{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b682eea8",
   "metadata": {},
   "source": [
    "<div class=\"licence\">\n",
    "<span>Licence CC BY-NC-ND</span>\n",
    "<span>Valérie Roy</span>\n",
    "</div>\n",
    "\n",
    "<img src=\"media/ensmp-25-alpha.png\" />"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "24f88a9f",
   "metadata": {},
   "source": [
    "# `matplotlib` & `pandas`\n",
    "\n",
    "\n",
    "Les fonctions de `matplotlib` ont été intégrées avec la librairie `pandas` de manière à faciliter leur utilisation à partir d'une dataframe. Nous allons voir quelques unes de ces fonctions. Référez-vous à la documentation pour aller plus loin dans cette utilisation. \n",
    "\n",
    "Une dataframe est un table de données en dimension 2 où chacune des colonnes peut être vue comme une variable aléatoire avec une certaine distribution représentant une information: un âge, un genre, une taille...\n",
    "\n",
    "`matplotlib` va apporter à `pandas` des facilités pour visualiser les données des colonnes sous des formes classiques comme: les boxplots (boîtes à moustaches), les histogrammes, les barcharts (diagrammes à bandes)...\n",
    "\n",
    "Ou encore pour visualiser les paires de valeurs des colonnes comme la taille en fonction de l'âge...\n",
    "\n",
    "Nous allons illustrer les quelques fonctions sur un exemple simple."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aa96be23",
   "metadata": {},
   "source": [
    "Importons les librairies:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "9f4b3f5d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "459714c3",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4797e0d4",
   "metadata": {},
   "source": [
    "## importons un jeu de données"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cf7c5f1b",
   "metadata": {},
   "source": [
    "Importons le jeu de données classiques sur trois types d'iris (Versicolor, Virginica et Setosa) décrits par quatre paramètres qui sont les longueur et largeurs des pétales et des sépales.\n",
    "\n",
    "Exemple des 4 mesures décrites sur un iris versicolor:\n",
    "\n",
    "<img src='media/versicolor-petal-sepal.jpg' width=200>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "8402c8a2",
   "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>SepalLength</th>\n",
       "      <th>SepalWidth</th>\n",
       "      <th>PetalLength</th>\n",
       "      <th>PetalWidth</th>\n",
       "      <th>Name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   SepalLength  SepalWidth  PetalLength  PetalWidth         Name\n",
       "0          5.1         3.5          1.4         0.2  Iris-setosa\n",
       "1          4.9         3.0          1.4         0.2  Iris-setosa\n",
       "2          4.7         3.2          1.3         0.2  Iris-setosa\n",
       "3          4.6         3.1          1.5         0.2  Iris-setosa\n",
       "4          5.0         3.6          1.4         0.2  Iris-setosa"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "file = 'iris.csv'\n",
    "df = pd.read_csv(file)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7bbb951f",
   "metadata": {},
   "source": [
    "Nous voici avec une table qui décrit 150 iris avec 5 paramètres (les 4 mesures et le type):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "fd41c5ca",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(150, 5)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4f0d886b",
   "metadata": {},
   "source": [
    "Les colonnes sont des nombres flottants pour les 4 mesures et de type `object` pour les types."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "acef523e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SepalLength    float64\n",
       "SepalWidth     float64\n",
       "PetalLength    float64\n",
       "PetalWidth     float64\n",
       "Name            object\n",
       "dtype: object"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "25236611",
   "metadata": {},
   "source": [
    "et s'agissant de `Name`, nous en avons bien 3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "2b180e85",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Name\n",
       "Iris-setosa        50\n",
       "Iris-versicolor    50\n",
       "Iris-virginica     50\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby('Name').size()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "247ac4c7",
   "metadata": {},
   "source": [
    "## encodons les catégories par des entiers"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "65adfa22",
   "metadata": {},
   "source": [
    "Nous allons créer dans la dataframe une nouvelle colonne, de nom `Type`, qui va coder ces trois noms par trois entiers (0, 1 et 2)\n",
    "\n",
    "Pourquoi on a envie de faire ça ? eh bien lorsqu'on parle de visualisation, c'est toujours plus facile de visualiser des nombres que des textes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6dddb5d1",
   "metadata": {},
   "source": [
    "Pour y arriver :\n",
    "\n",
    "1. on prend la colonne `name` qui est de type `object`\n",
    "1. on la transforme en une colonne de type `category` grâce à la fonction `astype` des dataframes\n",
    "1. on extrait les codes générés par `pandas` pour les trois noms de types d'iris `cat.codes`\n",
    "1. on ajoute cette colonne de codes (de type entier) à la dataframe, en l'appelant `Type`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "56a40e0d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# on crée une nouvelle colonne\n",
    "df['Type'] = df['Name'].astype('category').cat.codes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1af40030",
   "metadata": {},
   "source": [
    "Vérifions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "007b4c85",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SepalLength    float64\n",
       "SepalWidth     float64\n",
       "PetalLength    float64\n",
       "PetalWidth     float64\n",
       "Name            object\n",
       "Type              int8\n",
       "dtype: object"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "243071ca",
   "metadata": {},
   "source": [
    "On voit la nouvelle colonne de type `int8`, et elle contient bien ce qu'on veut :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "0714ab20",
   "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>SepalLength</th>\n",
       "      <th>SepalWidth</th>\n",
       "      <th>PetalLength</th>\n",
       "      <th>PetalWidth</th>\n",
       "      <th>Name</th>\n",
       "      <th>Type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   SepalLength  SepalWidth  PetalLength  PetalWidth         Name  Type\n",
       "0          5.1         3.5          1.4         0.2  Iris-setosa     0\n",
       "1          4.9         3.0          1.4         0.2  Iris-setosa     0\n",
       "2          4.7         3.2          1.3         0.2  Iris-setosa     0\n",
       "3          4.6         3.1          1.5         0.2  Iris-setosa     0\n",
       "4          5.0         3.6          1.4         0.2  Iris-setosa     0"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9dcab36d",
   "metadata": {},
   "source": [
    "## dessinons la dataframe - `df.plot()`"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5f0a6d09",
   "metadata": {},
   "source": [
    "Nous pouvons voir dans cet exemple, qu'une simple visualisation des colonnes numériques apporte beaucoup d'informations sur ces données.\n",
    "\n",
    "Par exemple, dans ce jeu de données, les mesures semblent discriminer les 3 types d'Iris."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "8cc0dd33",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWoAAAD4CAYAAADFAawfAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAAC8CklEQVR4nOydd5hcZd3+P2d62943m7rpdVNIBQkdAUWRbgEEsYsoYsMCFnwVFX3VnwXBV0UJTRAMVVpIAoH0ns2mbDbb6/R+fn8885zp27KbQua+rlyTnTlz2szc5z73tymqqpJDDjnkkMPJC92J3oEccsghhxz6R46oc8ghhxxOcuSIOocccsjhJEeOqHPIIYccTnLkiDqHHHLI4SSHYTRWWlpaqk6YMGE0Vp1DDjnk8J7Exo0bO1VVLcv02qgQ9YQJE3j33XdHY9U55JBDDu9JKIpyONtrOesjhxxyyOEkR46oc8ghhxxOcuSIOocccsjhJMegPGpFUW4HbgFUYDtwk6qq/qFsKBQK0dTUhN8/pLflMIKwWCzU1NRgNBpP9K7kkEMOQ8CARK0oyhjgS8BMVVV9iqI8ClwL/GUoG2pqaiIvL48JEyagKMqwdjaH4UNVVbq6umhqamLixIknendyyCGHIWCw1ocBsCqKYgBsQPNQN+T3+ykpKcmR9AmCoiiUlJTk7mhyyOEUxIBErarqUeA+oBFoAfpUVX0xdTlFUW5VFOVdRVHe7ejoyLiuHEmfWOTOfw45nJoYkKgVRSkCLgcmAtWAXVGUj6Uup6rqH1VVXaSq6qKysow52znkkEMOIwJPIMzjG5s4Xdo0D8b6OB84qKpqh6qqIeBJYPno7tbo4Ec/+hGzZs1i7ty51NXV8fbbb4/Yul977TUuu+wyAP7yl7/whS98YcTWnYpDhw7xj3/8Q/t7tLeXQw4nG57cfJQ7HtvKoS7vid6V44LBZH00AksVRbEBPuA84JQrO1y/fj3PPvssmzZtwmw209nZSTAYPNG7NSxIor7++utP9K7kkMMJQX2bCwCnL3SC9+T4YDAe9dvA48AmRGqeDvjjKO/XiKOlpYXS0lLMZjMApaWlVFdXs3HjRs4++2wWLlzIRRddREtLCwArV67ktttuo66ujtmzZ7NhwwYANmzYwLJly5g/fz7Lly9n7969g96Hv//97yxevJi6ujo+/elPE4lEAHA4HHz7299m3rx5LF26lLa2NgAaGhpYunQpc+bM4a677sLhcADwjW98gzVr1lBXV8cvf/lLAJqbm7n44ouZMmUKd95558ictBxyOElR3+YGwB0In+A9OT4YVB61qqrfA743Uhu9+5md7Gp2jtTqAJhZnc/3PjAr6+sXXngh99xzD1OnTuX888/nmmuuYfny5Xzxi1/k6aefpqysjFWrVvHtb3+bBx98EACv18uWLVt44403+OQnP8mOHTuYPn06a9aswWAw8PLLL/Otb32LJ554YsD92717N6tWrWLt2rUYjUY+97nP8fDDD/OJT3wCj8fD0qVL+dGPfsSdd97Jn/70J+666y5uu+02brvtNq677jp+//vfa+v6yU9+wn333cezzz4LCOtjy5YtbN68GbPZzLRp0/jiF7/I2LFjj/Gs5pDDyYn6dkHULn+OqN9TcDgcbNy4kTVr1vDqq69yzTXXcNddd7Fjxw4uuOACACKRCFVVVdp7rrvuOgDe97734XQ66e3txeVyccMNN1BfX4+iKIRCg7v1+u9//8vGjRs544wzAPD5fJSXlwNgMpk0f3vhwoW89NJLgLBrnnrqKQCuv/567rjjjqzrP++88ygoKABg5syZHD58OEfUORw3PLutmX1tbhTg8rpqJpU5Mi63vakPFZW5NYXD3laPJ0inOwCIoGImqKrK4xub+GBdNWaDftjbOllwQoi6P+U7mtDr9axcuZKVK1cyZ84cfvvb3zJr1izWr1+fcfnUdDZFUfjOd77DOeecw7/+9S8OHTrEypUrB7VtVVW54YYbuPfee9NeMxqN2rb0ej3h8NBVgrR0jmUdOeQwHKiqyldWbSUYiQLQ5Qnwww/Nybjsj1bvIhqFRz+zbNjb29/h1v6fzfrY2ezka49vI99q5KJZlcPe1smC06bXx969e6mvr9f+3rJlCzNmzKCjo0Mj6lAoxM6dO7VlVq1aBcCbb75JQUEBBQUF9PX1MWbMGEBYDoPFeeedx+OPP057ezsA3d3dHD6ctashAEuXLtVslUceeUR7Pi8vD5fLNeht55DDaMITjBCMRPnm+6czvsSGux87whOI0Os7tiD+/vaBibovFmTs8743go2nDVG73W5uuOEGZs6cydy5c9m1axf33HMPjz/+OF//+teZN28edXV1rFu3TnuPxWJh/vz5fOYzn+HPf/4zAHfeeSff/OY3mT9/fr+q9S9/+Qs1NTXav/z8fH74wx9y4YUXMnfuXC644AItcJkN999/P7/4xS+YO3cu+/fv16yNuXPnotfrmTdvnhZMzCGHbHhhZyuX/noNkejo5BxLUiywGrGZDLgDkazL+kKRY/aV69vcWI16THpd1nVJAnf63xtEfdp41AsXLkwiYYnS0lLeeOONjO/52Mc+xv3335/03LJly9i3b5/29w9/+EMAzVIBuPHGG7nxxhvT1nfNNddwzTXXpD3vdscVwpVXXsmVV14JwJgxY3jrrbdQFIVHHnlEyzAxGo288sorSetI3J4MMuaQA8Dmxl52NjvxhSI4zCP/k5eqtdBmxG7S4w1mJ2JfcASIut1Fbbmdll4/7kBmIpbe9Xsl2HjaEPWpiI0bN/KFL3wBVVUpLCzUslFyyGEo6PUKqyEYjoJ5gIWHs/6YlZFvNWIzGzSFnQn+UAR3IEwkqqLXDa+lwf52N0snleDyh7PaLDmiPk3w2muvnehd4KyzzmLr1q0nejdyOMXREyPqQDi7JXEskEUnhVYTDrOe5l5f1mV9IbEP7kCYAuvQ2+26/CFa+vxMLnewr82V1aOW9ovrPWJ9nDYedQ45nK7oiVkTgVB0VNbfG1t/gU141N5+UuYkUQ+XQGUgcUq5A4fZkFUxv9cUdY6oc8jhPY5eTVGPDlH3aYpaeNSeYGblHghHkT2Uhkugu1pEodzkcgd5FkM/ijpG1Fk87FMNOaLOIYf3OKSiDo4iURt0CjaTHrvZgCcQztjVzh+KE/hwifqJjU1MKrUzsdSOw5ydqHOKOocccjhloKpqgqKO2w7/3jrk2R9Z0esLUWAVRVt2s4FwVNWKXxLhSyLqoSvdXc1ONjX2cv2Scdq2sgYTgzmiPmVxPNqcqqpKaWkpPT09gGgGpSgKb775prZsWVkZXV1d3HLLLezatSttXYltS5966qmkZVauXMm7755yzQtzOEHwBCOEIkLdSuvjue2tfOmfmzmQUOF3LOjzhSiwicCgzSTKtb0Zcql9wWNT1P/YcBizQceVC2sAcFgMuHLBxPcWEtucbtu2jZdffnlUemEoisLSpUu1asd169Yxf/58LYd77969lJSUUFJSwgMPPMDMmTP7XV8qUeeQw1DQ44lXAUrrQ9oFh0eol3OfN6RlcNhNIpHMkyGXOklRD7HrnTsQ5l+bjnLZ3GoKbSYA8swGguFoxmwWj1bwklPUpxSOZ5vT5cuXa8S8bt06br/99iTiXrFihbYNqY4feughpk6dyuLFi1m7dq227L///W++9rWvUVdXR0NDAwCPPfYYixcvZurUqaxZs2a0TlkO7wH0JpRQS0Lzxx4Pd3kA2NPq5Mz/eYU25/Dmafb5QhRKoo4V1HgyKGp/P9bHH15v4Na/Zr9TfG57C55ghOuXjNOec/SzLUnU2Yj8VMOJyaN+7hvQun1k11k5B97/k6wvH882pytWrODuu+8GBLHffffd/OpXvwIE+S5fnjwgp6Wlhe9973ts3LiRgoICzjnnHO1C8MEPfpDLLrtMq1YECIfDbNiwgdWrV3P33Xfz8ssvj8gpzOG9B5lDDXHrQ6bpNXaLfOe1+7to6vGxq9lJRb5lyNvo9QWpLbMDYDML6yOjog7GfetU6+O/e9r7bX3c0OHBqFeYP7ZQe85hERcHtz9Msd2UtHzi+t3+MGbHqd1B77QpeDmebU7POOMMNm/ejMfjIRQK4XA4mDRpEvv372fdunV89atfTVr+7bffZuXKlchZk9dcc01SmXoqrrjiCkCUxR86dOiYzksO7x0c7vJwtNfH8tpS7bkkoo4RtFTUjd1CUcvc5KP9FKr0h0zWR0aPuh9F3dDuxh0IEwhHMrYlbXf6Kc+zoEuoZpSKOlMKnicYJs8sPGyXP0yJYxRKMo8jBiRqRVGmAasSnpoEfFdV1fuHvdV+lO9o4ni1ObXZbEyZMoUHH3yQBQsWAKIT3urVq2lvb2fatGnHdBzSvsm1M80hEf/vtQZe3NXGpu9coD2XZH1EkhW19Kj3t4tOjP1VFGZDJKriCoQpiPnG9piizpQ258uSntflDtAV89J7PCEqC9KJus3lpzw/mWzzLIK+MmV+eAJhxpfYcbW73xOZH4MZxbVXVdU6VVXrgIWAF/jXaO/YSON4tzldvnw5999/P8uWib67y5Yt41e/+hVLly5NuwAsWbKE119/na6uLkKhEI899pj2Wq6laQ6DRY83SLcnmOQFJytq8XxAU9ReolGVfbGxVsMhapc/hKqSrqgzWB9yvwptxiTyTGxb2uUJZNxOmzNARV6yLSMVdepFIRAWmS5VBRZtH091DDWYeB7QoKpq/42UT0Ic7zanK1as4MCBAxpRL1iwgKampjR/GqCqqorvf//7LFu2jBUrVjBjxgzttWuvvZaf/exnzJ8/XwsmHm987bGt/PKl7FZMDicHnD7xfexwxcmu1xvCbBA/c+lR+2OKOhCOsqvFqVUWNvcOPZiYWJUIiR519mBieZ45iTzrE4i625O5V3Wb009FiqJ2WDITtQwuVsb89vdC5sdQPeprgX9mekFRlFuBWwHGjRuXaZETiuPZ5hTgqquuSqrOMpvNBALJaiGx8dNNN93ETTfdlLYPK1asSErPS3xPaWnpcfGo3znUTYHNxO0XTB31beUwfMjey21OP2OLbYBQ1BX5Fhq7vQlEHSfR/+4WgyxKHWaa+4auqLU+H2kedaZgoiRqizZKC5IVdSai9gaFz1xRkKyo87IoapnxcVoqakVRTMAHgccyva6q6h9VVV2kquoiGRTL4b0BXyhCYyyVC2DH0T62N/WdwD3KIROkum1zxkmwxxuiyG7CZNBpedT+UETzd1/ZIybev29qKa19/iEPF9AUdazgZVPHW+hMXRpZbjzcrXng0qMuyzOnWR/jYheWLnc6UcvjSbM+snjUkrgrC6xA9uKa53e00O6K30W8uredI90jk1s+0hiK9fF+YJOqqm2jtTMnE1577TUWLVp0onfjpIA3GKHHG9IU211P7eDuZ3YO8K4cjjecvriiluj1BimyGTHrdZo3HQhHmVTmQK9T2NrUR57ZwPxxRYSjapJtMhj0Jkx3afe288VXvoCt9E3N+vjaY9v4+YviDtQXimA26CiwGpMmr9S3u1g0vgi9TsmoqOXxpKYOWo16dEp2RV1ZIKySTETtDYb57MObuHf1HgBa+nzc/Jd3eGDNgSEd//HCUIj6OrLYHjm8tyFvlRu7vKiqSn2bS/uB5nByIBrLvoBkou7xBimymTAbdUnWR57ZQHWhIL7JFQ5qCoX6HGqKXuIYrn/V/4uIGkFvCGrBxDanXwto+oMRrCa91vUuGlXp84VocwaYUpFHkc2oZX8kIk7UyR61oigZW51K4i6wGrEa9Rmtjw5XAFWF/2xvodsT5JENR4iq0JnFIz/RGBRRK4piBy4Anhzd3cnhZEMoEtV6RTR2e2np8+MJRk553++eZ3Zxy/+9856oWgNwB8NaC9EkRe0JUWgzYjbo43nUoSgWo47xxaJIZXKZg+oYUSdmfrS7/Kz82av9FqJIFW8363i8/nEADIYQ7kAEbzCMJxjRgpy+UASrURC1qopc58T+0sV2E90Zsj7aY9ZHeYZinDyLMWsw0W42kGfJ3LNaeuTBcJRH3mnkkXcaxflKyJL5zN828o0ntmXsBHi8MSiiVlXVo6pqiaqqOWPyNENi7uvhLq8WoT+Vc1PbnX7+uv4QL+9u53tP7zwpfojHCmfCHY70dEORKK5AWChqg07raCeLSsaVCF94SoVDU9eJRP3WgW4OdXnZcTT7z77XG8Ri1PFu+3paPa3oFT06XQhvIEynS5CetDl8oWiMqGMVhYEwDZKoKxwU2UxZrQ+LUUe+JT33wZGhg560PuymGFFnKIiRFk+J3cT9L9fT5gyQZzbQ44kv+86hbh555wi/f/3E2yGnTa+PHIYHf0KaVWO3h/o2ERjyBiOEM7SyHEmoqspTm4+OuOp99N0jhKMqV8wfwyPvHOHvbx17tmkoEuXJTU1ER2nS90CQqtWk19EWC5BJy6HIZsRk0Gl51P5QFLNRx/hYAG9KeR55FiN5ZgMtfXE1vr2pN2k9mSD6fJhYtXcVZdYy6srrUHRBPMEwHTHVKi8ivmAEnaUZZ+QQIC729e0uzAYdNUU2ShymzNaHK0BFviWt/gBEQDFVUcu/HWYDeRZjRlHREQtafvrsSQTDUaoKLJw/s0JT1NGoSo83iNWo56cv7OHe1bv5zSv1bG7syXouRhOnFVHr9XqtydJVV12F15s9wrtlyxZWr1494Dple1NIbk86Gjh06BD/+Mc/tL9He3sgCFnicJeXhoTWmNmato8UdjY7+fKqLbwSSyEbCUSiKv/ccIQVk0u476p5LJ5QzANvHjzm9b66p52vPLqVN/d3jsBeDh1StU4qs2tWQa82HVwoaq3XRziCxahn8cRiKvMtzKkpAKC60JrkUW+LZfb0eLPbXL3eEPlWA2+1vMVFEy4iz5gHuiDeYESzF1wxP9ofiuC0PcHzLX8Uz/tD7Gl1MblcBDaL7aakbn8SbU5/WsaHhN2c3upUU9T9WR+uAIoCH1s6ntoyO7e+bxIldpN2rL2+EFEVvnTeFBaNL+IPbxzgvhf38d2nT0wQ/bQiaqvVypYtW9ixYwcmk4nf//73WZcdLFEfT6QS9fGAtD6sRr2wPtriRD3a9odUVyMZ4HltbztHe318bMl4dDqFBeOLaO71HbMSbuoRBLctpkKPN6RqnVzuwB0I4w6ENdKTHnUwoeDFbNAxf1wRb33rPEpjfTCqCy2a9RGNqprl0TuAos63RQlFQ5TbyrEYLKAEcQfCGlGrqvDQfaEI6PwEVW9sn8Nsa+pjbuxCUWw30+sLpaUItjv9aTnUEnlmA+6UeIk7GMak12Ey6Mi3GDPGUzrdAYpsJmwmA//96kpuWjGRIrsJXyiCPxTRvPLqQguPfnoZ9T96P58+exJ7Wp0nJK5xWhF1Is466yz279+Px+Phk5/8JIsXL2b+/Pk8/fTTBINBvvvd77Jq1Srq6upYtWrVoNqbZsPf//53Fi9eTF1dHZ/+9KeJRMQH7XA4+Pa3v828efNYunQpbW0i87GhoYGlS5cyZ84c7rrrLhwOBwDf+MY3WLNmDXV1dfzyl78EoLm5mYsvvpgpU6Zw5513jvBZiivqqRUOWvp87G11UeoQfR2cgwwovrizlQ/9du2QyVASRO8IEvXf3zpMeZ6Z82dWADCm0EIooiYVYAwHkuC2naD8cll9N6U8DxDkJtVhg/ttDlvuxR+ODbmNKepUVBdateM40OnWUuwGsj5sFvF6vikfq8FKVAniDUSSUv36vCF8wQiqEiAUFduQVZFzxhQCwi9W1eTtqaoaKx/P3FQp0zguTyCs5VhnG4Db6Q5o32MJmQve6w1p+dwldjOKomDU66irKSQUUdnTcvxbOpyQ7nn/s+F/2NO9Z0TXOb14Ol9f/PVBLRsOh3nuuee4+OKL+dGPfsS5557Lgw8+SG9vL4sXL+b888/nnnvu4d133+U3v/kNAE6nc8D2ppmwe/duVq1axdq1azEajXzuc5/j4Ycf5hOf+AQej4elS5fyox/9iDvvvJM//elP3HXXXdx2223cdtttXHfddUmq/yc/+Qn33Xcfzz77LCCsjy1btrB582bMZjPTpk3ji1/84ogORJCpedMr89na1IcrEGZpbQUv7WrLOgYpFVubetlypBeXP6xNAhkMpCLs79Z7KDjS7eW1fR188ZzJGPVCo1QnpKVlyioYLGRV3/Z+Am+jCZkmN7VCXNRbnX7tQnfAvQ2vchB/2EckqhKKqFgydKirLrTS4w3hDYa1C05xgh2QbbvjqgLgh3xzjKgJ4AmGky5+Tn8IfyhClACBiPjerI3ZRHFFLYiz2xPUVL4rIJR4tvarDkumYGJEaw6VzfrocAUoSyH/olhjKdkzJXGfAM0i2na0j3kJ7VaPB06bNqcAPp+Puro6QCjqm2++meXLl/Pvf/+b++67DwC/309jY2Pae/v6+gZsb5oJ//3vf9m4cSNnnHGGtg/l5eUAmEwmzd9euHAhL730EiCm0Tz11FMAXH/99dxxxx1Z13/eeedRUCC+QDNnzuTw4cMjStRSUU+rzNOeWzCuiJd2tWk/gIYON73eIAvHF2dch0yXcgVCQyPqGEH0p+iGgn9uaEQBrl0cb3Egibqlz8/8Y1j30VifjJY+P+0u0ZLzeCLR+gCR0ibPnyvcBYA/EtAuvBZj+s30mIQUvW1NfViNehaMK9LaoWZCny+ExSSIusBUgNVgJawG8CRkfYj9E4QbJYA/Irb97uEeTHodUyvEd6skRopd7iCIGx7aYsHN1M55Eg6zAU8wQiSqoo+1QHX5w1ope57FiC8UIRSJahdngE53kPnjCpPWJRV1jzeo2W4lCap7TKGVYrspFmQdz55WJ25/mEUTMn/vRxInhKgHq3xHGtKjToSqqjzxxBNprUdT5ykOpr1pJqiqyg033MC9996b9prRaNQi2cNtWSpbnh7LOvqDT1PUcaKWX3CZ9vSLl/axvamPN+48J+M6hjsRWirCkSDqYDjKo+8e4dzpFRo5A1QXpOcPDwctvT4mldk50OFhe1Mf5804zkTtD5FnNlAVO7Y2p59tTb0iN9kvlGsw6tcCirJRUyJmVOWjKPCbV/bT2O1l9ph8Sh0mtmbx3f/21mG8wQhFeWFwxhW1SoSoGqap10u+xYDTH8bpD+ENhYniJxIGvU58JvPGFmKK7UuxI66oJbTy8SyKWpbCe4Jh8mNpf55AWOusl9gKtShBHQvrI7Oi7vWGtH2Qz4EosJkzpoBtTX2oqsoX/7GZHm+IDd86L6lP9mjgtPWoJS666CL+93//V8ul3bx5M5DeXnSw7U1Tcd555/H444/T3i4yF7q7uzl8uP90sKVLl2q2yiOPPKI9fyJansr0vHElNixGHXkWg6baJPF2OAO09vmz5iNLVT5Uoo4r6mO3Pl7Y2UqnO8jHliY3DMu3GrCb9MNumg/C8213BbhgZgU65cT41E5fmHyrEYdZHM/2o328tKuNKxfW0OHrACAY8Sco6nTrY1plHl+9YCpPbWlmU2Mvc8YUUmgz0esNpn22bx3o4u5/7+Tc6eXMGSvITCpqAHRBDnd6mVTmiO1fCH8oAKioqNhjvDt3TIG2zrj1EbdMspWPS2itThO+W55gWBsJJok68bvnCYTxBiNZiVpaH3lmg3YRkZhbU0B9u5vX93VQ3+6m0x1gT+vo/yZPe6L+zne+QygUYu7cucyaNYvvfOc7AJxzzjns2rVLCyYOtr3pX/7yF2pqarR/+fn5/PCHP+TCCy9k7ty5XHDBBdpcxmy4//77+cUvfsHcuXPZv3+/Zm3MnTsXvV7PvHnztGDiaEOWAttMBsYX25lS7kj78nd5AgQj0ayEKscyDbWaUSrp/rIOBotH3mlkbLGV901JbhimKEpSEG04aOsTxDK5zMGU8rwTkvnh9Ie0z6Ui38Lq7S2EoyrXnjGWDm+MqKOBfoka4PPnTObSuWLK0dyaAopsRkIRNaltaTAc5Qv/2MT4Ehv3X1uHKyQqF/PN+ViNgqgVXQhXIExtjKj7fCGC0XiOtsMi1id9X4gTZWIudUvM+y9P8ZM3t2/mA//6AEajWDY1bTSuqIXK3nykh7N/9ipv1ndq3nmqR50YTOz2BDWFn4i5NYVEoip3P7NLm7j+5v6ODGdyZHFaedRutzvtOavVyh/+8Ie054uLi3nnnXeSnhuovemNN97IjTfemLaua665hmuuuabf/bnyyiu1uYhjxozhrbfeQlEUHnnkES3DxGg08sorryStI3F7Msg4kvDFyo5tJj0/+NBsTAYdZoMek0GnZX3I28Q2pz9tdh3ExzIN3fqIKepjzPpwB8JsONjNJ8+cmPEWVRD18Aa7Qrw/xphCK3NqCnhtbzuqqmYs0BgtOH0h8mOtRsvzzRzo9HDWlFJKC6L4I+LYQtGA1os6k/UB4sJ135XzOGN8ERfNquSZrc2A+Awk+TV2e+l0B/nm+2eQbzHiDDoxKAZsBluSogaYWCqKatpdAdDFlbLdGgH0WiARwKgX1YeJ1seGQz3Ultk1hSzxbMOzHHIeoqrUSU2RlTse28ozXziT8nwLnkBYCybKasavP7ENfyjKq3vbuWROJUBa1ofFqMdq1NPjEYo603dZ7u/BTg83Lp/A2v2drKnv5Nb31WY8nyOF015Rn4zYuHEjdXV1zJ07l9/97nf8/Oc/P2H74guGURTxw148sZi6WLQ7PxZNj0RVrUGTvE092utjXULhhztwbIra6Q8PuQpy7f5OTWW9faCLUETl7CmZ2+8eq6KW760qtDK3poBOdzCpwm+0UN/m0irlnP64Ryttgo8uGaepaYCQGhA5wLoAe1xrs67XatJz44qJWE36JJUpIVuBToiRsDPgJN+cj6IoGlErMaIuz7eQZzbQ5vSjKPF1WM2i78fkmOKWKHGYNUXtD0XYcLCLszJ8buuaRW95X7SHP31iES5/mFv/tpFAOBLL+khW1JGomPiyramXjliQM9X6AFHF2eMN0eUJasHNRFTkWzR1/7Gl4zhrShlvH+xO6vE9GsgR9UmIs846i61bt7Jt2zbeeOMNJk+efML2RTbSSVWHsjS3xxvUmgHJirjfvLKfz/x9o7astE+GOmmj1xvCqBfb7RtCt75eb5BP/uUd7nx8GwBr6juxGHUsnFCUcfkxhRa6UkZYDQUaURdYmFmVD8De4+Bb/uA/u7l91RZAKmpBTgvGFTG9Mo/zZlTQ7o1XdaoE8QQiGPK28WD93RzsG7giUwbgEgO6h2O9ycfFmjr1BfvIN4nj1ohaEcuXOczkW43iu5GgqCeVGThvRjkGfTIFJVYnbjzcgz8U5awppUnLHHEeocndBEC7r50ZVfn8z0fmsuVIL//e0ownGLc+aoqslNhN/OjDc7hoViU7jjq1HtSp1gegefLdnkBGRQ1w/swKLppVweTyPM6aWkowHOWdQ939n8hjRI6oc+gX3qAg6lSI/NRQki3RGlPUhzo9OGNqG+JjmYZifQTDUdyxAaUwtIDi4xubCISjbDzcw+4WJ2vqO1gysSTjdGuAqoJ4it5w0Nzno9RhwmLUU1MkVOaxBCcHi0OdHg53e0Vptj+kKeoblk/g+S+/D6Nel0TU6IL0+UIoenGcDb0Dj3YrSkhZkzjc7cVm0scLn2KKGsBmsGnbAkGGeRYDbS6/prIBrllSwW+uX5C2PdFBTyz3Rn0HRr3C0kklScusb4kPo5Z3DJfNraK2zM4Daw6iqmiKushu4t27zufqRWOZW1OALxThrQNdKAoZibjIbtSCicX2zCmBP/7wHP7wcdGrfsnEYkx6HWvqR7d1QI6oc+gXvlDmKjZZSNCVlEolCKAxdmssI/HeYVgfvT7pcQqiTgwo+kMRLv31Gl7dk94DRFVV/vF2IzOq8jEZdPz8xb00dHjSVFkiMrX4HAqae/3aOsryzBh0ihYEGwnc+fhWfv3f+qTnQpEoR3t9qKqYkOIOhDWPOhEy4wNAUcTwByWmbAdD1IUJKWsSjV1exhXbtLusjIpaF7cX4oo6/hn6wpnPT6nDxNFeH32+EG/Wd7JgXFGaP72ueR1V9irKbeXahUhRFD66ZDx7Y03DEt8j91P6y2v2dVJkMyXlVSce75EeH6GImtH6SIXNZGDh+CLe2De6AcUcUefQL3zBiBbdTkSeWfRQkOrHqFdocwoPVFbpOf0holF1WIpaEsOk0nRFvavFyc5mp1bZloj1DV0c6PRw6/smctncKl6ONXTK5HNKjBlm03yJ5l6flo+t1ylUFliOKTiZCFVVWb29lfUNXWnblHcsmxt7UFUytgFt97ZjUGLP60KiMCbmFTf0DYKoremKurHbq43OAqGoC8yCBFODiSUOE/mxntGJitobztwQ7apFY/GHInzq/95lZ7Mz7QIbjobZ0LKB5dXLqbBVJF2IPrKgRivkcZjTv7OTSh3YTXpcgXBaIFGiyGbUSt+zWR+pOGtqKXtaXUljvUYaOaLOoV/4QmIqRyocKYq6tsxBu8vP0R6f5lm7/OGkftYDKWpfMMITG5sIR6KapTJRI+r4j1zOazycYb7dw283Umgz8v7ZVXx0yXhApHbJ0upMqCgwoyjDU9SqqgqiTiyiSelCl4rnd7QO2nNvdfpFg6WUFMXGhGPfeFgEFDMqam8HY/JE/r+ixKyPmKKWHnUoEmL1gdUZ8+ANepE7Ly+c0ahKY7eX8SVxos7sUYuBBUa9TvPOlUEo6gXjirjn8tlsiHm+qRfYHZ07cIVcLKteRpm1LMnaKbAZ+cDcagBsRj2rD6wmFImfZ51OYXYsbztTIBGSC1wypedlwlmTxT5mEg4jhcFOeClUFOVxRVH2KIqyW1GUZaO2R6OI0WxzqqoqpaWl9PSIH01LSwuKovDmm29qy5aVldHV1cUtt9ySNFlcIrFt6VNPPZW0zMqVK3n33XcHfawjBV+/HnWY7ljzmhlV+bQ5/Unk6fKHtBxq8Xd2Ra2qKnc8tpWvPraVdQ1dmoLOZH3IgpLGruTPr93p54WdrVy1sAaLUc+CcYUsnVTM5XXV/abKmQ16yhzmYRG10yemmMjG+wDVBZas62pz+vnM3zcOejafnIDSm+LRH44de57FwKbGXgDNo05Eu6+dKnsVOvRCUftDGmEe7DtIJBrhmQPP8PU1X2dnV+YWnkU2k3ahaHcFCISjjIvFDqJqFHfQnaaoFX28X4e2XwnBRG8o+2/vusXjuOXMiUwstWvEKrG+eT0KCksql1BmSyZqQHTBsxkJGQ/w9TVf56XDLyW9Lu2PbERdmEjUtsER9azqfIpsRtbsO8FEDfwKeF5V1enAPGD3qO3RKGI025wqisLSpUtZv14EOtatW8f8+fNZt06kEe3du5eSkhJKSkp44IEHmDlzZr/rSyXqE4VsilqOQOp0B8izGKgpstLhCnCwI94XwuUPa30+5N/Z8JtX9vOf7aIQqL7drRFzTbENg05Jsj5kQUljtzdJBa56RwwEuD6mpBVF4ZFbl/HtS/s/1zD8XGqpnFMVdbaJ3gc7xfl5Y5DBJ9lWNpOiNhl0LJ1UoqnrgiyKutxWjklvRtGFxICBGFEHIgGa3c1aqlunL/M+yZQ1iGd8yKEDrqALFTVNUZsNYcokUcf2azDWh8Rdl83kla+erfXvkFjfsp5ZJbMotBRSYavAGXTiD8c/t5nV+Wz6zgX4FJH/vb93f9L759QUApkzPuSxSgzW+tDpFM6cUsaa/Z2jNi1oQKJWFKUAeB/wZwBVVYOqqvaOyt4cR4xGm9Ply5drxLxu3Tpuv/32JOJesWIFkKyOH3roIaZOncrixYtZu3attuy///1vvva1r1FXV0dDg/ASH3vsMRYvXszUqVNZs2bNqJ8jyO5RSz/0SI+XEruJ8nwLURU2JkzAcAVCWp+PvAyTOCRe3NnKz1/ax4fqqim2m9jf7tKIochm1FKmQJT/7u9wU+oQvYOlnygGAjRy5uRSTYUPBWMKrRzp6Z88QAwIuPCXr+OL+e6JqXkS1YXWrBO95V3AtqbeQVVcytFngXBU2yYIwiyufoMuy9+156TFIBFVo3T4OiizlmHSWUAJxayPIAadWHZf7z7eankLgB5/5ukliedf3jFJ68MZiFUlxohar9Nj0pkwmsIaGWreuRLEqDNi0pnSrI+/7PgLX33tq0nPpd4FuYIutnVsY1m1uKEvswnLIdGnlu870CvuWA70Jd+5zIsp6uxEHSfnkkFaHwBnTS6lwxXQgpkjjcFUJk4EOoCHFEWZB2wEblNVNamllqIotwK3AowbNy5tJYlo/fGPCewe2Tan5hnTqfzWtwa17Gi1OV2xYgV33303ABs2bODuu+/mV7/6FSDId/ny5UnLt7S08L3vfY+NGzdSUFDAOeeco10IPvjBD3LZZZdp1Ypyvzds2MDq1au5++67efnll4d9vgYLbzB71geIW/Biu0nrF/zOwW5KHSY63UHc/rDW56My36Kl7yVib6uL21dtYW5NAT/5yFw+8eAG6tvc5FvE+CirUS8UXWyW3c5mJ6oKl8yp4q/rD9PY7aU838Kre9pp7vPz3Q8MrJ4zYW5NAf/Z3iKmifTT7vS3r+5nX5ubhg43s8cUaGo2MbimdaHr81GZ0vD+cKwTnarCuoYuLplT1e9+7W+P//B7vEGsJrHuw11e9IWHaA+3IeZOp1sfvYFewtEwZbYyzHoLii5O1FOLprKraxf/OfAf+gLCSur2Z84FLrIZOdApLhhHur3odYp2B+EMCqKW1geA1Whlbm0eX5gv8v8TFbXVYEOnKGnWxxP1T2TdvsSG1g1E1IhG1OVW0YWyw9vB2LzkjpEyoyU1s2V8iZ37rprH2VMzB5dlgY/FqMNmGnzh9pmxoOeafZ1Mr8wf9PsGi8FYHwZgAfD/VFWdD3iAb6QupKrqH1VVXaSq6qKysuwR9hMJ2eZ00aJFjBs3jptvvpkXX3yRn/zkJ9TV1bFy5cp+25xeddVVzJ49m9tvv52dO9P9vDPOOIPNmzfj8XgIhUI4HA4mTZrE/v37kxS1xNtvv83KlSspKyvDZDJlLDNPxBVXXAGIlqiHDh0a/okYAvyhLFkfMVI40u2l2G7WCKndFWBWtfjROv1hzaOuLLDgjo1kkujzhvjUX9/FZjbwx48vwmLUM6XcQX27mx5vkCKb6C6Y6JFK2+OyWNBIerUPvy0GApw3o2JYxyl/aG/2Y0nsaXXybixwJwm6sduLw2xIuk3uL92vsdvHmEIreRYDa+r7T+lSVZX6dreWJibPgaqqHOn2YjSG8IR7AXFO3ZF23mmNtz2QOcbltnLMejMoQZz+EDp9kHJrOeXWcv7b+F8ADIqB3kBvxv0otJno9Ujrw0t1oUVLbZMkLxU1CPujyKFq7UvlBUQQtRWrwZqkqFvcLRxyHsIVdBFVs1egrm9ej9Vgpa6sDogr6nZfepqmzGg54jqSFFAEuHJhzYCKusRuZnP75kEVBYH4zGvL7KwZpYDiYC4ZTUCTqqqy7+fjZCDqoWCwynekMdptTm02G1OmTOHBBx9kwQKRzL906VJWr15Ne3t72jaGCtnSdDTamWZDfwUvAOGoyDdNVKFTyh2sb+iKedQxos63oKqiQZMk+Zd2t9HY7eUftyzRiH5KuYM+X4h9bW7tR1NoM2qEvK2pj6oCC3VjC9Ep4la81xvk9X0dfObs2oy5sYPBjErR0nNNfQcfWViTcZmH32rEpBfTvOX+HO7yMDYhpxigKsNEb4nGLg+TyuzYTHre2NfZb0+QLk+QXm+Ii2ZV8MLONi2g2OUJ4glGqNSHCIdjBSxRKw/v/TMvHn6BN699E5PeRJtXTAwqt5Vj0Vs1j1opCGI1WplUOIn2lnZmFM+gN9Dbj6I24QqECUWiHO72Mr44bi1lVNQpRFyQoKjtRhsKStLrsoBFRcUVdCWtKxHrm9dzRuUZGPVG7biApDJ5EBZJu7edqUVT2dezj8POw0wuGlx1r/zOFdtNfGvNt8g357PqslWDeu9ZU8p4Zmsz4Ug0reLyWDHg2lRVbQWOKIoiWeY84MRHuUYII93mdPny5dx///0sWyZuz5YtW8avfvUrli5dmvaDXLJkCa+//jpdXV2EQiEee+wx7bUT0dI0FaqqaiXkqchLuM0udpgosZuQcZ/xJTatclE2ZJJEnBhQlHmndQkN3CfHRkntONqn3YYmKurtR/uYM6YAk0FHVYGVxi4P6xq6iKpw7vTyYR+rTqdw5uRS3tzflXFkmCcQ5l+bj3LZvCqK7Satmb4gLlvSsvmxid6ZgpOHYznIZ00p42ivj0Nd2X1xGUg8I9aYXp4DeZFQY2XaVcUhHGYDbd5WfGEfm9vFd1hT1FY5y1DkUSu6IDaDjdpC0UhoWfUyiixFWT3qInu830djl4dxial5WRR1IhFL71xvENu1GW1J1ocMZkKc+FPR5Gqi0dXI8uq4fZhvysekM6Vlfkhf+oLxwhIaTL64RJ7FgE4Rx9zqbWVX1y52dg5uoO3t509l/TfPG3GShsFnfXwReFhRlG1AHfDjEd+TEwBPIMw1n/oyvkBwxNqcrlixggMHDmhEvWDBApqamtL8aYCqqiq+//3vs2zZMlasWMGMGTO016699lp+9rOfMX/+fC2YeLwhO61ZM3h1eQnFFSV2Ewa9Tkt5Glts09L3pPUhFXciUXe6gthN+iQvcEos3zkcVeOK2m7UWk8e7PRoKVbjim00dntZU99BntlwzOORzpxSlrW/8LPbmnEHwnx0yXhtu5GoSlO3LymnWCJTLnWfL0SvN8T4EptWyNHf1HLpTy+eKIlaKGp5kYiqIlg5piRCgdWoEbMkvqPuowCUWkuxGoRHHYxEQREWxKSCSUCMqM3ZiVqmrG1q7KHHG0q6MElilSXkkIGoYxd1nS6E1ZhsfUSiEd5qeYtiizhGGZxMxZtHRZrrsqp4ZrCiKBlT9GQg8dxx56IQDywOBjqdsNry7UHCUfFdXbV3cIq6wGZM6189UhiUW66q6hZg0ajswXFEaptTfyiCYjTxtR/cx+QyR9KVcDhtTgGuuuqqpBQds9lMIJAc/X/ttde0/990003cdNNNafu6YsWKpPS8xPeUlpYeF486PoE8/cuXSNTSn63It9DuCjC+xB5r2hRKCiZCctFLpztAaYpXWB7rDeHyhzWCKLKZCEai/G29GLggB9OOL7Hx8u422pwBltaWDNv2kJDkuaa+g5nVyQGhV/a0M6bQyoJxhYwvsbHxcA+tTj/BSDRJYUokTvSWkBkf44ptjCsWgxgau7KPuapvd+MwG7QxaHLI7+EuL4qC1t/54rl2Jjvm8M2NgrDWN6/ntgW38dzB51hQvgCj3ij6ROuCgIqqBLAZbVwy8RKiapTFlYt5ev/THHIeyrgfMmXtq49upchm5LJ51dprzqATi94iPPAYrAZrko2iBRP1QlErKLR6WwHY072HvkAf10y7hlV7V9EXTB+6oKoqT9Y/yeTCyUwsmJj0Wmp1IghFbdKZqC2opSavZkiKGuC+q+YR0jfx+jpxN/Lcwee444w7ku4ajjdO68rEaIxQQxE1LScXxBek1xvUljvdIIk6U/Q7McMgTtRmdApasMzlD+MOhDHqFa3KK0lRZxiHpCgKU2ITZCRByDLmB9ceZNH4Ii2qPq7ERqc7yNFeH+/rp5fHYFGRb2FqhSNN5YYjUdY1dHHWlFIURWF8sY3mXh8NsdS5RM9WorrQmtbkSWZ8jCu2oygKlfkWbdRUItbUd/CH1xtYu7+TyeUOzAY9dpM+rqi7vFTmW/BFxIXAYvWyeJIDV9BFvimf3d27WX1wNU3uJq6ZJgLUVoNFtBlVwqCoWA1WHCYH106/Fp2io8hS1K9HDeL78NuPLtCyWkBYH6kElqiYt3dspyvQhKKAogtowURpfUh/+qIJFwGZFfXOrp3s7t7NNdOuSbMPy2xlaR51Q28DEwsmotfpmVQwKS1FbyCcM70cq1V8VrfMvQV/xM8zDc8MaR0jjdOaqGWL4+pYRkJqnq8vGKGx26sNDj3d4IvZFpYMWR9mg05rQSqJev64IhZPLMZk0OEwC6L2BsLYTAYtl9aZoKg7XIGMPRemxHzqeDBRPPb5Qnxs6XhtuUSC7K+Xx1BwzrRy3jrQlZQDvbWpD5c/rGWGjC22EY2l10Fyap5EdaGVbk8wJfc5pqhjCrw836I1spJ4eVcbn3hwA/c+t4eGDo/WOS4xl7mx28vYYpN2a97l66LTKy4ul0y8BIB7376XYksx548/HwC70Qq6ePm41uUuhmJLMb6wL6l4RGJskY0im5F7Lp/F8trkC6Iz6EyyPSCZqL+x5hv8evOvRNtRJYjNKDxq+fq2jm1MLJjIhPwJ2vpSsWrvKqwGK5dNuizttdQychCKelKhsHUmFU7iUN8h7VwNFlKln11zNlOLpvLqkVeH9P6RxmlN1FFVTC4utJlQFCWNqOUgUPl4usEXjE13yRBMVBRFCyhKov78OZN55FbhIUrrwxOMYDfptWVTFXWmNCk5kzEeTIw/Xjy7UltOesM1RdaMPvFwcNWisYQiKo9tPKI9t6a+A0WBFTGSkq1X39zfgUGnJJWPS8jnmhO66DV2eSl1mLReydIqkqhvc/HlVVuYVZ3Plu9ewK57LuIb758ujj3WfhNEQHJMcfwz6fJ3aSlqK8euJN+UjzPo5EOTP4RJLz4bu9EqekTHqgNtxuTzVWQWvboz+dQFNiObvnOB1jslEf0p6qgapdnTTKunlXyLUVgusSkwsjKxw9tBtb1aI/tUou4L9PH8wee5dNKlOEzp/VrKbeV4w148IaGAvSEvR91HqS0QgdLaglpC0RBNrqa09/YHSf5l1jKmF08fks89GjitiToSVdEpCnqdgt2kTxqQCYjAC6I38ukI2fA/Uwk5xH3qkgx9e6X14Y0NGk2dsxiKzVjM1HNhciygKCvD5OPVi8YmFd+MjSlZaUmMBCaXO1g2qYR/vN2olYC/Wd/J3DEFWhN9eVHYcdTJmCJrxii/7Ka39Uiv9tzhbk+S+q7IMycNBf7iPzdjMer548cXUWgzJVlOIvMlhDcYpsMVoLIgvs0uX5dGLJX2SpZULUFB4cqp8WIpi8ESU9SCqLUud3L9FkHU3YHM9ke28+sMOtPS6WwGG76Qjy5fF+FomA5vBwU2A1GS86hVVaXd1x4ryDFj0Vu0LBKJFw69gD/i5+qpV2fcvsylbvOIVMSDTpH3LBW1zGzZ0Loh4/tD0RAfX/1xnj2QPMauw9tBsaUYo95IbWEtHb6OtH07njitiTqqquhjX0CH2YAvFCGUMPJJEnRwiGOg3ivQgon9ELXVqM/4er7FgDsYxuUPYzOL5fQ6RQsmyvaomYj6rMmlfP8DM1kxWSjY2jIH91w+i8+uTJ5LV2A18our5/H5c0Z2As5Hl46jqcfHG/UdOP0hNh/p1WwPEAFP2U4zk+0BIuVwVnU+33t6p9ZY6Ui3T1PjIBS1LxTBFbPd9rS6uGnFhKS+IRLS+pCFNmVZiLrMVsYX6r7AT876SVK1ntVgRVFUFJ14fybrA7KXkWeDM+jMqKiD0aCWddLp7+Tr758ESlSzPqJqFF9YkLnMh5Z3Aomo76kn35TPjJIZZMK4PFEFfdgpAs1S+UpFPaN4BnVldfzsnZ+xuyu9RdGrja+ypWMLa5qSWzK0+9ops5YlrWuwxS+jgdOaqCNRVRt26ogpvkT7Q1oeJ0JRh8JR3Bnagkai0ePmmUt/NVMeNZBWkZeIPIsRVRXjuewmfcwqMWiKWnrAmYjaoNdx44qJ2kQWRVH4xLIJSZ3NJK5YUKNNVRkpXDizklKHmftfrud/nttDJKomeeCKomgEnc1yMRv0/PETizAZdHzqr+/yh9cbaO7zJRF7eb449nanX8sImVCSHpiEeGMk6XOXCBsfh9FBl7+LDm8HFr2FPGMekwonccmkS5LebzEIK0YxCIsgVVEXmguBZKKOqlGeP/Q8gUh6wFOiL9CX0aOGOLFF1ShVpV7tNfl6k7uJiBrRSsHzzflpqrXV00qVPXuZvUwxlJkdB/oOYFAMjM0XFym9Ts8vz/klBeYCvvTql9ICpo/ufVR7XyLave2aWpfqfKhByZHEaUHUXV1d1NXVUVdXR2VlJWPGjKGuro5Lz1lOOBS7FTTqMeiUJPtDEnQoEs1YBDGaaHX6OdiVnonS7QlyqMtzXC4e8fS8zEQ9Z0wB8xOKVRIhrY5Wpz9h0KhBU9QdbvHjz1bKeyJhMui4acUEth7p5eG3G6kqsLBgXPK8RTkvMFPGh8SYQiu///hCOlwB7n1O9LZJPF8yt7zNGdByo7MRf6HNhNMf4lCs+16RQ3wvxuaNpdPXqRFLNosiTtRC3ad51NL6SCCyVxpf4Wuvf40XD72YcZ0H+w7iC/vSiFQScSKxNTpFWwabwaapefmcJMRMirrF09IvUTtMDspt5ZqSbuhtYHz+eIy6eFZSqbWUX6z8Ba2eVl449ELS/r/d+jYOo0Nr+Sohuw4CVNursegtg5qIM1oYfNeRUxglJSVa6fj3v/99HA4Hd9xxB3tbXdotrKIoOMyiw5uqqkRVCEejWIx6/KEIwUgUiy4zYY00VFXFFduPUCSKKWHWnyxCCYajo5ZcLyFzoDP1+gD6bR8qg4d9vhD22PvzzEbtjqUzpqjLsvQFPtH4/DmTuWnFBFRVZLik+tBSGY/NYn1InDGhmE3fuYBQJIpepyR57HGi9mt3GNnWV2QTdyjbj/aRbzGg14vzWJNXw+7u3RzoO6DdqmeCRR8jar0g+lTrI9+Uj0ExJClqqTZTW4VKPLbvMQw6A++f+P6k563GdKKWOdpWoxUFJek5SYgF5gLNLpFo8bRQV16X9bhAWBNyWwf6DjC1aGraMrNLZ2PSmWhxtyTvv2Lgk7M/ya83/5pmdzNj88cSjobp8ndp51Ov0zOxYOKQ87FHEqekom7p89EyiCbvPd4gBzrcaarU5/MxceJEAsEgekXB6XQyceJEzHr4xBWX8IUv3cb8+fO54rxl1O8Q5bg9fS5uuukm5s5fyLy6Op5++ukRPaYOV4BDnR5UVcUfjhLOEsj0hwV5BiOjO54e0KZyZ0rPGwiJBTG2mKJ2WAzaJPLO2MCB0rzBt5I83rCZDNjNhozBwgmltqTH/mAy6LCbDWldCMtjdxNtzgCHu70U2owZe0pDPFVxa1Mv40vsWnpbjUP0JWnobaDClr0hVbyhvzvpbwlFUSi0FGqNmQ47D2s5zpkyHvxhP0/vf5rzx51PqTU5ZS/R+pD+tfSQZdZH4nOSEFMVtSfkwRl09quoQQQMD/QdwB/2c8R1RLNDEqFTdFTaK2nxCKKORCM8vf9pzh13LmdUngHE7ZNufzdRNapdQEDYH9kyP/6w9Q985bWv9LuPx4oToqjXPLqPziPugRfMAm8wjIKSFMQqHevgrKuTr6QuXwh3QEzDNujjt4RWq5WVK1fy2kvPc+VHruCRRx7hiiuuoMgRa93ocrPmrXd48j8v8rUvfZZHXljL//zkxyw782xu/8Ev0Ye8fPiilZx//vnY7UPvfZwJLr/YV18oktRsPxCJIpOSVFUlEDp+vvlAHnV/SCRqmY6WbzFwNNb/otMdwJZSPn4q4fK6MSiKwrRYh7jhwG42kGc20BbzqFN7hiRCpioe6fYxd04hvrBQvjV5gqjDalizEDIh1aNOtT6ApKKXx/c9jl7RM69sXkZv9oVDL+AMOrl6Wno2huZBu5pYWrWUt1vf1kjZaogr6sPOwygolFhFrni+OT+p4KXVI6oXByLqSYWT8IV9vNXyFlE1qmV6pKLKXqURdau3FWfQyfLq5Uke9MqxK7UCmsQ7lEkFk/jPgf/gDXmTzp035OWhnQ/hCXno8nVpxzLSOOUUtaqqqCpEGdgz9veTtXHzzTfzr1UPo9MpPPTQQ9x0002YDDoUReHiyz9CMBxh4dIVuF0uPM4+Xv3vy/z8vp9y9UVn8ZHLLs7aDnW4kMTb5Q7i8ocwG0QALpGQQxFVq5IczdzuDQe7aerx4g1FMOqVYZVmJzZtktaJzK0GcQdxMvrTg0WB1cjHl44/5rTAigIL7S6/SN3LEkiE5Ib240riBSOSqIEkBZiKuPWRWVEDFJuL6fH3EIgEeGr/U5w77lyWVC2hyd2UVgjz6N5HmVgwkUUV6Z0l5LpVVMbkjaHEUpKsqI1xRV1iLdGGGBSYCvCGvYSi4jsiSbXKMYCijmVlyLFbmRQ1kKSoj7hEnvzYvLHkm/Ipt5ZrHrTMoEk8n9kyP1YfXK3lcMsBDKOBEyJnUpXvUNDnC2njgGZXF2hZG6lQVTUpayM1YWDZ8uU0NzXy1ptvEIlEmD17NgAGnUIgFMUfimpjgMxGPdGoyv1//Bs1kyajqqLXbqaG+sNBNOZFK4qiDT0ttptw+cNJRB2I2R56RRnVlMFb//YuyyaVUJFvGZaahuSJ2HZTYjBRWh/p5eOnIyryzRzt8dHc6+fyedkVdSJRjy+OE/VYRzwFrz+PWrM+DB70ilEjx6RtWIrY3b2bFw+9SG+gl6unXU1voJeoGuWw8zDTikUDzd1du9nWuY2vn/H1jBeqxItAlb2KMlsZu7pE35pEj7rb382M4njanVb0EnBSYi0ZvKKOEfOrR15Fp+iYUDAh43JVjio6vB2EoiGNqOWFLtHaSEx11LZRGM8umVU6CxAc8+jeR5lcOJlOXyfrmtdx6aRL+93X4eKUU9SJJbmhaHayCoajmjedySaIROGyj1zLZ26+Makpkl6n8NwzT+L0hdi28W0KCgooKS5i6fvO5f/+/HtKYreg6zaM3KDZUFjcH5TYTURVoZodZgMmgy5p32Ug0WExjJr14fSLDm9r93fiDoSz5lAPhERFnZj1IYO1gqhPXn/6eKEiz8KuFieRqJqxuZNEoT1+PseV2LTKvkp7JTpF/IwHZX3oPZh06WoaRIpet7+bR/c+yvj88SyuXKwpycSMh0f3PYpFb+EDtR/IuJ5Uopbpd5Cc9QHJqrXAJApnZGOmFk8LekWf5oGn7belkGJLMa6gixpHTVKDqERU2ipRUenwdtDkasKgM2i+/qSCSTT0NWhFODpFp+WWg1DeBp0h6Tzs6Nyh9SBZUrWE9c3rT9zMxJMNMmUMIBzJflL8SUo0ndSiqsqlH76Kvt4errvuOu15nU7BbLbwkYvO4vt3fpk///nPIhf2S3cQDoe48KwlfOS8Zfzo7u8Pab8bu7zsONrHjqN9aV3VpDousBqxmQwoioJdEnUkfsEJhCMYdGJEUCSqagHHkURLzEN2+sO8fbBr2B6yxajDELsjsZsF2edbjESiKn2+EJ3uYE5RI/p9hGLf4/486jyzQTufMpho0pkw6o1a+Xe/1odG1F7MusyjxiTZbenYwlVTr0Kn6BifPx69otcCbe6gm/8c+A8XT7w4a4P/RKKutFcmXUCsBqtmfaTuc6KiBuFRl9vKM6r/VEhfWirfTJDKvMXTwhHXEWocNehjmVy1hbX4wj5aPa10eDsosZQkbdegMzAhfwJ7e+KzUh/d96jWg2R59XI6fB2jlsJ3SkVyVFXFFxRNfrzBcFIVYSoCMmPBqE+yCb7//e8Dohf15nfe4vIPX0FhYaH2ugJcec113Pn9eynPM1NZYKXLHcBitfLDn/2aaZV5NPf66Yl11dMNwqP0hyL0+oLkWYyEIlGc/hDVxL+s8kJiMugYU2glEI6g1ymY9DoiUVULhvpDUcxGnZaWFxyFSRKJF5Ej3T5mVA2vtaMscOnxhjSyl32Vn9p8lG5PjqhBWB8S/SlqRVEotBlx+sKic17IpxFeqbU0KZ0sEzSPWlEx6zMraplLbdKZuLz2cvF/vYmxeWM1b/bZA8/iC/u0rnyZ0B9R2ww2SPjJJL4mM0Rk5sdAOdSJmFQwiXda39HuADKh0lGprbfJ1ZTk70v75EDfAa2sPRVnjTmLv+76K+3edsx6M88ffJ7Lai/DYXJofbLXNa8b9DSZoeCkUdRRVaXbE9BGN2VCKBIlHFW1iRGhfhR1IBzFqBfDUTPZBF/58m386t67+ca3vp32mmxCJAlRPjosQu06LAaiqqrlGQO4/aGsF45uTxBFUagpslJgNRIMJxfQBMNRdIqCQScyWWQFnjmBkIXnHsFi0GGKkXPicUWH0JJ19fYW+rzx6sY36zu1PF7Z7F72j87Ui3qwkPaHzKOuG1vIzKp8fv+68AJPxWCiJ+ThjaY3Rmx9MpfaZNBRkZd9qC6IopeaYit6nRhlJQmxxFqCw+jImMkhkUieUl2nQhL1RRMuotBSqD0/qWASDb3CFnh036PMKJ7BrJJZWbclrQ0FhQpbhWYvGHQGjHojRp1RK0hJtEWkQpfViS3uFirsg5uBKRV1towPENaHXO8R15GkEnv5vifqn2B/z/6k/ZK4cuqVRNQI/6r/F880PJPUg6TKUcWE/Amsa1mX9r6RwKB+hYqiHFIUZbuiKFsURRk5czYFrX0BOt3Zy1UlMTrMBnSK0u+tvz8UwWwQ6jNTZeFPf/5Lnn1zU9ocw9dee433rViKXlE0JSj7VMi+yI7Yrbw3dlGJRlUOdnrTWlbK13q8QQosRox6nUa+MjAI8eKV1MCMppzD4gIViaqYjfqk5yVc/jCN3d4B88td/hCfe3gTD64VCqnLHeDjD77NA2sEebb0+TDoFC6fL5rDH0v6nEzRkx61oih8bOl4bRr5qaion214ls//9/NaoOtYIRX1uGJb1sC4xNwxBSyZKNK/Eol6duls5pXN6/e9yY39MxP6lMIpOIwOPjrzo0nP1xbW0uhs5A/b/kB9Tz0fnfHRfrNdjHojBsVAqbUUk96kKf1Eb1peVLIp6qgapdXbf/l4IhaULyDPmKcNvs0Em9FGobmQ3d27cYfcSURdZCmitqCWlw6/RJu3jZkl6cVc4/LHsbx6OY/XP86qvauYWzo3qQfJ8url7OzcOeSWqoPBUH6F56iqekwjdvsb5KlTFIrsRjpdQULhKMYMVXe+UARFEdVdBr2SVVHLjI9iuynJJkisLJRv1WfYHYtRz6wxcf/NoNdpk7UB9DqhaqUPHghHUVFx+8Npx9jrCxGJqlrjfJkpEghHscZiacFIVFPJiUhUzgZdzMox6NDrFAy65ECjlt7nCWIx6inJQIJ93iC9saySNfUd3H7BVN7c34mqwt42MfapuddPZYGFlVPL+cPrB44ps0XmT0uPGuDyump+vHo37kCYspO42CUbZJ7xYedhKu2VAyw9MMpjKro/f1riF9fUaf9PJOovzv/igO/V6/ToMBIllFaVKDGpcBLrrluX9hudVDiJsBrmt1t+y/snvp8P1n5wwO1ZDVaNZKUPnaj4bQYbfYG+JI86zyRy0p0Bp9Z5b7BEPa14GuuuH1jNVtmreLdVaM1EogZ4/IOPa2mImVqqAlw99Wq+/NqXAfjhih8mvfbZeZ/lK4u+MihPfag4btaHxWKhq6ur36hosd2Eikp3rO9uKnzBCFajDp2iYNTptKyPdpefI93xYZmhSJSoqgo/N4NNAGgKezAecyaYjXrNBw9o1YJRLdvkQIebnUf7ONrr0yZ0gFDJCoqWwaGqatZycJ1O5DAHwlHcsSIYc4ItE0i4owhFhH2SZzHS3OvX9k0iHInQ0NRCtw9uOXMiW5v66POFeLNeXHtlh7ejvT6qC6wsGF+IzaRPItmhQlofiarcbjbw4fliSHCZo/9b/eOB3275Ld9Z+51BLy8zEmR617GiPN+MovTvT2dCIlEPFgZFXBj7e18mIZXYie7u5XcPKnfcZrRpFzKpmhO3K/+f6KsbdAYcRgfOoDOeQz1Ioh4sKuwV9ARixUKO5GnzBp0Bh8mRlaQBzh57NuXWcvJN+dpUGolCS2HWjJNjxWCpXwVeVBRFBf6gquofUxdQFOVW4FaAcePGpa2gpqaGpqYmOjo60l5LRJ87QGeTSle+OekLoarittxm0hPqMtHtCRKKRAl2iikZkaiKO9Ye0h+K0OkOEu0xY9AptPX5CXQYtQ55INLQnL4wBqdlWEULfbGqx1CXFZc/pJVGBzqFxdHhCmA16tDrdFhNevb0JLSldPrp0yn0OMxEoiotfX58NiN95vSPo8MVoCWqEo2qWIx69rvEj63bEyQYFscPolAmHI0StZtocwYIdBo1ywGEgt94xEXthHFMslp44M2DrG/oZE2MqJt6fHiDYZp7fSwaX4TZoOdX186nqmD4ZJqfYn1I3Hb+FCaXOxhbPDSiGWm4gi7+b+f/oaBwz/J7BvU9kBkJI0XUZoOe+6+pS2v6NBB8YZ/mKQ8WRp2ZYMSDwzi0atppxdP42qKvcfHEiwd9cfjO0u9oRF1oLsSgMyRbHwYbBsWQdgz5JtFBTxL1SNy1JCKR+BODiYOFQWfg3rPuJRgNZvX6RwODJeozVVU9qihKOfCSoih7VFVNiqjEyPuPAIsWLUqTzUajkYkTJ6Y+nYYXd7Zy69828vuPLUya5nGgw83Nf32dn35kLstmjOUHz+7inxsa2XjXBVz6veeJqrDpOxdQbDfxxzca+PHqw2z57gUUWI1c870XuGrRWL7/wbif9OPVu/nr+qPs+cH7M+3GgFj1TiNff3o7b3ztHP73ud3sbXURjqpMrXBgNxt4ZU8Hb3/rvIwe7/1/e5f97W7++9WVvHOom0/9bT1/uekMzpiWHsB44NGtPLHpKFMrHDz5uRWanXD/y/v41X/r2fODizEb9Fz+27XkWww8dOM8rvzuC9x05gS++f748f5rcxM/euMQLy+azfgSG3aTngfXHqLV6WfltDJe29vBvjY3rX1+rR/yBTMzB3L29+wnSjRj85tESI86talTqcPMDcsn9PveY8WW9i2UWkv7/TE+0/CMVjjS5m0bFClIRT3UiSH94fK6MUN+jy/so9pQPfCCCTAogljspqFdIHWKjk/M+sSQ3nP22LOT3l9mLUu2Pow2Sm2lWg64RIG5AGfQGS92GaAqcajQ7Bhr+bCJdnHV4pHcpUFhUNaHqqpHY4/twL+AUdvTc6eXU1Vg4eG3Dyc9v/2o+IHMHSu84op8M95ghLcPdiHjhLJicX+7m1KHWRuxNa7Err0m4fKHcZgzN8AZDCbH5vrVt7uob3czudzBmVNKWdfQxXPbW/nIgpqsgbgp5Xkc6vISDEe1/sLjs5QPLxxfRFmemQc+cYZG0iD6FqtqfLJ1c6+PMYVi2sikMjv725J7qcjJ1WOLrRj1OpbVlrLhoPBbb1ohLqDrGjoJR9WMjesT8d113+UH638w0CliRlU+UyscxzwdfDj46utf5dtvpmf0SMiqMntMXQ42/3WkFfVwMRzrw24UxFRoyX5rP1qYVzaPKYVTtL+nFE3JGADNN+XT7GnmsX2PUWGrIM84/F4qmSCJejhq+kRiwF+Qoih2RVHy5P+BC4Edo7VDBr2Oa88Yx5r6Tq33LsC2pj4sRh2Ty8SXTKY1vby7TVtGTr+ob3drk6xBBGoaEzxsEAMCEhsHDRVyrt/uFieHOj1MqXDwvimleIOiJepHl6TbPxJTKhxEoiqHujw0dnm0yd2ZcP2Scbz1zfPSPEy5/f3tbgLhCB2uAFWx8U+Tyx3UtycTdWOXl6p8i9aM/6zYxJJJpXaW15Zg1Cu8vlfYUtn2BSAYCbK7e3faQNFMuHbxOF68/ewBlxtpRKIROn2dbGrfxP6ezC06N7VvoqGvgVvn3goMnqgTFfVoVaENBsMh6lKH+M7kmUemkdhQ8LOzf8Y3l3xT+/sbi7/BfWffl7Zcvjmf+p56jrqP8tP3/XTERqxJyLum1EDiyY7BSJ0K4E1FUbYCG4D/qKr6/Gju1LWLx6LXKfxzQ7zp0bamXmZVF2gFHjJa/vKudm346eFYo/39bW6mVCQQdYmNhg4Pc77/Ahff/waBcAS3P5SkUIeKAquR8jwzL+1uJxxVxay92lJ0iijsmNJPVzVJsvVtbjYf6aW60Npvb2l9hrSt2jIHiiIuSq19IlItB6pOLndwpMebPAG725tE9pKoz5pSilGvY0KJnY2HRZClKsOwVon6nnqtX++JJKpUfO7lz/H8QfG1lP0pQPQczoQn658kz5jHtdOupdhSPOjpHc6AEwUFV8h1Qmfo+cK+rNkb2WCNFboMleCPJ2Qu9beXfJsFFQtGfP1SUb/niFpV1QOqqs6L/ZulquqPRnunKvItXDCjgkffPYI/FCESVdlx1MmchJQ5mX/a6vSzcHwRFflmDnd5aXMGcAXCSYr6+iXjuOXMiSyZWMyeVhcHOz24A+FjImoQylgOL51SnkeB1cgvr6njnsuzFwNAnGTve3Eva+o7M053HghWk56aIiv17W6tSEUq4SnleagqNHTEVfXhLm/SGKiJpXZ+/OE53Hp2rXYs4ZiH1J/1sbNrJwCBSAB3aPitakcSvrCPNUfXaN3LOn0iQFpgLuDfDf/GG/KmvWdj20aWVi/FZrRpBR0DQVVVnEEnEwuEVXSi7I9INEIgEhgy4UpPdqgEfzxx3fTr+MGKHyQN5h1JVNgr+N6y73HFlCtGZf2jhZOmMjEVH1s6nh5viOd2tNDQ4cYXijC3JpGo46pvzphCxhfbaez2UN8u8oGlhwzC/73rspl89UJR3FLf5hYe9TFYHyAIEUBRBPmCCAxNr+y/7Npi1DO2yMbBTg+Xzq3iM2dn708w0Pbr21w090pFHSPqirgtAqJ/d6c7kOSDK4rC9UvGaeQuz1ee2UC+Jdm739m1k0N9h7T/S3T5ujLuV5unTctVHQoi0Qj/PfzfISt1uR/Sjunyi79vnHUj7pCb5w8l3wD2+Hs46j7K7FLRMTGxIU9/8IV9hKIhrSovkahD0RAvHHpBU/KjCX9EfN7DJerEXhsnG6YWTeVDkz80qtu4cuqV/TawOhlx0hL18toSppQ7uHf1Hl7aJXzouTWF2uuy6TqIAOO4EuFDS3KaXJ4eMJlYakcXsws8wbD2/uFCbqOmyDrkLnNLJhYzr6aAn105d9g+3JRyBwc6PVoOeWUslW5CiR29TtHOhfTns03MluuCzGr67nV3c8frd6CqKjs7d2oEIQkxFfe8dQ+3vXrbkI9nfct6vvzal9nSsWVI75P70eETHrsk7vPHnc+E/Alan2IJ2XJzdkmMqAsn4Qq6NCWeDbIHhaxaa3LHMz8e2/sYd7x+B28efXNI+z4cyEyVIRO1/uRX1DlkxklL1Dqdwv9ePx93IMzPXtiL3aRnUmlyEEROcZ4zpoDxxTbanAG2H+2j0GbM2ELTYtQzrtjG/nYX7hFQ1JKoZYBzKPjplXN58nMrjqlEu7bcQTAc5e2DXZQ6zFoVocmgY0KJTbu7iGeWZP+BTtaIOt2f9oa97O3Zy4bWDezv3c+SyiVAZkXd7G5mTdManEFn0rDQwUCmvA1EmKlIVdSyerDEWsL88vns6tqVpJblXYEs/5V9HgaaiSc96XJbOWXWMk1RywwSEE15Rhu+UIyoh6iMTwXrI4fMOGmJGmB6ZT6/uLoOgFlj0ocEVBZYGFNopdRh1gJlr+3tYEq5I6tKnVyeR32be2Q86hi59Rc4zAZFUTIGCYez/Y2HexiTQrBTyvO0zA+ZwtefopZ3G5kUdTAiKkXvffteImqEs2rOAuJK9qEdD/HZlz9LIBLg8X2Po8am73jCImvnjaY3uPmFmwckbpk7K+f2DRZyP7r93YSiIbp8XZh0JhxGB7NKZtHt79YKKED0EZ6QP0ErWZaVd9lm4klIRV1gLqAmr0YjaplBYtFbBiRqd9DNdc9ed0zTQGQv6qEqarn8yWx95JAZJzVRA1w8u5LfXD+fr188Le21r1wwlR9fMQeIk1C3J5jkT6diSoWwC0IR9ZgVdYnDzE8/MpdPLBt6MHAkIFVwKJKe+zy53MHhLi+BcITD3R7yLQatK18mWIx67r92Pp88M70oSY5GkorzrDFnoVN0mvJ9vel13jz6Jt9f932erH9S63XgDooLxeb2zWxo3TCgUpZkOtRsisT1dvm66PR1UmItQVEUbRpHore+s2tnUtOdUmspeaa8ATM/ZA51vimfsXljNaJetXcVecY8bp5zMwf7DvbbsOnZA8+yo2sHbzUPn6iHbX3kFPUpi5OeqAEum1vNwvHFac8vHF/M2VNFUCAxUDYlgz+d+Foklt1wrB41wNVnjKWm6MR88fMsRq3EO5WotVztTi+N3b6sBTWJ+OC8ai0omohQNKTNxiu1llJpr6TQXKhZDkdcR8gz5vHsgWfp8ndpvYxdQVfSY6u3/45zmqL29yY9H1WjvHT4paTsjXVH12kKN9GCafe20+Xv0qaCTC2aikFnYGenIOoObwft3nYtkAji7mYwmR+pirrd287/7fw/Xjr8Eh+c/EHOHXcuAOub12d8v6qqrNq7Cji2jJFj9ahP5vS8HDLjlCDqwaDIZtSIN1MgUWJKgto+VkV9MmByliDg3JpCFAV+/d96Dnd5htz0JxHBSJCZJTNZMWYFy6uXoyhicnSXvwt/2E+7t52Pz/w4l026jBnFM7hw/IUAWvqeVKKJ9kMmyNdTrY/fbfkdX3ntKzzT8Awgsko+/fKnNV+429+tlSK3e9vFNGiLaAdq0puYWjRVU9TyMbWf8vj88TQ6+x9WLIk635TP3NK5ANz37n0oKFwz7RqmFE6h1Fqa1f7Y0rGF/b37MegMJ4SoJxVMotxaTqG5cNjbzuHE4NRnqhhEqbiNnc3OpGKXVNSWx5XlsZSQnyyYXO5gTX0n1SnNkyaW2vn6xdP5yXN7ALh0zvB7JoSiIUx6E78773caIZZYSuj2ddPsbgZgbP5YPlv3WaJqVFOv0vpwhmKjldzZFXUkGtGCgYnWxwuHXuAP2/4AwI6uHVzDNezoEoWxkli7fF1MyJ8gpnPEFHWiYp5VMovnDz0vsla6dqJTdEwvnp60/RJrCd2B7n5b8fYF+tAreuxGOyvGrOCt698iHA1j0ps00lxevZw3mt4gqkbT+lis2rsKu9HO+ePO55XGV/rdVn8YLlGfM+4czhl3zpC3l8OJx3tGUYPIanCYDdp0kkywmQxa7rAWTGzbBb8/EzzH1G77hEDeIWQKAn76fZP4UJ1o3NNfILE/qKpKOBrGqDMmEU+ptZROX6emDGWll07RaW0iXaFk66M/Rd3h6yCiimCjVNRdvi6+s/Y7zCubx5LKJezoFAQtLwRy252+TiYXTsagGGj1ttLt704aTDqrZBauoItDzkOsa17HpIJJadNQis3FhKNhPKHknjCJcAad5JvyNXK1G+0UmAuSCHNp1VJ6A73s7t6d9t4XD73IByZ9gKlFU4+psnG4RJ3DqYv3FFF//pzJ3HfVwHnJUnFrvT72PQet2+HIhtHexRHHB+ZVcdelM5KqNiUUReEnH5nLN94/PakT4VAgA4lydJJEiUVYH6lEDfEG8FJRD4aopT9tN9o1om7obcAX9vGF+V+grryOA30H8Ia8Wh603HaXv4syWxmltlLqe+qJqlFKrCXaumVA8etvfJ1tHdv46IzkCSYQH0PV4+/Juo99gT5tAGs2LKsWs/NSfeodnTsIRUOcO+5c7Vwl5mEPBTmiPv3wniLqWdUFXDx74Ft8GWzU+iQ3bxaPHXtGa9dGDXkWI7ecNSnrGCeLUc9nzq7tN+OjP0iiNumT319iLSEQCbCnew92o12bhA3gMIrzKz1qLZjYTzaEJPFpRdM0pdnmFYVOFbYKZpXMIqpG2dO9R/OZ273t9AX68IQ8lFhKKLeWs6d7j7Z/ErWFtZj1ZnZ37+aqqVdlLE+WRN0d6M66j86gkwJT5snbEqXWUqYVTUsjanlxmVkyU+vcNlifenvHdm24LMSJOpe9cfrgPUXUg8Wy2hKKbKKpEgDNW8Rjx96s7zldEYoIok4dLySJcEvHFmocNUl3MWa9GYPOkJb10Z+ilq/NKJlBX7CPqBrVKg3LbeWaKn7p8Ev0BnpZUL4AFZXtndu1/SmzlWmpeqWWUm3dRp2RxZWLWVK5hG8u/iaZIC80/SlqZ8BJnnngnPll1cvY1L4pKUtlZ+dOxuWN0zJGYHBEvb1jOzc+fyP3b7xfe84X9mFQxKDYHE4PnJZEfe70CjZ95wKhqN0d0Bf7wXTmiDoVwagodkm1PiQRHnYeTutEpigKecY8PCEPgUiAQCSgWRpSDaaixd1CnimPKnsVUTWKK+iiw9uB3WjHbrRTbiun3FrO0w1PA2hjkLa0bwGEFZM41ilRUQP85rzf8McL/5iV3AZlfQT7BlTUIIg6HA3zblu838mOrh1aponVYE2qbMyGdm87t716G8FoMCkTZjgtTnM4tXFaEjUkzIaTtkflHOjYB9HRb6ozKKz9Ffx9dDqIDQX9WR8SmVpGOkwOXEGXpqZl0/hE+2NX1y6ufuZqOn2dtHrExGmZOtYX6KPd255EvjNLZ+IKujDqjFrOsuwLUmotpcIen0iTStQ6RZeWhZEIGXyU5eeZIIOJA2FB+QLMerNmf8jjk3cFQFLBjMRnXvoMZz5ypvbv0icvxR1yM6VoihaYhRxRn444bYlaQ/NmQIE5V0PIA86RG7E0bOx6Gl76Lux/GYbYL2OkIa2PtGBiAhFmmpbhMDpwh9waUcuxXYn2x8a2jezu3s0T+56g1ZtM1L2BXjp8HUlTqqUinVo0lQpbBTaDje0dCdZHjNSNOuOQJ4NYDVbMenNWRR1VozgDzgGDiSAqABeUL9CIWvrTibnbNXk1SeO8wtEw65rXMT5/PJdMvIRLJl7Ch6d8mN+f/3tmlczSctFB9PrIlYGfXnjP5FEPG82boXQq1IjKOzr2QmH26SyjjtYd8K/PgM4I0RD4esFeMuDbRgvZrI9CcyEKCipqRkWdZ8rDHXRrRSJTitIVtSTtx+sfxxPyMK9sntY4vjfQS7u3nbryOm15SXSzSmahKApj88ayt0fYVcWWYq11pSwfHwoURaHIUqRNqE6FO+RGRR2U9QEin/rnG39Om6eNnV07UVC0JlAgiPqZhmcIRALaBUJF5fLay7l62tVJ63q58WXtggc5RX06YtCKWlEUvaIomxVFeXY0d+i4QlWheRNUz4eyWAHEiQ4ovv170Bng/O+Jv33Zb8WPB7JZHwZdfIJ0RuvD6MAVilsftYW1KChJirrV04qCQqunFVfQpZWmg7A+OrwdlFvjinpu2VzyTHmsGLMiabt5pjxMepO2rKxKHCqKzEVZFbXMRBmMogZ4X837UFD42bs/Y0fnDiYVTNLmM8p9V1E56joKxPuVZNr3PFMe3rCXcFRMuveEPbmMj9MMQ7E+bgN2D7jUqQRXC7jbYMwCsBWDvezEp+j1NkLZNCiLqS/vCSbqLNYHCOVqUAwZp3c7TA7cwbj1UWIRWRkt7jhRt7hbOKPyDM2ySLQ+DjsPE4wGkxq8F5gLWHfdOs2flpaL7Oshl5V/DxXFluKsRK31+Rikop5UOInbFtzGC4deYE3TmiR/GuIXmcRccEj31gHNF5d56b2BXu3OI4fTA4MiakVRaoBLgQdGd3eOM2RaXlWdeCydduIVdV8TFNSALZaXfJIo6kxEXWoppcpRlZa6B3HrQxK1zOhItT7G5o3VxiJV2avIM+WhoLCvZx9Av5M4JNlJFZpvyseit2Qku8GgP+tD65w3SEUN8MnZn+SSiZegoiZ16wOocSSn6MnGUtkUNcTTHPv8fbl+HacZButR3w/cCWSN0CiKcitwK8C4cSfQ4x0KnOK2k+JYa8+yabD9cWGJjPD040FBVQVRT78ErLES6JNEUadaHwCfrfuspvJSIYOJ0jLIM+VRaa/UClKCkSBd/i4q7ZVcP+N6rAYrc8vmotfptUnUIIpdskEqaknMiqLwgxU/YHLh5GEda6G5MGvWh5w+PpisDwlFUbh7+d1MKZrCJRMvSXqt2FKM1WDVrKD+FLUMjDpDTlRVpTfQmyPq0wwDKmpFUS4D2lVV3djfcqqq/lFV1UWqqi4qKxvleWQde0dG+creHpIUy6ZDoA9c/bfjHDV4OiESgIKxwoqBk1pRzy+frw0RSEWeKQ8VlTZvG0adEbPeTJW9ihZ3C6qq0uYRVYdV9iryTfncPOdmTZkXmgu18urE9LxUpCpqgIsnXszkouERdbGlGF/Yhz/sT3tNKuqhWg4Wg4Vb5tyi+fkSiqJQaa/UiLrT14nVYE3rQQJxFe8KuvCFfQSjwZz1cZphMNbHCuCDiqIcAh4BzlUU5e+julcD4fFPwlOfO/b1eDvBWgT62I1FeSyg2LYz+3tGE7LwpqAGzPkiqHiCFbXM+shkb/QHWUbe7G4WdoaiMMYxhmA0SKunVSOoTP52Ign1Z31U2auotFemdcIbLvoretnbvRez3jyiSrbSVqlZQYmtWVORaH3IO5Scoj69MCBRq6r6TVVVa1RVnQBcC7yiqurHRn3PssHVCm07oH33sReneDrBlhB4qhQ9hmnZfGzrHS6kFZM/Rlgv1qITr6j7sT76g+yg1+Jp0ewCmZ62q2uXRtRV9vTeLLKcu8BcgFlvzroNg87AS1e+xIenfHhI+5YN2fp9eEIenj3wLBdNuGjI56E/VDmqkqyPbN66PH+uoEurUMwR9emFU6/g5cBr4jHkiRPbcOHtAlvCj8NaCCWT40FGVyv8qg5+Ogl+PgOa+nV/jh19sQKIgli6m7V45BV10At/vggOrRV/q6qogNzzn4yL92d99Afpq0pFDaLhkkExsLNrp0ZQidWEElJR92d7jAZkdWKPv4d/N/ybG5+/EWfQyX8O/Adv2JuW33ysqLRX0unrFH79IBW1JOqTzvp45KOw81/Hb3ut2+FP50HANfCy7wEMiahVVX1NVdXLRmtnBoWGV+L/P1af2tMJ9pRUrur58bLyvc9Bz0GY+n5wt0L9C8e2vYHQ1wQGa9yfthWDL3vviWHh0Jtw5C3xCODvhf0vwb7nMy6ereBlINhNImfYG/ZqRGMxWJhcNJmdXTtp9bRSYinJqJilWkysSjweSGzM9GT9k2xs28idb9zJo3sfZXrxdG2qy0hB3k20edro8nVlTSu0GWzoFB19gb6T0/oIemHPs3BwzfHb5uH1cPRd6Op/fNp7BaeWolZVaHgVakUe7YA5z+4O8YFmg7czWVGDIGrnUXC1wYFXhQ1x+W9EoLE5wRKpf2nk1W7fEeFPy4yT0VDUB14Vj65YPrMMnHbH22jStBGcYnLLcK2PxBJuSdQgqgp3du2k2d2c0faAOAkdb0UtrY+j7qNs7djK5MLJrD26lr09e7lq6lXDmsbSH+TxH3EfoTfQm9X6UBSFPFNesvVhKRzRfTkmyMk9Iy0q+oO3M/nxPY5Ti6jbdoKnHWZ/ZHDFKWvvh/+7TJRhpyIaFSSYpqgXiMej7wqbpfYcQZzVC+DoJnGx6D4AD18J/7wWwoEROLAYZA61hG0UPGp5RyIJWhJ2z2HxqKrw9w/Dy3cDw7c+pEcNyUQ9s2QmfYE+tnVuyxhIhPht/fFW1PmmfAyKgZcOv0Q4Gubri7/Ox2d+nCp7FZdOunTEtyeJelfXLlTUfisq84x5uEIJ1scgC2+OC+R3KWUo8ahCZmx5uvpf7j2CU4uopRqcdI5QuANZH137IRqGQxluyfy9oEaSg4kguugpOnj3QfD3xdV7dZ24evc1xcnuyNvwn68KchsJpBK1VNQjtv6j8YtbqqJ2NkE4KJS0vw+OCj9eI+oh9j6WWR+QTNRylqEn5MlK1CfK+lAUhUJLIft69mHRW5hfPp87z7iT1VesTir/HilIf16OFuuvUEcq6r5AH3aj/eTqRS2/SzlFPWo4tYi64VVRPVgwRjRS6tzbP4nJ2/mGV9Nfk1fkVEVtdoht7H8ZUGDiSvG8VNrNm8X6CsbBWXfA5r+JIpljRTggytmTFHWxyKtOaEB/TJAXujEL0xW1GhXl65LIu+rB39dvCXl/sBqs6BU9kFwkMqVwiraubNaHtCD6S80bLciLxMLKhZp/PtTUxMHCrDdTYinRhvX2R9T5pnzN+hhxf7qrAf54Drjbh/d+pyTq3hHbpQEhlfQpOOd0ODi1iLp1O4w9Q/y/bLpQfu62zMtGo9BzSPw/MQAp4Y190KkeNQifGqBqXrxzXcUskdfc9A4cfANqV8I53xad9nY+OdwjiiPmCacpahg5n7rhVbCXQ+15wkKKhOM/MhCB08S7lJathKIhDIqh317OmaAoimZ/JBK1UW9kWtE0QKSnZUJdeR23LbiNFdUrhrTNkYDM/Fhetfy4bK/SHs+lTpxKk4pEj3rEMz6a3hXNyQ6+Mbz3y4v98bQ+NEWdsz6OLyJh2PwwNL6d+XVvtyCXUvEjpyz2mM2ndrUINVo2XRBQYrAM4h90qqIG0aQJ4rYHgNEiyHrLwxBwitd0OkF6B9dATHlmRcu2/iPUWmpeiqKGZJ864M584ZGIhESqXWof62hUKOracyG/SihoT7s4T/KC0H1QnE9ZHde8mWAkOOzbbGl/JFofEB82m01RG3VGbplzCxZD9mnyowWp5uWQ2tFG4jkYyPpwBp30BUahz4f8fiUGy4cCeXfm6z1+gzc8OaI+MdDp4flvwPbHMr8ulZ5sRzpQW1Kpphd9UjweSLE/5Aed6lEDTHwf6M0w4wPJz1fPj30xFJh4tniu9hwIuoQqyYbmLfDnC+HPF8SDdqlIzaGGzIr6rd/B3z6ceT2qCqvvgEeuh8aUbJfWbWLfa8+BvBg5uFrEj6xqriDnnoPQuU80qSocB82bCUVDQ7Y9JCRBpxL1iuoVOIwOxuWffD1hphZNpbagdtj9QoYK6dNnKx+XGFVFLb9fRzcN7/1aywVViJjRRjQav7jkrI/jDEURKjmbQpbPSyXtKAdLQfble2IKesoFkF+T7lNLRZ3J+iibBt9uiStrCWmJVM+Pq92J7xPBx9QLgYS7XRQD2IpFYPOR64UqToUk6vzq+HOZFPX+/4rH5gw/qncegI1/Ef/3dCS/pgViV0JeLIjnahX/8qqhaIJQ1O27xfFXLzhmos6mqM8Zdw5rr1s7pAZHxwu3zr2VJz74xIin4mWDVNTScsmGPFMevrCPLl/X6Cnqlq3DmyjkagFi5+t4BBR9PeKOEHLBxBOC/tqMdu4Tqk8qTkURqnrz3+FnU+Cpzycv330QFL1YvnYlHHw9+Uvo6QKTQ1gamaDTpz9XncESsRaJ5xteEVVSf71c7JPE058XSva6f8KVD0L7Lnju6+nr7j0s1H3iiKVURe3vEx45pN+mtsXWWxPz8FMDOw2vQMVsQdJSUTubRQ5sXiUUTRQpif5ecV6r50PPIYJB1/CtD1NmogaG7HkfT+gzffbZ0LYrFojrGHjZDJA+/UA9tOU59Ia9I0/U8vsV8kBn/dDeq6riYl80Xvx9PHxqaXdYCgdW1L4e+NO58Wrj0cDbfxS/81HEyfVrKZsmfNNMwbOOPSLTQ5ewyyu/CXUfFUSz81/J/ljPQeH36o0wfoUgua798dczFbsMhIrZcMEPYPGtyc/XnivS2R69QeRe74gFF8MBoeQX3yICk5PPF+/d9kh6hP3I2yIFMBFW2ZM6plIOvSlSCg3WdKJueEW8dsUfk98DonKs8S2hpkHkoCs60TMlGhbEXTwxrsLLpmp3DyF3Bybd8PpbyKKXk1E5jxj2/kfc3QyzalUq6oGm0iSewxG3PnzdgvQg851afwi4BMGXx/ptH4/MD6miy6aLC0N/8aHGt8Rvc9ujo7c/W/8JWx+BkG/UNnGSEXXMd+7cl/5ax9746xK158AH7odFN6UPpu0+GO8zLS2LRHLLVD4+EHQ6WPElyEvpT1F7rrgVa/ivIL3mzUJptO0Ucw/HLIove8Ytghw3/y3+XO8RccyJSh3AYAJTXvzC1fAKGO0w50qhEBIvTM2bhcVTNFH464nK5vA6iATj69fpwVERPx95lcL6kCibLi4sQMjbOXTrw90OTRv7VdTvGUil1l+Atx9Ij3qgYQeJRK0p6p5DQtEfK7zdYmaoyTH0gKL0p+Vvc6jWR/dBLWd/0JAqWtqg/WVFyeMZ5ucj1rEleyJAOBgXPKPYdfMkI+osmRx+pyjrLpua5X0ZAos9BwVpgVDiRntysMTbmTmQOBzULBIEveAGeN8dQqH0Nsa/JPJCAVA6BSacBe/+JW7FSP84laghuTqx4RWYcCaMXSKCNt0H4ss1bxaKXFFEc6nEH0zDK4K8xyeknOVVxr9Y+dXxi5o5XxyLtRAq5xDqOciQjY/X7oW/f5jaglrGOMb02wHvlIf8jA+8NqyMh2JLMVX2qgFbtSZe7DSi/s8douXvscLXK34LVfOGQdSxtFKpqIdqfbz0HXjw/f0H41ORqKgT/84EeTwdu+MpsENB8xZ48OLs1kb7LiGCYPjB2EHg5CLqgrHCh071qaVvlqqoJVKJ2tcriEqSj06f/iX0dA1dUWeD3gi3bYMP/Cq5MKZ5k/CZU6ean3Ez9DXGA4MNrwpyzHR8sjqx55Ag5tpz0+8QfL3Q3RB/3lqUfAva8AqMX5bsf+dVCxUAcY8axMVSBtIu/x0hNYypp3FopfJtu8DfxzWTLuO5K54b/PtONbjahIComid809ZtQ16FTtHxwkdeGLAzX0aibt8lPvfhBAAT4esWgevq+aJWYaBU00RIRV0+TEXduV+k0T7y0eSc/v4gi12kcMvmU6uqIE/Zvlh23hws3O0i+B/2wZENQjCmQlpFevPw0xsHgZOLqHU6oTilov7XZ+C1/0nI+MhC1KmDaWVqniQfiH0Jt4l8bVUdnkfdHwwmQXAVs0BnjBH1FrHd1AyC6ZcJ62Htr8SP4sCroiw+U6aBrViQgPS9a88V58FgiX8xWrbEjxGE3yiVjatNqIlJ5ySvV2Z+gNiXgrEi+Crz1AGq5hIqm4Yh6IL7pop//7mj/2pQVY1/Du7245Y9cdzbbEL8/J/5FfE4zNvrwZyjRKIuMBfE7zIjwXjByXAQDkLQLQRB9XwI+0Xmz0DveehS2PdifNtFE8V3MtWjfu7rsP63mdejquK3OvkCsQ//ujXzcqnwdsbu/GIZUtlyqfuaxLLzPy4KvYb6+Tz9BSGSLvqxiP9kakXRvFkIo0lnn0ZEDfEeHkc3CZP+tR8LQtOboXD8wO+DeGpeou8qv4Qde0QAJBIcOUWdCINZkPXhdeILn5riB0KBn/MtOPwmrPqYUCGZbA8QP6DOffDqj2DKheJCpjcIlSC/GKkWS6L1Ic9Fxezk9crMD3uZ2B+DCT74v7As+RYvaCnAWDoDZn1IeO3v/Ane/EX243e3xy8Swy1JHir8TtFmcyRK+YeC5s0iKDv5fHF+j8UHHQBpHnViHCe1mGsokLaarSj+HRmIqNt3iu/u6/8jFLU5X7ResBSmK+pd/4Yt/8i8HlerUKtTL4KlnxXB8qBn4H32xESW/P1mI2r5uxizUMSzhmJPRSMiU2zhDSKuZLRnbkXRvFn87qoXiJYWmVJvRwAnH1GXThVKYe2vhA0y4SxxAiRBZUNZLLVPVeNf3OIURQ3iVkXLoR4FogZBzk0bxFU40Z9OxMIbYeFN8T7QMiMjFbZioTaKJsIVf4qr7ur58bzX5s3ioiTzrq1F4BN9izWydKT0zZCKOlFZz/8oVCRPyw5FQ5gKaoStc+3DMPtK+O8PYG/m/tV0JthWnmMkalWFA69DKH2GYRLkAIlRVDQZ0bxZ3IGYHYIIjrw9OKIZBmTvFINiEA2iUuMxw4UMxFmLoXiSaJPQubf/98jzfPRd0RNHfoeshcketbxzbd8tMo9SIe98iycKEaBGRQXvgPscI2qZvprN+mjeLI6nYpa4o/R0QNv2+OsNr4jma9q/h+JWTm+jEHblM4X4mrAi/UIc8gmbr3q++KdGh2V/DQaDGW5rURRlg6IoWxVF2akoyt2jsicS0t7Y9ZTIbrj6r1AyBcYu7v99pdPig2kb3xJ9pM0J2QbFk8BcID48+eUcDUUNyeScjagB3v9TcSEatyydSCVKp4ov5HX/FD8EifHLRabLul/D0c3J20lUNpIsHSmZKlJRy8csSCp4URShuksmw5qfZ35DIoEcq6Le+xz89YPw1Gf7t1tksZDsI348oKpxNQXic4wEhcc7CpA9qQvMBcIq6dgDepMgohFR1MXirqq4duCulM2bxW/JYBUprxpRp8RG5J2rGhGZEanQ7nwnxlNTB3OxlfElvUFsM1swsXmzIFqjJdbywQgvfU/Yn1v+KSp8n7094d+XxZ0rxO9YJB/VniviAYkVwa07YmJsQebMshHEYBR1ADhXVdV5QB1wsaIoS0dlbyDZh170SfEF+uw6uCQLMWjvi3mr+1+G+hdh3nXJr+t0UB0LKPZXPj4SkB+ao6J/IjSY4BNPww3PZl9m8afgq7E7ikTMvBxmXSH6Rvc1JhO1tUiUtUdCsUIMJf1YMynqDEjr9WGyiaKabGPQOvaIlEJIr44cKt79s/hx7Xwy+4UB4kQNcb9+tOFsFhdBaW3JQqzhZBYMEnmmvHggsWOvuIgXjB05RQ0iQDdQn/fmzVCzUPSFh/h33FKYTNSJBJopI6L7oLCOCsbGCrGqB0d0iRlbttLMilpeSOXnk1cBl/5cxIMevxGeuU1cXL+yW/y+vrpXtIWQ+6nFxWIBS2lNJlYgJ1qOeRVCHJ4oolYFpPFijP3rR94cI4omCKWQeJUymJILXTJBEvwrPxSPC29IX6Z6vgjwyaCFtApGGjLYlymQmAqdvn9LB8Txp0JR4PLfiv7ZkELUheLR3yfIxFacvo0hKOq0gpe8SnHnksnv69gL5TPEDz9bZ0OJtl0i9SnT3LvugyIr5qyvwpyrxOfa+Fbm9fQ1iUAoSv8/lGhUKKf/3hN/bu2v4YlbhpbpAPFovzzviWX5IFTfn85Lz78N+UUgTo5Cy4RHb4DXf5b2dL4pPz7ZpWOPECfFE+MWwjt/hoevitsM7/wZfjET7psm5mRmyg5JVNQgvrvdB0SWj6dTHEN7AnGHfMLKqJ4PZ3wy+ditRcnWR2J+c6bPRRalye/3mAXx5baugr9/JL7P9S+JNL6gN1YDEUsEsJdm9qh7Dop9SfxdLLwBFn8adj8j9vnqv4rU1LxK8W/s4rhN07EXHJXxorPSqYKIG1KI2l4eb/tQPX/UUvQG1WhXURQ9sBGYDPxWVdW0FneKotwK3AowbtwxNNvRG+Cy+8WPfShwlIsrursVpl6cnhIHwhcOuGPVeClFHiMJvTFmEdSOzvolTDa4fhVs+quwTyS0isZeYT/YMzTgt5fAJfeJAGU/CEVD6SXkeVXils/bKc57Ijr2iOBQwDmw9dG4TjSPat8Tb18rsfEvQm0tvEH0dNn9jMjqGJfhZq6vSfyITLb+ifq1e4UXqTOIH6zJJgJiQbfYxqUD3LUl4uAbIoYiL5TWIhHwllkQzZuFh9vwSvL3oHWbCMTtelrkxKcdy1Fh++16Snw/516lvfSF+V8QNlTQKzzUuo+Ki6Ekh40PCevlmS/B3GtFg64xi0Ra5sHXBaGnfifTFPV04bV27RfrPfquKOSS6XdtO8Xvp3qBCNK9/2dxtZmavy+VbmJxVSK6D6ZkZtWJoLCvF17/ibhg7H9ZfJ9e/6mI+2z6P1FEpinqkszFKJlqGAAu+pHoHjn9A+lCrXp+3KaRF0IJRRH1EonWVvsuqJwdF2MzLxcXzmh0YGE5RAyKqFVVjQB1iqIUAv9SFGW2qqo7Upb5I/BHgEWLFh2b4p7/0aG/R/b+OPJWvGNeKoonwWX9ZCyMJOaO7MTqrMivhpXfSH5Oqi5/ryDLbP734k8NuPpQJENTJk09tiQTtbdb2B1l04WXJ60PX49QKokFNxDPh5XkFgkLmyPoEf1Spr0/rlbGr8gcdYf4ZJyi8UKFq2r6nczOf8EbPxWpYPtfgs1/FeQUdIuL1TsPiKyHRTcNeE6AePGRIVbMoyjxOw0Q8y8h3UbQAnFZlJe8tS6dCv/+gjiHRitMfB9njokRe8tWQBVEYrKJz7mzXpBI6VTRgXLnv6B8FnziKXHuHzhPqMSSWqHqj8RaCvi6xd2fKda5Tys62xvfl8RjOJpyJ7EkIaXOWiTOZyQkxIq0PiZfEGsP7EqOG/UcTO5QKde59lexYi5FXFjzqwVJo4jXIB5fspeKIG4qmjeLC6csxJHQG+HM2zOd+fj2j26Cjn1Ql2Kflk0XgiEcEJZc5z4h/iTmXj1qv/sh0b6qqr3Aq8DFo7I3x4pxS8XJnHz+id6TEwtpffh6hPWRGkgcAjJ2z9PapLYmP5/YitZREVfUb/0/eOj9orghEfKHLNdz8DV48lMiqOPthCWfji9be67IRkj0oyX6joipP9XzxfGm+sQt2+Cpz0HNYpG5MvF9sPH/BAlUzIHrHhHPvfz9wRWP9DYKxZmaUplXFb/oyP1MDcxJos5WWNLwijh3N64WBPXCN8X5+M9X48sknmd5V/juQ+LxQ7+HudcIxXntw2CyC/KGOOFu+qtoHta5H7w9cTUNIlCs6AS5ywKRxGNIvd1PhCYQYhlHUlFPOR9QYxeYGPxOYVkkKuqqGFGu+1+hlJd/Efa9ILKMDBYhSOT5TVTU3u50G+7oZnG3M5SGYnlV4tzveVbEeBIVNYjzKO82+o6IyUvy3I4yBpP1URZT0iiKYgUuAAaINpwgnP99+MybmTvfnU5Isj46Mlsfg0RG6yM/oZ91IhJb0TrK44palqpvfCh5eflDTh2w++k34M6DgjwlamMFO6mqOhoRxFxQk1wVmriNRz4qSOSavwkFvOhm8UNr2yF8Vp1elP/7ewfXZU3uQ6YiIk1R90PUerOoxkvNV45GBTlOOkfcBX3ubfjKHhEYb94Uz3zp2CPsm+JJcaLb8nCsk2MdfPgP8OXt8Y52lnxhDcl9ORor1z66MV6VKGG0inqFHU8IIrWVxNNe5f5ni70kCgQQF1uDBcafGX+vRKZaB3uJ2HY0BPM/JhqYKYpoeDX7I7DkMyLTBOLFarZSYVckeuPRqAgq95dxlQmKIt4jC1tSC+y0Cug96f3xRxmDUdRVwKuKomwD3gFeUlW1nzSFEwhFGdoV9L0KqWycTSKFL5v1MQBUVRVZH6mKWip0SUrrfwc/nw4v3iV82/waUUgTdAsbQ6Y6bXk4ucNYqqLua4rlvc5O9w/LZ4rtpvb9dreLH3ZBTcwv1Cc3+Xn688LHvfbvcctm+qViXaY8EaiEGOkqgytaaXhFZCikKq786nRFndgNMuASP/BZHxZ/p3aqSxzuACLIll8l7hT9fXFya98jSNpgihOdv1dYGTq9+B2kBqBLE7I5pH3RvEnsm7ywS5RNF6loIG7tpYUWcIu7mkxFXJAsEEBYW7ZS8f0rGAuv/lh8T565Ld6nJrHWAeLkuvBGKBwLUy4Sfy+6WVwI5sQyTbRgYuy7/dvF8L8LhQ/ftV9894ZK1Inbh3QSlncbHXvT++OPMgaT9bFNVdX5qqrOVVV1tqqq9wz0nhxOMKSy6YgR5DAVdUSNoKKmZ33ojeIHIklp11PiCzz7Crj4JyKQIr3rvqMi2FOzWCitXU/H15PqUfc1CbLLdEekKMJqaHg1+TY3cTKO0ZqsiHy9Iltg2edE4Ctx/y//HXzot3HP1F4ienYMRNTRiFC9teekq8q8SkEQAZdQ7JK4pPpq2Qao4jxZCjK3qoX04id5p3B0k9h+47p4R0azI/75pir8RJRNFz62r1cMLgax/VRFDXHyqZgdv6vp2AOH14pb/0wBXYgLhERFLQn1wh+KuogxC0Wg+OVYOUZRClGfeTt84NfiQgRwwd1w4Y/iF4eV34LzvhevUp58nggMT71YkPSGPyVUJGa5oPQHea4TKx8ljBaxvx17xQXLXj56mWMpGFQwMYdTDHqjaFkplWxqZsYgEYrGJpBnukuRt/mqKr64s6+Ay34Zf12SR+N6cWu6+FOCFN75M8y7Vrwm06oSFXXiKLJU1J4r2gq0bo0rHxm0k7Mma8+FNfcJQjq0Rmx78gXp65qSIY5Re47wR1ODXiDWt/sZcVHx92Yu+U8cyOBsFoGynU+KH/X4ZcmZCNXz04n6wKvx4Q6JKJ8Rb/pTPDG95UDxRKHca/sj6mni7mrvavF36VRx4TBawJoyRFgr8jgnueFZ9wFhPYzNQtTywiRtCFnqDaIFwawPie/LU5+Drf8Qr1lSepVX1yX3ZS+blqxaC8bAWV+J/20rhkt+Kv4fcIq7tplucWc3HP9YbjtrA7hYBbTZcdzUNJyMJeQ5jAwshcdM1MFY+8aM/ahl4Ez29kj9YsttJvp9ddeL6L2nM1ZeLIk6FvyT2RvZINXd4YR5kLLwJpGo1ahIn2t4RVyw5NSbgVB7rkg9y5TjvO7XIgvj1R8JEshU8i8JtmWbsGPGLUvuBtm8SdhCjnJB1G274uXx4aAY7CxncSZCbxSBseYtCf54wvbHLBJKMFNKqoT8fLb+Uzwu+qTos+HrSVeFNWeIWoYZHxQWkblAKOqGV0TmTrapSJpH3SseM7USVhRxQR+7dHjWRH9Y9ElxPJsfFndHw4lVOcpFgDnbXUPZNGGttO85rkSdU9TvVViL4oMUhml9SEWdccJLXqWI4kuvLlW9SKI+uAZQRGVlb6N4ru+I8KKjIZFx4OsW/qeruX+izqsUKiyxF0Vfk2gKZCkQf9csEt5zwytCoU44K3PBUCaMXSKIteEVkRqYiP3/FfbN1f8nyD9VCUJcUctxaYXjkr3h5s0wJkZO1fPF8bftFFV+HbtFgLFmYfp65fJb/ykuQpVzk+MOF/5Q3Dn0B0kqB9eI/Zp8ARBL67SmEHXpZPjm0fh5K5smzmX3AVjwiezbSLM+ujO3aTBa4Mb/9L+/w8HEs4WP3LU/bmEMB7e+Jqy8TCibLj63YOi4BRIhp6jfu0jsCzLMnibhWL/qzNZHtVDTMqMj9UsrgzzuVpF9YLTGSbivKa6mK2Md21q2CjWbP6b/nUqdqymLXST0Rph4lrAceg71bwekwmAWudH7X07uLeLpEvs35QLhoWciaYgraknUBTXxro7dBwXRaQOSZYZKLLCXmp+ciur5wv9uXJd+TDrdwEF0W3Hsgq2KdRVPEhc4+VoqEi9uZdPiwb/+zqfeIC6Svm5xpxB0Z28lrDcMXJE7VCiKaHQGx6bW9YbsBSuJKjpnfeRwzJBEbS0ediZM/9ZHJaAKa8NckO6r6o1xz1KSuPSf+5riqXmyqbtGbv141CB+HO2740TadyRdhdeeG8/lzdY+NhtmfFCQUmOCvXLwNUAdeF3mPKG2ZfVaQY3oFeE8Cv+8Vpwn2R+joEbYIAffEH83bxaKNDW4JpFIPEM9JglJLNXzBRHFxq0N2Jddfn6OivQCklQUx4JtMqNntBqfZcPCG+Hsr6ffEY0UEu8cc4o6h2OGvA0dpj8NAwUTY7f5B9ckT4VJhLRcJEHYikVerWzoDvEeyIkqtD/IgaYyRzuTry2JrGCsuBUeCmZfIQj1nT/Hn2t4RVgrg1FpeZXi1tiUJ96TOAf0qgfj6XSKItTpwddFRWZ/+ckgzqHRlhTMCx09SuDAgcEfWyJRJzyqpkLca9eiZutQKN9Xe+7AvWtkkFR+PqPV+CwbzA7R693sGLFV+vftI3gkFrQ22aFgnPh92cv6fd9IIkfU71VINTsSRJ1VUZO5gktCbluSlaIIUk1S1JKoY0UYAxK1LHHeI4p5vF3pPVuKJ4ny6RkfHJhYUmGyi6yUXU+L9asqNLwm/M/BBKfkBaygRmy7qk4E5i78YXrFbO05Qvk3rhd9I/q7EOj0Yh+mXawF89r+56cc/XKWcuhMGLcs+YIz+TwwWHDvbObIzbfg37Yt8/uq5okLxMzLB97GmAXiQio/z+OtqEcYajBI48030/Sl2+IXsvHLRFD1eE0vIhdMfO9CWh/HUJU4YNaHRLZbQEnUieO9JFFLRV0yWahsd6tQstn8X21bCb0oZO/piWclL6MoIiA03ArVRZ+EDX+ALX+HaZeKoOz77hjcezWiHhN//MaRzJkSE1cCikgJjIYHVuzX/D3pz3BnJ8FDh1CjUZTBNAGa/RFx8ZL+86SV8M0mgn97GBDK0TpvXvr7HOXwjcPxvib9QR7D/pfF4/FW1CMM1yuvEOnoJNLRiX/bNnF+PvT/+u+PPgrIKer3KkbQ+jDpM2RN2EtjrUXpR1HHKhgTe2lrirpLjDcyWuPqfCA1DYIIzflCUR94Vdw5VNWlL2cwDZ+oy6eLJlCv3gsPxirjBhuUzHQs2dLZ7CUib7f+BfH3QAUaKQG4SF8fajBIuG2QwxIyVSzqjYRbRMFRcH+GLnQSBjNRv59DH/0Yzpdeyr5cWSznW3rv9gH871FG8NAhDl1zLf7dmceLqdEojZ+6lZ5HVmV8veefj2CorkJns9Hzz0fEk4NpTTzCyBH1exXS+jgGH61f60Onj5NSNqJecIPImU1UyQVjhXp2Ncd/xKkqtD8oSrzooOGVwVsSQ8WFPxSd0KZfAud9d/AtcROtj8FA+un2soEzXlIQcYqAabDxyJDel4pQsyDqQEM/RA34d+zAt3EjzV+7E/+uXZkXMpiEnRXyigu5FAwnABG3myOf/wK+rVvxvJWhwx4Q2LcPz5o1tN5zD+431ya/duAA3rffpuja68j/4AdwPvcckd7e47Dn6cgR9XsV0vo4BkXdr/UBgqiNdpG9kAnl09NbzkoCa90evy0eiqIGQdSNb4mCm+FmQAyEMQvg8t+I4QxnfXXg5SW0Yxkge0VCln0PZshEAlRVJdoriDrUdIxE3TI4ovbtEJ2NdQ4HRz7/BcJd6Q37fVu3EnbEMkNsJQT279fWfzyhRqM03/E1gocOoRiNhI40ZlzOs3YdAKZx4zj6la8QPHRIe6131SowGim84sMUXXstaiBA71NPpa0j1NaGf+++tOdHEjmifq+iuFYEsSpmDXsV/VofIKrlxi0dWpN0ScZd++OBpqGq0NJpIrMChpYnfTxQMUv0KpYDBQbC2CVikkh/fToyQPX7UUPiHByzoo4RabilhYg7+3Be/46dGCoqGPuH3xNuaaH3sceSXvesW8eh6z9K57pe8YS9lKbbb6flru8c0/4NB/7du3G/9hrlt38Z85QpBI9kaI8LeNauxTS5lrEPPADhMF1/jmf7OJ97nryVKzGUlmKZPh3LnDk4n3subR2t37+bI5/5zKgdC+SCie9dFI2HbzUfUzfBfq0PgEt/KSrlhoJEpWlLJepBqlAZvCyZ3H/Z9IlA2TRx3gdbDWkwwZe3CXIfAiJ9fdr/s6nFwSAaCBDp6sIyaxb+nTsJHjyAdU7mi4x/xw4sc2ZjnTUL45gxBOrj/cWDjY003f4ViEQIuYESUK3FhJpbCDUeIer3o7Nk8epHAeE20QvdtmQJvh07CWTwqKN+P95336Xoumsx1YzBOn8+vu3iriHU1k64vR3bGYu05W0LF9Lzj3+ghkIoRvF5qcEgnrffRvV6iTid6PMHCIYPEzlF/V7GMbZ8DUUGIGqdbuhBlcSG87IiThL1YD3axLzekxGDJWltefOQRzdF+pza/7MpaudLL9H4yZuJOJ0ZXwcIt4qGWPYzRc/oQJaAYsTpJHjoENbZIp3SVDtJs0pUVaXpy19GAczTpxPu84LRRtRQhOr1ogaDeN/dmHG9xwr/3n0cuu76pAsXQLhLZBUZSkowjR1LsLkZNZJcZu/duBE1GMS+QjSlssyZTaC+nqjfj3+nIGxL7Hjl/9VgkMD++AXKu2ULqlfMqBzIOjoW5Ig6h6wYUFEPB0ZrXElL62PqRbDym2K46GBQOA4uuAeWfm7k9usUQzQWSDRNmBAvxkiBc/VqPOvWcfSOO9JISkLaHrbFZ6AYjQQb9mdcTgYPLbMEcZlrJxM8eBA1EiHc3k5g125KPvsZrHNmE+rogMvuJzwpPu/Rs3ZtxvUeK7oeeADf5s1pWR2RmH+uLynBOLYGQiFCLckTiTxr16EYjdgWCdVsnT0bIhECe/bg37EDdDosM+KzW61zxLFLr16uQyKYI+ocTgQ0RT3SwxikFy0J25IvxiwNdjuKAituS286fxpBKkjL7NlE+/qI9PURam9Pysbwb9+BvrQUzxtr6PjlLzOuR2Z8mMaOxTRxYpKiVlUV78aNRINBQVyAZbaIeZgn16IGAoSOHsW/XZTMW+fNw1BWTqSzC3XmFYR1IpCts9uzEnWopYVAfX3243S58G3ZkvG1cE8PruefTzoO7bWOTnR5eejMZkyxYdupFpFn3TqsCxags9lixxYj4u078O3YgXnyZHRWq7a8cdw4dHl5+HfsTF5HXR2K2UygYQhVokPEYEZxjVUU5VVFUXYpirJTUZTbRm1vcjipEIwOkPUxXEiiPsWr1k4kpPUhVV7wSBMtd93F4RtuRA2FCPf0EGpqouTGGyi44gq6/vwg4Z6etPWEWkSLWUNlZZKdAeBZs4bDH/0YLd/4Jr5t2zHW1GAoEmmf5loxzTywv0EoTL0ey4wZGCoqQFUJd3URbhc+cd77Lyawbx+h9vSp9C3f/R6Nt3wqa/l65+/+H4c+9nGinvQgZ9+TT2oBVXkcEuGuLgyl4vtlGitiH4kWUbijg8CePZrtAWCoqEBfWop/x3b8O3Ym2R4AiqJgmT1LuzCFe3rw79iB/awzxUUuy93ISGAwijoMfFVV1ZnAUuDziqIM0Jklh/cCRsX6gHjQ8BSvWjuR0BT1LKFwPevW4VnzJlGXC9+2bfh3xqyK2bMp+MBloKrac4kItbSgLy1FZzJhrp1MqKmJqF/0yO75xz9Br8e5ejWul19OIi6TJOqG/fh37MQ8ZQo6iwVDucjbD7e3a8Rc+KEPAeBdn9Doilgwb8MGwm1tWVW15801EA4TOHAw6Xk1GqVn1aNYFy1EX1aalgIY6ezEUCLy9A2VlZCSoueJ7Yt9+XLtOUVRsM6ahfv1N4h0d2t3D4mwzp6Nv76eaCCA9+23QVWxL1+Ouba2/4KhY4SStRFLtjcoytPAb1RVzVqetGjRIvXdd9891n3L4QTjD1v/wG+2/IbNH9+MQTeCCULrfgMvfhu+tDk+cimHIaH9/vvZvLqB1gXXEGptRVEUTZXq8xyAQsTlwlgp8rpDra3o8/LQ5SU3K4p0daNGoxjKSlF9fsI9PRhKSlAMekJt7egdDtRImKjPjz4/D50j/v5wWxuKyYwa8KNYrOgLC4Sa7+jEUFyEGggS9XoxVFUSbm0TZdc6HTqrBV1+PmogQLhLzJPU5+ejc9iTDzISJRSrutQXFqKzxW0IbV+LCom4PSg6HfqSeLvWcHsHisGAvrgo9nc7isGo/R3p6UUN+AWJJyDqchNxuQAwlJaimJJFirbd0lKibjdqIIChspKoW7wvf/JYrr5ryeA/yAQoirJRVdVFmV4b0q9PUZQJwHwgrcxHUZRbgVsBxo07yVKmchgWgtEgCgp6ZYQr/+ZcJZrkZ2vpmcOAiPT10VU2l2gUSryHiAYCGKurUf1+cHegWCxEQ07yZoibX9eRjejC+dinJZOI66WN6PLzsU+bghoM4XplGxxtxFBZSbD3EPlLLhT+6969mCaWobPGU+w8HbuIdDuJ+v3Y5s/HNLGIqD+Ac99arOPnEfZ3in2YNoOgzUO4vZ2Iy0XkaC/5cy4mUH+UQF8DOqsVvd+BfeHypH0LHm7E2yN6j1vKpmKZJjKGIi437tfWorPbyZs7Hc877xJ1OslbXqu9t2/fWkzjxmGdJoSAp2s3UV+AvNjfztVvYSgtxTYtebBvqDWAZ91e0OkoOHt6Wg+VqNeL8/m3MOg6CXd1YZk+Dcv0IkJHfXga91JcPLTq0sFi0EStKIoDeAL4sqqqafk+qqr+EfgjCEU9Ynt4imFn104qbZWUWE9sj4P+sKltEzNKZmA1WPtdLhQNYdQZUUa6S1hexdCq/XJIQ7TPScg8nYqJ+cxs3Ihv7xbGfu0BfJs20vn7P6AvKMC+YgVjbhBEfXTbg3g3bWLK/7tJW4eqquy9/2MUXX01FbHl/CuMHLr+o6hb/DhWrmTsZ6XAS8+tbm16ip6//Q2ACT/6ENbZM1EjEfb8+uOUnGPHu28DitnM+Bu+BIj1Bw4c5MAll1B2UTHO+ufQFxZinjqV3sf+j6n/+3F05njjp6N3PISncz36okJMnmbG3nAVEaeTQ1dfQ8TlYuJjj2Ksrqat7T/0rFrFtL99EUVRiAYC7L33IcrO+xKlseNqbXySvqefZupfPkdgXz0H732Aqh/9kMKPJLu44Y4y6h/6PJaZM5l40zfTjllVVer/+iUie3twnH02NT/+BopeT+CAhQN//SJVNw2/wKw/DCrrQ1EUI4KkH1ZV9clR2ZP3AHr8PXxi9Sf45cbMEfaTAUecR7jh+Rt4fN/jAy4bioSyVyXmcEIRcToJGuxY80xY5szBPHUq9uXLRHAsGiXS05PksVpmzybc0kK4szO+jt5eVJ8PY3W8E6Jl5kyq7/0xisVC8Q39jN0iHlBUjEbMU0XjLUWvx1BaSri9g3B7u+ZZa++ZNBHb0qV0//3vBPbuxb5iBfbly1D9fnyb48N+1WgUz/r1wv+dPEUL1PWsWkXw0CFqfnU/xmqhsI1Vlag+n9aHQ0vNK43HQEzjxgp7orcXzzqRUpfoT0sYysq0c5kJiqJgW7IE85TJVN/3MxS9uNs0jR0LRiPBUcr8GFBRK0JO/RnYrarqL0ZlL94jeHr/0wSjQdY1r0NV1ZFXoiOAtc0iTWpfz8C9CaSizuHkQ7ivj1CxBavDSMU3v4EaDqPodFjnzkVntxP1eJIqDBNzgPNWrhTriAXgDFVVSevOf//7cZx3HjpT/xdp82RB1OZp05KWNZSXE25rI9zejrE8vddM0bXXcvTLXwbAvmI55gkTwGjEs3Yt9qViKEJg714iXV3YVywndKQJ14svEg0E8Ly5FvO0aVruc+L+h1taMBQVaT1IDCVxojaOjaXoNTaKsvHaWowpxy0x8fHHQJ/d7htz389Qo9GkY1aMRswTxo9a0ctgrI8VwMeB7YqibIk99y1VVVePyh6dooiqUR7b9xhGnZEOXwf7e/czpWjKwG88zljfLKLdB/oGvvKfSkR99CtfJf/SS8g777wTvSvHBX53ALVEhzXPhKLTocRIQzEasS1Zgvu117BMj/cJt8yYAYqCf8dOFEWh7Sf/owXNMhHWQCQN8cwPy5zkNDZDeTn+bdtQQyEM5RVp78s771z0ZaUQjmCZMQNFp8M2bx7df/s7ztWil0Y0Vu1nX7Ycn3kjRKP4d+3Ct2kTRR//eNL6jFVCWYdaWrDMnEm4I1aVWBq3H01jRUrokc99nkhvL0XXX5/1uJQBjl0xGMgkwUy1k/HvztJV8BgxIFGrqvomZNyvHBLwVstbNLoauX3h7fxy4y9Z17zupCPqUDTEhtYNABzoPTCg6g9FQiNf7DIKiLg9OFevBp3utCHqgEdUGloc6Z9P6ec+h+OsM9HZ41kUOrsdU+0kXC++SPeDD2KorMSxYgX6wsIkQh8KDEVFVHzzG1r5uYSxohx3hxjFZcigqBWjkaof/ADV59OCdaVf+iJ9TyS7qqbJtRgryolMEheE3kdWoYZCaZaFtG5k5WFi+bi2rtpaSm65WZC4QU/xR7MT9XDhWHk2hrKyUbmbPiWbMh1xHQEVxuYPsonPMKGqKm+3vs2iikVaeto7re8wt2wuZn3ytIvH9j5GkbmIj834GE/tf4r1Leu5YdYNo7p/Q8WOzh24Q24WVy5mQ+sG2r3tVNjTFY/EqaKow62xNp0Hhn7bGWppIerxYJ48xNmKJxBqNIo/KIjAmpf++Vhnz8KaMQd4Dn1PPYW+rJRxDz2IsSL7Zz9YFN+Q/h1PJOdMRA1o9ouEffFi7IsztxAwTZwAOh19q1ejmEzYFi1Mel1fXIxiMmlFL5k8akWno/yOQU7pGSYKP/QhiOWMjzROyRLyO16/g6+8/pVR386m9k186sVP8ejeRwHY3rGdT77wSR7Y/kDScuFomNeaXuPSSZdi0ptYXr2cja0bCUQCo76PQ8H65vXoFB3XTb8OgIa+/oktGAmeEopaFjsEGw5k7WmRDS3f+S6HP3ED0WBwNHZtVBB1uwkZRNmz1TH4YK9tyRIUi4Wx//u/I0LS2WAoG5iohwKdySTKwEMhbIsWpXXhUxQFY1WV5rmHO7u08vH3Ck45ou7ydbGraxd7uvfQ6esc+A3HgLVHReDtsX2Poaoqq/aKcT1P7HtCq9oD6PR1Eo6GmVQocjSXVS3DH/GzuX1z+kpPINY1r2N2yWzqyusAYX/0h1A0hEl38md9SKJWA/+/vTMPj7I6G/d9Zsskk2WSkJCEJISERQFFBZRFa0FEEC2ICEHUira1FRdEalX8vl+taBerZVWxivbrz0+WqoiAiiJgCIsIggSVQIBASEL2mSyzz/v98c4MCUlIgIQZ9NzXNRfzbud95jDzvE+e8ywOXMXFbZx9Cn9mnKeqitr1Z2gvFWJ4rFacejXxpCWLujViJoyn99Zcwq+4opMkU2lqUXdMp26Db+HSNLx5pAaALiU5UO/D3Sgr8cfCRaeot5dsD7z3L4y1xZrDa5i5cWYT5doethZvRa/Rc6jmEJuOb+KTo5+QGZNJua2czcc3B84rrVd9Y8km1Vc2OGkwOo2O2ZtnM+a9Mby297VmYy/es5gx741hzHtjmLNlDm6v+6xkO1usTiv7KvYxJGUI8cZ4YsJiOGw5jNvr5qEND/F54efNrjlX14dl7VqK//BkR4jdLhqnDzcuQdkWDV+rZS6FXk/1snfbd82uXRTefQ8uX73j+q++ovDue3AcOdLGlR2Hx2LBpY8CWvZRt4YQIlCAqDPxK2qt2dyuRcn2EJbpV9TDWzyuT04JfA88FRVou0hFHVS2FW8jJiyG2LDYdinqXSd38V9b/osNxzaw6fimdt+n2l7Nd5XfcU/fe4jSRzFnyxwcHgd/vu7PJJmSAu4QgJJ69QviV9QR+gieGPwEP+v2M1IiU1i8ZzEfHPwgcL7FYeGtvLeINkTTJ7YPqwtWM2/XvHbLdi7sLNmJV/EyLGUYQgiyYrIoqCngy6Iv2Vy0mVf2vtKsMM65uj6q3/lfLB9+GKgZ0dm4i0vQ+Aq2n02pyfrcXIReT/wDD2D7etcZq7j5qV2/noadOyl65GEcBQWcePgRdXvGQ4Eois7Ga7Hg0kei04NO3wn9Is8TvxXdEW4PP+ZJt5MwaxZhfVruz6lPTsZdVqamsFdWouvSMZZ8qHBRKOpCayFlDWUoisK24m0MSR7CkOQhbCvZhqIonKw/yaHqU5ZUlb2Kjwo+4oODHzBr0yxSo1JJMiUFXBen4/a62VGyo4mi2lGyAwWFkekjuTXrVmpdtVyecDl94/syqdcktpVso9BaCJxS1EmmU3UDpl4ylReue4HXb3yda5Kv4bntz7GnbA+gxls7PA6eG/4c80fOJ7tPNv/67l8s3rOY1QWr+a7yVIiPxWEJXNcYp8fJztKdgW2P18P2ku2tViHbWryVCF0ElydcDkCmOZMCS0HggXOw+iB7ytX7fF/5PZW2StxedxPXh+PIEWpWraJm1Soch0+5TVylpQEl56mrw7Z3r7q/qOX2R34Ul4uGdtSEURSF+u3b8TpO+fxte/bgtdnU+5SUENarF7qEhECpSfuBfNy+yIPWqM/NJXzQQGLvnOqzqlv+fjTGlrcfbWws9r3fcuS2iShA8vNzcR47RvHs35+1j/xc8FitOA2RhEeEnpIG1ZIWen2HKmpDejpdfvPrVqMp9MlJatW+sjJVUUvXx4XF6XFyz8f3MHXtVHaU7qDMVsbQ5KEMTRlKha2C7SXbmbZuGlPXTuW7yu+oc9Yx/ZPpPL3laf5763/j9rqZP3I+d/S+gx0lOzhqOdrsHuuOrONX639FzomcwL6txVuJMkTRL74fUy6Zgl6j5+5L1fjNib0mAgTcBSV1JUQbojHpTc3G1ml0/P1nf6drRFdmbpxJaX0pK/NXMiBhAH3iVOvgiaufYEjyEF7b+xpztsxh2tpp7Czdid1t57ef/Zbpn0zH4mjaweLt/W9z36f3BfzgHxz6gF+v/zVfHP+ixXncWryVq5OuDrgyMmMysTgs5Bbncm+/ezHpTaw4sIKdpTu5c+2d3PvJvdQ4agLnOw4f5ugdkyl58ilKnnyK4w/8FsWrtuEqnv17Cu++R/X57tgBPmXVWkF7P9Z16yi86+42kwSqlr7FsXunY12rhu67q6s5euc0qv5HTV92lZSgT0rC0DMLR0EB3vp6CqdNo3Tu862O6Sorw5GfT+Tw4eji4ogcdQO169efUQ7F48H+3XdEjxtHwqOPgKLQ7eWXMN9+O12ffJK6zZup3bDhjGN0BJ4a1aI2nsVC4oVECEHYJZdgvKSV7vSdgD+mu/Ltf+G1WpvEUP8YCHlF/Xnh51TZq6i0VfLwhocBGJqiKmqAR754BIvDQnRYNI988QizN8+m0FrI/BHzWTdxHesnrSczJpOJvSaiEzpW5q9sdo8tJ7YABKxLRVHYVqJa7lqNlsyYTHKycxjTYwwACREJJEYkBpJGSutLA26PljAbzSwcuRCb28Zd6+7iqPUoU/pMCRzXa/QsuXEJ6yau48MJH5IWncbjmx7niS+fIK8yD7fiDsQ/g2o9+z/H8gPLmyx0NnbJ+DluPU5RXVFgzgCyYtQvtlZouevSu7g181Y+Pfopj296nMSIRIpqizhWewy9Vo/HYqHowRkIg4GM//yHpD/+P1zHj1Ofm4s9P5+Gr7/GU1ND7aefqh0vfP3kXG0oan/nZkd+61mSdTk5lL30UpPzHAcPgteLbe9eFK8XV2kp+pRktevIoUNYPlqDt66O+q1bUdwt+/4bTitzGd6/P+7y8mYtnRrjPHwYxWYj/LL+dPnd7+j91Q4ifT7T2KnZ6JKTqVm27IyfuSPwLyZGxFy4HoRnS8Y7/5+Exx67YPeLuPJKzNlTArVHtNKi7jxu+/A2xr43lpvfv5l3vn8HgBX5K0iLSuOvP/srdo+djOgMUiJTSDIlkRmTid1j57lrn2PRyEUBC/EPV/+BkekjSYtKC1i5XcK7MDJ9JKsOrcLpORWK5VW8bC/ejk6j48uiLymuK2ZfxT5K60ubKLbTrWW/jxdU10djt0dL9IztyZ+v+zMnG04SExbD6IzRTY5rhIa0qDQyYzJZMGIBbq+bjcc38tsBvyVSH8nW4lMtf3JO5FBaX0pmTCbrj64n50QOP1T9QGZMJluLt3Lc2lRBbitRlVLjz+OPULk+9Xq6mroyuc9kXF4Xbq+bJTcu4alr1II0eo2e0mf/hPPECVIXLiC8fz/MEyeijYujetlyapavQBgM6Lt1o/rdZWoa8LChaCIimvXys366nmP33YfiC4Xz12/wdxVxFp3g6NQ7sf/wg7r/8BFOzHqcsN69MWRlBSxvvx/anpenxsy6XOiSkwnrmYW3oYGKJUtAr1drM/uKvIP6AC59/gUO3Tia0rnPo42LI8yX7HGqvnLrkTD+xqf+usyNu38IrZbYyXdQv3UbzqNHWx3Da7NROH069dubFaBsN16rBZchivCY0A0/EwZDoA7GhSLp6acDqeW6Lj+uWuchlfByecLlOD1Ojtce5y9f/QWb28auk7uYNXAWN2XchM1twxxmDpw/a+AsquxVjMlQLd2FNyykoKaA7D7ZLY4/LnMc6wvXs7d8L4OTBgNwoOoA1Y5qHr7yYRZ9s4g39r1B7olcEiMSGZU+qlVZs8xZvHfwPbyKl5L6kkDI25kYmT6SF69/EaPW2CxhpjEZMRm8MuoVdpftZnq/6RyoOsC24m2BjKflB5aTGJ7I3372NyZ9NIknc57EpDcxf8R8Jnw4gZX5K5k16FSc+bbibSSbksmIzgjs6xrRlUevepQb0tVMvl6xvXj6mqfpG9+XjJgMMmIy8Cgeepp7Yvv2aaJHjyZioJpoIAwGzLffTuWbb6IxGokeO4awSy+l7C9/BSB22p24T5bhbFSo3bYvj+InnkBxOLAfyCf8sv6BQut+BVyf8yW2b76h6MEZpL+1lKIZMxA6HWmLF1E2bz4Nu1R/tl+xu8vKAv5wfXJyIBPPXVJCwsxHKZ+/gPqtW4m48koAKpcsofrf/8b0s+vQms1EXnttIDPOn/DiKDhExFVXtvj/Ys/LQxMRgSEjo8Xj5kmTKF/8CtXLV9D1D0+0eI517Voatm2nQgHTkHOrW+z2uT7OJob6p4AwGOi2YD5VS5cS0UryzMVKSCnqZ4c9C4DdbWf6J9OZv3s+eo2e8T3HAzCh54Qm51+fdn2Tbf8iY2tcnXQ1WqFla/HWgKL2W6oTe03k2/JvWZm/EoPGwL/G/otYY2yrY2WaM7G5bRyuOYzVaT2j66Mx/odKW1yReEVA+Q9LGcbG4xs5XnscjdCQeyKXBwY8QJ+4PlyVeBW7y3Yzpc8UMmIyGJE2gg8OfUDP2J4IX+b/jpIdjM4Y3WQhRgjBry77VZN7+hNhTt8+YLGgjW06F+Ypk6l84w28DQ2Yp2QTltmD8n/MQ3E4MA0fTsPOrwOhcu6KCooefhiNyYTH4cC+P4+wrExcJ04ABBqq2nyK0F1ZyeFbf4Hi9dL9raXou3UjLCsL60cf4amrx1FQgDAaUex2aj9T1wn0KSnoEtSVfk1EBLF33U3t5xuoz91KwowZ1H7xBeXz5hN9yy2kvPi3ZotS+pQUhNF4xi4dtv15GPv2bdVS1CUkEDVqFJb33yesT+/APUSYkciRI9AYDIEFy4bt23EcPkJY5qma3LZ9eei7paCLUwvg2w/k4/hBbdoaPnAghlS1XoXTUo9Xo8d4FjHUPxV0cXGdnoEYDELK9eHHqDMyb8Q8kkxJjO85njhjXNsXtYNIQyQDEgY0CevbVryN3rG96RLehbv63oVBY+DZ4c/Sv0v/M4ykLsbBqWp07VXU54LfZZFzIoe52+ei1Wi5vdftANzd9250Gl3A533npXdS46hhzpY5PL3laZ7e8jS1rlp+nvbzc7q34vHgra1FGxPTZL8hNZWoUTdgvOwywq+8Aq3ZTMxtEzD06IEhMxN9ehquoiIUr5eqt9/GXVFB+hv/RGs2Y8vLC7RWMnTvjuNoIYrLhT1vP+EDB5I89zkUr5ekZ54hYrD6QDVkqfPtPHIYZ0EBkSN+DhoNtRs3AqpFrYuLQ989HfMdd6CNNGEaPhzb3r00fPMNxbN/j7FfP5LnPtdi5IDQaDBk9mh1YVNxuXB8/wPGRhXpWiLurml4LBZKnnyK4j88SfEfnuTEzJlq38F9+7Dn5RH/u9+CTkfN8lNRJl67ncK77+bYL+/FU1ePbd8+jk6efGqMx9S/kBRFofaoGmUUfhYx1JKLm5CyqBvT1dSVdbetQyM69lkyJGUIr+55lRp7DWG6MHaX7WbapdPUY8lDyJ2ai1HX9iKNfzHOn72YHNl5ijo9Kp1ukd2Yv3s+NreNPw79Y8AnPqr7KHKm5BBpUDPVBicNZsMdG3C4T4Wy6bX6Nn3oreGxqj0itDHRzY51e+klFK83oPiSnnlGLbcpBIa0dDWm9eRJ6rbkEnHVVRj79sXYvz/2vP0BKzrqppuofP117Pn5OA4dInLkCGJuvZWoG25okpwRlqW6Jmy7d+MuLye8f3+cBYdx5OejMZnQRKkJIJmrVgWqn5mGD6NyyRKO3Xc/GpOJ1MWLmqUfNyYsq2er4YKOQ4dQnM4W++g1JmLQIHpu3oziOBVDbvnoIyoWLqJh925EeDjx992H8+hRalatIuGxmWiMRjX5xm7HcfAgJ2Y9huNAPrr4eFJffZW6jRspnzcPW95+vA31NJRWQ7ezSx+XXNyEpEXtR6/Vo9V07ILEsJRhKChsL93O5uObcXldTRbZ2qOkQY3kiDPGsevkLqBzLWohBENThmJz27jzkju5vfftTY77lbSfxIhE0qLTAq9zVdIA3oCijml2TBgMTRSf0OkC23pfWUnbN9806fZsvKw/joMHse3fDzqdahmDGnrn8QRqKJ+eQWdIVwuzW32p3oasrMCini45KfCw0ISHB1wTEVdcgYiIALeb1IULAv0DWyMsKwt3SQmeuuYdr217vwXU6JC20HdNxJCeHnh1efBBoseNw11aSswt49BGRRGbPRWvxYL140+AU8k3CTMfpf7LHDxWK6mvLMbYpzex0+5EhIdTvexdapYtxx2jxidL18dPh5C1qDuLfvH9iDJE8V7+e+yv3E+v2F4M7jr4nMbKMmexs3QnWqGlS3jnrjLfdeldxBvjeWDAA516n9PxW9T+zL/2YvD1zaxeroYL+hV1eP/+4PFg/fhjDBndMfbuDYDlo9UAGPu1rAiFTkdYRga23bsBVam6+hdjef/9QD3iZtcYDCTNeRptbGxgQfFM+AvhO48cblJ0H8CyejWG7t3Rn0M/UCEEyXOfw5CRgfmOSQBEXD0YQ2YmNcuWYb5tgpp8M3Ag8Q88gCY8nLA+lwTKj2qjooi5ZRyWj9ageDzofvEwVEqL+qdESFvUnYFOo+OapGvYXrIdrdCyYMSCc64Q5/dTJ0YkdmyX7hbIMmfx0JUPXfCyo54aNa64JYv6TOiTk0Gno2HHDrXmcd9LgVOhbZ7yCsKyeqIxmdCnpOApr0CXkIC+a+vZbIaeWaAoCKMRfUpKwLptrVMHgPn224kaObJdMgdC9A4V4KmpwZa3H1AX9Wy7d2POzj7nOsOa8HASHn4oYNULIYjNnoJt717qcnJw5OdjGq6m98f98pfNIkLMU7LVxrUuF5r+agja2RRkklzctKmohRBLhRBlQoi8CyHQhWBk+kj0Gj0v//xlUqNSz3kcv6I+H9dCqOOxnpuiFjpdoKedadjQQBicLjFR7e4BhPkWCAOdQtpwK/gL8xgyeyC0WsL69EEbG4vx0nMrfH86hrQ0hF6Pfd8+Cu+dztHJk6nL2ULN8mUIg4GYCeM75D5+YsaPRxiNlMx5BiCQPNMS4f37ET5oIKbrrsNliEKr06APC80UcknH0x4z8G1gEfA/nSvKheOWzFsYkTaimW/3bMkyq4rjR62ofZl62rN0fYCq+FzHjjWpeCaEILz/ZdRt3BhQ0GFZWdTn5DRr6XQ6gR59voVFTVgYPb/YgOigusNCp8OQkUH1u2olPX23bpyYNQs8HqLHjkUX23q45rmgjYkh+uabsbz/fpPkm9ZIf/NNEIKDywoIj+qE7vCSkEW0VsSnyUlCZABrFEVpeyUFGDRokPJ1O4rtXOxU2CoYsWIE0/tPZ9bAzm9kEAwqXnuNrR8dw3rVLZxtRzZ3VRXe2lr0qd0Q2lM2gcdiwVNTgz4lGaE34K2rUwvpJCY2yfY7HcXlwlVcjNZsPmsLv90yV5TjrW9AGxuLxhShls70eNElJXVKIXrF6cBVUorGZGp3Nl291Yk5MZwpc35cSR0/dYQQuxRFGdTSsQ5zrAohfgP8BiD9HBZcLkbijfHMGjirWeLNjwlPjYXyxIEYFOja4+ysam8cuCu8GDKbxsErdj3OwgbCesaDECguI84CK2G9E0BzJm+cgkOpxJDeBWFsXaGfD54YD54qMGSpLjFPFy2eykoMmZ1XNtOhtaBPiD+rBdseA35cKdKSM9NhilpRlNeB10G1qDtq3FBGCMH0/tODLUan4i8A1OeKBK6d1JHNek83HNqOylBp1x91Fxlnjs2WSH5yUR+Ss8NhqcOr0cssOIkkiEhFLTkjdqta6S48SsbsSiTBoj3hee8C24A+QogiIcT9nS+WJFSwN6j1nKVFLZEEjzZ91IqiTG3rHMmPF5tNXW6QFrVEEjyk60NyRhwuNSTvbLpdSySSjkUqakmreJ1OnIoaOyxdHxJJ8JCKWtIqXosFpyESjVAwhP/k6ndJJCGDVNQ/EbwNDRy7/1eBvn/twWO14tJHEmZApitLJEFEKuqfCLa9e6nPzaViyWvtvsZjUXvzGcPl10QiCSbyF9hB2A8cwFNbG2wxWsWWp1rSdRs34Sotbdc1HosFpz4SY6R0e0gkwUQq6g7AU1fH0TsmUz5/QbBFaRV73n61kJHXS83K/7TrGr9FHRHV8cWIJBJJ+5GKugNo+OorFKeT+pycYIvSKva8PCKGDcV07bXUrFyJ4na3eY3XasVliCQ8tnMKIEkkkvZxUSrqitf/SdlLL9GeEq3twZ6fz+HxEygYezNHpkzBcfDgGc/3Ohwce+AB6nd8BUB97lYAnIWFOItONDm39PkXqHrnnTZlqF6+gtLnXzjHT3Bm3FVVuE6cILx/f2Kzp+AuK8O6dm2b1zmrrbh1EUTEmTpFLolE0j4uOkXtrq6mYuFCKv/5BlVLl3bImFVvvY3z2DGMl16C63gRx2c8hKemptXzaz/5hPrNX1Lx6quA2pjU0L27+n5rbuA8x+HDVP/731QsWIjX4WhxLFDjlcvnz6f6nXcChfo7Evt+taWUsf9lRF5/PcbLL6fk2T9hP5B/xutsNQ0AhEdL14dEEkwuOkVtef99FJeLiEGDKPv7S9Rt3nxe43lqarCuW0fML35Bt5dfJnXxItwlJRQ9OhPrunWBV+0XX6A41QJF1e8uA6Bh+3bqtuTiPHoU89RsdF27BqxrgJrly9V7WCzUfvJJqzLUrv8MT1UVeL3Ub99xXp9H8Xioy8lRZd60CcXtxu5bSDT264vQ6UhduBCtyUTRjBm4q6tbHctmVR8uMtlFIgkuF9VyvuL1Ur18BeGDBpL2+hKOTruLE4/PJmPFcsIyM89pTMuHH6I4HMROzQYg4sorSfrjHyl55hkadjRVmtHjxhH/619h27OH+F//msq336bkmVP97hz5B6ndsAHF40FxOqn5YBXRN4/F/t33VC9bTsz4lnvu1Sxbhj41FU9NDfW5uUTfNPqcPgtA2UsvN/lLwzw1G3dZOYYePdBGqq3H9F0TSV20kMK77+HEzMdIf+OfCH1zZWyrc4GQTVQlkmBzUVnU9Vu34Tp2jNjsqWgiIkhbvAhhMFD04Aw8VutZj6coCtXLlhM+YADGRv3qzLdPpOemjWSuXRN4dXnwQaxr11I04yFEWBjx999H9I2jcJeWoktMxNCzJ6Zhw/BaLNj378e67mO8Vivm7GzMU6Zg++Yb7AcONJPBcfAgDV9/TWz2FCKGXEN9bu45+95rVq2iaulSzFOmkLl2DXG/vIead5dRt3lzs36E4QMGkPSnZ2nYsYOTf/lri+PZG7wAGCNlQSaJJJiElEV9eOJEFHvrvlxPVRXa2FiiRt8IgD4lhdQF8ymcfh8F48ahjYom/LL+JM+di9DrqVm1iso33gCvgiEtjZS/v4g2KiowXt3GTTiPHCH5L39udi99167QtWtgu8vDD+E8egTruo+JmTABrdmMOTsb67qPMQ0fjhAC07ChAByfMQPFZseQlUXE4MEYe/em/B//4Nh99zfr9eexWhF6PTETJ6Ixmaj7fAOuY8do+HoXdTk5pPz5BTTh4Vg/+4yKhYtQ3G70SV1JefFFdPHxNOzezcm5z+O123EeP07E1VeT9MwchF5P4hNP4DhyhPovcwhvocO3ecIEHD8coOrtt6nPzW3WBqvBnQGZ0vUhkQSbkFLUxl698Pr8wK0RPXo0GsMpCy9i0CBS5/0Dy5o1KA4nlg9XozGZiBp9EyXP/BdhPXti6N6d2g0bKJ79e1JfWYzQanEeO0bxU08R1qsn0WPHtimbEILk559Hn5ZO7OQ71HsPHkyXGTMCDw5dXBwJjz2G/YfvATBPmoQQAq3ZTNc5c6jfvq3FsU1XX40uLg7TsGEAlM2bR+36z8DjoUSjIW76dIpn/x59aiphvXtTt2kTRY8+SsrcuaqFH24kfMAAIgYPJmHmowE3htBq6fbSS1QsWkTUTWNavHfi7McRxjCchYXND7r6gBvCTFJRSyTBpF1dyM+WYHYhP/nii1S9uRRhNKLv1o2M5cvQRkZS/e67lD77J8yTJ2Macg0Vr76Ku6ycjJUrMIRIM15FUSi4cTSuoiLCevUkctQoKl99DWE0oo2LpcfKleji47GsWUvx7NkIoxGh16s++h49OlyeTf97gILdZdz/9+s6fGyJRNKU8+5CLoQYA8wHtMAbiqL8pQPl61ASZ83CeagA2549pC1eFFhAi506FXt+PjXvLqNmxQrQ60l/fUnIKGlQrfbIkSOwrv6I1FdeQZ+aiut4EXVffEHa4sXo4uMBiLllHI6DB6l8801SFy7oFCUNYK91SreHRBICtGlRCyG0QD5wI1AE7ASmKoryXWvXBNOiBjU6xNtgQxvZNFFDURRchYUobjfa2NiA4gslFJcLr90e8KUrioK3vj7wwGmMp7a2ic+9o/ngpd0A3Pb4VZ12D4lEonK+FvXVwCFFUQ77BlsGjAdaVdTnyooXduJ2eTt62FaoBA5doHtdnFjLbWRcFnoPM4nkp0Z7FHU34Hij7SLgmtNPEkL8BvgNQPo5uhNikyLwuC+Uopa0RVxyBP2u7RZsMSSSnzwdFvWhKMrrwOuguj7OZYwb7+vXUeJIJBLJj4b2JLycANIabaf69kkkEonkAtAeRb0T6CWE6CGEMADZwOrOFUsikUgkftp0fSiK4hZCPAR8ihqet1RRlP2dLplEIpFIgHb6qBVFWQes62RZJBKJRNICF1VRJolEIvkpIhW1RCKRhDhSUUskEkmIIxW1RCKRhDidUj1PCFEOtFA3s110ASo6UJzOQMp4/oS6fCBl7CikjO2ju6IoCS0d6BRFfT4IIb5urTBJqCBlPH9CXT6QMnYUUsbzR7o+JBKJJMSRiloikUhCnFBU1K8HW4B2IGU8f0JdPpAydhRSxvMk5HzUEolEImlKKFrUEolEImmEVNQSiUQS4oSMohZCjBFCHBBCHBJCPBlseQCEEGlCiI1CiO+EEPuFEI/69scJIT4TQhz0/RsbArJqhRDfCCHW+LZ7CCF2+OZzua9EbTDlMwsh/iOE+EEI8b0QYmiozaMQ4jHf/3OeEOJdIYQx2PMohFgqhCgTQuQ12tfivAmVBT5ZvxVCXJBml63I+KLv//pbIcQHQghzo2NP+WQ8IIS4KRjyNTr2uBBCEUJ08W0HZQ7bIiQUta+B7mJgLNAXmCqE6BtcqQBwA48ritIXGALM8Mn1JLBBUZRewAbfdrB5FPi+0fZfgX8oitITqAbuD4pUp5gPfKIoyiXAAFRZQ2YehRDdgEeAQYqi9Ect6ZtN8OfxbWDMaftam7exQC/f6zfAq0GU8TOgv6Iol6M2x34KwPf7yQb6+a55xff7v9DyIYRIA0YDxxrtDtYcnhlFUYL+AoYCnzbafgp4KthytSDnh6jd2A8Ayb59ycCBIMuVivqDHQmsAQRqlpWupfkNgnwxwBF8i9eN9ofMPHKqN2gcavnfNcBNoTCPQAaQ19a8AUuAqS2dd6FlPO3YbcA7vvdNftuode6HBkM+4D+oRsNRoEuw5/BMr5CwqGm5gW5IdVUVQmQAVwI7gK6KopT4DpUCXYMll495wBOAvzNwPFCjKIrbtx3s+ewBlANv+dwzbwghTITQPCqKcgL4O6p1VQJYgF2E1jz6aW3eQvV3dB/wse99SMgohBgPnFAUZe9ph0JCvtMJFUUd0gghIoH3gJmKolgbH1PUx27QYhyFELcAZYqi7AqWDO1AB1wFvKooypVAPae5OUJgHmOB8agPlRTARAt/LocawZ63thBCzEF1Ib4TbFn8CCEigKeB/w62LO0lVBR1yDbQFULoUZX0O4qivO/bfVIIkew7ngyUBUs+YDjwCyHEUWAZqvtjPmAWQvg7+AR7PouAIkVRdvi2/4OquENpHkcBRxRFKVcUxQW8jzq3oTSPflqbt5D6HQkh7gVuAab5HigQGjJmoT6Q9/p+N6nAbiFEUojI14xQUdQh2UBXCCGAN4HvFUV5udGh1cAvfe9/ieq7DgqKojylKEqqoigZqPP2haIo04CNwCTfacGWsRQ4LoTo49t1A/AdITSPqC6PIUKICN//u1/GkJnHRrQ2b6uBe3yRC0MASyMXyQVFCDEG1R33C0VRGhodWg1kCyHChBA9UBftvrqQsimKsk9RlERFUTJ8v5si4Crf9zRk5rAJwXaSN3La34y6OlwAzAm2PD6ZrkX9s/JbYI/vdTOqD3gDcBD4HIgLtqw+eX8OrPG9z0T9ARwCVgJhQZbtCuBr31yuAmJDbR6BZ4EfgDzg30BYsOcReBfVZ+5CVSj3tzZvqIvIi32/oX2oESzBkvEQqq/X/7t5rdH5c3wyHgDGBkO+044f5dRiYlDmsK2XTCGXSCSSECdUXB8SiUQiaQWpqCUSiSTEkYpaIpFIQhypqCUSiSTEkYpaIpFIQhypqCUSiSTEkYpaIpFIQpz/A70wSVozq69HAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_24_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.plot();"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e079edd5",
   "metadata": {},
   "source": [
    "Naturellement la fonction `pandas.DataFrame.plot` aura les mêmes paramètres que la fonction `matplotlib.pyplot.plot` ! elles utilisent toutes les deux la même fonction ! Donc vous pourrez changer le titre, les noms des axes..."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "232e222a",
   "metadata": {},
   "source": [
    "Remarquez ici que l'encodage de la famille par notre colonne d'entiers `Type` nous permet de voir immédiatement les 3 familles de fleurs !"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5d829410",
   "metadata": {},
   "source": [
    "## dessinons des boxplots des colonnes - `df.boxplot`\n",
    "\n",
    "Nous pouvons les dessiner ensemble de manière à ce que les boxplots soient sur la même échelle, et puissent être comparés. Les boxplots comportent: le minimun, le maximum, la médiane, le premier et le troisième quartile..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ee66dac0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_28_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.boxplot();"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a8200d55",
   "metadata": {},
   "source": [
    "Nous pouvons dessiner en donnant la liste des colonnes à afficher."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "b17b5d2b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_30_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.boxplot(['SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth']);"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6aac9e02",
   "metadata": {},
   "source": [
    "On remarque des outliers dans la colonne des `SepalWidth`. Les outliers sont des points en *dehors* de bornes *calculées* indiquées par les moustaches. Ces points sont potentiellement des points *aberrants*. Pour comprendre comment sont calculés les points *extrèmes* lisez les documentations des boîtes à moustache.\n",
    "\n",
    "Affichons le boxplot de la colonne `SepalWidth`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "d54eca1e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_32_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.boxplot(['SepalWidth']);"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "de9e7a33",
   "metadata": {},
   "source": [
    "Nous pouvons grouper les boxplots suivant les valeurs d'une colonne. Vous vous rappelez `groupby`. C'est très utile:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "8ba43011",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_34_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.boxplot(['PetalLength'], by='Name');"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f9db1ca8",
   "metadata": {},
   "source": [
    "Nous remarquons que les iris *Setosa* ont des `PetalLength` bien plus petits que ceux des autres types d'iris."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ebb32bf3",
   "metadata": {},
   "source": [
    "## dessinons des histogrammes - `df.hist`\n",
    "\n",
    "Nous pouvons dessiner les histogrammes de nos dataframes. Ils représentent la distribution des valeurs d'une colonne. Les valeurs de la colonne sont rangées dans des intervalles (ou *bins*) et les nombres de valeurs par intervalles sont affichés."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "5ac004c3",
   "metadata": {
    "cell_style": "center"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 6 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_37_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.hist();"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2cd35d73",
   "metadata": {},
   "source": [
    "On peut dessiner l'histogramme d'une seule colonne, on peut décider du nombre d'intervalles (*bins=*), de la couleur (*color=*)..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "1888332e",
   "metadata": {
    "cell_style": "center"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXIAAAEICAYAAABCnX+uAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAAAT0ElEQVR4nO3df5TldX3f8edrARdljIvBTFegrKeH0pJtpTIlJNp0tphUbSORmhbaJKDxrElTYxpij/GcprQ2iTn1GPvbohhpVEaDSyWUGDmGLbVpON0lGBcJkegq4srvBQZlXdh3/7jfMddhZ+6dO3fmzmd9Ps65Z+79/nzd79x93e/9zvd+N1WFJKldmyYdQJK0Oha5JDXOIpekxlnkktQ4i1ySGmeRS1LjLHJ9R0myP8nLJ52jX5LdSd4w6Rxql0WuiUnysiR/kOTRJA8n+T9J/uY6rv+KJB9cr/VNap069h0/6QD6zpTku4AbgJ8BPgo8C/hbwKFJ5pJa5B65JuUvA1TVNVX1dFV9o6o+WVV/DJDk9UnuTPJIkt9LcsbCjEkqyc8l+UKSB5P8uySbunF/KcnvJ3moG/ehJFtWGi7J+d2nhYNJPpNktm/c7iRv7z5BPJ7kk0lO6Rv/k0m+1GX4lwuHc5K8Angb8I+SzCf5TN8qz1hqedIgFrkm5U+Bp5NcneSVSU5eGJHkQnqFdxHwAuB/A9csmv81wAzwEuBC4PULswO/BrwQ+KvA6cAVKwmW5FTgfwL/Fng+8IvAx5K8oG+yfwy8Dvgeep8mfrGb92zgvwD/BNgKPA84FaCqPgH8KvCRqpqqqhcPWp40DItcE1FVjwEvAwp4L/BAkuuTTAM/DfxaVd1ZVU/RK79z+vfKgV+vqoer6svAu4FLuuXeXVU3VdWhqnoAeBfwt1cY78eBG6vqxqo6UlU3AXuAV/VN85tV9adV9Q16h4bO6Ya/Fvidqvp0VX0T+OXuOQ6y1PKkgSxyTUxX1JdV1WnAdnp70e8GzgD+fXdY4yDwML097VP7Zr+n7/6XunlJMp1kLsm9SR4DPgis9DDFGcCPLay/y/AyenvYC77Wd//rwFR3/4X92arq68BDQ6xzqeVJA1nk2hCq6k+AD9Ar9HuAN1bVlr7bs6vqD/pmOb3v/l8Evtrd/1V6e8B/raq+i97edVYY5x7gtxat/6SqescQ8x4ATlt4kOTZwHf3jfdyoxo7i1wTkeSvJLk8yWnd49PpHR75Q+A9wC8l+d5u3POS/NiiRbwlycndfG8GPtINfy4wDzzaHet+y4Aom5Kc2HfbTG8v/keS/N0kx3XDZxeyDnBtN+8PJHkWvePz/W8k9wHbFv44K42DLyZNyuPA9wG3JnmCXoHvAy6vquuAXwfmusMj+4BXLpr/48Be4HZ6f5i8qhv+r+n9AfTRbviuATkuAb7Rd/uzqrqH3h9Q3wY8QG8P/S0M8e+lqu4A3gTM0ds7nwfu589Pq/zt7udDSW4btDxpGPE/llBrkhRwZlXdPeksgySZAg7Sy/vFCcfRMco9cmnMkvxIkuckOQl4J/BZYP9kU+lYZpFL43chvT++fhU4E7i4/OirNeShFUlqnHvkktS4db1o1imnnFLbtm1bz1V+myeeeIKTTjppYusfVis5oZ2s5hyvVnJCO1mXy7l3794Hq+oFRx0JUFXrdjv33HNrkm6++eaJrn9YreSsaierOcerlZxV7WRdLiewp5bpVg+tSFLjLHJJapxFLkmNs8glqXEWuSQ1ziKXpMZZ5JLUOItckhpnkUtS49b1K/pqw667Dgw97aZDh1c0/SAXnbV18ESSvo175JLUOItckhpnkUtS4yxySWqcRS5JjbPIJalxnn4osbJTLsfNUy61Wu6RS1LjLHJJapxFLkmNs8glqXEDizzJ6UluTvK5JHckeXM3/Iok9ya5vbu9au3jSpIWG+aslaeAy6vqtiTPBfYmuakb9xtV9c61iydJGmRgkVfVAeBAd//xJHcCp651MEnScFJVw0+cbANuAbYDvwBcBjwG7KG31/7IUebZCewEmJ6ePndubm7VoUc1Pz/P1NTUxNY/rEnnPHjo8PATH3oSNp84tnVv2XzC2JbVb9A2XdFzHrP+5zzp3/2wWskJ7WRdLueOHTv2VtXMUvMOXeRJpoD/BfxKVe1KMg08CBTwdmBrVb1+uWXMzMzUnj17hlrfWti9ezezs7MTW/+wJp1zRdcj37+PI9u2j23da/XlmEHbdKN8IWjSv/thtZIT2sm6XM4kyxb5UGetJDkB+BjwoaraBVBV91XV01V1BHgvcN5Kg0uSVm+Ys1YCXAXcWVXv6hvev+v0GmDf+ONJkgYZ5qyVlwI/AXw2ye3dsLcBlyQ5h96hlf3AG9cgnyRpgGHOWvk0kKOMunH8cSRJK+U3OyWpcRa5JDXOIpekxlnkktQ4i1ySGmeRS1LjLHJJapxFLkmNs8glqXHDfEX/O956Xxlv06HD7LrrwJpdCVDSscU9cklqnEUuSY2zyCWpcRa5JDXOIpekxlnkktQ4i1ySGmeRS1LjLHJJapxFLkmNs8glqXEWuSQ1ziKXpMZZ5JLUOItckhpnkUtS4yxySWqcRS5JjbPIJalxA4s8yelJbk7yuSR3JHlzN/z5SW5K8vnu58lrH1eStNgwe+RPAZdX1dnA+cDPJjkbeCvwqao6E/hU91iStM4GFnlVHaiq27r7jwN3AqcCFwJXd5NdDfzoGmWUJC0jVTX8xMk24BZgO/DlqtrSDQ/wyMLjRfPsBHYCTE9Pnzs3N7fq0KOan59nampqxfMdPHR4DdIs49CTsPlEtmw+YX3X21nR8+2yjstaPedBv/t1/x336X/Oo75G11srOaGdrMvl3LFjx96qmllq3uOHXUmSKeBjwM9X1WO97u6pqkpy1HeEqroSuBJgZmamZmdnh13l2O3evZtR1r/rrgPjD7OMTfv3cWTbdmbP2rqu612wkue7kHVc1uo5D/rdr/fvuF//cx71NbreWskJ7WRdTc6hzlpJcgK9Ev9QVe3qBt+XZGs3fitw/0gJJEmrMsxZKwGuAu6sqnf1jboeuLS7fynw8fHHkyQNMsyhlZcCPwF8Nsnt3bC3Ae8APprkp4AvAf9wTRJKkpY1sMir6tNAlhh9wXjjSJJWym92SlLjLHJJapxFLkmNs8glqXEWuSQ1ziKXpMZZ5JLUOItckhpnkUtS4yxySWrc0JexlbQ2+i+hu+nQ4XW7pO5FE7pMssbPPXJJapxFLkmNs8glqXEWuSQ1ziKXpMZZ5JLUOItckhpnkUtS4yxySWqcRS5JjbPIJalxFrkkNc4il6TGWeSS1DgvY6sNZa0u4bqel4eV1pt75JLUOItckhpnkUtS4yxySWrcwCJP8v4k9yfZ1zfsiiT3Jrm9u71qbWNKkpYyzB75B4BXHGX4b1TVOd3txvHGkiQNa2CRV9UtwMPrkEWSNIJU1eCJkm3ADVW1vXt8BXAZ8BiwB7i8qh5ZYt6dwE6A6enpc+fm5saReyTz8/NMTU2teL6Dhw6vQZplHHoSNp/Ils0nrO96Oyt6vl3WDc+cz7Ca19eo/5YmoZWsy+XcsWPH3qqaWWreUYt8GngQKODtwNaqev2g5czMzNSePXsGrm+t7N69m9nZ2RXPt95fJNm0fx9Htm3norO2rut6F6zk+S5k3ejM+UyreX2N+m9pElrJulzOJMsW+UhnrVTVfVX1dFUdAd4LnDfKciRJqzdSkSfpfyt/DbBvqWklSWtr4LVWklwDzAKnJPkK8K+A2STn0Du0sh9449pFlCQtZ2CRV9UlRxl81RpkkSSNwG92SlLjvIztBuZlVyUNwz1ySWqcRS5JjbPIJalxFrkkNc4il6TGWeSS1DiLXJIaZ5FLUuMscklqnEUuSY2zyCWpcRa5JDXOIpekxlnkktQ4i1ySGmeRS1LjLHJJapxFLkmNs8glqXEWuSQ1ziKXpMZZ5JLUOItckhpnkUtS4yxySWqcRS5JjbPIJalxA4s8yfuT3J9kX9+w5ye5Kcnnu58nr21MSdJShtkj/wDwikXD3gp8qqrOBD7VPZYkTcDAIq+qW4CHFw2+ELi6u3818KPjjSVJGlaqavBEyTbghqra3j0+WFVbuvsBHll4fJR5dwI7Aaanp8+dm5sbS/BRzM/PMzU1teL5Dh46vAZplnHoSdh84vquc1StZDXnM2zZfMLI8476b2kSWsm6XM4dO3bsraqZpeY9frUrr6pKsuS7QVVdCVwJMDMzU7Ozs6td5ch2797NKOvfddeB8YdZxqb9+ziybfu6rnNUrWQ15zPNnrV15HlH/bc0Ca1kXU3OUc9auS/JVoDu5/0jLkeStEqjFvn1wKXd/UuBj48njiRppYY5/fAa4P8CZyX5SpKfAt4B/FCSzwMv7x5LkiZg4DHyqrpkiVEXjDmLJGkEfrNTkhpnkUtS41Z9+uF6GccpgJsOHV73Uwklaa25Ry5JjbPIJalxFrkkNc4il6TGWeSS1DiLXJIaZ5FLUuMscklqnEUuSY2zyCWpcRa5JDXOIpekxlnkktQ4i1ySGmeRS1LjLHJJapxFLkmNs8glqXEWuSQ1ziKXpMZZ5JLUOItckhp3/KQDSJqMXXcdGHneTYcOr2r+i87aOvK8q7GazKu1ls/ZPXJJapxFLkmNs8glqXGrOkaeZD/wOPA08FRVzYwjlCRpeOP4Y+eOqnpwDMuRJI3AQyuS1LhU1egzJ18EHgEK+G9VdeVRptkJ7ASYnp4+d25ubqR1HTx0eOSc33LoSdh84uqXs9ZayQntZDXneLWSEzZM1i2bT1h2/Pz8PFNTU0cdt2PHjr3LHbpebZGfWlX3Jvke4CbgTVV1y1LTz8zM1J49e0Za1zjO/9y0fx9Htm1f9XLWWis5oZ2s5hyvVnLCxsk66Dzy3bt3Mzs7e9RxSZYt8lUdWqmqe7uf9wPXAeetZnmSpJUbuciTnJTkuQv3gR8G9o0rmCRpOKs5a2UauC7JwnI+XFWfGEsqSdLQRi7yqvoC8OIxZpEkjcDTDyWpcRa5JDXOIpekxlnkktQ4i1ySGmeRS1LjLHJJapxFLkmNs8glqXEWuSQ1ziKXpMZZ5JLUOItckhpnkUtS4yxySWqcRS5JjbPIJalxFrkkNc4il6TGWeSS1DiLXJIaZ5FLUuMscklqnEUuSY2zyCWpcRa5JDXOIpekxlnkktQ4i1ySGmeRS1LjVlXkSV6R5K4kdyd567hCSZKGN3KRJzkO+M/AK4GzgUuSnD2uYJKk4axmj/w84O6q+kJVfROYAy4cTyxJ0rCOX8W8pwL39D3+CvB9iydKshPY2T2cT3LXKta5WqcAD05w/cNqJSe0k9Wc49VKTmgn63I5z1huxtUU+VCq6krgyrVezzCS7KmqmUnnGKSVnNBOVnOOVys5oZ2sq8m5mkMr9wKn9z0+rRsmSVpHqyny/wecmeRFSZ4FXAxcP55YkqRhjXxopaqeSvLPgN8DjgPeX1V3jC3Z2tgQh3iG0EpOaCerOcerlZzQTtaRc6aqxhlEkrTO/GanJDXOIpekxh2zRZ7kuCR/lOSGo4y7LMkDSW7vbm+YUMb9ST7bZdhzlPFJ8h+6SyD8cZKXbNCcs0ke7duevzyJnF2WLUmuTfInSe5M8v2Lxm+UbToo58S3aZKz+tZ/e5LHkvz8omk2yvYcJuvEt2mX458nuSPJviTXJDlx0fjNST7SbdNbk2wbuNCqOiZvwC8AHwZuOMq4y4D/tAEy7gdOWWb8q4DfBQKcD9y6QXPOHm07Tyjr1cAbuvvPArZs0G06KOeG2aZdnuOArwFnbMTtOWTWiW9Tel+k/CLw7O7xR4HLFk3zT4H3dPcvBj4yaLnH5B55ktOAvwe8b9JZVulC4L9Xzx8CW5JsnXSojSrJ84AfBK4CqKpvVtXBRZNNfJsOmXOjuQD4s6r60qLhE9+eR7FU1o3ieODZSY4HngN8ddH4C+m90QNcC1yQJMst8JgscuDdwL8AjiwzzT/oPgpem+T0ZaZbSwV8Msne7lIGix3tMginrkuybzcoJ8D3J/lMkt9N8r3rGa7Pi4AHgN/sDqu9L8lJi6bZCNt0mJywMbbpgouBa44yfCNsz8WWygoT3qZVdS/wTuDLwAHg0ar65KLJvrVNq+op4FHgu5db7jFX5En+PnB/Ve1dZrLfAbZV1V8HbuLP3/3W28uq6iX0riD5s0l+cEI5BhmU8zZ6H2NfDPxH4H+sc74FxwMvAf5rVf0N4AlgI15eeZicG2Wbkt4X/l4N/PakMgxrQNaJb9MkJ9Pb434R8ELgpCQ/vtrlHnNFDrwUeHWS/fSuyPh3knywf4KqeqiqDnUP3wecu74Rv5Xj3u7n/cB19K4o2W9DXAZhUM6qeqyq5rv7NwInJDllvXPS2xv8SlXd2j2+ll5h9tsI23Rgzg20TaH3Bn5bVd13lHEbYXv2WzLrBtmmLwe+WFUPVNVhYBfwA4um+dY27Q6/PA94aLmFHnNFXlW/VFWnVdU2eh+xfr+qvu0db9ExvFcDd65jxIUMJyV57sJ94IeBfYsmux74ye7MgPPpfQw7sNFyJvkLC8fwkpxH73W17AtvLVTV14B7kpzVDboA+NyiySa+TYfJuVG2aecSlj5UMfHtuciSWTfINv0ycH6S53RZLuCZ/XM9cGl3/7X0OmzZb26u+dUPN4ok/wbYU1XXAz+X5NXAU8DD9M5iWW/TwHXd6+p44MNV9YkkPw1QVe8BbqR3VsDdwNeB123QnK8FfibJU8A3gIsHvfDW0JuAD3Ufsb8AvG4DbtNhcm6Ibdq9ef8Q8Ma+YRtxew6TdeLbtKpuTXItvcM8TwF/BFy5qJ+uAn4ryd30+uniQcv1K/qS1Lhj7tCKJH2nscglqXEWuSQ1ziKXpMZZ5JLUOItckhpnkUtS4/4/VJzalhASF+0AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_39_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.hist('SepalLength', bins = 10, color='lightblue');"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "56f9d646",
   "metadata": {},
   "source": [
    "## dessinons des barcharts (`DataFrame.plot.bar`)\n",
    "\n",
    "On va prendre un exemple qui illustre mieux cette possibilité. Celui des animaux, de leur vitesse et de leur durée de vie."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "e6e9fd7d",
   "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>speed</th>\n",
       "      <th>lifespan</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>snail</th>\n",
       "      <td>0.1</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pig</th>\n",
       "      <td>17.5</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>elephant</th>\n",
       "      <td>40.0</td>\n",
       "      <td>70.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>rabbit</th>\n",
       "      <td>48.0</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>giraffe</th>\n",
       "      <td>52.0</td>\n",
       "      <td>25.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>coyote</th>\n",
       "      <td>69.0</td>\n",
       "      <td>12.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>horse</th>\n",
       "      <td>88.0</td>\n",
       "      <td>28.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          speed  lifespan\n",
       "snail       0.1       2.0\n",
       "pig        17.5       8.0\n",
       "elephant   40.0      70.0\n",
       "rabbit     48.0       1.5\n",
       "giraffe    52.0      25.0\n",
       "coyote     69.0      12.0\n",
       "horse      88.0      28.0"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_animals = pd.DataFrame({'speed' : [0.1, 17.5, 40, 48, 52, 69, 88],\n",
    "                   'lifespan' : [2, 8, 70, 1.5, 25, 12, 28]},\n",
    "                  index = ['snail', 'pig', 'elephant',\n",
    "                           'rabbit', 'giraffe', 'coyote', 'horse'])\n",
    "df_animals"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d0011ab0",
   "metadata": {},
   "source": [
    "On peut avoir des barres verticales:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "4f7b42e7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_43_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_animals.plot.bar();"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8ba177b5",
   "metadata": {},
   "source": [
    "Des barres horizontales:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "282064b4",
   "metadata": {
    "cell_style": "center"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_45_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_animals.plot.barh();"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5f2f0fa3",
   "metadata": {},
   "source": [
    "On peut indiquer la vitesse par durée de vie:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "2e58bf49",
   "metadata": {
    "cell_style": "center"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_47_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_animals.plot.bar(x='lifespan', y='speed');"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "470e5b52",
   "metadata": {},
   "source": [
    "## dessiner des paires de colonnes - `df.plot.scatter`\n",
    "\n",
    "Dessiner en 2D les colonnes les unes par rapport aux autres peut mettre en valeur des informations intéressantes, surtout quand on ajoute des informations d'autres colonnes par des couleurs ou des tailles de points."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d9a5af8e",
   "metadata": {},
   "source": [
    "Dans le jeu des données des iris, on peut dessiner une colonne par rapport à une autre en mettant des couleurs différentes aux points suivant le type des iris."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "4c9b57ee",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_50_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.plot.scatter(x='SepalLength', y='SepalWidth');"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7f18636e",
   "metadata": {},
   "source": [
    "Ce serait bien plus intéressant si on ajoute le type en utilisant une couleur. Par exemple on va considérer que les 3 types, donnés par des entiers, sont 3 couleurs différentes i.e. ces 3 valeurs seront des codes de couleur différents dans la table de couleur par défaut.\n",
    "\n",
    "Il faut utiliser le paramètre *c=* de la fonction `scatter`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "70a796a4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_52_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['SepalLength'], df['SepalWidth'], c=df['Type']);"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "35eadb3b",
   "metadata": {},
   "source": [
    "On va donner aux points, une taille proportionnelle à la largeur des pétales."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "f11d2605",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/python-numerique/python-numerique/notebooks/_build/jupyter_execute/4-04-matplotlib-pandas-dataframe_54_0.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['SepalLength'], df['SepalWidth'], c=df['Type'], s=df['PetalWidth']*50); # parameter s"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a0823196",
   "metadata": {},
   "source": [
    "## Exercice"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c3434ac9",
   "metadata": {},
   "source": [
    "### visualisation de données sur des vins italiens"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2df7ee8e",
   "metadata": {},
   "source": [
    "Ces données sont le résultat d'analyses chimiques de vins, cultivés dans une même région d'Italie, mais issus de trois cultivateurs différents. Les données sont les quantités, trouvées dans les vins, de 13 constituants.\n",
    "\n",
    "Le fichier s'appelle `wine.csv`. La première ligne contient les noms des colonnes et la première colonne identifie le cultivaleur 1, 2 et 3.\n",
    "   1. lisez le fichier *csv* en ne gardant que les colonnes \\['cultivator', 'alcohol', 'malic-acid', 'ash','total-phenols', 'flavanoids','Color-intensity', 'Hue'\\]  \n",
    "   (indice utilisez: `use_cols`)\n",
    "   1. afficher le header de la dataframe\n",
    "   1. afficher les types déterminés par `pandas`\n",
    "   1. afficher les statistiques simples (minimum, maximum, moyenne, écart-type...)\n",
    "   1. plottez la dataframe en lui passant le paramètre *figsize=(10, 10)*\n",
    "   1. plottez la dataframe restreinte aux deux colonnes \\['flavanoids', 'cultivator'\\]\n",
    "   1. visualisez les boxplots de la dataframe utilisez la fonction *plt.xticks(rotation=90)* pour mieux voir les labels des abscisses\n",
    "   1. visualisez des histogrammes avec des regroupements de 20 éléments\n",
    "   1. afficher l'alcool en fonction de l'acide malique avec comme couleur les numéros des cultivateurs."
   ]
  }
 ],
 "metadata": {
  "jupytext": {
   "cell_metadata_filter": "all,-hidden,-heading_collapsed",
   "cell_metadata_json": true,
   "notebook_metadata_filter": "all,-language_info,-toc,-jupytext.text_representation.jupytext_version,-jupytext.text_representation.format_version",
   "text_representation": {
    "extension": ".md",
    "format_name": "myst"
   }
  },
  "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": "3.9.5"
  },
  "notebookname": "matplotlib & pandas",
  "source_map": [
   15,
   25,
   40,
   44,
   49,
   52,
   56,
   64,
   68,
   72,
   74,
   78,
   80,
   84,
   86,
   90,
   96,
   105,
   108,
   112,
   114,
   118,
   120,
   124,
   130,
   132,
   136,
   140,
   146,
   148,
   152,
   154,
   160,
   162,
   166,
   168,
   172,
   178,
   182,
   186,
   190,
   196,
   202,
   206,
   208,
   212,
   216,
   220,
   224,
   230,
   234,
   236,
   242,
   244,
   248,
   250,
   254,
   258
  ],
  "version": "1.0"
 },
 "nbformat": 4,
 "nbformat_minor": 5
}