07 - Box Plots with Matplotlib.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Boxplots With Matplotlib\n",
    "\n",
    "Boxplots are a great tool for data visualisation, they can be used to understand the distribution of your data, whether it is skewed or not, and whether any outliers are present. In this article we will look at what boxplots are and how we can display them using pandas and matplotlib.\n",
    "\n",
    "To accompany this article, I have made the following [YouTube Video](https://youtu.be/IpMhMUcmLJw)\n",
    "\n",
    "https://youtu.be/IpMhMUcmLJw\n",
    "\n",
    "## What are Boxplots?\n",
    "A boxplot is a graphical and standardised way to display the distribution of data based on five key numbers: The \"minimum\",  1st Quartile (25th percentile), median (2nd Quartile./ 50th Percentile), the 3rd Quartile (75th percentile) and the \"maximum\". The minimum and maximum values are defined as Q1 - 1.5 * IQR  and Q3 + 1.5 * IQR respectively. Any points that fall outside of these limits are referred to as outliers.\n",
    "\n",
    "Boxplots can be used to:\n",
    "- Identify outliers or anomalous data points\n",
    "- To determine if our data is skewed\n",
    "- To understand the spread/range of the data\n",
    "\n",
    "To construct a boxplot, we first start with the median value / 50th percentile (Q2). This represents the middle value within our data.\n",
    "\n",
    "A box is then formed between the 25th and 75th percentiles (Q1 and Q3 respectively). The range represented by this box is known as the inter-quartile range (IQR). \n",
    "\n",
    "From this box extends lines, which are also knwon as the whiskers. These extend to Q1 - 1.5 * IQR and Q3 + 1.5 * IQR or to the last data point if it is less than this value. \n",
    "\n",
    "Any points that fall beyond the whisker limits are known as outliers.\n",
    "\n",
    "\n",
    "\n",
    "## Importing Libraries and Data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The first few steps we will carry out in our Jupyter Notebook is loading in the libraries and data. In this case we are going to be using [lasio](https://lasio.readthedocs.io/en/latest/) to load our las file, [pandas](https://pandas.pydata.org/) for storing our well log data, and [matplotlib](https://matplotlib.org/) for visualising our data.\n",
    "\n",
    "\n",
    "Lasio is a library that you may not be familiar with, but it is used to load log ascii standard files which are commonly used within the oil and gas industry for storing and transferring well log data. You can check out my [first YouTube video](https://youtu.be/8U4gxMJybJs) which explains how to use this library."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import lasio"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next we will load in and view our data. We can do this using `lasio.read()` and passing in a text string. I have appended `.df()` to the end of this in order to convert it to a pandas dataframe.\n",
    "\n",
    "The dataset we are using comes from the publicly available [Equinor Volve Field dataset released in 2018](https://www.equinor.com/en/what-we-do/norwegian-continental-shelf-platforms/volve.html). The file used in this tutorial is from well 15/9- 19SR which contains a set of standard well log measurements."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = lasio.read(\"Data/15-9-19_SR_COMP.LAS\").df()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>AC</th>\n",
       "      <th>CALI</th>\n",
       "      <th>DEN</th>\n",
       "      <th>GR</th>\n",
       "      <th>NEU</th>\n",
       "      <th>RDEP</th>\n",
       "      <th>RMED</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DEPT</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3615.4340</th>\n",
       "      <td>95.7952</td>\n",
       "      <td>12.7249</td>\n",
       "      <td>2.3429</td>\n",
       "      <td>54.8754</td>\n",
       "      <td>44.5742</td>\n",
       "      <td>0.8941</td>\n",
       "      <td>0.8359</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3615.5864</th>\n",
       "      <td>94.2267</td>\n",
       "      <td>12.5961</td>\n",
       "      <td>2.3528</td>\n",
       "      <td>53.5158</td>\n",
       "      <td>62.1103</td>\n",
       "      <td>0.7367</td>\n",
       "      <td>0.8028</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3615.7388</th>\n",
       "      <td>101.3254</td>\n",
       "      <td>13.7632</td>\n",
       "      <td>2.3170</td>\n",
       "      <td>48.9803</td>\n",
       "      <td>71.9087</td>\n",
       "      <td>0.6423</td>\n",
       "      <td>0.7958</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3615.8912</th>\n",
       "      <td>99.5672</td>\n",
       "      <td>14.3249</td>\n",
       "      <td>2.2585</td>\n",
       "      <td>36.6762</td>\n",
       "      <td>44.8988</td>\n",
       "      <td>0.6571</td>\n",
       "      <td>0.7929</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3616.0436</th>\n",
       "      <td>100.5965</td>\n",
       "      <td>11.1429</td>\n",
       "      <td>2.2108</td>\n",
       "      <td>40.4632</td>\n",
       "      <td>49.5744</td>\n",
       "      <td>0.7442</td>\n",
       "      <td>0.7940</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4635.9044</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.7729</td>\n",
       "      <td>0.5978</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4636.0568</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.8369</td>\n",
       "      <td>0.6257</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4636.2092</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.8741</td>\n",
       "      <td>0.6888</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4636.3616</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.9002</td>\n",
       "      <td>0.8902</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4636.5140</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.9133</td>\n",
       "      <td>1.0363</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6701 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                 AC     CALI     DEN       GR      NEU    RDEP    RMED\n",
       "DEPT                                                                  \n",
       "3615.4340   95.7952  12.7249  2.3429  54.8754  44.5742  0.8941  0.8359\n",
       "3615.5864   94.2267  12.5961  2.3528  53.5158  62.1103  0.7367  0.8028\n",
       "3615.7388  101.3254  13.7632  2.3170  48.9803  71.9087  0.6423  0.7958\n",
       "3615.8912   99.5672  14.3249  2.2585  36.6762  44.8988  0.6571  0.7929\n",
       "3616.0436  100.5965  11.1429  2.2108  40.4632  49.5744  0.7442  0.7940\n",
       "...             ...      ...     ...      ...      ...     ...     ...\n",
       "4635.9044       NaN      NaN     NaN      NaN      NaN  0.7729  0.5978\n",
       "4636.0568       NaN      NaN     NaN      NaN      NaN  0.8369  0.6257\n",
       "4636.2092       NaN      NaN     NaN      NaN      NaN  0.8741  0.6888\n",
       "4636.3616       NaN      NaN     NaN      NaN      NaN  0.9002  0.8902\n",
       "4636.5140       NaN      NaN     NaN      NaN      NaN  0.9133  1.0363\n",
       "\n",
       "[6701 rows x 7 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "When we call the dataframe, we can see that we have a table representing the first 5 and last 5 rows of the data. Each column represents a logging measurement. Going from left to right, we have AC for Acoustic Compressional Slowness, CALI for borehole caliper, DEN for Bulk Density, GR, for Gamma Ray, NEU for Neutron Porosity and RDEP and RMED for deep and medium resistivity."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In order to work with some of the matplotlib plots, it is necessary to remove missing values which are represented by NaN. We can remove these by using `.dropna()`. Adding `inplace=True` allows us to remove these from the original dataframe rather than a copy of it."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.dropna(inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "When we call `df` again, we can see that the number of rows has reduced from 6701 to 6579."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>AC</th>\n",
       "      <th>CALI</th>\n",
       "      <th>DEN</th>\n",
       "      <th>GR</th>\n",
       "      <th>NEU</th>\n",
       "      <th>RDEP</th>\n",
       "      <th>RMED</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DEPT</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3615.4340</th>\n",
       "      <td>95.7952</td>\n",
       "      <td>12.7249</td>\n",
       "      <td>2.3429</td>\n",
       "      <td>54.8754</td>\n",
       "      <td>44.5742</td>\n",
       "      <td>0.8941</td>\n",
       "      <td>0.8359</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3615.5864</th>\n",
       "      <td>94.2267</td>\n",
       "      <td>12.5961</td>\n",
       "      <td>2.3528</td>\n",
       "      <td>53.5158</td>\n",
       "      <td>62.1103</td>\n",
       "      <td>0.7367</td>\n",
       "      <td>0.8028</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3615.7388</th>\n",
       "      <td>101.3254</td>\n",
       "      <td>13.7632</td>\n",
       "      <td>2.3170</td>\n",
       "      <td>48.9803</td>\n",
       "      <td>71.9087</td>\n",
       "      <td>0.6423</td>\n",
       "      <td>0.7958</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3615.8912</th>\n",
       "      <td>99.5672</td>\n",
       "      <td>14.3249</td>\n",
       "      <td>2.2585</td>\n",
       "      <td>36.6762</td>\n",
       "      <td>44.8988</td>\n",
       "      <td>0.6571</td>\n",
       "      <td>0.7929</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3616.0436</th>\n",
       "      <td>100.5965</td>\n",
       "      <td>11.1429</td>\n",
       "      <td>2.2108</td>\n",
       "      <td>40.4632</td>\n",
       "      <td>49.5744</td>\n",
       "      <td>0.7442</td>\n",
       "      <td>0.7940</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4617.3116</th>\n",
       "      <td>40.0000</td>\n",
       "      <td>6.0000</td>\n",
       "      <td>2.5547</td>\n",
       "      <td>87.1958</td>\n",
       "      <td>15.4080</td>\n",
       "      <td>2.6787</td>\n",
       "      <td>2.1338</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4617.4640</th>\n",
       "      <td>40.0000</td>\n",
       "      <td>6.0000</td>\n",
       "      <td>2.5662</td>\n",
       "      <td>90.9071</td>\n",
       "      <td>15.8777</td>\n",
       "      <td>2.6239</td>\n",
       "      <td>2.0865</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4617.6164</th>\n",
       "      <td>40.0000</td>\n",
       "      <td>6.0000</td>\n",
       "      <td>2.5702</td>\n",
       "      <td>86.2190</td>\n",
       "      <td>15.8576</td>\n",
       "      <td>2.5898</td>\n",
       "      <td>2.0461</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4617.7688</th>\n",
       "      <td>40.0000</td>\n",
       "      <td>6.0000</td>\n",
       "      <td>2.5674</td>\n",
       "      <td>74.8791</td>\n",
       "      <td>15.3727</td>\n",
       "      <td>2.5694</td>\n",
       "      <td>1.9925</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4617.9212</th>\n",
       "      <td>40.0000</td>\n",
       "      <td>6.0000</td>\n",
       "      <td>2.5552</td>\n",
       "      <td>64.8674</td>\n",
       "      <td>14.8943</td>\n",
       "      <td>2.5456</td>\n",
       "      <td>1.9997</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6579 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                 AC     CALI     DEN       GR      NEU    RDEP    RMED\n",
       "DEPT                                                                  \n",
       "3615.4340   95.7952  12.7249  2.3429  54.8754  44.5742  0.8941  0.8359\n",
       "3615.5864   94.2267  12.5961  2.3528  53.5158  62.1103  0.7367  0.8028\n",
       "3615.7388  101.3254  13.7632  2.3170  48.9803  71.9087  0.6423  0.7958\n",
       "3615.8912   99.5672  14.3249  2.2585  36.6762  44.8988  0.6571  0.7929\n",
       "3616.0436  100.5965  11.1429  2.2108  40.4632  49.5744  0.7442  0.7940\n",
       "...             ...      ...     ...      ...      ...     ...     ...\n",
       "4617.3116   40.0000   6.0000  2.5547  87.1958  15.4080  2.6787  2.1338\n",
       "4617.4640   40.0000   6.0000  2.5662  90.9071  15.8777  2.6239  2.0865\n",
       "4617.6164   40.0000   6.0000  2.5702  86.2190  15.8576  2.5898  2.0461\n",
       "4617.7688   40.0000   6.0000  2.5674  74.8791  15.3727  2.5694  1.9925\n",
       "4617.9212   40.0000   6.0000  2.5552  64.8674  14.8943  2.5456  1.9997\n",
       "\n",
       "[6579 rows x 7 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Simple Box Plots Using Pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now that our data has been loaded we can generate our very first boxplot. We can do this by typing `df['GR']` which selects the GR column from the dataframe, followed by `.plot()`. \n",
    "\n",
    "Within the arguments for the plot method, we pass in `kind=box` to tell the function we want a boxplot."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Simple boxplot using pandas\n",
    "df['GR'].plot(kind='box');"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "When we run this cell, we get a very basic looking box plot. We have the inter quartile range box, which contains the median line. Extending from either side are the whiskers which extend to 1.5 times the inter quartile range. And then at the top here we have a series of circles, which represent outliers.\n",
    "\n",
    "### Boxplots with Logarithmic Axes\n",
    "\n",
    "We can look at another curve, in this case RDEP (deep resistivity)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Viewing logarithmically scaled data\n",
    "df['RDEP'].plot(kind='box');"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If we repeat the same code as above, we can see that we have a tiny box down the bottom of the plot and a large number of outliers above that. From experience and prior knowledge, RDEP is usually plotted on a logarithmic scale and can range from lows of around 0.01 ohmm to around several thousand ohmm.\n",
    "\n",
    "To solve this we can switch the Y-axis to a logarithmic scale by adding in `plt.semilogy()`. You will see here that we are now using matplotlib notation, and that is because pandas is calling upon matplotlib to build this box plot."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df['RDEP'].plot(kind='box')\n",
    "plt.semilogy();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Making Boxplots Horizontal\n",
    "\n",
    "If we prefer to view our boxplots horizontally, we can add in a `vert` argument which is used to tell the plot to appear either vertical (True) or horizontal (False). By default, it is set to True. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Rotating the box plot so it is horizontal\n",
    "df['GR'].plot(kind='box', vert=False);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Boxplots with Matplotlib\n",
    "\n",
    "The above code cells have been done using the pandas wrapper around matplotlib, if we want to use matplotlib functions and syntax we can generate the same plot as follows. First we call `plt.boxplot()` and then set the x argument to `df['GR']`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWoAAAD4CAYAAADFAawfAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAAAPMklEQVR4nO3dX2xc6VnH8d8z45NxsnFsTzKyo9rj8aJKuBOhko1QkaoVWsRC92ZB6sVGkehFpUoLjuCCC0eWaLgEyVwgIayirtQg7BYKiN4gbWFWQr5gi1N2tynVtim0gtWyobBZwBeYPw8Xc85wxpk/HnuSeWb0/UhHHp/znvc877yvfztzxvGauwsAEFdh1AUAAHojqAEgOIIaAIIjqAEgOIIaAIKbehydXrp0yWu12uPoGgAm0t27d3/g7pVOxx5LUNdqNe3v7z+OrgFgIpnZ97sd49YHAARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AARHUANAcAQ1AAQ39kFdLpdlZqfadHv21H1kW7lcHvVTAmDCTI26gNN6//335e6n6+T27On7SJnZUPoBgMzYv6IGgElHUANAcAQ1AARHUANAcAQ1AARHUANAcOGCml9vi4l5AUYnXFADANoR1AAQHEENAMER1AAQXN+gNrNXzOyBmd17EgUhnt3dXUlSoVBQkiStP0C1vLysmzdv6sqVK4/8carz589rd3dXu7u7Wl5ebu2/ePGilpeXH+kr6y+7Vqcarly5omKxqCtXrrS163WsV5vT9Hmcaw7S7qTt+5138+ZNTU9Py8w0PT2tmzdvdjxneXlZy8vLA48nm/+j53Wb937tsq1QKHT8o2fZGsnqKBQKmp6ebvuan99830mStB3Pj6lTu+w5OVrLxYsXT7weTszde26SnpV0VdK9fm2z7ZlnnvGTapb0+Np39NkLp+8jNZR6AtnZ2fHV1VWX5JcuXfJyueyLi4t+69Ytn52d9UKh0Do+PT3tCwsL/txzz7kkT5LEL1y44IuLi/7qq6/6xsaGF4tFP3v2rM/MzPj58+e9UCj49evXfXFx0efm5rxSqfjOzk7HGhqNhh8eHnqj0fDV1VXf2dnpeazX+ZVKxSuVyon6PM41B2l30vb9znv++ed9amrKt7a2/ODgwLe2tnxqasrX19fbzrlz544vLi765cuX/c6dO8cez+bmpk9NTfnm5mbbddfX171SqTwy73Nzc239Z+3OnDnjkvzcuXN+7tw5l9TaSqWSm5mfO3fOZ2dnfXZ21i9cuOCVSsU3Nzd9dXXVb9y44cVi0W/cuOGrq6u+ubnplUrFZ2Zm/PLly76xseELCwteLpfbzsvmOqt1Y2PDFxcXvVwu+8zMjM/NzfnZs2ddks/MzPji4qJfv37dC4WCX7hwYeD10I+kfe+Ww90OeHtY1wjq45m0oK7X695oNFyS12o1bzQa3mg0vF6ve61W84WFBZfk8/PzbcdefvnlVlg3Go1WX1tbW54kiSdJ4rVazbe2tlrXqNVqXqvVvF6vd6whL7tOr2O9zs+udZI+j3PNQdqdtH2/88zMt7a22vZvbW15qVRqOyd7nL/WccaTzWe+XaPR8FKp1For+Xb5uc23y6+fWq3mxWLRC4VCa/1k52ZbtnayevJ15Ndmtvby4zt6Xtb2aLvsGkmSeLFYbHt+sjU86Hro54kEtaTPSNqXtF+tVgcq8EixA2+nNuSgntStUCj44eGhHx4eeqFQaP0wZVv+2MOHD9v2u7sXCgU/ODho7TczPzg4aPVrZq1+87Ljefkauh3rdX6hUHAzO1Gfx7nmIO1O2r7feZL84OCgbX/2/OfPOTqvxx1PNp/5dtl1zeyRec/PbdYuW0NZ30fXVDaGbL7y7fPn5NdRfm1m32fjy/rIt8tqzbfLxtBpbeefw9PM21G9gnpoHya6++fc/Zq7X6tUKqft69hbRIPUH32r1+tqNBqSpGq1qr29Pe3t7WltbU3ValULCwuSpPn5+bZjt27dkiQlSaK9vT1J0tramra3t5UkiZIk0crKira3t7W2tqa9vT2trKyoWq1qbW2t7fnMjudl1+l1rNf51WpVKysrJ+rzONccpN1J2/c7z8y0vb3dtn97e1ulUqntnOxx/lrHGU82n/l2e3t7KpVKWllZeWTe83ObtatWq5Kk2dlZ7e3tqVqtqlgsqlBoRlOSJK1zs/WRJEmrr6zO/DrK1ma29vLjW1lZaWu3trbWqjXfLlufSZKoWCy2PT/ZGh50PZzKMcOwJm59HMtQ6gmEe9Tco+52He5Rc4/6sbXviKDuaWdnp/VWcGpqqvVDtLS05Ovr616v1x95u/rUU0+1fhCWlpZa+8vlsi8tLT3SV9ZfrxCr1+teKBS8Xq8/EsTdjvVqc5o+j3PNQdqdtH2/89bX171UKrVCb319veM5S0tLvrS0NPB4svk/el63ee/XLtvytx06rZGsDjNrhXn2NT+/+b6npqbajufH1Kld9pwcraVcLp94PfTSK6jN+9w+MLNdST8h6ZKk9yR91t0/3+uca9eu+f7+fs9+e1xvoFsag7bv6PasdPuD0/UxzHoCmtRxAVGY2V13v9bpWN//Z6K7Xx9+SQCA4+JfJgJAcAQ1AARHUANAcOGCmg+sYmJegNEJF9QAgHYENQAER1ADQHAENQAER1ADQHAENQAENxFB3el/2TPINow+sm1+fn7EzwaASdP3b31EN6zf7/XbQ+kGAIZuIl5RA8AkI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCI6gBIDiCGgCCM3cffqdm/yzp+wOccknSD4ZeyJM3KeOQJmcskzIOaXLGMinjkIY7lhV3r3Q68FiCelBmtu/u10Zdx2lNyjikyRnLpIxDmpyxTMo4pCc3Fm59AEBwBDUABBclqD836gKGZFLGIU3OWCZlHNLkjGVSxiE9obGEuEcNAOguyitqAEAXBDUABDfyoDaznzGzt83svpltjLqeQZjZ98zsG2b2hpntp/vKZvZVM/tO+nV+1HV2YmavmNkDM7uX29exdmv6rXSO3jKzq6OrvF2Xcdw2s3fSeXnDzF7IHbuVjuNtM/vp0VT9KDNbNrPXzOxvzeybZvZL6f5xnJNuYxmreTGzaTP7mpm9mY7j19L9q2b2elrvl8zsTLq/lH5/Pz1eG1ox7j6yTVJR0nclPS3pjKQ3JX1klDUNWP/3JF06su83JG2kjzck/fqo6+xS+7OSrkq61692SS9I+jNJJuljkl4fdf19xnFb0q90aPuRdI2VJK2ma6846jGktV2WdDV9PCPp22m94zgn3cYyVvOSPrfn08eJpNfT5/oPJL2U7t+W9HL6+BckbaePX5L0pWHVMupX1D8m6b67/527H0r6oqQXR1zTab0o6Qvp4y9I+tnRldKdu/+lpH89srtb7S9KuuNNfyVpzswuP5FC++gyjm5elPRFd/9Pd/97SffVXIMj5+7vuvvX08f/Lulbkj6k8ZyTbmPpJuS8pM/tf6TfJunmkp6T9OV0/9E5yebqy5J+0sxsGLWMOqg/JOkfct//o3pPaDQu6VUzu2tmn0n3Lbj7u+njf5K0MJrSTqRb7eM4T+vpLYFXcrefxmIc6VvmH1XzFdxYz8mRsUhjNi9mVjSzNyQ9kPRVNV/tP3T3/06b5GttjSM9/oGki8OoY9RBPe4+7u5XJX1C0i+a2bP5g958DzSWv/84zrVL+h1JPyTpo5LelbQ10moGYGbnJf2RpF9293/LHxu3OekwlrGbF3f/H3f/qKQlNV/l//Ao6hh1UL8jaTn3/VK6byy4+zvp1weS/kTNiXwvewuafn0wugoH1q32sZond38v/QH7X0m/q/9/Gx16HGaWqBlsv+/uf5zuHss56TSWcZ0XSXL3h5Jek/Tjat5mmkoP5WttjSM9PivpX4Zx/VEH9V9L+nD6KeoZNW/Af2XENR2LmT1lZjPZY0nPS7qnZv2fSpt9StKfjqbCE+lW+1ck/Xz6mwYfk/RB7u14OEfu1f6cmvMiNcfxUvrp/KqkD0v62pOur5P0XubnJX3L3X8zd2js5qTbWMZtXsysYmZz6eOzkn5Kzfvtr0n6ZNrs6Jxkc/VJSY30XdDpBfhk9QU1PxX+rqTNUdczQN1Pq/lJ9ZuSvpnVruY9qb+Q9B1Jfy6pPOpau9S/q+bbz/9S8z7bp7vVruan37+dztE3JF0bdf19xvF7aZ1vpT88l3PtN9NxvC3pE6OuP1fXx9W8rfGWpDfS7YUxnZNuYxmreZH0I5L+Jq33nqRfTfc/reZ/SO5L+kNJpXT/dPr9/fT408OqhX9CDgDBjfrWBwCgD4IaAIIjqAEgOIIaAIIjqAEgOIIaAIIjqAEguP8Da4HJCZutefsAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Using matplotlib to make a boxplot\n",
    "plt.boxplot(x=df['GR'], vert=False);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Styling the Boxplot\n",
    "\n",
    "Matplotlib plots are not very stylish and the code used to generate them is very low level. This is why there have been a number of libraries, such as seaborn, that have been developed based on matplotlib, and bring in so much more to make the visualisations more appealing. \n",
    "\n",
    "First, we will add some colour to our plot by changing the colour of the outlier circles. To do this we create a new variable called `red_circle` and then we create a dictionary. Within this dictionary, we will set the the `markerfacecolor` and `marker`. These will be set these to red and to a circle respectively."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Changing the outlier markers\n",
    "red_circle = dict(markerfacecolor='red', marker='o')\n",
    "plt.boxplot(x=df['AC'], vert=False, flierprops=red_circle);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "When we run this code, we now have some colour to highlight our outliers.\n",
    "\n",
    "On the current boxplot we have the median value represented by an orange line within our IQR box. We can also add on the mean of our data by creating another dictionary variable called `mean_shape`. \n",
    "\n",
    "We set up the same parameters as before for the `markerfacecolor` and the `marker`, which will both be set to green and a diamond. To choose a diamond, we can use the letter D. \n",
    "\n",
    "Additionally, we will change the edge colour of our mean marker by adding in a `markeredgecolor` variable. By default it is set to black, but here we will set it to green."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Adding the mean\n",
    "red_circle = dict(markerfacecolor='red', marker='o')\n",
    "mean_shape = dict(markerfacecolor='green', marker='D', markeredgecolor='green')\n",
    "\n",
    "plt.boxplot(x=df['AC'], vert=False, flierprops=red_circle, \n",
    "             showmeans=True, meanprops=mean_shape);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Adding a Notch\n",
    "\n",
    "Instead of representing the median as a line, we can represent it by using a notch instead. This is done by simply by adding the argument `notch` and setting it to True."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Adding the median notch to the box\n",
    "red_circle = dict(markerfacecolor='red', marker='o')\n",
    "plt.boxplot(x=df['DEN'], vert=False, flierprops=red_circle, \n",
    "             showmeans=True, meanprops=mean_shape, notch=True);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Displaying Multiple Boxplots on a Figure\n",
    "\n",
    "There may be occassions where we want to create multiple boxplots on the same figure. The simplest way is to call `df.plot()`, and pass in `kind=True`. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Displaying all columns in the dataframe on a single figure\n",
    "df.plot(kind='box');"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This generates a plot with all of our columns, but it is not very appealing. Also, all of our measurements are on different measurement ranges. GR can typically range from 0 to 200 API, whereas DEN typically ranges from about 1.5 g/cc to around 3 g/cc.\n",
    "\n",
    "This can make it very difficult to read and identify outliers within the data. To make boxplots with different y-axes and to make a figure that is readable as well as useable we need to use subplots. If you want to find out more about subplots in matplotlib, [please check out my previous video which covers subplot2grid.](https://youtu.be/pPqLgmbyets)\n",
    "\n",
    "\n",
    "First we start be defining our outliers as a red underscore circle.\n",
    "\n",
    "```python\n",
    "red_circle = dict(markerfacecolor='red', marker='o', markeredgecolor='white')\n",
    "```\n",
    "\n",
    "We then define fig, axs as plt.subplots. In the arguments we pass in that we want 1 row, and then the number of columns. The number of columns will be equal to the length of df.columns. Finally, we will set the figsize to 20 by 10.\n",
    "\n",
    "```python\n",
    "fig, axs = plt.subplots(1, len(df.columns), figsize=(20,10))\n",
    "```\n",
    "\n",
    "We then need to create a small for loop which will loop over each of our plot axes. We are using the enumerate function here to keep track of i, our index value.\n",
    "\n",
    "```python\n",
    "for i, ax in enumerate(axs.flat):\n",
    "```\n",
    "\n",
    "Next we can add in our boxplot by calling upon `ax.boxplot()` and passing in df.iloc, which allows us to get columns by the index variable, i. We do this by creating square brackets, with a colon followed by a comma. This tells the iloc function to get all rows, and then we pass in the column index. Next we specify our outlier properties and pass in red_circle.\n",
    "\n",
    "```python\n",
    " ax.boxplot(df.iloc[:,i], flierprops=red_circle)\n",
    "```\n",
    "\n",
    "The next couple of lines allows us to set the title and the y tick label font size. At the end we call upon `plt.tight_layout` to space out the plots in a nice way."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABZgAAALICAYAAADyhJW9AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAACuXklEQVR4nOz9f3xcV33g/7/eihL/GCmBFCsJpYG0pTQLZtNguk0Q4BICbSkmJdml8oYQr782uxQvaaGwkGYbSNlS2kKoC13izTqQrAW7CQSFZvldlzqkXUzT4tAA2Q+BBfJDCgRHkn8EW+/vH2dUz8gjR7JmNNLo9Xw87uPMPffM6MjJ1dz7vue8T2QmkiRJkiRJkiTNVle7OyBJkiRJkiRJWpwMMEuSJEmSJEmSjosBZkmSJEmSJEnScTHALEmSJEmSJEk6LgaYJUmSJEmSJEnHxQCzJEmSJEmSJOm4GGCWJEmSJEmSJB0XA8yLWER8IiJyyvasGbzvhRHx3yLiaxHxSET8OCJ+GBF3RsRVEfGM+ei/NFcRcWpEvCkiPh0R90fEgYjYHxHfiogdEfHKiFgxzXv7IuKxKefPVx7n59W23TmD/q2d8p6rj+83leYmIp7W4PviUESMR8T3I+LvIuK6iHhRRESD91/d4P2NthumvG/nlON3NPjsqefJ5a37l5CaJyJOjojfioihiPhORIzVXFP9fUS8PyJ+PSJWTnnfDdOcPz+OiJGI2BURb4mI3nb9btJsTPMds6lBu7r/92vqp34PTLd9e8rnTf1uWvt4PzMintb8fwGp3jTnREbERPXa696IuCki+hu8d+q100T1HufhiPiniPh4RPyHiDh5lj/7qG3K+y4/Rtt9EfF/q+fTL7bq301LS5PPk4yIi6b5Ob/doO3VM/i8RtvlU97X6P5qX0Q8GOVa8MMR8YqIOKGJ/3QLlgHmRSoiTgd+rcGhjcd6T0R8GthZbfcvgCcA3cATgV8C3gF8usndlZouIl4DfBv4Y+AlwBnAMmA5cBYwANwCvGqaj7gMOHFK3bkR8S9b0V9pAToBWAk8GfhFYBPweeBLLbwBPz8ifqNFny3Nm4j4Tcp30J8DLwfOBCocuab6BeB1wG3Vcia6gScBzwPeBdwZEZWmdlyaP2+PKQ9XJBGUa6+fBf4t8MWI2DCD9ywDfgI4G7gI+ADw/yJiuvucZlsB/AzwGuBvI+KN8/RztTQdz3kC8DtHfVAJ7L6hud07phMo58tplGvBVwO3AndHxDnz2I+26G53B3TcXkPj/36XRsRbMvOx2sqIeBLw18DP1VQPU/5n/w7lJPiXwIUt6a3URBGxBfizKdV/BdwB7AeeArwIONZo/OkexmwE/uNc+ygtcLuBj1L+9v808OuUwBaUh41/GxHnZeZ907z/vwL/X4P6u2fws/8wIm7LzEOz7LO0IETEf6Dc3Ne6i/I9NEIJNP888AKgbwYf+V+AHwGnA5fWvOeZwL8Dts6509L8OwN4I3DNcbz3s8BnGtTvnVOPpPaZvO5aDpzHkYFiAfxRRHwoMyemee/vUoJWpwFrKUErgFOAj0TEqZn5FzP42bP10ep7TwTOAS6hDFAM4N0R8dnM/OpxfK40nbmcJwDPj4jnZGbtrORLgKceR19+d5r6Lx/jPd8C/oLyQOhM4FeBn6oe+3lgV0Sszczdx9GfRcEA8+L172pef5MjgeMnAeuAm6e0fw/1weVPAgOZOVbbKCJOpQSvpQUpIn6O8v/zpP3AKzPzUw3aXggcbFB/PuWP/KTac+jfRsTvZuZR75M6yNcy808md6qjzD5ICW5BuYm5AXjhNO//aGbuPM6f/QzKaOlj3QxJC1JEPB14X03VY8BlmXnUzXtEdAG/DOTUY1Nsy8xvV9/zWeB/1xz7F3PqsNRevxsRH8zM4Vm+70u131FSB5h63fW3wL+q7q6qbg81euPUcyEiLgFuogSxAP4sIj6fmd+cyc+ehU9l5g01P/e/AG+t7nYBFwMGmNVMx3ueHKY8hIEyivnf1hz7nQZtHtdxnjPfndL/buAPgLdUqyqUh0JnZ+aPj+PzFzxTZCxCEfF86oPF/xn4Rs3+xintT6P+JHuIBsFlgMz8YWa+t4ndlZrtDdQ/HPvPjYLLAJn52cz8YoNDtefIj4DX1uyfSpl6Ji0ZmbkP2ADsqal+QZPz7O0F9lVf/35E9DTxs6X58gbq0yv9fqPgMkBmTmTm5zPzC7P4/O9P2X94th2UFoAHqmUv8Pvt7Ii0QNX+rZ8AHpnpGzPzZsr9/6Ru4IrmdOuYpq6jccY8/EwtbTM9T74HTI5a/tcR8ZMA1dzNk/cyt7aig8eSmYcy8z8Bt9dU/wzQsekCHcG8ONUGx0aBIcpozKurdS+JiKdk5veq+79M/cOEjzQKLkuLxAU1rxP477N5czWo9W9qqm7JzJ0RcR8ldzOUGQLHM5VMWrQy81BE/Heg9iHjBcD/adD8VRGxpkH9RzPzu9P8iB8B/wN4G2WE9O9i4EGLT20qsQS2NeNDIyIoKTJqp2RO4HeRFqcbgN+kXFdtjohrM/PeWbz//Ih4U4P6L2Xml5rRQakdImI5cD713yU3T01vOQP/jZKrf3Jh5guO0faZ05xPd083SGcaz5uy/0DDVtIcHed58h7KfcaJwBbgP1HSNNUev3gWfWh0zhzvyOZt1K+fdgHwP4/jcxY8A8yLTJQVxf91TdWtmbk/InZwJMDcBVxOGY4PR/K+TPp6K/sotVjt/8/DmfnDWb7/VUDtyMkd1XKQEvgCeHFEnJmZ/+84+ygtVt+Ysv+Uadr9+2nqdwPTBZgB/gjYTEnn9MaIME2GFpvac2IkM39QezAiHqYsxFQnM2NqXY1Guc5HgP+QmTPJay4tNI8BV1KusbopgbAZ39hTggqN1oV5O2CAWYvRa6oLlE91K+W6aFYy84cRMcKRnP3TXa8BrKluU30IOFaA+Veq6zh1U3Iw18YgJoCPzbjD0szM5Tz5n5Tvmp+iPNgcpKSOBfi7zPxSeZY/Y388Tf3xBJhnen+16JkiY/H5TcqKmpP+B0B1VEBtsvANMcszSFoiavOX3w/srL7eUVPfRUkXIC01U783Hi937Kxk5qMcWfCpwpEHo9Ji1NTzo8ZhysJ+H2/R50vz4SMcmbL8yog4r52dkRagrwJXZebxLl5Ze83Wiu+jV1GCbH9YfT0ZO0rgrZn5jy34mdJUMzpPqouHTy6K/ETKmmOT/8++p+Gb5k9L768WEgPMi09teoxh4HM1+7UBsp+mrDILJSdNrZ9HWrxq/3/uqy5MOSMR8fOU6TaTPjK5Em1mfo36hSou9yGNlqBnTNmf+v0x6ZczMxpsO2fwM/4C+P+qrzc2+JnSQvZ430H/mZLmYjYrhP8XSrqYv6/unwC8A7j2OPsotV1mJvDmmqp3z+Ltb5/mO+bqKe2mTpde0eCzptbNNhWB1Ay7KefDdcCBat2zgb+JiJ+Z7YdFxE9QZoNNmu56DeBD05xPl8/iRx4EvgXcCDwvM2dzPkszNdfz5DpKClk4Mkr4O8Ats+3INOfM8cYGZnp/tegZYF5EIuKZHFlFE8qUmEMRkRGRHP1kZjIY/QXqn5K8KiIqreup1FK1D1WCkg5mpjZO2f+dyfOneg49u+bY0zh2PjOpo1RXOp46cv/zzf451VWTJ9PRdFO/UI200H225vVR30GZ+YFqfr6vzeIzt2XmOygPQGtznr8+Iv7VNO+RFrzqApf/u7rbT+O0F3MxMmX/rAZtfrrm9QTwgwZtpFb7Wmb+cWa+FhioqX8CR0ZdzsZG6kdFNv16DdhQE1hbnpk/k5mXZeadLfhZEszxPKmOcp66PtOfZebh5nXxuGyast+K83VBMMC8uEwNjj2eV0bEKZn5ENVUGlWnA/+jUZA5Ik6NiCvm0Eep1f4MOFSzf01EvKRRw4h4cUQ8v/r6ROCyWf6sf/f4TaTFLyJWUC7IVtdU78zML7fi52Xm/+RIIO3JrfgZUov8GfDjmv0/iIhfm67xbGTmQeANNVVBGd0sLWZvpgR2ofl/76cGul5XzRkLQES8nPrcs3dVzzOpbTLzVuDTNVW/Onm/MhMRcTFH0o1BuS+6timdkxaIOZwn11JSjQE8SlkQsy0iojsi3gX8ak31vXRwCjQX+VskIuIk4NU1VcPAXzVougp4UfX1CmA9ZTry7wC/BPxs9dgrgG9FxMcp0wZWAv+SMrLgIfyS0gKVmd+IiN8F3lutWgl8OiK+ANwB7KdMibmAMh1lA/A3wK9zZCEMgL8Dvt3gR/wiR0bA/EZEPDEzH2nQ7jkRMd0U6Ksz85Mz/62keTe5ovhy4Gco50ftVMuHOHYe8ldFRKMFY/Zm5rYZ9uF3gb+eYVtpQcjMb1bPnfdVq1YAfxkRuyjfNY9SvmuOawZMZv5tRHwOeHG16kUR0Z+Zu+bYdaktMvPuiPgQs1vb4vzqedbIddV8/pOfvZMjaQGfCfx/EXE30As8a8p7/2wWfZBa6RrgpTX7v8+Rv/t1qufCCZTvlrXAuVOabKmuxzSdZx7jfPpoZh5rcWapnWZ8nkzKzG9HxIXAKcCDk98Xs3WMc+buzJxuccyfqr7vJOBM4Ncoiw5OGgcGqvmiO5IB5sVjHfU3/9dm5h9ObRQRK4EHgJOrVf8O+IvMHImIF1LyJk0GoPuA17auy1JrZOa1ETFKucGfHIn/Io78v91I7QyAw8AlmXlU/qOI+LfATdXd5ZSHNO9v8Hk9wHOm+VlPmqZeWiimW1EcyoOaSzPz28d4/7+fpv47wIwCzJn5xYi4DXj5TNpLC0Vm/llEPEoJVvVWq/urWyM/nOWP+APqb6Cu5nFuqKQF7irKQuWNciQ3ciHTp9O4mfIgZ9KllOnGkzkuT6Z+vY1Jf56ZH57hz5daKjPvmPJw5IJjPEz842k+5hHg31dnhR3Lsa75dgMGmLUgzfI8qX1fo4GYszXdefchYLoA808f433/BKzv9MUxTZGxeNQGxw4B2xs1ysx91KfDWBMRz64euz8zL6CMqvnvwD2UC7TDlC+ov6Xkwnwp0gKXmdcDTwXeQsnL/CBl4ZaDwH2U1csvAT4aEU8GfqXm7f+7UXC56hbK+TBptqlppMVigjLi/wHgy5TA8Isys/9xgsvN9BaOTGOTFo3MvIGSq/9NwGco59FByvfQMGXq/p9TZoydMcvP/mvKaOhJF0TEdMFracHLzO/TotmR1c8+l5Je5q+Ahyn3Svspi5LtAC7IzC2t+PnSHFwzZf/qadolJTXTDyn377dSHvSfOYPgsrTYzfQ8WSiSskDhQ8BdlAGerwCe3enBZYAoC/xKkiRJkiRJkjQ7jmCWJEmSJEmSJB0XA8ySJEmSJEmSpONigFmSJEmSJEmSdFwMMEuSJEmSJEmSjkt3uzswE0960pPyaU97Wru7oSXoK1/5ysOZuard/ZgNzxe102I7Zzxf1E6eL9LMLbbzBTxn1D6eL9LMeb5IszPdObMoAsxPe9rT2L17d7u7oSUoIr7T7j7MlueL2mmxnTOeL2onzxdp5hbb+QKeM2ofzxdp5jxfpNmZ7pwxRYYkSZIkSZIk6bgYYJYkSZIkSZIkHRcDzJIkSZIkSdIMRMQLImIoIr4fERkRl9ccOzEi/igivhoR4xHxQETsiIgzp3zGsojYGhEPV9sNRcRT5v2XkZrEALMkSZIkSZI0Mz3A3cAbgP1Tjq0EzgXeWS1fAfwU8KmIqF0H7VrgYmAAeD5wMvDJiDihpT2XWmRRLPInSZIkSZIktVtm3g7cDhARN0w5the4sLYuIl4LfA04G9gTEacAG4ENmfnZaptXA98BXgx8usW/gtR0jmCWJEmSJEmSWuPkavlItXwOcCLwmckGmfld4B7g/PntmtQcBpglSZIkSZKkJouIk4A/BW7LzO9Vq08HDgMPT2n+UPVYo8/ZHBG7I2L3yMhIy/orHS8DzJIkSZIkSVITVXMu3wQ8Adgwl8/KzOsyc01mrlm1alUzuic1lQFmSZIkSZIkqUmqweVB4NnABZn5g5rDDwInAE+a8rbTqsekRccAsyRJkiRJktQEEXEi8FFKcPmXM3Nq0PgrwI+pWQwwIp5CWQTwS/PVT6mZutvdAUmSJEmSJGkxiIge4Geru13AmRFxDvBD4H7gfwHPBV4OZERM5lXem5n7M3NvRFwPvDsihoEfAO8Bvgp8bv5+E6l5HMEsSZIkSZIkzcwa4K7qtgJ4e/X1O4CnAK8AnkwZqfxAzfaqms+4Avg4ZaTzHcAY8PLMPDwvv4HUZI5gliRJkiRJkmYgM3cCcYwmxzo2+RkHgS3VTVr0HMEsSZIkSZIkSTouBpglSZIkSZIkScfFALMkSZIkSZIk6bgYYJYkSZIkSZIkHRcDzJIkSZIkSZKk42KAWZIkSZIkSZJ0XAwwS5IkSZIkSZKOiwFmSZIkSZKWqIh4a0R8OSIejYiRiLgtIp41pU1ExNURcX9E7I+InRHxzCltnhgRN0bE3up2Y0Q8YV5/GUlSWxhgliRJkiRp6VoLfAA4H3gRcAj4XEScWtPmzcAbgS3Ac4Fh4LMR0VvTZgdwLvAr1e1c4MZWd16S1H7d7e6AJEmSJElqj8x8ae1+RLwa2As8D7gtIgK4AnhXZt5SbfMaSpB5PfDBiDibElTuz8w7q21eC/xNRDwjM78xX7+PJGn+OYJZkiRJkiRN6qXECh6p7p8FnA58ZrJBZu4HvkgZ9QxwHjAGfKnmc+4AxmvaSJI6lAFmSZIkSZI06X3APwB3VvdPr5YPTWn3UM2x04GRzMzJg9XXwzVt6kTE5ojYHRG7R0ZGmtR1SVI7GGDuZIcPw969MDFRysOH290jaeGamIDR0fpSUmOeL9LMeb5IM+f50nYR8R6gH7g4M1t6A5mZ12Xmmsxcs2rVqlb+qM7lOSPNnOdLSxlg7lSHD8PwMFx0ESxbVsrhYYPMUiMTE+X8WLeunC/r1pV9v3DmXUT8VkR8tbqK+aMRcWdEvOxx3rM6Iv66uqL59yPiP1dzBaoVPF+kmfN8kWbO86XtIuK9wADwosz8Vs2hB6vlaVPeclrNsQeBVbXXYNXXfTVt1EyeM9LMeb60nAHmTjU2BuvXw86dcOhQKdevL/WS6o2Pw8BA/fkyMFDqNd++B7yFsur4GuALwK0R8exGjSPiZOCzlCmazwXeAPwu8Dvz0tulyPNFmjnPF2nmPF/aKiLex5Hg8tenHL6PEiS+sKb9cuD5HMm5fCfQQ8nFPOk8oEJ9XmY1i+eMNHOeLy3X3e4OqEV6e2HXrvq6XbtKvaR6lUrj86VSaU9/lrDM/MSUqisj4j9QblC+2uAt/xZYCbymutjM3RHx88DvRMR7avMAqkk8X6SZ83yRZs7zpW0i4v3Aq4GLgEciYjJn8lhmjmVmRsS1wNsi4uvAN4HfoyzqtwMgM++JiE8BH4yIzdX3fxD4ZGZ+Y/5+myXEc0aaOc+XlnMEc6caHYX+/vq6/v5SL6ne+Hjj88WnmW0VESdExG9SRsNMN/LlPOBvqsHlSZ8Gngw8bZrPdUGZufB8kWbO80WaOc+Xdnod0At8HnigZntTTZt3A+8F3g/sBs4AXpKZtTeY64F/pFyLfbr6+tWt7vyS5TkjzZznS8sZYO5UPT2wYwesXQvd3aXcsaPUS6pXqcDgYP35Mjjo08w2qeZUHgMOAv8V+I3M3DNN89NpvKL55LGjuKDMHHm+SDPn+SLNnOdL22RmTLNdXdMmM/PqzDwjM5dn5gsz8+4pn/NIZl6amSdXt0sz80fz/fssGZ4z0sx5vrScKTI61QknQF8f3HprSYsxOlqCyyec0O6eSQtPV1c5X4aGyhfM+Hgpu3wG1ybfAM4BTgEuAT4UEWun3sSoTTxfpJnzfJFmzvNFmh3PGWnmPF9azgBzJzvhBDjllPJ6spTUWFfXkRzl5ipvq8x8DPi/1d2vRMRzgd8GNjZo/iCNVzSfPKZW8HyRZs7zRZo5zxdpdjxnpJnzfGkpQ/WSpIWuC1g2zbE7gedXVzKfdCFwP/DtFvdLmlcR8VsR8dWIeLS63RkRL6s5HhFxdUTcHxH7I2JnRDxzymc8MSJujIi91e3GiHjCvP8ykiRJkjqGAWZJApiYKKlkakvNu4h4V0Q8PyKeVs3F/IfAWuB/VI//YUR8vuYtO4B9wA0R8ayIeCXwn4D3ZGbOd/+lFvse8BbgXGAN8AXg1oh4dvX4m4E3AluA5wLDwGcjonaIxo7q+3+lup0L3DgvvZckSZLUkQwwS9LEBAwPw7p1sGxZKYeHDTK3x+nATZQ8zJ+nBMl+NTP/d/X4GcDPTDbOzL2UEctPpqxo/n7gT4H3zGOfpXmRmZ/IzP+dmf83M7+ZmVcCo8B5ERHAFcC7MvOWas7y1wC9wHqAiDibElTenJl3ZuadwGuBX4+IZ7Tjd5IkSZK0+JmDWZLGx2FgAHbuLPs7d5b9oSFzM82zzLx8tsczcw/wghZ1SVqQIuIE4F8DPcCXgLMoD2g+M9kmM/dHxBeB84EPAucBY9X2k+4AxqttvjEvnZckSZLUURzBLM2ziHhrRHy5mj9zJCJui4hnTWnzuHk01USVCuzaVV+3a1epl6QFpJo6Zgw4CPxX4DeqD1lOrzZ5aMpbHqo5djowUps+pvp6uKbN1J+3OSJ2R8TukZGRJv4mkiRJkjqFAWZp/q0FPkAZLfYi4BDwuYg4tabNTPJoqlnGx6G/v76uv7/US9LC8g3gHOBfAX8BfGjqQ8pmyszrMnNNZq5ZtWpVq36MJEmSpEXMALM0zzLzpZm5PTPvro46ezWwCngelNHLPE4eTTVZpQKDg7B2LXR3l3Jw0BHMkhaczHysmoP5K5n5VuAfgN8GHqw2OW3KW06rOfYgsKr6PQP883dOX00bSZIkSZoVA8xS+/VSzsVHqvsN82gCk3k0j+IU5jnq6oK+vpJz+eDBUvb1lXpJWti6gGXAfZQg8YWTByJiOfB8juRcvpOSs/m8mvefB1Soz8ssSZIkSTPmIn9S+72PMgLtzur+sfJo/mSjD8jM64DrANasWZON2uhxdHUdWdDPhf0kLUAR8S7gL4HvcmRWy1rgZZmZEXEt8LaI+DrwTeD3KIv67QDIzHsi4lPAByNic/VjPwh8MjNd4E+SJEnScTHA3MkmJkoO2UrlSOmIzAUlIt4D9AP9mXm43f2RJC1opwM3Vcu9wFeBX83MT1ePvxtYAbwfeCLwd8BLMnO05jPWA1uByfcMAa9vfdeXMK/HJEmS1OG8uu1UExMwPAzr1sGyZaUcHi71WhAi4r3AAPCizPxWzaGZ5NGUJC0xmXl5Zj41M5dlZl9mvrgmuEwWV2fmGZm5PDNfWM3jX/sZj2TmpZl5cnW7NDN/NO+/zFLh9ZgkSZKWAAPMnWp8HAYGYOdOOHSolAMDpV5tFxHv40hw+etTDs8kj6YkSVroxsYaX4+NjbW7Z5IkSVLTmCKjU1UqsGtXfd2uXaVebRUR7wdeDVwEPBIRkzmXxzJzbCZ5NNUCTmGWJDVbT0/j67Genvb0R5IkSWoBoyedanwc+vvr6/r7HcG8MLyOsjjT54EHarY31bR5N/BeSh7N3cAZHJ1HU83iFGZJUiuMjTW+HnMEsyRJkjqII5g7VaUCg4NlGuauXeVmZnDQEcwLQGbGDNokcHV1U6vVppSBI1OYh4agt7edPZMkLWZdXfCRj8DoKJx1Ftx3X/lecYaMJEmSOohXt52qqwv6+kqA7ODBUvb1eUMjNWJKGUlSKyxfXmbDbNpUXm/aVPaXL293zyRJkqSmMdrYybq6joyScbSMND1TykiSWmH/fli/vn6Rv/XrS70kSZLUIYw4StJkSpm1a6G7u5SmlJEkzZUzZCRJkrQEGGCWJFPKSJJawRkybRURL4iIoYj4fkRkRFx+jLYfrLZ505T6ZRGxNSIejojx6uc9peWdlyRJWkSMnkgSmFJGktR8zpBptx7gbuANwLR5SSLiEuAXgfsbHL4WuBgYAJ4PnAx8MiJOaHZnJUmSFqvudndAkiRJ6khdXbBqFdx6a3l4OToKPT0+xJwnmXk7cDtARNzQqE1EPBV4H/Bi4H9POXYKsBHYkJmfrda9GvhOtf2nW9V3SZKkxcSrW0mSJKkVJiZgZAQuugiWLSvlyEipV9tFRDcwCPxBZt7ToMlzgBOBz0xWZOZ3gXuA8+elk5IkSYuAAWZJknRMETHrTRIl1/LAAOzcCYcOlXJgwBzMC8fbgYcz8y+mOX46cBh4eEr9Q9VjR4mIzRGxOyJ2j4yMNK+nkiRJC5gB5k42MVGmYtaWkiTNUmY23B7vmLTkVSqwa1d93a5d5mBeACJiLXA5JQVG02TmdZm5JjPXrFq1qpkfLUmStGAZYO5UExMwPAzr1pUpmevWlX2DzJIkSfNjfBz6++vr+vsdwbwwrAXOAB6IiEMRcQh4KvBHEfG9apsHgROAJ01572nVY5IkScIAc+dySqY0O474lyQ128qVsGMHrF0L3d2l3LGj1KvdPgA8GzinZrsfeC9wQbXNV4AfAxdOvikingKcDXxp3noqSZK0wBlg7lROyZRmzhH/kqRW2LcP7rgDbr4ZDh4s5R13lHq1XET0RMQ5EXEO5b7nzOr+mZk5nJl3126UYPKDmfkNgMzcC1wPvDsiXhwRvwDcCHwV+Fx7fitJkqSFxwBzp3JKpjRzjviXJLXCypVw7rlwySXlAeYll5R9RzDPlzXAXdVtBWVRv7uAd8ziM64APg58FLgDGANenpmHm9pTSZKkRcwAc6eqVGBwsH5K5uCgI5ilRhzxL0lqhbEx2Lix/gHmxo2lXi2XmTszMxpsl0/T/mmZ+SdT6g5m5pbM/InMXJmZL8/M787LLyBJkrRIzCjAHBEviIihiPh+RGREXH6Mth+stnnTlPplEbE1Ih6OiPHq5z1ljv3XdLq6oK8PhobKlMyhobLf5TMF6ShjY41H/BsAkCTNRW9v4weYvb3t6Y8kSZLUAjONNvYAdwNvAPZP1ygiLgF+kbJAxlTXAhcDA8DzgZOBT0bECbPor2ajq6vcwNSWko520kmNF2E66aR290yStJiZskySJElLwIwijpl5e2a+LTNvBhquehURTwXeB6ynLJBRe+wUYCPwu5n52cz8e+DVlJWbXzyH/kvS3D32GGzbBlu3woEDpdy2rdRLknS8TFkmSZKkJaC7GR8SEd3AIPAHmXlPRExt8hzgROAzkxWZ+d2IuAc4H/h0M/ohScelpweuuQZ+//eP1HV3w+/9Xvv6JEla/GpTllUqZeRypeKsMkmSJHWUZl3dvh14ODP/YprjpwOHgYen1D9UPXaUiNgcEbsjYvfIyEiTuilJDZiDWZLUKqYskyRJUoeb8xVuRKwFLqekwGiazLwuM9dk5ppVq1Y186MlqV5PT+MpzD097e6ZJEmSJEnSgtaMFBlrgTOAB2pSY5wA/FFEXJGZTwEerNY9Cagdjnwa8DdN6IMkHT+nMEuSJEmSJB2XZkRPPkBZrO+cmu1+4L3ABdU2X6Es/Hfh5Jsi4inA2cCXmtAHSZobpzBLkiRJkiTN2oxGMEdED/Cz1d0u4MyIOAf4YWb+P2B4SvsfAw9m5jcAMnNvRFwPvDsihoEfAO8Bvgp8rhm/iCRJkiRJkiRpfs10iN4a4K7qtoKyqN9dwDtm8bOuAD4OfBS4AxgDXp6Zh2fxGZIkSZIkSZKkBWJGI5gzcycQj9eupv3TGtQdBLZUN0laWCYmjuReNgezJEmSJEnSjBg96WQTEzA6Wl9KOtrEBAwPw7p1sGxZKYeHPWckSXPn9ZgkSZI6nAHmTmXATJq58XEYGICdO+HQoVIODJR6SZKOl9djkiRJWgIMMHcqA2bSzFUqsGtXfd2uXaVekqTj5fWYJEmSlgADzJ3KgJk0c+Pj0N9fX9ffbwBAkjQ3Xo9JkiRpCTDA3KkMmEkzV6nA4CCsXQvd3aUcHDQAIEmam/FxuOoq2LOnjGDes6fsez0mSZKkDtLd7g6oRSYDZgMDZaRMf78BM2k6XV3Q1wdDQ+UcGR8vZZfP4CRJc7ByJWzaBOvXH7ke27Gj1EuSJEkdwgBzpzJgJs1OVxf09pbXk6UkSXOxb18JLu/cWfZ37iz7Q0N+10iSJKljGGDuZAbMJEmS2scczJIkSVoCHM4qSZIktcLoaOM1MUZH29MfSZIkqQUMMEuSJEmt0NMD119fv4js9deXekmSJKlDGGCWJEmSWmHfPrjpJti6FQ4cKOVNN5V6SZIkqUOYg1mSJElqhUoFNm+GgYGSe7m/HwYHzcEsSZKkjmKAWZIkSWqFri7o64OhoRJUHh8vZZeTCCVJktQ5DDBLkiRJrdLVBb295fVkKUmSJHUQh09IkiRJkiRJko6LAWZJkiRJkiRJ0nExwCxJkiS1ysQEjI7Wl5IkSVIHMcAsSZIktcLEBAwPw7p1sGxZKYeHDTJLkiSpoxhg7mSOmJEkSWqf8XEYGICdO+HQoVIODJR6SZIkqUMYYO5UjpiRJElqr0oFdu2qr9u1q9RLkiRJHcIAc6dyxIwkSVJ7jY/DVVfBnj3lemzPnrLv9ZgkSZI6SHe7O6AWccSMJElSe61cCZs2wfr15Tqsvx927Cj1kiRJUodwBHOnGh8vNzG1+vsdMSNNx5zlkqRm27evBJdrZ5StX1/qJUmSpA5hgLlTVSowOAhr10J3dykHBx3BLDViznJJUis4o0zSIhERL4iIoYj4fkRkRFw+5XhOs72/ps0NDY7/7bz/MpKkeWeAuVN1dcGqVXDrrXDwYClXrSr1kuqZs1yS1ArOKJO0ePQAdwNvAPY3OH7GlO3l1fr/OaXd56a0+7VWdFaStLAYbexUExMwMgIXXVRGZF50Udl3RKZ0NEeYSZJaYeXKknO5dkaZOZglLUCZeXtmvi0zbwaOumnMzAdrN+AVwDcz86+nND04pe0P56P/kqT2MsDcqRyRKc2cI8wkSa2wbx9s2wZbt8KBA6Xcts0czJIWtYjoAX4T2NbgcH9EDEfENyNiW0T0zXP3JEltYIC5U1Uq8OQnw549JcC8Z0/Zd0SmdDRzlkuSWqFSgWuugdWry/fL6tVl3+8XSYvbeuAk4ENT6j8FXAZcALwR+EXgCxGxrNGHRMTmiNgdEbtHRkZa2V9JUot1t7sDapEDB+Cd74QNG8pU//5+2L691DstU6rX1QV9fTA0VG76x8dLac5ySdJcTM6Q2bnzSN3kDJne3rZ1S5LmaBPwicysiwpn5kdqdvdExFeA7wAvAz429UMy8zrgOoA1a9Zk67orSWo1oyed6tChElyuTZGxYUN5LeloXV3lZr+2lCRpLpwhI6nDRMQ5wBoap8eok5n3A98Dnt7ibkmS2swRzJ2qp6fxomU9Pe3pjyRJ0lLjDBlJnWczcB/wucdrGBFPAn4SeKDVnZIktZdXt51qbKzxomVjY+3pjyRJ0lLkDBlJi0BE9ETEOdURyl3AmdX9M2varAT+LXB9ZmaD9/9JRJwXEU+LiLXAbcAw8PH5+j0kaVoTEzA6Wl+qabzC7VTd3SXncu2UzO3by2tJkiRJko5YA9xV3VYAb6++fkdNm1cBFWB7g/cfBlYDnwC+SVkA8BvAeZk52rpuS9IMTEzA8DCsWwfLlpVyeNggcxMZYO5Uy5fDlVfC1q1lYb+tW8v+8uXt7pkkSdLS4WgZSYtAZu7MzGiwXV7TZntmdldzK099//7MfGlm9mXmSZn51My8PDO/O6+/iDQPIuIFETEUEd+PiIyIy6ccj4i4OiLuj4j9EbEzIp45pc0TI+LGiNhb3W6MiCfM5++xpIyPw8BA/TplAwOlXk1hgLlTjY/D/ffD6tVl1PLq1WXfk0eSJGl+OFpGkqRO1APcDbwB2N/g+JuBNwJbgOdSUsV8NiJ6a9rsAM4FfqW6nQvc2MI+L22VSuN1ylx4uWkMMHeqlSthx476FBk7dpR6SZIktZ6jZSRJ6jiZeXtmvi0zbwbqnhpHRABXAO/KzFsy827gNUAvsL7a5mxKUHlzZt6ZmXcCrwV+PSKeMY+/ytIxPt54nTKvyZrGAHOn2rcPtm2rT5GxbVuplyRJUus5WkaSpKXmLOB04DOTFZm5H/gicH616jxgDPhSzfvuAMZr2qiZKhUYHKwfhDk46DVZExlg7lSVClxzTX2KjGuu8eSRJEmaL2NjcNVVsGdPGcG8Z0/ZHxtrd88kSVJrnF4tH5pS/1DNsdOBkczMyYPV18M1bepExOaI2B0Ru0dGRprc5SWgqwv6+mBoCA4eLGVfX6lXU/gv2anGxxvf0Dj8X5IkaX6cdBJs2gRbtpSFlrdsKfsnndTunkmSpEUkM6/LzDWZuWbVqlXt7s7i1NUFvb31pZrGf81OtXJl4xsaczBLkiTNj8ceg/Xr63Mwr19f6iVJUid6sFqeNqX+tJpjDwKrqvmagX/O3dxX00ZaVAwwd6p9+xrf0JiDWZIkaX709DTOwdzT057+SJKkVruPEiS+cLIiIpYDz+dIzuU7gR5KLuZJ5wEV6vMyS4uGAeZO5aIykiRJ7TU21njFcnMwS5K0aEVET0ScExHnUOJqZ1b3z6zmUr4WeEtEvDIingXcQFnUbwdAZt4DfAr4YEScFxHnAR8EPpmZ35j/30iaOwPMncoczJIkSe110kmwY0f9iuU7dpiDWZKkxW0NcFd1WwG8vfr6HdXj7wbeC7wf2A2cAbwkM0drPmM98I/Ap6vbPwKvno/OS63Q3e4OqEUmczCvX19GLvf3lxsaczBLkiTNj8ceg23bYOtWOPtsuOeesn/FFWWNDEmStOhk5k4gjnE8gaur23RtHgEubXLXpLZxBHOnMgezJElSe/X0wDXXwOrVZQTz6tVl3xzMkiRJ6iAGmDuVOZil2ZmYgNHR+lKSpLkYG2ucsswczJIkSeogBpg71eho40VlRkcbt5eWsokJGB6Gdetg2bJSDg8bZJYkzU2lUlKWbdlSUmJs2VL2feAvSZKkDmKAuVP19MD119cvKnP99U7JlBoZH4eBgfqUMgMDLoopSZobU5ZJkiRpCTDA3KnGx+Gmm8qiMgcOlPKmmwyYLRAR8YKIGIqI70dERsTlU473RMTWiPheROyPiG9ExG+3qbudz5QykqRW8PtFkiRJS4AB5k51wglw2WX1UzIvu6zUayHoAe4G3gDsb3D8PcDLgFcDZwPvBN4VEa+etx4uJePjjVPK+EBGkjQXpiyTJEnSEmCAuZOtWAHbtpURzNu2lX0tCJl5e2a+LTNvBhol+j0fuDEz/yozv52ZHwb+FvhX89rRpaJSgcHB+pQyg4OOMJMkzU2lAjt21H+/7Njh94skSZI6igFmaWHaBbw8In4KICLOB84BPtWocURsjojdEbF7ZGRk/nrZKbq6oK8Phobg4MFS9vWVekmSjtf4eHnIX5uybNs2Z8hIkiSpoxg96VSZcNJJcOqpEFHKk04q9VoM/iPwj8D/i4gfA38NvCUzP9mocWZel5lrMnPNqlWr5rOfnaOrC3p760tJkuaitxeuuQZWry4jmFevLvu9ve3umSRJktQ0RlA61fLlZaTMxRfDsmWlPHCg1Gsx2EJJk7EOeA7w28CfRMSvtLVXkiRp5sbGGudgHhtrT38kSZKkFjDA3KnGx2H9eti5Ew4dKuX69U7JXAQiYgXwh8CbM/O2zPxqZv458BHgTe3tnSRJmrHubti+vT4H8/bt5bUkSZLUIQwwd6reXti1q75u1y6nZC4OJ1a3w1PqD+M5K0nS4rF8OVx5ZX0O5iuvdEaZJEmSOorBqk41OgpXXQV79pQRzHv2lP3R0Xb3TEBE9ETEORFxDuU8PLO6f2ZmPkrJufyuiFgbEWdFxOXAZcDH29drSZI0K+PjcP/99TmY77/fGWWSJEnzbWKixMRqSzWNAeZOtWwZvP71R0bILF9e9pcta2+/NGkNcFd1WwG8vfr6HdXjvwl8GfgfwD8B/wm4Cvjzee+pJEk6PpUKDA7Wp8gYHCz1kiRJmh8TEzA8DOvWlbjYunVl3yBz05gArlMdOgSPPgqbNpXUGP39JeffSSe1u2cCMnMnEMc4/iCwYd46JEmSmq+rC/r6YGioBJXHx0vZ5RgPSZKkeTM+DgMDZX0yKOXAQLlGM5VsU3h126kmJmDDhvpF/jZs8OmMNB2ny0iSWqGrq9y41JaSJEmaP5VK43XKnFXWNF7hdqqensYnT09Pe/ojLWROl5G0CETEWyPiyxHxaESMRMRtEfGsKW1uiIicsv3tlDbLImJrRDwcEeMRMRQRT5nf30aSJEmaJ+PjZWZ/rf5+18VoIgPMHSQi/nkb+fa3G548I9/+dl07ScDY2JHpMpMj/gcGSr0kLRxrgQ8A5wMvAg4Bn4uIU6e0+xxwRs32a1OOXwtcDAwAzwdOBj4ZESe0quNSO0TEC6oPUL5ffdhyec2xEyPijyLiq9UHLQ9ExI6IOHPKZ/hARpKkxc51MVrOHMwdJDOP7ExMlJNlYOBIDubBQVb19dW3k+SIf0mLQma+tHY/Il4N7AWeB9xWc+hgNZf/USLiFGAjsCEzP1vzOd8BXgx8ugVdl9qlB7gb+HB1q7USOBd4J/APwCnAnwKfiohnZ+ahartrgVdQHsj8AHgP5YHMczLzcKt/AUmS1ASui9FyBpg7Vc3JM7FyJV379nnySNMZGysPYSYT/kPZHxuDk09uW7ck6XH0UmajPTKlvj8ihoEfAX8NXJmZw9VjzwFOBD4z2TgzvxsR91BGRhtgbraJiSM3Md7MzKvMvB24HUr6mCnH9gIX1tZFxGuBrwFnA3t8ICNJUgeZXA8DXNivBby67WTVk+eE7m4XlZGOpbsbtm+vny6zfXt5LUkL1/soIy/vrKn7FHAZcAHwRuAXgS9ExLLq8dOBw8DDUz7roeqxOhGxOSJ2R8TukZGR5vZ+KTDH/2Iz+VR58qFNwwcywOQDGUmSJGGAWZJg+XI45RTYtg0OHCjlKaeUeklagCLiPUA/cHHtNP3M/EhmDmXmnsy8DfhV4BnAy47n52TmdZm5JjPXrFq1qil9X1LGxxvn+HdBmQUnIk6ipMi4LTO/V62e1QOZ6uf4UEaSJC05BpglqaurBJRPOw0iSnnKKY76l7QgRcR7KflgX5SZ3zpW28y8H/ge8PRq1YPACcCTpjQ9rXpMzVSpNM7x74IyC0pEdAM3AU8ANszls3woI0mSliKjJ5IER/Ix1ZaStMBExPs4Elz++gzaPwn4SeCBatVXgB9Tk3s2Ip5CyTn7paZ3eKkbHy85/Wv19zuCeQGpBpcHgWcDF2TmD2oO+0BGkiRpBoygSJIkLQIR8X7K6Mr1wCMRcXp166ke74mIP4mI8yLiaRGxFrgNGAY+Dv+8sNn1wLsj4sUR8QvAjcBXgc/N+y/V6SoVGBysz/E/OOgI5gUiIk4EPkoJLv9yZk4NGvtARpIkaQZcwUqSJGlxeF21/PyU+rcDV1Nyxa6mLPL3BMqo5b8C/k1mjta0vwI4RAmsrah+3mW1uZzVJF1dsGoV3HprmR0zOgo9Pc6SmSfVhy8/W93tAs6MiHOAHwL3A/8LeC7wciAjYjKv8t7M3J+ZeyNi8oHMMPAD4D34QEaSJKnOjK5uI+IFETEUEd+PiIyIy2uOnRgRfxQRX42I8Yh4ICJ2RMSZUz5jWURsjYiHq+2GqiMAJEmS9DgyM6bZrq4e35+ZL83Mvsw8KTOfmpmXZ+Z3p3zOwczckpk/kZkrM/PlU9uoSSYm4NFHYWQEMkv56KOlXvNhDXBXdVtBeRhzF/AO4CnAK4AnU0YqP1CzvarmM66gzAD4KHAHMAa83AcykiRJR8x0+EQPcDfwBmD/lGMrgXOBd1bLVwA/BXyqmtNs0rXAxZS8gc8HTgY+GREnHG/nJUmSpAXrwAHYuxc2bYLly0u5d2+pV8tl5s5pHspcnpnfPsZDmxtqPsMHMpIkSY9jRikyMvN24HaAiLhhyrG91OQlq7Z5LfA1Sn6yPRFxCrAR2JCZn622eTXwHeDFwKfn9FtIkiRJC82hQ7BhA+zcWfZ37iz7n/hEO3slSZIkNVWrEsCdXC0fqZbPAU4EPjPZoPrk/x7g/Bb1QZIkSWqfnh7Ytau+bteuUi9JkiR1iKYHmCPiJOBPgdsy83vV6tMpC888PKX5Q9VjjT5nc0TsjojdIyMjze6mJEmS1FpjY9DfX1/X31/qJUmSpA7R1ABzNefyTZSVyzfM5bMy87rMXJOZa1atWtWM7kmSJEnzp6cHBgdh7Vro7i7l4KAjmCVJktRRZpSDeSaqweVBYDWwNjN/UHP4QeAE4ElA7XDk04C/aVYfJEmSpAWjqwv6+mBoCCoVGB8vZVerstRJkiRJ868pV7cRcSLwUeDZwC9n5oNTmnwF+DE1iwFGxFMoiwB+qRl9kCQtfhHx1oj4ckQ8GhEjEXFbRDxrBu97aUTcGRGjEfFwRHwiIn5uPvosScfU1QW9vfWlJEmS1EFmdIUbET0RcU5EnFN9z5nV/TOrI5f/F/BLwACQEXF6dVsBkJl7geuBd0fEiyPiF4Abga8Cn2v+ryVJWqTWAh+gLAD7IuAQ8LmIOHW6N0TEWcAnKDNifgF4MbACuL3VnZUkSZIkaambaYqMNcBf1ey/vbp9CLgaeEW1/itT3rcBuKH6+gpKoOCjlBv/zwOXZebhWfZZktShMvOltfsR8WpgL/A84LZp3vYc4ETgrZPfKRHxh8AXIuJJmTl1gVlJkiRJktQkMwowZ+ZOII7R5FjHJj/jILClukmSNBO9lJkzjxyjzZcpaZj+fxHx34CVwGuALxtcliRJUseamDiS3988/5LayL88kqSF7H3APwB3TtcgM79DyfH/duAgZcTzauDXG7WPiM0RsTsido+MjDRqIkmSJC1sExMwPAzr1sGyZaUcHi71kjTPDDBLkhakiHgP0A9cfKx0ShFxOiXP/4eB51LyOI8C/zMijvqey8zrMnNNZq5ZtWpVS/ouSZIktdT4OAwMwM6dcOhQKQcGSr0kzbOZ5mCWJGneRMR7gd8Efjkzv/U4zX8LGM/MN9e8/1Lgu5TFAne1rKOS9HicvixJaoVKBXZNuczdtavUS9I88+pWkrSgRMT7gAHgRZn59Rm8ZSUwdYTz5L7fc5Lax+nLkqRWGR+H/v76uv5+RzBLagtvvCVJC0ZEvB/YAKwHHomI06tbT02bP4yIz9e87S+BcyPiP0fE0yPiXGA7ZQTzV+az/5JUx+nLkqRWqVRgcBDWroXu7lIODjqCWVJbGGCWJC0krwN6gc8DD9Rsb6ppcwbwM5M7mfkFSkD6FcBdwKeBHwO/kplGcSS1j9OXJUmt0tUFfX0wNAQHD5ayr880TNJ0Dh+GvXvLTLK9e8u+msa/PJKkBSMzY5rt6po2l2fm06a87yOZ+ZzM7MnMVZn58sz8p/nuvyTVcfqyJKmVurqgt7e+lHS0w4dLmrKLLippyy66qOwbZG4a//pIkiRJreD0ZUmSpPYbG4P16+vTlq1fX+rVFN3t7oAkSZLUkWqnL1cqZeRypeIIM0mSpPnU29s4bVlvb3v604G8upUkSZJaxenLkiRJ7TU62jht2ehoe/rTgbzClSRJklplYqLcvNSWkiRJmj/Ll8OOHfVpy3bsKPVqCgPMkiRJUitMTJQFZNatKwvKrFtX9g0yS5KawYeY0swcPAjf/jZ8/OPl9cc/XvYPHmx3zzqGAWZJkiSpFcbHYWCgfkGZgYFSL0nSXPgQU5q5SgVOOw1+4zfK+fIbv1H2XXi5aQwwS5IkSa1QqTReUMabGUnSXPkQU5q5sTHYuLH+fNm4sdSrKQwwS5IkSa0wPt54QRlv/iVJc+VDTGnmensbny+9ve3pTwcywCxJkiS1QqUCg4P1C8oMDnrzL0maOx9iSjPn+dJyBpglSZKkVujqgr4+GBoqi8gMDZX9Li/BJUlz5ENMaeY8X1quu90dkCRJkjpWV9eR6ZdOw5QkNUvtQ8xKpYzErFR8iCk14vnScv5LSpIkSZK0hEXECyJiKCK+HxEZEZdPOX5Dtb52+9spbZZFxNaIeDgixquf95R5/UWWmsmHmLWlpMY8X1rKf01JkiRJkpa2HuBu4A3A/mnafA44o2b7tSnHrwUuBgaA5wMnA5+MiBNa0F9J0gJiigxJkiRJkpawzLwduB3KaOVpmh3MzAcbHYiIU4CNwIbM/Gy17tXAd4AXA59udp8lSQuHI5glSZIkSdLj6Y+I4Yj4ZkRsi4i+mmPPAU4EPjNZkZnfBe4Bzm/0YRGxOSJ2R8TukZGRlnZcktRaBpglSZIkSdKxfAq4DLgAeCPwi8AXImJZ9fjpwGHg4Snve6h67CiZeV1mrsnMNatWrWpNryVJ88IUGZIEMDFxZCVZV5SVJEmS/llmfqRmd09EfIWS/uJlwMfa0ytJ0kJh9ESSJiZgeBjWrYNly0o5PFzqJUmSJNXJzPuB7wFPr1Y9CJwAPGlK09OqxyRJHcwAsySNj8PAAOzcCYcOlXJgoNRLkiRJqhMRTwJ+EnigWvUV4MfAhTVtngKcDXxp3jsoSVNNTMDoaH2ppjHALEmVCuzaVV+3a1eplyRJkjpcRPRExDkRcQ4lTnBmdf/M6rE/iYjzIuJpEbEWuA0YBj4OkJl7geuBd0fEiyPiF4Abga8Cn2vDryRJRzhrueUMMEvS+Dj099fX9fc7glmSJElLxRrgruq2Anh79fU7KIv3rQY+AXwT+BDwDeC8zByt+YwrKAHnjwJ3AGPAyzPz8Pz8CpI0DWctt5yL/ElSpQKDg+ULZteuElweHHQEsyRJkpaEzNwJxDGavHQGn3EQ2FLdNB9cqFyaGWctt5x/eSSpqwv6+mBoCA4eLGVfnxdnkiRJkhYmp/xLM+es5ZYzeiJJUILJvb31pSRJc+WCMpKkVhgbazzlf2ys3T2TFp6VK2HHDli7Frq7S7ljR6lXUxhBkSRJklrB0WWSpFbp6Wk85b+npz39kRayfftg2zbYuhUOHCjltm2lXk1hgFmSJElqBReUkSS1ythY4yn/jmCWjlapwDXXwOrVZQTz6tVl3xzMTWOAWZIkSWoFF5SRJLVKdzds314/5X/79vJaUr3xcbjqKtizpzz037On7PvQv2kMMEuSJEmt4IIykqRWWb4cTjmlTPM/cKCUp5xS6iXVW7kSNm2CLVvKObJlS9k3B3PT+GhLkiRJaoVKBT72MfjBD+Css+C+++AnfsIRzJKkuevqKgHl7m6IgNNOK98vLlYuHW3fPli/vqQrg1KuXw9DQ9Db286edQz/8kiSJEmtcvBgGSGzfHkpDx5sd48kSZ2iq6sEx2pLSUczbVnL+ddHkiRJagUX+ZMkSWo/05a1nCkyJEmSpFZwtIw0OxMT5Wa/UjlSOiJTkjRXpi1rOb+tJUmSpFZwtIw0cxMTMDwM69bBsmWlHB4u9ZIkzZVpy1rKALMkSZLUCpUKDA7C2rVlEaa1a8u+o2Wko5lSRpq9iQkYHa0vJR3N75iWM8AsSZIktUJXF/T1lRXKDx4sZV+fU/6lRkwpI82Oo/6lmfM7puW8upUkSZJapasLenvrS0lHM6WMNDuOyJRmbnQUrroK9uwp58uePWV/dLTdPesYXuFKkiRJktrLlDLS7DgiU5q5ZctK3uUtW0oO5i1byv6yZe3uWccwwCxJkiRJai9Tykiz46h/aeYOHoT16+tH/K9f70J/TeS3tSRJkiSp/UwpI82co/6lmevthSc/uT5FxpOfXOrVFN3t7oAkSZIkSZJmqVKBW26BJzwBfvQjOPHEdvdIWpj27YN3vhM2bCipZPr7Yfv2Ut/T0+7edQQfCUuSJEmSJC0mBw7AD34AF19c8shefHHZP3Cg3T2TFp6JCfjwh2Hr1nKObN1a9icm2t2zjmGAWZIkSZIkaTE5dKiMxqzNKbthQ3ktqV6lApdeWr/I36WXmlKmiQwwS5IkSZIkLSY9PWWqf61du5zuLzUyNgYbN9Y/kNm4sdSrKQwwS5IkSa1y+DDs3VumYO7dW/YlSZqrsbGSR7ZWf78BM6mR3t7GD2Rc5K9pDDBLbRARL4iIoYj4fkRkRFzeoM3PRcTHIuJHEbEvIv4+Is5uQ3clSdLxOHwYhofhootKfsyLLir7BpklSXPV0wODg7B2LXR3l3Jw0BHMUiOjo40fyIyOtqc/HcgAs9QePcDdwBuA/VMPRsRZwB3AfcCLgGcBvwf4OFqSpMVibAzWr6+fjrl+vaPLJElz19UFfX0wNAQHD5ayr6/US6rX0wM7dtQ/kNmxwwcyTdTd7g5IS1Fm3g7cDhARNzRo8k7gM5n5xpq6b81D1yRJUrM4HVOS1EpdXUe+U/xukaZ3wgnlAcytt5ZzZXS0BJdPOKHdPesYPtqSFpiI6AJeDvxTRHwqIkYi4ssR8ap2902SJM2C0zElSa00MVG+U2pLSY1FHBnh39VV9tU0BpilhaePkkLjbcBngAuBQeB/RMTLGr0hIjZHxO6I2D0yMjJ/PZUkSdNzOqYkqVUmJkpe/3XrSp7/devKvkFm6WieLy1ngFlaeCbPy09k5nsy8x8y8z3A/wRe3+gNmXldZq7JzDWrVq2at45KkqRjqJ2OefBgKfv6nI4pSZq78XEYGKjP8z8wUOrVVhFxQkRcExH3RcSBavkHEdFd0yYi4uqIuD8i9kfEzoh4Zjv73dE8X1rOALO08DwMHAL+aUr9PcCZ898dSZJ03E44AU45pUzFPOUUg8uSpOaoVBrn+a9U2tMf1XoL8FvAfwR+HnhDdf+tNW3eDLwR2AI8FxgGPhsRJtNuBc+XljPALC0wmfkY8GXgGVMO/RzwnfnvkSRJkiRpQRkfb5zn3xGZC8H5wG2ZeVtmfjszh4Ah4F9BGb0MXAG8KzNvycy7gdcAvcD6NvW5s3m+tJwBZqkNIqInIs6JiHMo5+GZ1f3JEcrvBl5Vza38sxGxCfhN4P1t6rIkSZIkaaFYubJxnv+VK9vdM8Eu4Jcj4ucBIuJfAC8Cbq8ePws4nbLmEgCZuR/4IiU4rWarVGBwsP58GRx0BHMTGWCW2mMNcFd1WwG8vfr6HQCZeSuwGXgTsIcybeayzPzLdnRWkiRJkrSA7NsH27bB1q1w4EApt20r9Wq3PwJuBP4pIn4MfA34UGZ+oHr89Gr50JT3PVRzrE518NnuiNg9MjLSij53tq6usg7G0FBZF2NoqOx3GRZtlu7HbyKp2TJzJxCP0+YG4IZ56I4kSWqViYky/bJSOVJ6MyNJmqtKBa65Bn7/94/UdXfD7/1e+/qkSa8CLqOku/gacA7wvoi4LzOvP54PzMzrgOsA1qxZk03q59KSWa7LoJTpP2MzeXUrSZIktcLEBAwPw7p1sGxZKYeHj9zcSJJ0vMbGGueUHRtrT39U64+BP8nMj2Tmnsy8EXgPRxb5e7BanjblfafVHFMzHT5crsEuuqhck110Udk/fLjdPesYBpglSZKkVhgfh4EB2LkTDh0q5cCAC8pIkuauuxu2b6/PKbt9e3mtdlsJTI1cHuZIDO4+SiD5wsmDEbEceD7wpfno4JIzNgbr19dfk61f7wOZJjLALEmSJLVCpQK7dtXX7drlgjLzJCJeEBFDEfH9iMiIuHzK8YiIqyPi/ojYHxE7I+KZU9o8MSJujIi91e3GiHjCfP4ektTQ8uVw5ZX1OZivvLLUq91uA/5TRLwsIp4WEb8B/A7wcYDMTOBa4C0R8cqIeBYlPeYYsKM9Xe5wvb2Nr8l6e9vTnw5kgFmSJElqhfHxxtOXHcE8X3qAu4E3APsbHH8z8EbKYsrPBYaBz0ZE7d3mDuBc4Feq27mUhZskqb3Gx+H++2H16jJqefXqsu93zEKwBbgZ+ABwD/CnwDbgypo27wbeC7wf2A2cAbwkM0fnt6tLxOho42uyUf+5m8UAsyRJktQKlQoMDtZPXx4cdATzPMnM2zPzbZl5M1CX+DoiArgCeFdm3pKZdwOvAXopizIREWdTgsqbM/POzLwTeC3w6xHxjHn8VSTpaH7HLFiZOZqZV2TmUzNzRWb+dPX76EBNm8zMqzPzjMxcnpkvrH4XqRV6euD66+vPl+uvL/VqCgPMkiRJUit0dUFfHwwNwcGDpezrK/Vqt7OA04HPTFZk5n7gi8D51arzKNOVa/Nh3gGM17SpExGbI2J3ROweGRlpRb8lqfA7Rpq5ffvgppvqU8rcdFOpV1P4l0eSJElqla6ukt+vttRCcHq1fGhK/UM1x04HRqq5MoF/zps5XNOmTmZel5lrMnPNqlWrmtxlSZrC7xhpZioV2LwZtmwpecq3bCn7jvhvGpcXlSSAiYmSr6xSOVJ6gSZJkiRJ0uJWO+Lfe/6WmNG/pCswS+poExMwPAzr1sGyZaUcHi71kiSpEz1YLU+bUn9azbEHgVXVfM3AP+du7qtpo2aamCgLLtWWkiQ1gyP+W2qm/5quwCypc42Pw8AA7NwJhw6VcmDAFZglSepc91GCxBdOVkTEcuD5HMm5fCflPui8mvedB1Soz8usZvCBvySplXyI2VIzCjC7ArOkjlapwK5d9XW7dpmPSZKkRSwieiLinIg4h3Lfc2Z1/8xqLuVrgbdExCsj4lnADZRF/XYAZOY9wKeAD0bEeRFxHvBB4JOZ+Y35/406nA/8JUmt4kPMlmvGePCWrMAsSfNmfBz6++vr+vu9oZEkaXFbA9xV3VYAb6++fkf1+LuB9wLvB3YDZwAvyczRms9YD/wj8Onq9o/Aq+ej80uOD/wlSa3iQ8yWa0aAuSUrMEfE5ojYHRG7R0ZGmtBNSZpGpQKDg7B2LXR3l3Jw0BsaSZIWsczcmZnRYLu8ejwz8+rMPCMzl2fmC6uzMWs/45HMvDQzT65ul2bmj9rx+3Q8H/hLklrFh5gtt2AzWmfmdZm5JjPXrFq1qt3dkdTJaleUPXiwlH19Jv2XJEmaLytXwo4d9Q/8d+wo9ZIkzcXYWOOHmGNj7elPB2pG9MQVmCUtfq4oK0mS1D779sEdd8DNN5cH/jffXPb37Wt3zyRJi113N2zfXv8Qc/v28lpN0YwIiiswS5IkSZKO38qVcO65cMklZQGmSy4p+45gliTN1fLlcOWVsHUrHDhQyiuvLPVqihkFmF2BWZIkqb0i4q0R8eWIeDQiRiLitup1V22biIirI+L+iNgfETsj4plT2jwxIm6MiL3V7caIeMK8/jKSNNXYGGzcWL8A08aNTl+WJM3d+Djcfz+sXl1GLa9eXfbN8980Mx3B7ArMkiRJ7bUW+ABwPvAi4BDwuYg4tabNm4E3AluA51IWVP5sRPTWtNkBnAv8SnU7F7ix1Z2XpGPq7W28AFNvb+P2kiTNVKUCg4P1KTIGB13kr4lmlGwkM3cCcYzjCVxd3aZr8whw6ax6J0mSJAAy86W1+xHxamAv8Dzgtur6FlcA78rMW6ptXkMJMq+nzCQ7mxJU7s/MO6ttXgv8TUQ8w5llktpmfLwsuLRz55G6/v5Sb5BZkjRXy5bBtm1w1llw331lX03jKlaSJEmLUy/lWu6R6v5ZwOnAZyYbZOZ+4IuUUc9Q1sAYo34NjDuA8Zo2kjT/HF0mSWqVsTF45Svh6U8v3zFPf3rZNw1T07hcoiRJ0uL0PuAfKIspQwkuAzw0pd1DwE/WtBmpzj4Dyky0iBiuef8/i4jNwGaAM888s2kdl6SjdHVBXx8MDZWg8vh4KbscEyVJmqOensZpmHp62tOfDuS3tSRJ0iITEe8B+oGLM/Nwq35OZl6XmWsyc82qVata9WMkqejqKukwaktJkuZqbAyuugr27CkLye7ZU/Ydwdw0fmNLkiQtIhHxXmAAeFFmfqvm0IPV8rQpbzmt5tiDwKpqvubJzwugr6aNJLXHxASMjtaXkiTN1UknwaZNsGULLF9eyk2bSr2awgCzJEnSIhER7+NIcPnrUw7fRwkSX1jTfjnwfI7kXL4T6KHkYp50HlChPi+zJM2viQkYHoZ168rCS+vWlX2DzJKkuXrsMVi/viwke+hQKdevL/VqCgPMkiRJi0BEvB/YAKwHHomI06tbD5RcysC1wFsi4pUR8SzgBsqifjuqbe4BPgV8MCLOi4jzgA8Cn8zMb8z37yRJ/2x8HAYG6m/+BwZKvSRJc2EO5pYzwCxJkrQ4vA7oBT4PPFCzvammzbuB9wLvB3YDZwAvyczRmjbrgX8EPl3d/hF4das7L0nHVKk0vvmvVNrTH0lS5xgfh/7++rr+fh9iNlF3uzsgSZKkx5eZMYM2CVxd3aZr8whwadM6JknNMHnzv3PnkbrJm//e3rZ1S5LUASoVGBwsM2N27SrfL4ODPsRsIkcwS5IkSa3iomXSzEze/K9dC93dpfTmX5LUDF1d0NcHQ0Nw8GAp+/pKvZrCf0lJkiSpFVy0TJo5b/4lSa3U1VVmxNSWahr/NSVJkqRWcNEyaXa8+Zdmx1ky0sx5vrSU39iSJElSK7homSSpVZwlI82c50vLGWCWJEmSWsEVyyUtEhHxgogYiojvR0RGxOU1x06MiD+KiK9GxHhEPBAROyLizCmfsbP63trtI/P+yywVzpKRZs7zpeUMMEuSJEmt4KJl0uw4fbmdeoC7gTcA+6ccWwmcC7yzWr4C+CngUxHRPaXtduCMmu21Lezz0uYsGWnmPF9azgCzJEmS1AouWibNnNOX2yozb8/Mt2XmzcDElGN7M/PCzPxoZn4jM/8PJXB8dnWrtS8zH6zZ9s7Tr7D0OEtGmjnPl5bz6laSJElqFRctk2bG6cuLzcnV8pEp9b8ZEQ9HxNci4k8ione+O7ZkOEtGmjnPl5abOp1FkiRJkqT55fTlRSMiTgL+FLgtM79Xc2gH8B3gfuCZwB8CzwZeMs3nbAY2A5x55pmNmuhYamfJVCrlYUyl4oNMqZGuLli1Cm69tTzwHx2Fnh7PlybyX1KSJEmS1F5OX14UqjmXbwKeAGyoPZaZ12XmpzNzT2Z+BHgVcGFEnNvos6rt12TmmlWrVrW6653JWTLSzExMwMgIXHRRScN00UVl3zRMTeNfH0mSJElSezl9ecGrBpcHKaOSL8jMHzzOW3YDh4Gnt7pvknRMpmFqOVNkSJIkSZLay+n+C1pEnAh8BHgWsDYzH5zB21YDJwAPtLJvS9rExJFzxXNGmp5pmFrOvzySJEmSJC1hEdETEedExDmUOMGZ1f0zqyOX/xfwS8AAkBFxenVbUX3/z0TEf46INRHxtIj4NUpA+i7gjvb8Vh1uYgKGh2HdujLlf926su+Uf+lopmFqOQPMkiRJkqT2MljWbmsoweC7gBXA26uv3wE8BXgF8GTgK5QRyZPbq6rvfwy4APg08A3gz4DPAC/OzMPz9lssJU75l2bONEwtZ4oMSZIkSVJ71QbL4EiwbGioLF6mlsrMnUAco8mxjpGZ3wVe2Mw+6XE45V+aOdMwtZz/kpIkSZKk9jJYJs3O2FjjKf9jY+3pj7TQdXWVB5a1pZrGf01JkiRJUnuZH1Oane5u2L69fsr/9u3ltSTNMwPMkiRJkqT2Mj+mNDvLl8OVV8LWrXDgQCmvvLLUS9I889GWJEmSJKm9MmHlSrjlFnjCE+BHPyqB5sx290xamMbH4f77YfXqI3Vr15Z685ZLmmeOYJYkSZIktdf+/fDDH8LFF8OyZaX84Q9LvaSjVSrwsY/BvffCoUOl/NjHHPUvqS0MMEuSJEmS2mtiAjZsgJ07S7Bs586yPzHR7p5JC9fBg7BpU0mLsWlT2ZekNjDALEmSJElqr54e2LWrvm7XrlIv6Wjj4zAwUP9QZmDAhTEltYUBZkmSJElSe42NQX9/fV1/f6mXdLRKpfFDGVNkSGoDA8ySJEmSpPaqVGDHjrJIWXd3KXfsMFgmTWd0tPFDmdHR9vRH0pJmgFmSJElqlYmJcrNfW0o62r59sG0bbN0KBw6Uctu2Ui/paD09cP319Q9lrr/etDKS2sIAsyRJktQKExMwPAzr1sGyZaUcHjbILDVSqcA118Dq1SVYtnp12XcEs9TYvn1w0031D2VuusmHMpLawgCzJEmS1AouwCTNnNP9pdmpVGDzZtiyBZYvL+XmzT6UkdQWBpglSZKkVnABJmnmnO4vzV6lArfcAgcPltLvF0ltYoBZkiRJaoXx8cYjMh3BLB3N6f7S7Bw4AD/6EVx8cUnDdPHFZf/AgXb3TNISZIB5ETr11FOJiBlvwKzan3rqqW3+DSVJkjpApQKDg/UjMgcHHWEmNeJ0f2l2Dh2Cyy6rT8N02WXltSTNs+52d0Cz98gjj5CZLfv8yaC0JEmS5qCrC/r6YGioBMnGx0vZ5RgP6SieL9Ls9PQ0TsNkWhlJbeC3tSRJktQqXV3Q21tfSpI0V2NjjdMwjY21pz+SljSvcCVJC0ZEvDUivhwRj0bESETcFhHPmsH7IiKuiIivR8TBiHggIt41H32WJElNMDEBw8Owbl3JJ7tuXdmfmGh3z6SF6YQTYPv2+jRM27eXekmaZwaYJQnKzcvoaH2pdlgLfAA4H3gRcAj4XEQ8XnL4PwVeB7wFOBv4NeCLreumJElqqvFxuO66+kX+rrvORTGl6UTAKafALbfAwYOlPOWUUi9J88wAsyQ5YmbByMyXZub2zLw7M/cArwZWAc+b7j0R8QxgC/CKzPxEZn4rM+/KzNvnqduSJGmuVq6ESy+tX+Tv0ktLvaSjLVsGmfDDH9aXy5a1u2eSliADzJI0Pg4DA/UrMA8MOGJmYeilfFc9cow2rwC+BfxKRHwrIr4dER+KiL5GjSNic0TsjojdIyMjLeiyJEmatbEx2Lix/nps40bzyUrTOXgQHn0UNm0qD2U2bSr7Bw+2u2eSliADzJJUqTRegblSaU9/VOt9wD8Adx6jzU8DTwV+E7icMur554HbIuKo77nMvC4z12TmmlWrVjW9w5Ik6Tj09ja+HuvtbU9/pIXu0CHYsKH+ocyGDeW1JM0zA8ySND7eeAVmRzC3VUS8B+gHLs7Mw8do2gUsA16dmV/MzL+hBJl/EXhu63sqSZLmbHwcrroK9uwpAbI9e8q+12NSYz09jR/K9PS0pz+SljQDzJJUqcDgYP0KzIODjmBuo4h4LzAAvCgzv/U4zR8ADmXmN2vq7gUOA2e2qIuSJKmZVq4sU/xrczBv2mQOZmk6o6ONB8mMjranP5KWNAPMktTVBX19MDRUcpYNDZX9Lv9EtkNEvI8jweWvz+AtdwDdEfEzNXU/DZwAfKcFXZQkSc22bx+sX18/3X/9+lIv6Wg9PXDDDfWDZG64wRHMktrC6IkkQQkm9/bWl5p3EfF+YAOwHngkIk6vbj01bf4wIj5f87bPAX8P/PeI+IWI+AXgvwN/B+yex+5LkqTj5ZoY0uzs2wcf+hBs3QoHDpTyQx/yoYyktjCCIklaSF4H9AKfp6S+mNzeVNPmDOCfRytn5gTw68Aw8EXg08D3gFdUj2mGTj31VCJixhswq/annnpqm39DSdKC5ZoY0uxUKrB5c31amc2bfSgjqS26290BSZImZWbMoM3lDeoeAP51K/q0lDzyyCNkZss+fzIoLS0pExMlQFapHCmdJSMdbXJNjIGBMnK5v981MaRjqU3z53eMpDbzL48kSZLUChMTMDwM69bBsmWlHB4u9ZLquSaGNHum+ZO0QPjXR5IkSWqF8fEyGrN20bKBAaf8S5IkqaMYYJYkSZJawUXLpJlzxL8kSYuWAWapDSLiBRExFBHfj4iMiMuP0faD1TZvmq6NJElagFy0TJo5R/xLkrRoGWCW2qMHuBt4A7B/ukYRcQnwi8D989QvSZLULJOLlq1dC93dpXTRMqkxR/xLkrRoGWCW2iAzb8/Mt2XmzUDDeX8R8VTgfcB64Mfz2T9JktQELlomzZwj/iVJWrS8upUWoIjoBgaBP8jMe9rdH0mSdJy6uqC3t76UdLQVK2DHjvoR/zt2lHpJkrSgeYUrLUxvBx7OzL+YSeOI2BwRuyNi98jISIu7JkmSJDXZ+Dhs2wZbt8KBA6Xcts0RzJIkLQIGmKUFJiLWApcDG2f6nsy8LjPXZOaaVatWtahnkiRJUov09sI118Dq1WUE8+rVZb+3t909kyRJj8MAs7TwrAXOAB6IiEMRcQh4KvBHEfG9tvask01MwOhofSlJkqT5MTraOAfz6Gh7+iNJkmbMALO08HwAeDZwTs12P/Be4IJ2daqjTUzA8DCsWwfLlpVyeNggsyRJ0nypVBrnYK5U2t0zSZL0OAwwS20QET0RcU5EnEM5D8+s7p+ZmcOZeXftBvwYeDAzv9HWjneq8XEYGICdO+HQoVIODJjzT5Ikab7s3984B/P+/e3umSRJehwGmKX2WAPcVd1WUBb1uwt4Rzs7tWRVKrBrV33drl2OmJEkSZovlUrjHMxej0nTM82fpAXCALPUBpm5MzOjwXb5NO2flpl/Ms/dXDrGxxvn/HMEsyRJ0vzwekyaHdP8SVpADDBLUqUCg4P1Of8GBx0xI0mSNF8qFfjYx+Dee0vKsnvvLftej0mNmeZP0gJigFmSoDz137at5Pzbtq3sS5KkjhURJ0TENRFxX0QcqJZ/EBHdNW0iIq6OiPsjYn9E7IyIZ7az3x0rs1yHbdoEy5eX8sCBUi/paKb5k7SAGGCWpPFxeOUr4elPLyOYn/70su/Tf0nSXJkfcyF7C/BbwH8Efh54Q3X/rTVt3gy8EdgCPBcYBj4bEb3z29UlYGwM1q+vH425fn2pl3Q008pIWkAMMEuST/8lSa1gfsyF7nzgtsy8LTO/nZlDwBDwr6CMXgauAN6Vmbdk5t3Aa4BeYH2b+ty5ensbX4/1GsuXGjLNn6QFxACzJPn0X5LUCubHXOh2Ab8cET8PEBH/AngRcHv1+FnA6cBnJt+QmfuBL1KC02qm0dHG12Ojo+3pj7TQdXVBXx8MDcHBg6Xs6yv1kjTPmvKXx/xlkhY1F5WRJLWCM2QWuj8CbgT+KSJ+DHwN+FBmfqB6/PRq+dCU9z1Uc6xORGyOiN0RsXtkZKQVfe5cPT2wY0f9aMwdO0q9pMa6usoo/9pSktqgWX99zF8maXE7eLB+UZmDB9vdI0nSYucMmYXuVcBllHQX51Zfvy4iNh7vB2bmdZm5JjPXrFq1qkndXCIiynVY7aLLy5eXekmStKA1K8Bs/jJJi5dTmCVJrWB+zIXuj4E/ycyPZOaezLwReA9HBsk8WC1Pm/K+02qOqVnGx2Hr1hJchlJu3er1mCRJi0CzAszmL5O0eDmFWZLUCubHXOhWAoen1B3myD3SfZRA8oWTByNiOfB84Evz0cElZeVKuPRS2LKljFzesqXsr1zZ7p5JkqTH0ayrW/OXSVq8nMIsSWoV82MuZLcB/ykiXhYRT4uI3wB+B/g4QGYmcC3wloh4ZUQ8C7gBGAN2tKfLHWxsDG666cgo5q1by/7YWLt7JkmSHkezrnDNXyZp8XIKsyRJS9EW4GbgA8A9wJ8C24Ara9q8G3gv8H5gN3AG8JLMHJ3fri4BPT2NRzC7yJ80vYkJGB2tLyWpDZoVYDZ/maTFyynMkiQtOZk5mplXZOZTM3NFZv50Zr4tMw/UtMnMvDozz8jM5Zn5wup6Mmo2RzBLszMxAcPDsG4dLFtWyuFhg8yS2qJZ0RPzl0la3JzCLEmS1D6OYJZmx4XKJS0gzYqgmL9MkiRJknR8xsZg48b6YNnGjY5glqbjQuWSFpBmBZjNXyZpcTN/mSRJUvv09jYOlvX2tqc/0kLnQuULWkScEREfioiRiDgQEf8UES+sOR4RcXVE3B8R+yNiZ0Q8s519luaiKQFm85dJWtTMXyZJahUfYEozMzraOFg26ngkqSEXKl+wIuIJwB1AAC8DzqYMzByuafZm4I3V+udWj302InyqpkXJJKOSZP4ySVIr+ABTmrmenhIcu/fecj12771l3xzMUmMuVL6QvRl4IDMvy8z/k5n3ZebnM/MeKKOXgSuAd2XmLdXBl68BeoH1beu1NAf+5ZEk85dJklrBB5jSzB04AD/+MWzaVBb527Sp7B848PjvlZYqFypfqC4C/i4iPhoRwxHxDxHx+mpgGeAs4HTgM5NvyMz9wBeB8+e9t1IT+NdHksxfJklqBR9gSjN36BBcdln9A5nLLiuvJWlx+WngdcC3gJcC7wPeBfxW9fjp1fKhKe97qOZYnYjYHBG7I2L3yMhI83sszZEBZkkyf5kkqRV8gCnNnIv8SeocXcDfZ+ZbM/OuzNwO/BlHAsyzlpnXZeaazFyzatWqpnVUahYDzJJk/jJJUiv4AFOaORf5k9Q5HgD+aUrdPcCZ1dcPVsvTprQ5reaYtKgYPZEkMH+ZJKn5fIApzVx3N3z4w/UPZD784fJakhaXO4BnTKn7OeA71df3UQLJF04ejIjlwPOBL81HB6Vm89takiRJapXJB5fgVH/pWJYvhxNPhG3b4Kyz4L77yv7y5e3umbRwTUyUtEuVypHSh5gLwXuBL0XElcBHgV8A/iPwNoDMzIi4FnhbRHwd+Cbwe8AYsKMtPZbmyL88kiRJkqT2GhuDgQF4+tPLqOWnP73sj421u2dLQkS8ICKGIuL7EZERcfmU4xERV0fE/RGxPyJ2RsQzp7R5YkTcGBF7q9uNEfGE+fw9lpSJCRgehnXrYNmyUg4Pl3q1VWZ+GbgI+DfA3cA7gauAD9Q0ezclEP1+YDdwBvCSzDQvkBYlA8ySJEmSpPZykb9266EEwt4A7G9w/M3AG4EtwHOBYeCzEVH7H2gHcC7wK9XtXODGFvZ5aRsfLw9hdu6EQ4dKOTDgQrILRGb+ZWb+y8xcnpk/l5l/lplZczwz8+rMPKPa5oWZeXc7+yzNhQFmSZIkSVJ7jY83XuTPYNm8yMzbM/NtmXkzUDcENiICuAJ4V2beUg2CvQboBdZX25xNCSpvzsw7M/NO4LXAr0fE1Fy0aoZKpfFDGReSldQGBpglSZKkVpmYgNHR+lLS0VauhB076hf527Gj1KvdzgJOBz4zWZGZ+4EvAudXq86j5I+tXaDsDmC8po2ayYcykhYQA8ySBAYAJEnNZ35Maeb27YM77oCbb4aDB0t5xx2lXu12erV8aEr9QzXHTgdGpqYAoKTSOJ0GImJzROyOiN0jIyNN7vISUKnA4GD9Q5nBQUcwS2oLA8ySZABAktQK5seUZm7lSjj3XLjkknI9dsklZd8RzB0rM6/LzDWZuWbVqlXt7s7i09UFfX0wNFQeygwNlf0uwzyS5p9/eSTJAIAkqRXMjynN3NgYbNxYfz22cWOpV7s9WC1Pm1J/Ws2xB4FV1XzNwD/nbu6raaNm6+oqC2HWlpLUBv71kSQDAJKkVjA/pjRzvb2Nr8d6e9vTH9W6jxIkvnCyIiKWA8/nSM7lO4EeSi7mSecBFerzMktSe5gWs6W6290BSWq7sbFyw79z55G6/v5Sf/LJbeuWNN/y90+Gq09p7edLS8lkfsyBgRIo6+83P6Y0ndHRxtdjo6NwSuu+m1RERA/ws9XdLuDMiDgH+GFm/r+IuBZ4W0R8Hfgm8HuURf12AGTmPRHxKeCDEbG5+jkfBD6Zmd+Yv99EkhqYTIs59ZrMtDJNY4BZkrq7Yft22LDhyJfN9u2lXlpC4u2PUrM2T/M/P4K8umUf3/Ei4gXAm4DnAE8GNmTmDTXHbwBeM+Vtf5eZv1TTZhnwJ8AAsAL4PPC6zPxeSzu/VNXmx6xUysjlSsUbGamRnh64/vqSFmPyeuz660u95sMa4K9q9t9e3T4EXA68m/K98X7gicDfAS/JzNGa96wHtgKfru4PAa9vaa+XuomJI98tfsdI06tNiwlH0mIODTlTpkmMnixCjjCTmmz5crjySti6Fc4+G+65p+zfeGO7eyZJtXqAu4EPV7dGPge8umb/sSnHrwVeQQkw/wB4D/DJiHhOZh5uam9VTObFBG9gpGPZtw9uuqn+euymm+C3f9tzZx5k5k4gjnE8gaur23RtHgEubXLXNB1HZEozZ1rMljPAvAg5wkxqsvFxuP9+WL36SN3ataXeGxpJC0Rm3g7cDv88WrmRg5nZcDGliDgF2EgZ+fzZat2rge8AL+bIiDNJmn+VCmzebEoZaaYckSnN3OS6GFPTMHnP3zQ+1pKkyRyZa9eWtBhr13pDI2mx6o+I4Yj4ZkRsi4i+mmPPAU4EPjNZkZnfBe4Bzp/nfkpSva4ueNKT4NZb4eDBUj7pSY7ElKbjiExp5rznbzm/rSWpNkfmwYOldGqZpMXnU8BlwAXAG4FfBL5QzbsMcDpwGHh4yvseqh47SkRsjojdEbF7ZGSkNb2WJIDDh2FkBC66CJYtK+XISKmXdLTJEZm1JkdkSqrnPX/L+S8pSXAkR2ZtKUmLSGZ+JDOHMnNPZt4G/CrwDOBlc/jM6zJzTWauWbVqVdP6KklHGRuD9evL9OVDh0q5fn2pl3Q0R2RKs+M9f0uZg1mSJKkDZeb9EfE94OnVqgeBE4AnAbXDkU8D/maeuydJ9Xp7G0/3Nzem1FjtiMxKpYxcrlQMmklqC//ySBKUVZhHR+tLSVrEIuJJwE8CD1SrvgL8GLiwps1TgLOBL817ByWp1uho4+n+o6Pt6Y+0GDgiU9IC4V8fSZqYgOFhWLeu5Pxbt67sG2SWtIBERE9EnBMR51Cu4c6s7p9ZPfYnEXFeRDwtItYCtwHDwMcBMnMvcD3w7oh4cUT8AnAj8FXgc234lSTpiJ4euOUWuPfekiLj3nvLfk9Pu3smSZIehwFmSRobg4GB+px/AwPm/JO00KwB7qpuK4C3V1+/g7J432rgE8A3gQ8B3wDOy8za4X9XUALOHwXuAMaAl2emq2hJaq8IeOwx2LQJli8v5WOPlXpJkrSgGWCWpJ4eePKTYc+eEmDes6fsO2JG0gKSmTszMxpsl2fm/sx8aWb2ZeZJmfnUav13p3zGwczckpk/kZkrM/PlU9tIUluMjzd+4D8+3u6eSZKkx+Eif5K0bx+8852wYUNZTKa/H7ZvL/UGmSVJklqvUmm8yF+l0p7+SJKkGXMEsyRNTJTgcu2ImQ0bzMEsSZo7F5GVZmZ8HK66qn5G2VVXOYJZkqRFwACzJPX0NB4x4+hlSdJcuIisNHMrV8LrX1/yL0MpX//6Ui9JkhY0A8ySNDZW0mLU6u93kT9J0tyYU1aauQMH4NFH6xf5e/TRUi9JkhY0A8yS1N0NH/4wrF1bXq9dW/a7TVMvSZoDc8pKM3f4cOOUZYcPt7tnkiTpcRhglqTly0s6jG3byiiZbdvK/uQUTUmSjsf4eOMZMo5glo5myjJJkhYtA8yS1NUFJ58Mq1ZBRClPPrnUS5J0vCoVGBysnyEzOOgIZqkRU5ZJkrRoGT2RpIkJGBmBiy4qizBddFHZdxEmSdJcdHVBXx8MDcHBg6Xs6/MBptRIV1fjlGWeL5IkLXh+W0uSizBJklqlqwt6e+tLSUdbvryM7q9NWVapmLJMkqRFwCtcSXIRJkmSpPYaH4cvfAGe+MSSsuyJTyz7PvCXJDXDxASMjtaXahoDzJLkIkySJEnt1dMDF1xQgstQygsucJE/SdLcTUzA8DCsW1fSYq5bV/YNMjeNAWZJqlTgYx+De+8tKTLuvbfsO4JZkiRpfhw8WFJjXHxxufm/+OKyf/Bgu3smSVrsTIvZcgaYJUmSJEnt9eMfw/r19Tf/69eXekmS5sK0mC1ngFmSDhyAvXth06aykMymTWX/wIF290ySJGlp6O1tfPPf29ue/kiSOodpMVvOALMkHToEGzbUj5jZsKG8liRJUuuNjja++R8dbU9/JEmdo1KBwUFYuxa6u0s5OOgI5iYywCxJPT2NR8y4qIwkaa5csVyame5u2L69/uZ/+/byWpKkuejqgr4+GBoquf2Hhsp+l2HRZvFfUpIcMSNJagVXLJdmbsUKuO02uPnmcvN/881lf8WKdvdMktQJurpK2qXaUk3jv6Yk9fTADTfUj5i54QZHMEuS5sYVy6WZ278fXv5yuOSS8kDmkkvK/v797e6ZtHA5S0bSAmGAWZLGxuBDH4KtW8vCflu3lv2xsXb3TJK0mLliuTRzrokhzY6zZCQtIAaYJalSgU2bYMsWWL68lJs2GQCQJM2NK5ZLM9fb2/iBTG9ve/ojLXTOkpG0gBhglqSDB0tg+ZZbyutbbin7Bw+2u2eSpMXMFculmRsba/xAxhllUmPOkpG0gBhglqTDh+GVr4Sf+Ak44YRSvvKVpV6SpOPliuXSzHV1wUc+AvfeW0Zj3ntv2fd8kRpzloykBcRv60UqIlq2PfGJT2z3ryfNr56exk//XeRPkjRXrlguzczy5ZBZ0pQtX17KzPJa0tGcJSNpAfEKdxHKzFlts33PD3/4wzb/htI8Gx1t/PR/dLQ9/ZEkSVpqzCcrzY6zZCQtIN3t7oAktV1PT8m7/MMfwllnwX33wamnOoJZkiRpvrjInzR7k7NjwHNFUlv5aEuSIuCxx+qnZD72WKmXJElS67nInyRJi5YBZklySqYkSVJ7nXACbN9en092+/ZSL0mSFjRTZEhSpdJ4SqYLZEiSJM2PTFixArZtO5KybMWKUi9JkhY0RzBL0vh44ymZjmCWJEmaH93dJaB86qklTdmpp5b9bsdESZK00BlglqRKBQYH66dkDg46glmSJGm+dHeXh/sXXwzLlpVyfNwAsyRJi4ABZqkNIuIFETEUEd+PiIyIy2uOnRgRfxQRX42I8Yh4ICJ2RMSZbexyZ+vqgr4+GBqCgwdL2ddX6iVJktR64+Owfn39mhjr1zujTJKkRcDoidQePcDdwBuA/VOOrQTOBd5ZLV8B/BTwqYhwCEerdHVBb299KUmSpPnR29t4TYze3vb0R5IkzZjBKqkNMvN24HaAiLhhyrG9wIW1dRHxWuBrwNnAnvnppSRJkjRPRkfLGhg7dx6p6+8v9aec0rZuSZKkx+cQPWlxOLlaPtLWXnSyiYlyA1NbSpIkaX5UKrBjR/2aGDt2uCaGJEmLgAFmaYGLiJOAPwVuy8zvTdNmc0TsjojdIyMj89vBTjAxAcPDsG5dWVRm3bqyb5BZkiRpfuzbB3fcATffXNbEuPnmsr9vX7t7JkmSHocBZmkBq+Zcvgl4ArBhunaZeV1mrsnMNatWrZqv7nWO8XE4fBhuvbXc0Nx6a9l3URlJ0lw5Q0aamRNPhOc9Dy65pDzwv+SSsn/iie3umSRJehwGmKUFqhpcHgSeDVyQmT9oc5c614oVZRsZgcxSTtZJknS8JiZg71546KHy/fLQQ2XfILN0tB//GB59tP6B/6OPlnpJkrSgGWCWFqCIOBH4KCW4/MuZ+WCbu9TZDhwoNzCbNsHy5aV89NFSL0nS8TpwoASUa79f9u71+0VqZOVKOPlkuOiiMoL5oovK/sqV7e6ZJEl6HAaYpTaIiJ6IOCcizqGch2dW98+sjlz+X8AvAQNARsTp1c0hta0wMQEbNpRVyw8dKuWGDY4wkyTNzaFDjb9fDh1qd8+khWd8HNavrz9f1q83ZZkkSYtAd7s7IC1Ra4C/qtl/e3X7EHA18Ipq/VemvG8DcEOL+7b09PTApz8N+/dDb2/JkbliRVnBXJKk49XTA7t21dft2lXqJdXr7W18vvT2tqc/kiRpxhzBLLVBZu7MzGiwXZ6Z357mWGTmDe3ue0c6dAh+8IP6KZk/+IEjzCRJczM2Bv399XX9/aVeUr3R0cbny+hoe/ojSZJmzACzJO3f33hK5v797e6ZJGkx6+6GD38Y1q4tr9euLfvOkFkwIuKMiPhQRIxExIGI+KeIeGHN8YiIqyPi/ojYHxE7I+KZ7exzx+ruhu3b68+X7ds9XyRJWgQMMEuSUzIlSa2wbBmceCJs21YW9tu2rewvW9bungmIiCcAdwABvAw4G9gCDNc0ezPwxmr9c6vHPhsRXiQ024oVcOWVsHVrOV+2bi37K1yCRJKkha5pAWaf/ktatEZH4dvfhh/9CA4fLuW3v+2UTEnS3IyNwcAAPP3pZRTm059e9k2RsVC8GXggMy/LzP+Tmfdl5ucz8x4o9y/AFcC7MvOWzLwbeA3QC6xvW6871ego3H8/rF5dzpfVq8u+12OSJC14TQkw+/Rf0qK2YgV0ddXnYO7qcsSMJGlunCGz0F0E/F1EfDQihiPiHyLi9dXAMsBZwOnAZybfkJn7gS8C5897bztdTw9cf319iozrr3dRTEmSFoFmjWD26b+kxcsczJKkVhgfb7xo2fh4e/qjqX4aeB3wLeClwPuAdwG/VT1+erV8aMr7Hqo5ViciNkfE7ojYPTIy0vwed7KxMbjppvoUGTfd5Ih/SZIWgWYFmC/Cp/+SFitHmEmSWqFSgcHB+hGZg4OlXgtBF/D3mfnWzLwrM7cDf8aRAPOsZeZ1mbkmM9esWrWqaR1dEioV2LQJtmyB5ctLuWmT54skSYtAswLMPv2XtHiNjpYb/ocfLjmYH3647JvzT5I0F11d0NcHQ0Nw8GAp+/pKvRaCB4B/mlJ3D3Bm9fWD1fK0KW1OqzmmZnnssZKqrHZRzGXLSr2kxiYmyj1LbSlJbdCsq1uf/ktavFasgOc9Dy65pNzIXHJJ2TcHsyRJnewO4BlT6n4O+E719X2UQPKFkwcjYjnwfOBL89HBJeXHP4Y///MSXIZS/vmfl3pJR5uYgOFhWLeu3MOsW1f2DTJLaoNmBZh9+i9p8TIHsySpFbz5X+jeC/xSRFwZET8bEf8a+I/A+wEyM4FrgbdExCsj4lnADcAYsKM9Xe5gPT1w6aX1KTIuvdRF/qTpjI/DwED9PczAgHn+JbVFswLMPv2XtHiZg1mS1Arj43DddfWLll13nTf/C0Rmfpmylsy/Ae4G3glcBXygptm7KYHo9wO7gTOAl2SmebSabWwMNm6sD5Zt3Ogif9J0KpXG9zDmLZfUBt1N+pz3Al+KiCuBjwK/QHn6/zYoT/8j4lrgbRHxdeCbwO/h039JC8HoKPzgB5BZgsqjoxBRylNOaXfvJEmL1cqVZQTmxo3lpr+/H66/vtRrQcjMvwT+8hjHE7i6uqmVfOAvzc74ePle2bnzSF1/f6n3vJE0z5oygtmn/5IWtRUryoXYRReVKcwXXVT2zcEsSZoLR2RKMzc6WoJjtfr7XXRZmk6lUhYmX7sWurtLOTjoCGZJbdG0Jawz8y8z819m5vLM/LnM/LPqE//J45mZV2fmGdU2L8zMu5v18yXpuJmDWZLUCo7IlGaup6eM8K8Nll1/vTmYpel0dUFfHwwNwcGDpezrK/WSNM/8yyNJBgAkSa0wOX251uT0ZUn1xsfhppvqc5bfdJPni3QsXV3lnqW2lKQ28K+PJI2Owo9+VLbDh4+8dkqmJGkunL4szdzKlfD618Py5WV/+fKyb85ySZIWPAPMklSpwKOP1udgfvRRAwBtEBFvjYgvR8SjETESEbdFxLNm8f6nR8RoRJjgVFL7OX1ZmrkDB0p6sk2bSnB506ayf+BAu3smICK+HRHZYPvL6vGrGxx7sN39liTND69uJWl8vHEOZqdktsNaygKx5wMvAg4Bn4uIUx/vjRFxEvAR4Iut7KAkzYrTl6WZmZiASy+tvx679NJSr4XgucAZNdv/v737j47zOg87/31ASAQ1gCjRJvWjiWu51SaupXO8Kb2NLbhG3LWTTXK4tOVtDCxjiVGp3bpm4x+NXcdWw+w5Sl1v6h+h5Tbi0ZKRFcDtmrZMbZPWPzasy9hxzW7dUKmt6BwzPxpZBCNREjAiKYJ49o8LWjPAUASpGbwzg+/nnPdc3Pu+M34gn0vMPO99n/tjQAL/uuGaRxZdc/MKxyhJqoifcCVpZASuvx6OHClfaI4cKX1rMK+4zPzJzNybmQ9n5hHg54GNwC3LePk/A/4Q+L87GaMkSeqA4eHWe2K4yV9XyMzjmfn4uQP4aeAZmhPMc43XZObxaqKVJK00E8yS9OyzsHcv/PAPQ0Rp9+4t46raCOVv1YkXuigifgb4WWDnSgQlScs2P19q+je2kpaamWm9KaZ7YnSdiAjgDuCBzDzZcOoVEfFYRByNiM9GxCsu8D53RsThiDh8/Li5aEnqZSaYJenyy+GJJ5prMD/xRBlX1T4JfBv4xvkuiIjrgT3Atsy8YO1lv8xIWjHz8zA9DVu2lL8vW7aUvklmaanhYdi3r3lTzH37XMHcnd4E3ED5/HXON4HbgZ8CdgDXAl+PiJec700y897M3JyZmzdu3NjBcCVJnWaCWZJOnmxdg/nkyQu9Uh0UER8DRoFbM/PsC1z6GeBfZOY3l/O+fpmRtGLq9fKI/+c+Vzb5+9znSt8a/9JSJ0+Wzf327Ckb++3ZU/p+HutGO4BvZeZ/OTeQmb+bmf86M/8wM79CebJsALitqiAlSSvHBLMkWYO560TEx4Fx4I2Z+b0LXP5G4FciYi4i5oD7gNpC/85OxypJ57VuHdxyC7ztbWUF89veVvrr1lUdmdR9zp6Ft78dbryxrGC+8cbSP/tC95i10iJiE/A/07x6eYmFp8r+CLhxJeKSJFXLBLMkWYO5q0TEJ3k+ufzdZbzkZuDVDcc/AU4u/OyGf5KqU6+3fkLGFczSUiMjrTf584Z/t7kdOA1MvdBFETEE/Cjw/RWISZJUMRPMkmQN5q4REfcA24EJ4EREXLtwDDdc808j4qvn+pn5cOMB/AUwv9B/wc0BJamjTJhJy+cmf11vYXO/vwd8dvG+FxHx6xHxhoi4ISL+FvA5oAb8VgWhSpJWmAlmSTp5stT527271Pzbvbv0rflXhXcCI8BXKStezh3/qOGa64C/tvKhSdJFmpmBu+5qLsF0110mzKRWhofhC18oN/nPni3tF77gJn/dZYxS8qJVeYwfoqxqfgT4PGWV849n5p+uWHSSpMoMVh2AJFVueBi2bYM77igry0ZH4b77/EJTgcyMZVxz+wXO7wP2tSciSXoRhoZgx45SFuPc35fJyTIuqdmZM89vvLx4vqxZU3V0AjLz94CWn9Uy8+0rHI4kqYu4glmSZmfh2LGySub06dIeO1bGJUm6VKdPt67BfPp01ZFJ3cf5IklSzzLBLEm1Grz85fCWt5QazG95S+nXalVHJknqZcPDrWsw+4SMtJQ1yyVJ6lkmmCWpXm+9YqZerzoySVIvq9dbb1rm3xdpKTf5kySpZ5lgliRXzEiSOqFWg6kpGBuDwcHSTk35hIzUymWXlZrLjfNlcrKMS5KkruYmf5J0bsXMwYPPj51bMbN+fWVhSZJ63MAAbNoEBw6UpHK9XtoB13hIS6xdC+vWwf79cNVV8NRTZa6sXVt1ZJIk6QL8dCtJ69a1XjGzbl3VkUmSet3AQHkiprGVtNTsLHzlK5BZ+pml76bLkiR1PVcwS9LgILzkJfDgg+XL/8xMSS4P+k+kJEnSiqjV4JZb4G1vK6XKRkfLDX9LykiS1PVcQiFpVYqI5481a5i47Tb+5M//nPlM/uTP/5yJ224j1qxpuk6SpIt29iw8/TTMz5f27NmqI5K6k5suS5LUs0wwS1qVMrPpmJya4uU33cSawUFeftNNTE5NLblGkqSLcvYsTE/D1q2ljuzWraVvkllayk2XJfWpiPhgRGREfKphLCJiV0Q8FhEnI+JgRLyqyjilF8MEsyRJktQJs7OtV2RaU1Za6tymy43ObbosST0qIn4cuBP4w0Wn3g+8D9gJvAaYBr4cEd5VU08ywSxJkiR1gisypeUbHobPfx6eeKKs8n/iidIfHq46Mkm6JBGxHvht4BeAEw3jAbwb+Ehm7s/Mh4HbgBFgooJQpRfNBLMkSZLUCa7IlJbv9Gk4dQpuvbWUlLn11tI/fbrqyCTpUt0LfC4zf2/R+A3AtcCXzg1k5knga8DrVi68VWZ+vnwGa2zVNiaYJUmSpE4YHob9++HRR0uJjEcfLX1XZEpLnTnTuqTMmTNVRyZJFy0idgB/Hfhwi9PXLrTHFo0fazi3+P3ujIjDEXH4+PHj7Qt0tZifL/tgbNlSbmJu2VL6JpnbxgSzJEmS1AkR8NxzsGMHDA2V9rnnyrikZpaUkdQnIuJHgF8DJjKzLXfJMvPezNycmZs3btzYjrdcXep1GB9vvok5Pl7G1RYmmCVJkqRO8MuMtHyWlJHUP14LvBT4o4iYi4g54A3AOxd+fmLhumsWve4a4PGVC3MVqdVa38Ss1aqJpw+ZYJYkSZI6wS8z0vINDcHkJIyNweBgaScny7gk9ZYHgZuBVzcch4HPLvz8x5RE8pvOvSAihoDXA19fwThXj3q99U1Mb/q3jQlmSZIkqRP8MiMt35kzMDAAe/aUzf327Cl9azBL6jGZ+VRmPtx4AHXgyYV+Ap8APhARb42Im4B9wCwwWVng/axWg6mp5puYU1Pe9G+jwaoDkCRJkvrSuS8z4+Nl5fLoqF9mpPOZn4e3v72UkjlnbAy++MWqIpKkTvoosA64B7ga+Cbw5sy0LlAnDAzApk1w4ED5HFavl3bAdbft4n9JSZIkqU0i4vljzRom3vMe/mT3buZPneJPdu9m4j3vIdasabpOEjA8DNdfD0eOlJrlR46U/vBw1ZFJ0ouWmWOZ+a6Gfmbmrsy8LjOHMvMNCyud1SkDA2Xj2MZWbeMKZkmSJKlNylOvS0UEmcnk1BSTU1MrHJXUA06ehLvvhu3bn1/xv3dvGXfVvyRJXc10vSRJkiSpWnNzJbl88GD5+eDB0p+bqzoySZJ0ASaYJUmSJEnVGhlpXSJjZKTqyCRJ0gWYYJYkSeoREfG3I+JARPxFRGRE3L7ofETEroh4LCJORsTBiHjVomuujojPRMTTC8dnIuKqlfw9JGmJZ58tJTJ27oShodLefXcZlyRJXc0EsyRJUu8YBh4GfhE42eL8+4H3ATuB1wDTwJcjonEJ4CTwY8BPLRw/BnymgzFL0oXNz7cukTE/X3VkkiTpAtzkT5IkqUdk5u8AvwMQEfsaz0VEAO8GPpKZ+xfGbqMkmSeA34yIV1KSyqOZ+Y2Fa/434D9ExI9k5iMr9KtIUrPh4bK5X6NDh8q4JEnqaq5gliRJ6g83ANcCXzo3kJknga8Br1sYei0wC3y94XW/D9QbrvmBiLgzIg5HxOHjx493Km5JgpkZGB1tHhsdLeOSJKmrmWCWJEnqD9cutMcWjR9rOHctcDwz89zJhZ+nG66h4dy9mbk5Mzdv3LixAyFL0oLBQdi7F8bGys9jY6U/6EO3kiR1OxPMkiRJkqRqrVsHH/oQ7N4Np06V9kMfKuOSJKmrmWCWJEnqD48vtNcsGr+m4dzjwMaFes3AD2o3b2q4RpJW3uwsPPYY3HxzWbV8882lPztbdWSSJOkCTDBLkiT1h6OUJPGbzg1ExBDwep6vufwNYJhSi/mc1wI1musyS9LKGhhoXSJjwK+skiR1O/9aS5Ik9YiIGI6IV0fEqymf41620H/ZQi3lTwAfiIi3RsRNwD7Kpn6TAJn5HeDfAr8ZEa+NiNcCvwn8P5n5yMr/RpK04Ior4KGH4HOfg9OnS/vQQ2VckiR1NRPMkiTpByKiY8fVV19d9a/XDzYD/3nhWAf86sLP/8fC+Y8CHwfuAQ4D1wFvzsyZhveYAP4L8O8Wjv8C/PxKBC9J5/Xss7B1K7ztbbB2bWm3bi3jkiSpq7klryRJAqAsgF2+iLjo1+jFycyDQLzA+QR2LRznu+YEsK3NoUnSizM/D+94Bxw8WPoHD5b+F79YZVSSJGkZXMEsSZIkSarW8DAcOtQ8duhQGZckSV3NBLMkSZIkqVqzszA62jw2OlrGJUlSVzPBLEmSJEmq1sAA7N0LY2MwOFjavXvLuCRJ6mrWYJYkSZIkVWtgADZsgP374aqr4KmnSqLZBLMkSV3Pv9aSJEmSpGpdfjnMzcGTT0JmaefmyrgkSepqJpglSZIkSdU6dQqeeQZ27IChodI+80wZlyRJXc0EsyRJkiSpWvPzcP/9sHt3SSrv3l368/NVRyZJki7ABLMkSZIkqVq1GmzbBjt3lhXMO3eWfq1WdWSSJOkCTDBLkiRJkqo1Owt33AEHD5baywcPlv7sbNWRSZKkCzDBLEmSJEmq1sgIHDrUPHboUBmXJEldzQSzJEmSJKlas7MwOto8NjrqCmZJknqACWZJkiRJUrXWrCmb+o2NweBgae+/v4xLkqSuNlh1AJIkSZKkVW5goGzot2cP3HADHD1a+gOuiZIkqdv511qSJEmSVK3nnoNbb4UbbywrmG+8sfSfe67qyCRJ0gWYYJYqEBF/OyIORMRfRERGxO2LzkdE7IqIxyLiZEQcjIhXVRSuJEmS1Flu8iddvPl5mJlpbiWpAiaYpWoMAw8DvwicbHH+/cD7gJ3Aa4Bp4MsR4SdsSZIk9Z+ZGbjrLjhyBObmSnvXXWVc0lLz8/D003DsGGSW9umnTTJLqoQJZqkCmfk7mfnLmfk5oOkTQEQE8G7gI5m5PzMfBm4DRoCJFQ9WkiRJ6rRaDXbsgJ07YWiotDt2lHFJS506VRLKO3aUObNjR+mfOlV1ZJJWIRPMUve5AbgW+NK5gcw8CXwNeF1VQUmSJEkdU6/DxAQcPFhWMB88WPr1etWRSd1pbg62b2+eM9u3l58laYUNVh2ApCWuXWiPLRo/BvyVVi+IiDuBOwFe9rKXdS4ySZIkqU3Kg3vF/NmzRIsazDkywkDDdZm5UuFJ3W14uHXd8uHhauKRtKq5glnqA5l5b2ZuzszNGzdurDocSZIk6YIy8wdHzM7C6GjzBaOjxOxs03WSFpxnzjA7W008klY1E8xS93l8ob1m0fg1DeckSZKk/jE8DFNTMDYGg4OlnZpyNaZ0Ps4Z6eLMz5eNYxtbtY0JZqn7HKUkkt90biAihoDXA1+vKihJkiSpYwYGYNMmOHCA+VOn4MCB0h/wK6vUUsOc4fRp54z0QubnYXoatmyBtWtLOz1tkrmN/JdHqkBEDEfEqyPi1ZR5+LKF/suyPPv3CeADEfHWiLgJ2AfMApNVxdyrNmzYQEQs+wAu6voNGzZU/BtKkiT1iYEBGBlhzeAgjIyYKJMuZGHONLWSlqrXYXy8eVPM8XE3km0jN/mTqrEZ+L2G/q8uHL8F3A58FFgH3ANcDXwTeHNmzqxsmL3vxIkTHa3X17g5jSRJkiRJ6jK1WutNMWu1auLpQx25vRURH4yIjIhPNYxFROyKiMci4mREHIyIV3Xif1/qdpl5MDOjxXH7wvnMzF2ZeV1mDmXmGzLz4YrDliRJkiRJ6i31eutNMV3B3DZtTzBHxI8DdwJ/uOjU+4H3ATuB1wDTwJcjYqTdMUiSJEnSxXCRjCRJfapWa70ppiuY26atCeaIWA/8NvALwImG8QDeDXwkM/cvrMS8DRgBJtoZgyRJkiRdDBfJSJLUx9wUs+Pa/V/yXuBzmfl7i8ZvAK4FvnRuIDNPAl8DXtfmGCRJkiRpWVwkI0nSKuCmmB3Vtv+aEbED+OvAh1ucvnahPbZo/FjDucXvd2dEHI6Iw8ePH29XmJIkSZLUqG2LZPwOI0mSVqO2JJgj4keAXwMmMvNMO94zM+/NzM2ZuXnjxo3teEtJkiRJ+oF2L5LxO4wkSVqN2rWC+bXAS4E/ioi5iJgD3gC8c+HnJxauu2bR664BHm9TDJIkSZK0LJ1YJCNJK2p+HmZmmltJqkC7EswPAjcDr244DgOfXfj5jymJ5Dede0FEDAGvB77ephgkSZIkablcJCMtU0TsiohcdDzecD4WrnksIk5GxMGIeFWVMfe9+XmYnoYtW2Dt2tJOT5tkls7n7Fl4+ukyR55+uvTVNm1JMGfmU5n5cOMB1IEnF/oJfAL4QES8NSJuAvYBs8BkO2KQJEmSpIvwIC6SkS7GI8B1DcfNDefeD7wP2Am8BpgGvhwRIysd5KpRr8P4OBw8CHNzpR0fL+OSmp09W27AbN1abshs3Vr6JpnbZnAF/7c+CqwD7gGuBr4JvDkzZ1YwBkmSJEkiM58Cnmoci4gfLJJZ6H8C+OWI+C4l4fxhXCSj1WsuM5es3o+IAN4NfCQz9y+M3UZJMk8Av7mSQa4atRocOtQ8duhQGZfUbHYWJibKjRgo7cQEPPggrF9fYWD9o10lMpbIzLHMfFdDPzNzV2Zel5lDmfmGcx/cJEmSJKkLfRT4OGWRzGHKqk0XyWi1esVCCYyjEfHZiHjFwvgNlI0vv3Tuwsw8CXwNeF0Fca4O9TqMjjaPjY66gllqZWSk9Q2ZER+yaJeOJZglSZIkqZe4SEY6r28CtwM/BeygJJS/HhEvWfgZ4Nii1xxrOLdERNwZEYcj4vDx48fbH3G/q9VgagrGxmBwsLRTU65gllqZmWl9Q2bG+8XtspIlMiRJkiRJUo/JzN9t7EfEHwDfA24D/uAS3/Ne4F6AzZs354uNcdUZGIBNm+DAgZJUrtdLO+A6QmmJWg3274cnn4QbboCjR2HDBm/ItJH/8kiSJEmSpGXLzFngj4AbKZthAlyz6LJrGs6pEwYGyiP+ja2kpZ57Dk6ehB07YGiotCdPlnG1hSuY+0jZW+HizmV6o1j9LX/lStjVuaL9+StXduy9JUmSpG4UEUPAjwK/BxylJJLfBHyr4fzrgV+qKkZJ+oG5Odi2rXmTv23b4ItfrDKqvmKCuY+YLJaWil99pqNzIyLIXR17e0mSJKlyEfHrwEPAnwGbgLuAGvBbmZkR8QnglyPiu8AfAx8GZoHJaiKWpAbDw603+RseriaePuTzE5IkSZIk6YX8EDAFPAJ8HjgN/Hhm/unC+Y8CHwfuAQ4D1wFvzkx30JJUvXq99SZ/9Xo18fQhVzBLkiRJkqTzysy3X+B8ArsWDknqLrUafP7z8MQTz2/y95KXuMlfG7mCWZIkSZIkSVL/On26eZO/06erjqivmGCWJEmSJEmS1J/qdRgfL5v7zc2VdnzcEhltZIJZkiRJkiRJUn+q1Vpv8meJjLYxwSxJkiRJkiSpP83Ott7kb3a2mnj6kAlmSZIkSZIkSf3p8sthchLGxmBwsLSTk2VcbWGCWZIkSZIkqdfMz8PMTHMraannnoM9e2D3bjh1qrR79pRxtYUJZkmSJEmSpF4yPw/T07BlC6xdW9rpaZPMUivDw/DII81jjzxSxtUWJpglSZIkSZJ6Sb0O4+Nw8CDMzZV2fLyMS2p28iR86lNw/fUQUdpPfaqMqy1MMEuSJEmSJPWSWg0OHWoeO3SojEtqNjBQSmPcemtZ8X/rraU/YFq0XfwvKUmSJEmS1EvqdRgdbR4bHXUFs9TKc8/BxETziv+JCWswt5EJZkmSJEmSpF5Sq8HUFIyNweBgaaemXMEstTIy0nrF/8hINfH0IRPMkiRJkiRJvWRgADZtggMH4PTp0m7a5CP/UiszM61X/M/MVBNPH/JfHkl9LyI6dlx99dVV/3qSJEmSVqOBgbICs7GVtNTatTA52bzif3KyjKstBqsOQJI6KTMv6vqIuOjXSJIkSZKkLnXZZTA8DPv3w1VXwVNPlbHLLqs6sr7h7S1JkiRJkiRJ/enMmbLCf82a0l+zpvTPnKk2rj5iglmSJEmSJElSf5qfL/WWt24tZTG2bi39+fmqI+sbJpj72bkJ1NhKkiRJkiRJq8XcHIyPw8GD5eeDB0t/bq7qyPqGCeZ+NT8P09OwZUu5O7NlS+mbZJYkSZIkSdJqMTwMhw41jx06VMbVFiaY+1W93vruTL1edWSSJEmSJOnF8qllaXlmZ2F0tHlsdLSMqy1MMPerWq313ZlarZp4JEmSJElSe/jUsrR8AwOwdy+MjcHgYGn37i3jagv/S/arer313RlXMEuSJEmS1Nt8allavqEhuPJK2LMHTp0q7ZVXlnG1hQnmflWrwdRU892ZqSlXMEuSJEmS1Ot8allavsHBklDeuBEiSnvllWVcbWGCuV8NDMCmTXDgAJw+XdpNm1z+L0mSJElSr/OpZWn55ufhL/8Stm4tJWW2bi19S8q0jdnGfjYwACMjza0kSZIkSeptPrUsLV+9DvfeC7t3lxIZu3eXvjdk2sa14JIkSZIkSb2k8anlWq0kymo1F5ZJrVxxBWzbBnfcUUrJjI7CffeVcbWF//JIkiRJkiT1Gp9alpZndrYklxs3xbzjjjKutvBfH0mSJEmSJEn9aWSk9aaYIyPVxNOHTDBLkiRJkiRJ6k+zs603xXQFc9uYYJYkSZIkSZLUny6/HCYnmzfFnJws42oLN/mTJEmSJEmS1J/Oni01yvfsgRtugKNHS//s2aoj6xuuYJYkSZIkSZLUn86ehd/8TTh1qvRPnSp9E8xt4wpmSZIkSZIkSf2pVoPbboPbby+b+42Owr59ZVxt4QpmSZIkSZIkSf1pdrYklw8ehLm50t5+u5v8tZEJZkmSJEmSJEn9aWSkrFxudOhQGVdbmGCWJEmSJEnqNfPzMDPT3EpaanYWvvY1OHGi1F0+caL0XcHcNiaYJUmSJEmSesn8PExPw5YtsHZtaaenTTJLrQwNwctfDm95S5kvb3lL6Q8NVR1Z3zDBLEmSJEmS1EvqdRgfb64pOz5exiU1O3kS9uyB3bvh1KnS7tlTxtUWJpglSZIkSZJ6Sa3WuqZsrVZNPFI3Gx6Gbdtg586yannnztIfHq46sr5hglmSJEmSJKmX1OswOto8NjrqCuYuEBEfjIhvRcQzEXE8Ih6KiJsWXRMRsSsiHouIkxFxMCJeVVXMfW92Fu64o3nF/x13WIO5jUww9zML/kvqMcv5MNbiNWMR8cWI+H5EPBsRfxgRv7BSMUuSJEkrrlaDqSkYG4PBwdJOTbmCuTuMAZ8GXge8EZgDvhIRGxqueT/wPmAn8BpgGvhyRIysbKirxMhI6xX/I/7nbhcTzP3Kgv+SetMYF/4wttjrgCPA24CbgH8B3BsRE50NVZIkSarIwABs3AgPPginT5d248Yyrkpl5k9m5t7MfDgzjwA/D2wEboGyehl4N/CRzNyfmQ8DtwEjgN9hOmFmBu66C44cKSuYjxwp/ZmZqiPrG/7L069mZ1sX/Hf5v6QudqEPY+d5za9l5ocz8/cz83uZ+S+AzwO3rlDYkiRJ0sqan4fjx2Hr1rKobOvW0ndRWTcaoeTfTiz0bwCuBb507oLMPAl8jbJ4ZomIuDMiDkfE4ePHj3c43D5Uq8GOHc01mHfscMV/G5lg7lfDw62X/1vAXFJvWfxhbLmuvITXSJIkSb2hXm+9qMwazN3ok8C3gW8s9K9daI8tuu5Yw7kmmXlvZm7OzM0bN27sSJB9rV6HiYnm+TIx4XxpIxPM/Wp2tnXBf1cwS+otiz+MXVBE/Czwd4B7z3Peu/+SJEnqbbVa60VlrsjsKhHxMWAUuDUzz1Ydz6plDeaOM8HcrwYGYO/e5oL/e/daj0lSz7iUD2MRcQswCfzDzPyPra7x7r8kSZJ6njVlu15EfBwYB96Ymd9rOPX4QnvNopdc03BO7eR86bjBqgNQh6xbB1deCXv2wA03wNGjpb9uXdWRSdIFLXwYezvwE4s+jL3Qa0aB3wH+yUIdZkmSJKk/naspOzFRVmKOjsLkpCuYu0REfBL4Ocr3me8uOn2Ukkh+E/CtheuHgNcDv7SSca4aa9e2ni9r11YdWd9wOWu/WrMG1q8vu8hGlHb9+jIuSV1s4cPYuTv9iz+Mne81fxv4XWBXZn6ig+FJXS0idkVELjoebzgfC9c8FhEnI+JgRLyqypglSdIlsKZs14qIe4DtwARwIiKuXTiGATIzgU8AH4iIt0bETcA+YJbyNKba7fTpsgBz9244daq0e/aUcbWFCeZ+di7JPDBgcllST7jQh7GFa/5pRHy1oT9GSS7/S2Cy4TXWv9Bq9QhwXcNxc8O59wPvA3YCrwGmgS9HhAXoJEnqJdaU7WbvpGxW/lXg+w3HP2q45qPAx4F7gMOUz2xvzkxrNnTC8DBs2wY7d8LQUGm3bSvjagsTzP1sfr7Uk2lsJam7LefD2HXAX2vo3w5csXBN42u+1flwpa40l5mPNxzHoaxeBt4NfCQz92fmw8BtlDk3UV24vWnDhg1ExLIP4KKu37BhQ8W/oSSpq83Olsf8G42OlnFVKjPjPMeuhmsyM3dl5nWZOZSZb1j4bKZOmJ2FO+5oXvF/xx3OlzYywdyv5udhehq2bCk1ZbZsKX2TzJK62DI/jN2emS9f1G/1mpe3+J+QVoNXLJTAOBoRn42IVyyM3wBcC3zp3IWZeRL4GvC6CuLsaSdOnCAzO3acOHGi6l9RktTN1qyBvXthbAwGB0u7d69PLkutjIzA9dc3b/J3/fWu+G8jE8z9ql6H8fHmuzPj49ZjkiSpv32Tsqr/p4AdlITy1yPiJQs/Axxb9JpjDeeaRMSdEXE4Ig4fP368MxFLkqSLlwnr1pU6sqdOlXbdujIuqdmzz8LddzeXyLj77jKutjDB3K9qtdb1mNxRVpKkvpWZv5uZ/zoz/zAzvwL8LOXz3m2X+H73ZubmzNy8caNlzSVJ6hpXXAHvfW9JLkNp3/veMi6p2fw8bN/evAhz+3af8m8jE8z9ql5vXY/JFcySJK0amTkL/BFwI/D4wvA1iy67puGcJEnqBfU6PPYY3HxzKZFx882l73d+aanh4daLMN3kr21MMPerWg2mpprrMU1NuYJZkqRVJCKGgB+lbHx5lJJIftOi868Hvl5JgJIk6dLUavD5z8Ojj5YVmY8+Wvp+55eWmp2Fu+5qrsF8111u8tdGg1UHoA4ZGIBNm+DAgfIHpl4v7YD3FCRJ6lcR8evAQ8CfAZuAu4Aa8FuZmRHxCeCXI+K7wB8DHwZmgclqIpYkSZfs9GnYsaOsxBwdLYvKJC112WVlrkxMPD9fJifLuNrCbGM/GxgoO2I2tpIkqZ/9EDAFPAJ8HjgN/Hhm/unC+Y8CHwfuAQ4D1wFvzsyZCmKVJEmXql6H8fHmmrLj45bIkFo5c6Yklxvny8REGVdbuIJZ6kIRsQbYBWyjfPn/PvDbwK7MnKswNElSF8vMt1/gfFL+vuxaiXgkSVKH1Gqta8paIkNayhrMHeeSVqk7fQD4B8A/pNTO/MWF/gerDKqvnT0LTz/N/ELL2bNVRyRJktQXNmzYQEQs+wAu6voNGzZU/BtKFajXy2P+jUZHXcEstTIz07oG84wP8bWLCeZ+Nj9fJktjq17xOuChzHwoM/8kMw8AB4C/VXFcfaPxS8mnfuM3yOlp2LqVWLsWtm4lp6f51G/8xpIvO5IkSbo4J06cIDM7dpw4caLqX1FaebVaqbk8NgaDg6WdmnIFs9RKrVZqMO/cCUNDpd2xw/nSRiaY+9X8PExPw5YtsHZtaaenTTL3jkPAT0TEjwJExN8A3gj8TqVR9ZHGLyXvuu02YlE9ppiY4F233dZ0nSRJkiR1hYEBeOlL4cEHy2Z/Dz5Y+u69JC1Vr7euweyK/7bxX55+ZcH/XvfPgM8A/zUizgB/BPxWZn661cURcWdEHI6Iw8ePH1/JOPvDyEjrekwjI9XEI0mSJEkv5OxZePbZ50v7Le5Lep7f+TvOBHO/suB/r/s54B3ABPBjCz+/MyLuaHVxZt6bmZszc/PGjRtXMMw+MTPTun6Z9ZgkSZIkdaPTp8sCsltvLU8t33pr6Z8+XXVkUvfxO3/HmWDuVxb873X/J/DrmfnZzDySmZ8BPoab/HXG8DBMTjbXL5ucdEdZSZIkSd3pzJnWj/yfOVN1ZFL3GRyEz34WHn20zJdHHy39wcGqI+sbbUkwR8QHI+JbEfFMRByPiIci4qZF10RE7IqIxyLiZEQcjIhXteN/Xy1Y8L/XXQEsfrbpLN4U6ow1a2DTpub6ZZs2lXFJkiRJ6jY+8i8t39AQnDpVNvYbGirtqVPlZ7VFu5JVY8CngddRNiKbA74SERsarnk/8D5gJ/AaYBr4ckT4r18nDAyUBNmBAyVhduBA6Vvwv1c8BPzjiPiZiHh5RLwFeC/whYrj6l9r1sD69WWOrF9vclmSJElS95qZgbvugiNHyorMI0dK30f+paVmZ+H225tX/N9+exlXW7Ql25iZP5mZezPz4cw8Avw8sBG4BcrqZeDdwEcyc39mPgzcBoxQasyqEwYGyt3Lxla9YifwOcqNm+8A/xzYA3yoyqAkSZIkrT7LfGp5X0TkouMPqoq579VqZRXmzp1lFebOnaXvU8vSUiMjcP31zTdkrr/eFf9t1KmM48jCe59Y6N8AXAt86dwFmXkS+Bpl1bOkBpk5k5nvzsy/mpnrMvMVmfnLmXmq6tj61vx8udvf2EqSpL5lmT/pooxx4aeWAb4CXNdw/PQKxri61OutazC775K01MmTcPfdzTdk7r67jKstOpVg/iTwbeAbC/1rF9pji6471nCuSUTcGRGHI+Lw8ePHOxKkJAElmTw9DVu2lB2Yt2wpfZPMkiT1szEs8ycty4WeWm5wOjMfbzieXPloVwlrMEvLNzcH998Pu3eX2su7d5f+3FzVkfWNtieYI+JjwChwa2Yu3qRs2TLz3szcnJmbN27c2L4AJWmxeh3Gx5vv/o+Pe/dfkqQ+Zpk/6UVZ/NTyOaMRMR0RfxwReyJiUwWxrQ4zMzA62jw2OmoNZqmV4WHYtq15BfO2bWVcbdHWBHNEfBwYB96Ymd9rOPX4QnvNopdc03BOkqpRq7W++2/9MkmSVhPL/EnLt/ipZYB/C7wD+DuUlf//A/D/RsTaVm/gU8svUq0G+/fDo4+WRTKPPlr6foeRlpqdhTvuaF5UdscdbvLXRm1LMEfEJ3k+ufzdRaePUhLJb2q4fgh4PfD1dsUgSZekXm99998VzJIkrSaW+ZOW4XxPLWfmZzPzQGYeycyHgP8J+BHgZ1q9j08tv0inT5f6sTt2lBWZO3aU/unTVUcmdR9LynRcWxLMEXEPsJ3yqNiJiLh24RgGyMwEPgF8ICLeurB5xj5gFphsRwySdMlqNZiagrExGBws7dSUd/8lSVolLPMnLc8LPLW8RGY+Bvw34MaViG3VmZsrj/g3rsjcts2aslIrlpTpuME2vc87F9qvLhr/VWDXws8fBdYB9wBXA98E3pyZ/r8pqVoDA7BpExw4UJLK9XppBzq1D6okSeoWCwmztwM/8QJl/v6sYdwyf1qVFp5a/jnKXFn81HKr618K/BXg+52ObVVyRaa0fMPDcN99pSzGoUMluXzffdZgbqO2ZE8yM85z7Gq4JjNzV2Zel5lDmfmGhY0yJKl6AwPlw1hjK0mS+ppl/qTludBTyxExHBG/HhGvjYiXR8QY8BAwDXyhqrj7misypeWbnYUHHoDdu+HUqdI+8IA1mNuoXSuYJUmSJKlnLCTMfh7YykLCbOHUbGbOZmZGxCeAX46I7wJ/DHwYy/xpdbrQU8tngZspm/xdRVm1/HvA3/Wp5Q4ZHi5l/WZn4YYb4OjRMuaKTGmpWq3UKZ+YeH4F8+SkZTHbyASzJEmSpNXIMn/SMmVmXOD8SeAnVygcQdnQ78yZkjQ7lzC7//4ybpJZanbqFFxxBezfD1ddBU89BWvWlHHnS1v4DLgkSZKkVccyf5J62vw8vOMdzZv8veMdZVzSUidOwK23wtq1pT1xouqI+ooJZkmSJEmSpF4yPNx6kz9XY0pLzc/D9u3NN2S2b/eGTBuZYJYkSZIkSeols7Nw111w5EhJmB05UvpuWiYt5Q2ZjjPBLEmSJEmS1EsGB+Fd74KhodIfGir9QbfakpaYmSl1yhuNjpZxtYUJZkmSJEmSpF6SCfV62eRvaKi09XoZl9RseBjuuw/GxspNmLGx0ncFc9uYYJYkSZIkSeolZ8+23uTv7NmqI5O6z+wsPPAA7N4Np06V9oEHLCnTRiaYJUmSJEmSesnwMFx/fXMN5uuvd0Wm1MrwMGzbBjt3lhX/O3eWvvOlbUww97P5+VJPprGVJEmSJEm97eRJuPvu5oTZ3XeXcUnNXMHccSaY+9X8PExPw5YtsHZtaaenTTJLkiRJktTr5uZg+/bmEhnbt5efJTW77LJSp7zxhsyOHWVcbWGCuV/V6zA+3vzHZny8jEuSJEmSpN41MtK6RMbISNWRSd1naAi+/W34whfg9OnSfvvbZVxtMVh1AOqQWg0OHWoeO3SojEuSJOlFyV+5Enat7+z7S5J0PudKZGzfXr7rj47C3r1l3O/9UrNnn4VXvhLe8pbm+fLss9ZhbhMTzP2qXi8T5uDB58dGR8u4dzSlpebny/yo1Z5vB3zIQ5LUWvzqM2Rm594/gtzVsbeXJPW6uTm4//5SS/aVr4TvfKf0f/EXq45M6j5nzz5fUgaeLynz4IMVBtVfzJ70q1oNpqZgbAwGB0s7NeWdTKkVa5ZLkiRJ6iXDw/Ce98AP/zBElPY973E1ptTKyEjrp/xdgNk2Jpj71cAAbNoEBw6U+jIHDpS+KzKlpaxZLkmSJKmXnDkDs7OwdWtZJLN1a+mfOVN1ZFL3mZmBu+5qrll+111lXG1hiQxJsma5JElSx1izXOqA06dhYqL5kf+JifLIvxuXSc1qNXjXu+DJJ0t/aKj0/c7fNiaY+9W5R/7Hx58vYD415SpmqRVrlkuSJHWMNculDvCRf2n5Tp2CZ56BHTuaN/m7/HLLyrSJmcZ+5SP/0vJZs1ySJElSL5mZKUmyRqOjPvIvtTI///wmf+dyZNu3u+9SG7mCuV/5yL+0fI01y2u1ciOmVnO1vyRJkqTuVKvB/v3lkf8bboCjR2HDBr/zS60MD7fOkbl6uW3MnvSrc4/8Nzr3yL+kpQYGyuNkja0kSZIkdaNTp+DkyfLI/9BQaU+eLOOSmrniv+PMoPQrH/mXJEmSJKk/zc/Dtm3Nj/xv2+Yj/1Irw8Nw333NObL77nMFcxuZYO5XjY/8nz5dWjf4kyRJkiSp9/nIv7R89To88ADs3l1W+e/eXfo+5d82Zhv7mY/8S5IkSZLUf2ZnWz/yPztbTTxSNxsYgDvugJ07S0mZnTtL3zxZ2/hfUpIkSZIkqZcMDMDkZPMj/5OTJsykVtatgzVrYM+esoJ5z57SX7eu6sj6hv/ySJIkSZIk9ZKhIVi7tjlhtnZtGZfUbHYWxsfhxhvLDZkbbyx9V/y3jQlmSZIkSZKkXlKvw6c+VZLLUNpPfcqaslIrIyOta5aPjFQTTx8ywSxJkiRJktRLRkbgkUeaxx55xISZ1MrMTOua5TMz1cTTh0wwS5IkSZIk9ZJnn4W7727etOzuu8u4pGZr1sDevc01y/fuLeNqCxPMkiRJkiRJvWR+HrZvh4MHYW6utNu3l3FJza64Aj70Idi9u5ST2b279K+4ourI+oYJZkmSJEmSpF4yPNy6puzwcDXxSN1sZgYeewxuvrmsYL755tK3REbbmGCWJEmSJEnqJbOzrWvKzs5WE4/UZSLiB0cOD8N99zWXyLjvPnJ4uOk6XToTzJIkSZIkSb3ksstgcrI5YTY5WcYlkZk/OGJ2Fh54oLlExgMPELOzTdfp0g1WHYAkSZIkSZIuwtmzZXO//fvhqqvgqacgooxLalarwY4dMDFRSsmMjpYbMrVa1ZH1DRPMkiRJkiRJvSQCnnuu1JBdvx6efBJGRuDyy6uOTOo+g4OwcSM8+CA5MkLMzJTk8qBp0XaxRIYkSZIkSVIvWbcO3vve8rg/lPa97y3jkpYaHIT16xlYs6bclDG53FYmmCVJkiRJknrJ7Cw89hjcfHNJlN18c+m7yZ+kCphgliRJkiR1VER07Lj66qur/vWklTcwAPff37zJ3/33l3FJWmGuB5ckSZIkdUxmXtT1EXHRr5FWnXXrymrlPXvghhvg6FG47DJLZEiqhLe2JEmSJEmSekm9DocOwdVXlw3/rr669Ov1qiOTtAqZYJYkSZIkSeolg4Nwyy3wtrfB2rWlveUWNy6TVAkTzJIkSZIkSb3kzBmYmICDB2FurrQTE2VcklaYCWZJkiRJkqReMjJSSmI0OnSojEvSCjPBLEmSJEmS1EtmZmB0tHlsdLSMS9IKM8EsSZIkSZLUS2o1mJqCsbFSd3lsrPRrtaojk7QKWf1dkiRJkiSpl8zPl2Ty/v1w1VXw1FNw2WVlXJJWmCuYJUmSpEsQER07rr766qp/PUlSNztzBp54Am69FdauLe0TT7jJn6RKmGCWJEmSLlJmXtRxsa958sknK/4NJUld7exZ2L4dDh6EubnSbt9exiVphVkiQ5IkSZIkqctFxA9+nj97ljh0qPmCQ4fI4WEGGq47d5NTkjrJFcySJEmSJEldrvFJl5iZgdHR5gtGR4mZmSVP0EhSp5lgliRJkiRJ6iW1GkxOwtgYDA6WdnKyjEvSCrNERj+bn4d6vfyBOdcOeE9BkiRJkqSeNjgIGzfCgw+SIyNlRXOtVsYlaYWZbexX8/MwPQ1btpQdZbdsKf35+aojkyRJkiRJL9bgIKxfz8CaNbB+vcllSZUxwdyv6nUYH2/eUXZ8vIxLkiRJkiRJPW7Dhg1ExLIP4KKu37BhQ8W/YW/w9la/qtWgxY6y1mOSJEmSJElSPzhx4kRHN7Q8l5TWC3MFc7+q11vuKOsKZkmSJEmSJEntYoK5X9VqMDXVvKPs1JQrmCVJkiRJkiS1jSUy+tXAAGzaBAcOlKRyvV7aAe8pSJIkSZIkSWoPE8z9bGAARkbKz+daSZIkSZIkSWoTl7NKkiRJkiRJki6JCWZJkiRJkqQusWHDBiJi2QdwUddv2LCh4t9QUr+xRIYkSZIkSVKXOHHiBJnZsfc/l5SWpHYxwSxJkiRJkiSp5+SvXAm71nf2/XVBJpglSZIkSZIk9Zz41Wc6vuI/d3Xs7fuGNZglSZIkSZIkSZfEFcySJEmSJEldwkf+JfUaE8z9bH4e6nWo1Z5vB1y03isi4jrgI8BPAyPA94C/n5n/vtLAJEmSJEkd4yP/knqN2cZ+NT8P09OwZQusXVva6ekyrq4XEVcBvw8E8DPAK4GdwHSFYfW3uTl4+ukyR55+uvQlSZIkXZSIeGdEHI2IUxHxnyLi9VXHJKm/RUTHjquvvrrqX68nmGDuV7OzMD4OBw+WRNnBg6U/O1t1ZFqe9wPfz8x3ZOZ/zMyjmfnVzPxO1YH1pbk5OH4ctm4tN2S2bi19k8ySJEnSskXEzwGfBH4N+O+BrwO/GxEvqzSwHmTCbHXwhsyLl5kXdVzsa5588smKf8PeYIK5Xw0Pw6FDzWOHDpVx9YKtwDcj4l9FxHREfDsi3hURUXVgfaleh4mJ5hsyExNlXJIkSdJyvRfYl5l7MvM7mbkT+D7w9yuOq6eYMFsdvCGjfrLiCWbvzqyQ2VkYHW0eGx11BXPveAXwTkrd5Z+k/NH5CPAPWl0cEXdGxOGIOHz8+PGVi7JfjIy0viEzMlJNPFKXOd/qlwudk1Yj54u0fM6X/hIRlwN/E/jSolNfAl638hH1H+dM3/GGTAc5X1bWiiaYvTuzggYHYe9eGBsrP4+Nlf6g+zr2iAHg/8vMD2bmf87MvcBvcJ4Ec2bem5mbM3Pzxo0bVzTQvjAz0/qGzMxMNfFIXeZiV9F0clMaqds5X6Tlc770nZcCa4Bji8aPAdcuvthFMhfPOdM/LvaGjPPl4jlfVtZKr2D27sxKGRqC9ethzx44daq069eXcfWC7wP/ddHYdwBvxnRCrQaTk803ZCYny7gk9SGfKJMkVc1FMlrlLuqGjPNF3W7FlrM23J359UWnfFymEwYGSkJ5cBAi4JprSrJswLLbPeL3gR9ZNPbfAX9aQSz9b3AQNm6EBx8sZTFmZsp8ccW/pD7U8ETZO4FDC+3vRsTfyMw/qzQ4SVIv+0vgLHDNovFrgMdXPhxJ0kpZyWyjj8ustIGBkixrbNUrPg78eER8KCL+ekT8L8A/BO6pOK7+NThYbso03pyRpP7kE2WSpLbLzOeA/wS8adGpN1HKY0p6njdk1Fe6NuPo8n+tZpn5LWAr8HeBh4G7gbuAT1cYliSpx1nvT7o0lpWRlu1jwO0R8fci4pUR8UngeuBfVhyX1FW8IaN+s5JL9Lw7I12EzPw3wL+pOg5JUl95oSfK/sfFF2fmvcC9AJs3b3bnE61KlpWRli8z/1VEvAT4MHAdZbHMT2empf6kpT4GfCYi/iOlTOb/jjdk1KNWbAWzd2ckSZIk9SDLykgXITM/nZkvz8y1mfk3M/NrVcckdaPM/FfAuyk3ZL4NjOINGfWolS4y6t0ZSZKk6vhEmXQR3KhcktRJmflpLIWpPrCiNZi9OyNJklQdnyiTLpoblUuSJF3ASq9g9u6MJElStXyiTOoQ65ZLkqTVaMUTzJIkSaqOGzBJF8WyMpIkSRewoiUyJEmSVD03YJKWx7IykiRJF+YKZkmSJEk6P8vKSJIkvQATzJIkSZJ0HpaVkSRJemEmmCVJkiTpBbhRuSRJ0vlZg1mSJEmSJEmSdElMMEuSJEmSJEmSLokJZkmSJEmSJEnSJTHBLEmSJEmSJEm6JCaYJUldIyI+GBHfiohnIuJ4RDwUETct43U3R8S/j4iTEfEXEfFPIiJWImZJkiRJklYzE8ySpG4yBnwaeB3wRmAO+EpEbDjfCyLiSuDLwDHgNcAvAr8EvLfTwUqSJEmStNoNVh2AJEnnZOZPNvYj4ueBp4FbgIfO87L/FbgCuC0zTwIPR8SPAu+NiI9lZnYyZkmSJEmSVjNXMEuSutkI5W/ViRe45rXAf1hILp/z74DrgZcvvjgi7oyIwxFx+Pjx4+2MVZIkSZKkVccEsySpm30S+DbwjRe45lpKeYxGxxrONcnMezNzc2Zu3rhxY1uClCRJkiRptbJEhiSpK0XEx4BRYDQzz1YdjyRJkiRJWsoEsySp60TEx4G3Az+Rmd+7wOWPA9csGrum4ZwkSZIkSeoQS2RIkrpKRHwSGAfemJnfXcZLvgG8PiKGGsbeBDwG/En7I5QkSZIkSeeYYJYkdY2IuAfYDkwAJyLi2oVjuOGafxoRX2142STwLLAvIm6KiLcC/xj4WGbmSsYvSZIkSdJqY4JZktRN3gmMAF8Fvt9w/KOGa64D/tq5TmY+TVmxfD1wGLgH+OfAx1YmZEmSJEmSVq/ohcVdEXEc+NOq4+hhLwX+suogetRfzcyNVQdxMZwvL5rz5cXpqTnjfHnRnC8vjvNldXG+vDg9NV/AOfMiOV9eHOfL6uOcuXTOl9XH+fLitJwzPZFg1osTEYczc3PVcUi9wPkiLZ/zRVo+54u0fM4X6eI4Z6Tlc750hiUyJEmSJEmSJEmXxASzJEmSJEmSJOmSmGBeHe6tOgCphzhfpOVzvkjL53yRls/5Il0c54y0fM6XDrAGsyRJkiRJkiTpkriCWZIkSZIkSZJ0SUwwS5IkSZIkSZIuiQnmPhUR/1dETEfEw1XHIvUC54y0fM4XafmcL9LyOV+ki+OckZbP+dJZJpj71z7gp6oOQuoh+3DOSMu1D+eLtFz7cL5Iy7UP54t0MfbhnJGWax/Ol44xwdynMvNrwJNVxyH1CueMtHzOF2n5nC/S8jlfpIvjnJGWz/nSWSaYJUmSJEmSJEmXxASzJEmSJEmSJOmSmGCWJEmSJEmSJF0SE8ySJEmSJEmSpEtigrlPRcQU8A3gRyLiv0XEHVXHJHUz54y0fM4XafmcL9LyOV+ki+OckZbP+dJZkZlVxyBJkiRJkiRJ6kGuYJYkSZIkSZIkXRITzJIkSZIkSZKkS2KCWZIkSZIkSZJ0SUwwS5IkSZIkSZIuiQlmSZIkSZIkSdIlMcEsSZIkSZIkSbokJpglSZIkSZIkSZfk/wcvkUmVKlkuFAAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 1440x720 with 7 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Creating subplot of each column with its own scale\n",
    "red_circle = dict(markerfacecolor='red', marker='o', markeredgecolor='white')\n",
    "\n",
    "fig, axs = plt.subplots(1, len(df.columns), figsize=(20,10))\n",
    "\n",
    "for i, ax in enumerate(axs.flat):\n",
    "    ax.boxplot(df.iloc[:,i], flierprops=red_circle)\n",
    "    ax.set_title(df.columns[i], fontsize=20, fontweight='bold')\n",
    "    ax.tick_params(axis='y', labelsize=14)\n",
    "    \n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "And when we run the cell, we have a much nicer looking plot, that we can read. Each subplot has its own y-axis scale. We can see that CALI, GR and NEU all have a large number of outliers. The final two subplots RMED and RDEP should be scaled logarithmically. \n",
    "\n",
    "To catch these, we can add a simple if statement to check if the column names are equal to RDEP and RMED, and then call upon `ax.semilogy()`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2160x720 with 7 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "red_circle = dict(markerfacecolor='red', marker='o', markeredgecolor='white')\n",
    "\n",
    "fig, axs = plt.subplots(1, len(df.columns), figsize=(30,10))\n",
    "\n",
    "for i, ax in enumerate(axs.flat):\n",
    "    ax.boxplot(df.iloc[:,i], flierprops=red_circle)\n",
    "    df.iloc[:,i]\n",
    "    ax.set_title(df.columns[i], fontsize=20, fontweight='bold')\n",
    "    ax.tick_params(axis='y', labelsize=14)\n",
    "    \n",
    "    #Checking if column names are equal to columns we expect to be logarithmic\n",
    "    if df.columns[i] == 'RDEP' or df.columns[i] == 'RMED':\n",
    "        ax.semilogy()\n",
    "    \n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Summary\n",
    "\n",
    "In this tutorial we have seen how to create basic boxplots of well log data using matplotlib and pandas, as well as creating single figures with multiple boxplots that have different y-axes / data ranges. Boxplots are very useful data visualisation tools that allow us to understand the range and distribution of the data, as well as identify anomolous data points, also known as outliers.\n",
    "\n",
    "This is one of many methods that can be used in the Exploratory Data Phase of a project.\n",
    "\n",
    "\n",
    "---\n",
    "\n",
    "*Thanks for reading!*\n",
    "\n",
    "*If you have found this article useful, feel free to check out my other articles looking at various aspects of Python and well log data. You can also find my code used in this article and others at GitHub.*\n",
    "\n",
    "If you want to get in touch you can find me on LinkedIn or at my website.\n",
    "\n",
    "Interested in learning more about python and well log data or petrophysics? Follow me on [Medium](https://andymcdonaldgeo.medium.com/) or on [YouTube](https://www.youtube.com/channel/UCn1O_4_ApzbYwrsUdRoMmOg)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}