{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "several-belly",
   "metadata": {},
   "source": [
    "# Stochastic Variational Inference\n",
    "\n",
    "Implementation of Stochastic Variational Inference (SVI) using [PyTorch](https://pytorch.org/), for the purpose of uncertainty quantification.\n",
    "\n",
    "We'll consider the [OLS Regression Challenge](https://data.world/nrippner/ols-regression-challenge), which aims at predicting cancer mortality rates for US counties.\n",
    "\n",
    "## Data Dictionary\n",
    "\n",
    "* **TARGET_deathRate**: Dependent variable. Mean per capita (100,000) cancer mortalities (a)\n",
    "* **avgAnnCount**: Mean number of reported cases of cancer diagnosed annually (a)\n",
    "* **avgDeathsPerYear**: Mean number of reported mortalities due to cancer (a)\n",
    "* **incidenceRate**: Mean per capita (100,000) cancer diagoses (a)\n",
    "* **medianIncome**: Median income per county (b)\n",
    "* **popEst2015**: Population of county (b)\n",
    "* **povertyPercent**: Percent of populace in poverty (b)\n",
    "* **studyPerCap**: Per capita number of cancer-related clinical trials per county (a)\n",
    "* **binnedInc**: Median income per capita binned by decile (b)\n",
    "* **MedianAge**: Median age of county residents (b)\n",
    "* **MedianAgeMale**: Median age of male county residents (b)\n",
    "* **MedianAgeFemale**: Median age of female county residents (b)\n",
    "* **Geography**: County name (b)\n",
    "* **AvgHouseholdSize**: Mean household size of county (b)\n",
    "* **PercentMarried**: Percent of county residents who are married (b)\n",
    "* **PctNoHS18_24**: Percent of county residents ages 18-24 highest education attained: less than high school (b)\n",
    "* **PctHS18_24**: Percent of county residents ages 18-24 highest education attained: high school diploma (b)\n",
    "* **PctSomeCol18_24**: Percent of county residents ages 18-24 highest education attained: some college (b)\n",
    "* **PctBachDeg18_24**: Percent of county residents ages 18-24 highest education attained: bachelor's degree (b)\n",
    "* **PctHS25_Over**: Percent of county residents ages 25 and over highest education attained: high school diploma (b)\n",
    "* **PctBachDeg25_Over**: Percent of county residents ages 25 and over highest education attained: bachelor's degree (b)\n",
    "* **PctEmployed16_Over**: Percent of county residents ages 16 and over employed (b)\n",
    "* **PctUnemployed16_Over**: Percent of county residents ages 16 and over unemployed (b)\n",
    "* **PctPrivateCoverage**: Percent of county residents with private health coverage (b)\n",
    "* **PctPrivateCoverageAlone**: Percent of county residents with private health coverage alone (no public assistance) (b)\n",
    "* **PctEmpPrivCoverage**: Percent of county residents with employee-provided private health coverage (b)\n",
    "* **PctPublicCoverage**: Percent of county residents with government-provided health coverage (b)\n",
    "* **PctPubliceCoverageAlone**: Percent of county residents with government-provided health coverage alone (b)\n",
    "* **PctWhite**: Percent of county residents who identify as White (b)\n",
    "* **PctBlack**: Percent of county residents who identify as Black (b)\n",
    "* **PctAsian**: Percent of county residents who identify as Asian (b)\n",
    "* **PctOtherRace**: Percent of county residents who identify in a category which is not White, Black, or Asian (b)\n",
    "* **PctMarriedHouseholds**: Percent of married households (b)\n",
    "* **BirthRate**: Number of live births relative to number of women in county (b)\n",
    "\n",
    "Notes:\n",
    "* (a): years 2010-2016\n",
    "* (b): 2013 Census Estimates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "plastic-monte",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from os.path import join\n",
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import torch\n",
    "from torch import nn\n",
    "import torch.nn.functional as F\n",
    "from sklearn.metrics import r2_score\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from scipy.stats import binned_statistic\n",
    "\n",
    "cwd = os.getcwd()\n",
    "if cwd.endswith('notebook'):\n",
    "    os.chdir('..')\n",
    "    cwd = os.getcwd()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "silent-chair",
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.set(palette='colorblind', font_scale=1.3)\n",
    "palette = sns.color_palette()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "enclosed-strain",
   "metadata": {},
   "outputs": [],
   "source": [
    "seed = 444\n",
    "np.random.seed(seed);\n",
    "torch.manual_seed(seed);\n",
    "torch.set_default_dtype(torch.float64)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "attempted-general",
   "metadata": {},
   "source": [
    "## Dataset\n",
    "\n",
    "### Load"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "eleven-sound",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>avgAnnCount</th>\n",
       "      <th>avgDeathsPerYear</th>\n",
       "      <th>TARGET_deathRate</th>\n",
       "      <th>incidenceRate</th>\n",
       "      <th>medIncome</th>\n",
       "      <th>popEst2015</th>\n",
       "      <th>povertyPercent</th>\n",
       "      <th>studyPerCap</th>\n",
       "      <th>binnedInc</th>\n",
       "      <th>MedianAge</th>\n",
       "      <th>...</th>\n",
       "      <th>PctPrivateCoverageAlone</th>\n",
       "      <th>PctEmpPrivCoverage</th>\n",
       "      <th>PctPublicCoverage</th>\n",
       "      <th>PctPublicCoverageAlone</th>\n",
       "      <th>PctWhite</th>\n",
       "      <th>PctBlack</th>\n",
       "      <th>PctAsian</th>\n",
       "      <th>PctOtherRace</th>\n",
       "      <th>PctMarriedHouseholds</th>\n",
       "      <th>BirthRate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1397.0</td>\n",
       "      <td>469</td>\n",
       "      <td>164.9</td>\n",
       "      <td>489.8</td>\n",
       "      <td>61898</td>\n",
       "      <td>260131</td>\n",
       "      <td>11.2</td>\n",
       "      <td>499.748204</td>\n",
       "      <td>(61494.5, 125635]</td>\n",
       "      <td>39.3</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>41.6</td>\n",
       "      <td>32.9</td>\n",
       "      <td>14.0</td>\n",
       "      <td>81.780529</td>\n",
       "      <td>2.594728</td>\n",
       "      <td>4.821857</td>\n",
       "      <td>1.843479</td>\n",
       "      <td>52.856076</td>\n",
       "      <td>6.118831</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>173.0</td>\n",
       "      <td>70</td>\n",
       "      <td>161.3</td>\n",
       "      <td>411.6</td>\n",
       "      <td>48127</td>\n",
       "      <td>43269</td>\n",
       "      <td>18.6</td>\n",
       "      <td>23.111234</td>\n",
       "      <td>(48021.6, 51046.4]</td>\n",
       "      <td>33.0</td>\n",
       "      <td>...</td>\n",
       "      <td>53.8</td>\n",
       "      <td>43.6</td>\n",
       "      <td>31.1</td>\n",
       "      <td>15.3</td>\n",
       "      <td>89.228509</td>\n",
       "      <td>0.969102</td>\n",
       "      <td>2.246233</td>\n",
       "      <td>3.741352</td>\n",
       "      <td>45.372500</td>\n",
       "      <td>4.333096</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>102.0</td>\n",
       "      <td>50</td>\n",
       "      <td>174.7</td>\n",
       "      <td>349.7</td>\n",
       "      <td>49348</td>\n",
       "      <td>21026</td>\n",
       "      <td>14.6</td>\n",
       "      <td>47.560164</td>\n",
       "      <td>(48021.6, 51046.4]</td>\n",
       "      <td>45.0</td>\n",
       "      <td>...</td>\n",
       "      <td>43.5</td>\n",
       "      <td>34.9</td>\n",
       "      <td>42.1</td>\n",
       "      <td>21.1</td>\n",
       "      <td>90.922190</td>\n",
       "      <td>0.739673</td>\n",
       "      <td>0.465898</td>\n",
       "      <td>2.747358</td>\n",
       "      <td>54.444868</td>\n",
       "      <td>3.729488</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>427.0</td>\n",
       "      <td>202</td>\n",
       "      <td>194.8</td>\n",
       "      <td>430.4</td>\n",
       "      <td>44243</td>\n",
       "      <td>75882</td>\n",
       "      <td>17.1</td>\n",
       "      <td>342.637253</td>\n",
       "      <td>(42724.4, 45201]</td>\n",
       "      <td>42.8</td>\n",
       "      <td>...</td>\n",
       "      <td>40.3</td>\n",
       "      <td>35.0</td>\n",
       "      <td>45.3</td>\n",
       "      <td>25.0</td>\n",
       "      <td>91.744686</td>\n",
       "      <td>0.782626</td>\n",
       "      <td>1.161359</td>\n",
       "      <td>1.362643</td>\n",
       "      <td>51.021514</td>\n",
       "      <td>4.603841</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>57.0</td>\n",
       "      <td>26</td>\n",
       "      <td>144.4</td>\n",
       "      <td>350.1</td>\n",
       "      <td>49955</td>\n",
       "      <td>10321</td>\n",
       "      <td>12.5</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>(48021.6, 51046.4]</td>\n",
       "      <td>48.3</td>\n",
       "      <td>...</td>\n",
       "      <td>43.9</td>\n",
       "      <td>35.1</td>\n",
       "      <td>44.0</td>\n",
       "      <td>22.7</td>\n",
       "      <td>94.104024</td>\n",
       "      <td>0.270192</td>\n",
       "      <td>0.665830</td>\n",
       "      <td>0.492135</td>\n",
       "      <td>54.027460</td>\n",
       "      <td>6.796657</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 34 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   avgAnnCount  avgDeathsPerYear  TARGET_deathRate  incidenceRate  medIncome  \\\n",
       "0       1397.0               469             164.9          489.8      61898   \n",
       "1        173.0                70             161.3          411.6      48127   \n",
       "2        102.0                50             174.7          349.7      49348   \n",
       "3        427.0               202             194.8          430.4      44243   \n",
       "4         57.0                26             144.4          350.1      49955   \n",
       "\n",
       "   popEst2015  povertyPercent  studyPerCap           binnedInc  MedianAge  \\\n",
       "0      260131            11.2   499.748204   (61494.5, 125635]       39.3   \n",
       "1       43269            18.6    23.111234  (48021.6, 51046.4]       33.0   \n",
       "2       21026            14.6    47.560164  (48021.6, 51046.4]       45.0   \n",
       "3       75882            17.1   342.637253    (42724.4, 45201]       42.8   \n",
       "4       10321            12.5     0.000000  (48021.6, 51046.4]       48.3   \n",
       "\n",
       "   ...  PctPrivateCoverageAlone  PctEmpPrivCoverage PctPublicCoverage  \\\n",
       "0  ...                      NaN                41.6              32.9   \n",
       "1  ...                     53.8                43.6              31.1   \n",
       "2  ...                     43.5                34.9              42.1   \n",
       "3  ...                     40.3                35.0              45.3   \n",
       "4  ...                     43.9                35.1              44.0   \n",
       "\n",
       "   PctPublicCoverageAlone   PctWhite  PctBlack  PctAsian  PctOtherRace  \\\n",
       "0                    14.0  81.780529  2.594728  4.821857      1.843479   \n",
       "1                    15.3  89.228509  0.969102  2.246233      3.741352   \n",
       "2                    21.1  90.922190  0.739673  0.465898      2.747358   \n",
       "3                    25.0  91.744686  0.782626  1.161359      1.362643   \n",
       "4                    22.7  94.104024  0.270192  0.665830      0.492135   \n",
       "\n",
       "   PctMarriedHouseholds  BirthRate  \n",
       "0             52.856076   6.118831  \n",
       "1             45.372500   4.333096  \n",
       "2             54.444868   3.729488  \n",
       "3             51.021514   4.603841  \n",
       "4             54.027460   6.796657  \n",
       "\n",
       "[5 rows x 34 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(join(cwd, 'data/cancer_reg.csv'))\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "blank-deficit",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>avgAnnCount</th>\n",
       "      <th>avgDeathsPerYear</th>\n",
       "      <th>TARGET_deathRate</th>\n",
       "      <th>incidenceRate</th>\n",
       "      <th>medIncome</th>\n",
       "      <th>popEst2015</th>\n",
       "      <th>povertyPercent</th>\n",
       "      <th>studyPerCap</th>\n",
       "      <th>MedianAge</th>\n",
       "      <th>MedianAgeMale</th>\n",
       "      <th>...</th>\n",
       "      <th>PctPrivateCoverageAlone</th>\n",
       "      <th>PctEmpPrivCoverage</th>\n",
       "      <th>PctPublicCoverage</th>\n",
       "      <th>PctPublicCoverageAlone</th>\n",
       "      <th>PctWhite</th>\n",
       "      <th>PctBlack</th>\n",
       "      <th>PctAsian</th>\n",
       "      <th>PctOtherRace</th>\n",
       "      <th>PctMarriedHouseholds</th>\n",
       "      <th>BirthRate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3.047000e+03</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2438.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>606.338544</td>\n",
       "      <td>185.965868</td>\n",
       "      <td>178.664063</td>\n",
       "      <td>448.268586</td>\n",
       "      <td>47063.281917</td>\n",
       "      <td>1.026374e+05</td>\n",
       "      <td>16.878175</td>\n",
       "      <td>155.399415</td>\n",
       "      <td>45.272333</td>\n",
       "      <td>39.570725</td>\n",
       "      <td>...</td>\n",
       "      <td>48.453774</td>\n",
       "      <td>41.196324</td>\n",
       "      <td>36.252642</td>\n",
       "      <td>19.240072</td>\n",
       "      <td>83.645286</td>\n",
       "      <td>9.107978</td>\n",
       "      <td>1.253965</td>\n",
       "      <td>1.983523</td>\n",
       "      <td>51.243872</td>\n",
       "      <td>5.640306</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1416.356223</td>\n",
       "      <td>504.134286</td>\n",
       "      <td>27.751511</td>\n",
       "      <td>54.560733</td>\n",
       "      <td>12040.090836</td>\n",
       "      <td>3.290592e+05</td>\n",
       "      <td>6.409087</td>\n",
       "      <td>529.628366</td>\n",
       "      <td>45.304480</td>\n",
       "      <td>5.226017</td>\n",
       "      <td>...</td>\n",
       "      <td>10.083006</td>\n",
       "      <td>9.447687</td>\n",
       "      <td>7.841741</td>\n",
       "      <td>6.113041</td>\n",
       "      <td>16.380025</td>\n",
       "      <td>14.534538</td>\n",
       "      <td>2.610276</td>\n",
       "      <td>3.517710</td>\n",
       "      <td>6.572814</td>\n",
       "      <td>1.985816</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>59.700000</td>\n",
       "      <td>201.300000</td>\n",
       "      <td>22640.000000</td>\n",
       "      <td>8.270000e+02</td>\n",
       "      <td>3.200000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>22.400000</td>\n",
       "      <td>...</td>\n",
       "      <td>15.700000</td>\n",
       "      <td>13.500000</td>\n",
       "      <td>11.200000</td>\n",
       "      <td>2.600000</td>\n",
       "      <td>10.199155</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>22.992490</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>76.000000</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>161.200000</td>\n",
       "      <td>420.300000</td>\n",
       "      <td>38882.500000</td>\n",
       "      <td>1.168400e+04</td>\n",
       "      <td>12.150000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>37.700000</td>\n",
       "      <td>36.350000</td>\n",
       "      <td>...</td>\n",
       "      <td>41.000000</td>\n",
       "      <td>34.500000</td>\n",
       "      <td>30.900000</td>\n",
       "      <td>14.850000</td>\n",
       "      <td>77.296180</td>\n",
       "      <td>0.620675</td>\n",
       "      <td>0.254199</td>\n",
       "      <td>0.295172</td>\n",
       "      <td>47.763063</td>\n",
       "      <td>4.521419</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>171.000000</td>\n",
       "      <td>61.000000</td>\n",
       "      <td>178.100000</td>\n",
       "      <td>453.549422</td>\n",
       "      <td>45207.000000</td>\n",
       "      <td>2.664300e+04</td>\n",
       "      <td>15.900000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>41.000000</td>\n",
       "      <td>39.600000</td>\n",
       "      <td>...</td>\n",
       "      <td>48.700000</td>\n",
       "      <td>41.100000</td>\n",
       "      <td>36.300000</td>\n",
       "      <td>18.800000</td>\n",
       "      <td>90.059774</td>\n",
       "      <td>2.247576</td>\n",
       "      <td>0.549812</td>\n",
       "      <td>0.826185</td>\n",
       "      <td>51.669941</td>\n",
       "      <td>5.381478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>518.000000</td>\n",
       "      <td>149.000000</td>\n",
       "      <td>195.200000</td>\n",
       "      <td>480.850000</td>\n",
       "      <td>52492.000000</td>\n",
       "      <td>6.867100e+04</td>\n",
       "      <td>20.400000</td>\n",
       "      <td>83.650776</td>\n",
       "      <td>44.000000</td>\n",
       "      <td>42.500000</td>\n",
       "      <td>...</td>\n",
       "      <td>55.600000</td>\n",
       "      <td>47.700000</td>\n",
       "      <td>41.550000</td>\n",
       "      <td>23.100000</td>\n",
       "      <td>95.451693</td>\n",
       "      <td>10.509732</td>\n",
       "      <td>1.221037</td>\n",
       "      <td>2.177960</td>\n",
       "      <td>55.395132</td>\n",
       "      <td>6.493677</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>38150.000000</td>\n",
       "      <td>14010.000000</td>\n",
       "      <td>362.800000</td>\n",
       "      <td>1206.900000</td>\n",
       "      <td>125635.000000</td>\n",
       "      <td>1.017029e+07</td>\n",
       "      <td>47.400000</td>\n",
       "      <td>9762.308998</td>\n",
       "      <td>624.000000</td>\n",
       "      <td>64.700000</td>\n",
       "      <td>...</td>\n",
       "      <td>78.900000</td>\n",
       "      <td>70.700000</td>\n",
       "      <td>65.100000</td>\n",
       "      <td>46.600000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>85.947799</td>\n",
       "      <td>42.619425</td>\n",
       "      <td>41.930251</td>\n",
       "      <td>78.075397</td>\n",
       "      <td>21.326165</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 32 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        avgAnnCount  avgDeathsPerYear  TARGET_deathRate  incidenceRate  \\\n",
       "count   3047.000000       3047.000000       3047.000000    3047.000000   \n",
       "mean     606.338544        185.965868        178.664063     448.268586   \n",
       "std     1416.356223        504.134286         27.751511      54.560733   \n",
       "min        6.000000          3.000000         59.700000     201.300000   \n",
       "25%       76.000000         28.000000        161.200000     420.300000   \n",
       "50%      171.000000         61.000000        178.100000     453.549422   \n",
       "75%      518.000000        149.000000        195.200000     480.850000   \n",
       "max    38150.000000      14010.000000        362.800000    1206.900000   \n",
       "\n",
       "           medIncome    popEst2015  povertyPercent  studyPerCap    MedianAge  \\\n",
       "count    3047.000000  3.047000e+03     3047.000000  3047.000000  3047.000000   \n",
       "mean    47063.281917  1.026374e+05       16.878175   155.399415    45.272333   \n",
       "std     12040.090836  3.290592e+05        6.409087   529.628366    45.304480   \n",
       "min     22640.000000  8.270000e+02        3.200000     0.000000    22.300000   \n",
       "25%     38882.500000  1.168400e+04       12.150000     0.000000    37.700000   \n",
       "50%     45207.000000  2.664300e+04       15.900000     0.000000    41.000000   \n",
       "75%     52492.000000  6.867100e+04       20.400000    83.650776    44.000000   \n",
       "max    125635.000000  1.017029e+07       47.400000  9762.308998   624.000000   \n",
       "\n",
       "       MedianAgeMale  ...  PctPrivateCoverageAlone  PctEmpPrivCoverage  \\\n",
       "count    3047.000000  ...              2438.000000         3047.000000   \n",
       "mean       39.570725  ...                48.453774           41.196324   \n",
       "std         5.226017  ...                10.083006            9.447687   \n",
       "min        22.400000  ...                15.700000           13.500000   \n",
       "25%        36.350000  ...                41.000000           34.500000   \n",
       "50%        39.600000  ...                48.700000           41.100000   \n",
       "75%        42.500000  ...                55.600000           47.700000   \n",
       "max        64.700000  ...                78.900000           70.700000   \n",
       "\n",
       "       PctPublicCoverage  PctPublicCoverageAlone     PctWhite     PctBlack  \\\n",
       "count        3047.000000             3047.000000  3047.000000  3047.000000   \n",
       "mean           36.252642               19.240072    83.645286     9.107978   \n",
       "std             7.841741                6.113041    16.380025    14.534538   \n",
       "min            11.200000                2.600000    10.199155     0.000000   \n",
       "25%            30.900000               14.850000    77.296180     0.620675   \n",
       "50%            36.300000               18.800000    90.059774     2.247576   \n",
       "75%            41.550000               23.100000    95.451693    10.509732   \n",
       "max            65.100000               46.600000   100.000000    85.947799   \n",
       "\n",
       "          PctAsian  PctOtherRace  PctMarriedHouseholds    BirthRate  \n",
       "count  3047.000000   3047.000000           3047.000000  3047.000000  \n",
       "mean      1.253965      1.983523             51.243872     5.640306  \n",
       "std       2.610276      3.517710              6.572814     1.985816  \n",
       "min       0.000000      0.000000             22.992490     0.000000  \n",
       "25%       0.254199      0.295172             47.763063     4.521419  \n",
       "50%       0.549812      0.826185             51.669941     5.381478  \n",
       "75%       1.221037      2.177960             55.395132     6.493677  \n",
       "max      42.619425     41.930251             78.075397    21.326165  \n",
       "\n",
       "[8 rows x 32 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "explicit-pollution",
   "metadata": {},
   "source": [
    "### Plot distribution of target variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "assured-happiness",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "_, ax = plt.subplots(1, 1, figsize=(10, 5))\n",
    "df['TARGET_deathRate'].hist(bins=50, ax=ax);\n",
    "ax.set_title('Distribution of cancer death rate per 100,000 people');\n",
    "ax.set_xlabel('Cancer death rate in county (per 100,000 people)');\n",
    "ax.set_ylabel('Count');"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "brave-anchor",
   "metadata": {},
   "source": [
    "### Define feature & target variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "settled-wrong",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "28 features\n"
     ]
    }
   ],
   "source": [
    "target = 'TARGET_deathRate'\n",
    "features = [\n",
    "    col for col in df.columns\n",
    "    if col not in [\n",
    "        target, \n",
    "        'Geography',                # Label describing the county - each row has a different one\n",
    "        'binnedInc',                # Redundant with median income?\n",
    "        'PctSomeCol18_24',          # contains null values - ignoring for now\n",
    "        'PctEmployed16_Over',       # contains null values - ignoring for now\n",
    "        'PctPrivateCoverageAlone',  # contains null values - ignoring for now\n",
    "    ]\n",
    "]\n",
    "print(len(features), 'features')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "happy-reporter",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(3047, 28) (3047, 1)\n"
     ]
    }
   ],
   "source": [
    "x = df[features].values\n",
    "y = df[[target]].values\n",
    "print(x.shape, y.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "certain-leather",
   "metadata": {},
   "source": [
    "## Define model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "passive-collective",
   "metadata": {},
   "outputs": [],
   "source": [
    "class VariationalModel(nn.Module):\n",
    "    def __init__(\n",
    "        self, \n",
    "        n_inputs,\n",
    "        encoding_size,\n",
    "        n_hidden,\n",
    "        x_scaler, \n",
    "        y_scaler,\n",
    "        n_mixtures=5,\n",
    "        n_enc_layers=1,\n",
    "        n_dec_layers=1,\n",
    "        jitter=1e-8,\n",
    "    ):\n",
    "        super().__init__()\n",
    "        \n",
    "        self.n_inputs = n_inputs\n",
    "        self.encoding_size = encoding_size\n",
    "        self.n_mixtures = n_mixtures\n",
    "        self.jitter = jitter\n",
    "        self.x_scaler = x_scaler\n",
    "        self.y_scaler = y_scaler\n",
    "        \n",
    "        # Prior\n",
    "        self.prior = torch.distributions.Independent(\n",
    "            torch.distributions.Normal(\n",
    "                torch.zeros(n_mixtures, encoding_size), \n",
    "                torch.ones(n_mixtures, encoding_size),\n",
    "            ), \n",
    "            1,\n",
    "        )\n",
    "        \n",
    "        # Encoder\n",
    "        enc_shared_layers = []\n",
    "        for i in range(n_enc_layers):\n",
    "            if i == 0:\n",
    "                layer = nn.Linear(n_inputs, n_hidden)\n",
    "            else:\n",
    "                layer = nn.Linear(n_hidden, n_hidden)\n",
    "    \n",
    "            enc_shared_layers.append(layer)\n",
    "            enc_shared_layers.append(nn.ReLU())\n",
    "            \n",
    "        self.enc_shared = nn.Sequential(*enc_shared_layers)\n",
    "        self.mean_gmm_layer = nn.Linear(n_hidden, encoding_size * n_mixtures)\n",
    "        self.std_gmm_layer = nn.Linear(n_hidden, encoding_size * n_mixtures)\n",
    "        \n",
    "        # Decoder\n",
    "        dec_shared_layers = []\n",
    "        for i in range(n_dec_layers):\n",
    "            if i == 0:\n",
    "                layer = nn.Linear(encoding_size, n_hidden)\n",
    "            else:\n",
    "                layer = nn.Linear(n_hidden, n_hidden)\n",
    "                \n",
    "            dec_shared_layers.append(layer)\n",
    "            dec_shared_layers.append(nn.ReLU())\n",
    "            \n",
    "        self.dec_shared = nn.Sequential(*dec_shared_layers)\n",
    "        self.mean_layer = nn.Linear(n_hidden, 1)\n",
    "        self.std_layer = nn.Linear(n_hidden, 1)\n",
    "        \n",
    "    def encode(self, x):\n",
    "        shared = self.x_scaler(x)\n",
    "        shared = self.enc_shared(shared)\n",
    "        \n",
    "        shp = (-1, self.n_mixtures, self.encoding_size)\n",
    "        mean = torch.reshape(self.mean_gmm_layer(shared), shp)\n",
    "        std = torch.reshape(F.softplus(self.std_gmm_layer(shared)) + self.jitter, shp)\n",
    "        \n",
    "        return torch.distributions.Independent(torch.distributions.Normal(mean, std), 1)\n",
    "    \n",
    "    def decode(self, x_enc):\n",
    "        shared = self.dec_shared(x_enc)\n",
    "        mean = self.mean_layer(shared)\n",
    "        std = F.softplus(self.std_layer(shared)) + self.jitter\n",
    "        return torch.distributions.Normal(mean, std)\n",
    "    \n",
    "    def forward(self, x):\n",
    "        gmm_dist = self.encode(x)\n",
    "        encoding = torch.mean(gmm_dist.mean, dim=1)\n",
    "        return self.decode(encoding)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "little-labor",
   "metadata": {},
   "outputs": [],
   "source": [
    "def compute_loss(model, x, y):\n",
    "    \"\"\"\n",
    "    ELBO loss - https://en.wikipedia.org/wiki/Evidence_lower_bound\n",
    "    \"\"\"\n",
    "    y_scaled = model.y_scaler(y)\n",
    "    \n",
    "    gmm_dist = model.encode(x)\n",
    "    encoding = torch.mean(gmm_dist.rsample(), dim=1)\n",
    "    y_hat = model.decode(encoding)\n",
    "    \n",
    "    neg_log_likelihood = -y_hat.log_prob(y_scaled)\n",
    "    \n",
    "    kl_divergence = torch.distributions.kl.kl_divergence(gmm_dist, model.prior)\n",
    "    \n",
    "    return torch.mean(neg_log_likelihood + kl_divergence)\n",
    "\n",
    "\n",
    "def compute_rmse(model, x_test, y_test):\n",
    "    model.eval()\n",
    "    y_hat = model(x_test)\n",
    "    pred = model.y_scaler.inverse_transform(y_hat.mean)\n",
    "    return torch.sqrt(torch.mean((pred - y_test)**2))\n",
    "\n",
    "\n",
    "def train_one_step(model, optimizer, x_batch, y_batch):\n",
    "    model.train()\n",
    "    optimizer.zero_grad()\n",
    "    loss = compute_loss(model, x_batch, y_batch)\n",
    "    loss.backward()\n",
    "    optimizer.step()\n",
    "    return loss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "brown-internship",
   "metadata": {},
   "outputs": [],
   "source": [
    "def train(model, optimizer, x_train, x_val, y_train, y_val, n_epochs, batch_size, scheduler=None, print_every=10):\n",
    "    train_losses, val_losses = [], []\n",
    "    for epoch in range(n_epochs):\n",
    "        batch_indices = sample_batch_indices(x_train, y_train, batch_size)\n",
    "        \n",
    "        batch_losses_t, batch_losses_v, batch_rmse_v = [], [], []\n",
    "        for batch_ix in batch_indices:\n",
    "            b_train_loss = train_one_step(model, optimizer, x_train[batch_ix], y_train[batch_ix])\n",
    "\n",
    "            model.eval()\n",
    "            b_val_loss = compute_loss(model, x_val, y_val)\n",
    "            b_val_rmse = compute_rmse(model, x_val, y_val)\n",
    "\n",
    "            batch_losses_t.append(b_train_loss.detach().numpy())\n",
    "            batch_losses_v.append(b_val_loss.detach().numpy())\n",
    "            batch_rmse_v.append(b_val_rmse.detach().numpy())\n",
    "            \n",
    "        if scheduler is not None:\n",
    "            scheduler.step()\n",
    "            \n",
    "        train_loss = np.mean(batch_losses_t)\n",
    "        val_loss = np.mean(batch_losses_v)\n",
    "        val_rmse = np.mean(batch_rmse_v)\n",
    "        \n",
    "        train_losses.append(train_loss)\n",
    "        val_losses.append(val_loss)\n",
    "\n",
    "        if epoch == 0 or (epoch + 1) % print_every == 0:\n",
    "            print(f'Epoch {epoch+1} | Validation loss = {val_loss:.4f} | Validation RMSE = {val_rmse:.4f}')\n",
    "        \n",
    "    _, ax = plt.subplots(1, 1, figsize=(12, 6))\n",
    "    ax.plot(range(1, n_epochs + 1), train_losses, label='Train loss')\n",
    "    ax.plot(range(1, n_epochs + 1), val_losses, label='Validation loss')\n",
    "    ax.set_xlabel('Epoch')\n",
    "    ax.set_ylabel('Loss')\n",
    "    ax.set_title('Training Overview')\n",
    "    ax.legend()\n",
    "    \n",
    "    return train_losses, val_losses\n",
    "\n",
    "\n",
    "def sample_batch_indices(x, y, batch_size, rs=None):\n",
    "    if rs is None:\n",
    "        rs = np.random.RandomState()\n",
    "    \n",
    "    train_ix = np.arange(len(x))\n",
    "    rs.shuffle(train_ix)\n",
    "    \n",
    "    n_batches = int(np.ceil(len(x) / batch_size))\n",
    "    \n",
    "    batch_indices = []\n",
    "    for i in range(n_batches):\n",
    "        start = i * batch_size\n",
    "        end = start + batch_size\n",
    "        batch_indices.append(\n",
    "            train_ix[start:end].tolist()\n",
    "        )\n",
    "\n",
    "    return batch_indices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "successful-maker",
   "metadata": {},
   "outputs": [],
   "source": [
    "class StandardScaler(object):\n",
    "    \"\"\"\n",
    "    Standardize data by removing the mean and scaling to unit variance.\n",
    "    \"\"\"\n",
    "    def __init__(self):\n",
    "        self.mean = None\n",
    "        self.scale = None\n",
    "\n",
    "    def fit(self, sample):\n",
    "        self.mean = sample.mean(0, keepdim=True)\n",
    "        self.scale = sample.std(0, unbiased=False, keepdim=True)\n",
    "        return self\n",
    "\n",
    "    def __call__(self, sample):\n",
    "        return self.transform(sample)\n",
    "    \n",
    "    def transform(self, sample):\n",
    "        return (sample - self.mean) / self.scale\n",
    "\n",
    "    def inverse_transform(self, sample):\n",
    "        return sample * self.scale + self.mean"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "absent-couple",
   "metadata": {},
   "source": [
    "## Split between training and validation sets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "center-kenya",
   "metadata": {},
   "outputs": [],
   "source": [
    "def compute_train_test_split(x, y, test_size):\n",
    "    x_train, x_test, y_train, y_test, train_ix, test_ix = train_test_split(\n",
    "        x, \n",
    "        y, \n",
    "        list(range(len(x))),\n",
    "        test_size=test_size,\n",
    "    )\n",
    "    return (\n",
    "        torch.from_numpy(x_train),\n",
    "        torch.from_numpy(x_test),\n",
    "        torch.from_numpy(y_train),\n",
    "        torch.from_numpy(y_test),\n",
    "        train_ix,\n",
    "        test_ix,\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "divided-pharmacy",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([2437, 28]) torch.Size([2437, 1]) 2437\n",
      "torch.Size([610, 28]) torch.Size([610, 1]) 610\n"
     ]
    }
   ],
   "source": [
    "x_train, x_val, y_train, y_val, train_ix, test_ix = compute_train_test_split(x, y, test_size=0.2)\n",
    "\n",
    "print(x_train.shape, y_train.shape, len(train_ix))\n",
    "print(x_val.shape, y_val.shape, len(test_ix))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "reduced-cabinet",
   "metadata": {},
   "source": [
    "## Train model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "southern-sport",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_scaler = StandardScaler().fit(torch.from_numpy(x))\n",
    "y_scaler = StandardScaler().fit(torch.from_numpy(y))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "interesting-alias",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "VariationalModel(\n",
       "  (enc_shared): Sequential(\n",
       "    (0): Linear(in_features=28, out_features=100, bias=True)\n",
       "    (1): ReLU()\n",
       "  )\n",
       "  (mean_gmm_layer): Linear(in_features=100, out_features=50, bias=True)\n",
       "  (std_gmm_layer): Linear(in_features=100, out_features=50, bias=True)\n",
       "  (dec_shared): Sequential(\n",
       "    (0): Linear(in_features=10, out_features=100, bias=True)\n",
       "    (1): ReLU()\n",
       "  )\n",
       "  (mean_layer): Linear(in_features=100, out_features=1, bias=True)\n",
       "  (std_layer): Linear(in_features=100, out_features=1, bias=True)\n",
       ")"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = VariationalModel(\n",
    "    n_inputs=x.shape[1],\n",
    "    encoding_size=10,\n",
    "    n_hidden=100,\n",
    "    x_scaler=x_scaler, \n",
    "    y_scaler=y_scaler,\n",
    "    n_mixtures=5,\n",
    "    n_enc_layers=1,\n",
    "    n_dec_layers=1,\n",
    ")\n",
    "model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "dense-company",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "14,302 trainable parameters\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pytorch_total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)\n",
    "print(f'{pytorch_total_params:,} trainable parameters')\n",
    "print()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "false-hampshire",
   "metadata": {},
   "outputs": [],
   "source": [
    "learning_rate = 1e-4\n",
    "\n",
    "optimizer = torch.optim.Adam(\n",
    "    model.parameters(), \n",
    "    lr=learning_rate, \n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "olive-coach",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1 | Validation loss = 3.1302 | Validation RMSE = 28.0765\n",
      "Epoch 50 | Validation loss = 1.4088 | Validation RMSE = 22.9438\n",
      "Epoch 100 | Validation loss = 1.3531 | Validation RMSE = 20.8623\n",
      "Epoch 150 | Validation loss = 1.3479 | Validation RMSE = 20.3298\n",
      "Epoch 200 | Validation loss = 1.3469 | Validation RMSE = 20.1943\n",
      "Epoch 250 | Validation loss = 1.3388 | Validation RMSE = 20.0699\n",
      "Epoch 300 | Validation loss = 1.3446 | Validation RMSE = 19.6804\n",
      "Epoch 350 | Validation loss = 1.3457 | Validation RMSE = 19.6464\n",
      "Epoch 400 | Validation loss = 1.3456 | Validation RMSE = 19.5523\n",
      "Epoch 450 | Validation loss = 1.3483 | Validation RMSE = 19.6363\n",
      "Epoch 500 | Validation loss = 1.3462 | Validation RMSE = 19.3257\n",
      "Epoch 550 | Validation loss = 1.3380 | Validation RMSE = 19.2351\n",
      "Epoch 600 | Validation loss = 1.3586 | Validation RMSE = 19.1674\n",
      "Epoch 650 | Validation loss = 1.3522 | Validation RMSE = 19.0560\n",
      "Epoch 700 | Validation loss = 1.3601 | Validation RMSE = 19.0464\n",
      "Epoch 750 | Validation loss = 1.3578 | Validation RMSE = 18.7227\n",
      "Epoch 800 | Validation loss = 1.3654 | Validation RMSE = 18.6508\n",
      "Epoch 850 | Validation loss = 1.3640 | Validation RMSE = 18.6167\n",
      "Epoch 900 | Validation loss = 1.3600 | Validation RMSE = 18.5071\n",
      "Epoch 950 | Validation loss = 1.3726 | Validation RMSE = 18.4926\n",
      "Epoch 1000 | Validation loss = 1.3745 | Validation RMSE = 18.4887\n",
      "Epoch 1050 | Validation loss = 1.3723 | Validation RMSE = 18.2981\n",
      "Epoch 1100 | Validation loss = 1.3841 | Validation RMSE = 18.2612\n",
      "Epoch 1150 | Validation loss = 1.3823 | Validation RMSE = 18.5471\n",
      "Epoch 1200 | Validation loss = 1.3951 | Validation RMSE = 18.5240\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "n_epochs = 1200\n",
    "batch_size = 64\n",
    "print_every = 50\n",
    "\n",
    "train_losses, val_losses = train(\n",
    "    model, \n",
    "    optimizer, \n",
    "    x_train, \n",
    "    x_val, \n",
    "    y_train, \n",
    "    y_val, \n",
    "    n_epochs=n_epochs, \n",
    "    batch_size=batch_size, \n",
    "    print_every=print_every,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "verbal-cartoon",
   "metadata": {},
   "source": [
    "### Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "embedded-retailer",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_dist = model(x_val)\n",
    "y_hat = model.y_scaler.inverse_transform(y_dist.mean)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "expected-input",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Validation RMSE = 18.29\n"
     ]
    }
   ],
   "source": [
    "val_rmse = float(compute_rmse(model, x_val, y_val).detach().numpy())\n",
    "print(f'Validation RMSE = {val_rmse:.2f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "skilled-bearing",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Validation $R^2$ = 0.57\n"
     ]
    }
   ],
   "source": [
    "val_r2 = r2_score(\n",
    "    y_val.detach().numpy().flatten(),\n",
    "    y_hat.detach().numpy().flatten(),\n",
    ")\n",
    "print(f'Validation $R^2$ = {val_r2:.2f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "collectible-composer",
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_results(y_true, y_pred):\n",
    "    _, ax = plt.subplots(1, 1, figsize=(7, 7))\n",
    "    palette = sns.color_palette()\n",
    "    \n",
    "    min_value = min(np.amin(y_true), np.amin(y_pred))\n",
    "    max_value = max(np.amax(y_true), np.amax(y_pred))\n",
    "    y_mid = np.linspace(min_value, max_value)\n",
    "    \n",
    "    ax.plot(y_mid, y_mid, '--', color=palette[1])\n",
    "    ax.scatter(y_true, y_pred, color=palette[0], alpha=0.5);\n",
    "    \n",
    "    return ax"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "tropical-mother",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x504 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = plot_results(\n",
    "    y_val.detach().numpy().flatten(),\n",
    "    y_hat.detach().numpy().flatten(),\n",
    ");\n",
    "\n",
    "ax.text(270, 120, f'$R^2 = {val_r2:.2f}$')\n",
    "ax.text(270, 100, f'$RMSE = {val_rmse:.2f}$')\n",
    "\n",
    "ax.set_xlabel('Actuals');\n",
    "ax.set_ylabel('Predictions');\n",
    "ax.set_title('Regression results on validation set');"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "multiple-freeware",
   "metadata": {},
   "source": [
    "## Uncertainty"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "roman-religious",
   "metadata": {},
   "outputs": [],
   "source": [
    "def compute_first_order_uncertainty(model, x):\n",
    "    gmm_dist = model.encode(x)\n",
    "    encoding = torch.mean(gmm_dist.mean, dim=1)\n",
    "    out_dist = model.decode(encoding)\n",
    "    \n",
    "    inv_tr = model.y_scaler.inverse_transform\n",
    "    y_hat = inv_tr(out_dist.mean)\n",
    "    std = inv_tr(out_dist.mean + out_dist.stddev) - y_hat\n",
    "    \n",
    "    return std.detach().numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "medical-research",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(610, 1)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "first_order_std = compute_first_order_uncertainty(model, x_val)\n",
    "first_order_std.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "harmful-overall",
   "metadata": {},
   "outputs": [],
   "source": [
    "def compute_second_order_uncertainty(model, x, n_samples=1000, std=False):\n",
    "    gmm_dist = model.encode(x)\n",
    "    encoding_sample = torch.mean(gmm_dist.rsample((n_samples,)), dim=2)\n",
    "    \n",
    "    inv_tr = model.y_scaler.inverse_transform\n",
    "    \n",
    "    shp = encoding_sample.shape\n",
    "    res = np.zeros((n_samples, shp[1], 1))\n",
    "    stds = np.zeros((n_samples, shp[1], 1))\n",
    "    for i in range(n_samples):\n",
    "        d = model.decode(encoding_sample[i])\n",
    "        mean = d.mean\n",
    "        res[i] = inv_tr(mean).detach().numpy()\n",
    "        stds[i] = (inv_tr(mean + d.stddev) - inv_tr(mean)).detach().numpy()\n",
    "        \n",
    "    second_order_std = np.std(res, axis=0)\n",
    "    std_std = np.mean(stds, axis=0)\n",
    "        \n",
    "    if not std:    \n",
    "        return second_order_std\n",
    "    else:\n",
    "        return second_order_std, std_std"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "offensive-mountain",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(610, 1)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "second_order_std, std_std = compute_second_order_uncertainty(model, x_val, std=True)\n",
    "second_order_std.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "compressed-harassment",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.hist(first_order_std.flatten(), bins=50);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "exotic-houston",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.hist(second_order_std.flatten(), bins=50);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "sized-emperor",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.hist(std_std.flatten(), bins=50);"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "noble-escape",
   "metadata": {},
   "source": [
    "### Uncertainty on an input not yet seen & very different from the rest of the dataset\n",
    "\n",
    "We'll consider an input made of the maximum of all features."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "global-error",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "torch.Size([1, 28])"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "max_input_np = np.zeros((1, x_val.shape[1]))\n",
    "for i in range(x_val.shape[1]):\n",
    "    max_input_np[0, i] = torch.amax(x_val[:, i]) * 2\n",
    "\n",
    "random_input = torch.from_numpy(max_input_np)\n",
    "random_input.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "rising-tender",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "First order uncertainty: 28.76\n",
      "Second order uncertainty: 9.42\n"
     ]
    }
   ],
   "source": [
    "r_first_order_std = compute_first_order_uncertainty(model, random_input)\n",
    "r_second_order_std = compute_second_order_uncertainty(model, random_input)\n",
    "\n",
    "print(f'First order uncertainty: {float(r_first_order_std):.2f}')\n",
    "print(f'Second order uncertainty: {float(r_second_order_std):.2f}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "lined-india",
   "metadata": {},
   "source": [
    "## Quantiles\n",
    "\n",
    "An instance's expectedness can be measured by its average feature quantile.\n",
    "\n",
    "We can then estimate the relation between uncertainty and expectedness."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "altered-confusion",
   "metadata": {},
   "outputs": [],
   "source": [
    "def set_feature_quantile(df, features):\n",
    "    series = []\n",
    "    quantiles = np.arange(0., 1., 0.01)\n",
    "    for q in quantiles:\n",
    "        series.append(df[features].quantile(q))\n",
    "        \n",
    "    def apply_quantile(row):\n",
    "        v = np.zeros((len(features)))\n",
    "        \n",
    "        for i, f in enumerate(features):\n",
    "            value = row[f]\n",
    "            for j, q in enumerate(quantiles):\n",
    "                if value <= series[j][f]:\n",
    "                    v[i] = q\n",
    "                    break\n",
    "        \n",
    "        return v.mean()\n",
    "    \n",
    "    df['quantile'] = df.apply(apply_quantile, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "respective-conflict",
   "metadata": {},
   "outputs": [],
   "source": [
    "set_feature_quantile(df, features)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "personalized-giant",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    0.589286\n",
       "1    0.413571\n",
       "2    0.550000\n",
       "3    0.568929\n",
       "4    0.481786\n",
       "Name: quantile, dtype: float64"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['quantile'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "oriental-birth",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df['quantile'].hist(bins=20);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "norman-progressive",
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_expectedness_vs_uncertainty(df, test_ix, y_val, std):\n",
    "    expectedness = np.abs(df['quantile'].iloc[test_ix].values - 0.5)\n",
    "    stds = std.flatten() / y_val.detach().numpy().flatten()\n",
    "    \n",
    "    _, ax = plt.subplots(1, 1, figsize=(12, 6))\n",
    "    ax.scatter(expectedness, stds, alpha=0.3)\n",
    "    \n",
    "    X = expectedness.reshape((-1, 1))\n",
    "    y = stds\n",
    "    linreg = LinearRegression().fit(X, y)\n",
    "    print(f'R2: {linreg.score(X, y):.2f}')\n",
    "    print(f'Correlation: {np.corrcoef(expectedness, stds)[0, 1]:.2f}')\n",
    "    \n",
    "    y_fit = linreg.coef_[0] * expectedness + linreg.intercept_\n",
    "    \n",
    "    ax.plot(expectedness, y_fit, '-', color=palette[1], alpha=0.5)\n",
    "    \n",
    "    return ax"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "adolescent-surgeon",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "R2: 0.01\n",
      "Correlation: 0.09\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = plot_expectedness_vs_uncertainty(df, test_ix, y_val, first_order_std)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "structured-matthew",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "R2: 0.01\n",
      "Correlation: 0.12\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtEAAAFuCAYAAABHvUQ6AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAACiWUlEQVR4nOz9eZRkd3ngeX/vHjf2XCKzcqm9pCpJCKlAQiDANltbbh1mhmn1a/weunEPajjGw5jTMrgNb/uMNf0OmjmAu+f0TB/z0vYB48H0MuNNZwQNMm4sBEilBAktJdVeWZmVFRmZGXvc/f0jMqJyrczINbLq+fwDioq48Yt7I/I+97nP7/kpURRFCCGEEEIIIdZN3e0BCCGEEEIIsddIEC2EEEIIIUSHJIgWQgghhBCiQxJECyGEEEII0SEJooUQQgghhOiQBNFCCCGEEEJ0aF1BtOd5PP744zzwwAM88MADfPGLXyQMwxu+ZnZ2lgcffJCzZ8+uus0PfvCDfPGLX+x81EIIIYQQQuyidQXRX/7yl3nmmWf4yle+wh/8wR/w53/+53z1q19d9fkzMzN8/OMfp1AorPqcP/zDP+T111/vfMRCCCGEEELssjWDaMdx+OY3v8nnPvc57rnnHh588EEee+wxvv71r7PSOi3PPPMMH/rQh/A8b9Vtvv766/zZn/0Zx44d29zohRBCCCGE2AX6Wk949dVXqdfr3Hfffe3H7rvvPvL5POPj4+zfv3/R87///e/zkY98hF/+5V/mAx/4wLLtBUHA7/7u7/LYY4/xf/1f/9eGBz47WyUMd26xxb6+JIVCZcfeT6xNjkn3kWPSneS4dB85Jt1Hjkl32s3joqoKPT2JVf99zSB6amqKZDJJInF9I7lcrv1vS4Poz3/+8wCMj4+vuL0/+qM/IpPJ8KEPfWhTQXQYRjsaRLfeU3QXOSbdR45Jd5Lj0n3kmHQfOSbdqVuPy5pBdL1ex7KsRY+ZpgmA67odvdn58+f56le/yn/8j/+xo9etpK8vueltdCqXS+34e4obk2PSfeSYdCc5Lt1Hjkn3kWPSnbr1uKwZRMdisWXBcuu/Y7HYut8oiiI+//nP8xu/8RvLstcbUShUdvTKJJdLkc+Xd+z9xNrkmHQfOSbdSY5L95Fj0n3kmHSn3TwuqqrcMGm7ZhC9b98+yuUy9Xod27YByOfzAAwODq57IBMTE5w6dYpXXnmFf/2v/zUAjUaDsbEx/uZv/oYnn3xy3dsSQgghhBBiN60ZRJ84cQLbtjl16hTvete7AHj++ecZGBhgZGRk3W80ODjId77znUWP/fZv/zZ33HEHn/jEJzocthBCCCGEELtnXeUcjzzyCI8//jhPPPEEjuPwpS99iV//9V8HYG5uDk3TSKVuXK+i6zoHDx5ctu10Ot1RMC6EEEIIIcRuWzOIBvjMZz6D4zg8+uijWJbFI488wsc+9jEAPvWpTzEyMsITTzyxrQMVQgghhBCiWyjRSium7AEysVDIMek+cky6kxyX7iPHpPvIMelO3TyxcF3LfgshhBBCCCGukyBaCCGEEEKIDq2rJloI0TRRajA2WaZQc+mLm5wcSjGcXn+/dCGEEELcHCQTLcQ6TZQaPHVmmrofkEua1P2Ap85MM1Fq7PbQhBBCCLHDJIgWYp3GJsukLZ2UpaMqCilLJ23pjE3KRBQhhBDiViNBtBDrVKi5JExt0WMJU6NQc3dpREIIIYTYLRJEC7FOfXGTqhsseqzqBvTFzV0akRBCCCF2iwTRQqzTyaEUJcen7PiEUUTZ8Sk5PieHbrxapxBCCCFuPhJEC7FOw+kYDx3rx9Y18hUXW9d46Fi/dOcQQgghbkHS4k6IDgynYxI0CyGEEEIy0UIIIYQQQnRKgmghhBBCCCE6JEG0EEIIIYQQHZIgWgghhBBCiA5JEC2EEEIIIUSHJIgWQgghhBCiQxJECyGEEEII0SEJooUQQgghhOiQBNFCCCGEEEJ0SIJoIYQQQgghOiRBtBBCCCGEEB2SIFoIIYQQQogOSRAthBBCCCFEhySIFkIIIYQQokMSRAshhBBCCNEhCaKFEEIIIYTokATRQgghhBBCdEiCaCGEEEIIITokQbQQQgghhBAdkiBaCCGEEEKIDkkQLYQQQgghRIckiBZCCCGEEKJDEkQLIYQQQgjRIQmihRBCCCGE6JAE0UIIIYQQQnRIgmghhBBCCCE6JEG0EEIIIYQQHZIgWgghhBBCiA5JEC2EEEIIIUSHJIgWQgghhBCiQxJECyGEEEII0SEJooUQQgghhOiQBNFCCCGEEEJ0SIJoIYQQQgghOiRBtBBCCCGEEB3Sd3sAQtyMJkoNxibLFGoufXGTk0MphtOx3R6WEEIIIbaIZKKF2GITpQZPnZmm7gfkkiZ1P+CpM9NMlBq7PTQhhBBCbBEJooXYYmOTZdKWTsrSURWFlKWTtnTGJsu7PTQhhBBCbBEJooXYYoWaS8LUFj2WMDUKNXeXRiSEEEKIrSZBtBBbrC9uUnWDRY9V3YC+uLlLIxJCCCHEVpMgWogtdnIoRcnxKTs+YRRRdnxKjs/JodRuD00IIYQQW0SCaCG22HA6xkPH+rF1jXzFxdY1HjrWL905hBBCiJuItLgTYhsMp2MSNAshhBA3MclECyGEEEII0aF1BdGe5/H444/zwAMP8MADD/DFL36RMAxv+JrZ2VkefPBBzp49u+jxF154gV/7tV/j5MmTvP/97+crX/nKmtsSQgghhBCim6yrnOPLX/4yzzzzDF/5yleoVqt89rOfJZ1O8/GPf3zF58/MzPCJT3yCQqGw6PGrV6/yT//pP+VXf/VX+cIXvsDZs2f53Oc+h2VZfPSjH938pxFCCCGEEGIHrJmJdhyHb37zm3zuc5/jnnvu4cEHH+Sxxx7j61//OlEULXv+M888w4c+9CE8z1v2b0899RQDAwN89rOf5dChQ7zvfe/j13/91/mLv/iLrfk0QgghhBBC7IA1M9Gvvvoq9Xqd++67r/3YfffdRz6fZ3x8nP379y96/ve//30+8pGP8Mu//Mt84AMfWPRv73vf+7j33nsXPaYoCuWyrOQmhBBCCCH2jjWD6KmpKZLJJIlEov1YLpdr/9vSIPrzn/88AOPj48u2tX///kXPr9Vq/Pt//+9517vetbHRCyGEEEIIsQvWDKLr9TqWZS16zDSbK6+57saXMfY8j8cee4xarcZv/uZvdvz6vr7kht97o3I5WSyj28gx6T5yTLqTHJfuI8ek+8gx6U7delzWDKJjsdiyYLn137HYxvrgNhoNPv3pT/OTn/yEP/7jP2ZwcLDjbRQKFcJweU32dsnlUuTzUnbSTeSYdB85Jt1Jjkv3kWPSfeSYdKfdPC6qqtwwabvmxMJ9+/ZRLpep1+vtx/L5PMCGgt9KpcLHPvYxTp06xR//8R9zzz33dLwNIYQQQgghdtOaQfSJEyewbZtTp061H3v++ecZGBhgZGSkozcLgoD//r//7zl37hx/8id/IgG0EEIIIYTYk9ZVzvHII4/w+OOP88QTT+A4Dl/60pf49V//dQDm5ubQNI1Uau16lT/7sz/jRz/6Ef/7//6/09fX185oa5pGb2/v5j6JEEIIIYQQO2Rdi6185jOfwXEcHn30USzL4pFHHuFjH/sYAJ/61KcYGRnhiSeeWHM7Tz31FFEU8clPfnLR4/39/TzzzDMbGL4QQgghhBA7T4lWWjFlD5CJhUKOSfeRY9Kd5Lh0Hzkm3UeOSXfa0xMLhRBCCCGEEItJEC2EEEIIIUSHJIgWQgghhBCiQxJECyGEEEII0SEJooUQQgghhOiQBNFCCCGEEEJ0SIJoIYQQQgghOiRBtBBCCCGEEB2SIFoIIYQQQogOSRAthBBCCCFEh/TdHoAQQojtM1Fq8HdXK5ybLNIXNzk5lGI4HdvtYQkhxJ4nmWghhLhJTZQaPHVmmprrk0ua1P2Ap85MM1Fq7PbQhBBiz5MgWgghblJjk2XSlk46ZqAqCilLJ23pjE2Wd3toQgix50kQLYQQN6lCzSVhaoseS5gahZq7SyMSQoibhwTRQghxk+qLm1TdYNFjVTegL27u0oiEEOLmIUG0EELcpE4OpSg5PqWGRxhFlB2fkuNzcii120MTQog9T4JoIYS4SQ2nYzx0rJ+4qZOvuNi6xkPH+qU7hxBCbAFpcSeEEDex4XSMe46myO9L7vZQhBDipiKZaCGEEEIIITokQbQQQgghhBAdkiBaCCGEEEKIDkkQLYQQQgghRIckiBZCCCGEEKJDEkQLIYQQQgjRIQmihRBCCCGE6JAE0UIIIYQQQnRIgmghhBBCCCE6JEG0EEIIIYQQHZIgWgghhBBCiA5JEC2EEEIIIUSHJIgWQgghhBCiQxJECyGEEEII0SEJooUQQgghhOiQBNFCCCGEEEJ0SIJoIYQQQgghOiRBtBBCCCGEEB2SIFoIIYQQQogOSRAthBBCCCFEh/TdHoDYmIlSg7HJMoWaS1/c5ORQiuF0bLeHJYQQQghxS5BM9B40UWrw1Jlp6n5ALmlS9wOeOjPNRKmx20MTQgghhLglSBC9B41NlklbOilLR1UUUpZO2tIZmyzv9tCEEEIIIW4JUs6xBxVqLrmkueixhKmRr7i7NCIhdpaUMwkhhNhtEkTvQX1xk6obkLKuH76qG9AXN2/wKiFuDq1yprSlk0s2fwtPnZnmoWP9XRNIS5AvhBA3Pynn2INODqUoOT5lxyeMIsqOT8nxOTmU2u2hCbHtur2cSeYsCCHErUGC6D1oOB3joWP92HqzhMPWta7KwgmxnQo1l4SpLXosYWoUat1RztTtQb4QQoitIeUce9RwOiZBs7gldXs5k8xZEEKIW4NkooUQe0q3lzO1gvyFuinIF0IIsTUkiBZC7CndXs7U7UG+EEKIrSHlHEKIPaeby5laQf7YZJl8pdmd48H92a4drxBCiI2RIFoIIbZYNwf5QgghtoaUcwghhBBCCNEhCaKFEEIIIYTokJRzCCFuOrJioBBCiO22rky053k8/vjjPPDAAzzwwAN88YtfJAzDG75mdnaWBx98kLNnzy56/OrVq3z84x/n5MmTvP/97+cv//IvNz76W8REqcGTp/N8fewKT57Oy8pnQtyArBgohBBiJ6wriP7yl7/MM888w1e+8hX+4A/+gD//8z/nq1/96qrPn5mZ4eMf/ziFQmHZv/3mb/4mpmnyH/7Df+DRRx/lc5/7HC+88MLGP8FNTgICITojKwYKIYTYCWsG0Y7j8M1vfpPPfe5z3HPPPTz44IM89thjfP3rXyeKomXPf+aZZ/jQhz6E53nL/u25557j9OnT/M//8//MsWPH+PCHP8wHP/hB/uRP/mRrPs1NSAICITrT7cuCCyGEuDmsGUS/+uqr1Ot17rvvvvZj9913H/l8nvHx8WXP//73v89HPvIR/rf/7X9b9m9jY2McP36cdDq9aFs//elPNzj8m58EBEJ0RlYMFEIIsRPWnFg4NTVFMpkkkUi0H8vlcu1/279//6Lnf/7znwdYMcCemppiYGBg0WP9/f1MTU11PvJbRCsgSFnXD5UEBEKs7uRQiqfOTAPNC86qG1ByfB7cn93dgQkhhLiprBlE1+t1LMta9JhpNgM41+0sG7ratoIgwPd9dH39zUL6+pIdvfdWyOV2ftne9xsaf/nyFIqpk7R0Ko5PFML77xokl43v+Hi6zW4cE3Fju31McrkUfX0JnrtcJF9x2Ndn88H9GUZv8d/Lbh8XsZwck+4jx6Q7detxWTNqjcViy4Ll1n/HYp21jIrFYszNzS3blmEYHQXQAIVChTBcXpO9XXK5FPn8ztchW8A79yUZmyxzplClL27yzqEUlhfsyni6qXXYbh2TndRN+3s9uuWYWMC79iWB+YvtXfq9dItuOS7iOjkm3UeOSXfazeOiqsoNk7ZrRq779u2jXC5Tr9exbRuAfD4PwODgYEeD2bdvHy+99NKix/L5/LISD7FYtywh3OoUkrZ0cslmmclTZ6Z56Fh/V4zvZiP7W4jtt9cuVIUQ3WPNiYUnTpzAtm1OnTrVfuz5559nYGCAkZGRjt7s3nvv5fTp01QqlfZjp06d4uTJkx1tR+wO6RSys2R/C7G9pIWoEGIz1gyiY7EYjzzyCI8//jgvvPACzz77LF/60pf46Ec/CsDc3Bzl8vpO6vfddx9Hjhzht3/7t3n99df51re+xV//9V/zj/7RP9rcpxA7QjqF7KxbeX/LAkNiJ8iFqhBiM9ZViPyZz3wGx3F49NFHsSyLRx55hI997GMAfOpTn2JkZIQnnnhize2oqsq/+Tf/hn/xL/4FjzzyCIODg3zhC1/g3nvv3dSHEDtDOoXsrFt1f0sZi9gphZpLLrn495QwNfKVm/9CVQixeUq00oope8CtMrGwmywMbha2Dtut4OZmPybdtr/XYyuOyZOn89T9xRcPZcfH1jUePp7b7BBvSTf7b2WjdvO7Jsek+8gx6U7dPLFwXct+CwHNCY4PHevH1puZGlvXujqg2+tu1f19K5exiJ11cihFyfEpOz5hFFF2fEqOz8mh7mynJYToLp31lRO3vG7pFLJdum2m/s2+v1dyq5axiJ3XulAdmyyTrzR/8w/uz95yvzkhxMZIEC3EPKnF3VobvSDZyhUHu+2iSHSfW/FCVQixNaScQ4h5MlN/62ymddhWlbFI+7L1k24oQgjROclECzFPZupvnYUXJED7f8cmy+sKhrciO7jZMdwq5A6MEEJsjGSihZjXqsVdSGpxN6YbJgd2wxj2ArkDI4QQGyOZ6C0gdZc3h62sxb3VdcPkwG4Yw14gd2CEEGJjJBO9SVJ3efPYay3lurmOtRtah3XDGPYCuQMjhBAbI5noTZK6y5vL0lrcVqDabXcZur2OtRtah3XDGPYCuQMjhBAbI0H0Jsmt0JtXNweqe+HirRtah3XDGLqdXGwIIcTGSBC9STtddyn11zunmwNVuXgTW0kuNoQQonNSE71JO1l3KfXXO6ubuztIHasQQgixuySI3qTNTkbrZHKYtKLaWd0cqMqkOSGEEGJ3STnHFtjordBOa27lFv7O6uYJV1LHKoQQQuwuCaJ3Uac1t9L3dmd1e6AqdaxCCCHE7pEgepdMlBr87fkCqAoZS+dwj01f3LxhZrmbM6M3KwlUhRBCCLESqYneBa0yDlPTiGkKrh8yNtHsuHGjzPJeWwxECCGEEOJmJZnoXdAq47hrMMkLkyXihkLMUHnlWoUjvfEbZpYlMyqEEEIIsfskE70LWq3TeuMGbxlKY6oarhfg+JFkloUQQggh9gDJRO+ChRMEe+MGvXGDsuNj65oE0EIIIYQQe4BkoneB9PgVQgghhNjbJIjeBTJBUAghhBBib5Nyjh0yUWowNtnswNEXNzk5lOLh47ndHpYQQgghhNgACaJ3wGorE54cTDFRcRcF1pKNFkIIIYTofhJE74CVViacrXt846UJTvQnmSq7vDBR4ulzM3zkzfs4OZLZ5RGLm8VKd0DkQk3sFfL9FUJ0Mwmid0Ch5pJLLl5AZarsUnICXi/UiBsqAymLubrLN16aYDBlyYniFrGdQcJqd0A2Un8vwYzYaVv5/RVCiO0gEwt3QKul3ULTNRffj4gbKrauoQI9MYMgaGauxc2vFSTU/YBc0qTuN4OEiVJjS7a/8A6IqiikLJ20pXf8/drucQqxkq36/gohxHaRTPQOODmU4qkz0wAkTI2qG6CpKroKlq61n9fwQ/oTJoWau+q2JCN481ipzKf1+FYc05XugCTMZkeYG1n6HZupuds6TiFWstHvrxBC7BTJRO+AlVrafeTN+0jHTObqLlEUUfcCal7IYNKgL26uuB3JCN5cWitXLpQwtRteRHVipTsgVTdY9fsFK3/Hnrk0h+Mv3s5WjlOIlWzk+yuEEDtJMtE7ZDgdWzFr942XJpiquPQnTG7PWGiquuqiK9uduRQ7a+HKlS1bGSSsdAek5Pg8uD+76mtW+o71x01ezVd5d8LalnEKsZKNfH+FEGInSSZ6F50cyfDYg4f5wLF+DmRiDKfsG06a2e7MpdhZ271y5UYW9VnpO3bHQIJ81ZMVNsWOkkWphBDdTjLRu2y1DPVKtjtzKXZWK0gYmyyTrzTrjx/cn93SIKGT7xes/B2zdJV3H+xpBzPbMU4hVtLp91cIIXaSBNF7iNze3LtWmxDabUHCat8xyQAKIYQQi0k5xx4itzf3pr00IVS+Y0IIIcT6SCZ6j+m2zKVY216bECrfMSGEEGJtkokWYpvJhFAhhBDi5iNBtBDbTPrdCiGEEDcfCaKF2Gbb3cpOCCGEEDtPaqKFmLddS6rvRCs7IYQQQuwsCaLFtpsoNXj63Aw/u1pGIeLuwRTvO9rXVUFkq4NG2tLJJU3Gi3WePj/NwUyco73xTQfUMllPCCFubduVqBG7R4Josa0mSg2+9fOrnJut0xPTiFB5bqJIvuby4buHuuYPyMIOGoWay08nK0xXXa7MNbhWcXm9UOVX37Rv18crf4SFEGLvWZqoqbrNVqfSQnRvkyBabKuxyTKFqkevrWPrzQ4VKjBT97qqxVuh5pJLNif6vXS1wmTFIWlqeGGEpsG52TpPn5vhI/cO79oY5Y/w3iUXP0LsLVv9m91rrU7F+sjEQrGtCjUXLwiw9Ost3mK6ihtGXdXibWEHjQtzdZKmigLEDQ1b1+iJafzsannZ6yZKDZ48nefrY1d48nR+yxdQWbj9r566QhBGpCwdVVFIWTppS2dscvm4RPfYS4vtCCG25zcrrU5vThJEi23VFzcxNA3Hv97ireGHmKrSVS3eFnbQiMIQN4hw/IjBRHOMEQoK0aLXbHdwtHT7MzWX09NVZmpe+znyR7j7LcxAycWPEN1vO36z0ur05iTlHDe53b6NfHIoxeuF6nxNdESEQrHhcShrt1u87fYYYXEHjd64ydWKw6Eem5SpUfcCig2P+4czi16z3bfnlm4/lzQpNjzOzdTpjRuA/BHeCxaWCrUkzOay6pvRDb8bIW5G2/GbPTmU4qkz0+1tVd2AkuPz4P7sZoYqdplkojdgu2/hb5VuuI08nI7xq2/axwMjGepehOMF3D+caU8q3IoxbtXxGE7HePh4jv/PLx3lXQd7iBsas45PEEUcytq872jfoudv9+25pds/3GMTRAr5qiP9pveQ7chAdcNvW4ib1Xb8ZluJGltvBuO2rsl8lpuAZKI7tJcmd3XLRIbhdIyP3DvMR7ZhjNtxPIbTMT5899CaWb7WH9rWmGFrM8NLt98XNznRbzNZ9qTf9B7SykDN1j2myi7TNRdNVfnIm/dteJvd8tsW4ma0XVljaXV685EgukN76eS1XbeRt9Jmx7jVx2PpLfL336Cf9Xbfnltp+5qq8uhbR7ruuyZWN5yOcXIwxTdemiAIoD9hMpg0GJsqM5iyNnQs98JvW4i9ShbIEuslQXSHdurktRX1jtudKd0Kmx3jVh6PTrPa2/2HVv6Q3zwmKi7v2N+z6HtedvwNX+zthd+2EHuZZI3FekgQ3aGdOHltVYnCXpjIsNkxbuXx2EhWe7v/0Mof8pvDVl9874XfthBC3OxkYmGHFrZC267JXVvVXmcvTGTY7Bi38nhIH0+xXbZ6otJe+G0LIcTNTjLRHWiVWFScgPGiQ9bSONqX2PJb7FuZtVqYyWyN/7tnC1vaEmuzpSebybZuZcmD3CIX22U7Msdyl0IIIXaXBNHrND5Xa5dY3NYfb58Et6M363YEc9vVVaQbupWsN5hYK9iXW+Riu+yl+nbpPy2EEOsjQfQ6PXe5uGNdObYjmNuuriJ7pVvJeoL9vRToiL1nL2SOu+GiWAixmFzYdq911UR7nsfjjz/OAw88wAMPPMAXv/hFwjBc8bnlcpnHHnuMt771rbz73e/mj//4jxf9+9TUFL/5m7/Jfffdxy/8wi/wpS99iSAIVtxWN8lXnB2rl92OesftqvfdK3XE660zby248o9PjvDw8Zz8oRJdYycWeZIlyoXoLrKwUndbVyb6y1/+Ms888wxf+cpXqFarfPaznyWdTvPxj3982XM///nPc+3aNf70T/+UCxcu8Lu/+7sMDAzw8MMPA/Bbv/Vb9Pb28q1vfYupqSk+85nPkEqlVtxWN8klLa4WKjtWL7ta1mqjV6TbVe+7V+qI16ozlyt9sZM6/b7tVIZY+k8L0V32yt3eW9WamWjHcfjmN7/J5z73Oe655x4efPBBHnvsMb7+9a8TRdGi5165coXvfOc7/Mt/+S85ceIEDz30EB/72Mf42te+BkCxWGRsbIzf+I3f4OjRozz44IN88IMf5Nlnn92eT7eF7t+f6bgLxNiVIo//zVl+4y9f5vG/OcvYleKG33+i1OAbP53g9//mLM9enkVT6eiKdLu6imx3t5Ktyr7dqDuCXOmLnbSR79tOZYi3Y7ljIcTG7ZW7vbeqNYPoV199lXq9zn333dd+7L777iOfzzM+Pr7ouT/96U/JZrMcO3Zs0XNffvllPM8jFosRj8f5T//pP+G6LlevXuVv//Zvueuuu7bwI22P0Wy8oxKLsStF/o/nLlNxPUYzMSqux//x3OUNBdKtk+5r+SqDSQNNUfjpZAU3CNd9It2ulljb2WprK4PbGwX7cgtb7KSNfN8WnkgLNZfnrxT5yZUif3u+sKUXezvRwlMIsX5yYdvd1iznmJqaIplMkkgk2o/lcrn2v+3fv3/RcwcGBha9PpfL4fs+09PTDA0N8fu///v8/u//Pv/+3/97giDgHe94B7/1W7+1VZ9nW3UyMeivXp/G1BQKdZ/xkoNtaMQ0hb96fZqTI5mO3rd10vXDEBWYqroUGx7TdZf3H+ml5t64pryTpazXu42Ft5+3a8LUVt7GutGkwe+eLcgt7F0wdqXIX70+zWS5wVAqxgdv7+/4t7EXbaRkonUidYOQsYkycUMlpimEirqlZR0yuVaI7iJdo7rbmkF0vV7HsqxFj5lm8wTgum7Hzz179iwPPPAAn/jEJ5ienuZf/st/yf/6v/6vfP7zn+9o4H19yY6evxVyufVnY65UXap+iK3r9FoGjh9S9H38qtvRdgDcMwWGszb2TJ3XpiokLZ3BtM5s3edn+ToPHu5ZdZvjczWeuVohYxscy9pUHJ9nrlb4r/oSjGbj63r/9W5jfK7Gc5eL5CsOuaTF/fsz636PG31uVVHaj6WiiKmy0/68nezLXC7FPUdzyx4/MpSh5vqkY0b7sVLD40jK7vhYifUdk+cuzvBHL12lN25wfCjNbN3jj166ymM9ce4/2LsDo9w9G/m+vd/Q+MuXpzg/V6E3HUNRoOYGvP1AFlNTOVfzuefojff7er/Lq/1OxNaTvy/dp9uOSS6Xoq8v0T637uuz+eAmz617Ubcdl5Y1g+hYLLYsWG79dywW6+i5P/rRj/iTP/kT/st/+S8kk80g2LIsPv7xj/OJT3yC/v7+dQ+8UKgQhtHaT9wiuVyKfH79t/cbjk/d9bBtBWe++0i94aGFdLQdADMImZiu0Kh7uF6Aq0Y0HNCJqDselbKz6ja/ezqP4gdEKpRdHwDF8/nuz6/y8PH1nSjXs42xK0W+8eJVgjCkP24ymDJ5fWJuUxmy1udeOGmx7PjN0pF8ueNjspojcZ2nJuZIW/qiK/2HjvVvyfb3iq2YXLneY/L1H1/CViJsoFH3sAFbifj6jy9xKG6s9fI9bSPfNwt4574kPzlXQCUiHTO5o9fGCEICP+BcoUp+3+qJha36rYitI8ek+3TrMbGAd+1LAvO/cS/oynFul908Lqqq3DBpu2ZN9L59+yiXy9Tr9fZj+XwegMHBwWXPbf1by7Vr1zAMg56eHl566SX279/fDqAB3vSmNxEEARMTE+v7RF1q6QS4fQkDJ4CK16wtrHg+TgC39dodb/vkUIrLxQanp6sEYchkySFfdRlOxXj7aIYwWv1iYismJay1jYlSg2+8NIGmRgykLLwo5PVCjSCMNlVXvFP1mbKE8s63UZosN8jEFgfLmZjBudnatrdx220b/b4Np2P80uFe7t+f5b7RNL3zFxtSHynEzWkn2lqKzVkzE33ixAls2+bUqVO8613vAuD5559nYGCAkZGRRc+99957KRQKnD9/nsOHDwNw6tQp3vSmN2GaJoODg4yPj9NoNNpZ7DNnzgAwOjq6pR9sJ63UfsqPFN6yL8Hlkkeh5tJjm7z1UJw7NnhLIooibEPF8SP2JTWSls49Q2kMTcHWtVVftxUt6NbaxthkmSCA/qSBAu3xTJVdLG1drchXtJP1mXthIYzttNNtlIZSMYoNj177+vdwouRQdf12IH8zL/Sx0e+b1EcKcWuQhY/2hjUjnFgsxiOPPMLjjz/OCy+8wLPPPsuXvvQlPvrRjwIwNzdHudzMNo6MjPCe97yH3/md3+GVV17h29/+Nv/u3/279nPf+973kkwm+cxnPsOZM2d4/vnn+b3f+z3+2//2v6W3d+/WQa402/5ELk7VD3n4eD+feNt+Hj7eT+/8LfKNbP9A1ubh4zkO99gc7onTHzd4eaqyLDO79Mp1OGkuyuZemqvx7OVZzs7U1n1lu1ZGuFBz6U+YNPzrC/BYusb0fFnAZsjiJztjp9soffD2fmbrPjN1lyCKmKm7XJxr8MBoWrqk3IDcNRHi1iBdo/aGdS228pnPfAbHcXj00UexLItHHnmEj33sYwB86lOfYmRkhCeeeAKAJ554gt/7vd/j137t18hkMnz605/mV37lVwBIJpN87Wtf4wtf+AK/9mu/Rjwe56GHHuKf/bN/tk0fb+utVDe60mz70UyMuhe2T3abyaK2tp9SdE4Opzg/W6fo+BCGi06gK125jk2VOTmYYqLi8ka+ysWiw4lcktFMbN1XtmtlhPviJk4Q8Pp0s+QnpqvMNTw0VZXWWHvETi+ac3IkwydpdrEZLza7c7x9JMVdg+lFz9vOLil7dYGdW/2uiRC3Aln4aG9QoqUrpuwRuzGx8Gdn8+0gdeGtVFNVqfs+16oeJccnbekMJAyGU/a6J+/dyJOn89T9YMUJdgu3v9bz1rudTrWC9yAMmap4TFddNA0+cvfwtrYs69ZJIHvRwguwpZPdOgnYNnNMtuv7uZLNfN69GHzLb6X7yDHpPt10THby72G36+aJhevKRIumsckyQRhxOl+j7HikLIOBpMFsw+XFaxV6bJ1MzKDY8LgwW+eT929NALneOsi1rly368p2Yaba0jRODqU3FFjsxeDkZrFb/YEXHnNVUbhWdTiQtbe93nejNeC3ap2i/DaF2Fky/2FvkCC6A2dnalwq1kmYGmnbwPEDTk+71NyQt41muFbxKDc8MpbJbX0JJiouJ7fgfdcb4Kx1S347b9mv9xbzaifjWzU4WctOBi87XSaw0jFXFIW6G1Cb/15uVyC/0QvKnZ6A2Q3ktynEzpOFj/YGCaI7MNfwUZXr3SdsXaPuBUzXXUYzMQ5kr7evC6NoS2uX1hPgrHXluttXtjc6Gd+KwclabvbgZaVjvj8T25HblRu9oLwV6xTlt9n95E7BzUnmP3Q/CaI7kLU0io5P3QuI6SoNPySIFPptY0cnZa1mrSvX3biyXfjH/cJcg6GUseLJeLXg5I3pZheRrTo5LD3ZDCdNJiruura/0yeqvRy8rGdf7WZAutELyp2egNkNbsULh73kZr/YFqKbSRDdgaN9CWxT5VrVY25+AuGJjEVM0yg5zZX81ntC3q6AbK0r1528sl36x/2FiRJFxydh6u2go3UyXik4GS82uFisMZy2tuTksHQ848UGf/7qFG8bTTOasW+4/d04UW1V8LKV37X1bGu9+2o3A9KNXlDu9t2c3dDpcZKs6M7ayxfbQux1G18J4xZ0ciiFpqoc70/wS4d7Od6fQFNV3ne0r6PerTu9OtxuWdrnMpew0JSI87PXV79snYxX6kX9Wr7Gif7ElvXJXDqeaxWPHlvnWtVDVRTcIOTcTI0/+OHFZT20v3e2wLmZGs9dKfLCRAk3CLe9Z2creFmo0yBzK79r693Wevub7tSKlKvZSA/yvdyneaOrn3VynG6Vv23dZKd7vAshrpNMdAfWUy6xHt2aOdhoBmm11y3NpB7ptTk14ZKvuIRRtCiLt9K+PZixGM0sXiZ9M7eRl46n7HhkYgYlx6dQcxmbKBMzVFTC9sn/oWP9ADxzaY5c0iRraTT8kLGJMvcOJaktCHK3OgO3FVnPrfquTZQafPXUFWbm9+HhHnvRipULt7XeDPpenTizF+sUx+dqG76T0slx6ta/bTezW7HESIhuIUF0h7biBLrVt+nPztSYa/hkLY2jfYkN1fWu5xZ8+/0KVeacgGxMpyemM1332J+JLXvd0j/uvXGD4/0JJsvuqhchC8f95Gm29OSwdDwpy6DYcMnEDM7P1okbKiiQjpmLTv4A/XETVQFFUbCNZtbn1XyVd+zvae+brS732Iogcyu+a63P1gqg3fmLiJPDKXpsY9m2Ojmp78WAdC967nJxU8Hteo+T1E/vvFuxxEiIbiFB9C7YiszB9QVOIi4V66gKFB0f21SZqjod1/WulUFauKDKxZKDpkSUHI9zsxFBBPuSVvvWfet1K/1x11SFR986sq4T8lafHJZubyBpcGGuxm19cd6YqRPTFOpexImhZPs5rZP/HQMJfnq1GVBbukZERL7qtW9pb1cGbqXgpZOM91Z811qfLZewcIOgfRFxfraOqanLtrVdJ3Wptd24fMVZ8Zb/Vge3khXdeXv1jo4QNwOpid4FK9UYXpqrM1v31l2v2ApsrlU8EqZGr22SNJqTHler1b1RrepadXXt96t6JA2VXtskYWpMVVx6YhrnZurLXrfZ+tGtrj9dur3hVIxP3r+f4ZQNYUQYKrxlKE1v3ACun/z74iaWrvKWoTSmqlGqe4ShwrsP9rTHspV1iTeqXe205nQr6o5bn+1Ir03Na5a6mLpKvuKuuK3tqBuWWtvNySWtTdfXr8du17nfqjZS3y+E2DzJRO+CpZkDhWaZQMxQSZga48UGT5+b4WDGapdnAIuycGdnatzWH6fseKTtZtAX01XmHH/VDNONbrWulUFqvbbk+GTnn2PpGlEUEaFQdrwVX7fZ2/Vbfbt/pe2d5Hr21NCUZfXaQDuD/5aRVPvf3nukt72NrcrArVUW0mnGeyuyVK3P1hs3eMtQmnMzdfIVh964uWpwvNXHTWptN+f+/Rn+dGIOAMcPefValemayzsPZJkoNbZsH0pWVAhxK5EgepcsDDKePJ3HNjVSls5MzeP1Qg1NjSi5AXU/4Fs/v0oURRzI2u3A6mKxhm2opKzmyom23pzwlrb0VYO3GwV6a92Cb702bek0/BDb0HD8gENZm2LDI20aKwafe8VaJ/+1AoOtKmFYK1jspOZ0afnD+4/2bSiYWfjZsrbO8VycofTqAfR2kFrbzRnNxnnoWD9Pn5vhBxdnySUM3n0oi6VrW96qUerchRC3CgmiN2nhZLvxkkPF9UmaGncPpnjfOoOWhQHCuZnmBLeYpnKl7KAo8MKVMjFDYV/KIqU0A6wT/Qley9cYSpr87GoV1w8xNZW37U+vGrwtDfTGi3Vem65yMBNv/vtgionK9Ul/R7M2Y5Nlvnu20GwJV3UYSBi8Nl2n7geEERzvT1B2fAYS1qoB5mZrWXeqFvZGJ//19N9eGGirioKhKHz3bKGjMa8VLPbFm/2tr1U8yo5HyjIYSBoMp7avr3U3ZBe3ah7BrVxTPZyO0WMbfOBY36L9CJLRF0KIjZAgehMWTrZ7tVDjSrGBrsKhHpvnJorkay4fvntozYByYYDQKs/IVx2uVVz6bANTjWgEUbsjQl/cZDRjM1VymKw2yNg6fhChKzBZcXjf4ZWD94XB0Bv5KheLDidySUYzMapuwNhUuR1krRSEKYpCTNM4mLba3TmGUzFO3n7jbiA3CubWCmxu9PpcrrvqLFuB9sIxt7LS6w1g1woWh5Mmf/7qFD22TibW7C5yYa7GJ+9PL9rOVpc/7PQiPUu/E5vN9Muqbk2S0RdCdJMo9MCrEgXV5v/6VfBrRH6VyK+BX6U47uM1VPSDH0Ixkrs95EUkiN6EVqByerpKxfGxDZViw+Olqcp8t4rGoqBltRP5ycEUY1PNiYBJU2eu7nKl5LA/bWEbGrqmoSsQN1TOz9bbgVaoqLxjf8+igKvs+ExUXE4uGevSwKQ3bjKcia0aZK0UhO3PxLB1jX90cmTZdlfLuN4omAPWDGxu9Pp7juY2eQS3x2YC2LWCxYmKy9tG01yrepQcn0zM4La++LJjvleDpRsFu+vJhq92USY11U3SPUMIsRFR4LaDW/zqfJA7H/B6VQhqRF6l+W+ht/YGOxBGJmHNJapfRTGObem2N0uC6E1YONmu4niUvBBDUYAIhYizs3WOFKpAM9hb7UQ+UXGvt5mL6cw6LmlTozfR7EKQiukQRUREFOdnvpccn2xMX1fbqpUCkx9cnOUXDvWQsha/9o3pGk+ezvPXp68xkopxtC/e7laxdNvrye7dKJhbT2Cz0WBwN2/dbyaAHU7HODmY4q9en2ay3CBlahzI2O2LlLOFKrflEhzIxtuvCaNoU72au8mNvhNrdR240fdxpWPi+CE/vlxc1Pf8aG/8pi7zkJ7CQtzcmsFuK4tbIWoFvt71zG47EN7iYHcjFFUHPYmix0FPXP9fo/X/k6T3DeLNhSiatfYGd5gE0ZuwcLJd1QtRAUUBS1MBhbiuMOdcbyt1o+Bq4e3y1upw+YpLLmHx7oPN2xcvT1UgDLF1jQf3ZxmbLK8rUFopMMklDF69VuXdh68/d7zY4GKxxnDaYiQdo+R4vDBZard9q7oBCs2JkIWay4W5BkMp84ZB8I2CufUEm6u9XgH+75cmOTdZXBYkb8et+53qzTxRajA2VebOgQRHe2P8eLzI6Zkabx/NUPcDLhYdbFNdFESvtO2tDJZ28oJkMxcgNwrAlx6TmZrHj8aLaESL+p7bxup91m8G3VDfLoRYGOwuzOzWlpU0dF+wmwA9fv1/jcT8/1/wv9rWJmu0WApFW962txtIEL0JrUDF0hRKTkDF8TA1tVlj7AUMJAyyseu7eL3B1XA6xqNvHVlWV3ukz152cl9PoLQwMCnUXM7PNntSXy46HOyJtWuiX8vXOJFLkLJ0jvTajE34KErE2UINQ0twaa7eXLHP1MglTX5waZafT5UYSMYYSloc6bXJ2vqigOdGwdx6LgJWen1rHIOuvyVt4NbSaVC+mQB24dhPT1fpiRmgwIXZBveNpjmRi/PadIWe+T7dq217q4Klna4l3swFyI0C8Pcf7Vt0TF6eqqAQETM0LE3FNjTqfsC1isfxXPymLvOQ7hlCrE8URRAuLGOYz+x6S4LcVtY39Hd7yCiqsSCgnQ9257O6zccWZH23ONi9FUkQvQmtW+/feGmCPlsnpiv4AczWPO4ZSnHPUHpR14ROgqv1BEHrDZRagYkbNJdrjhsqfXEDQ1F5bbpC3Qs52hvnYMZiNGO3X3NyOMW5mTpXSg1ODqcZSFjEDJWUpVOouRTrPkEUUXcD3DDghckSt/fFF33mtca40v44mrXb2e6+uLmsa0hrHOmYQdH1N9UGbj22ujfzjTK7C8c+WXaoeQF1P4Qw4kivzWgmRt0L2wuZ3Cg47jRYWmlcO11LvJkLkBvdtRibLFNxAsaLDllLww0CHhjN8OJUhZjeXHPK0psL6eyF2nEhxHXXg90FAe2i8oWlZQwrB7uzcRNnAwtkbcTiYHe+dGE+q9sqY2gHwhLsdi0JojdpouLyjv09vHU40w5QI5qr32mqsmilrk6zg+sJgtbznFZgcm6mRsxQQYG6F/HAgSyGpmDrGg8fz/HkaRYFIX1xE1NTOTmU5uHjOb4+dgXHDzmdL/HSVIkwighCKDoexzSbutfMZj98++IJf6uNcaX9cTRrMzZVXpT5XNg1BJgfR8CzF2a4Olcjbekcysaoza/IttX1wBsJylf7zGtldhde8FyruGgqGJpKhNK+SDnaG+fh41s7qXK1cVUaPrflEh199s3YTAb9RnctbFPjtv54Oyi/205h6dqyvucpy9gTteNC7EWLgl2vCkF1PthdmNlt1fBWiKJg7Y1us3awayRBa5YvtDK8i8sYJNi9FUkQvUmtACul6JwcTnF+tk7R8SEMV7zlvRXZwY32+f2DH15EJSQdMzkxlKQ3biyalLZWFlBVFJ4+V8ALQibKDjFdJQwj0jGdF6cqRGFIb4fBx9L98eTp/JqZTwX48XiR4Z4k2fkg6MfjRe4fzqzrc6xmtX296RrnBducqbnLPt9s3eWrp65wKBtr9+OeqXuMpC0uFRs4QcCJvgR+FK54kbKez7CW1TLO40VnxycobrTcoPU9f/rcDD++XEQhAuC2/sSyz9XwQkqOv6zv+Wh/TCbaiVteM9h12p0XFtbtLs7s1roo2DXna3ST7czuspIG7cbBbk8uhZ/vztpb0Z0kiN6khQFWX9ykL25SdnxsXdv07e6tXjDjlw73MlFuLtTxs8nSsoU61soCztZcJsoO2ZhOytSo+SEVN0DX4O59KcKo+cd3o2OcKDX4/vkZVCLSMZMjvTa9cWNZ5lNRFCIUUCIiRQGl2Q9FUZR1fY5O9/VmgvKl23zm0hzvPpRtB3OFmstr03WCIOT+0XS7H/dMzSNlatzWG0dRFAIi0pZB2lz9ezV2pcg3XpogCKA/YeIEwbonya2Wbc/GdEqO3/7v8WKD1/I1DmYsnjxNV3aycMOQB/ZnSJga3359mtPTVZKmvqjLTM0N2t+Ruhsu7nvehZ9J3NpWuzhuB7vzpQsL63avZ3tbNbzV7gl2jcVlDMtLGpLNYFc1dnu4QtyQBNGbNJw0FwUug0kDTVW3JJO1UnZwYday08z0ehbqWNifuVBz2/2ch9MxLpca3JFLUHQCGn5II4iIaSoNL4Komd07OZzC1NQ1a2aXnhSGkyZjU2UsXUFR1HaN9VuG0hiasijzGUYRbx/NcM0NmSo1SFkGbx9NEITRos/RSSC0dF97QcS5Qp1/de0Cv3i4b1ld9npKDFY6fv1xk1fzVd6daLbqOT9bR1MiehMWqqK0+3GXnYChlNlemTC9ysqEC/fnN168iqYq9CcNGn7I69N1bu+3VzwWS/e/qihU3aD5uWfqlB0PXVU5kUvw3iO9zQV6pmtcLDYnn45m7K5csGTpPs8lTYoNj3Mz9XYQ3cqkX/+OdGe/cXHziKIIgsaiRSQafoQ/fe16n92FGd4FwW7F8bk8U2NEUzmkKXiFiMsXQqzeOElr+07hy4Pdxe3HmhleCXbFrU2C6E1otSMbSsT4+bUKbxSq2IbOx986vCVBxdLs4EpZy06CmImKy/F+m5fzNV6frtETN7grt3ihjhtlZCMUkqbKQMKC3jglx+eZi7MEgKmrDCTNBeUs0aoB/krv8Y0Xr3IiZ3PnQLJdW27rCi9PVTjSZy+6KOmLN/tnv2MoQ7Gnuf2y49PwwsUTEju4wFi4r2dqzdZ+tq5ApFD3l9dld7rNljsGEvyXC7OUHb+dYdc1hSO9dvs5CVNDI+In48U1VyZsGZssE4QhfQkLBbCNZv/wqYqHpS3uJb7S/r9WdSg7AdN1j56YhqE3Fw66VnUA5mvm8wynra5esGTpPj/cY3NqwidfdQijSPoiixu6HuwuzOxWV+izuzzY7VQ9bhKsYxLbZNnB0lTM+Qmwpq60H7/N0pu9c9s1usll7ccW1exKsCvElpIgehOagUvEVM3lYE+M23MJ5uou3z5X4E370psOLJbW4q6UtWyNYz3vdbZQZbLicyAd4/beOA0/ZLLiY6prLwgzNlnmnn0pfnyliKIoWHpzIlaEQsbSKDs+V0oOubhBTFMIFXXVAH+l9wjCkKmKx/2j8TVry1vlFaWG1w6MLhcbRFFEzFBXLX25Ub3wwn19bqZO3FAhgoylbThYXKmW2tJV3n2wp91dozduMpQy21lSaGZKA5R1rUzYUqi59MdNHD/A1ptBc0xXmaq4nBxae0nwA1mbH18ukrE0nCAibWncsT+76K7CXlgFcek+74ubnOi3mSx70hf5JrI42F28sMTyPru17ihj0KwF5QtJrL4+nKrabj/GwiBYvf4344WxK+SSzbtFLa25LG9688hKbyWE2CESRG9CoeYyVXbns6bNwKUnZjA1vxrfZk/UrWBxtu4yVfH40aU5bFPlPYdtZmrNW9SlhkuIsq6s65wToClRO0vZ6o17owVhZmoeZws1rpQbPLg/S79t4AURVyp1Jiouo2mLTEzj/GwNNwBbV1BVlbcMpTA0ZcX9sFIw1h83ma667T7WJcfHVBWO55IrTs586Fg/52o+5wpV+uIm/baBbWorBv8AT5+b4QcXZ8klDO7IJaj7i4PshXXPpYaLaWg0vJDj850pNhIsrlZLvTSwf+rMdDsz3XpO1tIYzdhrrkzY0hc3cYKQ1ws1oNmuba7hoWks6hCz2v5PmBoV1+e9RwdWPFm33mMzkwx3YtGWlfa5pqo8+tYRCZx3QTPYrV8vY1jQkWF5n90qURTu9pAXBLsrtx9bXMaw8VNoPJeiuo5JbHt19VEhbgUSRG9CX9zkBxdmCFBoeAFxQyNjafQnmqvxbVa7D/WLVwnCkP5Ec4GNl69ViaiQS5iYhrbuyXzNSWIedT9oZ5LDiFUXhGmVNShEjKRj80GqxkDC4oeXmhcP2ZhO2jK4WnbRFIWZesDfO5Zd1vlj6X4bL9bbWda0pRMzFBqBz48uz5GJGViawmyjWV4wUWqsGEjfczRFfl9zNcevj11ZcQn0N/JVpqoO5wp1EobKxbkGL01VuKM/wdG+eDvIHpssU2n4jBcdrtVcXD+ix9Z5cbKMoijUvYDeuLniWG50/Dba63u9q1G2nBxK8Xqhih+EvDZbxw9DcgmLT9w3umrf8KXbHkrFbviem+nhvFOLtsiKfBvTCnbbmVtvtW4MrcxuNwS7setlDCu0H1tcxrB3T3WyVLsQ3Wvv/mXpAoYS8fK1KtAMROt+wFQVfjFtblmWYKLi8o4DmXZQ+4OLs7yWrxKGIfuzNilL510Hs+uazHe0N45tqFyreJTqHinLYLQ/tuqCMGcLNRQioqhZs9u67d/wQsIIjvTGiesqDT/E1FWGUxaWprZLE8aLDSbLLl8fu7Io87h8gqPHbN3nUNam7kV4fvMEnTQ0Ls7W+eqpK2tmElcLDOecgOFMjDmnWRcbM1TSls7ZmSpnZ2voisLT5y1O9Ce4LZdgvFjndD4kZmqYutoMTEMYycQYShkdB36b6fXd6YkziiISpsbBXhtTVei1DQZT1rLnrXZS/uDt/YxNlVd9z80EqDu5aMvNvCLfomB3UY1uZYU+u1Wi+TZ/O7mIxFLNYHe+jGFRsLtkopq2t4Pd7SIXhkJ0L/mLtUETpQbfPlfgeC7OxTmHihfQCEIOZmNMVlz+329Orb2RFba59Hb3slvvUUQQhkTQ7IMbNU+S6yk3ODmUYqrqcDwXXxQkrbYgzJVyg5F0jCO9dvuiIGFq/Phykf64iao0283ZhsZI2uLCbJ07cynCKGK82OAn40XeNppelnmcqLi8bTTT7DzR8MhYJrf1JXh9usZ7j/YyV/d5YbJEXFdIWib5irtm8LpaYJiNXV82XVXAVFWqvs9U1SOXMJh1AvZnY7w+XSdh6lyreoxkYqgoTNVcVEUlG1PImBoHsnHKjr8o8NuuEoVOT5xjk2UOZG3uGrx+LJeOdT3bHkxZa2bO1/p86/oe03311FupGezWVqjRrSzor1slCmqLgt3d1A52l7QfW5TRNRKgJVBUbe0Nii1zM18YCrGXSRC9QWOTZYIAbu9LMJSKMVV1KdV9okjhYCbeUXu3VhC70u1uU1UXTXjLJU0OuDYKEXcOpMhXHP7z2QIZU1+z3GC9gdnCP9h1f6VllCPuGEjw06tlKo7PbCOg1PCouAH7ks2gd7Ls8rbRdLumd2HmsVBzGc3EOJC93pEijCLemK5SdYP2xD5b16h7AbmkSdrSb5i1XKssImGo1DwFNwiZrnmYmoKuaigEZG0TxwvatdiZmEG54TOQMLm9VydSFEp1D1gc+G13iUInJ85Og9QbrSK5mbGPz9XW/B63bLSucysvXKIobGZ2l9XoVq/32V2Y4e2KYNduB7TLyhZai0ro8UXBriwiIYQQW0+C6A0q1Fz6EyYNPyRt6aQtnRC4VnY42htf9XWrBV6mqq54u7s+n1GF6xPe0pZORES+6jBednC8kD7bIK6rfOmZixzMWPTYBoqiEEbR4lKKDoKk1bK7dw+msHSVw9kYf3t+liBq9oveP5Akbmm8/2gf//HnV5mqePzs6jWqXkBcVxlKxUibGkf7EisGVHcPpijNl13kkiZ1L6A2P7lvPVnLG5VFZGMGpgb5mk/J8TncYzOcMpmZX+45pqvMzddnF+ez4ygRDT8EBVKWQaHm8sq1Co4f8eTp/IqrD8LyEoWdmFDXLZOPnrtcXPN7vJG6zigKwa9xdW6WH5wdJ6O7HFEbeDMVXpqsYOQ0soZ7vS1ZF1A0e0mNbnJBZnfBRDUtLpldIYTYgySI3qBmN4SA16frQLOd2FzDoxFEzNSW1wG3rFYb+uPLRd57tLfddaPseCRNnXRM55G7BhmbLBOiEEUR7zyYRUHhO2cKOF5IT9zkaE+cc3N1NDXiSrnBz66VmSw6GJqCpqoMJC0+8dYRTo5k1v0ZV8vuQjMwnSg73J5LoCpQ88L2wihPn5vhYtGh4ftMVz1UFWpuAETM6gbvPtizYu3tQ8f6geZS0/lKM7N6PJdorwK5kYCwvRS02uzOcTAbYzhlEtFc5fBtIwnOzdWpe0FzQZOEwYXZOrf1JYgbKk+fKzBTD+iJ6TxzqQAoHO6J8+zlWS7N1vnl2/sXBa5Lg/2dmlDXLZOP8uUaGbWM2Sih+0V0v0SfP0e9OsMdGY+rU1XqXsB+Q2MoZZG8oON0sP3CdJXjYdTumQvg+iFTUwrp/sSGxnw92G2VLyRXWFRiY8Fu+wKquH0XUEIIIXaHBNEb1Kovvr3fZqriMVVxaQQh+xLNVmutQGZpwLTabXeFZh3x64UacUMlbRvM1V1mnWZA9vDxXDtQMjWVhNnsBNIXj/PW4Uy7BCKmqfxkvIQbBpS9gDgag7bGRKnBH54a5/dSVkcn8dWyuw8d6+cPfngRlRBFUdAVhZ9eLZEydSZKDU4Op/nu2QKqCglTp+r55Gs+HziaYaLi3rCs5NG3jrQDz4SpcWmuvqmlpofTMT5y73B75b2zhSoXiw4ncnFGMzF0TeG1fK25pHbK5pP3N8d4tlDFUDUOZQ3OF6oUGwE9tkHa0tAUhYob8tx4kV85PtB+r6XZ362aULdaCdCixzpYVTEKA/CKRO4ckTNL5Db/P+5s87HQX/fYFrq74lKpucuC3B5VIWUmSC0IdCuOzxvTzaDabgXVN1iBTdHjzEU6diJNVUsQqjaBFsdXbPKOwZ23HZkvY+iOzO5OXUAJIYTYHRJEb1A7w3luhmKjjqkpGJrOSMZetVfx2GSZl6YqWAWFOweS7WCrVcrw06sVNLW1lHZAFCmc6I+3A66lmeGFC3X8bLJE2jZoeAEl10dXIhKGRhBFWJpK1tbIV7wt7YaQsnQuz9W4VvMwNRVdgTCC2YbPOw9mySUs6m5AzW0uAJKwdeKGxvfPz7QDv/cf7VuxJvvkYIq/en2ac7M1qq7PHf1xrpQdvn2mQLHhcVtfnP/m3hHuzyU20Ckj1w5K8xWX4VSMh2/PLV7QBXjyNNimxrWKx/NXiiTnL46u1Txu641zqDfGG9P1ZT2eF2Z/NzuhLgoDrs5M8XdnztOjVrldqRDkZ3nxfAErKDJiXV8K2AlC3t5aCtgBLtBRlrel4vhMlp11B7cLDactXio3ADA0BSfUKCsZ7hgaQcvkUMwMitXDVcfm2xddUoNWe9/9xPF56NCNA8yilufqkjr9suNj2xqq3V3Ld+9kRxIhhBA7T4LoDizNBg4nTdww5IH9GRKmxrdfn+b0dJWk2axZbq26V2n4nJ6ucCBrc+9Qih+NF/nR5TkeGM1g6RqXiw36bYPpagNVUal7EftSzVKGHttYFHAtzAwvXKgjaerM1V2iSCFlqBTdAEuLsOYzglGkYKjhlvSvbr3vUMrg+QmP6YrbXvY7iCJ0NeK5KyWGkhZuGLQnCLpBxI/Gm6vi3Sgz11pO/c6BBCowWanz4ytlgjDAD0HXVc7N1vj26Wucm7L51Tft6zgoWU9t+NmZGpeKdRKmhqk3L0imax7zHfhImhoHsrHm6oPlOoNmg3ft88m5V/EnikTOLHdXxolm5ohp1yekuX7IflXBeXF95QeF6Sq3LylhKNfrOAqYiebkzKVLAXdKUXUUs4fZIMFzc2CkejFiPUyESZ7zbX750OCq+2vh7+LIQIZET8CVirsoaz6wdNXKiTypmNJxgNktZSvrcat1JFlqJ+YCCCHEbpIgep1W6jrwjZcmONGfbAcAuaRJseHxs8kSQcR8eYXCFSfgwlydfSmL/kTzNvvLUxV+NlnmzfvSRFGEbWrc1p+k5HhEKBzpidMbN25YC7wwM52O6cw6Lif646jA312exQsUDmZMHD+k5gXsT8W2pBvCbN1rZ9hUIGWpuKFCxQm4dyhFw/N5Y6bOXQNJTk+71L2AIFII/BBFibhzIHnDZcsXZvAqrk/dBz+MqDghPbaOoalUXHD8iEK1s+x6FPrgFolaZQtucb6cYQ7cuUXLA99xbYajQYjtaZyIOZTn67oNX2V41qLuhYymY9ztpJq/pBCYhoWFEL1KgxfnqkRRRNzQSFgaqqKwP7P65NOl6l5AfH4hmUgx8PU0U6pKXUuTyo7i61l8PY2rJslXA3oP9W04eHnudJ56X4Bu6bhADEit0ioPlpcs1Fyf16cra5YsbDTA3Es9c7tlsudukFIWIcStQILodVqp60AQwFTZbbdqO9xjc2rC5+xMjTsHk6BA3YvosQ0yMZ2XrlZImnp70mBMVzg3W2em5lL3mwFiseGjKBFnCzUMLbEoy7ZaZmdpz+K6F3G0EmOi7DJebqDQXOK7J64vWwJ6LSudDH9wcZZfONRDympOqExbMUxdpeYGpC0dTVXYn44YTsWoeyFzjeYy1uOlBvcMpRcFESsFToWaSy6honsz7FcniBqT9CuzoBXZr9axowqaGRJv6CR9lYELJo6T3uCRXa5VzjBTd/HDZvu9bEzHCUIcv9kDOAqhxzY43GOvuA1FNSiGSV73VehPc9WxudqwccIUj7z5dvpGe9Y9nmtWflmrwTdqs6BEpNUk5wvN1nyGWmJfwtpU8NJpcLu0ZCEdM9ZsRwibCzD3Ss/cvZQ132pSyiKEuBVIEL1O+YqD4wecnq4yWXaoegGzNZfLxQZH+pqLkfTFTU7021wu1nG9gHTM5MRQknMzdQo1h7Ozde4dSpG2Da4Ua1wsOgwlYxzqieH6IRdmGxzqiTFb97kyPzmvlWVbT2ZnYXAxdiXLHz4/Tr7qoKsqw2mLdMzo+HN/72yBczM1ZuseNT8kYWhUXJ/nLhf5lRM5DmcNJgvXSIYVDqhV9lUcAmeWh9I+97sR70+EMF+18Eajip+PMGcXTzpbWtrwltkqfqFZvpAlIBtVqRDgayFW1HytqTUzutr8Yi8bpagmipkFqwfFzDDtJfjbiRCrr4c3UJmsOuSrPgNJk+SARsMPMVSVwcO93DaUom+1VnaWyUzNxc5ppCydg8BBmvW7E1Wfkx2McaVgrC9hUKy7y5dJr1Z460hqw8HLwuC2UHM5P1tv19+v1IN8oxnlWyHA3EtZ8612q5eyCCFuDRJEr5OiwI/Hi+iqQr7ioqrgBxEOwaL6Zk1V+a+ODxAzVPIVl++cKXC10mCy5DCUNIlpKvmqw6v5GqaqMF5qkLZUconm8sxzDZ/BpEEYNU9ECyclrjezM1Fq8FevTxPTVd4ykuFwj01/TKFRm+HHrzxPv1GjVp2hV69yKOGQUavNPrxLVByfxPkZ3qYplJ0ARYGoPt/Ob8YjfSbJP1AVzmt16l5IytSxXRXbUDmRThFFi79eQymLMzM1oDnpzAuak+GWljYsfF5MVxlJW7w6E1AM41SDJKqZpRqlsGM5hrMDvPnNR7E6KI+4kVOn82ipANvSOap4FL2QQ6ZO2jI4kUu0W/GttM+/9fOrFKoeXhBgaBqXinV++ba+G7bAW8lKdxyWBmO/+qZ9PH1uhtfyVTw/JGUZPLg/xY8vzzFV8TiQvb69ToKXVnA7W3d5bbqOpkTomsJQylwxo73RjHIrwPze2QI/uTxHhMI9+zpf5bPb7ZWs+Va7lUtZhBC3Dgmi10mh2Vc4X/WwDBVFAdPQGEnFSJs6P5ss84uH+9qZtP/f8+M8e3mWbEynP25yreJQqHu8eLVMEIGugKIqzNRcfnTZ4+7BBPuzcS7NlpmeKfHAAIxGDYLCLK9MzGI5cxyK1Wl4AbN1H9cPyGoqlq7iONl2CcJs3WPO8bjTC8naBsFshFeI6EtZRFHEpbkGqd44vZqC50acK4cca3V0WGKy7BA3NIqOh64qaKpCEEZ4YUQublJxArIxnUNZG0Vp9rC2rDhDfYNk0jkwMyhmFsXqQTF76DWS7C+7ywLEviVBhgU4CwPJYZO3J01ezlf54aXZ9mt/8c59N+zOsZGJTQszaL1xg7cMpTlbqDXvDAylV80kPn1uhnOzdXptnbhl4vgBZTfguSslfuX23A2zugvHqSoKZ2eqeAHtYPz1QpVffdM+Hj6+uPtEGEW881AWVVHaj/XHTaariwPmToKXVnD71VNXCIKQ3oTFkV67XZ+/dMnzmZrLM5fm6I+b3DGQQDH1jjLKXhTxtv3ZVVtCrkYmre2O9e73W+FOgxBCSBC9TmEEbx/N8Fev5XH8AC/wSWsOfrXA/QM2il/joewMUbkGfpUDs6+TjIpY9ToJzefvZZqBjudG5OIGV10XP4yImglogkJEf83gmKJwIBsj4xnQXGkaNwjJOy4lNAo1D0NTsAyNhhdQDwKulhpcrbpYmorjh6goOEFE3QtImM0Zb7N1Dz9sTm4zdZVQtcDK4EZJXqOHt48ebAa8Zg8YSRRF5YWxK2h9Cn/y0ytEUUSIgtq8muAfnxxhLoz4wMmRbdnfK2XwTo5k+Mi9w+3/zuVS5FdZynijE5tWyqA1/JCUeeOSkZ9dLdMT07D15vNsXeNwNsYbszUuzdVWzerC4uXev/PGNK9N17gzF6cvYeH4Aedm6zx9bmbRZ19trIMpk1nHvWHbvbUMp2Mcysa4fzS9KEBfbcnzdx/K8mq+yn+5MMvfT1rrrr/eaN2sTFrbHZ3s91u5lEUIceuQIHqdDgYvo+b/Mz2mQ8H3MC2FKAIlioguaYykY/hTzdvRFccnrE4xEtPQVZUg0nD8kChqBrZ1X0NXoOKHxA0VU1NpeCFOEDKaskgvCIpC1SKy09SjGKfrNkU1zqyXYMq18ZQE9+3PMuZF3DmaIGXp/M3ZAmnboFB1uVxqcEdPAlNrlpbUo5BfONyDkrielQyjiHzF5Z29y4PhvrjJRLmOpWtU3AAV8ENIWjo1L2A4tXK3htUyVZsNfpZu+/2GhrXKcxcGaAuzwONFh0ffOrLq+y3MoDl+yI/GiyhEPDCaoe6vPl6FiAh10WMJS2d/ymay7K2a1QUWBZKTZZdMTKPYCMglmsF4TyziZ1fLfOQGY20FzJqq8JG7h9e96Mpq1rodv3D/piyddyesZieZxPoX89lo3axMWtsdne73W7WURQhx65Agep3uPHCAn10I8YMQiPBDhQY2dixFgRjJWD/awH4UPc6L4y4/i5WpRzEMI4WHiWtEFOs+dTUkrEWUnYBIidBCFVWBlKkxmoqxP21z50Bi2WIS9XjAqXMFXi/UMDSV4ZTJSMriasVluuZx/2izO0XKMnD8gP64gRtEmKpGvuJgaiqmpvDceJHcgmDuRrf6Tw6lePr8NKNpk+m6j6pAGDZLBl7L13j49tyyUoRrVYcDWXvFIHm1k/DT52bosY0b3iJeKQD/y5eneOe+5Ion6laAVqi5jE2UiRsquaRJvuLeMHBfmEH78eVmT+uFC+PAykHDgYzN0+dmUNVmUNxjG3hhyDv2Z4igndWdqXk8P16i1HAJUdifiXFbf7Oee6bmka86+FGErnkMJE3Slk6EgsLymvWl2T5VUTAUhZeuVVZdyGbpPl3tgmet2/GrB8AOkFz1PRfaaN2sTFrbHbLfhRBiMQmi12n/gbuZece/4D/98AJVK6Dmh8R1tX3reyIEfV8zm/vS6xcI7AovTlRImQGDiYAAqLkB/+TkEH/60hRVL6DHNnGDkLoXcihrM5KJkbaaNaVwPXi5NFdHURRKTkBMVwmBqapHf8IipkMU0Q5GjvTavDBZou4FDCZNjufixE2VYt1lzgk5O1dnstJgvFTjLcMZNFVZ9Vb/cDrGwUycUsNHoUHVi1C15ueoOB7fO1tguu6xPxMjlzR55sIcJddjX8oipejLMlUrnYQdP+QHF2f5wLE+NBWevTzLX752jXcf7OGuXIKJ+UU7Lsw1GEoZiwJwxVy9lVorQDs/21wO3TY06n5ALmGt2YKtlUFrjXe1koaWiVIDNwzpiWs4QUTJ8Zlt+Ny7L8n7jjZ7NlfdAC+IeGGy1Lz7YGhEUcTFYg3bUEmaevPfdI1LpQaKAj+6NMdt/TaWrnH/cGbVsULzQuQHF2fJJQzuyCVumDVvjflGdwXWuh2/WgC8r2/lln8r2WjdrExa2x2y34UQYjEJotdpfK7G2GSZCIUe2+CdC7KTl+bqTJZdvj52BQV4ZbpG2tJ523CK04UarxVqJA2Vw1mbN2Yd3jKU5AeXS5Qcn7SlkTQNJioOlqZSanikTY1vX6tSdDwGkzFu77MZSFpUXZ8ggpiu4IcRP50sc9dggtt6YlwuNtqdIbwgohFEjKaaNbo6cLns4PoROhGz9YDpmk/SNPh/372Pscky3z1bWDELfLQ3zkS5jqLC1bLLVNUhF9cZSiU5XahSdAL2JS1URcEPQzIxg/OzdYD2io2EUXMC4Qon4VevVcklDNwg5KeTFYIopOr6fPPFCRRF5ZcOZ7lrMMUPLszw0lTAYLLCUMricI/NoVSMM4XqiserFaDlK81AuO4H5KseaTPkuctzhChrTkZbb9AwNlnmQNZmX8ri/GyrZ3NzwZzW9p86M81LV5sBaSMI0RSFXzzcg6EpvJavYesqQRAQKQqG1lx10gvh1XyN9x7u4X1H+1bMHLe2fa5QZzBpoKDw08kKJ4dTN7xYWO2uwPfOFuiNmxueOPbB/RnwgmXPX42hKIu6c6yntOdmmrS2lyZI3kz7XQghtoK69lPERKnB1567zLOXZ6l5AS9fq/K9s9NMVx0uzdX5yXiRoZRBLmlyulCl1HA5PV3jasWjP27QHzfojZt84LYcMzWXqg8fONLDUNLC1nVimkqh4nCpVOdyqcFfvzHNXMPj5FCawaTB9y/M8uJkmVzCYiBpoKsqzE/ys1SFQ70JomaBNpGqkLQ0bu+zeWS+o8Or0zVmah6qCn0Ji6G0RdrSmK46jE2Vmxna+UDzqTPTTJQa7c8+nDT5yXiJYsOj6vgEYcilokuPreOFET0xjXMzzaA5ZRkoREyWHcYmyrh+SExTMDWNp85MYygRz14q8v+czvPc5SKX5upM11zuyCU4P1sniEImSi6qquD4IZYOP7lS4vxMjZITEEbNlRddP2RsoszFmdqaqzn2xpslHK4fQRRhzWeBLV1Z9lmXHvPZusd/PlPgBxdmmK46lB2fkuMvW7CmUHNJmBp9cZP7RjK890gfd+QSvDRV5utjVxibLDOaNDlTqNMIQtIxg9GMxfm5BnFD52DGwg0CrpSb+/WdB3o40pdkf9qkP25yrK9ZHvHUmellx+rpczOkLR0/DIkZOrahETdUzs82lytfbZn31pgXcvyAZy7N3fD7sHT/2nozM2/rGicHUzx3ucjXx67w5On8qvu2tX+fOjONbWq852gfD+zP4IbLS1ZWstJ778VJha19sJ793Q1ulv0uhBBbRTLR6/C9swXOFOrYisJo2iKmq5yfqfPDi7MMpmzeNprmQLZZ1zpRcrhSahCECumYTrHsoakqoymD/oRJLmFRdFwiFP6bOwc4P1vnhxfnUDWVQz02r+ar2IaGG0ZcnKvz5n1pem2dn01VeNfBLOdm6/QlNGpuQLHh80q+iqmp3NYf567B68HdwnZkV8oNyo5HxQ2wNJVsTMfSFC4UHR5eY6LQRMXleF+Cl/NVXpoqY2gqKUvj+YkSgwmTCIWy02wjcqTX5oeX55ite/T0Gu0VG98ylKLi+nz7XIETuQRTFY/pqsus4/KmgSSWrlFyfOYaPpauwHz7v56YwZwT8NyVMqOZGOOlBuVGgNXXLM14earMJ9+yeneQ4XSMR9860s7U9icMiKDhhZwcTmFq6qp9tlulDr9wqIdXr1X5wYU53nkgu2LQsDRjXai5/Hi8SNo02qUST18qcrQ3RiZmtBeHqfsBr16r8o4DWY72JfjPZ6YZTJoo8+UjdT/AUFRm6h5fPXWFmfnyksM9dvvi4ceXi7z3aG+7Ft7WtWYfb8e/4a32Fe8K5Kv0x80NTRxr7bPR/uS6Jo1udnLgzTBpbS9OkFzvft9LGXYhhNgoyUSvw0tTZXrizeBHURRyCZO79iVJmDqHsjFGM8060Gbtbh1FbS44kksYqIpCr60R0gyMjvTahBHkKy49tsHx/gSaonDfSJqBhEXVDUgYGqamcK3aDE4P98RxghA/DDmStak6AZeKDram8pahNG4Q8dp0fVHWsZWFnCg1qHsBTgCaAn4YMV5yKDkBlnr9ec9fKfL0uQKv5aucXVAicXamxtWqQ6+tkbYMNBVmai4vT1V49VqFs4UquqoSRhGGptBvG5QbPi9dLXNpzuFwNkZv3GCq7BIEcCAb5/7RDL9yPMeJ/gQXiw2+e6bA+FyDaxWXCHD8qLkvvOYy4lfLzaxwzQupeAETxQZp0+BI3+o9olta2TM3CGgEzVUQTw43S0tWy9Q+fW6Gc4U6z48XuTDb4K7BJO8/1kdv3Fy1tKHk+JQdnzCK+Ml4kctFh7mGxwtXynhBRBCGWLpKzQupe0GzZWAE0zWXk0MpTg6l0DSYbXiENAPomhcS01UuFmvtALqVhW9lkhUiqm7AkV67uW2/Wa9vqMqKWfPVxlx2fPJVj6GUyfPjJf7mbIHnx0s4frhqNnuhVkCYjjW/8ylLb5eTrGSlTPiNMuc3o073wUSpwZOn8+vK9O+mvZZhF0KIjZIgeh2i+aVWFmq2NFPaGT2gPYmNCFQFDFXB1BVm6gEJQ2Wm5nFupk6x3px49sZ0DVvXGM1YEEW8MVOj7odMVR3cIGy/YxhF3Nln81q+xvfPz3BhtkavpTGStblnKE0uYaEpUbsWGa7X7o5NlrmzP0lPTMcNYKbuMlf3mK37HO2NM16st0svspZOyfG4WHTaJ7y5RrMrx5wTkLY0Km6IHzbHNOd4vJavMld3eSNfpeGFpCyNN+9L8+Z9SQ5kLM7PNijUXKZrLv0LWusVas0V8bwg5N2HsuQSBlMVj3zFQQVKjseluQY1x6XhhxQdj7ihcWcujm1qDKZMbs+t3QWilRGLUDBVZVEWd6VM7USpwQ8uzqKqEWnbwA0DXphsBpNnZ2orBjELb3O/MV3j7GyNw1mL4Uys/fqYruL4UTMDPp8pjqKIdx7ItrN7H7l7mCBUuFZ2MBSV2/viTFZcTvQnyCUs3CBcVK4xXmwe7/98psDL18ocysQIguYF2vG+BCcHU4xNllcMula6NX/3QILXCjXcMGh/9h+NFxdNrFxNpwHhwt9Ny9LjsVeCxo1azz5o2UuB6cIM+3ouqIQQYq+Sco51uGdfip9NV4mrYOkajh8w2wh4YCSzaLJN0fHJxgyiyCcb06l5IYMJk6mqhxeE/N+vXMX1m9nQE/02F4vNpa1VFH52tcJA0uRA2uJ0oUbVDTneF2em7jJRcpqT9zSPTEzj3EyDmh9Qc5tdPI702pyaaPYFDqNo0YSf754tcP/+DHOOx/m5BglTJxtTCMKQmK7wV69No9I8oWdtHVVVOJGLt28pZy2NouNTbHi4QUgmplOse9TcgF7bIJXW0TWVi0WH09MVemyLpKkydrVCGEbEdJWfjIdoqspg0mjv0xevlhkv1lAVlQtzDd62P0va0vjuuVlMPaA/YZLQFV6ZrjcvQBoKt/da9MdNZhser+Vr/ON3HFo0iW3pLeThpMnYVJkgjNAUOHWlxCvXKrzvSC+DqdiKk6LGJsvkEs0Jeiq0F095/kqRuh9yreIuW0mwFQQPp2M8eTrPtWoKTVn8+mLdR9PA1FTeMpxuH6P3He1rv/dgyuLefUlemipTdHwO9dgczFiMZmySps8LkyUATF3lwkyNC7MKbxvNEDc0Xr1W5aWpCu88kOWTR/cD3LD7Biy/Nf8nYy4KNZjvf040f7EYLb6AXEkrIOxZ8NiNykmGkybfePEqQRjSHzcZTJmLOsXshQVVNluy0MlEvb1U+iGt8IQQtwrJRK/De4/0cnsuSRBAsdYsS+i3myex754tUHN8fny5yOl8lboXkksYHOuP86Z9KUYzMUZSJpNlFyeI6EsY9MY0xq42M7elho+uAYqCF0SYmsqRrE3G0pmru0xVPAxVYbLskI3p3DWQ4o5cgl7bYKLs8JevXePcbI19SbM9iW7hhJ++uImlq+xLWhzIxBhKWQwmLe4cSOFFEIYRvXGDkuMzXmpwJGszmom1M4hH+xKc6LdJWTpFxydpavTYOvuzzW2lLZ3zs3U0NWK67lPzfJ65PEePrZGO6dS9gLOzNX75aA+aqlJ2fKarDi9ereAGETnb4HS+wrdeusrrhTqHszHeNpIloatEqAynLO7IJXnLYJLZuseVskPaMprB5XwdOqycqfvGi1eZqTWXGb9ScoCIS0WHP3phkp9cnuPk4PKgpzA/0XFp2cUr+SpeEKJpkImbaBrtlQTXen3Z8Tk3W6fHMnjlWpU38tVlk7JWm2jXOx+ctpYgb/b9dnFDeNtohgNZm/6EybsP97RLTgC+euoKL06WOZ2vMVf315UNjIAHRjPtTLmpqzwwmmHtELoZEF4uNvjeG9M8fWaaH5yf5XKxsWI5yUSpwdhUmRO55tinay6vTVcWHY9uz2ZuRWa4k4l6e6n8pZMMuxBC7GWSiV6H4XSMf3zfKN/9+VUKNRcFmK57xIzmMtunZ+ooRPy9o328VqhR83wabtjMPqoq9w9nODtbZyBloQJnCjWSpkrDj6i4Ppahcc9ggtlGyEDSIG3pZC2dF6cqfOBYH89dnuPsTI3xskNMV0kYCq/WPBRFoS8MKTaa5RmfvH8/J0cW9xNuZbsafsiJXIKZqsvlksPlYoOkpaGrsD8Ta/dRnqn75NwABXjydJ6zMzUuFmvclYtTbQQEhBQb0G/pOH5EEEbNxUViBpeVBvmaR9LU8EK4rS9O3QsIoggvUtp9h39yeY4e2yBlqlyru5iqSsbSODfbYDhpcbg3BkpEX9xkvOhQcnxu70+QtHRMXeV4f6Kd4W1ZKVMXhCHPXynhhaCpEW4IWVuj6oR4YcTYVDMga/Wi7os3e0Jb83XT52frzM23q7NUhZG0tWhZ75VWEuyLNwOq1uuvlJulMUeyNm8dzbSzja2sZSub+f3zM1i6wp0DyUU9tuvzzwfI2jrHc3GG0iYVJ2A0szjYSpjNcpKpqsNMzSVmqJyeLvOTK3PcmUvypsEENXf19nOtsd+34DtUdvxl+3o1rYx1pCrNTjGrZLAXHqsD2evvM1FxGZzfH399+hojqRhH++L0xo325+uWbOZWZYbXO1FvL/VollZ4QohbhQTR6zBRavCTfJUfni8QoVB3AwxdYarsMFX16LWbvZ7HSw4JXWWi6DFd8Tjen2A0E+NysY6lqe3uCTWvOXmw2PA50hMHJaKhqZhayHuONG/v/+B8c+GMlKWTjpnYhotPyFSlOdlwIG5S9QIiRSVjmdzW11yY5OSSsbeyXeNFhwszNUpuwGjGYrLs4IcRkaKQr7rkEiamrpKvONiGgqIo2KbGbf1xbEPltXyNwz0xzs3VycZ0YrrGQMLgjUKdoZTBK/NZ+Omaw1DKpOb61L3m5Lh7h5IUau6iRUzuGVL4i9euoanN8gQ3CEGBXNJs91rOWjpZW6fi+dT9YH58LkMpa9kJuXULuVV3XnY85hrNDPCJXIKZmoehAqikYwqTZZc7ByK+8dIE79jf0y4ZuFZ1UJTmSoILyy5ma+58bfx1K60k2AoggjAkimCy7BChcHsu3s6oAu2MaqtkQSVCUVSeuThHaj7jmDR10jGdR+4aXLboSWsBl9b2ZmoeL09VeKNQ4ba+JEEY8UahRsLQyMQ0xksNqp6/6qItC8cO14Ofy8UG/bbB18eu3LBkodUrezSXolhq1mov7BCz0rFaKGFqvJGvMlV1SFs6I+kYJcfjhckSbxlKr7m65k47W6hScgPKrk/a0jncY9NjG9sW5O+lwHSthXqEEKIT43M1vns635XdftYVRHuexxe+8AWefPJJAP7hP/yH/LN/9s9Q1eXVIOVymf/xf/wf+f73v088Hue/++/+O/7JP/kn7X+vVqt84Qtf4Nvf/jaapvHwww/zO7/zO5hmd5wcl5ooNfizlya5Wg+wDI2q4/F3l+awDZV9yWZ97mzD4EA6xsVig3uHUtzeH+dnVyvUg5C+uMG1istktYHlqeQSJjFDY7bhoqsqR3ptIiJ+dHmOtGm0a5qnay7vPpQFmjXPV8oNrpYdyvUG5fleybmEyS8e6uFIX5wwishX3FXrNB996whf+uF5euIGWdskX212uzjWG8fQlHaA2hs3GUhYxAy1HaAdyDYDBFvX+K2hFN87W+CZS3PYerPH8YW5OoamcMdAgjema0yWHHIJq5k1ziUwNXVRNrOV8UwaGpNlhyteM8N+IG2Rr7pcnK2TS5hcqzjUvJCkoXFpzkFXYH/WXrXN3HixwdhkiYrj44VQ8wKK9WYHioYfoikQENETa/azbnUMWZhNPJC1qbsBdTdYtAjIif4kb8zWUIGYrjYnOzY8buuJ8+SSH/fJwVS73ldXFEayzQmWWdugL27i+CE/vlzkb88XMDWNuwaTKIrCa/kqV0oNkqbGW0fSlFyPWacZlD18PLfsu9kKqhw/5EfjRRQi+hMmqhpxqdQgCCOSpoauaZTqPpGttNvnrWSlZcSjKMI2tXbgtlpdcid1sKtlVeecgOFMrL3y5tiEj6JEnC3UMLRE1wSNE6UGF4sOmtr8LjXmO6bc3m8znFr/io2d2GuB6c3QglAIsfsmSg2euVpBmS+d67b5MesKor/85S/zzDPP8JWvfIVqtcpnP/tZ0uk0H//4x5c99/Of/zzXrl3jT//0T7lw4QK/+7u/y8DAAA8//DAA//yf/3POnz/PH/3RH1Gv1/nt3/5tMpkM/8P/8D9s7SfbImOTZS4VG5QDqNddrlVd3CCg5jczQSFQqPlMFhtkbIM3pmtM11wyMZ1eW2+3SCte9tEUMBQVjQjHh3ccyhBGIa/mq8zWfWJaMxt3tC/BOw9ksfRmzeP52TqaouD6AdeqHrahMJKyONgTb2aGbQNDU1AV5YaTsVpLeJfqHiMpi5IbkDBVGkHE8f4EQymLh471892zhRXrL/OVZjb5H50caS9n/eTpa+gqHMrESJs6B7Ixql5Af1wnCuEnl4toqspH3ryvva2TQyn+7KVJ5hoeGVtvZ5ALNY/htEXC1HD9gNdn6rwpl+RIX7xdsvLB21f+4ZwcSvFXr11jouKQtXQMNUJTFHriGmemqyiqSkxvXviEUcTBnni7Y0hrH5ccn5SpQxgynLV52/5sO3j0gd6Yjh9FzDo+pqo0/xvadbGt/W0oCu84kCFl6Tw/XsINA4ia3VsUFH40XiRjabghqGrEDy7MNCctVl1svVkb//p0jcGEycnh1IrZ3IVB1Y8vN7d350CS87N1XD/E0FTiOuiaSqnuk7R03j6aIQhXLrGYKDV4+twMP7taRiHi7vme4wey9rpKFjqZWLhaVjUb09vfu75487Ofm6lzpdTg5HC646Bxu3oVj02WOZGL83qhRiMIseZLoV6brvLw7QOb3v5qJDAVQtxqxibLZGyDaD5n222TqtcMoh3H4Zvf/Cb/+l//a+655x4AHnvsMb70pS/xT//pP12U2bpy5Qrf+c53+Ou//muOHTvGiRMnOHPmDF/72td4+OGHOXv2LN/5znf4i7/4C06cOAHAJz/5Sb73ve9t08fbvLMzNc7N1hlIx4ibGtPXXGpeQBgBhoauwGzDZzqC47pCoQaXiw2ulRVmax4RcLWSgiji3FwdJxOyPxvnH96V4vR0jW+9OIWhqRzrsznWZ6Opansy1p+9NMmFuTqZmEGPrTGua9y9L8Zbh1Ocn20QN1QiIl6eqnCkz8ZQlHadZqusIV91GC86PPrWkfklvBsoleYCKRlLp9QIMDUFW9faQcp66i8XlmZoKlyYazDn+PTFTd59QOdHl8skzGaQOpg0GJsqM5iygOaX/0yhDijM1X1yCZOUqeGGCjUv5L++o7kITdbWqXlQcnwyMYPb+uIrlqy0xqMqkLGaga5taIzaJk4Q4AcOh3psJkouM3WPoz02R/vivJav4fo+f/7KNcIIMjGNiuNxreozmI4tCh73Z2Lk4iY9ttEOymbn6+KXBpk/uTzHPUNpTudLTFYc8lWHkZSJHmi8PFVBIVoU8JbdZpDdZxvNpd2BuNGcmDmasVctEVh4DHJJs92KbmyiTExXaLgBo2mLmt2clGjMH+elJkoNvvXzq83JjzGNCJXnJorM1jweuj3H/GEDVs8utwLjUsNb1iFmpXGvlFVdWqLSFzcxNZWTQ+kVM/E3sp3dPQo1l9FMjKSpc26mTqnukTYN0jF9W/+oywImQohbTaHmcixrU57vRgbdNT9mzSD61VdfpV6vc99997Ufu++++8jn84yPj7N///724z/96U/JZrMcO3Zs0XP/7b/9t3iex7PPPsuRI0faATTAhz/8YT784Q9v1efZcnMNH1tXcLyQ2apDyQ0IIlBo9kpWVBVTg4YP42WPoaSCpanN5bFLDfYlY1wq1mj4IQld510Hmxnmn+ervD5d48RAvH1L+PXpOrf324xNlnn4eI6BhMVMzcfzQ1KWwWg6Ro+tMVu/PnGt6PgQhu0MsuOHnLoyw8vXKmRiOqNpk5ma21xNLmnyk/EiPbZOJmY0l/L2Aj567+IJiZ3UX640Ge0HF2Y40mOTS5qUHB+lCgMJg++dLeBFzYmIyZjGmxIJpmseGcvgp/Pt2yDg/GydybLDcNqm3PDbdeKtkpXVJEyd/oRB3Gh+rd+YqZEyNYyMzcmhLPuSdWbrPknLYDgV42Da4os/vIjjRxgqzNYVNE1hMNFcHOZA1l6w7eYqkQuDua+PXVkxY1/1muUVvbbOcNrC0hTOzdYZSpokTY0HRjPtC5KxiTI1P8Ccf62iwIn+OElTZ87xGS/WmSx7N6xJXnjRo6CgKTBb85hzfPY3fO4byWBoyg3bpxWqHr223g6yVaBQ83j1WpV3H75+8bRadrkVGJ+r+ZwrVNcsN1gtq7qRut+VgstOJv51Gpy29ndv3GhPeuxkAuZG7IWWf0IIsdX64iYVx1/0WDfNj1kziJ6amiKZTJJIJNqP5XK59r8tDKKnpqYYGFh8OzOXy+H7PtPT01y6dIkDBw7wf/6f/ydf+9rX8DyPv//3/z6/9Vu/hWEYdKOspWFpKudm6sQ00JUQJwIiSBoqtqHjhyFEIYra7NoR11VqYYQfRNQ9n3LDA0Xh7aNxLsw1uG8kw0zdI191ONCTRYH2UtBTFQ9La/7/MIp456FsO8P4/JUiDT+k7Hj0xdP0xc32ybuZiW2WCszVPLK2jgKcnq5ze3+cIAz505emMFXIV33qXsS+lLlidreT+suVAu6Ls3WSMaO9gEvDD3ltuk7D9XjP0X5Slk7G0tt13a4fkY4Z+GGApaqczlfmFxMxOdF//Xu31g/nYMbie+dn0BWVdEznWsVB1xTuyCW5bzQNpJmuOvxsPmD6+VSFuhcSN1RCQFMUdAUqTsDYZJGK65OyDI702hiasuy9FwavrZKQfMVluuqQtDR6YzpK1KxL3p+xuH84Q+/8RUfr9SeHU0yUGzS8iEPpGEXHQ9dUan6I4wX8ZLzE20YzNwycWsdgtu5xerqKqsCJgRRDSZ3Jikuh5nG0N94ORpfWcBdqzd7Xcev654vpzeXhp2suZcdfV1A7nI5xz9EU+X1rL4Kz2us7rftdLbisNHxuyyUWPXel7MVGgtPdmOS3l/pEi60jdx/Ere7kUKpZE+2t7zy009YMouv1OpZlLXqsNQnQdd2OnlutVjl16hSe5/G//C//CzMzM/z+7/8+vu/zz//5P+9o4H19GztRd+otR/qZbPj4KMzWfVIxiwCHIIAABVVTMDSVMIQe26TseESqQsNvdm2oeCEJUyNhaFTCkDkvJJO20UyduG2gGlo7c2pHEZPlBkeGMuRyKY4MZai5PulY8wLjHlXlv5ybIZOMkUrFqDg+UQjvv2uQXDZOMmVhWwYzdZ+sbeAGEWak4CtwsepTdAN+6VgfDT+k5gbccyBLb9xkquyQyy3u55vLpbjn6Nq30HO5FH19CZ67XCRfcdjXZ3NkoAYK9MWb34UEQM3hWt1juD+Jqijco6r85PIctqFxbqrEaK/N6WsVAgVylsm+TMTl2QaoCr6i0JOwGEiafPDefeQW9IdujXt8roZpmwxn4/Ofz6cahBxI2bzzWD+ZpMV0xeFn+TqZlM2x4Qz/z9kZUBRCpXkMTV1FA8aLDQ71JsikYkDEC9cq3J5LLnvv9xsaf/nyFDNeyCuzDTRFIZUwCVQFTVVQDQ0XhWzK5K2HegkieP8dA3ztucucnqvgBiGmpnLvaJZs3ORgj03DD3hpssK1coNsMsYDg0kO9zaDwR6g1PA4V/O552hq0T7o60vwb/7uArqpY+sqCgrVEHpTNgcGkvz62w8xPlfjL1+eImMbHMvaVByfZ65WSKdjpGs+qkr7u1hzA4Z7Ne7al6I/YbWP7Qf3Zxb1517tO7FR6/3etfzd1Qqj/cn2b6S1j16aLKNZRvtx5h8/krIXjW+11y/dx0vHuPQ7v579shnumQLDWXvR6pGpKFrxt7uazRyXnTI+V2vv11zS4v5t3q+77UbHZHyuxjNXK8t+r/9VX+Km3ie7bS/8Tm4lu/H3thNrBtGxWGxZsNz671gs1tFzNU3DcRz+1b/6V6TTaQBqtRqf//zn+exnP7tit4/VFArNFfG225G4zkzZ4e7hNJEfUqg6PHtptrmwiOtjKOAHEUEU0fB8bLUZUGtqc5npjKXjBiGaouD7AdMlh2KpTuD6xBWFsUtzhPO9lmOGSsxQOBLXyefLHInrPDUxR9pqTrhquAH77GZruTMTRfriJu8cSmF5Afl8mVKpwT05m3ypwVSpQdbSOZI2OTdT50A2osfSmS018MOQy8UGb0yVOdprc7wvQT7f2SIWK2VI3jWfgXzhfIFLxTr4QXuFx6obkNZVJqYrpCwdAzjRE+OVaxVKNY/jPXEOp2PMOT7VuosRKdiGiqU2TyYxFcqEFApVrPlVCnO5VHvc3z2dp9dQeedomvOzda6WFSp1n1cmS/xx3eNYr43jhwQonBxIUC43qDserh9QdX0GEiaNIGCi7GJpKr94IM1sw6fk+FiqQiwM2/u5xQLeuS/JV09doVJzySUsjvTGm0u7Oy56FHHfSPN7Xm541N2A//DcZf7u7DRBEJGNafTYFvGEwX39zTsCczWXe/vjnLx7kO+eLZDVlHbLOGjenThXqC7L9lpAzlTZF7P56WSFuNGcSFlrhDz186u8LZdgbLKM4gdEKu36MsXzqdRC4krEuZlWTbRCseFxKGvztlxiPvM1/35L9sFSC4/JTjg3WSSXNCkuqJcLowgjDBmfrrR/O63sxUPH+heNb7XXr7SPF7Jg/vu+vv2yWWYQtn87La27UOt5350+Lhux8K5AwtS4WqjwpxNzN23JylrH5Lun8yv+Xr/786sdzxEQ67MXfie3otFcav68vzN/bxdSVeWGSds1g+h9+/ZRLpep1+vYdrNGNJ/PAzA4OLjsua1/a7l27RqGYdDT08PAwAC5XK4dQAMcOXKERqPBzMwM/f396/9kO2Q4HePdB3t4eabG+XwVx/dJWwYxTSVf83HDCFWFg0mLQiOg5oeYukpMAzcA1w9o+CHTYbNsoDejU55fwKPVxWKm5nK6UMXxI/6bE/2L3nvp7e0P3z206gmlVZ/894718cJkqVmmEIEXRpSdgISh8OPxOepexEDSIAqh6ARM1z0mSo11n6hudAscmnXkxbpPoda8/TKUtBjtj2HrWnvhkISpNVdn7I1zvC+BbWqUXZ/htIWiKLx8rcJoKsadAwnmHJ+7BlK8PFXhX/3wAr94uI+TQ6lFGYPW5LqU0qwLvlJsYGjNpbRtTeWlqxX8KOK/PjHQrmON6SqGpmBozTrimh8RRhHDSZOjfddLARbWYq908XAoG+P+0fSiLOHSZdgvzdVRFIVC1eNQNkbVDTkzU+NKyUFTNSZLDp9+8OCiY7CwXGThRNHeuLnseE2UGlyYa/CzyRJxU+NAxkZRFFQF+uNme8wrtaGruQG/+qZ9C7pzhNw/nOF9R/t2JHjZzC3r1SbBHu2Nt2ujb1QaslcWMdlLfaI3SkpWFpPl04XofmsG0SdOnMC2bU6dOsW73vUuAJ5//nkGBgYYGRlZ9Nx7772XQqHA+fPnOXz4MACnTp3iTW96E6Zp8pa3vIV/+2//LYVCgb6+5mSxN954g2QySTab3eKPtnXuyiX48dUyB7IW01UVVfUwDI3DfXHcoNmNw9AU3ns4w0+vlgnDiIoLYRSiqAoxvbmy4XTNJZdo9ls+0hNnOG1xdqbOeMnhSE+M/rhB3Y8W1WR20taqdaJNWzr37kvx6rUq0zWXoYRF3Q8YzcYo1D380OVKyeVgJsaD+7MYmrLmiWphoHNhrsFQymif5Nwg5NxMjf/v354jZigMJU3StoGmNJfMHkgaaKrCe4/0AiwLbKA5ocxQFWp+iKpAseHzpsEkDT9EReGFyRK2rkCktJdY7utLYAFjV4p879wM01WHgWSMpKFSdgMsXaXX0DnWF6fuB5wp1JmsOBybr7PuT1gUHY8ghHTMoE9t1rkPpBbvh1ZQtdrFg6mqiwKx3rjB8f4Ek2W3/Tlbvbenyg4qCmdnaxRqHnFDZTCp89JUmW/9/Cq/+qZ97ePQagV4qdjg3GwdW1fosU2GUsai70hrXHEDpqouSjXiSqnB7f1xUpbBvftS7QB1tYBxOB3jI/cOL1p9cSdsdsLcjYLL9fx29lJwaijKot7lN1uGVoLGxfbKBZ4Qt7I16ydisRiPPPIIjz/+OC+88ALPPvssX/rSl/joRz8KwNzcHOVyM60+MjLCe97zHn7nd36HV155hW9/+9v8u3/379rPffvb384dd9zBY489xunTp3n22Wf58pe/zIc//GF0vXsXT5youDx4sIdMzGCm7pGNGdzea1PzIu7MJXjHgQy2oZGJ6RzJ2vTaBvuzNgcyFilTpzduMJqJMZC0sHSFk0MpImA008zsZywNP4Q5J2Su4ZK29PaKdp1oZa5tXSMII95xIMvvvecoD+zPkLA0mK9+GU5ZDKVMDmZj9MYNEmazH/Wqn38+0Gn1Q56pubw2XadQay6XPTZRRlEUpqsumqIwVfE50hMjEzPwg4jJsrvoouDh4zn+8cmR9i3JsckyFSfA8SMuztYJAjiQsTg7U+WnV8ucn60RhiEKzfKYlKWTtnSeu1xk7EqR/+O5yyRNhaSlU3Jcfjw+x1SlQRjBYLKZdbZ0jaylka96lB2fMIrIWs2WZG8ZSnMwE+N4f4pfPNxL2tLbz7k0V+fZS0XOFqp89dQVgjAiZent1QfTlk4URZQcn0tzdZ67XOT/OZ3ntXyND97e3/6cYRSRMDVSlsHluQYNLyBhqESAqijNftVVb9lxVxSFfNXDVBRMTUNVFBKmvug7MjZZJghDpio+QykT29Dwg4jT+TpHsjaWrrYzvCXHb3+2suO3lyDfLQuzjwv36Xq//wu/8/mKi61rHQWXm339Tmj9/mxT4z1H+3hgfwY3DNd+4R7TChoXupWDxm78vQohFltX5PqZz3wGx3F49NFHsSyLRx55hI997GMAfOpTn2JkZIQnnngCgCeeeILf+73f49d+7dfIZDJ8+tOf5ld+5VcAUFWVP/zDP+R/+p/+Jz784Q9jWRb/4B/8Az796U9vz6fbIoWay7HhDL3NdaNx/eYCC1dKDg2/OTnsjv5Ec2KarmDoCllLp6KrXKu5OEHEgbRFn61zpezyBz+8SMrSuVZt8Gq+SsbSiRsKVd+n6oDjB9SWnEzWa6XsWwQ8MJrhwlyDKGouV328P07rPLzWiWrpbdZcwqLoNLtRAMQNFRRQFcjaJo4XMDffWq1VCrFSULIwC3lbfzMzf2mujqmqXCo1cIOIoz0xLs01OD/XYF/C5F2Hmst5NDNUDk9fnqPH1um1TbIxj6mKx5TuMdcIuHvAImU1g2jHD+ixTU7kEu2A6UQuQW+8uUrhwizk+w73MVFxeWO6xsVijRO5BKMZm2+/Pk3J8UjOXxi1xlFzg+YqhS9NEAQs6429sPf2kV6bn4zP4fhgas2r2GLDJ26ovDRVwgnCdjnD2GSZ/ZkYU2WHtG2gAnWv2QLwUDbGTy7PzXcZKaMozd7St/fFOTtbx1BV6m7AlZKDZajtzOxmVr3bjk4B68k+rvW+m12EpNsXMblVyhz20l2BnbDXVqkU4lakRFG0/bPztsFOTSyEZkswwzaIXH9B5jVCiRSm6w4z9YDhlDUfzBm851Avf/X6ND++PMu+ZIx9KQsIeW261lxEw9QwdZW/uzyHpSgMpS3ipobjR4ykLGxD5R37e7Zs8siTp/PU/eut2P7uYjP4IoLb+hL0JYxFZQRLfX3syqLFPGZqHqcmivhBhGmoxDSFuh+hAZahEtNU5hyfe/aleOVaBceP+KXDvcuCn4Xjaik7Pq9cq3LnQAIvaE52e2mqTETE4R673TO67Pjs60vy1R+eR42gEYTYhsa+pEUYhTx7eY4370uRmV/ie7YRcKTH5lff1Fw5sRWUKTSzvWEULfr/ffFmxt02tfb4nr9SpNjwyFjmfMu8xf2BF+7jVru73rjJo29tlj21LhieuzzHcxMlGn7YXEERBVtX0BWVgz0xjvTG232/c0mTF66UccMAW9eIoogrZQdVgbRp8M5DWZ65MMcLk0Xumf+8ZcfjcrF5EXIgE+PTDx7a9Il36aSvhRP1Fm6704k5S78DMzWPl6cquEHALx7uYzhpMjZVXvN9b2ZLf39wvU7/H58cucErr9srE6ZupZZue+WY3ErkmHSn3Twum55YKGA4afKf3pimUm2twNfsv9tj6RQdjUNZA1NVqLoB01UPXVE4nI0xUbJJxzSSpsqr+RpRBAlTZbrucyIXZzBuUnE8Ls057E9b3J5LoKvNXtGr3bLbyElmYYYniiIc38cNIoZTFigRa11H9cVNxosNrlU8yo5HyjLYl7Co+SEVxyNUVN4yP94XJkvUvYC6G/Aff36Vuhdyz75mL+SpqrMo+DlbqFJyA8quT9rSOdxj02MbTJYb7Yl6vfFmn+ZTE0UKdY/nLheZrrloqsr/qz9B1W3e6uyxTbww5OxsjT7b4G0jWe4eTM4H4AoPjGTaNdlLa3BLjs/JwVQzWDO1drD2zKU53n0o2w7wDvfYnJrwyVedZavytQLe1kVW3FDJJU3yFbdd49vKKo1kbOYcHz8McQPwggAniOhN6tw5kMTUVMYmy4uy1y/ML0YTRjBb9+iNm9w12GwXeNdgkpfzFc7N1rlnyEDXVAZTMW7vizOc2pos63ZlQ4eTJt948SpBGGJpCtN1n4Sp8sBohrof8I0Xr3Iit76lx7dCNwZx21Ub242ftdvvCgghxEISRK9hotRgbKrMXftSnJ0sN+t+VZWPvHmYiYrLiYHr3RNemCyR1hRKbsBwJsZQymSi7OD6EW4YcShrcaXsMppudqoYSJjEDI2DmRgTJYdzM3W8oNlZYLWxPHVmmiCMmCq7vDBR4ulzM3zkzfsWrTi4bPzzNcfjRYepcp2hpM37jyYXrbZ2o6BkOGny569OLVjp0GW27vPJ+/czmLKakwI1hYTZLCc4daXE+ZkaWdvgxHASQ1N4vVDj9r54+30mSg0uFh00NWqv2Dg2Ueb2fpuhVGxRV4oXr5Z58WqZqxX3/9/evcfGVd37Av/ueex5z9jjF34Q8nYCpMQkwTQ5Lo8EHQT3HtpK3F4BParKgUigPgQVUEClgEpbCVqVgirgVKCGVrRVWwqXliseCpeCOJCcBEoIIbGTEOdhj+2x5+F57Nl73T/GezIve2Yn2/Z4/P1I+SMz4z17z2/2rN9e+7fWwgl/Ehe2ebGyyYWX94ewttmNPafiiKcz2bm41QyOjqt4+MoVZT+TVw6EyiaDL382gvNbPQWPN7tl7A/F0efJznfd5JaxptmFk1Gl5PaqnugcDifgtlvgsluzNeQeR67G99rultxnfCKSxBv9o/jtRyeRVgX8Dit8shUSpFw5w7YVTSUDRT+fSCCayqDBacfAWLacJui2Y9vyIF49NIrhaArNbhmrm5ywWiTT6idnY9CXfm6taXFhKKZgz8kINAFs6Aiieeozz9Z6K1jSYN77zrQ/87kq4HRJ7WyUOcz3sRIR1QMm0RXoPXBdQQ+CtmxNdDSVwYlYuiCxGBjLJk96KYPPYcMFbT6sCHrQ6LLjrcOjkK1WtHgkNHmyf9PosiOmqBBCIJ5RsabZDVVIWNXsKtugZQeQCXw2mh1oF02rGI0n8MjbA7i3b3lJ0lhccxxPqzgRSWJtqzuXQAPTr+SWPxtHd7MbKTU7gC7gtJ9e6bAzkOthPTgyifFkBhYJ8DptWB50wZ/XezY0NQezfixrWtz4bHQSSTVbY57IqPh0JI5/Xd6E/9sfRiSpYCiWQkrVkMxoWN7ohNViyU7XJ9uQUdPw2my4elUTdp2IYGRSQaPLjhVtzmkvKqZLBvXe73xrWz34f0fCBSv2WS0W/MeGzpJEQ090QrHs9hMZFZOKhjXt3rKfb4ffia0rmrB3KAKrJGVryTMq/vtkpKAHWf9sJ9NqroZ7LKFAkiSktezrL273o83nwP+6oA1BtzwrPYv6RYJeYhNNKbBZLFhTtCqgEfm920sasnPhKhkVHxyP4vPxJHwOO5w2C0bihZ/dbA02m8/a40pJrdm1sYulzpqIaDYxia5AT7pG4il8OBhBdGpgmd9pw4qgO9djGk0p8LvsSCpqLnHUB51d292SS7IGRhNIKhlIkGCRJFy+tBHvfD4BuyQh4LRjWaMrt5x3cYM2OpnGUDQNTdNwPJKGwyah2WNHaFLB8x+dyg1i05VrKIt7V4HSpKS4Qf/vExFErBI2dARyyfdIPI2dh8dyCVuHV8ZQPIUOvwPxlIJI2oIDI9lBeX6HDQ6bFcPRFHo6/Llj6Qo44ZVtGBhLIJJQ4Jez9cuDsTTWtLjw7udpjCUzsFokeGUrmj0OpDMaYukMDocTaPU58Hkohk1dAaycmtc5v0a5nOlujef3fuscNgv6zmvMDUScKXnRE53BiVQ2kfY4sKbdCwGBd46GkcoIvHIgVJDY7jkZxZpmDz4bSSClqHDaLEgoKj4NTeLa1S257eqvf+VACE67Bef4HLmSEZdNwr6hGJY3uWa1F7Gn3Yfff3wKA+Hsgix2mwUTSQXD8ZShOcbzFV/QSAAOj6dgkySsanYjlVERiqdht1mqXnr8bMznFGuVklqzyxw4ndzcK77TsM1uhaPynxFRDWMSXYFeD3wsrkDSVPhddown0gin0uhb0oA9Q1GEE2kMxdLYPxLPrna3LDuDRH5yqidZb1rG8PbRMFo8dqxv98Jhy97Gv2Z1U+4W9tikgv7RSRyPJgEgl3g1ubMJbXYOZAmyNTv/dJNbhqppZZPu4oYyv3c1lVGxPxRHKK6g77zGXDJUMhuHV8ZEMrvYR9Btx9ikgvcGJxBwWHO9Zvm1q36njIwQOKIkcWwiifNbPBhPKrBaLLnyAj2ZDbrtBWUlnwzHc+99aCyBZEaF3WrBSFyBomnIaBqG4mlEUirWtvuRVDP4fHwSQzElW2pjBW5a1zFtPKe7Nf4/Vzdj59EwRuNKtkY5I5DUNJzrc2AgLKHBYa3Y+9nhd+I/NnTmLkBSGRX/NTgBAQmXTtX45vcuZi8kXPDINhwOJzAYSWJS0SCEyE3xlh/P/BpyqwVIqRo0ANC0Wb8N3+F3otllx+jUbDN+hxVrz23I1W+fyXuXu6BRhYBXtkLKTiMDj8OKVY3uqi5kztZ8zss710kt5yCeW+XuNLy0bwhbzvGy559oAWMSXUFPuw9vDozB68muUphUVAghYc3UMs09bT48/9Ep2KwWOKwSWjx2DISTkK0SrBZLQY+ZvqDFlcuDuR4Jl82KLUsa4JjqPdVrqyUIdPqdBYmXvi+j8QSaPXakMhrSmoYWjx2NTrlkrudyDaXeu5qYGjjX7JbxpaWNcNgsufcpbtCLB9TtG4pBgsD5rd7c3L75tavLgy6Mn1RwXiBbAz4Um0puv3B6tUU9mc1egGQT4KSqIZnOIJ5S4HfKsECCbWopeKfdml0FMZGGbLXAK1uR0QT8sh27j0fhtFnQ7JbR5pMLppYrNt2tcSA76BKSQExRcTKagtNmwSAAn8OKiVQGLtlSMjgyX3H9+aloEkFXdgBgfvmMnnTq8dETl/FEBh45e0zFCfee4xN4+/NxpFUNzW47Ghw2WCwWrG52ocPnmpOGWADYcl5j2VkizkTxBU1S0dDpk9HglDGeyg427e0KQNUwJ8scz+cUa3Od1HI6udlV3OscTigldxok2cbyGaIFjkl0BR1+J84LOJCxWTE0Pgm/w4bulmyds548fHFJoGRp5pNRpWztrL7N4iWb9Qatf3QSEgSEkLA86Cq4rXttdwv+dUUjHjkxjlPxFIIuGUsCMiwWC9p8ckmDO11DqSeR21Y2FTTa+vsUN+jFA+rSqorerkDB+zW7ZYzE07np3ZKKhrFJBc0uG66augAonttXvwBRNQ3OqVv2kbSKRk0grak4GU1gZFLB2KQCv8MKp80GoWXn4e7yO/EvK5rw3qFRNHss6FsazG274kDJMrfGXzkQwpIGFy5o82HX8Qk0u2UMhBOIpVSc1+BCQlExHFfQ3ewpu+1y9efHI0msbfXkeu8HxhKIJNPQkB3wlx+fgbEEJElAQMKKJndB3AHg+Y9OodUjY3AigSPjSaRVDUGnDZGUggeuaC17nGYzO9ErvqAJumW0+2QsaXDlXlOpPMdMczEv71wOHpwJ5yCePeV6nd8+GsaXljbCl1e/4XXYcGg0Pn87SkRnjUl0FVY0eWB32XFBsLBxb5oaxKX32uqlCTMtMFJOfoN2PJpEp9+J5UFXLjnRb+ueiCQxGEvjf3S34P1jEaRVDWMJFSuDctmZGGZqKPUp2fIVzwqhP1Y8oE6f2zdfm0/GYHQS7x0bR8BpR6PLCkgylje6ShJofWaK/3NgGIoGdDd7IIRAV4MTgZQNgxMpWABE0ipkSUKbR4YGIBRPYWOHH1uWBhF02xHwOKCoKoRFKtiX/M+r2im88uN4IpJEMqPh6EQCsiRhSYMDXtmG8am63HI9r+VqWls8duwfjuOCtuyy5W67BbI9O9dz8bR3xyNJdPqcWNHkLljIJRRL51YkDDhtOB61wCYJaJKEhKIhkTG2cl3xZ9LhlXODZCt9RrOR6OVf0OjJx1zUP1ezP2ab68GDlcz2sdba9HlzZabfgr5lp39zY1NtCBEtXEyiq9DT7sM7p2KQlNLGfc/JqCm9c/kNWvECJPr29B/nzqnXfnQqioOjk3j/+AT6ljTgzYGx3EIheqM1XUOZ36uY34MenNrvmRr0csmU1SLhwhYfTsUUKBkNPocdm8/1wW6VCnpuT0SSeOGfJ3FkPAFVSPDI2env4ukMLu7wocUtI60KjKUykCQJbtmCf1vbhqDbjrePjAFCKiiNsFutgFQ4z3U8rUJC6XzQM03hpX8eaVXDyKQCiwQ4rRaoGtAfTqDT60DQI08b27L15y0evH1kHPuGYnDZJEAASUVDT4cvV0usX/h4ZRuSqgqB08eiv9foZBrNbhkHRuIIOK1ocdshhMB4UsWSgLPqW8LFSdzgRBIv7h/CJV1+dAVcM35GxaUqDQ4rVjR5TE306r13dK4HD86XxT593ky/BfkXiEIDtnAJb6IFjUl0FTr8Tvxbkwevf3yqbONuZu/cTL19xb3Hqgac3+rFWDyFg+FJiHCiZAAbgBlvH4cTCg6MxGGRAKvVgnafPfe309WhTpfsvN4/ihXNnhlrZvecjGIsoaDRacdkWkNa1eB1SIimgGMTKSxvtKDd50AklcG5fgcc1tNLbBc3RJGkgiZPNqEs7r2ULRb481YbrDSFV272lLFJdPodODqehGyxwGaXoKgaPo+ksKbVM21sy9efZ+vd/zkUBYSEgMOK7hYPmtwyNCFwMBTHUDyVnQe63Yf3Bifw3rFx9HYF4LBZCy7UUqqGD45PIODKbj+uqLBI2c+kuBZ+OsVJ3HBMQaPLhuG4giUN7mk/o3KlKpFUZlZ6F+slkSxnscyIsdinz5vptyB/gOy2C9rgUNRpt7OYe/OJFgom0VXqanCXTSrN7j2baXv5P876oh6QgMkMsMRjByTgSDiZW5L6zYExpDVtxtvH/7n7ODKqQItXnnF6vXzT/bhXUzM7OplGWhNodFjR5rWjP5yAHRa47dn5gBtd2cFk+0NxhJMqNp/rK1hG2++wIpFWMZlWsdxXuIz3wVAc4ykVDU4bBidiuKjdV7Av+QlLuWO4emUzfv7uUdglCauCbkiShGhaRSyVASDQ4SstTdHNVH8edMsldxcGJxLYfTKKRqcNLR4Hlgdd2HxuA/YNxfDhySguW9ZU8D0aiqewrNGFkck0wooCqyThsmWNcNiyA/JeORCq2NgWJ3HRlIKA045IKlP2M9It9qTILItlRozFcrEwnZl+C/LPl5YG97RLGS/23nyihYJJtAnKDRSsJqmpdnu6/B/niVQGTquEhJKdEsxps0BIEiIJBUD2x/vN/lEE3XYomsgtq62vnqe/x9IGZ26Jbd1MDd5MP+7V1Mw2uWXIFgnJqZKPFY3AsYkkrJIF69o8WNfmhaoB3U0ejCQUxNIKPh1JwCoJ2KwSVjV7oAiBq1c246IVLQWN0FA8hY6AEx7ZiuFYGv81OIFLz23IJSl6wjLTMVy+LFiS8OqD22aaISL/4kdfdKbBYc1+1t7sjCH65zI4kcD7gxHINgktXhlp9fSiKVuWNiAUSxe8l75t2WLB20fDWOqxY22LBw6bFccmkhBCwDm1zPhMjW1xEudzZFefDDhPl8eUS+oWe1JklsUyI8ZiuViYjhkdK7xwJVoYLPO9A/VGT9ASGTW3ct2rh0ZwIpI8623rP84umxXQBDRNwsXtfpzjk5HMaEhlVPgc2YRocCKJwYkUJElCg8OG9NSy2qmMWnD7X2/w8s3U4OX/uOvT2+Un5vr+hWLZ6fuKk7medh+CLjvCSQVxJVtLHXDJ+JelDfju5vPw9Z5O/HtPJ77e04mvXXgOTkYVqKqGgEPGho4AljScvhCYab8uaPNCQMInwzFoU+UeegnCTMfQ0+5DJJVBNJUp+btq4tPT7oPXYcX5rR6savEgkVGxZyiKnjZf7nM5GVVwSVcASxtcSGc0uGxWuO0WDIwlpv3s9ekRH7hiBb54biNUDXDZrGh22bGkwVX2WIoVH1ur145wIoNWj33GYzX6HaHyqjk/6sHZnEP1osPvxLXdLfj3nk5c291iOMajk2l45MJZaTyyterSLSKaG+yJNlm5HoRwIo3/3H0cSxuchnqmpyubyK9ptlslLG1w5hb1WNMk4+3DYXw0FIXNKmEyrcJjt8Jlz/4g7w/F8cVzG3PvYbR3rFKvZKWa1g6/E/97XTve6B/FP4eiEJDQ2xnAlcuDJX9npKe8eL+Cbjsu7Qpgr8GZSc60F0mP1c7DY3DYJJzf6oVPOv09OJHXu/ybPcfR4pXhka3YcyKb7Mo2C0KxFNr98ow9k8Wf72/2HC/b2JbrJS4+tg6fE7dt8uNELD3jsc5HD2q91oPWc823rt4HiM6Fxd6bT7RQMIk2WXEyNzqZxqcjCaiqhk1d/qpr2yrVxOU3VJNpFZs6AphIKvhoKIYWjx3nBhxwWCV8NjUPaZNHhoBAKK4U9AgZbfDM+HHv8Dvx9Z7Oql5b7ftNt7DM5cuCJWUYlbZpNNHJj5UFApJkwZ4TUfR0+NDklkuS2vxFVno6fLl676BbNtwzaTQe5Y6tp8J7zHVSVE09aL0m2fViLi8W6vG7sFhKf4gWOibRJitOag6Hs/W8QY8jd7sdqFzbVk1NXHFD9cqBEM7xO+Fz2LDr+ATSGQ2rmySMJTKwW7Kr//Wd11i2x7faRudMftzPppGr9v2M7JfZDVR+rPxOGWlNhdtuweFwomRVwuL3b3TZIVuzM5Kcya39uWps5zIpqvTd56Ar0tXrd4G9+UQLA2uiTVZcDxiKpaGJ7FLYumpq286kJi7/b5Y1ujCpaHDLNrS6bdjYFcDyJheuXB6c9u+rYbSu82xrxKt9PyP7ZXZtav7nvjyY/dwFBCamvgfF9aBmvn891tlW+u7PVNNOi0s9fxfOtq6aiGYfe6JNVtyDoC9lnL9ASDXlD2dSNtHkzi4LPRxXEEllYLUA0aQCu9UKl81qWk+GkV5JM0aZV/t++mv0Xm+9IZ0ukTarUcqPVdBtx8XtfuwbigGaNu3nbub711udbaXvPmcLIR2/C0Q0n5hEz4L8ZG48oeDT0CQAoCvgrPp2+5ncpu/wynhx/xAaXTYEnHZMJBXEFQ23re9ET2fAlGMzai4bufm6tVscK7tVwvIml6H3rce6zjNV6bu/kAZdMa6zayF9F4io/rCcwyB9Dujf7DmOVw6EypYl5JcwrGrxYE2LC5+OxHBwZLLq2+1ncpv+RCyNS7oCCDhkRJMZBBwyLukK4MQ89srM5fRo83Vr92xLKmZzWsSFqNLnuVCmUGNcZ99C+S4QUX1iT7QB1fZ0FpcwLGlwo9Ell12wY6aeKqO36Ucn0+gKOLGk4XT9dfGy23NtLkeZz+etXSOlJMW4sEKpmb77Mw26qqWeX8Z19nEAHhHNJybRBlTbKFabzJldflCLtzbnspGbz+M/m1iyrtO4ckl2rc3UwLjOjXobE0BECweTaAOqbRSrTebM7qmq1blF56qRM3r8ZvZank0sa/HiZyGqtZ5fxpWI6LRaulNoFtZEG1BtfW+1dXrVTmNXTR02UJ/TnRlh5PjNrlc9m2V6WddpjlpbKplxJSLKqtcxIuyJNqDans5qSxiq6akyeot6od3aNPvKtNrjN7vX8mx6HVnXaY5a6/llXImIsmrtTqFZmEQbYKRRrCaZqyYpr9cvHjC/Naxm16uebSlNNd+XerwVZqZaLGdaaBe1RESzoV7HiDCJrsKJSBL/OBXDwMmJkuRFL7U4k8SmmqS8Xr94wPxeIJjdaznbvY61NmiuFrHnl4ioNtXanUKzMImuQE9eupq9JckLgLNObCr1VNXrFw+Y3wuE2ei1nM1ex3q+I2Em9vwSEdWeWrxTaAYOLKxAT178TnvJAh5zsbhHPQ9OmsuFWIottEGYtTZojoiIqFoLrc2tFnuiK6jUWzrbPan1fIt6vq9MF1KvZT3fkSAiovq3kNrcajGJrkBPXhrzHstPXuYisanHLx5Q3xcIZpvvCw4iIiIqxCS6Aj15iSQVaEKUJC9MbM5OvV4gmI0XHERERLWFSXQFevIyMJnBwGi8JHlhYkNzhRccREREtYNJdBU6/E5ctMKH0Dness8xsSEiIiJaXDg7BxERERGRQUyiiYiIiIgMYjkH1Qwua01EREQLBXuiqSboK0MmMipavDISmezqjyciyfneNSIiIqISTKKpJszF6o9EREREZmESTTWBy1oTERHRQsIkmmqCvjJkPi5rTURERLWKSTTVhJ52HyKpDKKpDDQhEE1lEEll0NPum+9dIyIiIirBJJpqgr4ypMtmRSiWhstmxdUrmzk7BxEREdUkTnFHNYOrPxIREdFCwZ5oIiIiIiKDmEQTERERERnEJJqIiIiIyCAm0UREREREBjGJJiIiIiIyiEk0EREREZFBTKKJiIiIiAxiEk1EREREZBCTaCIiIiIigxbsioUWi7Qo3pNmxpjUHsakNjEutYcxqT2MSW2ar7hUel9JCCHmaF+IiIiIiOoCyzmIiIiIiAxiEk1EREREZBCTaCIiIiIig5hEExEREREZxCSaiIiIiMggJtFERERERAYxiSYiIiIiMohJNBERERGRQUyiiYiIiIgMWpRJtKIoeOihh9Db24ve3l48+uij0DSt7Guj0SjuvPNObNiwAX19fXj22WcNPU/VMzMuO3bsQHd3d8G/7du3z8Vh1BUjMdGFw2Fs3rwZ/f39BY+fOnUKt956K3p6erBt2za89NJLs7nrdcvMmPzkJz8pOU8eeuih2dz9umUkLocOHcLNN9+MjRs34rLLLsNPf/pTpFKp3PM8V8xhZkx4rpjDSEz279+Pm266CevXr8eVV16JZ555puD5WjhPbHP+jjXgZz/7Gd555x08/fTTiMfjuOuuu+D3+3HrrbeWvPa+++7D8PAwfvvb3+LIkSP4/ve/j9bWVlx77bVVPU/VMzMuBw8exFe/+lXccccdub9xOBxzdiz1wkhMAGBsbAzbt2/H6OhoyXO333472tvb8cc//hG7du3Cvffei66uLlx88cWzfRh1xcyYHDx4ELfddhtuuOGG3GMul2vW9r2eVRuXeDyOW265BZs2bcLvf/97hEIh3HfffVBVFffeey8AnitmMTMmPFfMUW1MYrEYbr75Zlx99dV45JFHcOjQIXzve99Dc3MzvvKVrwCokfNELDLJZFJcdNFFYufOnbnH/vznP4stW7YITdMKXjs4OCi6u7vFwYMHc4/98pe/FNdff31Vz1P1zIyLEELccMMN4tlnn531/a5nRmIihBD/+Mc/xJe+9CVx3XXXidWrV4tDhw7lnnv//ffFBRdcICYmJnKP3XPPPeK73/3u7B5EnTEzJkIIcdlll4nXXntt1ve73hmJy2uvvSY2bNggUqlU7rG//vWvore3VwjBc8UsZsZECJ4rZjASkwMHDog77rhDZDKZ3GO33367uOeee4QQtXOeLLpyjv379yORSGDjxo25xzZu3IhQKITBwcGC1+7duxcNDQ1YuXJlwWv37dsHRVEqPk/VMzMuANDf349ly5bNzc7XKSMxAYCdO3fipptuwuOPP17y3J49e9Dd3Q2/31+wrb17987KvtcrM2MSj8dx8uRJnicmMBKXdevW4cknn4Qsy7nHJElCLBaDEILniknMjAnPFXMYicnq1avx2GOPwWq1QgiBXbt24YMPPsDmzZsB1E6bsuiS6KGhIXi9Xng8ntxjLS0tueeKX9va2lrwWEtLCzKZDEZGRio+T9UzMy6jo6MIh8P4+9//jq1bt+Kqq67CY489hnQ6PfsHUkeMxATIltjccsstsFhKf1bKxay5ubnsdmh6ZsZEr49+7rnncPnll+Oaa67Br3/964r11VTKSFza2trQ29ub+7+qqtixYwd6e3shSRLPFZOYGROeK+Yw+vul27RpE2688Ub09PTgmmuuyb2+Fs6TRVcTnUgkSmpj9avP4iSr0muNbItmZmZcjh07BgDw+Xx48sknceTIEfzoRz9CJBLBgw8+OFuHUHfM/H5Pty1VVZHJZGCzLbqfojNiZkz6+/thsVjQ2dmJp556Ch9//DEeeeQRqKo6bX01lXc2cXn44Yfx6aef4g9/+MOM2+K5YoyZMeG5Yo4ziYmmaXj22Wdx6tQp/PCHP8SPf/xj3H///TVzniy6s9HpdJYES/+/0+k09Foj26KZmRmXSy65BO+99x4aGxsBAGvWrAEA3HnnnbjvvvsKbtnR9Mz8fjudToyPj5dsy263MykwwMyYfPnLX8bll1+eO0+6u7sxPj6OHTt2MDEw6EzioqoqHnzwQfzpT3/CL37xi9zvFM8Vc5gZE54r5jiTmFgsFqxbtw7r1q1DPB7H/fffj7vuuqtmzpNFV85xzjnnIBqNIpFI5B4LhUIAsrd0il+rP6cbHh6G3W5HY2NjxeepembGBUDJ579y5UpkMhmMjY3Nxu7XJSMxqWZbxTELhUIlt+NoZmbGRJKksudJKBSCEOLsd3YRMRoXRVFwxx134C9/+Qsef/xxbNu2rWBbPFfOnpkx4bliDiMxGRwcxFtvvVXw2KpVq6AoCmKxWM2cJ4suiV6zZg1cLhd2796de2zXrl1obW1FZ2dnwWvXr1+P0dFRHD58OPfY7t27ceGFF0KW5YrPU/XMjMsLL7yArVu3FtSrffLJJ/B6vWyIDDASk0rWr1+PAwcOIBaL5R7bvXs3enp6TNvfxcDMmPz85z/HjTfeWPDYJ598gmXLlkGSJFP2d7EwGpcf/OAHeOutt/DUU09h69atBc/xXDGHmTHhuWIOIzH58MMP8Z3vfAfxeDz32L59+9DU1IRgMFg758mczgVSIx5++GFx1VVXid27d4t3331XbNmyRTzzzDNCCCHC4bCIRCK5127fvl1cf/31Yt++feLVV18V69evF3/729+qfp6qZ1Zcjh07JtavXy8eeOABcfjwYfHGG2+ILVu2iF/96lfzclwLmZGY6I4dO1YynZqqquK6664T27dvFwcOHBAvvPCCuPDCC8WePXvm6lDqhlkx2bt3r1i7dq144oknxNGjR8WLL74oenp6xEsvvTRnx1JPqo3Lzp07xerVq8Xzzz8vhoeHC/4JwXPFTGbFhOeKeaqNSSwWE1dccYX49re/Lfr7+8Vrr70ment7xY4dO4QQtXOeLMokOplMivvvv1/09PSISy+9VDz66KO5OQpvuukmcffdd+deGw6Hxbe+9S3xhS98QfT19YnnnnuuYFuVnqfqmRmXXbt2ia997WvioosuEn19feKJJ54oO48uzcxITHTlEjb98W984xti3bp1Ytu2beLll1+ek2OoN2bG5PXXXxfXXXedWLdundi6dav43e9+NyfHUI+qjcvdd98tVq9eXfZfMpkUQvBcMYuZMeG5Yg4jv18DAwPim9/8pli/fr3o6+sTTz/9dMG2auE8kYRgQQ8RERERkRGLriaaiIiIiOhsMYkmIiIiIjKISTQRERERkUFMoomIiIiIDGISTURERERkEJNoIiIiIiKDmEQTERERERnEJJqIiIiIyCAm0UREREREBv1/MEM6mlIj+RgAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = plot_expectedness_vs_uncertainty(df, test_ix, y_val, second_order_std)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "russian-pixel",
   "metadata": {},
   "source": [
    "## Uncertainty vs absolute error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "united-guarantee",
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_absolute_error_vs_uncertainty(y_val, y_hat, std):\n",
    "    absolute_errors = (torch.abs(y_hat - y_val) / y_val).detach().numpy().flatten()\n",
    "    stds = std.flatten() / y_val.detach().numpy().flatten()\n",
    "    \n",
    "    a = absolute_errors\n",
    "    b = stds\n",
    "    alpha = 0.3\n",
    "    \n",
    "    _, ax = plt.subplots(1, 1, figsize=(8, 8))\n",
    "    ax.scatter(a, b, alpha=alpha)\n",
    "    \n",
    "    X = a.reshape((-1, 1))\n",
    "    y = b\n",
    "    linreg = LinearRegression().fit(X, y)\n",
    "    print(f'R2: {linreg.score(X, y):.2f}')\n",
    "    print(f'Correlation: {np.corrcoef(a, b)[0, 1]:.2f}')\n",
    "    \n",
    "    y_fit = linreg.coef_[0] * a + linreg.intercept_\n",
    "    \n",
    "    ax.plot(a, y_fit, '-', color=palette[1], alpha=0.5)\n",
    "    \n",
    "    return ax"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "geological-insert",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "R2: 0.23\n",
      "Correlation: 0.48\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_absolute_error_vs_uncertainty(y_val, y_hat, first_order_std);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "tracked-mobility",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "R2: 0.24\n",
      "Correlation: 0.49\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_absolute_error_vs_uncertainty(y_val, y_hat, second_order_std);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "configured-hobby",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "R2: 0.24\n",
      "Correlation: 0.49\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_absolute_error_vs_uncertainty(y_val, y_hat, first_order_std + second_order_std);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "martial-advocacy",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "flexible-visiting",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}