{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "150df1b9-484d-4418-9dca-745823f883f2",
   "metadata": {},
   "source": [
    "# Results"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5bf68654-b830-4040-ac24-e772f8cdd3b7",
   "metadata": {},
   "source": [
    "## Data Loading"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "0f9893d9-828b-4492-9c22-2e3a714d774c",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [],
   "source": [
    "suppressWarnings(suppressMessages(library(\"tidyverse\")))\n",
    "suppressWarnings(suppressMessages(library(\"ggpubr\")))\n",
    "suppressWarnings(suppressMessages(library(\"rstatix\")))\n",
    "suppressWarnings(suppressMessages(library(\"plyr\")))\n",
    "\n",
    "library(tidyverse)\n",
    "library(ggpubr)\n",
    "library(rstatix)\n",
    "library(plyr)\n",
    "\n",
    "map_abb <- list(\"df\"=\"DF\", \"gm\"=\"GM\",\"wm\"=\"WM\", \"csf\"=\"CSF\")\n",
    "\n",
    "df_eval <- list(\"crossval\"= data.frame(), \"test\"= data.frame())\n",
    "\n",
    "\n",
    "for (evaluation in names(df_eval)){\n",
    "    for (mod in names(map_abb)){\n",
    "\n",
    "      filename <- sprintf(\"%s_%s.csv\", mod, evaluation)\n",
    "      path_col <- file.path(getwd(), \"..\", \"..\", \"..\", \"resources\", filename)\n",
    "      \n",
    "      df_mod <- read.csv(path_col)\n",
    "      df_mod$modality <- map_abb[[mod]]\n",
    "\n",
    "      df_eval[[evaluation]] <- rbind(df_eval[[evaluation]], df_mod)\n",
    "    }\n",
    "}\n",
    "\n",
    "df_val <- df_eval[[\"crossval\"]]\n",
    "df_test <- df_eval[[\"test\"]]\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "810ab79f-9767-4ed6-a5cd-3b1e60a5975c",
   "metadata": {},
   "source": [
    "#### Validation data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5ab0f65c-048c-4b4b-85d5-1bb1cb390570",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A data.frame: 6 × 4</caption>\n",
       "<thead>\n",
       "\t<tr><th></th><th scope=col>fold</th><th scope=col>MAE</th><th scope=col>r2</th><th scope=col>modality</th></tr>\n",
       "\t<tr><th></th><th scope=col>&lt;int&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><th scope=row>1</th><td>0</td><td>4.910286</td><td>0.8573168</td><td>DF</td></tr>\n",
       "\t<tr><th scope=row>2</th><td>1</td><td>4.177728</td><td>0.7937252</td><td>DF</td></tr>\n",
       "\t<tr><th scope=row>3</th><td>2</td><td>6.336831</td><td>0.7525602</td><td>DF</td></tr>\n",
       "\t<tr><th scope=row>4</th><td>3</td><td>6.220759</td><td>0.7729788</td><td>DF</td></tr>\n",
       "\t<tr><th scope=row>5</th><td>4</td><td>5.494937</td><td>0.7465731</td><td>DF</td></tr>\n",
       "\t<tr><th scope=row>6</th><td>5</td><td>6.471542</td><td>0.7765924</td><td>DF</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A data.frame: 6 × 4\n",
       "\\begin{tabular}{r|llll}\n",
       "  & fold & MAE & r2 & modality\\\\\n",
       "  & <int> & <dbl> & <dbl> & <chr>\\\\\n",
       "\\hline\n",
       "\t1 & 0 & 4.910286 & 0.8573168 & DF\\\\\n",
       "\t2 & 1 & 4.177728 & 0.7937252 & DF\\\\\n",
       "\t3 & 2 & 6.336831 & 0.7525602 & DF\\\\\n",
       "\t4 & 3 & 6.220759 & 0.7729788 & DF\\\\\n",
       "\t5 & 4 & 5.494937 & 0.7465731 & DF\\\\\n",
       "\t6 & 5 & 6.471542 & 0.7765924 & DF\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A data.frame: 6 × 4\n",
       "\n",
       "| <!--/--> | fold &lt;int&gt; | MAE &lt;dbl&gt; | r2 &lt;dbl&gt; | modality &lt;chr&gt; |\n",
       "|---|---|---|---|---|\n",
       "| 1 | 0 | 4.910286 | 0.8573168 | DF |\n",
       "| 2 | 1 | 4.177728 | 0.7937252 | DF |\n",
       "| 3 | 2 | 6.336831 | 0.7525602 | DF |\n",
       "| 4 | 3 | 6.220759 | 0.7729788 | DF |\n",
       "| 5 | 4 | 5.494937 | 0.7465731 | DF |\n",
       "| 6 | 5 | 6.471542 | 0.7765924 | DF |\n",
       "\n"
      ],
      "text/plain": [
       "  fold MAE      r2        modality\n",
       "1 0    4.910286 0.8573168 DF      \n",
       "2 1    4.177728 0.7937252 DF      \n",
       "3 2    6.336831 0.7525602 DF      \n",
       "4 3    6.220759 0.7729788 DF      \n",
       "5 4    5.494937 0.7465731 DF      \n",
       "6 5    6.471542 0.7765924 DF      "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "head(df_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "9440a41c-2a9d-44f6-86c1-1c4176249b7f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A data.frame: 4 × 3</caption>\n",
       "<thead>\n",
       "\t<tr><th scope=col>Group.1</th><th scope=col>r2</th><th scope=col>MAE</th></tr>\n",
       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><td>CSF</td><td>0.7068463</td><td>6.609508</td></tr>\n",
       "\t<tr><td>DF </td><td>0.7616746</td><td>5.843714</td></tr>\n",
       "\t<tr><td>GM </td><td>0.7508428</td><td>6.140916</td></tr>\n",
       "\t<tr><td>WM </td><td>0.7235893</td><td>6.501720</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A data.frame: 4 × 3\n",
       "\\begin{tabular}{lll}\n",
       " Group.1 & r2 & MAE\\\\\n",
       " <chr> & <dbl> & <dbl>\\\\\n",
       "\\hline\n",
       "\t CSF & 0.7068463 & 6.609508\\\\\n",
       "\t DF  & 0.7616746 & 5.843714\\\\\n",
       "\t GM  & 0.7508428 & 6.140916\\\\\n",
       "\t WM  & 0.7235893 & 6.501720\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A data.frame: 4 × 3\n",
       "\n",
       "| Group.1 &lt;chr&gt; | r2 &lt;dbl&gt; | MAE &lt;dbl&gt; |\n",
       "|---|---|---|\n",
       "| CSF | 0.7068463 | 6.609508 |\n",
       "| DF  | 0.7616746 | 5.843714 |\n",
       "| GM  | 0.7508428 | 6.140916 |\n",
       "| WM  | 0.7235893 | 6.501720 |\n",
       "\n"
      ],
      "text/plain": [
       "  Group.1 r2        MAE     \n",
       "1 CSF     0.7068463 6.609508\n",
       "2 DF      0.7616746 5.843714\n",
       "3 GM      0.7508428 6.140916\n",
       "4 WM      0.7235893 6.501720"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "aggregate(df_val[,c(\"r2\", \"MAE\")], list(df_val$modality), mean)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f00eac70-db09-46c8-ba98-0fc27d36d891",
   "metadata": {},
   "source": [
    "#### Test data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "3b576a4f-ddcd-4543-bebc-34de4ddcd0ce",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A data.frame: 6 × 5</caption>\n",
       "<thead>\n",
       "\t<tr><th></th><th scope=col>subjectID</th><th scope=col>gender</th><th scope=col>age</th><th scope=col>y_hat</th><th scope=col>modality</th></tr>\n",
       "\t<tr><th></th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;int&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><th scope=row>1</th><td>sub-517</td><td>0</td><td>36.16</td><td>40.94362</td><td>DF</td></tr>\n",
       "\t<tr><th scope=row>2</th><td>sub-303</td><td>0</td><td>25.46</td><td>37.59454</td><td>DF</td></tr>\n",
       "\t<tr><th scope=row>3</th><td>sub-232</td><td>1</td><td>28.81</td><td>35.01436</td><td>DF</td></tr>\n",
       "\t<tr><th scope=row>4</th><td>sub-462</td><td>1</td><td>75.08</td><td>67.79715</td><td>DF</td></tr>\n",
       "\t<tr><th scope=row>5</th><td>sub-331</td><td>0</td><td>23.49</td><td>30.64490</td><td>DF</td></tr>\n",
       "\t<tr><th scope=row>6</th><td>sub-294</td><td>1</td><td>27.08</td><td>29.80392</td><td>DF</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A data.frame: 6 × 5\n",
       "\\begin{tabular}{r|lllll}\n",
       "  & subjectID & gender & age & y\\_hat & modality\\\\\n",
       "  & <chr> & <int> & <dbl> & <dbl> & <chr>\\\\\n",
       "\\hline\n",
       "\t1 & sub-517 & 0 & 36.16 & 40.94362 & DF\\\\\n",
       "\t2 & sub-303 & 0 & 25.46 & 37.59454 & DF\\\\\n",
       "\t3 & sub-232 & 1 & 28.81 & 35.01436 & DF\\\\\n",
       "\t4 & sub-462 & 1 & 75.08 & 67.79715 & DF\\\\\n",
       "\t5 & sub-331 & 0 & 23.49 & 30.64490 & DF\\\\\n",
       "\t6 & sub-294 & 1 & 27.08 & 29.80392 & DF\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A data.frame: 6 × 5\n",
       "\n",
       "| <!--/--> | subjectID &lt;chr&gt; | gender &lt;int&gt; | age &lt;dbl&gt; | y_hat &lt;dbl&gt; | modality &lt;chr&gt; |\n",
       "|---|---|---|---|---|---|\n",
       "| 1 | sub-517 | 0 | 36.16 | 40.94362 | DF |\n",
       "| 2 | sub-303 | 0 | 25.46 | 37.59454 | DF |\n",
       "| 3 | sub-232 | 1 | 28.81 | 35.01436 | DF |\n",
       "| 4 | sub-462 | 1 | 75.08 | 67.79715 | DF |\n",
       "| 5 | sub-331 | 0 | 23.49 | 30.64490 | DF |\n",
       "| 6 | sub-294 | 1 | 27.08 | 29.80392 | DF |\n",
       "\n"
      ],
      "text/plain": [
       "  subjectID gender age   y_hat    modality\n",
       "1 sub-517   0      36.16 40.94362 DF      \n",
       "2 sub-303   0      25.46 37.59454 DF      \n",
       "3 sub-232   1      28.81 35.01436 DF      \n",
       "4 sub-462   1      75.08 67.79715 DF      \n",
       "5 sub-331   0      23.49 30.64490 DF      \n",
       "6 sub-294   1      27.08 29.80392 DF      "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "head(df_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "41a46de7-b69b-4496-91da-f8bc405eb3ad",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A data.frame: 4 × 4</caption>\n",
       "<thead>\n",
       "\t<tr><th scope=col>Group.1</th><th scope=col>age</th><th scope=col>y_hat</th><th scope=col>abs_diff</th></tr>\n",
       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><td>CSF</td><td>42.37309</td><td>49.54023</td><td>9.124851</td></tr>\n",
       "\t<tr><td>DF </td><td>42.37309</td><td>46.25928</td><td>7.096847</td></tr>\n",
       "\t<tr><td>GM </td><td>42.37309</td><td>45.49686</td><td>7.956941</td></tr>\n",
       "\t<tr><td>WM </td><td>42.37309</td><td>37.31041</td><td>9.990654</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A data.frame: 4 × 4\n",
       "\\begin{tabular}{llll}\n",
       " Group.1 & age & y\\_hat & abs\\_diff\\\\\n",
       " <chr> & <dbl> & <dbl> & <dbl>\\\\\n",
       "\\hline\n",
       "\t CSF & 42.37309 & 49.54023 & 9.124851\\\\\n",
       "\t DF  & 42.37309 & 46.25928 & 7.096847\\\\\n",
       "\t GM  & 42.37309 & 45.49686 & 7.956941\\\\\n",
       "\t WM  & 42.37309 & 37.31041 & 9.990654\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A data.frame: 4 × 4\n",
       "\n",
       "| Group.1 &lt;chr&gt; | age &lt;dbl&gt; | y_hat &lt;dbl&gt; | abs_diff &lt;dbl&gt; |\n",
       "|---|---|---|---|\n",
       "| CSF | 42.37309 | 49.54023 | 9.124851 |\n",
       "| DF  | 42.37309 | 46.25928 | 7.096847 |\n",
       "| GM  | 42.37309 | 45.49686 | 7.956941 |\n",
       "| WM  | 42.37309 | 37.31041 | 9.990654 |\n",
       "\n"
      ],
      "text/plain": [
       "  Group.1 age      y_hat    abs_diff\n",
       "1 CSF     42.37309 49.54023 9.124851\n",
       "2 DF      42.37309 46.25928 7.096847\n",
       "3 GM      42.37309 45.49686 7.956941\n",
       "4 WM      42.37309 37.31041 9.990654"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_test[\"abs_diff\"] <- abs(df_test$y_hat - df_test$age)\n",
    "\n",
    "result_mean <- aggregate(df_test[,c(\"age\", \"y_hat\", \"abs_diff\")], list(df_test$modality), mean)\n",
    "result_mean"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "99dcb8ad-54f6-4ab9-af98-1ca88031fc47",
   "metadata": {},
   "source": [
    "## Statistics"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2256d6b4-a619-461f-998e-3757dcc1357c",
   "metadata": {},
   "source": [
    "### Repeated Measures ANOVA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "b7636ae2-8422-4ab1-beec-3f6280996b01",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A anova_test: 1 × 7</caption>\n",
       "<thead>\n",
       "\t<tr><th></th><th scope=col>Effect</th><th scope=col>DFn</th><th scope=col>DFd</th><th scope=col>F</th><th scope=col>p</th><th scope=col>p&lt;.05</th><th scope=col>ges</th></tr>\n",
       "\t<tr><th></th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;dbl&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><th scope=row>1</th><td>modality</td><td>3</td><td>87</td><td>5.701</td><td>0.001</td><td>*</td><td>0.06</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A anova\\_test: 1 × 7\n",
       "\\begin{tabular}{r|lllllll}\n",
       "  & Effect & DFn & DFd & F & p & p<.05 & ges\\\\\n",
       "  & <chr> & <dbl> & <dbl> & <dbl> & <dbl> & <chr> & <dbl>\\\\\n",
       "\\hline\n",
       "\t1 & modality & 3 & 87 & 5.701 & 0.001 & * & 0.06\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A anova_test: 1 × 7\n",
       "\n",
       "| <!--/--> | Effect &lt;chr&gt; | DFn &lt;dbl&gt; | DFd &lt;dbl&gt; | F &lt;dbl&gt; | p &lt;dbl&gt; | p&lt;.05 &lt;chr&gt; | ges &lt;dbl&gt; |\n",
       "|---|---|---|---|---|---|---|---|\n",
       "| 1 | modality | 3 | 87 | 5.701 | 0.001 | * | 0.06 |\n",
       "\n"
      ],
      "text/plain": [
       "  Effect   DFn DFd F     p     p<.05 ges \n",
       "1 modality 3   87  5.701 0.001 *     0.06"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_val$modality <- factor(df_val$modality)\n",
    "\n",
    "res.aov <- anova_test(data = df_val, dv = MAE, wid = fold, within = modality)\n",
    "get_anova_table(res.aov)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6ce7d091-63e5-4a29-adef-431c129ab669",
   "metadata": {},
   "source": [
    "#### Post-hoc analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "82cab361-ea82-435f-b3f7-d9225e8d609a",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A rstatix_test: 6 × 14</caption>\n",
       "<thead>\n",
       "\t<tr><th scope=col>.y.</th><th scope=col>group1</th><th scope=col>group2</th><th scope=col>n1</th><th scope=col>n2</th><th scope=col>statistic</th><th scope=col>df</th><th scope=col>p</th><th scope=col>p.adj</th><th scope=col>p.adj.signif</th><th scope=col>y.position</th><th scope=col>groups</th><th scope=col>xmin</th><th scope=col>xmax</th></tr>\n",
       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;int&gt;</th><th scope=col>&lt;int&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;named list&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><td>MAE</td><td>CSF</td><td>DF</td><td>30</td><td>30</td><td> 4.4361533</td><td>29</td><td>0.000121</td><td>0.000726</td><td>***</td><td> 9.418840</td><td>CSF, DF </td><td>1</td><td>2</td></tr>\n",
       "\t<tr><td>MAE</td><td>CSF</td><td>GM</td><td>30</td><td>30</td><td> 2.0552780</td><td>29</td><td>0.049000</td><td>0.294000</td><td>ns </td><td> 9.621448</td><td>CSF, GM </td><td>1</td><td>3</td></tr>\n",
       "\t<tr><td>MAE</td><td>CSF</td><td>WM</td><td>30</td><td>30</td><td> 0.4207693</td><td>29</td><td>0.677000</td><td>1.000000</td><td>ns </td><td> 9.824056</td><td>CSF, WM </td><td>1</td><td>4</td></tr>\n",
       "\t<tr><td>MAE</td><td>DF </td><td>GM</td><td>30</td><td>30</td><td>-1.5010999</td><td>29</td><td>0.144000</td><td>0.864000</td><td>ns </td><td>10.026664</td><td>DF, GM</td><td>2</td><td>3</td></tr>\n",
       "\t<tr><td>MAE</td><td>DF </td><td>WM</td><td>30</td><td>30</td><td>-3.4434066</td><td>29</td><td>0.002000</td><td>0.011000</td><td>*  </td><td>10.229272</td><td>DF, WM</td><td>2</td><td>4</td></tr>\n",
       "\t<tr><td>MAE</td><td>GM </td><td>WM</td><td>30</td><td>30</td><td>-1.9403815</td><td>29</td><td>0.062000</td><td>0.373000</td><td>ns </td><td>10.431880</td><td>GM, WM</td><td>3</td><td>4</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A rstatix\\_test: 6 × 14\n",
       "\\begin{tabular}{llllllllllllll}\n",
       " .y. & group1 & group2 & n1 & n2 & statistic & df & p & p.adj & p.adj.signif & y.position & groups & xmin & xmax\\\\\n",
       " <chr> & <chr> & <chr> & <int> & <int> & <dbl> & <dbl> & <dbl> & <dbl> & <chr> & <dbl> & <named list> & <dbl> & <dbl>\\\\\n",
       "\\hline\n",
       "\t MAE & CSF & DF & 30 & 30 &  4.4361533 & 29 & 0.000121 & 0.000726 & *** &  9.418840 & CSF, DF  & 1 & 2\\\\\n",
       "\t MAE & CSF & GM & 30 & 30 &  2.0552780 & 29 & 0.049000 & 0.294000 & ns  &  9.621448 & CSF, GM  & 1 & 3\\\\\n",
       "\t MAE & CSF & WM & 30 & 30 &  0.4207693 & 29 & 0.677000 & 1.000000 & ns  &  9.824056 & CSF, WM  & 1 & 4\\\\\n",
       "\t MAE & DF  & GM & 30 & 30 & -1.5010999 & 29 & 0.144000 & 0.864000 & ns  & 10.026664 & DF, GM & 2 & 3\\\\\n",
       "\t MAE & DF  & WM & 30 & 30 & -3.4434066 & 29 & 0.002000 & 0.011000 & *   & 10.229272 & DF, WM & 2 & 4\\\\\n",
       "\t MAE & GM  & WM & 30 & 30 & -1.9403815 & 29 & 0.062000 & 0.373000 & ns  & 10.431880 & GM, WM & 3 & 4\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A rstatix_test: 6 × 14\n",
       "\n",
       "| .y. &lt;chr&gt; | group1 &lt;chr&gt; | group2 &lt;chr&gt; | n1 &lt;int&gt; | n2 &lt;int&gt; | statistic &lt;dbl&gt; | df &lt;dbl&gt; | p &lt;dbl&gt; | p.adj &lt;dbl&gt; | p.adj.signif &lt;chr&gt; | y.position &lt;dbl&gt; | groups &lt;named list&gt; | xmin &lt;dbl&gt; | xmax &lt;dbl&gt; |\n",
       "|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n",
       "| MAE | CSF | DF | 30 | 30 |  4.4361533 | 29 | 0.000121 | 0.000726 | *** |  9.418840 | CSF, DF  | 1 | 2 |\n",
       "| MAE | CSF | GM | 30 | 30 |  2.0552780 | 29 | 0.049000 | 0.294000 | ns  |  9.621448 | CSF, GM  | 1 | 3 |\n",
       "| MAE | CSF | WM | 30 | 30 |  0.4207693 | 29 | 0.677000 | 1.000000 | ns  |  9.824056 | CSF, WM  | 1 | 4 |\n",
       "| MAE | DF  | GM | 30 | 30 | -1.5010999 | 29 | 0.144000 | 0.864000 | ns  | 10.026664 | DF, GM | 2 | 3 |\n",
       "| MAE | DF  | WM | 30 | 30 | -3.4434066 | 29 | 0.002000 | 0.011000 | *   | 10.229272 | DF, WM | 2 | 4 |\n",
       "| MAE | GM  | WM | 30 | 30 | -1.9403815 | 29 | 0.062000 | 0.373000 | ns  | 10.431880 | GM, WM | 3 | 4 |\n",
       "\n"
      ],
      "text/plain": [
       "  .y. group1 group2 n1 n2 statistic  df p        p.adj    p.adj.signif\n",
       "1 MAE CSF    DF     30 30  4.4361533 29 0.000121 0.000726 ***         \n",
       "2 MAE CSF    GM     30 30  2.0552780 29 0.049000 0.294000 ns          \n",
       "3 MAE CSF    WM     30 30  0.4207693 29 0.677000 1.000000 ns          \n",
       "4 MAE DF     GM     30 30 -1.5010999 29 0.144000 0.864000 ns          \n",
       "5 MAE DF     WM     30 30 -3.4434066 29 0.002000 0.011000 *           \n",
       "6 MAE GM     WM     30 30 -1.9403815 29 0.062000 0.373000 ns          \n",
       "  y.position groups   xmin xmax\n",
       "1  9.418840  CSF, DF  1    2   \n",
       "2  9.621448  CSF, GM  1    3   \n",
       "3  9.824056  CSF, WM  1    4   \n",
       "4 10.026664  DF, GM   2    3   \n",
       "5 10.229272  DF, WM   2    4   \n",
       "6 10.431880  GM, WM   3    4   "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "pwc <- df_val %>%\n",
    "  pairwise_t_test(\n",
    "    MAE ~ modality, paired = TRUE,\n",
    "    p.adjust.method = \"bonferroni\"\n",
    "  )\n",
    "pwc <- pwc %>% add_xy_position(x = \"modality\")\n",
    "pwc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d7e5cd96-61b2-41b5-90fc-3da3633609f1",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Warning message in if (fill %in% names(data) & is.null(add.params$fill)) add.params$fill <- fill:\n",
      "“the condition has length > 1 and only the first element will be used”\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAAJYCAIAAADXJFGjAAAACXBIWXMAABJ0AAASdAHeZh94\nAAAgAElEQVR4nOzdd1xT1/sH8CdA2FtQECeCigNFVMBVR8W9xbrFVetW3KPVujeOal1YXHUL\n7oGzuC11YFGrgigIigrIXsnvj/Pt/aVJiAmQ3BA+7z98Xc499+bJ5RKfnHuGQCwWEwAAAACU\nfnp8BwAAAAAAJQOJHQAAAICOQGIHAAAAoCOQ2AEAAADoCCR2AAAAADoCiR0AAACAjkBiBwAA\nAKAjkNgBAAAA6AgkdgAAAAA6AokdAADooNu3b/ft29fBwUEoFNrZ2XXs2PHMmTN8BwWgdgIs\nKQYAADrm119/nTBhgkgksrOzq169emxs7IcPH4hoyZIl8+bN4zs6ADVCYgcAADolKiqqQYMG\n+fn5K1asmD59ur6+vkgkWrly5dy5c/X19Z89e+bi4sJ3jADqgkexAACgU3bt2pWfn9+9e/dZ\ns2bp6+sTkZ6e3pw5c5o0aVJQUHD27Fm+AwRQIwO+AwAAAChJbdu2tbCwaN26tVR5w4YN79+/\nn5iYyEdQABqCxA4AAHRK586dO3fuLFv+8eNHInJ0dNR4RACagz52AACg+xITE52dnfPy8l68\neFGtWjW+wwFQF/SxAwAAHVdQUDB8+PCsrKxx48YhqwPdhhY7AADQZTk5OYMGDTp27Ji3t/e1\na9eMjIz4jghAjdDHDgAAdFZKSkrPnj2vX7/evHnzM2fOIKsDnYdHsaAtfv/9d4FAIBAIFi9e\nzHcsJWPbtm3sHa1Zs4bvWADKotjY2ObNm1+/fr1Hjx5hYWFWVlZ8RwSgfuIyqWnTptwVePbs\nGd/hlGJDhw5V6X6rV6+e3PPcunWLfZP28/OT2pWfn3/kyBE/Pz9nZ2dTU1O2OlDz5s3nzZv3\n8uXLooVdUFBw4sSJ/v37u7i4mJmZCYVCe3v7Fi1aLFiwIDY2Vrb+qVOnlH+PNWrU4A4cP348\nEenp6YWGhhYt1BJ38eJFZd6Fp6enkics8sUpg549ezZr1qwGDRqUK1fOyMiocuXKHTt2DAoK\nys3N1fw5ixlMeHi4s7Mz+7UeOXKkyPGrT2xsbKVKlYho0qRJBQUFfIfzH1p1J4jF4hs3bowY\nMcLV1dXU1NTExMTFxWXYsGE3btwocjDAo7KY2D148EDyf5qAgAC+IyrF6tevr/x/6kQ0ZMgQ\n2ZOkpKRUrVqViCpXrpySkiK569mzZw0bNizsbEKhcMmSJarGHBsb6+PjU9g5jY2N165dK3VI\nkXOX7OzsevXqEZGNjc2bN29UDVUdDh8+rMy7QGJX4pYvX25oaCj3sjRs2PDFixeaPGdxgsnJ\nyZk5c6ae3v8/8NHCxC4pKalWrVpEtGjRIr5jkaZVd0J2dvb3339f2B/s+PHjRSJRMd4r8KAs\n9rH79ddf2Yadnd3Hjx937969bNkydLwoguzs7KdPn7LtSZMmCYXCrx7SsWNH2cJJkybFxsYS\nUVBQkOSzEvYY5dOnT0RkbGzcs2fPmjVrWllZvX379vTp0y9fvszLy5s/f75QKJw5c6aSMaem\nprZp0yY6OpqIqlSpMnHiRDc3N1tb23fv3p09e3b37t3Z2dnTpk0TCARTp07ljqpZs+aCBQsU\nnzk5OXnjxo1ExJJUxsjIaM+ePY0bN05OTh4xYkRYWJiScapPSkoK2+jcuXOTJk0Kq1axYkUl\nT1jki1OmrF27ds6cOWy7Xbt2bdu2tbS0fP369aFDh+Li4h4+fNihQ4e7d+/a2dlp4JzFCebR\no0dDhgyJjIwkIkNDw9zcXFUvhWYMHjz4+fPnM2bM+PHHH/mO5T+06k4Qi8X+/v4HDx4kIgsL\ni379+tWvXz8rK+vu3bunTp0qKCjYvHmzvb39V//AQbvwnVlq2pcvX8zNzYmofv363F/C/v37\n+Y6rVLp37x67gA4ODkU+ya1btwQCARF169ZNalfXrl3Z+b29vRMSEiR35efnT5o0ie01NjaW\naudTgEsB27Vrl52dLbX35MmTbK+JiUlSUpJKb2TYsGFEJBQKIyMjpXaNHDmSnfbYsWMqnVMd\nVq1axYIJDg7W2IsquDhlQXR0NPvaIxQKpR7KZ2Rk9OjRg/1GRo8erYFzFieYjRs3smYhIyOj\ndevWcT0xtK3F7tChQ0TUpEmT/Px8vmP5D626E8Ri8fbt29nehg0bvn37VnLXpUuXjI2N2e/6\n3bt3qrxL4FmZS+y2bNnC7uNFixb99ddfbLtVq1Z8x1Uqbdu2jV3ALl26FPkkLVq0YCd5/Pix\nZHlcXBxL+ArLsfLz82vUqMGODQkJUfLluF5B9+7dk1uhZcuWrMLevXuVfxfnzp1jR/3444+y\ne+Pj49l/hzVr1uS9r8/cuXNZqBrr9qf44pQFo0ePZldg8eLFsntTU1PZWggGBgZyu3iW7DmL\nE4ynpycR1alT5+HDh+J/83X1JXbcg5SsrCyxWBwdHT1jxoy6deuam5ubm5vXq1dvxowZiYmJ\nsgc2b96ciBwdHRvIM3DgQHVEqwytuhMyMzNZwzx7DCJ77KJFi3x9fadMmRIVFaVkMKANylxi\n16BBA/Y3wPrd165dm/349OnTwg7hFhxkX/7u3r3r7+9fo0YNExMTc3Nzd3f32bNnf/jwQcGL\nXrlyZdSoUbVr17ayshIKhRUqVPDx8Zk3b55spyvuSeX27dsVnLBdu3Zyk4+srKzt27d37dq1\natWqpqamBgYGdnZ2LVq0WLx4seIIi2bMmDHF/A/79u3b7Azffvut1K4nT54MHjy4c+fOU6dO\nLexwf39/dviWLVuUfEW2IjgRFdahePLkyayC8r330tLSKleuTEQuLi6yrYDM4MGDNZxOFWbs\n2LEskmvXrmng5ZS5OEXArePOelBFR0dPnz69Tp06lpaWJiYmderUmTdvXnJyckm9XHEUFBSw\nR2DGxsaFhTR//nz2dgIDA9V6zmIG07hx47Fjx2ZmZrIfNZnY7d+/38zMjGRYWVmFh4dLHVi3\nbl3Zmhzl+4+WLK26E8QS3W3L7DcuXVW2ErubN2+y+7hZs2asZOXKlaxEQfbArTmYlpa2du1a\n1owkpVKlSnK/YH358qVbt26Ffb6wxxmS9fft28d2tW/fvrB43r9/z7ITMzOz9PR0rvzhw4cK\nOjCVK1fuypUrKl8yhbjBxUVOVoYPH87OcOjQoSIcPmDAAHb477//ruQh7EE8/dsGIGvChAms\nwpo1a5Q8J/d499y5c4XV+eOPP1gd5Vs3f/vtt8J+m3I1aNBAmdNyF401uqibMhenCNatW8dO\nu3Xr1kOHDllYWMheEBcXl/j4eJVOq45rfvfuXVa5devWhdUJDw9ndRT84ZfIOYsZjNQ9o7HE\n7uDBg+yDt1y5cu3bt+/Zs6dk6mZra1viX1x1/k4Qi8X9+/dn5ZgaQseUrcRuyJAh7D4OCgpi\nJQkJCQYGBuyjobDmBC4zCwoKEggELi4uy5cvDwkJOXjw4MyZM7kvkT179pQ6MD8/n3vOWKFC\nhWXLll27di0iIuLUqVOjRo3imo42bdrEHZKens5OaGBg8PHjR7nxbN68mR04dOhQrvDTp08O\nDg6s3Nvb+9dffw0LC7ty5cquXbtatWrFyi0sLOLi4op1Bf/77kxMTNiZ5Tbjf1Vubq6NjQ0R\nGRsbp6WlqXr4p0+fbG1tiUgoFCrfBcTX15fFfPnyZbkV2EMcIrp586YyJ3z+/Dl7zCp7A0gq\nKChgvyBDQ0MlW5LUlNh16tSJ1X/9+rUy9YtDyYtTBNw4vu+//15fX79ixYozZ87cu3fvoUOH\nZs6cySUEnTp1Uum06rjmQUFBrPKMGTMKq5OVlcUSFyW7qxb5nCUbjMYSO1NTU1NT0507d0r2\nmTt79iz3PU3B2ykanb8TxGIxa0qXLPz8+fODBw/Cw8NfvHiBwbClVxkaFfv58+cjR44Qkbm5\neb9+/Vihg4ND586dT548+fnz56NHjw4aNEj2QG5U/9SpU7t3737o0CHu4+a7777z9fX99ttv\niejUqVMpKSnW1tbcgRs3brxx4wYR1a5dOzw8nBuR1KhRo65du3bt2rVXr15isXjWrFl9+vRh\n3SDMzMx69Ojx+++/5+fnh4SEjBo1SjYeNoKJiLg8lYi2bNmSmJhIRM2aNbt69arkuHd/f//e\nvXuHhoampaWtX79+9erVRbl8Mp4+fZqVlUVE9vb2bLIoVd27dy85OZmIWrRowX1AK+nZs2fD\nhg37/PkzEc2aNYtdPWUEBASwidxmzpx5+fJlqQlLT548yZp1vb29mzVrpuQJc3NzhUKh4gur\np6fn6+u7Z8+e3Nzca9eu9ezZ86tn9vHx4UZwK0PJYXTcqFgzM7Pdu3cfPnz4r7/++vTpk6mp\naZUqVdq2bTtu3LiaNWsq/7oKKHlxiuDZs2dsY/v27X379g0ODua+YvXr169NmzYsfz137tzL\nly9dXFyUPK06rvnz58/ZhoIGdWNjY3t7+w8fPiQmJqampn51Ht0in1MdwWhAdnb2hQsX2Cct\np1OnTqtWrRo3bhwRHThwgBsVVCJ0/k5IS0t7+/YtEbH+SOHh4YsWLbpy5YpIJGJHOTg4jB49\neubMmap+OAP/+M4sNWft2rXsLY8cOVKy/MSJE6y8ZcuWcg/kRhWVL18+NTVVtkKdOnVYBclO\nSyKRiFtqurDGoV69erEKy5cv5wrPnDnDCn19fWUPiY+PZ9+9nJycJLvhr1ixomPHjp6enkeP\nHpU9iuWXROTh4SE3kiLYs2cPO2fHjh2LdgbuP/v58+d/tXJMTMy0adOmTp06YsSIxo0bc+Mq\nJC+dkrjn6XZ2dj///PPx48evXLkSHBzs5+fHyitXrvzq1StlTsVd2IkTJ361Mjdwp8RbF1TC\n9Svl7lsp+vr6CxcuLP73dZUujqq4b1BeXl45OTmyFbhHdbt37y7xV1cJ199AcbOWu7s7q6bM\nNGZFPmfJBqOxFrvBgwfLrZCRkcFGbhKR9o/c1Ko74eHDh6zEz89vy5Yt3BMkKe7u7tp/YUFK\nGWqx48Z1c3NPMJ07d3Z0dExISAgPD3/69Kmbm1thZxg8eLClpaVsef369aOioojow4cPXOGj\nR49ev35NRJUqVWrbtq3cEw4cODAkJISIzp49O3v2bFbo6+trb2+flJR05cqVz58/s6eNnMOH\nD4vFYiIaNGiQ5AShs2bNmjVrVmGRc/+Fv3v3rrA6quLGFDdq1KhoZ3j8+DHb4Ea0KBAXF8el\n5kRkaWk5evTo2bNnqzTbExMQENCwYcP169efOnVKan4mJyenIUOGTJ8+vVy5csqcivVKNjEx\n4YaaKsDNtMy9cV5wLXZRUVE2Njbdu3evW7euUCiMjo4ODQ19+/ZtQUHBwoULs7KyVqxYUZwX\nUuniqCQmJoZ7F5s2bZI7L2utWrX+/vtvIvr48WPJvrqqMjIy2AbXdUEuLkFJT09X3znVEYwG\nDBw4UG65qampm5sbm3M+NjZW+ZZ7XmjVnfDlyxe28fz589DQUCcnp4ULF3bs2NHOzu79+/cn\nT55cuHBhUlLS48eP+/Xrd+3atcIyP9BCZWWt2CtXrrAmazc3N6lVBwwMDLjZmLjkTy5vb2+5\n5VzjQWZmJlf4559/Kj6KiBo3bsw2WJdkLh72pDg/Pz80NFTqEDY/ExF9dS0vkUiUk5OTnZ2d\nnZ3NpYDZ2dmKj1Iet4DHsmXLBEqQXckqJiaGbVSvXl3VV//y5cvatWu9vLzY8GGVjk1NTT17\n9uz9+/dldyUkJFy+fFnJRbfCw8OvXbtGRIMGDeI6OCrAvU3ujfOCS4nGjRsXGxsbHBw8Y8aM\nKVOmbNy48eXLl1OmTGF7V65ceevWrSK/iqoXRyXcvdeyZcvC5ljmvoPx/h8S90dX2MIADNc6\npcwfaZHPqY5gNEDBdz97e3u2kZqaqqlwikir7oS0tDS28fjx42rVqkVERAwfPtzR0VEoFFaq\nVGncuHG3b99mfaBv3Lhx7Nixr0YC2qOsJHZcbwmp5jqpwj179ij4W+I+QaSw4RdEJJlhvHnz\nhm1wE6fJqlKlCnv2l5aWxv2ZERHX1Y91CuTExsbeuXOHiDw8POSO5w8LCxsxYoS7u7uFhYWB\ngYGxsbGJiYmJiYlkz78SIZZoyVeSh4eHVElCQgLbcHJy+urhLVq0EIvFBQUFycnJd+7cmTNn\njoWFRXR09JgxY7jnQcqIi4vz9PRcu3bt+/fvhw8ffuvWrbS0tNzcXJbiuLq63r9/f+DAgdyc\nIAps2LCBbbBePl9VoUIFlmRwb5wXiYmJycnJqampmzdvlhpMamhoGBgYyPUQWLNmTZFfRdWL\noxLu3uvdu3dhddiCJSTxvYsvXGNJTk6OgmrcXsVNL8U8pzqC0QAFv0RuwZu8vDxNhVNEWnUn\nSFq3bp3so48aNWr89NNPbDs4OPirkYD2KBOPYt+/f8860gmFQskBBxxXV9eWLVuGh4ezIRTc\nlGNSuAROGdzXRwU9T/X09ExMTFg735cvX7g2Bh8fH2dn5+jo6MuXLycnJ7OvTaSwuS49Pb1f\nv37cTLDqFh0dzd6gubm5MnmVmZmZbFrMPUSQOz2VXHp6etbW1l5eXl5eXqNHj27duvWbN2/2\n7t37zTffyE3ZZQ0ePPjVq1dEtHXrVskVEqtUqTJs2DA/P782bdrcu3dv69atrVq14mYGkfX2\n7VvWnurt7S2bs8olEAhMTEzS09O5N86Lr3bHnj9/PushcOnSJZFIJPnEX0lFuDgq4VrsCuvk\nQETx8fFsgw3945HkDDsKqnHt/XKnbimpc6ojGA0owk2ohbTzTjA0NOTmCpDi5+fHVlYsTuM9\naF6ZSOx27tzJvszl5eVVqFBBceVt27YVltipA9fIJzU93sCBA5csWZKXl3fixAluGl6W2BkY\nGMj2OBkyZAjL6qysrAICAjp37uzs7GxpacmS0ezs7JL95s39z9q4ceNffvmlaCfhvkQWbaHe\n6tWrr1+/nrXZbNy4UZnE7s6dO9evXyeixo0by1332tTUdNWqVWxK6sDAQAWJ3e+//15QUEBE\nCurIMjY2Tk9PF4lEeXl5X11a9/nz51evXlX+5HZ2dn379lW+fmE8PDyMjIxycnLS0tI+f/5c\nhF6MRbs4ymMtdoaGhoX1iM3NzX3y5AnbVjxXrRR1XHPuM0dxSy3LRAUCQfny5b/6ukU+pzqC\n0Uk6fydw7QU2NjaFPcZ1cnIyNTXNzMxMTU3Nzs7mWgdBy+l+YicSiXbs2KF8/Rs3bkRFRRU2\nYFB53LMDyWesUgoKCrivWVLtKIMHD16yZAkRHTlyhCV2L1++ZOMVfH19pf7gHzx4wBpIjI2N\nr1+/LtsfpcQfUnAjJ4rTHsPlczk5OYo7iBSGW6gjMjJSmVSJmyVYQUtP8+bNBQKBWCyOiIjI\nzc0tLDCu9bR79+7KB8we9Ovp6X01VCK6ffu2Mk+EOQ0aNCiRxE4gEJiamrK0u2hdrIp2cZT0\n6dOnuLg4IqpYsWJhl/HRo0dscfpq1ap99bucJHVccy77VNC3MjU1lU39U7lyZWVmlyjyOdUR\njE7S+TvB1dVVX1+/oKBA8RANY2Nj1tqXn5//1WBAS+h+Ynfu3LnY2FgiqlSpkoJxo0R05syZ\n8+fPE9H27dvXr19fzNfl5jphD/7k4v4UbWxspP6Ga9Wq5enpGRERERYWxqbHU/AcNiwsjG30\n69dPbi/jEu+tz7XYcSM9i4B7ApuRkSH70OHSpUt//fVXQkKCn59fYVPKGRkZ6enpsYk5cnJy\nvpotceMGFHxiGhgYGBgY5OXliUSi9PR0qVHJTFxcHLsC9evX537RymB5vPKPnnmRnZ3NdSRQ\ncnSwpCJfHCVx956CZ8rcX0SHDh1KPABVcX8j3CIBsrhFcZT8plTkc6ojGFCSVt0JxsbGrq6u\nz549y8jIePv2rdweC7m5ueyjwNDQsMym+KWR7id2W7duZRtjxozhVouSy8fHhyV2e/bsWbFi\nRTGbnbnBerdv3xaLxXIXImMjISQrSxo0aFBEREReXt758+f79+/PBlJYWlrKtoKwqYmp8KdO\nUoMwio/7z7U4H/0VK1ZkWW98fLzswMnTp0+zDvgikaiwxO7Vq1dsOk1TU1NlPne4LI01+cj1\n4cMH1sCpr69fWJdt9jyXiKRGWCuWmJjIHlAqOSmDv78/9xS+pJw4ceLMmTNv3rzp379/YSe/\nfv06u6q1atUqwhP8ol0c5XH3Hjdfg6wDBw6wDW4qciWp45rXr1+/SpUqb968+fPPP9+/fy+3\nBZGbTZObNVNN51RHMDpJ5+8EIurcuTOb6PvEiRNy/3O8d+8e+8jipsGDUkEXeqQq8ObNG7ZY\nuIGBwYgRIxRX9vT0ZFOyJScnFz8TqlevHpsJNiEh4cKFC3Lr7N69m23IHdzXv39/1mX47Nmz\n0dHRjx49IiI/Pz/Z/2u5Eq5FSlJsbCzXDa5EmtPfvXv3/v17IjIyMlIw7d9XcdN/sAn/pHCP\nWffu3ZuUlCT3DLt27WIbSq4Swc0vc/bs2cIeT3MDUDw9PQvrss1NvVu/fn1lXpfh3qY62rGU\nlJSUtGPHjgsXLixdulTuMDqRSLR06VK2rWCZYwWKdnGUxyV2MTExrDFeysmTJ1kHu1q1arVp\n00YdMaiK9TXMy8vjlriV9Pbt2/379xORubm5MkuSFPOc6ggGlKRVdwI3/cKqVavkdhninlxx\n6xBC6cDXzMiaMW/ePPY2lVyqkpsVpXnz5lwh9y0nPDxc7lHjx49nFX777TfJ8m3btrFyFxeX\npKQkqaO4Nf4qVKhQ2EqpbAmdChUqBAYGssqSi1twuEXG3Nzc8vLyJHfFxMTUr1+/fv36XFfZ\nz58/Sx0+Z86c8ePHjx8/XsmloE+fPs1O1ahRI2XqF4abTePHH3+U3VtQUFCvXj1WwdvbW3Y1\n96CgIG6KMjZvsyS5byovL49bXWrChAmSS3cwb9684ZZH27p1a2GRc8vvXr9+Xfn3y91d06ZN\nU/6okpWens4NhujatavUSiqZmZncRPZmZmYJCQlShwcEBLCrGhMTU9hLqHpxVL392HcJQ0ND\ngUDQp08fqV/iq1evuNbfY8eOKXNCDfj48SMb866vr79//37JXR8+fPDy8mIBL1y4UPbYwq55\nkc9ZnGCkKL/yhKq/ZYbrhpuVlVVYnS5durA6p06dUv7MfNGqO0EsFvfp04ft7dChw5cvXyR3\ncZ/PJiYmsh8FoM10ObHLy8vjnnmdO3dOmUO+fPnC9X968uQJKyxyYicSibhh5I6OjmvWrLlx\n48aff/557Ngx7gmRvr6+gti4hajZOoBVq1aVu9BTeno61xeqbdu2Z8+ejYyMvHjx4pQpUywt\nLY2NjSMiIrg2rTFjxjx69OjNmzfc4VzrfVhYmDJXadGiRay+1OJsquJ6frRv315uhYiICK7v\nnYmJSd++fRctWrR69eqAgAAu5yMituSulMLe1NWrV7n/LRo3brxp06YrV67cvn371KlTM2fO\n5NLfNm3aSC43LoVLHZRZ84fDPdnhN+E4ceIE1xJpaWk5cuTI5cuXBwYGjhs3jvt7EQgEctem\n4/46WAcDuVS9OCrdfpmZmSyb9/Dw8PPzI6JWrVqx5W6vX7++cOFC7jc4fPhwZV5dYw4cOMD1\nx/jmm28WLVoUGBg4duxYLuBmzZrJTV8UXPMin7NoB4aHhy/4L65Hr5+fn2T56tWrpY5V9UOG\nKU5il5GRMWfOHGdnZyMjoypVqsyYMSMjI4N1sw4MDFQ+hhKnVXdCfHw8t8isk5PTrFmztm3b\ntnTp0qZNm3IfsEFBQWq5EKA2upzYcY9Tq1WrJts2Uxjuie2kSZNYSZETO7FYnJmZqWColK2t\n7enTpxUEk5qaKtnVb968eYXVPHXqlNzxm5aWlixxlGqlnzVrFnesqp+53AS2mzZtUqZ+YXJz\nc9nnjomJSUZGhtw69+/fr1WrVmEXkIhGjx4t9wNLwZu6dOkS1ywn14ABAwprQ2W4lsIPHz4o\n+WZFIlHFihWJSCgUyjaaalhISIiCSUzs7e3PnDkj90BlEjtVL45Ktx/XLXXQoEHx8fHcurdS\nRo0aJdV0rQ127txZ2LgZX1/fjx8/yj1K8TUv2jmLduDy5csLu2ekVKhQQepYDSd2IpGIjXy3\ntLT87rvvBg4caGNj06JFizFjxhDRli1blI9BHbTqTnjx4kVhY+CMjIy2bdtWYm8bNEWXE7t2\n7dqxu3PJkiXKH8X9z2FtbZ2ZmSkuXmLHXLt2bcSIETVr1rSwsDA0NHRwcPj222/Xrl0r9SBM\nLtYswSh+ivHgwYOBAwc6OTkJhUI7O7tGjRotWrSIW785Ly9v3rx5VapUMTIycnV1PXDgAHcg\n95l79erVr8YjFou5LmKFXRDlcWm03PYhJicn58CBA35+fs7OzmZmZgYGBra2to0bN54yZcqj\nR48KO0rxm8rIyNi1a1evXr2qVavGzmljY+Pp6TlhwoR79+4pjlly4bjs7Gwl3yk3w2fHjh2V\nPEStkpOT169f7+vr6+joaGhoaGxsXKlSpa5du27evDk9Pb2wo76a2BXh4qh0+3GPs1euXMne\nxeLFi93d3S0tLY2MjKpXrz5kyJDi35bqExMTM3fu3AYNGtjY2BgZGVWtWrVPnz7Hjx9XcMhX\nr3kRzlm0A0sksVPyQ4YpcmLH5hCwt7d//fo1K/nw4UOdOnXYI8tff/1V+RjURKvuhLy8vN9+\n+61Tp05OTk6GhoZWVlYNGzacOXOm5IMdKEV0ObED5bHOiPfv39fw63JptK+vb4mfnK83JRfX\nG0l7On5pD+V/U6zFhZTuXAHaQ01/j3ITO9Z17Oeff5asyY3X1obEDkB9dHxULCjp+fPnxMdo\nTS8vrxYtWhBRWFhYVFRUyZ6crzclKzExkQ1wcXV1xUhDWcr/prghsQpWhQftpMm/RzaD+jff\nfCNZ2KpVK9YdAkC3IbEDyszMvHTpkquraxEWjyq+lStXEpFYLJ47d24JnpbfNxNtYGcAACAA\nSURBVCVlwYIFbG6R5cuX68aqlyVI+d9UQUFBZGQkEZUvX17JuQBBS2j475GtryU76S7mY4Oy\nAP/HAO3cuTMlJUV2QQvNaNasGXvpEydOXLp0qaROy++bkvTw4UM2tU27du24yQWAo/xv6vnz\n52zpDjTXlTqa/HsUi8VsKTzZKT8VrFYCoDOQ2AEJBIIFCxZMnDiRrwA2bNhQpUoVIho5cqSC\n5QRUwvubYnJycoYOHVpQUGBtbc1NXgOSlP9NlchCdsALTf49CgQCtrqg7BTcClbuBtAZur+k\nGHwV79mPtbX1gQMH2rZt++bNm9GjR3Or4hYH72+KmT59emRkpEAgCA4OlrsaIyj/m3r48CHb\nQItdqaPhv8fy5cvHx8e/e/dOqksfW5IEQLehxQ60QrNmzdjzysOHDy9evJjvcErGjh072GJu\nK1euLMvLbpYUtNiBktiq2dyge+b27dtv3rzhKSIAzRGIxWK+YwAAACgxmzdvnjBhQrVq1e7f\nv8+Ga3z69KlNmzbx8fGfP3/+9ddff/jhB75jBFAXtNgBAIBOGTFiRO3atV+/fl2nTh1/f/9h\nw4bVrFmzWrVqWMweygIkdgAAoFNMTEzYej8CgeDgwYN3794NCAg4fvy4SCQiIkw5BLoNgycA\nAEDXVKhQgXXblZSYmEiY9AR0HRI7AADQKfHx8Tdv3jQxMenWrRtXmJWVxSa4rlOnDn+hAagd\nEjsAANApMTEx3333nZWV1c2bN9kIWZFINH/+/I8fP9apU6d+/fp8BwigRhgVCwAAumbYsGF7\n9uwRCoXt2rWzsrJ68ODBP//8Y2ZmdvHixWbNmvEdHYAaIbEDAABdU1BQEBwcHBQU9OLFi9TU\n1AoVKrRt23b27Nlubm58hwagXkjsAAAAAHQERn0DAAAA6AgkdgAAAAA6AokdAAAAgI5AYgcA\nAACgI5DYAQAAAOgIJHYAAAAAOgKJHQAAAICOQGIHAAAAoCOQ2AEAAADoCCR2AAAAADoCiR0A\nAACAjkBiBwAAAKAjkNgBAAAA6AgkdgAAAAA6AokdAAAAgI5AYgcAAACgI3QzsTt79qytre36\n9ev5DgQAAABAc3QzscvNzU1OTs7OzuY7EAAAAADN0c3EDgAAAKAMQmIHAADFFRkZ2a1bNxsb\nG1NTUy8vrxMnThSn8j///NOkSROBQHDt2jXldwEAIbEDAIBievHiRcuWLZ8/f7506dLt27db\nWVn16tUrNDS0aJW3bt3q4eHx/v172WMV7AIAxoDvAAAAoHT7+eef8/Pzr1+/7ujoSEQDBgzw\n9PScNm1ajx49BAKBSpVv3749derUNWvWmJmZDR8+XPJABbsAgIMWOwAA3de0aVMvL6/w8HAv\nLy9TU1MbG5tBgwZ9/PhRtqZYLP5YiJSUFNn6BQUFJ0+e7NKlC0vUiEhfX9/f3z86OvrRo0eq\nVra3t7979+748eNlX0jBLgDgoMUOAED3CYXCFy9eTJw4cc2aNa6urpcuXRo/fnxCQsKVK1ek\nar5//57LuqTUqlXr2bNnUoUxMTFpaWkNGjSQLPTw8CCiR48eNWzYUKXKLi4uhb0FBbsAgIPE\nDgBA9wkEgqSkpH379n377bdENHLkyMjIyA0bNkRFRdWpU0eypq2tbVhYmNyTmJmZyRYmJCQQ\nUYUKFSQLy5cvz+0qcmUAKAIkdgAAZYKRkVGbNm24H1u2bLlhw4aIiAipxM7Q0JAlf0piM4Ya\nGhpKvRa3q8iVAaAI0McOAKBMsLe3FwqF3I/lypUjoqSkpGKe1tjYmIhycnIkC1mWZmJiUpzK\nAFAEaLEDACgT9PX1JX8UiUREpKcn/fVeLBZ/+vRJ7hkMDAysra2lCitWrEhEiYmJkoXsuaqT\nk1NxKgNAESCxAwAoExITE/Pz8w0M/vexL7e7G6k+eKJ69eo2NjYRERGShffu3SMiT0/P4lQG\ngCJAYgcAUCbk5ORcuHChS5cu7MeLFy8Skbe3t1Q1VQdP6Onp9enTZ+/eva9fv65WrRoRZWdn\nBwUFubu7u7m5FacyABQBEjsAgDLBwcFhypQpMTExtWvXDgsL27NnT/fu3atXry5VTdXBE0T0\n008/hYaGtmnTZvLkyWZmZjt37oyNjWWJIxGdPHmyd+/e69atmzRp0lcr37x58+nTp0R069Yt\nIjpz5szLly+JqG3btgkJCYXtcnZ2LsaFAdApSOwAAMoEc3PzQ4cOTZ069c8//zQ0NBw2bNiG\nDRtK5MyVK1e+cePGzJkzFyxYkJ+f36hRo4sXL3IjcEUiUUFBAevS99XKe/fu3bZtG3fmNWvW\nsI0DBw5cu3atsF1I7AA4ArFYzHcMJS80NLRXr17Lly+fPXs237EAAPCvRYsWiYmJrIkLAHQY\npjsBAAAA0BFI7AAAAAB0BPrYAYDK7t69u3v37qpVq/IdCCgrLi4uPT195cqVfAcCZVpMTMwP\nP/wgtYIwlCwkdgCgsnPnzl24cEHVsZPAow4dOhBRdHQ034FAmXb+/HkXFxckdmqFxA4AVObo\n6Ojp6Sk5RBEA4Ku6du0qOyc2lCz0sQMAAADQEUjsAAAAAHQEEjsAAAAAHYHEDgAAAEBHILED\nAAAA0BFI7AAAAAB0BBI7AAAAAB2BxA4AAABARyCxAwAAANARSOwAQGUGBgb6+vp8RwEApYy+\nvr6BAZa8Ui9cXwBQ2aBBg7p168Z3FABQymzbts3W1pbvKHQcEjsAUJmxsbGxsTHfUQBAKePg\n4MB3CLoPj2IBAABAI/r1oyNH+A5CxyGxAwAAAI1ITKQPH/gOQschsQMAAADQEUjsAAAAoOTk\n52v6QJCAxA4AAABKyPPnZG9Pd++qfOCiRdS0qRoCKnOQ2AEAAEAJqVWLJk0iX1+6c0eFoxYu\npLVrafNmtYVVhmC6EwAAACg5P/9MRNShA124QN7eX6+/cCGtWUNnz5KPj7pDKwuQ2AEAAECJ\nUj6347K6Vq00E5rOQ2IHAAAAJU2Z3A5ZnRogsQMAAAA1UJzbIatTDyR2AAAAoB6F5XbI6tQG\niR0AAACojWRuxyCrUyckdgAAAKBOXG7n7Exnz9L168jq1AeJHQAAABRDRgbNm0dZWV+p5uJC\nDx7Q48fUpQvt30/79yuq7OlJ339fgjGWHZigGAAAAIpBLCaR6OvVBAISi4mI9PW/XrmgoLhR\nlVVosQMAAIBiMDenjRu/UmfhQnr2jNzdycmJrlxRdu5iUB1a7AAAAECduNESVlbUpQtNmUId\nOqi25hgoDS12AAAAoDayY2BVXXMMVIHEDgAAANSjsJlNkNupDRI7AAAAUAPF89Uht1MPJHYA\nAABQ0pSZhRi5nRogsQMAAIASpfzaEsjtShoSOwAAACg5qq4YhtyuRCGxAwAAgBLy/DkFBlJY\nGPn4qHAUy+3GjaO//lJTXGUH5rEDAACAElKrFiUlqZbVMT//jJntSgQSOwAAACg5hoaaPhAk\nILEDAAAA0BFI7AAAAEAj7O3J3p7vIHQcBk8AAACARhw7xncEug8tdgAAAAA6AokdAAAAgI5A\nYgdlS2RkZLdu3WxsbExNTb28vE6cOFHkykXbm5KSIihEaGgoq/PXX39169bN0dHR0tLSw8Nj\n69atBQUF3Jnz8vIWLVrk7OxsbGzs6uq6atUqsVhcMlcHAABKOfSxgzLkxYsXLVu2LF++/NKl\nSy0tLffs2dOrV6/jx4/37NlT1cpF3mtqarpjxw6p1woLCzt69KizszMR3b59u02bNk5OTtOn\nT7ewsDh27NjYsWNfvXq1evVqVnnQoEHHjx+fOnVqo0aNLl++PGvWrKysrAULFqj32gEAQKkg\n1kUhISFEtHz5cr4DAe0yaNAgMzOzd+/esR/z8/MbNGjg7OwsEolUrVycvVJSUlIqVqw4fvx4\n9mPr1q2tra0TExPZjwUFBY0aNTI1Nc3LyxOLxefPnyei9evXc4f37dv3m2++kXtmAAAoa/Ao\nFrRL06ZNvby8wsPDvby8TE1NbWxsBg0a9PHjR9maYrH4YyFSUlJk6xcUFJw8ebJLly6Ojo6s\nRF9f39/fPzo6+tGjRypVLs5e2cDmz5+fl5e3ZMkS9uPgwYM3b95coUIF9qOenp63t3dmZmZy\ncjIR7d6928rK6ocffuAOP3LkyLVr1wQCgVLXFwAAdBoexYJ2EQqFL168mDhx4po1a1xdXS9d\nujR+/PiEhIQrV65I1Xz//j2XOUmpVavWs2fPpApjYmLS0tIaNGggWejh4UFEjx49atiwofKV\nzc3Ni7xX6oWioqK2bt36yy+/WFtbs5KRI0dKRf7ixQs7O7ty5coR0e3bt729vY2MjIhIJBLp\n6eG7GQAA/D8kdqBdBAJBUlLSvn37vv32WyIaOXJkZGTkhg0boqKi6tSpI1nT1tY2LCxM7knM\nzMxkCxMSEoiIawljypcvz+1SvnJx9kq90I8//li9evVRo0bJfSNEdOTIkbCwsBUrVujp6YlE\notjY2A4dOuzYsWPVqlWvXr2ytrbu16/f6tWrLSwsCjsDAACUHUjsQOsYGRm1adOG+7Fly5Yb\nNmyIiIiQSuwMDQ1Z8qek7OxsdpTUa3G7lK9cnL2ShVFRUSEhIVu3btXX15cb85kzZ/z9/bt2\n7TpjxgwiyszMFIvFFy9e/Ouvv5YsWWJra3vx4sXAwMCXL19eunRJyesAAAA6DIkdaB17e3uh\nUMj9yB5BJiUlFfO0xsbGRJSTkyNZyDItExMTlSoXZ69k4ZYtW8zNzQcOHCg34M2bN0+ePLl3\n79779u1jj1zZZUlLS3v48KGlpSURtW/fvqCgIDAw8O7du15eXkpdCAAA0F3ooANaR6r5SiQS\nEZFsZzJVB09UrFiRiBITEyUL2bNRJycnlSoXZy9Xkp+ff+jQoU6dOpmbm8tGO3Xq1AkTJsyY\nMePQoUNc45+RkZGlpWX9+vVZVsf4+voSUWRkpOxJAACgrEGLHWidxMTE/Px8A4P/3Zxyu6yR\n6oMnqlevbmNjExERIVl47949IvL09FSpcnH2ciV37tz5+PFjp06dZOOfN2/exo0bt23b9v33\n30vt8vDwePfunWRJbm4u/fuoFwAAyjgkdqB1cnJyLly40KVLF/bjxYsXicjb21uqmqqDJ/T0\n9Pr06bN3797Xr19Xq1aNiLKzs4OCgtzd3d3c3FStXJy9zK1bt4hIapAsEYWFhS1btmzjxo2y\nWR0Rfffdd+PGjbt48SJrqCOiw4cPy70+AABQBiGxA63j4OAwZcqUmJiY2rVrh4WF7dmzp3v3\n7tWrV5eqpurgCSL66aefQkND27RpM3nyZDMzs507d8bGxrLEkYhOnjzZu3fvdevWTZo06auV\ni7OXYW2KNWrUkCzMz8+fMGGCnZ2diYnJzp07JXe1b9++atWqI0eODAoK6tWrV0BAgLOz8/nz\n5w8fPjx8+HBXV1eVLgUAAOgmnidIVg+sPFF6NW/e3MXFJSIiolWrVqamptbW1sOGDUtJSSmp\n8z979qx79+6WlpampqYtWrS4cuUKt4vdNoGBgcpULuZesVjcrVs3NoOJZKGCMSIhISGszufP\nn8eOHevg4CAUCmvUqLFkyRK2KAUAAIBArIvLh4eGhvbq1Wv58uWzZ8/mOxZQTYsWLRITE1++\nfMl3IAAAAKUPRsUCAAAA6AgkdgAAAAA6AoMnoFBZWVmySzKoW35+vkgkYgvegzbjpmIGAADt\ngcQOClWzZs24uDheXtrW1paX1wXl1a1b98mTJ3xHAQAA/4HEDgrl4uKyYcOG3r178x0IaJ1t\n27ZdvnyZ7ygAAEAa+tgBAAAA6AgkdgAAAAA6AokdFGrcy5e2z5/zHQUAAAAoC4kdFKphaqrF\nf9ebBwAAAG2GxA4AAADULj09/dSpU3fu3OE7EB2HxA4AAADUq0+fPpaWlt27d/fx8TE1Nd29\nezffEeksJHZlW1QUtW5N79+rfOC+fTRokBoCAgAAXfPDDz8cP36cW5s+KytrxIgRjx8/5jcq\nXYXErmyrUYNMTalNG9Vyu717adQo6tVLbWEBAIDu2LVrl1SJSCSaOHEiL8HoPCR2ZZuREYWG\nkosLffMNKTlO4uBBGj2adu2ivn3VHBwAAJR6IpEoLy9Ptjw2NlbzwZQFSOzKPENDOnqUatak\ntm2/ntsdPEj+/rRrFw0cqJHgAACgdNPT09PTk5NslCtXTvPBlAVI7KDQ3M7W1rZKlSr/Xw1Z\nHfzLx8enL5psAUA5Pj4+soUzZ87UfCRlARI7ICL5uV25cuXs7e3/VwFZHUhwd3fv168f31EA\nQOlw8eLFSpUqSZaMGDHiu+++4yse3aalid3ly5f9/f1r1qxpaWlpYmLi7Ow8YMCAs2fP8h2X\nTlPwTBZZHQAAFJWpqenbt2/37NkzYMCACRMmPHjwICgoiO+gdJYB3wFIS05OHjRo0Llz5yQL\nY2JiYmJiDh482LNnz3379pmZmfEVno5juV3fvtS2LV258r9CZHUAAFBsQ4YMGTJkCN9R6D7t\nSuyys7N9fX3//PNPIhIKhX369GnatKment7Dhw8PHTqUlZUVGhrap0+fs2fPyu2JCSVAMrcz\nNKS7d+m335DVAQAAlAralditWLGCZXWOjo4XLlyoX78+t2vevHnt27d//fr1hQsXdu3aNWrU\nKP7CLOVyc2n/fpI3+Pz/dexIsbH099/09980fDilp9P27Yrq161LzZuXbJgAAACgKi1K7PLz\n8zdu3Mi2g4ODJbM6InJxcTl69KiXl1dBQcGiRYtGjhwpEAj4CLP0+/SJdu6knJyvVEtLo4IC\n0ten+/fp4cOvVPb1RWIHAADAOy1K7O7fv5+cnExEbm5uvr6+shU8PT07dep0+vTpt2/f3r59\nu1mzZhqPUSc4OtLNm1+pw/rVVatG1taUlUXnzlHFihoJDgAAAIpOi3qqvXz5km14eXkVVqdD\nhw5s4+LFi5qIqWziRkvY2tL48crOXQwAAAB806LE7suXL2zDysqqsDo1atRgG3///bcmYiqD\npMbAGhiosC4FAAAA8EqLEjtzc3O2kZqaWlgdA4P/PTt+8eKFJmIqa+TObKLSmmMAAACFePz4\n8fv37/mOQsdpUWLn4uLCNtjAWLmePn3KNlJSUjQRU5miYL465HYAAFAMP/zwg4GBQYMGDRwc\nHGxtbc+cOcN3RDpLixK7Jk2aWFhYENGTJ0/++OMP2Qq5ubnbtm1j2+np6VJ74+LiLv3r0aNH\n6o5W13x1FmLkdgAAUCRz5szZtm1bQUEB+zE5OblHjx6vXr3iNypdpUWJnaGhITc73bBhw2Ji\nYiT3pqenDx48+OnTp2xqYrFYLHX46dOn2/9r4cKFGglZVyi5tgRyOwAAUF1gYKBUSUFBwZgx\nY3gJRudp0XQnRLRw4cITJ05ER0e/fv3a3d19+PDhTZs2JaLIyMj9+/fHx8ePGzdux44dIpGI\nte1JqlGjhp+fH9uOj4+/deuWpqMvpVRaMUxqzTHMgQIAAAqJRKIceTOnosVOTbQrsbO0tLx0\n6VKnTp2eP3+enp6+adMmyb3Dhw9ftGjRli1biEg2sWNtdWw7NDS0V69emom5dIuMJH9/2ruX\n/s2Jv87QkI4coV69aOhQunRJncEBAECpp6enp6enJxKJpMoVzIABxaFdiR0RVa9e/dGjR9u3\nbz9y5MiTJ08yMzOdnJy8vLy+//771q1bc7OcODs78xunjnBzo4cPqXZt1Y4yMqLQUIqNVU9M\nAACgUxo0aPDgwQOpwgkTJvASjM7TusSOiIyMjCZOnDhx4kTZXVxiV69ePc0GpaMMDFTO6hhD\nQ3J1LeloAABAB126dMnV1fXz589cSc+ePbHmu5poY2KnwIULF9gG1hMDAAAoFWxtbT99+rR8\n+fKrV6/a2NiMGjWK6zoFJU4bE7ukpCR7e3vZ8rS0tJCQECKysrLCPaEJhoZkZMR3EAAAoAvm\nzJkzZ84cvqPQfVo03QkR9ezZ08LCwsHBQe7CEsuXL09OTiYif39/Q0NDjUdX9pw4ocKgCgAA\nAOCbdiV27u7u6enpIpFo2LBhaWlpkruCgoJWrlxJRFZWVvPnz+cpwDKmfHky0MY2XQAAAJBL\nu/7bDggI2LVrV3x8/O3bt11cXIYOHVqjRo2UlJQzZ87cuHGDiAwMDA4cOGBnZ8d3pAAAAABa\nR7sSO2tr61OnTnXp0iUhIeHDhw9r1qyR3GtnZ7dz585OnTrxFR4AAACANtOuR7FE5OHh8fTp\n0xUrVjRv3tzGxkZfX9/e3t7Ly2v58uVRUVE9evTgO0AAAJAvJCTE19e3du3anTp1OnfuHN/h\ngHZ5+/bt6dOnr1+/npGRwXcsuky7WuwYKyurWbNmzZo1i+9AAABAWStXrpw9ezbbfv78+fnz\n5zdv3jxu3Dh+owJtIBKJAgICNm/enJ+fT0QODg47duzo2rUr33HpJq1rsQMAgFInPj7+xx9/\nlCqcNm3ap0+feIkHtEpgYOCGDRtYVkdEiYmJAwYMkDv9BRQfEjuQLy8v79mzZ+/fv+c7EAAo\nBe7cuZOXlydVmJ2dff/+fV7iAa2yYcMGqZL09PSdO3fyEozOQ2IHcqxbt65cuXJubm4ODg4+\nPj5PnjzhOyIA0Gr6+voqlUPZIRaL4+PjZcvfvn2r+WDKAiR2IG3Hjh3Tpk3j5hG8c+dO586d\nJdf4AwCQ0qxZM1NTU6lCS0tLLy8vXuIB7SEQCCpVqiRbXrVqVc0HUxYgsQNpP//8s1TJ27dv\ng4KCeAkGAEqF8uXLyz5u27p1q6WlJS/xgFYJCAiQKrGwsBg9ejQvweg8JHbwH5mZmXLbzNHL\nFQAUGzVq1M2bN1kTXYsWLe7fvz9gwAC+gwKtMGnSpBkzZgiFQvZjpUqVDh8+7OzszG9UugqJ\nHfyHiYmJubm5bHn58uU1HwwAlC7NmjUbNmwYEY0aNapx48Z8hwPaQiAQrFq1inXX9vb2/uef\nfzp27Mh3UDoLiR38h0AgGDFihFShiYnJoEGDeIkHAAB0A2sgsLa2NjEx4TsWXYbEDqStWLFC\n8ruUubn59u3b3dzceAwJAAAAlIHEDqSZmJicO3cuJCSEiJo0afLPP/8MHjyY76AAAADg65DY\ngXxNmjQhoipVqjg6OvIdCwAAAChF0VqxcieeKSlxcXHqOzkAAABAGaQosZM77QUAAAAAaCdF\niR1jamoqEAhK6vXEYnFmZmZJnQ0AAAAAOF9P7J4/f16Cz2Tj4uIqV65cUmcDAAAAAA4GTwAA\nAADoCCR2AAAAADpC0aPYdu3aEZGxsXEJvp6xsTE7LQAAAACULEWJ3aVLl0r89ezs7NRxWgAA\nAAD4+uAJucRicU5OjlRjnlgsvnnz5uPHjw0NDb29vevVq1cSEQIAAACAUorSx27jxo0VK1Y8\nePCgZGF8fLyPj0/Lli3Hjx8/evTo+vXr9+7dGzObAAAAAGiMyond5MmTJ0+enJiY+Pr1a66w\noKCge/fud+/elawZEhIybNiw4ocIAAAAAMpQLbG7f//+xo0bicjKyqp69epceXBw8F9//UVE\n5cqV++mnn9auXdugQQMiOnr06M2bN0s0YAAAAACQT7XEbteuXURkYWFx8+ZNyda4nTt3EpFQ\nKLx27drPP/8cEBBw69YtFxcXItq3b1+JBgyakJWV9dtvvxFRZGRkeHg43+EAAEDplpKSsmrV\nKiJ6/PjxoUOHxGIx3xHpLNUSu1u3bhHRkCFD6tatyxV++PCBPYTt27cvN2DC1NR0+PDhRCT1\nfBa03/v37+vWrfvjjz8S0T///NOqVat58+bxHRQAAJRW7969q1u37vLly9l2//79hwwZwndQ\nOku1xI71q2vVqpVk4ZUrV1jq3a9fP8lyluTFxMQUM0TQsHHjxkn91pYtW/bHH3/wFQ8AAJRq\nEydOfPfunWTJ/v37jx07xlc8uk21xC49PZ2IypcvL1l4/fp1ItLT02vdurVkuaWlJXcIlBYF\nBQWnT5+WLQ8NDdV8MABQusTExLAPkBMnTsTFxfEdDmiLCxcuyBaeO3dO85GUBaoldkZGRkSU\nl5cnWcgmHPbw8LC2tpYsT01NJSKhUFjcGEGD8vLycnNzZcsxcw0AKHb69Om6deuePXuWiEJC\nQmrXrn3lyhW+gwL+icViqbSBkVsIxadaYlehQgUi+ueff7iSqKioly9fElGHDh2kKr99+5aI\nypUrV9wYQYOMjY3r1KkjW+7p6an5YACgtEhNTfX398/KyuJKMjIyBg8eLFkCZZNAIPD29pYt\n9/Hx0XwwZYFqiV3Dhg2JKDg4OCcnh5UsXryYbfTo0UOqckhICBHVrl27uDGCZm3YsEGqpHHj\nxpiSEAAUuHHjxqdPn6QKExISMH4OiGjTpk0mJiaSJd7e3iNHjuQrHt2mWmLXu3dvIoqIiGjW\nrNm8efO6du3K1p9wd3dv2rSpZM3g4GDWCN++ffuSixY04dtvvw0LC2vcuDERGRsbjx079vz5\n84aGhnzHBQDaq7DeGhkZGRqOBLSQu7v7vXv3unXrRkQWFhZz5sy5ePEiemqpiUCluWTy8/M9\nPT0fP34sWainpxcWFta2bVuuZODAgQcOHCAic3PzmJgYOzu7kgpXSaGhob169Vq+fPns2bM1\n/NI6Iz4+vlKlSn369Dl69CjfsQCAtnvx4kXNmjWlCvX19d+8eVOxYkVeQgJtk5KSYmNj07Fj\nRwybUCvVWuwMDAzOnj3bvHlzrsTMzOy3336TzOqI6OPHj6zyrl27NJ/VQfGJxeLLly8TUXR0\ndHR0NN/hAIC2c3V1nTJlilThnDlzkNUBaJiBqgc4OTnduHHj8ePHT58+NTMza968uY2NjVQd\nT0/P7OzsZcuWtWjRooTiBM1JT0/v2LEjWwvuwYMHdevWXb9+/ZgxY/iOCwC02sqVK5OSkg4f\nPpyXl2doaDhs2LCFCxfyHRRAmaNyYse4u7u7u7sXtnfp0qV6eqq1BYL2NhbQeQAAIABJREFU\nCAgIkFzhNzs7e8qUKd7e3mz9XwAAuVasWLF//362nZubu2PHDjc3t6lTp/IbFUBZo1r6NX36\n9OnTpwcGBn7lpMjqSi2RSMR9NHOys7NZp0kAALnevHmzYMECqcI5c+YkJSXxEg9AmaVaBhYY\nGLh27Vp0e9RhOTk5cke3ff78WfPBAEBpcf/+fbahR9Tz38KcnJw///yTr5AAyibVEjsnJyci\nys7OVk8wwD8TE5OqVavKlsudtRgAgDEw+F/HHkeiECKu5zVmSgLQMNUSu549exLRvXv3EhMT\n1RMP8O+nn36SKrG3t8dMkgCgQPPmzc3NzYlIQMT9a2Nj4+XlxWNUAGWQaondokWL2rZtm5OT\n06NHD7ZiGOge2Zniv3z5gklPAEABOzu7LVu2SJYYGRnt3LmTZXsAoDGqjYq1srI6derU8ePH\nN2/e7Orq2q1bt1atWjk7O5ubm+vr6xd2FCY9KUXEYvG+ffukCnNycg4ePIhRsQDwPxERlJdH\n/10AdMiQIXXr1l3yww90/37Lli2XbNlSr1496QNv3CBLSyp8UgUAKCbVEjup4a5Hjx5VZlkC\nlRa3AH5lZ2fLHTwhuwokAJRdf/9NY8fSyZPUrp1kcaNGjXr16kX37/fv319OVnf2LPXpQ3v2\nILEDUB/MSwL/YWJiIjvjNP07bgYAgIho6FBaupS6d6dLl7iy7OzshQsXLlu2jIjmzp27YsWK\nvLy8/z/k/Hnq25dWryY/P83HC1B2qNZi17x5c2NjYyMjI319fUxWp6sKCgpkC0UikeYjAQDt\nxRYQ69GDTpygb78losmTJ2/fvr0SERGlpqaySezWrl1LRHT+PPXuTatW0YQJ/EUMUCaoltjd\nuHFDTXGAlsjMzPzy5Yts+bt37zQfDABoNYnc7qmT0/bt26X2r1+/fvLkyVWiopDVAWhMEZcU\nA11lYmJibW2dkpIiVY5HsQAgx7+53YeAANmdIpEoMTi4yooVyOoANEaNj1PfvHkze/bsgwcP\nqu8loMQJBILx48dLFVpYWAwdOpSXeABA202ZQkuXtli9+luZPR2JGi9bhqwOQJPUmNglJyev\nXLlSdrZb0HILFiwYMmQI92OFChV+//13Z2dnHkMCAK02ZUrewoUniCRzu45Ex4kKli9HVgeg\nSepK7JKTk9lklZjHuNQRCoXz58/39fUlIisrq0mTJnXo0IHvoABAq0W0bDmP6ARRSyIiakd0\nnGgm0d9t2vAcGUAZU5Q+dnFxcRs2bLh8+fK7d+/krhubn5+fkZHBtitUqFCsAEHjHj165OPj\nk5WVRUSpqanz5s27devWqVOnBAIB36EBgJZ6+/bteiIiCiIioj1EM4h+IfJ9+7Zhw4Z8RgZQ\nxqic2F29erVHjx5paWlK1h88eLCqLwH8Gjt2LMvqOGfOnDl8+PB3333HV0gAwL+tW2ns2MJ2\n9ifqL/GjMdEmok1E1L27onPu3k3ovwtQolRL7JKSkvz8/JTJ6mxsbNzc3Pz8/Cagd0Wpkpub\ne+fOHdnyP/74A4kdQJk2bBg1aVLYTpFINGrUKPPHj9cQGRLlEE0loqZNN2/eXGhjv0BAdeqo\nKViAMku1xG7btm1saalevXpNnz7dzc1NT0/P2tqaiLKysvLy8mJiYg4fPvzLL79UqlRp06ZN\njRo1UkvUoDaFfQRjXTiAss7EhDw9C9upR7Ri2jSr4cMXi0SLiRYRBerrZ0ybJmjcWJMxAoBq\nid358+eJ6Jtvvjl27BjLALg+dsbGxsbGxu7u7u7u7qNGjerWrVvz5s1DQkI6duxY4kGD+giF\nQmNjY6lHsYSVJ0BCUlLSzZs3s7KyGjdu7Orqync4oB3Ony//ww/i9estX76kjRvt5s83KlfO\naPhwsrVl61IAgGaoNir22bNnROTv76+4H321atVOnjxpaGjYv3//hISEYgUImpWdnS2b1RFa\n7OBfwcHBNWrU6NWr18CBA2vWrDlhwgTcG8CtGCaYONHBwYGIHB0d2fx21KOH5HqyAKBuqiV2\nqampRFS1alXZXVILjFavXn348OGpqalBQUHFiQ80zNDQ0MjISLbc0tJS88GAtvnzzz/Hjh0r\n2ct28+bNGzZs4DEk4J+CdWCR2wFonGqJnYGBAf03hzM0NGQbsguMdu7cmYhCQ0OLFSBolp6e\nXu/evWXL+/Tpo/lgQNsEBQXJznDEZqyEMkpBVscgtwPQLNUSu/LlyxPRq1ev/v94PT1TU1Mi\niomJkars6OhIRG/evClujKBZmzZtqvPfoWpLly719vbmKx7QHnJ7VqC7Rdn11ayOQW4HoEGq\nJXb16tUjouDg4Ly8PK6wevXq9O+4CklszQn29BZKkXLlyj18+DAwMJCI3NzcIiIi5s6dy3dQ\noBXYH7sULDdXRimZ1THI7QA0RbXErnv37kR0586d1q1bHzt2jBU2adKEiFavXh0ZGcnVzMvL\nW716Nf3byAeli1Ao9PPzI6I6depgzhrgjB8/3sLCQqpw9uzZvAQDfLp8mXr1ojVrVFgHdsoU\nWryYevSgGzfUGRlAWadaYjd06FA2cuLWrVsrVqxghf379yeilJQULy8vf3//VatWzZ07193d\n/dq1a0TUqlWrEg4ZAHji4uJy7Ngxrt3O3Nx83bp1AwYM4Dcq4EFGBm3dSuPGqXZUQABt2EDp\n6eqJCQCIVJ3HzsTEJCQkpHPnzomJifb29qywQ4cOnTp1OnfuXFZW1u7duyXrGxoazpw5s8SC\nBU2JjIycOHEiEV24cOGnn36aO3eusbEx30GBVmjfvv3z5899fHwiIiJiY2NtbW35jgj4oHih\nMAVGjSrROABAmmotdkTk4eHx5MmTxYsXt27dmis8fPhwz549pWra2dkdP368QYMGxQwRNOzO\nnTseHh7Xr18novT09MWLF/v4+GCCYuAIhUIzMzMiMjc35zsWAAD4D9Va7Jhy5crNnz9fssTc\n3DwkJOTBgwdhYWGJiYkmJibu7u7dunVjA2ahdOndu7fUrIQPHz7csGHD1KlT+QoJAAAAlFGU\nxK4wHh4eHh4eJXjC0i45OblPnz6yM/xpM7FYLHf2ivnz5+/fv1/z8RRH37590a8fQMMyzc0X\nENXAt3oAnpRkYgdSnj59evXqVaFQTyhU+ZG3tsnOznr69BHfUaggMzNfIBAgsQPQMJGBwSKi\nYIXLTgKA+pRMYpebm6uvr6+vr18iZ9Mxzb+p1LOvC99RqGDahGsF+dI96hp7OQwc5sZLPEUT\nMO4q3yEAAABoWhFbkrKysvbu3duvX78aNWqYmJgYGRmFh4dzeyMjI2/fvl1CEYKmtfm2slSJ\nUKjXtVcNXoIBAAAA5RUlsTt9+rSzs/PQoUOPHDkSHR0tu3bkzp07mzVrNm7cOKk++FAqdOlR\no1XbSgK9/z1JsbI2Gj/Vw9LSkN+oAACg9Hrx4sWYMWOI6Pbt20uWLMnKyuI7Ip2lcmJ35MiR\nHj16JCYmKqhz5swZIvr1118DAgKKHhrwRCCgJl6ONWvbmJsL7cubNPF2qOiEWS3gfwoKCrZt\n2xYVFUVEixYtSklJ4TsiANB2UVFRHh4ehw8fJqLU1NQff/yxY8eOaPpRE9USu0+fPo0cOVIk\nEunr648YMeLq1atpaWmy1Xbs2MHmpt+0adPjx49LJlLQlNfRqRtWRzyP+pyenpf0IevS+djt\nmx+JRGK+4wL+iUSirl27/vDDDx8/fiSipUuX1q9f/8OHD3zHBQBabeLEiRkZGZIlf/zxx2+/\n/cZXPLpNtcRu69ataWlp+vr6J0+eDAoKat26tdwZStu0aRMWFmZmZiYWi3ft2lVCoYKGHD3w\nT/5/B0+8/Cflz7uK2mihjPjtt9/Onz8vWRIXF8cWKQEAkEssFt+8eVO2XLJrPpQg1RK7Cxcu\nEJG/v3/nzp0V16xRo8bw4cOJ6I8//ihycKB5+fmi+Dg5rbCxMaVpNj5Qk+DgYNnCU6dOaTwQ\nACg1BAKBnp6cZMPAABOuqYVqid3z58+JqEePHspUbtWqFRFFR0cXISzgi56eQCBvAioDg1I/\nFR8U35s3b2QLc3JyNB8JAJQi7du3ly309fXVfCRlgWr/WycnJxNRpUqVlKlcsWJFIpJ6rA5a\nTk9PUKuOnGXd3eqV03wwoG2srKxkC+V+FwcA4Pzyyy/29vaSJb179+7Xrx9f8eg21T6R2dqv\nmZmZylRmWaClpWURwgIe9RtYy+K/k5s0b+VUW162B2VNz549ZQuxkCAAKFa5cuWoqKgpU6YQ\nUYUKFXbt2nXkyBG5T4eg+FRL7JycnIjo1q1bylS+ePEiKd28B9rDxtZ4zkLvTt2q129g59XM\nceRYd7+BtfgOCrTCtGnTqlSpIlliZGT0yy+/8BUPaJsPHz5cvXqViC5duvT582e+wwEtYmdn\nt2DBAiLy8PAYPnw4WvrVR7Ur27p1ayLauHEja41T4MGDB9u3b+cOgdLF1NSgQ5fqI8e6Dxjq\nVr+BHd/hgLawsrK6du1a37592fqB3t7eFy5caNq0Kd9xgVa4evVqrVq1jhw5QkT79u2rVavW\n3bt3+Q4KoMxRLbEbMWKEQCCIi4tr3779s2fP5NbJzc3duXNn27Ztc3JyBAIBGxsLpU5Kck7U\nk0+vY77k5UmvGwtlWfXq1Y8cOdK8eXMiun79+jfffMN3RKAVMjIyBg8eLDlh9cePHwcMGJCb\nm8tjVABlkGqDjT09PUeNGrVjx46IiIi6dev6+Pg0aNCA7QoODj516tQ///xz48YN7m/7+++/\nb9iwYQmHDGomEomPH35x41oc+9HG1njgMDfXWjb8RgVaRSRCug//ER4e/u7dO6nCmJiYu3fv\ntmzZkpeQAMomlR9yb968uW/fvkQkEolu3ry5ZcsWVr579+5169adPn36/9i777CmzjYM4E8C\nhI0gIkMRlOUE3LuKIHVvoVXrQq1aW62r2tZP62jVWqW11o17j9oq7qJWceMCQQEVRUSQIRAg\njCTfH6dNMQlLkpyT5P5dvXqdPBySGxLDk3Pe876yrm748OEYfKONzp9+LuvqiCg7S7RtY/Tb\nbPkVgUE/PXz40M/Pj5lutHnz5n/++SfbiYATcnOVT3WZk5Oj4SQAeq7ajZ2RkdGhQ4d27drV\nokWL8vZp2bLlnj17Dh48iOkHtdGlv5LlKgUFpTeuYuUJoPT09J49e168eFEqlRJRQkLCwIED\nmcHyoOeaN2+utF7BXwoAUIf3bLxGjRo1atSoR48e3bhx4/nz5zk5OXw+v1atWo0aNWrXrp27\nu7tqU4LGFBeL8/NLFOvZOGIHRKGhoampqXLF+fPnX79+nZU8wB1NmzYNCQnZunVr2eL06dNd\nXFzYigSgn2p0RK1x48aNGzdWVRTgAoHAwNzcSLG3s7ExYSUPcEpcXJxiMTY2VvNJgIPWrl3r\n4OAQGhqan59vaWk5d+7cuXPnsh0KQO9U71Tsxo0bMWBC53Xzd5armJkZtu/kwEoY4BSxWKxY\nxIgLYJiami5duvTHH38korVr13777bcCgaDS7wIA1apeYzd58mQHB4cRI0acPXsWl8XpqoBe\nLl261ZPdtKltMnZSC2scsYNyLobF9PEAANxR7Y/aIpFo3759+/btc3Z2/uSTT8aOHevh4aGO\nZMAWPp837GOvgF6ur14KTc0M6zewNDLCFOFAVM7BOUxUBgDAHdX7gz106FBTU1NmOzk5+fvv\nv/f09OzSpcvWrVvz8vLUEA9YY21j3LSFbUO3WujqQMbV1VWx2LBhQ40HAQAA5ar3N/vw4cPp\n6em7d+/u37+/bPBEZGTkhAkTHBwcRo8eHRERwcyDAAC657PPPrOwsCCiFkSD/y3OmzePxUgA\noC3u3btHRKmpqa9fY/4sNar2wRgLC4uRI0f++eefaWlpYWFhgYGBzNmZgoKCXbt2+fv7N2rU\naOHChU+fPlVDWgBgk4eHx5EjR1xcXHoRfUpkYWGxatWqESNGsJ0LuOL58+cnT54kouPHjysu\nRAF6q6SkJDg42M/Pj4ju37/v4eGxY8cOtkPprPc/y2ZtbT1u3LgzZ86kpqauX7++e/fufD6f\niJKSkhYvXuzu7t69e/cdO3bk5+erLi0AsCwwMDAhIaF+/fpElJSUNGvWLLYTAVecPHmyadOm\nJ06cIKIjR440btz44sWLbIcCTli8ePHBgwdlN4VC4eTJk+/fv89iJB2mguFTderUmTx58oUL\nF16+fBkaGtq2bVsikkqlly5dGjt2rIODw8SJE+/cuVPzBwKNeZNesHdH3MolN39dfffSX8li\nMU6vw3+MjIyYkRiWlpZsZwGuyM3NHTNmTEFBgaySl5c3cuRIkQhzmwNt2bJFriISibZv385G\nFt2nynHxjo6O06dPv3nz5v79+2vXrs0UhULhli1bWrdu7e/vf+PGDRU+HKjJqxThj0tv3byW\n+ipFmBif/fuhhLAN0Rg5qY8WL6bExGp/V2EhzZtH2dlqCATcdeXKlYyMDLniq1ev8LYPUqk0\nPT1dsa60CDWnysbu4cOHCxYs8PDw+Oijj7Kysv55AP4/DxEREdGxY8fZs2crneMUuOPgnsfF\nxe88Rw+jM+7dwb9A/fPyJXXvXr3errCQBg6kkyfJyEhtsYCLyht1IxQKNZwEuIbH47m5uSnW\nsfqomqigscvIyAgNDfXx8WnevPnSpUsT//0z0LBhw8WLF7948eLBgwfjx483MDCQSqU//fTT\nxx9/XPMHBTURl0qeP1OyuMiTeByA0T8bNlBAAHXtSspWElOisJAGDKCXL+nsWbKwUHM44BYf\nHx/FooGBga+vr+bDANd8++23chU7O7vJkyezEkbnvX9jJxaLw8PDhw4d6uTk9OWXXz548ICp\nGxsbBwcHnz179smTJwsWLKhXr16LFi22bt0aFRXl6elJRIcOHdq2bZtq4oPK8XhEShYSwOoC\n+ojPp7Aw+vBD6tGj8t6O6epSUigighywAJ3e8fT0/OKLL+SKX331Vb169ZTuD3pl9OjRa9as\nkY3K9fb2PnHihKOjI7updNX7NHaPHj2aN2+es7Nzv379jh49WlLyz4LxzZs3X7NmTUpKyv79\n+3v27CnXCvj4+Fy6dKlu3bpEtGHDhppHB3UwMOC5eVgr1j0b22g+DLCvir0dujogWrVq1cqV\nK+vUqUNE9vb2v/zyy+LFi9kOBVwxY8YM5oRet27d7t+/365dO7YT6azqNXZbtmzp3LlzkyZN\nVqxYkZqayhQtLCxCQkKuXbsWHR09Y8YMW1vb8r7dwcFhxowZRBSn7C/EiRMneFWGc/PqEzTS\ny8TknZWjWraxb+Frx1YeYFmlvR26OiAiIiMjozlz5jDN3IoVKz7//HMDAwO2QwGHMFfTy9av\nAjWp3lqxEydOLHuzQ4cOEyZMCA4OtqjyeJpmzZoRUVFRUbUeFzSprr3ZvIXtI84+f5ksNDU1\nbOFbp30nHDDXb0xvN3489ehBERHUpMl/X0JXBwDAJdVr7Bh16tQZNWrUhAkTmC6tWiQSib29\nvZOTk+KXPD09Fy5cWPG3Z2dn//LLL0Tk4uJS3YeGqrO2MR4S7Ml2CuASud6OUVhIw4ahqwMA\n4I7qNXY9e/YMCQkZPHiwbKHY6ho0aNCgQYOUfsnT03PRokUVf/vYsWOJyMjI6Oeff36/AADw\nnsr0dtaGhgZEhkOGUGoqujoAAO6oqLFjrn5ITk5mlg8iorNnz9bw8V6+fOns7ExE0urPeHv6\n9Glmdbl58+Y1b968hkkAQInMTMpRMt/NfxYsoOLigQcPlhDxnj+nPXuooIAqWBtaIKB/30AA\nAEDd3udULCuEQuGkSZOIyN3d/ZtvvmE7DoCOGjSIrlypdC9TIlMievKEOnSoZFcTE3r9mmrV\nUkk6AAComCpXnlCrJUuWJCcnE9HatWuNjY3ZjgOgoy5fJqm0ov8KCiggINvI6BWR1N6eYmMr\n2b+wEF0dAMi8x/k6qJbKj9g9ePDg9evXqnq891sbLj4+PjQ0lIgGDRrUq1cvVYUBgOr59xrY\nPx0dHV68cBgwgKd4nSwAgIIjR4589dVXRHT27Nn+/fuHhoYqXWcMaq7yxq5v374ayFGxmTNn\nFhcXGxkZ/fjjj2xnAdBXZWY2KezcmYhK164V8PlK5kABACjj1KlTw4YNY7alUumJEycePnx4\n9+7dWjicrwZacCo2MjIyPDyciCZPnox5iQHYUaarK65dm5mKMjcvj9avp4EDq7TmGOiBqKio\nvXv3EtHOnTujo6PZjgNcMWfOHLnKs2fPfvvtN1bC6LyKjtiNGTNGYzkqwCwebGpq+vXXX1ew\n27lz5zZv3sxsp6SkaCIZgJ4o09WduX9/0qRJwSkpjYlcXV0XLVo0e/16IsJxO9i5c6fsr0ZE\nRESbNm327t07dOhQdlMB66RSaWxsrGI9IiJi/vz5ms+j8ypq7LZv366pGOW6fPnyxYsXiWjk\nyJEOFc6V9eTJk0OHDmkolq579iTn1IlnKcl5pqaG3i3tAvu4yi0yBnqkTFcXn5s7bNgwoVDI\nfCU/P3/OnDmOjo4j0dvpvYyMjM8++6xspbi4eOLEiYGBgbKl30El/vrrr6ysLLZTqEBMTIzW\n/dX28fHx9OT67P1c/2stm4h46tSpFe/Zr18/2YnayMjISuc6hvI8TXz7y6o7zHa+sCTi7Itn\nT3I+n9WKz+exGwxY8O6KYb8tXy7r6mSWL18+cuRIQm+n3yIjIxVfG9nZ2Tdu3AgICGAlkk5K\nSEjQmd/n69evg4KC2E5RPa1bt759+zbbKSrB6cYuOTn52LFjRNShQ4eWLVtWvHP9+vVlEykr\nvr9A1R3eFy9XefYk59b111gxVu8orAOblJSkuNc/RR4PvZ2qnDlz5vPPPxeLxWwHqYb8/Hyl\n9U8++cTMzEzDYWrC0NBw48aN3bt3ZzuIcgUFBUREttZUry7bWarjgfyfFSIiU2Py0KrVQR8m\n/vP75zZON3Z79+5l3to+/vhjtrPoi9JSyasUJW3xi6RcNHZ6JziY0tLo0iWys2MKSi9h+6/I\n49Fvv1FREfXsSffvk62txpLqmIsXLyYkJFiakaEB21GqTCJRXhcJXxcpb/m4qKSUhIX0999/\nc7ax+4eFGbkoWXKdu+KeUkmpfLFuHe37KbQBpxu7AwcOMBsDBgxgN4n+4PN5fD5PIpGfQNLQ\nSAsuoAYVGzaM+vShOnVkBT5fycvAwKBM98Hn09attGULmZpqIKBu+/MHo+6+WvPv7skrqfvH\nxXJFPp9idwocbbVmFMfJ65K+X5WwnUIX8ZS9BrTm1a1luPt7ffny5d27d4moRYsWrq6ubMfR\nF3w+z8LCSLFubY3VPvTP6NFluzoiys7OVtxLfhw3n0+TJpFWnX2DmrsZq2Q5AYmEouKxzAAQ\nlShrl4vRQ6sFdxu7S5cuMRsdO3ZkN4lekUik+flK/rG9fVuk+TDANbbKzq7Webf5A/0U/Ux5\nAxefjMYOiJQuBGqC4wVqwd3G7sq/K5G3aNGC3SR6RSKRisVK3ohLissZQQP6ZNSoUcyGlEj2\nKhk9ejRbeYA78gqUN3DZuJINiMhVYSydAZ+cK5rCDN4bdxs72XyG3t7e7CbRK4aGfMd6For1\nBq6YiQrIz8/v+++/FwgEB4kWExHRwIEDmSnEQc81qKt8IJ2rvYaDACe5N3injTMyJN/GZGnO\nXiBdxt3GLj7+n6ujnZy06qoZ7Tc0WH72RdeGVm074JJYICKaP3/+gwcPBO7u14jOnz9/7Ngx\nIyMlgzJB34wIUDLTpYEBDflAe67sBfXh8ah2LRL8+15hYYauTn2429i9efOG2cAiwRrm7mn9\n+axW7p42JiaGtW1Nuvk7f/q5r4GB1lzXBurm5eXFfNzq2rUr21mAK+rZ8RaNl+/hVk81tMGx\nfiCi1Dd0//F/V0tk59L1B7h4Qk04Ot1JYWGhbHJOKysrdsPoITcP62kzK5kRGgCgrAWjDVt5\n8H85In6SIvVqwPsyyCCgNXePHYBGPXomXxEVUdIr8tSqCYq1RCWNHTOnfK1atWxsbKp71z//\n/POuXbuI6D3W3zA1NZVKcS0VAIA26duR37cjmjlQkF+opCjUglUctFEl/wIbNmzYsGHDZcuW\nKf3qo0ePHj16lJGRofSrycnJUVFRUVFRNc0IAAAA2stI2VEkAYbnqkWNPlo1adKkSZMmoaGh\nqkoDAAAAukbpzCb1tWq5W+3B0TF2wK7iIvHVK69SkvNMzQxb+Nh5eFX7RDwAAMA/Gjek3Hx6\n8+8qNXw+NXUjawygVws0diAvN6d4zYrb2Vki5ubfES/9A136D3FjNxUAAGgrPp86eFPmW3qb\nR4YGZFebzEzYzqSz0NiBvEP7Hsu6OsZfZ583aV7b3RPH7QAA4H3ZWpOtNdshdB8uX4J3SCTS\n2GglV8PE3Fd+iQwAAECVlJRSdi7l5RNmvVAnHLGDd4jFyteKLcZasQAA8N7ikyjxBYklRETm\npuTjhaN3aoLGTu2ys0TxcVmV78cZtW1NsjJFckWBgK9dPwUAAHDF81f0OOm/m/mFdCuGurUh\nU4y0Uz00dmp3/076/TvpbKeoqYt/JV/8K5ntFAAAoIUSX8hXSkrpeSo1bshGGh2HMXYAAACg\nToXyZ4GIiAqULUcBNYbGDgAAANTJ2FhJ0URZEWoMp2LVrlmLOm07KJt0m6v+PJqoOMauS7f6\n7p7aNNB1x5aHbEcAAAAiIjIWkKhIvmhjyUYU3YfGTu3s7M18W2vNwimlpZIdW2IU61KpVIt+\nCiLauRWNHQAAN+QJlRSfvSJHbfqzoi1wKhbewefzeDyeYt3QEC8VAAB4LxJlE9cVKBt4BzVW\npSN227ZtO3HiRHlf3bBhw+HDhxXrb968ef9cwBI+n+fVtHZcTKZcvUlzW1byAACA1uPxlExK\nLMA5Q7Wo0q81KysrK6vcOcwyMzMzM+X7ANBeQSO8Vi+/nZdbLKsK7HN7AAAgAElEQVR0/qBe\n46a1WYwE3CGVSr/77ruoqCgiGjdu3MaNGy0sLNgOBQDcVtuKMnPki+4ubETRfeiXQZ5NbZP5\nizpcvpD88kWemblRcx+7Fj512A4FnCCVSr28vBISEpibe/fuPXr06JMnT5ycnNgNBgCc1s6H\nLtx45/oJZwdysmMvkC6rpLE7d+6cZnIAp5iZGX7YF/NGgrxZs2bJujqGSCQKDAyMiVFywQ0A\nwD8M+dSzI71MozdZZGhIDRypFo70q0sljV1AQIBmcgDomxUrVpw/f57tFNUTGRmpWIyNje3Z\ns6fmw9SEg4NDWFiYkZER20EA9El9e6pvz3YI3af2U7GFhYWmpqbqfhQArbNhw4akpCS2U6iA\nVCrVug6ViBYuXOju7s52CgC9kZdPj55RjpCMDKiuLXm4kKEB25l0kxobu4cPH27atGnnzp3Z\n2dnqexQALSWVSg0s7BxnXWI7SDW82RVS9PSaXJFvYuX01XVW8ryfrN+/KnhwXKp4jR4AqEmu\nkK7cIbGEiKiQKDefMt9Sp5bEVzK7FtSQ6hs7kUh06NChjRs3Kj1rAwD/4fH4prXYDlENdT7+\n7dXydlJxSdli7SErtOun4BliISMAzYpO+Kerk8nOpeRUcsF1V6qnyllnY2NjZ8yY4eTkNHr0\naHR1ALrHwLKu/dTjhrYuxOMREd/U2nb4ajPvAWznAgBue5unpJilMAEKqIIKjtiJRKLDhw9v\n3LjxypUrZevm5ubBwcGTJk2q+UMAAEcI6rWwDV4rir8oLcoXNGht1rw324kAgPOULWhEfCxo\npBY1auzi4uI2bdq0Y8cOuVF0rVq1mjhx4siRIy0tscQvgE55G7449/JG2U1jl7Z1J+znGZmw\nGAkAuK5ubUpVWIyqLua9V4v3aeyKioqYQ3SXL1+W+1KvXr2WLVvWqlUrVWQDAG4pjDtftqsj\noqLnt96eXWHTdyFbkQBACzR3p+zcdyYormdPjpigWC2qdyD00aNHM2fOdHJyGjVqVNmurmvX\nrsxG37590dUB6KqC6ONKivf/1HwSANAmJsbUvS15NSSHOlTPnlo3pVZN2M6ks6p0xK6oqOjI\nkSMbN278+++/y9YdHR1Hjx4dEhLi4eHBU3oGHQB0iKRIqFiUKisCgBq9yaaoh2yHeC98Hkkl\nlPpGyZlZ7hOL2U5QJZU0do8fP2ZG0WVmZv73PYaGffr0CQkJ6dOnj6EhVpsF0BcCh8aFD0/L\nFY0c8MkbQLMKCqmgkO0QwFGVtGWNGzeWuzlu3LjRo0c7ODioMxUAcJFl54nC2wfFOa/KFq37\nfMtWHgAAkFOl42116tSZOHHi8OHDW7Zsqe5AAMBZfDNr+4kHMw/PLHoRRRKJoY1z7cHLjV3a\nsJ0LQM/w+WSAuUI0rrSU7QRVUqXGLiMj48SJE6amplZWVm5uburOBACcJbyxqyjpJrNdmv0i\n5681xg3bY7oTAI1ydiBvT7ZDVF92LuXkkaEB1bEhEy1cAOb0lcr34YBKWv727dszG9HR0f/7\n3//c3d07d+4cFhYmFGK4NIDeKW+6E7byAIB2kEjoVgxduUPRCXT3EUXcpOepbGfSWZU0dtev\nX7979+6kSZMsLCyYytWrV0NCQhwdHSdMmHDtmvxy4ACgw/Jv71dWPKj5JACgTR4n0euM/26K\nxRSTQDnK1hmDGqv8JL2vr+/GjRtfvXr122+/eXt7M0WhULh169ZOnTo1bdr0p59+Sk9PV3NO\nAGBf8es4xaJElKv5JACgTZJfy1ckEnqZxkYU3VfV0ZeWlpZTpky5f/9+ZGTkJ598YmLyz5Ca\nuLi42bNn169fX20JgR0pL4U3r6VG388oKNCO4aKgATy+AdsRgOsKRPTohVRUzHYO4JRiZS+I\nohKN59AL1Z6FrlOnTp06dQoNDd2+ffvGjRvj4+OJqKTkn6dnxYoVb9++HT9+vJOTk4qTgqaI\nSyW7tsXei/rnKKyZudFHoxp7t8TaL0AC51Ylb57IFQ2s7FkJA1zzVkhf/lq684xYIiEDPk3q\nb7ByiqGFKduxgAvMzCi/QL6IF4d6vOf10rVr1545c+bjx4//+uuvYcOGGRkZMfWXL18uWLDA\nxcVl8ODBp0+flkgkqosKGhL+51NZV0dEBfklu7fHvklX+DcJ+sey41glxS4TNR4EuGjc8pLt\np8TMu75YQuv/EE9ZjeP9QEREXq7yFWMBueAAkFrUdCKcHj16HDp06MWLF0uXLnVxcWGKpaWl\nx44d6927t5ub2/fff1/jkKA5UildvfxKrlhcJL59Q2GEBOgfgbNv7SEreQIzWcWi3UgrNHZA\ndCdeeuyy/Cf53WfF8clSVvIAt9SrS83c/pt7z8yU2rcgYwGrmXSWamY4dHBw+Oabb54+fXri\nxIl+/frx+f/cbVJS0jfffKOShwDNKCkRiwqVfMjOycGQGSAismg30mlOZJ2RG22HhzrOvFh7\nyEriYaJUoISXyhu4x2jsgIiKiulpCon/bf0LCilJ/ggCqIoq35H5fH7fvn2PHz/+7Nmzb775\nxtHRUYV3DpohEBhYWin5FGVnh8EQ8A8Dy7pmLfqZtx5uVNeD7SzAFXVqKa/XtdZsDuCmmEQq\nFL1TeZH6zgQooDpq+ajdoEGDpUuXvnjx4tChQ/7+/up4CFCfug5misVG7uW8bYOeEeemZR6c\nnrLU5+VCr/QtwcXJ99hOBJzQoRnfROEjobkJtfbCAV0gSs9UUkxTVoQaU+M/OUNDw2HDhp0/\nf159DwEqJ5XSyxdKJo2MjcnSfBjgGkmRMG3T0Pw7h8XCDEmRUJR4JW3T0OJXD9nOBey7Ey9R\nnOIkX0TRT3EqFoiUXkmJyyvVA5+l4B0lJeIikVixLszDGDugvMitpRnPylakJaK34YtYigMc\nkvJGef3lGzR2QGRtpaRoo6wINVbJPHYikajiHapCNpsxcJ9AYFDL2jjnbZFc3c5eyflZ0Dcl\nKdGKxeKXSoqgb5zrKq+72PM0GwQ4qbk7Xbn7ziG6WpbUAAPx1aKSxs7UVAVD5qVSfGLTJubm\nRoqNnYsrPloB8QRK3hCUFkHflPcuj7d/ICKyMCMLU8rN/69ib0t8nDNUC/xaQV7qq3zF4tmT\nSRoPApxj2vRDJcVmvTSfBLjmZTkLhr9IR2cHRDGJ73R1RBSfRFk5LKXRcVVaUozH43l7e7u5\nuRUVFYlEouLiYiwpoavyhSVKj7BmZ6vgpDxoO7MW/czbBOffPiCrGDk2se6NuSqh3FOxDeri\nVCwQvUxTUkx4Tu29NR5F91WpsZNKpffv33/79u2AAQOCgoI6d+7M4+Hfqm4yMzfi8ZScPbGy\nMmYjDnCO7bDVZi36iR5fkJYUCpxbmrcO5hlUe8lp0D0dmvHbN+XfiH3nM79fS763G/5YQDkX\nwOYXajyHXqjkVGx8fPzXX3/t7OxMRM+fP1+7dm3Xrl0bNWr03XffJSUlaSIgaBaPR5bKerh2\nHTHKFf5h6tXDZsCS2kNXWbQbia4OGAZ82r/QsGOz//6mdPfl7/7WEAcBoFylSmZggJqrpLHz\n8PBYtmxZUlLS2bNnP/74Y+ZaiqSkpEWLFjVq1Mjf33/Xrl0FBVgeXndIpVQkUrKk2Jt0PMsA\nUBFXB17kOqO7WwW/LzW6Hya48LORUx20dVABjL9UiypdPMHn83v27Ll3797U1NSNGzd27NiR\niKRSaURExOjRox0cHCZOnHj16lU1RwVNKC2VFBVhHjsAeB88Hvm68wZ1xRlYqAIDA7YT6Kbq\nXRVbq1atSZMmXb169dGjR/PmzatXrx4R5eXlbdmypXPnzl5eXsuXL09JSVFPVNAEIyO+tY2S\nU7GYxw4AquJZqvTSPcmLNByMgTIMlDUbVuYaz6EX3nO6Ey8vrx9++OHFixenTp0KDg5mpiCO\nj4+fP39+gwYNevfuffDgwaIi+bnQQCt82LehXMXSStChsxMrYQBAW6RmSnvPKWn0UXH36SUu\nQcWDvinJyEF7B0REJDBSUrSy1HgOvVCjeez4fH6vXr3279+fmpq6fv369u3bE5FEIjl9+nRw\ncLCjo+O0adOioqJUFBU0pKCgRK5SWiopKcYoVwAol0RCIxaXnr7538WPf1yRjP1ByYBd0EeK\nCwkTropVF9VMUGxtbT158uTr168/fvx42bJlnTp1MjQ0zM7OXrduXZs2bVTyEKAxF869kKsU\nFpTevJbKShgA0Ao3H0ku3pOf0iL8miTmGQ7aAZGhsuF0RhhjpxYqnqrAysqqbt26Dg4OlpaW\n2dnZqr1z0IDiYrEwT/6IHRFlZmKCYgCNOnFVEp+sNV3RrUfKo274Q6xFF1LEPNWaX7iWcbSj\nFwpHBxzLmdUaakY1jV1BQcGRI0fCwsIuXbokW7eAx+P16NFj/PjxKnkI0AwjIwMzM8OCAvkT\nKNbWmKAYQKN+OqAL4x/W/a4LPwXUVDM3yhFSTt5/FU8XqmPNXiBdVtPG7saNG2FhYfv378/N\nzZUVXVxcxowZM27cOFdX1xrevw54kZT715nnbKeoBhNTJY1dbk6xdv0UWHocAIArDA2payt6\nlU5vhWRoQPa2ZI0rJ9TlPRu79PT0Xbt2hYWFxcbGyorGxsaDBg0KCQkJCAjAmmNEZG5uTkRP\nE98+TXzLdpaaunpZ+2axMTPDFC0AANzA41E9e6pnz3YO3Ve9xq60tPTUqVNhYWHh4eElJf+N\nxPL19Q0JCRk5cqSNjY2qE2oxHx+fs2fPvn2rTV1dUVHRJ598olj39/f/9NNPNZ+nJnDhDmi1\njbMNW3uq5vo2DVh3TLztpJKzrp8PNRzzodb8FJExkum/aMOVvKIieqNto9gLRPTsJRWIyIBP\n1lbk4qR8cjsuk2jHmaCqNnaPHz8OCwvbuXPn69evZUUbG5uRI0eGhIT4+vqqJ57W69mzJ9sR\nqm327NlpaWlyxYCAgOHDh7OSB7hFUpp3fZco/oK0pFBQv6VVt6l8MwyUUQtPZ15rL6059dGi\nkfKorTxIi36KtGyuRzU0NCQiSsuktEy2s7wvsZjSMyldK/P/8/vntkoiCoXCAwcOhIWFlV0x\njM/n9+jRIyQkZPDgwcbGGFOva+bPnz9jxoyyFXt7+3HjxrGVBzhEKkkPGyVKvMzcEj25mn/n\nkMMXZwwscXWbvvuwrfKjLz1aadtRGW5r0qTJmjVryh5h0Qrr1q0TCoVyxXbt2vn5+bGS5/0Y\nGhr6+/uznaJylTR2Dg4O+fn5zDaPx+vQocPQoUODgoKcnZ3Vnw3Y8cUXX2RmZq5cuZJZO6RZ\ns2ZhYWH29hgYASS8tVfW1THEeenZfy6oM3IjW5GAI4rLOYFZgotiVYrP58t98OY+qVS6YsUK\nxXpOTs7y5cs1n0fnVdLYMV0dj8dr2bJlz54969SpU1xcvG3bNolEfiLKCixatKgmEUHDeDze\n4sWLR4wY0aRJk8DAwJMnTxpgqWYgIqL8e8cUi4WPzms+CXDN0b+Vd3DHLktmBeMNBJQoLdWG\n4YxaqEpni6VS6Z07d+7cufN+j4HGThtZWloy/0dXBzLi7JeKRWmpssWCQM+UliofnVaKI3Z6\nj8fjWVlZlZ0TjcEsQwoqh9EPAFBVPGNzZVWujzcHDejTQflfk77l1EGvrF27Vq5ibm6+bt06\nVsLovEqO2J07d04zOQD0kURcmqVN0z4bN2hd8vqRXNHItqF2/RTSony2I+igzi14HZvxrj18\nZz6Inm35zcu5Whb0yujRo0tLS2fOnJmTk0NE3t7eBw8etLbGBfVqUUljFxAQoJkcAHpInJ/5\namUntlPUVMmbRB34KaCGeDw6sVzw6aqSI39LpFLi8WhkT4N1M7RgbgjQjPHjxw8ZMsTGxqZn\nz55nz55lO44uw786AABQgdpWdGixUW4+PU+TujrwLLHyCyiDcdvqhsYOAABUxsq83MmKAYio\nWrNqwHtAYwfAGr6JpXWfb9lOUQ2ixMsFD07IFY0cmlh2GstGnPeUf/tA0Yv3vMYfAN7PgQMH\n5s6dS0Tnzp3r1avX2rVrPTw82A6lm9DYAbCGZ2Rq0W4U2ymqQRT/t2JRnJOiXT9FUdItNHYA\nmhQeHv7RRx8x21Kp9MyZM4GBgXfv3sX1E+qAC9EBoMr4ygbH8I00ngMAtMm8efPkKklJSb/9\n9hsrYXQeGjsAqCoTz26KRVPP7hoPAgBaQyqVxsXFKdYfPnyo+TD6AI0dAFSVRcshfNNa75R4\nfMuuk1iKAwBagMfjWVhYKNZtbGw0H0YfoLEDgKrKu7FHUpjzTkkqyf0rlKU4AKAdrKysFIu1\natVSLELN4eIJAKgqUcIlxWJh4mXNJwFuKiqhc7ckSa+lbvV4Aa35RvgLA0RSqTQ9PV2xnpKS\novkw+gD/7ACgqkrSHisWpcWFmk8CHBT9VDrk25LElH9WFWviwvvjeyOP+pjTTt/xeDyeshWl\n+XycM1QL/FpBidLS0mPHjhHR48ePY2Ji2I4DXCEtEiqrYrpRoOISCl70X1dHRHHPpcGLSsR4\ndQCRn5+fYrFHjx6aT6IP0NiBvOzs7LZt206bNo2IYmJi2rRp89NPP7EdCjhBSjj6AspFxkji\nnkvlincTpFGP5Yugh3799Ve5Kev69OkzcuRItvLoNjR2IG/69On37t2T3SwqKpo9e/atW7dY\njAScgT/SoFx6tvJ6WjZeM0B16tSpX79+2Yqvr6/S87NQc2js4B0SieTQoUOKdaVF0DtKJyjG\nmzMQudVT/jrAGDsgolmzZsmN6vn+++8jIiLYyqPb0NjBO4qKikQikWI9JydHsQj6hm+iZM4C\n4uFtBKi1J69PB/lXQpAfv3EDNHZAhw8frmIRag7vyPAOU1NTNzc3xXqLFi00Hwa4xqxpL8Wi\nwKGx5pMA1/B4tPMbw4/8+czpNR6PxvY22DQHy80BSaVSoVDJdVe5ubmaD6MP0NiBvFWrVslV\nmjZtOn78eFbCAKdY9ficb/ruQTsev/bgFSzFAW6xteLt+59R5nHju1sF2eHG2+YZ1jJnOxNw\nAI/Ha968uWLdx8dH82H0ARo7kDdo0KADBw40atSIiAwMDIYPH3769GkzMzO2cwH7Sl7FSgrf\n/ZAtlRQm/M1SHOAiG0vydeehpYOyFKdW8PT0nDJlCithdB4aO1AiKCjo77//JqKBAwcePHjQ\n2dmZ7UTACfl3lIyJyb+9X/NJAECL9OjR4+TJk8yQHgMDg6CgoHPnzildQBZqDitPQEVwOTqU\nJc7PVFIUKikCAJTVu3fvjh072tjY9OzZ88CBA2zH0WU4YgcAVWVUp6GSop2Sq20AAIAVaOwA\noKosO4fwDOSvc7Ts+ikrYQBAi5SWljLzoSYmJmLGe7XCqVgA1ojz0l/Mq8d2iprK3P9Z5v7P\n2E4BANyVm5vbvXv3u3fvElFiYmK7du0WLFiwePFitnPpJjR2AOwYOXLkmTNn2E5RPc+ePcvK\nypIrGhoaat20BY6Ojg0aNGA7BYC+mD17NtPVySxZssTPz8/Pz4+tSDoMjR0oUVxczAxujY2N\njYqKat26NduJdNCyZcuWLVvGdorqGTZs2JEjR+SKFhYWt2/fZiUPcIpEQttOiX86IE7JoAZ1\nefNGGYz4d75i0HPlrVSJxk4dMMYO5GVkZLi5uc2aNYuI4uLi2rRpM2/ePLZDASd06NBBsdix\nY0fNJwEO+vyX0gkrS+OeS3PzpTHPJKOWlHyzWcx2KGAfVp7QMDR2IG/o0KEvX74sW1mxYsWl\nS5fYygPcMW3aNG9v77IVCwuLNWvWsJUHuCMxRfrb7/Jt3PK9pa+zpKzkAe7AyhMaxq3G7ty5\nc7wqaNOmDdtJdZZEIrl8+bJifcmSJZoPA1xjYmJy8eLFmTNnMiuRDBs27Pbt215eXmznAvbt\nOy9RLEqldOiikjroG8WVKj08PLDyhJpwq7F7+/Yt2xH0XW5urlSq5BP2q1evNB8GOMjGxuan\nn35iPlzt2bMHXR0wsoXKj8zl5OOIHZC/v394eDhz3I5ZqfL8+fNYeUJNuHXxhKyx69OnT9u2\nbcvbzcnJSVOJ9I6VlRWPx1Ps7erV0/pZOQC0y4D5JYYGbIeosgKR8vr3O8WrD2jNSLuSUrYT\n6K4+ffq4uLg0b968VatW27ZtMzfHcsLqwtHGLigoaMyYMeyG0U98Pv+DDz5QHFH37bffspIH\nQA917979yJEjYrHW9ENEJM7IKCpRMhbexNzGxsZG83nem5Oh4QcffMB2Cl0jkUhmzpy5bt06\nIrp165a7u/vmzZv79evHdi7dxNHGztramt0k+mzatGlyjZ29vT2ufATQmA8//DA+Pp7tFNWz\nfv36qVOnKtY3bNgQFBSk+TzAKWvWrPn5559lN1+/fv3xxx/fuXPHw8ODxVS6iltj7LKzs5kN\nNHYs+t///idXSUtL27ZtGythAEArhISEKA6Zsra2Hj58OCt5gFPKdnUMoVC4ZcsWVsLoPG41\ndjhixzqRSBQXF6dYl5s0HACgLIFAcPLkSUtLS1nF2to6IiKChxmK9Z5UKk1JSVGsJycnaz6M\nPkBjB+8wMjISCASKdQx0BYCKde3aNTs7OyQkhIimTZuWlZXVsmVLtkMB+3g8Xv369RXrLi4u\nmg+jDzja2Jmbm+/YsaNv376Ojo4CgcDa2trb23vGjBlaN+5E6xgYGAwYMECxPnjwYM2HAW56\n8+ZNZmYmESUmJrKdBbjFwMCAWYGwTZs2OFYHMsxSRmVZWVlNnDiRlTA6j1uNnWyMXbdu3caO\nHXvy5MnXr1+XlJTk5ORER0f//PPPTZs2/e6775ROtAaqsm7dOnd397KVBQsWdOnSha08wCnb\nt293c3N7+PAhETVr1mzatGn49wgAFfv888/nzp1rZGTE3HR2dj548GCjRo3YTaWrOHpVbGxs\nrI2NzYABA5o1a2ZkZPT06dNjx44lJyeLxeJFixYVFhYuX75c7ntzc3MzMjKY7bS0NI3m1i11\n69aNjo4ODQ2dP3++l5fXtm3bcEksMG7fvj1lyhSR6L8py5iPATNmzGAxFQBwHI/HW7FixcyZ\nM+/fv1+rVi1vb29TU1O2Q+kuKZeYmJgwqaZOncosgSBTVFRU9o9HZGSk3PeuX79e7kf74Ycf\nNJhd1zDLxQ4dOpTtIMAhkydPVnwP8fDwYDsXcIJIJPrqq6+Yt3Fzc/PvvvuupKSE7VAAeodb\nR+xev34tlUr5fL6VlZXclwQCwZo1a54/f/77778T0apVq44ePVp2Bzs7O2ZsBxG9ffv2yZMn\nmsmsk8RicXh4OBHFx8c/evSocePGbCcCTkhNTa1iEfRQUFDQn3/+yWzn5+cvXLgwPj5+9+7d\n7KYC0DfcGmNXq1Yta2trxa5ORrb+wfnz5yWSd9aWHjp06O1/Ka43DFWXk5PTvn37Tz/9lIii\no6N9fX1DQ0PZDgWc0LBhQ8UiBsoAEd25c0fW1cns2bPn6dOnrOQB0Fvcauwq1bJlS2NjYyLK\ny8vLyspiO45umj59elRUlOxmUVHRl19+efv2bRYjAUd89tlnirPhfPnll6yEAU45fPhwteoA\noCZa1tjxeDwzMzNmu+wIblAViURy8OBBxfqhQ4c0Hwa4Ji4urri4WK54//59VsIAp0jLuTha\n7tQKAKibljV2IpEoJyeH2ba1tWU3jE4qKioqLCxUrMsuWAZ9prS/R9MPRDRkyBCl9WHDhmk4\nCYCe41Bj98cff0yaNKlXr17bt28vb59Lly4xn/+8vLxwsbQ6mJqaKh0y1bx5c82HAa7Jy8tT\nLObm5mo+CXBN27Zte/XqJVccPny43KSYAKBuHGrs3rx5s3nz5jNnzixbtqyoqEhxB4lEsmzZ\nMma7f//+mk2nR1auXClXady48fjx41kJA5zi7e2tWPTx8dF8EuCg33//ffr06cwoTBMTk/nz\n5+OSWADN41Bj9/HHH9epU4eIEhMThw0bJncYoLCwcMKECZcvXyYic3NzxfVJQFWGDh26Z8+e\nBg0aEBGfzx88ePDp06exViwQ0YwZM5gXhoyJicmPP/7IVh7gFBMTk9DQ0NWrVxPR+vXrv//+\ne6ULTwOAWnFoHjtzc/OtW7cOHjxYIpGcOHHC2dmZOYxvYmKSkJDw+++/M9Nl8Xi8HTt2ODg4\nsJ1Xl40YMaJbt27169cfOHCg3HyBoM9sbGwiIiJmz579559/SiSS1q1br1y5skOHDmznAk4Q\nCoVff/31hg0biOjTTz+Ni4tbtGgRxswAaBiHGjsiGjBgwJEjRyZOnJiRkZGbm7t161a5Hezs\n7LZv396nTx9W4ukhPp9Dx3SBC9zc3Hbv3t25c+f79+8fO3asfv36bCcCrpg0adK+ffuY7eLi\n4pUrV2ZnZ2/atIndVAD6hnN/tgcNGpSQkBAaGhoYGOjo6CgQCExMTOrXr9+vX79169Y9e/YM\nXR0Ai37//Xc3NzdmihN3d/eFCxeynQg44cGDB7KuTmbz5s1YBAhAw7h1xI5hbW09ffr06dOn\nsx0EAN7x8OHDUaNGFRQUMDeLiooWL17s7Ow8YcIEdoMB6+Li4sqru7m5aTgMgD7j3BE7AOCs\nDRs2yLo6GWawPOg5GxsbpfXatWtrOAmAnkNjBwBVlZycrFh88eKF5pMA13Tt2tXFxUWu6OXl\n1bZtW1byAOgtNHYAUFVKL5WQmwAF9JOpqem+ffvs7e1llXr16u3fv9/IyIjFVAB6CI0dAFTV\n5MmTFWev+PLLL1kJA1zTsWPHx48ff/LJJ0Q0YcKER48e+fr6sh0KQO+gsQOAqmrevPmuXbvs\n7OyYmwKB4Jtvvpk4cSK7qYA7atWq1bFjRyLq0qWLhYUF23EA9BEaO6gIszIvgMzQoUOfPn3K\nLCOWmJi4dOlSthMBAMB/0NiBEjt27GjTpg0RHTt2rF+/fk+fPmU7EXCIhYVFrVq1iKjsgCoA\nAOACLs5jB+w6cODA2LFjmW2pVBoeHh4fH3/nzh2cWAEAAIfMwX0AACAASURBVOA4HLEDefPm\nzZOrJCQkbNmyhZUwAAAAUHVo7OAdhYWFSUlJivXY2FiNZwEAAIDqQWMH7zA2Nlacz4IwfTwA\nAIA2QGMH7+Dz+SNGjJArmpiYBAcHs5IHAAAAqg6NHchbvXp1+/btZTeNjY1XrVrVsmVLFiMB\nAPeJRKJvv/12zpw5RPTFF18sXbq0uLiY7VAAegeNHcizsrK6evVqWFgYEfn4+ERHR3/22Wds\nhwIArps2bdqyZcvy8/OJKDc3d8GCBXPnzmU7FIDeQWMHSvD5/MDAQCJyd3f38PBgOw4AcF1s\nbOzWrVvlij///PPz589ZyQOgt9DYAQBATcXExCitR0dHazgJgJ5DYwcAADVlZWWltG5tba3h\nJAB6Do0dAADUVNeuXZ2cnOSKrq6u7dq1YyUPgN5CYwcAADVlbm6+e/fussfnbG1t9+3bJxAI\nWEwFoIfQ2AEAgAr4+fk9fvx4+PDhRDRq1Kj4+PgOHTqwHQpA76CxAwAA1ahbt66fnx8RBQQE\nYLkaAFagsQMAAADQEWjsAAAAAHQEGjsAAAAAHYHGDgAAVOPKlSvbt28nos2bN9+6dYvtOAD6\nCI0dAACowObNm7t27Xrz5k0iioyMbNeu3d69e9kOBaB30NgBAEBNpaenT58+Xa44ZcqUnJwc\nVvIA6C00dgAAUFNXr14tLCyUK+bm5jIH8ABAY9DYAQBATUkkkmrVAUBN0NgBAEBNtW/fXnH1\nMFNT07Zt27KSB0BvobEDAICaqlev3pIlS+SKP/30E9afANAwNHYAAKACc+fOPXbsWNOmTYnI\n29v79OnTU6ZMYTsUgN5BYwcAAKoxcODAadOmEdHMmTM//PBDtuMA6CM0dgBQPbt3746JiSGi\npUuXlpSUsB0HAAD+g8YOAKqhS5cun3zySVZWFhEtWbLEwcEBE5UBAHAHGjsAqKoffvghMjKy\nbCUrK6tXr15s5QEAADlo7EC527dvE1FycvLr16/ZzgJcERYWpljEkqAAANyBxg7kiUSifv36\nDRo0iIhu3rzp5eWFBR+BkZ+fr1jEDLQAANyBxg7kzZs3Lzw8XHYzNzd34sSJcXFxLEYCjmjU\nqJFi0dzcXPNJAABAKTR28A6pVKp4uq2goGDPnj2s5AFOWb9+vWLxyy+/1HwSAABQCo0dvKOw\nsDAvL0+xnpaWpvkwwDWXL19WLMbGxmo+CQAAKIXGDt5hZmbm5OSkWPf09NR8GOCaixcvKhYv\nXLig8SAAAKAcGjuQt3DhQrlK/fr1x48fz0oYAAAAqDo0diBv0qRJK1eutLCwYG62a9cuPDzc\n1taW3VTABd27d1cs9ujRQ+NBAABAOTR2oMScOXMyMzNjYmJSUlJu3Ljh7e3NdiLghEmTJjVu\n3LhsxdTUdPXq1WzlAQAAOWjsQDmBQNCsWTOl4+1Ab8XExCQlJZWtFBYWHj9+nKU4AAAgD40d\nAFTVpk2bRCKRXPGXX35hJQwAAChCYwcAVfXq1SvFYkpKiuaTADcVFRVFR0cT0YMHD0pKStiO\nA6CP0NgBQFW5uLgoFl1dXTUeBLgoOjq6efPmzCzWq1ev9vHxSUhIYDsUgN5BYwcAVTVlyhTF\nBcRmz57NShjglOLi4uDg4MTERFklLi4uODhYLBazmApAD6GxA4Cqaty48YEDB+rVq8fcNDU1\nXbZs2ZgxY9hNBVwQGRmpuKL03bt3o6KiWMkDoLcM2Q4AANqkb9++iYmJMTExQqHQ19fX2tqa\n7UTACenp6UrrWI0QQMPQ2AFA9ZiYmLRp04btFMAtbm5uSuseHh4aTgKg53AqFgAAaqp169Z9\n+vSRKwYFBcnNaA0A6obGDgAAaorH4+3cufOjjz7i8XjMzbFjx27atIntXAB6B40dAACogK2t\n7b59+zIzM+/evZudnb1t27ZatWqxHQq45dmzZ0KhkO0UOg6NHQAAqIyNjY2vry9aOpAzc+ZM\nIyOjRo0aWVpa2tnZnTt3ju1EOguNHQAAAKjRokWL1qxZU1paytzMyMjo06fP8+fP2U2lq9DY\nAQAAgBqtWLFCrlJaWjpx4kRWwug8NHYAAACgLhKJRCQSKdax4pyaoLEDAAAAdeHz+cy10nIs\nLS01H0YfoLEDAAAANWrRooVicerUqZpPog/Q2AEAAIAanTt3zsrKqmyld+/ekydPZiuPbsOS\nYgAAAKBGdevWzc7OXrhw4d9//21lZTVp0qT+/fuzHUpnobEDAAAA9eLz+UuWLGE7hV7AqVgA\nAAAAHYHGDgAAAEBHoLEDAAAA0BFo7AAAAAB0BBo7AAAAAB2Bxg4AAABAR6CxAwAAANARaOwA\nAAAAdAQaOwAAAAAdgcYOAAAAQEegsQMAAADQEWjsAAAAAHQEGjsAAAAAHWHIdgA1ysrKevr0\nKdspAAAAAFSmYcOGPB6v3C9LdVFkZKSXl5cGf8kAAAAAmpCfn19BC8STSqVsJ1SL06dPh4WF\nsZ1Ci719+/bcuXN2dnbdu3dnOwtwzpkzZ3Jzc/v162dqasp2FuCW2NjYhw8f+vj4eHp6sp0F\nuEUoFJ46dcrGxiYgIIDtLNpt165dxsbG5X1VZxs7qKH79+/7+vp269bt4sWLbGcBzmnWrFls\nbGxKSoqTkxPbWYBblixZ8r///W/VqlWzZs1iOwtwS2JiooeHR5s2bW7dusV2Fl2GiycAAAAA\ndAQaOwAAAAAdoctXxUJNWFpaBgQEeHt7sx0EuKhjx45OTk4VDPIAvdWoUaOAgAAXFxe2gwDn\nmJmZBQQEYPClumGMHQAAAICOwKlYAAAAAB2Bxg4AAABAR6CxAwAAANARaOx0TXFx8dGjRz/7\n7LNWrVrVq1fPxMTE1NTUwcGha9euM2fOvHTpUqX3IJVKIyIivvjii65duzo6OpqbmxsaGlpa\nWjZs2LBnz57fffddXFyc0m88f/48r5pEIpGqfwFQDeU9ZUZGRnZ2dp6enr179166dOnVq1ff\n737w1GsvsVh8/PjxmTNntm/f3sXFxcLCQiAQ2NjYNG3adMiQIT///POrV68q+PayLwlLS0uh\nUFiVB01ISMCLhCN69+7NPAvz58+veE9XV1dmz61bt1awW15enkAgYPa8e/cu4UWiPhpZ4gs0\nZNOmTQ0aNKj4Gff19b18+XJ59xAVFdWqVauK74HH440ePTovL0/ue8+dO1fdl19hYaGafyVQ\nkao/Zb6+vgcOHKj5/eCp1wpbtmxp2LBhxc+goaHhhAkTsrKylN6D3Etiy5YtVXncr7/+Gi8S\njvj111+ZZ8HHx6eC3WJjY2XP1/DhwyvY89ixY8xuTk5OEolEiheJ2mC6Ex1RUFAwduzYQ4cO\nySpubm6tW7e2s7OTSqUvX768fv16eno6Ed27d69bt26rV6+ePn263J3cuHHD398/Pz+fiMzM\nzAIDA1u3bm1vby8QCHJzc+Pj40+dOvXkyROpVLpz587k5OSzZ88aGip5CdWuXXvcuHFVia30\n20HzbG1tp02bJrtZWlqalZX16tWra9euyV42wcHBf/zxx4YNGywtLcu7Hzz12k4oFI4fP77s\nO0mjRo1atWpVp04dIkpLS3vy5MmDBw+IqLS0dMuWLRcvXjx79mwFXSCPx5NKpWFhYSEhIRU/\ntEQi2bVrl+xbVPPzwPvq27cv857w4MGD169fOzg4KN3t9OnTsu3z58+LxWIDAwOle545c4bZ\n6NOnD+/dBezxIlExNrtKUBGxWNyrVy/Zczp48ODo6GjFff788093d3fZbrt27ZLbp0mTJsyX\n+vXrl56ervhAEonkp59+4vP/OYO/Zs2asl+Vffzy8vJS7Q8IalKVp+zq1asDBw6UvWy6detW\nVFT0HvcD3FdaWtqzZ0/Zcz1ixIi4uDjF3Z4+fTpr1izZ+0CTJk0qOH4vOwPw6NGjih/97Nmz\nzJ4+Pj7MBg7GsKtp06bME7Ft27by9vnwww+JyMrKitnz6tWr5e3ZqFEjZp/ff/+dqeBFoiYY\nY6cLli1bxnxs4vF4oaGhR48ebd68udw+fD6/f//+N2/e9Pf3ZypTp05lDsYwbt26xQyec3Jy\nOnjwoJ2dneID8Xi8mTNnLly4kLm5evVqiUSijp8IuKNjx47Hjh3bvn27QCAgokuXLn3xxRds\nhwK1WLRoEfO31tDQcPv27Xv27GncuLHibg0bNly1alVERISJiQkRxcXFLVq0qLz7DAgIYA7P\nhIWFVfzo27ZtIyIXFxc3N7ca/BCgMv369WM2yh6WK6uwsJAZtz1mzBjmGLzssJycxMTEp0+f\nEpFAIAgICJD7Kl4kqoXGTutlZmYuX76c2Z4zZ47iCdaybGxsZE2bsbFx2UHxjx8/ZjY++OAD\nU1PTCu5kxowZY8eO/eGHH9atW1daWlrTHwC0wZgxY3777Tdme/PmzTExMezmAZVLS0tbtWoV\ns7148eIxY8ZUvH+3bt1+/fXX5s2bz5o1q2/fvuXtZmdn16FDByLatWuXWCwub7fc3FxmDNaA\nAQOKiore5wcAVZM9refOnVP6Gf7SpUvMtQv+/v7MIbTyGjtZa9itWzcLCwu5r+JFolpo7LTe\nunXrCgoKiMjZ2Xnp0qWV7l+7du0DBw5ERES8fv160KBBijvk5uZWfA9WVlbbtm2bN29e//79\nmaM4oA9CQkKYw70SieSHH35gOw6o2Nq1a5k/0p6enl999VVVviUkJCQ6OnrVqlV+fn7l7VNS\nUjJ06FAiSk1NPXnyZHm77d+/v7CwkIiCgoJwnSNHdOrUycbGhoiysrJu3rypuIOsjevUqVOn\nTp2I6NatW9nZ2RXsqfQzAF4kqoXGTuudOHGC2ZgyZYqRkVFVvsXPz8/Pz09uiGuzZs2YjXPn\nzt25c0e1IUE3zJ07l9k4deoUzsLrmPDwcGZj6tSpsvFzNVdSUhIUFMTcYQUn2rZv305Erq6u\nnTt3Li4uVtWjQ00YGhoyQ+ionLOxTLFp06Z2dnYffPABEYnFYsVr5IuLiy9evMhsl9fY4UWi\nQmjstJtQKJQ1Yb17967JXbVs2bJt27ZEVFJS4ufnt3r16koP3YG+6datGzOsKjs7m5mJCnRD\nTk4Oc60rEZW9fqLmJBKJs7Nzjx49iCg8PLzsuF6Zx48fX7t2jYjGjh3L4/HwmYE7ZH2YYmP3\n4sWLR48eEREzZs7Pz4/pzBTPxkZGRjJz1Hl5eZW9gE8GLxLVQmOn3Z49e8aMSBAIBC1atKjh\nve3evbtu3bpElJubO2vWLDs7O39//6VLl164cIGZAwX0nLGxsey6nGfPnrEbBlTo2bNnzF9K\nMzMz2dXxKsRMY1FSUsLMVSGHORLD4/EqHdgHGta7d2+mXbt161ZWVlbZL8kaOKaxs7W1bdmy\nJSlr7GSXslYwFpPwIlEdNHbaTfYvzdbWtrzZg6rO09Pz7t27Q4YMYS5QKi4ujoiIWLBgQY8e\nPaytrdu2bTt37twLFy7gggl9xsxnRkQZGRnsJgEVyszMZDZsbW3l5hhTicGDBzOjtZirGsuS\nzUzm5+fn6uqq8oeGmrC1tWUua5BIJLL+jME0cEZGRt27d2cqzLHelJSUhw8fKu5JlTV2eJGo\nCho77ZaXl8dsmJmZqeQOnZycjhw5Eh0d/dVXX8lG3RFRaWnp7du3f/zxxx49ejCTHVQwxOHx\n48dVWVRq1KhRKskMmmRubs5sKD2Ii6deS1XlneT06dMVPKehoaEV3L+xsfHIkSOJ6OHDhzdu\n3Cj7pbNnz6akpBDR2LFja/6DgMopPRsrFov/+usvIurQoYNsxvLAwEDFPdPT0+/du0dElpaW\nXbt2reCB8CJRFTR22k02L0lOTo4K77ZZs2bLly+PiYl5/fr10aNHZ8+e3blzZ2NjY+arL1++\nnDNnTpcuXZKTk1X4oKAVZOs5Ks5ZANpL1s+pb2Tt+PHjmQ250fHMKTZLS0vmukjgGlljd+bM\nGem/iz3cvHnz7du39O6IzM6dOzMf/MqejT137hzzXYGBgZVe3ocXiUpgVR/tZm9vz2xkZ2cX\nFhZWPP/c+93/4MGDBw8eTEQikejChQtbtmw5evQoEd26datPnz53795VXBvK2tqa+eBVsXbt\n2qk2LWgAM8soEdWvX1/xq3jqtZRswaiMjIzi4mKl0xg5Ozsrrvj08OHD69evV+UhWrZs6evr\ne+/evf3794eGhjJvVm/fvv3jjz+IKDg4WFWnHUC1fHx8nJ2dk5OTX79+ff/+fV9fXyozbE52\nlI6IBALBBx98cOrUqcuXL8v+HlVxgB0DLxLVYHvpC6gRkUgk66suXLigmQc9ceKE7H1/3759\nsjrWldI61X3K0tPTZQOwkpKS3vt+gGsKCwtl7yQVrAqlaM2aNcx3lbfA4MKFC2XFtWvXMsWd\nO3cylfXr1zOVyMhI2W6dO3dmilgtiiM+/fRT5hlZvnw5U2FmrbOxsRGLxWX3lL0eTp8+zVQc\nHR2JiMfjpaamyt0tXiRqglOx2s3Y2Lh9+/bM9uHDh6v+jcycxu+nb9++soXemWEWoCeOHDki\nlUqJyN3d3cXFhe04oDImJibMGHkiYib3V4eRI0cyIzpkJ9qYU2yenp5MowDcJDvYxiwglpeX\nx8xX7O/vLzfloewA3oULF4goJiYmNTWViFq3bi07KlwxvEhqDo2d1pONOdi+fbvS6X8UPXr0\nyNHR8fPPP3/x4kXZekpKimxhsYoxR+OpzMV0oPMKCgpkS06NGDGC3TCgcsHBwczGpk2bVDtm\nV8bGxoZZ7ebSpUtpaWnx8fHMGHnZB0XgJn9/f2YCy8jISIlEcuXKFWZuhLLnYRlNmzatV68e\nETEzEss++cuWna0UXiQ1h8ZO640bN65WrVpElJ+fLxt5WgGRSDRy5Mjc3Nxff/113bp1TPHU\nqVP29vb169cfNmyY9N/hsRV49eoVs8EsOwv6YN68eU+ePCEic3PzKVOmsB0HVGzs2LG2trZE\n9PbtW9mpt0pVsLKnUswoPalUeuLEiSNHjhARn8//5JNPqhkWNMrMzIxZNS43N/fevXtXrlxh\n6oqNHf17OUVUVJRQKLx8+TJTrMoAOxm8SGoIjZ3Ws7a2XrJkCbMdHh4+fvz4CuaZy8vLGzhw\nILNYhYuLyzfffMPUW7VqxVziFBMT8/PPP1f8iDk5OTt27GC2mWVkQLdJpdKFCxf++uuvzM1F\nixZV8awKaBELC4sff/yR2T5w4MAXX3xR6eT+R48eXbx4cbUexd/fnzmJf+rUKWYRs8DAQOYY\nD3CZrDO7fPlyZGQkEXl5eSkdj8E0dqWlpdeuXWNaQHt7+9atW1f9sfAiqSE0drpg2rRpw4YN\nY7a3bdvWrl27s2fPyr0pi8XiI0eO+Pr6MtcomZubHz582MrKivmqvb39jBkzmO1Zs2bNmTNH\nbpJxmdu3b/v5+THncBs1ajRkyBA1/VDAEffu3evVq9fixYuZQ7mDBw+eNWsW26FALcaNGzdh\nwgRme+3atZ07d/7rr78UD+EXFRWFh4f7+fkNHTqUmR6lTZs2w4cPr8pD8Pl8ZuWAiIgInGLT\nIrLGLiIi4tatW1TO4Toi6tmzJ3OJ1fbt29PS0oioT58+1Zr1Gi+SGsJ0J7qAx+Pt2bPHxMRk\n9+7dRHT37t0PP/ywTp06HTt2tLe3NzQ0TElJuXbtmmypgLp16x47dqxNmzZl72Tp0qUPHz4M\nDw+XSCSrVq1au3Ztly5dWrRoYW9vLxAI8vPznz9/fv36ddmU4ra2tgcOHFD5BCvAioyMjEWL\nFpWtFBUVpaam3rhxg1kOkjFixIht27apY2UC4IiNGzeamZn98ssvRHT9+vWAgAA7O7suXbo4\nODiYmJhkZma+ePHi+vXrIpGI2Z/H440ePXr9+vVVfysYN27ckiVLsrOzicjGxmbgwIFq+llA\nhVxdXZs1a8b8jWDOv3/44YdK97Szs/P19b179+6BAweYSrXOwzLwIqkRFq/IBZXbu3dvw4YN\nK3i6DQwMRo0alZaWpvTbxWLxDz/8wIzYq1jfvn0TExPlvh1zXmgd2VNWKVdX171791Z6P3jq\ndcOZM2e8vb0rfVX069fvzp07Su9B6UwWMv7+/sxXP/vsM8WvYiYLbpo7d67sqRcIBEKhsCp7\nGhkZ5eTkKN0NLxI1wRE7nfLxxx8HBQWdOnXq+PHjUVFRz549y83NNTQ0tLW1bdasmZ+fX3Bw\ncAWdH5/Pnzdv3tSpU//4449z5849fPjw+fPnQqGwtLTUwsLC1ta2SZMmHTp0GDp0qDqWCQdO\nMTAwsLS0dHFxadOmTf/+/fv27as4EzXoqsDAwMDAwMuXLx8/fvzGjRsJCQnZ2dklJSVmZmb1\n6tVr2rRply5dBg0aVPHHyAqEhIQw10tihSgt0rdv35UrVzLbnTp1kq0uqCgwMFC2Z9euXWVj\nfqoFL5L3xpNW4RJIAAAAAOA+XDwBAAAAoCPQ2AEAAADoCDR2AAAAADoCjR0AAACAjkBjBwAA\nAKAj0NgBAAAA6Ag0dgAAAAA6Ao0dAAAAgI5AYwcAAACgI9DYAQC8v1GjRvF4PB6Pd+LECZXc\nYffu3Zk7jImJkRW7dOnCFB89eqSSRwEAXYXGDgC45fz587x/WVpaCoXCqnxXQkICrwyRSKTu\nnAAAHITGDgC4SygUHjhwoCp7bt++Xc1Z2OTh4eHj4+Pj42NiYlK2PnnyZB6Pt3z5craCAQDX\nGLIdAABAOR6PJ5VKw8LCQkJCKt5TIpHs2rVL9i0aSadR27ZtU1q/ceOGhpMAAMfhiB0AcFTL\nli2J6OrVq48fP654z7/++is5OZmIvL29NZGMGwoKCsqOwwMAIDR2AMBZAQEBPB6PiMLCwire\nkzmg5eLi4ubmpolk3BAVFVVaWsp2CgDgFjR2AMBRdnZ2HTp0IKJdu3aJxeLydsvNzT127BgR\nDRgwoKioqOL7vHDhwsSJE5s0aWJtbS0QCBwcHDp16vTtt98yB/zKk5SU9Pnnn3t6epqZmdnY\n2LRo0eLrr79OSUmp9EcQiUSbN2/u37+/q6urubm5kZGRnZ1d165dly5d+ubNm0q/XUbuqthF\nixbxeLwPPviA+er8+fOZr/bq1atnz57M9pYtWyq4w2HDhjG7bdy4seoxAID70NgBAEeVlJQM\nHTqUiFJTU0+ePFnebvv37y8sLCSioKCgCi6GzcvLGzBgQI8ePbZs2fLo0aOcnJySkpK0tLRr\n164tW7bMw8NjzZo1Sr/x5MmTzZs3//XXXxMSEgoLC9++fRsTE/PDDz/4+vpevnyZzy/3XfT+\n/fuNGzeeNGnSiRMnnj9/XlBQUFpampGRceXKlQULFjRp0uTChQvV+HVUzYQJE5iN8oblEZFQ\nKGR+nyYmJh999JHKMwAAi9DYAQBHlZSUBAUFMZ1TBWdjmethXV1dO3fuXFxcrHQfsVjcp0+f\n48ePE5G9vf33339/8eLFqKio48ePT5gwwcDAoKioaObMmb/++v/27iwkyu+NA/gz7tr4c40U\nzSVSLENbxRQ0TdRKUSsVNFusLioMC0miyDTDbpKIf3URqUXhmgtqo5mWgWTYqpnRWLaQJmWa\nmhYu7+/i8DsMs2WL2/y/n6sz57znfc8MKA9ned7/yXXs6OiIjIz89u0bEa1Zs6agoODhw4e3\nb99OTU0dGxuLiorq6+tT+sQvX74EBwe/ffuWiDw9PS9cuFBTU1NXV5eVlcVm2np6esLCwiYy\n7ado//79Uqk0KSmJfUxKSpJKpVKpNDs7OyIiwsLCgtTuTSwrK2OhcEREhImJyW8MAABmLgEA\nYCapqalh/51SUlIEQQgICCAiXV3d7u5uxYt5wt7jx48LguDt7c0+Dg8Py16WmZnJ6l1cXD59\n+iR3k9LSUraZz8jIqLOzU7Zpy5YtrGN4ePj4+LhsU0dHh7W1Nf9fWl5eLtt64sQJVu/l5fXj\nxw/ZpvHx8fDwcNaalJQkNxhfX1/W1NLSwiv592pra+OVGRkZrDIjI0P2DomJiaw+OTlZ8RcT\nBCE0NJRdUF1drfQCAJi9MGMHADMay3UyMjLCEprIYdN1IpFo27Ztqu4gCMLZs2dZ+dy5c5aW\nlnIXhIWFsUhraGjo8uXLvH54eLi4uJjdPzMzkwV/nIODw8mTJ1U9VFdXNzg4eMWKFQcPHtTT\n05NtEolEfLKttrZW1R1+G1+NvXLliuLexL6+vurqaiKytbVlQTMAaBIEdgAwo0VERJiZmZGy\nTWM8fZ2fn5+Dg4OqOzx9+vTNmzdEZGtr6+/vr/SamJgYVpDdzNfY2Dg0NEREbm5ujo6Oir0i\nIyPlgjYuOTlZIpE8ePCAbROUs3jxYlbo7OxUNezf5urqyg6ddHV1VVVVybWWlJSwBeutW7eq\n2SAIALMU/qoBYEbT19ePjY0lotbWVrl8vDdv3mR71LZv367mDg8ePGAFFu4otXLlSlZ48uSJ\n8F+K4+fPn7OCu7u70l5isdjFxWUCX4KIaHx8/MePH9+/f//+/TuPqCbp1Wd80k5xb2JeXh4r\nqP/RAGCWQmAHADNdfHw8K8iFKWwd1tjYWOmsGPfu3TtWWLBggapr7Ozs2ErrwMDAwMAAq+Qn\nG2xsbNR0VPPompqa+Ph4Nzc3Y2NjHR0dAwMDQ0NDQ0NDU1NTNb3+XHR0tFgsJqLy8vLPnz/z\n+s+fP9fV1RGRt7e3k5PTpI4BAKYFAjsAmOmWLVu2dOlSkslsQkR9fX1lZWVEFB0dbWRkpKb7\n169fWYHFOkppaWkZGhqycn9/PysMDg6ywpw5c1R1VHXPwcHB9evXBwYGZmdnt7S0DA4OClP4\nrjOxWBwdHU1EIyMjV69e5fVFRUUsp/GOHTumbDAAMJUQ2AHALMCOUPT39xcVFbGavLw8to75\nt2IUHnjxQxK8Rk1MNjIyorQ+Li5OIpEQkYmJSWpqalNTU09Pz8jICDu2xsPTyaM0oV1+fj4R\nGRkZRUVFTfYAAGBaILADgFkgNjZWX1+fZFZj2TqsDaPxygAABSZJREFUs7Ozl5eX+r583ZOv\nsSoaGxvjwRZP7cYn6tgRCqX49J6sx48fs5dhGBgY1NfXHzt2bOXKlebm5jo6OuwCVeHgX+Tp\n6blkyRIiam5ubm1tJaKurq67d+8S0aZNm4yNjSd7AAAwLRDYAcAsYGZmxjKS1NfXd3d3v3z5\nkh2kmMh0HT8w++rVK1XXdHR08Afx1dV58+axgpo0wkrvyVPxRUVFKT14wR83qdg0J/13YKKg\noGB8fJxwbAJAoyGwA4DZgYUpgiBUVFRcv36diLS0tOLi4n7acdWqVaxw7949VYuqjY2NchcT\n0aJFi1jh6dOnSnt9+PDh9evXivUfP35kBVdXV6UdCwsLfzrsPxcXF8emOVlgd+3aNSKyt7f3\n8/ObgqcDwLRAYAcAs8PatWvt7e2JSCKRVFZWElFgYKCa86rckiVLWFKSrq4ulptXEc9LvHHj\nRl7p6empq6tLRM3NzUoDOFXvY+XnMJS+cOzt27f83WXsKMMfUnUTCwsLNs3Z3t6en5/f1NRE\nRNu2bZPLtAwAmgSBHQDMDlpaWuz1EnV1dRNfh2UOHDjACgkJCbLpP5isrKxbt24R0bx581jO\nPMbU1DQoKIiIBEHYv3+/XPzU2Nh46tQpbW1txce5ubmxQmlpqVyvN2/ehIaGzp8/n2Vd/vbt\nW29v7wS/hRy+d1Aqlaq6hq/G7t27l372ig4A0AAI7ABg1tixY4dIJOrt7R0dHTUzMwsLC5tg\nx927dwcGBhJRe3u7m5vb6dOnGxoaHj58WFxcHB0dzaIfbW3tnJwcufQlaWlpLHSrrKz08PA4\nf/78jRs3cnNzd+/e7ePjY25urnQtOCQkxMLCgoja2tqCgoIkEsmzZ89qamoOHDjg7u4ulUpz\ncnL4Ou/hw4ebm5vfv3//q7/GwoULWSEvL+/o0aNXrlxJT09nu+i4gIAA9s6ML1++EJGPj4+a\nZH4AoAmm5Q21AACq8JMHKSkpiq1r165lrfv27VNs9fb2Zq3Dw8NyTUNDQ5s3b1b1n9Dc3Lyi\nokLpeC5fvswWZOVYWlo2NDQcPnyYfSwpKZHtVV5ervRtY//8849EIhEEITMzU7Y+OTmZdfT1\n9WU1LS0tit+rra2NV46OjvLokOMZVbi0tDTempOTo+JXBwANgRk7AJhN+Nrirx7tNDQ0LCws\nvHPnTnx8vLOzs7GxsZ6enpWVVUBAwOnTpzs6OjZs2KC049atW588ebJz505HR0cDAwMTExNX\nV9dDhw49evTIy8vL3NycXSaXEiUkJOT+/fsxMTE2Nja6urqWlpbLly9PS0t78eJFcHAwESUk\nJBw5csTOzk5fX9/JyYllYP4l2traVVVVERERc+fO1dfXt7GxWbduneLrX+Pj41mlWCxWE9oC\ngGYQCVOYDB0AAKZYS0sL2/O3a9euixcvTvdwAGByYcYOAECTnTlzhhX27NkzvSMBgCmAGTsA\nAI3V3Ny8YsWK0dFRf3//2tra6R4OAEw6zNgBAGimjx8/RkVFjY6OikSi9PT06R4OAEwFneke\nAAAA/E1lZWVaWlqtra1nzpzp7u4mosTExNWrV0/3uABgKmApFgBAo1hZWbF4jomMjMzNzVWa\nSBkANA+WYgEANIq1tbWenp5YLPbw8Lh06VJBQQGiOoD/H5ixAwAAANAQmLEDAAAA0BAI7AAA\nAAA0BAI7AAAAAA2BwA4AAABAQyCwAwAAANAQCOwAAAAANAQCOwAAAAANgcAOAAAAQEMgsAMA\nAADQEP8Ch8FxrM9XlQoAAAAASUVORK5CYII=",
      "text/plain": [
       "plot without title"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 300,
       "width": 420
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "colors <- c(\"#909842\", \"#1E88E5\", \"#FFC107\", \"#004D40\")\n",
    "\n",
    "options(repr.plot.width = 7, repr.plot.height = 5)\n",
    "\n",
    "\n",
    "bxp <- ggboxplot(df_val, x = \"modality\", y = \"MAE\", add = \"point\", \n",
    "                 xlab = \"Modality\", ylab = \"MAE [years]\", fill=colors) + theme(text = element_text(size=20))\n",
    "\n",
    "\n",
    "bxp <- bxp + \n",
    "  stat_pvalue_manual(pwc, hide.ns = TRUE, coord.flip=FALSE, label = \"p = {p.adj}\", step.increase=0.035) +\n",
    "  labs(\n",
    "    subtitle = get_test_label(res.aov, detailed = TRUE),\n",
    "  )\n",
    "\n",
    "# add the MAE results for the test set\n",
    "bxp <- bxp + geom_point(data = data.frame(x = factor(result_mean[[\"Group.1\"]]), y = result_mean[[\"abs_diff\"]]),\n",
    "                   aes(x=x, y=y),\n",
    "                   color = 'red', shape=8, size=5)\n",
    "\n",
    "\n",
    "bxp"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "R",
   "language": "R",
   "name": "ir"
  },
  "language_info": {
   "codemirror_mode": "r",
   "file_extension": ".r",
   "mimetype": "text/x-r-source",
   "name": "R",
   "pygments_lexer": "r",
   "version": "4.1.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}