{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Partie 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from scipy.spatial import distance\n",
    "import seaborn as sns\n",
    "from sklearn.decomposition import PCA\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.manifold import TSNE\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_path = \"../data/\"\n",
    "\n",
    "df_genes_data = pd.read_csv(data_path + \"data.csv\")\n",
    "df_genes_labels = pd.read_csv(data_path + \"labels.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>Unnamed: 0</th>\n",
       "      <th>gene_0</th>\n",
       "      <th>gene_1</th>\n",
       "      <th>gene_2</th>\n",
       "      <th>gene_3</th>\n",
       "      <th>gene_4</th>\n",
       "      <th>gene_5</th>\n",
       "      <th>gene_6</th>\n",
       "      <th>gene_7</th>\n",
       "      <th>gene_8</th>\n",
       "      <th>...</th>\n",
       "      <th>gene_20521</th>\n",
       "      <th>gene_20522</th>\n",
       "      <th>gene_20523</th>\n",
       "      <th>gene_20524</th>\n",
       "      <th>gene_20525</th>\n",
       "      <th>gene_20526</th>\n",
       "      <th>gene_20527</th>\n",
       "      <th>gene_20528</th>\n",
       "      <th>gene_20529</th>\n",
       "      <th>gene_20530</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>sample_0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.017209</td>\n",
       "      <td>3.265527</td>\n",
       "      <td>5.478487</td>\n",
       "      <td>10.431999</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.175175</td>\n",
       "      <td>0.591871</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>4.926711</td>\n",
       "      <td>8.210257</td>\n",
       "      <td>9.723516</td>\n",
       "      <td>7.220030</td>\n",
       "      <td>9.119813</td>\n",
       "      <td>12.003135</td>\n",
       "      <td>9.650743</td>\n",
       "      <td>8.921326</td>\n",
       "      <td>5.286759</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>sample_1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.592732</td>\n",
       "      <td>1.588421</td>\n",
       "      <td>7.586157</td>\n",
       "      <td>9.623011</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.816049</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>4.593372</td>\n",
       "      <td>7.323865</td>\n",
       "      <td>9.740931</td>\n",
       "      <td>6.256586</td>\n",
       "      <td>8.381612</td>\n",
       "      <td>12.674552</td>\n",
       "      <td>10.517059</td>\n",
       "      <td>9.397854</td>\n",
       "      <td>2.094168</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>sample_2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.511759</td>\n",
       "      <td>4.327199</td>\n",
       "      <td>6.881787</td>\n",
       "      <td>9.870730</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.972130</td>\n",
       "      <td>0.452595</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>5.125213</td>\n",
       "      <td>8.127123</td>\n",
       "      <td>10.908640</td>\n",
       "      <td>5.401607</td>\n",
       "      <td>9.911597</td>\n",
       "      <td>9.045255</td>\n",
       "      <td>9.788359</td>\n",
       "      <td>10.090470</td>\n",
       "      <td>1.683023</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>sample_3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.663618</td>\n",
       "      <td>4.507649</td>\n",
       "      <td>6.659068</td>\n",
       "      <td>10.196184</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.843375</td>\n",
       "      <td>0.434882</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>6.076566</td>\n",
       "      <td>8.792959</td>\n",
       "      <td>10.141520</td>\n",
       "      <td>8.942805</td>\n",
       "      <td>9.601208</td>\n",
       "      <td>11.392682</td>\n",
       "      <td>9.694814</td>\n",
       "      <td>9.684365</td>\n",
       "      <td>3.292001</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>sample_4</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.655741</td>\n",
       "      <td>2.821547</td>\n",
       "      <td>6.539454</td>\n",
       "      <td>9.738265</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.566967</td>\n",
       "      <td>0.360982</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>5.996032</td>\n",
       "      <td>8.891425</td>\n",
       "      <td>10.373790</td>\n",
       "      <td>7.181162</td>\n",
       "      <td>9.846910</td>\n",
       "      <td>11.922439</td>\n",
       "      <td>9.217749</td>\n",
       "      <td>9.461191</td>\n",
       "      <td>5.110372</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 20532 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  Unnamed: 0  gene_0    gene_1    gene_2    gene_3     gene_4  gene_5  \\\n",
       "0   sample_0     0.0  2.017209  3.265527  5.478487  10.431999     0.0   \n",
       "1   sample_1     0.0  0.592732  1.588421  7.586157   9.623011     0.0   \n",
       "2   sample_2     0.0  3.511759  4.327199  6.881787   9.870730     0.0   \n",
       "3   sample_3     0.0  3.663618  4.507649  6.659068  10.196184     0.0   \n",
       "4   sample_4     0.0  2.655741  2.821547  6.539454   9.738265     0.0   \n",
       "\n",
       "     gene_6    gene_7  gene_8  ...  gene_20521  gene_20522  gene_20523  \\\n",
       "0  7.175175  0.591871     0.0  ...    4.926711    8.210257    9.723516   \n",
       "1  6.816049  0.000000     0.0  ...    4.593372    7.323865    9.740931   \n",
       "2  6.972130  0.452595     0.0  ...    5.125213    8.127123   10.908640   \n",
       "3  7.843375  0.434882     0.0  ...    6.076566    8.792959   10.141520   \n",
       "4  6.566967  0.360982     0.0  ...    5.996032    8.891425   10.373790   \n",
       "\n",
       "   gene_20524  gene_20525  gene_20526  gene_20527  gene_20528  gene_20529  \\\n",
       "0    7.220030    9.119813   12.003135    9.650743    8.921326    5.286759   \n",
       "1    6.256586    8.381612   12.674552   10.517059    9.397854    2.094168   \n",
       "2    5.401607    9.911597    9.045255    9.788359   10.090470    1.683023   \n",
       "3    8.942805    9.601208   11.392682    9.694814    9.684365    3.292001   \n",
       "4    7.181162    9.846910   11.922439    9.217749    9.461191    5.110372   \n",
       "\n",
       "   gene_20530  \n",
       "0         0.0  \n",
       "1         0.0  \n",
       "2         0.0  \n",
       "3         0.0  \n",
       "4         0.0  \n",
       "\n",
       "[5 rows x 20532 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_genes_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>Unnamed: 0</th>\n",
       "      <th>Class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>sample_0</td>\n",
       "      <td>PRAD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>sample_1</td>\n",
       "      <td>LUAD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>sample_2</td>\n",
       "      <td>PRAD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>sample_3</td>\n",
       "      <td>PRAD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>sample_4</td>\n",
       "      <td>BRCA</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Unnamed: 0 Class\n",
       "0   sample_0  PRAD\n",
       "1   sample_1  LUAD\n",
       "2   sample_2  PRAD\n",
       "3   sample_3  PRAD\n",
       "4   sample_4  BRCA"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_genes_labels.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_genes_data = df_genes_data.drop(columns=df_genes_data.columns[0])\n",
    "df_genes_labels = df_genes_labels.drop(columns=df_genes_labels.columns[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>gene_0</th>\n",
       "      <th>gene_1</th>\n",
       "      <th>gene_2</th>\n",
       "      <th>gene_3</th>\n",
       "      <th>gene_4</th>\n",
       "      <th>gene_5</th>\n",
       "      <th>gene_6</th>\n",
       "      <th>gene_7</th>\n",
       "      <th>gene_8</th>\n",
       "      <th>gene_9</th>\n",
       "      <th>...</th>\n",
       "      <th>gene_20521</th>\n",
       "      <th>gene_20522</th>\n",
       "      <th>gene_20523</th>\n",
       "      <th>gene_20524</th>\n",
       "      <th>gene_20525</th>\n",
       "      <th>gene_20526</th>\n",
       "      <th>gene_20527</th>\n",
       "      <th>gene_20528</th>\n",
       "      <th>gene_20529</th>\n",
       "      <th>gene_20530</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2.017209</td>\n",
       "      <td>3.265527</td>\n",
       "      <td>5.478487</td>\n",
       "      <td>10.431999</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.175175</td>\n",
       "      <td>0.591871</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>4.926711</td>\n",
       "      <td>8.210257</td>\n",
       "      <td>9.723516</td>\n",
       "      <td>7.220030</td>\n",
       "      <td>9.119813</td>\n",
       "      <td>12.003135</td>\n",
       "      <td>9.650743</td>\n",
       "      <td>8.921326</td>\n",
       "      <td>5.286759</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.592732</td>\n",
       "      <td>1.588421</td>\n",
       "      <td>7.586157</td>\n",
       "      <td>9.623011</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.816049</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>4.593372</td>\n",
       "      <td>7.323865</td>\n",
       "      <td>9.740931</td>\n",
       "      <td>6.256586</td>\n",
       "      <td>8.381612</td>\n",
       "      <td>12.674552</td>\n",
       "      <td>10.517059</td>\n",
       "      <td>9.397854</td>\n",
       "      <td>2.094168</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>3.511759</td>\n",
       "      <td>4.327199</td>\n",
       "      <td>6.881787</td>\n",
       "      <td>9.870730</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.972130</td>\n",
       "      <td>0.452595</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>5.125213</td>\n",
       "      <td>8.127123</td>\n",
       "      <td>10.908640</td>\n",
       "      <td>5.401607</td>\n",
       "      <td>9.911597</td>\n",
       "      <td>9.045255</td>\n",
       "      <td>9.788359</td>\n",
       "      <td>10.090470</td>\n",
       "      <td>1.683023</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>3.663618</td>\n",
       "      <td>4.507649</td>\n",
       "      <td>6.659068</td>\n",
       "      <td>10.196184</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.843375</td>\n",
       "      <td>0.434882</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>6.076566</td>\n",
       "      <td>8.792959</td>\n",
       "      <td>10.141520</td>\n",
       "      <td>8.942805</td>\n",
       "      <td>9.601208</td>\n",
       "      <td>11.392682</td>\n",
       "      <td>9.694814</td>\n",
       "      <td>9.684365</td>\n",
       "      <td>3.292001</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2.655741</td>\n",
       "      <td>2.821547</td>\n",
       "      <td>6.539454</td>\n",
       "      <td>9.738265</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.566967</td>\n",
       "      <td>0.360982</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>5.996032</td>\n",
       "      <td>8.891425</td>\n",
       "      <td>10.373790</td>\n",
       "      <td>7.181162</td>\n",
       "      <td>9.846910</td>\n",
       "      <td>11.922439</td>\n",
       "      <td>9.217749</td>\n",
       "      <td>9.461191</td>\n",
       "      <td>5.110372</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 20531 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   gene_0    gene_1    gene_2    gene_3     gene_4  gene_5    gene_6  \\\n",
       "0     0.0  2.017209  3.265527  5.478487  10.431999     0.0  7.175175   \n",
       "1     0.0  0.592732  1.588421  7.586157   9.623011     0.0  6.816049   \n",
       "2     0.0  3.511759  4.327199  6.881787   9.870730     0.0  6.972130   \n",
       "3     0.0  3.663618  4.507649  6.659068  10.196184     0.0  7.843375   \n",
       "4     0.0  2.655741  2.821547  6.539454   9.738265     0.0  6.566967   \n",
       "\n",
       "     gene_7  gene_8  gene_9  ...  gene_20521  gene_20522  gene_20523  \\\n",
       "0  0.591871     0.0     0.0  ...    4.926711    8.210257    9.723516   \n",
       "1  0.000000     0.0     0.0  ...    4.593372    7.323865    9.740931   \n",
       "2  0.452595     0.0     0.0  ...    5.125213    8.127123   10.908640   \n",
       "3  0.434882     0.0     0.0  ...    6.076566    8.792959   10.141520   \n",
       "4  0.360982     0.0     0.0  ...    5.996032    8.891425   10.373790   \n",
       "\n",
       "   gene_20524  gene_20525  gene_20526  gene_20527  gene_20528  gene_20529  \\\n",
       "0    7.220030    9.119813   12.003135    9.650743    8.921326    5.286759   \n",
       "1    6.256586    8.381612   12.674552   10.517059    9.397854    2.094168   \n",
       "2    5.401607    9.911597    9.045255    9.788359   10.090470    1.683023   \n",
       "3    8.942805    9.601208   11.392682    9.694814    9.684365    3.292001   \n",
       "4    7.181162    9.846910   11.922439    9.217749    9.461191    5.110372   \n",
       "\n",
       "   gene_20530  \n",
       "0         0.0  \n",
       "1         0.0  \n",
       "2         0.0  \n",
       "3         0.0  \n",
       "4         0.0  \n",
       "\n",
       "[5 rows x 20531 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_genes_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>Class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>PRAD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>LUAD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>PRAD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>PRAD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>BRCA</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Class\n",
       "0  PRAD\n",
       "1  LUAD\n",
       "2  PRAD\n",
       "3  PRAD\n",
       "4  BRCA"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_genes_labels.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "vscode": {
     "languageId": "javascript"
    }
   },
   "outputs": [],
   "source": [
    "unique_label_dict = {\n",
    "    'PRAD': 0,\n",
    "    'LUAD': 1,\n",
    "    'BRCA': 2,\n",
    "    'KIRC': 3,\n",
    "    'COAD': 4\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "vscode": {
     "languageId": "javascript"
    }
   },
   "outputs": [],
   "source": [
    "df_genes_labels['Class'] = df_genes_labels['Class'].map(unique_label_dict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "vscode": {
     "languageId": "javascript"
    }
   },
   "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>Class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Class\n",
       "0       0\n",
       "1       1\n",
       "2       0\n",
       "3       0\n",
       "4       2\n",
       "5       0\n",
       "6       3\n",
       "7       0\n",
       "8       2\n",
       "9       0\n",
       "10      2\n",
       "11      3\n",
       "12      0\n",
       "13      2\n",
       "14      2"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_genes_labels.head(15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "genes_data = df_genes_data.to_numpy()\n",
    "genes_labels = df_genes_labels.to_numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "genes_data.shape : (801, 20531)\n",
      "genes_labels.shape : (801, 1)\n"
     ]
    }
   ],
   "source": [
    "print(\"genes_data.shape :\", genes_data.shape)\n",
    "print(\"genes_labels.shape :\", genes_labels.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Reduced data shape: (801, 2)\n"
     ]
    }
   ],
   "source": [
    "#Méthod ACP\n",
    "\n",
    "N = 2\n",
    "\n",
    "pca = PCA(n_components=N)\n",
    "reduced_data_pca = pca.fit_transform(genes_data)\n",
    "\n",
    "print(f\"Reduced data shape: {reduced_data_pca.shape}\")\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "max sur x :  184.20318064011448\n",
      "min sur x :  -89.76368500205871\n",
      "max sur y :  126.46164593179076\n",
      "min sur y :  -150.9967762434913\n"
     ]
    }
   ],
   "source": [
    "print(\"max sur x : \", reduced_data_pca[:, 0].max())\n",
    "print(\"min sur x : \", reduced_data_pca[:, 0].min())\n",
    "print(\"max sur y : \", reduced_data_pca[:, 1].max())\n",
    "print(\"min sur y : \", reduced_data_pca[:, 1].min())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "colors = ['r', 'g', 'b', 'm', 'gold']\n",
    "\n",
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "for label in unique_label_dict:\n",
    "    indices = np.where(genes_labels == unique_label_dict[label] )\n",
    "    plt.scatter( reduced_data_pca[indices, 0], reduced_data_pca[indices, 1], c = colors[unique_label_dict[label]], label=label )\n",
    "\n",
    "plt.xlabel('Composante principale 1')\n",
    "plt.ylabel('Composante principale 2')\n",
    "plt.title('Utilisation de l\\'ACP pour afficher les différents clusters')\n",
    "plt.legend()\n",
    "\n",
    "plt.xlim( reduced_data_pca[:, 0].min() - 10, reduced_data_pca[:, 1].max() + 75)\n",
    "plt.ylim( reduced_data_pca[:, 1].min() - 10, reduced_data_pca[:, 1].max() + 10)\n",
    "\n",
    "plt.savefig('../images_rapport/ACP_cluster.png', bbox_inches='tight')\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Reduced data shape: (801, 2)\n"
     ]
    }
   ],
   "source": [
    "#Méthode TSNE\n",
    "\n",
    "tsne = TSNE(n_components=2, random_state=42)\n",
    "reduced_data_tsne = tsne.fit_transform(genes_data)\n",
    "\n",
    "print(f\"Reduced data shape: {reduced_data_tsne.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1UAAAIkCAYAAAD29gEWAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAADEtUlEQVR4nOzdeVxU5f4H8M8wLCLIKggyKIjmnt1ruYaCmlqZFiKu5VLaLzVFLa+lN5c0WzSXyjWXcs2Fsrw3valQlFm2qOWWmrggCqKAioIO5/fH8QyzzzmzsH7eveZlnDnLcw4zzPnO93m+j0oQBAFERERERERkF7fybgAREREREVFlxqCKiIiIiIjIAQyqiIiIiIiIHMCgioiIiIiIyAEMqoiIiIiIiBzAoIqIiIiIiMgBDKqIiIiIiIgcwKCKiIiIiIjIAQyqiIgUys/Px6xZs5Cenl7eTSGiKur8+fOYMWMG/vjjj/JuChHJwKCKyIxhw4YhKirKYJlKpcKMGTN0P69duxYqlQoZGRll2rbyOq41xtfGUVFRURg2bJjT9udszz//PL7++ms8/PDDsrdRqVQYO3asC1slqoivD3Kte/fuYfLkyYiMjISbmxuefvppAMDNmzfxwgsvICwsDCqVCsnJycjIyIBKpcLatWsVHWPGjBlQqVS4evWq809AYRsqgri4OMTFxel+tnRdd+3ahYceegg1atSASqVCXl4eAGDdunVo0qQJPDw8EBAQYLL/u3fvIikpCUeOHEHz5s1ddyIVlLnPYKKKjkEVVRm2PvRbtGhh8CF46dIlzJgxA4cOHSqbBir01ltv4YsvvijvZpCRRYsW4ciRI/jqq6/g7e1t8Nz+/fsxY8YM3Y1TVXDs2DHMmDFDUZBWXFyMRYsW4R//+Af8/PwQEBCA5s2bY9SoUThx4oRuPSkArFGjBjIzM032ExcXhxYtWhgsi4qKgkqlMvvo2bOn3edZma1evRrvvfceEhMT8cknn2DChAkAxL8ha9euxUsvvYR169bh2WefLeeWVi+5ublISkqCt7c3PvroI6xbtw4+Pj44ceIEhg0bhpiYGKxcuRIrVqww2Xby5MlQq9XYsGED3NzK71bNnvd/ZbBkyRLFXywQ2eJe3g0gKi+XLl3CzJkzERUVhYceesjguZUrV6KkpMTq9s8++ywGDBgALy8vl7TvrbfeQmJiou5b57I6LllWXFyMW7duYdeuXahdu7bJ8/v378fMmTMxbNgws98+V0bHjh3DzJkzERcXJ/ub4759++Lrr7/GwIEDMXLkSNy9excnTpzAzp070aFDBzRp0sRg/aKiIrz99tv44IMPZO3/oYcewqRJk0yW161bV9b2Vc2+ffsQERGBBQsWmCxv164dpk+frlsmCAJu374NDw+Psm5mlVa/fn2T63rw4EHcuHEDb775Jrp166ZbnpaWhpKSEixatAgNGzY02VdeXh4CAwPx5ZdfmnxxU9bsef9XBkuWLEHt2rUrdI8IqnwYVBGZIeeGQ61WQ61Wl0FrKsZxCfD09MTrr79e3s2o0A4ePIidO3dizpw5Jtfqww8/NJvFe+ihh7By5Uq89tprsgKjiIgIDBkyxFlNLjd37tyBp6enw5mI7Oxss0F8dnY2mjVrZrBMygxWVIWFhahZs2Z5N0Mxc9c1OzsbAEx+N5aWSwICAvDGG28oOv6tW7fg4+OjaBtyrnv37qGkpASenp7l3RQqJ+z+R9VSWloaHnnkEQDA8OHDdd2HpO4Acvpzmxu78ssvv6BHjx6oXbs2vL29ER0djREjRhhsN2/ePHTo0AHBwcHw9vZG69atsW3bNoN1VCoVbt26hU8++UTXNukbNUtjZpYsWYLmzZvDy8sLdevWxZgxY0xuYKXuVMeOHUN8fDxq1qyJiIgIvPvuu7KuW1FRESZMmICQkBDUqlULvXv3xsWLF82um5mZiREjRqBOnTrw8vJC8+bNsXr1alnHMXbt2jW88soraNmyJXx9feHn54fHH38chw8flrW9NJ5p69ataNasGby9vdG+fXvdAPDly5ejYcOGqFGjBuLi4sx2dfnpp5/Qs2dP+Pv7o2bNmujcuTN++OEH3fMzZszAq6++CgCIjo7W/d6M9/XFF1+gRYsWumuya9cuk2P9/vvvePzxx+Hn5wdfX1907doVBw4cMFnv6NGj6NKlC7y9vaHRaDB79myLGdavv/4asbGx8PHxQa1atfDkk0/i6NGjVq/b2rVr0a9fPwBAfHy87pzS0tIsbnPmzBkAQMeOHU2eU6vVCA4ONln++uuvQ6vV4u2337baHkdJ753vvvsOL774IoKDg+Hn54fnnnsO169fN1lfznvK0vg/4zE3aWlpUKlU2Lx5M6ZNm4aIiAjUrFkTBQUFFttr62+FNI4nNTUVR48eNfj9qFQqnD17Fv/5z38MXouWxv6cOHECSUlJCAkJgbe3Nxo3boypU6eatCkvL0+XifX398fw4cNRWFhost769evRunVreHt7IygoCAMGDMCFCxdMrlGLFi3w66+/olOnTqhZs6ZdX1rIOdapU6fQt29fhIWFoUaNGtBoNBgwYADy8/Nt7n/FihWIiYmBt7c32rRpY7ZAjfF1jYuLw9ChQwEAjzzyiO5veFRUlC5zGBISYjIeVc77dNiwYfD19cWZM2fwxBNPoFatWhg8eDAAoKSkBAsXLkTz5s1Ro0YN1KlTBy+++KLJ6zsqKgq9evXC999/jzZt2qBGjRpo0KABPv30U906tt7/cj7vLPn666/RuXNn1KpVC35+fnjkkUewceNGi+tLr2njvz3mXs+XL1/G8OHDodFo4OXlhfDwcPTp00f3tzgqKgpHjx7Ft99+qzsn/fdqXl4ekpOTERkZCS8vLzRs2BDvvPOOwd9W6bjz5s3DwoULERMTAy8vLxw7dgwA8MEHH6B58+aoWbMmAgMD8fDDD1s9P6oamKmiaqlp06aYNWsW3njjDYwaNQqxsbEAgA4dOti9z+zsbHTv3h0hISGYMmUKAgICkJGRgZSUFIP1Fi1ahN69e2Pw4MEoLi7G5s2b0a9fP+zcuRNPPvkkAHEQ8wsvvIA2bdpg1KhRAICYmBiLx54xYwZmzpyJbt264aWXXsLJkyexdOlSHDx4ED/88INB5u369evo2bMnEhISkJSUhG3btuFf//oXWrZsiccff9zqOb7wwgtYv349Bg0ahA4dOmDfvn26Nuu7cuUK2rVrpwtmQkJC8PXXX+P5559HQUEBkpOT5V5WAMDff/+NL774Av369UN0dDSuXLmC5cuXo3Pnzjh27Jis7EZ6ejq+/PJLjBkzBgAwd+5c9OrVC5MnT8aSJUswevRoXL9+He+++y5GjBiBffv26bbdt28fHn/8cbRu3RrTp0+Hm5sb1qxZgy5duiA9PR1t2rRBQkIC/vrrL2zatAkLFizQdQ8MCQnR7ef7779HSkoKRo8ejVq1amHx4sXo27cvzp8/rws2jh49itjYWPj5+WHy5Mnw8PDA8uXLERcXh2+//RZt27YFIN44xMfH4969e5gyZQp8fHywYsUKs92F1q1bh6FDh6JHjx545513UFhYiKVLl+LRRx/F77//bvELhE6dOmHcuHFYvHgxXn/9dTRt2hQAdP+aU79+fQDAhg0b0LFjR7i72/6YiY6OxnPPPYeVK1diypQpNn+fd+/eNTt20sfHR1Z3qbFjxyIgIAAzZszQvVfOnTunu3EDlL2nlHjzzTfh6emJV155BUVFRVa/1bb1tyIkJATr1q3DnDlzcPPmTcydOxeA+PtZt24dJkyYAI1Go+sqGRISgpycHJPjHDlyBLGxsfDw8MCoUaMQFRWFM2fO4KuvvsKcOXMM1k1KSkJ0dDTmzp2L3377DR9//DFCQ0Pxzjvv6NaZM2cO/v3vfyMpKQkvvPACcnJy8MEHH6BTp074/fffDTI0ubm5ePzxxzFgwAAMGTIEderUUXQ95RyruLgYPXr0QFFREV5++WWEhYUhMzMTO3fuRF5eHvz9/S3uf9WqVXjxxRfRoUMHJCcn4++//0bv3r0RFBSEyMhIi9tNnToVjRs3xooVKzBr1ixER0cjJiYGTz/9ND799FN8/vnnWLp0KXx9ffHggw8CUPY+vXfvHnr06IFHH30U8+bN02X3XnzxRaxduxbDhw/HuHHjcPbsWXz44Yf4/fffTV63p0+fRmJiIp5//nkMHToUq1evxrBhw9C6dWs0b97c6vtf7uedOWvXrsWIESPQvHlzvPbaawgICMDvv/+OXbt2YdCgQTa3t6Vv3744evQoXn75ZURFRSE7OxvffPMNzp8/j6ioKCxcuBAvv/wyfH19dV8cSK+7wsJCdO7cGZmZmXjxxRdRr1497N+/H6+99hqysrKwcOFCg2OtWbMGd+7cwahRo+Dl5YWgoCCsXLkS48aNQ2JiIsaPH487d+7gyJEj+Omnn5xyflSBCURVxPTp0wUAQk5OjtnnmzdvLnTu3Fn388GDBwUAwpo1a0zWHTp0qFC/fn2DZQCE6dOn635es2aNAEA4e/asIAiC8PnnnwsAhIMHD1ptZ2FhocHPxcXFQosWLYQuXboYLPfx8RGGDh1qsr3xcbOzswVPT0+he/fuglar1a334YcfCgCE1atX65Z17txZACB8+umnumVFRUVCWFiY0LdvX6vtPnTokABAGD16tMHyQYMGmVyb559/XggPDxeuXr1qsO6AAQMEf39/k2tgrH79+gbnfufOHYNzEwRBOHv2rODl5SXMmjXL6r4EQfzdeXl56a6ZIAjC8uXLBQBCWFiYUFBQoFv+2muvGVzfkpISoVGjRkKPHj2EkpIS3XqFhYVCdHS08Nhjj+mWvffeewbbGrfB09NTOH36tG7Z4cOHBQDCBx98oFv29NNPC56ensKZM2d0yy5duiTUqlVL6NSpk25ZcnKyAED46aefdMuys7MFf39/gzbcuHFDCAgIEEaOHGnQnsuXLwv+/v4my41t3bpVACCkpqZaXU9SUlKie53VqVNHGDhwoPDRRx8J586dM1lXei0fPHhQOHPmjODu7i6MGzdO93znzp2F5s2bG2xTv359AYDZx9y5c622TTpe69atheLiYt3yd999VwAg7NixQxAEZe8p49eqftv1/96kpqYKAIQGDRrYfP1L5P6tMHedpLY9+eSTBsvOnj1r8nevU6dOQq1atUx+R/qvd+nv64gRIwzWeeaZZ4Tg4GDdzxkZGYJarRbmzJljsN4ff/whuLu7GyyXXifLli0zd/ompDYoPdbvv/8uABC2bt0q6ziS4uJiITQ0VHjooYeEoqIi3fIVK1YIAAx+v+auq/7r29x56H9WKXmfDh06VAAgTJkyxWDd9PR0AYCwYcMGg+W7du0yWS69j7777jvdsuzsbMHLy0uYNGmSbpml97/czztjeXl5Qq1atYS2bdsKt2/fNnhO//Vm/BksvX+M22F83a9fvy4AEN577z2r7TC+H5C8+eabgo+Pj/DXX38ZLJ8yZYqgVquF8+fPGxzXz89PyM7ONli3T58+Zt+PVPWx+x+Rk0jfvu7cuRN37961uJ7+N+nXr19Hfn4+YmNj8dtvv9l13D179qC4uBjJyckGYzNGjhwJPz8//Oc//zFY39fX12A8iqenJ9q0aYO///7b6nH++9//AgDGjRtnsNw46yQIArZv346nnnoKgiDg6tWrukePHj2Qn5+v+Fy9vLx056bVapGbmwtfX180btxY9r66du1q8E2vlPHp27cvatWqZbJcuh6HDh3CqVOnMGjQIOTm5urO5datW+jatSu+++47m0VNJN26dTPIOD744IPw8/PTHUur1eJ///sfnn76aTRo0EC3Xnh4OAYNGoTvv/9e113sv//9L9q1a4c2bdro1gsJCdF1A5J88803yMvLw8CBAw1+F2q1Gm3btkVqaqqstsulUqmwe/duzJ49G4GBgdi0aRPGjBmD+vXro3///hYrIzZo0ADPPvssVqxYgaysLKvHaNu2Lb755huTx8CBA2W1cdSoUQbf2L/00ktwd3fXvcaVvqeUGDp0qOziA87+W2FOTk4OvvvuO4wYMQL16tUzeM5c+fL/+7//M/g5NjYWubm5utdlSkoKSkpKkJSUZPB6CwsLQ6NGjUxeb15eXhg+fLhdbZd7LCkTtXv3brNdFS355ZdfkJ2djf/7v/8zyCgOGzbManbLHva8T1966SWDn7du3Qp/f3889thjBvto3bo1fH19TfbRrFkzXS8NQPz70bhxY5ufBYD8zztz53njxg1MmTLFZAyaM8rle3t7w9PTE2lpaWa79NqydetWxMbGIjAw0OAaduvWDVqtFt99953B+n379jXojQCI1+bixYs4ePCgQ+dClQ+7/1G14so5Tjp37oy+ffti5syZWLBgAeLi4vD0009j0KBBBpX6du7cidmzZ+PQoUMoKipyuG3nzp0DADRu3NhguaenJxo0aKB7XqLRaEyOFRgYiCNHjtg8jpubm0k3ROPj5uTkIC8vDytWrDBbKhgoHagtl1Qpa8mSJTh79iy0Wq3uOXNjdMwxvmGUboqMu/BIy6UP5FOnTgGAbnyEOfn5+QgMDFTcBkC89tKxcnJyUFhYaHJNAbHLTUlJCS5cuIDmzZvj3LlzugBQn/G2Uvu7dOlitk1+fn42221Ofn4+bt++rfvZ09MTQUFBAMQb5alTp2Lq1KnIysrCt99+i0WLFmHLli3w8PDA+vXrze5z2rRpWLduHd5++20sWrTI4rFr165tUE1NqUaNGhn87Ovri/DwcN2YC6XvKSWio6Nlr+vsvxXmSDfQxqXrLTF+DUuv++vXr8PPzw+nTp2CIAgm11hi3G0yIiLC7oH9co8VHR2NiRMn4v3338eGDRsQGxuL3r17Y8iQIVaDI+n3bLx/Dw8Pgy89nEHp+9Td3R0ajcZkH/n5+QgNDTW7D+O/u7b+Hlkj9/POmDTmUu7rTSkvLy+88847mDRpEurUqYN27dqhV69eeO655xAWFmZz+1OnTuHIkSMmgZLE+Bqaez//61//wp49e9CmTRs0bNgQ3bt3x6BBg8yOM6WqhUEVVRnSt176N3r6CgsLXVr1SqVSYdu2bThw4AC++uor7N69GyNGjMD8+fNx4MAB+Pr6Ij09Hb1790anTp2wZMkShIeHw8PDA2vWrCmzQayWKgcKguCU/UtZmyFDhlgMRKQxBHK99dZb+Pe//40RI0bgzTffRFBQENzc3JCcnCw7S2TpvG1dD2n/7733nknpfYmvr69DbXDWtTdHav+6devM3lTIGfNkzvjx4/HJJ5/ofu7cubPZAhbh4eEYMGAA+vbti+bNm2PLli1Yu3at2eM2aNAAQ4YMwYoVKzBlyhS72lXWLAU4Wq3W7O9bbpaqIvytMEfO+0WlUuHrr782u67xe8WRkuFKjjV//nwMGzYMO3bswP/+9z+MGzcOc+fOxYEDB0yCk/Kg9H2qn73X30doaCg2bNhg9hjGgYIjf4/kfN45k7X3mbHk5GQ89dRT+OKLL7B79278+9//xty5c7Fv3z784x//sHqckpISPPbYY5g8ebLZ5x944AGDn829fps2bYqTJ09i586d2LVrF7Zv344lS5bgjTfewMyZM60enyo3BlVUZUgD5E+ePGmSfSgsLMSFCxfQvXt33TJXZa3atWuHdu3aYc6cOdi4cSMGDx6MzZs344UXXsD27dtRo0YN7N692+DbvDVr1pjsR2779M9b/9vT4uJinD171qFv9I2PU1JSgjNnzhh8g3/y5EmD9aTKgFqt1mnH3rZtG+Lj47Fq1SqD5Xl5eWbni3ImKTPn5+dn83wcfU2FhISgZs2aJtcUEKuzubm56V7b9evX1327rc94W6n9oaGhdv0+LJ3T5MmTDbqR2srUeXh44MEHH8SpU6d0XbTMmTZtGtavX29Q+MDZTp06hfj4eN3PN2/eRFZWFp544gkAyt5TgYGBZrs0njt3zqFshpK/FY6Q2vjnn386ZX8xMTEQBAHR0dEmN6DOpvRYLVu2RMuWLTFt2jTs378fHTt2xLJlyzB79myz60uvg1OnThlkkO7evYuzZ8+iVatWzjkROP4+lfaxZ88edOzY0WnzW9n6m2bt885SGwHx9WZuji5LpL8vxu81S1njmJgYTJo0CZMmTcKpU6fw0EMPYf78+bosuaXziomJwc2bNx3+7PLx8UH//v3Rv39/FBcXIyEhAXPmzMFrr71Woac0IMdwTBVVGV27doWnpyeWLl1qkr1YsWIF7t27Z1DdTprTw9IYD6WuX79u8g2flNmQuu6o1WqoVCqDb9cyMjLwxRdfmOzPx8dHVtu6desGT09PLF682OD4q1atQn5+vtnqfPaQrt3ixYsNlhtXQ1Kr1ejbty+2b99u9kbNXPUxW9Rqtcm13bp1KzIzMxXvS6nWrVsjJiYG8+bNw82bN02e1z8fR19TarUa3bt3x44dOwxKsV+5cgUbN27Eo48+qusG9MQTT+DAgQP4+eefDdpi/C11jx494Ofnh7feesvs2Adbvw9L59SsWTN069ZN92jdujUA8Qb0/PnzJvvJy8vDjz/+iMDAQItdawDxpmbIkCFYvnw5Ll++bLVt9lqxYoXBtVi6dKnB3wcl76mYmBgcOHAAxcXFumU7d+40KemtlJK/FY4ICQlBp06dsHr1apPfmz0Z1ISEBKjVasycOdNke0EQkJub61B77TlWQUEB7t27Z/B8y5Yt4ebmZtCt0tjDDz+MkJAQLFu2zOD3u3btWqd9bkgcfZ8CYmVGrVaLN9980+S5e/fu2dVmS+9/OZ935nTv3h21atXC3LlzcefOHYPnrL3e6tevD7VabTKmacmSJQY/FxYWmuw3JiYGtWrVMmiXpc/XpKQk/Pjjj9i9e7fJc3l5eSavI3OMX+Oenp5o1qwZBEFQNP6MKh9mqqjKCA0NxRtvvIFp06ahU6dO6N27N2rWrIn9+/dj06ZN6N69O5566ind+jExMQgICMCyZctQq1Yt+Pj4oG3btorGPOj75JNPsGTJEjzzzDOIiYnBjRs3sHLlSvj5+em+AX/yySfx/vvvo2fPnhg0aBCys7Px0UcfoWHDhiZjmlq3bo09e/bg/fffR926dREdHW12DE1ISAhee+01zJw5Ez179kTv3r1x8uRJLFmyBI888ojTJkl96KGHMHDgQCxZsgT5+fno0KED9u7di9OnT5us+/bbbyM1NRVt27bFyJEj0axZM1y7dg2//fYb9uzZg2vXrik6dq9evTBr1iwMHz4cHTp0wB9//IENGzY4fVyDOW5ubvj444/x+OOPo3nz5hg+fDgiIiKQmZmJ1NRU+Pn54auvvgIAXWAxdepUDBgwAB4eHnjqqacUTco5e/ZsfPPNN3j00UcxevRouLu7Y/ny5SgqKjKYT2zy5MlYt24devbsifHjx+tKqtevX9/gteTn54elS5fi2WefxT//+U8MGDAAISEhOH/+PP7zn/+gY8eO+PDDDy2256GHHoJarcY777yD/Px8eHl5oUuXLhbHbRw+fBiDBg3C448/jtjYWAQFBSEzMxOffPIJLl26hIULF9qcvHrq1KlYt24dTp48iebNm5s8n5mZaXZclq+vL55++mmr+wbEjFPXrl2RlJSke688+uij6N27NwBl76kXXngB27ZtQ8+ePZGUlIQzZ85g/fr1VqdAkEPJ3wpHLV68GI8++ij++c9/YtSoUYiOjkZGRgb+85//4NChQ4r2FRMTg9mzZ+O1115DRkYGnn76adSqVQtnz57F559/jlGjRuGVV15xSrvlHmvfvn0YO3Ys+vXrhwceeAD37t3DunXrdF8AWeLh4YHZs2fjxRdfRJcuXdC/f3+cPXsWa9ascfrfHkffp4DYBffFF1/E3LlzcejQIXTv3h0eHh44deoUtm7dikWLFiExMVFRuyy9/zdu3Gjz887SeS5YsAAvvPACHnnkEQwaNAiBgYE4fPgwCgsLDboU6/P390e/fv3wwQcfQKVSISYmBjt37jQZ4/TXX3/p3tvNmjWDu7s7Pv/8c1y5cgUDBgzQrde6dWssXboUs2fPRsOGDREaGoouXbrg1VdfxZdffolevXrpysvfunULf/zxB7Zt24aMjAybvSO6d++OsLAwdOzYEXXq1MHx48fx4Ycf4sknnzQoikRVUBlWGiQqE+vXrxfatWsn+Pj4CF5eXkKTJk2EmTNnCnfu3DFZd8eOHUKzZs0Ed3d3g7Ks9pRU/+2334SBAwcK9erVE7y8vITQ0FChV69ewi+//GKwn1WrVgmNGjXStW3NmjUmpYIFQRBOnDghdOrUSfD29hYA6Mo2Gx9X8uGHHwpNmjQRPDw8hDp16ggvvfSScP36dYN1LJVeNne+5ty+fVsYN26cEBwcLPj4+AhPPfWUcOHCBZNrIwiCcOXKFWHMmDFCZGSk4OHhIYSFhQldu3YVVqxYYfM45kqqT5o0SQgPDxe8vb2Fjh07Cj/++KNJ2WpLAAhjxowxWCaVxDUuvSuV7jUuv/z7778LCQkJQnBwsODl5SXUr19fSEpKEvbu3Wuw3ptvvilEREQIbm5uBr8nc20wd66CIL6WevToIfj6+go1a9YU4uPjhf3795tse+TIEaFz585CjRo1hIiICOHNN98UVq1aZfb1kZqaKvTo0UPw9/cXatSoIcTExAjDhg0zeX2as3LlSqFBgwaCWq22WV79ypUrwttvvy107txZCA8PF9zd3YXAwEChS5cuwrZt2wzWtVRyWhBKy0YrKalu6zUsHe/bb78VRo0aJQQGBgq+vr7C4MGDhdzcXJP15bynBEEQ5s+fL0RERAheXl5Cx44dhV9++cViSXUlZb3l/q1wtKS6IAjCn3/+KTzzzDNCQECAUKNGDaFx48bCv//9b93zlqassPT3aPv27cKjjz4q+Pj4CD4+PkKTJk2EMWPGCCdPnrTZbkvMnbucY/3999/CiBEjhJiYGKFGjRpCUFCQEB8fL+zZs0fWcZcsWSJER0cLXl5ewsMPPyx89913Jr9fR0uqS+S8T4cOHSr4+PhYbO+KFSuE1q1bC97e3kKtWrWEli1bCpMnTxYuXbqkW8fca0MQTKcCEATz73+5n3eWfPnll0KHDh0Eb29vwc/PT2jTpo2wadMmg3M0fj/n5OQIffv2FWrWrCkEBgYKL774ovDnn38aXPerV68KY8aMEZo0aSL4+PgI/v7+Qtu2bYUtW7YY7Ovy5cvCk08+KdSqVcukPP6NGzeE1157TWjYsKHg6ekp1K5dW+jQoYMwb9483VQMlj4/BEGcrqNTp066z4qYmBjh1VdfFfLz82VdG6q8VILgwhHSREREFYQ0KerBgwfx8MMPl3dziIioCuGYKiIiIiIiIgcwqCIiIiIiInIAgyoiIiIiIiIHcEwVERERERGRA5ipIiIiIiIicgCDKiIiIiIiIgcwqCIiIiIiInKAe3k3oCIpKSnBpUuXUKtWLahUqvJuDhERERERlRNBEHDjxg3UrVsXbm7Wc1EMqvRcunQJkZGR5d0MIiIiIiKqIC5cuACNRmN1HQZVemrVqgVAvHB+fn7l3BoiIiIiIiovBQUFiIyM1MUI1jCo0iN1+fPz82NQRUREREREsoYFsVAFERERERGRAxhUEREREREROYDd/4iIqhOtFkhLEx8AEBcnPtTq8msTERFRJcegioiorGm1QHo6kJUFhIcDsbFlE9SkpACjRgG5uaXLZs8GgoOBFSuAhATXt4GIiBQRBAH37t2DVqst76ZUSR4eHlA74TOYQRURUVlKSQHGjwcuXixdptEAixa5NqhJSQH69jX/XG6u+Nz27QysiIgqkOLiYmRlZaGwsLC8m1JlqVQqaDQa+Pr6OrYfQRAEJ7Wp0isoKIC/vz/y8/NZ/Y+InC8lBUhMBIz/7EpVhbZtsx7UWMpw2cp8abVAVJRhIGeORgNkZLArIBFRBVBSUoJTp05BrVYjJCQEnp6esqrQkXyCICAnJweFhYVo1KiRScZKSWzATBURUVnQasUMlbnvsQRBDKySk4E+fcwHNZYyXAMHAps2Wc98pafbDqgAcZ20NKBrV+vnUR5dF4mIqpni4mKUlJQgMjISNWvWLO/mVFkhISHIyMjA3bt3HeoGyOp/RERlwVZgIwjAhQviesakDJfx9hcvAu+9Z7o8M1NcPyVF/DkrS347k5JKtzPXjqgoID4eGDRI/DcqyvL6RETkMDc33q67krOyf/wtERGVBbmBjfF61jJclkjrJieL24eHy9/22jXDgExiKbAzDuCIiIiqIQZVRERlQW5gY7ye3K57xvQzX7GxYpdAJaSADLDdddF4fSIiomqGQRURUVmQAhtL3QxUKvF5rVYcI5WWJv6/kq575mRliWOeFi2Sv41xV0RHui7KJc2fpX/uRERUKQ0bNgwqlQoqlQqenp5o2LAhZs2ahXv37iEtLU33nEqlQkhICJ544gn88ccfZvfVo0cPqNVqHDx40OpxPDw8UKdOHTz22GNYvXo1SkpKXH2aBhhUERGVBf3AxjiwUqnEwOT2baBbN8PxSjt2OHZcKfOVkADMnKlsWymgkxvYZWYqC4ykQGrCBCAsjGO1iIiqkJ49eyIrKwunTp3CpEmTMGPGDLz33nu650+ePImsrCzs3r0bRUVFePLJJ1FcXGywj/Pnz2P//v0YO3YsVq9ebfU4GRkZ+PrrrxEfH4/x48ejV69euHfvnkvPUR+r/xERKeFI9buEBLFsunEVv6Agca4o/Ul5AXGdzz6zr51S5is2tnRZo0bK9iEFZHK7LiYnA1evlv4cESFONtyokem1MlfNUJ80VstWmXkiIrKunKq2enl5ISwsDADw0ksv4fPPP8eXX36J9u3bAwBCQ0MREBCAsLAwJCcno3fv3jhx4gQefPBB3T7WrFmDXr164aWXXkK7du3w/vvvw9vb2+JxIiIi8M9//hPt2rVD165dsXbtWrzwwgsuP1eAmSoiIvmUVL+z1J0tIUGcCyo1Fdi4EdizBzD6gHCahQsNPziVFKyIjCwNyGx1XZToB1SAGBhNn256rSwVvdDHsVpERI6rQFVbvb29TTJRAJCfn4/NmzcDADw9PXXLBUHAmjVrMGTIEDRp0gQNGzbEtm3bZB2rS5cuaNWqFVLK8DwrbVD19ttvQ6VSITk5Wbfszp07GDNmDIKDg+Hr64u+ffviypUr5ddIIqo6lFS/s/UhplYDcXHiHFNqtX2FKKzx8yvN8OgHd6mp8rZXqQwDMltdF+XKzAT69hWzV3KqGTpjrBYRUXVVQaq2CoKAPXv2YPfu3ejSpYtuuUajga+vLwICArBx40b07t0bTZo00T2/Z88eFBYWokePHgCAIUOGYNWqVbKP26RJE2RkZDjtPGyplEHVwYMHsXz5coP0IABMmDABX331FbZu3Ypvv/0Wly5dQgK7jRCRo+RWvysuBmbNEgMHuR9ijhaiMKegQPzXOLibNUve9m+8IXZJ1M+ySV0XIyIM161dW367pGtl3M3RFldcIyKiqqwCVG3duXMnfH19UaNGDTz++OPo378/ZsyYoXs+PT0dv/76K9auXYsHHngAy5YtM9h+9erV6N+/P9zdxdFKAwcOxA8//IAzZ87IOr4gCE6bg0qOSjem6ubNmxg8eDBWrlyJ2bNn65bn5+dj1apV2Lhxoy4KXrNmDZo2bYoDBw6gXbt25dVkIqrs5Fa/i4gw7QKnv45KJX6I9elTmgVS0iVPLpVKzAZdu6ZsfivJBx8YFrXQaMRMVUKC2Hb9vvmZmcCQIc5ruzmuuEZERFWZkqqtcXEuaUJ8fDyWLl0KT09P1K1bVxccSaKjoxEQEIDGjRsjOzsb/fv3x3fffQcAuHbtGj7//HPcvXsXS5cu1W2j1WqxevVqzJkzx+bxjx8/jujoaOeelBWVLlM1ZswYPPnkk+jWrZvB8l9//RV37941WN6kSRPUq1cPP/74Y1k3k4iqErmZEksBlcRcdza545WUEAQxG2RPQAWIwZg+/SybftfFuDjTzJUzqVSGY7uIiEgeeyecdyIfHx80bNgQ9erVMwmojI0ZMwZ//vknPv/8cwDAhg0boNFocPjwYRw6dEj3mD9/PtauXQutjQzbvn378Mcff6Bv375OOx9bKlWmavPmzfjtt9/M1qm/fPkyPD09ERAQYLC8Tp06uHz5stn9FRUVoaioSPdzgdRlhoiqJ0sVkpydKdH/EJPGK5XhH37FLGXZgNKgMDPT/iDOGuNiG0REZJu9E86Xk5o1a2LkyJGYPn06nn76aaxatQqJiYlo0aKFwXqRkZF47bXXsGvXLjz55JMAxPv5y5cvQ6vV4sqVK9i1axfmzp2LXr164bnnniuzc6g0maoLFy5g/Pjx2LBhA2rUqOGUfc6dOxf+/v66R2RkpFP2S0SVkLXiEs7OJjn6IRYS4px2KGGpaIS1IhbmqFRAcLD4r7X1IyNZTp2IyF5yJpyvYD0Bxo4di+PHj+Pdd9/F4cOHzWaZ/P390bVrV4OCFbt27UJ4eDiioqLQs2dPpKamYvHixdixYwfUZfilnEoQXPHVovN98cUXeOaZZwwujlarhUqlgpubG3bv3o1u3brh+vXrBtmq+vXrIzk5GRMmTDDZp7lMVWRkJPLz8+Hn5+fS8yGiCkSqkGT851D6MJJKuCYmiv868mdToxFLqkt/y7RaMXiTWwFw5kxgyhSgbl3lBR+cYf16YPBg0+W25p3St327+K/x+n5+QPfuwP/9n9i1kBkqIqrG7ty5g7NnzyI6Otq+hIL02QYYfm7pf7bxiyur17mgoAD+/v6yYoNKk6nq2rUr/vjjD4N+lQ8//DAGDx6s+38PDw/s3btXt83Jkydx/vx53SRjxry8vODn52fwIKJqRm6FpD59zFe/U5o1GjnSMFiwNZjY2Mcfy1vPzc2547QkEyaYL8Mrzb+lX+DCGv31g4LEZQUF4jUeNgzYscNJDSYiqqYsVW3VaBhQuUClGVNVq1Ytk36VPj4+CA4O1i1//vnnMXHiRAQFBcHPzw8vv/wy2rdvz8p/RGSZkgpJ5qrfdegAxMTID4waNTL8Wekg4QsXgCVLbGepSkqU7VeunBxx/NeWLUC/fqbPr1hhex/jx4vXcccOYMYM04BWKozBD30iIseY+9ySxguTU1WaoEqOBQsWwM3NDX379kVRURF69OiBJUuWlHeziKgiU1ohSap+p09JoYkrV8TsmCMl1f/6S/k2zjZwoJgJS0wsLfCxd68YENly8aI4/5W1DKGlwhhERKSMuc8tcrpKM6aqLCjpN0lEVURamliUwpbUVOsfSlu3ioGGnIkU9ed9ksZUKame5+MD3Lolb11Xe/VVcZJgJV0YAWDaNEBvrkGLbF13IqIqyuExVSRLtRtTRUTkEs6qkNSvH7B5s7xjGs/7JFXPk8vVAZWSLnfvvac8oFLChXOoEBEROQuDKiKq3myVBBcE+XMlJSaKle2Cg62vJwji4//+DyguLh1MXB6l0s1p1sy1+9do5GefKsgcKkRERNYwqCIikoIaqQqdPksBklYrdh3ctEn8V+r216cPILebRk6OGGCkpIhtuHgRqF3bnjNwrrg402pRzrRokZj5s3auFXAOFSIiIksYVBERSa5dM79M6qonMTdRcP36wKxZYjU7OcUaJDk5pfv39ASWL3dNKXS5QkLEQGbUKOfv289PHHsGiBUTr141v550/nIzhEREROWMhSr0sFAFUTVlawJelUrMKJ09K5YBNzdRsCP0969WK5tI1xU0GvEcFy50fF/e3sDt26U/BwfbLgcfGSkeW87YLqnyIEsFE1EVw0IVZYOFKoiInEXuXFX79lkuA+4I/bmwgNKJcYcPl78Plcr2WC65Ll50TkAFGAZUgO2AKiQEOH1aXkBlLmMYFWV+cmIiIiIXYlBFRCS3wlzfvmVX6W7HDmDNGvnbCgIweLDYxc4ZVKryyfjk5AD799teLyVFzKYZ/z70KysSEVG5GDZsGJ5++mmT5XFxcUhOTjZZvnbtWgQEBJgsv3jxIjw9PdGiRQuzx1GpVLqHj48PGjVqhGHDhuHXX3918AyUY1BFRCS3wtyNG2XTDq0WGDdO/nZu9/+UL14MFBQ4py2CIG/OLVewFeRqtdYnDgbEiYPLq/1EROQUa9euRVJSEgoKCvDTTz+ZXWfNmjXIysrC0aNH8dFHH+HmzZto27YtPv300zJtK4MqIiJbc1WVBY2mtNLd4MHKil2UlLimTeXFVpArt7um1J2SiKga05ZokZaRhk1/bEJaRhq0JZXjCydBELBmzRo8++yzGDRoEFatWmV2vYCAAISFhSEqKgrdu3fHtm3bMHjwYIwdOxbXr18vs/YyqCIismcCXmcbOVJsx+TJwGeflW9byovcMupyu2ty4mAiquZSjqcgalEU4j+Jx6CUQYj/JB5Ri6KQcrzid5FOTU1FYWEhunXrhiFDhmDz5s24deuWrG0nTJiAGzdu4JtvvnFxK0sxqCIiAqzPVVUWGjUSJwJ+//3yOX55U1JGXW53TU4cTETVWMrxFCRuScTFAsPMfmZBJhK3JFb4wGrVqlUYMGAA1Go1WrRogQYNGmCrNC2HDU2aNAEAZGRkuLCFhhhUEVH1ZG7y3oQEYMuW8mlPeDiwZIn8cUC+vq5tj6vVqmX4c0SEGNTKqfpnq7smJw4mompOW6LF+F3jIcB07Km0LHlXcoXtCpiXl4eUlBQMGTJEt2zIkCEWuwAak2aMUpVht373MjsSEVFFYW4eKI1G7ALYp4/4/5mZjpVOj4wUs06BgUC/foClft3SHFWxsaUT48px86b9basIjIt+mLvWluagkrprJiaK109/W04cTESE9PPpJhkqfQIEXCi4gPTz6YiLiiuzdvn5+SE/P99keV5eHvz9/XU/b9y4EXfu3EHbtm11ywRBQElJCf766y888MADVo9z/PhxAEB0dLSTWm4bM1VEVL3YKsW9Y0fp+Cp7vuFKTgZSU8WJfBMTgfz80up8xvQDgB07gA0blB3L0n4rkunTgZkzba936ZJhKXRbc1BJ3TUjIgz3o9HIz3gREVVRWTfkjSmVu56zNG7cGL/99pvJ8t9++80gUFq1ahUmTZqEQ4cO6R6HDx9GbGwsVq9ebfM4CxcuhJ+fH7p16+bU9lvDTBURVR+2SnGrVGJQdPaseGNunM2yJTkZWLCg9GcpgLOU8QoKAlasEP/f2nqWVPSqfxoN8PrrQEyM7XX1r39JCZCUZHo9pMBXCpoSEsTMorlsFhFRNRZeS96YUrnr2SM/Px+HDh0yWNarVy98+OGHGDduHF544QV4eXnhP//5DzZt2oSvvvoKAHDo0CH89ttv2LBhg25slGTgwIGYNWsWZs+eDXd3MYzJy8vD5cuXUVRUhL/++gvLly/HF198gU8//dTs3FeuwqCKiKoPJaW49W/Y9+4FZs+2vf8+fcR/pfFaI0daD5S8vYFevcSgw5GuhnK1awccOOD640g6dgTefFN+YCpd/9GjbQe+ffqUdgWMi3Nmq4mIKr3YerHQ+GmQWZBpdlyVCipo/DSIree6sadpaWn4xz/+YbDs+eefx3fffYepU6eiW7duKC4uRpMmTbB161b07NkTgJilatasmUlABQDPPPMMxo4di//+97/o3bs3AGD48OEAgBo1aiAiIgKPPvoofv75Z/zzn/902bmZoxKEsvgkrxwKCgrg7++P/Px8+Pn5lXdziMjZNm0Su5LZsnEjMHBg6c9ardj1zNI4K2lc1NmzYjc+JRmuBQuACRPkrUulUlMZTBFRlXbnzh2cPXsW0dHRqFGjhuLtpep/AAwCKxXErufbkrYhoSm7Slu7zkpig0rQIZ+IyAH6Vf6uXJG3jXEpbv15rIzHWRmPizI3XsuaM2fkr0ulOAcVEZFVCU0TsC1pGyL8DMeeavw0DKhcgN3/iKjqMlflT622XbY8J8d0mVQYwVzVwIULxe5oUVHKu/HJGW9kzLjiXVWhUgG1a5u//sZCQ13fHiKiSi6haQL6NO6D9PPpyLqRhfBa4YitFwu1G8eeOhszVURUNVmq8idnHqhJk8yvl5AAZGSIXc82biyt8peQYHu8ljGpy2CzZrYnHDYuvKDRyKuoVxl99JH1OagkQ4eWVgIkIiKL1G5qxEXFYWDLgYiLimNA5SLMVBFR1WOtyp8cUrEKc2N2LBVGUNIdTco03b4N9OhhfT0A2LxZzODoV7gDgJUrlQVyFVlICLBsmRigqtXm56DSJ5VgZ/l0IiKqAJipIqKqR2nWyBylY3aMx2FZI2WmcnOtryfNuZSYKAZyAweK/+pPgFuGs8W71IIFpcGRpTmo9EnBVnKyvOwjERGRCzGoIqKqxxlFDE6dUrZ+bKztbmtBQcD//gfYquIUFATs2VPatdCShATglVeUtbOiMg6gEhKAtWutb6NfAp+IiKgcMagioqpHSdbovq0j/wHtn0DJUUD7J7D14hemY3b0KwmmpRlmSGxVCFSpxO56Hh5iaXZrrl0rzUZZo9UCMmaWr9BUKiAysrRLo77sbHn7YCVAIiIqZwyqiKjqkZM10qP9E0ic8DvUasDN7f6Qngm/Q9u4b2nglJIiVveLjxfnuoqPF3/WD7wsdVuTuvElJMgPAD76yHzwpm/OHNtdCC3x9S3/roP65ejNBZByg2M7gmgiIiJnYlBFRFWPtayREe2fYiBljpsboD3hDsyaBfTtazpOKzNTHO9kHFhZqhAIyA8Atm2zHLwBYqAlnaM9bt4s/7LsKpXYfdFSF0dbwbG1LBcREVEZYlBFRFWTjGIHW0f+QxdQWZrT183tfldAcywVS5AqBOoXlpDExgLBwQpOBOaDt/R0sZtgZVZSArz3nuXS6HInXbbVTZKIiMjFGFQRUdWlnzVav14sS67/9PjfdcOdzJGeSxj/u+VjlEWxBHPBW1mNI1ISANrbndBaBT85XSqJiKhCGTZsGFQqle4RHByMnj174siRI7p19J/38/PDI488gh07dpjsa/v27YiLi4O/vz98fX3x4IMPYtasWbhm9MXi7du3ERQUhNq1a6OoqMjl52iMQRURVW1S1mjwYGD5cuhHUXJjAFnryQ1y0tPtGwclBW/DhgF79wKhocr3YY9nn5W3XnKy9RLo1tgKSm11qSQiIous1VhypZ49eyIrKwtZWVnYu3cv3N3d0atXL4N11qxZg6ysLPzyyy/o2LEjEhMT8ccff+ienzp1Kvr3749HHnkEX3/9Nf7880/Mnz8fhw8fxrp16wz2tX37djRv3hxNmjTBF198URanaICT/xJR9SFlPcaPBy5elD2kSNZ6csdKOZphWr9efAQHi49r1+SPjbI2ma45wcFAr15iFztb+vQB5s0Tg6OsLODKFWDCBPnHsnVdLE26TEREFqWk6D7ydDQasWe1q7+X8vLyQlhYGAAgLCwMU6ZMQWxsLHJychASEgIACAgIQFhYGMLCwvDmm29i0aJFSE1NRcuWLfHzzz/jrbfewsKFCzF+/HjdfqOiovDYY48hLy/P4HirVq3CkCFDIAgCVq1ahf79+7v2BI0wU0VE1Yte1iNl0T8gCJbjDOm5lEX/sL5PtRq4elXe14HOqlSXmys+rAVJxl33NBpgyxbxX7nHkLaTUyxCfyzZyy/LPw7ACn5ERE6WkiIOx5VTY8nVbt68ifXr16Nhw4YINtOt/N69e1i1ahUAwNPTEwCwYcMG+Pr6YvTo0Wb3GRAQoPv/M2fO4Mcff0RSUhKSkpKQnp6Oc+fOOf9ErGCmioiqn/s3//3ifoP2qApubmJsoh83SLFKSQnQb6WVMVWAGDz16ycGMfpd+8x9HShVtMvMdE71PV9foLBQbKj++U2cCMydW5o5Cg8vDXzUarGaoRzZ2eI5JCaaZrqsFYuQikwkJlo/T5VKvB6s4EdE5DRarZihMvfnV/q8S04WOxm4qtbPzp074evrCwC4desWwsPDsXPnTrjpldwdOHAg1Go1bt++jZKSEkRFRSEpKQkAcOrUKTRo0AAeHh42j7V69Wo8/vjjCAwMBAD06NEDa9aswYwZM5x/YhYwU0VE1Zq6yT2DeERfSQmgbqFgZ8Zjpcx9Haig3LssN2/C5ARKSsSueDt2iJmj+x9Q2LJFzKD16QPMnClv/+HhlotF+PqKz/n7m8/KSdtZKnbBCn5ERC6Rnm6aodJXFjWW4uPjcejQIRw6dAg///wzevTogccff9wgg7RgwQIcOnQIX3/9NZo1a4aPP/4YQUFB99so74tHrVaLTz75BEOGDNEtGzJkCNauXYsSSx/wLsCgioiqN7Ua6pPbsW3BP6DVivGIVgtsW/APZQGVOcZV+6TugUVFwIwZpkFKUBBQo4aDBzU67tat5ictbtbMemEJ4zmgpG6TM2eKwRQA3LgBbN8OdOsG1Kljvi9JQoI4vmrmTPH89LGCHxGRS8gdvuvKQrI+Pj5o2LAhGjZsiEceeQQff/wxbt26hZUrV+rWCQsLQ8OGDdG9e3esWbMG/fv3R3Z2NgDggQcewN9//427d+9aPc7u3buRmZmJ/v37w93dHe7u7hgwYADOnTuHvXv3uu4EjTCoIiJKSEC/ntOg7qmBW3MxO9Vv5e+lxSAcIX0dOGeOYXAzfbr43MyZpRXttmwB7txxyinpjpuUZL5DfVKS2A5zNeUtZZB27BDbffOm6fFyc8UuheYCK7UaeOMNsSshK/gREbmc3GGqZTmcVaVSwc3NDbdv3zb7fJs2bdC6dWvMmTMHADBo0CDcvHkTS5YsMbu+VKhi1apVGDBggC4rJj0GDBigG6dVFjimiogIEG/u+/QxHYMEiMv27gVmz7Z//9Onmy67dEnMWG3bJnbT27TJ/v0rIWWyVq8Wg51Vq0xLQy1caBjwSB30bRk/3nInfVbwIyIqE7aG75bFcNaioiJcvnwZAHD9+nV8+OGHuHnzJp566imL2yQnJ+OZZ57B5MmT0bZtW0yePBmTJk1CZmYmnnnmGdStWxenT5/GsmXL8Oijj2LQoEH46quv8OWXX6JFC8PuJc899xyeeeYZXLt2Tdel0JWYqSIikuhXr4uLKy3qEBcnBj/WquDZw7h7YFlXwMvNFTNlxhkzcxkkWx30JRcvuraTPhER2WRt+G5ZDWfdtWsXwsPDER4ejrZt2+LgwYPYunUr4qx8udazZ09ER0frslXvvPMONm7ciJ9++gk9evRA8+bNMXHiRDz44IMYOnQoPv30U/j4+KBr164m++ratSu8vb2xfv16V52iAZUgdxRYNVBQUAB/f3/k5+fDz8+vvJtDRBWNVJ8WcE7lPn2pqeJXhlFR8ioDBgWJn4xK5qmyRPqEtTa+adMmsbugHBs3ioEpERHZ7c6dOzh79iyio6NRw87xtubmqYqMNO2MUJ1Zu85KYgNmqoiI5LJUBU8ad2Xp60A5srLkVQbs2xfYs0ccn7RihePHBUwzZuYoyaJxzikiogpBb2pGDmd1MQZVRERKmPuEunJFrIJnHGxpNMpKl0v7Nxe4RUaKx9i2DejaVQzALK2r0YhV/5R0V7RVX1fqoG8L55wiIqpQzPVsJ+djoQoiIqXMFVywVuhi5Uplo4Ut7cvcJ6G1dd3czE/aa42l+rpSFs3WpMGLFvETm4iIqh0GVUREzmKput2iReaDG2ujhZVUyrO0rpTJMu5Qb421rnsJCWK2bNQo04mOg4PF7ojsU0JERNUQu/8REbmatW56rp78VuquuGeP6eS7+own+7W2vytXxP1NmyY+9uwRlzGgIiKiaoqZKiKisqCkS5+zqdXiOKyVK81XL1RaX1fan5kStkRERNURgyoiorJS3pPfWuoOaG6yXyIiIpKNQRURUXVSnhkzIiKiKopBFRFRdVPeGTMiIqIqhoUqiIiIiIiIHMCgioiIiIiInGbYsGF4+umnDZZt27YNNWrUwPz5802eHzZsGFQqFVQqFTw8PBAdHY3Jkyfjzp07Bvs4ffo0hg8fDo1GAy8vL0RHR2PgwIH45ZdfyuCsrGNQRURERERURQlaAdfTruPKpiu4nnYdglbmZPBO9PHHH2Pw4MFYunQpJk2aZHadnj17IisrC3///TcWLFiA5cuXY/r06brnf/nlF7Ru3Rp//fUXli9fjmPHjuHzzz9HkyZNLO6zLHFMFRERERFRFZSTkoPT40+j6GKRbpmXxgsNFzVESEJImbTh3XffxfTp07F582Y888wzFtfz8vJCWFgYACAyMhLdunXDN998g3feeQeCIGDYsGFo1KgR0tPT4eZWmhd66KGHMH78eJefhy3MVBERERERVTE5KTk4mnjUIKACgKLMIhxNPIqclByXt+Ff//oX3nzzTezcudNqQGXszz//xP79++Hp6QkAOHToEI4ePYpJkyYZBFSSgIAAZzXZbsxUERERERFVIYJWwOnxpwFzPf0EACrgdPJp1O5TGyq1yiVt+Prrr7Fjxw7s3bsXXbp0sbn+zp074evri3v37qGoqAhubm748MMPAQCnTp0CADRp0sQlbXUGZqqIiIiIiKqQvPQ8kwyVAQEoulCEvPQ8l7XhwQcfRFRUFKZPn46bN2/aXD8+Ph6HDh3CTz/9hKFDh2L48OHo27ev2Fyh7MeBKcWgioiIiIioCinOKnbqevaIiIhAWloaMjMz0bNnT9y4ccPq+j4+PmjYsCFatWqF1atX46effsKqVasAAA888AAA4MSJEy5rr6MYVBERERERVSGe4Z5OXc9e9evXx7fffovLly/LCqwkbm5ueP311zFt2jTcvn0bDz30EJo1a4b58+ejpKTEZP28vDwnt1w5BlVERERERFVIQGwAvDRegKXhUirAK9ILAbEBLm9LZGQk0tLSkJ2djR49eqCgoEDWdv369YNarcZHH30ElUqFNWvW4K+//kJsbCz++9//4u+//8aRI0cwZ84c9OnTx8VnYRuDKiIiIiKiKkSlVqHhoob3fzB+Uvyn4cKGLitSYUyj0SAtLQ1Xr16VHVi5u7tj7NixePfdd3Hr1i20adMGv/zyCxo2bIiRI0eiadOm6N27N44ePYqFCxe6/iRsUAmVYeRXGSkoKIC/vz/y8/Ph5+dX3s0hIiIiomrqzp07OHv2LKKjo1GjRg279mF2nqpILzRcWHbzVFV01q6zktiAJdWJiIiIiKqgkIQQ1O5TG3npeSjOKoZnuCcCYgPKLENVnTCoIiIiIiKqolRqFQLjAsu7GVUex1QRERERERE5gEEVERERERGRAxhUEREREREROYBBFRERERERkQMYVBERERERETmAQRUREREREZEDGFQRERERERE5gEEVERERERGRAxhUERERERGRU12+fBkvv/wyGjRoAC8vL0RGRuKpp57C3r17devs378fTzzxBAIDA1GjRg20bNkS77//PrRardl9NmnSBF5eXrh8+bLJc3FxcVCpVFCpVPDy8kJERASeeuoppKSkuOwc9TGoIiIiIiKqqgQtcCsNKNgk/iuYD1icKSMjA61bt8a+ffvw3nvv4Y8//sCuXbsQHx+PMWPGAAA+//xzdO7cGRqNBqmpqThx4gTGjx+P2bNnY8CAARAEwWCf33//PW7fvo3ExER88sknZo87cuRIZGVl4cyZM9i+fTuaNWuGAQMGYNSoUS4/Z5Vg3OJqrKCgAP7+/sjPz4efn195N4eIiIiIqqk7d+7g7NmziI6ORo0aNezbyY0U4Mp44N7F0mXuGqDOIqBWgnMaasYTTzyBI0eO4OTJk/Dx8TF4Li8vDx4eHqhfvz46d+6M7du3Gzz/1VdfoXfv3ti8eTP69++vWz58+HCEhYWhc+fOGD9+PE6ePGmwXVxcHB566CEsXLjQYPmaNWswYsQIfPPNN+jWrZtJW61dZyWxATNVRERERERVzY0UIDPRMKACgHuZ4vIbrukWd+3aNezatQtjxowxCagAICAgAP/73/+Qm5uLV155xeT5p556Cg888AA2bdqkW3bjxg1s3boVQ4YMwWOPPYb8/Hykp6fLas/QoUMRGBjo8m6ADKqIiIiIiKoSQStmqGCuQ9r9ZVeSXdIV8PTp0xAEAU2aNLG4zl9//QUAaNq0qdnnmzRpolsHADZv3oxGjRqhefPmUKvVGDBgAFatWiWrPW5ubnjggQeQkZEh/yTswKCKiIiIiKgqKUw3zVAZEIB7F8T1nEzJyCK5665evRpDhgzR/TxkyBBs3boVN27ckH0clUolu132YFBFRERERFSVaLOcu54CjRo1gkqlwokTJyyu88ADDwAAjh8/bvb548eP69Y5duwYDhw4gMmTJ8Pd3R3u7u5o164dCgsLsXnzZpvt0Wq1OHXqFKKjo+04G/kYVBERERERVSXqcOeup0BQUBB69OiBjz76CLdu3TJ5Pi8vD927d0dQUBDmz59v8vyXX36JU6dOYeDAgQCAVatWoVOnTjh8+DAOHTqke0ycOFFWF8BPPvkE169fR9++fR0/OSsYVBERERERVSU1Y8Uqf7DU5U0FuEeK67nARx99BK1WizZt2mD79u04deoUjh8/jsWLF6N9+/bw8fHB8uXLsWPHDowaNQpHjhxBRkYGVq1ahWHDhiExMRFJSUm4e/cu1q1bh4EDB6JFixYGjxdeeAE//fQTjh49qjtuYWEhLl++jIsXL+LAgQP417/+hf/7v//DSy+9hPj4eJecq4RBFRERERFRVaJSi2XTxR+MnxT/qbNQXM8FGjRogN9++w3x8fGYNGkSWrRogcceewx79+7F0qVLAQCJiYlITU3F+fPnERsbi8aNG2PBggWYOnUqNm/eDJVKhS+//BK5ubl45plnTI7RtGlTNG3a1CBbtXLlSoSHhyMmJgYJCQk4duwYPvvsMyxZssQl56mP81Tp4TxVRERERFQRuG6eqkgxoHLhPFWVibPmqXJ3ZSOJiIiIiKic1EoAfPuIVf60WeIYqpqxLstQVWcMqoiIiIiIqiqVGvCJK+9WVHkcU0VEREREROQABlVEREREREQOYFBFRERERETkAAZVREREREQVFAt1u5azri+DKiIiIiKiCsbDwwOAOKEtuU5xcTEAQK12rCIiq/8REREREVUwarUaAQEByM7OBgDUrFkTKpXxRL7kiJKSEuTk5KBmzZpwd3csLKo0QdXcuXORkpKCEydOwNvbGx06dMA777yDxo0b69a5c+cOJk2ahM2bN6OoqAg9evTAkiVLUKdOnXJsORERERGRcmFhYQCgC6zI+dzc3FCvXj2HA1aVUEk6avbs2RMDBgzAI488gnv37uH111/Hn3/+iWPHjsHHxwcA8NJLL+E///kP1q5dC39/f4wdOxZubm744YcfZB1DyazJRERERERlQavV4u7du+XdjCrJ09MTbm7mR0QpiQ0qTVBlLCcnB6Ghofj222/RqVMn5OfnIyQkBBs3bkRiYiIA4MSJE2jatCl+/PFHtGvXzuY+GVQRERERERGgLDaotIUq8vPzAQBBQUEAgF9//RV3795Ft27ddOs0adIE9erVw48//lgubSQiIiIioqqv0oyp0ldSUoLk5GR07NgRLVq0AABcvnwZnp6eCAgIMFi3Tp06uHz5stn9FBUVoaioSPdzQUGBy9pMRERERERVU6XMVI0ZMwZ//vknNm/e7NB+5s6dC39/f90jMjLSSS0kIiIiIqLqotIFVWPHjsXOnTuRmpoKjUajWx4WFobi4mLk5eUZrH/lyhVd5RRjr732GvLz83WPCxcuuLLpRERERERUBVWaoEoQBIwdOxaff/459u3bh+joaIPnW7duDQ8PD+zdu1e37OTJkzh//jzat29vdp9eXl7w8/MzeBARERERESlRacZUjRkzBhs3bsSOHTtQq1Yt3Tgpf39/eHt7w9/fH88//zwmTpyIoKAg+Pn54eWXX0b79u1lVf4jIiIiIiKyR6UpqW5pQq41a9Zg2LBhAEon/920aZPB5L+Wuv8ZY0l1IiIiIiICqsk8Va7AoIqIiIiIiIBqMk8VERERERFRRcCgioiIiIiIyAEMqoiIiIiIiBzAoIqIiIiIiMgBDKqIiIiIiIgcwKCKiIiIiIjIAQyqiIiIiIiIHMCgioiIiIiIyAEMqoiIiIiIiBzAoIqIiIiIiMgBDKqIiIiIiIgcwKCKiIiIiIjIAQyqiIiIiIiIHMCgioiIiIiIyAEMqoiIiIiIiBzAoIqIiIiIiMgBDKqIiIiIiIgcwKCKiIiIiIjIAQyqiIiIiIiIHMCgioiIiIiIyAEMqoiIiIiIiBzAoIqIiIiIiMgBDKqIiIiIiIgc4F7eDSAiIiIiqggErYC89DwUZxXDM9wTAbEBUKlV5d0sqgQYVBERERFRtZeTkoPT40+j6GKRbpmXxgsNFzVESEJIObbMNRhAOheDKiIiIiKqVowDirs5d3Gs/zFAMFyvKLMIRxOPovm25lUqsKpuAWRZYFBFRERERNWGuYACapgEVMD9ZSrgdPJp1O5TW1Emx1mZIGdnlHJScnA08Wi1CSDLCoMqIiIiIqoWLAUU0FrZSACKLhQhLz0PgXGBsoIcZ2WCnJ1RErQCTo8/7fQAkhhUEREREVEVYinosRpQyFCcVSwryHFWJsgVGaW89DzDDJ0xowCS5GNQRURERERVgrWgxz3I3XpAYUPhqUKcm3HOapBTu09tWZmg4F7ByN+fbzHb5aqMUnFWsVPXo1IMqoiIiIio0rOV2YkYH2HfjlWAZ4QnslZm2Qxy1P5qWZmgHyN+xN2rd3WLjbNd9mSU5HRL9Az3lHXK+T/kI39/PrxjvBExOgJunvKntq2uVQUZVBERERFRpSYns5O9IVv5ju/HAnVH1kXG9AwrDbgf5KTlydqtfkAFmHbpU5pRkjv2KiA2AF4aLxRlFlntBnnpo0u6/z/zyhlEToxEzLsxNttTnasKyg87iYiIiIgqIDmZnbs5d+FR20MXKMnhHuSO5tuaw7uRt6z1C08Uyt+5UfsAMdslaAXZGSXPcE9dhs74/KVALSclR7dMpVah4aKGytqmBS68dwFnJp+xupqSdlRFDKqIiIiIqFKTm9mp0bCGokIV93LvAZDfbU5upsosvS59UkbJYgCoArwiveDfwd96hg6lgZo+9yDlndUuvH8BJcUl5ptuK1MoAKfHm7ajKmFQRURERESVmtyg58aBG4r3fWr8Kfh38LcZ5HiEeODe1XuK92+sOKvYMKNkfMz7Pzdc2BD5+/Nlj70CSrNJUrCoiBY4PdF8YGQzUwig6GIRzs05p/y4lYSioGrJkiXo1q0bkpKSsHfvXoPnrl69igYNGji1cURERERUPQlaAdfTruPKpiu4nnbdapYjIDYAnhHyAiulii8WI39/vs0gx6+tn1OOJwWIIQkhaL6tObwivAye99J42TX2ytGS8oA41upA1AGDrnyCVsD1vddlbZ8xPaPKdgOUHVQtXrwYr776Kpo0aQIvLy888cQTmDt3ru55rVaLc+eqbvRJRERERGUjJyUHB6IO4HD8YRwfdByH4w+b3Mzru7rjKkrumO+a5gy5O3KtBjnNtjRDwYECxw5yv0tfQGyAblFIQgjaZbRDq9RWaLqxKVqltkK7s+10RR+UjL2Sk02SQ3+MlPR7Oj/7vOztzXVHrApkd6hcvnw5Vq5ciUGDBgEAXnrpJTz99NO4ffs2Zs2a5bIGEhEREVH1oXTS2+xt2TjW75hL25S1KgvBvYJRu09t1O5T26RkeF56nklFP0X0uvQZlx9XqVUWJ+KVU83PI8QD/h38kbPdSRmi+9UUT446iXvX7inOfFXVyYVlB1Vnz55Fhw4ddD936NAB+/btQ7du3XD37l0kJye7on1EREREVE0onfQ2e2s2jg10bUAFANobWhzudthieXBHJ8v10nih4ULlZcelsVdHE4+KgZmZ63Y35y5+ivkJYSPDHGqjAQH2jcu6T+qOWJXms5IdVNWuXRsXLlxAVFSUblmLFi2wb98+dOnSBZcuXbK8MRERERGRDUomvb137R6OJbk+oNJnnC2TAoNbx24p3le9afXg08zH4YBC6pZoPD+UcbvPzTgH92B3u7JLznb71G0ciDpQpeazkh1UPfroo0hJSUFsbKzB8mbNmmHv3r2Ij493euOIiIiIqPqQXXghsxh/T/nbxa0x434w8tf//YW8b/OQvTHb7m5/gV0DZXeBs5XVCUkIQXCvYPyo+RF3c8y05367hbtC+QZUKrGcu7mJlC1176wsZAdVU6ZMwa+//mr2uebNm2Pfvn3Yvn270xpGRERERNWL3MILxTnFTim6YK+7OXeRuTjTvo1VYlZGvyCFJYJWQMacDGQuyhQzTPeZy+rk7883H1Dp0RZo4ebnBpQAJTddV9jDLFuJODPdOysT2UHVgw8+iAcffNDi8y1atECLFi2c0igiIiIiqn5sFl64H5B4hHg4fjA3AGUcV1grSGEsJyVHLAZhZuySuayO3CxfSUFZn7TIM8IT4SPDcW66lWrhQuUtZMHJf4mIiIioQpA76a1nmBPmpCqL2MLoTlt/jilrclJycLSvlUl67wec+uXJ5Wb5AIjXUi1/dWe5d11ecQspQFQyV1l5k52pIqpqtFogPR3IygLCw4HYWEBdDn9giIiIqJSlwgtShTwAODHsRHk1T5kSIGZBDDzreMouSKGrgGiLUVZHTnl1/W2hvf//FqoGOlvxxWJkLpTXZdIz3BM5KTnmXwMVtJgFgyqqllJSgHHjgEy993ZEBLB4MZCQUH7tIiIiIjGw0s0HlVmM4pxieIR44OafN3Fuxrlyr16nhGcdT9QZWEf2+kon6ZWyOgbl1WXSJGtwed1lh8qjK6KCmL3TWn7eS+OFu1fvipUdZc5VVhEwqKJqJyUF6NvXdHlmprh8+3YGVkREROVNpVbh3rV7+HvK38qKUqhh+aa9HBSeKlS0vtI5r/S7/UlZvr/+7y+bRSsAQB2oNiiA4XLWMmT3fw4bEYa/XvxL9lxlFYXsMVXZ2dlWn7937x5+/vlnhxtE5EpaLTBqlPV1Ro0S1yMiIqLyk5OSg6OJR5VX+atgn+HnZpxDTkqO7mdb44SUjI3yijStIhiSEIL2F9vDo7aVYh4qwFPjiayVWeWS9dMka+AV4WWwzD3IHe7B7jg385z1QE+v22NFIjuoCg8PNwisWrZsiQsXLuh+zs3NRfv27Z3bOiInS0sDcnOtr5ObK65XXrRa8fibNon/MsAjIqLqRjeuqBJ187NGKiiRk5KDA1EHcDj+MI4POo7D8YdxIOqAQdAljY2yWYJcZVhFUD9Yy0vPQ92xdS1uBwB1R9ZF8UVlWTFnCe4TjHYZ7dAqtRWabmyK+jPr4961e4q6ISrN6Lma7O5/gmD4qs7IyMDdu3etrkNU0cgNltLSgK5dXdkS81JSgPHjgYsXS5dpNMCiReySSERE1YfScUUV2v3MSsacDLPjwYzHCRmMjbJQRMI92B2NVzTWjSsyV9TBEqngh/Z2OXxre3/MlH8Hf91kxh6hHsiarDxjpqjaYRlw6pgqlari9Gukyqk6V+RLSQESEwHj7yYuXuRYLyIiql5yd9joVmKOSpwLCQCKM4srXJYrc1GmrHFCgNgVTjNeg8vrL+Pe1dLsjTpIjcjxkag3pR7y9+fjyqYruH3qNjKmZ8hqQ/2Z9RE1NQpXd1zFmQlnHD8pJe6HCaEDQvFTzE/2B80KJk8uSyxUQRVGWWRp4uKA2bPlrVeWtFrx3K0le0eNAvr0qT5BJhERVU+CVsCV9VeUbXT/hr3RokYAYDXLY43vI74ozip2Sbc4OeOEMuZk4PLKy1YDjlvHbuFAgwNi4KiECrj88WX4NPMxW1nP1bwivBA6MBQX5l2w/9gKJk8ua7LHVKlUKty4cQMFBQXIz8+HSqXCzZs3UVBQoHsQ2UvK0ugHVIBYkS8xUXzeGa5dA9xsvOqDg8s+qEpPNz13Y7m5wJw5ZdMeIiKi8pKXnoe7V21XrtPnHuSu6z4nVcCTslZK3Dx4E6H9QxE1M0rxttaoa8n7RvTc9HNWAyrtNS1yPstRHlABusDt5AsnyyWLFzo0FNmbsh06ttzJk8uDSpA5EMrNzc2ge58gCGZ/1lbiUfUFBQXw9/dHfn4+/Pz8yrs51YZWC0RFWQ4qVCoxY3X2rGNZGkvd64yVRze7TZuAQYNsrxccDFy5wmwVERFVXVc2XcHxQccVbeOl8UK7jHYG2Ytre6/hSLcjyhugBjoVdkLuzlz89eJfigM8ssCBSYbdg93R7LNmCIgNQP7+fBRnFcueTNkRSmID2d3/UlNTHW4YkTm2sjSCAFy4IK5nbwZJTvc6tRrYvLl8xi2Fh8tbLzfXsetARERU0dlTgKDoolhiOzAuULfsbradwZAWuPjBRdSbVA8lt0twfIiCAM8NQIl9h63y7Amo7sdLjVc0hjZfazIWy0vjhYaLGlaIzJXsoKpz586ubAdVYo4Wl8jKcu565sjpXqfVArVr238MR8TGAkFBYvdEWxy5DkRERBWdVFK8KLNI0Y14UWYRrqdd12UxPEKtzNNkQ8b0DHhHeyvvQsiAyqmkSoXA/XFyNionlicWqiCHOKO4hNwsjdz1zHEkcCuLioRqtXgdp0+3va4j14GIiKiik1NS3JwzE87gbk5pdspT4wn3YHexQITCLEnJrRIcTTyKZp81syvAI/vFzIuBZ11PXfc+ADgQdUBW5cTyLF4hu1CFm5sb1Gq11Ye7O2O06sRZxSViY8VAzFJFfpUKiIwU17OXvYFbSoo43is+XhzzFB8v/uyswhn6pk4Vx0xZYu914GTCRERU2UjFJrwivGRvox9QAWJZ9Xu593Q33vY4M+kMYhbEiD9UrGJzVZZnXU/UGVgHgXGBUKlVuJ523Xr59fsFOPLS88qsjebILlSxY8cOi8/9+OOPWLx4MUpKSnDnzh2nNa6ssVCFfM4uLiEFaIDhuCcp0Nq2zbGxTlJ7MzPNj6sy115LhS2UtklJpstZx9TfHycTJiKiykrQCshLz8PVHVeRuTBTebEDlVgZ0K2Gm30V8wC0Sm2Fe9fuyZ5ct6KoM7QOrnyisDR9BdAqtZVubFxOSg5OjjxpvRz9fU03NkWdgXWc2hYlsYHsoMqckydPYsqUKfjqq68wePBgzJo1C/Xr17d3d+WOQZV8aWli1saW1FT5RRXMBQCRkcDChYYBgL3d8ZQEbs4KGu0JauReB1ucHaARERGVp5yUHJPAxiPEwyRDZU6rPa0ANcTxVqGeuLjsInK3yZtgWLpZF7QCzr5xFuffOm/3OZQZ/YmQXTDnlqt4RXqh3VmximNOSo7ZcVSW6AdjzuKS6n/6Ll26hOnTp+OTTz5Bjx49cOjQIbRo0cKuxlLl5IriEn36AP7+YsAGiMFYXJxh0OJI5iUhQQwkjLevXRtYssRwe2dUJLQU1EjdIy0FNQkJ4rVwZByXtWqHgiAGVsnJlicTLotxZEREREqEJISgdp/ayEvP0xWjKM4sllWdrzi7WJfFyEnJwc0DN2UfV6pGeHXHVVxafsm+xtup/vT6ECDg0geXDLM1tqoMCmIwVX96fZybec7VzXQaaVJfQSvg9PjT8gIqlVjQQhp/VV4UBVX5+fl466238MEHH+Chhx7C3r17EevIQBeqtOSOUQoNFYMkWzfn5oKltWsNgyV7gxR9CQliwDB6NHD1qrgsJweYMEGcFFja3tGgsbgYePFF+4MatVp+hk8aM6UfjAL2B4XsMkhERBWVSq0yyEZcT7suazspMFKU/dC7WVeaNVFMDUBvzLNHiAcaLWmE0MRQAED0v6MNu0HKrDJ4++/b8g7vp4a2oHwHXdefWV9XwS8vPU9RV0spGCtPsgtVvPvuu2jQoAF27tyJTZs2Yf/+/QyoqjGpuIQt/fvbLvIgp+CFrcwLIAYptoowpKSIbZICKnPHAhyrSJiSIl4b42MYt1kKahyRkgLUqQN06wbMni0+unUDnn5a3vbGQaGzio8QERGVBan8usUiEiqxS1lAbIDi7AcAXTlv2dspVHdsXbRKbYWmG5rCo3ZpCfi7OXdxZsIZ5KTkiM1RqxAQG4Cr26zcXJiRvS5b3orlXAreU+OJqKlRup+Ls+R3WXTzccOtP2/hyqYruJ52HYK2fMo0yh5T5ebmBm9vb3Tr1g1qK/2AUirxXRfHVCmzdSuQlKRsG5VKDCikLE2HDkBMjPWsSkgIMHIk8NZbtvdvbQyXknFSgPLCFoDlbJolGzcCAwdaft5aN7yUFKBvX3nHsUT/ejm7+AgREVFZ0GWRAMPA535gJM1hdD3tOg7HH5a1T69IcX4kpdspJRXBMJsFc6D9lU3z7YbzTDlyrs6cEFhJbCA7U/Xcc88hKSkJQUFB8Pf3t/ig6iPEjteqFGwsXChmriIibE/Km5MjL6ACrHfbkztOKi1NXNdScCQVeli40DC4sJZNs8RaRsxaOXfpWPYyV55dyTgyIiKiisJS+XUvjZfBpLBysx/1ptVDu7PtFG8HQNdl0KOu7YmHvTRe8O/gbzkLdn/Z6eTTELSCsnYoUc6l4qNmRpkEQDYzkFZIEwJLWb6yIntM1dq1a13YDKqMMjMd34e1LnL2uHJFDDjMZVLkjpNKSgKuXSv9Wa027Fao0ZivxGcrKDEWFCTuV9q3fkYqJ0fspmhp/NiMGcqOpc9SUOiK4iNERERlwVwRi4DYAINxNtK4KlsCuwbatZ2k4SKxy+DRvkdtrpe/P1/2HExK2yFbOU9q7N3I22SZwQTQSpXThMAOz9Z77tw53Lp1C02aNIGbm+zEFzlZWVVr0z/Ojz86f/+OmjABmD/ffFGF0FB5+9APqACg5H4/Y6nLopTdMS7AoTTYuHZNHP8kTfibq1fZVa22XuRi0SL5xwkKMjwn/aBQ//f5zTfy9id3vJlS9ryGWaWQiIgkxkUsjEnZj6LMIvOBhIUqcja3u8+421nz7c1xctRJcQJiPe7B7mi8ojFCEkJwZZO8eaSKs4oRmhQqqx2Vze1T5otpSBlIufNUGdALRp1dZt0S2UHV6tWrkZeXh4kTJ+qWjRo1CqtWrQIANG7cGLt370ZkZKTzW0lWlVW1NnPHqYjMVQOU2m4PKZDZvh2YNw/YsQMYN84wUxcRAYwaZd/+9YMpibWCG4JgGvhZs2WLGGgYBx72/D41GsMug87irPm8WKWQiIgsMch+GE8irFeYwjizYXW7+6JmRqH+1PoG20rZs+tp15GXlgcACIwLREBcaQZNbvbJM9zTsexNBZYxPQM+LXzMjoEKSQiBu787Dnezb3yVy7pMmiE7tbRixQoEBpZGert27cKaNWvw6aef4uDBgwgICMDMmTNd0kiyrKyqtVk6TkVkXA3QGW2XxhO9+aZYHMK462NmJjB9uph1UpVR32Q5xwkMNB8E2XtNRo50fibIntcwqxQSEZE95I6/kr1dpBeab2+OqDeizHYzU6lVCOoahAZvNkCDNxuYdC307+APjxAr46/0qhdK7Yh8pYolMFSl48bMCYgLgKfGvq6PLusyaYbs6n/BwcFIS0tDy5YtAQAvvfQScnJysG3bNgBAWloahg8fjrNS6bRKqLJV/yuram22juMsISHiWCJn2rMHGDbMdtsDA4Hr8qa6sMrXF7h5s7TKYUUgtUmi0QC3b5vPkNliq1qhPjld8+x5DbNKIREROUrQClbHXzl7O3NyUnJwevxpy2OqjKr/Scf/oc4PJl0Kq4JWqa0sdtXLScmxOUbNwP2unO3OtnNoTJVLqv/dvn3bYGf79+9Hp06ddD83aNAAly9ftqO5ZK+yqtamtACDUlIluosXxRLf69fbV1nQnGXL5LV96lTnHO/mTTFjFRFhuDwoyDn7t4d+QAWI18OegAqQP57KWuVCffa8hlmlkIiIHCWNv6ozsA4C4wJl33jbu50xqQy8tSIV5rJn19OuV6iAqs7QOuL/GF8GlfiIfDUS7kHyRhtZ66oXkhCC5tubwz1Yxr6sdOV0JdljqurXr49ff/0V9evXx9WrV3H06FF07NhR9/zly5dZUr2MlVW1trKo9rZwIeDpWTpn0uHDwHvvOb7f+4lUm8LCxOyGM4JHrRbIyDDM0mi1YlGKykrK/khdCW3Nn2WuHL25sW72vIYrcpVCFs4gIiJb5ExC7BHigban28LN0zD/IY3NsiV0SCiCnwjGzT9v4sJbFxxorXXXvrmGyFcjkb0p2yBA9NKUzvMV2CMQR7odsbkvW131dBUe0/JwPe1+9yI1cHnVZRRfLA3I9I9dlmQHVUOHDsWYMWNw9OhR7Nu3D02aNEHr1q11z+/fvx8tWrRwSSPJPLlZA0ertcndftgwICBADJDkCgkRs0n6hQW0WmDTJgUNtMDNrbRyny1hYcCCBUC/fo4fFxBvpPUnIdZqxaDE0mTCFZlxCXZrBSL69LE8V5dU8EOqoqhW2/callvFUe56zmLuuoSEAB9+KLaFgRYRUdUnp3tgXnqe9TLqAO7m3EX+/ny7K9fViKqBOgPrwDPN06VB1d1Ld3Fh3gU0+6wZPEI8zJ53YFygXVUXzVGpVQjsGojArqXXJfrf0U7rkukI2UHV5MmTUVhYiJSUFISFhWHr1q0Gz//www8YKHewBTmFnDmejCd4tUdsrLwsztq1peXB5VqwwPH5niyRG1ABwNCh9lfvM6YfTEnUauD998U5sCob/RLstrJQtubP0u+aFxdX+tqyFGwaZ8gqKkvXRZpvTB8rFBIRVU3mxkgZl1kH5FekM7deYFwgzs8+b3NbKRgLiA2Ae7C7si6DFiocWnNm0hmL45fsrboou7k2SumXFdljqtzc3DBr1iz8/vvv+Prrr9G0aVOD57du3Yrnn3/e6Q0k84qLgdGjba83f77j34qr1fKLEygdq3PihDjfk34J8fLotiVV73OUn5/lant6sxFUCq+/Lo5xO3u2dE4ra1koQP78WdLvWK0u3cZcNUNBAF54wXBZdra8Y8hdTymtVnzNbtok/ltcbPm6mMMKhUREVYegFXA97TpOTTiFo31Nx0gVZRbhaOJR5KSUVuJSUkbdWEBcgM1xRe7B7giICwAAXN1x1WZAZbw/L40X6s+sL6uNAAzmhLLE3qqLlYlDs/WOHj0aV+WkS8ipUlLEQghyKuXZKvhgfINobn4kZ3XHM2f2bNMiBq6aXLYsFBQAMTGGN8yVqRy9vmXLxPmwpKBcToEIufNn6f+OExLEcVbGxT0k06eL60+YIL5G5Xbrc8XryFwBDqVj8YxL/hMRUeUhBVFXNl3B2Vln8WPUjzgcfxiZCzMtbCD+o18yXJpM2KS4g8SojLrBU2oVGq9obLWNjVc0hkqtKh27ZYV7sDs6XOqAVqmt0HRjU7RKbYV2Z9shamqU9TaaYSsDF5IQgnYZ7UyOVRUCKkBBSXVz/Pz8cOjQITRo0MCZbSo3laGkuqVuRpZYK4Etd/LUtDTx5tGVpCzFtm3ieJuoqIo9/sjPTwygzDF3LpUtoNI3c6ZYHXHLFjGQsCUoSCxPb+l3FxwMXLlivrz6nDm2M4ZSSfhr16x3GXR2SXWl7z05UlPNdxclIqKKx2YJdBv0S4ZL1f8AmO0OZyt7k5OSg1PjT5kWaNDrang97ToOx9ueNNdSKXNdG2V+7lkriV5ZuaSkujkOxGNkB2vdryyx9G29kslTy6I7nv6394D1LmHWOKsUuy3PPQfUrm3+Of1zSUur3AEVIAY59esDp07JW9/WazQ3F9ixw/xzK1fa3r9UEl4qfKHPuKiGs9jz3pOjPLq6EhGRcnJKoNuin8lxtDtcSEII2me0N8z6ZLQzmM/q+l55E3BayjBJbbQ58a6VzFp14lBQRWVLSQEHae4nc+N75IyN0e+aVFbd8aQiBh98IGZ4rHUJ0xcSIrY3NVUsfFEW1q2zXihEOpd9+8qmPa4mjTmrUcP6esHBwJQp1guWSBUAjbu+zZmjLAANCgLq1jVcVru22FU1KMh6l1alXDVXW2Xu6kpEVF3IKYEuh/EYKUe7w1maMysnJQcHog7IKmhhrl3GbWyf0R5RM6MsNEL8p6znhKqIHAqqbty4UWW6/lUGlr7dt8TSt/VyJ0+dMUO8Ke3QQexOpTRrpE+tFgM5OSZMELvMAbaDpJkzxW/7FywQu1HJCcKcIT9f3noffODadjjCy8v2Osbu3LG9Tnq69YIl5ibnTUlRXijk2jWgY0fD7GRODjB4sO1Jh5VydkbJ2pceRERUscgpgW6VjTFSliYT1h+/dT3tum5MljWKMmoyM0wqtQpRb0Sh+fbm4jgrPVWp0ISjZJdUl6jVamRlZSHUaLR4bm4uQkNDoeXIa5fQaoH16+Wta27uJ31ybxBnzxYfGo04LmvePPFm0J4uUFptaaAkR2Ym0Lev7YzHxx+L430ktkp0l7UbN8q7BZYVOfD5YElurhiIy7F3b2lQITfgNrZli+ky4z9B5iYdVsrZGSVBcH4XRSIicg25JdDNsjOTY278lkdtD9QZUgfBfYLNzsWkKKNmR7t0k+9WgDmhKiLFmSpL46iKiorg6SmvRCQpl54ub14qlQo4d876zaPSG8TMTDGgeuUV00yQry/QubO8/YSEyM94SS8zpRkP/RLdVLHNni0G2kq7/SllqdqenMqX0npardilkIiIqh+5JdDNkZPJMc5IZW/NNpttunv1Li4uvIjD8YdxIOqAQZl2QFlGzd4Mk7XMWnUnO1O1ePFiAIBKpcLHH38MX19f3XNarRbfffcdmjRp4vwWVnNarRg0bN8ub31BAH76yXpFsdhYMQMkd04pqSDA5s3AmTPA22+Lgcu1a8DNm8C338rbz4kTYnetzz6Tt75cUuZNulZFRWLXRamNVLbUavEhJ2ntrPnBbDGedFhu5Utz68llLasrjSvr04fZKiKiik4qgV6UWSR7XJUmWWMxo6TPbEVBNWwep+hiEY72PYpmW5ohtJ/Ye0xuRq3etHqInhHNgMjJZAdVC+4PbhEEAcuWLYNa707A09MTUVFRWLZsmfNbWI3Ze0Pniopi0k3p22+LAYs9Xetmz3Z6swCImTdz18pa10FyDTc3YNYs+a+Psu6imZVluTS6cTdBR0uoW9vOOMgjIqKKS6VWoeGihmJ5cRWsBjxekV5ouLChrAyQxZLlCkbSHBt4DFABoYmhsjNqgV2ZYXIF2UHV2bNnAQDx8fFISUlBYGDVqkNf0ThyQ3flitilKTxczEoZfxNuq5CANYsWVYyxSkDpfEQ5OUD//qbtsvccrfH0BIod6Fpd1ZWUlHcLrAsNBYYNs1z5Usog9erlmhLqxlhSnYiocpDKixtnlTw1nqg7si68G3krGmPkrIqC0ALH+h2DarsKtfvUtp5RU4nd/qp76XNXUVyoIjU11RXtID3FxcCLL9p3Q6dWi9XzJOa6NDlyI1dRutNJ47Lef188X1vXyt4CG8YYULmWs35P5var0Yj/L6fy5ZIlZTO/GEuqExFVHs4s1OBwRUEjJ4adwKPXH7WcUWPpc5fjPFUVTEqKePMnpyiFOZYqn+mXlLbnRk6lkj9Q/+mngSFDlB9DiaAgsZtW7drybn4tTdRLFcfMmaaFUCIjgVdfdaycv/6EwNnZ8rY5c8b+48nBkupERJWTswo1OFRR0AztDS0yZmc4PKkw2U9xpopcx5Euf5YKA+h3aZIGxUtlx5VMJCwIwL178tb/4gu5rbafSgXcvi2W5ZZjwQLxhn3vXteN7apsfH2BW7cqRnfOyEixNP7UqWL31Kwsw+6rvr72F7TQaMSAKiFBfrn3mBj7jiWHfpDHIhVERNWTIxUFLbk4/yKipkWx9Hk5qZKZqo8++ghRUVGoUaMG2rZti59//rm8m2STVqt8DMeCBcDGjeK/1iqtGZceV6vFbnNySRmqggL527ja1atiNkxugBQWJhYEaNbMpc1yCUeyNPr70GjEwET6fd68WTECKgAYMKC0amBcnDgvWlxcadDRqJF9+12wADh7trT7q/SFgqVrKmWQRo92fMJriXHgpNE4NmcWERFVflJFQVj7nFH4xZv2hhZ56XkAWPq8PFS5oOqzzz7DxIkTMX36dPz2229o1aoVevTogWy5/X7KSXq6ssxRZCTw8svizWedOvK20x9LFSIz+ztvnrz1Krphw8RMYGUZwzJkCDBtGjB0qOOBjxQYDBwoVuarKOPi9G3ebP2LAXt+b9J7RD+o0Z/HzDhg0s8geXo6Pt+ZSlU6FUFqqvgFSGqqYZBHRETVk1RRUPzB+Enx0WxzM7RKbYXgBPnljJ3drZDksyuoSk9Px5AhQ9C+fXtkZmYCANatW4fvv//eqY2zx/vvv4+RI0di+PDhaNasGZYtW4aaNWti9erV5d00q5QWj1i4UPw3LQ04dkzeNvo3pnKPd+CAa6rolTVpbFlOjvMyENbYO4ZLCpjXrhVL13/1leNt0WjEucE2bao4mSljxpM4G+vQQfk1HTEC2LLFdGLfhAQxU2Q8fss4g2RpPbkiIsTtExPNZ9+IiKh6szX+KTQxFIFxgWixpQXcasm7ZXdFt0KSR3FQtX37dvTo0QPe3t74/fffUVQkVi7Jz8/HW2+95fQGKlFcXIxff/0V3bp10y1zc3NDt27d8OOPP5Zjy2yT+018SIh4owYAUVFAfLztLnDmBsXLPd7u3fLWU8KtHPKjUjAxaZLYJQxwXWClVgPnz4uZJiWMx9qkp9ufVZo3Tzz+tGnAmjVil7+yqGbnCEuBfkqKOMZJafGWmTOBQYPE90hUlGGxloQEICPDdgYpIQE4d07cl1Jr1zIjRURE1oUkhKBdRju0Sm2FphubolVqK7Q7286goIRKrUKTVU1s7ssrkuXSy5Pi29vZs2dj2bJlWLlyJTw8PHTLO3bsiN9++82pjVPq6tWr0Gq1qGPUH65OnTq4fPmyyfpFRUUoKCgweJQXW2M9ADGgkm6MExPl3SRbGhQvZ2xJSAhw44as5itSXnMZSWPLate2LwMRGSnOh2WLVgv89BPQtauy/RtnSuwpfa9SiZMeL1woBtuzZwPdugFJScr3VdbMBfpS8RZHA0JzVTAtjd8yplYDb7wBbN9eWpZdjgre45iIiCoIOeOfQvuFIvLVSCs7Ybn08qY4qDp58iQ6depkstzf3x95eXnOaFOZmTt3Lvz9/XWPyEgrL1YXszXWQ6UCli0T11NS0MLcoHitVsyCSJUGLY0tGTzYvnOp6LKyxOuxdq289aXxTWvWAE89Jf8YsbHyy9BPm2aaKVE6jkiq0pibaxqEuHIclTMyfubKi9tTvMUSaR/JydbHblkjZbekTKctlWX8HhERVQ4x78ag2dZm8AjxMFjuFcly6RWB4qAqLCwMp0+fNln+/fffo0GDBk5plL1q164NtVqNK1euGCy/cuUKwsLCTNZ/7bXXkJ+fr3tcuHChrJpqlpyxHnILWkybZr5LU0pKabdBaVyW8U2xdLw+fRw5m7JXq5a89UJDxX/lZhLWry/N+CQny9smPLw0AJbDw8M0UyIne6kvIkLMUpW12rVtv1Y6drT+vFT9T5+S4i1yGFfBtIdaLRa/kFNBkHNQERGRs4UmhqJDVger3QWpfCgOqkaOHInx48fjp59+gkqlwqVLl7Bhwwa88soreOmll1zRRtk8PT3RunVr7NWbvKikpAR79+5F+/btTdb38vKCn5+fwcMVtFpxsPymTaaD5o3ZGuuxY4e8YzZrZtqlyVJXKv3ueLVrA/Pni8dTelNfViy1R25XxaFD7a8EaGtcj/EN9dSp8gKdGTMMu6YBpdlLa5mamTNLXydr19pXVMTR3+/8+cCvv1pf5/x54JVXLD8/b57p+dvT/VEOR/crt4IgC1IQEZErsFx6BSUoVFJSIsyePVvw8fERVCqVoFKphBo1agjTpk1TuiuX2Lx5s+Dl5SWsXbtWOHbsmDBq1CghICBAuHz5ss1t8/PzBQBCfn6+09qzfbsgaDSCIN4aiw+NRlyu1L17glC7tuG+LD1SU023NW6HpYdKVdq+7dvFn1UqedsCghAYKAiJifLXl/vQaARhyxb552Ht/FSq0n0pOTfj/Zhbbvy73b5d3r4iI8Xfk5Jt9Y+1caN95xEZKQgzZ9p/PRcskLdeSIiy809Ndf5rCDB9b9jL3Hs7MtK+9zYRERFVPEpiA9h7kKKiIuHo0aPCTz/9JNy4ccPe3bjEBx98INSrV0/w9PQU2rRpIxw4cEDWds4OqqSAxNJNvdKbL7k3mSEhpjfnSm5QjW9wzd08WnsEB9t3k+7raz2ACw4WhK1bBWHPHkF4/XVBqFXL/htr6Ry3blUeNEoPPz/zbTT3e5V7PfRv+G0Fwsa/J3uCkAULxO23bhUEtVr5NdRoxN+Fvb8HOedvb9Br63o5w717Yps3bhT/dea+iYiIqHwpiQ0Ud/8bMWIEbty4AU9PTzRr1gxt2rSBr68vbt26hREjRjg7kWaXsWPH4ty5cygqKsJPP/2Etm3blnkbrA2yl5YpHTQvt9vS4MGmXY+UdHkSBHHsyQcfiF0Wg4KAM2fELmbr19ueLyg3F5g+Xfn4nps3xS5iloo75OYC/fqJY5veesuxyoTSOR4+LHa9s2cuInPFInNzTavMAUCjRvL2qf97sjWmSDoHaYyQPd01Q0KAOXPE66q0gIMgALdvi78LZ9E/f2vd7JRyVbc8uRUEiYiIqGpTHFR98sknuH37tsny27dv49NPP3VKo6oCpTfEcsgdA2SuaIA944cmTCid5ycmRqwgFxGhfL4gJdasAby8bK/nLLNniwGgIJSOT5Jb3c0SQQBGjTIMUuRef3smaJbW0w9C5EpOFs/fXnLGcEnl+eUwvk6WircoHf5orgomERERkbPIDqoKCgqQn58PQRBw48YNg7mdrl+/jv/+978IlcqqkeIbYjnkZCKCg81XHXO06IQ0z4/cQhmAfUUTrl4FLl1Svp2jLl0SM1ZeXraru8mRmytmgCTS9bfEkQma9dezFIRY4soAGSi9hh99ZH/FPHPFW5YskXf8sWMtT+xLRERE5Cyyg6qAgAAEBQVBpVLhgQceQGBgoO5Ru3ZtjBgxAmPGjHFlWysVe26IbZFTDS4313zg42hXKumYGzYo37Yy0O+SCdiu7ibHokWl2aodO8SuctaO/8ILhsvkTNBsLhBJSADOnRMzb+VNyhD16ydmAM29duV0zTPuZic3aOzbl93yiIiIyPVUgmDtFr3Ut99+C0EQ0KVLF2zfvh1BegNfPD09Ub9+fdStW9dlDS0LBQUF8Pf3R35+vsPl1bVacT6ozEzLN5IajfgNupIbPq0WqFPHchbI1n5TUsSxXo7M/xMSAuTk2L99RZeaKt6Im7tWkZFi8CO3y1xqqthtUppo2RaNRgzGpKyKVAYfMNxeCkRsdWkzdw5l9fubNk3M/qnV1l93kZFiQKUkk+Sq9xcRERGRRElsIDuokpw7dw6RkZFwc1M8HKvCc2ZQBTh+Q2xOWpo4xskWKTAwR6sVi1BMmKDs2JLk5NKJg63RaMTzvnRJXkDhKmq1siIMGzeKGREAKC4Wu5qdOSOOKxs9WtxfaKgYLNmyfj0wZYr8INbca8NSYDR4sDh+LjbWeuCg1Ypj97KyxMxoZiYwZIi89phrn9zfpX5wai2o3LJFzGQp5Yr3FxEREZHEpUEVAOTl5eHnn39GdnY2SvRnjgXw3HPPKd1dheHsoAqwnO1Q+s28ZNMmsXiELfqBgSP7MUfKvgwdKlbss2TSJKBDB/M3vmVtwQIxuzd7tu11rWWqgoLEZSUl8rrXLVigPHg1l2WRAqMdO8QumPqZJuPsli1yA3NzIiPFyX4nTpSXJQLEjJKloNLRjJKz319EREREEpcGVV999RUGDx6Mmzdvws/PDyq9AR8qlQrX5Hx9X0G5IqgCTDMFtjIL1si9IZ45E3jjDcf3o0/JzTIgnuPmzYCbm+mNr5ubGJiUlY0bgaQk+V3Gduywnl0JDgaKiiwHldK+5s61PytknG20lPFRmpmx1XVOotGIQWHt2qavXblZImdkVuWcj7PeX0REREQSJbGB4j58kyZNwogRI3Dz5k3k5eXh+vXrukdlDqhcyZlz2cTGyhukv3Kl9S5v9lQDFITSYgK2SsYD4vGlbl3G1dtu3pRfZtsZwsOtF+vQL5YAWJ5jTJKbaz2gkvZlz/xXEv3KkM6c90xO0ZKZM8XfWWKi+FoJDxfbk54uHsNSlUHj0uWuqIJpjHNFERERUXlTHFRlZmZi3LhxqFmzpivaQzao1eIcSLZcvGh9Dix7qgEGB5fOgaXkJliqqKd/4+vtDSxbJh7b0YldbdEvMy8nGJATMOrv29q+HCllr18Z0tnznlm6DiEh4u+rUyfx55QUMasVH186Z1lUlLjcXKlz49LlrqiCSURERFTRKA6qevTogV9++cUVbSGZGjWSt56twEfpnEa5uaU37Upugi3d7Cs5vkolBjDW5nqyxLjMvK1gQEnAmJsLfPKJ5X3ZE7yaK5XuSMZHqxW74W3aJP4rZbP0r0NystjNLydHzLDFx4tVJvv2NQ3mpDnLUlJsZ4nsLQtPREREVJm4K93gySefxKuvvopjx46hZcuW8PDwMHi+d+/eTmscmefMb/8TEsTs04wZ8oo4SDft0s2y3IzOqlVi0QpPT/PHl4owmKsqKN2Qr1hRuu727cCHH8o7tkolBg19+pTe9EvBgEQKPLKygCtX5O1Xkp1tvSiIFDzKLWUvCMCAAYYBitLfuX5hi/XrDSf51S9soVaLRUfMzX9mqWy/IJi/puZIQWViomnlQDnzUxERERFVBooLVVgrpa5SqaBVUru6gnFVoQpnc8UcPfYUFEhJETMZcqnVYtW4d9+1vI7cam72FNqwVAzB3DGVlGGXW2TBuKDCzp1iJT1zVCrgs8/E7nhZWWIJ96FDLZenNy6yYS2A0y8m0aeP7YIj1sg9d1bpIyIiosrG5SXVq6rKElQBzp+jx95AbetWMauipJLfq6+aD6ykoCMzU+yGFhIidg00V81NbgU7febKzNuaQ8kaR8qBS+23VT1RP7ALDhazR5bmiho3Tlxnxgzb5yO1fc0aoFs3ZW3XZ6t0vz5Hq/Sxyh8RERGVJZdW/6OKQW71NbnkVsYzvont1w/497+VHev998VJdfXpF0QYMkSc22ncOOC772y3Vy7jLnTWKupJLCVmHe26Jrd6oj6puGZQkPn1Fy8Gpk+XFyBKhS3S0myva42SsXWOVOmzVjDDHpbGmRERERHZQ/GYKgC4desWvv32W5w/fx7FRnfH48aNc0rDyDb98UjO+Pbe0tgfjcZ6N63GjZUdR6sFliwprQpoKVt07ZoYJCxeLI6nMj6+3LFKUlbGuBiCnMCmpAQYNgz48svSoAawfU1ssaeEuDSWqSKwdE1dwdLrQyqYofRLBHNdEZVOoExERESkT3H3v99//x1PPPEECgsLcevWLQQFBeHq1auoWbMmQkND8ffff7uqrS5Xmbr/uZLSblb2jG8aOxb44AN53eAkW7aUzntl3N45c8QAzJi17pCbNolZD1ukiYOd2fXMnmvmCnv2iEGjkm6U9nYxtYet14fSLpjOmkCZiIiIqj6Xdv+bMGECnnrqKVy/fh3e3t44cOAAzp07h9atW2PevHl2N5oqDqXdtOyZiykmRvxXyZxQAweKN73m2vvGG2JFQOOS69a6Q8rtuhYa6vyxPI7MX+UskZHi79dWt8/gYMPl9nYxtYcz5+dy5gTKRERERPoUB1WHDh3CpEmT4ObmBrVajaKiIkRGRuLdd9/F66+/7oo2UgWndHyTWg2MHi3+v5JucFqtmKmyNI5GzmS0+uTMoRQcLFbdc9ZYHok981c52/z5Yjusjc/bvl0sMS/3mjqbI/NzGXP2BMpEREREEsVjqjw8PHRl1UNDQ3H+/Hk0bdoU/v7+uHDhgtMbSJWDkrmYJk4sna9KSaEDibX5kYznn7LG1hxKgmB+riZ7x/IYd6vs00fZ/FXOFhJS+v8JCUCvXuJYt1OnxPNv27a0KIbca+pszpyTzZkBGhEREZE+xZmqf/zjHzh48CAAoHPnznjjjTewYcMGJCcno0WLFk5vIFUe+pmiXr1MK+ep1abl1KVskRLOzCZYytJERJh2e5PY01XMUvU6oPSaPf648vY7Qj94SEkRu2ROmCAGVh99BDz3nNjO8HBxeXlUyZOTTYyMlFcww5kBGhEREZE+xYUqfvnlF9y4cQPx8fHIzs7Gc889h/3796NRo0ZYvXo1WrVq5aq2uhwLVThXcbF4g37mjBhAtGwpZn6MxyUpnUQYUDY/khzGWSStVt78TXImv5VTHAFQfg0cJbVdyVxd5VElz1lzsrli0mwiIiKqujj5r50YVLmGrRLWWi1Qp475rnaWyAlmHKGkMqC14E5O9bqICPEmPzPTrqaa0GiA27fFEvC2ggdAfvVF/e3LukqeuddQZKTysvbOnjSbiIiIqi6XVv+7ffs2CgsLdT+fO3cOCxcuxP/+9z/lLaUqT7qJNb5pl8YlpaSIGSK5AZWS7l6OcFZXMTnFES5edDygGjMGWL9eDDYzMsR5vQDbEzkrqb6or6yr5CktQmJtP86cNJuIiIgIsCOo6tOnDz799FMAQF5eHtq0aYP58+ejT58+WLp0qdMbSJWX3BLWSgMKKSBwJWeN5SmrogcdOwKDB5eWwJcbPNg7CXF5VMlTWurfEmcFaEREREQSxUHVb7/9htj7d5Lbtm1DWFgYzp07h08//RSLFy92egOp8pJbwjonR97+QkLKLptgreS5cbbHmrIqemDuOHKCB0faV5mr5DkrQCMiIiIC7CipXlhYiFq1agEA/ve//yEhIQFubm5o164dzp075/QGUuUl96Y7JETMoFgqICCtc/FiaSn2smCpTLxGI38sj5TxslYcQRpTdemSvGIRxttrNJYzZrZKzNtqnzWskkdEREQkUpypatiwIb744gtcuHABu3fvRvfu3QEA2dnZLO5ABuTedEdEWM8KqVTAsmVlG1BJHO0qJifjtWgRICV5La1j7TlHukMqnbhZOm5ZjGsjIiIiqiwUB1VvvPEGXnnlFURFRaFNmzZo3749ADFr9Y9//MPpDaTKS8m4pIpcQMDRrmJyzs3aOtu3iw9XXRvp2HLmC3NGIFfdaLXiHF+bNpXPXF9ERETkenaVVL98+TKysrLQqlUruN2f4fXnn3+Gn58fmjRp4vRGlhWWVHc+pSWsjeeL0p/PqrKTc27W1nH1tZH2n5kpjnM7e1bMzl29WrqOPWXMKxNnX2Nb0wkQERFRxVVm81RdvH+noJHzFXclwKDKNZw1xxCVvaoU5No6F2cGQFotMGcOMH266XOcE4uIiKhycGlQVVJSgtmzZ2P+/Pm4efMmAKBWrVqYNGkSpk6dqstcVUYMqlynKt2ck2u54rViLmAKCQGWLCmdLy0x0bRYh0olLps5E2jUSF57zB3LmP4EzHwfEBERVUxKYgPF1f+mTp2KVatW4e2330bHjh0BAN9//z1mzJiBO3fuYM6cOfa1mqo0W1XoiADXdJezFDDl5AD9+gGTJgGffWZ9PjX9jJO19mzdCiQl2W6T/lxffF8QERFVfoozVXXr1sWyZcvQu3dvg+U7duzA6NGjkal0JtcKhJkqovJjLVsE2NddTqsFoqKsZ42UktqzZQtQu3ZpRi07Gxg0SFkhio0bxQIoREREVPG4NFN17do1s8UomjRpgmvXrindHRERtFoxQ2UpW6RSAcnJQJ8+yrrL2ZqA2h5SGwcMcLyS36VLwN69YkDGbrFERESVl+IBUK1atcKHH35osvzDDz9Eq1atnNIoIqpebAU/+t3llJA7AbU9nFEa/ZVXgG7dxAxXfLyYVUtJcXy/REREVLYUZ6reffddPPnkk9izZ49ujqoff/wRFy5cwH//+1+nN5CIqj65wY/SIEnuBNQVRWam2AWSlQGJiIgqF8WZqs6dO+Ovv/7CM888g7y8POTl5SEhIQEnT55EbGysK9pIRFWc3OBHaZAUGytW+asspK6FycmcJJiIiKgycWieqqqGhSqIyodUUCIz0/y4KpUKiIgA1q5VPv5o2zaxyl9lk5rKyoBERETlyaWFKgDg+vXrWLVqFY4fPw4AaNasGYYPH46goCB7dkdE1ZxaLZYpT0wsnRtKIv18+7Y4/kgip9S6VitW6GvXDjhwwHXtd4W9ezmvGxERUWWhOFP13Xff4amnnoK/vz8efvhhAMCvv/6KvLw8fPXVV+jUqZNLGloWmKkiKl/m5qkKDgZyc03XtVVqXc4kvJWFo3N1ERERkXJKYgPFQVXLli3Rvn17LF26FOr7X51qtVqMHj0a+/fvxx9//GF/y8sZgyqi8qfVilX+srKA0FBg2DDLgZFKJQYcZ88aZnIszXlVWTkyVxcRERHZx6VBlbe3Nw4dOoTGjRsbLD958iQeeugh3L59W3mLKwgGVUQVS1qaWGrclj17xKBKCsSGDhXHZ1UllgJIIiIicg2Xjqn65z//iePHj5sEVcePH+c8VUTkVHJLqCclAVV97nH9ubpYwIKIiKhiURxUjRs3DuPHj8fp06fRrl07AMCBAwfw0Ucf4e2338aRI0d06z744IPOaykRVRvFxcCSJcC338pbv6oHVPpcOaExERER2Udx9z83N+tTW6lUKgiCAJVKBW0lm2iF3f+Iyt/kycD777t+nqY2bYCff3btMVyBpdaJiIjKhku7/509e9buhhERWTN5MvDee64/jpsb8Pffrj+OM0ljqjjHOhERUcWjOKiqX7++K9pBRNVccbGYoSoLJSXA1atlcyxnkKr/LVzIIhVEREQVkV2T/166dAnff/89srOzUVJSYvDcuHHjnNIwIqpelixxfZc/Z4iMBF54AZg+veyOqdGIARXLqRMREVVMioOqtWvX4sUXX4SnpyeCg4Ohkr5ChTieikEVEdnjzJnyboFtISHA6dPAjh1ixsjVQWBwMPDZZ+IYKmaoiIiIKi7FQdW///1vvPHGG3jttddsFq0gIpIrJqZsjqNSARER4v9nZiqbIDgnB3j7bWDGDNdPLKxSAStWAF27uvY4RERE5DjFUVFhYSEGDBjAgIqInGr0aNdnY6TE+qJF4kN/mVyLFrk+oAKAV15hdz8iIqLKQnFk9Pzzz2Pr1q2uaAsRVWOensDEic7Zl0oldp2TMlISjQbYtk0MVhISxP83XseWspoTa/PmyjHGjIiIiOyYp0qr1aJXr164ffs2WrZsCQ8PD4Pn3y+r8l0uwHmqiMqfuXmq1GqgVy/g11+Bixetby9lnrZtA/r0AdLTxQlzw8PFcuTG2TCtFkhLA5KSbAdMQUFlO9Ew56QiIiIqPy6dp2ru3LnYvXs3GjduDAAmhSqIiBzx7rvA7NliNcAzZ8SxVqNHi5ksrdYwSLp6FZgwwTDQMq6UZysoUavFh5xgqXdvYO1aOWchICREhQ8/BCZNMmxfSAgwYADwwQe295KVJedYREREVN4UB1Xz58/H6tWrMWzYMBc0h4hIDKCSk02Xq9WmQdIzz9jORtkiN3jp1g3Ys8d2tgxQIScHCA0FMjJM25eeLi+oCg+X1y4iIiIqX4qDKi8vL3Ts2NEVbSEiUsxcoKWU3OAlIkIsVNG3r7z1d/zyM+Li2pi0LzZWzKhZqj6oUonPx8bKOw4RERGVL8WFKsaPH48P5HzFSkRUSUhBjqUezCqVOOlvbKzYrXDmTHn73XB2HrQlptUm1GrL1Qelnxcu5NxURERElYXiQhXPPPMM9u3bh+DgYDRv3tykUEVKSopTG1iWWKiCqPpKSQESE8X/1/+rqF/4QhqnpdUCYZo7uHrZE+a/myoB/C4CydFIHb4XcVFxFo85frxhd8LISMMxYURERFQ+XFqoIiAgAAn8tCeiKkYqsW4c5BgXvgDEDNKQyQexcGJHACUwDKxKxH96JgNuJci6YXnAVkKCvAqFREREVLEpzlRVZcxUEZFxhUFLQU5aRhri/7UY2LUIKIgsfcLvvBhQNfscAJA6NNVipoqIiIgqLpdmqiQ5OTk4efIkAKBx48YICQmxd1dERBWG3MIXsfVioWn3LC42iQbOPQrcDAd8s4D66YBbCVRQQeOnQWw9VpsgIiKq6hQXqrh16xZGjBiB8PBwdOrUCZ06dULdunXx/PPPo7Cw0BVtJCKqcNRuaizquQgqtxKoor8DWm4Gor/VBVQAsLDnQqjd2JePiIioqlMcVE2cOBHffvstvvrqK+Tl5SEvLw87duzAt99+i0mTJrmijUREFVJC0wRsS9qGCL8Ig+UaPw22JW1DQlOOPyUiIqoOFI+pql27NrZt24Y4o/4xqampSEpKQk5OjjPbV6Y4poqI7KEt0SL9fDqybmQhvFY4YuvFMkNFRERUybl0TFVhYSHq1Kljsjw0NJTd/4ioWlK7qVmMgoiIqBpT3P2vffv2mD59Ou7cuaNbdvv2bcycORPt27d3auOIiIiIiIgqOsWZqkWLFqFHjx7QaDRo1aoVAODw4cOoUaMGdu/e7fQGEhERERERVWR2zVNVWFiIDRs24MSJEwCApk2bYvDgwfD29nZ6A8sSx1QRERG5HschElFl4PJ5qmrWrImRI0fa1TgiIiKqvlKOp2D8rvG4WHBRt0zjp8GinotYMZOIKi3FY6rmzp2L1atXmyxfvXo13nnnHac0ioiIiKqelOMpSNySaBBQAUBmQSYStyQi5XgKADGTlZaRhk1/bEJaRhq0JdryaC4RkWyKM1XLly/Hxo0bTZY3b94cAwYMwL/+9S+nNIyIiIiqDm2JFuN3jYcA01EH0rLxX4+HtkSLif+byEwWEVUqijNVly9fRnh4uMnykJAQZGVlOaVRREREVLWkn083yVAZu3jjIpK2JdnMZBERVTSKg6rIyEj88MMPJst/+OEH1K1b1ymNIiIioqol64b9X7xKmazkXcnsCkhEFZLi7n8jR45EcnIy7t69iy5dugAA9u7di8mTJ2PSpElObyARERFVfuG1THu5KCFAwIWCC0g/n+7SybbtqUzIaoZEpDioevXVV5Gbm4vRo0ejuLgYAFCjRg3861//wmuvveb0BhIREVHlF1svFhG1IpB5I9Oh/WTdyHJZEGNPZUJWMyQiwM55qgDg5s2bOH78OLy9vdGoUSN4eXk5u21ljvNUERERuc6AbQPw2dHPHNrHzLiZWPnbSqcFMVKAtuPkDiw8sNDkeRVUAIBtSdtM9i9VMzQuvmFtGyKqPJTEBnYHVVURgyoiIiLX0JZoEfB2AG7evWnX9iqoEOQdhNzbuWafA5QHMeayTJaOrfHT4Oz4s7qMmLZEi6hFURa3NbcNEVUuSmIDxYUqiIiIiJRKy0hzKKCyxp5CFpbmzLK0f2k8l8RWNUNz28jBObqIKifFY6qIiIiIlErLSLN7W42fBi/88wVMT5tucR1bhSz0x2EFewfjxZ0vmp0zy5rMgkykZaQh60YWjuUck7WNkqqHHJ9FVHkxqCIiIqIKa1rsNMyIm4EtR7fIWn/7se0AYFC8Qm43P1uSdyfjauFVRduE+oTKWs/S+Cxpji6OzyKq2DimSg/HVBEREVnmSNW9vX/vRbd13RQfc8+ze6B2U2Pv33sxO3227O2kDA8As8FKWYmoFYHFjy+2GhBxfBZRxcRCFXZiUEVERGSeo13TtCVa1JlXx2yhCXOkwhQ13GvYVYZdGodlqbiFkv04EpDJKaKRlpGG+E/ibe4rdWiqS+foIiJDLFRBRERETmOpqIPUNS3leIrNfajd1Fjx1ArZxxQgIPd2rt3zWgn3/3MkoAKA2jVrO7S9nCIacsddKRmfRURli0EVERERWaQt0WL8rvFmszVKq+71adwHM+NmIqhGkM11fT19lTfWBe6V3HN4H7YqAYbXCpe1H7nrEVHZY1BFREREFjmrdHjK8RRELYrC9LTpuHbnms3j3iy2XX796cZP21zHUdfvXHfavixlmmLrxULjp7FYOl4FFSL9IhFbL9ZpbSEi52JQRURERBY5o2uakjmhlGgR2sKp+7OHCiqE1AyRta6lSoBqN7WuqIZxYCX9vLDnQhapIKrAGFQRERGRRY52TbPWfdBRaje11QxPWRAg4LlWz8laN2lrEmZ9O8tsV8mEpgnYlrQNEX4RBss1fhqWUyeqBFj9Tw+r/xERUVVQfK8YS35ZgjPXziAmKAajHx4NT3dPu/YllfvOLMg0GxjZKvctt7KdPVRQ4ZUOr2De/nkAUG5l04O9gxUVxAj2DsaKp1aYDZQcKVtPRM5V5ar/ZWRk4Pnnn0d0dDS8vb0RExOD6dOno7i42GC9I0eOIDY2FjVq1EBkZCTefffdcmoxERFR+Zj8zWTUfKsmJuyegA8PfogJuyeg5ls1MfmbyXbtz9Guaa6uWLf5z834LPEzkwyPLfMem4eNCRsxLXaaw21QWmEw93Yu+m7pa7ZqotpNjbioOAxsORBxUXEMqIgqiUoRVJ04cQIlJSVYvnw5jh49igULFmDZsmV4/fXXdesUFBSge/fuqF+/Pn799Ve89957mDFjBlaskF++lYiIqDKb/M1kvLf/PWgFw+5lWkGL9/a/Z3dg5UjXNFdWrJOKZIT4hCBjfAaeffBZ2dvWrVUXA1sOhIfaw2Xts0Vu1UQiqvgqbfe/9957D0uXLsXff/8NAFi6dCmmTp2Ky5cvw9NT7OIwZcoUfPHFFzhx4oSsfbL7HxERVVbF94pR862aJgGVPrVKjcLXCx3qCqi0a5qt7oPOsDFhI7zcvdB3S1/Z26QOTcW129eQuCWx3LoNAsC02Gno2qAru/kRVUBVrvufOfn5+QgKKp3n4scff0SnTp10ARUA9OjRAydPnsT1684rh0pERFQRLfllidWAChAzVkt+WWL3MeR2TdOWaJGWkYZNf2xC+vl0vN/9fZcGLqE+oRi/a7zs9X09fNFB08FlBTSUmJ0+G/GfxCNqUZSsSZSJqGJyL+8G2OP06dP44IMPMG/ePN2yy5cvIzo62mC9OnXq6J4LDAw02U9RURGKiop0PxcUFLioxURERK515toZp65njpxMVcrxFIzfNd6gfLrGT4P+zfvjs6Of2X1sa5b9skxRufZ/hv8TS35Z4vQS747ILMhE4pZEVvojqqTKNVM1ZcoUqFQqqw/jrnuZmZno2bMn+vXrh5EjRzp0/Llz58Lf31/3iIyMdGh/RERE5SUmKMap6xmTJu+N/yQeg1IGmc2uWJqPKrMg02UBFQBsO75N0frfnf8OE3ZPcFFr7CNlzDjOiqhyKtcxVTk5OcjNtV4xp0GDBroufZcuXUJcXBzatWuHtWvXws2tNCZ87rnnUFBQgC+++EK3LDU1FV26dMG1a9dkZ6oiIyM5poqIiCodV46pkoIlS13lktslo1ejXhj6xVBk3shUtG8ylTo0FXFRceXdDKJqT8mYqnLt/hcSEoKQEHmzkGdmZiI+Ph6tW7fGmjVrDAIqAGjfvj2mTp2Ku3fvwsNDrOTzzTffoHHjxmYDKgDw8vKCl5eXYydBRERUAXi6e2Ji+4l4b/97FteZ2H6i4oBKzuS9Cw8sxMIDCxXttyoKqRmCnMIch/djXIaec1cRVXyVolBFZmYm4uLiUK9ePcybNw85OTm4fPkyLl++rFtn0KBB8PT0xPPPP4+jR4/is88+w6JFizBx4sRybDkREVHZefexd/Fqh1ehVhnecKtVarza4VW8+5jy+RvTz6c7feyRpfmugr2DDZYHewfDz7Py9BwpKSmBr6evw/u5cuuKrgugnG6XRFT+KkVJ9bVr12L48OFmn9Nv/pEjRzBmzBgcPHgQtWvXxssvv4x//etfso/DkupERFQVFN8rxpJfluDMtTOICYrB6IdHW8xQ2cqCbPpjEwalDHJa22bGzcTK31YaBGqRfpFY2HMh+jTug7SMNKRlpAEA4qLi0EHTAeHvhyO/KN9pbagMNH4aDGwxEPP2zzPJEkpBKItaELmWktigUgRVZYVBFRERVSdbj27F6P+OxtXCq7plGj8NFvVcpLtZT8tIQ/wn8U45XkjNECzosQBhvmEAgOxb2QaBnKXKgQOaD8C8H+dZ2m21pIIKGj8Nzo4/y66ARC7CoMpODKqIiKi6mPzNZIvjr1RQ6bIgrpq81zh4s1QMQ8rK9G7cGztO7nDa8ctbsHcwcm9bL9YlB4taELlOtZj8l4iIiOyz7eg2qwUtBAi60t5qNzUW9VwEwHQslCOkeZlSjqdYLYYhLfst6zds7rsZtWvWdlobykOkXyS2J23HlVeuYEGPBQ7vz7ioBRGVDwZVREREVZy2RIu0jDRs+mMT9v69Fy/95yWb21wouID08+kAgISmCdiWtA0RfhFOa5P+vExpGWlWi2EIEHCh4ALq+NbB5UmXsefZPXi68dOKjhfsHYygGkGONNkh02KnIXVoKs6OP4uEpglQu6lRx6eOw/u9cusKNv2xCWkZaZzfiqgclWtJdSIiInItc+OU5Fp0YBG0JVrERcWhT+M+8PfyR1pGGo5fPY7tx7dDBZVDXQKlYEkqTGFL1o0s7Di5Q/H5LOixAC+3eRkAMCd9DqanTbenuQ4pEUqw9++92Pv3XsRFxSEuKg7htcId2qdapTaYxNi4SyURlR2OqdLDMVVERFSV2Jq0Vy5fT194qb0MxgBJ5c+dMS5oWuw0zE6fbXO9mXEzMSNthqLz0fhpkDE+AwB0VQ5PXTuFlb+uxMUbzi0Vr0SwdzCWPbkME/43weZ4NbnBK6sCEjkXC1XYiUEVERFVFVKBCWfPMSWRbuDf6PwGtCVanMs/h3VH1tm1r92Dd+P5r563GFyooEKEXwQEQUDmjUxF+96etB0ATLJbgTUC0adxH9StVRdvff+Wzf1Mi52GD37+wOml3V/t8Crm7RcrG+qfu3R9X+nwCjb9ucmg7WqVGlrBfFc/VgUkch4GVXZiUEVERFWFM0uhW2PtBl8uTS0NBrYcaDW4mBE3Q1G3vWDvYKx4agUAWM3WBdUIgkqlwrXb1yyu48ysnDGNnwbvd38fE/830ezcXVIFRinLduXWFYMuf5awKiCR45TEBhxTRUREVAWVVVU4RwMqAMi8kYl5++eZzcpo/DRY2HMhiu4VydrX042fxtg2Y3UBRdSiKKtd567duab7f0vd7FwRTEkuFlxEiE8IMsZnWJyEWe2m1p3Ppj82ydovqwISlS0GVURERFWQo0UQypIAASqosPnPzTjz8hnsv7jfJLiQW8xifLvxugDEVlVBfcHewfB29y6XcVZZN7IMAidr5P5eK9Pvn6gqYEl1IiKiKii2Xiw0fhqnzi3lSlIlwP0X9yMuKg4DWw5EXFScLlvTQdPB6hxVKqgQ6ReJ2HqxumVKsjW5t3Px/D+ft/8EHGAcAOmXwDculW7r92ruOhCR6zGoIiIiqoJcNWmvq5kLhFKOp6Du+3VxtfCq2W2k81vYc6FBcQal2Zr5P85XtL4zaPw0BgFQyvEURC2KQvwn8RiUMgjxn8QjalEUUo6nALD+e7V0HYjI9RhUERERVVGumLTX1YwDoZTjKei7pa/VcU1B3kFmy4hLWR25bhbfVNZYJ1jUc5EuAJJK4Bt3WcwsyETilkRdYGXp96r5//buPDrq+t7/+GsSmEkCmZiEQIAEEhFZFPF3WGygaBBKlNaDsl2VekPhiiwim4hoFfCHgtjKVlyovVxtxQUIWlyqXiTIVeBaFBFEjvojRUMCYZEEEAIzn98fw4wZMjOZyYRMlufjnBwy3/WdfI/iy8/38/7Y02inDkQI3f8qoPsfAKAhcnePW/fVOv3p0z+FfH5Mkxg1a9rMK9jURNe/iny1Anc4HWr1h1ZVNopo27yt/jXtXz5HZ4JdqyvchYxDvba7O6E7AFXVAt/f78dfcwsA4aP7HwAA8KjYBKE6oers+bN66daXlBSb5GkYER0VrXmb59VIfe7X1v446I9eIeHMuTNBdd4rPFmoLQe2+Gz04B7VGbdhXMBrXapAVfHaw7sMV+cWnZWdke01X0xyLUwcqKmGe85ZxZ8z2OYWAC49QhUAAI2E+3U4f4vsBjLh7QmKaRLjtfhucmyyjv90XE45w6orzZ6m26++vdJaTaEoLC1UfkG+z1GboV2GakinIRqVN0qv7XktrFov1iKuhd+5Xhfb/K/Nennoy7I2sVbaF2xTDVqlA3UToQoAgEbC3eRg+OvDQ3rdzcj4HOUJtGBuMNf/zZW/0YysGTpy6ohGrh0Z1mjRtPemqeR0iedzmj1NS29a6jW/6OPvP6729X2xyKIVN6/Q7etuD6r2ktMlaru4rZ7/zfOV5j3RKh2o32hUAQBAI1KTzSvc60slxyarbbz39S6LuUx2W+A5CF8Uf6E+aX007f1pYb9+VzFQSZWbO1T1el11GBm1bN5Sa0euVVJMUlDnHDl9xKsuN1qlA/UboQoAgEZmaJehKphSoE25m7R66Gotzllc7Wu5R7FevPVFzcuep6RYV7g4fua4Ss+WBjz3+9Lv9cw/n6nxsOOuS5Km/mOqHE6H3vz6zRq/h+R6HW9ol6F6qN9DIZ3nrsuNVulA/UaoAgCgEXI3Obij2x2a3Hty2AsFv/XNW5qbP1fHfjoW0nnfHfuu2vesiru5Q35Bvl7+8uWgzrFbQ+v+634dL7V5ash1bTmwxWs7rdKB+otQBQBAI1cTCwX/bdffqvUKX4ekDtW6nyQN6zwsqOPyC/IrvR7oS0pcikpmlmhe9jwlxiQGPPbi1/Gq8zqlr6YTF48ibsrdpP1T9hOogDqOUAUAAAKOkiTHJgec65MSlxJ0B7yK56Xb0zWx58RqjZKl2dM0odeEoI7dfXh3UMeNumaUrE2sevSGRz3hyhdfr+OFutCw5L/pRMVRxItbrwOomwhVAABAku9RkoIpBVp5y0pJ/uf6jOo2KqT7VAwl1iZWzyhZKJbetFTZGdlBBbI39r0R1DWHdBri+T46KlqP3vCo1o1cp7R477DU1t620ut47tG+YMIhTSeAhodQBQAAPHyNklQ112dI5yF+rubbxXOEhnYZqvv73B/UucmxyVo3cp3n3LH/Z2zYnQOrCjkXX98Y3/dz/54CjVjRdAJomCzG378ZGqHS0lIlJCToxIkTsttDm6gKAEBD53A6tOXAlkoL7DqcDmUszQi4qHBKXIoW5yxWW3tbr4V53dfNWJoRsAtgvDVe60au042ZNyo6Klp5e/M0bsM4n+tnhcIdcnw1gsjbm6fhrw+v9DMFOsf982w5sEVvfv2mXv7yZa/5XOn2dC25aQlzpIB6IJRsQKiqgFAFAED1uAOI5D2yU1UAkVyNJPq/2L/Ke2zK3aTsjGzl7c3TsNeDa1JRFX8hp6qgZ5FFafY07Z+yP+CIk78gCqDuCyUbNKmlmgAAQD0UbChwv/o25R9TvIJImj2tUmhxOB3KL8hXfkG+JMlpnEHVUlRWJIfTofvevS+8H0rSTVfcpFl9Z/n9eapaLLhiW/TsjGy/x7lfpwTQsBGqAABo4Ko7WpK3N89nSFp601Kfo05DuwzVkE5DKt1Lco1GFZUV6Ztj32jZ9mXVem3v0KlDyi/IV2FZYcjnXmzHwR0Bfw++2p2HcxyAho1QBQBAA7Z2z1pNeHuCjvz0c8vztvFttezmZQHn9fibT1RYWqjhrw/3+zrfxSMzvoJZdU17b5qSYpPCvo4klZwuCTjK5K/deXWPA9Cw0f0PAIAG6oEPHtCItSO8ApUkFZYVatjrw5S3N8/neQ6nQ1P+McVn0wn3tqn/mCqH0xHw/u5gVhOByu3YT8dq7FqBRpnc604FWp+LtugA3AhVAAA0QGv2rNFTnzwV8JhxG8b5DEahzCfyJ1AwqysCjTK5152S/K/PRVt0AG6EKgAAGhiH06EJb0+o8rijPx31NIuoqCbmE1UVzC61qAD/iRPsKFNV63PRFh2AG3OqAABoYLYc2BJ0I4j8gnwNuHyA17aamE8UqQYO1iiryp3lcipwR8FgR5n8Nd9ghApARYQqAAAamHADjXs+kb/FfN1rNAUa6YlUA4dyZ3nA/dGWaL0y7JWQRploiw6gKrz+BwBAAxNKoPEVFmpiPlFVjR4ixWEcSmmWEukyADQwhCoAABqYfu36qW182yqPS45N9jsCE+58okDBLNJYWwpATeP1PwAAGpjoqGgtu3mZhr0+LOBxK29ZGXC0Kdz5RO5gVlPrVNUU1pYCUNMsxpi62+u0lpWWliohIUEnTpyQ3W6PdDkAAIQlb2+exm0YV6lpRXJsslbesrLWutc5nA5tObBFhaWFmvreVB05faTqky6RaEu0Tj90WtYm1ojVAKB+CCUbMFIFAEAD5R5pyi/I97ROz87IVnZGdq12r3M3esgvyI9ooJJcc6o++eETGk8AqFGEKgAAGrDoqGgNuHxApbbpkVDTc5ksslRrcWHmVAGoaTSqAAAAtaIm5zJNvW5qpSYaKXHBdfVjThWAmsZIFQAAqBVVrX8ViiGdh+gPg/7g1USjT1ofdVjeIaz1tQCgOhipAgAAtSKYNutzbpijtHj/61tZZFG6Pd3ThTA7I1t3dLtD2RnZsjaxhr2+FgBUB6EKAADUGn/rX6Xb07Vu5DrNzZ6rpTdXPxiFu74WAFQHLdUroKU6AAC1w91m3d/6V3l78yqtb5VuT9eSm5YEFYyquj4AVCWUbECoqoBQBQBA3UEwAhBJrFMFAADqPfecKQCo65hTBQAAAABhIFQBAAAAQBgIVQAAAAAQBkIVAAAAAISBUAUAAAAAYSBUAQAAAEAYCFUAAAAAEAZCFQAAAACEgVAFAAAAAGEgVAEAAABAGAhVAAAAABAGQhUAAAAAhIFQBQAAAABhIFQBAAAAQBgIVQAAAAAQBkIVAAAAAISBUAUAAAAAYSBUAQAAAEAYCFUAAAAAEAZCFQAAAACEgVAFAAAAAGEgVAEAAABAGAhVAAAAABAGQhUAAAAAhIFQBQAAAABhIFQBAAAAQBgIVQAAAAAQBkIVAAAAAISBUAUAAAAAYSBUAQAAAEAYCFUAAAAAEAZCFQAAAACEgVAFAAAAAGEgVAEAAABAGJpEugAACItxSKe3SI4iKbq1FNdPskRHuioAANCIEKoA1F9ledKhKdL5H37e1iRNarVUih8auboAAECjwut/AOqnsjypcLh3oJKk84Wu7WV5kakLAAA0OoxUAajbjEM6nS+dypcskmKzXa/4HZoiyfg6QZJFOjRVaj6EVwEBAMAlR6gCUHeV5UlF4yTn0Qob50sWu2RKA5xopPPfu+ZaNcu+xEUCAIDGjtf/ANQ9xiGVPCYVDrsoULn3BwpUFTiKarYuAAAAHxipAlA9l6rrXlmeVHyf5CgM/1rRrcO/BgAAQBUIVUBjVt1gdKm67rmbT/icKxUKi6ueuH5hXgcAAKBq9e71v7Nnz+raa6+VxWLRzp07vfbt2rVL/fr1U0xMjNLT07Vo0aLIFAnUB2V50ncZ0vf9pYN3uv78LqPqrnmXquuecQRoPhEKi+uPVktoUgEAAGpFvQtVDzzwgNq0aVNpe2lpqQYNGqT27dtrx44deuqppzR37lytXLkyAlUCdVx1g1HA4GNcX0XjJWd56DWd3lK5nmBE2b0/N0mT2q51jZgZh6trYOkrrj+NI/TrAwAAVKFevf737rvv6v3339e6dev07rvveu17+eWXVV5erv/8z/+U1WrVVVddpZ07d+rpp5/WuHHjIlQxUAdVGYwCtCMPJvg4S6Tv0qTU50J7FbC6TSUs8VJ6nuQ47P0KIwsDAwCAWlJvRqoOHTqku+++W3/9618VFxdXaf/WrVt1/fXXy2q1erbl5ORo3759On78eG2WCtRtVQajCu3ILxZs8HGU/DziFexoUXWbSjgKJUVL9jtc7dPdgYqFgQEAQC2pFyNVxhiNHj1a48ePV8+ePVVQUFDpmOLiYmVmZnpta9WqlWdfYmJipXPOnj2rs2fPej6XlgbZphmoz4IORj6OCyn4GKnod66RpIqd/PyNFsX1c+07X6iQ51VVrLXKkTi59rMwMAAAqCERHal68MEHZbFYAn59/fXXWr58ucrKyjR79uwavf+CBQuUkJDg+UpPT6/R6wN1UlTL4I7zFaAcRySFEEScpZVbo/sbLbJEu8JWdVSsNZhXFM//IB19vHr3AgAAuIjFGBNuq61qKykp0dGjPhb2rODyyy/XyJEjtWHDBlksFs92h8Oh6OhojRo1Si+++KL+/d//XaWlpXrjjTc8x2zatEk33nijjh07FvRIVXp6uk6cOCG73V7peKDe8zXPyKdoqc2rkn34z5tK10oHR9RQIRdannfYX3m0qCxPOjhOMoH/3eDRJN37OqWvuLoZBqPtOuZXAQAAn0pLS5WQkBBUNojo638pKSlKSUmp8rhly5Zp/vz5ns8HDx5UTk6OXnvtNV133XWSpKysLD388MM6d+6cmjZtKkn64IMP1KlTJ5+BSpJsNptsNlsN/CRAPRDSGlAO6eBIyXKhi17pGungHTVYTIV5W82yvXfFD5USv5COPRbcpS5unR7KK4r+GnIAAACEoF7MqWrXrp3X5+bNm0uSOnTooLS0NEnSnXfeqXnz5mns2LGaNWuWdu/eraVLl2rx4sW1Xi9Q51R3DahDUyXjdAWsS8HXvC3jkH78U3DnJ04NMDcriPbs/oIdAABACOpN97+qJCQk6P3339f+/fvVo0cPzZgxQ48++ijt1AGpmmtAXRhNOjTxkpQkyfeo0uktkvNYcOc3H1J5myVaahnC/0ypbit3AACAC+rFSNXFMjIy5Gsq2DXXXKMtW3y0gQYau3CCg6Ok5uqoyJLoGlWqdL8ga41K9n1+WZ5UPD74Oqrbyh0AAOCCehmqAISoTgaHs9LJNyu/vhdsrYn3uf48le8KYtGtXd0Jg26mcaFZhq9gBgAAEAJCFdAYVHsNqHhJZZemJnPa1Tij7VrvYHX+UBAnR0nWTtJ3GRe91hhsw4kLnUQvbnIBAABQDQ1mThWAAKq9BtQlClQeRiq6Wzq10dWgwjikw5ODOM8pFd3uY56YI7jbRiVIbV6nnToAAKgRhCqgITIO12txpa+4/jQOV4BIuj/SlVXmPCZ9P9A16nT08Us3h8vrnj9Kh6dVXoAYAACgGnj9D2hofC3w2yTN1RGv9JXI1VWV84XSkTm1ez9frx8CAACEiJEqoCFxL/B78Wtx5wtdDRxCbqtem0JcQ6um7ndoqmskDwAAoJoIVUB9537V78TLF1qJ+wontR1Y6osLa3GVzP35NUkAAIAQEaqA+qwszzUX6fv+UtFva2c+Ul0QlSxPBz/fB4R2vWPzXb/D7zKYZwUAAEJGqALqK3+v+jUElvhAOy/kKaPKwcri+mq9Woqyh35f9zwrghUAAAgBoQqoj4zD1Yyiwb3WZ5GiUyQTqJW7kRxHpRbzpCZtvXc1SXM1nji3T3KWVuP+zLMCAACho/sfUB+d3tIAR6gujDrZR0nHl1R9uLWjdPl30vFnpHPfSU07SIkTXWtyHcwNo44L86xOb5GaZYdxHQAA0FgQqoD6yFEU6QpqXpM0qdUSKSopuFBV/o30/zp4h8vjf5QSxkrmZPj1NMTfMQAAuCQIVUB9FN060hXUjBbzXCNO0a2luH6uUSZnuaRoSVW8fudrTavzhdLReTVTW0P5HQMAgEuOUAXUR3H9XCM75wtVL+dVNUl3jUr5WnT3p09UZaDyqyZ+FxbX7zauXw1cCwAANAY0qgDqI0u01Gqp+0P414tKDv8awWg+TErfJHXY7ztQSbX82p2v7oFyBT5LdC3WAQAA6jNCFVBfxQ91dbq7uANeVFIIF4mW2qyRWq+s0dJ8apImtX3N1fwhUGCpjdfuLM1dP7e/7oH+Ah8AAIAPvP4H1GfxQ6XmQ1yd6hxFFwKJQ/p+YJAXcEjRLVyvukUlS86jl67W2L4/hynj8K7ZPZ9KulBLC8l55NLVkjxTsg+X4m/zXwcAAECQCFVAfWeJ9m79bRwX5lsF2XLdUSSdzr+0gUqSyl6Tyka6vj80xbu+Jmmu1xnjh7p+ntRnpIMjL00d0clS8sOu7y/+3QEAAFQDr/8BDY3XfKsglH8jFV6iAHOxonFS4fDKge98oWt7WZ7rs32ElDSzGjew+Pm+wrbUlYxGAQCAGkWoAhqi+KGuOUMKFB4srlGbI3Mk57Haqct5VL479F3Ydmiqa6RNkloukpLnhnb9JmlS23Wur0rzpdKZLwUAAC4JXv8DGir7cEmv+HmN7sIoTp3qxm6k89+75ji5X8mzXRncqZfdK8UP854TdfFcM+ZLAQCAS4SRKqAhs4+4MGqT5r29SZprFOhSz6Oqjoot1YPtBBg/rHJXQfd8KfsdVXccBAAACAMjVUBD56tDYFw/qez1SFfmW8UgVeUixyzUCwAAIo9QBTQGvrrchbQelEWKbiu1/ov00xbp7G7p5BvVqCNJMscVdEByN90oHO7a73UeC/UCAIC6gdf/gMbKPQrks0ueD6lLpeaDpJT/KyVOqd49zY9yBaOL7xkgIPlb5JiFegEAQB3BSBXQWAUcBaqgSbor7FQML1W+lueP88K9m0nmZIV7pFW+R0X+XmFkhAoAANQBhCqgMXOPAl28GG90imQf5QoyvsJLsIHMH/OTlPaeq1FGsAGJhXoBAEAdRagCGrvqjgL5C2SWBMmcqOKmDunsV1Ly1HCrBwAAiDhCFYDqjwL5CmRla6Qfn6n63HPfhX4/AACAOohQBSA8FweyMzuDO69ph0tRDQAAQK2j+x+AmpU4UVJVDSSiLxwHAABQ/xGqANSsKKuUND3wMUnTXccBAAA0ALz+B6DmtVzk+vPY05IcFXZEuwKVez8AAEADQKgCcGm0XCS1mC8df8bVlKJpB9crf4xQAQCABoZQBeDSibLSNh0AADR4zKkCAAAAgDAQqgAAAAAgDLz+V4ExRpJUWloa4UoAAAAARJI7E7gzQiCEqgrKysokSenp6RGuBAAAAEBdUFZWpoSEhIDHWEww0auRcDqdOnjwoOLj42WxWCJdTqNQWlqq9PR0ff/997Lb7ZEuB9XEc2wYeI4NA8+x4eBZNgw8x/rLGKOysjK1adNGUVGBZ00xUlVBVFSU0tLSIl1Go2S32/kXTQPAc2wYeI4NA8+x4eBZNgw8x/qpqhEqNxpVAAAAAEAYCFUAAAAAEAZCFSLKZrNpzpw5stlskS4FYeA5Ngw8x4aB59hw8CwbBp5j40CjCgAAAAAIAyNVAAAAABAGQhUAAAAAhIFQBQAAAABhIFQBAAAAQBgIVah1BQUFGjt2rDIzMxUbG6sOHTpozpw5Ki8v9zpu165d6tevn2JiYpSenq5FixZFqGIE8vjjj6tPnz6Ki4vTZZdd5vOYAwcO6Ne//rXi4uLUsmVLzZw5U+fPn6/dQlGlFStWKCMjQzExMbruuuv0v//7v5EuCQF89NFHuuWWW9SmTRtZLBa98cYbXvuNMXr00UfVunVrxcbGauDAgfrmm28iUyz8WrBggXr16qX4+Hi1bNlSt956q/bt2+d1zJkzZzRp0iQlJyerefPmGjZsmA4dOhShiuHLs88+q2uuucazwG9WVpbeffddz36eYcNHqEKt+/rrr+V0OvX8889rz549Wrx4sZ577jk99NBDnmNKS0s1aNAgtW/fXjt27NBTTz2luXPnauXKlRGsHL6Ul5drxIgRmjBhgs/9DodDv/71r1VeXq5PPvlEL774ov7rv/5Ljz76aC1XikBee+01TZ8+XXPmzNFnn32m7t27KycnR4cPH450afDj1KlT6t69u1asWOFz/6JFi7Rs2TI999xz2r59u5o1a6acnBydOXOmlitFIJs3b9akSZO0bds2ffDBBzp37pwGDRqkU6dOeY6ZNm2aNmzYoDVr1mjz5s06ePCghg4dGsGqcbG0tDQtXLhQO3bs0D//+U/deOONGjJkiPbs2SOJZ9goGKAOWLRokcnMzPR8fuaZZ0xiYqI5e/asZ9usWbNMp06dIlEegrBq1SqTkJBQafs777xjoqKiTHFxsWfbs88+a+x2u9fzRWT17t3bTJo0yfPZ4XCYNm3amAULFkSwKgRLklm/fr3ns9PpNKmpqeapp57ybPvxxx+NzWYzr7zySgQqRLAOHz5sJJnNmzcbY1zPrWnTpmbNmjWeY/bu3Wskma1bt0aqTAQhMTHRvPDCCzzDRoKRKtQJJ06cUFJSkufz1q1bdf3118tqtXq25eTkaN++fTp+/HgkSkQ1bd26Vd26dVOrVq0823JyclRaWur5P3iIrPLycu3YsUMDBw70bIuKitLAgQO1devWCFaG6tq/f7+Ki4u9nmlCQoKuu+46nmkdd+LECUny/J24Y8cOnTt3zutZdu7cWe3ateNZ1lEOh0OvvvqqTp06paysLJ5hI0GoQsR9++23Wr58ue655x7PtuLiYq//CJfk+VxcXFyr9SE8PMu678iRI3I4HD6fE8+ofnI/N55p/eJ0OjV16lT17dtXV199tSTXs7RarZXmrPIs654vv/xSzZs3l81m0/jx47V+/Xp17dqVZ9hIEKpQYx588EFZLJaAX19//bXXOYWFhbrppps0YsQI3X333RGqHBerzrMEAIRn0qRJ2r17t1599dVIl4Jq6NSpk3bu3Knt27drwoQJys3N1VdffRXpslBLmkS6ADQcM2bM0OjRowMec/nll3u+P3jwoPr3768+ffpUakCRmppaqSuO+3NqamrNFAy/Qn2WgaSmplbqIsezrFtatGih6Ohon//M8YzqJ/dzO3TokFq3bu3ZfujQIV177bURqgqB3HvvvXrrrbf00UcfKS0tzbM9NTVV5eXl+vHHH71GOvjns+6xWq264oorJEk9evTQp59+qqVLl+rf/u3feIaNAKEKNSYlJUUpKSlBHVtYWKj+/furR48eWrVqlaKivAdNs7Ky9PDDD+vcuXNq2rSpJOmDDz5Qp06dlJiYWOO1w1soz7IqWVlZevzxx3X48GG1bNlSkutZ2u12de3atUbugfBYrVb16NFDGzdu1K233irJ9RrSxo0bde+990a2OFRLZmamUlNTtXHjRk+IKi0t9fwfdNQdxhhNnjxZ69evV35+vjIzM7329+jRQ02bNtXGjRs1bNgwSdK+fft04MABZWVlRaJkBMnpdOrs2bM8w0aCUIVaV1hYqOzsbLVv315/+MMfVFJS4tnn/j82d955p+bNm6exY8dq1qxZ2r17t5YuXarFixdHqmz4ceDAAR07dkwHDhyQw+HQzp07JUlXXHGFmjdvrkGDBqlr16666667tGjRIhUXF+v3v/+9Jk2aJJvNFtni4TF9+nTl5uaqZ8+e6t27t5YsWaJTp07pd7/7XaRLgx8nT57Ut99+6/m8f/9+7dy5U0lJSWrXrp2mTp2q+fPnq2PHjsrMzNQjjzyiNm3aeIIz6oZJkyZp9erVevPNNxUfH++ZY5OQkKDY2FglJCRo7Nixmj59upKSkmS32zV58mRlZWXpF7/4RYSrh9vs2bN18803q127diorK9Pq1auVn5+v9957j2fYWES6/SAan1WrVhlJPr8q+uKLL8wvf/lLY7PZTNu2bc3ChQsjVDECyc3N9fksN23a5DmmoKDA3HzzzSY2Nta0aNHCzJgxw5w7dy5yRcOn5cuXm3bt2hmr1Wp69+5ttm3bFumSEMCmTZt8/rOXm5trjHG1VX/kkUdMq1atjM1mMwMGDDD79u2LbNGoxN/fh6tWrfIc89NPP5mJEyeaxMREExcXZ2677TZTVFQUuaJRyZgxY0z79u2N1Wo1KSkpZsCAAeb999/37OcZNnwWY4ypzRAHAAAAAA0J3f8AAAAAIAyEKgAAAAAIA6EKAAAAAMJAqAIAAACAMBCqAAAAACAMhCoAAAAACAOhCgAAAADCQKgCAAAAgDAQqgAA8CM/P18Wi0U//vhj2NfKyMjQkiVLqjzO4XBo4cKF6ty5s2JjY5WUlKTrrrtOL7zwgueY0aNHy2KxaOHChV7nvvHGG7JYLJXq9/VVXFzst4b77rtPPXr0kM1m07XXXhvyzwoAjU2TSBcAAAB+Nm/ePD3//PP605/+pJ49e6q0tFT//Oc/dfz4ca/jYmJi9OSTT+qee+5RYmJiwGvu27dPdrvda1vLli0DnjNmzBht375du3btqt4PAgCNCCNVANDIOZ1OLVq0SFdccYVsNpvatWunxx9/3LP/yy+/1I033qjY2FglJydr3LhxOnnypGf/6NGjdeutt+qJJ55Qq1atdNlll+mxxx7T+fPnNXPmTCUlJSktLU2rVq3ynFNQUCCLxaJXX31Vffr0UUxMjK6++mpt3rzZq7bNmzerd+/estlsat26tR588EGdP3/es3/t2rXq1q2bp7aBAwfq1KlTkqRPP/1Uv/rVr9SiRQslJCTohhtu0GeffeZ1fYvFohdeeEG33Xab4uLi1LFjR/3973/31Ni/f39JUmJioiwWi0aPHu35nS1YsECZmZmKjY1V9+7dtXbtWr+/4+zsbP3rX//StGnTPCNF/vz973/XxIkTNWLECGVmZqp79+4aO3as7r//fq/jBg4cqNTUVC1YsMDvtdxatmyp1NRUr6+oKP//CbBs2TJNmjRJl19+eZXXBgAQqgCg0Zs9e7YWLlyoRx55RF999ZVWr16tVq1aSZJOnTqlnJwcJSYm6tNPP9WaNWv03//937r33nu9rvHhhx/q4MGD+uijj/T0009rzpw5+s1vfqPExERt375d48eP1z333KMffvjB67yZM2dqxowZ+vzzz5WVlaVbbrlFR48elSQVFhZq8ODB6tWrl7744gs9++yz+stf/qL58+dLkoqKinTHHXdozJgx2rt3r/Lz8zV06FAZYyRJZWVlys3N1f/8z/9o27Zt6tixowYPHqyysjKvGubNm6eRI0dq165dGjx4sEaNGqVjx44pPT1d69atk+Qa6SkqKtLSpUslSQsWLNBLL72k5557Tnv27NG0adP029/+tlIodMvLy1NaWpoee+wxFRUVqaioyO/zSE1N1YcffqiSkpKAzy06OlpPPPGEli9fXun3CgCoZQYA0GiVlpYam81m/vznP/vcv3LlSpOYmGhOnjzp2fb222+bqKgoU1xcbIwxJjc317Rv3944HA7PMZ06dTL9+vXzfD5//rxp1qyZeeWVV4wxxuzfv99IMgsXLvQcc+7cOZOWlmaefPJJY4wxDz30kOnUqZNxOp2eY1asWGGaN29uHA6H2bFjh5FkCgoKgvpZHQ6HiY+PNxs2bPBsk2R+//vfez6fPHnSSDLvvvuuMcaYTZs2GUnm+PHjnmPOnDlj4uLizCeffOJ1/bFjx5o77rjD7/3bt29vFi9eXGWde/bsMV26dDFRUVGmW7du5p577jHvvPOO1zG5ublmyJAhxhhjfvGLX5gxY8YYY4xZv369qfhXu7v+Zs2aeX117dq1yjqMMWbOnDmme/fuQR0LAI0ZI1UA0Ijt3btXZ8+e1YABA/zu7969u5o1a+bZ1rdvXzmdTu3bt8+z7aqrrvJ6naxVq1bq1q2b53N0dLSSk5N1+PBhr+tnZWV5vm/SpIl69uypvXv3eu6dlZXl9apc3759dfLkSf3www/q3r27BgwYoG7dumnEiBH685//7DXv6NChQ7r77rvVsWNHJSQkyG636+TJkzpw4IBXDddcc43n+2bNmslut1eqs6Jvv/1Wp0+f1q9+9Ss1b97c8/XSSy/pu+++83ueLxXPHz9+vCSpa9eu2r17t7Zt26YxY8bo8OHDuuWWW/Qf//EfPq/x5JNP6sUXX/T83nzZsmWLdu7c6fl65513QqoTABAYjSoAoBGLjY2tkes0bdrU67PFYvG5zel01sj9JFdQ++CDD/TJJ5/o/fff1/Lly/Xwww9r+/btyszMVG5uro4ePaqlS5eqffv2stlsysrKUnl5eZW1B6rTPZ/s7bffVtu2bb322Wy2kH6GnTt3er6v2EgiKipKvXr1Uq9evTR16lT97W9/01133aWHH35YmZmZXte4/vrrlZOTo9mzZ3vmfF0sMzNTl112WUi1AQCCx0gVADRiHTt2VGxsrDZu3Ohzf5cuXfTFF194mj9I0scff6yoqCh16tQp7Ptv27bN8/358+e1Y8cOdenSxXPvrVu3euZIue8dHx+vtLQ0Sa4A1LdvX82bN0+ff/65rFar1q9f7zn2vvvu0+DBg3XVVVfJZrPpyJEjIdVntVoludqcu3Xt2lU2m00HDhzQFVdc4fWVnp4e8FoVryPJ69xA3fi6du0qSV7PoaKFCxdqw4YN2rp1a9A/GwCg5jBSBQCNWExMjGbNmqUHHnhAVqtVffv2VUlJifbs2aOxY8dq1KhRmjNnjnJzczV37lyVlJRo8uTJuuuuuzzNLMKxYsUKdezYUV26dNHixYt1/PhxjRkzRpI0ceJELVmyRJMnT9a9996rffv2ac6cOZo+fbqioqK0fft2bdy4UYMGDVLLli21fft2lZSUeEJZx44d9de//tXTlnzmzJkhj8y1b99eFotFb731lgYPHqzY2FjFx8fr/vvv17Rp0+R0OvXLX/5SJ06c0Mcffyy73a7c3Fyf18rIyNBHH32k22+/XTabTS1atPB53PDhw9W3b1/16dNHqamp2r9/v2bPnq0rr7xSnTt39nlOt27dNGrUKC1btszn/sOHD+vMmTNe25KTkyuN0rl9++23OnnypIqLi/XTTz95RtS6du3qCZoAgAoiPakLABBZDofDzJ8/37Rv3940bdrUtGvXzjzxxBOe/bt27TL9+/c3MTExJikpydx9992mrKzMs79i0wS3G264wUyZMsVrW8VGDe5GFatXrza9e/c2VqvVdO3a1Xz44Yde5+Tn55tevXoZq9VqUlNTzaxZs8y5c+eMMcZ89dVXJicnx6SkpBibzWauvPJKs3z5cs+5n332menZs6eJiYkxHTt2NGvWrKnULEKSWb9+vdc9ExISzKpVqzyfH3vsMZOammosFovJzc01xhjjdDrNkiVLTKdOnUzTpk1NSkqKycnJMZs3b/b7e966dau55pprjM1mM4H++l25cqXp37+/SUlJMVar1bRr186MHj3aqyGHr9/5/v37jdVq9dmowtfX1q1b/dZwww03+Dxn//79fs8BgMbMYkyF9yoAAKgFBQUFyszM1Oeff65rr7020uUAABAW5lQBAAAAQBgIVQAAAAAQBl7/AwAAAIAwMFIFAAAAAGEgVAEAAABAGAhVAAAAABAGQhUAAAAAhIFQBQAAAABhIFQBAAAAQBgIVQAAAAAQBkIVAAAAAISBUAUAAAAAYfj/HBBpbF341n4AAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "for label in unique_label_dict:\n",
    "    indices = np.where(genes_labels == unique_label_dict[label])\n",
    "    plt.scatter(reduced_data_tsne[indices, 0], reduced_data_tsne[indices, 1], c=colors[unique_label_dict[label]], label=label)\n",
    "\n",
    "plt.xlabel('composante t-SNE 1')\n",
    "plt.ylabel('composante t-SNE 2')\n",
    "plt.title('Utilisation de la méthode t-SNE pour afficher les différents clusters')\n",
    "plt.legend()\n",
    "\n",
    "plt.xlim(reduced_data_tsne[:, 0].min() - 2, reduced_data_tsne[:, 0].max() + 2)\n",
    "plt.ylim(reduced_data_tsne[:, 1].min() - 2, reduced_data_tsne[:, 1].max() + 2)\n",
    "\n",
    "plt.savefig('../images_rapport/TSNE_cluster.png', bbox_inches='tight')\n",
    "\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}