9OhRWa3WErdbTFnpGCRJ+fn52r9/vyIiImSxWCq1Lzk5OYqPj9fevXsVGRlZqX2Bb+CcQXlxzqC8OGdQXpwzKC9vOmeMMTp69Kji4uIUEFDynVmMbLkoICBA9evXr+xuOImMjKz0Ew2+hXMG5cU5g/LinEF5cc6gvLzlnCltRKsABTIAAAAAwANItgAAAADAA0i2fFBoaKiefvpphYaGVnZX4CM4Z1BenDMoL84ZlBfnDMrLF88ZCmQAAAAAgAcwsgUAAAAAHkCyBQAAAAAeQLIFAAAAAB5AsgUAAAAAHkCy5SXGjRsni8Xi9IiNjXVsN8Zo3LhxiouLU1hYmBISEvT999877SM3N1cjRoxQ7dq1FR4erl69emnfvn0VfSjwkC+//FI9e/ZUXFycLBaLFi9e7LTdXedIVlaW+vfvL6vVKqvVqv79++vIkSMePjp4QlnnzN13313kunP11Vc7xXDOVB0TJkxQ27ZtFRERoejoaPXp00c//fSTUwzXGZzNlXOG6wzO9vrrr+uyyy5zLErcvn17LV261LHdH68xJFte5NJLL1VGRobjsWPHDse2iRMnatKkSZo6daq2bNmi2NhYdevWTUePHnXEpKSkaNGiRVq4cKHWr1+vY8eOKTExUTabrTIOB252/PhxtWrVSlOnTi12u7vOkeTkZG3fvl3Lli3TsmXLtH37dvXv39/jxwf3K+uckaQePXo4XXc+++wzp+2cM1XH2rVr9cADD2jTpk1auXKlzpw5o+7du+v48eOOGK4zOJsr54zEdQZ/qV+/vp5//nlt3bpVW7du1fXXX6/evXs7Eiq/vMYYeIWnn37atGrVqtht+fn5JjY21jz//POOtlOnThmr1WreeOMNY4wxR44cMcHBwWbhwoWOmPT0dBMQEGCWLVvm0b6j4kkyixYtcjx31znyww8/GElm06ZNjpiNGzcaSebHH3/08FHBkwqfM8YYM3DgQNO7d+8SX8M5U7UdOHDASDJr1641xnCdQdkKnzPGcJ1B2WrWrGnefvttv73GMLLlRX755RfFxcWpcePG6tevn37//XdJUlpamjIzM9W9e3dHbGhoqK677jpt2LBBkrRt2zadPn3aKSYuLk4tWrRwxMB/uesc2bhxo6xWq9q1a+eIufrqq2W1WjmP/NSaNWsUHR2tpk2baujQoTpw4IBjG+dM1ZadnS1JioqKksR1BmUrfM4U4DqD4thsNi1cuFDHjx9X+/bt/fYaQ7LlJdq1a6e5c+dq+fLlmj59ujIzM9WhQwcdOnRImZmZkqSYmBin18TExDi2ZWZmKiQkRDVr1iwxBv7LXedIZmamoqOji+w/Ojqa88gP3XjjjXr33Xe1atUqvfzyy9qyZYuuv/565ebmSuKcqcqMMRo1apSuueYatWjRQhLXGZSuuHNG4jqDonbs2KEaNWooNDRU9913nxYtWqRLLrnEb68xQRX+jijWjTfe6Pjvli1bqn379rrooos0Z84cx42kFovF6TXGmCJthbkSA//hjnOkuHjOI/90++23O/67RYsWatOmjRo2bKhPP/1USUlJJb6Oc8b/Pfjgg/ruu++0fv36Itu4zqA4JZ0zXGdQWLNmzbR9+3YdOXJEH374oQYOHKi1a9c6tvvbNYaRLS8VHh6uli1b6pdffnFUJSycjR84cMCR/cfGxiovL09ZWVklxsB/uesciY2N1Z9//llk/wcPHuQ8qgLq1q2rhg0b6pdffpHEOVNVjRgxQh999JFWr16t+vXrO9q5zqAkJZ0zxeE6g5CQEP3tb39TmzZtNGHCBLVq1UpTpkzx22sMyZaXys3N1a5du1S3bl01btxYsbGxWrlypWN7Xl6e1q5dqw4dOkiSWrdureDgYKeYjIwM7dy50xED/+Wuc6R9+/bKzs7WV1995YjZvHmzsrOzOY+qgEOHDmnv3r2qW7euJM6ZqsYYowcffFCpqalatWqVGjdu7LSd6wwKK+ucKQ7XGRRmjFFubq7/XmMqth4HSjJ69GizZs0a8/vvv5tNmzaZxMREExERYXbv3m2MMeb55583VqvVpKammh07dpg77rjD1K1b1+Tk5Dj2cd9995n69eubzz//3Hz99dfm+uuvN61atTJnzpyprMOCGx09etR888035ptvvjGSzKRJk8w333xj/vjjD2OM+86RHj16mMsuu8xs3LjRbNy40bRs2dIkJiZW+PHi/JV2zhw9etSMHj3abNiwwaSlpZnVq1eb9u3bm3r16nHOVFH333+/sVqtZs2aNSYjI8PxOHHihCOG6wzOVtY5w3UGhY0dO9Z8+eWXJi0tzXz33XfmH//4hwkICDArVqwwxvjnNYZky0vcfvvtpm7duiY4ONjExcWZpKQk8/333zu25+fnm6efftrExsaa0NBQc+2115odO3Y47ePkyZPmwQcfNFFRUSYsLMwkJiaaPXv2VPShwENWr15tJBV5DBw40BjjvnPk0KFD5s477zQREREmIiLC3HnnnSYrK6uCjhLuVNo5c+LECdO9e3dTp04dExwcbBo0aGAGDhxY5HzgnKk6ijtXJJlZs2Y5YrjO4GxlnTNcZ1DY4MGDTcOGDU1ISIipU6eO6dKliyPRMsY/rzEWY4ypuHE0AAAAAKgauGcLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwAAAAA8gGQLAAAAADyAZAsAAAAAPIBkCwBQbhaLRYsXLy415u6771afPn1c3ufu3btlsVi0ffv28+qbtzjf41+zZo0sFouOHDnikf752783AHgjki0AqOLKmxRIUkZGhm688UZJJX9onzJlimbPnu2eTkpq2bKl7rnnnmK3LViwQMHBwfrzzz8lScYYvfXWW2rXrp1q1KihCy64QG3atNHkyZN14sQJSdK4ceNksVjUo0ePIvubOHGiLBaLEhIS3Nb/ssTHxysjI0MtWrSosPcEAHgWyRYAoNxiY2MVGhpaaozVatUFF1zgtvccMmSI3nvvPUeydLaZM2cqMTFRMTExkqT+/fsrJSVFvXv31urVq7V9+3Y99dRTWrJkiVasWOF4Xd26dbV69Wrt27fPaX+zZs1SgwYN3NZ3VwQGBio2NlZBQUEV+r4AAM8h2QIAOElISNBDDz2kRx99VFFRUYqNjdW4ceOcYs6eRti4cWNJ0hVXXOE0GlR4xGzZsmW65pprdMEFF6hWrVpKTEzUb7/95nK/+vfvr9zcXL3//vtO7Xv27NGqVas0ZMgQSdJ7772nd999VwsWLNA//vEPtW3bVo0aNVLv3r21atUqde7c2fHa6Ohode/eXXPmzHG0bdiwQf/3f/+nm2++2eW+2Ww2jRo1ynFsjz76qIwxTjFlHX9p0/qOHz+uyMhIffDBB07tH3/8scLDw3X06NEy+/jVV1/piiuuULVq1dSmTRt98803RWLWrl2rq666SqGhoapbt64ef/xxnTlzxrH9gw8+UMuWLRUWFqZatWqpa9euOn78uGP7rFmz1Lx5c1WrVk0XX3yxpk2bVma/AMCfkWwBAIqYM2eOwsPDtXnzZk2cOFHPPvusVq5cWWzsV199JUn6/PPPlZGRodTU1GLjjh8/rlGjRmnLli364osvFBAQoFtuuUX5+fku9alWrVrq3bu3Zs2a5dQ+a9YsxcTEOKY1vvvuu2rWrJl69+5dZB8Wi0VWq9WpbfDgwU7THWfOnKk777xTISEhLvVLkl5++WXNnDlTM2bM0Pr163X48GEtWrTIKeZ8jj88PFz9+vUr9tj79u2riIiIUl9//PhxJSYmqlmzZtq2bZvGjRunRx55xCkmPT1dN910k9q2batvv/1Wr7/+umbMmKF//etfkuxTR++44w4NHjxYu3bt0po1a5SUlORIKqdPn64nnnhC//73v7Vr1y6NHz9eTz31lFMiCwBVjgEAVGkDBw40vXv3djy/7rrrzDXXXOMU07ZtW/PYY485nksyixYtMsYYk5aWZiSZb775ptT9FnbgwAEjyezYsaPU/Zxt6dKlxmKxmN9++80YY0x+fr5p1KiRGTt2rCOmefPmplevXqUcsd3TTz9tWrVqZfLy8kx0dLRZu3atOXbsmImIiDDffvutGTlypLnuuuvK3I8xxtStW9c8//zzjuenT5829evXP6/jX716tZFksrKyjDHGbN682QQGBpr09HRjjDEHDx40wcHBZs2aNWX278033zRRUVHm+PHjjrbXX3/d6f3+8Y9/mGbNmpn8/HxHzGuvvWZq1KhhbDab2bZtm5Fkdu/eXex7xMfHm/nz5zu1Pffcc6Z9+/Zl9g8A/BUjWwCAIi677DKn53Xr1tWBAwfOa5+//fabkpOTdeGFFyoyMtIx/XDPnj0u76N79+6qX7++Y4Rn1apV2r17twYNGuSIMcbIYrG4vM/g4GDdddddmjVrlt5//301bdq0yPGXJjs7WxkZGWrfvr2jLSgoSG3atHGKO9/jv+qqq3TppZdq7ty5kqR58+apQYMGuvbaa8t87a5du9SqVStVr17d0XZ2fwti2rdv7/Rv17FjRx07dkz79u1Tq1at1KVLF7Vs2VJ///vfNX36dGVlZUmSDh48qL1792rIkCGqUaOG4/Gvf/2rXFNFAcDfkGwBAIoIDg52em6xWFye7leSnj176tChQ5o+fbo2b96szZs3S5Ly8vJc3kdAQIDuvvtuzZkzR/n5+Zo1a5auvfZaNWnSxBHTtGlT7dq1q1x9Gzx4sN5//3299tprGjx4cLle6yp3HP8999zjSDRnzZqlQYMGuZRYmkL3j5UUU3hfBa+zWCwKDAzUypUrtXTpUl1yySV69dVX1axZM6WlpTnOjenTp2v79u2Ox86dO7Vp0yaXjw8A/A3JFgDgvBTc22Sz2UqMOXTokHbt2qUnn3xSXbp0UfPmzR2jIuU1aNAg7du3T6mpqUpNTXUUxiiQnJysn3/+WUuWLCnyWmOMsrOzi7RfeumluvTSS7Vz504lJyeXqz9Wq1V169Z1SirOnDmjbdu2OZ676/jvuusu7dmzR//5z3/0/fffa+DAgS697pJLLtG3336rkydPOtoKJ0GXXHKJNmzY4JSYbdiwQREREapXr54ke9LVsWNHPfPMM/rmm28UEhKiRYsWKSYmRvXq1dPvv/+uv/3tb06PghE8AKiKSLYAAOclOjpaYWFhWrZsmf78889ik5maNWuqVq1aeuutt/Trr79q1apVGjVq1Dm9X+PGjXX99dfr3nvvVXBwsPr27eu0/bbbbtPtt9+uO+64QxMmTNDWrVv1xx9/6JNPPlHXrl21evXqYve7atUqZWRknFO5+pEjR+r555/XokWL9OOPP2r48OFOixG76/hr1qyppKQkjRkzxjGl0hXJyckKCAjQkCFD9MMPP+izzz7TSy+95BQzfPhw7d27VyNGjNCPP/6oJUuW6Omnn9aoUaMUEBCgzZs3a/z48dq6dav27Nmj1NRUHTx4UM2bN5dkX7dswoQJmjJlin7++Wft2LFDs2bN0qRJk8p9nADgL0i2AADnJSgoSP/5z3/05ptvKi4urtgqgAEBAVq4cKG2bdumFi1a6OGHH9aLL754zu85ZMgQZWVlqV+/fk73IUn20Zf58+dr0qRJWrRoka677jpddtllGjdunHr37q0bbrih2H2Gh4ef87pgo0eP1oABA3T33Xerffv2ioiI0C233OLY7s7jHzJkiPLy8so13bFGjRr6+OOP9cMPP+iKK67QE088oRdeeMEppl69evrss8/01VdfqVWrVrrvvvs0ZMgQPfnkk5KkyMhIffnll7rpppvUtGlTPfnkk3r55ZcdVSDvuecevf3225o9e7Zatmyp6667TrNnz2ZkC0CVZjGuTOQGAABe4d1339XIkSO1f//+cpWnBwBUPJapBwDAB5w4cUJpaWmaMGGChg0bRqIFAD6AaYQAAJTh7HLmhR/r1q2rkD5MnDhRl19+uWJiYjR27FinbePHjy+xfwXT/AAAFY9phAAAlOHXX38tcVu9evUUFhZWgb0p6vDhwzp8+HCx28LCwhzVBAEAFYtkCwAAAAA8gGmEAAAAAOABJFsAAAAA4AEkWwAAAADgASRbAAAAAOABJFsAAAAA4AEkWwAAAADgASRbAAAAAOAB/w+QchBlX19VqAAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(42623.84857342132, 0.0017300082971885011)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.metrics import mean_squared_error, r2_score\n",
    "\n",
    "# Drop any rows with missing values in the target columns\n",
    "df = df.dropna(subset=['Initial VCM_daily_dose', 'TDM_AUC'])\n",
    "\n",
    "# Separate features and target variable from the dataset\n",
    "X = df[['Initial VCM_daily_dose']]\n",
    "y = df['TDM_AUC']\n",
    "\n",
    "# Split the data into training and test sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
    "\n",
    "# Initialize the model and fit it to the training data\n",
    "model = LinearRegression()\n",
    "model.fit(X_train, y_train)\n",
    "\n",
    "# Predict the target variable for the test set\n",
    "y_pred = model.predict(X_test)\n",
    "\n",
    "# Evaluate the model\n",
    "mse = mean_squared_error(y_test, y_pred)\n",
    "r2 = r2_score(y_test, y_pred)\n",
    "\n",
    "# Plotting\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.scatter(X_test, y_test, color='blue')\n",
    "plt.plot(X_test, y_pred, color='red')\n",
    "plt.xlabel('Initial VCM_daily_dose')\n",
    "plt.ylabel('TDM_AUC')\n",
    "plt.title('Prediction of TDM_AUC based on Initial VCM_daily_dose')\n",
    "plt.show()\n",
    "\n",
    "mse, r2\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "f50fcf72",
   "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>Age</th>\n",
       "      <th>VCM_dose</th>\n",
       "      <th>ACEi</th>\n",
       "      <th>TDM_AUC</th>\n",
       "      <th>VCM_dose_log</th>\n",
       "      <th>TDM_AUC_log</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>71</td>\n",
       "      <td>1000</td>\n",
       "      <td>0</td>\n",
       "      <td>1564.0</td>\n",
       "      <td>6.908755</td>\n",
       "      <td>7.355641</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>77</td>\n",
       "      <td>800</td>\n",
       "      <td>0</td>\n",
       "      <td>1150.0</td>\n",
       "      <td>6.685861</td>\n",
       "      <td>7.048386</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>78</td>\n",
       "      <td>750</td>\n",
       "      <td>0</td>\n",
       "      <td>1082.0</td>\n",
       "      <td>6.621406</td>\n",
       "      <td>6.987490</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>58</td>\n",
       "      <td>800</td>\n",
       "      <td>0</td>\n",
       "      <td>1069.0</td>\n",
       "      <td>6.685861</td>\n",
       "      <td>6.975414</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>78</td>\n",
       "      <td>750</td>\n",
       "      <td>0</td>\n",
       "      <td>1025.0</td>\n",
       "      <td>6.621406</td>\n",
       "      <td>6.933423</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Age  VCM_dose  ACEi  TDM_AUC  VCM_dose_log  TDM_AUC_log\n",
       "0   71      1000     0   1564.0      6.908755     7.355641\n",
       "1   77       800     0   1150.0      6.685861     7.048386\n",
       "2   78       750     0   1082.0      6.621406     6.987490\n",
       "3   58       800     0   1069.0      6.685861     6.975414\n",
       "4   78       750     0   1025.0      6.621406     6.933423"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Selecting the columns of interest based on the specified variables and their closest matches in the DataFrame\n",
    "# Log-transforming the specified columns\n",
    "\n",
    "selected_columns = ['TDM_trough', 'Age', 'VCM_dose_regimen', 'VCM_dose', 'ACEi', 'Initial_VCM_daily_dose', 'TDM_AUC']\n",
    "log_transformed_columns = ['TDM_trough', 'VCM_dose', 'Initial_VCM_daily_dose', 'TDM_AUC']\n",
    "\n",
    "# Checking if the selected columns are present in the DataFrame\n",
    "available_columns = [col for col in selected_columns if col in df.columns]\n",
    "\n",
    "# Log-transforming the available columns\n",
    "for col in log_transformed_columns:\n",
    "    if col in df.columns:\n",
    "        df[col+'_log'] = np.log1p(df[col])\n",
    "\n",
    "# Updating the available columns to include the log-transformed ones\n",
    "available_columns += [col+'_log' for col in log_transformed_columns if col in df.columns]\n",
    "\n",
    "# Confirming the log transformation and column selection\n",
    "df[available_columns].head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "936e8ea4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(0.01573329562460341, 0.8963235754485745)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Preparing the data for machine learning model training\n",
    "# Using the available columns for features and 'TDM_AUC_log' as the target variable\n",
    "\n",
    "X = df[available_columns].drop('TDM_AUC_log', axis=1)\n",
    "y = df['TDM_AUC_log']\n",
    "\n",
    "# Splitting the data into training and testing sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
    "\n",
    "# Initializing and training the Linear Regression model\n",
    "model = LinearRegression()\n",
    "model.fit(X_train, y_train)\n",
    "\n",
    "# Making predictions on the test set\n",
    "y_pred = model.predict(X_test)\n",
    "\n",
    "# Calculating the evaluation metrics: MSE and R^2 score\n",
    "mse = mean_squared_error(y_test, y_pred)\n",
    "r2 = r2_score(y_test, y_pred)\n",
    "\n",
    "# Visualizing the results\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.scatter(y_test, y_pred, color='blue')\n",
    "plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], linestyle='--', color='red')\n",
    "plt.xlabel('True Values')\n",
    "plt.ylabel('Predictions')\n",
    "plt.title('Prediction Performance of the Machine Learning Model')\n",
    "plt.show()\n",
    "\n",
    "mse, r2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f9317c72",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}
