Skip to content

M
mooc-rr
Commit 88f38cea authored by 61cbc2a4c93a3237a08f8b8e6c523229's avatar 61cbc2a4c93a3237a08f8b8e6c523229
Browse files
Options

a

parent 9b7540a5
Show whitespace changes
Inline Side-by-side
Showing with 22795 additions and 0 deletions
Untitled Folder/StatGradeReport-Bioinfo.ipynb 0 → 100644
View file @ 88f38cea
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"hideCode": false,
"hidePrompt": false
},
"source": [
"# Analyse des Quiz et exercices du Mooc Bioinformatique/session selg-paced\n",
"A partir des rapports de FUN de type inria_41016_self-paced_grade_report*.csv\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"hideCode": false,
"hidePrompt": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Fichier le plus récent : inria_41003_selfpaced_grade_report_2020-06-02-0932.csv\n"
]
}
],
"source": [
"## Projet Maman 2\n",
"\n",
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"# liste_fichiers=fichiers csv à prendre en compte\n",
"# le premier fichier est le plus récent, celui qui est utilisé pour les statistiques générales et les QuizP\n",
"liste_fichiers=['inria_41003_selfpaced_grade_report_2020-06-02-0932.csv']\n",
"\n",
"donnees = pd.read_csv(liste_fichiers[0])\n",
"from IPython.display import Markdown, display\n",
"def printmd(string):\n",
" display(Markdown(string))\n",
"\n",
"def printBold(string):\n",
" printmd('**' + string + '**')\n",
"\n",
"print (f\"Fichier le plus récent : {liste_fichiers[0]}\")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"hideCode": false,
"hidePrompt": false
},
"outputs": [
{
"data": {
"text/markdown": [
"**Chiffres clé de la session 3 du Mooc RR à la date du 2020/06/02 :**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9418 élèves inscrits (session1 : 3589 ; session2 : 2192)\n",
"2733 élèves ont commencé les exercices (grade>0) = 29.02% des inscrits (session1 : 21,52% ; session2 : 16,93%)\n",
"2527 élèves ont fait le 1er quiz (quiz1>0) = 26.83% des inscrits (session1 : 17,89% ; session2 : 14,69%)\n",
"955 élèves ont au dessus de la moyenne (grade>0.5) = 10.14% des inscrits: (session1 : 291 ; session2 : 135)\n",
"Gitlab/Jupyter : 573 forks le 26/05 (456 forks 05/05), (session1 : 601 ; session2 : 283)\n",
"Forum: 925 utilisateurs, 92 topics, 420 posts le 05/05 (226 le 9/4)\n"
]
}
],
"source": [
"## Données supplémentaires\n",
"\n",
"liste_date=[(((i.split('_'))[5].split('-'))[:3]) for i in liste_fichiers]\n",
"exos=sum(donnees.loc[:,\"grade\"]>0)\n",
"quiz1=sum(donnees.loc[:,\"Quiz 01\"]>0)\n",
"moyenne=sum(donnees.loc[:,\"grade\"]>0.5)\n",
"nb_inscrits=len(donnees)\n",
"printBold(f\"Chiffres clé de la session 3 du Mooc RR à la date du {'/'.join(liste_date[0])} :\")\n",
"print(f\"{nb_inscrits} élèves inscrits (session1 : 3589 ; session2 : 2192)\")\n",
"print(f\"{exos} élèves ont commencé les exercices (grade>0) = {round(100*exos/nb_inscrits,2)}% des inscrits (session1 : 21,52% ; session2 : 16,93%)\")\n",
"print(f\"{quiz1} élèves ont fait le 1er quiz (quiz1>0) = {round(100*quiz1/nb_inscrits,2)}% des inscrits (session1 : 17,89% ; session2 : 14,69%)\")\n",
"print(f\"{moyenne} élèves ont au dessus de la moyenne (grade>0.5) = {round(100*moyenne/nb_inscrits,2)}% des inscrits: (session1 : 291 ; session2 : 135)\")\n",
"print(\"Gitlab/Jupyter : 573 forks le 26/05 (456 forks 05/05), (session1 : 601 ; session2 : 283)\")\n",
"print(\"Forum: 925 utilisateurs, 92 topics, 420 posts le 05/05 (226 le 9/4)\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"hideCode": false,
"hidePrompt": false,
"scrolled": true
},
"outputs": [
{
"data": {
"text/markdown": [
"**Participation aux quiz et exercices du Mooc**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2527, 2403, 2330, 1832, 2010, 1814, 1266, 1652, 1538, 1577, 1083, 1405, 1358, 1264, 1145, 530, 1074, 1183, 1062, 934, 957, 1053, 824, 1005, 976, 975, 906, 851, 899, 988, 996, 992, 926, 728, 871, 834, 882, 824, 257, 838, 867, 856, 832, 828, 815, 815, 791]\n",
" Type Nb %/inscrits Id Label\n",
"0 Quiz 2527 26.83% 1 Semaine 1\n",
"1 Quiz 2403 25.51% 2 Semaine 1\n",
"2 Quiz 2330 24.74% 3 Semaine 1\n",
"3 Quiz 1832 19.45% 4 Semaine 1\n",
"4 Quiz 2010 21.34% 5 Semaine 1\n",
"5 Quiz 1814 19.26% 6 Semaine 1\n",
"6 Quiz 1266 13.44% 7 Semaine 1\n",
"7 Quiz 1652 17.54% 8 Semaine 1\n",
"8 Quiz 1538 16.33% 9 Semaine 1\n",
"9 Quiz 1577 16.74% 10 Semaine 1\n",
"10 Quiz 1083 11.5% 11 Semaine 2\n",
"11 Quiz 1405 14.92% 12 Semaine 2\n",
"12 Quiz 1358 14.42% 13 Semaine 2\n",
"13 Quiz 1264 13.42% 14 Semaine 2\n",
"14 Quiz 1145 12.16% 15 Semaine 2\n",
"15 Quiz 530 5.63% 16 Semaine 2\n",
"16 Quiz 1074 11.4% 17 Semaine 2\n",
"17 Quiz 1183 12.56% 18 Semaine 2\n",
"18 Quiz 1062 11.28% 19 Semaine 2\n",
"19 Quiz 934 9.92% 20 Semaine 2\n",
"20 Quiz 957 10.16% 21 Semaine 3\n",
"21 Quiz 1053 11.18% 22 Semaine 3\n",
"22 Quiz 824 8.75% 23 Semaine 3\n",
"23 Quiz 1005 10.67% 24 Semaine 3\n",
"24 Quiz 976 10.36% 25 Semaine 3\n",
"25 Quiz 975 10.35% 26 Semaine 3\n",
"26 Quiz 906 9.62% 27 Semaine 3\n",
"27 Quiz 851 9.04% 28 Semaine 3\n",
"28 Quiz 899 9.55% 29 Semaine 3\n",
"29 Quiz 988 10.49% 30 Semaine 3\n",
"30 Quiz 996 10.58% 31 Semaine 4\n",
"31 Quiz 992 10.53% 32 Semaine 4\n",
"32 Quiz 926 9.83% 33 Semaine 4\n",
"33 Quiz 728 7.73% 34 Semaine 4\n",
"34 Quiz 871 9.25% 35 Semaine 4\n",
"35 Quiz 834 8.86% 36 Semaine 4\n",
"36 Quiz 882 9.37% 37 Semaine 4\n",
"37 Quiz 824 8.75% 38 Semaine 4\n",
"38 Quiz 257 2.73% 39 Semaine 4\n",
"39 Quiz 838 8.9% 40 Semaine 4\n",
"40 Quiz 867 9.21% 41 Semaine 5\n",
"41 Quiz 856 9.09% 42 Semaine 5\n",
"42 Quiz 832 8.83% 43 Semaine 5\n",
"43 Quiz 828 8.79% 44 Semaine 5\n",
"44 Quiz 815 8.65% 45 Semaine 5\n",
"45 Quiz 815 8.65% 46 Semaine 5\n",
"46 Quiz 791 8.4% 47 Semaine 5\n"
]
}
],
"source": [
"## Tableau\n",
"printBold(\"Participation aux quiz et exercices du Mooc\")\n",
"## Semaine 1 : Quiz1 à Quiz10\n",
"## Semaine 2 : Quiz11 à Quiz20\n",
"## Semaine 3 : Quiz21 à Quiz30\n",
"## Semaine 4 : Quiz31 à Quiz40\n",
"## Semaine 5 : Quiz41 à Quiz47\n",
"\n",
"Type_init= list(donnees.columns[3:13])+list(donnees.columns[13:23])+list(donnees.columns[23:33])+list(donnees.columns[33:43])+list(donnees.columns[43:50])\n",
"Type=[i.split()[0] for i in Type_init]\n",
"##Id=[int(i.split()[1]) for i in Type_init[:-1]]+[4]\n",
"Id=[int(i.split()[1]) for i in Type_init]\n",
"\n",
"Num=[(sum(donnees.loc[:,type]>0)) for type in Type_init]\n",
"print(Num)\n",
"Label=[\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\n",
" \"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\n",
" \"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\n",
" \"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\n",
" \"Semaine 5\",\"Semaine 5\",\"Semaine 5\",\"Semaine 5\",\"Semaine 5\",\"Semaine 5\",\"Semaine 5\"]\n",
"pourcentage=[f'{round(Num[i]*100/nb_inscrits,2)}%' for i in range(len(Num))]\n",
"tableau=pd.DataFrame({'Type':Type,\"Id\":Id,\"%/inscrits\":pourcentage,\"Nb\":Num,\"Label\":Label})\n",
"col=[\"Type\",\"Nb\",\"%/inscrits\",\"Id\",\"Label\"]\n",
"tableau = tableau.loc[:, col]\n",
"print(tableau)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"hideCode": false,
"hidePrompt": false,
"scrolled": true
},
"outputs": [],
"source": [
"### Graphs deuxième version\n",
"\n",
"def Graphique(*donnee_toutes):\n",
" fig1,(ax1,ax2)=plt.subplots(1,2,figsize=(25,7),sharey='all')\n",
" for donnee in donnee_toutes:\n",
" donnees = pd.read_csv(donnee)\n",
" Type_init= list(donnees.columns[3:13])+list(donnees.columns[13:23])+list(donnees.columns[23:33])+list(donnees.columns[33:43])+list(donnees.columns[43:50])\n",
" Type=[i.split()[0] for i in Type_init]\n",
" Id=[int(i.split()[1]) for i in Type_init[:-1]]+[4]\n",
" Num=[(sum(donnees.loc[:,type]>0)) for type in Type_init]\n",
" Label=[\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\"Semaine 1\",\n",
" \"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\"Semaine 2\",\n",
" \"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\"Semaine 3\",\n",
" \"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\",\"Semaine 4\"] \n",
" tableau=pd.DataFrame({'Type':Type,\"Id\":Id,\"Nb\":Num,\"Label\":Label})\n",
" col=[\"Type\",\"Nb\",\"Id\",\"Label\"]\n",
" tableau = tableau.loc[:, col]\n",
" \n",
" ##ax1.plot(Id[-4:],tableau.loc[(tableau.loc[:,\"Type\"]==\"Exercices\") ,\"Nb\"],\"ro-\")\n",
"\n",
" ax2.plot(tableau.loc[(tableau.loc[:,\"Label\"]==\"Semaine 1\") & (tableau.loc[:,\"Type\"]==\"Quiz\"),\"Id\"],list(tableau.loc[(tableau.loc[:,\"Type\"]==\"Quiz\") & (tableau.loc[:,\"Label\"]==\"Semaine 1\"),\"Nb\"]),\"ro-\")\n",
" ax2.plot(tableau.loc[(tableau.loc[:,\"Label\"]==\"Semaine 2\") & (tableau.loc[:,\"Type\"]==\"Quiz\"),\"Id\"],list(tableau.loc[(tableau.loc[:,\"Type\"]==\"Quiz\") & (tableau.loc[:,\"Label\"]==\"Semaine 2\"),\"Nb\"]),\"bo-\")\n",
" ax2.plot(tableau.loc[(tableau.loc[:,\"Label\"]==\"Semaine 3\") & (tableau.loc[:,\"Type\"]==\"Quiz\"),\"Id\"],list(tableau.loc[(tableau.loc[:,\"Type\"]==\"Quiz\") & (tableau.loc[:,\"Label\"]==\"Semaine 3\"),\"Nb\"]),\"go-\")\n",
" ax2.plot(tableau.loc[(tableau.loc[:,\"Label\"]==\"Semaine 4\") & (tableau.loc[:,\"Type\"]==\"Quiz\"),\"Id\"],list(tableau.loc[(tableau.loc[:,\"Type\"]==\"Quiz\") & (tableau.loc[:,\"Label\"]==\"Semaine 4\"),\"Nb\"]),\"mo-\")\n",
" ##ax2.plot(tableau.loc[(tableau.loc[:,\"Label\"]==\"Semaine 5\") & (tableau.loc[:,\"Type\"]==\"Quiz\"),\"Id\"],list(tableau.loc[(tableau.loc[:,\"Type\"]==\"Quiz\") & (tableau.loc[:,\"Label\"]==\"Semaine 5\"),\"Nb\"]),\"xo-\")\n",
" \n",
" \n",
" \n",
" ax2.legend([\"Semaine 1\",\"Semaine 2\",\"Semaine 3\",\"Semaine 4\"])\n",
" #ax1.set_title(\"Exercices\")\n",
" ax2.set_title(\"Quiz\")\n",
" fig1.text(0.5, 0.02, 'Id', ha='center',size=\"xx-large\")\n",
" fig1.text(0.09,0.5,\"Nombre de participants\",ha='center',rotation='vertical',size=\"xx-large\")\n",
" fig1.text(0.13,0.06,\"Semaine 1\",color=\"red\")\n",
" fig1.text(0.24,0.06,\"Semaine 2\",color=\"blue\")\n",
" fig1.text(0.34,0.06,\"Semaine 3\",color=\"green\")\n",
" fig1.text(0.34,0.06,\"Semaine 4\",color=\"green\")\n",
" fig1.suptitle(\"Graphe des participants aux exercices et quiz\",fontsize=40,y=1.05)\n",
" #ax1.xaxis.set_ticks(range(1,4))\n",
" ax2.xaxis.set_ticks(range(17))\n",
" #ax1.grid()\n",
" ax2.grid()\n",
" plt.show()\n",
" \n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"hideCode": false,
"hidePrompt": false
},
"outputs": [],
"source": [
"##printBold(\"Date des courbes affichées :\")\n",
"##for i in liste_date:\n",
" ## print('/'.join(i))\n",
"##Graphique(*liste_fichiers)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"hideCode": false,
"hidePrompt": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Type Nb %/inscrits Id Label\n",
"0 Quiz 2527 26.83% 1 Semaine 1\n",
"1 Quiz 2403 25.51% 2 Semaine 1\n",
"2 Quiz 2330 24.74% 3 Semaine 1\n",
"3 Quiz 1832 19.45% 4 Semaine 1\n",
"4 Quiz 2010 21.34% 5 Semaine 1\n",
"5 Quiz 1814 19.26% 6 Semaine 1\n",
"6 Quiz 1266 13.44% 7 Semaine 1\n",
"7 Quiz 1652 17.54% 8 Semaine 1\n",
"8 Quiz 1538 16.33% 9 Semaine 1\n",
"9 Quiz 1577 16.74% 10 Semaine 1\n",
"10 Quiz 1083 11.5% 11 Semaine 2\n",
"11 Quiz 1405 14.92% 12 Semaine 2\n",
"12 Quiz 1358 14.42% 13 Semaine 2\n",
"13 Quiz 1264 13.42% 14 Semaine 2\n",
"14 Quiz 1145 12.16% 15 Semaine 2\n",
"15 Quiz 530 5.63% 16 Semaine 2\n",
"16 Quiz 1074 11.4% 17 Semaine 2\n",
"17 Quiz 1183 12.56% 18 Semaine 2\n",
"18 Quiz 1062 11.28% 19 Semaine 2\n",
"19 Quiz 934 9.92% 20 Semaine 2\n",
"20 Quiz 957 10.16% 21 Semaine 3\n",
"21 Quiz 1053 11.18% 22 Semaine 3\n",
"22 Quiz 824 8.75% 23 Semaine 3\n",
"23 Quiz 1005 10.67% 24 Semaine 3\n",
"24 Quiz 976 10.36% 25 Semaine 3\n",
"25 Quiz 975 10.35% 26 Semaine 3\n",
"26 Quiz 906 9.62% 27 Semaine 3\n",
"27 Quiz 851 9.04% 28 Semaine 3\n",
"28 Quiz 899 9.55% 29 Semaine 3\n",
"29 Quiz 988 10.49% 30 Semaine 3\n",
"30 Quiz 996 10.58% 31 Semaine 4\n",
"31 Quiz 992 10.53% 32 Semaine 4\n",
"32 Quiz 926 9.83% 33 Semaine 4\n",
"33 Quiz 728 7.73% 34 Semaine 4\n",
"34 Quiz 871 9.25% 35 Semaine 4\n",
"35 Quiz 834 8.86% 36 Semaine 4\n",
"36 Quiz 882 9.37% 37 Semaine 4\n",
"37 Quiz 824 8.75% 38 Semaine 4\n",
"38 Quiz 257 2.73% 39 Semaine 4\n",
"39 Quiz 838 8.9% 40 Semaine 4\n",
"40 Quiz 867 9.21% 41 Semaine 5\n",
"41 Quiz 856 9.09% 42 Semaine 5\n",
"42 Quiz 832 8.83% 43 Semaine 5\n",
"43 Quiz 828 8.79% 44 Semaine 5\n",
"44 Quiz 815 8.65% 45 Semaine 5\n",
"45 Quiz 815 8.65% 46 Semaine 5\n",
"46 Quiz 791 8.4% 47 Semaine 5\n"
]
},
{
"data": {
"text/markdown": [
"**Participation aux quiz avec le rapport le plus récent**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABJwAAAHcCAYAAACTTrAXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAIABJREFUeJzs3Xt8VtWZ6PHfIpDQiAgEb4iSQNHBlBAbbNEOksrV2FGUKk7x0qlKT7G20rH1OOjUSzNjZzpW7amlWDham6r1wtAq0BYBoUOgGA4qKBRtw8WiBSsIEpDLOn/sN2mAAAHeN4Hw+34++bx7r73Xs5/3xf7R57OetUOMEUmSJEmSJCldWjV3ApIkSZIkSWpZLDhJkiRJkiQprSw4SZIkSZIkKa0sOEmSJEmSJCmtLDhJkiRJkiQprSw4SZIkSZIkKa0sOEmSJEmSJCmtLDhJkqQjTghhaQih9DBj5IcQYgihdZrSkiRJUiNZcJIkSWkXQvhiCOG1EMKWEMI7IYSHQwgnNHZ+jLEwxjg7gynuVwihXwjhtyGEv4YQ1oUQng4hnFrvegghfDeE8F7q7z9CCCF17aQQwhMhhD+HEDaGEP4nhPDpPeJ/IYSwMoTwYQjhv0MInfa4nh1CWB9CaBdCyAkhTAohfJD6Lb+xx71ZIYTvpJ63KYTw/0IIHfa45zchhCGp47GpOBtTcXNS4zkhhImpvGrjXJTeX1aSJB0rLDhJkqS0CiH8M/Bd4JvACUA/IB/4TQihTTOmdjA6AhNI8u4GbAL+b73ro4HhQB+gCPgc8OXUtXbAQqAE6AQ8BrwQQmgHEEIoBH4MXAOcDGwBHt7j+RcAi2OMm4G7gJ6pPD4LfCuEMKzevXcD5wPnAe1TcbfWXgwhHJfK5aUQwlDgfwMDU9+te2o+QGtgNTCA5N/tTuAXIYT8A/5akiRJewgxxubOQZIktRAhhPbAn4EvxRh/UW+8HfBH4JsxxsdCCI8Ca2KMd6SulwI/izF2TZ1XAzfEGGeEEDaQFEMAApALFMQYq/d4dhZJoeuLwAfAfwH/B2gTY9xRP2bq/ruAj8cYr27E9/ok8FKM8fjU+Tzg0RjjhNT59cCNMcZ++5j/AfDZGGNVCOHfgPwY4xdS13oAbwB5McZNqbH7U7/P/SGEt4F/ijH+JnXtXqBnjPGqEEJHkiJRnxjjW/t49iWp731JCOHnQHWM8V9S1wYCFTHGU/Yx91Xg7hjjswf6jSRJkupzhZMkSUqn84G2wHP1B1MrdaYBQw42YIyxQ4yxXYyxHfAgMBd4u4FbbyRZaXQO0Bf4/ME+az8uAJbWOy8EXql3/kpqbC8hhGIgG3izobmpQtFHwJn1ppWRrIrqCHTZz7N6AzuAz6fa5P4QQrhpjxTKgBf2k/fJIYS8BvI+OZXT0j2vSZIkHYgFJ0mSlE6dgfUxxh0NXFsLnHiogUMII4EvACNijNsbuOVK4IEY4+oY41+Bfz/UZ+3x3CLgX0laBGu1AzbWO98ItKvdx6ne3PbA4ySrhDbuY27t/NrVU91JVmUtT90Lez/r+NRxV5L2tzOBApIi210hhMH17r8ImLqfvKkXrzbvNkAF8FiMcRmSJEkHyYKTJElKp/VA5328Ge5UYN2hBA0hnEPSHndZjHFfMbqQtJfVWnkoz9rjuR8nWZn19Rjj3HqXNpPsl1SrPbA51turIITwMeBXwPwY47/vZ27t/E2p44v5W4Foc73rDd1bk/q8J8ZYE2N8FXiSZFUTIYTewAcxxtrfpaG8qRePEEIrkiLZR8BXkSRJOgQWnCRJUjpVAtuAy+sPpjauvgh4KTX0IcleTLUa3EMoNfdEYDLw1Rjj/9vPs9cCp9c7P2OP641+Zuq53YAZwL0xxsf3uLyUZMPwWn2o13qWevPbf5O0/n1596m7z02taMoB/pAaqmuBizG+n/pe+3rWq6nPfW3KWb+dbl95vxtjfC+VSwAmkmxmvq+VZJIkSQdkwUmSJKVNqm3sbuAHIYRhIYQ2qbecPU2y+qkidetioCyE0CmEcApwS0PxUiulniXZ2PqpAzz+F8DXQghdU3sf/e89ri8GrkrltN89nkIIpwEzgR/GGMc3cMtPgW+EEE4LIXQB/hl4NDW3DfAMyeqja2OMu/aYWwH8Qwihf6oQdw/wXIxxU2pV1KeA2Xs8644QQscQwt+R7FX1KNTt/zQXGBdCyAkh9AJGAs+n5tZfLVUb6/oQwtmp3+iO2lgpPwJ6Af8QY6xBkiTpEFlwkiRJaRVj/A/gX4DvkbRq/YlkZdGgGOOHqdseJ9mwuhr4DbCvYlJXoD9wSwhhc72/PVcvATwC/DoVdxF7bFwO3An0AN4nKYr9fD9f4wagO/Dt+s+td/3HJO1yrwFLSFYR/Th17XySzcuHABvqze+f+n2WAv+LpPD0F5L9k8ak5g4EKmOMW+s969vAWyQtgi8B/xljnF7v+j8C3YD3UnncGWN8MYRwAknxaF7tjal5/wHMSsVbmYpfu6Lry0Ax8E69vEft53eSJElqUKi31YAkSVLahRC+RFLg+UyMcVVz53MkCyE8DCyJMT6chlhXAp+PMV55+JlJkiQdnIY29JQkSUqbGOOkEMJ2kpU/Fpz2bzHJyql02AB8P02xJEmSDoornCRJkiRJkpRW7uEkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0suAkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0suAkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0suAkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0suAkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0suAkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0suAkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0suAkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0suAkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0suAkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0suAkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0suAkSZIkSZKktLLgJEmSJEmSpLSy4CRJkiRJkqS0at3cCWRK586dY35+fnOncdg+/PBDjjvuuKMmbiZjG9e4xjWucVtW3EzGNq5xjWtc47asuJmMbVzjNkXclqSqqmp9jPHEA94YY2yRfyUlJbElmDVr1lEVN5OxjWtc4xrXuC0rbiZjG9e4xjWucVtW3EzGNq5xmyJuSwK8HBtRl7GlTpIkSZIkSWllwUmSJEmSJElpZcFJkiRJkiRJadViNw2XJEmSJEkt1/bt21mzZg1bt25NW8wTTjiBN954I23xjmZt27ala9eutGnT5pDmW3CSJEmSJElHnTVr1nD88ceTn59PCCEtMTdt2sTxxx+fllhHsxgj7733HmvWrKGgoOCQYthSJ0mSJEmSjjpbt24lLy8vbcUm/U0Igby8vMNaPWbBSZIkSZIkHZUsNmXO4f62FpwkSZIkSZKUVhacJEmSJEmSDkF5eTmFhYUUFRVRXFzMggULMvq8srIyNmzYcNhxli1bxnnnnUdOTg7f+9730pDZ3tw0XJIkSZIktXwVFTBuHKxaBWecAeXlMGrUIYerrKzk+eefZ9GiReTk5LB+/Xo++uijNCa8t6lTp6YlTqdOnXjooYf47//+77TEa4grnCRJkiRJUstWUQGjR8PKlRBj8jl6dDJ+iNauXUvnzp3JyckBoHPnznTp0gWAqqoqBgwYQElJCUOHDmXt2rUAlJaWMnbsWC644AJ69erFwoULufzyy+nZsyd33HFHXezhw4dTUlJCYWEhEyZMqBvPz89n/fr1VFdX06tXL2688UYKCwsZMmQINTU1ALz11lsMGzaMkpIS+vfvz7Jly/bK/aSTTuLcc8+lTZs2h/z9D8QVTpIkSZIk6eh2yy2wePG+r8+fD9u27T62ZQtcfz088kjd0Md27oSsrOSkuBgeeGCfIYcMGcI999zDmWeeyaBBgxg5ciQDBgxg+/bt3HzzzUyZMoUTTzyRp556inHjxjFp0iQAsrOzmTNnDg8++CCXXnopVVVVdOrUiR49ejB27Fjy8vKYNGkSnTp1oqamhnPPPZcRI0aQl5e32/NXrFjBE088wSOPPMKVV17Js88+y9VXX83o0aMZP348PXv2ZMGCBYwZM4aZM2ce3O+ZBhacJEmSJElSy7ZnselA443Qrl07qqqqmDt3LrNmzWLkyJHcd9999O3blyVLljB48GAAdu7cyamnnlo375JLLgGgd+/eFBYW1l3r3r07q1evJi8vj4ceeojJkycDsHr1alasWLFXwamgoIDi4mIASkpKqK6uZvPmzcybN48rrrii3lc89O94OCw4HalSvaUD0tRbKkmSJElSi7WflUgA5OcnbXR76tYNZs+uO63ZtInjjz++0Y/NysqitLSU0tJSevfuzWOPPVbXCldZWdngnNoWvFatWtUd157v2LGD2bNnM2PGDCorK8nNzaW0tJStW7fuM05tHjU1NezatYsOHTqweH+rvZqIezgdier1loY09ZZKkiRJknTMKi+H3Nzdx3Jzk/FDtHz5clasWFF3vnjxYrp168ZZZ53FunXr6gpO27dvZ+nSpY2Ou3HjRjp27Ehubi7Lli1j/vz5jZ7bvn17CgoKePrppwGIMfLKK680en46WXA6Eo0bl/SS1rdlSzIuSZIkSZIOzqhRMGFCsqIphORzwoTD6iTavHkz1113HWeffTZFRUW8/vrr3HXXXWRnZ/PMM89w22230adPH4qLi5k3b16j4w4bNowdO3ZQVFTEnXfeSb9+/Q4qr4qKCiZOnEifPn0oLCxkypQpe93zzjvv0LVrV+6//36+853v0LVrVz744IODes6BZKylLoRwOvBT4BRgFzAhxvhgCOEu4EZgXerWf4kxTk3NuR24HtgJfC3G+OvUeAnwKPAxYCrw9RhjzFTuzW7VqoMblyRJkiRJ+zdqVFq3qikpKdlnIam4uJg5c+bsNT67XvtebSteQ9emTZvWYNzq6mogeSPekiVL6sZvvfXWuuOCggKmT5++39xPOeUU1qxZs997DlcmVzjtAP45xtgL6AfcFEI4O3Xt+zHG4tRfbbHpbOAqoBAYBjwcQkhtDc+PgNFAz9TfsAzm3fzOOKPh8exseO+9ps1FkiRJkiTpIGWs4BRjXBtjXJQ63gS8AZy2nymXAk/GGLfFGP8EvAl8KoRwKtA+xliZWtX0U2B4pvI+IjTUW5qdDTt2wHnnwZtvNk9ekiRJkiRJjdAkeziFEPKBc4AFqaGvhhBeDSFMCiF0TI2dBqyuN21Nauy01PGe4y1Xvd7SWNtbOmkSvPQSvP8+9OsHv/tdc2cpSZIkSZLUoJDprZBCCO2Al4DyGONzIYSTgfVABO4FTo0xfimE8EOgMsb4s9S8iST7Na0C/j3GOCg13h/4VozxHxp41miS1jtOPvnkkieffDKj360pbN68mXbt2tWdt337bYpuv52277zDsm9+k78MHpyWuOmUqdjGNa5xjWvclhU3k7GNa1zjGte4LStuJmMb9+iNe9ppp/Hxj388rXF37txJVlbWgW88Rrz55pts3Lhxt7HPfvazVTHGvgecHGPM2B/QBvg18I19XM8HlqSObwdur3ft18B5wKnAsnrj/wj8+EDPLikpiS3BrFmz9h78619jLC2NEWK8664Yd+1KT9w0yVRs4xrXuMY1bsuKm8nYxjWucY1r3JYVN5OxjXv0xn399dfTHveDDz5Ie8yjWUO/MfBybERNKGMtdSGEAEwE3ogx3l9v/NR6t10G1G6r/kvgqhBCTgihgGRz8N/HGNcCm0II/VIxrwX2fqffsaRjR/j1r+GLX4S77oJrr4Vt25o7K0mSJEmSJCCzezh9BrgGuDCEsDj1Vwb8RwjhtRDCq8BngbEAMcalwC+A14HpwE0xxp2pWF8BfkKykfhbQMPvBzyWZGcn+zqVl8PPfgaDB/sGO0mSJEmSmlB5eTmFhYUUFRVRXFzMggULDjzpMJSVlbFhw4bDjlNRUUFRURFFRUWcf/75vPLKK2nIbnet0x4xJcb4OyA0cGnqfuaUA+UNjL8MfCJ92bUQIcC//At0756sdjrvPHjhBejZs7kzkyRJkiTpiFJRAePGwapVcMYZyfqNUaMOPV5lZSXPP/88ixYtIicnh/Xr1/PRRx+lL+EGTJ26z5LKQSkoKOCll16iY8eOTJs2jdGjR6e9WNYkb6lThl11Fcyc+bc32M2d29wZSZIkSZJ0xKiogNGjYeVKiDH5HD06GT9Ua9eupXPnzuTk5ADQuXNnunTpAkBVVRUDBgygpKSEoUOHsnbtWgBKS0sZO3YsF1xwAb169WLhwoVcfvnl9OzZkzvuuKMu9vDhwykpKaGwsJAJEybUjefn57N+/Xqqq6vp1asXN954I4WFhQwZMoSamhoA3nrrLYYNG0ZJSQn9+/dn2bJle+V+/vnn07FjRwD69evHmjVrDv2H2IeMrXBSEzv/fJg/Hy6+GAYNgokT4eqrmzsrSZIkSZIy7pZbYPHifV+fP3/vrY+3bIHrr4dHHvnb2M6dH6P2JXXFxfDAA/uOOWTIEO655x7OPPNMBg0axMiRIxkwYADbt2/n5ptvZsqUKZx44ok89dRTjBs3jkmTJgGQnZ3NnDlzePDBB7n00kupqqqiU6dO9OjRg7Fjx5KXl8ekSZPo1KkTNTU1nHvuuYwYMYK8vLzdnr9ixQqeeOIJHnnkEa688kqeffZZrr76akaPHs348ePp2bMnCxYsYMyYMcycOXOf32PixIlcdNFF+/6ih8iCU0vSowdUVsKIEXDNNfDmm/Dtbyetd5IkSZIkHaP29Z6tw3n/Vrt27aiqqmLu3LnMmjWLkSNHct9999G3b1+WLFnC4MGDAdi5cyennvq396ddcsklAPTu3ZvCwsK6a927d2f16tXk5eXx0EMPMXnyZABWr17NihUr9io4FRQUUFxcDEBJSQnV1dVs3ryZefPmccUVV9T7jvv+krNmzWLixIn87ne/O/QfYh8sOLU0HTvC9Onw5S/D3XfDW2/BT34CqSV+kiRJkiS1NPtbiQSQn5+00e2pWzeYPftv55s21XD88cc3+rlZWVmUlpZSWlpK7969eeyxx+pa4SorKxucU9uC16pVq7rj2vMdO3Ywe/ZsZsyYQWVlJbm5uZSWlrJ169Z9xqnNo6amhl27dtGhQwcW72+5V8qrr77KDTfcwLRp0/YqZqWDezi1RL7BTpIkSZKkOuXlkJu7+1hubjJ+qJYvX86KFSvqzhcvXky3bt0466yzWLduXV3Bafv27SxdurTRcTdu3EjHjh3Jzc1l2bJlzJ8/v9Fz27dvT0FBAU8//TQAMcYG30C3atUqLr/8ch5//HHOPPPMRsc/GBacWqraN9g9+ST8/vfJZuJ/+ENzZyVJkiRJUpMbNQomTEhWNIWQfE6YcHhvqdu8eTPXXXcdZ599NkVFRbz++uvcddddZGdn88wzz3DbbbfRp08fiouLmTdvXqPjDhs2jB07dlBUVMSdd95Jv379DiqviooKJk6cSJ8+fSgsLGTKlCl73XPPPffw3nvvMWbMGIqLi+nbt+9BPaMxbKlr6UaOhNNPh0svhfPOgzFj4PHHGZCu90BKkiRJknQUGDUqvf/3t6SkZJ+FpOLiYubMmbPX+Ox6/Xu1rXgNXZs2bVqDcaurq4HkjXhLliypG7/11lvrjgsKCpg+ffp+c//JT37CT37yk/3ec7hc4XQsqH2DXXY2fOc7sHIlIV3vgZQkSZIkSdqDBadjRY8e0LqBBW1btsC4cU2fjyRJkiRJarEsOB1L3n674fFVq5o2D0mSJEmS1KJZcDqWnHFGw+NZWcnm4jt3Nm0+kiRJkiSpRbLgdCxp6D2Q2dlw8snwj/8IRUXwi1/Arl3Nk58kSZIkSWoRLDgdS+q9BzLWvgdy0qSkpe7JJyHG5K12ffrAM89YeJIkSZIkSYfEgtOxZtQoqK7mpZkzobo6OW/VKik0vfYa/PznsH07XHEFnHMOPPechSdJkiRJkhpQXl5OYWEhRUVFFBcXs2DBgow+r6ysjA0bNhx2nClTptTl3LdvX373u9+lIbvdWXDS32RlJa11S5fCz34GNTUwYgSUlMCUKckKKEmSJEmSjkIVr1WQ/0A+re5uRf4D+VS8VnFY8SorK3n++edZtGgRr776KjNmzOD0009PU7YNmzp1Kh06dDjsOAMHDuSVV15h8eLFTJo0iRtuuCEN2e3OgpP2lpWVrHx6/XV47DHYvBmGD4e+feFXv7LwJEmSJEk6qlS8VsHoX41m5caVRCIrN65k9K9GH1bRae3atXTu3JmcnBwAOnfuTJcuXQCoqqpiwIABlJSUMHToUNauXQtAaWkpY8eO5YILLqBXr14sXLiQyy+/nJ49e3LHHXfUxR4+fDglJSUUFhYyYcKEuvH8/HzWr19PdXU1vXr14sYbb6SwsJAhQ4ZQU1MDwFtvvcWwYcMoKSmhf//+LFu2bK/c27VrRwgBgA8//LDuOJ1apz2iWo7WreHaa+ELX0hWPN17L1xySVJ4uusuKCuDDPxHKUmSJEnSwbhl+i0sfmfxPq/PXzOfbTu37Ta2ZfsWrp9yPY9UPVI3tnPnTrKysgAoPqWYB4Y9sM+YQ4YM4Z577uHMM89k0KBBjBw5kgEDBrB9+3ZuvvlmpkyZwoknnshTTz3FuHHjmDRpEgDZ2dnMmTOHBx98kEsvvZSqqio6depEjx49GDt2LHl5eUyaNIlOnTpRU1PDueeey4gRI8jLy9vt+StWrOCJJ57gkUce4corr+TZZ5/l6quvZvTo0YwfP56ePXuyYMECxowZw8yZM/fKf/Lkydx+++385S9/4YUXXjjwj3yQLDjpwFq3hi9+MVn19PjjSeHpc5+DT30qKTwNG2bhSZIkSZJ0xNqz2HSg8cZo164dVVVVzJ07l1mzZjFy5Ejuu+8++vbty5IlSxg8eDCQFLFOPfXUunmXXHIJAL1796awsLDuWvfu3Vm9ejV5eXk89NBDTJ48GYDVq1ezYsWKvQpOBQUFFBcXA1BSUkJ1dTWbN29m3rx5XHHFFX/7jtsa/o6XXXYZl112GXPmzOHOO+9kxowZh/xbNMSCkxqvTRv40pfgmmuSVrt7701WOfXrlxSe1q+HceMYsGoVnHEGlJcnRSpJkiRJkjJofyuRAPIfyGflxpV7jXc7oRuzvzi77nzTpk0cf/zxjX5uVlYWpaWllJaW0rt3bx577LG6VrjKysoG59S24LVq1aruuPZ8x44dzJ49mxkzZlBZWUlubi6lpaVs3bp1n3Fq86ipqWHXrl106NCBxYv3vdprTxdccAFvvfUW69evp3Pnzo2edyDu4aSD16YN3HADrFgB48fD228nq5yuvRZWriTECCtXwujRUHF4m7BJkiRJknS4ygeWk9smd7ex3Da5lA8sP+SYy5cvZ8WKFXXnixcvplu3bpx11lmsW7euruC0fft2li5d2ui4GzdupGPHjuTm5rJs2TLmz5/f6Lnt27enoKCAp59+GoAYI6+88spe97355pvE1P7MixYt4qOPPtprBdXhsuCkQ5edDV/+clJ46tQJdu3a/fqWLTBuXPPkJkmSJElSyqjeo5jwDxPodkI3AoFuJ3Rjwj9MYFTvQ+/K2bx5M9dddx1nn302RUVFvP7669x1111kZ2fzzDPPcNttt9GnTx+Ki4uZN29eo+MOGzaMHTt2UFRUxJ133km/fv0OKq+KigomTpxInz59KCwsZMqUKXvd8+yzz/KJT3yC4uJibrrpJp566qm0bxxuS50OX04OvP9+w9dWrWraXCRJkiRJasCo3qMOq8C0p5KSkn0WkoqLi5kzZ85e47Nnz647rm3Fa+jatGnTGoxbXV0NJG/EW7JkSd34rbfeWndcUFDA9OnT95v7bbfdxm233bbfew6XK5yUHmeccXDjkiRJkiSpxbLgpPQoL4fc3fthyc1NxiVJkiRJ0jHFgpPSY9QomDABTjstOe/QITn3LXWSJEmSJB1zLDgpfUaNgjVr2Ny9O5xzjsUmSZIkSZKOURaclHZ//fSnYe5c2LixuVORJEmSJEnNwIKT0u69fv1gxw6YMaO5U5EkSZIkSc3AgpPS7oPCwmQPp6lTmzsVSZIkSZIypry8nMLCQoqKiiguLmbBggUZfV5ZWRkbNmxIW7yFCxeSlZXFM888k7aYtVqnPaKOeTErC4YOTQpOu3ZBK+uakiRJkqTm9W7Fu/xx3B/ZtmobOWfk0L28OyePOvmQ41VWVvL888+zaNEicnJyWL9+PR999FEaM97b1DQu7Ni5cye33XYbQ4cOTVvM+qwEKDPKyuCdd2Dx4ubORJIkSZJ0jHu34l2Wj17OtpXbIMK2ldtYPno571a8e8gx165dS+fOncnJyQGgc+fOdOnSBYCqqioGDBhASUkJQ4cOZe3atQCUlpYyduxYLrjgAnr16sXChQu5/PLL6dmzJ3fccUdd7OHDh1NSUkJhYSETJkyoG8/Pz2f9+vVUV1fTq1cvbrzxRgoLCxkyZAg1NTUAvPXWWwwbNoySkhL69+/PsmXLGsz/Bz/4ASNGjOCkk0465N9gf1zhpMwYNgxCSFY5ffKTzZ2NJEmSJKkFW3HLCjYv3rzP6x/M/4C4Le42tmvLLpZdv4w/P/LnurGdO3eSlZUFQLvidvR8oOc+Yw4ZMoR77rmHM888k0GDBjFy5EgGDBjA9u3bufnmm5kyZQonnngiTz31FOPGjWPSpEkAZGdnM2fOHB588EEuvfRSqqqq6NSpEz169GDs2LHk5eUxadIkOnXqRE1NDeeeey4jRowgLy9v9++8YgVPPPEEjzzyCFdeeSXPPvssV199NaNHj2b8+PH07NmTBQsWMGbMGGbOnLnb3LfffpvJkyczc+ZMFi5c2Lgf+SBZcFJmnHQSnHsuvPAC1KvSSpIkSZLU1PYsNh1ovDHatWtHVVUVc+fOZdasWYwcOZL77ruPvn37smT0HuIWAAAgAElEQVTJEgYPHgwkRaxTTz21bt4ll1wCQO/evSksLKy71r17d1avXk1eXh4PPfQQkydPBmD16tWsWLFir4JTQUEBxcXFAJSUlFBdXc3mzZuZN28eV1xxRd1927Zt2yv3W265he9+97t1xbVMsOCkzCkrg7vvhvXroXPn5s5GkiRJktRC7W8lEkBlfmXSTreHnG45nDP7nLrzTZs2cfzxxzf6uVlZWZSWllJaWkrv3r157LHH6lrhKisrG5xT24LXqlWruuPa8x07djB79mxmzJhBZWUlubm5lJaWsnXr1n3Gqc2jpqaGXbt20aFDBxYfYHubl19+mauuugqA9evXM3XqVFq3bs3w4cMb/d0PxD2clDkXXwwxwvTpzZ2JJEmSJOkY1r28O61ydy+BtMptRffy7occc/ny5axYsaLufPHixXTr1o2zzjqLdevW1RWctm/fztKlSxsdd+PGjXTs2JHc3FyWLVvG/PnzGz23ffv2FBQU8PTTTwMQY+SVV17Z674//elPVFdXU11dzec//3kefvjhtBabwIKTMumTn0xa69K4i74kSZIkSQfr5FEnc9aEs8jplgMhWdl01oSzDustdZs3b+a6667j7LPPpqioiNdff5277rqL7OxsnnnmGW677Tb69OlDcXEx8+bNa3TcYcOGsWPHDoqKirjzzjvp16/fQeVVUVHBxIkT6dOnD4WFhUyZMuVgv1pa2FKnzGnVCi66CH75S9i5EzLYGypJkiRJ0v6cPOrkwyow7amkpGSfhaTi4mLmzJmz1/js2bPrjmtb8Rq6Nm3atAbjVldXA8kb8ZYsWVI3fuutt9YdFxQUMP0gOo0effTRRt97MFzhpMy6+GJ4/304iCWAkiRJkiTp6GbBSZk1eHCyssm2OkmSJEmSjhkWnJRZHTrA3/89vPBCc2ciSZIkSZKaiAUnZV5ZGbzyCrz9dnNnIkmSJEmSmoAFJ2VeWVnyuY9NzyRJkiRJUstiwUmZV1gIZ5xhW50kSZIkSccIC07KvBCSVU4zZsC2bc2djSRJkiRJaVFeXk5hYSFFRUUUFxezYMGCjD6vrKyMDRs2HHac2bNnc8IJJ1BcXExxcTH33HNPGrLbXeu0R5QacvHFMH48zJ0LgwY1dzaSJEmSpGPMu+9W8Mc/jmPbtlXk5JxB9+7lnHzyqEOOV1lZyfPPP8+iRYvIyclh/fr1fPTRR2nMeG9T0/gG+P79+/P888+nLd6eXOGkpvHZz0JODqTxfxySJEmSJDXGu+9WsHz5aLZtWwlEtm1byfLlo3n33YpDjrl27Vo6d+5MTk4OAJ07d6ZLly4AVFVVMWDAAEpKShg6dChr164FoLS0lLFjx3LBBRfQq1cvFi5cyOWXX07Pnj2544476mIPHz6ckpISCgsLmTBhQt14fn4+69evp7q6ml69enHjjTdSWFjIkCFDqKmpAeCtt95i2LBhlJSU0L9/f5YtW3bI3/FwuMJJTeO446C0NCk43X9/c2cjSZIkSWpBVqy4hc2bF+/z+gcfzCfG3bd42bVrC8uWXc+f//xI3djOnTvJysoCoF27Ynr2fGCfMYcMGcI999zDmWeeyaBBgxg5ciQDBgxg+/bt3HzzzUyZMoUTTzyRp556inHjxjFp0iQAsrOzmTNnDg8++CCXXnopVVVVdOrUiR49ejB27Fjy8vKYNGkSnTp1oqamhnPPPZcRI0aQl5e3x3dewRNPPMEjjzzClVdeybPPPsvVV1/N6NGjGT9+PD179mTBggWMGTOGmTNn7pV/ZWUlffr0oUuXLnzve9+jsLDwwD/0QbDgpKZz8cXwta/BW29Bjx7NnY0kSZIk6RixZ7HpQOON0a5dO6qqqpg7dy6zZs1i5MiR3HffffTt25clS5YwePBgIClinXrqqXXzLrnkEgB69+5NYWFh3bXu3buzevVq8vLyeOihh5g8eTIAq1evZsWKFXsVnAoKCiguLgagpKSE6upqNm/ezLx587jiiivq7tvWwF7Kn/zkJ1m5ciXt2rVj6tSpDB8+nBUrVhzyb9EQC05qOmVlScFp6lS4+ebmzkaSJEmS1ELsbyUSQGVlfqqdbnc5Od0455zZdeebNm3i+OOPb/Rzs7KyKC0tpbS0lN69e/PYY4/VtcJVVlY2OKe2Ba9Vq1Z1x7XnO3bsYPbs2cyYMYPKykpyc3MpLS1l69at+4xTm0dNTQ27du2iQ4cOLF6879VeAO3bt687LisrY8yYMaxfv57OnTs3+rsfiHs4qen06AFnnQUvvNDcmUiSJEmSjiHdu5fTqlXubmOtWuXSvXv5Icdcvnz5bquCFi9eTLdu3TjrrLNYt25dXcFp+/btLF26tNFxN27cSMeOHcnNzWXZsmXMnz+/0XPbt29PQUEBTz/9NAAxRl555ZW97nvnnXeIMQLw+9//nl27du21gupwucJJTausDB5+GD78MNnXSZIkSZKkDKt9G10631K3efNmbr75ZjZs2EDr1q35+Mc/zoQJE8jOzuaZZ57ha1/7Ghs3bmTHjh3ccsstjd4jadiwYYwfP56ioiLOOuss+vXrd1B5VVRU8JWvfIXvfOc7bN++nauuuoo+ffrsds8zzzzDj370I1q3bs3HPvYxnnzySUIIB/WcA7HgpKZVVgbf/z7MmgWf+1xzZyNJkiRJOkacfPKowyow7amkpIR58+Y1eK24uJg5c+bsNT579uy649pWvIauTZs2rcG41dXVQPJGvCVLltSN33rrrXXHBQUFTJ8+fb+5f/WrX+WrX/3qfu85XLbUqWn17w/t2tlWJ0mSJElSC2bBSU0rJwcGDUo2Dk/1i0qSJEmSpJbFgpOa3sUXw6pVcBCbpkmSJEmStKfoQoaMOdzf1oKTmt5FFyWfU6c2bx6SJEmSpKNW27Ztee+99yw6ZUCMkffee4+2bdsecgw3DVfTO+006NMnKTh961vNnY0kSZIk6SjUtWtX1qxZw7p169IWc+vWrYdVZGlJ2rZtS9euXQ95vgUnNY+LL4bvfhc2bIAOHZo7G0mSJEnSUaZNmzYUFBSkNebs2bM555xz0hrzWGVLnZpHWRns3Am//W1zZyJJkiRJktLMgpOaR79+0KkTvPBCc2ciSZIkSZLSzIKTmkdWFgwdCtOmwa5dzZ2NJEmSJElKIwtOaj5lZfCXv8CiRc2diSRJkiRJSiMLTmo+w4ZBCLbVSZIkSZLUwlhwUvPp3Bk+/WmYOrW5M5EkSZIkSWlkwUnN6+KLYeHCpLVOkiRJkiS1CBac1LzKyiBGmD69uTORJEmSJElpYsFJzau4GE45pXna6ioqID+fARdeCPn5ybkkSZIkSTpsGSs4hRBODyHMCiG8EUJYGkL4emq8UwjhtyGEFanPjvXm3B5CeDOEsDyEMLTeeEkI4bXUtYdCCCFTeauJtWqVrHL69a9hx46me25FBYweDStXEmKElSuTc4tOkiRJkiQdtkyucNoB/HOMsRfQD7gphHA28L+BF2OMPYEXU+ekrl0FFALDgIdDCFmpWD8CRgM9U3/DMpi3mlpZGWzYAJWVTffMceNgy5bdx7ZsScYlSZIkSdJhyVjBKca4Nsa4KHW8CXgDOA24FHgsddtjwPDU8aXAkzHGbTHGPwFvAp8KIZwKtI8xVsYYI/DTenPUEgweDK1bwwsvNN0zV606uHFJkiRJktRoTbKHUwghHzgHWACcHGNcC0lRCjgpddtpwOp609akxk5LHe85rpaifXvo379p93E68cSGx884o+lykCRJkiSphQrJoqEMPiCEdsBLQHmM8bkQwoYYY4d619+PMXYMIfwQqIwx/iw1PhGYCqwC/j3GOCg13h/4VozxHxp41miS1jtOPvnkkieffDKj360pbN68mXbt2h01cQ819ulPPUWP8eOpfOoptp10UoP3pCvntm+/Td/rryfro4+S/ZtSdmZns/yb3+QvgwYd9jPg6Pu3M65xjWvcpo6bydjGNa5xjWvclhU3k7GNa9ymiNuSfPazn62KMfY94I0xxoz9AW2AXwPfqDe2HDg1dXwqsDx1fDtwe737fg2cl7pnWb3xfwR+fKBnl5SUxJZg1qxZR1XcQ479+usxQozjx6c37p4++CDGwsIYO3aM8f77Y+zWLe4KIcasrBhPPjm5niZH27+dcY1rXOM2ddxMxjaucY1rXOO2rLiZjG1c4zZF3JYEeDk2oiaUybfUBWAi8EaM8f56l34JXJc6vg6YUm/8qhBCTgihgGRz8N/HpO1uUwihXyrmtfXmqKX4u7+D/PzMttXt2gXXXQdvvAG/+AWMHQvV1bw0cybMnAnr1sGYMZDhVX+SJEmSJLV0mdzD6TPANcCFIYTFqb8y4D5gcAhhBTA4dU6McSnwC+B1YDpwU4xxZyrWV4CfkGwk/hYwLYN5qzmEABdfDDNmwNatmXnGvffC5MnwX/8Fe7bNXXABfPvb8LOfwWOPNTxfkiRJkiQ1SutMBY4x/g4I+7g8cB9zyoHyBsZfBj6Rvux0RCorgx/+EObMgSFD0ht78mS4665khdPXv97wPePGwezZcNNN8OlPQ69e6c1BkiRJkqRjRJO8pU5qlNJSaNs2/W11r70G11yTFJHGj09WUzUkKytZ4XTccTByJNTUpDcPSZIkSZKOERacdOTIzYULL4QXXkhfzPfeg0svhfbt4bnnkoLW/nTpAj/9aVKk+sY30peHJEmSJEnHEAtOOrKUlcGbb8KKFYcfa8cOuPJKePvtpKWuS5fGzRs2DL75zWQ11NNPH34ekiRJkiQdYyw46chSVpZ8pmOV0623Jm+fmzAhaac7GOXlyZwbboA//enwc5EkSZIk6RhiwUlHloKCZLPuw93H6f/+X3jwQbjllmSj8IPVpg08+WSy39NVV8FHHx1ePpIkSZIkHUMsOOnIU1YGL70Emzcf2vz58+F//S8YOBD+8z8PPY/8fJg4EX7/++QNdpIkSZIkqVEsOOnIc/HFyYqiF188+Ll//jNcfjl07QpPPQWtWx9eLiNGwFe+At/7XvrfnidJkiRJUgtlwUlHns98Bo4//uALPFu3wmWXwaZN8MtfQl5eevK5/34oKoJrr002IJckSZIkSftlwUlHnuxsGDIkKTjF2Lg5McKXv5y0vz3+OBQWpi+ftm2T1VI1NTBqFOzcmb7YkiRJkiS1QBacdGQqK4M1a+C11xp3/wMPwE9/CnffDcOHpz+fv/s7ePjhZG+pe+9Nf3xJkiRJkloQC046Ml10UfLZmLa63/4Wbr012bvpjjsyl9N118E11yQFp9mzM/ccSZIkSZKOchacdGQ69VT45CfhhRf2f9+bb8LIkXD22fDYY9Aqw/9JP/wwfPzj8IUvwLp1mX2WJEmSJElHKQtOOnKVlcG8efD++w1f37QJLr0UQoApU6Bdu8zn1K5dsp/TX/+arHjatSvzz5QkSZIk6ShjwUlHrosvTgo6v/nN3td27Ura25Yvh6efhu7dmy6v4mL4r/+CadOSN9hJkiRJkqTdWHDSkevccyEvr+G2urvvTlY1ff/7cOGFTZ/bmDFw2WVw++2wYEHTP1+SJEmSpCOYBScdubKyYNiwZCVR/da1Z5+Fe+6BL30JvvrV5sktBJg4EU47Da66CjZsaJ48JEmSJEk6Allw0pHt4oth/XpYuDA5f/VVuPZa6Ncv2cA7hObLrWNHeOIJWL0abrwRYmy+XCRJkiRJOoJYcNKRbejQus8BF16YvLkuOxueew5ycpo3N4DzzoPycnjmGfjxj5s7G0mSJEmSjggWnHRkmzYNWrWCjRsJMcLOnbB1K8yc2dyZ/c03v5kUxm65JVmBJUmSJEnSMc6Ck45s48btvn8TJAWnceOaJ5+GtGoFP/1p0mI3ciR8+GFzZyRJkiRJUrOy4KQj26pVBzfeXE46CX72M1i+HC66CPLzkxbA/HyoqGju7CRJkiRJalIWnHRkO+OMgxtvTgMHwqWXwty5sHJl0gK4ciWMHm3RSZIkSZJ0TLHgpCNbeTnk5u4+lpubjB+JFi3ae2zLliOrBVCSJEmSpAyz4KQj26hRMGECdOtGDAG6dUvOR41q7swatnp1w+NHWgugJEmSJEkZZMFJR75Ro6C6mpdmzoTq6iO32ARHVwugJEmSJEkZYsFJSqejrQVQkiRJkqQMsOAkpVNtC+AppyTnnTsf2S2AkiRJkiRlgAUnKd1GjYI1a9hx3HEwfLjFJkmSJEnSMceCk5QJWVm8f8458NvfQozNnY0kSZIkSU3KgpOUIe9/8pOwciX88Y/NnYokSZIkSU3qgAWnEMJxIYRWqeMzQwiXhBDaZD416ei2oaQkOXjxxeZNRJIkSZKkJtaYFU5zgLYhhNOAF4F/Ah7NZFJSS7Dl9NPhtNNgxozmTkWSJEmSpCbVmIJTiDFuAS4HfhBjvAw4O7NpSS1ACDBoEMycCbt2NXc2kiRJkiQ1mUYVnEII5wGjgBdSY60zl5LUggwcCO+9B6+80tyZSJIkSZLUZBpTcPo6cDswOca4NITQHZiV2bSkFmLgwOTTtjpJkiRJ0jGkMQWnk2OMl8QYvwsQY/wjMDezaUktRJcu0KuXG4dLkiRJko4pjSk43d7IMUkNGTQI5syBbduaOxNJkiRJkprEPvdiCiFcBJQBp4UQHqp3qT2wI9OJSS3GoEHwgx/A/PkwYEBzZyNJkiRJUsbtb4XTn4GXga1AVb2/XwJDM5+a1EIMGACtWrmPkyRJkiTpmLHPFU4xxleAV0IIP48xbm/CnKSW5YQT4FOfSgpO997b3NlIkiRJkpRxjdnD6VMhhN+GEP4QQvhjCOFPIYQ/ZjwzqSUZNAgWLoSNG5s7E0mSJEmSMq4xBaeJwP3A3wPnAn1Tn5Iaa+BA2LkTXnqpuTORJEmSJCnjGlNw2hhjnBZj/EuM8b3av4xnJrUk550HH/sYvPhic2ciSZIkSVLG7XMPp3pmhRD+E3gOqHuve4xxUcayklqanBzo39+NwyVJkiRJx4TGFJw+nfrsW28sAhemPx2pBRs0CL71Lfjzn6FLl+bORpIkSZKkjDlgS12M8bMN/Flskg7WoEHJ58yZzZvHnioqID+fARdeCPn5ybkkSZIkSYehMSucCCFcDBQCbWvHYoz3ZCopqUXq0wfy8pK2uquvbu5sEhUVMHo0bNlCAFi5MjkHGDWqOTOTJEmSJB3FDrjCKYQwHhgJ3AwE4AqgW4bzklqeVq3gwguTjcNjbO5sEuPGwZYtu49t2ZKMS5IkSZJ0iBrzlrrzY4zXAu/HGO8GzgNOz2xaUgs1cCCsWQN/+ENzZ5JYtergxiVJkiRJaoTGFJxqUp9bQghdgO1AQeZSklqw2n2cjpS31Z1xRsPjp5zStHlIkiRJklqUxhScng8hdAD+E1gEVANPZDIpqcXq3j3ZmPvFF5s7k8Tddzc8vn49/PznTZuLJEmSJKnFaMxb6u6NMW6IMT5LsnfT38UY/zXzqUktUAhJW92sWbBzZ3NnA8cdl3yedBIxBOjWDX74Q+jXL9k0fOxY2L69eXOUJEmSJB11GrNpeNsQwjdCCM8BPwe+FEJoe6B5kvZh0CDYsAEWLWruTODRR6FrV/jzn3lp5kyoroYxY5IVWF//OjzwQJLvO+80d6aSJEmSpKNIY1rqfgoUAj8A/g/QC3g8k0lJLdqFFyafzb2P09q1MH06XHstZGXtfq1Nm6TYVFEBCxdCSQlUVjZPnpIkSZKko05jCk5nxRivjzHOSv2NBs7MdGJSi3XSSVBU1PwFp4qKpK3vuuv2fc8XvgDz50PbtjBgAPzoRxBj0+UoSZIkSToqNabg9P9CCP1qT0IInwb+J3MpSceAQYPgf/4HamoOfG8mxJi0051/Ppx5gPpxURG8/DIMHpy0233pS82XtyRJkiTpqNCYgtOngXkhhOoQQjVQCQwIIbwWQng1o9lJLdXAgbBtW1J0ag5VVbB0KXzxi427v2NH+NWv4NvfTgpVf//3yX5PzaGiAvLzGXDhhckb/yoqmicPSZIkSdI+tW7EPcMynoV0rLngAmjdOtmce9Cgpn/+o48mbXJXXtn4Oa1awV13Qd++cPXVyb5OTz6ZrHxqKhUVMHo0bNlCAFi5MjmH5K16kiRJkqQjwj5XOIUQ2qcONzX0F2NcGWNcmfkUpRaoXTs477zm2cdp2zb4+c/h8svhhBMOfv7nPpe02HXpAsOGwX33Nd2+TuPGwZYtu49t2ZKMS5IkSZKOGPtrqft56rMKeDn1WVXvXNLhGDgwaW3761+b9rm/+hW8/37j2+ka8vGPJ5uJX3kl3H47jBgBH3yQthR389FHMGcO/Ou/JiuaGrJqVWaeLUmSJEk6JPssOMUYP5f6LIgxdk991v51b7oUpRZq0KBkZdDs2U373Ecfha5d4cILDy/OccclK6W+/3345S/hU5+CN944/PxihNdfhwcfTFZT5eUlb8grL4fs7IbnnHHG4T9XkiRJkpQ2B9w0PIRwWQjhhHrnHUIIwzOblnQM+NSnkta6pmyrW7sWpk+Ha6+FrKzDjxcC3HJLshfV++8n3+nZZw8+zrvvJvszffGLcPrpUFiYxF2+HK65Bp57Dt57DyZNgtzc3efm5ibFKEmSJEnSEaMxm4Z/O8Y4ufYkxrghhPBt4L8zl5Z0DGjTJlm505QFp4oK2LkTrrsuvXEHDEjaA6+4Aj7/ebjttqRodOedDFi1KlmBVF7+t429t2yBuXPht79N/l5NvfCyU6ek1XDw4OQvP3/359TOHzeOuGoVYc+4kiRJkqQjQmMKTg2tgmrMPEkHMmgQvPBCsgdRptvCYkza6c4/H848M/3xu3ZN2gNvuQW++93krXa7dv3tbXI33JC03q1fD//zP8nm5dnZ8JnPwL/9W1JgOuecA6+8GjUKRo3ipdmzKS0tTf/3kCRJkiQdtgO21AEvhxDuDyH0CCF0DyF8n2TjcEmHa+DA5PPFFzP/rKoqWLr08DYLP5CcHPjRj5J9l3bt2v3a1q3wi1/AunVw000wbVrShjdzZrLxeN++6WnzkyRJkiQ1u8asVLoZuBN4CgjAb4CbMpmUdMz4xCfgpJOSgtM//VNmn/Xoo9C2bfJmuUzb15v3Qvhb+5wkSZIkqcU6YMEpxvgh/H/27jyu6ir/4/jrXEAQVBAFUhNQy90WrYyCVLSpmRZtt7BtKttm2texdZJptfpV00xW5jTRvltNJe6VVlrmbpoCaoYruKCA3PP74wsmyir33u8F3s/H4z4u99x7z/eD4sKbcz6HuwJQi0jzY4yzyik729nyZox/rlNc7Jwod/bZEB1d++sbKjHR2UZX1biIiIiIiIg0edVuqTPGPF1+P8kY8/H+t9omNsZMMMZsMMYs2mfsAWPMOmPM/PLbn/Z57m5jzEpjzHJjzCn7jA8wxiwsf+4ZY/z1HbmIS4YNc05pW7zYf9eYNMnZvubP7XT7yszUaXIiIiIiIiLNWE0rnP5bfv/EQc49EXgOeHW/8aestZXmNMb0BkYCfYCOQLYxpru1tgz4FzAamAN8BpwK/O8gaxIJPsOGOfdTpjhb7Pxh4kSnqXd6un/m359OkxMREREREWnWql3hZK2taAx+lLV2xr434KjaJrbWzgSqaeRygOHAm9baYmvtamAlcJwxpgPQxlo721prccKrEXWcU6RxSEyEww5zttX5w/r18PnncMklgW3KnZEBOTnMmDoVcnIUNomIiIiIiDQjdTml7tIqxi5rwDX/YoxZUL7lrm35WCdgzT6vWVs+1qn84/3HRZqWYcNgxgwoLfX93FlZUFYGl1b1R1lERERERETE94yzcKiKJ4y5ELgISANm7vNUa6DMWjus1smNSQY+sdb2LX+cAGwCLPAQ0MFa+2djzD+B2dba18pf9zLO9rk84OGKaxlj0oA7rLVnVHO90Tjb70hISBjw5ptv1lZi0NuxYwetWrVqNPP6c+6mPG/7GTPo+8AD/PDss2yrZVtdveq1lmP//Gf2REXx43PP+W7eetC8mlfzal435ta8mlfzal7N27Tm9efcmlfzBmLepmTIkCHzrLXH1PpCa22VNyAJGAzMBgbtc+sPhFb3vv3mSAYW1fYccDdw9z7PfQGkAB2AZfuMXwi8UJdrDxgwwDYF06ZNa1Tz+nPuJj3v5s3WGmPtgw/6dt7vv7cWrB0/3rfz1oPm1byaV/O6Mbfm1byaV/Nq3qY1rz/n1ryaNxDzNiXAXFuHXKamHk65wCxgp63cw+kHa+2eesVf5cp7MlU4C6g4we5jYKQxJtwY0wU4HPjOWrse2G6MOb78dLpLgI8O5toiQS02Fvr3dxqH+9LEiRARAeef79t5RURERERERGpQ0yl1WGvLjDFFxphoa21hfSY2xryBs0KqvTFmLXA/MNgYcxTOlroc4Ory6yw2xrwNLAH2ANdb54Q6gGtxTrxriXM6nU6ok6Zp6FB46inYuROioho+X3ExvP46nH02REc3fD4RERERERGROqoxcCq3G1hojJkM7KwYtNbeUNObrLUXVjH8cg2vzwQyqxifC/jprHiRIDJsGDz2GMyaBaee2vD5Jk2CrVvhsssaPpeIiIiIiIhIPdQlcPq0/CYi/pSaCuHhkJ3tm8Bp4kQ49FBIT2/4XCIiIiIiIiL1UGvgZK39TyAKEWn2WraEE05wAqeGWr8ePv8c7rwTQkIaPp+IiIiIiIhIPVTbNLyCMeZwY8y7xpglxphVFbdAFCfS7AwbBj/9BBs3NmyerCwoK4NLL/VNXSIiIiIiIiL1UGvgBLwC/AunmfcQ4FXgv/4sSqTZGjrUuZ869eDnsNbZTnfCCdC9u0/KEhEREREREamPugROLa21UwBjrc211j4AqCmMiD8MGOCcKDdlysHPMW8eLF6sZuEiIiIiIiLimjqdUmeM8QArjDF/AdYB8f4tS6SZCg2FIUMa1sdp4kSIiNtdP9YAACAASURBVIDzz/dZWSIiIiIiIiL1UZcVTjcBkcANwADgYkCNYUT8ZehQWL0aVh1Eq7TiYnj9dTjrLGellIiIiIiIiIgLag2crLXfW2t3ANuAG6y1Z1tr5/i/NJFmatgw5/5gttVNmgRbt2o7XRDJyoLkZEhPH0RysvNYRERERESkqavLKXXHGGMWAguAhcaYn4wxA/xfmkgz1aMHdOx4cNvqJk6ETp1+bz4ursrKgtGjITcXrDXk5jqPFTqJiIiIiEhTV5ctdROA66y1ydbaZOB6nJPrRMQfjHFWOU2dCl5v3d+3fj18/jlccgmEhPivPqmzMWOgqKjyWFER3HmnO/WIiIiIiIgESl0Cp+3W2lkVD6y1XwHb/VeSiDBsGGzaBAsW1P09WVlQVgaXqsVasMjLq3p83ToYOBAeewx++SWwNYmIiIiIiARCXQKn74wxLxhjBhtjBhljngemG2P6G2P6+7tAkWapYktcXbfVWetsp0tJcbbkSVBITKx6PCbGyQbvvBMOOwyOOgrGjoWlSwNbn4iIiIiIiL/UJXA6CugO3A88APQCTgDGAU/4rTKR5qxjR+jVq+6Nw+fNg8WL1Sw8yNx004FjkZHw3HMwd65zGOG4cRAVBffeC717O7d774X5850cUUREREREpDGqyyl1Q2q4pQeiSJFmadgwmDkTiotrf+3EiRARAeef7/eypO5ycpyWXJ06gTGWpCQYPx4yMpznk5Phllvg669h7Vp49llISIB//AOOPhoOP9xZBfXddwqfRERERESkcanLCicRccPQoU6H6Tlzan5dcTG8/jqcdZazV0uCQkEBvPyyEy6tXQtTp84gJ+f3sGl/nTrBX/4C06Y5/d/Hj3e22z35pNPvKSnJWTE1a5azHS8rywms0tMHkZysk+9ERERERCS4KHASCVaDB4PHU/u2ukmTYOtWbacLMuPHw44dcOut9X9vfDxcdZVz6OCGDfCf/zgrnv79bzjpJIiNdX67c3PBWkNuLowerdBJRERERESChwInkWAVHQ3HHlt74/CJE53lMRWNxsV1JSXwzDOQnu40BG+Itm3hkkvgo49g40Z44w3Ys8e57auoCMaMadi1REREREREfKXWwMkYE2mMudcY82L548ONMaf7vzQRYdgwp4HPtm1VP79+vbMM5pJLICQksLVJtd5+G9atO7jVTTVp3RpGjoRdu6p+Pi/Pt9cTERERERE5WHVZ4fQKUAyklD9eC4z1W0Ui8rthw5yGPTNmVP18Vpbz/KWXBrYuqZa1zslzvXrBqaf65xqJiVWPG+OshBIREREREXFbXQKnbtbax4BSAGvtLsD4tSoRcaSkQMuWVW+rs9bZTpeSAj16BLw0qdq0aTB/vnP6nMdPm5YzMyEysvJYRISzs3LECLjgAsjP98+1RURERERE6qIu3w6VGGNaAhbAGNMNZ8WTiPhbeDikpVXdOHzePFi8WM3Cg8y4cU7T71Gj/HeNjAynKXlSEhhjSUqCl16CX35xwqgPP4TeveG115xcUkREREREJNDqEjjdD3wOdDbGZAFTgDv8WpWI/G7oUCdYWr++8vjEic6ylvPPd6UsOdCSJfDZZ3D99c5vjT9lZEBODkydOoOcHOdxWBj87W/OCqsePeDii+G009TbSUREREREAq/WwMlaOxk4G7gMeAM4xlo73b9lichew4Y591On/j5WXAyvvw5nnQUxMe7UJQd48kknaLr2Wnfr6NULZs1yTsqbORP69IHnnwev1926RERERESk+ag2cDLG9K+4AUnAeuBXILF8TEQC4aijIDa2ch+nSZNg61Ztpwsi+fnw3/86/dvj4tyuxjm08K9/hUWLnDZf118PgwfDzz+7XZmIiIiIiDQHNa1wGld++yfwLTAeeLH842f8X5qIAE7n6fR0J3CqaMgzcaLTIXroUFdLk9/9859QUgI33+x2JZUlJ8MXX8Arr8DChXDEEfDoo7Bnj9uViYiIiIhIU1Zt4GStHWKtHQLkAv2ttcdYawcARwMrA1WgiOBsq1u7FlasoMXmzfD553DJJc4yFnFdUZGzZe2MM4LzwEBjnMVwS5c6PZ3uugsGDoSffnK7MhERERERaarq0jS8p7V2YcUDa+0i4Cj/lSQiB6jo45SdTUJ2NpSVOXu3JCi8+ips3gy33eZ2JTU75BB47z14911Ytw6OOQbuuQd273a7MhERERERaWrqEjgtNca8ZIwZbIwZZIx5EVjq78JEZB9du0JSEmRnc8jnnztNeYJxKU0z5PXCU0854U1amtvV1M055zgn6mVkQGYmHH00fPON21WJiIiIiEhTUpfA6XJgMXAjcBOwpHxMRALFGKcZzwcfEJWTA8uXQ1aW21UJ8MknTiPuW291fpsai9hYpxXY5587WwJTU+HGG2HCBOdLLT19EMnJ+jITEREREZGDE1rbC6y1u4Gnym8i4oasLJg9+/fHW7bA6NHOxxkZ7tQkAIwbB4mJcO65bldycE45xTnJ7m9/g2eecUIzpze9ITdXX2YiIiIiInJw6rLCSUTcNmaMcwTavoqKnHFxzdy5MHOmszIotNb4Pni1bg3PPgsJCb8fhFhBX2YiIiIiInIwFDiJNAZ5efUbl4AYNw7atIErr3S7Et/YsKHqcX2ZiYiIiIhIfdU5cDLGRPmzEBGpQWJi/cbF7/Ly4J134KqrnNCpKajuyykhIbB1iIiIiIhI41dr4GSMOcEYs4Tyk+mMMUcaY573e2Ui8rvMTIiMrDwWGemMiyv+7/+c+xtucLcOX6rqy8wY2LQJXn/dnZpERERERKRxqssKp6eAU4DNANban4CT/FmUiOwnIwPGj4ekJKwxkJTkPFYnZ1cUFsKLL8L55zetRWb7fJlhjCUpCZ5/Hk44wXnub38Dr9ftKkVEREREpDGo05Y6a+2a/YbK/FCLiNQkIwNycpgxdSrk5ChsctFLL8H27XDrrW5X4nvlX2ZMnTqDnBy45hqYPNk5re7hh2HECNi2ze0qRUREREQk2NUlcFpjjDkBsMaYFsaY2yjfXici0tyUlsLTT8OgQTBggNvVBEaLFvDvf8Nzz8FnnzkrnlatcrsqEREREREJZnUJnK4Brgc6AWuBo8ofi4g0O++8A2vXNs3VTTUxBq6/Hr74An79FY49FqZNc7sqEREREREJVjUGTsaYEOBia22GtTbBWhtvrR1lrd0coPpERIKGtTBuHPToAaed5nY17hg6FL7/3jm57uSTnR5PIiIiIiIi+6sxcLLWlgHDA1SLiEhQmzEDfvgBbrkFPHXqgNc0desGc+bAqac6q56uvdbZaigiIiIiIlKhLt8yfW2Mec4Yk2aM6V9x83tlIiJBZtw4iIuDiy92uxL3tWkDH30Ed97p9Hc6+WTYtMntqoJfVhYkJ0N6+iCSk53HIiIiIiJNUWgdXnNC+f3f9xmzQLrvyxERCU7LlsEnn8D990PLlm5XExxCQuCRR6BfP7jiCqev08cfO4/lQFlZzml/RUUAhtxc5zHo0EkRERERaXpqXeFkrR1SxU1hk4g0K089BeHhcN11blcSfDIyYNYsKC52TrD76CO3KwpOY8ZUhE2/KypyxkVEREREmppaAydjTDtjzDPGmB+MMfOMMf9njGkXiOJERILBxo3w6qtwySUQH+92NcHp2GNh7lzo1QtGjIDMTKfJuvwuL69+4yIiIiIijVldeji9CWwEzgHOLf/4LX8WJSISTJ5/HnbvdpqFS/U6dnQaq2dkwD33wIUXHriip7myFtq2rfq5Tp0CW4uIiIiISCDUJXCKtdY+ZK1dXX4bC8T4uzARkWCwaxf8859w2mnQs6fb1QS/li3hv/+FRx+Ft9+Gk06CtWvdrspdO3Y4jea3bKn6dMOiIvjpp8DXJSIiIiLiT3UJnKYZY0YaYzzlt/OBT/1dmIhIMHjtNWdL3a23ul1J42EM3HGH00D855/hmGPggQea5+lsCxc6n/8bb8Df/w4TJ0JSEhhjSUqCsWOdkO7EE9X7SkRERESalmoDJ2PMdmPMNuBq4HWgpPz2JnBzYMoTEXGP1wtPPglHHw2DB7tdTeNz+ukwZ46znezBByE3F6z9/XS2ph46vfIKDBwIBQWQnQ333uusdMrJgalTZ5CT4zQM//576N0bzjrLWRmm3lciIiIi0hRUGzhZa1tba9uU33ustaHlN4+1tk0gixQRccP//gfLljmrm4xxu5rGqXdvaNHiwPGmfDrbzp1w2WXw5z9DSgrMnw9DhlT/+g4dnN5X558Pd90Fl1/unPgnIiIiItKYhdblRcaYI4DkfV9vrX3fTzWJiASFcePg0EOdIEAO3rp1VY83xdPZliyB886DpUvh/vudVU0hIbW/r2VLZ9tdr17O9sOVK+GDDyAuzu8li4iIiIj4Ra2BkzFmAnAEsBjwlg9bQIGTiDRZP/wA06bBY49BWJjb1TRuiYnOdrqqxpuSV1+Fa6+FVq3gyy9h2LD6vd8YJ6Tq2dNZIXXccTBpEvTt65dyRURERET8qi5Nw4+31h5jrb3UWnt5+e3Pfq9MRMRF48Y5wcFVV7ldSeOXmQmRkZXHIiOd8aagqAiuuAIuvRSOPRZ+/LH+YdO+LrgAZs50ttWlpMCnOqZDRERERBqhugROs40xvf1eiYhIkFizBt56ywmbYmLcrqbxy8iA8eOd09nAEh7uPM7IcLuyhlu2zGkM/sorTk+q7Gzo2LHh8x57rNNMvHt3OOMMp3m9momLiIiISGNSl8DpPzih03JjzAJjzEJjzAJ/FyYi4pZnnnHub7zR3TqakowM53S2c89dizFw7rluV9RwWVlwzDHw229Og/mxYyG0Tp0R66ZTJ2el09lnO43rr7oKSkp8N7+IiIiIiD/VJXCaAFwMnAqcAZxefi8i0uTs3BnC+PFOIOKsyBFfOuKIQnbvdnpkNVa7dsHo0TBqFPTv75xCd8op/rlWVBS8/Tbccw+8/DKcfDJs2uSfa4mIiIiI+FJdAqc8a+3H1trV1trcipvfKxMRccFnn3Vg2zZnRYn4Xt++hQDMmuVyIQfp55+dvkovvgh33QVTpzorkfzJ44GHHnJWVH37rbOFb8kS/15TRERERKSh6hI4LTPGvG6MudAYc3bFze+ViYgEUFaWs6Lp+ee7ER7uBAvie23bltK9O3z1lduV1N9bb8GAAbB2LXz2GTz8sG+30NXmootg+nTYudMJvT7/PHDXFhERERGpr7oETi2BYuAPOFvpKrbViYg0CVlZzhapvDwAQ3Gx8zgry+3KmqbUVPj6a/B63a6kellZkJwM6emDSEx0Tp0bORKOOMI5he6Pf3SnruOPh+++gy5d4LTTnH5jaiYuIiIiIsGo1p/NWmsvD0QhIiJuGTPGOdp+X0VFznhTOEkt2KSlwYQJzglvvYPwDNSKANL5mjCsWeOcXHjaafDBBxAW5m59iYnOCrFRo5zG9kuWwLPPul+XiIiIiMi+al3hZIw51BjzgTFmgzEm3xjznjHm0EAUJyISCM7KprqPS8Okpjr3wdrHqaoAEmDRouAJdVq1gvffd/pIvfACHHUUdO7srMhKTtbqPBERERFxX1221L0CfAx0BDoBk8rHRESahMTE+o1Lw3TrBgkJwdvHqbEEkB6P00fq6qudVU5r14K1htzc5r0lNGthFslPJ5M+I53kp5PJWthMfyFEREREXFaXwCnOWvuKtXZP+W0iEOfnukREAiYzEyIjK49FRjrj4nvGOKucgjVwamwBZFXNwyu2hDY3WQuzGD1pNLmFuVgsuYW5jJ40WqGTiIiIiAvqEjhtMsaMMsaElN9GAZv9XZiISKBkZMD48c4pdcZYkpKcx+rf5D9paZCT46zKCTaZmdCyZeWxYA4gG8uKrEAYM2UMRaWV90MWlRYxZkozTN9EREREXFaXwOnPwPnAb8B64NzyMRGRJiMjwwlApk6dQU6OwiZ/q+jjFIyrnDIy4MILKx4FfwBZ3cqr6Ojmd4JdXmHVKVt14yIiIiLiP7UGTtbaPGvtmdbaOGttvLV2hLU2NxDFiYhI03TkkRAVFZyBE8D27dCpU+MIIKvaEhoSAgUFcNNNUFbmTl2BtHHnRka+OxJL1QlbYnSQ7ocUERERacJCq3vCGHNfDe+z1tqH/FCPiIg0A6GhkJISnIGT1wtTpsAZZzj9poJdRRg2Zgzk5VkSEw1jx8IPP8BTTznbFl977cBtgk3Fu0ve5bpPr6NgdwHn9jqXz1Z+VmlbXcvQlmQODdL9kCIiIiJNWE0rnHZWcQO4ArjTz3WJiEgTl5YGCxZAYaHblVQ2fz5s2QLDhrldSd3tvyV01Ch48knn9sEHcPLJsLmJdV/csHMD579zPue9cx6J0YnMGz2Pd85/h/FnjCcpOmnv6wYlDSKjXxAvURMRERFpoqoNnKy14ypuwHigJXA58CbQNUD1iYhIE5Wa6vQY+uYbtyupLDvbuR861N06fOHmm+Gtt2DuXDjxRFi92u2KGs5ay9uL36bP8334aPlH/CP9H8y5cg79EvoBkNEvg5ybcpg2aBrXHnMtX676ku/Xfe9y1SIiIiLNT409nIwxscaYscACnO13/a21d1prN9Q2sTFmgjFmgzFm0X7zTTbGrCi/b7vPc3cbY1YaY5YbY07ZZ3yAMWZh+XPPGNMYNjiIiEhtBg50eg0F27a67Gzo0wc6dHC7Et847zyYPBny851tjPPmuV3Rwcvfkc9575zHBe9eQJeYLvww+gfuTrubUE/VHQIeHvowCVEJjP5kNHu8ewJcbd1kLcwi+elk0mekk/x0MlkLs9wuSURERMQnqg2cjDGPA98D24F+1toHrLVb6zH3RODU/cbuAqZYaw8HppQ/xhjTGxgJ9Cl/z/PGmJDy9/wLGA0cXn7bf04REWmEoqKgf//gCpx274ZZsxrXdrq6SEuDr7+G8HAYNAg+/9ztiurHWssbC9+gz/N9mPTzJB4Z+gjfXPENfeL71Pi+6IhonvvTc8z/bT5Pz3k6QNXWXdbCLEZPGk1uYS4WS25hLqMnjVboJD6Xn5XP7OTZkA6zk2eTn5Uf1POKiEjTUNMKp1uBjsA9wK/GmG3lt+3GmG21TWytnQls2W94OPCf8o//A4zYZ/xNa22xtXY1sBI4zhjTAWhjrZ1trbXAq/u8R0REGrm0NPjuOygudrsSx9dfO6FTUwucAHr3htmz4bDD4PTTYcIEtyuqm992/MbZb5/NRe9fxGGxh/Hj1T9yZ+qd1a5q2t9ZPc9ieI/h3DftPlZvDa49hWOmjKnU4BygqLSI6z+9ns9WfEb+Dn3z3tz4Y8VbflY+y0cvpzi3GCwU5xazfPTyBodD/ppXRESaDuPkOH6a3Jhk4BNrbd/yxwXW2ph9nt9qrW1rjHkOmGOtfa18/GXgf0AO8Ii1dlj5eBpwp7X29GquNxpnNRQJCQkD3nzzTX99agGzY8cOWrVq1Wjm9efcmlfzat6mN++sWe25776+PPfcD/TpU+vPMuo878F68cUuvPVWZz7++GsiI8sa/a9vVXbuDOGBB/owd24sl122mksuya31ND43/s2w1pK9IZtnVz7L7rLdXNHlCs499FxC9i6Arvu8G4s3cun3l9K3TV8e7fcoDdmd78tfiyEzhtT6mvYt2tO9dXd6tO5B91bd6d66O7EtYut8jab4NdxU583Oz+aJn5+g2Pt7Ah/uCee27rcxLKEBKfhIoKoMKAxnb0FY+a3Ffvf7j+8/9k+gqkMfEnA6vvpAY/h907yBm9efc2tezRuIeZuSIUOGzLPWHlPb6+r240H/q+p/fraG8SpZa8fjNDjnmGOOsYMHD/ZJcW6aPn06/vg8/DWvP+fWvJpX8za9eXv3hvvug507+9OQy/mq3ttvd/oc/elPaT6dd39uz/uHP8CVV8LEiV0ICenCv/4FYWENn/dgVDX3+u3ruebTa/h4+cekHJrChOET6Nm+Z4Pm/S3mN274/AbWt1/PRf0u8mm9B6OotIiwWWGUeksPeK5zm868dvZrzPt1HvPWz2Pur3OZmDMRW/5foEPbHMqADgOcW0fnPqFVQqU5shZmMWbKGPIK80iMTiRzaKZPTuvz17wV3P6z4ea8lz19WaWwCaDYW8xr619j7AVjD3re6RumV/1EKUS3isZb7MW7w4u32Istts7j4t8f2z31/OH0Bnz2a9IYft80b+Dm9efcmlfzBmLe5ijQgVO+MaaDtXZ9+Xa5iubja4HO+7zuUODX8vFDqxgXEZEmID4eund3+jjdcYe7tWzZ4jTUvv9+d+sIhLAwmDgREhNh7Fj49Vd4+21w+4d51lpeW/AaN3x+A7v37GbcH8Zx48AbCfHUbVVTTa479jpeW/gaN31+E6cediqxLeu+SsjXrLVc8fEVlHpLCQ8Jp7js95AhMiySh4c9zElJJ3FS0kl7x7cXb+fH335k7q9zmbd+HvN+ncdHyz/a+/y+IdT24u089/1z7NqzC2BvbyigQeFQRc+pim2AvppXHHmFefUar6vwxHBn29v+40nhHD3r6Frfb8ss3pIDA6n5g+ZTsr7kgNebUEP+m/nEnRuHJ7TG84lERKSJC3Tg9DFwKfBI+f1H+4y/box5Eqdv1OHAd9basvKeUccD3wKXAM8GuGYREfGj1FT48EPwesHj4vcm06aBtU2zf1NVjIGHHoJDD4XrroPBg+HTTyEhoda3+sW6beu4+pOr+XTFp5zY+UQmDJ9A93bdfTZ/iCeEF894kQHjB3D7l7fz8vCXfTZ3fT05+0neXPQm/0j/B4kxiXVaMdQ6vPUBIdS24m38uP7Hvaug5q2vHELtq6i0iD9/9Gee+fYZDAaP8VS6GVN5rKrXfPnLl3tDrH3nHTNljAKnBthctJk7s+/cu4Jtf4nRiQ2av2tmV5aPXo63yLt3zBPpoWtm1zq934QYQlqGENKycvDb7fFuB8xrWhhCY0NZeuFSVt21is43d+aQKw4htFWwbKoQEZFA8tvf/saYN4DBQHtjzFrgfpyg6W1jzBVAHnAegLV2sTHmbWAJsAe43lpbVj7VtTgn3rXE6ev0P3/VLCIigZeW5jSwXrbM2WLnluxsZ4XPcce5V4Mbrr4aOnWCCy5wthP+73/Qo4f/r7vv1qzY72IpKikCA0+f8jR/Oe4vPlnVtL8jEo7gtpTbeOTrRxh1xCiGdKm9h5KvZa/K5o7sOzi397nclXoXxhgy+mUc1PL9NuFtGJQ8iEHJg/aOFe4upO2jbasML0rKSohtGYvXevFaL9bavR+XecsotaVYfh/b/zX7h00VGroCp7my1jJx/kRun3w7BbsLOO3w05i6emqlX+fIsEgyh2Y26DoJGU6KvGrMKorziglPDKdrZte9476eN/7CeDZP2kze43msvGklOQ/m0PHajnT6ayfCDwlv0DVFRKRx8VvgZK29sJqnhlbz+kzggH9RrbVzgb4+LE1ERIJIaqpzP2uW+4HT4ME19zJqqk4/3VnhdfrpcOKJ8PHHcMIJ/rve/luzNu/ajMd4ePzkx7nx+Bv9d2HgvkH38c6Sd7j6k6tZcO0CIkIj/Hq9fa3eupoL3r2AXu178crwVxrUvLw60RHRJEYnkluYe8BzSdFJ/C/j4H9ul/x0cpXzAtw37T5uGHgD7SPbH/T8zcniDYu59tNrmZU3ixM7n8i/TvsX/RL6+a1HVkJGAgkZCUyfPp2UwSk++Axqnrf98Pa0H96ewtmFrHliDXkP57HmiTUkXJxA59s6E9Uzymc1iIhI8NLGahERcVW3bs42rq++cq+GnBxYubL5bKerynHHwTffQNu2MHQofPCB/641ZsqYvWFTBa/18sy3z/jvouVahrXk36f/mxVbVpA5s2ErR+qjqLSIs946C6/18uHID2nVwn8NszKHZhIZFllpzBcrZaqaNyI0ggEdB/DQzIdIejqJW764hXXb1jXoOk3ZzpKd3JV9F0e9cBSLNy7mpTNeYublM+mX0A9wemHl3JTD1EFTybkpp9FvVYxOiabve305bvlxdPhzBzZkbeD7Xt+z8MyFFMwqwJ+nZYuIiPsUOImIiKuMcVY5uRk4ZWc79805cAI47DAndDriCDjnHLjsMkhOhvT0QSQnQ1aWb67jr+bIdTWs6zAuPuJiHvn6ERZvWOz361lrufLjK1mQv4DXz36dw2IP8+v1MvplMP6M8SRFJ2EwJEUnMf6M8Q0OL6qa96UzX+L7q75n8XWLOafXOTzz7TN0+b8ujJ40mpVbVvroM2oaPl7+MX2e78OjXz/KxUdczPK/LOeK/lfgMU3/v+ORh0fS/V/dOT73eJLuS6Lwm0LmnzSfH47/gQ3vbsCWKXgSEWmKmv6/cCIiEvTS0pxVRmvXunP97Gzo0MHdLX3BIi7O2V531FHwn/9Abi5Ya8jNhdGjfRM6VdcEuaHNketj3B/GER0ezehPRuO13trf0ABPzn6SNxa9wdj0sfzx8D/69VoV/LVSprp5e8f15tWzXmXFX1dwZf8refWnV+nxXA8ueu8iFuQv8Mm1G6u8wjxGvDmC4W8Op1WLVsy8bCYThk9oltsPW8S3oMuDXUjJS+Hwfx5O6eZSlpy3hG97fMu659dRVlRW+yQiItJoKHASERHXVfRxcmOVk9cLU6Y4q5v80FKnUYqMhM2bDxwvKoIxYxo+v7+2fNVHXFQcT57yJN+s+Ybx88b77ToVTcLP6XUOd6fe7bfrBIsubbvw/GnPs/rG1dyaciuTfp7Ekf8+kjPfOJM5a+e4XV5AlZaV8vjXj9Prn72YvGoyjw57lB+v/pG0pDS3S3NdSGQIna7rxMDlA+nzbh/C2oex4voVzE6czer7V7Pu3+uYnTwb0mF28mzys/LdLllERA6CAicREXHdkUdCVJQ7gdOCBbBpk7bT7W/NmqrH83yw681fW77q6+IjLmZol6HcmX0nv27/9/nokgAAIABJREFU1efz79skfOKIiX5pEh6sOrTuwGMnP0buTbk8OPhBvl7zNSkvp5D+n3SyV2U3+d49X+V9Rf/x/bkj+w6GdR3GkuuWcMeJdxAW0gxPJaiBCTHEnRNH/9n9OWrmUUSfEE3u33NZce0KinOLwUJxbjHLRy9X6CQi0ggpcBIREdeFhkJKijuBU0X/pqFVnqHafCVWs7utuvH6CobmyMYY/n36vykpK+GG/93g07mLSos4++2zA9IkPJjFtozlvkH3kXtTLuP+MI5lm5Zx8n9PZuBLA/lw2Yd+384YaJuKNnHFR1eQ9koahbsL+fCCD/lo5EckxSS5XVpQM8YQkxZDv4/70aJDiwOe9xZ5WTVmlQuViYhIQyhwEhGRoJCW5qw2KiwM7HWzs6FXL+jUKbDXDXaZmc7Wun1FRjrjTclhsYdx30n38d7S9/h4+cc+mbOiSfhPv/0UkCbhjUGrFq24JeUWVt+4mhdOf4HNuzZz1ltn0e9f/XhtwWv896f/kvx0Mukz0kl+OpmshT7qUB8gXutlwo8T6PlcT15d8Cq3n3A7S65fwvCew90urdEp+a2kyvHivOIAVyIiIg2lwElERIJCaipY65ySFijFxTBzprbTVSUjA8aPh6QkMMaSlOQ8zmjcp7RX6bYTbqNvfF+u/+x6thdvb/B8T815KuBNwhuL8NBwRg8YzfK/LCfr7CwMhos/uJhLP7yU3MJcLJbcwlxGTxod1KFT1sKsvQFZx3Ed6flcT674+Ap6xfXix6t/5LGTH2u2q9oaKjwxvF7jIiISvBQ4iYhIUBg4EEJCArutbvZs2LVLgVN1MjKc0wOnTp1BTk7TDJsAwkLCePGMF1m3bR33TL2nQXNNWTWF2yff3myahB+sUE8oF/W7iAXXLiAuMg5L5Z5ORaVF/G3K31yqrmZZC7MYPWn03oBs/Y71rNjinM4347IZ9I3v63aJjVrXzK54Ig/8FiXu/DgXqhERkYZQ4CQiIkEhKgr69w9s4JSd7YRcgwYF7poSnI4/9HiuP/Z6nv3uWb5b991BzZFTkMMF715Az/Y9eWX4K82qSfjB8hgPm4o2VflcXmEeT81+io07Nwa4qurt3rObmz+/maLSogOem/zLZDxG/7VuqISMBHqM70F4UjgYCO8cTotDW5A/MZ/i9dpW5wv5Wfk6BVBEAkL/KoqISNBIS4PvvnO2ugVCdjYcdxxERwfmehLcModm0rF1R66adBWlZaX1em9RaRFnvXUWe7x7+PCCD2kd3tpPVTY9idFVd6JvEdKCW768hY5PduSst87i4+Uf1/v3xRd279nNR8s+YtT7o4h/PJ6NRVUHYHmFPjjCUQAndErJSYGpkJKXwpFfHknZjjKWXrwU623aJxz6W35WPstHL9cpgCISEAqcREQkaKSmwu7d8MMP/r/W1q3w/fdw8sn+v5Y0Dm3C2/Dcn55jQf4CnprzVJ3fZ63lqklXOU3Cz3mdw9sd7scqm57MoZlEhlXuUB8ZFsmE4RNYdO0ibhx4I9+s+Ybhbw6n81Oduf3L21mycYlfa9pVuosPln5AxvsZxD8ez4i3RvC/lf/j/D7nEx8ZX+V7qgvOpOGiekVx2DOHUTClgLxHgy/Ya0wrhlaNWYW3qPLpkDoFUET8RYGTiIgEjRNPdO5nzfL/taZPB69X/ZukshE9R3BWz7N4YPoD/LLllzq956k5T/H6wtd5aMhD/OnwP/m5wqYno18G488YT1J0EgZDUnQS488YT0a/DPrE9+GJPzzB2pvX8tHIjzj+0ON5+tun6fN8H45/6XhemPsChbt9c7TlrtJdvL/0fS5870Lin4jn7LfP5ouVX3BBnwv4YtQX/Hbrb7x05ks8eeqTVQZkmUOb2BGOQabDFR2IOz+O1feupnB2gI8zrUFjWTFkvZaCrwqcOqtQnFeMt9Rb5XNSf/n5WcyenQykM3t2Mvn5wXsIgog/KXASEZGgER8P3bsHpo9TdrbTN2rgQP9fSxqXZ//4LKGeUK799FqsrXn7TkWT8LN7nc3f0oKzyXVjkNEvg5ybcpg6aCo5N+WQ0a9yh/qwkDDO7HEmH478kHW3rGPcH8axo2QH13x6DYeMO4RR749iyqopeG39vmEuKi3ivSXvMfLdkcQ9Hsc5b59D9qpsLup7EV+O+pL1t67nxTNf5A/d/kBYSNjeWqsLyMR/jDH0GN+DiM4RLLlwCaUFgd9eWZVqVwzd7f6KIVtmKZhZwIq/rmD2obOZnza/hhfDnKQ5rLpnFbtydgWuyCYoPz+L5ctHU1ycC1iKi3NZvny0T0InBVnS2IS6XYCIiMi+0tLggw+c1UceP/5YJDvbaRbeooX/riGNU6c2nXhk2CNc/9n1ZC3MYtQRo6p83b5NwicOn6gm4QESHxXPLSm3cPPxNzP317m8Mv8V3lj0BlkLs0iKTuLSIy/lsqMuo0vbLmQtzGLMlDHkFeaROD+RzKGZjOgxgs9WfMa7S9/lk58/oai0iLjIOEYdMYrzep/HoORBhHpq/i9yRr8MMvplMH36dAYPHhyYT1wIjQ6l1xu9+DH1R34e/TO93+rt+p+74rxqVgytKeaHE3+gbXpbYobE0CalDSEtQ/xejy2zFH5VyIZ3NrDpvU2U/FaCJ8JD7B9jiTsvjrKdZay8cWWlkMwT6aHjNR0pWl5E3j/yyPtHHrGnxNLh6g60O70dnlCtUaiPVavG4PVWPljA6y1i6dJLyM0dS1hYe0JD2xEW1o6wsPaV7p3xirFYjPn9a6YiyKqYuyLIAkhIUOAtwUmBk4iIBJXUVHj5ZVi2DHr39s818vLg55/hmmv8M780ftcccw2vLXiNm7+4mVMPO5X2ke0rPa8m4e4zxnBsp2M5ttOxPHnKk3y47EMm/DiBh2Y+xN9n/p1e7Xvxy9ZfKCkrASC3MJdLP7gUj/FQ6i0lPiqeS464hPP6nMdJSSfVGjJJcIg+PpqumV1Zddcq1p+8no5XdXS1ntDYUPZs3nPAeEibEGyZJffhXHLH5mLCDdEp0cSkxzgB1HFt8LTwTZBjyywFswrY+M5GNr2/T8j0JydkandaO0Jb//71HdIyhFVjVlGcV0x4YjhdM7uSkJEAwO683ax/eT3rX1rP4rMW06JDCzpc0YEOV3YgIinCJ/U2dcXF1fUZ8xIV1Y/S0k3s3r2a7du/p7R0E9aWVPN6Q2hozN4AaseOn/B6K68+83qLWLVqjAInCVr6l1VERIJKaqpzP2uW/wKnKVOce/Vvkup4jIfxZ4zn6BeO5vbJt/PK8Ff2Prdvk/BPLvpETcKDQERoBCP7jmRk35HkFebx6k+v8uCMB9njrRwElNkyWoa15IuRX3BS0kmEePy/4kR8r/Ptndk6ZSsrb1hJ9AnRRPWJcqWO3/7zmxM2eYB9dtV5Ij10f747CRkJ7Nm2h8KvCtk6dSsF0wrIuT8H7nNeE50aTcyQGNqmt6VV/1b1Wknk3eOlcGYhG9/dyMb3N1KaX4qnpRMyxZ8XT+xpsYS2qvpbvYSMBBIyEpg+fTopg1MqPReRGEGXB7uQdG8SWz7bwq8v/EpuZi65mbnEnhpLx6s7EntabJNZ9ZSfle80TM+D2YmzK4VvBys8PLF8O93+40n06fN2pTFrLWVlO9mzZzOlpZsoLa36fs+ezQeETRWKi3OZP38IkZG9iYrqs/e+RYu4Bn0eIr6gwElERIJKt26QkOD0cbr6av9cIzvb6RfVt69/5pemoW98X+444Q7+8dU/uPiIi0nvkg7A03Oe5vWFrzN2yFg1CQ9CidGJ3HPSPdw37b4qn99ZspMhXYYEuCrxJeMx9Hy1J3OPnMviCxYz4PsBAdmutq/1E9az/MrltB3WlviL4sl5MKfKFUOhbUJp96d2tPtTOwBKt5RSMLOAgqkFFEwrYPXdq1nNakJahxB9UvTeLXitjmzFhjc2VApDkh9KJqJjhLNd7v1NlG4sxRPpod1p7Yg711nJFBLlm18HT6iH9me2p/2Z7dmdW77q6eX1LBqxiBYd91n1lNh4Vz1VNHyv2F5Y0fAdaFDo1LVrZqWtbwAeTyRdux54sIAxhtDQVoSGtiIiIqnGeWfPTq4yyPJ4ovB6d5Of/1/KyrbvHQ8La09kZB+iovYNonoTFhZ/wFbU/PwsVq0aA+Qxe3YiXbtm+mTVlL/mlcZDgZOIiAQVY5w+Tv5qHG6tEzgNG+ZcS6Qm95x0D28veZsL37uQ8JBw1mxbA8AxHY7h7rS7Xa5OapIYnUhu4YHfnCVGJ7pQjfha+CHh9Hq1FwtOXcAvt/xC9391D9i1f33pV36+6mfa/qEtfT/sS0jLEDpc3qHKFUP7C4sNI25EHHEjnNUnJRtKKJhesHcF1JZPtwBgogx2t4Uy533FucUsv8QJQzyRHtqd3s7ZLvdH34VM1YlIiqDL37uQdF8SWz4tX/U01tkqGPvH8lVPf4pl41sbfb5ayJ+qbfg+ZlWD6q4IVFatGkNxcR7h4b4JWqoLsnr0eIGEhAystRQXr6OoaDE7dy6hqGgJO3cuJj8/i7KybXvfExrarlIIVVy8nnXrnt67gspXvaHUc0pAgZOIiASh1FR4911YuxYOPdS3cy9aBBs2aDud1E3LsJac1/s8Hv7q4Urjizcu5o1Fb+hksiCWOTST0ZNGU1T6+zdnkWGRZA49cJWBNE6xp8TS+bbOrHliDW2HtSXuHP9vIfr1hV/5+Zqfif1jLH3e70NIRMPCnhbxLYg/P5748+MBKF5XzNZpW/n5mp+xZQeekhnWPozjc48nJDLw20E9oR7aD29P++Hlq55eKl/1NHwRITEheHd6saVOzb5aLeRP1TZ8r2a8PhISMkhIcA4WSEkZ3OD5KuaE6oMsYwwREYcSEXEosbGn7H2ftZaSkl8rhVA7dy5hw4Y32bOnoMpreb1FLFv2Z9avfwljwvF49r1FHDBW1eOVK2+usnm6L3pOaUVW46HASUREgk5FH6evvoKRI3079+TJzr0CJ6mr1xe+fsDYrj27GDNljAKnIFbxe7P3lLpo55Q6/Z41LV0yu1Awo4DlVy6n9TGt/drYet3z61hx/QpiT4ul73t98YT7vo9ReKdwDhl1CMsuWVbl86WbS10Jm/YXkRRBl4e6kHR/Eps/2czSC5fuDZsq+GK1kD+FJ4ZTnHtguBSeGO5CNXVzMEGWMYbw8E6Eh3ciNvbkveNOEPUbs2d3Ag4MN60twdo9lJXtxOstxustxtrivR9XPLb2wKb5NSkuzuXbb3vQokUCLVokEBaWsPfj/R+HhEQe8H5/rZzSiiz/UOAkIiJB58gjISrKP4FTdjb06AGdO/t2Xmm68gqrPnGounEJHhn9Msjo53xzNnjwYLfLET/wtPDQ+43ezD16LksylnDU9KP80tB67XNrWfnXlbQ7ox193unjl7BpX40lDPGEeogbEcfi4sVVPu+L1UL+0jWzK0svXlopa/FEeuia2dW9ogLICaI61Njk/OijZ9U6j7VlB4RQXm8x8+cPpqRk/QGvDwlpTatWR1JSks+OHQspLc2udqVVSEirAwKp/Pw3qlw5tXLlLYSGtqvjZ3+glStv8duKrOZMgZOIiASd0FBISfF9H6eSEpgxAy6/3LfzStOmXkAiwa1lt5Z0f6E7Sy9aSu6DuXR5qItP51/7f2tZedNK2o9oT++3euNp4f8T2rpmdq3U0BqCOwxpLAHZvtqe0hYshMSEUFZYdkDD9+aiPk3Oq2JMCCEhkQesRurW7fEq5+3e/V8HBDhebzElJRsoKcmntDSfkpL88o837P24qOhnCgtnUVZWWGUdpaUbWLjwj3X9tOusuDiXX365i6io3uWN13sREuLOyZiNkQInEREJSmlp8MADUFgI0dG+mXPOHCgq0nY6qR/1AhIJfgkXJrB18lZyM3OJSY+h7ZC2Ppl3zZNr+OXWX2h/dnt6v9kbT5j/wyb4ve/RqjGrqjz9Ltg0toAMoHCmE1wc8ckR/Fj6Y60N35sqfzU5r8+8Hk84ERGdiYioffn57NlJFBcfuMI4LOwQ+vb94KDrXbToLEpLfztg3Jgw1q59CmtL9o5FRCQfcAJgZGQvQkNbVTl3RW8oX/76NhYKnEREJCilpjonyn3zDfzRRz+wys4Gjwe0s0bqQ72ARBqHw589nMJvClk6ainHzD+GFnEtGjRf3mN5rLpzFXHnxdErq1fAwqYKCRkJJGQk1On0O7dVCsjKVzp1ebhL0AZkAAXTC/C09ND62NbwjdvVuMsfTc79NW/Xrv+ocuXUYYc9QXT08Qc972GHPVHNKYDjiYu7gN27f9nbcL3iJMCtWydXCqLCw5MqhVBRUb3ZsWMRK1fe0Gx7QylwEhGRoDRwIISEONvqfBk4HXssxMT4Zj5pPtQLSCT4hUSF0PvN3vww8AeWXb6MfpP6YYw5qLlyH85l9d9WE3dBHL1e6+WXvlBNzd6AbMJ0uALCosPcLqlGBTMKiD4xOiBbJMV33FqRFRnZg8jIHsTFnb33PV7vHnbvXlUphNq5czFbt07F2ur7lzWn3lAKnEREJChFRUH//r7r41RYCN99B3fd5Zv5REQk+LQ+qjXdnujGyhtWsvb/1tL5pvqfEJEzNoece3OIvyienv/pqbCpvpIhrH0YW6du5ZBLD3G7miqVbi5l54KdxI+Nd7sUOQjBsiLL4wklMrI7kZHdgRF7x60tY9euVRQVLWHRohFVvreqbYFNkf72FBGRoJWW5oRExT445GbGDCgrU/8mEZGmrtNfOtHuzHasumMV23/YXq/35jzohE0JoxLo9apWNh0UD8QMjqFgWgHW2tpf74KCmc6paDGDteRZfM+YECIjD6d9++GEhydV+Zrw8OZx8Ij+BhURkaCVmgq7d8O8eQ2fKzsbIiOd0+9ERKTpMsbQc0JPwuLDWDJyCXu276n1PdZaVt+/mpwHcki4NIGeE3tiQg5uO55ATHoMxWuK2b1qt9ulVKlS/yYRP+raNROPp/IJfvU5BbCxU+AkIiJB68QTnXtfbKubPBlOOgnCg/eEZhER8ZGwdmH0zurNrl92seIvK2p8rbWW1feuJvfvuRxy+SH0fFlhU0PFDHFWDm2dutXlSqpWML2ANie0Uf8m8buEhAx69BhfvtLJEB6eRI8e45tF/yZQ4CQiIkEsPh66d2944LR2LSxbpu10IiLNScygGJLuTSL/1Xx+e+3A486hPGz622ryMvPocGUHerzUQ2GTD0T2iKTFIS0omFbgdikHKN1Sys6FO7WdTgImISGDlJQcBg/2kpKS02zCJlDgJCIiQS4tDb7+Grzeg59jyhTnXoGTiEjzknRPEtFp0ay4dgVFK4oqPWetZdWdq8h7JI8OV3eg+wvdMR6FTb5gjCEmPTj7OBXMLACr/k0igaDASUREglpqKmzZ4qxQOljZ2RAXB/36+a4uEREJfp5QD72yemHCDEsuXIK3xPnphbWWX277hTWPr6HjtR3p/rzCJl+LGRJDyW8lFC0rqv3FAVQwvQBPhIc2x7ZxuxSRJk+Bk4iIBLXUVOd+1qyDe7+1TuA0dCh49K+eiEizE9E5gp6v9GTHvB183f5rSIevor9i7ZNr6fTXThz+z8MVNvlB2yFtAYJuW93e/k3h+k+BiL/pT5mIiAS1bt0gIeHg+zgtWQK//abtdCIizVnZjjJMqKFsexlYKNvuPG49sDXGKGzyh4iuEYQnhgdV4FS6pZSdC9S/SSRQFDiJiEhQM8bp43SwgVN2tnOvwElEpPlaNWYVdk/lXkJ2j2X1mNUuVdT0GWOIGRLD1mlbsd7g6ONUOKtQ/ZtEAkiBk4iIBL3UVMjJcU6bq6/sbDj8cEhK8nlZIiLSSBTnFddrXHyj7ZC27Nm8h52LdrpdCrBP/6bj1L9JJBAUOImISNCr6ONU31VOpaUwfbpWN4mINHfhieH1GhffiBnirCQKlm11BdMLaJOi/k0igaI/aSIiEvSOPBJatap/4PTdd7BjhwInEZHmrmtmVzyRlb/18UR66JrZ1aWKmoeIxAgiukWwdepWt0uhdGspO37aoe10IgGkwElERIJeaCikpNQ/cJo82ekBNWSIf+oSEZHGISEjgR7jexCeFA4GwpPC6TG+BwkZCW6X1uS1HdKWghkF2DJ3+zipf5NI4ClwEhGRRiE1FRYsgMLCur8nOxuOOQbatvVfXSIi0jgkZCSQkpMCUyElJ0VhU4DEpMdQVljGjvk7XK2jon9T6+Nau1qHSHOiwElERBqF1FSwFr75pm6v37YN5szRdjoRERE3VawocntbXcH0Atoc34aQiBBX6xBpThQ4iYhIozBwoLO1rq7b6mbOhLIyBU4iIiJuCu8QTmTPSFcbh5duLWXHfPVvEgk0BU4iItIoREVB//51D5yysyEiAk44wb91iYiISM1i0mMonFWIt9TryvULv1L/JhE3KHASEZFGIzXVOXmuuLj212ZnQ1qaEzqJiIiIe2KGxFC2o4ztc7e7cv2C6QWYcEPrgerfJBJICpxERKTRSE2F3bth3ryaX7d+PSxeDCefHJi6REREpHoVK4vc2lZXML2A6JRo9W8SCTAFTiIi0miceKJzX9u2uilTnHv1bxIREXFfi/YtiDoiypXAqbSglB0/7iB6UHTAry3S3ClwEhGRRiM+Hrp3rz1wys6Gdu3gyCMDU5eIiIjULGZIDIVfFeItDmwfJ/VvEnGPAicREWlU0tLg66/BW83/V62FyZNh6FDw6F85ERGRoNA2vS3e3V62fbstoNet6N/U5vg2Ab2uiChwEhGRRiY1FbZsgWXLqn5+2TL49VdtpxMREQkm0SdFgyfwfZwKphfQ5vg26t8k4gIFTiIi0qikpjr3s2ZV/Xx2tnOvwElERCR4hMWE0eroVmydujVg16zo3xQzSNvpRNygwElERBqVbt0gIaH6Pk7Z2dC1K3TpEti6REREpGZt09uybc42ynaVBeR6hV8Vglf9m0TcosBJREQaFWOcPk5VBU579sC0aVrdJCIiEoxihsRgSyzbvglMH6fCGYWYFurfJOIWBU4iItLopKZCTg6sXVt5/PvvYft2OPlkV8oSERGRGkSnRkMIAdtWt7d/U0v1bxJxgwInERFpdCr6OO2/yik721kBNWRI4GsSERGRmoW2DqXNcW0C0jh8T+Eetv+wXdvpRFykwElERBqdI4+EVq2qDpz694d27dypS0RERGoWMySGbd9tY8/2PX69zt7+TWoYLuIaBU4iItLohIZCSkrlwGnHDpg9W/2bREREglnMkBgoKw+E/KhgRoH6N4m4TIGTiIg0SqmpsGABFJb/f3XWLCgtVeAkIiISzKJPiMa0MH7fVlcwvYA2A9sQEqn+TSJuUeAkIiKNUmoqWAvffOM8njwZwsPhxBPdrUtERESqFxIZQpvj2/i1cfiebXvYPk/9m0TcpsBJREQapYEDna11FdvqsrOdEKplS3frEhERkZrFDIlhx487KC0o9cv86t8kEhwUOImISKMUFeU0CP/qK9iypQULF2o7nYiISGPQNr0teKFwpn/6OBVML8CEGdqkqH+TiJsUOImISKOVmgrffQfffhsLwMknu1yQiIiI1KrNwDZ4Ijx+21ZXMEP9m0SCgQInERFptFJTYfdueOutzsTGwlFHuV2RiIiI1MYT7qHNiW380jhc/ZtEgocCJxERabR++825z82NYvduePNNd+sRERGRummb3padC3ZSsqnEp/MWfl0IZShwEgkCCpxERKRRysqC2277/XFR0f+3d/exddX3Hcc/38SJgxPH1zylYYTQVDRtR9tAAmp4CDhUDCiiZYyJKpWYaBetajdgajdQpqpVFakPdJ20bu2y0hWVp1IKLa1UGkYe2FQgJJBAIARoEsJDSCDLtZ0E8mB/98c5hhvnnmP7/n7X99h+v6QrXx9ff/zTuf76/O7X5/yutHhxsh0AABRbqSNpCJVXxT3LifWbgOKg4QQAGJGWLEmaTJX270+2AwCAYmud16pxk8dFv6yuvLqs1rNbWb8JKAAaTgCAEWn79qFtBwAAxTFuwjiVFpSiNpwOdx9W91rWbwKKoiENJzPbZmbPmNl6M1ubbjvWzB4ysxfTj+0Vj7/ZzF4ys81m9meNGDMAoFhOOWVo2wEAQLGUOkrav2m/Duw4ECWP9ZuAYmnkGU4d7j7H3eeln98k6WF3P03Sw+nnMrOPSLpG0p9KukTSv5sZ50cCwBi3dKnU0nLktpaWZDsAACi+2Os4lVeVZU2mtvltUfIAhCnSJXWflnRbev82SZ+p2H63ux9w962SXpJ0dgPGBwAokEWLpGXLpJkzJTPXzJnJ54sWNXpkAABgMFrPaNX4tvHRLqvrXN2ZrN80mfMTgCIwdx/+H2q2VdIeSS7pP9x9mZmV3b1U8Zg97t5uZj+Q9Ji7355uv1XS79z93iq5iyUtlqRp06bNvXsUvD/23r17NWXKlBGTW89scskll1xyR1duPbPJJZdccskdIblLJG2TNIh3mc3NflvS5ZI+K+kLg//xA+YGIJfc0aqjo2NdxdVq2dx92G+STko/nihpg6QFksr9HrMn/fhvkj5Xsf1WSVcN9DPmzp3ro8HKlStHVG49s8kll1xyyR1dufXMJpdccskld2Tkbv/+dl+plf729reDsnc/uNtXaqXvXr57SD9/oNwQ5JI7Wkla64Po/TTkkjp3fz39uEvS/UoukdtpZtMlKf24K334q5JmVHz7yZJeH77RAgAAAADqoX1h8l5RoZfVvbt+0zms3wQUxbA3nMxsspm19t2XdLGkjZIekHRt+rBrJf06vf+ApGvMrNnM3i/pNElrhnfUAAAAAIDYJp8+WU3HNWnPij1BOeVVZbWexfpNQJE0NeBnTpN0v5n1/fw73f1BM3tC0j1m9nlJ2yVdLUnu/qyZ3SPpOUmHJX3J3XsaMG5VMvGJAAAR0klEQVQAAAAAQEQ2ztTe0a7yyrLcXenrxCE5vPewutd2a8ZXZwz8YADDZtgbTu6+RdLHq2zfLemijO9ZKok3ugYAAACAUabUUdKb976pd7a+o2NmHTPk7+/6Q5f8sKt0YWngBwMYNg1ZwwkAAAAAAClpOEmq+bK6vvWbpp4zNeawAASi4QQAAAAAaJiWD7Vo4vsm1rxweHlVWa3zWtU0pRErxgDIQsMJAAAAANAwZqZSR+nddZyGomdfj7qf6OZyOqCAaDgBAAAAABqq1FHSwR0HtX/z/iF9X+cfOlm/CSgoGk4AAAAAgIZqX9guSUO+rK68qiyNl6aey/pNQNHQcAIAAAAANNSkWZPUPKO5pobT1LOmsn4TUEA0nAAAAAAADXXEOk69g1vHqWdfj7rXdKvtgrY6jw5ALWg4AQAAAAAarn1huw69dUj7nt03qMd3Psr6TUCR0XACAAAAADRcqSNpHA32srq+9ZvazuUMJ6CIaDgBAAAAABpu0imTNGnWJO1ZsWdQjy+vKqt1XquaWlm/CSgiGk4AAAAAgEJoX9iuztWd8p78dZx69ifrN5Uu4HI6oKhoOAEAAAAACqHUUdLh8mHt3bA393Fdj3bJD7F+E1BkNJwAAAAAAIXQt47TQJfVsX4TUHw0nAAAAAAAhdA8vVktH2oZcOHw8qqyWue2qmkq6zcBRUXDCQAAAABQGKWOkjof6VTvod6qX+/Z36Oux7tYvwkoOBpOAAAAAIDCKHWU1LO3R93ruqt+nfWbgJGBhhMAAAAAoDD6GklZl9WVV5elcVLbeazfBBQZDScAAAAAQGFMPGGiJn90cnbDifWbgBGBhhMAAAAAoFBKHSV1/m+neg8cuY7Tu+s3cTkdUHg0nAAAAAAAhdK+sF29b/eqa03XEdu7HuuSH3QWDAdGABpOAAAAAIBCaVvQJtnR6zixfhMwctBwAgAAAAAUyoT2CZpyxhTtWbHniO3lVWW1ntmqpjbWbwKKjoYTAAAAAKBw2he2q+vRLvW83ZNsOJBcUsf6TcDIQMMJAAAAAFA4pY6S/KCr69F0HafnJD/oaruAy+mAkYCGEwAAAACgcNrOb5PG673L6taL9ZuAEYSGEwAAAACgcJpamzT1rKnvLRy+QZpyxhRNKE1o7MAADAoNJwAAAABAIZU6Supe062Dbx2UnhPrNwEjCA0nAAAAAEAhlRaW5Iddr9zyinSIhhMwktBwAgAAAAAUUts5bbIJptd+8JpkrN8EjCQ0nAAAAAAAhTS+ZbwmzZqk3n29kktr56zVzjt2NnpYAAaBhhMAAAAAoJB23rFT72x5593PD7x8QJsXb6bpBIwANJwAAAAAAIW0ZckW+SE/Ylvv/l5tWbKlQSMCMFg0nAAAAAAAhXRg+4EhbQdQHDScAAAAAACF1HxK85C2AygOGk4AAAAAgEKatXSWxrUc+bJ1XMs4zVo6q0EjAjBYNJwAAAAAAIU0bdE0zV42W80zmyWTmmc2a/ay2Zq2aFqjhwZgADScAAAAAACFNW3RNM3fNl9aIc3fNp9mEzBC0HACAAAAAABAVDScAAAAAAAAEBUNJwAAAAAAAERFwwkAAAAAAABR0XACAAAAAABAVDScAAAAAAAAEBUNJwAAAAAAAERFwwkAAAAAAABR0XACAAAAAABAVDScAAAAAAAAEBUNJwAAAAAAAERFwwkAAAAAAABRmbs3egx1YWZvSnq50eOI4HhJb42g3Hpmk0suueSSO7py65lNLrnkkkvu6MqtZza55A5H7mgy091PGOhBo7bhNFqY2Vp3nzdScuuZTS655JJL7ujKrWc2ueSSSy65oyu3ntnkkjscuWMRl9QBAAAAAAAgKhpOAAAAAAAAiIqGU/EtG2G59cwml1xyySV3dOXWM5tccskll9zRlVvPbHLJHY7cMYc1nAAAAAAAABAVZzgBAAAAAAAgKhpOBWVmPzGzXWa2MXLuDDNbaWabzOxZM7s+Uu4kM1tjZhvS3G/EyK3IH29mT5nZbyNmbjOzZ8xsvZmtjZhbMrN7zez5dD/Pj5A5Ox1n363LzG6INN4b0+dso5ndZWaTIuVen2Y+GzrWavVgZsea2UNm9mL6sT1S7tXpmHvNrKZ3p8jI/W76O/G0md1vZqVIud9MM9eb2XIzOylGbsXXvmJmbmbHRxrv183stYrf5ctijdfM/tbMNqfP33cijffnFWPdZmbrI+XOMbPH+v7+mNnZkXI/bmaPpn/bfmNmU2vIrXqcCK25nNygmsvJDaq5nNygmsvKrfh6TTWXM96gmssbb0jN5Yw3qOZycoNqLic3qOYsY/4Uod6ycmMc47KyQ2suKze05nLnqAE1lzXe0JrLHG9gzWWNN7TmsnJDay4rN/g4l+Yc8doitOZycoNrLiM3eF6ZkRs8r6yWW7G95nllxniD55VZ4w2pN1Rwd24FvElaIOlMSRsj506XdGZ6v1XSC5I+EiHXJE1J70+Q9LikT0Qc999LulPSbyNmbpN0fB2eu9skfSG9P1FSKXL+eElvSJoZIetPJG2VdEz6+T2S/ipC7umSNkpqkdQk6b8lnRaQd1Q9SPqOpJvS+zdJ+nak3A9Lmi1plaR5Ecd7saSm9P63I453asX9v5P0oxi56fYZkn4v6eVaaiVjvF+X9JXA369quR3p71lz+vmJsfZDxde/J+lrkca7XNKl6f3LJK2KlPuEpAvS+9dJ+mYNuVWPE6E1l5MbVHM5uUE1l5MbVHNZuennNddczniDai4nN6jm8vZDxWOGXHM54w2quZzcoJpTxvwpQr1l5cY4xmVlh9ZcVm5ozWXOUQNrLmu8oTWXlRtacwPO1WusuazxhtZcVm7wcS793iNeW4TWXE5ucM1l5AbPKzNyg+eV1XLTbUHzyozxBtVbTm7wvJJbcuMMp4Jy90ck/V8dcne4+5Pp/W5Jm5Q0HUJz3d33pp9OSG9RFggzs5MlfUrSj2Pk1VP6X5YFkm6VJHc/6O7lyD/mIkl/dPeXI+U1STrGzJqUNIhej5D5YUmPuft+dz8sabWkK2sNy6iHTytp7in9+JkYue6+yd031zLOAXKXp/tCkh6TdHKk3K6KTyerhrrL+XvzfUn/UEvmALlBMnK/KOlb7n4gfcyuSLmSJDMzSX8p6a5IuS6p77+ybaqh7jJyZ0t6JL3/kKSrasjNOk4E1VxWbmjN5eQG1VxOblDNDXAcrrnm6nh8z8oNqrmBxltrzeXkBtVcTm5QzeXMn0LrrWpupGNcVnZozWXlhtZc3hw1pObqMvfNyQ2tudzxBtRcVm5ozWXlBh/nMl5bBM8rq+XGqLmM3OB5ZUZu8Lwy57Vb0LyyXq8JM3KD55VI0HAaw8zsVElnKPmPQYy88elpuLskPeTuUXIl/YuSP069kfL6uKTlZrbOzBZHypwl6U1J/5WelvljM5scKbvPNarhRW817v6apFskbZe0Q1Knuy+PEL1R0gIzO87MWpT8Z2tGhNxK09x9h5S8EJB0YuT8erpO0u9ihZnZUjN7RdIiSV+LlHmFpNfcfUOMvH6+nJ6u/ZNaT1mv4oOSzjezx81stZmdFSm3z/mSdrr7i5HybpD03fR5u0XSzZFyN0q6Ir1/tQLrrt9xIlrNxT7+DCI3qOb658aqucrcmDVXZT9Eqbl+udFqLuN5C665frnRaq5fbnDNZcyfguutjvOywWTXVHNZuaE1Vy03Rs3l7IegmsvIDa65AZ63mmsuIze45jJyYxznqr22iHGMq9drloFyaz3GVc2NcIw7KjfSMS5rP4Qe46rl1nteOWbQcBqjzGyKpF9KuqFfJ7tm7t7j7nOUdNjPNrPTQzPN7HJJu9x9XfAAj3auu58p6VJJXzKzBREym5Rc4vJDdz9D0j4lp+VGYWYTlRxkfxEpr13Jf3TeL+kkSZPN7HOhue6+ScnpvQ9JelDSBkmHc79pjDCzJUr2xR2xMt19ibvPSDO/HJqXNgmXKFLzqp8fSvqApDlKmpzfi5TbJKldyen2X5V0T/rf2lg+q0iN3tQXJd2YPm83Kj0rMoLrlPw9W6fksp+DtQbV4zjRiNzQmquWG6PmKnPT8UWpuSrjjVJzVXKj1FzO70NQzVXJjVJzVXKDa64e86d65g6UHVJzWbmhNVcl92OKUHMZ4w2uuYzc4Job4Hei5prLyA2uuYzcoJqr12uLRuXWWm95uSH1Vi03xrwyZ7xB9ZaTW+955ZhBw2kMMrMJSiZLd7j7fbHzPbmEbJWkSyLEnSvpCjPbJuluSQvN7PYIuXL319OPuyTdL2nIi/ZW8aqkVyv+Y3SvkgZULJdKetLdd0bK+6Skre7+prsfknSfpHNiBLv7re5+prsvUHLZT6wzQ/rsNLPpkpR+LPyprmZ2raTLJS1y9yiXnPZzp2o4tbyKDyhpQm5Ia+9kSU+a2ftCg919ZzqB7JX0n4pTd1JSe/elp+CvUfJfqpoWpOzPkstN/1zSz2Pkpa5VUm9S0kCOsh/c/Xl3v9jd5yp54fDHWnIyjhPBNVev409WbmjNDWK8NdVcldwoNVdtvDFqLmM/BNdczvMWVHMZucE1l7F/o9RcmlU5f4p2jIs8L8vNjnWcyxlz0HGuIrfvn21RjnOV4415nOu3H6Id56o8b1GOc/1yox3n+u3f0JrLem0RWnP1es2SmRtYb4MZby31dlSupJ8pvN6qjjdCvWXth7rNK8caGk5jTNqZvVXSJnf/54i5J1j67ghmdoySRsbzobnufrO7n+zupyq5lGyFuwefgWNmk82ste++koX3gt8R0N3fkPSKmc1ON10k6bnQ3Aqxz7LYLukTZtaS/m5cpGRdimBmdmL68RQlk5iY45akB5RMZpR+/HXk/KjM7BJJ/yjpCnffHzH3tIpPr1CcunvG3U9091PT2ntVyWK5b4Rm903mUlcqQt2lfqVkUiMz+6CSBfvfipT9SUnPu/urkfKkZC2LC9L7CxWpIVtRd+Mk/ZOkH9WQkXWcCKq5Oh5/quaG1lxOblDNVcuNUXM54w2quZznLajmBvh9qLnmcnKDai5n/wbVXM78KbTe6jIvy8uOUHNZuaE1Vy33qQg1lzXe0JrLeu5Cay7vdyKk5rJyQ2sua/8G1VzOa4ugmqvXa5as3NB6y8kNqreM3KtC6y1nvEH1lvO81XNeObZ4AVYu53b0TcmL8x2SDikpys9Hyj1PydpFT0tan94ui5D7MUlPpbkbVcM7OQ3iZ1yoSO9Sp2StpQ3p7VlJSyKOc46ktem++JWk9ki5LZJ2S2qLvF+/oeRgslHJfyCaI+X+j5Jm2wZJFwVmHVUPko6T9LCSCczDko6NlHtlev+ApJ2Sfh8p9yVJr1TUXS3vJlct95fpc/e0pN8oWdQ4OLff17eptnepqzben0l6Jh3vA5KmR8qdKOn2dF88KWlhrP0g6aeS/iby7+95ktal9fG4pLmRcq9X8u5ZL0j6liSrIbfqcSK05nJyg2ouJzeo5nJyg2ouKze05nLGG1RzOblBNZe3H0JqLme8QTWXkxtUc8qYP0Wot6zcGMe4rOzQmsvKDa25AeeoNdZc1nhDay4rN7TmMvdDYM1ljTe05rJyg49zFT/jQr33rmTB88qM3OCay8gNnldm5AbPK6vl9ts+5HrLGW/wvDIjN3heyS25WbpDAQAAAAAAgCi4pA4AAAAAAABR0XACAAAAAABAVDScAAAAAAAAEBUNJwAAAAAAAERFwwkAAAAAAABR0XACAAAYZma2N2P7T83sL4Z7PAAAALHRcAIAAAAAAEBUTY0eAAAAwFhlZibpXyUtlLRVkjV2RAAAAHFwhhMAAEDjXClptqSPSvprSec0djgAAABx0HACAABonAWS7nL3Hnd/XdKKRg8IAAAgBhpOAAAAjeWNHgAAAEBsNJwAAAAa5xFJ15jZeDObLqmj0QMCAACIgUXDAQAAGud+JQuGPyPpBUmrGzscAACAOMyds7gBAAAAAAAQD5fUAQAAAAAAICoaTgAAAAAAAIiKhhMAAAAAAACiouEEAAAAAACAqGg4AQAAAAAAICoaTgAAAAAAAIiKhhMAAAAAAACiouEEAAAAAACAqP4fZXwq4hB/HfgAAAAASUVORK5CYII=\n",
"text/plain": [
"<Figure size 1440x504 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"## Quiz\n",
"print(tableau)\n",
"printBold(\"Participation aux quiz avec le rapport le plus récent\")\n",
"fig2,ax3=plt.subplots(1,1,figsize=(20,7),sharey='all')\n",
"ax3.plot(tableau.loc[(tableau.loc[:,\"Label\"]==\"Semaine 1\") & (tableau.loc[:,\"Type\"]==\"Quiz\"),\"Id\"],list(tableau.loc[(tableau.loc[:,\"Type\"]==\"Quiz\") & (tableau.loc[:,\"Label\"]==\"Semaine 1\"),\"Nb\"]),\"ro-\")\n",
"ax3.plot(tableau.loc[(tableau.loc[:,\"Label\"]==\"Semaine 2\") & (tableau.loc[:,\"Type\"]==\"Quiz\"),\"Id\"],list(tableau.loc[(tableau.loc[:,\"Type\"]==\"Quiz\") & (tableau.loc[:,\"Label\"]==\"Semaine 2\"),\"Nb\"]),\"bo-\")\n",
"ax3.plot(tableau.loc[(tableau.loc[:,\"Label\"]==\"Semaine 3\") & (tableau.loc[:,\"Type\"]==\"Quiz\"),\"Id\"],list(tableau.loc[(tableau.loc[:,\"Type\"]==\"Quiz\") & (tableau.loc[:,\"Label\"]==\"Semaine 3\"),\"Nb\"]),\"go-\")\n",
"ax3.plot(tableau.loc[(tableau.loc[:,\"Label\"]==\"Semaine 4\") & (tableau.loc[:,\"Type\"]==\"Quiz\"),\"Id\"],list(tableau.loc[(tableau.loc[:,\"Type\"]==\"Quiz\") & (tableau.loc[:,\"Label\"]==\"Semaine 4\"),\"Nb\"]),\"mo-\")\n",
"ax3.plot(tableau.loc[(tableau.loc[:,\"Label\"]==\"Semaine 5\") & (tableau.loc[:,\"Type\"]==\"Quiz\"),\"Id\"],list(tableau.loc[(tableau.loc[:,\"Type\"]==\"Quiz\") & (tableau.loc[:,\"Label\"]==\"Semaine 5\"),\"Nb\"]),\"yo-\")\n",
"ax3.legend([\"Semaine 1\",\"Semaine 2\",\"Semaine 3\",\"Semaine 4\",\"Semaine 5\"])\n",
"ax3.xaxis.set_ticks(range(1,47))\n",
"ax3.grid()\n",
"fig2.suptitle(f\"Quiz du {'/'.join(liste_date[0])}\")\n",
"plt.xlabel(\"Id\")\n",
"plt.ylabel(\"Nombre de participants\")\n",
"plt.show() "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"hideCode": false,
"hidePrompt": false
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"hideCode": false,
"hidePrompt": false
},
"outputs": [],
"source": []
}
],
"metadata": {
"celltoolbar": "Hide code",
"hide_code_all_hidden": false,
"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": "3.6.4"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Untitled Folder/StatProblemGradeReport-BioInfo.ipynb 0 → 100644
View file @ 88f38cea
This source diff could not be displayed because it is too large. You can view the blob instead.
Untitled Folder/inria_41003_selfpaced_grade_report_2020-06-02-0932.csv 0 → 100644
View file @ 88f38cea
This source diff could not be displayed because it is too large. You can view the blob instead.
Untitled Folder/inria_41003_selfpaced_problem_grade_report_2020-06-02-0932.csv 0 → 100644
View file @ 88f38cea
This source diff could not be displayed because it is too large. You can view the blob instead.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment