{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Automated ARIMA forecasting with Python\n",
    "\n",
    "Feng Li\n",
    "\n",
    "School of Statistics and Mathematics\n",
    "\n",
    "Central University of Finance and Economics\n",
    "\n",
    "[feng.li@cufe.edu.cn](mailto:feng.li@cufe.edu.cn)\n",
    "\n",
    "[https://feng.li/python](https://feng.li/python)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# ARIMA: Autoregressive Integrated Moving Average\n",
    "\n",
    "This notebook provides an example of how to train an ARIMA model to generate point forecasts of product sales in retail. We will train an ARIMA based model on the Orange Juice dataset.\n",
    "\n",
    "An ARIMA, which stands for AutoRegressive Integrated Moving Average, model can be created using an `ARIMA(p,d,q)` model within `statsmodels` library. In this notebook, we will be using an alternative library `pmdarima`, which allows us to automatically search for optimal ARIMA parameters, within a specified range. More specifically, we will be using `auto_arima` function within `pmdarima` to automatically discover the optimal parameters for an ARIMA model. This function wraps `ARIMA` and `SARIMAX` models of `statsmodels` library, that correspond to non-seasonal and seasonal model space, respectively."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "- In an ARIMA model there are 3 parameters that are used to help model the major aspects of a times series: seasonality, trend, and noise. These parameters are:\n",
    "    - **p** is the parameter associated with the auto-regressive aspect of the model, which incorporates past values.\n",
    "    - **d** is the parameter associated with the integrated part of the model, which effects the amount of differencing to apply to a time series.\n",
    "    - **q** is the parameter associated with the moving average part of the model.,\n",
    "\n",
    "- If our data has a seasonal component, we use a seasonal ARIMA model or `ARIMA(p,d,q)(P,D,Q)m`. In that case, we have an additional set of parameters: `P`, `D`, and `Q` which describe the autoregressive, differencing, and moving average terms for the seasonal part of the ARIMA model, and `m` refers to the number of periods in each season.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Looking in indexes: https://mirrors.163.com/pypi/simple/\n",
      "Requirement already satisfied: pmdarima in /home/fli/.local/lib/python3.9/site-packages (1.8.3)\n",
      "Requirement already satisfied: pandas>=0.19 in /home/fli/.local/lib/python3.9/site-packages (from pmdarima) (1.3.4)\n",
      "Requirement already satisfied: scipy>=1.3.2 in /usr/lib/python3/dist-packages (from pmdarima) (1.7.1)\n",
      "Requirement already satisfied: urllib3 in /usr/lib/python3/dist-packages (from pmdarima) (1.26.5)\n",
      "Requirement already satisfied: joblib>=0.11 in /usr/lib/python3/dist-packages (from pmdarima) (0.17.0)\n",
      "Requirement already satisfied: numpy>=1.19.3 in /usr/lib/python3/dist-packages (from pmdarima) (1.19.5)\n",
      "Requirement already satisfied: Cython!=0.29.18,>=0.29 in /usr/lib/python3/dist-packages (from pmdarima) (0.29.24)\n",
      "Requirement already satisfied: statsmodels!=0.12.0,>=0.11 in /usr/lib/python3/dist-packages (from pmdarima) (0.12.2)\n",
      "Requirement already satisfied: setuptools!=50.0.0,>=38.6.0 in /usr/lib/python3/dist-packages (from pmdarima) (58.2.0)\n",
      "Requirement already satisfied: scikit-learn>=0.22 in /usr/lib/python3/dist-packages (from pmdarima) (0.23.2)\n",
      "Requirement already satisfied: python-dateutil>=2.7.3 in /usr/lib/python3/dist-packages (from pandas>=0.19->pmdarima) (2.8.1)\n",
      "Requirement already satisfied: pytz>=2017.3 in /usr/lib/python3/dist-packages (from pandas>=0.19->pmdarima) (2021.3)\n"
     ]
    }
   ],
   "source": [
    "! pip3 install pmdarima --user"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Global Settings and Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "System version: 3.9.7 (default, Sep 24 2021, 09:43:00) \n",
      "[GCC 10.3.0]\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import sys\n",
    "import math\n",
    "import warnings\n",
    "import itertools\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "# import scrapbook as sb\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from pmdarima.arima import auto_arima\n",
    "\n",
    "pd.options.display.float_format = \"{:,.2f}\".format\n",
    "np.set_printoptions(precision=2)\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "\n",
    "print(\"System version: {}\".format(sys.version))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Parameters\n",
    "\n",
    "Next, we define global settings related to the model. We will use historical weekly sales data only, without any covariate features to train the ARIMA model. The model parameter ranges are provided in params. These are later used by the `auto_arima()` function to search the space for the optimal set of parameters. To increase the space of models to search over, increase the `max_p` and `max_q` parameters.\n",
    "\n",
    "> NOTE: Our data does not show a strong seasonal component (as demonstrated in data exploration example notebook), so we will not be searching over the seasonal ARIMA models. To search over the seasonal models, set `seasonal` to `True` and include `start_P`, `start_Q`, `max_P`, and `max_Q` parameters in the auto_arima() function."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": [
     "parameters"
    ]
   },
   "outputs": [],
   "source": [
    "# Forecasting settings\n",
    "N_SPLITS = 1\n",
    "HORIZON = 2\n",
    "GAP = 2\n",
    "FIRST_WEEK = 40\n",
    "LAST_WEEK = 138\n",
    "\n",
    "# Parameters of ARIMA model\n",
    "params = {\n",
    "    \"seasonal\": False,\n",
    "    \"start_p\": 0,\n",
    "    \"start_q\": 0,\n",
    "    \"max_p\": 5,\n",
    "    \"max_q\": 5,\n",
    "    \"m\": 52,\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Data Preparation\n",
    "\n",
    "\n",
    "- We store the training data and test data using dataframes. \n",
    "\n",
    "    - `train_df` contains the historical sales up to week 135 (the time we make forecasts) \n",
    "    - `aux_df` containing price/promotion information up until week 138. Here we assume that future price and promotion information up to a certain number of weeks ahead is predetermined and known. \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "    \n",
    "- In our example, we will be using historical sales only, and will not be using the `aux_df` data. The test data is stored in `test_df` which contains the sales of each product in week 137 and 138. \n",
    "\n",
    "- Assuming the current week is week 135, our goal is to forecast the sales in week 137 and 138 using the training data. There is a one-week gap between the current week and the first target week of forecasting as we want to leave time for planning inventory in practice."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [],
   "source": [
    "train_df = pd.read_csv(\"data/OrangeJuice_train.csv\")\n",
    "test_df = pd.read_csv(\"data/OrangeJuice_test.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Process training data\n",
    "\n",
    "Our time series data is not complete, since we have missing sales for some stores/products and weeks. We will fill in those missing values by propagating the last valid observation forward to next available value. We will define functions for data frame processing, then use these functions within a loop that loops over each forecasting rounds.\n",
    "\n",
    "Note that our time series are grouped by `store` and `brand`, while `week` represents a time step, and `logmove` represents the value to predict.\n",
    "\n",
    "Let's first process the training data. Note that the training data runs from `FIRST_WEEK` to `LAST_WEEK - HORIZON - GAP + 1` as defined in Parameters section above."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "lines_to_next_cell": 2,
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "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>store</th>\n",
       "      <th>brand</th>\n",
       "      <th>week</th>\n",
       "      <th>logmove</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>40</td>\n",
       "      <td>9.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>46</td>\n",
       "      <td>8.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>47</td>\n",
       "      <td>8.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>48</td>\n",
       "      <td>8.99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>50</td>\n",
       "      <td>9.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84178</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>131</td>\n",
       "      <td>9.63</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84179</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>132</td>\n",
       "      <td>9.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84180</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>133</td>\n",
       "      <td>9.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84181</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>134</td>\n",
       "      <td>8.91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84182</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>135</td>\n",
       "      <td>9.90</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>84183 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       store  brand  week  logmove\n",
       "0          2      1    40     9.02\n",
       "1          2      1    46     8.72\n",
       "2          2      1    47     8.25\n",
       "3          2      1    48     8.99\n",
       "4          2      1    50     9.09\n",
       "...      ...    ...   ...      ...\n",
       "84178    137     11   131     9.63\n",
       "84179    137     11   132     9.70\n",
       "84180    137     11   133     9.00\n",
       "84181    137     11   134     8.91\n",
       "84182    137     11   135     9.90\n",
       "\n",
       "[84183 rows x 4 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Select only required columns\n",
    "train_df = train_df[[\"store\", \"brand\", \"week\", \"logmove\"]]\n",
    "train_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "Notice that the unit sales of the products are given in logarithmic scale. We will use this quantity for training the forecasting model, as it smooths out the time series, and results in better forecasting performance. We will convert the `logmove` to a unit scale for evaluation, for consistency across our examples."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "lines_to_next_cell": 2,
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [],
   "source": [
    "def df_from_cartesian_product(dict_in):\n",
    "    \"\"\"Generate a Pandas dataframe from Cartesian product of lists.\"\"\"\n",
    "    from itertools import product\n",
    "\n",
    "    cart = list(product(*dict_in.values()))\n",
    "    df = pd.DataFrame(cart, columns=dict_in.keys())\n",
    "    return df\n",
    "\n",
    "def complete_and_fill_df(df, stores, brands, weeks):\n",
    "    \"\"\"Completes missing rows in Orange Juice datasets and fills in the missing values.\n",
    "    \"\"\"\n",
    "    d = {\"store\": stores, \"brand\": brands, \"week\": weeks}\n",
    "    data_grid = df_from_cartesian_product(d)\n",
    "    # Complete all rows\n",
    "    df_filled = pd.merge(data_grid, df, how=\"left\", on=[\"store\", \"brand\", \"week\"])\n",
    "    # Fill in missing values\n",
    "    df_filled = df_filled.groupby([\"store\", \"brand\"]).apply(lambda x: x.fillna(method=\"ffill\").fillna(method=\"bfill\"))\n",
    "    return df_filled"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "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>store</th>\n",
       "      <th>brand</th>\n",
       "      <th>week</th>\n",
       "      <th>logmove</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>40</td>\n",
       "      <td>9.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>41</td>\n",
       "      <td>9.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>42</td>\n",
       "      <td>9.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>43</td>\n",
       "      <td>9.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>44</td>\n",
       "      <td>9.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>87643</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>131</td>\n",
       "      <td>9.63</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>87644</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>132</td>\n",
       "      <td>9.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>87645</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>133</td>\n",
       "      <td>9.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>87646</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>134</td>\n",
       "      <td>8.91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>87647</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>135</td>\n",
       "      <td>9.90</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>87648 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       store  brand  week  logmove\n",
       "0          2      1    40     9.02\n",
       "1          2      1    41     9.02\n",
       "2          2      1    42     9.02\n",
       "3          2      1    43     9.02\n",
       "4          2      1    44     9.02\n",
       "...      ...    ...   ...      ...\n",
       "87643    137     11   131     9.63\n",
       "87644    137     11   132     9.70\n",
       "87645    137     11   133     9.00\n",
       "87646    137     11   134     8.91\n",
       "87647    137     11   135     9.90\n",
       "\n",
       "[87648 rows x 4 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create a dataframe to hold all necessary data\n",
    "store_list = train_df[\"store\"].unique()\n",
    "brand_list = train_df[\"brand\"].unique()\n",
    "train_week_list = range(FIRST_WEEK, LAST_WEEK - (HORIZON - 1) - (GAP - 1))\n",
    "\n",
    "train_filled = complete_and_fill_df(train_df, stores=store_list, brands=brand_list, weeks=train_week_list)\n",
    "train_filled"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Process test data\n",
    "\n",
    "Let's now process the test data. Note that the test data runs from `LAST_WEEK - HORIZON + 1` to `LAST_WEEK`. Note that, in addition to filling out missing values, we also convert unit sales from logarithmic scale to the counts. We will do model training on the log scale, due to improved performance, however, we will transfrom the test data back into the unit scale (counts) by applying `math.exp()`, so that we can evaluate the performance on the unit scale."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "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>store</th>\n",
       "      <th>brand</th>\n",
       "      <th>week</th>\n",
       "      <th>actuals</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>137</td>\n",
       "      <td>9792</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>138</td>\n",
       "      <td>16960</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>137</td>\n",
       "      <td>6240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>138</td>\n",
       "      <td>14784</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>137</td>\n",
       "      <td>1920</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1821</th>\n",
       "      <td>137</td>\n",
       "      <td>9</td>\n",
       "      <td>138</td>\n",
       "      <td>384</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1822</th>\n",
       "      <td>137</td>\n",
       "      <td>10</td>\n",
       "      <td>137</td>\n",
       "      <td>40384</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1823</th>\n",
       "      <td>137</td>\n",
       "      <td>10</td>\n",
       "      <td>138</td>\n",
       "      <td>7232</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1824</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>137</td>\n",
       "      <td>7424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1825</th>\n",
       "      <td>137</td>\n",
       "      <td>11</td>\n",
       "      <td>138</td>\n",
       "      <td>6144</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1826 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      store  brand  week  actuals\n",
       "0         2      1   137     9792\n",
       "1         2      1   138    16960\n",
       "2         2      2   137     6240\n",
       "3         2      2   138    14784\n",
       "4         2      3   137     1920\n",
       "...     ...    ...   ...      ...\n",
       "1821    137      9   138      384\n",
       "1822    137     10   137    40384\n",
       "1823    137     10   138     7232\n",
       "1824    137     11   137     7424\n",
       "1825    137     11   138     6144\n",
       "\n",
       "[1826 rows x 4 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Evaluate prediction accuracy\n",
    "test_df[\"actuals\"] = test_df.logmove.apply(lambda x: round(math.exp(x)))\n",
    "test_df = test_df[[\"store\", \"brand\", \"week\", \"actuals\"]]\n",
    "\n",
    "test_week_list = range(LAST_WEEK - HORIZON + 1, LAST_WEEK + 1)\n",
    "test_filled = complete_and_fill_df(test_df, stores=store_list, brands=brand_list, weeks=test_week_list)\n",
    "\n",
    "test_filled"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Model training\n",
    "\n",
    "We next train an ARIMA model for a single time series, for demonstration. We select `STORE=2` and `BRAND=6` and filter our data based on these values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "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>store</th>\n",
       "      <th>brand</th>\n",
       "      <th>week</th>\n",
       "      <th>logmove</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>566</th>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>126</td>\n",
       "      <td>8.52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>567</th>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>127</td>\n",
       "      <td>8.03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>568</th>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>128</td>\n",
       "      <td>8.15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>569</th>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>129</td>\n",
       "      <td>8.03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>570</th>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>130</td>\n",
       "      <td>7.74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>571</th>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>131</td>\n",
       "      <td>7.45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>572</th>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>132</td>\n",
       "      <td>7.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>573</th>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>133</td>\n",
       "      <td>7.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>574</th>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>134</td>\n",
       "      <td>7.27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>575</th>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>135</td>\n",
       "      <td>6.96</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     store  brand  week  logmove\n",
       "566      2      6   126     8.52\n",
       "567      2      6   127     8.03\n",
       "568      2      6   128     8.15\n",
       "569      2      6   129     8.03\n",
       "570      2      6   130     7.74\n",
       "571      2      6   131     7.45\n",
       "572      2      6   132     7.70\n",
       "573      2      6   133     7.93\n",
       "574      2      6   134     7.27\n",
       "575      2      6   135     6.96"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "STORE = 2\n",
    "BRAND = 6\n",
    "\n",
    "train_ts = train_filled.loc[(train_filled.store == STORE) & (train_filled.brand == BRAND)]\n",
    "train_ts.tail(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ARIMA(order=(1, 0, 0), scoring_args={}, suppress_warnings=True)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_ts = np.array(train_ts.logmove)\n",
    "\n",
    "model = auto_arima(\n",
    "    train_ts,\n",
    "    seasonal=params[\"seasonal\"],\n",
    "    start_p=params[\"start_p\"],\n",
    "    start_q=params[\"start_q\"],\n",
    "    max_p=params[\"max_p\"],\n",
    "    max_q=params[\"max_q\"],\n",
    "    stepwise=True,\n",
    ")\n",
    "\n",
    "model.fit(train_ts)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "Let's look at the model summary. As seen from the summary, the selected ARIMA model is `(p=1, d=0, q=0)`. This is a relatively simple model, also referred to as first-order auto-regressive model. It indicates that the time series is stationary and can be predicted as a multiple of its own previous value, plus a constant.  This is an `ARIMA(1,0,0)+constant` model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>SARIMAX Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>           <td>y</td>        <th>  No. Observations:  </th>   <td>96</td>   \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>           <td>SARIMAX(1, 0, 0)</td> <th>  Log Likelihood     </th> <td>-18.335</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>            <td>Fri, 12 Nov 2021</td> <th>  AIC                </th> <td>42.670</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                <td>12:27:01</td>     <th>  BIC                </th> <td>50.363</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Sample:</th>                  <td>0</td>        <th>  HQIC               </th> <td>45.779</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th></th>                       <td> - 96</td>      <th>                     </th>    <td> </td>   \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>        <td>opg</td>       <th>                     </th>    <td> </td>   \n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "      <td></td>         <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>intercept</th> <td>    3.5490</td> <td>    0.686</td> <td>    5.172</td> <td> 0.000</td> <td>    2.204</td> <td>    4.894</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>ar.L1</th>     <td>    0.5579</td> <td>    0.086</td> <td>    6.468</td> <td> 0.000</td> <td>    0.389</td> <td>    0.727</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>sigma2</th>    <td>    0.0855</td> <td>    0.012</td> <td>    6.973</td> <td> 0.000</td> <td>    0.061</td> <td>    0.109</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Ljung-Box (L1) (Q):</th>     <td>0.21</td> <th>  Jarque-Bera (JB):  </th> <td>1.39</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Q):</th>                <td>0.64</td> <th>  Prob(JB):          </th> <td>0.50</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Heteroskedasticity (H):</th> <td>1.48</td> <th>  Skew:              </th> <td>-0.28</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(H) (two-sided):</th>    <td>0.27</td> <th>  Kurtosis:          </th> <td>3.15</td> \n",
       "</tr>\n",
       "</table><br/><br/>Warnings:<br/>[1] Covariance matrix calculated using the outer product of gradients (complex-step)."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                               SARIMAX Results                                \n",
       "==============================================================================\n",
       "Dep. Variable:                      y   No. Observations:                   96\n",
       "Model:               SARIMAX(1, 0, 0)   Log Likelihood                 -18.335\n",
       "Date:                Fri, 12 Nov 2021   AIC                             42.670\n",
       "Time:                        12:27:01   BIC                             50.363\n",
       "Sample:                             0   HQIC                            45.779\n",
       "                                 - 96                                         \n",
       "Covariance Type:                  opg                                         \n",
       "==============================================================================\n",
       "                 coef    std err          z      P>|z|      [0.025      0.975]\n",
       "------------------------------------------------------------------------------\n",
       "intercept      3.5490      0.686      5.172      0.000       2.204       4.894\n",
       "ar.L1          0.5579      0.086      6.468      0.000       0.389       0.727\n",
       "sigma2         0.0855      0.012      6.973      0.000       0.061       0.109\n",
       "===================================================================================\n",
       "Ljung-Box (L1) (Q):                   0.21   Jarque-Bera (JB):                 1.39\n",
       "Prob(Q):                              0.64   Prob(JB):                         0.50\n",
       "Heteroskedasticity (H):               1.48   Skew:                            -0.28\n",
       "Prob(H) (two-sided):                  0.27   Kurtosis:                         3.15\n",
       "===================================================================================\n",
       "\n",
       "Warnings:\n",
       "[1] Covariance matrix calculated using the outer product of gradients (complex-step).\n",
       "\"\"\""
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "The model summary contains a lot of information. The coefficient table in the middle provides the estimates for the weights of the respective p and q terms. Notice that the coefficient of the AR1 term has a low p-value (`P>|z|` column), indicating that this term is significant. It also shows that the constant term is significant with a low p-value.\n",
    "\n",
    "Next, let's also examine the diagnostics plot for the selected model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x576 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "model.plot_diagnostics(figsize=(10, 8))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "In the top left, the residual errors fluctuate around a mean of zero and have a uniform variance, which may indicate that there is no bias in prediction. The density plot in the top right suggests normal distribution with mean zero.\n",
    "\n",
    "The Correlogram, or the ACF plot, in the lower right shows the residual errors are not autocorrelated. Any detected autocorrelation in this plot suggests that there may be some pattern in the residual errors which are not explained in the model, so adding additional predictors to the model may be beneficial.\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "In the bottom left, we do not see significant deviation of residuals from the red line, which indicates that the model is a good fit.\n",
    "\n",
    "Overall, based on the above, it seems to that the model is a good fit for this data.\n",
    "\n",
    "\n",
    "It is worth noting that selecting the best parameters for an ARIMA model can be challenging - somewhat subjective and time intesive, and should be done following a thorough data examination (seasonality, trend, bias). We use an `auto_arima()` function to search a provided space of parameters for the best model, mostly to demonstrate its usage and functionality.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Model evaluation\n",
    "\n",
    "Let's now take a look at the predictions. Since auto_arima model makes consecutive forecasts from the last time point, we want to forecast the next `n_periods = GAP + HORIZON - 1` points, so that we can account for the GAP, as described in the data setup. As mentioned above, we are also transforming our predictions from logarithmic scale to counts, for calculating evaluation metric."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "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>predictions</th>\n",
       "      <th>store</th>\n",
       "      <th>brand</th>\n",
       "      <th>week</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2,199.00</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>137</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2,546.00</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>138</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   predictions  store  brand  week\n",
       "0     2,199.00      2      6   137\n",
       "1     2,546.00      2      6   138"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "preds = model.predict(n_periods=GAP + HORIZON - 1)\n",
    "\n",
    "predictions = np.round(np.exp(preds[-HORIZON:]))\n",
    "pred_df = pd.DataFrame({\"predictions\": predictions, \"store\": STORE, \"brand\": BRAND, \"week\": test_week_list})\n",
    "\n",
    "pred_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "To evaluate the model, we will use *mean absolute percentage error* or **MAPE**."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "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>predictions</th>\n",
       "      <th>store</th>\n",
       "      <th>brand</th>\n",
       "      <th>week</th>\n",
       "      <th>actuals</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2,199.00</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>137</td>\n",
       "      <td>5760</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2,546.00</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>138</td>\n",
       "      <td>1440</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   predictions  store  brand  week  actuals\n",
       "0     2,199.00      2      6   137     5760\n",
       "1     2,546.00      2      6   138     1440"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Combine actual units and predictions\n",
    "test_ts = test_filled.loc[(test_filled.store == STORE) & (test_filled.brand == BRAND)]\n",
    "\n",
    "combined = pd.merge(pred_df, test_ts, on=[\"store\", \"brand\", \"week\"], how=\"left\")\n",
    "combined"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [],
   "source": [
    "def MAPE(predictions, actuals):\n",
    "    \"\"\"\n",
    "    Implements Mean Absolute Percent Error (MAPE).\n",
    "\n",
    "    Args:\n",
    "        predictions (array like): a vector of predicted values.\n",
    "        actuals (array like): a vector of actual values.\n",
    "\n",
    "    Returns:\n",
    "        numpy.float: MAPE value\n",
    "    \"\"\"\n",
    "    if not (isinstance(actuals, pd.Series) and isinstance(predictions, pd.Series)):\n",
    "        predictions, actuals = pd.Series(predictions), pd.Series(actuals)\n",
    "\n",
    "    return ((predictions - actuals).abs() / actuals).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAPE of the forecasts is 69.31423611111111%\n"
     ]
    }
   ],
   "source": [
    "metric_value = MAPE(combined.predictions, combined.actuals) * 100\n",
    "\n",
    "print(f\"MAPE of the forecasts is {metric_value}%\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Model training for all stores and brands\n",
    "\n",
    "Now let's run model training across all the stores and brands. We will re-run the same code to automatically search for the best parameters, simply wrapped in a for loop iterating over stores and brands."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [],
   "source": [
    "def train_store_brand(data, store, brand):\n",
    "    train_ts = data.loc[(data.store == store) & (data.brand == brand)]\n",
    "    train_ts = np.array(train_ts[\"logmove\"])\n",
    "\n",
    "    model = auto_arima(\n",
    "        train_ts,\n",
    "        seasonal=params[\"seasonal\"],\n",
    "        start_p=params[\"start_p\"],\n",
    "        start_q=params[\"start_q\"],\n",
    "        max_p=params[\"max_p\"],\n",
    "        max_q=params[\"max_q\"],\n",
    "        stepwise=True,\n",
    "        error_action=\"ignore\",\n",
    "    )\n",
    "\n",
    "    model.fit(train_ts)\n",
    "    preds = model.predict(n_periods=GAP + HORIZON - 1)\n",
    "    predictions = np.round(np.exp(preds[-HORIZON:]))\n",
    "\n",
    "    pred_df = pd.DataFrame({\"predictions\": predictions, \"store\": store, \"brand\": brand, \"week\": test_week_list})\n",
    "    test_ts = test_filled.loc[(test_filled.store == store) & (test_filled.brand == brand)]\n",
    "\n",
    "    return pd.merge(pred_df, test_ts, on=[\"store\", \"brand\", \"week\"], how=\"left\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training ARIMA model...\n",
      "12:29:25.881911 - Forecasting for store: 2\n",
      "12:29:44.320624 - Forecasting for store: 5\n",
      "12:29:55.796922 - Forecasting for store: 8\n",
      "CPU times: user 2min 31s, sys: 6.6 s, total: 2min 38s\n",
      "Wall time: 40.4 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "    \n",
    "from datetime import datetime\n",
    "    \n",
    "# Just train a few stores to save time\n",
    "store_list = store_list[0:3]\n",
    "\n",
    "result_df = pd.DataFrame(None, columns=[\"predictions\", \"store\", \"brand\", \"week\", \"actuals\"])\n",
    "\n",
    "print(\"Training ARIMA model...\")\n",
    "for store, brand in itertools.product(store_list, brand_list):\n",
    "    if brand == 1:\n",
    "        print(f\"{datetime.now().time()} - Forecasting for store: {store}\")\n",
    "\n",
    "    combined_df = train_store_brand(train_filled, store, brand)\n",
    "    result_df = result_df.append(combined_df, ignore_index=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "Let's compute `MAPE` for all predictions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "69.31423611111111"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "metric_value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAPE of the forecasts is 68.78729124622176 %\n"
     ]
    }
   ],
   "source": [
    "metric_value = MAPE(result_df.predictions, result_df.actuals) * 100\n",
    "# sb.glue(\"MAPE\", metric_value)\n",
    "\n",
    "print(f\"MAPE of the forecasts is {metric_value} %\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "When building a model with `auto_arima` for a large number of time series, it is often difficult to examine each model individually (in a similar way we did for the single time series above). As `auto_arima` searches a restricted space of the models, defined by the range of `p` and `q` parameters, we often might not find an optimal model for each time series.\n",
    "\n",
    "Let's plot a few examples of forecasted results."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABDAAAARRCAYAAADQPHLpAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOzdd3xc1Zn/8c+jLlmSJVmScS/YuFCMbFNMC2DApIFDSCAVkvxCetlsSHB2s5BCICEbUnZTWCCQhAQIAUIK3TgUm2JjwBhsbINtyTa2uiWrS+f3x70jj+VRn3JH+r5fr3mNdOaWMzN35p459znPMeccIiIiIiIiIiJBlpLoCoiIiIiIiIiI9EcdGCIiIiIiIiISeOrAEBEREREREZHAUweGiIiIiIiIiASeOjBEREREREREJPDUgSEiIiIiIiIigacODAkEM3NmtqpH2TV++Zkx2ud0f/u3xWL7o4GZbTez7Qna92Ize9TMqvz38aVE1COazOw8M1ttZrX+c7o/0XUaTWL9nTOA/V/u7//yROw/mQTxtTKzs/w6fSDRdRkMM7vNr/f0sLKYnx/NbJWZuVhtX4LHzM70j6trEl2X0WCkv95mNsnMms3se4mui8SXOjBGEf9LLPzW6f/4W2lmH0l0/WIhUseIxFY8fliYWT7wD+BE4E7gO8CvY7W/ePB/PPwVmAH8Fu853ZnIOkl0jfTG5GhmZinAjcDLwD0Jrk4gROoYEQkaHacDY2afMrPfmNlzZtbkv2bf72P5Y83sZjNbb2aVZtZqZuVm9piZXWRmFmGd0EWE3m7nhy/vnNuF1/b7dzObEv1nLUGVlugKSEJ8x79PB+YAy4GzzGyRc+5rCavV4f4H7wfczhhtfxcwD6iP0fYldk4ESoH/cM79INGViZJzgCzg351zf0x0ZSQh7gOeBfYkuiJJIGiv1aXAAuAjzrmREFUQj/Pjx4GcGG5fRKLnv4GxQC2wGziyn+UX4f2+eBZYjfddcgTwXuAvwB+Aj/Wy7u3A9gjlWyOU3QB8Cfg2cEU/dZIRQh0Yo5Bz7prw/81sKfAo8FUz+7lzbnsi6tWTc64KqIrh9tuBTbHavsTURP9+d0JrEV0j8TnJIDjn6lGH6oAE8LX6ArAfr2Ml6cXj/Oici9XFCRGJvkuB151zO/wI29/2s/ydzrnbehb6EbTPAh81s184556PsO5tzrlVA6mUc263mT0KfMTMrvTPDTLCaQiJ4Jx7HK+hYsAJcOhYcDP7sB8y1hie78DMcsxshZm9ZGYH/MfXmNmHIu3HzDLM7Ntmts0PJXvLzL5vZpm9LN/reHQzm2tmt5qXg6HVzPaZ2VNm9jn/8cvDxta+o0cI2jX+Mr2O8TWzCWb2v/722/zwt3vNbFGEZbuHTJg3BnqVmTWY2X4z+4eZzevj5e+5re4QczM70V+/pmd4o5l9yMyeMC9XQouZvW5m/xnptTSz083sb2ZW4b9Wb5vZs2Z2dY/leh2PbAMcFmLecJ3QSe23PV736f4yef5x8Kr/GjX4x8RdkV7fHtuf7tfx9gj7uDxsuaG+f+f7r0N9b69Fj3WPMrPrzWytHQyR3GFmN5nZ5P7W97dxpr+vUGTUE2HP6cyw5YrM7Dr/vW726/i4mZ3XY3vL/HWv7VF+dth2p/R47G6/fOYA6jvezH5sZpvN+9zX+X/fFr6+eZ/3L5rZP/3XpNU/lh8zs3f2su3t/i3XzG40L9y02bzvmOX+Mmlm9i0z2+If+9vM7Iu9va7+Z2mJv996/3h72MwW9/dce2xvrv8cy/3nstfM/mhmcwa4/m3AE/6/V/f4bJzpLxPxcxbN1yVsm8v896bKfz7bzOwGMysYxGsyqM+ymZ1kZveY9x3U5j+P35jZxAjLrvJfiwwz+y//GGv1X8c+v5PMbLKZ/Y+ZvemvU21mD5jZCcN9Dr28DnOBU4AHnHPNER4PvX9j/Xrt8t+j18zsy2aHhlJb2LnJvO+Yu8w7x3XZod8Jg3oPzewc886TB8z7LN7v1z3Ssn2dH3PM7Jvmfe81mHfuf93Mfm5m4/1lHHCZv8pbYcf69rDtRDznmFmKmX3WzF7wt33A//tz5g3V6bm887dVbN537x7/9dhoZp+IsLyZ2WXm5Ruq9N+LcvO+Fy6J9HpE2MZE/7h8Jux43m3ed8Jh5/xYvae91C28/fYhM1tnXsj/bjP7ifntBPPOCav8477WzH5vZuMibO8s/3V9zV+22f+8XG1mWb3UYbyZ3WLe92Tou+qySMuGrTOgc9wAnv9yM/uDmb1hB9um68z7rKX0WLbf47SXfUTtPGuDPLfYINvevWwjy7zvYmdeW6nf34POuYecczsGug/nXEsv5fuBh/1/Zw90e/24Ey+a69IobU8CThEYEhJqQPVsTPw7cC7wN7zG91gA/2S6EigDXgRuxesQWwb80cyOds79Z/fGzQy4G7gQ2IY3PCQD+CRw7KAqavZu4M9AJvAQ8CegAC989xvAr4CX8H4QXg3sAG4L28SqfrY/A3ga74r4Sn/7U4APAO82s/c75/4eYdX3+M/vQbwxefOBdwEnmNl8P6JkoJYAK/x63AoUA21+/W7Be90qgHuBOuBk4HvAUjM71znX4S97Pl6uiP3AA3hhwUV4ocGf5+CP5mi5za/PhXj5HF4Ke6zOPw4ewmvsrwFuBjrwXt8zgaeAdX1svw6vzsdH2MdLMKz372LgfA6+f9P7f7pcBHwW77OxGu89Ohr4f8B7zWyxP0azL9v953Qm8A4ODZ3c7j+naXjH7XS81+ghYAzeMfeQmX3GOfd//jpP+fVYCvxH2H7ODvt7Kf5nwn9PzgS2O+fe7KuiZpYDPIMXOvoo3veCAdPw3o97gNA2ioCf4b0ujwKVwAS88NF/mtmnnXM3R9hNur98Ed77mwF8CPiL35D9PHAS3vvUive+/sLMKp1zd0XY3kl4n6XHgP8FZuG9b2eY2XnOuaf6es7+8z4f77OW7j/nrcBkfzvvNrOznHMv9rOZ+/37y4B/cej30Pb+6kAUXxcz+y+8Y64G+DuwDzgO+DrwLjNb4jcyezXYz7J5PyT/z6/bA0A5XuM19Fk5uZcr8n/B61h/EO813NdPvRYCj/iv08N471sxXijz02b2PufcP4fyHPpwjn//dB/LZOAdgwV4je0M4P14n5E5eBEcPR0JPAe8AdwBZON9lw/6PTSzi4G78L4b7sIbenOa/7xfGcBzDG2nEO/7bgGwGe/81ObX9ZN4r/dev27L/eV+hvfdTdh9X34PfBjvGLkZr13yPuCXfp0j5ewqwPtuasP7HsrC+06/1cy6nHO3hy17Ld53wlt47ZJ6vO+mE/A+N5G+R3o6A7gK77X4C9CIdzxfDFxgZqc6516OsF7U3tMB+BLwTrzPzSrgPODfgCIz+yvecfgP4Ca8z8BH8T4rPTuYvwnMxfsu/wfea3sqcA1wppmd45zrDC3sd4KsBmbifSaexnt9f4332TzMIM9x/bke6MJ7nXfhtVvPxjsOT+DQYQtDPU6jcp4d7LllsG3vSPzP8AN47+EK59z1/TzXqPLbEaHXaUMvi51mXgdyGt758fF+2tDP+PfnAr+JRj0l4Jxzuo2SG14jwEUoPwfvy74LmOaXXeMvfwAoi7DObf7j3+hRnoV34ukCjg8r/7C//BogK6y8CK9DwwGremwrVIczw8qK8RobbcA7ItRrcoTnvKrncv5j0/3Hb+tR/rBf/h89yk/Ba9xWA7lh5Zf7y3cAS3usc12k16mP9+jM0PsEfCbC46F93Qtk9/J6fSWs7C9+2YII2yru8f+qSMdHj/1e3qN8O94Jud9l/ceO9R+7L8JjKUDhAF+nvvYx1PevCzh/kJ+pSUBmhPLzgE7gV4PY1mHHe4/3pgu4tEd5AV7HTTMwPqz8Sf+5jg0rW4PX4KkCfh9WvsDf7y0DqON7/WVvjPBYBpAX9n8mPT6PfvlY4FW8RnrPY3i7v/2/hb+uwOl+eQ3wAlAQ9thMvO+D9X18lr7Y47EL/fItQEpf7wFQiDfmtwqY32M7R+P9cHlxgO9xqE7XDOFzFq3X5Sx/ndXhy/fY/2Hvb4S6DvizDBzl12UrMKnHsmfjfVbu61G+yt/+K/T4rurttcJr7G4FWuhxfsDr0NyF98M9c7DPoZ/X4k5/O4t6eTz0/j3d4/0LP/+dEVY+PezY/UGE7Q3qPQRy8b732oHFPZa/MWxf0yPU4bYey//RL/8VYZ8d/7E8Dv3Oua3ndiO9xz3KPuSv8yKHfk+PAdb6j324xzqh+t8MpIaVz8f7Hnytx/LVeBcAciLU6bBjrZe6lxL2fRdWvgDvO+HBHuVRfU/7qds1/vL1wLyw8kxgI97nrZqwz4h/vD/qr3d8j+3NBCzCfr7nL39Jj/KbItUXWOwfg4d9BzLIc1w/z//ICGUpeBcHHHBSj8f6PE772M+wzrMM4dzC4NveZ4a/3ngXG17D+z7+6GCeby/H5PcHsOws/5j8nn9s7OrjcxA6dnveWvz1DzsOw9atBfYN9Tnplly3hFdAtzi+2Qe/CK7xb9fiXano8Mt/ErZs6EvkxgjbGeev80Iv+wl9Uf8orCx0YjwrwvKhL8JVPcpDdTgzrOzf/bKfDeI5r+rlsen0aKDh9Xw7vKiN9Ajr/N5//OMR6v+HCMvP8B+7Z4D1DZ1s1vfy+Hq8BkBBhMdS8U6Ez4eVhTowjhrAvlcRvw6MPw7zWO6tPsN5/+4bTp0i7OsV4M1BLH/Y8e6Xhz5Pf+5lvQv9xz8fVna1X3aB/3+ef9z8EC96aXfYsl8jwo+CXvYV6sA4rOExyNcmtM8zepRv98sjNUDf9B87O8JjT+B9J4X/eAl9lg7ppOh5vHNoI/6w9wD4il/2hV6ey43+4/MjPd5j2VCdrhnkcR3N1+U+f/mje6nDegbQCBzMZznsNXp3L4/f59czvAMs9P5cONDXKuyzcEMv64Tey3cN9jn08/xW+9uZ2Mvjoffv9D6ex2/Dyqb7ZW8TuYN0UO8hXsSCA26PsOxYvKvNjn46MPB+tHfi5ekZM4DX5bae2+3x+CoO78AItRXOi7D8Uv+xlT3KHd7FlvwI6/zLfzz82KrGi7447LWNxg3v6nYLYeegaL+n/ez/Gn9b34vw2H/5j/0uwmOX+Y9dNsD9jPOXvzWsLN1/L/YT9sM+wjFxTVjZoM9xQ3xfFvrb+a/BHKd9bG9Y51kGeW5haG3vM0OvN17k6m68jq2lg3muEfZ1OQPvwDifQzsjWvGiiiJ1ir0P+ARe2zkLmIoXpfc2/bQ9gNf9ZbKG+rx0S56bhpCMTlf79w6v4fIUXq/wHyIsGym5zgl4P5Z7mw4w3b8PHwe6EK9nOFKI7ap+a3zQyf79g4NYZzDK/PunnJfErKeVeGGWZcDvejy2NsLy5f594SDrcdjr7ofdLcDrpPiqHT4DFXgnhvDX/Q68UMTnzOwuvB80zzjnKgZZn2h5De9qyof8kNG/4h0Ta51zbVHY/nDev0jHep/8sNCP4J3MF+C9z6lhi0TjOS3x78f28nkr8e/D3/eVeA2WpXiN6XfgXZ1+HO/H1MVmNs859zoHQzlXDqAu/8K7enKVH6r/T7zQzZdcWAhxiJkdDVyJF249Aa9BEm5ShH3UOee2RSjfjdeoiRTSvwvvdT/C/zvcU865rgjrrMJ7Xcr859Wb0Ou/oJfX/yj/fh7e8R0r0XpdluA1sj9gZh+IsE4GUGJm45xz1X3UZzCf5dBr+A6LkIcC74dxKt5r2fN5DOZzGdrPtF7eq9B463l4x260vo9CeQNq+1imA6+jo6dV/n1ZhMdeds61Rigf7Hu40C8/7Dh3ztWb2Ut4n4X+nIB3JftJ59yBASw/FKG2wqoIj/0LrwMl0mu1xUUeXhE6BxcADf7fd+ANr9hoZn/2t7vGDTL5nz+c9bN4kQXFHD4su5jDZ8mJ1ns6EJHaJKEk0b19X4B3IaCbmY3B+7H9PrzPaB4Hhx3Dod/jc/FyETzVy+u5ioM5J0KGco7rlT+E5Uq8Ibwz8aJ3wkU67wzFcM+zgz23DKXtHXIaXidKA96Fg0jDm2LCOfcQXnMpHa9D4iPAD/DOB+8P/651zt3XY/WdwM1m9iJe4s+vm9lPXOThJDX+fTFehJWMYOrAGIWccxF/+fbi7QhlocbaCf6tN7lhf48Fanr5URlpH70p8O/7yyswVGP9+96m5guVF0R4rK5ngXOuw+9oSD1s6b5Fek0K8RoNJRzshOqTc+5eM3sPXuTKJ4HPAJjZOryxj48Osl7D4pzrNLOz8a4CXYx3pQKgwcxu9+vUOIxdDOf9G8xxGPIT4Kv+dh/GOy5DSfwuxwvXHK7Q5+1c/9ab8M/bs3hXwZb6/y/F60x5moP5Fpaa2Ra8zoXXnHP9Pn/n3H4zOxlv3PAFeONuAarM7Jd4V2PaAfzlVnKwQfcA3lW5Lg7mMImUwLe3HxEdfh0iPd7h36dHeGxvL9sLPd+xvTweEnr9P93Pcrn9PD5c0XpdxuG9J/19h4SGHUQ0yM9y6DW8cgD77Gkwn8vQfiL9ADxsP1H8Pgp95rPC/u6pKlInH30fh70998G+h6Ft9/dZ6E+Bfx+r8y8cbCsc1oHkn0+r8Dq8eqrrZXuhz0D4Ofjf8IbufBIvj8VVQIeZ/RNvGutIUzUewsy+jJczoRYvamQn0IR3YWg5Xod2pO+3aL2nA9HXd8KAvi/8H50r8aYufxUvP0glXmcLfn3Dn+dQjrWhnOMi8nNEvIDXqfs83oWKGrznVoDXERMxcfwQDPc8O9hzy1Da3iFleB1Pq0nQ7Ht+22Ab8F0za8MbYv1l4McDWPdFM3seL2/HErzhlD1l+/e9fQfLCKIODOmPi1AWOvHd6Jz72gC3U4+XOCo9QifGEYOoT51/P4nek/8MR+i59VanCT2Wi5W+Xvf1zrmFER6PvCHn/gH8w7+KchJeUqzPAX83szLnXOiqcRd4sxk4PwlomILBVL6f+tTiNSD/zcxm4V21+AzwRX8/vc0LPhDDef8ivea9MrNSvJPvq8ApzrmGHo8POCN4P0J1/Ypz7ucDWcE5125mTwPLzGwCXsNqjXOuCXjDzCrwct+8iNeoGUj0RWjbFcCn/OiT+XhXlr6A9yMwBW8udoD/xGtQnOV6TIdmZivwOjDiYXwv5aFjpL/PcujxBc65ASc7DLB6vCE1RcPd0CA+y6HXcGwvV8n72sdgPpeh/VzonHtggNuPxvdRKLHoOHqPwig2s9QInRh9HYe9PffBvoehbff3WehPnX8frSvYkfTaVjCzNLyrq4M6hnry34OfAT/zv8dPw5u94APA0X4ixEhREuH1+A7ej/GFzrk9PR5fEnFFf/e9lEftcxllF+J1XtzunLs8/AH/3NKzw2Uox9qgz3F9+H94nRffcc5dE/6A/758ZZjb7xaF8+xgzy1DaXuH/A/exa/PAQ+Y2XIXYcakOHoQrwPjTAbQgeGr9O97RtSEhIbY1PTyuIwgmkZVhuJ5vB+7pw9inRfxjrfTIjx25iC286x/H3Eaxgi6GFz0w3r//jS/kdLTWf59fzMORJ1/JXAjXgNr0I0c59wB59xK/8T3A7yQ1PDXMdTwnnLYyl6I7ECFGuj9vu7Oua3OuVvwfjQ0MvwftfF8/2biHdOPROi8mOw/Hg2hY34wnzfwoh7Aa5gfE/Y/eA2pMzl4tSv8sQFxno3OuV+EbWd52CKz8K6kroqw+kDC1aPlNIs8RdyZ/v36CI+FG+rrH8mAPxsx9CxQ6A/viZp+PsvRfA37Mqz9DOP7KPTjI+KUpL40vETCPZ3p3/d3HIYb7HsY+r477HNnZmPxIqIGInTuP8PvEO/PUI739Xjfq2dEeOwMf1tRO/865/Y55+51zn0Q73vxSLzvy74U43VurY7QeZHLwSE7gxGTz2UUzPLv/xLhsUjf45vwIlGO94+tns6MUBbN74fB1heG9708nPPsYJ/3UNreIc4593ngp3hJxv8xwM9wrIQ6QXteLIvIjwQKfa4Omy3Nfy6TgFcG2ektSUodGDJozrl9eGNIF5vZtyP9UDSzI82bzjLkt/79tRY2b7j/Q7zPKZ96uB3v6svnzOywBo7/wzFcNZF/kEfkX11+FC/h1ld7bPskvNlUavESbiXCT/A6Hm61CPPCm1mhn5sg9P9SM8vuuRwHr440hZWFxpofEs5oZkvxMsMPVCi8dWqE+s3opYFWiBfWOawrAnF+/7b796eZWXfDx2/A/h9RinBzzq3Fy1NzkZl9MtIyZnasfyUxXOhqz1V4Q496NqzG4k292dt480j7OcbMpkd4KNLxtB3vSupxPbbxKQ4OPYmH2XjPM7wOF+I1ZrfivbZ9+S3eleerzezEng+aWYqZnTnAuvT62YijG/37/zOziT0fNLMx/vCfPg3ys/w/eCHnN5rZUT1XMLMMM4vGj5e/4oUof8HM3hVpATNbYl4+oWh+H63y7/t73a4zs+7w9R7nv99GXiWiwb6Hf8X73vuwmfXsjL6G/odRAeCcq8SbcWUC8OOeHYNmltvjR+tQjvdb/fvrQu+Tv+0cvOkxAW4ZxPYOYWaZ/nnRepSn480KA4d+j0Wyz19mkf99H76Nn+F1cAxWVD6XMbDdvz8zvNDMZnJwyFU3P2rmDryIg2t6rLOYCFPgDuMcN5j6luFNnRvJcL6Xh3OeHdS5ZYht70M45/4NL/LhLOBhM8vv++kNnZmd5n8mepaXcPCz/I+w8jwzOz7C8hl4HS9T8TrIIuV2ORGvA+qJYVdckoKGkMhQfRHvh8F3gY/5YXR78aaqm4c3Pu9DeJm+Af4EXII3bv5V8+YgT8cbd/wC3lWPfjnnqszsw3izpzxhZg/iXf3Kx5svfQpe+GDI48ClZvY3vKRVHXgJyJ7sYzefxUtMeIOZnYf3ZTkFL7y0C/hEzyvu8eKcu9W8ubE/D2wzs4fxxt4W4T3vM/BOip/1V/lvYLqZrcI7sbcBi/DC/nfgNUZDfos3Rn2FmS3ASxp1FF6Uxn3A+wdYzTV4jbuv+g300FjYX+CNC77PvBwcr+IlFCvBu9KZToQG0RDE5f1zzr1tZnfiXXl5ycwewWusnIuXgf4lBn5lsz8fxmsM3WLe2Ovn8Bo+k/GO+2PwxoXuC1tnPV4oZSne1eTwZIihRlYpXsLCugHW4xzgJ2YWGke7z6/DhXiv7Q1hy/4Ur6PiaTO7Gy/8dTFeFNY9eJ/9eHgI+G8zeyfwMt4Vuovw3qNPucgJPrs556rN7GK8z8CzZvY4XiRUF16Dagle6GrPBKWRbMbLH3CpeWOAd+KFlP/eObdjKE9usJxzj5vZVXiN2C3mjft/C2/c9DS8jp2n8TLH92XAn2Xn3Cb/h8mteIkTHwLe8JebindFsZK+IxgG8tzazewivHw0//CP05fwvo+m4J2XZuL9AG8azHPox0q8z+Myeu+Q34PXKfKqmT3AwfPfBOCX/ZyTej7PQb2HzrlGM7sCL3/BU+YldN6D91k8Bm86yEgRD5F80V/ns8CZ/jmoDe/8swzvHL/KX/ZxvHPK/5nZPXjfQ3XOuf/p47n90e9g/CDesXI/B/NKzADuds7dMcC6RpINPAZsN7Pn8M6DWXjf2/OAB/yki71yznWZ2c/xfrRu8NszGXg/CovwfkSd1ccmIm0zWp/LaPsbXkfv18zsWLzzylS8oaj/IPKP/m/hDaf4qt9p8TTecX4JXvLcCyKsM5RzXCS/wzvmfmpmZ+HNQjXbr++9fh16GvRxGmbI59khnlsG2/Y+jHPuW2bWgjcM6lEzO98fStcnM/t/HIyiDkW6vNcOXjjc5Jy7PmyV/wGOMLNn8M51nXgXl96F9zm8n4MdlvjPdb15SYVfwfuOKsH7LM3AS2D/oV7O2ef595Eib2QkcgGYCkW3+NzwpzAa4LLX0GM6wQjLZOB9ma7G+3HSivcl9Tje1e9xEZb/L7zwr1a8H9TX4jXqHAOYRjXssaPxTlS78BpPe/EyiV/RY7lSvHnr9+J9eToOzoc9nR7TxIWtNwlvnvsd/var8L5sT4iw7OVEmPqwx+u+KtJjEZY9M7yOfSz3HuDveCfzNryxuM8D3wfmhi33QbzOoy14J9f9eA31a4GSXl7Xf+Jlqm7k4EwNEZ8jEaZR9cvPx+vIaAwdd/7rPRlv+Mozfp1b8bJFPwi8cxDHcn+vedTev37qkeO/llvxfhCXA/+LdyJexQA/bwP5zOFd0foWXkdcI97V4bfwGpFXEGFaQw5Oo/uPCI9t9h/74SDqOA8vCmgt3g/O0Of4Hrw8IJGO02f946kOeATvh9Kgjif/sV5fTyJMg8eh08ctwfvRst+vyyO9HAu9vgf+8fs/eJ+lFn9bm/Cm5l0+iNfwBLzvyHq8hmr3/uLxuoQ9dhpwN96P9jb//XzJf38XD+B5DPqzjDdt6W14n8tWvIb/q8Bv6DENbF/Pq7/PLd73/vX+tpvwPi9b/OP0o0DaUJ9DH/W50a/PvAiPbfdvY/G+H3b5+3odL4+O9Vh+Or2cm4bzHuL9SH/af01q8SIz5kY6TvqqA94Y9P/A+5HRhPeZeg2v07K0x7Jf859nq7+97WGPRXyP8aKDP4/3PdPk39bh5dqJNCVyr+fYns8Nr+PoG/57vBPvs1yJ9z31WSBjgO93mv/cXsP7Ln4b77tg2mBfz2h+Lv1tXEPv32OX0/vn5kwitD/wOv/u4GCS6o3+a5jW22uPl+viVr/+zf5zuLy3ffjrDPoc18vzn4+XNHofXpLNdXi5MXp9D/o6Tgewv2GdZxnkuYVBtL37eb2v9B97ESgewPMMHde93Vb1WP5j/mvzpv9+tvnH9d/xOpJ6fu/lAz/H+yy+7S/fiHfh4Xp6fLf0+L4ox5sNbUDvmW7JfzP/zRcRERkx/NDbJ4iQzE0k2vyhVZuA3zjnvtLjse0Azrnpca+YiMgIZmbvxeuw+phz7g+Jro/Eh3JgiIiIiAyDc2473tXDK8wslrN0iIgI4Oey+Q5etNZwhpZJklEODBEREZHh+z5eyPp0vHB7ERGJnSPwoi/udxpSMKqoA0NERERkmJxz+/GuBoqISIw5bxrjaxJdD4k/5cAQERERERERkcBTDgwRERERERERCTx1YIiIiIiIiIhI4KkDQ0REREREREQCTx0YIiIiIiIiIhJ46sAQERERERERkcBTB4aIiIiIiIiIBJ46MEREREREREQk8NSBISIiIiIiIiKBpw4MEREREREREQk8dWCIiIiIiIiISOCpA0NEREREREREAk8dGCIiIiIiIiISeOrAEBEREREREZHAUweGiIiIiIiIiASeOjBEREREREREJPDUgSEiIiIiIiIigacODBEREREREREJPHVgiIiIiIiIiEjgqQNDRERERERERAJPHRgiIiIiIiIiEnjqwBARERERERGRwFMHhoiIiIiIiIgEnjowRERERERERCTw1IEhIiIiIiIiIoGnDgwRERERERERCTx1YIiIiIiIiIhI4KkDQ0REREREREQCTx0YIiIiIiIiIhJ46sAQERERERERkcBTB4aIiIiIiIiIBJ46MEREREREREQk8NSBISIiIiIiIiKBpw4MEREREREREQk8dWCIiIiIiIiISOCpA0NEREREREREAk8dGCIiIiIiIiISeOrAEBEREREREZHAUweGiIiIiIiIiASeOjBEREREREREJPDUgSEiIiIiIiIigacODBEREREREREJPHVgiIiIiIiIiEjgqQNDRJKCmTkzmzVa9y8iIiLRlehze6L3L5KM1IEhIgCY2TVm9oc47u8yM1tnZvvNrMLMfmRmafHafyyYWZGZVZrZ04mui4iISKKpbTE8ZnaOmb1oZgfMrNzMPpjoOokkmjowRCQqhtBAyAG+ChQDJwFLga8nqC7R8kPg9QTtW0REZEQZzW0LM5sP/BH4D2AscDywLp51EAkidWCIjDJm9k0z22VmDWa22cyWmtn5wLeAS8ys0cxe9pedaGYPmFmNmW01s0+HbecaM7vHzP5gZvuBy81srJndYmZ7/H1838xSI9XDOfcr59xTzrk259wu4A7g1H6q/y4ze9PMqszsBjNL8etyuZk9Y2Y3mlkNcI2ZHWlmK82s2l/+DjMrCKv/djP7upm9Ymb1ZnaXmWWFPX6l/zx2m9knB/C6LgGOAX7b37IiIiIjidoW3fWPZtviP4HfOOcedM51OOeqnXPb+llHZMRTB4bIKGJmc4AvAic45/KAZcB259xDwA+Au5xzuc65Bf4qfwIqgInAxcAPzGxp2CYvBO4BCvAaCbcDHcAsoAw4D/h/A6zeGcDGfpZ5H7AYWOjvO/zkfxLwJlAKXAsYcJ1f93nAFOCaHtv7IHA+MAM4DrgcwG90fR04F5gNnNNXpfyG1P/ivbaun+cgIiIyYqhtEZu2BXCyv94Gv9PjD2ZW1M86IiOeOjBERpdOIBOYb2bpzrntvfXmm9kU4DTgm865FufcS8DNwMfCFlvjnLvfOdcF5APvBL7qnDvgnNsH3Ahc2l+lzOwTeI2HH/ez6A+dczXOuZ3AT4EPhT222zn3C/8qRbNzbqtz7lHnXKtzrhL4CfCOHtv7uXNut3OuBvgbXngmeI2P3zrnXnXOHeDwxklPXwaec84ptFNEREYbtS0OFa22xWS81+X9eB0e2cAv+llHZMRL2qQ2IjJ4zrmtZvZVvJPm0Wb2MPA159zuCItPBGqccw1hZTvwGgMh5WF/TwPSgT1mFipL6bHMYcxsOXA9cI5zrqqfpxC+rR1+HSM9hpmVAj8HTgfy/LrU9tje22F/N4VtbyKHjjPd0Uf9J+J1YCzqp+4iIiIjjtoW0W9b+JrxOjze8Pf9A+CxftYRGfEUgSEyyjjn/uicOw2vUeDwEk/C4UMfdgNFZpYXVjYV2BW+ubC/y4FWoNg5V+Df8p1zR/dWFz+c8v+A9zrnNgyg+lN61CW8cdSz/tf5Zcc55/KBj+KFfg7Engj76s2JwATgNTN7G/gZcKKZvd3bGF0REZGRRG2LARlM2wLglQj7Fxn11IEhMoqY2RwzO9vMMoEWvN79Tv/hvcD0UPIq51w5sBq4zsyyzOw44FN441EP45zbAzwC/LeZ5ZtZip/sqmdoZaguZ/vber9z7vkBPoUrzazQD0H9CnBXH8vmAY1AnZlNAq4c4D4A7sZLHDbfzHKAq/tY9kFgOl6I6PHAfwHrgeOdc529riUiIjICqG0xYINpW4CXFPwTZjbTX/6bwN8HsT+REUkdGCKjSyZeSGUVXohjKV6GcIA/+/fVZvai//eH8H6c7wbuA652zj3ax/Y/DmQAr+GFVN6DF50QybfxpgX7p5+dvNHMHuyn/n/FC798CfgHcEsfy34HLyFXvb/svf1su5tz7kG8cbArga3+fW/Ltjrn3g7d/P21+3+LiIiMdGpbDMBg2hb+8rcCvwOewxtu0oo3ZFVkVDPnFJkkIiIiIiIiIsGmCAwRERERERERCTx1YIiIiIiIiIhI4KkDQ0REREREREQCTx0YIiIiIiIiIhJ46sAQERERERERkcBLS3QFgqK4uNhNnz490dUQEZFherPyAAAzS8YkuCajx7p166qccyWJrkfQqG0hIjIyqG0Rf721LdSB4Zs+fTpr165NdDVERGSYLvnNGgDu+sySBNdk9DCzHYmuQxCpbSEiMjKobRF/vbUt1IEhIiIjiq6OiIiISDSpbREc6sAQEZER5bqLjkt0FURERGQEUdsiOJTEU0REREREREQCTxEYIiIyoqy49xXg0Ksl7e3tVFRU0NLSkqhqjQhZWVlMnjyZ9PT0RFclaelYjA4diyIST5HaFpIY6sAQEZERJZQpPFxFRQV5eXlMnz4dM0tArZKfc47q6moqKiqYMWNGoquTtHQsDp+ORRGJt0htC0kMDSEREZERr6WlhXHjxukH4zCYGePGjVPkwDDpWBw+HYsiIqOXOjBERGRU0A/G4dNrGB16HYdPr6GIyOikDgwREZEAWbVqFatXrx7WNnJzc6NUGxntdDyKiEiQKAeGiIgc5v71u7jh4c3srmtmYkE2Vy6bw/KySYmu1oDMn5if6CoMy6pVq8jNzeWUU05JdFVEdDyKiJC8bYtkbs/1RhEYIiJyiPvX72LFvRvYVdeMA3bVNbPi3g3cv35Xoqs2IFe/92iufu/Rw9rG/et3cer1K5lx1T849fqVUXnuy5cvZ9GiRRx99NHcdNNNADz00EMsXLiQBQsWsHTpUrZv386vf/1rbrzxRo4//nieeuopLr/8cu65557u7YSuZjc2NrJ06VIWLlzIsccey1//+tdh11GCJxbHIuh4FBEZjGi0LeIt2dtzvVEEhoiIHOKGhzfT3N55SFlzeyc3PLw56XvtByJ0wg+9BqETPjCs53/rrbdSVFREc3MzJ5xwAhdeeCGf/vSnefLJJ5kxYwY1NTUUFRXx2c9+ltzcXL7+9a8DcMstt0TcXlZWFvfddx/5+flUVVVx8sknc8EFFyg3wAgSq2MRdDyKiIx0I7U9pw4MERE5xO665kGVB81X71wPwE8vLYv4+Hf+tpHXdu/vdf31O+to6+w6pKy5vZNv3PMKf3p+Z8R15k/M7/fKzM9//nPuu+8+AMrLy7nppps444wzuqeBLCoq6nP9npxzfOtb3+LJJ58kJSWFXbt2sXfvXo444ohBbUcSJ1HHIuh4FBEZjP7aFkGU7O253qgDQ0REDjGxIJtdEU5uEwuyE1CbwdtTP7ypFXv+YOyvfCBWrVrFY489xpo1a8jJyeHMM89kwYIFbN68ud9109LS6Ory9u2co62tDYA77riDyspK1q1bR3p6OtOnT9e0kiNMLI5F0PEoIjJYw21bJEKyt+d6ow4MERE5xJXL5nDlPS/T3um6y7LTU7ly2ZwE1ip6+rs6fer1KyOe8CcVZHPXZ5YMaZ/19fUUFhaSk5PDpk2bePbZZ2ltbeVf//oXb7311iEh+3l5eezff/Cq/PTp01m3bh0f/OAH+etf/0p7e3v3NktLS0lPT+eJJ55gx44dQ6qbJE4ijkXQ8SgiMhpcuWwOV937Ci3tBzu9R0J7Tkk8RUTkEMvLJnHe/PHd/08qyOa6i45N6vGSg3Hlsjlkp6ceUjbcE/75559PR0cHxx13HN/+9rc5+eSTKSkp4aabbuKiiy5iwYIFXHLJJQC8973v5b777utOmvjpT3+af/3rX5x44ok899xzjBkzBoCPfOQjrF27lsWLF3PHHXcwd+7coT9pCaRYHIug41FEZDRYXjaJr517VPf/R4zNGhHtOUVgiIjIYUrzswA4c04Jt33ixATXJr5CJ/ZoTjuWmZnJgw8+GPGxd77znYf8f9RRR/HKK68cUvbss892/33dddcBUFxczJo1ayJus7Gxcch1leCIxbEIOh5FREaLOUccnP711stOSNrpYMOpA0NERA5T2dB6yH0yWTitcNjbWF42KemvUMjIoGNRRCTxotG2SITymqbuv/c1tDAfdWCIiMgIVNXYesh9Mvnm+QpdFxERkehJ1rZFeW14B0bytekiiVkODDO71cz2mdmrER77upk5MysOK1thZlvNbLOZLQsrX2RmG/zHfm7+hOJmlmlmd/nlz5nZ9LB1LjOzLf7tslg9RxGRkaqqsa37vqvL9bO0iIiIiARNRU0zE8Z6w4KTMao2klgm8bwNOL9noZlNAc4FdoaVzQcuBY721/mlmYWyVv0KuAKY7d9C2/wUUOucmwXcCPzQ31YRcDVwEnAicLWZJWfMj4hIglQ2tJKWYnR2OWqb2hJdnUH57O/X8dnfr0t0NURERGSESNa2RXltE7NKc8nLSmPf/uSbCjaSmHVgOOeeBGoiPHQj8A0g/JLehcCdzrlW59xbwFbgRDObAOQ759Y45xzwO2B52Dq3+3/fAyz1ozOWAY8652qcc7XAo0ToSBERkchaOzqpb25nVmkucDAaI1nUNrUlXaeLiIiIBFeyti3Ka5qYUpRDSV4mlUk4LDiSuE6jamYXALuccy/3eGgSUB72f4VfNsn/u2f5Ies45zqAemBcH9sSEZEBqPY7LOZN8BI9jZSQQxEREZHRorG1g9qmdqYU5lCal8m+/SOjPRe3DgwzywH+A/ivSA9HKHN9lA91nZ51usLM1prZ2srKykiLiIiMOqHEnfMm5AFQ2TgyQg5HilWrVvGe97wHgAceeIDrr7++12Xr6ur45S9/Oeh9XHPNNfz4xz8ech1l9NDxKCISTKEZSKYUZVOal6UknkNwJDADeNnMtgOTgRfN7Ai8KIkpYctOBnb75ZMjlBO+jpmlAWPxhqz0tq3DOOducs4tds4tLikpGdaTExEZKUIRF/MnjAWgqiH5QiaTUWdn56DXueCCC7jqqqt6fXyoPxhFdDyKiCS37g6MUARGQwteVobkFrcODOfcBudcqXNuunNuOl5Hw0Ln3NvAA8Cl/swiM/CSdT7vnNsDNJjZyX5+i48Df/U3+QAQmmHkYmClnyfjYeA8Myv0k3ee55eJiMgAhCIwphfnkJmWknRjJk+dVcyps4r7X7A/e/bAO94Bb7897E1t376duXPnctlll3Hcccdx8cUX09TUxPTp0/nud7/Laaedxp///GceeeQRlixZwsKFC/nABz5AY2MjAA899BBz587ltNNO49577+3e7m233cYXv/hFAPbu3cv73vc+FixYwIIFC1i9ejVXXXUV27Zt4/jjj+fKK68E4IYbbuCEE07guOOO4+qrr+7e1rXXXsucOXM455xz2Lx587Cfs0RRFI9F0PEoIjJYUWtbxFF5bTMAU4pyKM3PpKW9i4bWjgTXavjSYrVhM/sTcCZQbGYVwNXOuVsiLeuc22hmdwOvAR3AF5xzoa7/z+HNaJINPOjfAG4Bfm9mW/EiLy71t1VjZt8DXvCX+65zLlIyURERiSCUtLM4N9NL+pRkIYdfXjo7Ohv63vfg6ae9+//932FvbvPmzdxyyy2ceuqpfPKTn+y+Ep2VlcXTTz9NVVUVF110EY899hhjxozhhz/8IT/5yU/4xje+wac//WlWrlzJrFmzuOSSSyJu/8tf/jLveMc7uO++++js7KSxsZHrr7+eV199lZdeegmARx55hC1btvD888/jnOOCCy7gySefZMyYMdx5552sX7+ejo4OFi5cyKJFi4b9nCVKonwsgo5HEZHBiFrbIo7Ka5oYk5FKYU46pXneVKr79reSn5We4JoNT8w6MJxzH+rn8ek9/r8WuDbCcmuBYyKUtwAf6GXbtwK3DqK6IiLiq2xoJS8rjaz0VEryMrsjMkaUM888vOyDH4TPfx6ammDpUnj+eejqgl//GtavhyuugMsvh6oquPjiQ9ddtarfXU6ZMoVTTz0VgI9+9KP8/Oc/B+j+Afjss8/y2muvdS/T1tbGkiVL2LRpEzNmzGD27Nnd6950002HbX/lypX87ne/AyA1NZWxY8dSW1t7yDKPPPIIjzzyCGVlZQA0NjayZcsWGhoaeN/73kdOTg7gDQWQOEnAsQg6HkVERrqK2iYmF+ZgZpTmZQKwr6Gle5a5ZBWzDgwREUlOlY2tlOR6J7ri3MzuMZTJ4rJbnwfg9k+eOPSN7NgBoXGiznn/D5M3EvLw/8eMGePvxnHuuefypz/96ZDlXnrppcPWHSrnHCtWrOAzn/nMIeU//elPo7YPibIYHIug41FEZDCi0raIs/KaZqYUZQNQmu+165ItqjaSuE6jKiIiwVfZ0Eqx31OfjENIWto7aWnvJwHhqlWH3z7/ee+x+nqorT30R2NtLZx/vvd/cfHh6w7Azp07WbNmDQB/+tOfOO200w55/OSTT+aZZ55h69atADQ1NfHGG28wd+5c3nrrLbZt29a9biRLly7lV7/6FeAlYNy/fz95eXk0NDR0L7Ns2TJuvfXW7lwGu3btYt++fZxxxhncd999NDc309DQwN/+9rcBPSeJggQci6DjUURkMAbUtggQ5xzlfgQGQEnYEJJkpw4MERE5RFVYBEZJbiY1TW10dHYluFZx9L3veeH64To7vfJhmDdvHrfffjvHHXccNTU1fO5znzvk8ZKSEm677TY+9KEPcdxxx3HyySezadMmsrKyuOmmm3j3u9/NaaedxrRp0yJu/2c/+xlPPPEExx57LIsWLWLjxo2MGzeOU089lWOOOYYrr7yS8847jw9/+MMsWbKEY489losvvpiGhgYWLlzIJZdcwvHHH8/73/9+Tj/99GE9V4mSGB2LoONRRGQkqznQRlNbJ1OKvA6M/Kw0MtNS2NfQkuCaDZ+NhKlUomHx4sVu7dq1ia6GiEjCHXvNw7x/4WSuueBofv/sDr59/6s8/62llOZnJbpqA3LJb7yrynd9Zkl32euvv868efMGtoGyMvCTDB7i+OO9/ANDsH37dt7znvfw6quvDmn9IIn0WprZOufc4gRVKbAitS0SfSzCyDkeB/VaiogMQ6S2RZC9VF7H8v99hps+tojzjj4CgNN/tJKFUwv52aVlCa7dwPTWtlAODBER6dbS3klDSwfFuRkA3ZEY+xpak6YDY9iG8cNQJKp0LIqIyBCE8peFIjAASvOyRsQQEnVgiIhIt+oDB6dQBS8HBpBUM5EsnVea6CocZvr06Ul/tVtGDh2PIiKDE8S2RV/Kaw/vwCjJzWTLvobeVkka6sAQEZFuoYSdoY6LUARGMiXyvOKMIxNdBRERERlBkq1tUV7TTGFOOrmZB3/ul+ZnsnpbVQJrFR1K4ikiIt2q/I6KUARGcZ43lKQyiSIweqOcT8On1zA69DoOn15DEZHeVdQ2HRJ9AVCal8n+lo6kmk0lEnVgiIhIt1BHRSgCIycjjdzMNKoa2hJZrUG55DdrupNthWRlZVFdXa0fPcPgnKO6upqsrFGSCyVGdCwOn45FEYm3SG2LICuvaWJKYc8ODO87M5miaiPREBIREekWisAY5yfxBCjOzUj6CIzJkydTUVFBZWVloquS1LKyspg8eXKiq5HUdCxGh45FEZHIOrscu+qaWXbMEYeUl+SHErO3HBadkUzUgSEiIt2qGlv9ucJTu8tK8jKpTPJ5w9PT05kxY0aiqyGiY1FERGJq7/4W2jtdhAgMvwMjyWci0RASERHpVtnY2j18JKQkL5OqxuQZQiIiIiIyWkWaQhUODiHZl+RDSNSBISIi3aoa2roTeIYU52Ym/XhJERERkdGgvLYZgCmF2YeUjxuTQWqKsS/Jo2o1hERERLpVNrZy9MT8Q8pKcjOpb26ntaPzkKElQfWe4yYkugoiIiIygiRT26K8pgkzmNSjAyMlxSjOzUj6ISTqwBARkW5VDa2HRWCEhpRUN7YxsSA70mqB8rEl0xNdBRERERlBkqltUV7bxPi8rIgXnUrzsjSERERERoaW9k4aWjsOy4ER6tBIlmEkzW2dNLcl9xznIiIiEhzJ1LaoqG1mSlHkC06leZnqwBARkZEh1EFR0ksERrJ0YFz+2+e5/LfPJ7oaIiIiMkIkU9uioqbpsBlIQkrzk39mOXVgiIgI4E2hClCcl3FIeagDI/S4iIiIiARPW0cXe/a3MLkocgdGSV4W1Qfa6OjsinPNokcdGCIiAoRHYGQdUj4uN+OQx0VEREQkeHbXNePc4TOQhJTkZeIcVDW2xblm0aMODBERAQ6ezHpGYGSmpTI2O51KRWCIiIiIBFZ5bRMAU3qJwChNsmHBkagDQ0REgIMns3FjMg97rCQvU0NIRERERAKsvKYZ6L8DY18S58HQNKoiIgJ4OS4KctLJSDu8b7s4NyNpeusvXjQ50VUQERGRESRZ2hbltU2kpxpH5GdFfLzUL0/mmUjUgSEiIoDXgVGce3j0BXhJnzZU1MW3QkP0gcVTEl0FERERGUGSpW1RXtPExIJsUlMs4uOhmeb27U/eDgwNIREREcAbQtJzCtWQktzMpEn4VHOgjZoDyVFXiT0z225mG8zsJTNb65cVmdmjZrbFvy8MW36FmW01s81mtiysfJG/na1m9nMzi9w6FBGRESdZ2hbltc29TqEKkJGWQmFOelIPIVEHhoiIAH4ERl7kDozivAwaWztoauuIc60G73N/WMfn/rAu0dWQYDnLOXe8c26x//9VwOPOudnA4/7/mNl84FLgaOB84Jdmluqv8yvgCmC2fzs/jvUXGbT71+/i1OtXMuOqf3Dq9Su5f/2uRFdJJGklS9uioqaJKUWRZyAJKc3LSuohJOrAEBERoP8IDICqhuBffRAZgAuB2/2/bweWh5Xf6Zxrdc69BWwFTjSzCUC+c26Nc84BvwtbRyRw7l+/ixX3bmBXXTMO2FXXzIp7N6gTQ2QEO9DaQfWBNib3EYEBUJqfqQ4MERFJbk1tHRxo6zxsCtWQktC0W5qJRJKPAx4xs3VmdoVfNt45twfAvy/1yycB5WHrVvhlk/y/e5aLBNIND2+mub3zkLLm9k5ueHhzgmokIrFWUdv3DCQhJXmZVO5P3iEkSuIpIiLdkRW9RWCEknsmy0wkImFOdc7tNrNS4FEz29THspHyWrg+yg/fgNdJcgXA1KlTB1tXkajYXdc8qHIRSX7lNU0ATCnsfwhJZWMrzjmSMZ1TzCIwzOxWM9tnZq+Gld1gZpvM7BUzu8/MCsIeG1TSLDPLNLO7/PLnzGx62DqX+Ym5tpjZZbF6jiIiI0UosqK3HBilisCQJOWc2+3f7wPuA04E9vrDQvDv9/mLVwDhqeYnA7v98skRyiPt7ybn3GLn3OKSkpJoPhWRAZtYEPkHTG/lIpL8ymv9Dox+IjBK8zJp73TUNrXHo1pRF8shJLdxeIKrR4FjnHPHAW8AK2DISbM+BdQ652YBNwI/9LdVBFwNnITXSLk6PLu4iIgcrsrvmOgtAqNoTAZmUJUEERgfPXkaHz15WqKrIQFgZmPMLC/0N3Ae8CrwABC6wHEZ8Ff/7weAS/2LJDPw2h3P+8NMGszsZP9CysfD1hEJnCuXzSE99dArq9npqVy5bE6CaiSS3JKhbVFe00x2eirjxkQeDhxSmu9PpZqkM5HErAPDOfckUNOj7BHnXCiF/bMcvJoxlKRZ4Qm47gGW+o2KZcCjzrka51wtXqeJMoWLiPQhNDSkpJcIjLTUFIpyMpIiAuO9Cyby3gUTE10NCYbxwNNm9jLwPPAP59xDwPXAuWa2BTjX/x/n3EbgbuA14CHgC865UCKBzwE347VRtgEPxvOJiAzG8rJJzC7NJcXvwxibncZ1Fx3L8jKlbhEZimRoW5TXejOQ9DcspDQvC4B9+4PfposkkTkwPgnc5f89Ca9DIySUHKud3pNmdSfacs51mFk9MI7eE3AdRuNURUQ8oQiMoj567UvyMpMiB0ZojLdCpcU59yawIEJ5NbC0l3WuBa6NUL4WOCbadRSJhY7OLnbWNHPpiVNZtWkfC6cVqvNCZBiSoW1RXtPElH5mIIGDF6uSdSaShMxCYmb/AXQAd4SKIizWX9KsYSfa0jhVERFPZUMrRWMySE/t/bRQkpfZ3dERZP9210v8210vJboaIiIJs2FXPY2tHZxy5DjKphayfmddoqskktSC3rZwzlFR29xv/gsIy2umDoyB8ZNqvgf4iD8sBIaWNKt7HTNLA8biDVnpbVsiItKLqsZWinP7HjNZnJscERgiIqPd6m3VAJw8cxxlUwvYVdfMviSeNlFE+lbX1E5jaweT+5mBBGBMZhpjMlKVA2MgzOx84JvABc65prCHhpI0KzwB18XASr9D5GHgPDMr9JN3nueXiYhILyobWrunSu1NaAjJwb5nEREJojXbqpl7RB7FuZmUTS0AYH15XULrJCKxM9AZSEJK87OSdghJzHJgmNmfgDOBYjOrwJsZZAWQiTcPO8CzzrnPOuc2mlkoaVYHhyfNug3IxkuYFUqadQvwezPbihd5cSmAc67GzL4HvOAv913n3CHJREVE5FBVjW3djdzelORm0trRRWNrB3lZ6fGpmIjExf3rd3HDw5vZXdfMxIJsrlw2RzkTklRrRycvbK/hwyd5+d2OnjiW9FRj/c46lh19RIJrJyKxUF7j5egYSA4M8C9KKYnnoZxzH4pQfEsfyw8qaZZzrgX4QC/buhW4dcCVFREZ5bwhJH1HYBTneUNMKhta1YEhMoLcv34XK+7dQHO7d+1oV10zK+7dAKBOjCT00s46Wju6OOXIYgCy0lOZPyGf9TtrE1wzEYmVgxEYA0syWpqXyau76mNZpZhJ5CwkIiISAAdaO2hq6+x1CtWQklxv2q3KhlZmluTGo2pD8unTZya6CiJJ5YaHN3d3XoQ0t3dyw8Ob1YGRhFZvqybF4MQZRd1lZVMLueuFcjo6u0jrI1mziEQW9LZFeU0TBTnpA77AVJqXxb6GfTGuVWzoG0xEZJQLzSwykBwY3vJtMa/TcJwzfzznzB+f6GqIJI3Q9IADLZdgW7OtmmMnjWVs9sEfMmVTC2hu72Tz3oYE1kwkeQW9bVFe2zzg4SMApfmZNLV10tjaEcNaxYY6MERERrnQzCL9RWCEZimpDHjW6m2VjWyrbEx0NUSSRml+5M/+xIKBhSJLcDS1dbC+vJYl/vCRkIVTCwE0narIEAW9bVFR0zTg4SNwcCrVZJydSB0YIiKj3MEIjL6nUS3MySA1xahsDHbSp2/du4Fv+eP3RaR/R0TowMhMS+HKZXMSUBsZjrXba2nvdJxy5LhDyicXZlOcm6EODJEhCnLboqvLUTHYCIw8b1hwMs5Eog4MEZFRrtIfElLSzxCSlBSjODeDqoZgDyERkYF7cWctL1fsZ9n88UwqyMaAFPM6NS5YMDHR1ZNBWr2tmvRUY/H0wkPKzYzjpxSyvlyJPEVGmn0NrbR1djF5gFOowsHIu2TswFASTxGRUa6yoRUzKBrTdwQGeHkygh6BISID45zjun++TnFuJj+55HjGZHrNwntfrOBrd7/MH5/fyUdPnpbgWspgrNlWRdmUQnIyDm/il00t4LHX91LX1EZBTv/f9yKSHLpnICnUEBIRERkFqhpbKcrJGFBm+pK8zO6cGSKS3B59bS8vbK/l386d3d15AfC+skmccuQ4fvjQpqRs3I5W9c3tbNhVz5Iew0dCyqYWALC+vC5+lRKRmCuvCU2hOvAIjLHZ6WSkpiRlm04dGCIio1xlQ2u/CTxDSnIzu3NmiEjyau/s4vqHNjGzZAyXLJ5yyGNmxveXH0NrRxff/ftrCaqhDNbzb9XQ5ei1A+O4yQWkmBJ5iow05TXejFGTBpF42cwoycvUEBIREUk+VY2t/U6hGlKc53VgdHU5UlIsxjUbmi+dPTvRVRAJvLteKOfNygPc9LFFEaOvZpbk8sWzZvGTR9/g/Yv2cdac0gTUUgZj9bYqMtNSuiMtesrNTOOo8Xms36k8GCKDFeS2RXltE+PzM8lKTx3UeskaVasIDBGRUa6yobXfGUhCSnIzae901De3x7hWQ3fa7GJOm13c/4Iio1Rjawc/fewNTpheyLnzx/e63GfeMZMjS8bw7ftfpamtI441lKFYs62aE6YXkZnW+4+YsqmFvFReR1eXi2PNRJJfkNsW5TVNg5qBJKQ0L5N9Dck3TFAdGCIio5hzjqrGQQwh8ZcL8jCSjbvr2bi7PtHVEAms/3vyTaoa2/jWu+Zh1nskVWZaKj9437FU1Dbzs8e3xLGGMlhVja1seruh1+EjIWVTC2ho6eDNqsY41UxkZAhy26KitnlQ+S9CSvOTcwiJOjBEREaxA22dtLR3DXwIib9ckEMOv/u31/ju3zRuXySSfftb+L+n3uTdx06gbGphv8ufNHMclyyews1PvcXre/bHoYYyFM++WQ3AKf10YCz0h5e8qDwYIoMS1LZFe2cXe+qbBzUDSUhpXhZ1Te20dnTGoGaxow4MEZFRLNQRMdgIDE2lKpKcfvr4Fto6urhy2ZwBr7PiXXMpyE5nxb0bNPQgoFZvqyY3M41jJ43tc7mZxbnkZaUpkafICLG7rpkuB5OHEoGRF/yLUpGoA0NEZBQLDQUZaARGSZKe7EQEtu5r4K4XyvnoydOYXjxmwOsV5GTwn++Zx0vlddzx/M4Y1lCGas22ak6aUdTvdNgpKcbxUwqUyFNkhAjNQDKkHBj5Xpsu2YaRqANDRGQUG2wERn5WmjdvuCIwRJLO9Q9uJic9lS+dPWvQ6y4/fhKnzhrHjx7cxN79yZf0bSTbXdfMW1UH+s1/EbJwaiFv7G2gsVWJWUWSXXltEwBTioY2hARg3/7katOpA0NEZBQbbARGaN5wRWCIJJfn3qzmsdf38tkzj2TcAD/v4cyM7y8/ltbOrkCOAx/N1mwL5b8Y2AwJZVML6HLwSkVdDGslIvFQXtNEWooxYexQOjBCUbXJ1SmdlugKiIhI4lQ1tJJiUDRmYNOoAhTnZVLV2BbDWg3PN84f+Nh+kdHAOccPHtzEEflZfPLUGUPezoziMXz57Fn8+JE3eP+mvZw9t/cpWCV+Vm+rpjAnnblH5A1o+eOnFACwfmfdgDs9REa7oLYtymubmViQTWpK7zNK9WZcbiYppiEkIiKSRCobWykakzmoE19JbkagIzAWTSti0bSiRFdDJDD+ueFtXi6v42vnHUV2RuqwtnXFGUcyqzSXb9+/kaY2DUFINOcca7ZVseTIcaQM8Hu8ICeDmSVjlMhTZBCC2rYor2ka0vARgNQUY1xupoaQiIhI8qhsaKM4d+DRF0Dgh5Cs21HDuh01ia6GSCC0dXTxo4c3MWd8Hu9fOHnY28tIS+EH7zuWXXXN/OyxLVGooQzHjuomdte3sGSQkRRlUwp5qbwW5zSrjMhABLVtUVHbNKQEniGleZnsS7IhJOrAEBEZxSobWwecwDOkJDeTmgOtdAZ0OsUfPbSZHz20OdHVEAmEO57bwY7qJq5619whhRhHcuKMIi49YQo3P/0WG3fXR2WbMjSru/NfDCyBZ0jZ1AKqGtuoqG2ORbVERpwgti2a2jqoamxjyhCmUA0pycvUEBIREUkeVQ2tlAwyoV9xXiZdDmoOBDcPhojA/pZ2fv74Fk45chxnHlUS1W1f9c65FOak8637Xg1sZ+ZosHpbFePzM5k5iGlxwevAAHhR06mKJK1QB+TkwqENIYFQBIY6MEREJAk456hsbKV4CBEYQKCHkYgI/HrVNmqb2vnWu+ZhFp3oi5CCnAy+/Z75vFxexx3P7YjqtmVgvPwX1ZxyZPGg39854/PITk9VHgyRJFZeE5pCdThDSLKobgxuVG0k6sAQERmlGlo7aOvoGnQERmjISWgKVhEJnj31zdzy9FssP34ix0waG5N9XLBgIqfPLuZHD21m7/7kGkM9Eryxt5HqA20sGeTwEYC01BSOmzyW9YrAEEla3R0Yw8mBke9F1VYfSJ42nTowRERGqSo/gqI4b3BJPIsVgSESeD955A2cg38/L3ZT/5kZ319+DO2dXXznbxtjth+JbPW2KmDw+S9CyqYWsnH3flraO6NZLRGJk/LaZrLSUwadjD1cqX9RKplmIklLdAVERCQxQh0QJblZg1ovFIFRGdAIjP967/xEV0EkoV7fs597Xqzg/502Y1ihxQMxbdwYvrx0Njc8vJnHX9/L0nnjY7o/OWj1tmqmFuUweYhXX8umFtDR5di4uz6Q00OKBEkQ2xblNU1MLswZ1hDBkjyvDZhMF6UUgSEiMkpVNXpJOAcbgTEmM42cjNTuCI6gOXriWI6eGJuQeZFkcP2Dm8jLTOMLZ82Ky/4+ffpMjhqfy3/9dSMHWjviss/RrrPL8eyb1UOOvgAom1IAoDwYIgMQxLZFeW0zU4aRwBPCIjCSaCpVdWCIiIxSlf7JarA5MMAbRhLUCIynt1Tx9JaqRFdDJCGe3lLFv96o5Etnz6YgZ+hhxYORkZbCD953LLvqmvnpY2/EZZ+j3cbd9TS0dAwp/0VIaX4Wkwqy1YEhMgBBa1s456ioaRp2lF1JEg4hiVkHhpndamb7zOzVsLIiM3vUzLb494Vhj60ws61mttnMloWVLzKzDf5jPzc/RsbMMs3sLr/8OTObHrbOZf4+tpjZZbF6jiIiyayqsY3UFKNwCD9ySvIyAxtu+IuVW/jFyi2JroZI3HV1Oa578HUmFWTzsSXT4rrvxdOL+NCJU7n1me28uqs+rvsejdZsqwYYVgcGwMJphUrkKTIAQWtb1De309DaMawEngBZ6amMzU5PqqlUYxmBcRtwfo+yq4DHnXOzgcf9/zGz+cClwNH+Or80s1R/nV8BVwCz/Vtom58Cap1zs4AbgR/62yoCrgZOAk4Erg7vKBEREU9lQytFYzJISRn82MmS3EzNQiISMA+8vJuNu/dz5bI5ZKWn9r9ClF11/lwKc9L51n0bkmpKvmS0els1s0tzKc0bXA6jnsqmFLC7voW365MnfFxEoLymGYApRcMbQgLeMBINIQGcc08CNT2KLwRu9/++HVgeVn6nc67VOfcWsBU40cwmAPnOuTXOOQf8rsc6oW3dAyz1ozOWAY8652qcc7XAoxzekSIiMupVNbYOafgIeHkzghqBITIatbR3csPDmzl6Yj4XLJiYkDqMzUnn2++ZzysV9fx+zfaE1GE0aOvo4oXtNcPKfxFSNrUAgJfKFYUhkkzKa70pVIeaxDdcaX6mIjD6MN45twfAvy/1yycB5WHLVfhlk/y/e5Yfso5zrgOoB8b1sS0REQlT1dhKcd7QOjBKcrOobWqnvbMryrUSkaH43Zrt7Kpr5lvvmjekqKpouWDBRE6fXcyPH3mDPfXNCavHSPZKRR1NbZ0sObJ42NuaPzGfjNQU5cEQSTLlNV4HRjRmmirNy1IOjCGIdKZ1fZQPdZ1Dd2p2hZmtNbO1lZWVA6qoiMhIUdkw9AiMUNKnan8mExFJnLqmNv5n5VbOnFPCqbOG/6N2OMyMa5cfS3tnF9954LWE1mWkWr2tGjM4eebwpz7NTEvl6En56sAQSTLltU3kZ6UxNjt92Nsq9fOaeQMegi/eHRh7/WEh+Pf7/PIKYErYcpOB3X755Ajlh6xjZmnAWLwhK71t6zDOuZucc4udc4tLSkqG8bRERJKLc46qxrZBT6EaUpzrrRfEYSQ/uOhYfnDRsYmuhkjc/O8TW2lo7eCqd85NdFUAmDouh6+cM5uHNr7No6/tTXR1RpzV26o4emJ+1GaZKZtSyCu76hRRJ9KHoLUtymuaoxJ9Ad5FqbbOLuqb26OyvViLdwfGA0BoVpDLgL+GlV/qzywyAy9Z5/P+MJMGMzvZz2/x8R7rhLZ1MbDSz5PxMHCemRX6yTvP88tERMS3v7mDts6uYUdgVDYGL+nTkSW5HFmSm+hqiMRFeU0Tt6/ewcULJzP3iPxEV6fbp0+fyZzxeVz911c50NqR6OqMGC3tnby4o45TojB8JKRsagEt7V1s2tMQtW2KjDRBa1uU1zYNewaSkO6pVAN4USqSWE6j+idgDTDHzCrM7FPA9cC5ZrYFONf/H+fcRuBu4DXgIeALzrlOf1OfA27GS+y5DXjQL78FGGdmW4Gv4c9o4pyrAb4HvODfvuuXiYiIr9KfQaRkqDkw/PWqGoI3hOSx1/bymK76yijx349sxgy+dt5Ria7KIdJTU/jBRcewu76Fnzz6RqKrM2Ks21FLW2fXsKdPDRdK5LleiTxFehWktkVXl6OitjkqM5AA3bMZBTGqNpK0WG3YOfehXh5a2svy1wLXRihfCxwTobwF+EAv27oVuHXAlRURGWVCU6AWD3UWktxQBEbwTnb/99SbAJwzf3yCayISW6/uquf+l3bz+TOPZMLY6DRko2nRtCI+fNJUbnn6LR54eTdVDa1MLMjmymVzWF6m/OpDsXpbFWkpxgnTh5//ImRSQTYleZms31nHx5dEbbMiI0qQ2haVja20dXRFbQhJaX4oAiN4UbWRxKwDQ0REgivUyz7UCIys9FTystKSprdeZKRxzvGDf75O0ZgMPnvmkYmuTq+OmeQNawl9V+yqa2bFvRsA1IkxBKu3VbNgSgG5mdFrwpsZZVMKWL9TERgiyaB7BpIoDSEpDQ0hSZKZSIIyC4mIiMTRcCMwwOv8CGIEhshosOqNSlZvq+bLZ88iP2v4Wehj5X9XbjusrLm9kxse3pyA2iS3hpZ2Xqmo55QoDh8JKZtayPbqJmoOBG9YoIgcqrw2NIVqdCLvcjPTyE5PVQ4MEREJrsqGVtJSjIJhTL9VnJupCAyRBOjsclz/z01MG5fDh0+alujq9Gl3XfOgyqV3L2yvobPLRTX/RUgoD8ZLyoMhEngVNd735+QoRWCYGaX5merAEBGR4KpqbGVcbgYpKTbkbZTkZVKVJCc7kZHkLy9WsHlvA99YNpeMtGA35SYWRL5C2Fu59G711moy0lJYOLUw6ts+bvJYUlOM9Tvror5tEYmu8tomSvIyyUpPjdo2S/My2bdfOTBERCSgKhtahzV8BKAkN5MnAziE5MZLjk90FURiprmtk5888gYLphTwrmOPSHR1+nXlsjmsuHcDze2d3WWZaSlcuWxOAmuVnFZvq2bR1MKo/mgJyclIY+4ReerAEOlFkNoW5TXNTCmMbidwaV4Wr+/ZH9Vtxoo6MERERqGqxrYhJ/AMKcnLpKGlg5b2zpg0qIdKV3ZlJLp//S5ueHgzu/yhFx9YPBmzoUdQxUsoUecND2/uHjYyb0KeEngOUu2BNl7bs59/Pzd20+WWTS3g/vW76exypA4jOk9kJApS26K8tolF06IbiVWSl8m/3gjeRalIgh13KCIiMVHVGJ0IDAjevOF/e3k3f3t5d6KrIQFiZqlmtt7M/u7/X2Rmj5rZFv++MGzZFWa21cw2m9mysPJFZrbBf+znFsfeg/vX72LFvRu6Oy8Abn7qLe5fvyteVRiW5WWTeOaqs3nr+nfzpaWzeam8XjNeDNKzb1YDcMqs6Oe/CCmbUkhjawfbKhtjtg+RZBWUtkVHZxd76luiNgNJSGl+Jo2tHTS1dUR1u7GgDgwRkVHGOUdVY2tUIjDg4IwmQfGHZ3fwh2d3JLoaEixfAV4P+/8q4HHn3Gzgcf9/zGw+cClwNHA+8EszC4UX/Qq4Apjt386PT9W96IXwIRiQvDN5XHHGTIpzM7juwU045xJdnaSxels1ORmpHDe5IGb7CCXyVOeSyOGC0rbYU99CZ5eL2gwkIaV5WUByTKWqDgwRkVGmvrmd9k437AiM4oBGYIiEM7PJwLuBm8OKLwRu9/++HVgeVn6nc67VOfcWsBU40cwmAPnOuTXO+9X9u7B1Ym4kzeSRm5nGV845iuffquHx1/clujpJY/W2Kk6cUUR6auya7jOKxzA2O115MEQCrLzGn0I1yhEYoYtSyTATiTowRERGmVCHQ3FuxrC2EzrZVQYsAkOkh58C3wC6wsrGO+f2APj3pX75JKA8bLkKv2yS/3fP8rgYaTN5XHrCFGYWj+G6B1+no7Or/xVGub37W9hWeYBTYjB9ajgzo2xqgTowRAKsvNbvwCiK8hCS7g6M4M9Eog4MEZFRJtThMNwhJOP8DpCqhrZh10kkFszsPcA+59y6ga4Socz1UR5pn1eY2VozW1tZWTnA3fbtymVzyO6RKDc7PTVpZ/JIT03hm++cy7bKA9y9tqL/FUa5Ndv8/BdHFsd8X2VTCnljXwMNLe0x35eIDF55TTOpKcaEsVlR3W53B4aGkIiISNBUNXodDiXDHEKSnppCYU46lY3B762XUetU4AIz2w7cCZxtZn8A9vrDQvDvQ2MZKoApYetPBnb75ZMjlB/GOXeTc26xc25xSUlJVJ7E8rJJXHfRsUwqyMaASQXZXHfRsUk9k8d588ezeFohNz72Bgdag580LpFWb6tibHY68ybkx3xfZVMLcA5eLq+P+b5EZPDKa5uYMDaLtCgPJyvMySAtxZIiqlbTqIqIjDKhISTDjcAIbSNoOTB+9dFFia6CBIRzbgWwAsDMzgS+7pz7qJndAFwGXO/f/9Vf5QHgj2b2E2AiXrLO551znWbWYGYnA88BHwd+Ec/nsrxsUlJ3WPRkZqx41zze/6vV3PzUW3zlnNmJrlJgrd5Wzckzi+IytemCKQWAl8jztNmxj/gQSRZBaVuU1zRFPf8FQEqKUZKXqQgMEREJnqrGVtJTjbHZ6cPeVkleZndER1AUjcmgaMzw8nvIiHc9cK6ZbQHO9f/HObcRuBt4DXgI+IJzLjT9x+fwEoFuBbYBD8a70iPNommFvPOYI/jNk9sC1xEaFOU1TVTUNsdl+AjA2Ox0ZpXmsr68Li77E0kWQWlblNc2R30GkpDSvEzlwBARkeCpbGilODcTs+FfzSvODV4Exp/XlvPnteX9LyijinNulXPuPf7f1c65pc652f59Tdhy1zrnjnTOzXHOPRhWvtY5d4z/2Bed5gCNim+cP5e2ji5+9vgbia5KIK3eVgUQ8wSe4cqmFLB+Z62muRUJE4S2RUt7J5UNrTGJwAAoycsKXJsuEnVgiIiMMlWNrcOeQjWkJIAdGPesq+CedUoMKJIMZhSP4SMnTeVPz5ezdV9joqsTOKu3VVOcm8ms0ty47bNsaiG1Te3sqG6K2z5Fgi4IbYuKGM1AElKan6lpVEVEJHi8CIzohEGW5GXS3N6pJHwiMmRfWjqb7PRUfvTQpkRXJVCcc6zeVs0pR46LSsTcQJVNLQBgfXlt3PYpIv0rr2kGiOkQkpoDbbR1BHt6a3VgiIiMMlWNrVFJ4Al0R3IELQpDRJJHcW4mn33HTB55bS8vbK/pf4VRYltlI5UNrXEdPgJw1Pg8xmSksn5nXVz3KyJ9Kw9FYMRoCElpnjc1a1XAZyJRB4aIyCjS1eWobmyL3hASvyMkGabdEpHg+tRpMxmfn8kP/vm6ci/4Vm+rBohbAs+Q1BRjwZQCdWCIBEx5TROZaSlRuwjVU6m/3aAPI1EHhojIKFLX3E5Hl4vayS+0naqAn+xEJNiyM1L52rlHsX5nHQ+9+naiqxMIq7dWM6kgO2bh4n0pm1rA63v209zW2f/CIhIX5TXNTC7MjtmQstJ8vwNjf7BnIum3A8PMPmBmef7f/2lm95rZwthXTUREoi0UFhitCIzuISQBisC47RMnctsnTkx0NSTK1B4Z+S5eNIWjxufyw4c2BX4Mdqx1dTmefSv++S9CyqYU0tHleHV3fdz3LRJEQWhblNc2xSyBJxwcQjISIjC+7ZxrMLPTgGXA7cCvYlstERGJhVCuimh1YBSNySDFgpUDIzsjleyM1ERXQ6JP7ZERLjXFWPHOeWyvbuJPz+9MdHUS6vW391PX1M4ps+Kb/yLk+FAiz51K5CkCwWhblNc0xSz/BcC43AzMRkYHRih27N3Ar5xzfwWik75eRETiKhSBEa0hJKkpxrjczEAlfPr9mu38fs32RFdDok/tkVHgzDklLJk5jp89voWGlvZEVydh1vj5L5bMjG/+i5Di3EymFuUoD4aIL9Fti/rmdva3dMR0SFl6agpFORlUNiT5EBJgl5n9Bvgg8E8zyxzgeiIiEjChSImSKEVggNfQDVIExt9f2cPfX9mT6GpI9Kk9MgqYGSveNZeaA2385l9vJro6CbN6WzUzS8ZwxNishNWhbKoSeYqEJLptUV4T2xlIQkryMtm3PzhtukgGcuL/IPAwcL5zrg4oAq6MZaVERCQ2KhtbyUhNIT87LWrbLMkLVgeGjFhqj4wSx00u4IIFE7n56Td5uz7YVwJjob2zi+ferI779Kk9lU0p4O39Leypb05oPUQEKkJTqMYwBwZAaX5WoPKaRdJvB4ZzrgnYB5zmF3UAW2JZKRERiY2qhjaKczOimhSuJDeTqsa2qG1PJBK1R0aXK5fNoasLbnz0jURXJe427KrnQFtn3KdP7alsaiEAL+6oS2g9RMSbgQRiH4FROhIiMMzsauCbwAq/KB34QywrJSIisVHZ2Br1+cOL8zKobGjFORfV7YqEU3tkdJlSlMPHl0zjz+vK2fx2Q6KrE1eh/Bcnz0xsBMa8CflkpKUokadIAJTXNpGXlcbYnPSY7qc0z8tr1tUV3DbdQIaQvA+4ADgA4JzbDeQNZ6dm9m9mttHMXjWzP5lZlpkVmdmjZrbFvy8MW36FmW01s81mtiysfJGZbfAf+7n5lxTNLNPM7vLLnzOz6cOpr4jISFHV0Bq1GUhCSnIzaevsYn9zR1S3K9JD1NsjEmxfPHsWuZlpXP/g64muSlyt3lbFvAn5FI1JbI7ajLQUjp00lvXldQmth4jEfgaSkNK8TDq6HDVNwY2sHUgHRpvzLqs5ADMbM5wdmtkk4MvAYufcMUAqcClwFfC4c2428Lj/P2Y233/8aOB84JdmFprD5lfAFcBs/3a+X/4poNY5Nwu4EfjhcOosIjJSVDbGoAPDj+gIypjJuz6zhLs+syTR1ZDoi2p7RIKvICeDL5w1iyc2V7J6a1WiqxMXLe2drN1em/D8FyFlUwrYsKueto6uRFdFJKES3bYor22O6QwkIaX5XuLgIA8jGUgHxt1+1u8CM/s08Bjwf8PcbxqQbWZpQA6wG7gQb053/Pvl/t8XAnc651qdc28BW4ETzWwCkO+cW+M3aH7XY53Qtu4BloaiM0RERquuLkfNgbaoDyEJzWiiRJ4SY7Foj0jAXXbKdCYVZHPdg5sCHdIcLet31tHa0RWcDoyphbR1dPH6nv2JrorIqOWco6I2fhEYAPsCPJXqQJJ4/hivE+AvwBzgv5xzvxjqDp1zu4AfAzuBPUC9c+4RYLxzbo+/zB6g1F9lElAetokKv2yS/3fP8kPWcc51APVAMM4EIiIJUtvURmeXozg3umHJQYvAuOnJbdz05LZEV0OiLNrtEUkOWempfH3ZUWzYVc/fXtmd6OrE3JptVaSmGCfOKEp0VQBYOK0AQHkwZNRLZNuisrGVlvaumM9AAlCa50dgBPii1IDmT3fOPeqcu9I593Xn3KPD2aGf2+JCYAYwERhjZh/ta5VIVeqjvK91etblCjNba2ZrKysr+664iEiSC3UwlPgnp2gJDUmpCsjJ7vHX9/H46/sSXQ2JgWi2RyR5XLhgEvMn5HPDw5tp7ehMdHViavW2ao6dNJa8rNgm6huoCWOzOSI/S3kwZNRLZNuiewaSuAwhCX5Uba8dGGbWYGb7I9wazGw4cWTnAG855yqdc+3AvcApwF5/WAj+fegIqQCmhK0/GW/ISYX/d8/yQ9bxh6mMBWp6VsQ5d5NzbrFzbnFJSckwnpKISPBVNXgJmaIdgTE2O530VAtMBIaMLDFsj0iSSEkxvvWueVTUNvP7NTsSXZ2YOdDawUvldYEZPhJSNrWA9TvrEl0NkVGrorYJiP0UquBFveVlpbFvfxIOIXHO5Tnn8iPc8pxz+cPY507gZDPL8fNSLAVeBx4ALvOXuQz4q//3A8Cl/swiM/CSdT7vDzNpMLOT/e18vMc6oW1dDKx0mt9PREa5ykbvZBTtHBgpKUZxbmage+slecWwPSJJ5LTZxZxxVAm/WLmV+qb2RFcnJl7YXkNHl+OUI4sTXZVDlE0tYGdNE1XqpBZJiPIarwNjchw6MMBrJyb9EBIAMys1s6mh21B36Jx7Dm8M64vABr8ONwHXA+ea2RbgXP9/nHMbgbuB14CHgC8450Lxg58DbsZL7LkNeNAvvwUYZ2Zbga/hz2giIjKadUdgRLkDA7xhJGrcSjxEqz0iyWfFO+eyv6WdX67amuiqxMSabdVkpKawaFphoqtyiLKpXn1eUhSGSEKU1zRTnJtJdkZq/wtHQWnAOzDS+lvAzC4A/hsvX8U+YBpexMTRQ92pc+5q4Ooexa140RiRlr8WuDZC+VrgmAjlLcAHhlo/EZGRqLKxlYy0FPIy+/3qH7SSvEz2BiTcMCs9Pid4ia9YtEckucybkM/7F07mt6u387El0+J2NTJeVm+r5vipBXH7kTJQx0wcS1qKsb68lnPmj090dUQSIpFti/LaprjkvwgpzctifXlwE/cOJALje8DJwBvOuRl4nQzPxLRWIiISdVUNrZTkZhKLWaVLAjSE5PZPnsjtnzwx0dWQ6FN7RPjauUdhwE8eeSPRVYmq+qZ2Xt1dH7j8FwDZGanMm5CvPBgyqiWybVEepylUQ0rzMtm3v5WgZmAYSAdGu3OuGkgxsxTn3BPA8bGtloiIRFtlY2tMho8AFOdlUH2gja6uYJ7sZERQe0SYWJDNJ0+bwX0v7eLVXfUx39/963dx6vUrmXHVPzj1+pXcv35XTPbz7FvVOEfg8l+ElE0t4OXyOjrj9B0fr9ddJOg6OrvYXdcS3wiM/ExaO7poaO2I2z4HYyAdGHVmlgs8CdxhZj8DgvlsRESkV5V+BEYslORm0tnlqG1qi8n2B+Pnj2/h549vSXQ1JPrUHhEAPnfmkRRkp3Pdg6/H9Arh/et3seLeDeyqa8YBu+qaWXHvhpj8mF6zrZqs9BSOn1IQ9W1HQ9nUAg60dfLG3oaY7yuer7vIQCWqbbGnvoXOLhfnCIwsAPbtD0ZkbU8D6cC4EGgC/g0vieY24L2xrJSIiERfVWMbJXnRnUI1pMQ/2QVhKtVntlbxzNaqRFdDok/tEQEgPyudL509m2e2VvPklth81nfXNfOdv22kub3zkPLm9s6YdJys3lbFCdOLyEgbcH79uCqb4iXyjMcwkhse3hzxdb/h4c0x37dIbxLVtigPTaFaFN8hJAD7GoKR26ynAWdyc851mNkaYC6geddFRJJIZ5ej5kArxTGKwCjO9TpGqhra4IiY7EIEUHtEPB89eRq3rd7Odf98ndNmFZOaMvTcPu2dXWza08DaHTWs21HLuh217KnvveG+d38rS65byaJphd23+RPzSU8dWudDZUMrb+xt5H1lk4f6FGJu2rgcCnPSWb+zlg+fFNvJf3bXNQ+qXGQkq6jxjvu4RmDke23FoOQ262kgHRhPAqebWSHwOLAWuAT4SCwrJiIi0VNzoI0u580WEguh7VY2BrO3XkYEtUekW0ZaCt84fw5f/ON67lu/i4sXDfzHf31TOy/u9Doq1u6o4eXy+u4r/hPHZrF4ehGLphbwv6u2RWzAj81O58QZRazbUcs/NuwBICs9hQWTC1g0rZDF0wtZOLWQgpyBRbytebMaIJAJPEPMjLKphawvr4vpft7Y24AZRApwOWJsVkz3LRJE5bVNpBhMKIjf8V8S8CEkA+nAMOdck5l9CviFc+5HZrY+1hUTEZHoqfKHdsQqAqO7AyOgvfUyIqg9Iod497ET+L/Jb/K9v2/kJ49sZk99CxMLsrly2RyWl00CwDnH9uom1m6v4cWdtazdXsuWfY0ApKYYR0/M55ITpnRHUkwsOJgoryAngxX3bjhkOEN2eirfueDo7u2/Xd/S3RHy4o5abnryTX65yvv1Pas0l0VT/SiN6YXMLB5zyCxQ96/fxQ0Pb2ZXXTMGbNvXwIKA5sAAKJtSwMpN+6hvbmdsdnrUt79uRw2fvG0tYzJSaet0tHZ0HfJ4WopR3djKuBidx0SCqLymiQljs4cc4TUU+VlpZKalJPUQEjOzJXhXOD41iPVERCQgQh0LsYrAyM30TnZVjYlP4lk4wKueknTUHpFDmBmnzy7m5Yp66pu9fK676pr5xl9e4fHX99Lc3sWLO2upOeB9L+VnpbFoWiEXHj+RRdOKWDBlLDkZvR9CoU6KGx7ezO665sM6R8CLCnj3cRN493ETAGhu6+TlirruoSgPbXybu9aWA1CYk86iaYUsnFZIU2sHNz/9Fi3t3o90B/zH/RtJSUk5ZPtBsnCalwfj5fI6zjiqJKrbfmLTPj53xzqOyM/i9586iXU7ag953d95zBH8/tkdfODXa/jdp05kchzD6UUgcW2L8trmuM5AAt53a2l+JvsCelFqICf+rwArgPuccxvNbCbwRGyrJSIi0RTrCAwzoyQvMxARGL/+2KJEV0FiQ+0ROcx963cfVtbW0cXfXtnDzOIxnD23lMV+dMWRJbmkDDJXxvKySYPqUMjOSOXkmeM4eaY3HKSry/FmVWN3h8baHbU89vq+iOuGElUGtQPjuMljMfMSeUazA+PeFyu48p5XmDchj9s+cSLFuZlMKco57HVYdswRfOq2F3j/r1bzu0+exJwj8qJWB5H+JKptUV7TxDui3GE4EKV5Wck7hMQ59yTeuNPQ/28CX45lpUREJLpiHYER2nYQOjBkZFJ7RCLpLbGjASu/fmZc6xJJSooxqzSPWaV5XHKCl/yy5kAbC7/3aMTlg5yoMi8rnaNK81hfXhu1bd781Jt8/x+vc8qR4/jNxxaRl9X70JQTphdx92eXcNmtz/OBX6/m1stPYPH0oqjVRSRoWto72dfQGtcZSEJK8zLjMm3yUARzriYREYmqqsZWstJTGJORGrN9FOdmdkd6JNIPH9rEDx/alOhqiEgchOesGEh5EBSNyWBSEtYboGxqAet31g17GlnnHNc/uInv/+N13nXsEfz2Eyf02XkRMveIfO757CmMy83ko7c8x8pNe4dVD5GBSkTboqLWn4EkzkNIwLsoFdQhJOrAEBEZBSobvClUwxPIRVtQIjBe3FHLizuid4VQRILrymVzyE4/tGM2Oz2VK5fNSVCNBiZZ6102tYD65nbeqjow5G10dHbxzb+8wq//tY0PnzSVX3xoIZlpA+9cn1KUw58/u4TZpXl8+nfr+Mu6iiHXRWSgEtG2KK9tAuI7hWpIaV4mDS0dtIQlMQ6KfjswzOzUgZSJiEhwVTW2xXT4CEBJbiY1TW10dHb1v7DIIKk9IpEsL5vEdRcdy6SCbAyYVJDNdRcdG9g8EiHJWu+yqV4iz/U764a0fkt7J5/9w4vcvbaCLy+dzbXLjyF1kHlJwIv4+9MVJ3PyzCL+/c8v839Pvjmk+ogEWUWN14GRiKS1pQGeSnUgSTx/ASwcQJmIiARUVWPsx1AW52XinDe+uzQ/fvOVy6ih9ohENNhEm0GRjPWeVZJLXmYa68tref+iyYNat765nU/fvpYXdtTwnQuO5rJTpg+rLrmZadx6+Ql87a6Xufafr1PV2MpV75wb00hDkXgqr20mIy2F0hhfgIqkJN/b576GFqaOC9asP712YPhTlZ0ClJjZ18IeygdiN4haRESirrKhtXsKvFgpyQ2d7FrVgSFRo/aISHCkpBgLphQMOgJj3/4WPn7r82yrbORnl5ZxwYKJUalPZloqP/9QGYVj0vnNk29SfaCN6y86lrRUjZKX5Fde08TkguxBz54UDaFOkyAMDe6prwiMDCDXXyZ8nqL9wMWxrJSIiERPR2cXNU1tMZtCNSQ0RKUywYk8J4xV58kIo/aISICUTS3gl6u20dTWQU5G/8Hcb1Ud4OO3Pkd1Yxu3Xn4Cp8+O7pSQqSnG9y48huLcTH762Bbqmtr4xYcWkh3DpNUy+iSibVFe28TkBMxAAmFDSJKpA8M59y/gX2Z2m3NuRxzrJCIiUVRzoA3noCQ3I6b7CUVgVCX4ZPfTS8sSun+JLrVHRIKlbGoBnV2OVyrqOXnmuD6XfXVXPZf/9nk6uxx/+vTJLJhSEJM6mRlfPecoxo3J4L8e2MjHb32Omz9+AmNz+p/ZRGQgEtG2KK9pZsHkgrjvF2DcmAxSU4x9DS0J2X9f+hpC8lPn3FeB/zGzw+ZKcs5dEMuKiYhIdIQiImKdxLM4L+OQ/YlEg9ojIsFy/JSDiTz76sBYva2KK363jrHZ6fzuUydyZEluzOv2sSXTKRyTwb/d9RKX3LSG2z95IuM1pFGS0P6Wduqb22Oev6w3KSlGcW5G0iXx/L1//+N4VERERGIjNH4x1kNIcjLSyM1MS/h4ye/8bSMAV7/36ITWQ6JG7RGRACkak8H0cTms39n7lJIPbtjDV+58ienFOfzukydxRBzD799z3EQKsjP4zO/X8v5freZ3nzyRmXHoPJGRLd5ti/KaxE2hGlKal5V0Q0jW+ff/il91REQk2qoa24DYR2AAFOdmdO8vUV7bvT+h+5foUntEJHgWTi3kqa1VOOcOm/Xjjud28J/3v0rZlAJuvfwECnJiO3wxktNmF/OnK07m8t++wAd+vYbbPnEix04eG/d6yMgR77ZFeU0zAFOKsuO633CleZnsrg/eEJJ+U/Sa2alm9qiZvWFmb5rZW2amyZZFRJJEVWN8IjDA6ySpDOB4SUl+ao+IBEfZ1AIqG1rZVdfcXeac4xePb+E/7nuVM48q4Y7/d3JCOi9CjptcwD2fXUJWeiqX3rSGZ7ZWJawuIoNVURuACIz8YLbpBjLH0C3AT4DTgBOAxf69iIgkgcqGVnIyUhmT2X+2+OHyOjCCF24oI4LaIyIBUTb1YB4MgK4uxzUPbOS/H32Di8omcdPHFwdiFpCZJbnc+/lTmFyYwyd++wL/eGVPoqskMiDlNU3kZqZRkMBEtCV5WVQfaKOjsythdYhkIK3ZeufcgzGviYiIxERVY2tcoi/Ai/J4prE6LvuSUUftEZGA2Py2F07/pT+t57p/vs74/CzWl9fx/06bwbfeNY+UFOtnC/EzPj+Luz+zhE/d/gJf/NOLPLF5Mmu2VbO7rpmJBdlcuWwOy8smJbqaIocor21mcmH2YUO04qk0LxPnvKHI8cxj05+BdGA8YWY3APcC3ZfVnHMvxqxWIiISNZUNrRTHeArVkJLcTOqb22nt6CQzLTFX32aWjEnIfiXm1B4RCYD71+/iP+/f2P3/7voWdte38N7jJvAf756X0B9cvRmbk87vP3US7//VM9yzrqK7fFddMyvu3QCgTgzpU7zbFuU1TUwvTmx7JpQ7bV9DS9J1YJzk3y8OK3PA2dGvjoiIRFtVYysz4nQSDJ3sqhrbmFSQmMRT1110XEL2KzGn9ohIANzw8Gaa2zsPK39xZ10gOy9CsjNSqWtuP6y8ub2TGx7erA4M6VM82xbOOSpqmzl9dknc9hlJaagDI2BTqfbbgeGcOyseFRERkdioamzjhOlFcdlXaKhKVUNrwjowZGQaSnvEzLKAJ4FMvDbPPc65q82sCLgLmA5sBz7onKv111kBfAroBL7snHvYL18E3AZkA/8EvuKcc8N7ViLJZ3dY4s6BlAfJnrrICQmToe4yelQ1ttHc3pnQGUgASvO9qIugTaXabweGmf1XpHLn3HejXx0REYmm9s4uag60xWUKVTgYgZHIRJ4r7n0FUCTGSDPE9kgrcLZzrtHM0oGnzexB4CLgcefc9WZ2FXAV8E0zmw9cChwNTAQeM7OjnHOdwK+AK4Bn8TowzgeUk0NGnYkF2YfMPhJeHnTJXHdJrHi2LYIwAwl4w4LBG0ISJAOZheRA2K0TeCfeFQsREQm4mgNtQHymUIWwDozGxHVgvFl5gDcrDyRs/xIzg26POE+j/2+6f3PAhcDtfvntwHL/7wuBO51zrc65t4CtwIlmNgHId86t8aMufhe2jsiocuWyOWSnH5rjKDs9lSuXzUlQjQYuUt3TUy0p6i6JFc+2RXmt18k2pSixHRgZaSkU5qQHbna5gQwh+e/w/83sx8ADw9mpmRUANwPH4DUkPglsJkrhnGaWide4WARUA5c457YPp84iIskodNKJVwfGOD9ZaFXATnaS/IbaHjGzVGAdMAv4X+fcc2Y23jm3x9/uHjMr9RefhBdhEVLhl7X7f/csFxl1Qrkibnh4c9LN5NGz7umpKWSmGefOH5/gmokcVF7jRWBMLkx8ZFBpXlbyDSGJIAeYOcz9/gx4yDl3sZll+Nv8FtEL5/wUUOucm2VmlwI/BC4ZZp1FRJJOKBIiXkNIMtNSGZudntAIDBk1BtQe8dsLx/sXT+4zs2P6WDxSBkLXR/nhGzC7Aq9twtSpU/urnkhSWl42KSk6LCIJr/u6HbW8/1erufmpt/jKObMTXDMRT0VtE+PGZDAmcyg/1aOrND8zcB0Y/Q4hMbMNZvaKf9uIFynxs6Hu0MzygTOAWwCcc23OuTqiG84Zvq17gKUW5LTIIiIxEorAKIlTBAZ4nSVBCzeU5Dfc9ojf1liFd7Fjr9+OwL/f5y9WAUwJW20ysNsvnxyhPNJ+bnLOLXbOLS4pSWwGeRHp26JphbzzmCP4zZPbdN6SwCivaWZygoePhJTkZVK5P/lyYLwHeK9/Ow+Y6Jz7n2HscyZQCfzWzNab2c1mNgY4JJwTCA/nLA9bPxS2OYnewzm713HOdQD1wLhh1FlEJClV+ZEQxXkZcdtncW5G934TYf7EfOZPzE/Y/iVmBt0eMbMSP/ICM8sGzgE24Q09ucxf7DLgr/7fDwCXmlmmmc0AZgPP++2SBjM72b8g8vGwdUQkiV25bA5tHV387PE3El0VCbB4ti3Ka5uYEoDhI+ANIalsbCVIk24NJAfGjhjscyHwJX8c6s/whov0ZijhnAMK9VSYp4iMdFUNbYzJSCUnI35hiCV5WWyoqIvb/nq6+r1HJ2zfEjtDbI9MAG7382CkAHc75/5uZmuAu83sU8BO4AP+Pjaa2d3Aa0AH8AV/CArA5ziYd+tBNAOJyIgwsySXD580lTue28knTp3BkSW5ia6SBFC82hadXY7ddc2869gJcdlff0rzMmnvdNQ2tVM0Jn4Xw/oykAiMaKsAKpxzz/n/34PXoRHNcM7udcwsDRgL1PSsiMI8RWSkq2xsjVv+i5CSXA0hkWBwzr3inCtzzh3nnDsmNOWqc67aObfUOTfbv68JW+da59yRzrk5zrkHw8rX+ts40jn3RReky1EiMixfXjqb7PRUfvjgpkRXRUa5t/e30N7pEj6FakhpfvCmUo17B4Zz7m2g3MxC8xUtxbvSEc1wzvBtXQysVENDguz+9bs49fqVzLjqH5x6/UruX78r0VWSEaKqoTVuM5CEFOdlcKCtk6a2jrjuN+Srd67nq3euT8i+RUQk+RTnZvLZd8zkkdf28sL2w655isStbRGagWRKUXCGkADs2x+cC1OJiMAA+BJwh5m9AhwP/AC4HjjXzLYA5/r/45zbCITCOR/i8HDOm/ESe27jYDjnLcA4M9sKfI2+h6iIJNT963ex4t4N7KprxgG76ppZce8GdWJIVFQ2xr8DI5QwtKqhLa77DdlT38Ke+uBcKRARkeD71GkzGZ+fyQ/++XqgxvtLMMSrbdHdgRGQCIxQFG+QZiJJyNwszrmXgMURHlray/LXAtdGKF8LHDYdmnOuBX88q0jQ3fDwZprbOw8pa27v5IaHNyftFGUSHFWNrSyZGd8cxqGTXWVjC1PHBeMELCIi0pfsjFS+du5RfPMvG3jo1bd5Z0ByEMjoUl7bjBlMLAhKBIaGkIhID7vrmgdVLjJQbR1d1DW1x38Iib+/ygRFYIiIiAzF+xdO5qjxufzwoU20d3YlujoyClXUNDEhP4uMtGD8TB+TmcaYjFQNIRGRg3rrYQ1Kz6skr+oD3skm3kk8S7sjMIJzshMREelPWmoKV71zLturm/jjczsTXZ0RRfneBqa8tonJRcGKXi3NzwpUcnZ1YIgk2JXL5pDZo5c1Oz2VK5fN6WUNkYEJ5aAozo3vtFdFYzIwI2Enu4XTClk4rTAh+xYRkeR21pxSTp5ZxM8e30JDS3uiqzMijIR8b/FqW5TXNAcm/0VISV6mhpCIyEHLyyaxbP74Q8q+/Z55yn8hw1bZ6J1siuMcgZGWmkJRTgZVCYrA+Ob5c/nm+XMTsm8REUluZsa33jWPmgNt/OZfbya6OiNCX/nekkU82hatHZ3sbWgJzAwkIaV5mYrAEJFD7WtsZe4Redzz2SWAdwVbZLhCERglcc6BAV5vfZBOdiIiIgN13OQCLlgwkZuffpO3NavVsCnf28Dsqm3GueDMQBJSmpcVqFlI1IEhkmD7W9pZu72Ws+aWsmBKAbmZaTy1pSrR1ZIRIJSDIt45MEL7TFQHxmd/v47P/n5dQvYtIiIjw5XL5tDZ5bjx0TcSXZWkNxLyvcWjbVFe63XoTAlcDoxMmto6aWztSHRVAHVgiCTcM1uq6OhynDWnlPTUFE6eWcQzW9WBIcNX2dBKXmYaWempcd93cW5mwoaQ1Da1UdukGVBERGTophTl8PEl0/nzunI2v92Q6OoktXPmlR5Wlmz53uLRtiivaQII5BASgH37gxGNpA4MkQR7YvM+8rLSWDi1AIBTZxWzvbqp+0tMZKiqGlvjnv8iJBSB4ZxLyP5FRESG64tnzWJMZhrXP/h6oquStMprmrh3/S6mFWUzsSALADP4/vKjle+th/LaJjJSUxifl5Xoqhyi1K9PUIaRqANDJIGcczyxuZIzjiohLdX7OJ4+uxiApxWFIcNU2dCakPwX4OXdaO3ooiEg4YYiIiKDVTgmgy+cNYsnNleyWu2yQWvv7OLLd64HB3/4fyez+qql/OZji3AOJowNVpRBEFTUNDOpMJuUFEt0VQ5Rmu9HYKgDQ0Q27t5PZUMrZ805GFp3ZEku4/Mz1YEhw+ZFYCQmIWxov1UBOdmJiIgMxeWnTGdSQTbXPbiJri5FFQ7GjY++wfqddfzgomO78zqcMbuErPQUHnltb4JrFzzltU1MLgxex46GkIhIt1Wb9wHwjqNKusvMjNNmlbB6a5VOlDIslQ2tFCcsAiOruw7xduqsYk6dVRz3/YqIyMiTlZ7Kv593FBt21fO3V3YnujpJ45mtVfzqX9u4ZPEU3rtgYnd5dkYqp88u4ZGNbyfVMNN4tC3Ka5oCl8ATYGx2OhmpKYGZXU4dGCIJ9MTmSo6bPPawWSJOn11MbVM7r+3Zn6CaSbJr7ehkf0tH4oaQ+Md0ZQISeX556Wy+vHR23PcrIiIj0/LjJzFvQj43PLyZ1o7ORFcn8KoaW/nqXS8xs3gMV18w/7DHz5s/nt31Lby6K3naubFuWzS2dlDb1B64KVTBu7hakpepISQio13tgTbW76zlzDmHZ2Y+ZdY4AE2nKkNW1ehlyk5UEs/iXA0hERGRkSElxfjWu+ZSUdvM79fsSHR1Aq2ry/H1P79MfXM7//PhheRkpB22zNJ540kxeOS1txNQw2AK6gwkIV4HhoaQSADdv34Xp16/khlX/YNTr1/J/et3JbpKI9aTWyrpcnDWnJLDHivNy2LuEXmaTlWGLNRxkKgIjMKcDFJTLCERGJfd+jyX3fp83PcrIiIj1+mzSzh9djG/WLmV+qb2RFcnsG595i1Wba7kP989j3kT8iMuUzQmgxOmF/HIxuTJgxHrtkV3B0YAIzDAy4Oxb38wLkqpA0O63b9+Fyvu3cCuumYcsKuumRX3blAnRoys2lxJ0ZgMjptcEPHxU2cV8/z2GlraFaoog1fldxwkKgIjJcUozs1IyHjJlvZOfW5ERCTqVrxzHvtb2vnlqq2Jrkogbaio54cPbeK8+eP52MnT+lz2vKOPYPPeBrZXHYhT7YYn1m2L8tpmgEDmwABvJhINIZHAueHhzTT3+GA2t3dyw8ObE1Sjkauzy/GvNyp5x1ElpPYyVdJps4tp6+jihe01ca6djAShjoPQUI5EKM7N7B7KIiIikuzmT8znorLJ/Hb1dipqmxJdnUBpbO3gS396keLcTH508XGY9T0V6HnzxwPwqGYjAbwIjDEZqRTmpCe6KhGV5mVR39x+eCfOnj3wjnfA2/EbDqQODOm2u655UOUydK9U1FFzoI0zIwwfCTlpRhHpqabpVGVIuiMwEjSEBLzxkkHJWC0iIhIN/37eUQD85JE3ElyTYPn2/a+ys6aJn11aRkFO/xdPphTlMG9CvvJg+CpqvRlI+uv4SZTQVKpVPYcGf+978PTT3n2cqANDuk0siJw0prdyGbonNleSYt5c2L3JyUhj4dRCnlYiTxmCyoZW8rLSyEpPTVgdSnLVgSEiIiPLxIJsPnnqDO57aRev7qpPdHUC4S/rKrhv/S6+vHQ2J84oGvB6y44ez9odtYf/KB5l7l+/i1WbK9n0dkNgcxCW5nsdGIcMI6mogN/+Frq6vPs4RWGoA0O6XblsDumph/b6pacaVy6bk6AajVyrNu+jbGohhWP67qE+fXYxG3fvp+aAwvBlcKoa2w6bnjfeivMyqT7QSldXfOd5XzqvlKXzDp/dR0REJBo+d+aRjM1O57oHX8e5+J7jgubNyka+/ddXOXFGEV86e3DTjJ43/wicg8dfD/4wkli1LbwchK/Q4beVgpqDsDQvC+BgIs/6ejj1VGjxZybp7IxbFIY6MKTb8rJJTCvKITXFMCAtxRifl8mFx09MdNVGlMqGVl6pqI84+0hPp84qBtBsJDJolY2tCR0+Al4ERnuno745vtnarzjjSK4448i47lNEREaPsdnpfOns2TyztZonR3GkbGtHJ1++cz0ZaSn87NLje83r1pt5E/KYXJidFLORxKpt4eUg7DqkLIg5CENDSCobWmDrVli8GHbuPLhAW1vcojDUgSHddlQfYGvlAb527lG8df27ufq986moa+HlCoXHRdO/3qgE4Mw5/ffiHje5gLysNHVgyKBVNbQmPAIjtP9ETKUqIiISSx87eRpTi3K47p+v0xnnSMOg+NFDm3l1135+9P7jmDB28EPOzYzz5h/BU1urONDaEYMaBl+y5CAcl5tJikHmU/+CE0+E8nJISzt0oThFYagDQ7rdvbacFIP3L5wMeBEZORmp3PHsjgTXbGR5YvM+SvMyOXpi5Lmxw6WmGKccOY6ntlSN+hBFGZzKxlZKEhyBEYoAqYpzHoxLfrOGS36zJq77FBGR0SUjLYUrl81h09sN3BewcP94eGLTPm55+i0+vmQa5x19xJC3c97R42nr6Oq+wBdUsWpbJEsOwtQUY9yYDE66+ScwcSLMnAkdPTqd2tpg9eqY10UdGAJAR2cX96yr4Kw5pRwx1hvjlJeVzvKySfztld3UN8U3BHyk6ujs4sk3KjlzTsmAswyfNruEXXXNbK/WdF0yMC3tnTS0dCR0ClVQBIaIiIxs7z52Agsmj+W/H9l8+PSSI9je/S38+59fZu4ReXzrXfOGta3F0wopzEnnkY2jczaSK5fNoecvguz01GDlIGxvh8ZGSvOzuPFz13mdFK+9Bs4dflu/PubVUQeGAN6whr37W/ngCVMOKf/oSdNoae/inhcrElSzkeXFnXU0tHRw1gCGj4Sc5ufB0HSqMlChbN6BGUKimUhERGQESkkxrnrnPPbUt3DrM28lujpx0dnl+Le7XqK5rZP/+XDZsGc7S0tNYem88Ty+aR/tnV39rzDCLJpWiAPGZqdhwKSCbK676FiWl01KdNU8VVVw7rnwoQ9RmpvBltQ8yO8/ijyW1IEhANz5QjnFuZmcPffQH9bzJ+ZTNrWAO57boSEMUfDE5n2kpRinzi4e8DrTx+UwqSCbp7cEO7ROgiPUYZDoJJ75WWlkpKYoAkNEREasJUeOY+ncUn71xLZRMWvcr/+1jdXbqrnmgvnMKs2LyjbPmz+ehpYOnnuzJirbSyZPbN4HwH2fP5W3rn83z1x1dnA6L1591ct38eyzcOmllORnHTqNaoKoA0PY19DCyk37eP+iSaSnHn5IfPSkabxZeYA126oTULuR5YlN+1g8vZD8rPQBr2NmnD67mNXbqkdtkigZnKpGrwGV6AgMM6MkL1MRGCIiMqJd9c65HGjr4BcrtyS6KjG1bkcNP3n0Dd5z3AQ+uHhK/ysM0OmzS8hKT+GR10bfMJKVm/YxfVwOM0tyE12VQz3wACxZ4k2T+uST8JGPUJqXRXVja8J/j6gDQ/jLul10djku6eWL6N3HTaAgJ50/PKdknsOxp76ZTW83DGr4SMips4ppaOnglYq66FdMRpzQEJJER2AAFCegA+M9x03gPcdNiOs+RURk9Jo9Po9LTpjCH57dwY7qA4muTkzUN7fz5T+9xMSCLH5w0bEDzuU2ENkZqZwxu4RHNu4NbMR3LNoWzW2drNlWzVlzB//bIKaamuBzn4O5c+GFF7woDKA0P5MuB9UJjqxNWAeGmaWa2Xoz+7v/f5GZPWpmW/z7wrBlV5jZVjPbbGbLwsoXmdkG/7Gfm/9JMrNMM7vLL3/OzKbH/QkmCeccd68t58TpRb32/GWlp/KBRZN5ZONe9u1viXMNR45Vm70hIEP5kjo1lAdjFM81LgMX6jAYl+AkngAluRndESHx8rEl0/nYkulx3aeIiIxuXz3nKNJSUrjh4c2JrkrUOedYce8r7N3fws8vLRtUJPFALTv6CN7e38KGXfVR33Y0xKJtsebNKlo7uoZ0cTMmWlq8qVBzcuDRR+Ff/4JJB4ezlPqRvYkeRpLICIyvAK+H/X8V8LhzbjbwuP8/ZjYfuBQ4Gjgf+KWZhbLF/Aq4Apjt3873yz8F1DrnZgE3Aj+M7VNJXs+/VcNbVQe45IS+w8A+fNI0Orocd71QHqeajTxPbNrHpIJsZpcOPkSsaEwGR0/MVyJPGZCqxlbGZqeTmTa8xFrRkIghJM1tnTS3jZ5s8CIiknjj87P49Okz+Psrezjh+48x46p/cOr1K7l/BEyx+qfny/nnhrf59/PmUDa1sP8VhuDsuaWkphiPbNwbk+0PVyzaFis37SMnI5WTZhZFdbtDsns3nHEG/Od/ev/Pn+91ZIQpyfNmqtzXkNgL2gnpwDCzycC7gZvDii8Ebvf/vh1YHlZ+p3Ou1Tn3FrAVONHMJgD5zrk1zos1+l2PdULbugdYatGMcxpB7lpbTl5mGu86tu+QqBnFYzhtVjF/en5nwsc9JaPWjk6e2Vo1qOlTezptdjEv7qzlQGtH/wvLqFbZ0JrwKVRDSnIzqTkQ3/GSl//2eS7/7fNx25+IiAjAxIJswJs+3AG76ppZce+GpO7EeGNvA9/520ZOn13MZ86YGbP9FI7J4MTpRYHNgxHttoVzjic2VXLqrOLEX3BauxZOOMGbGtUfLhJJaUBml0tUBMZPgW8A4XPljHfO7QHw70OxNJOA8Mv+FX7ZJP/vnuWHrOOc6wDqgXFRfQYjQH1zO//csIcLjp9Idkb/H5yPnjyV3fVewk8ZnLXbaznQ1jmsELHTZhXT3ul4fvvoy9Asg1PV2JrwBJ4hxXneeMnRkJldRERGt1+s3HpYWXN7Z9IOK2lp7+RLf1xPXlYa//3BBaSkxPZ68HlHj+eNvY28VTUy84iEe2NvI7vqmg+bATLu7rwTTj8d0tNh9Wp43/t6XTTUtty3f5R1YJjZe4B9zrl1A10lQpnro7yvdXrW5QozW2tmaysrR98UlQ+8vJuW9i4uPWHqgJY/Z954xudn8odnlcxzsJ7YtI+M1BROmTX0frQTpheRkZaiPBjSLy8CIxgdGCW5weitFxERibXddc2DKg+67//jNTbvbeC/P3g8pf7wgVg6d/54AB4NaBRGNIWmT01o/ouKCrj8cli8GJ5/Ho47rs/Fs9JTGZudPipzYJwKXGBm24E7gbPN7A/AXn9YCP596DJ/BRCeoGEysNsvnxyh/JB1zCwNGAscdtnaOXeTc26xc25xSUlJdJ5dErn7hXLmTcjnmEn5A1o+LTWFS0+YypNbKtlZ3RTj2o0sT2zex0kzi8jJSBvyNrLSUzlxehHPKA+G9KOqsS0wERihelQmOGO1iIhIrIWGkAy0PMgeenUPf3h2J1ecMZN3HBWf30mTC3M4emI+Dwc0D0Y0rdy0j3kT8jlibOw7hg7T3u7dT54Mjz0Gjz8OpQPrSCnNyxx9OTCccyucc5Odc9PxknOudM59FHgAuMxf7DLgr/7fDwCX+jOLzMBL1vm8P8ykwcxO9vNbfLzHOqFtXezvQ4kbwmzcXc+GXfVcesKUQeVk+NCJU0kx44/P74xh7UaWndVNbKs8EJUe1lNnFbPp7YaEf3FIcDW3ddLY2hGYCIxQPaoUgSEiIiPclcvmkJ1+6LDstBTjymVzElSjwbl//S5OvX4lM676B5/7w4tMKczm6+fFt+7nzT+CF3fWjui2bn1TO+t21HL23ARcQN++3Yu4+OMfvf9POw0yBp43rTQ/c1RGYPTmeuBcM9sCnOv/j3NuI3A38BrwEPAF51woBezn8BKBbgW2AQ/65bcA48xsK/A1/BlN5KC7XygnIy2F5cdP6n/hMEeMzeKceaXcvbac1g5l+R+IVW/4IWJRGON2+mxvOlVFYUhvqvxIh5KAdGAkIgLj4kWTuXjR5P4XFBERiaLlZZO47qJjmVSQjQFZ6Sl0djlmFI9JdNX6df/6Xay4dwO76ppxeGPv9zW08s8Ne+Jaj/OOHo9z8Pjrwcq5F822xZNbKunscvHLf7FnD7zjHXDffV6yzh07oLh4SJsqzctKeA6MocezR4FzbhWwyv+7Gljay3LXAtdGKF8LHBOhvAX4QBSrOqK0tHdy3/pdvPOYIxibM/h5nD9y0jQe3riXh159mwsH2QEyGj2xaR/Tx+VE5eQ1f0I+hTnpPL2lmveV6QeaHC7UURCUISRjMtPIyUiNaw6MDyzue1poERGRWFleNonlZV77uK6pjXf97Cm+fOd6/v6l08jLGny7O15ueHgzze2HXpxs7ejihoc3dz+feJh7RB5TirJ5ZOPbfOjEgeXpi4doti2e2LSPgpx0jp8SmylpD/O978FTT3m32bPhb3+Do44a0qZK8zKpbGjFOTfkmRWHK0gRGBInD298m/0tHVwyxA/iabOKmTYuR8k8B6ClvZPV26o5M0oJelJSjFNmFfP01ko0KkoiCXUUBGUICXh1qYpjBEbNgTbNeiIiIglXkJPBTy8to7ymiW/f/2qg225BSUBqZpw3/wie2VpNY2tHXPfdl2i1Lbq6HKveqOQdR5WQGuNZXQAv+uKWW/4/e/cdH1d15n/8c0a9d8myJHfj3g0x2BC6CSHgEFoqKRsSfskm2d2QQHbTl0BCNnU3hTRIo4TQEjrYBmwMxhVX4V5kydLIVrXq6Pz+mDtCtiXbkmbm3pG+79dLL43OzL330VhjHT1zzvOAtWAMPPnkgJMXEHyDrD3QRX1LRxiD7B8lMIahB1cfYFRuKgvGDawjhs9n+PC7RvHm3qNsr2oIc3RDy6rdtbR1doVl+0jIogn5HG5oY1dNU9jOKUOH32MrMCAYSzRXYNz657Xc+uczbXQlIiISOeeMzeWLl5zF4xsO8fd1FW6H06e8Pt74cKMA6eJpI2gPdPFyuXe6RIZrbrHxYB1Hmtujt33ku99953Z8PPzsZ4M6XXcrVRfrYCiBMczsq21m1e5abphfOqheztfPKyMx3sdf31Axz1NZvr2a5AQf7xqbG7ZzLpoQ3LP2qtqpSi/8jcF3B/LSz7wgU6QVpEc3gSEiIuIln794Au8am8s3ntjMbg++AbXH38yxtg5O/MsgJSHOlQKk80bnkJuWyPNDsJ3qsu3V+AzR6exSWQl/+AO0OytH2tuDX1cN/HkNtdN1sw6GEhjDzMNrDuAzcN28we3jyklL5KoZxTy6roJmDy3v8hJrLcvKa1g4Pp/kEypSD0ZZbipj8lJVyFN6VdPUSnZqAglx3vnvPT8jMapbSERERLwkzmf4yU2zSYz38a8PrPdUIfzapjY+/ofVJCfG87Urp3QXIC3JTuGua2dEtf5FSJzPcOmUQpZur6a9syvq14+kpeXVzB2VQ3ZqFN5o+u53oeuE5y8QOH5VRj8VZoZWYLjXJcY7M1yJuM5AF39bc5ALJxWGpefwhxeMoqmtkyc2HApDdEPPbn8z+48c48IILBFbOCGf13cfoSMwtP5Tl8HzN7Z7pgNJSEF6MkePdQy5SYiIiMiZKs5K4Z7rZrHlUAN3P7Pd7XCAYOv1T92/hqr6Vn7zsfl8+oJxrLz9Yvbc/V5W3n6xK8mLkMunjqCxtZM39tS6FkO4VTe0srmiIaxby09p1ap3Vl+EtLfDa68N+JSF2kIi0fTy2zVUN7Zx49nhqaI7d1QOk0dk8OfX93m6KJFblm0Ptn+6MAJLxM6fmE9TWycbDtSF/dwS22qa2jxVwBPe2S9Z26xVGCIiMnxdNrWIj583hj+s3MtL2w67Gkugy/LFB9ez8WAdP71pNvNGR6kjxhlaNDGflIQ4nt/i7vMUTsudmh4Xham4/2mtXx8s3nnix/r1Az5lelI8KQlx2kIi0fHgmwfIT08KW9EYYwwfWTCarZUNrNcf0idZXl7DhMJ0ynJTw37uc8fl4zOwQnUw5AT+pjZPFfAEyHfqcYTqc0TaRxaM5iMLRkflWiIiIv1x+3smM6U4ky//bSNV9e4sw7fW8t1/buX5rYf5+nuncsX0YlfiOJXkhDjefVYBz2+toqvL/TdKwzG3WLq9muKsZKYUZ4QpqugzxlCYmUSNi1uDlcAYJqobW1m6vZoPzCsJ6974JXNKSEuMU0vVEzS3BZe8XTQpMgV6slITmFGazQrVwZAT1DR6dwVGTVN0JmrvmzWS980aGZVriYiI9EdyQhz/+6E5tHZ08aWH1hNw4Y/z363Yw32v7eVTi8byyUVjo379M3X5tCION7TxVkW926EMem7R3tnFip1+LpxUiDFRaJ8aQYUZSVQ3qAaGRNjf11YQ6LLcOD8820dC0pPief/cEv75ViV1x6Lz7mosWLnTT0fARnSJ2PkT8tlwoI7GVvf6MIu3HGvv5Fh7wHMrMLoTGFHaL3moriXqfevFm4wxZcaYZcaYbcaYLcaYLzrjucaYF4wxO5zPOT2OucMYs9MYU26MWdxjfJ4xZpNz389MrM9ARcQ14wvS+fY103h99xF+uXxnVK/99KZK7nx6G++ZPoL/vHJKVK/dXxdPLiTOZ3h+i/vdSAY7t3hz7xGa2jqj1z41ggozkl3tLqcExjBgreXhNQc4Z0wu4wrSw37+D79rNO2dXTyy9mDYzx2rlpXXkJYYx/wx4WufeqKFE/IJdFle330kYteQ2BLaopHvoRaqQPeKEH9TdJKc//bQBv7toQ1RuZZ4XifwH9baKcAC4HPGmKnA7cBL1tqJwEvO1zj33QRMA64AfmGMCbWR+iVwCzDR+bgimt+IiAwt188r5epZI/nxiztYuy86c7k1e4/wpYc2MHdUDj++cTY+n7fzsNmpibxrbC7Pb3W/DsZg5xbLtleTGOfjvPF54QvKJQUZSSriKZG1es8R9vibw1a880RTijOZNzqHv7yx3xN71NxmrWV5eTWLJuaTGB+5l9jc0dmkJMSpnap0C23RyPfYCozkhDgykuNdzdbL8GStrbTWrnNuNwLbgBLgGuB+52H3A0uc29cAD1pr26y1e4CdwDnGmGIg01q7ygarVv+xxzEiIv1mjOHO90+nJDuFLzywgfpjkV1Ru7umiX/54xpKslP4zcfmk5wQd/qDPODyqUXsrG5iV02T26EMytLyat41Lpe0pHi3Qxm0wswkmto6Odbe6cr1lcAYBh568wAZSfFcOSNyBXo+smAUe/zNvLZr6LQ6Gqjyw41U1rdGvMJwUnwc54zN5dUdNRG9jsSOGmcFhtfaqEIwW68EhrjJGDMGmAO8ARRZayshmOQAQv9hlwAHehx20BkrcW6fOC4iMmAZyQn87INzONzQyu2PvhWxrn7+pjY+/oc3iTOG+z5xNrlp3lqpeSqXTxsBwAseWIUxUPtqm9ld0zwkto9AcAsJ4FonEiUwhrj6lg6e3lzJ1bNHkpIYuUzre6YXk5OaoGKewLLtwYTChVFokXT+xHx21TRTWa/9/kJ3RWiv1cCA4DYSNytWy/BmjEkH/g58yVrbcKqH9jJmTzHe27VuMcasMcasqalRgllETm12WTa3LZ7EM5ur+Ovq/WE//7H2Tj51/xqqG1v57c3zGZ2XFvZrRNLI7BRmlGR5og7GQC3dXg1EsX1qhBU680y3tpEogTHEPbnxEK0dXRHbPhKSnBDHDfPLeGHbYQ67WJXWC5aVVzOlOJMRWckRv9bCCfmA2qlKkL+xDWPw5DsrBRlJ+LUCQ1xgjEkgmLz4i7X2UWf4sLMtBOdztTN+EOj5C7MUOOSMl/YyfhJr7b3W2vnW2vkFBZHpRCUiQ8unzx/HBWcV8J1/bKW8qjFs5w10Wb7wwAbeOljHz26aw5xROac/yIMun1rE+gN1rna+GIxl5TWMy09jTH5sJY/6UtCdwHDn30MJjCHu4TcPMKU4kxklWRG/1gfPGUWgy/Lg6gOnf/AQ1dDawdp9RyPWPvVEk0dkkJ+epHaqAgSXiOakJoa1VXK4FKRHbwvJp88fx6fPHxeVa4m3OZ1Cfgdss9b+qMddTwI3O7dvBp7oMX6TMSbJGDOWYLHO1c42k0ZjzALnnB/rcYyIyKD4fIb/uX4WGcnx/OsD62hpDwz6nNZavv2PLby47TDfet+07q0YsejyaSOwFl7cVn36B0fIQOcWx9o7eX13LRcNke0j0GMFhraQSLhtrqhnU0U9N84vjUq/4TH5aZw/MZ8HVu+nM9AV8et50YodfgJdNmr/SRljWDQhj5U7/RHbNymxo6axzXMdSEIKMpJobOuktWPwk7LTuXRqEZdOLYr4dSQmLAQ+ClxsjNngfFwJ3A1cZozZAVzmfI21dgvwMLAVeBb4nLU29EN7K/BbgoU9dwHPRPU7EZEhrSAjiR/dMJu3Dzfx3ae2Dvp8v311D39ctY9Pnz+Wm88bM/gAXXRWUTqj81J5fqt720gGOrdYubOW9s6uIVP/AiAnNZF4n9EWEgm/h9ccIDHex5I50asz9pEFo6lqaOWl7e5lSN20bHs1mcnxzCnLjto1F07Ix9/UzvYwLjmU2ORvavNk/Qt4p7BoNFZh7KqJ/WrlEh7W2hXWWmOtnWmtne18PG2trbXWXmKtneh8PtLjmDutteOttZOstc/0GF9jrZ3u3Pd5q6yxiITZBWcV8JkLxvHXN/bzzKbKAZ/nn28d4s6nt/HeGcXc8Z4pYYzQHcYYLp9axGs7a2lsjWy3lr4MdG6xdHs16UnxnD0mNwJRucPnM04rVW0hkTBq7Qjw+PoK3jN9BNmp0XtH9pLJhRRnJQ/LYp5dXZblb9dwwVkFxEdxCf+iicE6GGqnKjVNbeR7sAMJvLNfMhqFPL/26Ca+9uimiF9HREQk3P7j8knMKs3iq39/i4NHj/X7+NV7jvDvD21k/ugc/ueGWfh8kV+FHQ2XTxtBe6CL5eXuFEceyNzCWsvy8moWTcgnMX5o/dld6GJ3uaH1TEq3ZzdX0dDayY3zI1u880TxcT5uOnsUr+7ws9ffHNVru21rZQM1jW1RrzBcnJXC+II0XlUhz2HNWou/sd2TLVSB7sSKCnmKiIj0LTHex88/OJcuC196cEO/tmXvqmni039cQ2luCr/52HySEyLXgTDa5o7KIS8tkedjqJ3q9qpGKutbuWjy0CvoXJCRrBoYEl4PvXmAUbmpLBiXF/Vr33h2GXE+wwMRaAXlZcucbTPvjlIBz57On1jAG3tqaeuMfH0B8abm9gAtHQHyvbqFJIorMERERGLZqLxU7nz/dNbsO8pPX9pxRsfUNLbx8T+sJiHOcN/HzyHHgx3JBiPOZ7h0ShHLtlfHzHx3qLVP7akwM8m1OZ0SGEPQvtpmVu2u5Yb5pa4sGxuRlcxlU4p4eM2BqBTs84pl5dXMKs1yZQn/wgn5tHZ0sW5fXdSvLd4QWtng1RUYeU5xUbeWG4qIiMSSa2aXcP28Uv532U5e23XqVbbH2jv51P1vUtPYxu9uPptRealRijK6Lp9WRFNbJ6/vPnL6B3vAsu3VTC/JpDAz2e1Qwq4wI4kjze20d0a/cYMSGEPQw2sO4DNw3bzobh/p6SMLRnP0WAfPbB54AaJYcqS5nfUH6rjQpQzrgnG5xPkMK3a6sy9Q3Od3suBeXYGREOcjJzWhO04RERE5tW9fM42x+Wn820MbONLc3utjOgNd/Otf17O5op7//eBcZkWxkHy0LZyQT2piHM9vca8byZk62tzOuv1HuXgIrr4AKMwIJmXcmNcpgTHEdAa6+Nuag1w4qZARWe5l+84bn8fY/DT+/Prw2Eby6o4arMW1Hs8ZyQnMKctmxc5aV64v7gutbPBqG1UIbiOJxgqMf714Iv968cSIX0dERCSSUhPj+fkH53C0uYPb/raRE5sfWWv51j+28NL2ar599bQh30I8OSGOCycV8MLWw3R1RbcRVH/nFq/sqKHLwoVDqH1qT4XOG2ZutFJVAmOIWV5eQ3VjGzee7d7qCwi21/nwu0axdt9RtlU2uBpLNCzbXk1eWiIzS7Jci2HhhHw2Hayj/pg77aXEXaEMuFfbqEL0EhiLJuZ3d+cRERGJZdNGZvG1Kyfz0vZq/rBy73H3/fqV3fz59f185t3j+Oi5Y1yJL9ounzqC6sY2Nh6si+p1+zu3WLa9mty0RGaVZkcuKBcVZjoJjIbot1JVAmOIeWjNAfLTk7jYA9m+D8wtJTHex1/eGNotVQNdlpffruHdZxW42qrq/In5dFlYtVvdSIajmsY2jIHcKLZN7q/89CT8Tb0vgQ2nLYfq2XKoPuLXERERiYabzxvDpVOKuPOprZx954uMvf0p5nznee5+ZjvvmzWSry6e7HaIUXPRpELifSbq3Uj6M7cI/W1w4VkFxA2RNrYnCm0h0QoMGZTqhlaWbq/mA/NKSIhz/582Jy2Rq2YW89i6CpraOt0OJ2I2Hqzj6LEO15eIzSrLJj0pXu1Uh6mapnby0hKJ98Brvy8F6cEVGCcugQ237/xjK9/5x9aIXkNERCRajDFcNKmAgA2+YWGBo8c68Bl498R8V99Ai7as1AQWjMuLeh2M/swtNhw4ytFjHa5tLY+GvPREjFECQwbp7+sqCHRZbpjv7vaRnj6yYDTN7QEeX1/hdigRs3x7NT4DF7i8ZD0hzseCcbms2KkExnBU09jmSgec/ijISKKlI0Bz+/DpTiQiIhIOv1i+66SxLgs/fvHM2qwOJZdPK2JXTTM7q5vcDqVXy7bXEOczXDCxwO1QIiYhzkduaiI1jdpCIgNkreXhNQc4Z0wu4wvS3Q6n25yybKYWZ/Ln1/dF/F1Xtywrr2HuqByyPbB0f+GEfPbVHuPAkWNuhyJR5m/yfgIjFJ9frVRFRET65VBdS7/Gh7JLpwSLlT6/1ZvdSJZur2beqByyUhPcDiWiCjKSqG4YBiswjDFlxphlxphtxpgtxpgvOuO5xpgXjDE7nM85PY65wxiz0xhTboxZ3GN8njFmk3Pfz4wxxhlPMsY85Iy/YYwZE+3vM9pW7znCHn+z68U7T2SM4SMLRrO9qpF1+4+6HU7YVTe2sqmi3jNLxM53VoFoFcbw429q83QBT3inwGiNWqmKiIj0y8jslH6ND2Ujs1OYWZrF81uiWwfjTFTVt7K1ssEzfxtEUmFm8rDZQtIJ/Ie1dgqwAPicMWYqcDvwkrV2IvCS8zXOfTcB04ArgF8YY+Kcc/0SuAWY6Hxc4Yx/CjhqrZ0A/Bj4fjS+MTc99OYBMpLiuXJGsduhnOSa2SNJT4ofki1VXy6vAeDCSd5YIja+IJ0RmclKYAwz1lpnC4n7q4BOpTuBoRUYIiIi/XLb4kmkJMQdN5aSEMdtiye5FJG7Lp9axIYDdRx2oQvGqSwrrwbwREOFSCvMSKJ6OGwhsdZWWmvXObcbgW1ACXANcL/zsPuBJc7ta4AHrbVt1to9wE7gHGNMMZBprV1lg3sT/njCMaFzPQJcElqdMRTVt3Tw1KZKrp49kpTEuNMfEGVpSfG8f04JT22q5Ehz5DsQRNPy8hoKM5KYWpzpdihAcMXLwgn5vLbTH/X+2OKeprZO2jq7PL8Co3sLSYRXYHzlikl85YrhOaETEZGhacmcEu66dgYl2SkYoCQ7hbuuncGSOSVuh+aKy6eNAOCFKHUjOdO5xbLt1ZRkp3BWkXe29EdKYUawu1wgyn9zxEf1aidwtnbMAd4Aiqy1lRBMchhjQmmrEuD1HocddMY6nNsnjoeOOeCcq9MYUw/kAce9LW2MuYXgCg5GjRoVtu8r2p7ceIi2zi7PbR/p6SMLRvOn1/fxyNoD3HLBeLfDCYuOQBev7KjhyunFeCk/dv7EfP6+7iBbKxuYXpLldjgSBaEVDV6vgZGblojPRH4FxrzRuRE9v4iIiBuWzCkZtgmLE00sTGdsfhrPbz3MRxaMjvj1zmRu0dYZYMVOP++fU+Kpvw0ipTAjiUCX5Uhze1TfRHOtiKcxJh34O/Ala23DqR7ay5g9xfipjjl+wNp7rbXzrbXzCwq8sQVgIB56cz9TijOZ4eE/VieNyODsMTn85Y39Q2ZlwLp9R2ls7eSiyd762TlvQh6A2qkOI/6m4Momr6/AiPMZ8pxWqpG0dt8R1u47EtFriIiIiHuMMVw+tYhVu/w0tHZE/HpnMrdYvecIx9oDw2L7CARrYED0twa7ksAwxiQQTF78xVr7qDN82NkWgvO52hk/CPRcWlAKHHLGS3sZP+4YY0w8kAUMydns5op6Nlc0cOP8Us9n+j6yYDT7ao8NmfoMy8priPcFt2x4SWFGMpNHZLBiZ43boUiUhLZkeH0FBgRjjPQWkh88W84Pni2P6DVERETEXZdPK6IjYFleHvk575nMLZZuryYp3sd54731t0GkFDpvnEW7DoYbXUgM8Dtgm7X2Rz3uehK42bl9M/BEj/GbnM4iYwkW61ztbDdpNMYscM75sROOCZ3rOmCpHaI9PB9ec4DEeF9MLCe7YvoI0hLjuOWPaxh7+1MsvHspj6+vcDusAVteXs3ZY3LJSPZei6SFE/J5c+9RWjsCbociURArW0gguEpERTxFRERksGaX5ZCfnsTzW7zRTnXZ9mrOHZ/nyZqEkVCYEVyBEe1OJG6swFgIfBS42Bizwfm4ErgbuMwYswO4zPkaa+0W4GFgK/As8DlrbeivsluB3xIs7LkLeMYZ/x2QZ4zZCfw7TkeToaa1I8Dj6yu4YtoIslO93X0A4JlNVbR1dtHa2YUFKupauOPRTTGZxDhU18L2qkbPbR8JWTQxn/bOLt7cOyQXHskJ/E1t+EywxoTXFURhC4mIiIgMfXE+w2VTC1leXkNbp7tv2u3xN7O39tiw2T4CUJjpTne5qBfxtNauoPcaFQCX9HHMncCdvYyvAab3Mt4KXD+IMGPCs5uraGjt5CYPF+/s6Z7nyuk8of5FS0eAe54rj4kVJD2FlqpdNMmb/0m9a2wuCXGGFTv9nD/Rm0kWCZ+axjZy05KI83l7GxlAfkYi/qZ2rLWe3/YmIiIi3nb51BE8sPoAq3bVcqGL8/Kl24PVD7z6t0EkJCfEkZEcT3WUW9m6VsRTBu7x9RUsvHspX3poA3E+w+F6b/U/7suhupZ+jXvZsvJgi6QJhd5skZSaGM/cUTmsUCHPYcHf1Ob5Ap4hBelJtAe6aGjpdDsUERERiXHnjs8jLTGO57ZEp51qX5Ztr2ZCYTpluamuxhFthRlJw2ILiQzC4+sruOPRTVQ4f/QHuixfe3xzTGzDGJmd0ut4cVZylCMZnLbOACt3+rlocoGn30E+f2I+Ww41cKS53e1QJMJqGtvIT/f+9hF4p1NKTVPkEq/feN9UvvG+qRE7v4iIiHhDckIcF04q5IWthyPa6fBUc4umtk7e2FM7rLaPhBQogSGnc89z22k5oTBjaBuG1922eBIpCScXtYmLMzG1J/7NPUc51h7w/BKxUHeUlUOk64v0zd/UTkEMFPAEuuOsaYxcYm3ayCymjfRuW2kREREJn8unFeFvamP9gbqIXeNUc4uVO/10BKzn/zaIhMKM5KHfhUT6r6U9wNLth/mvxzdRUdf7D0gsbMNYMqeEu66dQUl2CgYoyU7hkwvHUNPYxpL/W8nbhxvdDvGMLCuvJjHex7nj89wO5ZRmlmaTkRyvbSRDnLWWmljaQtK9AiNyScsVO/z6uRcRERkmLpxUiAFu/v3qiHU6PNXcYtn2ajKS4pk/Jies1/S6x9dXsHT7YQ4caWHh3S9FbUdA1It4ypk5ePQYy7ZXs3R7Na/tqqWts4vUxDiS4320dnad9Pi+tmd4zZI5JScV7Fwyp4RP3b+GD/ziNf7vw3O54CxvF51cVl7NgnF5pCZ6++UT5zOcNz6PFTv9Kpg4hDW0dtLe2RUTLVShRwIjgquufr50BxDsxiMiIiJD27Lt1RgT3MoB73Q6BMLWKKCvuYW1lmXl1Zx/Vj4JccNnbUCorEFoZ0BFXWvYn/O+DJ9n2eM6A128sbuWu57ZxuU/fplF31/G15/Ywm5/Mx88ZxR//OQ5rP/GZdz9gZknbcNISYjjtsWTXIp88GaWZvPE5xZSkpPCJ+57k7+8sc/tkHr1+PoK3vW9F9ld08zGA0djou7IookFVNS1sLf2mNuhSIT4nZUMsbICIyslgYQ40x23iIiIyGDc81w5J5a/iNYW+y2HGjjc0Dbsto/c81y5a2UNvP0W8hB3pLmd5eXBVRavvF1DQ2sn8T7DOWNzuWF+GRdNLmRcftpx75yHMlr3PFfOoboWRmancNviSTHXhvREI7NTeOTW8/j8X9fxn49tZk9NM3dcOcUzbSFPzDLWt3RGLcs4GOc7dTBW7PQzNj/N5WgkEkIrGWJlBYYxhvz0pJiqeyMiIiLe5Wanw2VO+1Q3W7i6wc3nXAmMCHl8fcVJSYZrZo9ky6GG4NaQ8mo2HKjD2uAfHounjeDiyYUsmphPRnLCKc/d2zaMoSA9KZ7ffmw+3/3nVn67Yg/7jhzjpzfN9sRWjVNlGb38bzE6L5WS7BRW7KjhowtGux2ORECsrcCAYKxKYIiIiEg4jMxO6e7QeOJ4pC0rr2ZmaVZMzcPCwc3n3P2/DIegk/cEtfAff9vIN57YRENrcGxmaRZfuHgil0wpZPrILHweWWngtvg4H9++Zjpj8tP47j+3csOvV/G7m8+mKNO9Vqst7YFeX6Dg/eKpxhjOn5jPU5sq6Qx0ET+M9uYNF/7uFRix0UYVgknbww3RrVgtvSfWvZyAFRERORO3LZ503N9eITecXRrR6x5pbmf9gTq+cPHEiF7Hi3p7zqNV1kAJjAjo7d36QJelPWD5wXUzuXBSAYUZ7v1BHgs+sXAso3JT+dcH1rPk/1byu5vPZurIzKjG0NoR4K9v7OcXy3f1+ZhYKJ66cEI+D755gE0V9cwZNbyqIw8HNU1txPkMOamxk8AoSE9ic0V9xM7/vWtnROzcsaq3xHosbIMTERE5nRO32BdmJtER6OLXL+9mTllOWBoE9Da3ePntaqyFiycPr+0j4G5ZAyUwIqCvd+XbOrq4YX5ZlKOJXZdMKeJvnz2XT923hut/9Ro//9AcLp5cFPHrtnd28dCaA/zf0p1UNbSyYFwuH3pXGb95ZY8rWcbBWhiqg7HDrwTGEORvbCcvLTGmVnEVZCRR29xOV5eNSNzjC9LDfs5YF6vb4ERERM7EiVvsqxtbufn3b/Kp+9/kh9fP4prZg/td19vcYun2GvLTk5hRkjWoc8cqt8oaaD15BPT1rnwsvFvvNdNGZvHE5xcytiCNf7l/Dfet3BOxa3UEunjozf1c9MPlfP3xzZTkpPDXf3kXD95yLv9+2STuunYGJdkpGKAkO4W7rp0RExP/3LREpo3MZMXO3ntXS2yraWqLmQKeIfnpiQS6LEePtUfk/C9uPcyLWw9H5NyxyFrbvQ2uoOkID/31dgqajgLe3wYnIiIyEIUZyTz0mQXMGZXDlx7aMOi/IU6cW3QGunjl7RounFQQU28iDQVagREBbu4JGoqKMpN5+DPn8oUHNvCtf2xlj7+Zr181NWz1HAJdlic2VPDTl3awr/YYs0qz+N61M7hgYv5JHWBiIWHRm6LMJJZur2Hs7U9p7/sQ429qi7nCUQXOFrqapjbyIpB8+c2ruwG4dGrkV2yFXWUl3HQTPPQQjBgx6NNVN7by1Ufe6v76Cysf4OwDW/jX1x7gG5f/PyXWRURkyMpMTuCPnzyHLzywnm/9Yyu1ze38+2VnHTe/P1Mnzi3WH6ijvqVj2LVP9QIlMCJgqLY6dVNqYjy//ug87np6G79dsYf9R47x8w/NJT1p4D/CXV2WpzZV8uMX32Z3TTNTizP57cfmc8mUwgH9x+ZVj6+vYMWOWgAs2vs+1NQ0tjGxMMPtMPollHCpaWxj8uD/Rh9avvtdWLEi+Pn//u/0j7cW2tqgpQVynC1iW7fCoUOs27KfR1/Zzuhjx7hrTAG/TJrA9Ztfwofl+k0v8pt3f5j/WDw7ot+OiIiIm5IT4vjFh+fyX49v5udLd+Jvaue/l0wnbpCrJpZurybeZzj/rPwwRSpnSgmMCInld+u9Ks5n+K+rpjI6P41vPbmF63+1it/dPL/f7yBaa3luSxU/fmEH5YcbOasonV9+eC6Lp40YkkvA7nmunPZA13FjLR0B7nx6G1fPGjkkv+fhwlpLbVN7zK3ACHVMCbWAFUdlJfzhD9DVBffeC+3twQRFU1Nw7OGHg4/7t3+Dv/0tON7UBIEAFBfDoUMAdNx2GwlPP81cYG7o3BMm8K455+Kzwf8L4mwX91c8x7g5H4r6tykiIhJN8XE+7rp2Bnnpifzfsl0cbW7nJzfNJjkhbsDnXLa9mvljcshMTghjpHImlMCQmPPRBaMZlZvK5/6yrrtDyYzS0xfPsdaydHs1P3rhbbYcamBcfho/vWk2V80cOegsrJf1tce9prGNc773Iosm5HP+xALOn5hPoYvtaqX/Glo6aQ90xVQLVTh+BYb08N3vBhMVAJ2d8Mc/QkEBpKdDVo//4yZPhiuuCI6HPnJzAXhjdy2/HH8NLR++gKsWTuKmi6eSkJUJTU2MmzEDAp0AJAY6GffPv0HV98OyVUVERMTLjDHctngyeWlJfOefW/n4H1bzm4/NJ2MACYhDdS1sr2rka1dOjkCkcjpKYEhMevdZBfz91vP45H1vcsOvV/GTm2azeFrvk3BrLa/u8POjF95mw4E6RuWm8sPrZ7Fk9siw1dHwspHZKd0F/HrKTk1g4YR8Xt3h5/ENwXduJ4/I4PyJwYTGOWNzB5WZlsiraWoFiLkVGKEiWN97ejv3v7ZPW+zgndUX7T0Km8bFwZo1JycYPvOZ4EcPbZ0BfvT0Nu59dTejyybyP/8xm3mje3Qd+n//753kSEggcOZbVURERIaATy4aS25aIl/+20Zuuvd17vvEOf2eRy0rrwZQ/QuXKIEhMWvSiAwe+9x5fPr+NXz2z2u5euZI1uw7wqG61u66I0WZyfzohXLe3HuUkVnJ3HXtDK6bV0rCMEhchPRVVPZb75vGkjkldHVZtlY28OoOP6/uqOH+1/bxm1f3kBjv411jc7tXaEwpzhhStUGGgprG4B+7BTHUheTx9RV87bHN3V9HoibLj2+cHZbzRFXP1RchZ5hg2FbZwL89tIHtVY186F2j+M8rp5B2Yn2gVauOT45A8OvXXgtD8CIiIrFjyZwSslMTuPXP67juV6/xp0++i1F5qac8pufcYtn2akpzUphQqLbtbjDWWrdj8IT58+fbNWvWuB2GDEBLe4Ab732Ntw42HDfuM9Blgx04Pn/RBG44u4yk+OG5ouDx9RVnXFT2WHsnq/cc6U5ovH24CYD89CRndUY+iybmU+h0kujPuSW8ntx4iC88sJ7n/+0CziqKjUKeC+9e2uuKoJLsFFbefrELEXnEnDmwYcPJ47Nnw/r1vR4S6LL8bsVufvjc22SmJPCD62Zw8WR3Oq8YY9Zaa+e7cnEP09xCRMS71u8/yifue5OEOB/3f+Icpo7MPO0xrR0B5nznBa6fX8p3rpkehSiHr77mFlqBITEvJTEOf1P7SeNdFrJS4nn5touG/VaI/hSVTU2M58JJhVzoLIurqm/l1R01vLrDz8tv1/DY+goguN2kOCuZlTtru4uEqsNJ9Dy+voJvPhlcyXDz71fz1Ssmx8Rz3ldNloq6Ft46WMeMkqxBr/T5x8bglqj3zRo5qPNEVR9Jir4cPHqM/3h4I2/sOcLiaUV87/0zItKSVkREZKiaMyqHRz57Lh/93Wpu/PUqfnvzfN41Lq/Xx4bmFhnJ8bR0BLhosraPuEUJDBkSKutaex1vaOkc9smLwRqRlcz188u4fn5Z93aTV3bU8OrbfpaV15z0+JaOAN97ehtXzSweFjVG3PD4+orjtgVV1rfGTOKor5osAFf/70pKslO4csYI3jOjmNml2QPqkvPn1/cBMZbAOEPWWh5dV8E3n9wCwD3XzeS6eaXa3iUiIjIAEwoz+Put5/HR373BR3+/mv/94Bwu76WuXmhuMaU4k+QEH+f2keiQyFMCQ4aEvv4o6m+LVTk1n88wvSSL6SVZ/L8LJzD29qfobRNadWMb0775HJNHZDB1ZBZTR2YytTiTKcUZpCbqv52Bstayt/YY3/rHluNqmkAwcXTPc+WeT2D0VZPlv947hYR4H89squS+1/bym1f3UJyVzBXTR3DljGLmjcoZ9i1/jzS385+PbeKZzVWcMyaX/7lhFmW5p96zKyIiIqc2MjuFRz57Hp+4700+++e13HXtDG48e1Svj126vZrzxufrDVIX6S8JGRL6+qPotsWTXIxq6OsrcZSTmsAH5pay5VADT2+q5IHV+wEwBsbmpzG1OJNpPRIbp6r+HMkaG16v39HaEWBzRT1r9x1lzb6jrNt3lNrmk7dLhfS1PcNLQs9vX8/7DfPLqG/p4KVth3lmcxV/eWM/f1i5l8KMJK6YPoL3TC/mnLG5Q7r1cW+WlVfzlUfeou5YO7e/ZzKfPn/csHsOREREIiUnLZG//Mu7uPUv6/jq3zdR29zOre8ef9wKx5aOAPuPHOPTF4xzMVJRAkOGhNP9USSR0Vfi6JtOhxMIrho4VN/Klop6tlY2sPVQAxsO1PHPtyq7jynISGKak8yYOjKY3Bidm8qTGw8dd/5w1Niw1tIRsPx93QG+/eRWWju9U7+jprGNtfuOsm7/UdbsPcLmiobu+iJj8lK5cFIh80bn8JMX36a6se2k42NlxdHparJkpSRw7dxSrp1bSlNbJ0u3V/PMpkoeXnOAP67aR15aIpdPG8GVM0awYFzekO4qdKy9kzuf2sZf3tjPpKKMMy4yJiIiIv2TlhTPbz82ny//bSM/eLac2qZ2/vPKKd0rQOuOdQBwsepfuEoJDBky+lOoUsLjTBJHxhhKslMoyU45bk9h/bGOYELDSWpsOVTPih1+OruCm1JSE+PoDNjuP+BDWjoCfOOJzez2N9PWEaC1I0BrRxetnQHanM/dYx0B2jq7nK+DY22dAbr6aL7U0hHgtkc28vSmSoqzkhmRlUJxVjJFmcnO18n9WjJ4qhUeXV2Wt6sbWbvvKGv3HmXt/qPsqz0GQGKcj5mlWXxi4Rjmjc5h7ugc8nsUaExNjBs2K47Sk+K5etZIrp41kmPtnSwvr+HpTZU8saGCB1bvJzs1gcunFvGeGcUsHJ/P05sqWb+/jvZAFwvvXhpTicwTf16un1/KExsOsbe2mVsuGMe/X3aWlqyKiIhEUGK8j5/cOJvctER+t2IPR5rb+cF1MwGoO9bOpKIMSmLkDaOhSm1UHWp1JuK+ts4AOw43dSc17ntt7ykfnxTvIzkhjuQE53N88HZSfBxJobGEOJJPfFxCHPc8V97neScVZVBZ30JDa+dJ9+WkJnQnNkZkJVOc6XzOSnE+J5OWFH9SoU0IJiYumVJIc3uA9fuP0uicPz89kXmjc5yPXKaXZJ625a/Xt79EWmtHgFferuGZzVW8uPUwjW2dJMUbOgMQ6PF7LSUhjruuneH5bUe9/bwAZKck8MuPzOPc8d4uFqY2qr3T3EJEJDZZa/nF8l3c81w5U0ZkUNvUTnVTG+lJ8fz3kunDas7llr7mFkpgODTJEPGehXcv7b04a1YyK2+/eFCdF/o6d0l2CitvvxiA5rZOqhpaqapvpbK+lar6Fuez83VDK0d6qUmRkRxPS3ugezXJiSYVZTBvTA7zRuUwf0wOo3JT1UViENo6A6zc6efzf13PsfbASffH+wwzSrNISYgjJSGO5MS47tupicGEVkqPseTEOFKdsWRnLCUxjpffrubuZ7bT2vHOqqDkBB9fu3IyF08uoiNg6Qh00d7ZRXugi47Q5+4x28tYFx2dlt+8upumtpMTZsVZyay645KIPn/hoARG7zS3EBGJbV95ZCMPrzl43Fi43xyR3vU1txjSW0iMMVcAPwXigN9aa+92OSQR6Ye+amx85YrJg/6D/0wKv6YlxTO+IJ3xBel9nqe1I8DhhtbjExv1Ldy/al+vjzfAc/92waBil+Mlxcdx8eQiWnpJXgB0dlnSk+Jp7QjQ0NpBS3twO9Gx9k5anK1FA9Xa0cU3ntjKN57YOuBznEpVfe8touXMGWN+D1wFVFtrpztjucBDwBhgL3CDtfaoc98dwKeAAPAFa+1zzvg84D4gBXga+KLVu0AiIkPayp21J43FSue3oWrIJjCMMXHA/wGXAQeBN40xT1prIzPLFJGwi2Rx1nCdOzkhjtF5aYzOSztu/MVt1WrtG2V9dcUpyU7hT596V5/HdXVZ2jq7aOkIBD/aO2lp7/l1sIbKlx7a0Oc5fvCBmSTG+0iI85EQZ0iM95EY5yMh9DnOR2K8ITEujoR443z9zn0X/GCZfl4i5z7gf4E/9hi7HXjJWnu3MeZ25+uvGmOmAjcB04CRwIvGmLOstQHgl8AtwOsEExhXAM9E7bsQEZGo66vDWyx0fhuqhmwCAzgH2Gmt3Q1gjHkQuAZQAkMkhkSyOGskz63WvtE30Ofc5zPBLSSJp647cs9z5X0mSG44u2xgQTv08xI51tpXjDFjThi+BrjQuX0/sBz4qjP+oLW2DdhjjNkJnGOM2QtkWmtXARhj/ggsQQkMEZEhra83R/QGg3uGbu85KAEO9Pj6oDMmIhJxS+aUcNe1MyjJTsEQ/CNX+yUjK/ScJzptVcP9nN+2eBIpJ3QBCVeSQT8vUVdkra0EcD6HeuL1NXcocW6fOC4iIkNYJH/3y8AM5RUYvW2QP26vqjHmFoLLQRk1alQ0YhKRYUStfaNvyZwSHli9H4CHPnNu2M8NkdnSFDq/fl5c19fc4bRziu4TaG4hIjJkhH4vf+WRt2gPdFEyDDu/ec1QTmAcBHqu6S0FDvV8gLX2XuBeCFYKj15oIiISi5RkGDIOG2OKrbWVxphioNoZ72vucNC5feL4STS3EBEZWiL55oj031BOYLwJTDTGjAUqCBbl+pC7IYmISKTd94lz3A5BvO9J4GbgbufzEz3G/2qM+RHBIp4TgdXW2oAxptEYswB4A/gY8PPohy0iIm7Q3MI7hmwCw1rbaYz5PPAcwTaqv7fWbnE5LBERibDTFeOU4cUY8wDBgp35xpiDwDcJJi4eNsZ8CtgPXA9grd1ijHmYYMHvTuBzTgcSgFt5p43qM6iAp4jIsKG5hXcM2QQGgLX2aYKtzkREZJj406q9AHz03DGuxiHeYK39YB93XdLH4+8E7uxlfA0wPYyhiYhIjNDcwjuGchcSEREZhv75ViX/fKvS7TBERERkiNDcwjuUwBARERERERERz1MCQ0REREREREQ8TwkMEREREREREfE8JTBERERERERExPOMtdbtGDzBGFMD7IvAqfMBfwTOG2mxGjcodrcodncodnco9uONttYWhPmcMS9Ccwv97LlDsbtDsbtDsbsjVmOPVNy9zi2UwIgwY8waa+18t+Por1iNGxS7WxS7OxS7OxS7uCWW//0UuzsUuzsUuzsUe/RFO25tIRERERERERERz1MCQ0REREREREQ8TwmMyLvX7QAGKFbjBsXuFsXuDsXuDsUubonlfz/F7g7F7g7F7g7FHn1RjVs1MERERERERETE87QCQ0REREREREQ8TwmMQTDG/N4YU22M2dxj7B5jzHZjzFvGmMeMMdk97rvDGLPTGFNujFnsStDvxHLGsRtjLjPGrDXGbHI+X+xa4PT/eXfuH2WMaTLGfDnqAR8fR39/ZmYaY1YZY7Y4z3+yK4HT75+ZBGPM/U7M24wxd7gVtxNPb7F/14l7gzHmeWPMyB73ef212mvsMfJa7fN5d+738mv1VD8znnit9vPnxVOvUwnS3MIdmlt4O26v/X+leYU7NK9wh+fmFtZafQzwA7gAmAts7jF2ORDv3P4+8H3n9lRgI5AEjAV2AXExEvscYKRzezpQESvPe4/7/w78DfhyrMQOxANvAbOcr/Ni6GfmQ8CDzu1UYC8wxmOxZ/a4/QXgV87tWHit9hV7LLxWe429x5iXX6t9Pe+eea32M25PvU71ccp/Q80tPBR7j/u9/P+V5+cW/YzbU/9f9fP/2lh4nWpe4aHYvfQ6HUDsEX+tagXGIFhrXwGOnDD2vLW20/nydaDUuX0NwX/MNmvtHmAncE7Ugj1Bf2K31q631h5yxrcAycaYpKgFe4J+Pu8YY5YAuwnG7qp+xn458Ja1dqPzuFprbSBqwZ6gn7FbIM0YEw+kAO1AQ7RiPVEfsfeMJ41gzBAbr9VeY4+R12pfz3ssvFb7it0zr9V+xu2p16kEaW7hDs0tok/zCndoXuGOWJ1XONf31NxCCYzI+iTwjHO7BDjQ476DzphX9Yy9pw8A6621bVGOpz+6YzfGpAFfBb7takRnrufzfhZgjTHPGWPWGWO+4mJcZ6Jn7I8AzUAlsB/4obX2SF8HusUYc6cx5gDwYeAbznBMvFb7iL0nz75We4s9Vl6rfTzvnn+t9hF3TLxO5SSaW7hDc4vo07wiijSvcEeszivAvbmFEhgRYoz5T6AT+EtoqJeHebIFTC+xh8anEVzO9xk34joTvcT+beDH1tom96I6M73EHg8sIvifwiLg/caYS1wK75R6if0cIACMJLhc8j+MMeNcCq9P1tr/tNaWEYz7885wTLxW+4gd8P5rtY/YY+K12kfsnn+t9hF3TLxO5R2aW7hDc4vo07wi+jSvcEeszivAvbmFEhgRYIy5GbgK+LC1NvQf1EGgrMfDSoFDJx7rtj5ixxhTCjwGfMxau8ut+E6lj9jfBfzAGLMX+BLwNWPM53s/g3tO8TPzsrXWb609BjxNcP+Zp/QR+4eAZ621HdbaamAlMN+tGM/AXwm+swAx8lrtoWfsMfFa7aFn7DHxWu3hxJ8Zz79WHT3jjrXX6bCmuYU7NLeIPs0rXKd5hTtidV4BUZ5bKIERZsaYKwguV7ra+YELeRK4yRiTZIwZC0wEVrsRY1/6it0EK0A/BdxhrV3pUnin1Ffs1trzrbVjrLVjgJ8A37PW/q87UfbuFD8zzwEzjTGpzj6ydwNb3YixL6eIfT9wsQlKAxYA292IsS/GmIk9vryad+KLhddqr7HHyGu119hj5LXa18+Mp1+rp4jb869TCdLcwh2aW0Sf5hXu0LzCHbE6rwCX5xbWxWqssf4BPEBwf08HwUzZpwgW5jkAbHA+ftXj8f9JsPJwOfCeWIkd+C+Ce5k29PgojIXYTzjuW7hfgbi/PzMfIVh4aDPwg1iJHUgnWPF5C8H/cG/zYOx/d57Xt4B/ACU9Hu/112qvscfIa7XP573HcV59rZ7qZ8YTr9V+/rx46nWqj1P+G2pu4aHYTzjOq/9feX5u0c+fF0/9fzWA3xFef51qXuGx2L3yOh3Az0zEX6vGuZCIiIiIiIiIiGdpC4mIiIiIiIiIeJ4SGCIiIiIiIiLieUpgiIiIiIiIiIjnKYEhIiIiIiIiIp6nBIaIiIiIiIiIeJ4SGCIS84wxy40x892OQ0RERIYGzS1EvEkJDBERERERERHxPCUwRCTqjDFfMcZ8wbn9Y2PMUuf2JcaYPxtjLjfGrDLGrDPG/M0Yk+7cP88Y87IxZq0x5jljTPEJ5/UZY+43xvx39L8rERERcYvmFiLDgxIYIuKGV4DzndvzgXRjTAKwCNgE/BdwqbV2LrAG+Hfn/p8D11lr5wG/B+7scc544C/A29ba/4rOtyEiIiIeobmFyDAQ73YAIjIsrQXmGWMygDZgHcHJxvnAk8BUYKUxBiARWAVMAqYDLzjjcUBlj3P+GnjYWttz4iEiIiLDg+YWIsOAEhgiEnXW2g5jzF7gE8BrwFvARcB4YA/wgrX2gz2PMcbMALZYa8/t47SvARcZY/7HWtsaseBFRETEczS3EBketIVERNzyCvBl5/OrwGeBDcDrwEJjzAQAY0yqMeYsoBwoMMac64wnGGOm9Tjf74Cngb8ZY5ScFRERGX40txAZ4pTAEBG3vAoUA6ustYeBVuBVa20N8HHgAWPMWwQnHZOtte3AdcD3jTEbCU5Izut5QmvtjwguGf2TMUb/v4mIiAwvmluIDHHGWut2DCIiIiIiIiIip6QsooiIiIiIiIh4nhIYIiIiIiIiIuJ5SmCIiIiIiIiIiOcpgSEiIiIiIiIinqcEhoiIiIiIiIh4nhIYIiIiIiIiIuJ5SmCIiIiIiIiIiOcpgSEiIiIiIiIinqcEhoiIiIiIiIh4nhIYIiIiIiIiIuJ5SmCIiIiIiIiIiOcpgSEiIiIiIiIinqcEhojEBGOMNcZMGK7XFxERkfBy+3e729cXiUVKYIgIAMaYbxlj/hzF691sjFlrjGkwxhw0xvzAGBMfreuHkxP7Aed72WeM+U+3YxIREXGbC3OLjxtjAsaYph4fF0br+uFkjLnBGPOaMeaYMWa52/GIeIUSGCISFgNIPqQCXwLygXcBlwBfdimWwfodMNlamwmcB3zIGHNtlGMQEREZUgb4+3yVtTa9x8dyF2MZjCPAT4C7o3xdEU9TAkNkmDHGfNUYU2GMaTTGlBtjLjHGXAF8DbjRebdio/PYkcaYJ40xR4wxO40xn+5xnm8ZYx4xxvzZGNMAfNwYk2WM+Z0xptK5xn8bY+J6i8Na+0tr7avW2nZrbQXwF2DhacK/0hiz2xjjN8bcY4zxObF83Biz0hjzY2PMEeBbxpjxxpilxpha5/F/McZk94h/rzHmy8aYt4wx9caYh4wxyT3uv835Pg4ZYz55qqCsteXW2uYeQ12AloSKiMiw4JW5xQB5dW7xorX2YeBQGL9XkZinBIbIMGKMmQR8HjjbWpsBLAb2WmufBb4HPOS8WzHLOeQB4CAwErgO+J4x5pIep7wGeATIJpiAuB/oJPjH+xzgcuBfzjC8C4Atp3nM+4H5wFzn2j1/+b8L2A0UAncCBrjLiX0KUAZ864Tz3QBcAYwFZgIfB3AmXV8GLgMmApeeLnhjzO3GmCaCz1ca8NfTHSMiIhLrPDi3mOMkF942xnz9DFZOeHZuISInUwJDZHgJAEnAVGNMgrV2r7V2V28PNMaUAYuAr1prW621G4DfAh/t8bBV1trHrbVdQCbwHuBL1tpma2018GPgptMFZYz5BMHJww9P89DvW2uPWGv3E1xW+cEe9x2y1v7cWttprW2x1u601r5grW2z1tYAPwLefcL5fmatPWStPQL8A5jtjN8A/MFau9lZWfGt030P1tq7gQyCE6A/AfWnO0ZERGQI8NLc4hVgOsGEwwcIzhNuO038np1biMjJlMAQGUastTsJ1p34FlBtjHnQGDOyj4ePBI5Yaxt7jO0DSnp8faDH7dFAAlBpjKkzxtQBvyY4ieiTMWYJwf2d77HW+k/zLfS83j4nxt7uwxhT6Hx/Fc4y1D8TrLfRU1WP28eAdOf2yF6udVo2aD3QAnz7TI4RERGJZV6aW1hrd1tr91hru6y1m4DvEFzlcSqenluIyPGUwBAZZqy1f7XWLiI4KbDA90N3nfDQQ0CuMSajx9gooKLn6XrcPgC0AfnW2mznI9NaO62vWJzllL8B3udMNE6n7IRYeu4LPTH+u5yxmU5xzY8QXPp5Jip7uVZ/xAPj+3mMiIhITPLS3OLE0Dj97/5YmVuICEpgiAwrxphJxpiLjTFJQCvBlQIB5+7DwJhQ8Spr7QHgNeAuY0yyMWYm8CmC+1FPYq2tBJ4H/scYk2mM8TnFrk5cWhmK5WLnXB+w1q4+w2/hNmNMjrME9YvAQ6d4bAbQBNQZY0o4/RLSnh4mWDhsqjEmFfhmXw90vs/POHEZY8w5wOeAl/pxPRERkZjksbnFe4wxRc7tycDXgSdO8y14bm4BYIyJcwqAxgM+5/lK6Mf1RIYkJTBEhpckgts1/ASXOBYSrBAO8Dfnc60xZp1z+4PAGILvRjwGfNNa+8Ipzv8xIBHYChwlWISruI/Hfh3IAp427/Rqf+Y08T8BrAU2AE8RbF/al28TrEdR7zz20dOcu5u19hmC+2CXAjudz6fyfmAX0EhwOenPnQ8REZGhzktzi0uAt4wxzcDTBH/3f+808Xt1bvFRgsmgXwLnO7d/c6bXExmqjLUnrowSEREREREREfEWrcAQEREREREREc9TAkNEREREREREPE8JDBERERERERHxPCUwRERERERERMTzlMAQEREREREREc+LdzsAr8jPz7djxoxxOwwRERmk3TXNAIwrSHM5kuFj7dq1fmttgdtxeI3mFiIiQ4PmFtHX19xCCQzHmDFjWLNmjdthiIjIIN3x6FsA3HXtTJcjGT6MMfvcjsGLNLcQERkaNLeIvr7mFkpgiIjIkKLJhYiIiIST5hbeoRoYIiIiIiIiIuJ5SmCIiMiQcsejb3Uv9RQREREZLM0tvENbSEREZEgJFdrqqaOjg4MHD9La2upCRENHcnIypaWlJCQkuB2KiIhI1Jw4t9C8Inz6O7dQAkNERIa8gwcPkpGRwZgxYzDGuB1OTLLWUltby8GDBxk7dqzb4YiIiLhG84rwGMjcQltIRERkyGttbSUvL0+TjEEwxpCXl6d3m0REZNjTvCI8BjK3UAJDRESGBU0yBk/PoYiISJB+J4ZHf59HbSEREZEhZerITLdDGJTly5eTmJjIeeedN+BzpKen09TUFMaoREREhi/NLbwzt1ACQ0QkBj2+voJ7nivnUF0LI7NTuG3xJJbMKXE7LE/45vumDfocbj6/y5cvJz09fVCTDBER6Z1+f8pADHZu4fbP3VCaW2gLiYhIjHl8fQV3PLqJiroWLFBR18Idj27i8fUVboc2JETq+V2yZAnz5s1j2rRp3HvvvQA8++yzzJ07l1mzZnHJJZewd+9efvWrX/HjH/+Y2bNn8+qrr/Lxj3+cRx55pPs86enpADQ1NXHJJZcwd+5cZsyYwRNPPDGo+EREhjr9/hQ3RPLnbjjOLTy3AsMYEwesASqstVcZY3KBh4AxwF7gBmvtUeexdwCfAgLAF6y1zznj84D7gBTgaeCL1lob3e9ERCQy7nmunJaOwHFjLR0B7nmuXO8iAV96cD0AP7lpTq/3f/sfW9h6qKHP49fvr6M90HXcWEtHgK888hYPrN7f6zFTR2ae9t2Z3//+9+Tm5tLS0sLZZ5/NNddcw6c//WleeeUVxo4dy5EjR8jNzeWzn/0s6enpfPnLXwbgd7/7Xa/nS05O5rHHHiMzMxO/38+CBQu4+uqrtSdXRKQP+v0pA3WquYVb8woYnnMLzyUwgC8C24DQRqPbgZestXcbY253vv6qMWYqcBMwDRgJvGiMOctaGwB+CdwCvE4wgXEF8Ex0vw0Rkcg4VNfSr/HhprJ+cF0yTpxknG78TP3sZz/jscceA+DAgQPce++9XHDBBd1tw3Jzc/t1PmstX/va13jllVfw+XxUVFRw+PBhRowYMag4RUSGKv3+lIEazNwiUvMKGJ5zC08lMIwxpcB7gTuBf3eGrwEudG7fDywHvuqMP2itbQP2GGN2AucYY/YCmdbaVc45/wgsQQkMERkiRmanUNHLZGtkdooL0cSe072jsfDupb0+vyXZKTz0mXMHdM3ly5fz4osvsmrVKlJTU7nwwguZNWsW5eXlpz02Pj6erq7gJMdaS3t7OwB/+ctfqKmpYe3atSQkJDBmzBi1OBUROQX9/pRIcGNeAcN3buG1Ghg/Ab4C9ExHFVlrKwGcz4XOeAlwoMfjDjpjJc7tE8flDDy+voKFdy9l7O1PsfDupdoTKOJBty2eREpC3HFjKQlx3LZ4kksRDS2ReH7r6+vJyckhNTWV7du38/rrr9PW1sbLL7/Mnj17ADhy5AgAGRkZNDY2dh87ZswY1q5dC8ATTzxBR0dH9zkLCwtJSEhg2bJl7Nu3b8DxiYgMB/r9KW6I1M/dcJ1beCaBYYy5Cqi21q4900N6GbOnGO/tmrcYY9YYY9bU1NSc4WWHLhU2EokNS+aU8O2rp3Z/nRTv465rZ2j/bpgsmVPCXdfOoCQ7BUPwHZLBPr9XXHEFnZ2dzJw5k69//essWLCAgoIC7r33Xq699lpmzZrFjTfeCMD73vc+Hnvsse5CW5/+9Kd5+eWXOeecc3jjjTdIS0sD4MMf/jBr1qxh/vz5/OUvf2Hy5Mnh+PZFRIas0P/viXHBP4HijNHvT4m4SMwrYPjOLYxXalsaY+4CPgp0AskEa2A8CpwNXGitrTTGFAPLrbWTnAKeWGvvco5/DvgWwUKfy6y1k53xDzrHf+ZU158/f75ds2ZNJL61mHGq5U0rb7/YhYhEpC+7a5q4+H9eJjM5Hgts/Mbl+HzeKbDkpu8/ux2Ar17xzi/dbdu2MWXKFLdCGlJ6ey6NMWuttfNdCsmzNLcQ8aaLfricPf5mAN78z0spyEhyOSLxuhPnFppXhFd/5haeWYFhrb3DWltqrR1DsDjnUmvtR4AngZudh90MhHq5PAncZIxJMsaMBSYCq51tJo3GmAUmWC71Yz2OkVNQYSOR2FHlFJO6fNoIGls72VnT5HJE3vHVKyYfl7wQERHpyd/YxrSRwX4Bbx2sczcYiQmaW3iHZxIYp3A3cJkxZgdwmfM11totwMPAVuBZ4HNOBxKAW4HfAjuBXaiA5xnpq4CRChuJeE9VQzCB8d4ZxQCs3XfUzXBERERiQmtHgMa2Ti6cVIDPwMYDdW6HJCL94MkEhrV2ubX2Kud2rbX2EmvtROfzkR6Pu9NaO95aO8la+0yP8TXW2unOfZ+3Xtkn43HBAjPH/0gkJ/hU2EjEg0LtvN41LpfctEQlMHr47J/W8tk/nWk5JRERGU78TW0AjMpN5ayiDNYrgSFnQHML7/BkAkPcsWROCV+6dOJxY9fPK1VhIxEPOtzQSlZKAqmJ8cwdlcM6JTC6HT3WztFj7W6HISIiHuRvCv5+yE9PYs6obDYeqEPvdcrpaG7hHUpgyHES44Mtfl657SKKMpOobmxzOSIR6U1lfSsjMpMBmDc6h93+Zo406xeriIjIqfiduW1+ehKzSrNpaO1kb+0xl6MSkTOlBIYcZ+VOP6PzUhmVl8p7phezvLyG5rZOt8MSkRMcbmhlRFYwgTF3VDaAVmGIiIicRmgLSX5GErPKsgHVwRCJJUpgSLeOQBev7z7Cwgn5AFw5o5i2zi6Wbq92OTIROVHPFRgzS7OJ9xnW7VcCYzhYvnw5V111FQBPPvkkd999d5+Praur4xe/+EW/r/Gtb32LH/7whwOOUUTEq2qd1Yp5aYlMLEwnJSGODUpgyDAXS3MLJTCk24YDdTS1dXK+k8CYNzqHgowknt5U6XJkItJTR6ALf1Nb9wqMlMQ4po3MVCFPx8IJ+d2J2EGprIR3vxuqqgZ/rjMQCARO/6ATXH311dx+++193j/QSYaIyFBV09hGRlI8yQlxxMf5mFGSxUa1UpXTCMvcIsrzChiacwslMKTbih1+jIHzxgdfnHE+w3umj2BZeTXH2rWNRMQrqhvbsJbuBAbA3NE5bDxYR0egy8XIvOELl0zkC5dMPP0DT+e734UVK4KfB2nv3r1MnjyZm2++mZkzZ3Lddddx7NgxxowZw3e+8x0WLVrE3/72N55//nnOPfdc5s6dy/XXX09TUxMAzz77LJMnT2bRokU8+uij3ee97777+PznPw/A4cOHef/738+sWbOYNWsWr732Grfffju7du1i9uzZ3HbbbQDcc889nH322cycOZNvfvOb3ee68847mTRpEpdeeinl5eWD/p5FRLzI39RGfkZS99ezyrLYcqiB9k79/pS+hWVuEcZ5BQzfuUV8WM4iQ8KKnX5mlmSRlZrQPfae6cX8cdU+lm2v4b0zi12MTkRCqpwWqj0TGPNG5/CHlXvZVtnAzNJslyKLIRdeePLYDTfA//t/cOwYXHIJrF4NXV3wq1/B+vVwyy3w8Y+D3w/XXXf8scuXn/aS5eXl/O53v2PhwoV88pOf7H73Ijk5mRUrVuD3+7n22mt58cUXSUtL4/vf/z4/+tGP+MpXvsKnP/1pli5dyoQJE7jxxht7Pf8XvvAF3v3ud/PYY48RCARoamri7rvvZvPmzWzYsAGA559/nh07drB69WqstVx99dW88sorpKWl8eCDD7J+/Xo6OzuZO3cu8+bNO/PnU0QkRvib2shPT+z+elZZNu2v7qG8qpEZpVkuRiYxzYV5BQzPuYUSGAJAQ2sHGw7U8dl3jztu/JyxueSnJ/L05kolMEQ8ojuBkXl8AgNg7b6jwz6BcfPvVwNw/yfPGfhJ9u2DUFs9a4NfD1JZWRkLFy4E4CMf+Qg/+9nPALonDa+//jpbt27tfkx7ezvnnnsu27dvZ+zYsUycOLH72Hvvvfek8y9dupQ//vGPAMTFxZGVlcXRo8dvK3r++ed5/vnnmTNnDgBNTU3s2LGDxsZG3v/+95OamgoEl4+KiAxF/qZ2Jhamd3892ynkueHAUSUwpE+DnltEYF4Bw3NuoQSGAPDG7iMEuiyLJhQcNx7nMyyeNoJH11XQ0h4gJTHOpQhFJKSqIZjAKO6xAqM4K4XirGTW7a/jEwvdiswbWjvOYL/nqd7ZqK+Ho0ePn2gcPQpXXBH8Oj//jN8Z6ckY0+vXaWlpzmUsl112GQ888MBxj9uwYcNJxw6UtZY77riDz3zmM8eN/+QnPwnbNUREvMzf1Ma54/K6vy7JTiE/PZENB+r56LkuBiaedtq5hQvzChiecwvVwBAAVuyoISUhjrmjs0+6770zimnpCPDy2+pGIuIFhxtaSYr3kZWScNz43NE5aqUaDt/9bnCJZ0+BwKD3rO7fv59Vq1YB8MADD7Bo0aLj7l+wYAErV65k586dABw7doy3336byZMns2fPHnbt2tV9bG8uueQSfvnLXzrhBmhoaCAjI4PGxsbuxyxevJjf//733ftfKyoqqK6u5oILLuCxxx6jpaWFxsZG/vGPfwzqexUR8aKOQBd1xzrIT3+nBoYxhlml2SrkKZEToXkFDM+5hRIYAsCrO/2cMzaXpPiTV1icMzaX3LREntoUvYq5ItK3yvpWirOST8pqzxuVQ0VdC5X1LS5FNkSsWgXt7cePtbfDa68N6rRTpkzh/vvvZ+bMmRw5coRbb731uPsLCgq47777+OAHP8jMmTNZsGAB27dvJzk5mXvvvZf3vve9LFq0iNGjR/d6/p/+9KcsW7aMGTNmMG/ePLZs2UJeXh4LFy5k+vTp3HbbbVx++eV86EMf4txzz2XGjBlcd911NDY2MnfuXG688UZmz57NBz7wAc4///xBfa8iIl5U2xT8vz0/I/G48Vll2eyqaaKhtcONsGSoi9C8Aobn3MLY0FKWYW7+/Pl2zZo1bofhikN1LZx391L+671T+Jfzx/X6mDse3cSTGypY+/XLSE7QNhIRN93wq1UYAw995vi1rhsP1HHN/63k/z40d1jXrLnx18F3Ino+P9u2bWPKlCluhcTevXu56qqr2Lx5s2sxhEtvz6UxZq21dr5LIYVi2As0AgGg01o73xiTCzwEjAH2AjdYa486j78D+JTz+C9Ya59zxucB9wEpwNPAF6211hiTBPwRmAfUAjdaa/eeKqbhPLcQ8aLNFfVc9fMV/Pqj81g8bUT3+Mtv13Dz71fz1395F+eFow23DDknzi3cnlfA8J1baAWGsGKnH+CUvY2vnDGC5vYAL79dE62wRKQPlQ0tx9W/CJk6MpPkBB9rh/k2kkumFHLJlEK3wxB3XGStnd1jwnM78JK1diLwkvM1xpipwE3ANOAK4BfGmFB2/pfALcBE58PZpMyngKPW2gnAj4HvR+H7EZEw8je1ARzXhQRgllO8c4O2kUgfNLfwDhXxFFbs8JOfnsTkERl9PmbBuDxyUhN4ZlPlcRlrEYkuay2H69so6iWBkRDnY2ZJNmv3D+8Exi0XjHc7hJOMGTNmSLxDEoOuAS50bt8PLAe+6ow/aK1tA/YYY3YC5zirODKttasAjDF/BJYAzzjHfMs51yPA/xpjjNVSVpGY4Q9tIelRAwMgOzWRMXmpbDxQ50JUEgs0t/AOrcAY5rq6LCt3+lk0Ie+UVWIT4nxcPnUEL26rPrMK/yISEUea22kPdB3XQrWnuaNz2HqoXq9TGY4s8LwxZq0x5hZnrMhaWwngfA69fVYCHOhx7EFnrMS5feL4ccdYazuBeiAPEYkZ76zASDrpvtll2WxQAkPE85TAGOa2VzVS29x+yu0jIVfOLKaprZNXd/ijEJmI9Ka3Fqo9zRudQ0fAsqmiPpphecqNv17VvVe1J71RPngefw4XWmvnAu8BPmeMueAUj+0tY29PMX6qY44/sTG3GGPWGGPW1NRo26WIl/gb20hJiCMt6eRF6LPKsjnc0EZVfasLkYnX9Ta38PjvxJjR3+dRCYxhbsXO4OTq/IkFp33seePzyEoJbiMREXeEJlZFfa3AGJUNMOzrYJwoOTmZ2tpaTTYGwVpLbW0tycm9/+y5zVp7yPlcDTwGnAMcNsYUAzifQ/3ADwJlPQ4vBQ4546W9jB93jDEmHsgCjvQSx73W2vnW2vkFBaf/3Soi0eNvajupA0nIrLJsAK3CkDOieUV4DGRuoRoYw9yKnbVMKExnRB/v5vYU3EZSxLObq2jrDPTaclVEIuudFRgpvd6fl57E2Pw0JTBOUFpaysGDB9E74oOTnJxMaWnp6R8YZcaYNMBnrW10bl8OfAd4ErgZuNv5/IRzyJPAX40xPwJGEizWudpaGzDGNBpjFgBvAB8Dft7jmJuBVcB1wFLVvxCJLf6m9l63jwBMLc4k3mfYeLCOK6ar3pucmuYV4dPfuYUSGMNYa0eA1XtquensUWd8zJUzivnb2oOs3Onn4slFEYxORHpTVd+Kz5xcQb2nuaNyWF5ejbX2lLVthpOEhATGjh3rdhgSOUXAY87PezzwV2vts8aYN4GHjTGfAvYD1wNYa7cYYx4GtgKdwOestaHCMbfyThvVZ5wPgN8Bf3IKfh4h2MVERGKIv6mNstzUXu9LTohjSnGmCnnKGdG8wj1KYAxj6/YdpbWji0X96He9cEI+GcnxPPVWlRIYIi6oqm+lMCOZ+Li+dwDOHZ3N39cdZP+RY4zOS4tidCLusNbuBmb1Ml4LXNLHMXcCd/YyvgaY3st4K04CRERik7+pjTmjcvq8f1ZZFo+vP0RXl8Xn0xsAIl6kGhjD2IqdfuJ8hgXjz7yIemK8j8umFvHC1iraO7siGJ2I9KaqobXXFqo9zRsdnJwN120kV80s5qqZxW6HISIiHhLoshxpbqfgFCsYZ5Vm09TWyW5/UxQjk1iguYV3KIExjK3Y6WdOWTbpvVRiPpX3ziimobWTlbvUjUQk2qrqWynuo4BnyMTCDDKS4odtAuOj547ho+eOcTsMERHxkKPH2umywVpRfZnjFMJev78uOkFJzNDcwjuUwIiQx9dXsPDupYy9/SkW3r2Ux9dXuB3ScY42t7Opop5FE898+0jIoon5ZCTFqxuJiAuq6ltPW3Q3zmeYPSp72CYwWtoDtLQHTv9AEREZNvxNbQB9FvEEGJefTnpSPBsP1kUpKokVmlt4hxIYEfD4+grueHQTFXUtWKCiroU7Ht3kqSTGqt21WAvnDyCBkRQfx6VTi3h+62E6AtpGIhItzW2dNLZ1nlHXoHmjcyg/3Ehja0cUIvOWj/9hNR//w2q3wxAREQ/xN7YDpy6C7fMZZpZmsfFAfbTCkhihuYV3KIERAfc8V05Lx/EZupaOAPc8V+5SRCd7dYef9KR4ZpZmD+j490wfQd2xDlbtqg1vYCLSp1AL1RGn2UICwU4k1qJJmIiICD1WYGT0vQIDYFZZNtsqG2jt0LvtIl6kBEYEHKpr6de4G1bsrGHBuDwSTtHJ4FQuOKuAtMQ4ntY2EpGoqap3EhhnsAJj9qhsjBm+hTxFRER6OpMtJBAs5NnZZdla2RCNsESkn5TAiICR2Sn9Go+2/bXHOHCkZUDbR0KSE+K4ZEoRz22polPbSESiojuBcQYrMDKTE5hUlMHa/UpgiIiI1DS1kRjnIzP51MXrZ5dlA7DxQF3kgxKRflMCIwJuWzyJlIS448ZSEuK4bfEklyI63qs7awBYOGHgCQyAK2cUc/RYB6/vPhKOsETkNLq3kJzBCgyAuaNzWL/vKF1dNpJhiYiIeJ6/sZ389ESMMad83IisZIoyk5TAEPGo/vXPlDOyZE4JEKyFUVHXgs/AnUumd4+7bcUOP8VZyYwvSBvUeS6cVEBqYhxPb64cUDcTEemfqvpWslMTSD4hQdqXeaNy+Osb+9lR3cSkERkRjs47rptX6nYIIiLiMf6mttPWvwiZXZbNBiUwpAfNLbxDKzAiZMmcElbefjG/+PBcuizknKLicTQFuiyv7apl0YT802agTyc5IY6LJxfy3GZtIxGJhsr61jPaPhIyb3QOMPzqYFw/v4zr55e5HYaIiHiIv6nttPUvQmaVZbO39hh1x9ojHJXECs0tvEMJjAi7dEoRuWmJPLT6gNuhALC5op76lo6wrZi4ckYxtc3trN6rbSQikXa4ofWMt48AjM5LJTctkXXDrA7GkeZ2jjRr0ikiIu+obWonL+3M3lCc7XTp23hQnbwkSHML71ACI8IS4318YG4JL2473F392E0rdvqBwde/CLloUiEpCepGIhIN/V2BYYxh7qgc1g2zFRi3/nktt/55rdthiIiIR1hrqW0+8y0k00uzMEaFPOUdmlt4hxIYUXDj2WV0dlkeXXfQ7VBYscPPlOLMM15CdzopicFtJM9uPkxAhQJFIqa9s4va5rZ+rcCA4DaS3f5mvWsgIiLDVn1LBx0Be8bz38zkBMYXpCuBIeJBnkpgGGOSjTGrjTEbjTFbjDHfdsa/ZYypMMZscD6u7HHMHcaYncaYcmPM4h7j84wxm5z7fmYGW/BhECYUZjB/dA4PvnkAa937I7+lPcDafUdZNCEvrOd9z4wR+JvaeFPbSEQiprqxFWvPrIVqT6E6GMNtFYaIiEhIaBV0fj9q0s0qzWbjwTpX5+4icjJPJTCANuBia+0sYDZwhTFmgXPfj621s52PpwGMMVOBm4BpwBXAL4wxofL8vwRuASY6H1dE79s42Y1nl7G7ppk1Lv4R8caeWtoDXSyaWBDW8140qZDkBB/PaBuJSMQc7mcL1ZCZpVnE+wxrh1kdDBERkZCaxuAqxIJ+rECeXZaFv6mdirqWSIUlIgPgqQSGDWpyvkxwPk6V9rwGeNBa22at3QPsBM4xxhQDmdbaVTaYNv0jsCSCoZ/We2cWk54Uz4MuFvNcudNPYpyPc8bkhvW8aUnxXHhWIc9srqJL20hEIqKyfmAJjOSEOKaNzNQKDBERGba6V2CcYQ0MgNllwRWMaqcq4i2eSmAAGGPijDEbgGrgBWvtG85dnzfGvGWM+b0xJscZKwF6ZgQOOmMlzu0Tx12TmhjP+2aN5KlNh2ho7XAlhld3+Jk3OoeUxLjTP7ifrpxZTHVjm97lFYmQKieBUZyZ0u9j547OYePBOjqGSbvjjywYzUcWjHY7DBER8Yh3tpCceQJj0ogMEuN9qoMhgOYWXuK5BIa1NmCtnQ2UElxNMZ3gdpDxBLeVVAL/4zy8t7oW9hTjxzHG3GKMWWOMWVNTUxOG6E/tprPLaO3o4skNhyJ+rRPVNLaxvaoxbO1TT3Tx5EIS43089Za2kYhEwuGGVpITfGSmxPf72Hmjc2jt6GJbZUMEIvOe980ayftmjXQ7DBER8Qh/UxtxPkN2SsIZH5MY72PayEw2HlArVdHcwks8l8AIsdbWAcuBK6y1h53ERhfwG+Ac52EHgbIeh5UCh5zx0l7GT7zGvdba+dba+QUF4a0L0ZuZpVlMHpHBQ29GfxvJa7uC7VMXhal96onSk+K58KwCntU2EpGIqKxvpTgrhYHUIw4V8lw7TLaRHKpr4ZD2LIuIiMPf2E5eWiI+X/9+h84qzWZTRT2dw2QFo/RNcwvv8FQCwxhTYIzJdm6nAJcC252aFiHvBzY7t58EbjLGJBljxhIs1rnaWlsJNBpjFjjdRz4GPBGt76MvxhhuOruMTRX1bDkU3Wzuqzv8ZKUkML0kK2LXuHJGMVUNraw/MDz+SBKJpsMNrRRlDqz9cXFWCiOzkodNAuPfHtrAvz20we0wRETEI2qb28jrx/aRkNll2bR0BNhR3XT6B8uQprmFd3gqgQEUA8uMMW8BbxKsgfFP4AdOS9S3gIuAfwOw1m4BHga2As8Cn7PWBpxz3Qr8lmBhz13AM1H9TvqwZE4JifE+Ho7iKgxrLSt2+Fk4IY+4fmae++OSKYUkxvl4elNVxK4hMlyFVmAM1NzROSrkKSIiw1JNU3u/WqiGzCrLBlAdDBEP8VQCw1r7lrV2jrV2prV2urX2O874R621M5zxq50VFqFj7rTWjrfWTrLWPtNjfI1zjvHW2s9bjzRxzk5N5D3TR/DY+gpaOwKnPyAMdtU0U9XQysIIbR8JyUhO4IKz8nlmU6W2kYiEUVeXpbqhjaLM/nUg6WnuqBwO1bdSWa/ljyIiMrz4G9v61UI1ZExeKlkpCWw8WBf+oERkQDyVwBgubjy7jIbWTp7dHJ2VCit2BAuUnj8h8nU+rpxRzKH6Vv1HLxJGR4610x7oorifLVR7CtXBWLevLkxRiYiIeJ+1Fn9TW79aqIYYY5hVls36/XXhD0xEBkQJDBcsGJvHqNxUHnxzf1Sut2Knn1G5qYzKS434tS6ZUkRCnOHpTepGIhIuoRaqg1mBMXVkJskJvmFTB0NERASgqa2Tts6uAW0hAZhdmsXbhxs51t4Z5shEZCCUwHCBz2e48ewyXt99hD3+5oheqyPQxeu7j0R8+0hIVkoC508s4OlNVXhk145IzAslMEYMYgVGQpyPmaXZrN0/9BMYnz5/HJ8+f5zbYYiIiAf4m9oByB/AFhII1sHosrC5Yni0IpfeaW7hHUpguOS6eaX4DDy8JrLFPDceqKOprZPzJ0YngQHwnukjqKhr4a2D6pstEg5VDcEExmC2kEBwG8mWivqo1d9xy6VTi7h0apHbYYiIiAf4m9qAgScwZpZmAyrkOdxpbuEdSmC4pCgzmYsnF/LI2oMR7S396g4/xsB54/Mido0TXT51BPE+w9ObtY1EJByq6luJ85kBT75C5o3KobPLsqliaCcXd9U0satGLe9ERCRYwBMGnsAoyEiiJDuFDarvNqxpbuEdSmC46MazR1HT2May8pqIXWPlTj8zSrLITh3Yvr+ByEpNYOGEfJ7eVKltJCJhUNXQSmFG0qDbIM8ZlQ0w5OtgfO3RTXzt0U1uhyEiIh7QvQIjY+Bz4dll2VqBMcxpbuEdSmC46KJJBRRmJPFQhIp5NrZ2sP5AHYuiVP+ip/fOKObAkRa2HNJ+QZHBqqpvHVQBz5C89CTG5qcN+QSGiIhIiL+pHWMgdxBv5s0uy+bg0ZbuZIiIuEcJDBfFx/m4bl4pS7dXdxfpC6fXdx8h0GVZFMX6FyGXTS0izmd4St1IRAatqqF10PUvQuaOymHdvqNaHSUiIsOCv6mNnNRE4uMG/mfPrLJsQHUwRLxACQyX3TC/jC4Lf193MOznXrnTT3KCj3mjc8J+7tPJSUvkvPF5PKNtJCKDFq4VGBAs5Fnb3M6+2mNhOZ+IiIiX+ZvaBtxCNWR6SSY+owSGiBcogeGyMflpLBiXy0NvHqCrK7x/6L+6o4ZzxuaRFB8X1vOeqStnFLO39hhbK7WNRGSgmto6aWrrDNsKjFBCU9tIRERkOPA3tQ+6CHZqYjxnFWWwQR32RFynBIYH3HT2KPYfOcbru2vDds7K+hZ21TRzvgv1L0IWTxtBnM/wzKYq12IQiXWh7WUjwpTAmFiYTkZSPOv2D90Exr9ePJF/vXii22GIiIgHBFdgDC6BAe8U8tTK4uFJcwvvUALDA66YPoLM5HgefPNA2M65YocfgIUuJjBy0xJZMC5X3UhEBqE7gRGmLSQ+n2H2qOwhvQJj0cR8V2r/iIiI9/gbw5PAmFWWTX1Lh7ZgDlOaW3iHEhgekJwQx/vnlPDslirqjrWH5ZwrdvrJT09k8oiMsJxvoK6cUcxufzPlhxtdjUMkVlU1hHcFBgS3kZQfbqSxtSNs5/SSLYfq2XJIy3xFRIa7lvYAze2BQbVQDZlVmg3AxoN1gz6XxB7NLbxDCQyPuPHsUbR3dvH4+opBn6ury7Jyp5+FE/Lx+UwYohu4xdNG4DPw9FvqRiIyEFX1LQBhK+IJwQSGtbBhiBYj+84/tvKdf2x1OwwREXFZqO1pOFZgnFWUTkpC3JD93SmnprmFdyiB4RFTR2YyszSLB988MOjtFuWHG/E3tbu6fSQkPz2Jd43N4+nNqoMhMhBVDa3kpCaQnBC+Yryzy7IxRoU8RURkaKtxEhgFYUhgxMf5mFGSpQSGiMuUwPCQG88uY3tVI28NssJxqP7F+R7Zp3XljBHsrG7ibW0jEem3cLZQDclITmBSUQbr9teF9bwiIiJeUtsU3JqdN8g2qiGzyrLYcqiB9s6usJxPRPpPCQwPuXrWSFIS4gZdzPPVnX7GF6RRnJUSpsgGZ/H0ERgDT2/SNhKR/qpqaA1bC9We5o7OYf2+o2Fv3ywiIuIV4dxCAsFCnu2dXZRX6U05EbcogeEhGckJXDmjmCc3VNDc1jmgc7R1Bli9p5ZFHtg+ElKYkczZY3KVwBAZgKr61rAW8AyZNyqHxrZOdlQ3hf3cIiIiXuBvDCYwwrYCwynkuUGFPEVcowSGx9x0ThnN7QGeGuAf+2v3HaW1o4tFEwvCHNngvHdGMW8fbmJntTLWImeqvbMLf1M7IzLDv5pq3ugcYGjWwfjKFZP4yhWT3A5DRERc5m9qIzM5nqT48NSRKs1JIS8tkY2qgzHsaG7hHUpgeMz80TmMK0jj4QFuI1mxw0+cz7BgXG6YIxucK7q3kaiYp8iZOtzdQjU8S197Gp2XSl5a4pBMYMwbncu80d76P1BERKLP39ROfkb4focaY5hVlq0ExjCkuYV3KIHhMcYYbjq7jDX7jg5otcLKnX5ml2WTkZwQgegGrigzmfmjc7SNRKQf3klghH8FhjEmWAdj/9BLYKzdd4S1+464HYaIiLispqktbPUvQmaXZbOzponG1o6wnle8TXML71ACw4OunVtKvM/wUD9XYdQda+etinpP1b/o6T3Ti9le1cjuGu25FzkTlfVOAiPMXUhC5o7KYbe/mSPN7RE5v1t+8Gw5P3i23O0wRETEZf6mtrC0UO1pVlk21sKmQXYNlNiiuYV3KIHhQfnpSVw2tYi/r6voV5um13bVYq132qee6D0zRgDwzGZtIxE5E++swIhMAiNUB2PdENxGIiIi4m9sIz9MBTxDZpVmASrkKeIWJTA86sazyzjS3M6L2w6f8TErdvpJT4pnVll25AIbhOKsFEbnpvDjF95m7O1PsfDupTy+vsLtsEQ8q7K+lZSEODKT4yNy/pmlWcT7DGuH4DYSGZ6MMXHGmPXGmH86X+caY14wxuxwPuf0eOwdxpidxphyY8ziHuPzjDGbnPt+ZowxzniSMeYhZ/wNY8yYqH+DInLG2ju7aGjtJC/MKzCyUxMZk5eqOhgiLlECw6POn1jAyKxkHuzHNpIVO/wsGJdLQpw3/1kfX1/BofpWOrssFqioa+GORzcpiSHSh6qGVoqzknH+fgq75IQ4ppVkDclCnjJsfRHY1uPr24GXrLUTgZecrzHGTAVuAqYBVwC/MMaE2hT8ErgFmOh8XOGMfwo4aq2dAPwY+H5kvxURGYza5mAL1XDXwACcQp7aQiLiBm/+pSvE+QzXzS/j1R01HDx67LSP3197jP1Hjnm2/gXAPc+V0xGwx421dAS45zntJxPpzeH6VooiVP8iZN6oHN46WEdH4My3q4l4kTGmFHgv8Nsew9cA9zu37weW9Bh/0FrbZq3dA+wEzjHGFAOZ1tpV1loL/PGEY0LnegS4xEQquygig+ZvDNZ3CvcWEoBZpdlUNbRS5dSqEpHoUQLDw66fVwrA39YcPO1jV+z0A7DIo/UvAA7VtfRrXGS4q6wPrsCIpHmjc2jt6GJbZUNErxNN33jfVL7xvqluhyHR9xPgK0DPbFyRtbYSwPlc6IyXAD2XOB50xkqc2yeOH3eMtbYTqAfyTgzCGHOLMWaNMWZNTU3NIL8lERkof5OzAiOMbVRDQtu1N6oOxrChuYV3KIHhYWW5qSyakM8jaw8S6LKnfOyKnTWMyExmfEF6lKLrv5HZvbeC7GtcZDjr6rJUN7ZSFOEExtzR2QBDahvJtJFZTBuZ5XYYEkXGmKuAamvt2jM9pJcxe4rxUx1z/IC191pr51tr5xcUFJxhOCISbjVOAiPcXUgApo3MJN5nVAdjGNHcwjuUwPC4m84eRUVdS/cKi94Euiwrd9ayaGJ+xPbKh8NtiyeRkhB33FhKQhy3LZ7kUkQi3lXb3E5HwEZ8BUZxVgojs5KHVAJjxQ4/K3b0/X+mDEkLgauNMXuBB4GLjTF/Bg4720JwPlc7jz8IlPU4vhQ45IyX9jJ+3DHGmHggCzgSiW9GRAavewVGBBIYyQlxTCnO1AqMYURzC+9QAsPjLp1aSG5aIg+9ub/Px2w5VE99S4en618ALJlTwl3XzqAkO/gHWVK8j7uuncGSOSWnOVJk+Am1UI10DQyAuaNzhlQr1Z8v3cHPl+5wOwyJImvtHdbaUmvtGILFOZdaaz8CPAnc7DzsZuAJ5/aTwE1OZ5GxBIt1rna2mTQaYxY49S0+dsIxoXNd51zj1MsjRcQ1/sZ20hLjSEmMO/2DB2BWWRZvHain6zSrpGVo0NzCO5TA8Lik+DiunVPCC1sPd2eST/Sqkw1c6PEEBgSTGCtvv4RPLRqLBS6bWuR2SCKeVOkUBhsRhQTGvNE5HKpvpbJe9WhkyLkbuMwYswO4zPkaa+0W4GFgK/As8DlrbcA55laChUB3AruAZ5zx3wF5xpidwL/jdDQREW/yN7VFpP5FyKzSbBrbOtntb4rYNUTkZEpgxIAbzy6jI2B5bF3v7UZX7PAzeUQGBRH8TzrcLp1SRHtnF6/uUIEzkd5UOSswIr2FBIIJDIB1++oifi2RSLPWLrfWXuXcrrXWXmKtneh8PtLjcXdaa8dbaydZa5/pMb7GWjvdue/zoVUW1tpWa+311toJ1tpzrLW7o//diciZ8je1RWT7SMhsp5DnBrVTFYkqJTBiwMSiDOaOyubBN/dz4mrVlvYAa/cd9fz2kROdPSaHrJQEnt962O1QRDypqr6FOJ8hL4KTr5ApxZkkJ/iGVB0MEREZ3mqb2slLC38L1ZBxBemkJ8WrkKdIlCmBESNuOnsUu2qaT/oDY/XeI7QHujzdPrU38XE+Lp5cyLLt1XQGuk5/gMgwU1XfRlFGEnG+yBfmTYjzMbM0m7X7lcAQEZGhIdJbSOJ8hhklWSrkKRJlnkpgGGOSjTGrjTEbjTFbjDHfdsZzjTEvGGN2OJ9zehxzhzFmpzGm3BizuMf4PGPMJue+nxkvt+c4A++dWUxaYhwPvnnguPEVO2pIjPNxzthclyIbuMumFnH0WIfe9RXpRVVDS8RbqPY0b3QOWyrqae0InP7BHve9a2fwvWtnuB2GiIi4pDPQxZFj7RHdQgIwe1Q22yobhsTvTjk1zS28w1MJDKANuNhaOwuYDVxhjFlAsFDWS9baicBLztcYY6YSrDY+DbgC+IUxJlRq+JfALQQri0907o9ZaUnxXD17JE+9VUlja0f3+IqdtcwdnU1qYryL0Q3MBWcVkBjn48Vt2kYicqKq+tao1L8ImTcqh84uy1sHY38v7/iCdMYXpLsdhoiIuOTIsXashYL0yG0hgWAhz46AZVtlQ0SvI+7T3MI7PJXAsEGhUr4JzocFrgHud8bvB5Y4t68BHrTWtllr9xCsGH6O0+s901q7yim+9ccex8SsG88eRUtHgH9srASgprGNbZUNnD+xwOXIBiY9KZ5zx+fxwtbDJ9X2EBnuqupbo9JCNWSuU8hzKKyIenHrYV5UfR0RkWHL39gOEPkVGN2FPOsieh1xn+YW3uGpBAaAMSbOGLMBqAZesNa+ARQ5vdlxPhc6Dy8Beu6pOOiMlTi3TxyPabNKs5g8IoOH3twPwGu7gu1TY62AZ0+XTi1ib+0xdtWoBZVISGNrB83tgaiuwMhNS2RcfhrrhkAdjN+8upvfvKoGESIiw5W/qQ0gojUwAEZkJVOUmaRCnsOA5hbe4bkEhrU2YK2dDZQSXE0x/RQP762uhT3F+PEHG3OLMWaNMWZNTY3323kaY7jx7DI2Hqxn66EGVuzwk5WSwPSSLLdDG7BLpwRzUepGIvKOqvpgC9VorsAAmDMqh3X7jmpFlIiIxLTuBEYUOnnNKs1m4xDYfikSKzyXwAix1tYBywnWrjjsbAvB+VztPOwgUNbjsFLgkDNe2sv4ide411o731o7v6AgNrZhvH9OCYnxPh56cz8rdvo5b3xeVLoUREpxVgozSrK0JEukh6qGYAKjOCslqtedNzqH2uZ29tUei+p1RUREwumdBEZka2AAzCrLZo+/mbpj7RG/loh4LIFhjCkwxmQ7t1OAS4HtwJPAzc7DbgaecG4/CdxkjEkyxowlWKxztbPNpNEYs8DpPvKxHsfEtOzURKYVZ3L/qn1U1reyalctj6+vcDusQbl0ShHrD9RR09jmdiginhBagTEiyisw5g2hOhgiIjJ8+ZvaSYr3kZ4U+SL3oToYQ6EItkgs8FQCAygGlhlj3gLeJFgD45/A3cBlxpgdwGXO11hrtwAPA1uBZ4HPWWtDfYxuBX5LsLDnLuCZaH4jkfL4+gq2HHqn0nFdSwd3PLopppMYl00twlpYul2rMETgnQRGYWbkl772NLEwnYykeNYOgToYIiIyfPmb2shPTyL4PmZkzSjNwhhUB0MkSjzVe9Na+xYwp5fxWuCSPo65E7izl/E1wKnqZ8Ske54rpz3QddxYS0eAe54rZ8mc2KxTOqU4g5LsFF7Yepgbzx7ldjgirqtqaCU3LZHkhLjTPziMfD7DnNHBOhix7Mc3znY7BBERcZG/qT0q20cAMpMTGF+QzsaDdVG5nrhDcwvv8NoKDDmNQ3Ut/RqPBcYYLptaxKs7/LS0B05/gMgQV1XfGvXtIyFzR2VTfriRxtYOV64fDiOzUxiZHd36ISIi4h3+xraoFPAMmVWazYYDdSqCPYRpbuEdSmDEmL5eOLH+grp0ShFtnV2s2Ol3OxQR11U1tDIiii1Ue5o3OgdrY7un/T82HuIfG0+q2ywiIsNEaAtJtMwuy8Lf1E5FDL+hKKemuYV3KIERY25bPImUE5aVpyTEcdviSS5FFB7vGpdLRnI8L2ytcjsUEddV1bdGvYVqyOyybIyJ7UKef359H39+fZ/bYYiIiAu6uiy1ze3kZ0RnCwkEO5EAbDygQp5DleYW3qEERoxZMqeEu66dQUl2CgYoyU7hrmtnxGz9i5CELxYcqAABAABJREFUOB8XTirkpW3VBLq0/E6Gr7bOALXN7RS7tAIjIzmBSUUZMZ3AEBGR4auupYNAl43qCozJIzJJjPOpDoZIFHiqiKecmSVzSmI+YdGby6YW8Y+Nh9hw4CjzRue6HY6IK6obgu2E3aqBAcFtJE9uOERXl8Xni3wFdxERkXDxNwV/j0YzgZEY72PqyMyY3n4pEiu0AkM8491nFRDvM7ywtdrtUERcU9UQbKHqVg0MCCYwGts62VHd5FoMIiIiA+FvjH4CA4JbMDcdrKfzhG6BIhJeSmCIZ2SlJLBgXJ7qYMiwVlnvfgJj7qgcILbrYIiIyPBU46zAKIhiDQwIJjBaOgLsrFHyXySSlMAQT7l0SiG7aprZrf/8ZZg67IEExui8VPLSEmM2gfHLj8zjlx+Z53YYIiLigtqmdgDy0qK7AiNUyHPD/rqoXleiQ3ML71ACQzzl0qlFALy47bDLkYi4o7K+ldTEODKS3CtRZIyhOCuZxzdUMPb2p1h491IeX1/hWjz9lZuWSG5adN95ExERb/A3tRHvM2SlJET1umPyUslMjlchzyFKcwvvUAJDPKU0J5UpxZm8qDoYMkwdbmhlRFYyxrhXPPPx9RVsr2ok0GWxQEVdC3c8uilmkhh/W3OAv6054HYYIiLiAn9TG3npiVEvQm2MYVZZNhvUSnVI0tzCO5TAEM+5bGoRa/Yd4Uhzu9uhiERdVUOrqx1IAO55rpzOE9oZt3QEuOe5cpci6p9H1h7kkbUH3Q5DRERc4G9qj3oBz5DZZdm8fbiRY+2drlxfIkdzC+9QAkM857IpRXRZWLpdqzBk+Kmqb3W1/gXAobqWfo2LiIh4hb+pzbUExqzSbAJdli2HGly5vshwoASGeM70kkxGZCarG4kMO11dNriFxOUVGCOzU/o1LiIi4hX+RhcTGE4hz40H6ly5vshwoASGeI4xhkunFvLK235aOwJuhyMSNf7mNjq7LMUur8C4bfEkUhLijhtLSYjjtsWTXIpIRETk9Ky1wS0kUW6hGlKQkURJdgoblMAQiRglMMSTLp1SREtHgNd2+d0ORSRqDtcHe9cXubwCY8mcEu66dgbZqcEK7oUZSdx17QyWzClxNS4REZFTaWjtpD3QRYFLKzAgWAdDCQyRyIlInz5jzPXAs9baRmPMfwFzgf+21q6LxPVk6Dl3fB5piXG8sLWaiycXuR2OSFRU1gdrTBRnub9VY8mcEqaXZHLpj17htsWTYip5cd8nznE7BBkgzR9EYsPj6yu457lyDtW1MDI7xTO/J/xNwTcC3NpCAhDng4NHWxh7+1Oeem5kcDS38I5IrcD4ujP5WAQsBu4Hfhmha8kQlBQfx7snFfDitsN0ndANQWSoOtzQCkBRlnsTr57G5aeTkRwfc+8kpSTGkZIYd/oHihdp/iDicY+vr+CORzdRUdfiuVbbtU3BDnZ56e5sIXl8fQXPbjkM4LnnRgZHcwvviFQCI1S44L3AL621TwDu/E8iMeuyqUXUNLbxVoX6acvwUFnfSrzPkJ/mjQSGz2eYVRp7S2H/tGovf1q11+0wZGA0fxDxuHueK6flhBplXmm17fYKjHueK6e9s+u4Ma88NzI4mlt4R6QSGBXGmF8DNwBPG2OSIngtGaIumlRInM/w4tbDbociEhVVDa0UZSbj8xm3Q+k2uyyb7VWNtLTHTkHdf75VyT/fqnQ7DBkYzR9EPM7LrbbdTmB4+bmRwdHcwjsiNSm4AXgOuMJaWwfkArdF6FoyRGWnJnL2mBxeUAJDhomq+laKMr2x+iJkdlmwp/3mQ1oJJVGh+YOIx3m51ba/sQ2fgdw0dxZuefm5ERkqIpLAsNYeA6qBRc5QJ7AjEteSoe3SKUWUH25kf+0xt0MRibiqhlZPFPDsKdTTfsP+OlfjkOFB8wcR7/Nyq+2apnZy0xKJc2klY2/PTXKCzxPPjchQEZEEhjHmm8BXgTucoQTgz5G4lgxtl00NdiB5YZtWYcjQZq11VmC420L1ROppL9Gk+YOI9y2ZU8L33j+dUIogKd7nmVbb/qY2VzuQhNqQl2SndD8/751R7InnRmSoiNQWkvcDVwPNANbaQ0BGhK4lQ9jovDTOKkpXHQwZ8hrbOjnWHqA4y1sJDIDZo2KvkKfELM0fRGLAuePzsUC8z5CdmuCZP9DdTmBAMImx8vaL2X3XlcwbncPru4/QEeg6/YEickYilcBot9Zagh2EMMakReg6MgxcNrWI1XuPUHes3e1QRCKmqj7UQtV7CYw5ZdlU1LVQ3djqdihn5KHPnMtDnznX7TBkYDR/EIkBu2qaADh3fB6HG9pobO1wOaKgYALDG42LjDF87qLxVNS18MSGQ26HI4OkuYV3RCqB8bBTRTzbGPNp4EXgNxG6lgxxl04pItBlWV5e43YoIhETSmB4cgWG6mBI9Gj+IBIDQgmMy52tvnv8zW6G083f2O76CoyeLppUyOQRGfxi+U4CXdbtcETC6vH1FSy8eyljb3+KhXcv5fH1FVG5bqSKeP4QeAT4OzAJ+Ia19ueRuJYMfbNKsynISFI3EhnSqhqCCYwRHquBATC9JIt4n4mZbST3vrKLe1/Z5XYYMgCaP4jEhl3VTaQnxXPu+Lzg105Cw03H2jtp6QiQ56EERnAVxgR21zTz3JYqt8ORQdDc4niPr6/gjkc3UVHXggUq6lq449FNUUliRKy3urX2BWvtbdbaL1trX4jUdWTo8/kMl04p5OW3a2jrDLgdjkhEhFZgFHqsjSpAckIck4szYiaB8dK2al7aVu12GDJAmj+IeN+ummbGF6QxKjeNOJ9hV7X7KzD8jcGtxl7ZQhJy5Yxixuan8X/LdhLcISexSHOL493zXDktHcf/XdbSEeCe58ojfu2wJjCMMY3GmIZePhqNMQ3hvJYML5dOKaKprZPXdx9xOxSRiKhqaCUvLZGk+LjTP9gFs8uyeetgvZbASkRo/iASW3bVNDG+IJ3EeB+jc1PZ7Xd/BUZNUxsA+RneeiMgzme49d3j2XKogZff1nZoGRoO1bX0azycwprAsNZmWGsze/nIsNZmhvNaMrwsnJBPSkKcupHIkFVV38oID9a/CJldlkNTW6cnlgnL0KP5g0jsaGrrpLK+lfGF6QCMK0j3xgoMJ4FR4KEtJCFL5pQwMiuZ/1u20+1QRMJiZHZKv8bDKWJbSACMMYXGmFGhj0heS4a25IQ4zp+Yz4vbDmv5nQxJVfWtnqx/EaJCnhJNmj+IeNeemmCyYnxBWvfnPbXNrq/QCyUwvFTEMyQx3sctF4zjzb1HWb1Hq4kl9t22eBIpCcevGk5JiOO2xZMifu2IJDCMMVcbY3YAe4CXgb3AM5G4lgwfl00torK+lS2HtJpYhp6qhlZPtlANGZefRkZyPBsO1rkdymklJ8SRnBCZrThuVdweLjR/EPG+0Eq88QXp3Z/bO7uoOBr5peOnEqqBkeexGhghN549iry0RK3CiFGRnFvEoiVzSvjvJdO6vy7JTuGua2ewZE5JxK8dH6HzfhdYALxorZ1jjLkI+GCEriXDxMWTC/EZeH7rYaaXZLkdjkjYtHYEONLcTrGHV2D4fIbZZdkxsQLj/k+eE5Hzhipuh4pWhSpuA1H5hT1MaP4g4nG7apqI8xlG5aUCML4wrXs8NOYGf1Mb2akJJMRFdIH5gKUkxvHJRWO557lyNlfUay4bYyI1t4hlU4qDP8M/vWk218yO3jwoUq/wDmttLeAzxvistcuA2RG6lgwTeelJzBudozoYMuRUNwSXvXp5BQYEt5GUH26kpX14dgP63tPbXKu4PYxo/iDicbtqmhiVm9pddHpcfnr3uJv8TW2e3D7S00fPHU1GcrxWYciQsKmiDoCZpdlRvW6kEhh1xph04BXgL8aYnwKdEbqWDCOXTilia2UDFVGocCsSLVUNwRaqxTGQwAh0WTZV1Lsdyin97KUd/OylHWE737r9R/n0H9dQ3djW6/3RqLg9jAxo/mCMSTbGrDbGbDTGbDHGfNsZzzXGvGCM2eF8zulxzB3GmJ3GmHJjzOIe4/OMMZuc+35mjDHOeJIx5iFn/A1jzJhwf/MisWBXdXN3/QuAnLREctMS2VXjbiHPYALDm9tHQjKTE7j53DE8u6WKndWNbocj/RDuucVQsKminoykeEbnRnflVaQSGNcAx4B/A54FdgHvO91BxpgyY8wyY8w2ZwLyRWf8W8aYCmPMBufjyh7H9GsCIrHtsqlFAFqFIUNKZX3wD2AvF/EEmBUq5HngqLuBnMbKnX5W7vQP6hzWWpZtr+aGX6/i2l+8xpt7j5CR3Puuy2hU3B5GBjR/ANqAi621swiu2LjCGLMAuB14yVo7EXjJ+RpjzFTgJmAacAXwC2NMaHPzL4FbgInOxxXO+KeAo9baCcCPge8P6jsViUGBLssef3N3/YuQ8QVprq/AqG1qJ8/jKzAAPrFwDEnxPn65fLfboUg/hGNuMdRsOhjcCuXzRffP7IhuErPWdgKrCBbhOpPKi53Af1hrpxDcA/s5Z5IB8GNr7Wzn42kY8AREYti4gnTGFaTx4jYlMGToOOyswPByG1UIVnYvzUlhw4E6t0OJmM5AF4+vr+A9P32VT9z3JgePHOPrV01l5Vcv5rvXTD+p4nZygi8qFbeHm/7OH2xQ6K+nBOfDEkyI3O+M3w8scW5fAzxorW2z1u4BdgLnGGOKgUxr7SobbHn1xxOOCZ3rEeASvTkiw83Bo8doD3SdlMAYl5/ObpcTGDVNbZ5soXqivPQkPnjOKB7fUMGBI8fcDkdkQDoCXWyramRGafRruUQqgfEKkGyMKSH4jscngPtOd5C1ttJau8653QhsA05VEWQgExCJcZdNLeL13bU0tHa4HYpIWFTWt5KWGEdGcoLboZxWrBTy7K+W9gD3rdzDu+9Zzpce2kCgy/I/18/i5a9cxKcWjSUtKZ4lc0q469oZlGSnEPqr9ZLJhSrgGV4Dmj8AGGPijDEbgGrgBWvtG0CRtbYSgnMMoNB5eAlwoMfhB52xEuf2iePHHeMkWOqBvP59eyKxrbsDSWHacePjC9PwN7VTf8yduVlrR4DG1k7PbyEJueWCcfgM3PuKVmFIbHr7cCPtnV3McKEYbaQSGMZaewy4Fvi5tfb9wNTTHHP8CYJ7S+cAbzhDnzfGvGWM+X2PPawDmYBIjLtsShEdAcvL5TVuhyISFocbWj2/+iJkdlk2h+pbqXZWjcS6o83t/PTFHSz8/lK+9Y+tjMhK5rcfm89zX7qAD8wrPama/ZI5Jay8/WL23P1ezp+Yz9p9dXQEulyKfkga8PzBWhuw1s4GSgm+mTH9VNfp7RSnGD/VMcef2JhbjDFrjDFramr0e0qGll3VwToXocKdIaEVGbv87qzCqG0OtlD1ehHPkOKsFD4wt5SH1hygunFo/D6V4WXTwWA9tCGVwDDGnAt8GHjKGTvjlq1OAa+/A1+y1jYQ3A4ynuC+1krgf0IP7eXw001Ael5Hk4wYNGdUDnlpibygOhgyRFTWx04CY86obADWe3gbSU5qIjmpp34X7lBdC9/5x1YWfn8pP37xbeaUZfO3z57L3289j0unFp3Rfs6bzx1DVUMrz22pClfoMsj5A4C1tg5YTnDr6GFnVSbO52rnYQeBsh6HlQKHnPHSXsaPO8YYEw9kAUd6uf691tr51tr5BQUF/QldxPN21TSRl5ZITtrx/8eOCyUwqt1JYPidIsuxksAA+Oy7x9MZ6OJ3K/a4HYqcgTOZWwwnmyrqyUiOZ7QLrZP7NSnohy8CdwCPWWu3GGPGAcvO5EBjTALB5MVfrLWPAlhrD/e4/zfAP50vBzIB6WatvRe4F2D+/PknJTjEm+J8hosnF/Lslio6Al2e7fctcqYO17dy7vh8t8M4I9NGZhHvM2w4UMfiaSPcDqdXv/rovD7ve/twI796eRdPbgj+Srh61kg+8+7xTBqR0e/rXDS5kFG5qdz/2l6umjlywPHKcQY0fzDGFBBswVpnjEkBLiVYZPNJ4GbgbufzE84hTwJ/Ncb8CBhJsFbWamttwBjT6BQAfQP4GPDzHsfcTLA2x3XAUmebqsiwsaum6aT6FwBlOSkkxBl2+93pROJvchIYGbGTwBiTn8ZVM0fy51X7uPXd48nWH8eedqq5xXC0qaKeGSVZuFEKKiIJDGvtKwT3sYa+3g184XTHOcWwfgdss9b+qMd4cWgPK/B+YLNzeyATEBkCLptaxN/WHmT1niMsnBAbf/iJ9CbQZalubGNEVmxMupIT4phSnOnZOhiPr6/gnufKOVTXwsjsFG5bPIklc0pYs/cIv3p5Fy9uqyYlIY6Pnjuafzl/HCWD6CAS5zN87NzR/PdT29hcEazELYMz0PkDUAzc7xTy9gEPW2v/aYxZBTxsjPkUsB+43jnvFmPMw8BWggXEP2etDTjnupVg3Y0U4BnnA4Lzkz8ZY3YSXHlx02C+V5FYtKummcXTik4aj4/zMSYvzb0VGKEERozUwAi59cLxPLnxEPe/to8vXjrR7XBEzkh7ZxfbKxv5xMIxrlw/UiswBmoh8FFgk1OIC+BrwAeNMbMJbgPZC3wGBjwBkSFg0cR8kuJ9vLD1sBIYEtNqm9ro7LKMyIqdVpyzy7J5dN1BAl2WuCi3zjqVx9dXcMejm2jpCP4aqKhr4SuPvMVPX3qbPf5j5KQm8KVLJ3LzuWNOWv48UNfPL+NHL7zNfa/t5YfXzwrLOaX/rLVvEaybdeJ4LXBJH8fcCdzZy/ga4KT6GdbaVpwEiMhwdKS5nSPN7b2uwAAYV5DGTtcSGLFVAyNkSnEml04p5A+v7eFfzg8WjBZv+v6z2wH46hWTXY7EfW8fbqQ90OVKBxKIcBvV/rLWrrDWGmvtzJ4tU621H7XWznDGr+6xGgNr7Z3W2vHW2knW2md6jK+x1k537vu8lnkOLamJ8SyakM8LWw+jf1qJZVWhFqqZsVEDA4IJjOb2gGsT1b7c81x5d/IipD3Qxf7aFr75vqmsvP1ivnTpWWFLXgBkpSTwgbmlPLnhUPc7gCIiQ1GoTWpfCYzxBensP3LMlcLGNY1tpCfFk3xCq+tY8P8umkDdsQ7++sZ+t0ORU1i37yjr9h11OwxP2FThXgFPiFACwxiz8EzGRAbjsqlFVNS1sL2q0e1QRAassj6YwCiOkSKeALOdQp4bDnjrF/mhupZex7us5RMLx5KaGJl3tm4+bzTtgS4eXK3J52Bp/iDiXbtOk8AYV5BOR8By4MixaIYFBLuQxNr2kZC5o3I4b3wev3l1N60nJOFFvGhTRT2ZyfGMyo1+AU+I3AqM3upNqAaFhNXFUwoxBnUjkZh22FmBURRDKzDG5qWRmRzPBo91IhnZRz2LvsbDZUJhBudPzOdPr+9TS9XB0/xBxKN21TSTGO+jJKf3/1PHF6R1Py7a/I1tMbd9pKfPXTSB6sY2/r7uoNuhiJzWpoP1zCh1p4AnhDmBYYw51xjzH0CBMebfe3x8C4i9NV3iaYUZycwuy+bFbUpgSOyqrG8lIc6QF8ZtDZHm8xlmlWWz4UC926Ec57bFk0hJOP7XWkpCHLctnhTxa39i4RgON7Tx7Ga1VB0IzR9EvG9XdRPj8tP6rH0UaqUa2moSTf6m2E5gnDc+j1ll2fzq5V10KhEuHtbWGWB7VYOrhcvDvQIjEUgnWBw0o8dHA8GWYyJhdemUIt46WE+VswxfJNYcrm+lMCMZn4eKYZ6JOWXZlFc1cKy90+1Qui2ZU8Jn3j2+++uS7BTuunYGS+aURPzaF55VyOi8YEtVGRDNH0Q8rq8WqiFZKQnkpyd1bzWJJv//Z+/O46Msr/6Pf67sOwkkYUnY9x0EUcQdFdRaqXVttVp9tLX21+VpbbX7U+uj1lqf2kVrq3WtVq1rXRDFXQRRkACCEtaEkIWQZbIv1++PuSeEkIQsM3PPTL7v1yuvJPfM3HMCk8k1Z851jqeBzNTweSOgI2MM3z5lAnvK63hhw163w5FODB+UEFbbfQPls30emloss3LSXYvBrxuCrbVvAW8ZYx6w1u7y57lFOnPGtKHcvnwrr31azKXHjnY7HJFeK6qsZ1gY/kGcMyqdVustIzxm3BC3w2nT0NxKdJTh45+dzqCk2KDdb1SU4WsLx3DTfza3lVZKz2n9IBLaGppb2F1eyxdnj+j2euOzkoO+haSppZUDtU1hXYEBsHhKNpOHpvKXN/I5d3ZO2L2xEen+7+LDBl0NSG438AT/byH5P+fLPxljnu/44c/7EgGYkJ3C6CFJ6oMhYau4KjwTGLNz0wFCrg/Ga5uLOWbs4KAmL3wumJ9LUlw0D/SnCqOoCE46CfYFaCtKoM/fR1o/iIS2XftrabUwPrvrCgzwXh7sLSTlNeE5QrWjqCjDt04Zz+clHlZoe7SEqLzCCgYlxjJycGD7i3XH31tIHnY+/w64o5MPEb8yxnD61KGsyt+PpyF0StlFesJa663ACKMGnj5DUuIZOTgxpBIYO8tq+LzEQ0ur5X9e2BT0+09LiOX8ebm88Ek/RqredBO8+673cyAE+vx9p/WDSAjLL+l+AonPuMxkDtQ2tSUVgqG02vt8G+4JDICzZw5n9JAk/vzGNqy1bocj7fzPC5tcWVuEmrzCSmbmuNfAE/y/heQj5/Nb/jyvSHdOmzaUv7+7g3c+K+XMmcPdDkekx6rqm6lragnbPZVzRmawdme522G08TX0bWhuZfPeKldi+NrCMTy0ahePrd7N/1s8sXc3LiqCf/wDWlvhnntg3TqIc/Z0X3ghfOtbUFsLZ511+G2vuML7UVYG53fSMuLaa+HEE+H++73n/8c/4Oc/h2HDevsjBoTWDyKhzdfXYmxmcrfX81Vo5Jd6GJw8OOBxAW0J46ww7oHhExMdxTdPGs+NT+fx7rYyTpiY5XZI4nBrXRFKGppb2Lqvmv86YZyrcQRkjKoxZpExZoUx5jNjzHZjzA5jzPZA3JfI/NEZpCfFahuJhB1f89lwGqHa3pyR6RRV1reNgnXbis3FTBmWSnxMoCaEH9mE7BROnJTVt5GqN93kTS4AWAu7/NwK4qabvOcFaGkJxSoMrR9EQlR+aQ0jBiWQHN/9e58TXJhEst/jrfYYkhz+FRgA5x2Vw7C0BP78xja3QxE5xNZ91TS1WFf7X4CfKzDauQ/4PvAR0BKg+xABvNnqUydns3JrCc0trcREu/fiRaQ39jkv/MO3AiMdgHW7K1g6w9138g/UNPLhznKuO2UCa3a4WxXy9ePG8PUHPuTljfuO2PCuja/6otEpu7YWDhyAxx8/tEoiKQnefLPr82Rmdn55UZG3QsN3/sbGkKvCcGj9IBKC8ks9R+x/ATAiPZG4mKigNvL0VWBkpkZGAiM+JpqrTxzHTf/ZzEe7ypk3OjiVLCJHEgoNPCFAFRhApbX2ZWttibV2v+8jQPclwunThlJR28TaXQfcDkWkx4rDvAJj+og0YqNNSPTBeGNrCa3WO1rZbSdNymJMb0eqtq++8PFnlUSgz+8/Wj+IhBhrLfkl3Y9Q9YmOMozLTA5qBUaZp4GE2CiS46KDdp+BdsmCkWQkxfLnN/LdDkWkTV5BJelJseRmuNfAEwKXwHjDGHO7MWahMeYo30eA7kuEEyZlERcdxWvaRiJhpCjMExgJsdFMHZ7G+j3uJw5XbC5maFo8M3MGMS4rmXFZ3e/TDiTfSNWPdh1gQ0FFz260atXB6gifxkZ4/33/BBXo8/uP1g8iIaa4qoGaxhbG9/B5dXxWSpArMBrJTIl3tamgvyXFxXDlorGs3FLCpr2Vbocj4PraIhSEQgNPCNwWkmOcz/PbHbPAqQG6PxngUuJjOG7CEFZ8WsxPz57q+i+WSE/sq6onMyWOOBd7NvTXnJHp/PujAlpaLdEuzayvb2rhrc9KWTY3h6gowy3nzXIljvbOn5/LHa9u5YH3d/L7C+cc+Qbr1gU2oECf33+0fhAJMb4Gnj3ZQgLeF3qvbNpHY3NrUP6+lXkaImICSUdfWziGv769nbvfzOdPX1Ee122hsLZwU32Tt4HnNSe628ATAlSBYa09pZMPLT4koE6bOpRd+2vZVhLc+eMifbWvso5hYdr/wmfOyHRqGlv4vKTatRhWbd9PbWMLp09zf/uIj2+k6n8+KWob8SdHpvWDSOjxJTAm9GALCXgrMFpaLbvLg1OFUVodmQmMQUmxXLZwNC/mFQV1S45IZ7buq6a51f0GnhC4KSS/6OwjEPcl4tPs7O8+/c63WXTrSp5dV+hyRCLd21fVwLAw3T7i42vkuX53hWsxvLa5mKS4aBaOGwLAjU9v4ManN7gWj8/XjhtDY0srj63Z7XYoYUPrB5HQk1/iITU+hqweNsn09crYVhKcBEaZpzEiRqh25spFY4mLjuKet9QLw22hsrZwS1sDz9wITWAANe0+WoAzgTEBui8Rnl1XyG0vb237vrCijhufzlMSQ0JaJFRgjM1MZlBirGuNPFtbLa99WsyJE7NIiPU2cNteWsP2IO6/7sr4rBROmpTFIx/sorG5lyNVBy6tH0RCTH5pDeOyU3q8PXes0ycgPwhVAy2tlvKayKzAAMhKjefio0fy9MeFFFbUuR3OgBYqawu35BVUkpEUS066uw08IXBbSO5o93EzcDKQE4j7EgG4fflW6poOnbhX19TC7cu3dnELEXfVN7VwoLYp7CswjDHMHpnuWgJj495KiqsaQmr7SHtXLBpDSXUDL28scjuUsKD1g0joyS/19LiBJ3j7kg1LSwjKi70DtY20WiI2gQFwzUnjAfjb29tdjkQGsrzCSmaEQANPCFwFRkdJgPsdPyRi7e0iK93VcRG3FVeF9wSS9uaMTOez4mpqGpqDft8rNhcTZeCUKdlBv++eOGliFmMzk3s3UlXa0/pBxEWehmaKKut7NEK1vXFZyUGpwNjv8U5XGpISmVtIAHLSE/nS3Bwe/3A3ZR71VJLgq29q4bPiamaFwPYRCFwPjDxjzAbnYxOwFfhDIO5LBGBEF+VMXR0Xcds+Z4Tq8EHh/xidOzKdVntwf2QwrdhczPwxgxmcHJqLV+9I1dF8vLuCT1yqUgknWj+IhJYdThVFbxMY3lGqHqy1gQirje8FfSRXYAB88+TxNDS3cv+7O9wORQagLSHUwBMCV4HxBeAc5+MMYIS19k8Bui8Rrl8ymURn/7tPQmwU1y+Z7FJEIt3b51RgDBsU/ouu2b5GnkF+gb6nvJYt+6o5feqh20emjUhj2oi0oMbSnfPn5ZIcF60qjJ7R+kEkhGwr9U6YmpDd8y0kAOOzkqmub6bMqZAIlIGSwBiflcJZM4fz8KpdVNY1uR3OgBRqa4tgyiuoAGBmbrqrcfjEBOKk1tpdgTivSFeWzfVukb59+Vb2VtRhgXNmj2g7LhJqfBUYwyKgAmNwchyjBicFfRLJa58WA3Bah/4XvzxnelDjOJLUhFgumD+SR1fv4oazppCdGv7bhgJF6weR0JJfUkN0lGHU4N4lMMY5FRv5pZ4eTy/pC9+Y6qwIT2AAfOvk8by4oYhHPtjFdadMcDucASfU1hbBlFdYyeDkOEaESOP5YPXAEAm4ZXNzeO+GU9l+y1mMzUymqKLe7ZBEulRUWU9KfAwp8QHJIwfdHBcaea7YXMyE7BTGZvZuYe2Gry0cTVOL5bHVe9wORUSkx/JLPYwenERcTO9eMozPPpjACKQyTyNx0VGkJUbG39LuTB8xiKnDUrnj1a2MveFFFt26UtP2JCg2FFQyM0QaeIISGBKBjDGcNXMYq7bvp7wmsKWLIn1VXFUf9iNU25szMp19VfVtlSWBVlnbxOod5Z1OH/ne4+v43uPrghJHT43LSuHkyVk8slojVUUkfOSXetqqKXpjeFoCibHRAZ9EUuZpYEhKXMi8sAqkZ9cVkl9WQ6sFCxRW1HHj03lKYgRJKK4tgqG+qYXPSzwh0/8ClMCQCHXmjOG0tFpe3bTP7VBEOlVUWR/2I1TbmzMqHYD1ew4E5f7e/KyEllbLaVMPT2AUVdZTFKRESm9ccdwYSjVSVUTCRHNLKzvLahnfy/4X4G1gPDYz8JNIyjwNEd//wuf25VsPS4DXNbVw+/KtLkU0sITq2iLQPi2qoqXVMkMJDJHAmj4ijdFDkngxTy8UJDRFWgXGtOFpxEYb1gVpG8mKzcVkpsQx12kgGg5OnJjFuMxk/vHeTrdDERE5ooIDdTS2tPZ6AonP+OyUICUwQnMKlb/trajr9HhhRR3/2bCXhuaWIEckA4FvwlyojFAFJTAkQhljOHPGcN7P388BbSORENPSaimpboioCoyE2GimDU8LSiPPxuZW3tpayuIpQ4mKCp+y4agow+XHjWH9noqg9wsREektX/KhzwmMrGQKDtRR3xS4F9Zl1Y0DpgJjRHrnTb+jDXz7n+s45n9f55fPbWSjCyPNJXLlFVQyJDmO4SH0ppsSGBKxzp7p3UayYnOx26GIHKLM00BLq42oCgzw9sHIK6ykpdUG9H5W79hPdUNzp/0vQt2X5+WSEh+jkaoiEvIOJjD61ih5XFYK1sLO/YHpg2GtZX9NA0MGSALj+iWTSYyNPuRYYmw0t58/m4euXMAJE7N47MM9fOGP73LmH97hH+/tUC846be8wkpm5oZOA09QAkMi2IycNHIzEnlJ+80lxLSNUI2gCgzw9sGobWzhs+LqgN7Pa5uLSYiNYtGEzE4vP2p0BkeNzghoDH2VEh/D+fNy+c+GvZRUD7y9tCISPvJLashMiSM9qW9bNHyJj/ySwCQwquqaaWqxA2YLybK5Odxy3kxy0hMxQE56IrecN5Pz5uVy4qQs/njJXD78yWncdO50YqIM//PCZo7539f41qMf8caWEppb1EC6P0J5bREodY2h18ATIPJnDsmAZYzh7JnDuf+9HVTWNjEoKdbtkEQA2ppARV4FhvcP+/o9FUwdnhaQ+7DWW1V1wsQsEuOiO73Oj5dOCch9+8vlx43hgfd38s/Vu/neaZPcDkdEpFN9nUDiMy7Te9vtAeqDUeppACArdWBUYIA3ibFsbk6Xlw9KiuWyhWO4bOEYPi2q4sm1BTy7vpCX8vYxNC2e847K5YJ5uf36fx2oQn1tEQibnQaeoZbAUAWGRLQzZw6nqcWy4lNtI5HQUVwVmQmMMUOSSE+KDWgfjM1FVeytrOf0TqaPhIuxmcmcMjmLRz7YrZGqIhKy8ks9fe5/AZAYF01OemLAGnmWOQmMgdIDo7emDk/jF+dM44MbF3PPpUcxY8Qg7n17O6fe8Rbn3/0+//pwN56GZrfDlBDm66cyM4QaeIISGBLhZucOIic9kZc0jURCSFFlPXHRUQzuY1luqDLGMDs3PaANKldsLsYYOHVqdpfX+ebDH/HNhz8KWAz+cMWisZR5GvTcJCIhqbymkQO1TX3uf+EzLiuZ/NLAbCFRAqNn4mKiWDpjOPddcTSrbjiVG86cwoHaRn787zyO/s1r/OCJT1i9fT/WWp5dV8iiW1cy9oYXWXTrSp5dV+h2+CEjHNYW/pZXWElmSlzIbXnWFhKJaN5pJMN4cNVOquqbSEvQNhJxX3FVPdlp8WE1QaOn5oxM567PP8fT0ExKvP//xLz2aTFHjcrodsF6oDb0m5adMCGTcVnJ/OP9nd2WA4uIuKGtgWd2/7YajM9K4cm1e7DW+r0JYFm1L4ERWW8GBFJ2WgLfPGk83zhxHB/vruCpj/bwwidF/PvjAoYkx1JZ10yz04i7sKKOG5/OA9DfKcJjbeFveQWVzMwJrQaeoAoMGQDOmuXdRvKappFIiCiqrAu5bLa/zBmVjrXeP3r+treijo2FVWE5faSjqCjDFceN4ZM9FazbfcDtcEREDpFf4k1gTOhnr4TxWcnUNLZQXNXgj7AOUeZpJDrKkBFh1YzBYIxh3ugMbjlvFmt+upjfXzib6oaWtuSFT11TC7cv3+pSlOImbwPP6pDrfwFKYMgAMCc3neGDEngpb5/boYgAUFzVEHH9L3zm5KYDBGQbyetOL5vTwrj/RXvnHaWRqiISmvJLPcTHRDEiPbFf5/H10AhEH4wyTwODk+MispoxmJLiYjjvqFyauujJtLeiLsgRSSjYXFRJq4WZzroulIRUAsMYM9IY84Yx5lNjzCZjzHed44ONMSuMMZ87nzPa3eZGY8w2Y8xWY8ySdsfnGWPynMvuMqFW+yJBExVlOHPGcN7+vJTq+ia3w5EBzlob0RUYGclxjBmSxPo9/q8qeHVzMWMzk/u9JztUpMTHcMH8XF7MK6KkSiNVRSR05JfWMDYzmeh+Jgd80y4CMYmkzNOg/hd+1FWyamiEvuEi3fNV0qoC48iagR9Ya6cCxwLXGWOmATcAr1trJwKvO9/jXHYxMB1YCvzFGOObq3c3cA0w0flYGswfRELLWTOH0djcysotJW6HIgNcVV0z9U2tEVuBATB7pP8beVbXN/HB9v2cPm3oEfdiLpqQyaIJmX69/0C5fOEYmlstj67e7XYoIiJt8ks9/e5/ATA0LZ7kuOiANPIs8zSq/4UfXb9kMomxh48nb2puCdgo3HASTmsLf9hQWElWajxD00IvSRhSCQxrbZG19mPn62rgUyAHOBd40Lnag8Ay5+tzgcettQ3W2h3ANmCBMWY4kGatXWWttcBD7W4jA9BRozIYmhbPixsGZsd/dZUOHUVV3lLMSE5gzBmZTnFVA0WV/is7feuzUppabI+2j3xn8US+s3ii3+47kMZkJnPK5GweXb2bhuYWt8MREaG+qYU95bX9GqHqY4xhfHZKwLaQqALDf5bNzeGW82aSk56IAXLSE/nu4olYDOfd/T5rdpS7HaKrwmlt4Q8bC0OzgSeEWAKjPWPMGGAusBoYaq0tAm+SA/DNz8sB9rS7WYFzLMf5uuPxjvdxjTFmrTFmbWlpqd9/Bgkdvm0kb35WOuBmXj+7rpAbn86jsKIOy8Gu0kpiuGNfpXerwPAIT2AArN9d4bdzvra5mIykWOaNzjjylcPMFceN0UhVEQkZu/bX0mrx23a9cZnJbPdzBYa11klgqALDn5bNzeG9G05lx61n894Np/L90yfxzLeOY3ByHJf+fTXPrdfacSCobWxmW4mHGSG4fQRCNIFhjEkB/g18z1pb1d1VOzlmuzl+6AFr77XWzrfWzs/KyupbsBI2zpo5fEBuI7l9+Vbqmg59Z1ddpd3jS2AMjdAeGADTRqQRFx3lt20kTS3e39tTpwzt0X7sy+9fw+X3r/HLfQfDCRMzGZ+VzAPv7XQ7FBGRgyNU/VCB4TtPYUUdtY3+ewOpprGF+qZWVWAEweghyTx97XHMGZXOdx9fzx9f/xxvgfvAEm5ri/7YvLeKVguzlMDoGWNMLN7kxaPW2qedw8XOthCcz75XoAXAyHY3zwX2OsdzOzkuA9j80Rlkp8bz0gDbRtJV92h1lXbHvqp6jIHs1MhNYMTHRDN1RBrr/JTA+HBnOVX1zT0en1rf1EJ9U/hsxzDGGalaUKmRqiLiOt8I1XF+qsDw9dLYUea/Koyyau9YViUwgiM9KY6Hr1rAl+bmcMeKz/jRUxto7GJqSaQKt7VFf+QVOg08c5XAOCJnUsh9wKfW2t+3u+h54HLn68uB59odv9gYE2+MGYu3WecaZ5tJtTHmWOecX2t3GxmgoqIMS2cM442tJdQMoG0kw9M7f6Hc39Fo0jfFVfUMSY4nLiaknn79bu7IdPIKKmlu6f8CZ8XmYuJiojhhYuQ2zzrvqFxS42N4QCNVRcRl+aUectITSYqL8cv5fIkQfzbyLPM4CYxUJTCCJT4mmt9fOJvvLJ7Ikx8VcMU/1lBZp+l+kSivoJLs1PiQrRYOtRX0IuAy4FRjzHrn4yzgVuB0Y8znwOnO91hrNwFPAJuBV4DrrLW+1Ni1wN/xNvbMB14O6k8iIemsmcNpaG7lja0DZxvJ4inZhx1LjI3i+iWTXYhGiirrI7r/hc+ckenUNbXwWXH/GrdZa3nt02KOn5BJcrx/FtOhKDk+hqNGpfPc+r1qtisirsovrfFb9QXAmCHJGHOwssMf2hIY6oERVMYY/vv0Sfzugtms2VHO+Xe/T8GBWrfDEj/Lcxp4hqqQSmBYa9+11hpr7Sxr7Rzn4yVr7X5r7WJr7UTnc3m729xsrR1vrZ1srX253fG11toZzmXftgNxs5Yc5ugxg8lMieflvH1uhxIUra2WNTsOMDQ1nhHtKjGuPnEcy+Ye1tdWgmBfZX3IZrT9qa2RZz+3kXxW7GFPeV2Ppo+Es2fXFfKB0+FdzXZFxC3WWu8IVT/1vwBIiI1mZEYS2/24haTU0whAlraQuOL8ebk8dOUC9lXVs+zP7/OJn0eni3tqGprZVuoJ2e0jEGIJDJFAi44yLJ0xlJVbSqhrjPx9bCu3lLC1uJobzprC+zcsZvOvl5CWEOP3buDSc/uqBkYFxughSWQkxbJ+T/96OqzY7E02njb18Eqiriyems3iXlw/FNy+fCsNHfYTq9muiATbvqp6ahtb2vpW+Mu4rGT/VmA4PTAGJ6sCwy3HTcjkmW8dR0JsFBfdu4pXN0X2m4PhuLboi81FVViLKjBEQslZM4ZT19TCmxG+jcRay5/e2EZuRiLnzBoBQFJcDBcvGMXLG/dRVKkmnsFW39RCRW0TwwZAAsMYw+yR6f2uwFjxaQmzR6aT3YuqlWtOHM81J47v1/0Gm5rt9o8xZqQx5g1jzKfGmE3GmO86xwcbY1YYYz53Pme0u82Nxphtxpitxpgl7Y7PM8bkOZfd5fTSwum39S/n+Gpn3LtIRMkv8b7B4a8Rqj7js1LYXuahtdU/BdH7axrISIolJlovZdw0ITuVZ761iMnD0vjGIx9x/7s73A4pYMJxbdEXeQVOA08lMERCx4KxgxmSHMeLeZE9jWTV9v2s31PBN08af8gf+MuOHY21lkc/2O1idAOTb4TqsAGwhQS820g+L/FQXd+3Jl/FVfV8sqeCM3o4fSScddVUV812e6wZ+IG1dipwLHCdMWYacAPwurV2IvC68z3OZRcD04GlwF+MMdHOue4GrsHbGHyicznAVcABa+0E4E7gtmD8YCLB5BuhOsGPW0jAm8Cob2qlqKreL+crq27UBJIQkZUaz+NXH8sZ04by6/9s5lfPb6LFT4kqCb68wkqGpsX36o2jYFMCQwacmOgozpg+jJVbSiJ6HNKf39hGVmo858/LPeT4yMFJnDZ1KP9cszuif/5QtM9ZuA2ECgzwJjCsPZjN763XP/VWSfW2/8VFf13FRX9d1af7dMv1SyaTGBt9yLGYKKNmuz1krS2y1n7sfF0NfArkAOcCDzpXexBY5nx9LvC4tbbBWrsDb8PvBc6o9jRr7Sqnd9ZDHW7jO9dTwGJfdYZIpMgv9ZAaH0OWn6d7tE0i8dM2kjJPgxIYISQxLpq/fHUe/3X8WB54fyfXPLQ24ib+hePaoi9CvYEnKIEhA9TZM4dT29jCm1tL3Q4lINbtPsB72/Zz9QljSejwogjgiuPGUF7TyAuf7HUhuoHLV4ExEJp4QrtGngUVfbr9is37GDU4iUlD/ftOYChaNjeHW86bSU56IgbvpCBjYNGEyB0dGyjO1o65wGpgqDNaHeezbwNzDrCn3c0KnGM5ztcdjx9yG2ttM1AJDAnIDyHikvxSD+OyU/B3bs7XFNRX4dFfZZ4GjVANMdFRhp99YRo3nTudN7aWcNG9qyjxU8WNBIenoZn8Ug8zc9LdDqVbSmDIgHTsuMFkJMXy8sbI3EbylzfzGZQYy1eOGd3p5QvHD2HS0BQeeH8nGtATPAOtAiM9KY6xmcms313R69vWNDTzXv5+Tps61O8L6VC1bG4O791wKjtuPZsXv3MCrRb+tPJzt8MKK8aYFODfwPestVXdXbWTY7ab493dpmMM1xhj1hpj1paWRmaSXCJXfkmN3/tfgHfcqT+biJd5GjVCNURdtnAMf798PttLa1j25/fYsq+7p2IJJZv3Og08c9PcDqVbSmDIgBQTHcWS6cN4/dPI20aydV81KzYXc8VxY0iJj+n0OsYYrjhuLJv2VrF2V/+mREjP7ausJzU+psv/l0g0O3cQ6/dU9DpR9s7npTQ2t3L6AOh/0ZlxWSlcfPRIHl29m137NTWoJ4wxsXiTF49aa592Dhc720JwPvu6NxcAI9vdPBfY6xzP7eT4IbcxxsQAg4ByOrDW3mutnW+tnZ+VleWPH00kKDwNzeyrqvfrCFUfYwzjslL8UoFR39SCp6FZW0hC2KlThvLENxbSYi3n372Ktz9TMjccbHAqZmdoC4lIaDpz5nA8Dc2883mZ26H41d1vbiMpLporjhvT7fWWzR3BoMRYHnhvZ1DiEm8CY6BUX/jMGZlOSXUDRZW9KyNdsbmEQYmxzB+TceQrR6jvLp5IbHQUd7z6mduhhDynF8V9wKfW2t+3u+h54HLn68uB59odv9iZLDIWb7PONc42k2pjzLHOOb/W4Ta+c50PrLQqYZMIst1JLgQigeE7rz8SGKXOCNUsJTBC2oycQTx73SJyMxL5+gMf8uOnPmHRrSsZe8OLLLp1Jc+uK3Q7ROlgY2Elw9ISyE4N7bWqEhgyYB03fgiDEmN5KYKmkezeX8vzn+zl0mNHk3GE2ehJcTFcfPRIXtmkkarBUlQ1ABMYo7wJiN6MU21uaWXllmJOmZxFbB9G5H1h1nC+MGt4r28XarLTErjy+DE8/8leNhb2rRHqALIIuAw41Riz3vk4C7gVON0Y8zlwuvM91tpNwBPAZuAV4Dprra8c71rg73gbe+YDLzvH7wOGGGO2Af+NM9FEJFK0TSDJ9v8WEoDx2ckUVzXg6WdzxzKPN4GRmaotJKFu+KBEnvzmQiZkp/CvtQUUVtRhgcKKOm58Oi+skhiRsrboTl5hZchXX4ASGDKAxUZHcca0oby2uZiG5sjYRnLP2/nEREXxX8eP7dH1L3VGqj7ywa4ARyYAxZX1A2aEqs/U4anERUf1KoHx8e4KDtQ2cfq0YX26z8sWjuGyhWP6dNtQ842TxpOeFMttr2xxO5SQZq1911prrLWzrLVznI+XrLX7rbWLrbUTnc/l7W5zs7V2vLV2srX25XbH11prZziXfdtXZWGtrbfWXmCtnWCtXWCt3e7GzyoSKPklNURHGUYNDkwCY1ymt7Jjez+rMMo8jQDaQhImUhNiOx2nXtfUwu3Lt7oQUd9E0tqiM56GZraX1TArVwkMkZB21qzhVDc0824EbCMprqrnqbUFXDA/t8ezm0cOTuL0aUP552qNVA205pZWSqoHXgVGfEw000ak9aqR54rN+4iNNpw4qW8TOOoaW6hrjIzHc1pCLN8+ZQLvfF7G+9vC/3lKREJXfqmH0YOTiIsJzMsDX2VHf7eR7HcqMIYogRE2iio630a6tyJ8KoAjaW3RmU2Fld4GnqrAEAlti8ZnkpYQw0t5+9wOpd/+/s52WqzlGyeO79XtLj9uDAdqm3heI1UDqszTSKsdOBNI2pszMp28wkqaW1qPeF1rLSs2F7NwfCapCbF9ur8r/rGGK/6xpk+3DUWXHjuaEYMSuPWVLZoaJCIBk1/qYVyA+l8AjBqcTHSU6fckEt8WkiFH2CoroWNEemKnx9MSY2htDY+/a5G2tugoz9mqqi0kIiEuLiaK06cNY8XmfTQ2H/nFVag6UNPIo6t388XZIxg1JKlXt104bgiTh6bywHsaqRpIbSNUB9gWEoC5o9Kpa2pha3H1Ea+bX+ph5/5aTp+aHYTIwkNCbDT/fcZkNhRURkSyVURCT3NLKzvLahkfoP4X4F1zjRqc1O8KjDJPI6kJMSTERvspMgm065dMJrHD/1eUgcq6Zq588MO2pJS4J6+wkuGDEshKDf3KJiUwZMA7a+YwquqbeS8/fMuzH3h/J7WNLVx7cu+qL8AZqbpoDJuLqvhwp0aqBso+p1HqQK3AgJ418lyx2Tvl8rQBOj61K1+am8Pkoan87tWtNPWgkkVEpDcKDtTR2NIasAkkPuOzkskv6V8FRqmnQRNIwsyyuTncct5MctITMUBOeiJ3XDCbm86dzvv5+znzD+/wnrZJuiqvoDIsto+AEhgiHD8xk9T4GF7aEJ7TSDwNzTzw/k7OmDaUSUNT+3SOZXNyvCNV39/h5+jEZ1/lwK3AGDU4icHJcT3qg7Fi8z5m5KQxfFDn5aYDVXSU4folk9lRVsMTa/e4HY6IRJj8AI9Q9RmXlcKO/TW09GPbQFl1gxp4hqFlc3N474ZT2XHr2bx3w6l86ahcLls4hueuW0RaQgyX3rea25dv6dF2U/Gv6vomtpfVKIEhEi7iY6I5bdpQXt1cHJbvbP5z9S4q65r41ikT+nyOxLhoLl4wkuWbisOqoVI4KaqqJy46isEDcM+uMYbZuYOOWIFRWt3Auj0VnD61b9NHIt3iqdnMH53B/732ObWN/RtDKCLS3sEERuC2kPjO39jcSuGBvq81yjwNGqEaQaYOT+OF/3c8F84byZ/fyOeiez+g4ECt22ENKBsLqwCYEQYTSEAJDBEAzpo5nMq6Jt7P3+92KL1S39TC397ZwfETMtvK9PvqMo1UDajiynqGDorHGON2KK6YMzKDbaWeTkep+byxpQRr4bRp/et/cf68XM6fl9uvc4QiYww3nDmF0uoG/vHeTrfDEZEIkl9SQ2ZKHOlJgU0M+Co8+tMHo8zTqAqMCJMUF8Nt58/irkvmsnVfNWf94R1ezgutyuhIXVsAbHQaeKoCQySMnDAxk5T4mJB7sjySpz4qoLS6gW+d0vveFx3lZiRxxrRhPLZGI1UDoaiyfkBuH/GZMyoda2FDQWWX13l1czE56YlMG57Wr/u6YP5ILpg/sl/nCFXzxwzmtKlDuefNfA7UNLodjohEiEBPIPEZ188ERmNzK5V1TUpgRKgvzh7BS985gbFZKVz76Mf85Jm8kFmTRvLaIq+wkhGDEsLm90oJDBG8Xf4XT81m+aZ9YbONpKmllXveymfuqHQWjhvil3NescgZqbpeI1X9rbiqnmEDuK/DnNx0oOtGnnWNLby7rZTTpmb3u0qlvKaR8gh+cf+jpZOpaWzmz29sczsUEYkQ+aWegPe/ABicHEdGUiz5fRylur/GGaGaoi0kkWrUkCSe/MZCvnHiOP65ejfn/uk9PuvBFLNAi+S1RV5hJTPDZPsIKIEh0ubMGcM5UNvE6u3lbofSIy98speCA3Vcd/IEv21LOGbsYKYMS+Uf72ukqj9Za50KjPDIbAfCoKRYxmUms66LRp7vbiujvqmV06f1v//FtY98xLWPfNTv84SqSUNT+fJRuTy0aheF6lkjIv1UXtPIgdqmgPe/8BmfldLnCoz9Hu8LyHB5p1j6Ji4mihvPmsqDVy5gf00DX/zTuzy2Zrera9NIXVtU1TexI4waeIISGCJtTp6cRVJcNC+GwTaS1lbLX97MZ8qwVE6d0r9+Ae0ZY7jiuDF8WlTFmh3hkcgJB5V1TTQ0tw7oCgyA2SPTWb+notMFyGubi0mNj2HB2MEuRBZ+vn/6JDBw54rP3A5FRMJcWwPP7MBXYACMy0pmex8rMEo93goMJTAGhpMmZfHSd09g/ujB3Ph0Ht/+5zoq67rupSW919b/wqmUDQdKYIg4EmKjOXVKNq9u2hfyI5xe3VzMthIP1548nqgo/zaFPHdODulJsTzw/k6/nncgKxrAI1TbmzMynTJPA3udfw+fllbL61uKOXlKNnEx+rPUEyPSE7l84Wj+/XEBW/e5X1orIuErv8SbwJgQhC0k4K3AKPM0UFnb+xeiZdXeBEaWEhgDRnZqAg9duYAfL53CK5v2cfZd7/Dx7gNuhxUxwq2BJyiBIXKIs2cOZ39NY0hXH1hr+cub2xgzJIkvzBrh9/MnxkVz8dGjWL5pn8rT/WRflZPAGKQEBsD6DttI1u+poMzTyGlT/VdNNBB86+QJpMTHcPvyLW6HIiJhLL/UQ3xMFCPSg1Ml2DaJpKz320jKfFtINEZ1QImKMlx78nie/OZCAC68ZxV3v5lPa6u2O/fXhoJKctITGZwcPr9TSmCItHPy5GwSY6N5aWPobiN5d1sZGwoq+eZJ44n2c/WFz2ULRwPw8CqNVPWHfZVKYIB31ntcTBTr9xz6zsmKzcXERBlOnqwERm9kJMfxzZPG89qnJXy4M3STriIS2vJLaxibmRywNUVH45xeG33ZRlLmaSApLpqkuBh/hyVh4KhRGbz4nRNYMn0Yt72yhcv/sYaS6voj31C6tLGwMqyqL0AJDJFDJMZ5t5G8srGYlhDN6v75jW0MS0vgS0flBOw+ctITWTJ9GI9/qJGq/rCvsh5jIDt1YJe8xsVEMX1E2mGTSF77tJhjxg1mUGKsX+7n0mNHc+mxo/1yrlB35aKxZKfGc9vLW9R4V0T6JL/UE7T+FwAjBycRG2361MizzNOg/hcD3KDEWP70lbncct5M1uwo56w/vMNbn5Xy7LpCFt26krE3vMiiW1fy7LpCv95vJK4tKuua2Lm/NqwmkIASGCKHOXPmMMo8DSH5juZHu8r5YHs5V584jviY6IDe1xXHjaGitonn1vv3D8BAVFxVT2ZKPLHResqdMzKdvMLKtnHFO8pq2Fbi4bSpQ/12H+fMHsE5s/2/vSoUJcZF873TJrF21wFe+7TE7XBEJMzUN7Wwp7w2KCNUfWKjoxg9JJntfU5ghE+puwSGMYZLFozihf93PIOT47j8/jX88MlPKKyowwKFFXXc+HSeX5MYkbi22BSG/S9ACQyRw5wyOZuE2CheCsFpJH95I5+MpFguWTAy4Pe1wDdS9T2NVO2vosp6hg/w7SM+c0amU9/U2tZ48rXNxQB+TWDsrahj7wDq33Lh/FzGZSZz+/ItIVs5JiKhadf+WlotQRuh6jMuM5n8vmwhqW5UBYa0mTQ0lee/fTxJcdE0d/j7V9fUwu3Lt/rtvsJ6bVFUBCedBPv2HXI4zx8JjC7OHUhKYIh0kBwfw8mTsnl5476Qag60eW8Vr28p4cpFY4Oy99MYw9cXjWHLvmpWh3BT03BQXFXP0AE+gcRn7sgMgLZtJCs2FzNlWCojByf57T6+/6/1fP9f6/12vlAXEx3FD5dM5rNiD09/XOB2OCISRtpGqAaxAgO8I1t37a/p9dS3/TUNDFECQ9pJiI2mrrHz7c7+TDiE9drippvg3Xe9n9vZUFhJbkYiGf1p4NnFuQNJCQyRTpw1azil1Q2s3RU6Y5rufiuflPgYvrZwTNDus22k6ns7g3afkUgVGAeNHOztdL1+TwXlNY2s3VXOGdP8V30xUJ05YxizR6Zz54rP1LdGRHrMN0J1nAsVGE0tlj0Hev4Cs6XVUl7TSJa2kEgHXU3QscClf1/Nc+sLB+7fxqIi+Mc/oLUV7rkHjjsOTj4ZTj6ZCU8+5K2+qK1tO3bIxwMPeM9RVtb55ffcc/Dc//hH0KowlMAQ6cSpU7KJiwmdbSQ7ymp4ccNeLj12NIOS/NPosCcSYqO5ZMEoXt28j4IDtUG730hS19hCZV2TKjAcxhjmjExn/Z4KVm4podXCaUpg9Jsxhh8vnczeynpNDxKRHssv9ZCTnhj0qR6+pqG+BEpPlNc00mohc4A3xJbDXb9kMomxh/aGi4+JYsm0oewoq+G7j6/n6Jtf42fP5vHJnoqBtTX6ppu8CQYAa2GXd43Q3GrZX9PIjP5sH3n66YPnbmkJWhWGZhCJdCIlPoaTJ2Xx8sYifvGFaUQFabRYV/76Vj6x0VFcdfzYoN/3pceO5t63t/PwB7u48cypQb//cLevyjveSxUYB80Zmc4bW0t4Zl0BQ9Piw655VKg6bnwmJ07K4s9vbuPCo0f6baqLiESu/NKaoE4g8Rmf6SQwSj2cRs+S2GWeBgD1wJDDLJvrncx3+/Kt7K2oY0R6ItcvmcyyuTm0tlpWbd/Pk2v38OTaAh75YDeThqZw4fyRLJubE9mPJ1/1RWOj93tr4cABePxxVntieOTvq3k4dxAkJcGbb3Z9nszMwy8vKoJx4w6eu7HRe18//zkMGxaIn6aNKjBEunDWzOEUVzWwbo+720iKKuv498cFXHT0SLJceNfBO1J1KI+v2dPlHkPp2r5KbwJjmCow2tQ2NmMtvLdtP9X1zTy3fq/bIUWMHy+dTEVtE399K9/tUEQkxFlrvSNUg7x9BGBQUiyZKXFs70UjTyUwpDvL5ubw3g2nsuPWs3nvhlPbkhpRUYZFEzL5v4vnsuanp3Hzl2aQGBfDb178lGP/93WueWgtKzYXt01Hiyjtqy98nEoJXwPPGSP6+CZSN+cONFVgiHRh8dRs4qKjeHHDPuaNHuxaHH97ewfWwjUnjnMthiuOG8tLeft4bn0hFy8Y5Voc4WhflXd/71BVYADw7LpCHnh/Z9v3tY0t3Ph0HnDwHZT+uvoE935X3DZ9xCDOnTOC+9/bweXHjdHWJRHp0r6qemobW4LewNNnXFZKWxPRnjiYwFAPDOmbQYmxfPWY0Xz1mNF8VlzNUx8V8PTHBby6uZjMlHjOOyqHC+blMnFo6mG3Dcu1xapVByskfBob4f33yTvuKkYO7kcDz27OHWghVYFhjLnfGFNijNnY7tivjDGFxpj1zsdZ7S670RizzRiz1RizpN3xecaYPOeyu4wx7tb/S1hKTYjlxEmZvLyxyLVpJPs9DTy2ZjfnzskhN8N/Uxp66+gxGUwdnsYD72ukam/tq/QuuFSB4XX78q3UNx2asff3qLPTpg0d0H01fnD6ZFpaLX94/XO3QxGREJZf4q1+cCuBMb63CYxq74sl9cAQf5g0NJWfnDWVVTcu5m9fm8/cUenc/+4OTr/zbZb9+T3+uXo3VfVNgPfNl18+v4mrH1rLoltX8uy6Qpej76F167zbRjp+rFtHXmFl/7bwdnPuQAupBAbwALC0k+N3WmvnOB8vARhjpgEXA9Od2/zFGOPr3nI3cA0w0fno7JwiR3TWzOEUVdazvqDClfv/x3s7qW9u4dqT3c36GmP4+nHekaofbNdI1d7YV1lHakIMyfEqeIOuR5r5c9RZfqmnV4viSDNqSBJfPWY0//pwz4D+dxCR7rWNUM0O/hYSgPFZyRyobaK8pvHIV8ZbgREXE0Wq/p6KH8VGR3H6tKH87Wvz+eAni/nZ2VOpbWzmJ8/kseDm1/jyX97jR09toLCiDgsUVtRx49N54ZPE6ERFbSO7y2uZmZPudih9ElIJDGvt20BPXx2dCzxurW2w1u4AtgELjDHDgTRr7Srrfav4IWBZQAKWiHfatKHERhtedmEaSVV9Ew+u2snS6cOYkH14KVuwfXHOCDKSYnng/R1uhxJW9lVphGp7XY066+p4X/zk6Tx+4mxLGai+feoEEmKiuONV/1W2iEhkyS/1kJoQQ5ZLPSV8lR/be5hoLfU0kJUSjwqrJVAyU+L5rxPGsfx7J/LcdYv48lG5fLy7gsaWwFaOBtvGwiqAsG2iHlIJjG582xizwdlikuEcywH2tLtOgXMsx/m643GRXktLiOWEiVm8lLcv6FsnHvlgF9X1zXzr5AlBvd+u+EaqrthczJ7yyBip+uy6QhbdupKxN7wYkJLAZ9cVsnJLCZ8Ve8Kr5DCAOht1lhgbzfVLJrsUUWTyLcJeytvH+j0VbocjIiHI28AzxbWEgC+B0dNKsf2eRoao/4UEgTGG2SPTuflLM7u8jj8rR4NtQ2EFADNy0twNpI/CIYFxNzAemAMUAXc4xzt7trXdHD+MMeYaY8xaY8za0tJSP4QqkeismcMprKhjQ0Fl0O6zrrGF+97ZwUmTspiZGzrZ0UuPHY0xhkc+2OV2KP327LpCbnw6L2Algb7zN7V4n34ioeTQH5bNzeGW82aSk56IwTvl5pbzZvqtgaccdPWJ4xiSHMdtL29R75oIEOiEqww8+SU1rvW/AMjJSCQuJqrHk0jKPA2aQCJBF4zK0WDbWFjJqMFJpCeFZ0Iw5DeRWWuLfV8bY/4G/Mf5tgAY2e6qucBe53huJ8c7O/e9wL0A8+fP1+pOOnX6VO82kpfyipg9Mj0o9/nE2j3sr2nkulNCo/rCZ0R6IkunD+OxNbv57mkTSYoL+aeQLt2+fCt1TYeOha1rauGm/2xmcF87Mrdz0382d3r+25dvHfAv1pfNzRnw/wbBkBIfw/87dQK/emEzb39exkmTstwOSfrIlxD1Paf4EqLgv+k9MrB4GprZV1XvWv8LgOgow9ghyT2uwCjzNDB9RHi+Yyzh6/olkw95/vU5bsIQlyLqv7zCSmaFaf8LCIMEhjFmuLXW14DgS4BvQsnzwD+NMb8HRuBt1rnGWttijKk2xhwLrAa+Bvwx2HFL5BiUFMuiCZm8tLGIG86cEvBSy8bmVv76Vj5Hj8lgwVj3xrd25YpFY3gxr4hn1+3lK8eE70jVrkr/9tc08rX71wT9fkUC4SvHjOa+93Zw28tbOGFCJlFR2jsejrpKuN6+fIsSGNInvr4TblZggLeB6KdF1Ue8XmurZb+nURUYEnS+59gfPbWBxpZWRgxKYFBiLE99VMCxY4fw5Xm5RzhDaDlQ08ie8jq+esxot0Pps5BKYBhjHgNOBjKNMQXAL4GTjTFz8G4D2Ql8A8Bau8kY8wSwGWgGrrPW+v66X4t3okki8LLzIdJnZ80Yzo/+vYGNhVUB39Lx3PpC9lbWc/N5Xe+7c9P80RlMG57Gg+/v5JIFI8O2mdaI9EQKO0kmZKbE8dfL5vX7/N94+CPKPId3Vg/nksNw8f9Oneh2CCEjLiaKH54xme8+vp4XNuzl3Dl6sRuOukp8FlbU8/NnN3LqlGwWjh9CQof+MiJdyQ+RBMa4zBSWbyqmsbmVuJiud7ZX1jXR3GqVwBBXLJub0/bYO35iJvVNLVz5wIdc/9QnJMRGc/as4S5H2HMb93q3xIdrA08IsQSGtfaSTg7f1831bwZu7uT4WmCGH0OTAe6M6UP5yTOGlzYWBTSB0dJqufutfKYNT+PkEC33NsZwxaIx/OipDazavp/jxme6HVKf/PCMSfzgyU9obbd5LDE2mp+dPY15o/tf+fKzs6cdVnKoZpXBcfzE8HxMBso5s0bw17e2c8ern3HmjOHdvkiQ0NRVwjUhJoqnPirg4Q92kRAbxXHjMzllSjanTskmR8lS6ca2Eg8xUYbRQ5JcjWN8djItrZbd5TXdTlwr8zQAkJmqBIa4o/3aIiE2mr9fPp/L71/Ddx9fR1yMdxRrOPD19JsxInwTGFrFiPRAelIc47OSufft7QFpoOZrzjb+Jy+xvbSGo8dkhHRlwxdnj2BwchwPvLfT7VD6LD0pjlYLgxJjA9JMUs0q3bNpbyWb9gav6W6oi4oy/GjpZHaX13L0za+pCWQY6mp6z61fnsW6X5zOg1cu4OKjR7GtxMPPn93IoltXsuTOt7n15S2s3r6f5g4jAEXyS2oYNSSJ2Gh3Xwr4KkC2lXTfyLPUl8DQFBJxSce1RVJcDPdfcTTTR6Rx3aMf8/Zn4TEQYmNhJaOHJDEoKdbtUPospCowRELVs+sK2V5WQ0vroRMloP8N1Do2ZwNvE8+5ozJC9sWud6TqSO5+M5895bWMHOzuOzi91dJque2VLYweksSK758UsHek1azSHb9+YTMA//rGQpcjCR0HahqJMt4ybFATyHDj+z+6fflW9lbUMSI9keuXTG47ftKkLE6alMUvz5lGfmkNb2wpYeWWEv7+znbueSuftIQYTpyUxalTsjl5crZfGhVLePONUHXb2ExvE9HtZd038vRtyczSFhJxSWdri9SEWB68cgGX/G011zy8lge+voBjx4V2c88NBZXMGZXudhj9ogSGSA/cvnxr2zhMn7qmFn745Cfc+/b2fp37s+Jqmls7nrs15KdVXHrsaO55azsPf7CLn5w11e1weuW59YVs2VfNXZfMVTm9DAi/e/UzOjzNaCpOmOlJQtQYw4TsFCZkp3D1ieOoqm/i3c/LWLmlhDe3lvKfDUUYA3NGpnPq5GxOmZLN9BFpGGN4dl1hlwkSiSzNLa3s3F/D4qnul7ynJsQyNC2e/CNUYJRV+yowlMCQ0JKeFMfDVy3g4ns/4KoHPuShq45h3ugMt8Pq1IGaRgor6vjawvBt4AlKYIj0SFcN1Jpbbb+bMm4uqurVfYaK4YMSWTpjGI+v2c33wmikakNzC3e8+hnTR6TxhZnh03RJpD+6ej4J9ecZ6Z+0hFjOmjmcs2YOp7XVsnFvJSu3lPDGlhLuWPEZd6z4jKFp8YwdkszHuw/Q2OL/KkMJPXsO1NHUYhmf5d4I1fbGZ6UccZTq/poGoqMMgxLDt+xdIldmSjyP/tcxXPjXVVzxjzU8dvWxzAjBJpl5heHfwBOUwBDpka4aqOWkJ/L3y+f369yLbl3Z6bnDYVrF148bw4sbinhmXWHYjGN69IPdFFbUceuXZ2qkpAwYXT2HhcPzjPhHVJRhVm46s3LT+d5pkyitbuDNrSW8sbWEl/P20aFAh7qmFm54egOrd5STkRRLRlIcg5zPGUmxpDufByXGEnOEPgqq7ggt+SXOBJJs97eQAIzLSub59Xux1nbZ/6usupEhyXH6uy0ha2haAo/+1zFc9NcPuOy+1Tx+zUImD+u6Ma0bfAmM6UpgiES+65dMDthEiUCeO9Dmjc4gNz2BXz63iZ89szHkF6bV9U386Y1tLJowhBMmhuaUF5FACOfnGQmMrNR4Lpg/kgvmj2TsDS92ep36plZWbN7Hgdqmth5QnUlNiGlLbAxyPmckxZGeFMvu/TW8sKGobRumqjvc1zZCNTM0Ehjjs1Koqm+mzNNIVhdTRso8Ddo+IiEvNyOJf159DBfcs4qv/n01T3zjWMaFQK8Zn7yCSsYMSQr7SiYlMER64EgN1EL13IH23Pq9FFc3tPXwCPWF6d/e3k55TSM/XjrF7VAkgH60VC/KOwrn5xkJvO6qDN+74VSstVQ3NFNR00RFXSMHapuoqG3kQE0jFXVNVNQ2caDWe7yytpGdZTUcqG2kur650/tT/xV35Zd6yEyJD5kpBL4XePmlnu4TGBqhKi7q6dpi9JBk/nm1txLjK39bzZPfXBgyze7zCis5KkT7c/SGEhgiPRTIiRLhOq2iq+amobgwLamu5+/v7uDsWcOZlZvudjgSQPNGD3Y7hJAUrs8zEnhHqtAxxpCWEEtaQiyj6PlCvLmllYk/ffmw7Smg/ituyi+tCZn+F0BbLNtLa7qc4FDmaQyZLS8yMPVmbTEhO5WHrzqGS/72AZf87QOe/OZChg9yd8vmfk8DhRV1XH5ceGz57o7a74tIn4VTY8A/vr6NxuZWfniG3p2PdB/tKuejXeVuhyESNpbNzeGW82aSk56IwVt5cct5M/ud8IqJjuqyz0pUlOGTPRX9Or/0nrWWbSWekEoGjBiUSEJsVJeNPK21lHoaNEJVXNXbtcW0EWk8fNUCKmub+OrfVlNSXR/A6I7sYAPPdFfj8AclMESkz7pamIZaY8CdZTU8tmY3Fx09sm3mvESu376yld++stXtMETCyrK5Obx3w6nsuPVs3rvhVL9V61y/ZDKJsdGHHIuLiSI1Ppov3/0+f3t7O63d9NcQ/yqvaaSyronxIbQvPyrKMDaz60kk1Q3NNDa3qgeGuKova4tZuen84+tHU1RZz6V/X015TWOAojuyjW0NPNNci8FflMAQkT7rbGEaZeCHZ0xyKaLO3bHiM2Kjo/ju4oluhyIiMqB0Vt3x2y/P4s3rT2Hx1GxufulTvv7Ah5R5GtwOdUDIL60BCKktJOCNZ7sTW0dl1d7HRmZqXDBDEvGL+WMGc9/l89m1v5bL7ltNZV2TK3FsKKhkbGYyaQmh0fumP5TAEJE+67gwTUuIodVCXVOr26G1ySuo5IVP9nLV8WPJTktwOxwRkQGns+qO9KQ47rl0Hjctm8Gq7fs58w/v8N62MrdDjXhtE0hCqAIDvPHsOVBLfbs+LD5lHu+71qrAkHB13IRM7rlsHp8VV3PFP9bgaei8wXEgbSysZGaYj0/1UQJDRPql/cJ0/S/O4PgJmfz6P5vYVtJ5KWiw/Xb5FjKSYrnmpHFuhyIiIu0YY7js2NE8d90iBiXGcul9q7l9+RaaWkInCR5p8ks8xMdEkRNiWz3HZSVjLezaX3vYZfud6pwhyUpgSPg6ZXI2f7zkKDYUVHLlAx9S13h4si5QyjwN7K2sVwJDRKSjqCjDHRfOJjE2mu8+vo6G5uA9OXfm3c/LeOfzMq47ZUJElMyJSOeMMfcbY0qMMRvbHRtsjFlhjPnc+ZzR7rIbjTHbjDFbjTFL2h2fZ4zJcy67yxhjnOPxxph/OcdXG2PGBPUHjHBTh6fx/LcXceG8kfz5jXwu+usq9pQf/kJW+i+/1MO4rBSioozboRxifLtRqh35thdpC4mEu6UzhvH7C2fz4c5yrnl4bacVR/727LpCltz5NgB/fTufZ9cVBvw+A00JDBHxq6FpCfz2/Nls2lvFHa9+5locra2W217ZQk56IpceG/4jo6TnfnHONH5xzjS3w5DgegBY2uHYDcDr1tqJwOvO9xhjpgEXA9Od2/zFGONr5nM3cA0w0fnwnfMq4IC1dgJwJ3BbwH6SASopLobbzp/FXZfM5bNiD2fd9Q4v5RW5HVbECbURqj7jnJjyO6neLPU0YgwMTlICQ9zjr7XFuXNyuO3Ls3jn8zK+/c+PA1px9uy6Qm58Oo/9TvPQMk8jNz6dF/ZJDCUwRMTvTp82lK8eM4p7397Ou5+7s6f5pY1F5BVW8v3TJ5HQodGoRLbpIwYxfURklElKz1hr3wY6zrc7F3jQ+fpBYFm7449baxustTuAbcACY8xwIM1au8paa4GHOtzGd66ngMW+6gzxry/OHsFL3zmBcVkpfOvRj/nJM3lBeZdyIKhvamHPgdqQ638B3gTWiEEJbC87vJFnmaeBwUlxxETrZYu4x59riwvnj+Smc6fz2qclfO/x9TT3M4lhrWW/p4G8gkpe2biP+9/dwW/+s5kbnt5AXYfnz7qmFm5fHt6T2mLcDkBEItPPzp7G6h3l/PcT63nleycyODl475w0tbTyu+VbmTw0lS/5aRSghA9f0uz4iZkuRyIuG2qtLQKw1hYZY7Kd4znAB+2uV+Aca3K+7njcd5s9zrmajTGVwBDgsAytMeYavFUcjBo1ym8/zEAyakgST35jIXes2Mpf39rO2p3l/OkrRzFpaKrboYW1nftrsBbGZ4deAgO8cXW6haS6QQ08xXX+XltctnAM9U2t3PzSpxRX1bG3sp6iinpGpCdy/ZLJh4yyrm9qoaiynr0VdRRW1LG37ePgsYbmQ5MgCbFR1HfRVH9vRZ1ffga3KIEhIgGRGBfNHy6ew5f+/D4//vcG7r1sHsF6w/LxD/ewc38t910+n+gQ2+crgffHlZ8DSmBIlzp7UrDdHO/uNocftPZe4F6A+fPnd3odObK4mChuPHMqx43P5AdPrOeLf3qXX3xhOpcsGBm0vyWRJr8kNEeo+ozPSuHJtXuw1h7yf1zmaVD/C3FdINYWV584jo93H+DljfvajhVW1PGDJz/h/ne3gzHsrahrm8TjYwxkp8YzIj2RqSPSOG3aUEYMSmBEemLbR0ZSLMff9gaFnSQrRoRYE9/eUgJDRAJm+ohB/GjpZH7z4qf8c81uvnpM4HtR1DY2c9frn3P0mAxOnZJ95BuISKQqNsYMd6ovhgMlzvECYGS76+UCe53juZ0cb3+bAmNMDDCIw7esSACcNCmLl757Aj944hN+8kwe720r43/Pm8mgRDVm7i1fdcO4zNCswBiXlUxNYwsl1Q0MbTf2vMzTyNxR6e4FJhJAGwoqDjvW0mrZXFTNogmZTB8xiJz0g8mJnPREhqYlEBdz5C1V1y+ZzI1P5x2yjSQxNprrl0z2548QdEpgiEhAXbloLG99VspN/9nMMWMHMyE7sCXA97+7g9LqBu659Ci9SycysD0PXA7c6nx+rt3xfxpjfg+MwNusc421tsUYU22MORZYDXwN+GOHc60CzgdWOn0yJAiyUxN48OsL+Ovb27nj1a2s31PBH78yl6NGZRz5xtImv9RDTnoiiXGh2ReqbRJJiadDAkNbSCRy7a2o7/R4S6vlwSsX9Ovcvm0oty/fyt6Kuk63p4QjdcMRkYCKijLcccFskuJi+M5j6wM6WrW8ppF73trO6dOGMm/04IDdj4iEFmPMY3iTC5ONMQXGmKvwJi5ON8Z8DpzufI+1dhPwBLAZeAW4zlrre2K6Fvg73sae+cDLzvH7gCHGmG3Af+NMNJHgiYoyXHvyeJ745kKMgQvuWcVf3txGa6vySD2VX+oJ2f4X0Pko1drGZmobW5TAkIjV1XYOf23zWDY3h/duOJUdt57NezecGvbJC1AFhogEQXZaArd9eRZXP7SW3y3fyk/PDsyIyz+/sY3axmZ+FOalcSLSO9baS7q4aHEX178ZuLmT42uBGZ0crwcu6E+M4h9Hjcrgxe+cwE+ezuO3r2zl/W37OWN6Nn99a0dEvcPob62tlvySGo5eELrJ/aFp8STHRZNfenASyX5n7/+QFPXAkMgUqds8AkkJDBEJitOnDeXSY0fxt3d2cOKkLE6YmOXX8xccqOXhVbs4f14uE9WpfkD73/Nmuh2CiATQoMRY/vSVuRz/YSY/fzaPd7cdHAZTWFHHjU/nASiJ0c6+qnrqmlpCcoSqjzGGcVmHTiIp9TQAkKUKDHFZoNYWkbrNI5CUwBCRoPnpWdP4YHs5P3jiE17+7gkM8eOC5PcrPgMD3zttkt/OKeEplBfoIuIfxhguWTCKO1d8Rkl1wyGX1TW1cPvyrXoB0I4vKRDqz4/jspJZu/NA2/dlzv+ttpCI2wL5u7Nsbo6er3pBPTBEJGgS46K56+K5VNQ28eN/b8BfPfC27KvimXWFXHHcmLAfDSX999rmYl7bXOx2GCISBKUdkhc+ezsZHTiQ5Zc4CYzs0Byh6jM+K4XCijrqGr3l9L7xkRqjKm7T2iJ0KIEhIkE1bUQaPz5zCq99WsIjq3f75Zy3v7KVlPgYvnXyeL+cT8Lb397Zzt/e2e52GCISBF0lreNiothTXhvkaEJXfmkNqQkxIb8Vw/cu9/Yyb8KlzNlCMiQ5tOOWyKe1RehQAkNEgu7rx43hxElZ/OY/m/m8uLpf51qzo5zXt5Rw7cnjSU/SOzQiIgPJ9Usmkxh76FjQ2GhDq7Wccefb/O3t7TS3tLoUXejIL/UwPisl5MeLj8vyVoj4GnmWeRoYlBhLXIxesoiIl54NRCTooqIMv7tgFinxMXzn8b6PVrXWcuvLnzI0LZ6vHzfWz1GKiEioWzY3h1vOm0lOeiIGyElP5PbzZ/Pm9adw3Pgh3PzSp5z75/fYUFDhdqiHeXZdIYtuXcnYG15k0a0reXZdYcDuy5fACHVjM5MxBraXHqzAyNQEEhFpR008RcQV2akJ/Pb8WVz14Fp++8pWfv6F3o9WXbG5mI93V3DLeTNJjIs+8g1ERCTidNUA7++Xz+fljfv41fObWPbn97j8uDH84IzJpMS7v/x9dl3hIaMTAzk9pbq+ieKqhpDvfwGQEBtNbkbiwQqM6kY18BSRQ6gCQ0Rcs3jqUL62cDT3vbuDtz8r7dVtm1ta+e3yrYzLSuaCebkBilBERMKVMYazZg7ntR+cxFeOGcUD7+/kjN+/FRKN+G5fvrUteeHjm57ib9udZEA4VGAAjMtMaWs6WuZpIDNVCQwROUgJDBFx1U/OmsqkoSn84MlP2O/pvJt8Z57+uJBtJR6uP2MyMdF6KpOD7rxoDndeNMftMEQkRKQlxPKbZTN56pvHkZoQy389tJZrH/mI4qr6oMdirWXz3ioKu5iSUlhR1+dtlV0JlxGqPuOzUthRVkNrq/UmMJK1hUTcp7VF6NCqX0RclRAbzR8unktlXRM/eqpno1Xrm1q487XPmD0ynaUzhgUhSgknI9ITNU5XRA4zb3QGL/y/47l+yWRWbinhtDve4uFVO2lt9c9I7+7s3l/Ln1Z+zhl3vs1Zd73T7XUX3rKSW17+lN37/TNFJb/UQ0yUYfSQJL+cL9DGZydT19TCrvJaquqbtYVEQoLWFqFDCQwRcd3U4WncsHQKr28p4ZEPdh3x+g++v5OiynpuWDol5DuqS/C98MleXvhkr9thiEgIiouJ4rpTJrD8eycya+Qgfv7cJr58z/ts2Vfl9/sqrW7gwfd3ct5f3uPE29/gd69+RnpSLDctm8Fvlk0/bHpKYmwU3zxpHEePyeDv7+zgpN+9weX3r2HF5mJa+pFkyS+pYdSQJGLDpFpxXKa3UuTDHeUA2kIiIUFri9DhfhcjERHg64vG8NZnpfzmxU85ZtwQJg1N7fR6lXVN/OXNfE6alMXC8UOCHKWEA18S7JzZI1yORERC1ZjMZB656hieWVfIb178lC/c9S7XnDiO7yyeSEJs35tCV9c3sXxTMc+tL+T9/P20tFqmDEvlx0uncM7s4eRmHKyCSImP5fblW9lbUceI9ESuXzK5rYFnUWUdj6/Zw+Mf7ubqh9YyYlAClywYxUULRpKdmtCrmMJlAomPr9noBzv2A6gCQ0KC1hahI6QSGMaY+4EvACXW2hnOscHAv4AxwE7gQmvtAeeyG4GrgBbgO9ba5c7xecADQCLwEvBd25O6dBFxjTGG310wm6X/9zbfeWwdz163qNNF5D1v5VNV38SPl05xIUoREYkUxhjOOyqXkydn878vfcpf3sznxbwibl42k+MnZvb4PPVNLby5tZTnPynk9U9LaGhuJTcjkW+eNI4vzs5h8rDOE/JdTU8BGD4oke+fPolvnzqB1z8t5pEPdnPHis/4w+ufs2T6ML567CgWjhtyxCrE5pZWdu6vYfHUoT3+edyWlRJPakIMq7c7FRgaoyoi7YRUAgNv0uFPwEPtjt0AvG6tvdUYc4Pz/Y+NMdOAi4HpwAjgNWPMJGttC3A3cA3wAd4ExlLg5aD9FCLSJ1mp8dx+wSyufMA7WvUX5xw6WnVfZT33v7uDc2ePYNqINJeiFBGRSDI4OY7fXTCb847K4afPbOTS+1bzpbk5/OzsqbzzeVmnVRItrZYPtu/nufWFvLxxH9X1zQxJjuPio0fyxTk5HDUq3S9bHGOjo1g6YzhLZwxne6mHf67ezZMfFfBiXhHjs5L56jGj+fK8XAYlxnZ6+z0H6mhqsYzPCv0Rqj7GGMZlpfDJngpAFRgicqiQSmBYa982xozpcPhc4GTn6weBN4EfO8cft9Y2ADuMMduABcaYnUCatXYVgDHmIWAZSmCIhIVTpwzl8oWjuf+9HZw4KZOTJ2e3XfaH1z+j1Vp+cMZkFyMUEZFIdNz4TF7+7gn85Y1t3P1WPq9sLKK51dLU4i3iLayo48f/3sAzHxfw6b5qSqobSImPYcn0YZw7ZwTHjR8S0KlY47JS+NkXpvHDJZP5z4YiHvlgF7/+z2Z+u3wLX5w9gkuPHc2s3PRDbuMbRzo+O3y2kACMz0puS2BkqQeGiLQTUgmMLgy11hYBWGuLjDG+VzM5eCssfAqcY03O1x2Pi0iYuPGsqXywvZwfPrmBV753Apkp8Wwr8fDE2gIuO3Y0IweHRyd1EREJLwmx0fz3GZM5Z/YIzr7r3bbkhU9DcytvfV7GkulDOXdODqdOye5Xz4y+xnj+vFzOn5fLxsJKHl29i2fX7eWJtQXMyh3EpceM5pzZI1i+aR+/eG4jANc9+jE/Xjqlyy0rocbXsyMlPibo/74iEtrCIYHRlc7q8mw3xw8/gTHX4N1qwqhRo/wXmYj0S0JsNHddMpdz/vQul/19NVX1TRRW1GM42NxLpCt3XzrP7RBEJMxNHJpKU0trp5cZ4K+XzQ9uQF2YkTOIW86bxY1nTeXZdYU8vGoXP/r3Bn7xXB5NrbRNLymqrOfGp/MAwiKJUeapB8DT0MyiW1ce0uBUxA1aW4SOcJinVGyMGQ7gfC5xjhcAI9tdLxfY6xzP7eT4Yay191pr51tr52dlZfk9cBHpu8nDUvnCzGF8uq+awgrvQsYC//viFp5dV+hucBLSBifHMThZTd9EpH9GpCf26rib0hJi+drCMbz6/RN54hsLMSbqsNGrdU0t3L58q0sR9tyz6wr55+o9bd8XVtRx49N5+tsvrtLaInSEQwLjeeBy5+vLgefaHb/YGBNvjBkLTATWONtNqo0xxxpv96SvtbuNiISR1c4M+PbCZQEm7nly7R6eXLvnyFcUEenG9Usmk9hh+0JibDTXLwndPkzGGBaMHUx9U0unl++tqAtyRL13+/KtNDQfWv2iv/3iNq0tQkdIbSExxjyGt2FnpjGmAPglcCvwhDHmKmA3cAGAtXaTMeYJYDPQDFznTCABuJaDY1RfRg08RcLSXqfy4vDjob8AE/c89ZG3DdIF80ce4ZoiIl3zbVnobApJqBuRnkhhJ38rQ7F6pKOu/sbrb7+4SWuL0BFSCQxr7SVdXLS4i+vfDNzcyfG1wAw/hiYiLgjnBZiIiIS/ZXNzwiJh0dH1SyZz49N51LWrxAj16hEf/e0Xke6EwxYSERmgwrF8V0RExG3L5uZwy3kzyUlPxAA56Yncct7MsEjG6G+/iHQnpCowRETaC+fyXRERETeFa/WI/vaLSHeUwBCRkBauCzARERHpG/3tF5GuKIEhIiIR5YGvL3A7BBEREYkgWluEDiUwREQkoiTGRR/5SiIiIiI9pLVF6FATTxERiSgPr9rJw6t2uh2GiIiIRAitLUKHEhgiIhJR/rOhiP9sKHI7DBEREYkQWluEDiUwRERERERERCTkKYEhIiIiIiIiIiFPCQwRERERERERCXlKYIiIiIiIiIhIyDPWWrdjCAnGmFJgVwBOnQmUBeC8gRaucYNid4tid4did4diP9Roa22Wn88Z9gK0ttBjzx2K3R2K3R2K3R3hGnug4u50baEERoAZY9Zaa+e7HUdvhWvcoNjdotjdodjdodjFLeH8/6fY3aHY3aHY3aHYgy/YcWsLiYiIiIiIiIiEPCUwRERERERERCTkKYERePe6HUAfhWvcoNjdotjdodjdodjFLeH8/6fY3aHY3aHY3aHYgy+ocasHhoiIiIiIiIiEPFVgiIiIiIiIiEjIUwJDREREREREREKeEhj9YIy53xhTYozZ2O7Y7caYLcaYDcaYZ4wx6e0uu9EYs80Ys9UYs8SVoA/G0uPYjTGnG2M+MsbkOZ9PdS1wev/v7lw+yhjjMcb8MOgBHxpHbx8zs4wxq4wxm5x//wRXAqfXj5lYY8yDTsyfGmNudCtuJ57OYr/JiXu9MeZVY8yIdpeF+u9qp7GHye9ql//uzuWh/Lva3WMmJH5Xe/l4CanfU/HS2sIdWluEdtyh9nyldYU7tK5wR8itLay1+ujjB3AicBSwsd2xM4AY5+vbgNucr6cBnwDxwFggH4gOk9jnAiOcr2cAheHy797u8n8DTwI/DJfYgRhgAzDb+X5IGD1mvgI87nydBOwExoRY7Gntvv4OcI/zdTj8rnYVezj8rnYae7tjofy72tW/e8j8rvYy7pD6PdVHt/+HWluEUOztLg/l56uQX1v0Mu6Qer7q5XNtOPyeal0RQrGH0u9pH2IP+O+qKjD6wVr7NlDe4dir1tpm59sPgFzn63Px/mc2WGt3ANuABUELtoPexG6tXWet3esc3wQkGGPigxZsB738d8cYswzYjjd2V/Uy9jOADdbaT5zr7bfWtgQt2A56GbsFko0xMUAi0AhUBSvWjrqIvX08yXhjhvD4Xe009jD5Xe3q3z0cfle7ij1kfld7GXdI/Z6Kl9YW7tDaIvi0rnCH1hXuCNd1hXP/IbW2UAIjsK4EXna+zgH2tLuswDkWqtrH3t6XgXXW2oYgx9MbbbEbY5KBHwP/42pEPdf+330SYI0xy40xHxtjfuRiXD3RPvangBqgCNgN/M5aW97VDd1ijLnZGLMH+CrwC+dwWPyudhF7eyH7u9pZ7OHyu9rFv3vI/652EXdY/J7KYbS2cIfWFsGndUUQaV3hjnBdV4B7awslMALEGPNToBl41Heok6uF5AzbTmL3HZ+Ot5zvG27E1ROdxP4/wJ3WWo97UfVMJ7HHAMfjfVI4HviSMWaxS+F1q5PYFwAtwAi85ZI/MMaMcym8Lllrf2qtHYk37m87h8Pid7WL2IHQ/13tIvaw+F3tIvaQ/13tIu6w+D2Vg7S2cIfWFsGndUXwaV3hjnBdV4B7awslMALAGHM58AXgq9Za3xNUATCy3dVygb0db+u2LmLHGJMLPAN8zVqb71Z83eki9mOA3xpjdgLfA35ijPl252dwTzePmbestWXW2lrgJbz7z0JKF7F/BXjFWttkrS0B3gPmuxVjD/wT7zsLECa/q+20jz0sflfbaR97WPyuttPxMRPyv6uO9nGH2+/pgKa1hTu0tgg+rStcp3WFO8J1XQFBXlsogeFnxpileMuVvug84HyeBy42xsQbY8YCE4E1bsTYla5iN94O0C8CN1pr33MpvG51Fbu19gRr7Rhr7Rjg/4D/tdb+yZ0oO9fNY2Y5MMsYk+TsIzsJ2OxGjF3pJvbdwKnGKxk4FtjiRoxdMcZMbPftFzkYXzj8rnYae5j8rnYae5j8rnb1mAnp39Vu4g7531Px0trCHVpbBJ/WFe7QusId4bquAJfXFtbFbqzh/gE8hnd/TxPeTNlVeBvz7AHWOx/3tLv+T/F2Ht4KnBkusQM/w7uXaX27j+xwiL3D7X6F+x2Ie/uYuRRv46GNwG/DJXYgBW/H5014n3CvD8HY/+38u24AXgBy2l0/1H9XO409TH5Xu/x3b3e7UP1d7e4xExK/q718vITU76k+uv0/1NoihGLvcLtQfb4K+bVFLx8vIfV81Ye/EaH+e6p1RYjFHiq/p314zAT8d9U4dyQiIiIiIiIiErK0hUREREREREREQp4SGCIiIiIiIiIS8pTAEBEREREREZGQpwSGiIiIiIiIiIQ8JTBEREREREREJOQpgSEiYc8Y86YxZr7bcYiIiEhk0NpCJDQpgSEiIiIiIiIiIU8JDBEJOmPMj4wx33G+vtMYs9L5erEx5hFjzBnGmFXGmI+NMU8aY1Kcy+cZY94yxnxkjFlujBne4bxRxpgHjTG/Cf5PJSIiIm7R2kJkYFACQ0Tc8DZwgvP1fCDFGBMLHA/kAT8DTrPWHgWsBf7bufyPwPnW2nnA/cDN7c4ZAzwKfGat/VlwfgwREREJEVpbiAwAMW4HICID0kfAPGNMKtAAfIx3sXEC8DwwDXjPGAMQB6wCJgMzgBXO8WigqN05/wo8Ya1tv/AQERGRgUFrC5EBQAkMEQk6a22TMWYn8HXgfWADcAowHtgBrLDWXtL+NsaYmcAma+3CLk77PnCKMeYOa219wIIXERGRkKO1hcjAoC0kIuKWt4EfOp/fAb4JrAc+ABYZYyYAGGOSjDGTgK1AljFmoXM81hgzvd357gNeAp40xig5KyIiMvBobSES4ZTAEBG3vAMMB1ZZa4uBeuAda20pcAXwmDFmA95FxxRrbSNwPnCbMeYTvAuS49qf0Fr7e7wlow8bY/T8JiIiMrBobSES4Yy11u0YRERERERERES6pSyiiIiIiIiIiIQ8JTBEREREREREJOQpgSEiIiIiIiIiIU8JDBEREREREREJeUpgiIiIiIiIiEjIUwJDREREREREREKeEhgiIiIiIiIiEvKUwBARERERERGRkKcEhoiIiIiIiIiEPCUwRERERERERCTkKYEhIiIiIiIiIiFPCQwRCQvGGGuMmTBQ719ERET6x+2/5W7fv0gkUAJDRAAwxvzKGPNIEO/PGGN+Y4wpNMZUGmPeNMZMD9b9+5Mx5gFjTKMxxtPuI9rtuERERIJJa4m+M8ZcaIx53xhTa4x5s5PL5xhjPnIu/8gYMyf4UYq4TwkMEfELY0xML29yAXAlcAIwGFgFPOxSLP7wW2ttSruPFhdiEBERCVsDfC1RDvwfcGsnscQBzwGPABnAg8BzznGRAUUJDJEBxhjzY+edimpjzFZjzGJjzFLgJ8BFTvXAJ851RxhjnjfGlBtjthljrm53nl8ZY54yxjxijKkCrjDGDDLG3GeMKXLu4zfdVCKMBd611m53Xuw/Akw7QvhnGWO2G2PKjDG3G2OinFiuMMa8Z4y50xhTDvzKGDPeGLPSGLPfuf6jxpj0dvHvNMb80BizwXnX5l/GmIR2l1/v/Bx7jTFX9v5fWkREJDJpLdEWv9/WEtba16y1TwB7O7n4ZCAG+D9rbYO19i7AAKce4WcViThKYIgMIMaYycC3gaOttanAEmCntfYV4H+BfznVA7OdmzwGFAAjgPOB/zXGLG53ynOBp4B04FG87wg0AxOAucAZwH91Ec7jwARjzCRjTCxwOfDKEX6ELwHzgaOc+26/GDgG2A5kAzfj/cN+ixP7VGAk8KsO57sQWIp3ATQLuALAWYT9EDgdmAicdoS4AL7lLM4+MsZ8uQfXFxERCTtaSwR0LdGV6cAGa61td2yDc1xkQFECQ2RgaQHigWnGmFhr7U5rbX5nVzTGjASOB35sra231q4H/g5c1u5qq6y1z1prW4E04Ezge9baGmttCXAncHEXsRQB7wBbgTq8ZaDfP0L8t1lry621u/GWWV7S7rK91to/WmubrbV11tpt1toVzjsVpcDvgZM6nO8ua+1ea2058AIwxzl+IfAPa+1Ga20Nhy9WOroL7+IkG/g58IAxZtERbiMiIhKOtJY4lL/WEt1JASo7HKsEUvtxTpGwpASGyABird0GfA/vH9ESY8zjxpgRXVx9BFBura1ud2wXkNPu+z3tvh4NxAJFxpgKY0wF8Fe8L+o780vgaLzvZiQA/wOsNMYkdfMjtL+/XU6MnV2GMSbb+fkKnbLUR4DMDufb1+7rWrwLBJzzdryvLllrP7bW7ncWPC/hfQfpvO5uIyIiEo60lgjMWuIIPHiTO+2lAdWdXFckoimBITLAWGv/aa09Hu8iwQK3+S7qcNW9wGBjTPvs/iigsP3p2n29B2gAMq216c5HmrW2q/LG2XjLTAucF/4P4G1M1d3e1ZEdYmm/T7Rj/Lc4x2ZZa9OAS/GWgvZEUSf31Ru2F/clIiISVrSW6JH+riXa2wTMMsa0v+9ZznGRAUUJDJEBxBgz2RhzqjEmHqjHW27pm5ZRDIzxNbOy1u4B3gduMcYkGGNmAVfhrS44jLW2CHgVuMMYk2aMiXKaX3UstfT5ELjAGDPUue5leN912dbNj3C9MSbDKUn9LvCvbq6bivcdiwpjTA5wfTfX7egJvI3Epjnv4vyyuysbY843xqQ4P8cZeBc4z/fi/kRERMKC1hI91tu1RLTTADQGiHL+vWKdi9/E+2/8HWNMvDHm287xlb2IRyQiKIEhMrDE4x3PVYa35DEbb8dwgCedz/uNMR87X18CjMH77sQzwC+ttSu6Of/XgDhgM3AAb1Ou4V1c9zbgE2A9UIF3z+qXrbUV3Zz/OeAj5zYvAvd1c93/wdugq9K57tPdXPcQ1tqX8e6LXYl3EXSkBcJ38b6bVAHcDlxtrX2zp/cnIiISRrSW6IE+rCUuw5sMuhvvWNg64G/OuRqBZXj/bSrwNh5d5hwXGVDMoc1sRURERERERERCjyowRERERERERCTkKYEhIiIiIiIiIiFPCQwRERERERERCXlKYIiIiIiIiIhIyFMCQ0RERERERERCXozbAYSKzMxMO2bMGLfDEBGRftpeWgPAuKxklyMZOD766KMya22W23GEGq0tREQig9YWwdfV2kIJDMeYMWNYu3at22GIiEg/XfTXVQD86xsLXY5k4DDG7HI7hlCktYWISGTQ2iL4ulpbKIEhIiIRRe+OiIiIiD9pbRE6lMAQEZGIcst5s9wOQURERCKI1hahQ008RURERERERCTkqQJDREQiyo1PbwAOfbekqamJgoIC6uvr3QorIiQkJJCbm0tsbKzboYQtPRb9Q49FEQmmztYW4g4lMEREJKL4OoW3V1BQQGpqKmPGjMEY40JU4c9ay/79+ykoKGDs2LFuhxO29FjsPz0WRSTYOltbiDu0hURERCJefX09Q4YM0QvGfjDGMGTIEFUO9JMei/2nx6KIyMClBIaIiAwIesHYf/o39A/9O/af/g1FRAYmJTBERERCyJtvvsn777/fr3OkpKT4KRoZ6PR4FBGRUKIeGCLSL8+uK+T25VvZW1HHiPRErl8ymWVzc9wOSwawaSPS3A6hX958801SUlI47rjj3A5FRI9HERECu7bQWrp3VIEhIn327LpCbnw6j8KKOixQWFHHjU/n8ey6QrdDkwHsl+dM55fnTO/XOZ5dV8iiW1cy9oYXWXTrSr88ppctW8a8efOYPn069957LwCvvPIKRx11FLNnz2bx4sXs3LmTe+65hzvvvJM5c+bwzjvvcMUVV/DUU0+1ncf3brbH42Hx4sUcddRRzJw5k+eee67fMUroCcRjEfR4FBHpDX+sLTqjtXTvqQJDRPrs9uVbqWtqOeRYXVMLty/fqsyxhC3fYsL32PYtJoB+Pa7vv/9+Bg8eTF1dHUcffTTnnnsuV199NW+//TZjx46lvLycwYMH881vfpOUlBR++MMfAnDfffd1er6EhASeeeYZ0tLSKCsr49hjj+WLX/yiegNEkEA9FkGPRxGRUKC1dO8pgSEifba3oq5Xx0WC4XuPrwPg/y6e2+nl//PCJjbvrery9ut2V9DY0nrIsbqmFn701AYeW7O709tMG5F2xHdm7rrrLp555hkA9uzZw7333suJJ57YNgZy8ODB3d6+I2stP/nJT3j77beJioqisLCQ4uJihg0b1qvziHvceiyCHo8iIr1xpLVFX2kt3XtKYIhIn41IT6SwkyfYEemJLkQj4lVU2b/Rih1fMB7peE+8+eabvPbaa6xatYqkpCROPvlkZs+ezdatW49425iYGFpbvfdtraWxsRGARx99lNLSUj766CNiY2MZM2aMxkpGmEA8FkGPRxGR3urv2qIrWkv3nhIYItJn1y+ZfEh5M0BibDTXL5nsYlQi3TvSu9OLbl3Z6WIiJz2Rf31jYZ/us7KykoyMDJKSktiyZQsffPABDQ0NvPXWW+zYseOQkv3U1FSqqg6+Kz9mzBg++ugjLrzwQp577jmamprazpmdnU1sbCxvvPEGu3bt6lNs4h43Hougx6OISKi4fslkrn/qE5pabNsxraW7pyaeItJny+bmcMt5M4mN9u5xHpwcxy3nzdSePQlr1y+ZTGJs9CHH+ruYWLp0Kc3NzcyaNYuf//znHHvssWRlZXHvvfdy3nnnMXv2bC666CIAzjnnHJ555pm2polXX301b731FgsWLGD16tUkJycD8NWvfpW1a9cyf/58Hn30UaZMmdL3H1pCUiAei6DHo4hIqFg2N4eTJ2W1fZ+Tnqi19BGoAkNE+mXZ3BxuX76Vwoo6vn/6JD3hStjzPYb9OdIsPj6el19+udPLzjzzzEO+nzRpEhs2bDjk2AcffND29S233AJAZmYmq1at6vScHo+nz7FK6AjEYxH0eBQRCSWDk+MBGJeZzMofnuxuMGFACQwR6RdrLaWeBgBKqxtcjkYEjhqd0e9zLJubo2SchAQ9FkVE3OePtUVXSqq9/TUKKupobbVERWl6U3e0hURE+qW6oZnGZm9DNyUwJBT8eOkUfrxU5euRyBhzvzGmxBizsZPLfmiMscaYzHbHbjTGbDPGbDXGLGl3fJ4xJs+57C7jzPo0xsQbY/7lHF9tjBnT7jaXG2M+dz4uD/CPKiIiISSQa4sSZ/3c2NxKmUdr6SNRAkNE+qWsXdJCCQwRCbAHgKUdDxpjRgKnA7vbHZsGXAxMd27zF2OMr6HE3cA1wETnw3fOq4AD1toJwJ3Abc65BgO/BI4BFgC/NMYE7u04EREZMEqqG8hK9W4j2XNA41OPRAkMEemXMo93hF5cdFTbVhIRN33z4Y/45sMfuR2GBIC19m2gvJOL7gR+BNh2x84FHrfWNlhrdwDbgAXGmOFAmrV2lbXWAg8By9rd5kHn66eAxU51xhJghbW23Fp7AFhBJ4kUERGJTIFaW7S0WvZ7GjhqVDoABQdq/X4fkUYJDBHpF1+p28ShKYdUY4i45UBtIwdqG90OQ4LEGPNFoNBa+0mHi3KAPe2+L3CO5Thfdzx+yG2stc1AJTCkm3OJiMgAEKi1xX5PA60WjhrlLeorUAXGESmBISL94ktgTB2eRml1A943NEVEAs8YkwT8FPhFZxd3csx2c7yvt+kY0zXGmLXGmLWlpaWdXUVERAQ42P9i9JBkBifHKYHRA0pgiEi/lFU3EGVg8tBUGltaqaprdjskkYj25ptv8oUvfAGA559/nltvvbXL61ZUVPCXv/yl1/fxq1/9it/97nd9jjGIxgNjgU+MMTuBXOBjY8wwvFUSI9tdNxfY6xzP7eQ47W9jjIkBBuHdstLVuQ5jrb3XWjvfWjs/KyurXz9cONDjUUSk73wTSLLT4snNSNQWkh5QAkNE+qXU08jg5DiGDkpwvq93OSKR8NTS0tLr23zxi1/khhtu6PLyvr5gDBfW2jxrbba1doy1dgzeRMNR1tp9wPPAxc5kkbF4m3WusdYWAdXGmGOd/hZfA55zTvk84Jswcj6w0umTsRw4wxiT4TTvPMM5FrH0eBQRCbySKm8FRnaqN4FRqAqMI1ICQ0T6pbS6gcyUeLJSvN2TS9QHQ1y2aEImiyZkHvmKR1JUBCedBPv29ftUO3fuZMqUKVx++eXMmjWL888/n9raWsaMGcOvf/1rjj/+eJ588kleffVVFi5cyFFHHcUFF1yAx+MB4JVXXmHKlCkcf/zxPP30023nfeCBB/j2t78NQHFxMV/60peYPXs2s2fP5v333+eGG24gPz+fOXPmcP311wNw++23c/TRRzNr1ix++ctftp3r5ptvZvLkyZx22mls3bq13z9zIBhjHgNWAZONMQXGmKu6uq61dhPwBLAZeAW4zlrre1V+LfB3vI0984GXneP3AUOMMduA/wZucM5VDtwEfOh8/No5Fhx+fCyCHo8iIr3lt7VFB74Jflmp8YzMSKKgoo7WVm3H7k6M2wGISHgr8zgJDGf8k0apitu+s3iif050003w7rvez3/+c79Pt3XrVu677z4WLVrElVde2fZOdEJCAu+++y5lZWWcd955vPbaayQnJ3Pbbbfx+9//nh/96EdcffXVrFy5kgkTJnDRRRd1ev7vfOc7nHTSSTzzzDO0tLTg8Xi49dZb2bhxI+vXrwfg1Vdf5fPPP2fNmjVYa/niF7/I22+/TXJyMo8//jjr1q2jubmZo446innz5vX7Z/Y3a+0lR7h8TIfvbwZu7uR6a4EZnRyvBy7o4tz3A/f3Ilz/8fNjEfR4FBHpDb+tLTooqW4gPSmW+JhocjMSaWxupczTQHZaQkDuLxIogSEi/VLmaWDMkCQlMCS8nHzy4ccuvBC+9S2orYXFi2HNGmhthXvugXXr4Jpr4IoroKwMzj//0Nu++eYR73LkyJEsWrQIgEsvvZS77roLoO0F4AcffMDmzZvbrtPY2MjChQvZsmULY8eOZeLEiW23vffeew87/8qVK3nooYcAiI6OZtCgQRw4cOCQ67z66qu8+uqrzJ07FwCPx8Pnn39OdXU1X/rSl0hKSgK8WwEkSFx4LIIejyIioaCkup5sZw2dm+F9zttzoE4JjG4ELIFhjBmJd7b6MKAVuNda+wdjzGDgX8AYYCdwoTNTHWPMjcBVQAvwHWvtcuf4POABIBF4CfiutdYaY+Kd+5gH7AcustbudG5zOfAzJ5zfWGt9c91FxE+stW0VGGkJMcTFRFHqUQJD3HX5/WsAePDKBX0/ya5d4JuoY633+37ytls4/Pvk5GTnbiynn346jz322CHXW79+/WG37StrLTfeeCPf+MY3Djn+f//3f367D/GzADwWQY9HEZHe8MvaohMl1Q1kp3qTFbkZiQAUHKhl3ugMv95PJAlkD4xm4AfW2qnAscB1xphpePeTvm6tnQi87nyPc9nFwHRgKfAXY0y0c667gWvwNuCa6FwO3mTHAWvtBOBO4DbnXIOBXwLHAAuAXzpNt0TEj2oaW6hvaiUzNR5jDFkp8arAENfVN7VQ33SEBoRvvnn4x7e+5b2sshIOHDj0ReOBA7DU+dOTmXn4bXtg9+7drFq1CoDHHnuM448//pDLjz32WN577z22bdsGQG1tLZ999hlTpkxhx44d5Ofnt922M4sXL+buu+8GvA0Yq6qqSE1Npbq6uu06S5Ys4f7772/rZVBYWEhJSQknnngizzzzDHV1dVRXV/PCCy/06GcSP3DhsQh6PIqI9EaP1hZ9UFLV0FbFnNOWwFAjz+4ELIFhrS2y1n7sfF0NfArkAOcCvmqIB4FlztfnAo9baxustTvwNtZaYIwZDqRZa1c5ncAf6nAb37meAhY7HcWXACusteVOdccKDiY9RMRPynyNh5wGnlmpSmBIBLjpJm+5fnstLd7j/TB16lQefPBBZs2aRXl5Oddee+0hl2dlZfHAAw9wySWXMGvWLI499li2bNlCQkIC9957L2effTbHH388o0eP7vT8f/jDH3jjjTeYOXMm8+bNY9OmTQwZMoRFixYxY8YMrr/+es444wy+8pWvsHDhQmbOnMn5559PdXU1Rx11FBdddBFz5szhy1/+MieccEK/flbxkwA9FkGPRxERt1lrKa1uaNtCkhQXw5DkOCUwjiAoPTCMMWOAucBqYKgzwgxrbZExJtu5Wg7wQbubFTjHmpyvOx733WaPc65mY0wlMKT98U5uIyJ+UuZsF8lMPZjA2FOu+dUS5latgsbGQ481NsL77/frtFFRUdxzzz2HHNu5c+ch35966ql8+OGHh9126dKlbNmy5bDjV1xxBVdccQUAQ4cO5bnnnjvsOv/85z8P+f673/0u3/3udw+73k9/+lN++tOfHunHkGAK0GMR9HgUEXFbZV0TjS2tbRUY4N1GUnBAa+nuBDyBYYxJAf4NfM9aW9XNnsbOLrDdHO/rbdrHdg3erSmMGjWqq7hEpAttCYyUOMCbwFi3+0B3NxEJfevWuR2BiJceiyIiEavEqVpu37AzNyOJT4uq3AopLASyBwbGmFi8yYtHrbW+QeHFzrYQnM8lzvECYGS7m+cCe53juZ0cP+Q2xpgYYBBQ3s25DmGtvddaO99aOz8rK6uvP6bIgFXq8b4z2LaFJCWe/TWNNLe0dnczkYBaPDWbxVOzj3zFIBozZgwbN250OwwRQI9HEZHeCsTaoqTKSWB0rMCoqKO19bD33sURsASG04viPuBTa+3v2130PHC58/XlwHPtjl9sjIk3xozF26xzjbPdpNoYc6xzzq91uI3vXOcDK50+GcuBM4wxGU7zzjOcYyLiR2XVDRgDg5MPVmBYC+U1jUe4pUjgXHPieK45cbzbYYiIiEiECMTaoqS6Hjg8gdHY3Kqpft0I5BaSRcBlQJ4xZr1z7CfArcATxpirgN3ABQDW2k3GmCeAzXgnmFxnrfW1er2Wg2NUX3Y+wJsgedgYsw1v5cXFzrnKjTE3Ab6Nm7+21pYH6OcUGbBKPQ1kJMURE+3Nhfr28JVUN2h+tYQca61GM/aTtXpHyB/0WOw/PRZFJNyVdrGFBLyjVIdqLd2pgCUwrLXv0nkvCoDFXdzmZuDmTo6vBWZ0crweJwHSyWX3A/f3NF4R6b2y6oa2/hdwMIGhrLG46aK/ekdD/usbC9uOJSQksH//foYMGaIXjn1krWX//v0kJGhB1R96LPafHosiEmydrS36q6S6gaS4aFLiD74kz203SnVe50OeBrygTCERkchU5mkgM+Vg2ZuvF4ZGqUqoyc3NpaCggNLSUrdDCWsJCQnk5uYe+YrSJT0W/UOPRREJdyXtRqj65LRLYEjnlMAQkT4r8zQyZ2R62/dtFRhKYEiIiY2NZezYsW6HIaLHooiIAFBSVU926qGVZElxMQxJjtMo1W4EdAqJiES2Mk/DIbOrE2KjSU2IUQJDRERERKQbpdWHrqN9cjMSVYHRDSUwRKRPahubqW1sOWQLCXirMNQDQ0RERESkayVdJjCSlMDohraQiEiflFV7R6W2b+IJ3j4YqsAQN31h1nC3QxAREZEI4u+1RW1jM56GZrLTOq/AWLG5mNZWS1SUmj13pASGiPSJr8oiM/XwCozNe6vcCEkEgMsWjnE7BBEREYkg/l5blFQ5I1RTD5+mlJuRSGNLK6WeBo1S7YS2kIhIn5Q5CYyszraQqAJDXFTX2EJdY4vbYYiIiEiE8PfaoqTal8DofAsJoEaeXVACQ0T6xJek6KwHRnVDs15Aimuu+McarvjHGrfDEBERkQjh77WFbx3d1RYS0CjVriiBISJ94qvAGNJJD4z2l4uIiIiIyEEl1fVAV1tIfBUYSmB0RgkMEemTMk8D6UmxxEYf+jTi66bse2IWEREREZGDSqobiI02ZCTFHnZZYlw0mSlx2kLSBSUwRKRPyqobD9s+AgcTGOqDISIiIiJyuJKqBrJS4jGm8ykjORql2iUlMESkT8o8DYeNUAUlMEREREREulNSXU9WNxNGcjMSlcDogsaoikiflHkamJmbftjxIcnxRBklMMQ958/LdTsEERERiSD+XluUVje09broTG5GIis2FdPaaomK6rxKY6BSAkNE+qTM09hpBUZ0lGFwcjylauIpLrlg/ki3QxAREZEI4u+1RUl1A0eNzujy8tyMJBpbWin1NDC0m0qNgUhbSESk1+qbWvA0NHfaAwO820hUgSFuKa9ppLym0e0wREREJEL4c23R2NxKeU0j2amdr6Oh/ShVNfLsSAkMEek1X3IiSwkMCUHXPvIR1z7ykdthiIiISITw59qizKlS7myEqs/ItgSG+mB0pC0kItJrvifezNTDt5CAN7Gxrbg6mCGJiIiElWfXFXL78q3srahjRHoi1y+ZzLK5OW6HJSIB5nuTr7sKjJx0b38MJTAOpwSGiPSa74m32y0kngastV2OhxIRERmonl1XyI1P51HX1AJAYUUdNz6dB6AkhkiEK/ElMNK6TmAkxkWTmRLHnnJtIelIW0hEpNfKPN49gN0lMJpaLJV1TcEMS0QinDHmfmNMiTFmY7tjtxtjthhjNhhjnjHGpLe77EZjzDZjzFZjzJJ2x+cZY/Kcy+4yTqbVGBNvjPmXc3y1MWZMu9tcboz53Pm4PDg/sUSq25dvbUte+NQ1tXD78q0uRSQiwVJSXQ90v4UEICcjSRUYnVACQ0R6zbeFZEgnU0jAm8AAjVIVEb97AFja4dgKYIa1dhbwGXAjgDFmGnAxMN25zV+MMdHObe4GrgEmOh++c14FHLDWTgDuBG5zzjUY+CVwDLAA+KUxpuv28SJHsLei8xclXR0XkchRUtWAMXQ6za+93IxENfHshBIYItJrZZ4G0hJiiI+J7vRyX3NPJTDEDZceO5pLjx3tdhgSANbat4HyDsdetdY2O99+AOQ6X58LPG6tbbDW7gC2AQuMMcOBNGvtKmutBR4ClrW7zYPO108Bi53qjCXACmttubX2AN6kScdEikiPjUhP7NVxEXGXP9cWJdUNDEmOIya6+5fiuRmJFFbU0dpq/XK/kUIJDBHptTJPQ1uVRWfaKjA8SmBI8J0zewTnzB7hdhjijiuBl52vc4A97S4rcI7lOF93PH7IbZykSCUwpJtzifTJ9Usmkxh76JsAibHRXL9ksksRiUh3/Lm2KK2u73Ibdnu5GUk0tdi2nhnipQSGiPRaWXVjt0+82kIibtpbUacy7AHIGPNToBl41Heok6vZbo739TYd47jGGLPWGLO2tLS0+6BlwFo2N4dbzptJnPMObEyU4ZbzZqqBp0iI8ufaoqS6gey07vtfgLcCA9A2kg6UwBCRXivzNJDZTQVGWkIMcTFRSmCIK77/r/V8/1/r3Q5DgshpqvkF4KvOthDwVkmMbHe1XGCvczy3k+OH3MYYEwMMwrtlpatzHcZae6+1dr61dn5WVlZ/fiyJcMvm5pCRHAuAMfCFWcNdjkhEuuLPtUVJVUO3I1R9RrYlMPSmTHtKYIhIr5V6Gtr6XHTGGENWSrwSGCIScMaYpcCPgS9aa9u/TfU8cLEzWWQs3mada6y1RUC1MeZYp7/F14Dn2t3GN2HkfGClkxBZDpxhjMlwmnee4RwT6bOG5haKqxrIzUikqcWyRy9SRCJea6ulzNOzBEZOehKgCoyOlMAQkV6pb2qhur75iJ2Ts1Lj1QNDRPzKGPMYsAqYbIwpMMZcBfwJSAVWGGPWG2PuAbDWbgKeADYDrwDXWWt9cyuvBf6Ot7FnPgf7ZtwHDDHGbAP+G7jBOVc5cBPwofPxa+eYSJ8VVXhHKZ44yVupk1/icTMcEQmC8tpGmlttjxIYiXHRZKbEqQKjgxi3AxCR8OIboXqk5kNZqfHsKVfGWET8x1p7SSeH7+vm+jcDN3dyfC0wo5Pj9cAFXZzrfuD+HgcrcgS+FyUnTszin6t3s73MAwx1NygRCShfdXJPemAA5GQkKYHRgSowRKRXyjyNQM8SGNpCIiIi0jlfWfj0EWkMTo5je2mNyxGJSKD5Jor0pAIDvI08tYXkUKrAEJFeKXOeeLtr4gmQlRJPeW0jTS2txB5hzrWIP119wji3QxAROaLCijqiowzDByUwPitZCQyREOavtUVJlXfrWHZqzyowRmYk8eqmfbS2WqKiOhuINfAogSEivXJwC8mRe2BYC+U1jQztYZmciD+cNk0l2CIS+goO1DEsLYGY6CjGZabw2qfFbockIl3w19qirQIjrecVGE0tlpLqBoYN0noatIVERHqpNz0wAG0jkaDLL/WQX6pmeCIS2goO1JLjjEkcl5XM/ppGKmubXI5KRDrjr7VFaXUDqQkxJMRG9+j6uW2jVLWNxEcJDBHplTJPY4+eeJXAELf85Ok8fvJ0ntthiIh0q/BAXduLk3FZKQDklyn5KhKK/LW2KKmub1sj90Ruhm+Uqhp5+iiBISK9UuppIOsI1RdA23WUwBARETlUU0sr+6rqyU33JjDGZyUDqA+GSIQrqWrocQNPUAVGZ5TAEJFeKatuOOL2EWhXgeFRAkNERKS9fZX1tNqD766OHJxETJRhu7a/iUS0kuqGHjfwBEiIjSYzJV4VGO0ogSEivVLmaSAztfsGnuB9wk1NiFEFhoiISAd7nHdTfe+uxkZHMWpIkvr3iEQway0l1fW9qsAA3yhVJTB8lMAQkV4p8zT2qAIDvFUYSmCIiIgcyvdixNfEE2BcZoq2kIhEME9DM/VNrT2eQOLjTWBoC4mPxqiKSI81NLdQWdfU8wRGihIYEnz/79SJbocgItKtwgN1GAPDBx1MYIzPSubtz0ppabVERxkXoxORjvyxtmgbodqLLSTg3Wq2fNM+WlstUXpuUAJDRHpuv6cROPIIVZ+s1Hg27a0KZEgihzl+YqbbIYiIdKvgQB3D0hKIizlYDD0+K4XGllYKDtQyekiyi9GJSEf+WFuUVPkSGL2vwGhqsRRX1x+S9ByotIVERHqszGnImZly5B4YoC0k4o5NeyvZtLfS7TBERLpUcKCWnPRDX4iMcyaRqA+GSOjxx9qipLoeoE9bSECjVH2UwBCRHmtLYPQwc5yVGo+noZnaxuZAhiVyiF+/sJlfv7DZ7TBERLpUWFHX9qLEZ1xWCqBRqiKhyB9rC9+bell92EICGqXqowSGiPRYWbV3C0lWL3pgtL+diIjIQNfc0kpRZX3bixKfwclxpCfFkq8EhkhEKqluIC4mirSE3nVxaKvAKFcFBiiBISK9UOrxZY57XoHhvV19wGISEREJJ/uq6mlptYdMIPEZn5XCdm0hEYlIJVXeEarG9K4RZ0JsNJkp8dpC4lACQ0R6rMzTQEp8DAmx0T26flsCQ30wREREAO8EEuCwLSQA4zKTVYEhEqFKqht63cDTJzcjkYIKbSEBJTBEpBfKPI09buAJSmCIiIh0VNCWwEg67LJxWSmUeRqoqm8KdlgiEmDeBEbv+l/45GYkqgLDoTGqItJjZdUNPR6hCjAkOZ4oowSGBNePlk52OwQRkS75XoQMH3T4CxnfJJLtpTXMGZkezLBEpBv+WFuUVNVz3PghfbptbkYSyzfto6XVEh3Vuy0okUYJDBHpsVJPAxOcLuk9ER1lGJwc39Y7QyQY5o0e7HYIIiJdKqyoJTs1vtPtmOPbJpF4lMAQCSH9XVvUN7VQVd/cry0kTS2Wkup6hg86fPvZQKItJCLSY2WeBjJTe76FBLzbSFSBIcH00a5yPtpV7nYYIiKdKjhw+AhVn1GDk4iOMhqlKhJi+ru28K2F+7OFBNA2EpTAEJEeampppaK2qVdbSEAJDAm+376yld++stXtMEREOlVwoI6cTvpfAMTFRDFqcBL5mkQiElL6u7YocdbCWWl9rcDwPmcUHFAjTyUwRKRH9nsaAXqdwMhWAkNERASAllZLUWXXFRjgnUSiCgyRyFJaXQ/Qry0kAAXlqsBQAkNEeqTM6WPRpwoMTwPW2kCEJSIiEjZKqutparHkpHedwBifncKO/TW0tOrvpkikKOnnFpKE2GiyUuO1hQQlMESkh3yNOLN6mTnOSomnqcVSWaeRcCIiMrAVto1Q7b4Co7G5lb0VeqEiEilKqhqIMjA4uXe95NrLzUikoEJbSJTAEJEeKfPt3etDBQZolKqIiEhBWwKj8x4YAOOcSSTb1AdDJGKUVNeTmRLfrxGouRlJqsBAY1RFpIfKfD0w+jCFBLwJjIlDU/0el0hHvzhnmtshiIh0yteAr7stJOOykgHYXlrDKZODEpaIHEF/1xYl1Q1k97GBp09uRiKvbCyipdX2KxES7pTAEJEeKfM0kBQXTVJc75422hIYHlVgSHBMHzHI7RBERDpVWFFHZkociXHRXV5nSHIcgxJj2a4KDJGQ0d+1RUlVA8MG9a3/hU9uRiJNLZaS6nqGD+o6CRrpAraFxBhzvzGmxBizsd2xXxljCo0x652Ps9pddqMxZpsxZqsxZkm74/OMMXnOZXcZY4xzPN4Y8y/n+GpjzJh2t7ncGPO583F5oH5GkYGkzNPQ6waeoC0kEnzvfl7Gu5+XuR2GiMhhuhuh6mOMYVyWJpGIhJL+ri1KPQ19nkDic3CU6sDeRhLIHhgPAEs7OX6ntXaO8/ESgDFmGnAxMN25zV+MMb7U9N3ANcBE58N3zquAA9baCcCdwG3OuQYDvwSOARYAvzTGZPj/xxMZWEqrG8hM6X3jodT4GOJjopTAkKD548rP+ePKz90OQwKgizdHBhtjVjhvWqxo/zdfb45IqCk4UEduN9tHfMZlppCvCgyRkNGftUVLq2W/XxIYzijVAwO7kWfAEhjW2reB8h5e/VzgcWttg7V2B7ANWGCMGQ6kWWtXWe8MxoeAZe1u86Dz9VPAYmcBsgRYYa0tt9YeAFbQeSJFRHqhrxUYxhjvKFUlMESk/x7g8L/pNwCvW2snAq873+vNEQk5ra2Wwoq6bieQ+IzLSqakuoHqek3wEgl3+z0NtFrISuvfFhJf75yCclVgBNu3jTEbnHdRfH/8c4A97a5T4BzLcb7uePyQ21hrm4FKYEg35zqMMeYaY8xaY8za0tLS/v1UIhGuzNNIZh8zx1mp8eqBISL91sWbI+3f0HiQQ9/o0JsjEjLKPA00Nrf2KIEx3mnkuaNM20hEwl2J8yZefyswEmKjyUqNZ48qMILqbmA8MAcoAu5wjnfWRtV2c7yvtzn0oLX3WmvnW2vnZ2VldRO2yMDW3NLKgdrGPlVggHf0qiowRCRAhlpriwCcz9nOcVfeHBHpyh5n33pOjxIY3lGq6oMhEv5KquuB/icwwLuNRD0wgshaW2ytbbHWtgJ/w1uGCd6FwMh2V80F9jrHczs5fshtjDExwCC878p0dS4R6aPymkasPdiQs7e0hUREXODKmyOq7pSuFFZ4X3TkHqGJJ8CoIUlEGTSJRCQClFQ5FRj93EIC3ucPJTCCyCnb9PkS4GvC9TxwsdM8ayze/ahrnHdSqo0xxzolnF8Dnmt3G18TrfOBlU4p6HLgDGNMhrNF5QznmIj0kW/7R1YfmniCN4FRXttIU0urP8MS6dT/njeT/z1vptthSPAU+9YXzucS57grb46oulO64mu8l9ODJp7xMdGMHJxEviowREJCf9YWvi0kfWmG31FuRiJ7K+poae00hz4gBHKM6mPAKmCyMabAGHMV8Fun6/cG4BTg+wDW2k3AE8Bm4BXgOmtti3Oqa4G/4927mg+87By/DxhijNkG/DdO0y5rbTlwE/Ch8/Fr55iI9FGZpxGg71tIUuOx1lvJIRJo47NS2sqvZUBo/4bG5Rz6RofeHJGQUXCgjoykWJLjY3p0/XGZyZpEIhIi+rO2KKmuJz0plviY6CNf+QhyMxJpbrUUV9X3+1zhqmfPoH1grb2kk8P3dXP9m4GbOzm+FpjRyfF64IIuznU/cH+PgxWRbpW1ZY773gMDvKNYh/qhfE6kO69tLgbgtGlDXY5E/M15c+RkINMYU4B3MsitwBPOGyW7cdYG1tpNxhjfmyPNHP7myANAIt43Rtq/OfKw8+ZIOd4pJlhry40xvjdHQG+OSB8UHqjr0fYRn/FZKazavp/WVktUVGe7mEQkWPqztiip6v8IVR/fc0jBgTpG9KCaKxIFLIEhIpGjzNlC0p8pJID6YEhQ/O2d7YASGJGoizdHABZ3cX29OSIho+BALZOGpvb4+uOyUqhvamVvZe8SHyLif/1ZW5RUN5Cd6p838HxTjAoO1LJg7GC/nDPcuDFGVUTCTJmngYTYKJLj+lb6pgSGiIgMZNZaCivqetT/wmecM0pVfTBEwltptf8qMHzPIQO5kacSGCJyRKXVDWSmxOPdLt57vq0nvmagIiIiA8n+mkbqm1rb3j3tCV8CQ5NIRMKXtZbS6gay0vyTwEiIjSYrNb6tKfBApASGiBxRmaexz/0vwPtkm5YQowoMEREZkHzvlvZmK0hWSjypCTFsVwWGSNiqrGuisaXVb1tIwLuNRBUYIiLdKPM09CuBAd5tJEpgiIjIQFTovNjI6UUFhjGGcVkpbC9TBYZIuPKNUPXXFhLwJkIHcgJDTTxF5IjKPA3MHZXRr3MogSHBcudFc9wOQUTkEL5y794kMADGZybzfv7+QIQkIr3Q17VFSVUgEhiJvJxXREurJXoATihSBYaIdKul1VJe00hWSly/zpOVmqAeGBIUI9ITB+xoMREJTQUH6v5/e/cd3lZ5Nn78+0iy5b1lJ7Gd4cRxQoghJIQ9ApRQRqGUAJ3Q8ist3YsW+rZvB+WFlu7FaAu00LICDatAIUBYYSQEEjKdOMuOY1mJh+QhW9Lz+0NHjpPYjoekcyTdn+vyZflI5+i2rfHoPs9z3+RlOMjLSBvVflWubPZ29NDpD8QoMiHESIx1bOH29gAHCtpHQ2VhFoGQprmjJ2rHTCSSwBBCDGt/Zy8hPfYWqhGuHJmBIeLjyff38OT7e8wOQwgh+jW2ja0V6nRXDgDbPVIHQwgzjXVs0b+EJC+6NTAgdTuRSAJDCDEsjzFrIho1MHz+AF29chZJxNb9b+7k/jd3mh2GEEL0a2jtGlUHkogqI4GxTTqRCGGqsY4t3B1+stLt5DijV7nhQAIjNTuRSAJDCDGsaCYwADze3nHHJIQQQiQKrTUNrd2jrn8BMKU4C6WQTiRCJCi3tyeq9S+A/qUsMgNDCCEGcSCBMd4aGOEX7xZfaq7XE0IIkZrauvro6g2OaQlJRpqdisJMmYEhRIJq8fqj2kIVwq8LpblOmYEhhBCDidStiEYNjIHHE0IIIVJB5CzpWJaQAFSV5MgMDCESVIvXjysvujMwIPx6IjMwhBBiEB5fL+kOG7njXLvXPwNDEhhCCCFSSH8L1TF2R5ruymG7p5NQSEczLCFEHLi9/qgvIQGoKMxK2QRG9KqJCCGSksfrx5XjRKnx9Zkuyk7HpiSBIWLv9k/NNzsEIYTo19gW/pBROYYlJBBupdrdF2RvR4+0iBbCJGMZW3T1BvD5A1FfQgLhGRj/WddEMKSx28Y3Rk80MgNDCDGsFp9/3PUvAOw2RXGOkxafJDBEbBVlp1OUPf7HrBBCRENDaze5Tgd5mWM7b1jlygakE4kQZhrL2MLdYbRQjdEMjEBIs7cj9WrLSQJDCDEsj6+3f/nHeLlynDIDQ8TcI6t288iq3WaHIYQQQHgJSXlh5phnMk43WqlKHQwhzDOWsYXbGPOWxqgGBkDD/tQr5CkJDCHEsDw+/7hbqEa4ciWBIWJv6eoGlq5uMDsMIYQAwjMwxlrAE8Jnb3OcDuplBoYQphnL2MLtDc+OiNaJwIH6ExgpWAdDamAIIYYUCmn2d/ZGNYFR1+yNyrGEEEKIRNDY2s2JVcVj3l8pRZUrm3qPzMBIBMvWNHLbc5vZ09bNpIJMrl9cwyXzys0OS5jgwBKS6NfAiNTDScUEhszAEEIMqbWrl2BIR6UGBhgzMHx+tJZK6kIIIZJfe3cfXn9gzB1IIqpKstnmlhkYVrdsTSM3PraOxrZuNOECrjc+to5laxrNDk2YwO31k2ZXFGalRf3YGWl2SnOd/V2OUokkMIQQQ/L4egEoiWINjL6gpr27LyrHE0IIIaws8uFiPEtIAKpcOexp76GrNxCNsESM3PbcZrr7ggdt6+4Lcttzm02KSJjJ7e2JSie/oVQUZsoMDCGEGMhjdAyJ5hISkFaqQgghUkPkw0XFGFuoRkQKeW6XZSSWtqdt8A+TQ20Xya3F68eVF/3lIxEVhVk0tMkMjMMopZYopXKNyz9QSj2mlDou9qEJIcwWSTRIAkMkkns/u5B7P7vQ7DDEMGRsIVJFo5HAKB/3DIxwK1XpRGJtk4ZYKjTUdpE4xjK2aPH6Y9JCNaKiMJOmth4CwVDM7sOKRjID44daa69S6lRgMfB34PbYhiWEsILIDAxXtBMYPklgiNjJTLeTmW43OwwxPBlbiJTQ0NpNVrp93Gvgp5Vko5QkMKzu+sU1pNkPXi6QmWbn+sU1JkUkomUsYwt3zBMYWQRCmuYUOzE4kgRGZCHXBcDtWuvHgehU9BNCWFqLz0+63UZeZnQaFskMDBEP963cwX0rd5gdhhiejC1ESmho7aK8IHPca+Az0uxMys9km7RStbRL5pWzcGpR/89F2encculc6UKSBEY7tugNhNjf2RuTDiQR/a1U96fWMpKRJDAalVJ3ApcD/1FKOUe4nxAiwXm8vZTkpEet+FCu04HTYZMEhoipp9Y28dTaJrPDEMOTsYVICY1t3eMu4BkxvTSHeo8kMKwuqDWzJ+ZhU/CpEyZL8iJJjHZsEZnFXJoX2yUkkHqtVEcyWLgceA44T2vdBhQB18cyKCGENXh8/qh1IIFwL3tXrlMSGEIIGVuIlNDQ2j3uAp4RVSXZbG/plFbkFlfX7OOYinyqS3NZ29hudjjCJG5jrBvLJSSR2iqSwDiE1roLcAOnGpsCQF0sgxJCWIPH549aAc8IV65TamAIkeJkbCFSgbenj/buvnEX8IyY7sqmszdIc4e8h1rVPp+ffZ29zCjNYW5FPusa2iXhlKLcHT3AgeXTsZCRZqcsz9nfrjlVjKQLyY+A7wE3GpvSgPtjGZQQwhrCCYzoLkt35cgMDCFSnYwtRCpobIu0UI1OAqPKaKUqdTCsa6s7/L+pLsultiKffZ297GnvMTkqYYYDMzBiVwMDjFaqMgPjMB8FPgJ0Amit9wC5sQxKCGG+UEizz9cbmxkYksAQItXJ2EIkvYb9kQRGlJaQ9LdSlQSGVdVFEhilOcwtzwdgXUObiREJs7i9fpQi6icCD1VRmElDm8zAOFSvDs990gBKqezYhiSEsIL27j4CIR2TBMb+rl76UqxntYifh75wEg994SSzwxDDi/rYQin1TaXUeqXUB0qpB5RSGUqpIqXU80qpOuN74YDb36iU2qqU2qyUWjxg+3yl1Drjut8ro4qxUsqplHrI2P6WUmrqeGMWyS0yrbu8IDozMCbkZZCVbmebtFK1rK1uH9npdibmZzB7Yh4Om2Jtg9TBSAajHVu0eP0UZ6fjsMe2PnVFYSZNbT0EUmhcPZK/6MNGpfACpdTngReAv8Q2LCGE2SJ1KqJZxBPCCQytYX9nb1SPK4RIKFEdWyilyoGvAQu01kcDduBK4AZguda6Glhu/IxS6ijj+jnAecCflVJ243C3A9cC1cbXecb2a4BWrfUM4DfAz8car0gNjW3dOB22qJ2BVUpR5cqm3iMJDKuqc3uZUZaLUoqMNDs1E3JZJ4U8U1KLtwdXjJePQHiGVyCkaU6h2c0jKeL5S2Ap8ChQA/yv1voPsQ5MCGEuj/FCGIsaGABuKUImYuSuV7Zx1yvbzA5DDCNGYwsHkKmUcgBZwB7gYuDvxvV/By4xLl8MPKi19muttwNbgYVKqYlAntZ6pTFD5B+H7BM51lLg7MjsDCEGE+5Akhm1VuQAVSU5bHPLEhKrqmv2UV2a0/9zbUU+a6WQZ1IY7djC7fXHtANJRH8r1f2ps4xkRHNatNbPa62v11p/R2v9fKyDEkKYLzIDwxWDJSTh40tRKxEbyze6Wb7RbXYY4giiObbQWjcCvwR2AU1Au9b6v0CZ1rrJuE0TUGrsUg7sHnCIBmNbuXH50O0H7aO1DgDtQPF44hbJraG1m/Io1b+IqHJls6e9m56+YFSPK8avvasPt9fPzLIDCYy55QW0d/exe39qFVlMRqMdW7g74pXACL/GpFIhzyETGEopr1KqY5Avr1KqI55BCiHiz+MLL/GIRQ0MQAp5CpGCYjW2MGpbXAxMAyYB2UqpTw23yyDb9DDbh9vn0FiuVUqtUkqtamlpGT5wkdQa27qj1oEkYrorB61huywjsZw6txeA6tID9YhrK8KFPNc2tpkRkjBJKKTx+PyU5sU+gTGpILxMRRIYgNY6V2udN8hXrtY6L55BCiHiz+Pzk2ZX5GemRfW4kYSIJDCESD0xHFucA2zXWrdorfuAx4CTgWZjWQjG98jpswagcsD+FYSXnDQYlw/dftA+xjKVfGD/IL/jXVrrBVrrBS6Xaxy/kkhkXb0B9nf2Rj2BcaATiSQwrCbSgWTGgCUkM8tySbfbWCeFPFPK/q5eAiEd8xaqAE6HnbI8J7tbZQnJYZRSpUqpyZGvWAYlhDCfx+unONuJzRbdJd4ZaXbyMhySwBBCRHNssQs4USmVZdSlOBvYCDwBXGXc5irgcePyE8CVRmeRaYSLdb5tLDPxKqVONI7zmUP2iRzrMuBFLQvbxRAajbOh0epAEjGtRFqpWlVds4/MNPtB//N0h43ZE3N5X1qpppRInTdXHJaQQHgZSUMKJTAcR7qBUuojwK8IT8l0A1MIDwrmxDY0IYSZPD4/Jbmx6V3tynX219gQItoy0uxHvpEwVbTHFlrrt5RSS4F3gQCwBrgLyCHc8eQawkmOJcbt1yulHgY2GLf/stY6UlTgOuBeIBN4xvgC+Btwn1JqK+GZF1eOJVaRGiLTuSuiXAMjK93BpPwMtkkCw3Lq3F5mlOYcduJnbkU+y9bsIRTSUT8pJOJnNGMLtzdc5y0eNTAgXMhz9c7WuNyXFRwxgQHcBJwIvKC1nqeUWgR8PLZhCSHM5vH1Rr3+RYQr1ykzMETM/P1zC80OQRxZ1McWWusfAT86ZLOf8GyMwW5/M3DzINtXAUcPsr0HIwEixJFEzoZWRnkJCcD00hxppWpBW90+Tqo6vK5vbXkB97+5i+37OpnuyhlkT5EIRjO2cBtj3HgsIYFwAuOptU0EgiEc9hEvsEhYI/kN+7TW+wCbUsqmtX4JODa2YQkhzObx+WOYwMiQBIYQqU3GFiKpNbR1k263xeR9tKokm/qWTmnNaSHenj6a2nuYUXZ4gmKuUchT6mCkjsgYNx5FPCE80ysY0uztSI0OfyNJYLQppXKAV4B/KqV+R3i6pRAiSWmtY5vAyJEZGCJ2fr+8jt8vrzM7DDE8GVuIpBZuoZoZkyUDVa4cfP6AvI9ayFajgOfADiQR1aU5OB021koCI6GNZmzR4vWTm+GI25LWSLHgVOlEMpIExsVAF/BN4FlgG3BRLIMSQpirvbuPvqCmJCd2NTA6e4N0+uXzioi+17d6eH2rx+wwxPBkbCGSWkNrd9QLeEZEOpFslToYllHXHP5fzBxkBobDbmPOpDzWSSvVhDaasYXb2xO3+hdwoNaOJDAOobUOACuBHcCYe7ULIazP44tt9eTIcT1SyFOIlCZjC5GsGlu7o95CNSJSR0FaqVpHnduL02EbsmhrbUUBHzR2EAzJsp9U4O7wx63+BcCkgvB9pUonkpEkMF4BMpRS5cBy4LOEq3MLIZJUi7cXIKZFPMP3IwkMIVKUjC1E0urpC+Lx+WOWwJiQl0Fmml0SGBZS5/Yx3ZWDfYglQ3PL8+nuC0r3mBTh9vrjVv8CwOmwU5bnlBkYAyitdRdwKfAHrfVHgaNiG5YQwkwxn4GRIwkMIVKcjC1E0op8iCiPUQLDZlNMK8mm3iMfhq2irtlH9SDLRyKOqQwX8pQ6GMlPax33JSQQXkYiMzAOUEqpk4BPAk8b20bSflUIkaAiCYyYz8CQJSQiBgqz0inMik39FhE1MrYQSauxLZzAGGo5QTRUubLlbL5FdPoDNLZ1U106dAJjWkkO2el21jW0xS8wEVUjHVt4/QF6+kJxXUIC4UKeqTIDYySDha8DNwL/1lqvV0pVAS/FNiwhhJk8Pj92m6IgMy0mxy/KTsemZAaGiI07Pj3f7BDEkcnYQiStyFnQWC0hgXAdjKfXNdHTF4xbpwMxuEgiacYgHUgi7DbFnPJ81jbKDIxENdKxhbsjtrOYh1JRmMlTa5sIBEM47CMuc5mQjpjA0Fq/QnitauTneuBrsQxKCGEuj7eX4uz0mLR/g/AbebG0UhUiZcnYQiSzhtZuHDYV0zOwVa5stIad+7qomTD0B2cRe5EOJMMtIQGoLc/nvjd30hcMkZbkHzBTmdvbA2DKEpJgSLO3oyems7+sQJ49QojDeHz+mC0fiXBJAkPEyM+f3cTPn91kdhhCiBTV2NrNpILMIQs6RsOBTiSyjMRsdW4f6XYbU4qG/9A4tyIffyDUn/AQiWWkY4vI2DaeRTwBKlOolaqsNxVCHMbj81MS48yxK9cpNTBETLy7s9XsEIQQKayhtSumy0cAppVkA1DvkU4kZqtr9lLlyj7itP3aigIA1jW2cdSkvDhEJqJppGOLSALDZUINDEiNBMYRZ2AopU4ZyTYhRPJo8fopyYltEURXrszAECJVydhCJLPGtm7KC2KbwMh2OpiQl8E2t5zNN1ud28eMYQp4RkwpyiI3wyGdSJKc2+vH6bCRlxHfeQITCzJQipToRDKSJSR/GOE2IUQS0Frj8fX2tzqNFVeuE4/PTyikY3o/QghLkrGFSEr+QJDmDn9c1qBPL81mm8zAMFV3b5DdrV1UD1PAM8JmU8wtz2edFPJMau6OHkrznCgVuyVkg3E67JTlZqTEDIwhU0NGe7OTAZdS6lsDrsoDpNyxEEmqoydAbzAUlxoYfUFNe3cfhdnS8lKIVCBjC5Hs9rSFC/jFegkJQFVJDsvea0RrHfcPSyJsW4sPrY9cwDNibkU+d7+2HX8giNMhL3nJyO31x72FakS4lWpqz8BIB3IIJzlyB3x1AJfFPjQhhBk8Rl2KktzYLyEBpA6GiLqJ+RlMzDdn8CCOSMYWIqk1Gmc/y+ORwHBl4+0J4PH1xvy+xOC2Gkt4qkewhASgtryAvqBm815vLMMSMTDSsUU4gRHfAp4R4QRGCs/A0FqvAFYope7VWu8c7YGVUncDFwJurfXRxrYi4CFgKrADuFxr3WpcdyNwDRAEvqa1fs7YPh+4F8gE/gN8XWutlVJO4B/AfGAfcIXWeoexz1XAD4xQfqa1/vto4xciVXkixYdyYvsBsD+B4fUzs0xawIno+e2V88wOQQxhvGMLIawucvYzLjMwjE4k21p8/e+pIr7q3F4cNsWU4uwR3b62Ih+AtQ3t/UU9RWIY6djC3dHDKdOLYxzN4CoKs3hybROBYOiIRWUT2ZC/mVLqt8bFPyqlnjj0awTHvhc475BtNwDLtdbVwHLjZ5RSRwFXAnOMff6slIrMq7oduBaoNr4ix7wGaNVazwB+A/zcOFYR8CPgBGAh8COlVOEI4hVCQP+ZnLjNwJBCnkKkjCiMLYSwtIbWbuw2xYS82M8Cm+4yOpG0SB0Ms9Q1+5hakk26Y2QfFisKMynISmOdFPJMSj19QTp6AqYlFCsKMwmGNE3tPabcf7wMVx71PuP7L8dyYK31K0qpqYdsvhg407j8d+Bl4HvG9ge11n5gu1JqK7BQKbUDyNNarwRQSv0DuAR4xtjnx8axlhIeDClgMfC81nq/sc/zhJMeD4zl9xAi1fQvIYlDEU+QBIaIvp88uR6AH100x+RIxCDGNbYQwuoa27qZkJcRl7Ofk/IzyUizUd8inUjMUuf2MWvCyGeRKhUu5LlWCnkmnJGMLSJjWvNqYISLBze0dlNZFPtCwmYZbgnJauP7iijeX5nWusk4bpNSqtTYXg68OeB2Dca2PuPyodsj++w2jhVQSrUDxQO3D7KPEOIIPD4/NgWFWbGdgZHrdOB02KQGhoi6DXs6zA5BDCFGYwshLKOhtSsuy0cg3NVianE29dKJxBQ9fUF27uvkomMmjWq/2op87lhRT09fkIw0KeSZKEYytnB7wzMfXHnmzcCAyFI2c5axxMMR08NKqVOUUs8rpbYopeqVUtuVUvVRjmOw0sl6mO1j3efgO1XqWqXUKqXUqpaWlhEFKkSy8/j8FGU7sdtiW9FcKYUr1ykzMIRIQXEaWwgRdw2t3XFpoRox3ZXDNpmBYYrtnk5CeuQFPCNqKwoIhjQbmiTZnmzcHZEZGOYkMCYWZKAUSV/IcyTz2/4G/Bo4FTgeWGB8H4tmpdREAOO729jeAFQOuF0FsMfYXjHI9oP2UUo5gHxg/zDHOozW+i6t9QKt9QKXyzXGX0mI5NLi7aUkJz5tTSWBIUTKiubYQghL6A2EaO7oiUsHkojprmx27+/CHwjG7T5FWF2kA8kIW6hGRAp5Sh2M5BOZVWzWEhKnw05ZboYkMIB2rfUzWmu31npf5GuM9/cEcJVx+Srg8QHbr1RKOZVS0wgX63zbWG7iVUqdaNS3+Mwh+0SOdRnwotZaA88B5yqlCo3ineca24QQI9Di88et+JArRxIYQqSoaI4thLCEve09hHR8OpBEVLlyCGnYta8rbvcpwrY2e7EpmFYysg4kERPyMijJcbJWEhhJx93hx25TFGfH50TgYMKtVJP79WC4Ip4RLymlbgMeA/o/aWit3x1uJ6XUA4QLdpYopRoIdwa5FXhYKXUNsAtYYhxrvVLqYWADEAC+rLWOpJKv40Ab1WeMLwifvbnPKPi5n3AXE7TW+5VSNwHvGLf7aaSgpxDiyDxeP1WjfDMeK1euk1U7W+NyXyJ1VLni8/gV4zKmsYUQVtbfQrUgngmM8OvdtpZOqqUleVzVuX1MLc7G6RhdHQulFLUV+axrbItNYCImRjK2cHt7KMlJxxbjZdjDqSjM5J0dyT22HkkC4wTj+4IB2zRw1nA7aa0/PsRVZw9x+5uBmwfZvgo4epDtPRgJkEGuuxu4e7j4hBCH01rj8fnjuoRkf2cvfcEQaUncr1rE1y2X1podgjiyMY0thLCyhrbwtO141sCInP2v90gdjHirc/uYMcr6FxFzy/N5ebObTn+AbOdIPo4Js41kbOH2+k1bPhJRUZjFk2ubCARDcemGZIYjPmO01oviEYgQwnw+fwB/IBS/JSTG/ezz9TIh39wXfCFE/MjYQiSjhtZubIq4vp/lZqRRludkm1s6kcRTbyDEDk8ni+eUjWn/2op8Qho2NHVw/NSiKEcnzOLu8DPR5PFsRWEmwZCmqb0naVupHjGBoZT638G2a61/Gv1whBBm8vh6ASjJiV8NDAj3zZYEhoiWGx9bC8hMDCuTsYVIRg2tXZTlZZDuiO9Zz6qSHJmBEWc79nUSCGmqS8e2bGduebiQ59qGdklgJIiRjC3cXj/HVObHK6RBRWaANbR2p24CAxiY0s0ALgQ2xiYcIYSZPEb15LglMIwZGC2+HsKNhIQYv/oWOROZAGRsIZJOY2t3XAt4RlS5snlqbRNaa8I170Ws1TWPrQNJRGleBhPyMljX0BbFqEQsHWlsEQiG2Nfp7z85Z5bIa1C4Jk+xqbHEykiWkPxq4M9KqV8S7gAihEgyHq9JCQzpRCJESpGxhUhGDa3dLJwW/7PpVa4c2rv72N/ZS7HJH55SRZ3bi1Iw3TW2BAbA3Ip81jZKJ5Jksa+zF63BlWfujOKJBRkoRVK3Uh3LHLcsoCragQghzNc/AyM3PkU8S3IkgSGEAKIwtlBKFSilliqlNimlNiqlTlJKFSmlnldK1RnfCwfc/kal1Fal1Gal1OIB2+crpdYZ1/3eaOOO0er9IWP7W0qpqeOJVySXQDDE3o4eyuPYgSRiYCcSER91bh+Ti7LISBtdB5KBasvzqW/pxNvTF8XIhFncHeGxbGmc6sgNxemwU5abkdoJDONNfK3xtR7YDPwu9qEJIeKtxdeLUlCUFZ8ERkaanbwMhyQwhEgxMRpb/A54Vms9CziG8JKUG4DlWutqYLnxM0qpowi3X58DnAf8WSkV+SRyO3AtUG18nWdsvwZo1VrPAH4D/Hyc8Yoksrejh2BIm7KEZIYxC6C+RepgxMvWZh/VY+xAEjG3Irx09oPGjmiEJEwWXg5tfgIDoLIos7+tczIaSQ2MCwdcDgDNWutAjOIRQpioxeunKCs9rm2XXLlOWnySwBDRc9SkPLNDEEcW1bGFUioPOB24GkBr3Qv0KqUuBs40bvZ34GXge8DFwINaaz+wXSm1FViolNoB5GmtVxrH/QdwCfCMsc+PjWMtBf6olFJaaz3WuEXyiJztjGcL1YhJBZmkO2zUe2QGRjwEgiHqPT4WzSod13EihTzXNbZx0vTkrFWQTI40tuifgWHyEhIIvw69vX2/2WHEzEhqYOyMRyBCCPN5fP641b+IcOU6ZQaGiKofXTTH7BDEEcRgbFEFtAD3KKWOAVYDXwfKtNZNxn02KaUinzjKgTcH7N9gbOszLh+6PbLPbuNYAaVUO+EKaZ4o/y4iATUaCYxyE2Zg2G2KacXZMgMjTnbu76IvqMc9A6M4x0l5QSZrG6QORiI40tjCbYxlzS7iCeFCnk+830MgGIrrScl4Sb7fSAgxZh6fP271LyJcuRmSwBBCjJcDOA64XWs9j3CXkxuGuf1grRr0MNuH2+fgAyt1rVJqlVJqVUtLy/BRi6QRmYExqcCcs69VrmypgREn4+1AMlBtRb6lEhjL1jRyyq0vMu2Gpznl1hdZtqbR7JAShtvbQ2FWWtzbKA+mojCTYEjT1N5jdigxYf5fWAhhGabMwMiRGRgiur7x4Bq+8eAas8MQ8dUANGit3zJ+Xko4odGslJoIYHx3D7h95YD9K4A9xvaKQbYftI9SykG49/Nhc3S11ndprRdorRe4XK4o/GoiETS0dlGW58TpGHtRx/GY7sph1/4uegMhU+4/ldQ1e4HxdSCJqK0oYNf+Ltq6esd9rPFatqaRGx9bR2NbNxpobOvmxsfWSRLDcKSxhbvDT2mu+ctH4MBStmQt5CkJDCFEP4+3N+5T31y5Tjp7g3T6pbSOiI6m9p6kPesgBqe13gvsVkrVGJvOBjYQbs16lbHtKuBx4/ITwJVGZ5FphIt1vm0sN/EqpU40uo985pB9Ise6DHhR6l+IiMa2blM6kERUubIJhjS79idv4T6rqHP7qCjMJNs5klKCw6utiNTBMH8Wxm3Pbaa7L3jQtu6+ILc9t9mkiKzlSGMLt9dPaZ75y0eA/mLCyVrIc/zPPCFEUuj0B+juC1IS5+rJLuP+PD5/VAYDQoiU9VXgn0qpdKAe+CzhEzUPK6WuAXYBSwC01uuVUg8TTnIEgC9rrSMj9+uAe4FMwsU7nzG2/w24zyj4uZ9wFxMhgPCZzmMrC0y7/6oBnUhmjLM2gxhenXv8HUgijp4UTmCsbWjntGpzZ2ztaRv8bP1Q28XBWrz+/pbGZpuYn4lSyTsDQz4tCCGAcAIBMKWIJ4Rf+KcUW+OFXwiReLTW7wELBrnq7CFufzNw8yDbVwFHD7K9ByMBIsRAwZBmT1s3F9ZONC2GyAcn6UQSW8GQZluLj9OqS6JyvPysNKYWZ7HOAnUwJhVk0jhIsmKSiTOLEoXWmhavv39Ma7Z0h40JeRnsTtIZGLKERAgBDExgxLmIZ86BBIYQQgiRaNzeHgIhbUoHkoi8jDRcuU62uaUTSSztNuqMRHOWy9yKAkssIfn62dWHbctMs3P94ppBbi0GauvqozcYskwNDAgvI0nWGRiSwBBCANDiDReQMm0Ghk8SGCI6jptSyHFTCs0OQwiRIiIfEiKF88xSVZItMzBirM5IEEVrCQlAbXk+jW3d/SeSzBLpnlGYlQZAXoaDWy6dyyXzyofbLWUMN7aItFAttcgMDAi/HjUmaQJDlpAIIYADMzDiPf2tKDsdm5IZGCJ6vnfeLLNDEEKkkEihPDOLeEK4DsazHzSZGkOyq3OHO5BEdwbGgUKei2pKo3bc0Xpk9W4qizJZ8Z1FfPh3r1Kcky7JiwGGG1u0WDKBkcnj73XTFwyRZk+uOQvJ9dsIIcYs8uJblB3fJSR2m6JYWqkKIYRIUI39MzDMTWBMd2XT2tXH/k7zW3Imq7pmHxPzM8jNSIvaMedMykMpTK2D0dDaxRvb9nHZcZXYbIozZ7l4Z8d+vD19psWUSNzecHeS0jxrLSEJadibhF3ZJIEhhADCMzAKs9JMydK6JIEhouiL963mi/etNjsMIUSKaGjtpiTHSUaa3dQ4pg/oRCJio87tjXqXl9yMNKpKsllrYgLj0dWNAHxsfnjGxZkzS+kLal7fus+0mKxmuLGFVZeQAElZyFMSGEIIIJzAiHf9iwhXrlNqYIioae3qpbVLzkAKIeKjobXb1AKeEf2dSFqkDkYshEKarW4fM8tyo37s2ooC1jW2Rf24IxEKaZa+u5uTpxf3f+hdMLWQHKeDFVvcpsRkRcONLdwdfrLT7WQ7rVOdITIjLBkLeUoCQwgBgMfXa1r7J1euzMAQQgiRmBrbuk1fPgLhM67pdhvbPDIDIxYa27rp6QtFtYBnxNzyfJo7/DR3xH+6/9s79rN7fzdL5lf2b0uz2zituoSXNrWgtY57TInG7e2x1PIRgIn5mSglCQwhRBIzewaGx+cnFJI3SSGEEIkjFNI0tlojgWG3KaYUZ8kMjBiJFPCsLot+AqM2UsjThGUkj6xqINfpYPGcCQdtP7PGxd6OHjbt9cY9pkTj9vpNOwk4lHSHjQl5Gf1FhpOJJDCEEAB4vCYmMHKc9AU17d1SLEoIIUTi8Pj89AZDVJjcgSSiypXNNqmBERN1zeG/6wxX9JeQHDUpD5uCtY3xTWD4/AH+s66JC4+ZSGb6wTVczjQ6ory8uSWuMSWiFgsmMCC8jERmYAghklJ3b5DO3iAlufHtQBIRedGXOhgiGk6ZUcIpM0rMDkMIkQJ293cgyTI5krDprhx27euiLxgyO5SkU+f2UZrrJD8reh1IIrLSHcwsy2VdQ1vUjz2c/6xtorsvyGUDlo9ElOVlcNTEPF7aLHUwYPixhbujx1IFPCMqCrP6uyQlE+tUGhFCmMZjJA7MXEIC4Qx2LIpjidTytbOrzQ5BCJEiItOzrbCEBKDKlUMgpNm9v4sqV/SXOqSyOrcvJstHIuaW5/PSZjdaa5RSMbufgR5ZvZsqVzbHTS4Y9Poza1zc+Uo97d195GdGP3GTSIYaW3T6A3T2BinNtVYNDAi/Lj3+Xjd9wZApXQZjJXl+EyHEmEVmPrgskMAQQgghEkVjW/jsphW6kIB0IokVrTVbm71Ul8buJEttRT4eXy9N7fEp5Lnd08k7O1pZMr9yyITJolmlBEOa17d64hJTImqxYAvViIrCTEIa9sbpMRUvksAQQvS/+FphBoYQ43XV3W9z1d1vmx2GECIFNLR2U5SdTla6NSY1Ty8JzxCol04kUbWnvYfO3iAzYtCBJGJuRQEAa+O0jGTp6t3YFFx6XPmQt5lXWUBehoOXNskykqHGFu5IAiPPigmM8NK23UlWyFMSGEKIA0tITKqBket04HTYpAaGiIqeviA9fUGzwxBCpIAGi3QgicjPSqMkJ51tbpmBEU11zeFOHLFc5jprQi4Om2JtHDqRBEOaR1c3csZMF2XDtP902G2cNtPFy1taUr5T3FBjC7c3PLvBiktIKo0ERrIV8pQEhhACj7cXgOJsc7LHSilcuU6ZgSGEECKhNLZ2UW6RDiQRVSU5MgMjyra6w3/P6hjOwMhIs1MzIZd1cehE8tpWD3s7eliy4PDinYdaVFNKi9fPhqaOmMeViNwd1l1CMiE/A5uSBIYQIgl5fH4KstJId5j3kiAJDCGEEIlEa225GRgQroMhNTCiq67ZR0lOOoXZsZ2pWluRz9qGdrSO7WyHpasbKMhK4+zZpUe87RkzXQC8LN1IBuX2+km32yiIQXea8Up32JiQl9FfbDhZSAJDCIHH5zet/kWEK0cSGEIIIRKHx9eLPxCyTAvViCpXNvs6e2nr6jU7lKRR5/bGtP5FxNzyAtq7+9i9P3ZnzNu7+nhu/V4uPmYSTof9iLd35TqNDiktMYspkbm9PbhynXHrHDNaFYVZMgNDCJF8wgkMc+pfRLhynVIDQ0TF2bNLR3RWSQghxqO/A4nFlpBMN9qnbpNZGFGhtQ63UI1hB5KI2op8ANY2tsXsPp5Yu4feQGhEy0ciFtW4WLOrNaWTYkONLVq8/v5i9FZUUZhJoyQwhBDJxuPrNX8GRq6T/Z299AVDpsYhEt+1p0/n2tOnmx2GECLJRaZlVxRZK4FRZSQw6lukDkY0uL1+vD0BqstiPwNjZlku6XYb62JYyHPpqt3MmpDLnEl5I97nzFmlhDS8Upe67VSHGlu4O6yfwGhq706q8bUkMIQQeLwWWEJivPjv86Vudl8IIUTiiEzLttoMjMrCTNLsinqPzMCIhi1GB5J4LCFJd9iYPTE3Zp1ItjR7eb+hnSULKke15OGYigIKs9J4WdqpHsbt7bFkAc+IisIsQhqa2nrMDiVqJIEhRIrr6Qvi9QdMzx67jASK1MEQ43XFnSu54s6VZochhEhyja3d5GemkZthreJ9DruNyUVZMgMjSuqaIx1IYr+EBGBuRT4fNLbHpG3pI6t247ApLjl20qj2s9sUp890sSKF26kONrboDYRo7eqzZAvViEiR4WQq5CkJDCFSnMeoO2GFGhgALb7kyRALIYRIXg2tXZbrQBIx3ZUjNTCipM7toyArLW7jpNryArz+ADv2Rff/1xcM8e81jZw9u5TiMcy6XVRTyr7O3ri0eU0UkTF0aZ61Z2BAcrVSlQSGECkuMuPBKktIZAaGEEKIRNDY1m255SMRVa4cdu7rJJBE697NstXtZWZpbty6TMw1CnlGO1Hw8uYWPL5elswfefHOgU6f6UIpeEnaqfZzG2NWKy8heXv7PgC+++haTrn1RZataTQ5ovGTBIYQKc5j1JwwO4FRIktIhBBCJAitNQ2t3ZZroRpR5cqmL6iT6qyrGbTWbGn2MSMOBTwjqktzyEizRb0OxiOrdlOS4+SMGteY9i/KTueYigJppzqAuyM8a9iqS0iWrWnkh4+v7/+5sa2bGx9bl/BJDElgCJHi+peQmJw9zkizk5fhkASGEEIIy2vt6qOrN2jhJSTZANR7pA7GeHh8vbR391EdhwKeEQ67jTmT8qPaiWSfz8+Lm9x8dN4k0uxj//i3qKaUtQ1t7JO298CAGRgWXUJy23Ob6e4LHrStuy/Ibc9tNimi6JAEhhApzuO1Rg0MCC8jaZE3RTFOF9ZO5MLaiWaHIYRIYo2RDiQWTWBUlURaqUodjPGoc4c7kMSrgGfE3PJ8PtjTTjBKBTOXvbeHQEizZMHYlo9ELJrlQmt4pS71ZmEMNrZwe/0oBcXZ5o+hB7OnbfAZWENtTxSSwBAixXl8fvIyHDgddrNDCScwZAaGGKdPnzSVT5801ewwhBBJLFLR36ozMAqz0ynKTmebdCIZl/4OJHFcQgJQW5FPV28wKp1ktNY8smo3x1TkM7NsfImYoyflU5KTzkubUi+BMdjYosXbQ3G2E8c4ZrXE0qQhavQMtT1RWPOvLYSIG4+v1/TlIxGu3AxJYIhx6+4N0t0bPPINhRBijCK1JaxaAwOgqiRbOpGMU53bS26GI+5FGmuNQp7RqIOxfk8Hm/Z6uWycsy8AbEY71VfqWqI2OyRRDDa2cHf4LV3A8/rFNWSmHXyCMs2uuH5xjUkRRYckMIRIcS0+v+kFPCNcOTIDQ4zf1fe8zdX3vG12GMIESim7UmqNUuop4+cipdTzSqk643vhgNveqJTaqpTarJRaPGD7fKXUOuO63yuj9YBSyqmUesjY/pZSamrcf0FhGY1t3eQ6HeRnppkdypCqXNmyhGSc6pp9VJfmxK0DScS0khyy0+1R6UTyyKrdpDtsfKR2UhQiC9fBaOvq473dbVE5XqIYbGzh9vr7u+hZ0SXzyrnl0rmUF2SiAKfDhsOmWDSr1OzQxkUSGEKkOI/Pj8sqCYxcJ529QTr9AbNDEUIkpq8DGwf8fAOwXGtdDSw3fkYpdRRwJTAHOA/4s1IqcprqduBaoNr4Os/Yfg3QqrWeAfwG+HlsfxVhZQ2tXZatfxFR5crB4/PT3t1ndigJa6vbF/f6FwB2m2JOeT7vN7SN6zj+QJDH39/D4jkTyM+KTrLttOoSbApelnaquL09lp6BAeEkxus3nMX2Wy/g0etOpicQ4s8vbzU7rHGRBIYQKc7j9VuigCfQn8X2SCFPIcQoKaUqgAuAvw7YfDHwd+Py34FLBmx/UGvt11pvB7YCC5VSE4E8rfVKrbUG/nHIPpFjLQXOVvE+LSssw8otVCOmuyKFPKUOxljs8/nZ19kb9/oXEbXl+WzY00FfMDTmY7ywwU1bVx9L5ldELa6CrHSOm1zIyyneTjUU0nh8vZbtQDKYo8vz+eix5dzz+g4aE7iQpyQwhEhhPX1BOnoC1llCYiQwZBmJEGIMfgt8Fxg42i/TWjcBGN8j82bLgd0DbtdgbCs3Lh+6/aB9tNYBoB0ojupvIBKC1prG1m7LFvCMiLRQ/eif3+CUW19k2ZpGkyNKLFvdkQKe8Z+BATC3Ih9/INRfSHQsHlm9m4n5GZwyoySKkcGiWaWsa2zH7e2J6nETyf6uXoIhTWluhtmhjMq3zp0JwK8SuJWqJDCESGH7OnsBrFPEM0cSGEKI0VNKXQi4tdarR7rLINv0MNuH2+fQWK5VSq1SSq1qaUntM5TJqqM7gNcfsHQCY9maRn7z/Jb+nxvburnxsXWSxBiFukgCo9SkGRgVBQCsa2wb0/5723t4ZUsLHzuuArstupPFzpjpAmBFCs/CcHeEx6pWX0JyqIrCLD57ylT+/V4jH0ShxooZJIEhRArzGIkCy83AkCUkYhwum1/BZVGcLisSwinAR5RSO4AHgbOUUvcDzcayEIzvkUXbDcDAkvwVwB5je8Ug2w/aRynlAPKB/YcGorW+S2u9QGu9wOVyRee3E5ay2+ItVAFue24zPX0HLz3o7gtyWwKfdY23rW4f2el2Juabc4Z9SlEWuRmOMXcieWxNAyENH4vB++GcSXmU5jp5eUvqJDAOHVtEZp8k0hKSiC+dOYP8zDRueWYj4dWSiUUSGEKksEitCatUUC7KTsemZAaGGJ8lCypZEoV2cSJxaK1v1FpXaK2nEi7O+aLW+lPAE8BVxs2uAh43Lj8BXGl0FplGuFjn28YyE69S6kSjvsVnDtkncqzLjPtIvJGfGLfI2vHyAuvWwNgzxPr2obaLw21p9jKjLDfuHUgibDbF3PL8MXUi0VqzdHUDx08tZFpJdtRjU0pxZo2LV7a0EBhHjY5EcujYwu2NzMBIrCUkAPmZaXz1rGpe37qPFQmYhJIEhhApLJLAsEoRT7tNUSytVMU47e/sZb+xPEqkvFuBDyml6oAPGT+jtV4PPAxsAJ4Fvqy1Dhr7XEe4EOhWYBvwjLH9b0CxUmor8C2MjiYi9TS0hpMAVp6BMalg8NiG2i4OV+f2mbZ8JGJuRT4bmzrwB4JHvvEA7+5qo76lkyXzY5fMP7OmFG9PgHd3tcXsPqzk0LFFZKxqlZOAo/XpE6cwuSiLW5/ZRDCUWLl4SWAIkcI8PqMGhkWWkEC4DoYkMMR4XHf/aq67f6SlEESy0Vq/rLW+0Li8T2t9tta62vi+f8DtbtZaT9da12itnxmwfZXW+mjjuq9EZllorXu01ku01jO01gu11vXx/+2EFTS0dpGdbqcgSm0pY+H6xTVkptkP2paZZuP6xTUmRZRY2rp6afH6TU9g1JYX0BfUbNk7ukKeS1fvJjPNzvm1E2MUGZxaXYLdplKmneqhYwt3Rw95GQ4yDnmeJYp0h43vnlfDpr1eHn234cg7WIgkMIRIYS1eP7lOa734unKdUgNDCCGEZTW2dlNemGna0oKRuGReObdcOpfyATMuPn96FZfMKx9mLxFxoAOJyQmMinwA1o6ikGd3b5An32/i/LkTyXE6YhQZ5GWksWBKIS+laCFPt9efsLMvIi6YO5FjKgv41X830907ulk+ZpIEhhApzOPzW6YDSYQrV2ZgCCGEsK6G1m4qCq1b/yLiknnlvH7DWaz/yWKy0+3saUvdlpejdaADiTktVCMqCjMpzEpj3SgKeT67vgmfP8CSBbEvZn1mTSkbmzrY2556jy2315+Q9S8GUkrx/Q/PornDz92vbzc7nBGTBIYQKczj81um/kWEK9eJx+cnlGDr8YQQQqSGxrbug2Y2WF2208FHjp3E02ub8Pb0mR1OQqhr9pGZZjf9/6yUYm5Fwag6kTyyqoHJRVmcMK0ohpGFLZpltFPdkhrLSAZye3sSsgPJoU6oKuac2WXc/vK2/tp4VmdKAkMptUMptU4p9Z5SapWxrUgp9bxSqs74Xjjg9jcqpbYqpTYrpRYP2D7fOM5WpdTvjYrhGFXFHzK2v6WUmhr3X1KIBODx9Vqq/gWE+2n3BTXt3TLIEkIIYS0dPX20d/dZuoDnYC5fUEl3X3hpgTiyOreXGaU52GzmLxOqLc9nS7OXnr4jT/Hfvb+LN7bt47L5FXFZ4lRTlsvE/Axe2pRay0i01rR4/ZRabBbzWN3w4Vl09wX5/fI6s0MZETNnYCzSWh+rtV5g/HwDsFxrXQ0sN35GKXUU4ZZoc4DzgD8rpSIL9m8HriXc/qzauB7gGqBVaz0D+A3w8zj8PkIknBav33IJjMh6QrcsIxFj9KkTp/CpE6eYHYYQIgk19ncgsf4SkoGOrSxgZlkOD63abXYoCWGrBTqQRMytyCcQ0mxs6jjibR99twGl4NLj4lPrJNxOtZTXtnroDSR3O9WBYwuvP0BPXyjhl5BEzCjN4crjK/nXW7uobxldwVgzWGkJycXA343LfwcuGbD9Qa21X2u9nXBbs4VKqYlAntZ6pVEh/B+H7BM51lLgbBWPNKQQCaQ3EKK9u896CQwjHqmDIcbqomMmcdExk8wOQwiRhCIJjPIEm4GhlOKK4yfz/u42Nu098gfhVNbR00dTew8zTC7gGREp5LmucfhlJKGQZunqBk6eXhzXBNuZNS58/gCrd7bG7T7NMHBs4e4Ij1GTYQlJxNfPqSbdYeMXz242O5QjMiuBoYH/KqVWK6WuNbaVaa2bAIzvpcb2cmBgurjB2FZuXD50+0H7aK0DQDtQHIPfQ4iEta8z/OJbkmu9GhgALb7UKwglomNPWzd72rrNDmPUlq1p5JRbX2TaDU9zyq0vsmxNo9khCSEO0dDaBZBwS0gAPjqvnDS74qF3ZBbGcLZapIBnxIS8DEpynEesg/HW9v00tHazZH5lnCILO2VGCWn25G+nOnBs4faGx6iJ3oVkoNLcDL5w+nSeXb+X1Tv3H3kHE5mVwDhFa30c8GHgy0qp04e57WAzJ/Qw24fb5+ADK3WtUmqVUmpVS0tqrd0SwuPtBQ7MeLCK/gSGzMAQY/TNh97jmw+9Z3YYo7JsTSM3PraOxrZuNOEigTc+tk6SGEJYTENrNxlpNoqzrZX8H4mi7HTOPWoC/17TiD+QOC0T421rcySBYY0ZGEopaivyj9iJ5JHVu8l1Olg8Z0KcIgvLcTpYOK2Il5I8gTFwbBEZoybLEpKIz58+DVeuk5uf3kh4gYM1mZLA0FrvMb67gX8DC4FmY1kIxvfIs6ABGJhKrAD2GNsrBtl+0D5KKQeQDxyWStJa36W1XqC1XuByuaLzywmRICKVhq3WRjXH6SAjzSYJDJFSbntuM92HFGjr7gty23PWn8opRCqJdCBJ1JXJVxxfSVtXH89vaDY7FMuqc3txOmxUFlmnzsnc8nzq3F66egODXu/zB3hm3V4uPGYSmen2QW8TS2fOLGVLs4/GBJz9OBbJuIQEICvdwbc+NJN3d7Xx7Ad7zQ5nSHFPYCilspVSuZHLwLnAB8ATwFXGza4CHjcuPwFcaXQWmUa4WOfbxjITr1LqRKO+xWcO2SdyrMuAF7WV00hCmKDFSGBYbQaGUgpXrlMSGCKlDLXkJRGXwgiRzBpauxOugOdAp84oobwgU5aRDKPO7WO6Kwe7BTqQRNRW5BPSsH7P4PVLnl67h+6+IEsWVAx6faxF2qkm+zKSCLe3h4w0G7lOh9mhRN2S+RVUl+bw82c30Re0ZmFWM2ZglAGvKaXeB94GntZaPwvcCnxIKVUHfMj4Ga31euBhYAPwLPBlrXXkNNV1wF8JF/bcBjxjbP8bUKyU2gp8C6OjiRDigP4ZGBZLYEA4qdKSIL2ohYiGSQWDr6cfarsQwhwNrV0JWf8iwmZTXDa/gte2eti9v8vscCyprtlHtUUKeEbMLQ8X8hyqDsYjqxqY7spmXmVBHKM6YLorh4rCzJRpp+r2+nHlOhN2JtZwHHYbN3x4Fjv2dfGvt3aZHc6g4p7A0FrXa62PMb7maK1vNrbv01qfrbWuNr7vH7DPzVrr6VrrGq31MwO2r9JaH21c95XILAutdY/WeonWeobWeqHWuj7ev6cQVufx9pKdbjdlquGRyAwMkWquX1xDmv3ggVC63cb1i2tMikgIcahOf4DWrr6E60ByqMhZ+kdWNxzhlqmn0x+gsa3bMvUvIkrzMpiQl8G6hrbDrqtv8bFqZytLFlSa9oE63E7VxRvbPClRX8Xd4U+6+hcDnTWrlBOrivjd8jq8PX1mh3MYK7VRFULEkcfnt1z9iwhJYIjx+PxpVXz+tCqzwxiVC2onkp1uJ91uQwE2BdNc2Vwyr/yI+woh4iOyvj+Rl5BAOP5TZ5SwdNVugiFZYT1QpAPJDIt0IBlobkU+awdppbp0dQM2BZea/H6xqKaUrt4g72xPznaqA8cWLT4/pRYdQ0eDUorvnz+b/Z293LFim9nhHEYSGEKkKI/Pb8nlIwCunAxau/roDVhz7Z2wtnOOKuOco8rMDmNUnnhvD23dAe789Hy233oB31lcw+a9XtbvGb7qvBAifhK5heqhrji+kj3tPby21WN2KJZSF2mharElJAC15fnUt3QedEY8GNI89m4jZ8x0UZpn7oyAk6YXk+6wJW03koFjC3dHT1InMABqKwr4yDGT+Our22lqt1Y9LklgCJGiWrx+SnKs2QYu0kp1X6fMwhCjt63Fx7YWn9lhjFgopLljxTZmTcjlzJpwIbRPnjCFHKeDO1fICkghrKKx1ZiBkQS1aT50VBmFWWk89I4117ibpc7tJc2umGKhDiQRtUZ9iw8aDxTyfLWuhb0dPSxZUDnEXvGTle7ghGlFSVvIMzK26OkL0tETMD1hFA/XL65Ba/j1f7eYHcpBJIEhRIqy9AwMI4Ehy0jEWHz/sXV8/7F1ZocxYss3ualz+7juzOn965fzM9P4xAmTeXpdkxTaE8IiGlq7SXfYLPveORpOh52Pzqvg+Q3N7JOi2f22NvuoKsnBYbfeR6RIIc91jW392x5Z3UBBVhpnzy41KaqDLaopZVtLJ7v2Jd/7VmRsERmbupJ8BgZAZVEWnzlpCkvfbWBj0+AdcMxgvWenECLm+oIhWrv6LPviKwkMkSq01vz55a1UFGZywdyJB133uVOmYVPw11dlFoYQVtDQ2k1FQSY2C7XXHI8rjq+kL6j595pGs0OxjDq3jxkWXD4CUJSdTkVhZn8nkvauPp5f38wlx5bjdFijIPuiWeFEystbknMWBoRbqAJJv4Qk4itnzSDX6eDWZzaZHUo/SWAIkYL2d/YC1myhCpLAEKnj7e37WbOrjWtPrzrsjN+E/AwuObach1bt7n/OCiHM09DWnfAdSAaqmZDLsZUFPPTOboxGfimtuzfI7tYuZlqwgGdEbUU+64xCnk+830hvMMRl8ytMjuqAaSXZTCnO4qVNSZzA6AiPTZO5C8lABVnpfPWsalZsaeG1OmvUzJEEhhApKJIYsGoCI1KbQxIYItndsWIbxdnpLJk/+PrlL5xRRU9fiL+/sSO+gQkhDtPY2pUUBTwHuuL4SurcPtbsbjM7FNNta/GhtTULeEbMLS9g574u2rv6eGR1A7Mn5nG0sbTEKhbVlLKyfh89fcnZTtVtjE1L86w5ho6FT580hfKCTP7vPxsJWaBzkSQwhEhBHl9k/Z41i3g6HXbyM9NokXW5IoltbOrgpc0tfPaUqWSmDz79d0ZpLufMLuMfK3fQ1RuIc4TCSpataeSUW19k2g1Pc8qtL7JMpv3HVU9fEI+vl/IkKOA50EXHTCIr3c7D7+w2OxTTRVqoVpdaN4FRWxFOVix9t4G1De0ssdDsi4gza1z09IV4s36f2aHEhNvbg92mKMqy5hg6FjLS7Hz3vBo2NHWw7D3z33skgSFECvL4rL2EBMLLSGQGhhiLr55VzVfPqjY7jCO6Y8U2stPtfPrEqcPe7rozq2jt6pMPGCls2ZpGbnxsHY1t3Wigsa2bGx9bJ0mMOGqIdCAptF53ivHIcTq4YO5Ennx/D53+1E6Sbmn24rApphRnmx3KkHbu6wTgpqc2AJDusN5HuROrinE6bLy8ucXsUKIqMrZwd4S7+CVLLZyRuqh2EnPL8/nlc5tNn11jvUe9ECLmIjMwLJ3AyJEEhhibU6tLOLW6xOwwhrVrXxdPvr+HT544hfystGFvO39KEQumFPKXV7fTFwzFKUJhJbc9t5nuQwaM3X1Bbntus0kRpZ6G1nBXhWRbQgLhZSSdvUGeXttkdiimqnP7mFqSbcmkAIQTmTc9tfGgbTc/vdFyicyMNDsnTy9OunaqkbGF2+tPmfoXA9lsihvPn8We9h7ueX2HubGYeu9CCFN4vH4y0+xkOx1mhzIkV65TlpCIMVm/p531e9rNDmNYf3m1HofNxjWnThvR7b94xnQa27r5z7rU/oCRqva0dY9qu4i+RuNvnUxFPCPmTylkuiubh1al9iyvrW6fpZePJFIic9GsUnbs62K7p9PsUKImMrZo8fpTpgPJoU6eXsJZs0r580tbTS0uLgkMIVJQi89PiUXrX0TIEpLkFeu1/D99cgM/fXJDVI8ZTS1ePw+v2s2lx5VTljeyszhnzSqlujSHO1bUS7eAFDRpiLoLE/JT7yygWRpau0mzq6Q886qU4orjK1m9s5Wtbq/Z4Ziipy/Izn2dlk5gJFIi88yZ4XaqydSNJDK2cHv9KVXA81A3fHgWnb0B/vBinWkxSAJDiBTk8fktvXwEwgmMrt5gyq/JTTaylh/ufWM7vcEQ155eNeJ9bDbFtadXsbGpg1cs0sZMxM/1i2vITDu80GuGw0Z7d58JEaWehtZuJhVkYk/Sde+XHleBw6Z4KEVr7Wz3dBLSMKPMui1Uh0pkDrXdTJOLs6hyZfPyluSqg6GBfZ1+XEmYyBypmWW5XL6gkvvf3NlfkyXeJIEhRAryeHutn8Aw4pNZGMklkabAxoK3p49/rNzJh4+eQJVrdGf6Lj62nAl5Gdzx8rYYRSes6pJ55dxy6VzKCzJRQHlBJlefPIWGtm4+fteb/XWNROw0tnYlXQeSgUpynJwzu4zH3m2kN5B6tXbqjA4kMy3cQnWwRGZmmp3rF9eYFNHwFtWU8mb9vqTqoBUIhtCalF1CEvHND83EYbPxC5PGbpLAECIFeXx+XBZ/8Y3EJ3UwkksiTYGNhX+9tQtvT4AvnjF91PumO8I1M1bW7+P93W3RD05Y2iXzynn9hrPYfusFvH7DWfz4I0fz16uOp97j4/I7VqbMc8gsDa3dSVnAc6Arjq9kX2cvyzc2mx1K3G1t9mJTMK3Euh1IBktk3nLpXC6ZV252aINaVFNKbyDEym3J0041ktxL9QRGWV4Gnz9tGk+vbWLNrta4378kMIRIMYFgiP1dCTADI1dmYCSbZz/YO+R1zjQbbm9PHKOJP38gyN9e284pM4qprSgY0zE+fsJkcjMc3PmKzMIQcMZMF/ddcwItXj9L7lhJfYvP7JCSUk9fELfXn3QtVA91+kwXE/IyUrKYZ53bx9TibJyOw5dqWcmhiUyrJi8Ajp9WSFa6PanaqUY6gZWOsH5VMrv2jOnkOO1cceebMatpNhRJYAiRYvZ39aI1uHKsX8QTJIGRDHoDIX7y5Hq+eP9qKgozcR7Sos5hU/QFQnzo16+wdHXDuItUfve8Gr57nvWm1P773UbcXj/XnTFjzMfIcTr49IlTeOaDvUlV3X28lFKVSqmXlFIblVLrlVJfN7YXKaWeV0rVGd8LB+xzo1Jqq1Jqs1Jq8YDt85VS64zrfq+UUsZ2p1LqIWP7W0qpqXH/RQdx/NQiHrj2RHr6glx+50o27OkwO6Sk09QeTq4m8xISALtNsWRBBa9saUm5GT1bmr3MsHABz0TkdNg5eXoJL212J0Xx6e+eV8OiWeHipKk+AwPghQ3N+AMheoOhuNc0kwSGECnG4w23PbL6DIzCrHTsNiUJjAS3e38XS+5cyT2v7+Czp0xl+bfP5Ocfqz1oCuwvlxzDf791BtWlOXznkfe56p53+lsWjsX8KUXMn1IUvV8iCoIhzZ2v1DO3PJ9TZhSP61ifPWUaaXYbf3m1PkrRJYUA8G2t9WzgRODLSqmjgBuA5VrramC58TPGdVcCc4DzgD8rpSKnXm8HrgWqja/zjO3XAK1a6xnAb4Cfx+MXG4mjy/N5+IsnkWa3ceVdK1m9c7/ZISWVhtYugKRfQgKwZH4lIQ1LVzeYHUrc9AZC7NjXRbWF618kqkWzXDS0drMtCWaHzZ9SRGaaA7D+GDoebntuM33BgxNT8appJgkMIVJMpNhbicWzx3abojg7XRIYCez5Dc1c8PtXqW/xccenjuNHF80h3WEbdArsdFcOD3/hJH7ykTms2rGfc3+9gvtW7iAUGv1Zm9U791vuA9xz68MzJq47czrGCf0xc+U6uWx+BUtXNyT9spuR0lo3aa3fNS57gY1AOXAx8HfjZn8HLjEuXww8qLX2a623A1uBhUqpiUCe1nqlDp8y/Mch+0SOtRQ4W433nxlF0105PPLFkyjKTudTf32bV+uSZ9q2mZataeSr/1oDwNceXJP0HZMmF2dxyoxiHl61e0yvv4lox75OgiFNdal1O5AkqjNrwjMWkmEZyeqd+1m/p53CrDTSHfIR2syaZvLXFyLF9CcwEiB77Mp1ShHPBNQXDHHz0xv4/D9WMbk4i6e/ehrnHT3xiPvZbIqrTp7Kc984neOmFPLDx9dz5V1vjnpd/y+e3cwvnrVOVxOtNbe/vI1pJdksnjMhKsf8/GlV9AVD/P2NHVE5XjIxlnbMA94CyrTWTRBOcgClxs3KgYEL/RuMbeXG5UO3H7SP1joAtAPjm04TZRWFWTz8xZOYUpzFNfeuGrbujDiySNvnNqNVbXOHPyXaPl++oJKG1m5W1idP8cXh1DWH32NkCUn0lRdkMrMsh5c2u80OZdx+8exm3tmxn9IUbqE6kJltfSWBIUSKOZDAsHYNDDASGDIDI6E0tnVz+Z0r+cur2/nMSVN49LqTmVw8usJ3lUVZ/ONzC7ntslo27e3gw797lTtWbCMQTMzWfq9v3ce6xna+cHoVdlt0TthPK8nmw0dP4L6VO/H5k6dF3XgppXKAR4FvaK2HKwYx2D9CD7N9uH0OjeFapdQqpdSqlpb4n3Uszc3goWtPYk55Hl/65+qUWgoQbana9nnxnAnkZ6bx4DupUcyzzu1FqfAsJhF9i2pKeXv7/qR4r+oNhijNs/4JwHgws62vJDCESDEtXj9Oh40cp8PsUI7IlSMJjETy4qbwkpG6Zh9//MQ8fnrx0WOu6K6UYsmCSl741hmcWePi1mc28dE/v8HGpsQrUHj7iq2U5jr56HHRrRb/hdOn09ET4IG3dkX1uIlKKZVGOHnxT631Y8bmZmNZCMb3yGnABqBywO4VwB5je8Ug2w/aRynlAPKBw9Yqaa3v0lov0FovcLlc0fjVRi0/K437rzmBk6YX851H3ufe17ebEkeiS9W2zxlpdj46r5znPthLa2ev2eHEXJ3bx+SiLDLTrd2BJFGdUeOiL6h5Y6vH7FDGrS+g+4vMJ5SmJjjjDNgbvVl5kba+tbYuHvrXDcy1d8etra8kMIRIMR5fuIWqhZZuD8mV68Tj8yfsOtxlaxo55dYX495eKt76giFueWYjn7t3FZPyM3nyq6dyYe2kqBy7NC+DOz41nz994jia2ru56A+v8ev/bsYfCB55Zwt4f3cbr2/dx/87bVrU2/MdU1nASVXF/O217f296VOVUYvib8BGrfWvB1z1BHCVcfkq4PEB2680OotMI1ys821jmYlXKXWicczPHLJP5FiXAS9qC5fWz3Y6+NtVx3PuUWX8+MkN/GF5XVJ0AoinoWpFxWOKtNkuX1BJbzDEsveS831roK3NPqpl+UjMLJhSRI7TwUtJUAejLxhKzCUkN90Er70W/h5Fl8wr54m2lzihcQNPtr0Ut7a+1j8FK4SIKo/PnzDZY1euk0BI09bdR1G29Ze8DBRZOx2ZfhxpLwVYum/7aDW1d/PVf61h1c5WPnHCZP73wqPISIvuB3WlFBfUTuTk6cX89KkN/P7FrTy7fi8//1gt8yYXHvkAJrpjxTZyMxx8fOHkmBz/C2dUcfU97/D4e40sWVB55B2S1ynAp4F1Sqn3jG3fB24FHlZKXQPsApYAaK3XK6UeBjYQ7mDyZa11JCt2HXAvkAk8Y3xBOEFyn1JqK+GZF1fG+Hcat4w0O3/+5HF899G1/Or5LXT09PH982cnRALbbFuavXT29KE4eJ1QvKZIm+2oSXnMLc/noXd2c/XJU5P2MdMXDFHv8fW3xxTRl+6wceqMEl422qkm6mMpENJoErCFalMT3HMPhEJwxx2wZg2kG2Pqyy+HL30Jurrg/PMP3/fqq8NfHg9cdtnh11955YFj33MP/PCHMCE6tb6GIzMwhEgxLV5/QhTwBPoTLYm4jCQV1k6/vNnNBb9/jY1NHfzuymP5v4/OjXryYqDC7HR+c8Wx3HP18Xh7Anzs9jf42VMb6O49+O/8vxcdxf9edFTM4hip+hYfz67fy2dOmkJuRlpM7uOMmS5mT8zjrlfqE3amUjRorV/TWiutda3W+ljj6z9a631a67O11tXG9/0D9rlZaz1da12jtX5mwPZVWuujjeu+EpllobXu0Vov0VrP0Fov1FonRB9bh93GLy87hqtPnspfXt3ODY+uI5jCj5WR2OHp5JN/fYucjDS+f/7sg9o+x2uKtBVccXwlm/Z6WdfYbnYoMbNzXxd9QS0zMGLszBoXTe09bGlO3Haq15wyDSDxamDcdFM4wQCgNezcGb1jP/bYgWMHg1Gf4TEUmYEhRIrx+HqZN7nA7DBGxJVzIIFRMyGx2psl89rpQDDEb17Ywp9e2sasCbn86ZPHxbX42aJZpfz3m6dz6zOb+Otr23l+YzO3XlrLSdPDDSHmTMqPWyzDueuVetLtNq4+eVrM7kMpxRfPqOLrD77Hi5vcnHNUWczuSyQum03xo4uOIi/Dwe9f3IrPH+A3VxwrrQAH0djWzSf/+haBYIiHv3AS1WW5fP70KrPDMsVHjp3Ez57ewIPv7Ka2osDscGJiq9sLQHWZJDBiKdJO9aXN7piN55ataeS25zazp62bSQWZXL+4JqrJxtzM8MfmhFpCEpl90WvUstEaWlvhwQcPnimRlQUvvzz0cUpKDr++qQmqqg4cu7c3brMw5J1LiBQSDGn2dybgDAxfj8mRjM47O/ZjG2KKZLbTjrsjsX6fgZo7evjkX9/iTy9t48rjK1n25VNMqdyem5HGzR+dywOfPxGAj//lTW58bB0PvL2T+Tc9z1ST647sbe/h0XcbuHxBZcyXbF0wdyLlBZnc+cq2mN6PSGxKKb51bg3/c/5snl7XxOf/seqw2Uupzt3Rwyf/8iYdPX3cd80JVJclVuI82vIy0jj/6Ik8+d6epH2sRFqoSgeS2JqQn8HsiXm8tCk27VQjy3Yb27rRHFi2G80xwGt14SKkCbWEZODsi4hozZSI5bGPQBIYQqSQ1q5eQprES2AkyBKSQDDEb1/YwhV3rqQgy4HzkLObdqXw+YOc+ouX+OGyD2ho7TIp0rF5ta6F83/3Kmsb2vnNFcdw68dqY7pkZCROml7Ms18/nc+fNo0H3t7FjY99wD6jan4sBjAjdffr2wlpuDYOZ24ddhufP20a7+xoZfXOw5piCHGQz59exa2XzuWVuhY+c/dbdPT0mR2SJbR29vKpv72F2+vn3s8ez9Hl1pjJZbYrjq/E6w/wn3VNZocSE3VuH+UFmWQnQGe2RLeoxsXqna1Rf83xB4Lc8szGQZft3vLMRtwdPfj8gXEts1y2ppG/vhpeNfjxv7yZOEXZV648MEMiorcX3njD2sc+Anm2CpFCPL5wIiBREhg5TgcZabaESGA0tnXzjQfX8M6OVi6dV85PLzmaFzY0Hzadcd7kAu5YsY0H39nFA2/v4qPzyrnuzOlUWfjsTzCk+d0LW/jDS1upLs3hoU8ex4xS65yZzEy38z8XHMWyNXto8R38WInUHYnnmvX2rj7++eZOLqydSGVRVlzu8/LjK/nd8jpuf7mev15VFJf7FInryoWTyclw8I0H3+Pjd73JPz63kOIEeV+IhY6ePj5z99vs2NfFvVcfz/wp8hyKWDitiGkl2Tz0zm4+Nr/iyDtESayXA0TUuX2yfCRO7DZFIKSp/fF/KT/C/1RrTUdPgBZvD26vnxbjy93/vaf/57auoRMizR1+Fv7f8v6fM9JsZKc7yEy3k53uIMtpJyvdTla6o/97drqxzRnetrGpg0dXNxA08h9N7T2JU5R9zZrEPPYRSAJDiBTi8YYzpSU5idHRQymFK9dp+QTGf9Y1ccOjawlp+O0Vx/a/oV0yr3zQN7dbLq3lq2dVc9cr9Tzw9i4efbeB8+dO5MuLZjB7Yl68wx/UwMFjmsNGbyDEZfMr+OnFc8hKt+Zbh8c3+OMk3nVH7ntzB529Qb54xvS43WdWuoPPnDSV3y2vY6vba6kEk7CmC2snkZ3u4Iv3r+byO1fy6ZOm8JdXtsf8A6PVdPUG+Nw977Bpbwd3fno+J88oMTskS1FKsWRBBb94djP1Lb64JNvj1cUrGNJsa/Fx6oziqB1TDG7Zmkb+8uqBuseNbd18d+laVm7zUF6YdVhSosXrxz9Ie/B0h43SXCeuXCfTSrJZOK2I0twM7n5tO23dhycyCrPS+Pa5NXT1BujqDRpfAbr8QToHbNvn66K7L0inP0h3b4DOIyyZMuPkiDjAmqNQIURMRGpJDNXb3opcOc7DzqpbRVdvgJ8+GS5wdkxlAb+/8limFGePaN9JBZn8+CNz+PKiGfztte3ct3IHT61t4pzZZXzlrBkcW1kQ2+CHcejgsTcQIs2uOHVGiWWTFxD+mzYOkqzIz4pNB5DBdPcGuef1HSyqccU9GXXVyVO585Vt3LmintuWHBPX+xaJadGsUv7xuYV85m9v8ZMnNvS3C03Wts+H6ukLcu0/VvPurlb++InjOGuWFMEdzGXHVfCr/27h4VUN3PDhWTG/v+G6eEXz8bh7fxe9gVDK1zqJh9ue20xP38EJid5giIdWNQBQkJXWn5g4fmoRrlxn/88HLmeQl+EYtA3r5KKsg8YtEG55/KOL5ozpMRMKaXoC4eTG8T97gcEWnyRDUfZEZd2RqBAi6g7MwEigBEauk+2eTrPDOMz6Pe187YE11Hs6+dKZ0/nmh2aSZh99WSFXrpMbPjyLL55Rxb1v7OCe13dwyZ9e57TqEr6yaAYnVMXnzFBXb4B1De2s2d3Gb1/YcthAoy+oLX+24frFNYcNYGwK2rr6uPGxdfzooqNiXrPjkdW72dfZy3Vnzojp/QymKDudKxZU8q+3d/Htc2uYkJ9AldKFaU6oKiYvK/2wmW7JfoaxLxjiK/96l9e2evjVkmM4f+5Es0OyrNK8DBbVlLJ0dQPfPnds73WjMdQHw8a2bprau5mYnxmV+9nSbHQgkRaqMTfU/1QBm352Hk7H+N6bI69T0Vp2ZLMpY1mJY8iTI5MKovM4FKMnCQwhUojH5yfdYSMvI3Ge+q5cJ29vt05hQq01d7++g58/s4mCrDT+ec0JUZlyXJCVzjfOmcn/O62Kf765k7+8Ws8Vd73J8VML+fKiGZwx0zXoWYexCIU09Z5O1uxq5b3dbazZ1cbmZi/BIxS4svrZhshA5f/+sxG31095QSbf/lA1dS2d3P7yNj5obOfPnzwuZnUpAsEQd71Sz3GTCzh+amFM7uNI/t9pVdz/1i7ufn073z9/tikxiMTjGWKZntWf82MVDGm++dB7vLDRzU2XHB3X2g6J6orjK3lhYzMvbXJz7pzYtEhs8fr5xbObBj3bHXHSLS8yZ1Ie58wu45zZZRxdnjfm98Y6d7gDyQxJYMTccEmA8SYvIoZatjteg50cyUyzc/3imqjflxiZxPkUI4QYtxafH1eOM2ofhOPBlZNBa1cfvYEQ6Q5zGyd5fH6uf+R9Xtrcwjmzy/jFZbUUZUe3nkiO08EXzpjOVSdP5aF3dnPHim1cfc87zC3P58uLZnDuUWXYbKP7/7V29vJeQzhRsWZXK+/vbqOjJwBArtPBMZUFXHfGdOZNLuDYygI+8sfXE/Zsw1ADmHmVBXz74fe56I+v8dsrju3vSR9NT69roqG1mx9dNMe051hlURYXzJ3Iv97axZcXzSA/M37LZ0TiGurDxcQknMUTCmm+9+hanlrbxPfPn8WnT5xidkgJYVGNi9JcJw+v2h31BEZfMMQ/Vu7kt89vobsvyKIaFyvr9x00EzAzzcY3zqlGo3hhQzN/eLGO3y2voyzPydmzyzhndiknTy8Z1Sy7rW4fE/MzyM2Q18lYS+QkQLRnd4jxkwSGECnE4+tNmAKeEZFWqvs6/VGbNjoWr2xp4VsPv09HTx83XTyHT504JaYfUjPS7Fx18lQ+vnAy/17TwJ9f3sYX71/NzLIcvrxoBsFgiF89X3fYm2lfMMSmJi9rdreyZlcb7+1u61+CY1MwsyyXC2onMa+ygHmTC5juyjksIZLIAw2AFzY0A3DOUQfWs587ZwJPfjWXL96/ms/e+w5fO6uar51djX2UyaChaK25/eVtVJfmcPas6CdHRuMLZ1TxxPt7+OdbO/mSCUtZROIZ7DkP4HTYcHf0UJqXHIkMrTU/eXI9S1c38PWzq7n29PgV2k10DruNj82v4M4V22ju6KEsSo+JN7Z6+PGT69nS7OO06hJ+dNEcZpTmDNuF5ItnTGefz89Lm1tYvrGZx9c08q+3dpGZZufU6hI+NLuMRbNK+8cPQ6lze2X2RZwkehLgknnl5BitdgeOLYQ5lNZj74mbTBYsWKBXrVoVtePFq/2TEKNx/u9eZWJ+Bn+7+nizQxmxm57awN9e244CU55LvYEQv/zvZu56pZ6ZZTn8/uPzmDUh/p1CAsEQT69r4k8vbWVLsw8FB02zddgUlYWZ7Gnv6a/c7cp1Mq+ygGMnFzCvspDaivwR97pP5NewK+5cCcBDXzjpsOu6e4P8z7J1PPZuI6fPdPHbK46Nyiyalza5+ey97/CrJcdYYjr6p//2FhubvLz2vUUxr/sBoJRarbVeEPM7SjDRHlvE0qHP+bNnl/LIqgZyMxzc/qnjEr61qNaanz+7mTtWbOPzp03j++fPTqjZiFaw3dPJol++zPWLa/jyovElRxvburn56Q38Z91eKgoz+eGFR3HuUWVj+p/4A0HerN/PCxuaWb6xmT3tPSgFx1YW9C81mVmW03/sZWsa+cVzm9jT1kO2087Nl8xNmPc3YZ7hxhYiNoYaW0gCwxDNQcahFfwhfPbylkvlBTKRPxQlg4U3v8CimlJ+flmt2aGMyLI1jXzv0bUHtdKK53Npu6eTrz2whnWN7XzqxMn84ILYF4E8klBIs+DmF9jf2XvYdel2G585aUo4YTG5kEn5GSk5QD/SIENrzQNv7+bHT6zHlevkz588jmPG2fXl8jtW0tDaxYrvLhpfgbumJrjySnjoIZgw9mnab2z18Im/vsUtl87l4wsnR/34h5IExuASKYExmM17vVx73yr2tHXzvxceFfOZZ7H0xxfr+OV/t/DJEybzs0uOTtjfw2xX3LmSvR09vPydM8f0N+zpC/KXV+r508tb0Rq+dOYMvnBGVdTeW7XWbGjqYPlGNy9sbGZtQzsAFYWZnDO7jMw0O/e8sf2Q5SkyRhdHJgmM+BtqbGHugvIkNVz7p1QWSew0tnWjOdCmbdmaRrNDSwmhkGZfZy8luYmzhOS25zYf1gc8Hs8lrTWPrNrNBb9/ld2tXdz56fn87JK5picvIFwZu3WQ5AWE1xH/4MKjuLB2EuUFmTJAH4JSik+cMJml14UHIUvuWMn9b+5krAn9VTv28/aO/Xz+9KrxV+e/6SZ47bXw93E4aXoxtRX53PVK/cHFWaN0fJEaaibk8sRXTuW0ahc/fHw91y9dS88h45tE8LfXtvPL/27h0nnl3HSxJC/G44rjK9m5r4s360dXXFtrzfMbmjn3N6/wq+e3sKimlOXfPoOvn1Md1fdWpRRzJuXztbOreeIrp/LW98/mlkvnUlOWywNv7+L2FdsO67IlY3QhEovUwIiBoap272nrJhTSoy7AlyyGSuz84rlNkvWOg7buPmokrdsAABjhSURBVIIhnVAtVIdrpXbLfzZSXZZLTVkuM0pzyEyPzgCoo6eP//n3Bzz5/h5OrCriN1cca2rtjcFIS6/oqK0o4Kmvnso3HnqPHyz7gHd3tnLzR+eO+rF0x4ptFGalccXxleMLqKkJ7rkHQiG44w5YswbSjYTj5ZfDl74EXV1w/vmH73v11eEvjwcuuwwF3NPZS12zl/aHcin6ztfh9NPh7rvDx7/nHvjhD6M6C0Mkp/zMNP76mQX8bnm4aOLmvV5u/9RxVBTGpptPtD3w9i5uemoD582ZwC8uq03ZMVi0fPjoifzoifU8vGo3J00fWZvv+hYfP3lyAyu2tDCjNId//r8TOCUK3btGoiwvg48vnMzHF06muzfI7P99dtDbJWvHHSGSkSQwYmCoDxcaWPh/y1lU4+KsWaWcWl2SMpWPff7AoH8TgD1tPZzz6xVMKcpiSnE2U0uymFyUxdTibMoLM2PebzxVeHzhNnmJlMAY6rnksCnueX0HvcHwWRSlYHJRFtWludRMyGFmWS4zy3KpcmUP257r0CVNSxZUsHR1A03tPVy/uIYvnjE9akUeoynRi2xaSWF2OvdcfTx/eHErv12+hQ1NHdz+qflMK8ke0f6b93p5YaObb54zk6z0cb6l3nRTOLkAoDXs3AnV1WM+XFF2Os40O41t3RRqjbrppvBxAYLB8P396U/ji1mkBJtN8c0PzWRueT7ffOg9PvLH1/nDx+fF7UPoWD3+XiPf//c6zqxx8fuPz8Mh44lxy0y3c/Gxk3hkVQM//sicYTsd+fwB/vBiHXe/tp0Mh50fXDCbq06eatq4LjPdTrmcABAi4UkNDEOsa2BkpNn42PxyOrqDrNjspqMnQJpdccK0YhbNKuXsWaVMHeGAOZHsaevm3jd28MBbu/D6A4PeJsfp4JQZxezc18XOfV0H/d3sNkV5QSZTisMJjSnFRpKjOIvKoqyDph1KfY3hvb7Vwyf/+hYPfP7EEZ81Mdtw9WQurJ3Izv1dbNnrZUuzjy3NXrY0e9nu6SRgTJm32xRTi7OYWZbbP1tjZlkOU0uyeXpt06BV94uy0/jrVcdz3OTCuP6uoyWP96FFzqSNdkC6YksLX39wDcGg5peXH8PiEbQK/NZD7/Hs+r28/r2zKBxPMdCmJqiqgp6eA9syM6G+flyzJO5/cyc/WPYBSy+eyoKzFkT9+BFSA2NwiV4DYzD1LT6+cN9qtrX4+N55s7j29CpLLsl4bv1evvTPdzl+aiH3fnahJZYAJot1De1c9MfXuOniOXz6pKmHXa+15vH39vB//9mI2+vnsvkVfO+8WUfsChIPUqdOjNVYxxZi7IYaW8gMjBg4UqugvmCI1TtbeWmTm+Wb3Nz01AZuemoDVSXZnDWrlLNml3L81KKEnnnwQWM7f3m1nqfXNqGBDx89geqyHO54uf6wN42fXXJ0/99Ga02L18+OfV3s3NfJzn1d7NjXya79XTz+XiMdPQcnQSbmZzC5KAsFrNrZ2v/BNVJfA5A3JENkBoYrgWpgHOm5NN2Vw3RXDh+ee2Cf3kCI7Z5ONjd7qWv2snmvl017vTy7fm//yec0u0Jr+h8vAzkddssnLyD8t5HH9uDGOrg4Y6aLp756Kl/657t84b7VfOGMKq4/t2bIs7YNrV08/v4erjpp6viSF3Dw7IuIKMySuGx+Bb99YQvt//O/MTm+SD1VrhyWffkUrl/6Prc8s4m1je384mO1I+5wFA8rtrTw1X+tobYin79edbwkL6Ls6PI8jpqYx0Ordh+WwFi/p50fP7Ged3a0UluRzx2fnm+p99REb+cpzCOJC+uQGRgGM8+S7NrXxYubmlm+yc1b9fvpDYbIdTo4fWZ4qcmZNS6KB0z7t+qZ11BI8+ImN395tZ63tu8nx+ngiuMrufrkqVQWhdfKjjf2tq7ew5IbO/d1sWZXK4N8FiUr3c4PLzyKueX5zCzLJd2RuEmh8frrq/X87OmNvP+/55KflRpLlwbq6Quy1R2ZqeHjjhXbBr2dArbfekF8gxNR9eT7ewC46JhJY9rfHwjy0yc38M+3dnHCtCL+8Il5lOZmHHa7Hz+xnvvf3Mkr3100/oHNvHnw3nuHbz/22HAtjHH400tbOfPKxcxx18fk+CAzMIaSjDMwIrTW3PlKPb94dhPVpbnc8emRL72Kpbfq93HVPW9TVZLDA58/MSXf7+LhWw+/x2PvNva3OP/youlsaOrgX2/toiArne8uruHyBZVSc0QkjfGOLcToSRvVI7DKIKPTH+C1rR5e2uTmxU1u3F5/fy/rs2pKUTb404tb6bZQ+6fu3iCPvtvA3a9tp97TyaT8DD57yjSuWFhJXpxqfEy74WmO9EhOt9uYNTGXo8vzqS3P5+gUS2rc+swm7n5tO5t/dp4lp/vG2ym3vjjoOtjygkxev+EsEyIS0RKtVmePrm7gf5atIy8jjT998jiOn1rUf93+zl5OvnU5F9ZO4pdLjhnX/cRae1cfJ9+6nHPnTOA3Vxwbk/uQBMbgrDK2iKXX6jx89YF3CYQ0v73iWM6eXRb3GAaeHAFw5Tp55uunHXTyR0TPsjWN3PDY2sO6eQBcffJUvnnOTEkciaQjbVTjT5aQJIhsp4PFcyaweM4EQqEDvaxf3NTMr57fMug+kfZP8U5gtHj93LdyB/e9uZPWrj7mlufzuyuP5fy5E+O+/GWoYo/lBRn88/+dyLrGdj5obGddYztPvr+Hf721CziQ1Jhbns9cI6lRMyF30PitOvNlpDw+P8U56ZK8MEghTHEkH5tfwVGT8rju/tVcedeb3PjhWRRnp/PL/27pf72pLjX/jPOR5Gel8fGFk7nnjR18+9yZCdM9QiSGU6tLeOIrp/LF+1dzzd9X8Y1zqvnaWdVxO/M+WE2Dju4+Xq3zJNR7dCK57bnNgyYvSnOd/Pgjc0yISAiRSiSBYWE2m+Jo40P118+pxu3tYeHNywe9bWNbNz96/APmTMrnqEl5VJflDNt9YTy2NHv526vb+fd7jfQFQ5w9q4zPnzaNhdOKTPtwPPSH0VlMLclmakl2/5SvUEiza39Xf1JjbUM7T7y/h39GkhoOG7MnhGdqzC3PZ25FPpuaOvjBsvX9x0+0GhvL1jTy5Pt78AdCnHLriwmXfIkFWQcrRmL2xDye+OqpfOfh9/nZ0xuxKQ5arvbbF7ZSlpdp+cfN506dxt9e287i375Clz8oj3cRVZVFWTx63cl8/9/r+O0LdaxraOfXVxw7bIeK8fIHgmxq8vKjJ9YfVoy5JxAy5cROqhiq5WiL1x/nSIQQqUgSGAmkNDdjyPZP6XYbS1c38PeVO4FwkcIZpbnMmRQutDRnUh5HTcobc9tWrTWvb93HX16tZ8WWFjLSbFy+oILPnTKNKlfOuH6vaBjNh1GbTQ2b1FjX2M66Q5Iag+nuC/KL5zZZfoAUOTvlD4TPliRa8iWWpBCmGIm8jDTu/PR8jvnJfw8rJGzWDLjRenv7fmxK0elPzCSssL6MNDu/WnIMx1YW8NMnN3DJn17nzk/PZ2ZZ7riP3RsIsXmv13iPbmNdYzub93rpCw69eHSoD9li/Iaa9SpFDoUQ8SAJjAQz1EyDWy6dy0eOmcTO/V2s39PO+j0dbNjTwcubW1i6uqH/tpOLspgz6UBCY86kfEpznf0zJw5dJvHNc6pBKf76aj2b9nopyXHy7Q/N5JMnTqFovFX3o2w8H0aHS2qsbWznaw8MXuRuT1sPH/r1CqaWZFNl7D+1OJsqV/ZBf9d4C4Y0+3x+9nb08NOnNhx2dipRPnQJYRVKKbw9g7eCToQPSrc9t5ngITWv5HVARJtSis+cNJXZE/P40j/f5ZI/vc5tlx3DBbUTR3yMvmCILc1e1jW0s9aYKbmpyUtvMJyEz89Mo7Yin/93WhW15fn8+Mn1NHccfuZfPkzHjizBFEKYSRIYCeZIMw2mlWQzrSSbC2sPVMh1d/Swvimc0Niwp4P1e9p55oO9/deX5KQze2Ie6XYbr9S19J/RaGzr5jtL1wJQU5bLLy6r5eJjJ8VsaYrVDExq/PyZTYOebchxOphWks12TycrtrTQGziwJjQr3c6U4khiI4tpJTlMK8lianE2RdkH16IYTX2Nrt4Ae9t72NvRQ3NHD3vb/cb3A9vcXj/BwdqyDJAIH7qEGIvbPzU/JsdN5LOOQz3f5XVAxMLxU4v6WxJ/+V/v8ui7Ljbt9dLU1nPQe1wgGKLO7TOSFW2sa+xgY1NH/3tpboaDueX5fPbUqdSWFzC3PJ/KosyD3j/9gZB8mI4zWYIpUlGsxhZi9KQLiSEVKoUP5O3pY9NeL+sbjdkaTR2s39Mx6G2Ls9NZ9YNzUrr442BFwg7t/hIMafa0dbNjXyc7PJ3Ue8Lft3s62d3afVBCIS8jnPiYWpKNvy/I8k3ug6bCptsVHzlmEmX5Gf0JiuaOcIJisLPAOU4HZXlOJuRnUJaXwYS8jP7LP/j3B7T4Dj87Jd02hBidkbwOWFWsu+5IF5LBpdrY4lC9gRCfvectXt+2/6DtdpuioiCDvR3+/uWNuU4Hc8rzqK0o6C+sPaU4a0Rjj0Qvsi2EEOJw0oVEHCQ3I43jpxYd1BZwqFak+zt7Uzp5ASM722C3KSqLsqgsyuK0atdB+/cFQzS0drPd42O7p4vtHh87PF2s2tE66IeK3qBm6buN2G0KV46TsvwMqlzZnDy9mLJ8I0GRl0GZkaTIcQ79VO7uDcrZKZFSHlm1G4AlCyqjetxEPusoU76FGdIdNnbsO/w9LhjSNLX7+cxJU5hbEU5WTC3OHnPnEqlnJISItViNLcToSQJD9Evk6dHxMJ4BUprd1r+851BDJY4UsOVnH8Y+zlZ0ifyhS4ixiNT9icUgI1E/KMnrgDDLUMuU+oIhfnDhUXGORgghxiaWYwsxOpLAEP3kDJ05hkscjTd5EZGoH7qEENEjrwPCDHJyRAghRDTZzA4glpRS5ymlNiultiqlbjA7Hqu7ZF45t1w6l/KCTBThtdGJsLY70V2/uIbMtIMLo0riSAghrEfGFaMn73FCCCGiKWlnYCil7MCfgA8BDcA7SqkntNYbzI3M2uQMXfzJ1G4hhLA+GVeMjbzHCSGEiKakTWAAC4GtWut6AKXUg8DFgAw0hOVI4kgIISxPxhVjJO9xQgghoiWZExjlwO4BPzcAJ5gUixBCiDi597MLzQ5BJKcRjSuUUtcC1wJMnjw5PpEJIYSIKRlbWEcy18AYrPrhQc0elFLXKqVWKaVWtbS0xCksIYQQsZSZbicz3X7kGwoxOkccVwBore/SWi/QWi9wuVyD7CKEECLRyNjCOpI5gdEADOxzUwHsGXgDGWQIIUTyuW/lDu5bucPsMETyOeK4QgghRHKSsYV1JHMC4x2gWik1TSmVDlwJPGFyTEIIIWLsqbVNPLW2yewwRPKRcYUQQqQoGVtYR9LWwNBaB5RSXwGeA+zA3Vrr9SaHJYQQQogEJOMKIYQQwnxJm8AA0Fr/B/iP2XEIIYQQIvHJuEIIIYQwVzIvIRFCCCGEEEIIIUSSkASGEEIIIYQQQgghLE9pfVgHsJSklGoBdsbg0CWAJwbHjbVEjRskdrNI7OaQ2M0hsR9sitZa2nkdIkZjC3nsmUNiN4fEbg6J3RyJGnus4h50bCEJjBhTSq3SWi8wO47RStS4QWI3i8RuDondHBK7MEsi//8kdnNI7OaQ2M0hscdfvOOWJSRCCCGEEEIIIYSwPElgCCGEEEIIIYQQwvIkgRF7d5kdwBglatwgsZtFYjeHxG4OiV2YJZH/fxK7OSR2c0js5pDY4y+ucUsNDCGEEEIIIYQQQliezMAQQgghhBBCCCGE5UkCYxyUUncrpdxKqQ8GbLtNKbVJKbVWKfVvpVTBgOtuVEptVUptVkotNiXoA7GMOHal1IeUUquVUuuM72eZFjij/7sb109WSvmUUt+Je8AHxzHax0ytUmqlUmq98ffPMCVwRv2YSVNK/d2IeaNS6kaz4jbiGSz2m4y431NK/VcpNWnAdVZ/rg4ae4I8V4f8uxvXW/m5OtxjxhLP1VE+Xiz1PBVhMrYwh4wtrB231V6vZFxhDhlXmMNyYwuttXyN8Qs4HTgO+GDAtnMBh3H558DPjctHAe8DTmAasA2wJ0js84BJxuWjgcZE+bsPuP5R4BHgO4kSO+AA1gLHGD8XJ9Bj5hPAg8blLGAHMNVisecNuPw14A7jciI8V4eKPRGeq4PGPmCblZ+rQ/3dLfNcHWXclnqeytew/0MZW1go9gHXW/n1yvJji1HGbanXq1G+1ibC81TGFRaK3UrP0zHEHvPnqszAGAet9SvA/kO2/VdrHTB+fBOoMC5fTPif6ddabwe2AgvjFuwhRhO71nqN1nqPsX09kKGUcsYt2EOM8u+OUuoSoJ5w7KYaZeznAmu11u8bt9untQ7GLdhDjDJ2DWQrpRxAJtALdMQr1kMNEfvAeLIJxwyJ8VwdNPYEea4O9XdPhOfqULFb5rk6yrgt9TwVYTK2MIeMLeJPxhXmkHGFORJ1XGHcv6XGFpLAiK3PAc8Yl8uB3QOuazC2WdXA2Af6GLBGa+2Pczyj0R+7Uiob+B7wE1MjGrmBf/eZgFZKPaeUelcp9V0T4xqJgbEvBTqBJmAX8Eut9f6hdjSLUupmpdRu4JPA/xqbE+K5OkTsA1n2uTpY7InyXB3i72755+oQcSfE81QcRsYW5pCxRfzJuCKOZFxhjkQdV4B5YwtJYMSIUup/gADwz8imQW5myRYwg8Qe2T6H8HS+L5gR10gMEvtPgN9orX3mRTUyg8TuAE4l/KJwKvBRpdTZJoU3rEFiXwgEgUmEp0t+WylVZVJ4Q9Ja/4/WupJw3F8xNifEc3WI2AHrP1eHiD0hnqtDxG755+oQcSfE81QcIGMLc8jYIv5kXBF/Mq4wR6KOK8C8sYUkMGJAKXUVcCHwSa115AWqAagccLMKYM+h+5ptiNhRSlUA/wY+o7XeZlZ8wxki9hOAXyildgDfAL6vlPrK4EcwzzCPmRVaa4/Wugv4D+H1Z5YyROyfAJ7VWvdprd3A68ACs2IcgX8RPrMACfJcHWBg7AnxXB1gYOwJ8Vwd4NDHjOWfq4aBcSfa8zSlydjCHDK2iD8ZV5hOxhXmSNRxBcR5bCEJjChTSp1HeLrSR4wHXMQTwJVKKadSahpQDbxtRoxDGSp2Fa4A/TRwo9b6dZPCG9ZQsWutT9NaT9VaTwV+C/yf1vqP5kQ5uGEeM88BtUqpLGMd2RnABjNiHMowse8CzlJh2cCJwCYzYhyKUqp6wI8f4UB8ifBcHTT2BHmuDhp7gjxXh3rMWPq5Okzcln+eijAZW5hDxhbxJ+MKc8i4whyJOq4Ak8cW2sRqrIn+BTxAeH1PH+FM2TWEC/PsBt4zvu4YcPv/IVx5eDPw4USJHfgB4bVM7w34Kk2E2A/Z78eYX4F4tI+ZTxEuPPQB8ItEiR3IIVzxeT3hF9zrLRj7o8bfdS3wJFA+4PZWf64OGnuCPFeH/LsP2M+qz9XhHjOWeK6O8vFiqeepfA37P5SxhYViP2Q/q75eWX5sMcrHi6Ver8bwHmH156mMKywWu1Wep2N4zMT8uaqMOxJCCCGEEEIIIYSwLFlCIoQQQgghhBBCCMuTBIYQQgghhBBCCCEsTxIYQgghhBBCCCGEsDxJYAghhBBCCCGEEMLyJIEhhBBCCCGEEEIIy5MEhhAi4SmlXlZKLTA7DiGEEEIkBxlbCGFNksAQQgghhBBCCCGE5UkCQwgRd0qp7yqlvmZc/o1S6kXj8tlKqfuVUucqpVYqpd5VSj2ilMoxrp+vlFqhlFqtlHpOKTXxkOPalFJ/V0r9LP6/lRBCCCHMImMLIVKDJDCEEGZ4BTjNuLwAyFFKpQGnAuuAHwDnaK2PA1YB3zKu/wNwmdZ6PnA3cPOAYzqAfwJbtNY/iM+vIYQQQgiLkLGFECnAYXYAQoiUtBqYr5TKBfzAu4QHG6cBTwBHAa8rpQDSgZVADXA08Lyx3Q40DTjmncDDWuuBAw8hhBBCpAYZWwiRAiSBIYSIO611n1JqB/BZ4A1gLbAImA5sB57XWn984D5KqbnAeq31SUMc9g1gkVLqV1rrnpgFL4QQQgjLkbGFEKlBlpAIIczyCvAd4/urwBeB94A3gVOUUjMAlFJZSqmZwGbApZQ6ydieppSaM+B4fwP+AzyilJLkrBBCCJF6ZGwhRJKTBIYQwiyvAhOBlVrrZqAHeFVr3QJcDTyglFpLeNAxS2vdC1wG/Fwp9T7hAcnJAw+otf414Smj9yml5PVNCCGESC0ythAiySmttdkxCCGEEEIIIYQQQgxLsohCCCGEEEIIIYSwPElgCCGEEEIIIYQQwvIkgSGEEEIIIYQQQgjLkwSGEEIIIYQQQgghLE8SGEIIIYQQQgghhLA8SWAIIYQQQgghhBDC8iSBIYQQQgghhBBCCMuTBIYQQgghhBBCCCEs7/8Dt6x39bvYn9gAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 1080x1080 with 6 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "num_samples = 6\n",
    "min_week = 120\n",
    "sales = pd.read_csv(\"data/yx.csv\")\n",
    "sales[\"move\"] = sales.logmove.apply(lambda x: round(math.exp(x)) if x > 0 else 0)\n",
    "\n",
    "result_df[\"move\"] = result_df.predictions\n",
    "from data.plot import plot_predictions_with_history\n",
    "\n",
    "plot_predictions_with_history(\n",
    "    result_df,\n",
    "    sales,\n",
    "    grain1_unique_vals=store_list,\n",
    "    grain2_unique_vals=brand_list,\n",
    "    time_col_name=\"week\",\n",
    "    target_col_name=\"move\",\n",
    "    grain1_name=\"store\",\n",
    "    grain2_name=\"brand\",\n",
    "    min_timestep=min_week,\n",
    "    num_samples=num_samples,\n",
    "    predict_at_timestep=max(train_df.week),\n",
    "    line_at_predict_time=True,\n",
    "    title=\"Prediction results for a few sample time series (predictions are made at week 135)\",\n",
    "    x_label=\"week\",\n",
    "    y_label=\"unit sales\",\n",
    "    random_seed=2,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Additional Reading\n",
    "\n",
    "- Rob J Hyndman and George Athanasopoulos. 2018. Forecasting: Principles and Practice. Chapter 8 ARIMA models: https://otexts.com/fpp2/arima.html\n",
    "\n",
    "\n",
    "- Hyndman, R.J., & Athanasopoulos, G.著. 预测：方法与实践（第2版），康雁飞、李丰（译) https://otexts.com/fppcn/arima-cn.html"
   ]
  }
 ],
 "metadata": {
  "celltoolbar": "Slideshow",
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.9"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": false,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}