{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "17aa2aac",
   "metadata": {},
   "source": [
    "In this tutorial, we are going to discuss the various R functions that can be used to perform **nonparametric** tests that we have learned in class.\n",
    "\n",
    "Remember that nonparametric tests are used as an alternative to parametric tests when the assumptions of the latter are not met. Here is a summary of the nonparametric tests that can be used as an alternative to the tests covered in this course:\n",
    "\n",
    "- Parametric: `t.test` $\\longleftrightarrow$ Nonparametric: `wilcox.test`\n",
    "- Parametric: `aov` $\\longleftrightarrow$ Nonparametric: `kruskal.test`\n",
    "- Parametric: `cor.test(...,  method = \"pearson\")` $\\longleftrightarrow$ Nonparametric: `cor.test(...,  method = \"spearman\")`"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "37f23c24",
   "metadata": {},
   "source": [
    "# Wilcoxon rank-sum  and signed-rank tests\n",
    "\n",
    "The **Wilcoxon rank-sum test** is a nonparametric alternative to the **t-test** (one and two-sample). In the case of two samples, it is generally used to determine if they have the same distribution or not, based on their rank order. In some special cases, when both distributions have the same shape and only differ in their location, the test can be referred to as a test of the difference in medians.\n",
    "\n",
    "Similarly, for the two-sample case, the Wilcoxon rank-sum test is also known as the **Mann-Whitney U test**, and both terms are often used interchangeably.\n",
    "\n",
    "In the case of two paired samples, the **Wilcoxon signed-rank test** is an alternative to the **paired-sample t-test**.\n",
    "\n",
    "In R, we can perform both nonparametric tests using the `wilcox.test` built-in function."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "950fdda5",
   "metadata": {},
   "outputs": [],
   "source": [
    "?wilcox.test"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c228cd86",
   "metadata": {},
   "source": [
    "- If only one vector is supplied, we would run a one-sample Wilcoxon rank-sum test.\n",
    "- If two vectors are supplied instead, we would run a two-sample rank-sum test.- \n",
    "- In this last case, if we set the argument *paired* to TRUE, we would be assuming that both samples are paired, and it would correspond to the Wilcoxon signed-rank test."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4a6a5936",
   "metadata": {},
   "source": [
    "Let's show the use of this function by means of the following datasets:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "acda973b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "── \u001b[1mAttaching packages\u001b[22m ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
      "\u001b[32m✔\u001b[39m \u001b[34mggplot2\u001b[39m 3.4.0      \u001b[32m✔\u001b[39m \u001b[34mpurrr  \u001b[39m 1.0.1 \n",
      "\u001b[32m✔\u001b[39m \u001b[34mtibble \u001b[39m 3.1.8      \u001b[32m✔\u001b[39m \u001b[34mdplyr  \u001b[39m 1.0.10\n",
      "\u001b[32m✔\u001b[39m \u001b[34mtidyr  \u001b[39m 1.2.1      \u001b[32m✔\u001b[39m \u001b[34mstringr\u001b[39m 1.5.0 \n",
      "\u001b[32m✔\u001b[39m \u001b[34mreadr  \u001b[39m 2.1.3      \u001b[32m✔\u001b[39m \u001b[34mforcats\u001b[39m 0.5.2 \n",
      "── \u001b[1mConflicts\u001b[22m ────────────────────────────────────────── tidyverse_conflicts() ──\n",
      "\u001b[31m✖\u001b[39m \u001b[34mdplyr\u001b[39m::\u001b[32mfilter()\u001b[39m masks \u001b[34mstats\u001b[39m::filter()\n",
      "\u001b[31m✖\u001b[39m \u001b[34mdplyr\u001b[39m::\u001b[32mlag()\u001b[39m    masks \u001b[34mstats\u001b[39m::lag()\n"
     ]
    }
   ],
   "source": [
    "library(tidyverse)\n",
    "\n",
    "set.seed(1234)\n",
    "sample.1<-rnorm(15, 110, 15)\n",
    "sample.2<-rnorm(15, 124, 15)\n",
    "\n",
    "well.data<-rbind(data.frame(iq=sample.1, group=\"standard\"),\n",
    "                 data.frame(iq=sample.2, group=\"hyper IQ\"))\n",
    "well.data$type<-\"well\"\n",
    "\n",
    "outlier.data<-rbind(data.frame(iq=sample.1, group=\"standard\"),\n",
    "                    data.frame(iq=c(sample.2, 30), group=\"hyper IQ\"))\n",
    "outlier.data$type<-\"outlier\"\n",
    "\n",
    "ranksum.dat<-rbind(well.data, outlier.data)\n",
    "ranksum.dat$type<-as.factor(ranksum.dat$type)\n",
    "ranksum.dat$type<-relevel(ranksum.dat$type, \"well\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a8b889e2",
   "metadata": {},
   "source": [
    "Both datasets are the same, with the only difference being that in the \"outlier\" dataset, we have added one outlier to the Hyper IQ group:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f326a67d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Warning message:\n",
      "“\u001b[1m\u001b[22mRemoved 2 rows containing missing values (`geom_segment()`).”\n",
      "Warning message:\n",
      "“\u001b[1m\u001b[22mRemoved 2 rows containing missing values (`geom_segment()`).”\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAACWAAAASwCAIAAADwxubWAAAACXBIWXMAABJ0AAASdAHeZh94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\nc9WqmgAAAABJRU5ErkJggg==",
      "text/plain": [
       "plot without title"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 600,
       "width": 1200
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "options(repr.plot.width=20, repr.plot.height=10)\n",
    "\n",
    "ggplot(ranksum.dat, \n",
    "       aes(x = group,\n",
    "           y = iq,\n",
    "           color = group)) +\n",
    "  geom_boxplot(outlier.color = NA) +\n",
    "  geom_jitter(size = 3, width = 0.3) +\n",
    "  stat_summary(fun = \"mean\",\n",
    "    color = \"black\", shape = 8) +\n",
    "  scale_color_manual(values =\n",
    "        c(\"darkgreen\", \"darkblue\"),\n",
    "        guide = NULL) +\n",
    "  labs(x = \"\",\n",
    "       y = \"IQ\",\n",
    "       caption = \"* Mean\") + theme_bw(30) + facet_grid(~type)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "32116c73",
   "metadata": {},
   "source": [
    "Since we generated the data from a Gaussian distribution, we can use the two-sample t-test to test whether there are significant differences in means:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "eb5ed33b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tTwo Sample t-test\n",
       "\n",
       "data:  iq by group\n",
       "t = 3.0282, df = 28, p-value = 0.005238\n",
       "alternative hypothesis: true difference in means between group hyper IQ and group standard is not equal to 0\n",
       "95 percent confidence interval:\n",
       "  4.926668 25.525651\n",
       "sample estimates:\n",
       "mean in group hyper IQ mean in group standard \n",
       "              120.1667               104.9405 \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "t.test(iq~group, data = well.data, var.equal = TRUE)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "edc61231",
   "metadata": {},
   "source": [
    "As we can see, at the usual Type I error rate of $\\alpha=0.05$, we reject the null hypothesis that both groups have similar means in IQ.\n",
    "\n",
    "Now, let's see what happens if we use the same test on the dataset contaminated with one outlier:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "75e0e180",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tTwo Sample t-test\n",
       "\n",
       "data:  iq by group\n",
       "t = 1.2637, df = 29, p-value = 0.2164\n",
       "alternative hypothesis: true difference in means between group hyper IQ and group standard is not equal to 0\n",
       "95 percent confidence interval:\n",
       " -5.930769 25.112250\n",
       "sample estimates:\n",
       "mean in group hyper IQ mean in group standard \n",
       "              114.5313               104.9405 \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "t.test(iq~group, data = outlier.data, var.equal = TRUE)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f7b8d933",
   "metadata": {},
   "source": [
    "Now the p-value is greater than 0.05, so we should stick to the null hypothesis, even though our data seemed to indicate that both groups differ in their IQ values!!! What is happening here is that the presence of the outlier is contaminating the estimation of the mean, and this is affecting the t-test since it is a test on the means. \n",
    "\n",
    "Let's see what happens if we instead run a Wilcoxon rank-sum test."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "fbb67fee",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum exact test\n",
       "\n",
       "data:  iq by group\n",
       "W = 175, p-value = 0.02975\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(iq~group, data = outlier.data)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3ad1b29f",
   "metadata": {},
   "source": [
    "Since this test uses ranks instead of the actual observed values, it is not as sensitive to outliers and allows us to reject the null hypothesis, as we expected."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8da6671b",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-info\"> <b>Practice</b>: The dataset in <a href=\"https://raw.githubusercontent.com/jrasero/cm-85309-2023/main/datasets/drug_depression.csv\"> https://raw.githubusercontent.com/jrasero/cm-85309-2023/main/datasets/drug_depression.csv </a> contains information about the levels of depression of several participants measured through the Beck Depression Inventory (BDI) on two different days (Sunday and Wednesday) after taking either ecstasy or alcohol. In this dataset, the column <i> Drug</i> is a categorical variable indicating which drug the participants took, and <i> BDI_sunday</i> and <i> BDI_wednesday</i> represent the measured levels of depression on sunday and wednesday respectively.\n",
    "    \n",
    "Use either a Wilcoxon rank-sum or a Wilcoxon signed-rank test to show:\n",
    "    <ol>\n",
    "    <li> If there are differences in depression levels measured on sunday and wednesday between both groups.\n",
    "        <li> If there are differences in depression levels between both days in the \"Ecstasy\" group.\n",
    "            <li> If there are differences in depression levels between both days in the \"Alcohol\" group.\n",
    "        </ol>\n",
    "    \n",
    "In all cases, assume a type I error rate $\\alpha=0.05$ to conclude whether we reject the null or not."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "0bd53c32",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Your response here and below using more cells"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0eb7c279",
   "metadata": {},
   "source": [
    "# Kruskal-wallis test\n",
    "\n",
    "The **Kruskal-Wallis test** is the nonparametric alternative to **ANOVA** and tests whether two or more groups of data come from the same distribution. It can be used, for example, when the data are not normally distributed and small sample sizes or the data are ordinal or interval.\n",
    "\n",
    "In R, we can run the Kruskal-Wallis test using the `kruskal.test` function. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "ed4c9029",
   "metadata": {},
   "outputs": [],
   "source": [
    "?kruskal.test"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6f831dff",
   "metadata": {},
   "source": [
    "Let's generate some data for this part of the tutorial, consisting of values for three different groups:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "ce4293e0",
   "metadata": {},
   "outputs": [],
   "source": [
    "set.seed(1234)\n",
    "# Generate random data for group 1 with mean 10 and standard deviation 2\n",
    "anova.data.good<-rbind(data.frame(value=rnorm(10, mean = 8, sd = 2), group='a'),\n",
    "                       data.frame(value=rnorm(10, mean = 11, sd = 2), group='b'), \n",
    "                       data.frame(value=rnorm(10, mean = 10.5, sd = 2),  group='c'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "b47a828e",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Warning message:\n",
      "“\u001b[1m\u001b[22mRemoved 3 rows containing missing values (`geom_segment()`).”\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABwgAAANICAIAAABc5iyuAAAACXBIWXMAABJ0AAASdAHeZh94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\nTkSuQmCC",
      "text/plain": [
       "plot without title"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 420,
       "width": 900
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "library(tidyverse)\n",
    "\n",
    "options(repr.plot.width=15, repr.plot.height=7)\n",
    "\n",
    "ggplot(anova.data.good, \n",
    "       aes(x = group,\n",
    "           y = value,\n",
    "           color = group)) +\n",
    "  geom_boxplot(outlier.color = NA) +\n",
    "  geom_jitter(size = 3, width = 0.3) +\n",
    "  stat_summary(fun = \"mean\",\n",
    "    color = \"black\", shape = 8) +\n",
    "  labs(x = \"\",\n",
    "       y = \"Value\",\n",
    "       caption = \"* Mean\") + theme_bw(30)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c8ba4650",
   "metadata": {},
   "source": [
    "If we run an ANOVA test and assuming $\\alpha=0.05$, we should reject the null that the three groups have a similar mean:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "67ab2873",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "            Df Sum Sq Mean Sq F value   Pr(>F)    \n",
       "group        2  65.81   32.91   9.587 0.000715 ***\n",
       "Residuals   27  92.68    3.43                     \n",
       "---\n",
       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "summary(aov(value~group, data = anova.data.good))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a46e6aab",
   "metadata": {},
   "source": [
    "Let's see again what happens if we add an outlier to one of the groups and run the ANOVA test again:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "5b81702f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A data.frame: 6 × 2</caption>\n",
       "<thead>\n",
       "\t<tr><th></th><th scope=col>value</th><th scope=col>group</th></tr>\n",
       "\t<tr><th></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>26</th><td> 7.603590</td><td>c</td></tr>\n",
       "\t<tr><th scope=row>27</th><td>11.649511</td><td>c</td></tr>\n",
       "\t<tr><th scope=row>28</th><td> 8.452689</td><td>c</td></tr>\n",
       "\t<tr><th scope=row>29</th><td>10.469723</td><td>c</td></tr>\n",
       "\t<tr><th scope=row>30</th><td> 8.628103</td><td>c</td></tr>\n",
       "\t<tr><th scope=row>31</th><td>50.000000</td><td>a</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A data.frame: 6 × 2\n",
       "\\begin{tabular}{r|ll}\n",
       "  & value & group\\\\\n",
       "  & <dbl> & <chr>\\\\\n",
       "\\hline\n",
       "\t26 &  7.603590 & c\\\\\n",
       "\t27 & 11.649511 & c\\\\\n",
       "\t28 &  8.452689 & c\\\\\n",
       "\t29 & 10.469723 & c\\\\\n",
       "\t30 &  8.628103 & c\\\\\n",
       "\t31 & 50.000000 & a\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A data.frame: 6 × 2\n",
       "\n",
       "| <!--/--> | value &lt;dbl&gt; | group &lt;chr&gt; |\n",
       "|---|---|---|\n",
       "| 26 |  7.603590 | c |\n",
       "| 27 | 11.649511 | c |\n",
       "| 28 |  8.452689 | c |\n",
       "| 29 | 10.469723 | c |\n",
       "| 30 |  8.628103 | c |\n",
       "| 31 | 50.000000 | a |\n",
       "\n"
      ],
      "text/plain": [
       "   value     group\n",
       "26  7.603590 c    \n",
       "27 11.649511 c    \n",
       "28  8.452689 c    \n",
       "29 10.469723 c    \n",
       "30  8.628103 c    \n",
       "31 50.000000 a    "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "anova.data.outlier<-rbind(anova.data.good, \n",
    "                          data.frame(value=50, group=\"a\")) # Here we are adding an outlier to group a\n",
    "tail(anova.data.outlier)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "10cb4fea",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Warning message:\n",
      "“\u001b[1m\u001b[22mRemoved 3 rows containing missing values (`geom_segment()`).”\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABwgAAANICAIAAABc5iyuAAAACXBIWXMAABJ0AAASdAHeZh94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\nRK5CYII=",
      "text/plain": [
       "plot without title"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 420,
       "width": 900
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "options(repr.plot.width=15, repr.plot.height=7)\n",
    "\n",
    "ggplot(anova.data.outlier, \n",
    "       aes(x = group,\n",
    "           y = value,\n",
    "           color = group)) +\n",
    "  geom_boxplot(outlier.color = NA) +\n",
    "  geom_jitter(size = 3, width = 0.3) +\n",
    "  stat_summary(fun = \"mean\",\n",
    "    color = \"black\", shape = 8) +\n",
    "  labs(x = \"\",\n",
    "       y = \"Value\",\n",
    "       caption = \"* Mean\") + theme_bw(30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "425f3703",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "            Df Sum Sq Mean Sq F value Pr(>F)\n",
       "group        2   10.9    5.43   0.087  0.917\n",
       "Residuals   28 1755.4   62.69               "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "summary(aov(value~group, data = anova.data.outlier))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "994cad05",
   "metadata": {},
   "source": [
    "As we can see, just one outlier can completely change our conclusion! \n",
    "\n",
    "However, if we know about the existence of this outlier, we could try running a Kruskal-Wallis test, which should be less sensitive to such points.\n",
    "\n",
    "As we said before, in R we can run the Kruskal-Wallis test using the `kruskal.test` function. We could use the formula syntax like with `aov`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "454babbf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tKruskal-Wallis rank sum test\n",
       "\n",
       "data:  value by group\n",
       "Kruskal-Wallis chi-squared = 8.774, df = 2, p-value = 0.01244\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "kruskal.test(value~group, data = anova.data.outlier)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e9fce0e9",
   "metadata": {},
   "source": [
    "or by passing the vector of values to the first argument, and the vector with the group assignments to the second argument:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "c572bb3a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tKruskal-Wallis rank sum test\n",
       "\n",
       "data:  anova.data.outlier$value and anova.data.outlier$group\n",
       "Kruskal-Wallis chi-squared = 8.774, df = 2, p-value = 0.01244\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "kruskal.test(anova.data.outlier$value, anova.data.outlier$group)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5d398cb0",
   "metadata": {},
   "source": [
    "In either case, we can see that assuming $\\alpha=0.05$, we can now reject the null hypothesis that the distributions of points are similar among the three groups. This is consistent with the result obtained earlier without the outlier using ANOVA."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "db840047",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-info\"> <b>Practice</b>: A psychologist is interested in whether reaction times differ across three different experimental conditions. Participants are randomly assigned to one of the three conditions, and their reaction times are recorded. The dataset can be found in <a href=\"https://raw.githubusercontent.com/jrasero/cm-85309-2023/main/datasets/reaction_times_experiment.csv\"> https://raw.githubusercontent.com/jrasero/cm-85309-2023/main/datasets/reaction_times_experiment.csv </a>.\n",
    "\n",
    "Use a Kruskal-Wallis test to assess whether there are statistical differences in the distributions of reaction times among the three experimental conditions, assuming a type I error rate of $\\alpha=0.05$. As a follow-up, determine which pairs of experimental conditions differ in terms of these reaction times?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "16fb9593",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Your response here and below using more cells"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d5e7e0f3",
   "metadata": {},
   "source": [
    "# Spearman's correlation test\n",
    "\n",
    "The **Spearman's correlation**, $\\rho$, is a measure used to determine the strength and direction of the association between two variables. It measures the monotonic relationship between two variables, which means that variables increase or decrease but not necessarily at a constant rate. As a result, it is suitable as an alternative to the **Pearson's correlation** when the relationship is non-linear.\n",
    "\n",
    "The Spearman's correlation coefficient, $\\rho$, is just the Pearson's correlation between the ranks of each variable separately, instead of between the actual data. As a result, it is also suitable when the data are ordinal or in the presence of outliers.\n",
    "\n",
    "Once the the Pearson's correlation between the ranks are calculated, the significance of the association is determined by first transforming this correlation to a t-statistic. Then, the p-value is calculated using the t-distribution, similar to how it is done for Pearson's correlation.\n",
    "\n",
    "In R, testing the association between two variables using the Spearman's correlation can be done using the `cor.test` function, but setting the argument *method* equal to \"spearman\"."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "1d320787",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[1m\u001b[22m`geom_smooth()` using formula = 'y ~ x'\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABwgAAANICAIAAABc5iyuAAAACXBIWXMAABJ0AAASdAHeZh94\nAAAgAElEQVR4nOzdeXxU5b0/8GeykxB2UEFEUQG1dcG9CQYV6q1aa6ldr1X03u5778966+3t\nXpVuv24/b1tvF612s9Zqq1aJmgCRRatVCyoqagVl37IvM/P7Y5IhIGQhIZPJeb//OjPzzJfv\nKyfnMPnMc54TSyaTAQAAAAAgSnIy3QAAAAAAwEATjAIAAAAAkSMYBQAAAAAiRzAKAAAAAESO\nYBQAAAAAiBzBKAAAAAAQOYJRAAAAACByBKMAAAAAQOQIRgEAAACAyBGMAgAAAACRIxgFAAAA\nACJHMAoAAAAARI5gFAAAAACIHMEoAAAAABA5glEAAAAAIHIEowAAAABA5AhGAQAAAIDIEYwC\nAAAAAJEjGAUAAAAAIkcwCgAAAABEjmAUAAAAAIgcwSgAAAAAEDmCUQAAAAAgcvIy3QAZFo/H\n6+vr+6VUMplMbcRisX4pSEak92OKvZnVHJVDg6NyKHFUDg2OyqHEUTk0OCqHmNQOtR+zmqNy\niBlsR+Xw4cNzcvpnrqdgNOpWrlx55ZVXZroLAAAAAOjefffdN3bs2H4p5VJ6AAAAACByzBil\n3cc//vFDDz20LxXq6+sTiUReXt6wYcP6qysGXm1tbXo7FosNHz48g83QR42NjW1tbbm5ucXF\nxZnuhf2XOrumH5aWlmawGfqoubm5paUlJyenpKQk072w/xoaGuLxePphSUlJf13MxcBraWlp\nbm4Ozq5ZrqmpqbW1Nf2wuLg4Nzc3g/3QF62trU1NTSGE4cOHD57rdumt1Gee9MOioqL8/PwM\n9kNfxOPxhoaGMAjOrk899dStt97avzUFo1GX/lg/Y8aM6dOn971ULBbzt0FW6/yXXgjBZ8qs\nlkgkksmkozLbOSqHkmQymUgkHJXZbo+jMicnx5/u2St1VAZn1yyX+syTfuiozGrpo9J+zGrp\n/Zhib2a1wXNUpu+R0/m3q48Eo7RLJBJ7fMrfP8lksl/qMEjYm0OAo3KIsTeHAEflENOPH83J\nIEflUOKoHBrsx6HE3hwaMr4fD0QDgtGoS4f9hYWFfbwEvrm5OZFI5ObmFhQU9EdrZEZjY2N6\nOxaLFRUVZbAZ+ih1VObk5BQWFma6F/ZfU1NT51kwlivJaq2trW1tbc6u2S51dk0/LCwsNAU4\ne7W1tbW2tjoqs13q7Jp+6KjMavF4PHUJdlFRkTmG2St1dk0/LCgoMDE/eyUSidSyMxk/u6bj\npn48OQhGoy79Oz1s2LA+rnfW2tqaWmPUumlZrXMEE4vF7M2slvpYmZubaz9mtZaWlj1WM8xg\nM/RRfX19W1ubNUazXVtbW+dgNOPrbdEXjY2NqT/dHZVZra6urnMwajXDrJZem7K4uFjAnb0a\nGho6B6OFhYXmamSv1tbWVDA6bNiwvLxMBonp36J+DEadZQAAAACAyBGMAgAAAACRIxgFAAAA\nACJHMAoAAAAARI5gFAAAAACIHMEoAAAAABA5glEAAAAAIHIEowAAAABA5AhGAQAAAIDIEYwC\nAAAAAJEjGAUAAAAAIkcwCgAAAABEjmAUAAAAAIgcwSgAAAAAEDmCUQAAAAAgcvIy3QAAAAAA\n0FctLS333nvvPffc89JLL9XX1x9yyCFlZWXveMc7Jk+enOnWBinBKAAAAABkt7vuuuszn/nM\nmjVrOj/5hz/84eqrr/7Qhz503XXXlZSUZKq3Qcul9AAAAACQxa677rq3ve1te6SiKS0tLT/8\n4Q9nzZq1cePGgW9skBOMAgAAAEC2uummm6655pquxzz++OPz5s1raWkZmJayhWAUAAAAALLS\n5s2bP/WpT/VkZE1NzQ033HCg+8kuglEAAAAAyEo33HDDjh07ejh4wYIF8Xj8gPaTXQSjAAAA\nAJCV7rjjjp4PXr9+/dKlSw9cM1lHMAoAAAAA2SeZTK5atapXb1m5cuUBaiYbCUYBAAAAIPvU\n1tb29n5KmzdvPkDNZCPBKAAAAABkn9LS0oKCgl69Zdy4cQeomWwkGAUAAACA7BOLxd7whjf0\n6i1vfOMbD1Az2UgwCgAAAABZ6eKLL+754EMOOeSMM844cM1kHcEoAAAAAGSlj33sY6NGjerh\n4M9//vM5OcLAXfwsAAAAACArjRkz5oc//GFPRs6aNevDH/7wge4nuwhGAQAAACBbXXrppQsW\nLOh6zCmnnHL77bfn5+cPTEvZQjAKAAAAAFnsc5/73N1333300Ue//qXCwsLPfvazixYtGj9+\n/MA3NsjlZboBAAAAAKBPzj///Llz595///333HPPSy+9VFtbO2nSpLKysnnz5k2cODHT3Q1S\nglEAAAAAyHr5+fkXXHDBBRdckOlGsoZL6QEAAACAyBGMAgAAAACRIxgFAAAAACJHMAoAAAAA\nRI5gFAAAAACIHMEoAAAAABA5glEAAAAAIHIEowAAAABA5AhGAQAAAIDIEYwCAAAAAJEjGAUA\nAAAAIkcwCgAAAABEjmAUAAAAAIgcwSgAAAAAEDmCUQAAAAAgcgSjAAAAAEDkCEYBAAAAgMgR\njAIAAAAAkSMYBQAAAAAiRzAKAAAAAESOYBQAAAAAiBzBKAAAAAAQOYJRAAAAACByBKMAAAAA\nQOQIRgEAAACAyBGMAgAAAACRIxgFAAAAACJHMAoAAAAARE5ephsYRJrWP1FdWf3Ik8+ueXXL\nzvrWvOGjx4ydMOW4U8tmlZ86Y3xhT0rEd76wbOHCxY+tfP6fm7bXteYOHz1m7MFHnlhWcXb5\nyVNKe5JC970CAAAAANAdwWgIIYSW12p+9f0f37VqR7LTczs2NuzYuHbNP2r+fPPYE972gQ+/\n502Tirqq8cqDP/72TytfbOj03I6N63ZsXLfmyUV33Drjwo98+vKyiQUHtAIAAAAA0BOmIIbQ\nvOaOr1614M5dqWgsv3j0+PFjSws7fjrxLU/88frPfOG255v3VaNlzZ++dPX3OmWaOYWlo0cW\n58XaHyZ3PvPnBVd9/d518QNXAQAAAADoITNGGx7/3+t++eTO1IOiyWe9d/4755w0pTQvhJBo\nXL+q+o5f3vzX1XXJEJpW/+or35v0o6vfNPL1NZ648dpfrKwLIYQQG3HsW6+Yf3H5jHGFISTq\n1z6+8Pc/v7XqleYQQu3ff/KVnx/2ow8c9/pJn32vAAAAAAD0WNRnjCZf/tON921ITRUtnPbe\n677zf95+aioVDSHkDDv4Df/ykesX/Nsbh6We2FHzyztWJ/esEV/9+x/fvzH19IhTPrrgG/9+\n7oxxqSVJc0oOPfniz373uvcfk6qQWH/3z+585QBUAAAAAAB6IeLBaPLJe+5dm9qMTbnkU+85\nci+LiOZNfusH33po+4P1NQ+v2eP1hqW337MulVQWn3blp8+blLtnhcKj3nnNh08rCSGEkHj+\n9t8/0tLfFQAAAACA3oh4MLr2ueca2xfxnDH3zZNjex8VmzJ9WkdiunH9+t2na9Y+/MDyptTm\nqLPfVjFi7yVGzr5k7rjUZsOy6kea+rcCAAAAANArEV9jdPIl373totpNr65duzHviNH7HBZv\nbOyYolk6cuRu8WnL3x99KpHaHH7K6W943VzPDrHpp5826k/3bA8hNK+o+VtrWVl+v1UAAAAA\nAHon4jNGQwixgtIJhx8z87Sj952LNix7+In26LJg2rTDd3vtpdWr2zPT2LRjZuxjymkIIcSO\nnj6t/afd/PSqTtfj970CAAAAANA7gtFuJOtW337djx9uCCGEEDvognfNHt755YZ/vry5fXPc\nYZP3skLpLgWHHjqhfXPL2lca+68CAAAAANBLEb+Ufq+SyUSitWnnxn8+99SK6r/eV/NibWq6\n6MiTP/Tfl87Y/VL3zZs6Us0wbty4ruuOHTs2hPUhhBA2btoYwpR+qgAAAAAA9JJg9HVq7//C\nv/6/p3Z/btjkN13yb1e+feaEPX9e27dv79gcMWIft03qMLw0Pdm0rrau/yrsW1VV1csvv9z1\nmMbG9qmnzc3N6e39k0gkQgjxeLyPdRg8ksmkvZnVUkdlIpGwH7NaMrnbXf/szazW1tYWnF2z\nX+rsmtbU1JST4zKsbNXa2pracFRmtXg83vlhc3Nz6nxLNkrvu6amplisi8XmGNT2OAZbWlr2\n+N+TLJI+xzY3N6f/38yIlpb2tSj3+BOpLwSjr7Nxw8Y9n8obNizUrn9tW8uE8QW7v9LU1PEB\nKnfYsII937e7gmHDckOIh7Db566+V9i3e+6558EHH+x6zJFHHpnaaGxsrK+v775od9ra2nwK\nGTKSyWS//FaQWfF43H4cSuzNISCRSNiPQ4lAbQjwmWeIaWpqynQL9IOGhoZMt0C/aW5ubm5u\nznQX9FXGP/Okf4sEowdQYuP2tkOnnzhx3PDc5h3rX3z2pS0tybatqx/+0+qH7/nL7I/91yfP\nnrTrh5Zsbev4ajI3b5/3k++Qm9sRa7bFO5LDvlcAAAAAAHpLMLqnnDM/+Yszdz1sevXRO268\n4Xd/25wIoWVt1fe+EC/63lVnjky/no6oY6H7Of57HdH3CgAAAABA71gOqRtFE0957xe/c1XF\n+FQkmdyy+IZfPpqe/x3LS8/ybNt9WZu9iacnhxbkd1w03/cKAAAAAEBvmTHaA7HRZR/72DlP\nfvmBbSGEsKP6nof//ZSzS0IIIRQXF4dQG0II8aameAhdXQzf2tjUEWsWFhV2PNv3Cvt26aWX\nvvnNb+56zObNm7/97W+nGiktLe2+6L7V19cnEom8vLxhw4b1pQ6ZVVdXl16tIxaLDR8+vOvx\nDGaNjY1tbW25ubnFxcWZ7oX9lzq7ph/28VxNZjU3N7e0tOTk5JSUlGS6F/ZfQ0ND5zu9lJSU\nuPlS9mppaUktWObsmtWampo63w+kuLg4N7fbdcoYpFpbW1OrxA4fPtzNl7JX+uyaUlRUlJ+f\nn8F+6It4PJ5a8zfjZ9eioqLURj+eHASjPVM0818qJjzwp40hhNC28h/PJs+eGQshhJEjR7bH\nmqG2dmcIo7uoUVtb27E5atSojs2+V9i3448/vtsxTz75ZGqjoKCgsLAHaeu+NTY2JhKJ3Nzc\nPtYhs+rq6tLbsVjM3sxqqc8iOTk59mNW2+POA/ZmVkvdn9DZNds1NTV1DkYLCgpEMNkrkUg0\nNzc7KrNda2tr52A0Pz9fBJPVUsFoQUGBr52yV3z3S2Lz8/OdZrNX+gRbUFCQl5fJIDF9bu/H\nYNRZpqemTp3asdm4eVPHPSsnHDSh49ktW7Z0XWHXgNi4sWM7nu17BQAAAACgl6IdjCZbaje9\n8vw/Hq15YOGTm7oZm5efv5c4uuiwwzpyzY1r17a+fsAuLevWbWzfnDBlSlH/VQAAAAAAeina\nl9I/e8snPvenrSGEEGZceeI3Lx7fxdhNGzd03D8+f/SY9KqLh0+fVhA2toQQ4qufeyHMnrHP\nAs8/u7p9hbiCo48+bNfzfa8AAAAAAPROtGeMHj51asd6UM/W1HQ5Z3Tb8hXPt2/GZsyYln4+\n74SZx7fX2Lpi+fPJ178zJfnsshXbUps5x888odOCN32vAAAAAAD0TrSD0aJTy04qSG0mn73r\nj0+17Gtg7aM3376yfbZm/hvLTx+566XhZ1ac3L6C8Ib7b19S+/o3hxDCzurbK9uD16LTz3nT\nbrf57nsFAAAAAKBXoh2MhpLyt88d1769+d7v/2jp1r1M2GxY/Ydrv/tA6or7EDvkrZfN3e3O\n8SVl8958UGqztuaGBXe+/Lp1Qlte/OP1P16WutN3bNL5884s3qOLPlcAAAAAAHoj4sFoKHzj\npR+ZMz51V6XExqrrP33NzypXbmxMTQ5NNmx4+qFfffVT19y8MpVJhoKj3v0f7522x8Ksece+\n54Ozx6S265/82eeu+sHdT21oSoYQQrJp/ZN3/+Cqq3/5j4YQQgixCXM/9K7puSH0dwUAAAAA\noBeiffOlEEIoOfWjX/nQtmt+8rftyRCS21fe+YPP3/mjgtKRw3Nb6nbWtyR2jRx25Fuv+uL7\nphW+vkbpqR/9r8s2funmVXUhhMY1lT/5r8r/LRo5qiRZv31nU3zXP3Xs5dd88MS9TvbsewUA\nAAAAoMeiPmM0hBDyDj3/v7//lfeePL6g45lES+22rds7paL5495w0VXfXfCBU0bto0bR0Zd8\n+dpPnjN1eKz9iXjTji1bOmWaxVPO+eT1X5k3tWAfBfqhAgAAAADQQ2aMhhBCyBl94nu/9NO3\nrF68sGrF31c+t3bTjtrGRH5J6chxhx593Aknv+nss44b292PqujwOZ/+v6ddWPNg1dIVTzz3\n6tZtOxoSBcUjJxx29LEnl8+d+6ajRnZ3AXzfKwAAAAAAPSEY3SV31LTZ75w2+519KBEbcVT5\nxUeVX5zJCgAAAABAd1xKDwAAAABEjmAUAAAAAIgcwSgAAAAAEDmCUQAAAAAgcgSjAAAAAEDk\nCEYBAAAAgMgRjAIAAAAAkSMYBQAAAAAiRzAKAAAAAESOYBQAAAAAiBzBKAAAAAAQOYJRAAAA\nACByBKMAAAAAQOQIRgEAAACAyBGMAgAAAACRIxgFAAAAACJHMAoAAAAARI5gFAAAAACIHMEo\nAAAAABA5glEAAAAAIHIEowAAAABA5AhGAQAAAIDIEYwCAAAAAJEjGAUAAAAAIkcwCgAAAABE\njmAUAAAAAIgcwSgAAAAAEDmCUQAAAAAgcgSjAAAAAEDkCEYBAAAAgMgRjAIAAAAAkSMYBQAA\nAAAiRzAKAAAAAESOYBQAAAAAiBzBKAAAAAAQOYJRAAAAACByBKMAAAAAQOQIRgEAAACAyBGM\nAgAAAACRIxgFAAAAACJHMAoAAAAARI5gFAAAAACIHMEoAAAAABA5glEAAAAAIHIEowAAAABA\n5AhGAQAAAIDIEYwCAAAAAJEjGAUAAAAAIkcwCgAAAABEjmAUAAAAAIgcwSgAAAAAEDmCUQAA\nAAAgcgSjAAAAAEDkCEYBAAAAgMgRjAIAAAAAkSMYBQAAAAAiRzAKAAAAAESOYBQAAAAAiBzB\nKAAAAAAQOYJRAAAAACByBKMAAAAAQOTkZboBMiyRSKQ2Ghoaamtr+1IqHo+HEFpbW/tYh8xK\nJpOdt+3NrNbW1hZCiMfj9mNWS5+oU+zNrJY6KhOJhP2Y1VL7Ma2+vj4Wi2WqGfoo9Qk2OLtm\nuT2OyoaGhpwcc4CyVfqorKurc3bNXun9mNLU1NTS0pKpZuij9N8j9fX1mT27NjY2pjY6Bxd9\nJBiNuvQvU0tLS3Nzc98LJhKJfqnDYJBMJu3NIcBROcTYm0OAs+sQ4y+9IcBROcS0trZmugX6\ngbPrUOKoHBoyvh/TX4MJRuk36a/g8vLy8vPz+1Kqra0tmUzGYrG8PL9XWazzmc7ezHaOyqEh\ntR/TD/t4riaz4vF4IpFwVGa7PY7KvLw8c5qyVyKRSE1rcnbNaqmza/qhozKrpY9K+zGrpfdj\nSm5urnnc2WvwHJW5ubmpjX5sw4fyqEufm4YPHz5y5Mi+lNq+fXtbW1tBQUFpaWl/tEZmbNmy\nJf3HXiwW6+NvBZm1c+fOlpaWvLw8+zGrbdu2rfPHSnszq9XX1zc2Nubk5NiPWW3Hjh2dv0cs\nLS1Nf0wn6zQ2NqYWQ3BUZrW6urqmpqb0w5KSEkl39mpubk4tbTFixAhRWvZqaGhoaGhIPywu\nLi4sLMxgP/RFa2vrjh07QgjDhw/P7Lf7xcXFqY1+DEadZQAAAACAyBGMAgAAAACRIxgFAAAA\nACJHMAoAAAAARI5gFAAAAACIHMEoAAAAABA5glEAAAAAIHIEowAAAABA5AhGAQAAAIDIEYwC\nAAAAAJEjGAUAAAAAIkcwCgAAAABEjmAUAAAAAIgcwSgAAAAAEDmCUQAAAAAgcgSjAAAAAEDk\nCEYBAAAAgMgRjAIAAAAAkSMYBQAAAAAiRzAKAAAAAESOYBQAAAAAiBzBKAAAAAAQOYJRAAAA\nACByBKMAAAAAQOQIRgEAAACAyBGMAgAAAACRIxgFAAAAACJHMAoAAAAARI5gFAAAAACIHMEo\nAAAAABA5glEAAAAAIHIEowAAAABA5AhGAQAAAIDIEYwCAAAAAJEjGAUAAAAAIkcwCgAAAABE\njmAUAAAAAIgcwSgAAAAAEDmCUQAAAAAgcgSjAAAAAEDkCEYBAAAAgMgRjAIAAAAAkSMYBQAA\nAAAiRzAKAAAAAESOYBQAAAAAiBzBKAAAAAAQOYJRAAAAACByBKMAAAAAQOQIRgEAAACAyBGM\nAgAAAACRIxgFAAAAACJHMAoAAAAARI5gFAAAAACIHMEoAAAAABA5glEAAAAAIHIEowAAAABA\n5AhGAQAAAIDIEYwCAAAAAJEjGAUAAAAAIkcwCgAAAABEjmAUAAAAAIicvEw3MIjEd7yw9MHq\nR596evVLG7bX1TW25RWXjhh98BEzjjvh9HPOOeXQ4lj3JXa+sGzhwsWPrXz+n5u217XmDh89\nZuzBR55YVnF2+clTSnuSQve9AgAAAADQHcFoCCGE+ObHfvejH93+2ObWzs+21W5rqt228Z9P\nL7//9lsOq3j/Zz98wdTifdZoeeXBH3/7p5UvNnR6bsfGdTs2rlvz5KI7bp1x4Uc+fXnZxIIu\nuuh7BQAAAACgJ0xBDKFt3b1f+8yXf9spFY3lFpWOHjOqpCD940k2/LPqJ1f9xw2P7dh7jZY1\nf/rS1d/rlGnmFJaOHlmc1zHJNLnzmT8vuOrr966L76uLvlcAAAAAAHrIjNGWp3725R935J05\no4+74L3vfkvZGw4tzQshJJs2r35k4W2/+sOK9a0hhNZ1f73+2knfu/5tE/e4qL7hiRuv/cXK\nuhBCCLERx771ivkXl88YVxhCon7t4wt///Nbq15pDiHU/v0nX/n5YT/6wHGvn/TZ9woAAAAA\nQI9FfcZo8uU7fnLPhmQIIYTcSed94XvXfuBfTkyloiGEWNG46bPe+4XvXffuaUWpZ5qe/vUv\nqveYNRpf/fsf378xVWPEKR9d8I1/P3fGuMIQQgg5JYeefPFnv3vd+48ZFkIIIbH+7p/d+Upy\nzy76XgEAAAAA6IWIB6PJZxbe/8/2lHHi2//jw6eM3tsNloqn/evV8zsmaTY+Uvnwzs6vNiy9\n/Z51qRrFp1356fMm5e75/sKj3nnNh08rCSGEkHj+9t8/0rL7632vAAAAAAD0RsSD0ZcfeXRT\n++a0884/6nWBZNr4c847qX0aaeLpVc90eqX24QeWN6U2R539tooRe3//yNmXzB2X2mxYVv1I\nU+fX+l4BAAAAAOiVaAejLS+9/Fr75pjp08Z1NbRo4sQx7Zut27fX7yrx90efSqQ2h59y+hv2\nGa3Gpp9+2qjUZvOKmr+17nql7xUAAAAAgN6J9s2X8s/4+I9/uHnr1q1bt7YdfFjXY+vqOtLQ\nWHFxUfrpl1avbr+sPTbtmBl7uxC/411HT5+Wc8+KRAih+elVa0LZ9H6rAAAAAAD0TrSD0VjR\n6EOmjD5kSvcjk8///cmOYPSgiRPT0zob/vny5vbNcYdNLnr9G3cpOPTQCWHF+hBC2LL2lcYw\nfVg/VQAAAAAAeinal9L3WP3Ddyzc0L49/vTTp6Zf2LypI9UM48Z1eS1+CGPHju3Y3LhpY/9V\nAAAAAAB6KdozRnuo/rH//dni9vmiedMuOr/TJezbt2/v2BwxYh+3TeowvHR4x2ZdbV3/Vdi3\n5557btu2bV2Pee219mVW29raWlv7tHJpMpkMISQSiT7WYVCxN7Na6qhMJpP2Y1ZL7cc0ezOr\nJRLt64rbj1ltj6Oyra0tvWfJOvF4PLXhqMxqexyDbW1tmeqEvksflW1tbbFYF4vNMajtcVTG\n43Gn2eyVPqm2tbXt8SlogKXPD/1IMNqd+Kv3LPjOA+2zOnMOvegDFx7S6dTc1NTYvpU7bFhB\n15UKhg3LDSEeQgiNjR1v64cK+3bjjTc++OCDXY858sgjUxt1dXU7duzovmh3Wltb+6UOg0Ei\nkbA3h4C2tjb7cSixN4eAeDxuPw4ltbW1mW6Bvkomk47KoaS+vr77QQx6O3fuzHQL9JuGhoZM\nt0A/qKvrwRy9Ayn9i9SP30m7lL5L8Q1V3/niT//e/mG36JjLPv/+6Z1vG59sbesIq3Pz9nk/\n+Q65uR1D2uIdX2H2vQIAAAAA0FtmjO5b67r7v/3F/7d0U2qWcO7B5/yfz8+bvGd2mZ5CHAvd\nz/Hf64i+VwAAAAAAekcwug91z/zmG1/7zcr2uaK5B8/+P9/45Gmj9hwVy8vruLa9rfuFDuLp\nyaEF+R0Xzfe9AgAAAADQW4LRvWhZV/Wjr/+oal1L6mHR1Av/80sfmDl6b7M1i4uLQ6gNIYR4\nU1M8hK4uhm9tbOqINQuLCvuvwr6dccYZo0a9Ls3dXSwWe+GFF0IIBQUFRUVF3Rfdt5aWlkQi\nkZubm5+f35c6ZFZTU1N6OxaLFRb24FeNwSp1VObk5BQU+C4lizU3N3de47yP52oyq62tLXUr\nCWfXrJY6u6YfFhYWuj1I9kodlcHZNcu1trZ2viNHQUFBTo5V47JV+i49zq5ZLX12TcnPz9+1\nNCDZJpFItLS0hEFwdk3HTf14chCM7iG59bGbvvHNPz7XvpxrbPRJ8//7P99+1LB9DB85cmR7\nrBlqa3eGMLqL0p0W5u8UV/a9wr7Nmzev2zFPPvnk7bffHkIoLi4ePnx4t+O7sH379kQikZeX\n18c6ZFbnCCYWi9mbWW3nzp0tLS25ubn2Y1bb4489ezOr1dfXt7W15eTk2I9ZbceOHZ2D0eLi\nYn/sZa/GxsbU1xWOyqxWV1fX+f/KYcOGmauRvZqbm1PBaElJiYA7ezU0NHQORouKinwrnL1a\nW1tTwWhxcXFeXiaDxPS3mILRA6Rh9Z++fe0vH93a/kG3aOr5n/3CB84Y18UH3QkHTQhhbQgh\nhC1btnQda27ZsqV9KzZu7Nj+qwAAAAAA9JKvXzoktiz7n6uv+XlHKpo7/syPLKEf5dQAACAA\nSURBVLj+w12moiGEosMOm9C+uXHt2tauhrasW7exfXPClCnpK3X6XgEAAAAA6CXBaAghhPj6\nB7919fX3vty+qmjpjHd/9bv/+ZYjepA9Hj59WvvKffHVz73Q1cjnn13dPhO14OijD+vPCgAA\nAABA7whGQ0huXvSda75fszEVOuYdfNZnv/WNf33jyJ4tV5B3wszj2yeVbl2x/PnkvsYln122\nYltqM+f4mSd0WvCm7xUAAAAAgN4RjLa98Ntrv79kcyqPLJz61i996z9mT+xF6jj8zIqT21cQ\n3nD/7Utq9z5qZ/XtlZtSm0Wnn/Om3VZ273sFAAAAAKBXoh6MNq38xTd/+3xqZc/YhLOv+vIH\nTujhVNG0krJ5bz4otVlbc8OCO19+3TqhLS/+8fofL6tL/SOTzp93ZnF/VwAAAAAAeiPid6Vf\nd9eNd7/WfvF6wfQz3tj81OLF3b+r5PBTZ07etf5o3rHv+eDsmq9VbQ0h1D/5s89d9fJl//bu\nc99wUFEsJJvWP/XA7392U+WLTSGEEGIT5n7oXdNfdz+nvlcAAAAAAHoh0sFo8yO33bkm0fGo\n5Zm7fvBMj953xGU/mTn5kE5PlJ760f+6bOOXbl5VF0JoXFP5k/+q/N+ikaNKkvXbdzbF08NK\njr38mg+euNfJnn2vAAAAAAD0WJQvpU8+tXT5Phb07LWioy/58rWfPGfq8I7r8ONNO7Zs6ZRp\nFk8555PXf2Xe1IIDVwEAAAAA6KEozxit3bC+vh/LFR0+59P/97QLax6sWrriiede3bptR0Oi\noHjkhMOOPvbk8rlz33TUyO4ugO97BQAAAACgJ6IcjI644Nq7LujfkrERR5VffFT5xZmsAAAA\nAAB0J8qX0gMAAAAAESUYBQAAAAAiRzAKAAAAAESOYBQAAAAAiBzBKAAAAAAQOYJRAAAAACBy\nBKMAAAAAQOQIRgEAAACAyBGMAgAAAACRIxgFAAAAACJHMAoAAAAARI5gFAAAAACIHMEoAAAA\nABA5glEAAAAAIHIEowAAAABA5AhGAQAAAIDIEYwCAAAAAJEjGAUAAAAAIkcwCgAAAABEjmAU\nAAAAAIgcwSgAAAAAEDmCUQAAAAAgcgSjAAAAAEDkCEYBAAAAgMgRjAIAAAAAkSMYBQAAAICh\noq4urFiR6SayQ16mGwAAAAAA+qC+PixdGpYsCTU1YfHiEIuFbdtCUVGm2xrsBKMAAAAAkG06\nh6GLFoWWlt1eXbEinHVWhjrLGoJRAAAAAMgGXYehnVVVCUa7JRgFAAAAgMFq586weHGorg7V\n1eGxx0JbW1eDDz00zJ4dZs8Oc+YMVH9ZTDAKAAAAAINJXV1YtixUVoYlS8Ijj3Q1MzSEcMgh\nobw8zJkTysrCcccNVItDgWAUAAAAADKtcxi6YkVobe1qsDC0PwhGAQAAACAThKEZJRgFAAAA\ngIFSWxuWLxeGDgaCUQAAAAA4kLZuDYsXh4ceCtXV4cknQyLR1eCpU0NFRZg9O1RUhClTBqrF\nKBKMAgAAAEB/S88MrawMjz/eTRianhk6d2444oiBajHqBKMAAAAA0B82bw6LFoXq6lBVFf7x\nj27C0KOOChUV7ZNDJ08eqBbZRTAKAAAAAPtr06awbFmoqenRzNCpU0NZWSgvD29+czj88AHq\nkH0QjAIAAABAb2zcuGtm6MqVIZnsavC0abtmhk6aNFAt0j3BKAAAAAB0Z+PGUF3dHoauWtVN\nGDp9+q4wdOLEgWqR3hGMAgAAAMDebNwYli9vv0z+sce6CUPTl8n/y7+Eww4bqBbZf4JRAAAA\nAOiwfn37tNDq6vD0090MPuaYMHt2++TQgw8ekP7oN4JRAAAAAKLttdd2haHPPNPN4GOP3RWG\nHnTQgPTHASEYBQAAACB6NmwIixaFJUtCTU2PLpOfMyeUlYVzzgmHHjpQLXJgCUYBAAAAiIb1\n68PixcJQUgSjAAAAAAxd+xeGnntumDRpoFokMwSjAAAAAAwtqTC0sjIsWRJWrepmcCoMnTMn\nnH12GDduQPpjUBCMAgAAAJD9XnstLFkiDKXnBKMAAAAAZKf9C0PPOSeMHTsg/TGoCUYBAAAA\nyB6vvhpqanoUhubkhBkzQnm5MJS9EowCAAAAMLilw9DKyrBmTVcjO4eh554bxowZqBbJPoJR\nAAAAAAafdBi6cGF48cWuRubmhunThaH0lmAUAAAAgMFBGMoAEowCAAAAkDnPPx+qq0NVVaiq\nCmvXdjUyLy/MnBkqKkJFRZg1K4wYMVAtMjQJRgEAAAAYWM89F6qq2vPQdeu6GpmXF04+eVcY\nWlo6UC0y9AlGAQAAADjw1qwJS5aEmppw333h5Ze7GpmbG048MZSVhfLyMHduGDVqoFokWgSj\nAAAAABwQuc89l/vYY6GmJlRVhdde62poXl449dT2maHl5WH48IHqkegSjAIAAADQb3Kefbbo\ngQfyH344v6YmZ+PGrobm5+8KQ8vKhKEMMMEoAAAAAH2zZk2orAxLloSqqqJXXulqZF5eOOGE\nMGdOKCsLZ50VRo4cqBZhT4JRAAAAAHopmQxPP91+A6Xq6rBhQ1eDCwrCaaeFioowe3Y488xQ\nUjJQXUJXBKMAAAAA9Ex6ZuhDD4W1a7samZfXdtxxrRUVeRUV+XPmhBEjBqpF6CnBaNQlEonU\nRktLS1NTU99LxePxPtZh8Egmk/ZmVovH4yGERCJhP2a1ZDLZ+aG9mdVSR6Wza7ZLf3xKaW5u\nzsnJyVQz9FFbW1tqw1GZ1VJn17SWlpY9niGLpI/K5ubmWCyW2WZol0zGVq3KWbQoZ9GinCVL\nYps3dzW4sDBxyimt5eVNp5/eduqpyaKiEEJRUVE8Ly8402an9Bm1paUlfYRmRGtra2pjjz+R\n+kIwGnXpX6aGhoa6urq+F2xra+uXOgwGyWTS3hwC4vG4/TiU2JtDQCKRsB+HkoaGhky3QF/5\nzDPENDY2ZroF+kF9fX2mW4i63Jdfzq+uzq+uzl+yJGfr1q6GdswMbTnrrLbTT0+FoZ358mlo\nyPhnnvQvkmAUAAAAGLwSiURVVdV99923evXq2traMWPGvPGNb7zwwgtPOumkTLfGPvVjGApZ\nQTAadbm5uamNUaNGjRs3ri+ltm/f3tbWVlhYWFpa2h+tkRlbtmxJf/eSk5MzZsyYzPZDX+zc\nubOlpSU/P3+k+zxms23btnW+HrCP52oyq76+vrGxMTc3d/To0Znuhf23Y8eO9JVcIYTRo0en\nP1CRdRobG+vr62Ox2NixYzPdC/uvrq6u83y0kSNH5ufnZ7AfQghLly79yEc+8sQTT3R+8qGH\nHvrBD37wlre85YYbbjj88MP3+sbm5uba2toQwpgxYyxUMkBSa4ZWVoaHHgpdXyafvpv8nDmh\nvDyvqCgvhGF7G9jQ0NB5dmFpaWlhYWE/t81AaW1t3bFjRwhh1KhReXmZDBLTcVM/nhwEowAA\nAEC/+d3vfjd//vx9XT197733nnbaaXffffepp546wI2xSzoMffDBsGVLVyOHDQszZ4by8lQY\nGswMZWgRjAIAAAD9o6ampotUNGXTpk0XXXTRo48+OmnSpAFrLOoSifD006GmRhgKnQlGAQAA\ngH4Qj8c/+MEP9uROO+vXr//c5z536623DkBX0RWPh2eeaQ9DH3ggdL1maHFxOOkkYShRIxgF\nAAAA+sFdd921atWqHg7+9a9//fWvf/2II444oC1Fzn6HobNmBcuAEj2CUQAAAKAf3Hnnnb0a\nf9ddd33qU586QM1ESOcwtLIybNvW1WBhKHQiGAUAAAD6Qc+ni+7feHaJx8Pf/x6WLGnPQ7sO\nQ0tKwplnhrKyUF4uDIXOBKMAAABAP9ja9YXbr7Ol61sAsYf9DkPPOisUFAxUl5BNBiwYXXXP\nLzcee0nF4cNjA/UvAgAAAANn3LhxL7zwQs/Hjx8//sA1M0R0DkMXLgzbt3c1WBgKvTRwwejP\nr3jnHz9++FmXXDb/8ssvmT1VQAoAAABDyfHHH798+fKejz/hhBMOXDNZTBgKA2VAL6VP1r9U\nfdNXq2/62senlL/jsvnzL3/n7CNLBaQAAAAwBMybN+/GG2/s4eC8vLyLLrrogPaTTdrawhNP\nhMrKsGRJWLw47NjR1eDhw8MZZ4Q5c0JZWTjtNGEo7LeMrDGarH958c1fW3zz1z4xZda8yy6f\nf/m7zj6yNCcTnQAAAAD947zzzjv11FMfeeSRngy+8sorJ06ceKBbGtT2Oww9/fSQnz9QXcJQ\nNmDBaHFJcQgNezzZ8PLiW762+JavfXJy+dsvmz//8neec/QIASkAAABkoVgsduONN5aVldXX\n13c98ogjjrj22msHpqvBpaUlrFgRqqpCdXV4+OHQsGdQsptRo8KsWWH27FBREU48MeTmDlSX\nEBUDFoye/4v1L1x228033/yrPy5aU5fc/cWGV5bc+o0lt37jE5PfNO/9l19++bvPnTZSQAoA\nAADZ5YQTTrj99tvf+c531tbW7mvM4Ycffvfdd48dO3YgG8ukVBj60EOhujosXdpNGDp69K4w\n9IQThKFwQA1c/JhTOvXcK798U9UL619cdPPX/n3O3qLPxlcevvXaD715+iFT3vS+a3563+od\niQFrDwAAAOi78847b/ny5XPmzNnrq5dffvmKFSuOOeaYAe5qoLW1hb/9LSxYEN761jB+fJg1\nK3zxi+GBB/aeipaWhjlzwvXXh8WLw4YN4c47w2c+E2bOlIrCgZaBNUZLpsx6/xdmvf8LP1y3\n7M5bbr75V7+7f+XWtt2HNK5d+pvrlv7muk9NOvPiSy+fP//dc2aMcjYAAACAbHDMMccsXLjw\nscceu/POO5999tmtW7cedNBBJ5544tvf/vapU6dmursDprk5LF8eqqpCVVVYtiw0NnY1eMyY\ncNZZ7TNDjz8+5LhuFjIgIzdfSimadMa7rz7j3Vd/b8Pf/vLrm2+++Tf3/H1T6+5DmtYt/e2C\npb9d8OmJp7/t/ZfPv/w9c48ZLSAFAACAwW/mzJkzZ87MdBcHWFPTbmFoU1NXg8eObQ9DZ88O\nb3iDMBQyLoPBaIeCg06e95mT533mO1v+cc9vbrr5plv/8uhrzbsPaXp1+e8WLP/dgs9MPO2i\nS+fPn/+e8wSkAAAAQAak7yZfWRlqarqZGVpaGk4/PcyZE+bMCSedJAyFQWUQBKMd8sa+4aKP\nf+uij1+/7ZkHbvv1b373+zurn90W321I86srbvvmitu++ZmDT73o/VdeeeV73zzDTZoAAACA\nA6uxMSxb1j4zdMWKbmaGjhsXKipCRUX7zNBYbKC6BHpnEAWjHXJHz3jzB7/65g9+tXXTk5V3\n3vWXe++974HlL+zoHJE2r3/ktm89ctu3Pju5/F3//qGPfOBdpx9SkLF+AQAAgKGnsTH87W+h\npiZUVoYlS7oJQ8ePD6efHsrLzQyFLDIIg9G0/PHHv+VfJ0ycNOnQg0p++vOFLzW/bkTjK0tu\n+tKSm75x1Znv+8x///cn3jJ1WAbaBAAAAIaGhoawdGmorg4PPRRWrAgtLV0NnjBh18zQY481\nMxSyziANRhvWLr/7tt/9/ne33b1ibWOyu9Et65f+8urzf3PDW79008+urhjvWxkAAACghxoa\nwmOPtc8MXbw4NL9+XlYnEyaE005rnxk6c6YwFLLa4ApG49ufqbztlltu+fUdi1+s30ceWjTx\ntLe9/5ITm5fd9pu/PLah01c3zS//+ZpzT3/yVw/d+t4pslEAAABgX4ShwGAJRls2/O3u39xy\nyy2/vftv6/d1Lio4+JSLLr3iiived96xo3JDCOE/v71t5V9vufGGH/3sntV17YPiL/52/rzj\njlvxhePdtB4AAADYpaEhPPxwWLIk1NR0H4YedFA466xQVhbKy4WhMFRlNBhN1r+05I5bb7nl\nltsqn9nj/vO75B900oWXXnHFFf/6luPG7N5t7ujjLvjE9y746FX3fu6t7/zu4/WpZ1seu/5L\nf/jkHe8ecWB7BwAAAAa7+vqwdKkwFNirjASj8W1PL/z9Lbfccuufal7e1xXzIX/8CRe8b/4V\nV156/vHjuuwyd9JbvnPnt5+Y9pEH2u8PV3/vnZWt756X389dAwAAAINf5zB00aJubqAkDIUI\nG9BgtHn9o3/5zS233PLbe3ZbHHSPjsa+8S3vveKKKy69cOb4Hmebk99/5dxPPPDntvZ/5/nn\nXwlhat8bBgAAALJAr8LQgw8Os2YJQ4EBC0Yf++557/vaA89u39cV8yF3zHHnvXf+FVe8/6KT\nDyrodfmSI46YEMKr7Y9yctx9CQAAAIa0/QhD58wJZWXh2GOFoUAYwGB0zcP3P7t9by/kjpox\n9z3zr7jisreddkjh/tdvbW1NbxdOnTpx/ysBAAAAg1NdXVi2LFRWhiVLwiOPdBOGHnJI+63k\ny8rCcccNVItA1sjczZdyRkw7993zr7jisrefOamoz9W2P//85vbNvJK5583u/ZxTAAAAYBDq\nHIauWBE6TYzaC2Eo0GMDH4zGSo88+13zr7ji8neUTR7Wb1XbZn7qTwu/PHny5MMOmzh2WG6/\n1QUAAAAG3PbtoaYmVFWFqqrwxBMhvs+F+UIIYcqUMHt2mD07VFSEI44YqBaBrDdwwWjO8CPO\nvuTyK66Y/46zphT3e/VxJ15wUb8XBQAAAAZKbW3OkiUlf/1r3rJlOY8/bmYocKANWDB6/i/W\nv6OkxNrGAAAAQIetW8Pixe0zQ598Mj+RyO9i8BFH7JoZOmXKgPUIDFUDFowWl5QM1D8FAAAA\nDFq1tWH58lBZGSorw+OPh0Siq8HpmaFz57pMHuhfmbv5EgAAABARvQlDEwcdFJs1KzZ3rjAU\nOKAEowAAAMABsGlTWLQoVFeHqqrwj3+EZLKrwUcfHSoq2srKdp58cuKQQ8aMGRPLyRmoRoGI\nEowCAAAA/WTTplBd3R6GrlzZTRg6bVqoqAgVFWH27DBpUggh3tycqK0doFaByBOMAgAAAH2w\naVNYtizU1ITKyvDYY92EoVOnhrKyUF4ezjvPDZSAzBKMAgAAAL20YcOumaGrVnUzeMaM9mmh\nFRXhkEMGpD+A7glGAQAAgB7YuDEsX96LmaFz5oSysjB7djjssIFqEaAXBKMAAADAPmzYEBYt\nCkuWhJqaXoShZ58dJk8eqBYB9pNgFAAAAOhEGApEg2AUAAAAIm/9+rB4ca/D0HPOCYceOlAt\nAvQzwSgAAABE0v6FoeeeGyZNGqgWAQ4gwSgAAABERioMrawMS5aEp5/uURg6Z044++wwbtxA\ntQgwQASjAAAAMKS99lpYsqQ9DF21qpvBwlAgMgSjAAAAMOTsXxh6zjlh7NgB6Q8g8wSjAAAA\nMCS8+mqoqelRGJqTE2bMCOXlwlAgygSjAAAAkLVefDFUV4eqqlBdHV56qauRubnhhBNCRUWY\nPTvMmhVGjx6gDgEGK8EoAAAAZJX0zNCFC8OLL3Y1Mjc3TJ/ePjP03HPDmDED1SJAFhCMAgAA\nwKD3wgvtM0OrqsIrr3Q1Mjc3nHTSrpmhI0cOVIsAWUYwCgAAAINSembo/fd3f5l8embonDku\nkwfoCcEoAAAADBrPPde+YGhVVVi3rquReXlh5swwe3aoqAizZoXS0oFqEWCIEIwCAABARj37\nbKiubg9DX321q5F5eeGUU0JFRaioCOXlwlCAvhCMAgAAwIBbsyYsWRJqasJ994WXX+5qZG5u\nOPHEUFYWysvD3Llh1KiBahFgiBOMAgAAwIB4+un2maHV1eG117oamZ8fTj21fWZoWVkYPnyg\nWgSIEMEoAAAAHDCrVu0KQ9ev72pkfn447bRdYWhJyUC1CBBRglEAAADoV2vWhMrKsGRJqKoK\nr7zS1ci8vHDCCWHOnFBWFs46K4wcOVAtAiAYBQAAgL5Lh6EPPRTWru1qZOcwtKIijBgxUC0C\nsBvBKAAAAOwXYShANhOMAgAAQI+lwtDKyvDQQ2Hz5q5GpsPQVB46bNhAtQhAjwhGAQAAoCuN\nK1fGHnigKDUzVBgKMFQIRrtQV/OtDy9YvDOMuuD6mz90bE/eEd/5wrKFCxc/tvL5f27aXtea\nO3z0mLEHH3liWcXZ5SdPKc0ZkAoAAAD03Zo1z/3P/2z9/e+PXrt2TCLR1cjOYWh5eSgqGqgW\nAegTweg+bV38ox8v3tnz8S2vPPjjb/+08sWGTs/t2Lhux8Z1a55cdMetMy78yKcvL5tYcEAr\nAAAAsP86LpNPPvBAbOvWo/c9MJmXFxOGAmQ5weje1a/85Ze///COHo9vWfOnL33h5yvr0k/k\nFJaOLIrX7mxoS4YQQnLnM39ecNUrH/nml94yKfcAVQAAAKB3Eonw9P9n787joizXP45fM+yy\nK4Ib4pZruSaooCDiWm6ZuVTmMbcW+3VsMctjJ5dMLXNLrdQW7ZSWlZqmiAqyKJhr5S7uIi7I\nvs0M/P4YHAlhmIGZYfHzfvXH8Mz13M+FwxB8ue/nPinR0RIWJnv2yJ072sOK4mqzRA6LRImE\nifzl5LRz7dq2bdtaslkAgGkRjD4o/+6hNf/9aMvFXIPPyDz25YdfFWSaCpfWA/81dkhASw87\nkbyMq0d2bVz7XfiVHBFJO/r5B2sbLp/Q5sFJn+UfAQAAAABgCI1GTp0qCEN375akJD21mSJH\n7oWhUSLZuieSkwcPHnzs2DEX9pcHgCqLm1b+U97dw9/NeG3Wlgs5hp+jObNxVejNfBERcXn8\n5flzx/dq6WEnIiJKxwadhkxdNO/5Vtobbufd2LZm85V8048AAAAAACiZRiN//y1ffCHPPCOe\nnvLoozJpkvz4Y7GpaKZItMh8kd4iNUUCRN4RCSucioqIyMWLFxcuXGiZ9gEA5kAwel/m5ai1\n7732wYY/U4zKHTP3b9p+TXtGDd9xr/d9cKG7XbPh7072dRQRkbxzmzYezDX1CAAAAACAIjQa\nOXhQPv5YBg6UWrX0h6FZSmWoyHsi/iJuhcJQ/XNmPv/8c41GY6b2AQDmxlJ6ERH17T+3/+/r\njXvOpt7badC2flBAzQN7/szWe56ISFrM7tiCKreegwNLWEThGvR073Vxv94WkcwDEQezff3t\nTTgCAAAAAEBERKNRHD4sBw4UrJS/e1dfcY0a0q1bbufOUzZs+CY+3oh1g/fcunXrjz/+8PPz\nK2u7AICKxIxREZE/vv3v6jBdKmrfMHDSR59M7VHHkH+c3KN//FlwntPjfo+WuC2SooWfr5v2\nYU5c9CGVKUcAAAAAgIeYWm196JDDsmUuo0bVatbMuksXef11+fHH4lNRJyfp10/mzZP9+yUl\nRXbtej8//4sypaJa8fHx5WgdAFCRmDH6Dw4Nuj41fvywjrWtRQ4bdMbFM2cKlrUrmrdqWezO\nhQVPP9KiuXJ7XJ6I5Jw8ES/+LUw2AgAAAAA8ZNRq+eMPiYiQiAjHyEhFerq+YmdnCQiQwEAJ\nCpJOncT6/i/CKSkpS5cuLU8jWVlZ5TkdAFCBCEa1lI7enfsOHfFUcHMXoybRZl6+dLvgoUdD\nb72L220bNPCUuBsiIneuXsmSFg4mGgEAAAAAHgZqtRw8KBEREh4u0dFyLwwtfnqJi4sEBEhQ\nkAQGSseOhcPQwnbs2JGZmVmepurVq1ee0wEAFYhgVESkzZgVX3vUtivDmbdv3Us1xcPDQ39t\nrVq1RG6IiMjNWzdFfEw0AgAAAABUV2q1HDsmYWESFSWRkZKSoqc239FR/fjjyj59rHr0EF9f\nsbUtdfhjx46VpzsbGxtuMAoAVRfBqIiIs0ftMp6ZnJx876GLSwnbJt3j5Ox072F6mm6dR/lH\nAAAAAIDqRKWSuDgJD5eICImJkYwMfcWuruquXXO6dlV166Z+7DGxsnJ1dbWysTHwUrdu3SpP\np/3793d3dy/PCACACkQwWj7Z2fduJ2Pl4FDKXyNtHRysRDQi/7gLTflHKNnbb7+9Z88e/TVN\nmzbVPkhOTr59+7b+YkPk5OTk5JT5xuWoXPLy8kzyVYGKpVKpeB2rE17NakCj0fA6Vid39e95\njaogPz+fd2XFU6ut//7bJiLCJjbW5sABRWqqnlrtzNDcHj3Ufn6qjh3lnzFoit5ZpUXY2+u9\nn1lp3njjDb54zCQpKamiW4DJpKWlpaWlVXQXKK9CU/sqhu6rKC8vz1RjEoyWS75KrSl4aGVd\n4n7y91hZ3Ys11Rq1yUYAAAAAgKpIkZtrffiwTXS0TUyM9cGDCr2zP/Ld3FRduqj8/VXduqnb\ntBGrUn99Mkjz5s3LfO7s2bNbt25tkjYAABWCYLSc8u89UJRwx+/Ciq0o/wgAAAAAUEUUnhm6\nf79C7ySyfCcndadOuT16qAID1Y89Jkqjtso1SO/eva2trdVqoyeefPDBB5MnTzZ5PwAASyIY\nLReFtfX9KZya0qo1usmhtjb3Fs2XfwQAAAAAqNTuhaG2+/ZZx8YqsrP11FogDC3Mw8Nj5MiR\n69evN7BeqVR27959xowZ7du3N2tjAAALIBgtnxo1aoikiYhosrM1IvpWc6iysu/Fmnb2dqYb\noWQNGjRo1aqV/pqaNWueP39eRKysrKyty/X1oNFo8vPzFQqFlYlWtaBCFPlreTm/KlCxeFdW\nD7wrq5O8vLy8vDzelVWd9rur7kMrKyuFgmU9VZX2XSl8dzUHtdrqr7+sw8NtIiKsDhwoNQzV\nPP64KjBQHRSkadtWF4Ya+KroXkctY9+V//nPf/bs2XP9+vVSK//v//7vpZde8vLyMnxwGCs/\nP1+j0QjvyiqunO9KVCq6d2WFv47Ke/93MGEbfKMpH1dX14JYU9LSUkX0bUdY6E7Dbm5uphuh\nZK+99lqpNcePH4+OjhYRZ2dngwYtWXJyslqttrW1dXZ2Ls84qFh37tzR/bKnVCrL+VWBipWa\nmpqbm2ttbe3q6lrRvaDs7t69qym0poB3ZZWWkZGRlZXFd9eqLiUlRaVSbF4S3AAAIABJREFU\n6T50cXEh6a66srKyMjIyFAoF70rTUKvl2DEJC5OwMImKEr1hqLi4iK+vhIRISIiiQwdrpbLM\nv52mp6dnF7qWk5OTjcG70ouIm5vbtm3b+vXrl5iYqKds+fLlr7zySll7hKFycnK0v/m6uLgo\nzTxfGOaTmZmZmZmp+7BGjRp2dgZM70KlpFKptJvaOTs7V+xfLBwdHbUPCEYrDU8vT5GrIiJy\n584d/bHmnTt3Ch4pPGrVMt0IAAAAAFBRsrLk0CGJjjYoDK1dW/z8JCBAQkKkQwdzL5M3XPv2\n7Q8ePDhp0qTff//9wWebNWu2fPnyvn37Wr4xAIBZEYyWj33Dhp5y+KaIyM2rV1XSrOS/S+Ze\nu3az4KGnj4+96UYAAAAAAEuqFmFoEd7e3tu3b4+Njf3pp5/i4uISExPd3d2bNWs2aNCgIUOG\nGDUFFQBQVRCMllOjFs1t5WauiGjOnD0vQS1LrDx3+kzB/TVsH3mkoSlHAAAAAAAzy8yUw4cN\nDUM9PcXXtyAM7dhRqs69Bf38/Pz8/Cq6CwCAhRCMlpN1u45traL+0IhIUlzsufEtmxX/v/z8\n0wfi7mofKtt2bGdjyhEAAAAAwAwKh6GRkZKTo6/YDGGoRqOJiYk5ffp0UlKSl5dX27ZtO3To\nUP5hAQDQIhgtL6eugZ0+/yMuR0QSQzdFPTWte3EbD6VGbAq7pX1o7xfczcm0IwAAAACAaRgb\nhgYGir+/BASYdmZoVlbWkiVLFi1adOvWrcLHmzZtOnPmzOeee45teQAA5UcwWm6O/k/1WR+3\nNVFE0qJXzN/c8P3BPv+czpl74eePVh1IFxERRf0BT3WtYeoRAAAAAKDM0tMlOlrCwyUiQg4e\nFLVaX3HduhIUJIGBEhgoLUu+E1g5XLlyZdCgQUePHn3wqfPnz7/wwgubNm367rvvnJyYLwIA\nKBeC0fKzbj1yYlD07PAkEck4vubtty6NeXFEr0e97BWSn33jz90b13wTdkF7Ax6FZ+9Jz7Sw\nMv0IAAAAAGCMjAzZv1+ioiQ6Wvbtk9xcfcVeXtKjhzlmhj7o7t27ISEhZ86c0VOzZcuWYcOG\nbd++3cqK340AAGVHMGoKzp1ffm/Mzfe/PZEuIlnxYZ+/F7ba3tXNMT8jOTVboytzbP3CuxPb\nFzvZs/wjAAAAAIB+aWkSGSkRERIRIYcOlTIztH79+zNDmze3VIvyyiuv6E9FtUJDQz/55JO3\n337bAi0BAKorglHTsH/k6f9+6LZq8dq98en5IiKa7JQ7hbdprOETPP7Nl0J8bM03AgAAAAAU\nZdTM0Dp1pHt3y8wMLdaff/75/fffG1g8b968l156ydm5uD0aAAAwAMGoydg3Cnn9U98no/eE\n7487dvZ60t2UzDzbGq6eDR9p3Smgd+9uzVxLW+RR/hEAAAAAQFJS7s8MPXxYNBp9xd7eBTND\ng4KkaVNLtVi8H374wfDi5OTk33///ZlnnjFfPwCA6o1gtEQdp/ywZYqR5yhcmgUMaRYwpOxX\nLf8IAAAAAB5CyckFYWh4uBw9WkoY2rChBAUV5KFNmliqxdJFR0cbVR8VFUUwCgAoM4JRAAAA\nAKia0tPlwAEJC5OoKImLE5VKX3HduhIQICEh4u8vbdpYqkXj3Lhxw6j6hIQEM3UCAHgYEIwC\nAAAAQNWRliaxsdUpDC3M3t7eqHoHBwczdQIAeBgQjAIAAABA5ZaUJJGREh4u4eFy/Ljk5ekr\nbtz4/jJ5Hx9LtWgajRs3PnbsmFH15msGAFDtEYwCAAAAQOWjmxkaFiZHjpQShupmhvbuLVU5\nK+zfv/+vv/5qeP2AAQPM1wwAoNojGAUAAACAyqFsYWifPtKokYU6NLMRI0a8++67d+7cMaS4\nc+fOvr6+5m4JAFCNEYwCAAAAQMW5dUsOHJDoaIPC0CZNxN9fAgKqUxhamKur64cffjhp0qRS\nK+3s7D799FOFQmGBrgAA1RXBKAAAAABYVtnC0L59q9w9Q8tg4sSJx48f/+yzz/SXLVmyxN/f\n3zItAQCqK4JRAAAAADA/wlCDLV++3MfHZ+bMmdnZ2Q8+6+Hh8cUXXwwdOtTyjQEAqhmCUQAA\nAAAwj8REiYiQiAgJD5eTJyU/X19xy5YSGCiBgRIUJHXrWqrFSuqtt94aOXLk0qVLt2zZcvbs\n2fz8fGtr67Zt2z799NMvv/yyq6trRTcIAKgOCEYBAAAAwHRu3pTY2IKZoYcPlxKG6maG9usn\nDRtaqsWqwdvbe+HChQsXLlSpVKmpqe7u7kqlsqKbAgBUKwSjAAAAAFA+N25IeHjB5NCTJ0sp\nbt26YFpoYKB4eVmkv6rNxsamVq1aFd0FAKAaIhgFAAAAAOMlJBSskY+IkFOn9FUqFNK6dUES\n2qMHYSgAAJUEwSgAAAAAGCYxUfbtk6goiY42aJl8SIj4+0twsDRoYKkWAQCAoQhGAQAAAKBk\n169LeHjBzNAzZ/RVKhTSpo0EBUlQkPToIbVrW6pFAABQFgSjAAAAAPBP167dD0PPntVXqVDI\no48WLJMPDBQPD0u1CAAAyotgFAAAAABEbtyQyEgJC5OoKDl50qBl8iEh0rMnYSgAAFUUwSgA\nAACAh5Ti6lW7XbtsY2LkwAE5f15fqVIpjz1WsJt8jx7CJukAAFR9BKMAAAAAHiaXL+uWydvH\nx9vrqVQqpW3b+2FozZoW6xEAAFgAwSgAAACA6u76dYmOLlgmf+KEvkqlUlq2lIAACQmR4GBm\nhgIAUI0RjAIAAACoji5ckIiIgg2ULl7UV2llJe3aFcwM7d5d3N0t1CEAAKhQBKMAAAAAqgvd\nzNBdu+TCBX2VVlbSooW6S5csf39Vjx41mzWzVIsAAKCyIBgFAAAAUJWdP18wMzQ8XK5c0Vdp\nZSUdOtyfGerqqsrKysnIUCgUluoVAABUIgSjAAAAAKqac+fuh6FXr+qrtLKSjh3vh6EuLpZq\nEQAAVHYEowAAAACqgvh4iYqS6GgJDS39nqHt24u/f8EeStwzFAAAFIdgFAAAAEBlpQtDd+6U\nS5f0VRYOQ3v3Fjc3S7UIAACqKoJRAAAAAJXJ6dMFW8mHh0tCgr5Ka2vp3FkCAyUwUAICxMnJ\nUi0CAIDqgGAUAAAAQEXTzQzdsUMuX9ZXycxQAABgIgSjAAAAACpCfLyEhUlUVOm7yVtbS7t2\nEhIi/v7So4e4ulqqRQAAUJ0RjAIAAACwFMJQAABQaRCMAgAAADAnXRi6d69cvaqvsnAYGhgo\nLi6WahEAADyMCEYBAAAAmBphKAAAqPQIRgEAAACYgi4M3bNHrl3TV6kLQ7V5qIODpVoEAAC4\nj2AUAAAAQFlpw9CwMNm7V27f1ldJGAoAACoZglEAAAAAxihbGBoQIPb2lmoRAACgdASjAAAA\nAEqjC0P37JE7d/RV2thI27aEoQAAoPIjGAUAAADwgLw8OXlSoqMNCkMdHKRjRwkIIAwFAABV\nCMEoAAAAABER0Wjk2DGJiJC9eyUyUpKT9RXXqCHduklgoAQFia+v2NpaqksAAADTIBgFAAAA\nHmIajRw5IhEREhFRehjq6Hg/DO3cmTAUAABUaQSjAAAAwENGo5FTpwqWye/eLUlJ+opr1JAO\nHQqWyXfvLnZ2luqyCkhOTt62bduhQ4du3rzp7u7erFmzQYMGNW7cuKL7AgAABiEYBQAAAB4C\narUcPnx/Zmhqqr5iJyfx95fAQAkMlM6dxcbGUl1WGZmZmbNnz166dGlmZmbh46+//vrTTz+9\nYMEC4lEAACo/glEAAACgmlKr5dCh+2FoWpq+YicnCQi4H4Za85tCiRISEp588snDhw8X++xP\nP/20Z8+en3/+OTAw0MKNAQAAo/DjDgAAAFCNaDRy9KhERUl0tOzaVfo9Q7t2FX9/CQiQHj24\nZ6ghMjMz9aSiWklJSYMGDYqJiWnTpo3FGgMAAMYiGAUAAACqOLVaDh6UiAgJD5foaElP11fs\n7Czdu0tQkAQGSseOzAw11pw5c/Snolqpqanjxo07cOCAQqGwQFcAAKAM+DEIAAAAqIK0M0PD\nwiQqSiIjJSVFX7GTk3TpIiEh4u8vvr7MDC2z5OTkJUuWGFgcFxe3ffv2J554wqwtAQCAMiMY\nBQAAAKoIlUri4iQ8XCIiJCZGMjL0Fbu63p8Z2qGDWFlZqsuqJD8//9ixY3/99Vd2drazs3Or\nVq0CAgJsSt5savv27UV2W9Jv06ZNBKMAAFRaBKMAAABAJaZWy7FjZZkZ6ufHbvJ65OXlffPN\nN7Nmzbp48WLh4+7u7v/+97+nTp3q6Oj44FlHjhwx6iqHDh0qT5MAAMCsCEYBAACASqZwGLpv\nn6Sm6ismDDVeenr6s88+u2XLlgefunv37syZMzdu3Lhly5bGjRsXefbmzZtGXcjYegAAYEkE\nowAAAEAlYFQY6uwsfn6EoWWj0WiefvrpnTt36qn566+/evXqFRcX5+HhUfi4m5ubUdcyth4A\nAFgSwSgAAABQQXRhaFiYREdLVpa+Yl0YGhIiHTqIUmmpLqukv/7668yZM3fv3vX09OzQoUOD\nBg10Ty1atEh/Kqp14cKFl19+eePGjYUPNm/e3Kg2WrRoYVQ9AACwJIJRAAAAwIIIQ81JpVKt\nXr36448/jo+P1x1UKBRdunSZOXNmv3790tPT582bZ+BoP/7445EjRzp06KA7MnDgwFdffdXw\nfgYNGmR4MQAAsDCCUQAAAMDMCoehUVGSna2v2MVFfH0JQ8vg5s2bQ4cOjYmJKXI8Pz9///79\n/fv3nzBhQnBw8N27dw0f84cffigcjDZs2HDEiBEbNmww5NwGDRqMGjXK8GsBAAALIxgFAAAA\nzCArSw4dkuhog8LQ2rXFz08CAghDDXf+/Pldu3Zdu3ZNrVbXr1/f19f3xRdf/Ouvv/Sc8uWX\nX0ZGRhp1lejo6CJH5s+fv3v37tu3b5d67rJlyxwcHIy6HAAAsCSCUQAAAMBECEMt4uDBg2+/\n/XZ4eHgZzj116pRR9QkJCUWO+Pj4/PLLLwMHDkxOTtZz4ieffDJkyBCj+wMAABZEMAoAAACU\nQ2amHDtmaBjq6Sm+vgVhaMeOolBYqsvq48svv5wyZUpOTo5lLlfslM+AgID9+/e/+OKLDy7b\nFxFvb+9ly5YNHjzY/N0BAIByIRgFAAAAjKPIzLSOi7OJibGJjrY6ckRUKn3VXl4SGChBQRIY\nKK1bW6rH6un777+fOHGiJa/YpEmTYo+3bNkyOjo6NDT0p59++uOPP27evOnq6tqyZcuBAweO\nGDGCFfQAAFQJBKMAAACAATIz5fBhiY523LHDKiZGkZurr9jTUwIDxd9fAgKYGWoqCQkJEyZM\nsPBFBwwYoOfZPn369OnTx2LNAAAA0yIYBQAAAEqQni7R0RIeLhERcvCgqNWi5wfounULpoUG\nBkrLlhbs8mExf/78jIwMS16xVq1abCsPAEA1RjAKAAAAFJKWJlFREhEhERHyxx/aMLQkeXXq\nKHr2VGjz0BYtLNbjQyg/P3/Tpk2mGs3Kykqj0ZRaNm/ePFdXV1NdFAAAVDYEowAAAHjoZWTI\n/v0SFSXR0bJvn+hdJp/v5ZXr56f281P5+anbtnWvWdPKyspinT60rl69evXqVVONNnDgwF9/\n/VV/zauvvmr5lfsAAMCSCEYBAADwUDImDJU6daR7d+09Q1ObNlXpnUYKc0hMTDThaNOnTx8/\nfvyLL75Y7LAODg5z5syZOnWqCa8IAAAqIYJRAAAAPDRSUiQysmCZ/OHDon8xtbd3wT1Dg4Kk\nadN/DAKLc3JyMtVQHTt27Ny5s0KhOHfu3LJlyzZt2vTnn3/m5uZaWVk98sgjgwcPnjJlSv36\n9U11OQAAUGkRjD7s8vPztQ80Go26fHMftEPl5+eXcxxUKryaVRrvyupB941ai1ezSsvLyxPe\nlZaXnq6IjVXs3q2IjlYcPCgqlb7iunXz/f3ze/XK79Ytv3Xr+8cLvWQPviuLHIE51K1b19bW\nNlf/xF7DLFy4UHuDUXt7+9dee23ChAkKhSI/P9/Z2Vl3VwTepFWL9rurjkajUSgUFdUMykl3\n/1+1Wq1UKiu2GZTZg+9Kvq9WXbp3pSG357ZMJyZEMPqw0323SktLS05OLv+Aubm5JvmBFZVB\nXl6eSb4qULHUajWvY3XCq1kN8N3VAhQpKTYHDthER9tER1v//bf+maF53t4qf3+Vv7+qWzdN\nw4b3nzDsZUpLSytntzCQv7//3r17yznI7Nmz27ZtW+Q9qI22eSmrjfT09IpuASaQmppa0S3A\nZDIzMzMzMyu6C5RXhf+PUvdVVCR5Lw+CUQAAAFQHivR060OHbPftsz5wwObIEf0zQ/O8vFR+\nfqrAQJWvr6ZlS4s1ifKYNGlSeYJRR0fHBQsWPPPMMyZsCQAAVGkEow873doEZ2dnNze38gyV\nlpam0WhsbW1r1KhhitZQMVJSUnTrAZVKpYuLS8X2g/LIyMhQqVTW1tYmvC8bLC81NbXwX0TL\n+b0aFSsrKysnJ4fvrqaUlqaIi1Ps3q3YvVtx9Kjonz6gWybfq1d+48ZWIlYi9sZfMz09vfB6\nwMLrr6u93NzciIiIo0eP3rp1y8XFpUWLFn369HF1dbXM1YcNGzZ48ODNmzeXWlm7dm2NRpOU\nlKT9sFGjRsOGDfv3v//t5eVVpDInJycrK0uhUFjss4A5ZGZmFl615uTkZG3Nr7pVVW5urnZS\nmIuLC0vpq67s7Ozs7GzdhzVq1LC1ta3AflAearVaOxO/wn/m0cVNJvzmwP8tHna6m+9YWVmV\n86cH7VAKhYKfQqoTXs0qjXdl9VDkLmm8mlWa9mc43pXllZYmsbESFiZhYXLkSKlhqAQESEiI\n9O4tjRsrRMp/38EH35UPQzCqUqmWLl06b968O3fuFD5ua2s7ceLE999/38PDwwJtrFu3rlev\nXgcPHtRT06xZs3379tWpUycxMTE1NdXT01PPn5RU92YW866s0or8hlz+X21QgXT3ELS2tiYY\nrbp4V1YnurlTFf46muMnLr4uAQAAUOmVIwy1VIvVWVJS0rBhw8LDwx98Kjc3d/ny5Vu3bt2y\nZUvbtm3N3Ymzs3NERMSUKVPWrFlTbMHQoUNXr15ds2ZNEalTp06dOnXM3RIAAKi6CEYBAABQ\nKaWmSlycoWFokybi7y8BAdKnjzRqZKEOHw65ublDhgyJjIzUU3Pp0qU+ffrExcU1LLx7lXk4\nODisXr16ypQpX3311a5duy5dupSXl9egQYOePXuOGTPG39/f3A0AAIBqg2AUAAAAlcatW3Lg\ngERHGxeG9u0rPj6WavGhM3/+fP2pqFZiYuL48eNDQ0Mt0JKItGvXbvHixZa5FgAAqK4IRgEA\nAFChCEMrsbS0tI8//tjA4l27dkVGRnbv3t2sLQEAAJgKwSgAAAAs7uZNiY0tCEMPH5Z7N/Uv\nni4M7ddPzL9SG4Vt3749NTXV8PqNGzcSjAIAgKqCYBQAAAAWQRhaBenf//1BsbGxZuoEAADA\n5AhGAQAAYDYJCRIRUfDfyZOlFLduLYGBEhgoQUHi5WWR/lCKxMREo+pv3Lhhpk4AAABMjmAU\nAAAAJpWYKPv2SVSUREcbNDM0JET8/aVnT/H2tlSLMJSTk5NZ6wEAACoQwSgAAADK7fp1CQ+X\niAgJD5czZ/RVKhTSurUEBUlQkPToIZ6elmqxmsjOzr5586aDg0Pt2rUtcLlmzZoZVf/II4+Y\nqRMAAACTIxgFAABAmdy4IZGRRs8MDQ6WBg0s1WL1kZ6evnz58o0bNx45ckR7xM3NrX///q+9\n9lqXLl3Md90nnnjizTffNKrefM0AAACYFsEoAAAADHb1qoSHF0wOPXdOX6VCIY8+en9mqIeH\npVqshvbs2TN69Ogit/tMTk7+/vvvv//++7Fjx65cudLe3t4cl27ZsmW/fv127NhhSLGXl9fo\n0aPN0QYAAIA5EIwCAABArytX7oeh58/rq1Qq/xGG1qplqRars82bN48YMSInJ6ekgq+//jo+\nPj40NNTOzs4cDXzyySdRUVHp6emGVHKPUQAAUIUQjAIAAOABCQkSFSVhYRIVJSdOlFKsXSYf\nEiLBwYShpnXmzJnnnntOTyqqtW/fvqlTp3722Wfm6KF169bffffdiBEjsrOz9ZS99957zz77\nrDkaAAAAMBOCUQAAAIiIyMWLBbsnRUTIhQv6KpVKaddOAgMlKEi6d5eaNS3VYpX3559/njx5\nMjk52dPT87HHHmvatKn++unTpxsyVVNEvvzyy5deeunRRx81RZtFDRo0aM+ePWPHjj1T3M5a\n7u7un3zyyb/+9S9zXBoAAMB8CEYBAAAeYhcu3A9DL17UV2ll9Y8w1N3dQh1WC2q1es2aNQsW\nLIiPjy98vH379v/5z3+GDh2qUCgePCsxMfHXX3818BIqlerLL79csmSJCdotTteuXf/666//\n/e9/P/300+HDhxMTE2vWrNm8efPBgwePHz/ena8HAABQBRGMAgAAPGSuX5foaAkLk127SpkZ\namUlLVpIQICEhEivXswMLZvbt28PGzZs3759Dz519OjRYcOGjRw5cu3atQ4ODkWeDQ0NzcvL\nM/xCBm6RVGY2NjYvvPDCCy+8YNarAAAAWAzBKAAAwEOAMLSCZGRk9OnT58iRI3pqfvjhh/T0\n9M2bNyuVysLHL126ZNS1Ll++nJ+fX+zkUwAAADyIYBQAAKCa0oWhoaGlL5PXhaEhISyTN6E3\n3nhDfyqq9dtvvy1evHjq1KmFD+bm5hp1LZVKlZeXZ2VlZVyLAAAADyuCUQAAgGokPl6ioiQ6\n2qAwtH178fcvyEMJQ0uQl5d34MCBXbt2Xb58WaPRNGjQoHPnzr6+vjY2NqWee+7cubVr1xp4\noblz506YMMHZ2Vl3pF69eka1WqdOHVJRAAAAwxGMAgAAVHG6MHTnTtG/+LpwGNq7t7i5WarF\nqmrnzp1vvPHG33//XeS4t7f3e++9N2zYMP2nb9iwQaVSGXitpKSk7du3jxgxQneke/fuRnXb\no0cPo+oBAAAecgSjAAAAVRBhqPnNnTt3xowZxT515cqVyZMn79+/f/78+XpGKHbDJf31hYPR\nNm3atG/f/ujRowae/uyzzxp1OQAAgIccwSgAAEAVoQtDd+yQy5f1VRKGltuKFStKSkV1vvnm\nG2dn58WLF5dUkJCQYNRFr1+/XuTIRx991K9fP0PO7dGjxxNPPGHU5QAAAB5yBKMAAACVWHy8\nhIVJVJRERJQShlpbS7t2EhIi/v7So4e4ulqqxWro4sWLRfZBKsny5ctHjhzp7+9f7LO2trZG\nXffB+r59+7799tsLFizQf2KdOnXWr19v1LUAAABAMAoAAFDJ6MLQ8HC5ckVfJWFoIbdu3fr5\n55/37t177do1pVLZqFGjkJCQIUOGFN7OyEAfffRRTk6OgcWzZ8/esWNHsU/5+PgcOnTI8Os2\natTowYPz5s2zsbGZO3duSWc1b958y5Yt3t7ehl8IAAAAQjAKAABQKejC0L175epVfZWFw9DA\nQHFxsVSLlZdGo5k7d+7ChQvT09N1B/ft2/ftt996eHjMnj178uTJho+Wl5f3yy+/GF6/Z8+e\nu3fvuru7P/hU3759f/75Z8OHKnbVvFKpnDNnzoABA2bMmBEREZGXl6d7ytPT89VXX506daqj\no6PhVwEAAIAWwSgAAEAFIQw1haysrKeeeqqkOZu3b99+6aWXYmNj16xZo1QqDRnw6tWrN2/e\nNLwBlUr1559/Frsj/DPPPDN9+vSkpCRDxmndurWebeW7deu2Z8+exMTEuLi4GzduODg4NG/e\nvFOnTlZWVoa3CgAAgMIIRgEAACzH6tIlu8hIOXxY9uyRa9f0lerCUG0e6uBgqR6rmHHjxpWU\niup8/fXXdevW/fDDDw0Z8NatW8b2kJiYWOxxNze3WbNmvfrqq4YMsmjRolJTTi8vr4EDBxrb\nHgAAAIpFMAoAAGBm2pmhYWE19uxxvHNHXyVhqJF+++23H374wZDKjz/+eNSoUY899lipla7G\n36rVzc2tpKdeeeWVw4cPr127Vv8I8+bN69u3r7HXBQAAQHkQjAIAAJjBvTBU9u6V27e1xxTF\nVhKGloOBk0BFRKVSffTRR999912pld7e3jVq1MjMzDS8jZYtW+p5dvXq1d7e3vPmzcvNzX3w\nWUdHx6VLl44bN87wywEAAMAkCEYBAABMIS9Pjh+XiAgJD5d9+0T/bSUdHKRLFwkKkqAg8fMT\nOztLdVmtJCQkxMbGGl6/bds2lUplY2Ojv8zOzq5v376G77/Uvn17/TvCKxSK//73v6NHj160\naNHmzZtv3LihPd6kSZNhw4ZNnTq1Tp06Bl4LAAAAJkQwCgAAUFZ5eXLypERHS1iY7Nkj+pfJ\nOzho2rXL9fXV9Ozp1K+f2NtbqkuzyMnJsavoPPfkyZOFt2gvVUpKypUrV5o0aVJq5Ztvvml4\nMPrmm28aUta8efNVq1atWrUqKSkpOTm5du3azs7OBl4CAAAA5kAwCgAAYAyNRo4duz8zNDlZ\nX3GNGtK1a8HMUF/fbJUqKyvLysqqaqWiGo0mMjLy6NGjiYmJly5dOnfu3Pnz55OSkmxsbHx8\nfAYMGDB58uRWrVpZvjEDd3sv7M6dO4YEo926dRs/fvzq1atLrezZs+eIESOM6qFmzZo1a9Y0\n6hQAAACYA8EoAABAaTQaOXWqYGbo7t2lLJOvUUM6dJCAAAkJke7d/7FMXqUyd6empVarV65c\nOXfu3GJ3XVepVOfOnVu6dOnKlStfeeWVBQsWlLpK3bRq1apl7CkeHh4GVn722WfXrl37/fff\n9dS0a9fuiy++UCiKv3ksAAAAKjmCUQAAgOJoNHL4sERESESEREZKSoq+YkdH8feXwEAJDBRf\nX7FsPmgmycnJw4cPDwsLK7VSpVItXrz45MmTW7dutWQ22rp1a6VEadz7AAAgAElEQVRSafhq\nend3d/03Ay3M1tZ269at//3vfz/++OPs7Owiz9rY2Dz77LOzZs1yYLMsAACAKotgFAAA4B61\n+h9haGqqvmInp/thaOfO1SMM1VGpVEOHDg0PDzf8lJ07d7755ptLliwxW1NFeXl5devWLSoq\nysD6J5980traiJ9+raysZs+ePWnSpPXr1+/atevy5ctqtdrb27tr165Dhw5t1qxZmboGAABA\nZUEwCgAAHm4ajRw9KlFRBSvl797VV+zoKF27ir+/BAQUXSZfvcyfP9+oVFRr5cqVEyZMePTR\nR83QUfHee++9/v37G1JpY2PzzjvvlOESDRo0eOeddwqfm5KSoqpqd0UAAADAgwhGAQDAw0et\nlkOHJDxcIiIkKkrS0vQVOztLQEDBzNDHHxdjphxWUampqQsXLizDiSqVasWKFStWrDB5SyXp\n16/fmDFjvv3221Ir33vvvdatW1ugJQAAAFQV1f8newAAABERtVr++KNgN/moKElP11fs7Czd\nu0tgoAQFSceOFRWGnj9/fuPGjVFRUVevXnV0dGzYsGG/fv2GDRvm7Oxs1utu3749Vf9tBPSe\na9pmSvXFF1/cvXt369atemomT548c+ZMi7UEAACAKoFgFAAAVF9qtRw8WBCGRkeXEoa6uPwj\nDLWyMkdHGo0mOTnZ0dHR1ta2yFMJCQkXL17My8urV6+ep6fnG2+8sXbt2sJLtvfv379hw4Zp\n06bNmzdv3Lhx5mhPKy4ursznXrlyRaVSWXILJjs7u19//fWTTz758MMPk5OTizxbt27dDz/8\ncOzYsRbrBwAAAFUFwSgAAKheCt8zNDS0lN3knZykSxcJCRF/f/H1lQfCSlO5ePHiO++8s2/f\nvhs3buTn54uIg4ODh4eHiCQnJ2dkZBTZWt3W1jY3N7fYoW7evPniiy8eOXJk2bJlZur2xo0b\nZT43Ly8vMzPT1dXVhP2USqlUvvXWWxMmTNi8eXN4ePiVK1esra0bNmzYu3fvJ554okaNGpZs\nBgAAAFUFwSgAAKj6VCqJiyuYGRoTIxkZ+opdXaV7dwkKksBA6dDB5DNDs7KywsLCzp8/f+vW\nrStXrly8ePHYsWMPrkzPysq6cuVKSYOUlIrqLF++3Nvb++233zZBxw9wcnIq87mOjo4WTkV1\n3NzcXnjhhRdeeKFCrg4AAIAqh2AUAABUTWq1HDsmYWESFSWRkUbMDPXzEyMXep8/f37//v0J\nCQnXr19PSkqysbFxcHBo0KBBq1atzp07d/bs2eTkZE9PzxYtWpw4ceKrr77KzMws16dmmPff\nf3/EiBE+Pj4mH7lJkyZlPrdbt24m7AQAAAAwH4JRAABQdeTmSlyc7N0rERGyf7/ozx/d3e/P\nDG3XrmwzQ3fu3Dljxow//vijjA2bU3Z29qeffrp48WKTj/zEE09Mnz69bOeOGDHCtM0AAAAA\nZkIwCgAAKrfCM0P37RP9u6U7O4ufX5lnhham0WjeeuutTz/9tMwjWMCvv/5qjmD0scceCw4O\n3rNnj7EntmjRYsyYMSbvBwAAADAHglEAAFD56MLQsDCJjpasLH3FujA0JEQ6dBCl0iQtvPHG\nG0uWLDHJUOZz6dKlzMxMc2wutGjRom7duhl1TwBHR8fvv//ekvvRAwAAAOVBMAoAACqHMoWh\necHByk6dTBWG6mzbtq3yp6JaSUlJ5ghG27Vr9/XXXz///PM5OTmG1Ht4ePz0008dOnQweScA\nAACAmRCMAgCAilM4DI2KkuxsPbVZNjbH7e33Wlkdcnc/4+iYeu7czZiYzHfeqVWrVqdOnYYP\nHz5mzBhbW1uT9PXuu++aZBxzUygUHh4eZhp8+PDhnp6eY8eOvXjxop4yW1vb5557btasWfXr\n1zdTJwAAAIA5EIwCAABLyMrK2rZtW2ho6K3LlxsnJXXNywvIzq5z7pxC/4TE2rWTW7T4+ty5\n9TduHFGp8lQqEZHk5MIld+7cCQ0NDQ0NnTdv3rp168q/K/rff/99/Pjxcg5iGS1atLC3tzff\n+IGBgadOnfrmm29++umno0eP3rp1y8XFpVGjRk2aNHnkkUc8PT0bNWrUu3dvV1dX8/UAAAAA\nmAnBKAAAMLvvvvxyy/Tpj96587yIr4id/mpPT+nRQwIDJShoy/nzI0eNytK/rP6e+Pj4Xr16\nbdy4ceDAgeXpNiYmpjynW9JTTz1l7kvY2dlNnDhx4sSJIpKfn69QKMx9RQAAAMAyCEYBAIBx\n1Gp1dHT0yZMnU1JSPDw82rVr16lTp2LyssxMiYmRiIjza9YMT0h4Vu+Y+bVrK4KCtGGotG4t\nCoWIHDt2bPSzzxqYimplZ2c/++yzcXFxLVu2NPbz0klISCjzuZbk4uLy+uuvW/KKpKIAAACo\nTghGAQB4uFy4cCEmJiYxMdHBwaFp06YdO3bcvHnz77//fvbs2ezsbE9Pz65du44YMaJTp07a\n+lu3bv3yyy+RkZHXr1+3sbFJTk4+efJkampq4TF9fHxmzJjxr3/9yyonRw4fluhoCQuTyEjJ\nyRGRpiV0clMkTiRKJEykdd++365bV6RgypQpGRkZxn6CaWlpb7311tatW409UcfBwaHM51rS\nsmXLateuXdFdAAAAAFUVwSgAANXWiRMnLly4kJOTU6dOnQ4dOkRFRc2YMSMuLq5wjUKhyM/P\n13145syZqKiohQsXDh06dNmyZatWrVq0aFFmZqaeqziKtLh06eaECaffeqt1RoZobwNaghsi\nESLhIhEiJwsdP7R+/chRowYMGKA7cuDAgcjISOM+4Xt+++23+Pj4Jk2alO30xo0bl+1ES1qw\nYMGYMWMqugsAAACgCiMYBQCgqlKr1bGxsfHx8dnZ2V5eXl26dPH09BSRrKysZcuWrVix4tKl\nS7piGxsbVXGRZeFUtLBffvnl999/zy5hm3gnEX+RIJFAkc66nyf+uSeSTsK9JDRC5FTJn87c\nuXMLB6NbtmwpubZ027dvf/XVV8t2bkhISEn/XJVB69atP/300z59+lR0IwAAAEDVRjAKAIB5\n5eTkxMfH37p1q2bNmo0aNXJyciq2LDc3Nyoq6vTp02lpaZ6enp06dXrsscfu3r27Zs2a77//\n/uLFi9nZ2QqFwsvLq3fv3sOHD9+zZ8/nn39+584d3QhKpTI4OHjixIkzZ848dapoAlmGmK9I\nKuoo0lUkQMRfpIeIrf6Tvbzyu3d/b/v20MzMwyLFh6//dODAgYSEhLp162o/PHPmjLENF3b+\n/Pkyn+vm5jZ69OhvvvmmPA2YRM2aNSdOnJiUlHT9+nV7e/tGjRr1798/MDDQysqqolsDAAAA\nqjyCUQAAzOWvv/6aO3futm3b0tLStEfs7e179eo1bdq07t2768rS0tIWLFiwbNmylJSUwqd7\neXmlpKQUSSfj4+M///zzzz///MHL5eXlhYWFhYWFmfBTcBbpLhIoEijSqbSfG66JhIvE2tvP\niYx0efzxq1euzPvpJ8OvlZeX9/fff+uC0eQS5p8aqAw3Jy1s9uzZW7duTUpKKs8g5VGnTp3n\nn39+2rRptWrVqqgeAAAAgOqNYBQA8FBQqVQ5OTnFztZMSUn57rvvfvvttwsXLqSmptatW9fP\nz2/EiBE9evTQP+ahQ4c2btx44MCBxMREJyenpk2bPvHEE08//XSNGjXy8/NnzZo1Z84ctVpd\n+JTs7Oxt27Zt27Zt/Pjxn332ma2t7dmzZwcOHHj69OkHx09MTCzPp1xmRs0MvSESKRItEiVS\nMDM0O7vzyZPPP/544dmsBrp9+7busfa2AGWmC1jLxtvb+8cffxw4cKD++6uWjZWVlYODg7Oz\nc/369XNzc7Xxt42NjZeXl7+/f//+/X18fFq0aKFUKk1+aQAAAAA6BKMAgCrp9OnTmzdvPnHi\nxN27d2vVqtW+ffvBgwf7+PgUKTt69OjKlSt37Nhx+fJlEXFycvL39x81atSzzz5rbW0tIl99\n9dXbb79dOI+7fv36oUOHVqxYERISsnbtWm9v7wevnpiYOHny5F9//bXwQW1OOn369EWLFsXE\nxCxdulRP/6tXr75x48bKlSuDg4OvXr1a5n8HU3ER6XFvZmhHEf3rtK8UumfoueIKYmJinn/+\n+Zo1axrbRuHZkR07dvz++++NHUGnW7duZT5XKzg4OCIiYuTIkcauym/YsKG9vf3ly5ezs7Od\nnJw8PT09PT29vLwaNGjQvn37Hj161K5d293dvZztAQAAACgnglEAgOXcuXMnOzvb09PTxsam\nzINcvHhx6tSpv/zyS5HjU6dOff755+fPn6+daZiTk/N///d/RZacp6en79y5c+fOnQsWLNiw\nYcO6desWLFhQ0oXCwsI6d+4cGhratm3bwsfPnDnTu3dvbdL6oOvXr48cOdKQT+S33347ffp0\nBaaiTiJdREJEAkR8RfS/JAkiUSJhItEif5c2ckJCgojUq1fP3d397t27BvajUCjatGmj+3Do\n0KFvvfWWgecW4enpGRQUVLZzC3v88cdPnDjx1VdfbdiwYf/+/drbGtja2lpbWzs7Ozdr1qxu\n3brZ2dmXLl3S3hm2Y8eOw4cPDw4O1p6enZ1tb29feMCMjIysrKzyNwYAAACg/AhGAQBmFxUV\ntXz58h07dmjvoalUKn19fUeNGjVx4sQisVGpYmJiBg8eXHiCp45Go/n666/37t27bdu2Zs2a\nDRgwYM+ePSWNc+LEic6dO5e05bpOYmLioEGDDh06pJvJmJKSMnDgwJJSUWOdPXvWJOMYznxh\naGEODg4iYm1t/eSTT65bt87As/z8/OrVq6f7sGnTpmPGjPn222+NuXKBmTNn2tnZleHEB9na\n2k6aNGnSpEkikpyc7ODgYPjIxn55AwAAALAkglEAgGg0mpiYmLNnzyYlJWlnvT366KMmGTkz\nM3P8+PFFFkTn5eUdOHDgwIEDixYt2rBhg5+fn4GjnTt3buDAgfr3w7l06dKAAQOCgoL0pKJa\npaaiugFnzZq1ZMkS7Ydz584t527plucs4mf+MLSwJk2aaB9Mmzbthx9+UKlUhpz17rvvFjny\nySefREZGXrhwwairDxw48KWXXjLqFAO5ubmZY1gAAAAAFYJgFADMKyEhYc+ePdeuXcvPz2/Q\noEHPnj0Lz4mrcJmZmYsXL/7000+LzMFs2bLl+++/P2LECIVCUZ7Bg4ODY2NjSyq4dOlSz549\nt27d2qtXL0MGnDx5siG7hF++fLls0wxL8vnnn8+ePdvFxSUjI+Ozzz4z4cjmowtDQ0Q6iOjf\nxEcXhoaJxJvi6gMGDNA+aNOmzbRp0+bMmVPqKSNGjBg4cGCRgx4eHr///vsTTzxh+F0+hwwZ\nsm7dOrYtAgAAAFAqgtFKRpN6/sCuXZGH/z53+VZyusrKyb1mrTpN2/sH9gzo5OPMb3lAlXL8\n+PHp06fv2LEjLy9Pd1ChUPTt23fevHnt27evwN60Ll++PHDgwOPHjz/41KlTp0aNGvXzzz9/\n/fXXNWrUKNv4kydP1pOKamVlZT3zzDPHjx+vX7++/sqYmJjdu3eXrZNyysnJCQ0Nffrpp8PC\nwsyxR7mplC0M3SVi3ITM0nTs2LFr1666Dz/44IOEhIQ1a9boOaVPnz5r164t9qkWLVrExcXN\nmDFj9erV+mee+vj4vP/++2PHji1Pmg8AAADg4UEwWonkXtmz6uMvwi4U/pU75ea1lJvX4o/v\n++W7lk++9PoL/vVsK6w/AMb46quvXn755QcXa+fn5+/YsWPv3r1Lly6dOHFihfSmdefOneDg\nYP0T8X788cecnJxffvmlDPPvYmNjDby5ZFJS0syZM/UHZyKyadMmY3swodOnT4vIyZMnK7CH\nYlWSMFTHzs5u8eLFhb9glErl6tWrfX19Z8yYcevWrSL1Tk5Ob7311rvvvmttXeLPJDVr1lyx\nYsX777+/ZcuWv/766+bNm7Vr127atKmLi8udO3eSk5O9vLw6d+7s6+vLRFEAAAAAhiMYrSxy\n4399f8bav9N1B5R2zq72mrTUTHW+iEh+6qmt89+68tKC9/vXt6qwLmEKKpWqPPtxo0r44Ycf\nxo0bp6cgJydn0qRJDg4Ozz//vMW6KmLy5MmGLE/esmXL8uXLX3vtNWPHL7IdvH7ffffd4sWL\nnZ2d9dQUO7PVYrTbRiUnJ1dgDzouIr4Gh6HxItEiUSKhIhfN39vixYu7d+/+4PGJEyeOGjVq\n8+bNu3btunjxokajqV+/fnBw8FNPPVW7dm1DRvby8powYYKp+wUAAADw8CIYrRwyj3354VcF\nqajCpfXAf40dEtDSw04kL+PqkV0b134XfiVHRNKOfv7B2obLJ7Rh2qhearU6Pj7+5s2bbm5u\nPj4++qMWy7h+/fqqVau2bt16+vTprKwsd3f3jh07Dh8+fOzYsabaNxmVx7Vr11588UVDKidN\nmhQYGNiwYUNzt/Sgw4cP//TTTwYWz549e/z48cYuqN+xY4fhxTk5OXv37h00aJCemgcnG1qS\np6eniBgY4ZlDbZEuIv5GhqE7RS6V46Kurq7aRNgQHh4eX3zxxdChQ0sqcHZ2fu6555577rly\ndAQAAAAAJsOKs8pAc2bjqtCb+SIi4vL4y/Pnju/V0kMblikdG3QaMnXRvOdbOYiISN6NbWs2\nX8mvsFYru/Pnz7/44oteXl4tWrTo3r37Y4895uHh0bdv39DQ0Ars6tNPP33kkUdmz5599OjR\nrKwsEbl79+7u3bsnT57cokWLffv2VWBvMId58+YZeBvKrKwsQzalMYci28Trd/v27V27dhk1\nfk5Ozo0bN4w65eLFi/oL3N3djRrQtDp16iQi7dq1s+RFa4sMFPlI5A+RGyJbRKaJdCrhf97x\nIutEJok0EmkqMkbki3Kkoi4uLnPmzLl69eq0adPs7e0fLLCxsbGyshIRW1vbxx9//KOPPjp/\n/ryeVBQAAAAAKhtmjFYCmfs3bb+mzTpr+I57ve+DS+Xtmg1/d/LpyZ/GZYjkndu08eDgN3yZ\nNPqA5cuXv/HGG7m5uYUP5ubmhoaGhoaGPvPMM2vXrnV0dLRwV1OmTFm+fHlJz166dKlPnz7/\n+9//nnrqKUt2BfPRaDQbN240vP7HH3/87LPPLH93hejoaKPqo6KiBg8ebHh9bm5ufr5xf8R5\n8H6sRbRq1So8PNyoMU3Fy8tLuzw8MDDQw8Pj9u3bphq5V69eRXaU8hIJFAkUCRJpJaJ/F6FT\nIhEiESLhIgmFjiuVysJbfhXm5OTUpEmT06dP5+TkiEi9evUGDBgQHBwcHx9/9uzZ7OxsLy+v\nrl279u/f39XVVUQ++uij//u//9u0adO+ffuuX79ua2vbqFGj/v37P/nkk3Z2dikpKRUbWAMA\nAABAmRGMVry0mN2xBWmAW8/BgS7FV7kGPd17Xdyvt0Uk80DEwWxf/2Lm7zzM5s6dO2PGDD0F\nGzduTEhICAsLs7W1XKi8cuVKPamoVk5OzpgxY1q0aNGmTRvLdAWzOnfunFErvpOTk0+dOvXY\nY4+Zr6ViGTudMyEhofSiQpydnZ2dndPS0gw/pdRd6QcPHrxy5Uqj2jCVGTNmaLcGsrGxeeed\nd958802TDNurV6/ff/99/PjxO7791u/eMvmOpYWhumXyO0QuF1fg7e39/fffJyYmrlixIiIi\nQq1Wa483a9Zs9OjRU6dO1Saet2/fdnR0dHBwKLXPunXrvvrqq6+++uqDT5GKAgAAAKi6WEpf\n4XKP/vFnwawep8f9Hi1xYyVFCz9fN+3DnLjoQypL9FZl7Nq1S38qqhUZGfn2229boB+tpKSk\n9957z5DKjIyMN954w9z9wDKMDRzF+MzRJIpdHK2HIfFZEcXuwFMShUJRan3v3r07dOhg4IAm\nnB7ep0+fyZMn6z6cMmWKIZ+anZ3dM888o6dg8uDB255/3ua11745eDCx0DL5YlPREyIrRUaK\n1L23TP4rG5vuzz47fPhwbcopIgqFonPnzosWLTp9+rS/v/9TTz0VFhaWkpJy4sSJo0eP3rhx\n4+zZsx988IGu3sPDowwvKwAAAABUGwSjFe7imTMFS78VzVu11DNNSPFIi+YFr1fOyRPx5u+s\nqsjPzzd89tbKlSvPnj1r1n501q9ff/fuXQOLd+7cefr0abP2A8swdoeisp1Sfo0bNzZrvYiM\nHj3a8OKAgIBSN6FSKpWrVq0yJNJ1d3f/4YcfnJycSq0cNmyY/rLg4OANGzZop4tq2dra/vzz\nz127dtVzloODw1dffbVhw4bY2FjtknPt8boizyqVm+vWTff2Xrl5s93YsbJqlZw8+eAI+SIX\na9Q45u+fsXbt5s8/nzls2OLmzSPr1bNt2LBPnz4rVqy4fv36+vXrN27cmJycfPPmzcuXL2dl\nZcXFxf373/8uHHfWqFGjVatW7dq18/LyKvVfAwAAAAAeKgSjFS3z8qV7t6rzaOit99d92wYN\nPAse3rl6Jcu8fVUhf/zxx/Hjxw0szs3NXbdunVn70dm2bZtR9du3bzdTJ7Ckxo0bKxT6V0IX\n1aRJEzM1o0f//v3NWi8iI0eONHyrog8//NCQMl9f33Xr1unPRl1cXDZt2vTkk0/u2LFDu5V8\nSd5+++2NGzfGxcUV+9m5ubnNnz9/586dbm5uRZ7y8PDYu3fvjBkzip2XGhAQEBUVNWrUKG3D\nW1evTv7yyxsjRiQ3a3ZdoViflzcoIcHxypXie2rSJG/8+MyVKxVXrjTKyGgXFeX4r3/1GD58\n1apV0dHRx44dO3To0M6dO1966SUPDw/dSbVr1/b29tbFrwAAAAAAQ3CP0Yp2+5ZuC4/Cv+UW\nq1atWiLaVbo3b90U8TFrZ1WGsZtl79q1a9asWWZqprALFy4YVX/+/HkzdQJL8vDw8PX1jY2N\nNbC+Q4cO9erVM2tLxRo9evR//vOf5ORkQ4q7detm+Bp2HSsrqw0bNnTp0qXUq3zwwQcBAQEG\nDvv00097e3tPnjz56NGjDz4bEBDwxRdftGrVSkT8/f2PHTv2wQcffP3110V2dvLz85s7d26v\nXr1EpFWrVtu3bz9z5sxvv/0WHx+fkpJSt27dLl269O3bV896fDs7u9mzZ//73//+7bffYmNj\nr1+/7uzs3LRp0yeffLJTp05y7Zp8952Eh0tEhJw9ay9SYpSrUEibNtKzpwQGSo8eUru2UqQC\nphADAAAAwMOHYLSiFQoMXFxK2HjpHidn3XrP9LT00sdeunTpwYMH9dfUrFlT+yAtLc3AiKQk\nGo1GRHJzc8s5jrGMzRMvXbpkmQ6N2nZGRO7evWvhf7piFd5JPC8vrzK0VOWMGzfO8GD0xRdf\nNN8/svZdqVarH7yEUqmcPn36tGnTSh3Ezs5u1qxZZWvSy8tr8+bNo0ePvnbtWkk177333pQp\nU4wav0WLFrt37w4LC9u+ffupU6eSkpI8PDweffTRgQMHau/+qRvN3t5+3rx5//nPf/bt23fp\n0iXtlut+fn7aOwMUvqinp+e4ceMKX0WlUpXalVKpHDRo0KBBg0REef26dVSU9ZIledHRyni9\n9ztRKDStWqkDAtQBAepu3fJr1br/VHFX1L6OhUp4V1ZheXl5wnfXqq/IuzI1NdXYtQKoPLTv\nyvz8fN6VVZr2ddRJT0/nXVl16X4fSU1NrdhOUB5F3pWZmZlZWax7rap078q0tLSK/e6akZGh\nfVA4uCgngtGKlp1973uDlYNDKbul2zo4WIloREQM+pZy9erVk8Xduq6wpk2bah9oNBrdzsXl\nkZ+fb5JxDFfkl5NS5eXlWaZDT09Po/bh8fT0tPA/nSEqYUuV35AhQ9auXWtINtq5c+enn37a\n3P/IJb0rx40b9+eff65fv17/6QsXLmzXrl2Zm2zdunVERMSSJUu+/fbblJQU3XGlUtm9e/fp\n06d36tTJ2HexVnBwcHBwcJGDxfZpa2sbEhJSalkZKBMTbWJjbSIibGJjrUq7TbDGx0cVGKgK\nDFQFBOTd+6OUthujLsq7shqw/P8rYVZl+yaGyoZ3ZXXCu7J64F1ZnfCurB4q/HXUBe4Eo9VH\nvkp978vKyrrEHenvsbK6F4yqNfw/4h5jlyHXr1/fTJ0U0blzZ8NvfqqtN18zsCSlUvn1118/\n8cQT8XqnDfr4+Hz11VdWVqW+881o0aJFPj4+CxcuzM3NffDZWrVqLVmypG/fvuW8iqur68yZ\nM6dPn37w4MHLly9nZGTUq1fv8ccfr127djlHrhDKq1dtoqNtoqNtYmKsLl3SW6pUt26t6tZN\n5e+v6to1393dUj0CAAAAAEpHMFrhdCG3Qkqfj8x6kGJ079593rx5RtWbr5nChgwZsmbNGgOL\na9as2aNHD7P2A0vy8PDYsWPHlClTdu7cWWxBr169VqxYUbPwtMGKoFAoXn/99WHDhn3++eeh\noaHaG+NaW1u3adNm4MCB48aNc3Z2NtW1bGxsunXr1q1bN1MNaEnKGzds4uIMmhmqVGoeeUTl\n56cKDMwNCMiv6JcYAAAAAFASgtEKprC2vj8JtNQpyRrd9FJbm1KW3T9EOnXq1KxZs3PnzhlS\nbGNjM3z4cHO3pNWlS5eePXvu3bvXkOKpU6fq32gbVY67u/v69eujoqL+97//7du3LzExUUQ8\nPT179OgxcuTIwMDAim7wPm9v7zlz5syZMyc3Nzc9Pd3NzU2pVFZ0UxWPMBQAAAAAqjeC0YpW\no0YNkTQREU12tkZE36JaVVb2vWDUzt6u9LE/+OCDGTNm6K85derUyy+/LCKurq61Cm8AYryU\nlBS1Wm1nZ+fk5FR6tUktXLhw6NChhlSOHTvWkhPWvv32W19f34SEBP1l/fv3nzZtWsUuqdZJ\nSkrS3a1DqVS6s/i3fAYPHjx48GAR0a5Vt7W16N800tLScnNzbWxsSt3bDQWuX5fo/2/vzuOj\nKu/9gT+TPWEJIIsKghuguKCoIIR9UX/1atVWr7a2LrWrXUhFq88AACAASURBVPQW23vrVrtY\nrWtvrW3V21Vb26qttnWNkgABRNwVZFdBRHYIhGyT+f2RyRAwmbCEbPN+v/rHOTNPjt++hu8s\nn/Oc55REnn8+PPdcWL482cj09DB4cBg9OjZpUpg0Ka1Hj+wQduONeW9s2rSp/mo++/heTeuq\nvfNAenp6t27dWrsW9t6WLVuqqqoSu926dWsjH+LshfLy8m3btkUikVa/jIN9sW3btvLy8sRu\n165dMzMzW7Ee9kVFRcXWrVtDCN27d3e2vv3a5W5LnTt3zs7eT1+W2e+qqqpqb4aWn5+fkdGa\nQWIibmrGNwfBaGvLz8+PB6OhtHRLCMlCqHp3Od+t31O5ubm5ubnJxyRmKUYikea6uVjL36Ts\nnHPOmTp16u2335582LBhw+6+++6WLK9fv36FhYVnn3320qVLGxtz9tlnP/jgg6375pKEG3o2\nl9b9HuB1TGbVqlBSEgoLdz8MDZMnh0mTQo8eoTWWOPFqdgxex46kGb9E0Yq8iB2JrmzXEq+d\n17Fd2+W182q2a22nK/fHf72NZjEppHef3iGsDCGEsH79+uTB6Pr16+NbkZ4mDO3ipz/9adeu\nXW+44YbGBpx++ukPP/xwXl5eS1YVQhgyZMi8efNuvvnme++9d9u2bfWf6t+//w033HDZZZc5\nEQotLRGGPvtsePfdZCPrh6GTJwdzqAEAADoKwWhry+nfv3d4ZU0IIaxZubIqHNn4JR+VH3yw\nJr7Ze8AAy1HuLBKJXH/99WefffZNN9301FNPJS6liUQiJ5988tSpU88///zWOrPRrVu3n/70\npzfddFNhYeHixYs3bNjQp0+fU045Zfjw4SJRaDnLloWZM0NJyW6FoSecEAoK4nmoMBQAAKAj\nEoy2ukMHD8oKaypDCNFFi5eG8Uc1OnLJwkU1tVtZAwf2b5nq2puhQ4c+9thj27Zte/PNNz/6\n6KMePXocccQRBx98cGvXFUIIubm5Z511VmtXASkmEYY+80x4771kI4WhAAAAKUYw2uoyhg47\nPn3mvGgIYcPcF5dccdSRDc9qjC2cM3dj7Wba8cOGWks8iU6dOp166qmtXQXQSvYuDJ0yJbgZ\nDgAAQCoRjLa+ziPHnfTreXMrQggfPfvozPO+O6ZLA6O2FD9auLZ2M2fExFEtfdt3gDYtEYY+\n/XR4//1kI4WhAAAAhBAEo21Cp4LzTntw7j8/CiGUltx76+P9b/zkgJ0nhFYuf+yWX83ZGkII\nIdL3E+eNbOkbCAG0PQsWhOLiUFQUiovD6tXJRmZmhlNOCePHh3HjQkFB6NSppUoEAACg7RKM\ntgUZQy780viSHxZtCCFse+P/vnPNe5//wn9OOrZPTiTEyle/+fxf/+/3hctr7yUU6T3lyxcM\nTm/degFay7JlobAwzJwZiorCihXJRmZkhKFDw+TJoaAgjB0b8vNbqkQAAADaB8Fo29DllK9d\n+/k1N/5h/tYQwvZlhb++tvCBnPxunWLbNm0pjyaGdRpyyfe+dILpokDqiMXC/PnxaaHFxWHN\nmmSDs7LC8OHxmaGjRoU8b5cAAAA0SjDaVuQM/PT3b+72q7t/M23Z1lgIIUTLN68vrzcgb8DE\nK6Z+dfKArFYqEKAFJWaGTpsWVq5MNrL+zNBx40LXri1VIgAAAO2bYLQNyTl08lV3Df+PkheK\nZs99ffGqDRs3l9Vk5eX37j9wyEmjp0wZdWS+S+iBjioWC2+9FZ8ZOn16WLs22eDs7DBiRHxm\n6MiRITe3paoEAACg4xCMtjGRrkeOPufI0ee0dh0A+19NzU5h6Lp1yQbn5OwIQ089VRgKAADA\nPhKMAtCyai+TLywM06Y1EYYmLpOvvVJeGAoAAEDzEYwCsJ/V1IQ33gjFxWHatDBjRtiwIdng\n3Nxw6qlh/PgwfnwYMSJkZ7dUlQAAAKQWwSgA+0FNTXj99R1h6MaNyQbn5oaRI+Nh6PDhwlAA\nAABagGAUgGZSUxMWLAglJaGwMDz/fBMzQ/PywoknhtGjw+TJYfTokJPTUlUCAABACIJRAPZJ\nNBreeWdvwtAxY8wMBQAAoBUJRgHYQ8JQAAAA2j/BKAC7IRoNr70WZs6M56HJ1wzNywujRoWC\ngjB6tDAUAACAtkkwCkAj9igM7dQpjBwpDAUAAKC9EIwCUE/9MPS558KmTckG1w9Dx44NWVkt\nVSUAAADsK8EoQMoThgIAAJB6BKMAKWmPwtDOncOppwpDAQAA6EgEowApo7o6vP56KCwMM2eG\nGTPC5s3JBteGoZMnh4KCMGJEyMxsqSoBAACgJQhGATq06ur0t98Oc+YIQwEAAKA+wShAh1NZ\nGebODUVFeYWFXebOjWzfnmxw9+5hzJgwfnwYNy4MHRrS01uqSgAAAGhNglGADqH+ZfLTp4ct\nW0KSt/guXcKIEWaGAgAAkMoEowDtViIMLSwMJSUh+czQRBg6eXI48cSQltZSVQIAAEBbJBgF\naFfKy8OLL4aiolBUFObMCeXlScbGevSoGjmyZsyYnDPOCMcdJwwFAACABMEoQJu3fXuYMycU\nF4eiovDii8nD0NCzZxg7NowbF8aPL+3fv7K6OjMzMyc/v6VqBQAAgPZBMArQJm3fHl5+OZSU\nxJcNTR6G9uoVRowIo0fvepn8li0tUCkAAAC0R4JRgDajrCzMnh2fGTp3bqioSDa4d+/EzNBw\nzDEhEmmpKgEAAKAjEIwCtKqysvDKK7s7M7R37zB8eHxm6LBhwlAAAADYa4JRgBa3bVuYNSs+\nM/Sll0JlZbLBffrEp4WOGxeGDGmpEgEAAKCDE4wCtIj6M0NnzGj6Mvlx40JBQRg92sxQAAAA\n2B8EowD7zbZtYfbsMHNmKClpOgzt0yeMHSsMBQAAgJYhGAVoVvXD0OnTm75MXhgKAAAArUEw\nCrDP9igMPfDAMGaMMBQAAABal2AUYK8IQwEAAKA9E4wC7LatW8OcOaGwMMyc2fTd5GvD0MmT\nQ0FBOOaYlioRAAAA2C2CUYCk6oehc+eGqqpkgw86KIweLQwFAACAtk8wCvAxwlAAAADo6ASj\nACEEYSgAAACkFsEokMI2bAgzZoSiolBcHF5/PdTUJBt82GFh3LgwfnwYPz4MGNBSJQIAAAD7\nhWAUSDGlpeHFF0NhYSgsDK++2kQYmpgZOmVKOOywlioRAAAA2O8Eo0AKWL8+TJ8eiotDUVF4\n880mwtAjjtgxM/SQQ1qqRAAAAKBFCUaBDmrvZoaedlo49NAWqhAAAABoPYJRoANZty5Mnx6K\nikJRUXjrrRCLJRs8cOCOmaF9+7ZUiQAAAECbIBgF2rm1a+OXyU+bFt5+u4kwdNCgHWHowQe3\nVIkAAABAmyMYBdqhNWt2zAydP7+JMHTw4DBuXDwPFYYCAAAAIQTBKNBurFkTXnwxlJSEwsLw\nyitNhKGHHx4KCsLo0eGMM0L//i1VIgAAANBuCEaBNmz16lBcHP/f/PlNDD766B0zQw88sEXq\nAwAAANorwSjQxqxeHYqK4mHoggVNDB4yJB6GjhsnDAUAAAB2n2AUaAM++ihMnx5mzgwlJbt1\nmfzkyaGgIEyYEA45pKVKBAAAADoUwSjQSlat2jEzdOHCZCMjkTBkSPxW8mPHht69W6pEAAAA\noMMSjAItaPXqMGPGHs8MnTgx9OvXUiUCAAAAKUEwCuxnK1eGoqL45NAlS5KNjETCscfumBna\ns2dLlQgAAACkHMEosB98+GGYOTMUFoaZM5u+m3ztzNDJk8OECcJQAAAAoGUIRoFmsndh6MSJ\n4YADWqQ+AAAAgB0Eo8A+EIYCAAAA7ZNgFNhDq1aFkpLdCkPT0sJRR4XRo4WhAAAAQFsjGAV2\nQyIMLSwMy5YlG5meHgYPjoehkyaFHj1aqkQAAACAPSAYBRqWtnp11ksvhTlzwnPPheXLkw0V\nhgIAAADtjWAUqGfVqqynn84sLs6cNi19xYpkI+uHoZMnh+7dW6pEAAAAgGYgGIWUt2xZmDkz\nlJSEZ58N777bJcnI9PRwwgmhoCCehwpDAQAAgHZLMAopKRGGPvNMeO+9ZCOFoQAAAEBHJBiF\nlLFwYSguDsXFoagorFqVbGRGRvUJJ1SNGlU9enSXM84IXZLNIgUAAABojwSj0KElZoY+/XR4\n//1kI+tmhpYOHVo5blwsPz+EkJaWJhUFAAAAOiTBKHQ4CxbEp4UWF4fVq5ONzMwMp5wSxo8P\n48aFgoLQqVMIoXL9+lgs1kKlAgAAALQSwSh0CMuWhcLCMHNmKCoKye8mn5ERhg4NkyeHgoIw\ndmzIz2+pEgEAAADaEMEotE+xWJg/Pz4ttLg4rFmTbHBWVhg+PD4zdNSokJfXUlUCAAAAtFGC\nUWg/YrHw9tvxMHT69CbC0OzsHWHoyJHCUAAAAID6BKPQtsVi4a23doSha9cmG5ydHUaM2BGG\n5ua2VJUAAAAA7YxgNNVFo9HajU2bNq1bt27fD1hRUVFRUbHvx0lx6e+9l1lcnFlcnDlzZtqG\nDcmGZmRUH3NM1bhxlWPHVo8YEcvJiT++bVvYtm0fy6ipqWmWfxW0rqqqKq9jR+LV7ACi0ajX\nsSPZuHFja5fAvorFYrqyI9m8eXNrl0Az2JD8dxDtSmlpaWlpaWtXwb7atGlT6xaQ+FdUU1PT\nXMcUjELbUFOTsWBBZklJ5qxZmbNnR5J+CYhlZ1effHJVQUFVQUH1SSfFsrNbrEwAAACAjkEw\nmuoikUjtRm5ubqdOnfblUNu3b6+pqcnIyMiW0+22yPLl6dOmpb3wQlpRUfIwNGRm1hx7bM3E\nidEJE2pGjQo5OZEQskLIau6SysrKYrFYvLxIJM/ipO1ZeXl5NBpNT0/PSUwlph2qfXdN7O7j\nezWtq7KysqqqKi0tLddqJ+1Z7btrYjc3NzctLa0V62FfVFVVVVZW+s7T3tW+uyZ2c3Jy0tPT\nW7Ee9kV1dXXtNYh5eXmJn6u0O7Xvrond7OzsjAwBVHsVjUbLy8tDG/jOk4ibmvHNwb/LVJf4\nN52dnb2PP9IqKipqamrS09P92EumpiYsWBBKSkJhYXjhhbB+fbLBublh2LAwenSYPDmMHp2W\nk5O2/5u2rKwssR2JRLya7VpVVVU0GhXBtHe130ISvJrtWk1NTVVVlXfX9q6ysrJ+MCqCae9q\nf7rrynYtGo3WD0azs7MzMzNbsR72RWJxtpycHKed2q9YLFY/GM3KyjKDqv2qqqqq/UnS6gF3\nVlZ8bphgFNqVPQpD8/LCiScmwtBgoh8AAADAfiAYhf0jGg3vvBMPQ59/PiS/TL5+GDpmTHAm\nDQAAAGA/E4xC8xGGAgAAALQTglHYN/XD0MLCsHFjssF5eWHUqFBQEEaPFoYCAAAAtCLBKOy5\naDS89lqYOTOehyYPQzt1CiNHCkMBAAAA2hTBKOye+mHoc8+FTZuSDa4fho4dG+rumwYAAABA\nGyEYhcYJQwEAAAA6KMEo7EwYCgAAAJACBKMQQnV1eP31UFgYZs4MM2aEzZuTDe7cOZx6apg8\nORQUhOHDhaEAAAAA7ZFglFRVWRleeikUFYXi4jBrVti2Ldngbt3CmDFh3Lgwfnw44YSQnt5S\nVQIAAACwXwhGSSX1Z4ZOnx62bEk2uP7M0BEjQmZmS1UJAAAAwH4nGKWjq6gIc+eGadNCcXGY\nPTts355scPfuYcyYMGFCGDcuDB0a0tJaqkoAAAAAWpRglI7rN78JDz4Y5sxpIgzt0WNHGHr8\n8cJQAAAAgFQgGKXjmj8/TJvW8FNduoQRI8LkyWHy5HDiicJQAAAAgFQjGKXjGjcu3HHHjl1h\nKAAAAAB1BKN0XGPHhgMPDAUF8bvJH3tsiERauyYAAAAA2gTBKB1Xfn748MPWLgIAAACAtsjV\nxAAAAABAyhGMAgAAAAApRzAKAAAAAKQcwSgAAAAAkHIEowAAAABAyhGMAgAAAAApRzAKAAAA\nAKQcwSgAAAAAkHIEowAAAABAyhGMAgAAAAApRzAKAAAAAKQcwSgAAAAAkHIEowAAAABAyhGM\nAgAAAAApRzAKAAAAAKQcwSgAAAAAkHIEowAAAABAyhGMAgAAAAApRzAKAAAAAKQcwSgAAAAA\nkHIEowAAAABAyhGMAgAAAAApRzAKAAAAAKQcwSgAAAAAkHIEowAAAABAyslo7QJoK/76178e\ncMAB+3KEioqKmpqa9PT0rKys5qqKlrd9+/bEdiQSycnJacVi2Ee1XZmWlpadnd3atbD3ysvL\nY7FYYjc3N7cVi2EfVVVVVVdXe3dt72rfXRO7OTk5kUikFethX1RXV1dVVQXvru1cZWVlNBpN\n7GZnZ6elmQPUXkWj0crKyuDdtZ2r/c6T2M3KykpPT2/FetgXNTU1FRUVoQ28u7777rvNfkzB\nKHH/+te/WrsEAAAAAGghgtFUl52d3bdv32Y5VO3UiUgk4rReu1ZZWVn/FczMzGzFYthHiQlN\nJk20a7VTmRJ0ZbsWi8Vq5//qynaturq6/jxuXdmu6cqOIRqN1p/HnZGR4SdJ+6UrO4ZdujIt\nLc2M0farDXZlM1YSqf+tDmDs2LFlZWW12z179nz66adbtx7g/PPPX758eWJ37ty5becbCaSm\nr3/963PmzEnsPvHEEwcffHAr1gP88Ic/fPzxxxO7999//4knntiK9QD33Xfffffdl9j98Y9/\nfPrpp7diPdAYv6wAAAAAgJQjGAUAAAAAUo5gFAAAAABIOYJRAAAAACDlCEYBAAAAgJQjGAUA\nAAAAUo5gFAAAAABIOYJRAAAAACDlCEYBAAAAgJQjGAUAAAAAUo5gFAAAAABIOZFYLNbaNQBt\nyLRp06LRaO12VlbW2LFjW7ceYPbs2du2bUvsTpo0KRKJtGI9wCuvvLJhw4bEbkFBQW5ubivW\nA8yfP3/VqlWJ3ZNPPrlbt26tWA+wbNmyZcuWJXaPPfbYAw88sBXrgcYIRgEAAACAlONSegAA\nAAAg5QhGAQAAAICUIxgFAAAAAFKOYBQAAAAASDmCUQAAAAAg5QhGAQAAAICUIxgFAAAAAFKO\nYBQAAAAASDkZrV0A0BLKV79eXFj80hsLl61av2VbVUbn7j0O6D3gmFMKxow+5ahe2btziOiW\npXOee27GK28veX/tpq1V6Z279zjgwCNOKBg3YfRJA7o4yQLNouaDx/77qt+9UxFCGHTZA7ef\n27uJ8RoTmkv5tB/8513zYrszNHPi9Y9edUojT+pKaG5V696ZNaNk7rw3l61ev3HT1qr0vM49\n+hw28JhhYyZPPHlA5ybbSlfCPlr3xNTLH1i053939BW/ufXsng08oStpSyKx2G59AQTaq8oP\nS/74s189MX9zw72efsDQT37xKxeO6puT7BgrXvjV7fcVLi9r6MlI16P+46tXXVJwcFZzlAup\nrGrJQ9dc85dl0RDCbgSjGhOa04IHLvnuExt3a2ijwaiuhGYWXfPSX+6777G5H1U2+HSk8xFT\nvnj1Fyf0b/Qsv66EZtCswaiupK0RxUOHVrHs7z+45tbHd6Sikcy87r16HdAlu675o+tff+yW\nq6/725KKxo5RuewfN3737nofXWnZXbrn52VE4ruxLe/889ZrfvTUB9H99H8CUkT5W7+77a/L\ndrORNCY0r41Ll+5eKtooXQnNrPL9f//4mh89XC8VTc/J79kzPze9bj+2demzd/339/+xvKrh\nA+hKaE1p2dmZuzykK2mDXEoPHVjZqw/85HdvbKndyTlk7EWXnj/5xAFdMkIINdtXzy/+++/+\n8PSirbEQyhf98aa7+97z3VH5Hz/G6/ff/Nu3t4YQQoh0HXLWZZeeM/qontkh1Gxb+epzf/3N\nQ0UrKkIIpa/9+qbf9L/ni8c4twd7p3TevXf+88PdvIpDY0Iziy1dujy+2WfcVy499eOfh/Wk\n9TnyY4/pSmhmG4vuuPbX8zbX7nQZeNqFnzln0gn98tJDiFVuWPLik3/6/aMvr4mGELa+/bvb\nHjrmfy8duMtPW10JzaXrSZ+7pvuW3RhYtuDx+/+1qPZcRtdhX/7K5J0/TnUlbZJL6aHDir33\npyu/8fDKEEII2YMuuuVHFx2x6+Xy1SueuHHqA29uDyGEcOB5t//60kGRnQZEF/3u69c89kEs\nhBC6nnzlrdee3jd9pwEVS/52w7V/XLA9hBDSjvzcz+84/5CdjwDsjo1FN3/zzjmb6z/U+KX0\nGhOa3aq/fPMrD70bQgi5E69/+KpT9rBldCU0s81FP/7ynS+WhRBCWq+RX73p26f32zUi2Tz7\njqt+Urw+hBBC1vCrf3vdhC71ntWV0NJia4t+/F93zt0cQgjp/c760R1fPCa3/vO6kjbKpfTQ\nUcXeePKp2lQ0RAZ8+lsXfiwVDSFkHHLWl87qF99ZXTJr2S7Pl81+9Mnaj66QN/zyq3b96Aoh\nZB95/ve+MrxTCCGEmiWP/vWlhleAApKIrX7yzl/O2RxCiPTo0a3J4RoTml3V0qUr4ptHDhy4\nxz/DdCU0r5pFjzxYm4qG9EPPv/47H09FQwj5I7/8+ZPjj1e+XDJvp2WhdCW0sOj7j9x6T20q\nGrIGfe67l++ciupK2i7BKHRUKxcv3h7/aXfUlNMaO9kWGTB4UF1iumb16p1nkJfOev7F8trN\nbhM+Oa5rw4fIH//pKfEltcvmFL9Uvm9lQ8qJvvfobb95fXsIIf2QT33z0wOaGq8xofm9t6xu\nfd9eAwc1fXpiF7oSmlfVy08+t6Z288Czvnb+oR+LT+I6F5z7mUmnfeKs8y646LMj+tQPRnUl\ntKyqRQ/d9qf4NfQ5x1029dwBu/atrqTNEoxCR3XIp+/8298eeuB/b/3+dVeM6d7osOj27XVn\n4rrk5+8Un1a+Nu/NmtrNziePOLax76QhMnjE8PivyIq5JS83vPo90KDKRX+87aHFlSGEzIEX\nTf3s4CbXUtKY0PxKly6NhzAZgwYdtqd/rSuheUVfnzW3drpoZMhZ5xyV5JMx67jzvvX1r3zx\n0osv+vSUIfVyFl0JLap6yV9+9th7tWcYc479/Dc/ceDHZuXoStouwSh0YJGsLr0PPXrY8IGN\n56Jlc2a9Hv+Eyho06NCdnnt3UfykX4gMOvqoJBcWRgYOHhR/M6lYMH/X6/GBRpW99sDtf38/\nGkLIOeaSqecf1uiXxB00JjS/ZUvrWuSwgfXu3xKLVlZUN70av66E5rXsjTdqb84SjjjllB57\ncwRdCS2o5v1H7nl0Re1vyoxBn/n6mX0aaDpdSdvlrvSQumJbFz12669mxc/I9znzgvGd6z9d\n9v576+KbPfsf0sAKpTtk9evXO8xdHUII61eu2B4G5yYbDdTaPPuXdz29OhZC6DTsy98+66Dd\nWddQY0LzW7t0afxeu90GDexZ9sG8F555Yfarby9euak8GkvL6tyj76ChJ5064f9NPr5XA1+d\ndSU0r82LF6+t3eo08MgDQwghVK5758WiacUvvv3eR2s3bAt53XoePHDoKaMnn15weJcGPjx1\nJbSgdc/c/0h8PZrIIed8+ayDG/pGqytpwwSjkFJisZqaqvIta95f/Obc4qefKVleWntqL/+k\nL19/8VE7T1Zbt7buwyv07Nkz+XEPOOCAEFaHEEJYs3ZNCE2ukggpL7buhZ/dU7wxhBDyC668\nalLP3bvdi8aEZhdduvS9+Gbn1c9d86XiRVvqTROtqdy6bvkrzy9/5fnHHxn26W9efeHxO687\noyuhmX3wwQfxrT59+oRY6aJ/3XvX70s+qHcXls1rV2xeu2LBrH8/dsRpV0z90sS+mTsfQVdC\niymb+/s/vR5vz+4Tv3DBwIavf9KVtGGCUUglpc9e99lfvLnzY7mHjPr0Fy4/d1jvXd8ONm3a\nVLfZtWsjq2PX6dwlMdl0a+nWfa4TOrzYqifu+NW80hBC6Dn5W18fvds3e9GY0OxWLF1al7is\nfLmo8XFVa175841XL//Gj/974kH1VqPSldCsqtetq+up/K5pr9w79YfPfBhteGhs69Jn7v7O\n+2tvvOk/B9WfgaYroYXE3nv8wem1d6IPmcdd8Jlhjc0F1ZW0YYJRSCVrPlqz60MZubmhdPWH\nGyt799plafvy8u3xrfTc3CZuCJOVm5seQjSEELZv3558LFC97OHbf/92eQghctCZ3/7SyZ12\n/081JjS37UuXflhvN7P38VPO/H/jTxnct1e37OjWdSsWvTrzqX889fJHlSGEEF035+c//L8+\nt3/xmLy6P9CV0KxKt2yp29zw3B0/XfBhNIRI1yMnnHP2hJOOOqRHdrR0zfI3Sp567MmX11SG\nEELpgod+8vN+d11TsOMco66EllE2689PvBu/yKL3GZ87vVejI3UlbZhgFFJIzZpN1f0Gn3Bw\nz87pFZtXL1/47vrKWPWGRbP+sWjWk/8af+W135zQt94tJ6qq687Op2c0eUeY9PS6T6/qaPX+\nqR46ivIFf7jtL0uqQwjpA86fetkxSZdZ2oXGhGa3bNmyuivnI30KvnrdN88YsGM5s24HDx5+\n8ODhk6c8d+dN98xeGwshRFf+8xePTLjn80fWzhrVldC8tpeX122+t2BBCCF30Hnfu/6SoYlF\nLPK79+o3ePjECf++5cZfv7IphBDWz/jVHyed/I1h2bUDdCW0jFVPPTp7W+1m+nHnnXtU4/GS\nrqQtE4xCCkkb+c3fjtyxW75q3t/vv/cvL6+rCaFyZdHd10Vz7r5mZH7i+cQKa5HQ9OKHu7c8\nIrDtlftuf/yDmhBC1qDPTr1oYBPnzD9GY0LzivUZc9mVfT766KM1a6OD/vOLp/Vr6Adbdv8p\nU6/fcM3VD9XeXmLlP/82+4L/KYif1dCV0Jyi1TsFIT3GXXXDpUM/fuVtzmFnfveald+89t8f\nhRDC5hceLbx42Jnd40/qStj/at7517+XxJut67jzJiVfOVRX0nalNT0E6KByDj75ohvuuGZc\nr9pPntj6Gff+bl5F3bORjMTJvOpoIys77RBNnAPMJm16igAAD9hJREFUytzTnAdSyKYZ99xd\nuDYWQsg97tKpnxrQ5CnzXWhMaG6RnkeNO/3sCz7/xa9/+ysNp6K1Mg8993MT6k4eVrz60hvx\n7EZXQvPKzKrXG+lDzr9kZGPrEeYed+GnT4zfdyn69rxXy+KP60poARVzn3y+7oZKfU8/q27G\ndsN0JW2ZYBRSW6R7wZVXTqw7vb65+MlZ2+qeysurWz8tWl7exMdX1fbEiOycpB+KkMJia565\n+xclm0IIofPJX776Pw7ci9PhGhNaTdYJp55Ut/RF+eIldffN1pXQrPJy83bsDC4YlWwWWv6I\n4YPjmzULFy5JHEJXwv62ffYLs+Prf0aOmDLliCa+1epK2jDBKKS8nGFnjOsd365++62FdZc5\n5OcnrqovLd3y8b+rr7S0tG6zW7fdvr02pJToisdve+CVshBCyB/z9W9NTH69UWM0JrSe9H79\nDqzb3nF/XV0JzSo3d8cqv50P6dc9ydAQuh1ySN3tq7du3lyXpehK2N+2zi6qu9Qw/dgpkw5M\nPlpX0qZZYxQIhx9+eAi196vfvm7tthA6hxBC7z69Q1gZQghh/fr1IST7Xrp+/fr4VqTnAQfs\nz1qh3fpw1rSF8S+Qm2fc8rkZTY1f9Nsrzv5t7Wba+O/9479ODSFoTGhVuTmJm6XFYjXxLV0J\nzSqzd69uIdSeecjIaOrnal5eXghbQwghlJdXhJAXgq6E/W77vDmJFWWOHVOQn3x00JW0aWaM\nQgcVqyxdu2LJW/NKnn/ujbVNjM3IzGzg2oec/v3rJpKuWbmyKtkBKj/4YE18s/eAAXtyi21g\nz2hM2C+iFVs3bimPNTFqy45JLPld634G6kpoXocedljdF9PNGzY2cc1tWVndyqJpnTrVTTXV\nlbB/Vb360mt1uegxo05tOhfVlbRlglHooBY++I0vXPlf3/vBrT/7+YMlTSSja9d8VPdbMLN7\nj7oLksKhgwfFF7uOLlq8NNkBlixcFJ84kzVwYP+9rhlomsaEZvXOQ9+85LMXnHve+Z+55Nq/\nr0g+tmzpkg/jm5mHHd6v7mFdCc0q7/DD+8Q3Y4sXLkl6wmLjihVb45sH9eubONGvK2F/ir3z\n2uvl8e2BJ5+yW1e760raLpfSQwd16OGHp4cN0RBCWFhSsvacc3o1OnTji3PrFquPHHXUoMTj\nGUOHHZ8+c140hLBh7otLrjjqyIbX1I4tnDN3Y+1m2vHDhmY2S/3Q4fQ5/Tt3n1LRxKDtc+79\nn4cXhRBCGPDJG66e0COEEEKky46VmzQmNKs++TkbS2t/3r3/yivrLurf+PK/W2bNfCP+Wy39\n6KHHJm6UqyuheR126qm9H/3HmhBCWDdr+oLLBw9Jb2Rk6byXFsU3848/bkeCoithf1rx1lt1\ny4T2PHrI7i2brytpu8wYhQ4q55SCE+O/2WILn3jszcrGBpbO+8Ojb8d/6GUeN3pEvSshOo8c\nd1L8PoAfPfvozNKP/3EIIWwpfrQwPiU1Z8TEUZ0bHgUpL7Nb38ObdGjPxC0nsnv0r3v0sF71\n7tCrMaE5dR8+ou63WWzhv/6xoNGPy7LXH3q47kYTnQvOHOfjEvaXyOBJE/vGt9c/89vHVzUy\nabRy0aOPvRrv2Z5jxw6pF7PoSth/She8szK+mXn00Ufs5l/pStoswSh0VJ1Gnzul7vTduqd+\nds/sDQ18qSxb9MjNdz6/oXYnctBZn5+y0zrYnQrOOy1+LVNpyb23Pv7ex5aDqVz+2C2/mlN7\nDVOk7yfOG5m36wigmWlMaE69J589oq5F1vzrrl/O3djAx2X5sn/ecvtT8TXPsgb/50Wn7rTo\nma6E5jXgzAtHdq3drFz4p1vvn/fxvqxZN/ue2/7+Qe3jmUefd/YxO/2y1ZWw3yxftqxu88gh\nR+/2nE5dSVuV/v3vf7+1awD2i4w+Rx+8dvqMZWUhhNi2d0uK3izrclC/g3p2yoyEECv76J2Z\nf//lbfc+tXx77fCsIy+8/qrxvXZeXyOt16CDPiya/u72EELVR68WzVub1/fQ/r07Z0RCrHz1\nm8/85tbbH1tUe4BI79OmTv3Ewa52gH1RtXTao3M/CiGEcMCJZ592dKeGBmlMaE45hw7uNL9w\n3kdVIYTY1uUzi98q63pg34N7dcqIhBAq1i+Z/cR9t/388cXbaod3GvqlG78yrOvOVwDqSmhe\nOYce3/vdF0pWVoQQopsWzZg5f2tOr779enXOiIRQuWHR9L/c+dP/m7uuNhbNGnTxtV8d3m3n\nKT+6EvaTTXMfffiV2lmdnU869+LhfZoYn6AraaMisVhT998E2q/qlU/++Hu/fnnTjj5Py+qS\n3zm9cuuWbZU1O8blHnHWNTd+8eQGF84uX/zI92/8w/ytiQfSc/K7dYpt27SlfMd9QjsNufTH\nPzjv8KyGDgDstm3PXn/RPa+HEEIYdNkDt5/bu7GBGhOaU9mCP1x34yNLync8kp6T371LRmXp\nTj0VOh936Q9uOO/I7IaOoSuheVW8++9bbrzv5XqTRSMZed26ZVds3lRWlXgw/aCJU2/+VsEB\nDS1XqCthP3jnvku+86/aZUAPv/i+uy84sInxO9GVtEFmjEKHltZ14NjxR0dWvLXow7Laj5pY\ntLJ8e3lVNPF1MrPnsf9x5fVTzz2qwZlpIYSMA4aMPqnX+oVvv7uxdhWnWHXF9u0V1Ykj5A2Y\n+NUbrjnzsAZ/JwJ7YrdmjIagMaF5ZfYaOqGg77Ylby1dV1HbRbHqirKy+j2V2XvY+Vdd+7Up\n/RtrKl0JzSuj26AxowenrVm8eGVpPDGpqSovK69KnNvP6jPis9+79rKTujd8ExddCftBzTvP\n/r6kdo3RyMBJl409bI/WZ9SVtEFmjEJKiG5aNOO5ormvvb145drNpdtrMjt1ye/Zb+AxQ08a\nNWHsMQdkNH2EENuypOSFotlzX1+8asPGzWU1WXn5vfsPHHLS6ClTRh2Z39jNQoE9stszRuM0\nJjSryrVvFhfOfPnNBUtWrtuydXs0q3O37gcceOgxJ48sGHPqkJ67M3lFV0Izi25YNGv6zBdf\nemPJh+s3bt5amZbbrXe/I4YMGzXptLFH9diNb7G6EprR1meu+8wv3gghhND9zJt//+Vj9+Yg\nupK2RDAKAAAAAKQcd6UHAAAAAFKOYBQAAAAASDmCUQAAAAAg5QhGAQAAAICUIxgFAAAAAFKO\nYBQAAAAASDmCUQAAAAAg5QhGAQAAAICUIxgFAAAAAFKOYBQAAAAASDmCUQAAAAAg5QhGAQAA\nAICUIxgFAAAAAFKOYBQAAAAASDmCUQAAAAAg5QhGAQAAAICUIxgFAAAAAFKOYBQAAAAASDmC\nUQAAAAAg5QhGAQAAAICUIxgFAAAAAFKOYBQAAAAASDmCUQAAAAAg5QhGAQAAAICUIxgFAAAA\nAFKOYBQAAAAASDmCUQAAAAAg5QhGAQAAAICUIxgFAAAAAFKOYBQAAAAASDmCUQAA2FPbir4x\nMD2yQ/qgq2dvT/4n6x676OD6f3HklYWlLVMsAAANEYwCAMCe6jT+pw/+15CMxH7N4v+9/MbZ\nFY3/wQd/vOKLD3+Y2M08/rsP3zG5y/4sEQCA5ASjAACw53JH/PjB64ZmJfZr3rnzCze91HA0\nGlv+60u+/viGxH7eyFse/sHJOfu9RgAAkhCMAgDA3sg68bqHfnDqjngzuuC2y3/wauXHxkUX\n3n7xfz2/JbHf7RM///PVR2d8bBwAAC1KMAoAAHsn/ZhrHvzJ2M6J/eq3fnr5za9W7zSm6tUf\nfea6WWWJ/YMufOB3lw+ItFiNAAA0QjAKAAB7K+2Ib/3hrin5if3q126+/JY3dkSj2+dc99kf\nvZKYRZp2+Fce/PWnerVsjQAANEgwCgAAey8y4Irf3XNOj8R+1Ws/vOK2d2pCCCFsLfr2Z29f\nkIhJM4/93sN3Teza8jUCANCASCwWa+0aAACgXVv3yIXHnf+X1XW7OaPvenP6Vb2e+sJxZ/5m\nRd2DeQW3vVQ8dUh661QIAMCuBKMAALDPNj51yfGf+MPKut0up995x0G3f+l3q+oe6H7G/a89\neUV/a4sCALQZglEAAGgGW164cujke99t8Mv1gRc89sZfzrW2KABAW2KNUQAAaAZdJ97+x6uP\nauBK+bTDvvbgfVJRAIC2RjAKAADNInf0zQ9997jMnR/MPP6/H75jUn7DfwEAQOsRjAIAQDPJ\nHva968/N2+mhQ88454ScVioHAIAkBKMAANBMyud+//uPle300OI7L732xe2tVA8AAI0TjAIA\nQLPYVvSdi++cX73Lo9Xz77z4u0XbWqUiAAAaJxgFAIBmsPnZqy+5Z3FN3W6nTp3qNmuW3HPJ\n1c9sap2yAABohGAUAAD22fonvnrp/e/H6nZ7X/DHl357Xs+63dj791925T/Xt05pAAA0SDAK\nAAD7aM3DX7rizx8mdntdeO895x59/i9+dm73xGMf/ukLX/7zR61RHAAADRKMAgDAPlnx2y98\n9bG1id3e59/z80/1CiEc+Jl77zprRzS69tGvfeF3K1qhPgAAGhKJxWJNjwIAABoSW/7LSUO/\nNq20br/Xp/729iOf7lW3u+r3nxhy6VOb63a7TPjl689/5bBIS1cJAMDHmDEKAAB7K7rojoun\n7khFQ8/z77l3RyoaQjj4kl/f+Ymuid3Sad/+3B2Loi1YIQAAjRCMAgDA3ql+4ycXXzerLLHf\n61M//8UFvXcZdMjlv77ttB3RaFnJdRff8kZ1C1UIAECjBKMAALA3KuZ9/7M/eKkisd/z3Hvu\nvbBXAwP7fen+2yZ12fF3L9302ZvmVTQwEACAFiQYBQCAPVc2678vvuWtqsR+j0/9/Jcfmy1a\np/+X7r91UqfEbtVbP7n4f2aXNTIYAIAWIRgFAIA9VVr47c/9bOGOtUIPOPfn917YJ8kfHPaV\nB34yfkc0Gl1498VTn9+6HysEAKAJ7koPAAB7ZuOTlx935m8/SOz3+OSf5/8jaS4aQgixpfeM\nO/4bM3ZMFO172b/f/M0nuu+nIgEASE4wCgAAAACkHJfSAwAAAAApRzAKAAAAAKQcwSgAAAAA\nkHIEowAAAABAyhGMAgAAAAApRzAKAAAAAKQcwSgAAAAAkHIEowAAAABAyhGMAgAAAAApRzAK\nAAAAAKQcwSgAAAAAkHIEowAAAABAyhGMAgAAAAApRzAKAAAAAKQcwSgAAAAAkHIEowAAAABA\nyhGMAgAAAAApRzAKAAAAAKQcwSgAAAAAkHIEowAAAABAyhGMAgAAAAApRzAKAAAAAKQcwSgA\nAAAAkHIEowAAAABAyhGMAgAAAAApRzAKAAAAAKQcwSgAAAAAkHIEowAAAABAyhGMAgAAAAAp\nRzAKAAAAAKQcwSgAAAAAkHIEowAAAABAyhGMAgAAAAApRzAKAAAAAKSc/w92c5DW32yjlAAA\nAABJRU5ErkJggg==",
      "text/plain": [
       "plot without title"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 420,
       "width": 900
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "set.seed(1234)\n",
    "x <- rnorm(50, mean = 50, sd = 10)\n",
    "y <- (x^6/1000000) + sample(c(100:500), 50, replace = TRUE)\n",
    "y<-y/500\n",
    "\n",
    "library(tidyverse)\n",
    "\n",
    "options(repr.plot.width=15, repr.plot.height=7)\n",
    "\n",
    "ggplot(data.frame(x=x,y=y), \n",
    "       aes(x = x,\n",
    "           y = y)) +\n",
    "geom_point(size=4) + geom_smooth(method=\"lm\", color=\"red\", se=FALSE) + \n",
    "  labs(x = \"x\", y = \"y\") + theme_bw(30)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0229470f",
   "metadata": {},
   "source": [
    "This is clearly a nonlinear relationship. We can see that using the Pearson's correlation and the Spearman's correlation give different results. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "23f6bc1c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tPearson's product-moment correlation\n",
       "\n",
       "data:  x and y\n",
       "t = 10.23, df = 48, p-value = 1.198e-13\n",
       "alternative hypothesis: true correlation is not equal to 0\n",
       "95 percent confidence interval:\n",
       " 0.7142349 0.8991103\n",
       "sample estimates:\n",
       "      cor \n",
       "0.8279763 \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "\n",
       "\tSpearman's rank correlation rho\n",
       "\n",
       "data:  x and y\n",
       "S = 18, p-value < 2.2e-16\n",
       "alternative hypothesis: true rho is not equal to 0\n",
       "sample estimates:\n",
       "      rho \n",
       "0.9991357 \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cor.test(x,y, method = \"pearson\")\n",
    "cor.test(x,y, method = \"spearman\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fdb174df",
   "metadata": {},
   "source": [
    "As we can see, the Pearson's correlation underestimated the association between both variables. This is because Pearson's correlation measures the **linear** relationship between variables, but here we have a non-linear relationship."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af935bea",
   "metadata": {},
   "source": [
    "Finally, let's show that Spearman's correlation it is just the Pearson's correlation on the ranks instead of on the actual data:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "1bbe344e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tPearson's product-moment correlation\n",
       "\n",
       "data:  rank(x) and rank(y)\n",
       "t = 166.53, df = 48, p-value < 2.2e-16\n",
       "alternative hypothesis: true correlation is not equal to 0\n",
       "95 percent confidence interval:\n",
       " 0.9984694 0.9995120\n",
       "sample estimates:\n",
       "      cor \n",
       "0.9991357 \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Pearson's correlation test on the ranks, instead of on the actual data\n",
    "cor.test(rank(x), rank(y),  method = \"pearson\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e7a61764",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-info\"> <b>Practice</b>: Does the number of cylinders correlate with the number of forward gears in cars? Test this using the variable `mtcars`, which is a native R dataset that contains a data frame comprising fuel consumption and 10 aspects of automobile design and performance for 32 automobiles. The number of cylinders in this data frame is located in the column \"cyl\", whereas the number of forward gears corresponds to \"gear\". Since both variables could be considered ordinal (at least \"gear\", i.e. we can't have two and half forward gears), then Spearman's correlation seems more appropriate than Pearson's correlation for testing the association between.\n",
    "    \n",
    "Is this association significant at a significance level of $\\alpha=0.05$?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "f21e38f5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Your response here"
   ]
  }
 ],
 "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": "4.2.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}