SARIMA.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "7jrXLPQyIaVT"
   },
   "outputs": [],
   "source": [
    "import itertools\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import statsmodels.api as sm\n",
    "import warnings\n",
    "from pylab import rcParams\n",
    "from ljungbox import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "tGl2jSIGIoee"
   },
   "outputs": [],
   "source": [
    "warnings.filterwarnings('ignore')\n",
    "%matplotlib inline\n",
    "rcParams['figure.figsize'] = 18, 6"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 228
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1248,
     "status": "ok",
     "timestamp": 1558260386374,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "katc2_KyJCMV",
    "outputId": "fc63901a-325b-44cf-9f11-03db4da3619b"
   },
   "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>co2</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>date</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1958-03-29</th>\n",
       "      <td>316.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1958-04-05</th>\n",
       "      <td>317.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1958-04-12</th>\n",
       "      <td>317.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1958-04-19</th>\n",
       "      <td>317.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1958-04-26</th>\n",
       "      <td>316.4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              co2\n",
       "date             \n",
       "1958-03-29  316.1\n",
       "1958-04-05  317.3\n",
       "1958-04-12  317.6\n",
       "1958-04-19  317.5\n",
       "1958-04-26  316.4"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# working with dataset called \"Atmospheric CO2 from Continuous \n",
    "# Air Samples at Mauna Loa Observatory, Hawaii, U.S.A.\n",
    "y = pd.DataFrame.from_records(sm.datasets.co2.load().data)\n",
    "y['date'] = y.date.apply(lambda x: x.decode('utf-8'))\n",
    "y['date'] = pd.to_datetime(y.date, format='%Y%m%d')\n",
    "y = y.set_index('date')\n",
    "y.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "q3wlZA96JNRu"
   },
   "outputs": [],
   "source": [
    "# Weekly data can be tricky to work with since it’s a briefer amount of time, \n",
    "# so let's use monthly averages instead.\n",
    "# The 'MS' string groups the data in buckets by start of the month\n",
    "y = y['co2'].resample('MS').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 138
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1222,
     "status": "ok",
     "timestamp": 1558260389114,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "aeaoKXaLIaVh",
    "outputId": "1fdc363c-033e-4c20-e32a-6a7a438c8c48"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "date\n",
       "1958-03-01    316.100000\n",
       "1958-04-01    317.200000\n",
       "1958-05-01    317.433333\n",
       "1958-06-01    315.625000\n",
       "1958-07-01    315.625000\n",
       "Freq: MS, Name: co2, dtype: float64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# The term bfill means that we use the value before filling in missing values\n",
    "y = y.fillna(y.bfill())\n",
    "y.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 392
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1958,
     "status": "ok",
     "timestamp": 1558260391781,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "eEOzBGGHIaVj",
    "outputId": "bf9e4a64-6d20-4177-8551-a3db84b5475f"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#time series e as a data visualization\n",
    "y.plot(figsize=(15, 6))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "RN1SxSrTIaVm"
   },
   "source": [
    "The time series has an obvious seasonality pattern, as well as an overall increasing trend."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "OSwDhfL0IaVm"
   },
   "source": [
    "# The ARIMA Time Series Model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "covm97saIaVn"
   },
   "source": [
    "One of the most common methods used in time series forecasting is known as the ARIMA model, which stands for AutoregRessive Integrated Moving Average. ARIMA is a model that can be fitted to time series data in order to better understand or predict future points in the series.\n",
    "\n",
    "There are three distinct integers (p, d, q) that are used to parametriz\n",
    "\n",
    "1. p is the auto-regressive part of the model. It allows us to incorporate the effect of past values into our model. Intuitively, this would be similar to stating that it is likely to be warm tomorrow if it has been warm the past 3 days.\n",
    "\n",
    "2. d is the integrated part of the model. This includes terms in the model that incorporate the amount of differencing (i.e. the number of past time points to subtract from the current value) to apply to the time series. Intuitively, this would be similar to stating that it is likely to be same temperature tomorrow if the difference in temperature in the last three days has been very small.\n",
    "\n",
    "3. q is the moving average part of the model. This allows us to set the error of our model as a linear combination of the error values observed at previous time points in the past.\n",
    "\n",
    "\n",
    "\n",
    "When dealing with seasonal effects, we make use of the seasonal ARIMA, which is denoted as ARIMA(p,d,q)(P,D,Q)s. \n",
    "\n",
    "Here, (p, d, q) are the non-seasonal parameters described above, while (P, D, Q) follow the same definition but are applied to the seasonal component of the time series. \n",
    "\n",
    "The term s is the periodicity of the time series (4 for quarterly periods, 12 for yearly periods, etc.)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "nyc6Zm8WIaVo"
   },
   "source": [
    "The seasonal ARIMA method can appear daunting because of the multiple tuning parameters involved."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "QRPDOu1HIaVo"
   },
   "source": [
    "# Parameter Selection for the ARIMA Time Series Model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "Rq4M9xuAIaVp"
   },
   "source": [
    "When looking to fit time series data with a seasonal ARIMA model, our first goal is to find the values of ARIMA(p,d,q)(P,D,Q)s that optimize a metric of interest.\n",
    "\n",
    "We will use a \"grid search\" to iteratively explore different combinations of parameters. For each combination of parameters, we fit a new seasonal ARIMA model with the SARIMAX()."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "qwIVbLTfIaVp"
   },
   "source": [
    "# select the optimal parameter values for our ARIMA(p,d,q)(P,D,Q)s time series model."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "XGA9ffiEIaVq"
   },
   "source": [
    "We will use a \"grid search\" to iteratively explore different combinations of parameters. For each combination of parameters, we fit a new seasonal ARIMA model with the SARIMAX() function from the statsmodels module and assess its overall quality. Once we have explored the entire landscape of parameters, our optimal set of parameters will be the one that yields the best performance for our criteria of interest."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 104
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 982,
     "status": "ok",
     "timestamp": 1558260400574,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "sPJHirYXIaVr",
    "outputId": "44b445ea-ab48-4dfa-df59-cb94f5e25194"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Examples of parameter combinations for Seasonal ARIMA...\n",
      "SARIMAX: (0, 0, 1) x (0, 0, 1, 12)\n",
      "SARIMAX: (0, 0, 1) x (0, 1, 0, 12)\n",
      "SARIMAX: (0, 1, 0) x (0, 1, 1, 12)\n",
      "SARIMAX: (0, 1, 0) x (1, 0, 0, 12)\n"
     ]
    }
   ],
   "source": [
    "# Define the p, d and q parameters to take any value between 0 and 2\n",
    "p = d = q = range(0, 2)\n",
    "\n",
    "# Generate all different combinations of p, q and q triplets\n",
    "pdq = list(itertools.product(p, d, q))\n",
    "\n",
    "# Generate all different combinations of seasonal p, q and q triplets\n",
    "seasonal_pdq = [(x[0], x[1], x[2], 12) for x in list(itertools.product(p, d, q))]\n",
    "\n",
    "print('Examples of parameter combinations for Seasonal ARIMA...')\n",
    "print('SARIMAX: {} x {}'.format(pdq[1], seasonal_pdq[1]))\n",
    "print('SARIMAX: {} x {}'.format(pdq[1], seasonal_pdq[2]))\n",
    "print('SARIMAX: {} x {}'.format(pdq[2], seasonal_pdq[3]))\n",
    "print('SARIMAX: {} x {}'.format(pdq[2], seasonal_pdq[4]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "hfzHt69gIaVt"
   },
   "source": [
    "The code chunk below iterates through combinations of parameters and uses the SARIMAX function from statsmodels to fit the corresponding Seasonal ARIMA model. Here, the order argument specifies the (p, d, q) parameters, while the seasonal_order argument specifies the (P, D, Q, S) seasonal component of the Seasonal ARIMA model. After fitting each SARIMAX()model, the code prints out its respective AIC score.\n",
    "\n",
    "\n",
    "\n",
    "When evaluating and comparing statistical models fitted with different parameters, each can be ranked against one another based on how well it fits the data or its ability to accurately predict future data points. \n",
    "\n",
    "\n",
    "AIC (Akaike Information Criterion) value, which is conveniently returned with ARIMA models fitted using statsmodels. The AIC measures how well a model fits the data while taking into account the overall complexity of the model. A model that fits the data very well while using lots of features will be assigned a larger AIC score than a model that uses fewer features to achieve the same goodness-of-fit. Therefore, we are interested in finding the model that yields the lowest AIC value."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1123
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 43798,
     "status": "ok",
     "timestamp": 1558260449404,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "gvRGoFrjIaVu",
    "outputId": "835fe3db-8d43-42e1-b519-d9c8ad1dea8b"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ARIMA(0, 0, 0)x(0, 0, 0, 12)12 - AIC:7612.583429881011\n",
      "ARIMA(0, 0, 0)x(0, 0, 1, 12)12 - AIC:6787.343624045894\n",
      "ARIMA(0, 0, 0)x(0, 1, 0, 12)12 - AIC:1854.828234141261\n",
      "ARIMA(0, 0, 0)x(0, 1, 1, 12)12 - AIC:1596.7111727638985\n",
      "ARIMA(0, 0, 0)x(1, 0, 0, 12)12 - AIC:1058.9388921320035\n",
      "ARIMA(0, 0, 0)x(1, 0, 1, 12)12 - AIC:1056.2878343061825\n",
      "ARIMA(0, 0, 0)x(1, 1, 0, 12)12 - AIC:1361.65789780726\n",
      "ARIMA(0, 0, 0)x(1, 1, 1, 12)12 - AIC:1044.7647912981681\n",
      "ARIMA(0, 0, 1)x(0, 0, 0, 12)12 - AIC:6881.048754228841\n",
      "ARIMA(0, 0, 1)x(0, 0, 1, 12)12 - AIC:6072.6623278300995\n",
      "ARIMA(0, 0, 1)x(0, 1, 0, 12)12 - AIC:1379.1941067373248\n",
      "ARIMA(0, 0, 1)x(0, 1, 1, 12)12 - AIC:1241.4174716840016\n",
      "ARIMA(0, 0, 1)x(1, 0, 0, 12)12 - AIC:1090.0766333165652\n",
      "ARIMA(0, 0, 1)x(1, 0, 1, 12)12 - AIC:982.8342911419691\n",
      "ARIMA(0, 0, 1)x(1, 1, 0, 12)12 - AIC:1119.595789362531\n",
      "ARIMA(0, 0, 1)x(1, 1, 1, 12)12 - AIC:807.0912987989984\n",
      "ARIMA(0, 1, 0)x(0, 0, 0, 12)12 - AIC:1675.8086923024293\n",
      "ARIMA(0, 1, 0)x(0, 0, 1, 12)12 - AIC:1240.2211199194076\n",
      "ARIMA(0, 1, 0)x(0, 1, 0, 12)12 - AIC:633.4425586468699\n",
      "ARIMA(0, 1, 0)x(0, 1, 1, 12)12 - AIC:337.79385466470865\n",
      "ARIMA(0, 1, 0)x(1, 0, 0, 12)12 - AIC:619.9501757829037\n",
      "ARIMA(0, 1, 0)x(1, 0, 1, 12)12 - AIC:376.928376042531\n",
      "ARIMA(0, 1, 0)x(1, 1, 0, 12)12 - AIC:478.32969081693074\n",
      "ARIMA(0, 1, 0)x(1, 1, 1, 12)12 - AIC:323.32465987866135\n",
      "ARIMA(0, 1, 1)x(0, 0, 0, 12)12 - AIC:1371.1872602338485\n",
      "ARIMA(0, 1, 1)x(0, 0, 1, 12)12 - AIC:1101.8410734302947\n",
      "ARIMA(0, 1, 1)x(0, 1, 0, 12)12 - AIC:587.9479710065286\n",
      "ARIMA(0, 1, 1)x(0, 1, 1, 12)12 - AIC:302.4948999528895\n",
      "ARIMA(0, 1, 1)x(1, 0, 0, 12)12 - AIC:584.4333533089834\n",
      "ARIMA(0, 1, 1)x(1, 0, 1, 12)12 - AIC:337.199905130641\n",
      "ARIMA(0, 1, 1)x(1, 1, 0, 12)12 - AIC:433.0863608138467\n",
      "ARIMA(0, 1, 1)x(1, 1, 1, 12)12 - AIC:281.51901760707915\n",
      "ARIMA(1, 0, 0)x(0, 0, 0, 12)12 - AIC:1676.8881767362059\n",
      "ARIMA(1, 0, 0)x(0, 0, 1, 12)12 - AIC:1241.9354051972482\n",
      "ARIMA(1, 0, 0)x(0, 1, 0, 12)12 - AIC:624.2602350563734\n",
      "ARIMA(1, 0, 0)x(0, 1, 1, 12)12 - AIC:341.2896612794466\n",
      "ARIMA(1, 0, 0)x(1, 0, 0, 12)12 - AIC:579.3895879696504\n",
      "ARIMA(1, 0, 0)x(1, 0, 1, 12)12 - AIC:370.5917899787062\n",
      "ARIMA(1, 0, 0)x(1, 1, 0, 12)12 - AIC:476.050042695133\n",
      "ARIMA(1, 0, 0)x(1, 1, 1, 12)12 - AIC:327.58085565747774\n",
      "ARIMA(1, 0, 1)x(0, 0, 0, 12)12 - AIC:1372.608588170917\n",
      "ARIMA(1, 0, 1)x(0, 0, 1, 12)12 - AIC:1199.4888094615062\n",
      "ARIMA(1, 0, 1)x(0, 1, 0, 12)12 - AIC:586.4485732985465\n",
      "ARIMA(1, 0, 1)x(0, 1, 1, 12)12 - AIC:305.62738340011174\n",
      "ARIMA(1, 0, 1)x(1, 0, 0, 12)12 - AIC:587.2528906139443\n",
      "ARIMA(1, 0, 1)x(1, 0, 1, 12)12 - AIC:399.36675243131685\n",
      "ARIMA(1, 0, 1)x(1, 1, 0, 12)12 - AIC:433.54694644086055\n",
      "ARIMA(1, 0, 1)x(1, 1, 1, 12)12 - AIC:285.7463928649827\n",
      "ARIMA(1, 1, 0)x(0, 0, 0, 12)12 - AIC:1324.311112732457\n",
      "ARIMA(1, 1, 0)x(0, 0, 1, 12)12 - AIC:1060.9351914421777\n",
      "ARIMA(1, 1, 0)x(0, 1, 0, 12)12 - AIC:600.7412682702173\n",
      "ARIMA(1, 1, 0)x(0, 1, 1, 12)12 - AIC:312.1329632525503\n",
      "ARIMA(1, 1, 0)x(1, 0, 0, 12)12 - AIC:593.6637755657694\n",
      "ARIMA(1, 1, 0)x(1, 0, 1, 12)12 - AIC:349.20914659652135\n",
      "ARIMA(1, 1, 0)x(1, 1, 0, 12)12 - AIC:440.13758839992397\n",
      "ARIMA(1, 1, 0)x(1, 1, 1, 12)12 - AIC:293.7426223042796\n",
      "ARIMA(1, 1, 1)x(0, 0, 0, 12)12 - AIC:1262.6545542464783\n",
      "ARIMA(1, 1, 1)x(0, 0, 1, 12)12 - AIC:1052.063672405869\n",
      "ARIMA(1, 1, 1)x(0, 1, 0, 12)12 - AIC:581.3099934474939\n",
      "ARIMA(1, 1, 1)x(0, 1, 1, 12)12 - AIC:295.9374059333453\n",
      "ARIMA(1, 1, 1)x(1, 0, 0, 12)12 - AIC:576.8647111792127\n",
      "ARIMA(1, 1, 1)x(1, 0, 1, 12)12 - AIC:327.9049130712576\n",
      "ARIMA(1, 1, 1)x(1, 1, 0, 12)12 - AIC:444.1243686511973\n",
      "ARIMA(1, 1, 1)x(1, 1, 1, 12)12 - AIC:277.78022014777855\n"
     ]
    }
   ],
   "source": [
    "AIC = []\n",
    "parm_ = []\n",
    "parm_s = []\n",
    "for param in pdq:\n",
    "    for param_seasonal in seasonal_pdq:\n",
    "        try:\n",
    "            mod = sm.tsa.statespace.SARIMAX(y,\n",
    "                                            order=param,\n",
    "                                            seasonal_order=param_seasonal,\n",
    "                                            enforce_stationarity=False,\n",
    "                                            enforce_invertibility=False)\n",
    "\n",
    "            results = mod.fit()\n",
    "            AIC.append(results.aic)\n",
    "            parm_.append(param)\n",
    "            parm_s.append(param_seasonal)\n",
    "\n",
    "            print('ARIMA{}x{}12 - AIC:{}'.format(param, param_seasonal, results.aic))\n",
    "        except:\n",
    "            continue"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 993,
     "status": "ok",
     "timestamp": 1558260456048,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "5tCBVbW5IaVw",
    "outputId": "32f144ed-f45b-4c61-8e42-a9ec55143238"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "277.78022014777855"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "min(AIC)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "TFJFBHtpIaVz"
   },
   "outputs": [],
   "source": [
    "pos = AIC.index(min(AIC))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 790,
     "status": "ok",
     "timestamp": 1558260459129,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "l-9iXTy6IaV1",
    "outputId": "a30000bd-b890-4687-b2f5-cc7c9d0e5f69"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1, 1, 1)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "parm_[pos]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 985,
     "status": "ok",
     "timestamp": 1558260464559,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "c76bclkbIaV4",
    "outputId": "cc6ff45d-dc41-4e1c-914a-904e9570898c"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1, 1, 1, 12)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "parm_s[pos]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "OmnXeWdmIaV7"
   },
   "source": [
    "The output of our code suggests that SARIMAX(1, 1, 1)x(1, 1, 1, 12) yields the lowest AIC value of 277.78. We should therefore consider this to be optimal option out of all the models we have considered."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "kKcd8S06IaV8"
   },
   "source": [
    "# Fitting an ARIMA Time Series Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 173
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 4321,
     "status": "ok",
     "timestamp": 1558260472677,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "hybYT48dIaV8",
    "outputId": "4de4a67f-bcd0-4b07-88f9-527873747299"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "==============================================================================\n",
      "                 coef    std err          z      P>|z|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "ar.L1          0.3182      0.092      3.442      0.001       0.137       0.499\n",
      "ma.L1         -0.6254      0.077     -8.162      0.000      -0.776      -0.475\n",
      "ar.S.L12       0.0010      0.001      1.732      0.083      -0.000       0.002\n",
      "ma.S.L12      -0.8769      0.026    -33.812      0.000      -0.928      -0.826\n",
      "sigma2         0.0972      0.004     22.632      0.000       0.089       0.106\n",
      "==============================================================================\n"
     ]
    }
   ],
   "source": [
    "mod = sm.tsa.statespace.SARIMAX(y,\n",
    "                                order=parm_[pos],\n",
    "                                seasonal_order=parm_s[pos],\n",
    "                                enforce_stationarity=False,\n",
    "                                enforce_invertibility=False)\n",
    "\n",
    "results = mod.fit()\n",
    "\n",
    "print(results.summary().tables[1])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "ik6p9NDZIaWt"
   },
   "source": [
    "When fitting seasonal ARIMA models (and any other models for that matter), it is important to run model diagnostics to ensure that none of the assumptions made by the model have been violated. The plot_diagnostics object allows us to quickly generate model diagnostics and investigate for any unusual behavior."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 730
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 2692,
     "status": "ok",
     "timestamp": 1558260484172,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "_vUdjjgDNIAu",
    "outputId": "943f860f-da9e-43b9-fe1e-b6562c0b13f5"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA3oAAALJCAYAAADielEXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvOIA7rQAAIABJREFUeJzs3Xl4W+WZ9/HvLcmOkzh7AglxNiAsYQsQdgJZYFgLnUJblrK00zJMgem09G1p6UvpQl9aGKAtpcuUthTCGrowECCQBcIaEhII2chK4sRZTWI78Sbpef84R7ZsS7Zky5Js/z7XlSvWOc8555Ys6zy3ns2cc4iIiIiIiEj3Ech1ACIiIiIiIpJZSvRERERERES6GSV6IiIiIiIi3YwSPRERERERkW5GiZ6IiIiIiEg3o0RPRERERESkm1GiJ5KEmU0xs9IMnm+smTkzC/mPXzSz6zJ1fv+cd5rZY5k8Z5LrfN/M/tjK/o1mdk4GrnO9mb3R0fOIiGSLmS03sym5jiOXzGy+mX0113EkY2ZVZnZwruNIxK8nHJpi2U6/53dGXUWyR4me5DUzO9PM3jKzvWZWbmZvmtlJ/r4unQQ45y5wzj2S6zjawzn3M+dc3t7ERUQ6Q6IvsZrfi5xzRznn5rdxniZf/EnnSZR0OueKnXPrO+FaXbpekkh8XaU7Pr/uTh8wkrfMrD/wPPAfwNNAITAZqM1lXKkws5BzLpzrOFrTFWIUEZH06fNdREAtepLfDgNwzj3hnIs456qdc7Odcx+a2ZHA74DT/C4YewDM7CIzW2JmFWa22czujJ0s7hvU68xsk5ntMrPb4/b3NrO/mNmnZrYCOCk+GDO7zczWmVmlma0ws3+N23e939p4v5mVA3eaWdDM7vWvsx64qNn5Gr5lNLMP/OcR++diXX/M7FS/VXOPX25K3DnGmdlrfkyvAEOTvZixrqhm9l0z2wb82d9+sZkt9c//lpkdG3fMd81si3/+1WY23d/epLuImV1jZp+Y2e7419Tf9xcz+2nzOFJ5XUVEupr4Vj8zO9nMFvn3pO1mdp9f7HX//z3+Z/5pZhYwsx/4n6U7zOyvZjYg7rzXxn3O/t9m17nTzGaa2WNmVgFc71/7bf+zvczMHjSzwrjzOTP7upmt8T9/f2Jmh/jHVJjZ0/Hlmz3H2D3v1+b1uFkVuz8kKNv8ftF8GMP1Zrbej2GDmV2d5DyBuPvFbj++wf6+Iv+57/af73tmdqCZ3YX3BfGD/uv8YNxzP9T/+S9m9pB5XRSr/Oc13MweMK8+sMrMjo+LI+E9y5LXS3qZVxfY5L8HfmdmvePO93/8389WM/tKouceV3actXLPt9brC/P93/Gb/vGzzWxoa69f3HFfTfT8zOwk/zmF4q5zmZktbe15SPYo0ZN89jEQMbNHzOwCMxsU2+GcWwncCLztd8EY6O/aB1wLDMRLrP7DzD7b7LxnAocD04E7/A8vgB8Ch/j/zgOa90lfh3fDGAD8CHjMzEbE7T8FWA8cANwFfA24GDgemARcnuyJOueO859HMfAtYDXwvpmNBF4AfgoMBr4NPGtmw/xDHwcW433Y/yRBzM0N988zBrjBzE4A/gT8OzAE+D3wnH9jOhy4GTjJOdfPf002Nj+hmU0AfgtcAxzkn6ekjTjitfW6ioh0Vb8Efumc6493b3na336W//9A/7P/beB6/99U4GCgGIglJhOAh4CrgRF4n5cjm13rUmAm3v1vBhABvol3fzgN75739WbHnA+cCJwKfAf4g3+NUcDRwJWtPLfYPW8o3v3zb7HEK1Vm1hf4FXCBf585HUiWJPwn8FngbLx7zafAb/x91+G9JqPw7kE3AtXOuduBBcDN/ut8c5JzfwH4gf9caoG3gff9xzOB++LKJrxntVIv+TneF9cTgUPxfm93+M//fLz7+rnAeKCtse1J7/kp1BcArgK+jFdPKfTLQJLXL/7CiZ6fc+49YLcff8yXgEfbeB6SJUr0JG855yrwkjIH/A+w08yei33LlOSY+c65Zc65qHPuQ+AJvJtCvB/5rYMfAB8Ax/nbvwDc5Zwrd85txrv5xJ/7GefcVv/cTwFrgJPjimx1zv3aORd2zlX753vAObfZOVcO/L+2nrOZnYn3IX2J//y/BMxyzs3yr/sKsAi40MxG47U6/l/nXK1z7nXgf9u4RBT4oV++Gi8Z/b1z7l2/1fQRvJvcqXiVhF7ABDMrcM5tdM6tS3DOy4HnnXOvO+dqgf/rXyclKbyuIiL55B9+a8Yev9XmoVbK1gOHmtlQ51yVc+6dVspeDdznnFvvnKsCvgdc4beWXA78r3PuDedcHV6i4Jod/7Zz7h/+Z2m1c26xc+4d/560Ee+LvOb3w5875yqcc8uBj4DZ/vX3Ai/ifVGZzA68e1y9/9m9mmY9V1IUBY42s97OuTI/lkT+HbjdOVfq32vuBC73X596vATlUP9etti/h6bq7/4xNcDfgRrn3F+dcxHgKeJeh3TuWWZmePfZb/p1i0rgZ8AVfpEvAH92zn3knNvnP6eEUrjnJ60vxJX5s3PuY//+/zRe8gkde/0e8a+Nn+ifh5eQSh5Qoid5zTm30jl3vXOuBO/bxYOAB5KVN7NTzGyeme00s7143z417864Le7n/XjfmuKfe3Pcvk+anftaa+ziuMePJ/7c8ce2eb4EsY/C++C9zjn3sb95DPD5ZpWKM/G+0T0I+NS/OaR0DWCnfyOLGQPc2uz8o4CDnHNrgf/Cu/HsMLMnzeygBOds8jz9eHa3EUeDFF5XEZF88lm/NWOg32rTvJUs3r/hteas8rvDXdxK2YNo+hn+Cd5cCgfS8nN2Py0/Z5vcg8zsMDN73sy2mded82e0/GzdHvdzdYLHxSS3xTkXn2x+4seZMv9+8UW8e3WZmb1gZkckKT4G+HvcvWIl3heSB+K1IL0MPOl3gfyFmRWkEUrKr0Oa96xhQB9gcVz5l/ztkF49oa17fmv1hZhk9Z+OvH6PAZ8xs2K8xHWBc64sxWOlkynRky7DObcK+Avehyq0/DYTvG+RngNGOecG4PUntxQvUYaX5MSMjv1gZmPwWhVvBob4N/ePmp27eTxJz9ec31//H3jfjr4Yt2sz8Gh8pcI519c5d7d//kF+15c2r5Ekxs14rZjx5+/jnHsCwDn3uHPuTLwbiMPrgtJck+dpZn3wvhmM2Yd3o4sZHlc2lddVRKRLcs6tcc5diddV7ufATP8zO9H9ayveZ23MaCCMl3SUEdcl3r9nDKGp5uf8LbAKGO+8rqPfJ7OfrSP9Fqv4eLcmKJf0HgDgnHvZOXcuXkKyCu+ekMhmvC6e8ferIufcFr9V8UfOuQl43T8vxhvGAYlf63ZJ4Z7V/Fq78BLFo+JiHuC8YRqQRj2Btu/5rdUXWtXG69ekaIJjt+B1df1XvCEc6raZR5ToSd4ysyPM7FYzK/Efj8IbLxDr+rIdKLGmg8X7AeXOuRozOxmvP3qqnga+Z2aD/GveErcvdmPe6cfyZRoTztbO959mVuKPL7ytlbJ/AlY5537RbHvsm7LzzJvcpci8yUxKnHOf4HXL+JGZFfrdPj+T6pP1/Q9wo98SambW17wJbfqZ2eFmNs3MegE1eDerSIJzzAQuNm8pjELgxzT9bFmK19V0sJkNx2sljGnP6yoi0iWY2ZfMbJhzLgrs8TdH8D7zonhj8WKeAL5p3oQbxXgtcE85b/bMmXj3gtP9z9kf0XbS1g+oAKr8VrL/yNgT8xyAd48rMLPPA0cCsxKUWwqcZWajzZtc5nuxHeZNmHKJn7zUAlUkvs+A98XtXX6yhZkNM7NL/Z+nmtkxZhbEe871cefZTtPXuSPaumc1qZf4v/f/Ae43swP8Y0aa2Xl++afxJs6Z4H9J+sNkF07hnp+0vtDWk2rj9YuXqN4F8Fe8MZ7H4HV9lTyhRE/yWSXeYO93zWwfXoL3EXCrv38usBzYZma7/G1fB35sZpV4YxieJnU/wusGsQGYTdy3Us65FcB/431rtR3vw+zNNs73P3hdIT7AG9T9t1bKXgH8qzWdeXOy88YKXor3TexOvG/s/g+Nf7tX4b1G5Xg3iL+m/Gy957UIb/zAg3gD29fiTQYA3vi8u/G+kdyGd1P/foJzLAduwmtNLfPPE7/Q/KN4r8FGvNf1qbhj2/O6ioh0FecDy82sCm9iliucczV+18u7gDf9bnan4n3h9yjejJwb8L5guwUaPmdvAZ7E+5ytxBsj19pyQ9/Gu0dU4t2PnmqlbHu8izeByC7/uVzunGvRbd8fK/YU8CHeRCLPx+0O4N3Tt+Ldx84meVfYX+L12Jnt3+Pfwbv/gddKOBMvSVkJvIaX+MSOu9y8GTR/RQekcM9KVC/5Lt699R2/C+2reBPC4ffgecA/bq3/f2uS3vNTqC+0prXXL16i5wdecjcGb6zjvgTHSY5Y0+7VIiIiIpLP/Ba/PXjdMjfk4PrXA1/1u/aLYGbrgH93zr2a61ikkVr0RERERPKcmX3GzPr43RzvBZaRYMkbkWwzs8vwurS21SIpWRZqu4iIiIiI5NileF07DW+s1hVO3bIkx8xsPjABuMYfkyh5RF03RUREREREuhl13RQREREREelmulTXzaFDh7qxY8fmOgwREelkixcv3uWcG9Z2SQHdH0VEepJU75FdKtEbO3YsixYtynUYIiLSyczsk1zH0JXo/igi0nOkeo9U100REREREZFuRomeiIiIiIhIN6NET0REREREpJvpUmP0RERERESke6uvr6e0tJSamppch5JTRUVFlJSUUFBQ0K7jleiJiIiIiEjeKC0tpV+/fowdOxYzy3U4OeGcY/fu3ZSWljJu3Lh2nUNdN0VEREREJG/U1NQwZMiQHpvkAZgZQ4YM6VCrphI9ERERERHJKz05yYvp6GugRE9ERERERKSbUaInIiIiIiISp7i4uOHnWbNmMX78eDZt2sSdd97JyJEjmThxIuPHj+dzn/scK1asaCg7ZcoUDj/8cCZOnMjEiRO5/PLLcxE+oMlYREREREREEpozZw633HILs2fPZvTo0QB885vf5Nvf/jYATz31FNOmTWPZsmUMGzYMgBkzZjBp0qScxRyjFj0REREREZFmFixYwNe+9jVeeOEFDjnkkIRlvvjFL/Iv//IvPP7441mOrm1q0UtDdV2EW554nx9+5ihGDe6T63BERERERLq3F2+Dbcsye87hx8AFd7dapLa2lksvvZT58+dzxBFHtFr2hBNOYNWqVQ2Pr776anr37g3Aueeeyz333NPxmNtBiV4aXlm5nVdX7qBXQZDfXHVCrsMREREREZFOUFBQwOmnn87DDz/ML3/5y1bLOueaPM6XrptK9EREREQkr4y97YVch5C2jXdflOsQuqc2Wt46SyAQ4Omnn+acc87hZz/7Gd///veTll2yZEleJHbNaYxeO2hVDxERERGR7q1Pnz48//zzzJgxg4cffjhhmWeffZbZs2dz5ZVXZjm6tqlFT0REREREJIHBgwfz0ksvcdZZZzF06FAA7r//fh577DH27dvH0Ucfzdy5cxtm3ISmY/SGDh3Kq6++mpPYleiloXn/WxERERER6X6qqqoafh41ahQbNmwA4NJLL+XOO+9Metz8+fM7ObLUqetmO5ip86aIiIiIiOQvJXoiIiIiIiLdTE4TPTMbaGYzzWyVma00s9NyGY+IiIiIiEh3kOsxer8EXnLOXW5mhYBWIRcREREREemgnCV6ZtYfOAu4HsA5VwfU5SoeERERERGR7iKXXTcPBnYCfzazJWb2RzPr27yQmd1gZovMbNHOnTuzH2UCmopFRERERETyWS4TvRBwAvBb59zxwD7gtuaFnHN/cM5Ncs5Nil+fQkRERERERBLLZaJXCpQ65971H8/ES/xERERERERyxsy49dZbGx7fe++9TdbPe+CBB/jrX/8KQHl5Oeeeey7jx4/n3HPP5dNPP21xvt27dzN16lSKi4u5+eabm+w755xzEh7TUTlL9Jxz24DNZna4v2k6sCJX8aRC66WLiIiIiHR/vXr14m9/+xu7du1qsS8cDvOnP/2Jq666CoC7776b6dOns2bNGqZPn87dd9/d4piioiJ+8pOfcO+997bYd8011/DQQw9l/DnketbNW4AZ/oyb64Ev5zielGi9dBERaYuZnY83u3QQ+KNzruWd3yt3OfAMcJJzbpG/7XvAvwER4D+dcy9nJ2oRkfzy84U/Z1X5qoye84jBR/Ddk7/baplQKMQNN9zA/fffz1133dVk39y5cznhhBMIhbxU6p///Cfz588H4LrrrmPKlCn8/Oc/b3JM3759OfPMM1m7dm2La11yySVMnjyZ22+/vQPPqqWcrqPnnFvqj7871jn3Wedc5tssRUREsszMgsBvgAuACcCVZjYhQbl+wH8C78ZtmwBcARwFnA885J9PRESy6KabbmLGjBns3bu3yfY333yTE088seHx9u3bGTFiBAAjRoxgx44daV1n0KBB1NbWsnv37o4HHSfXLXoiIiLd0cnAWufcegAzexK4lJZDFH4C/AL4dty2S4EnnXO1wAYzW+uf7+1Oj1qk23H0pYZ+7MeAMgaj+dO7lrZa3jpT//79ufbaa/nVr35F7969G7aXlZVx5JFHZvRaBxxwAFu3bmXIkCEZO6cSPRERkcwbCWyOe1wKnBJfwMyOB0Y55543s283O/adZseObH4BM7sBuAFg9OjRGQpbJI8F9hMIVSbcdaRt5LLA2xwZqWAA1fRjP/1sP/3YT9AaJ1nYFB3G/OhE5keP4+3oBKopylb00kX913/9FyeccAJf/nLjCLPevXtTU1PT8PjAAw+krKyMESNGUFZWxgEHHJD2dWpqapokk5mgRC8NDs3GIiIiKUnUZNBwEzGzAHA/cH26xzZscO4PwB8AJk2apBuUdGvBvh/Te+QMLFibcP8mvD+o0yqD/Ov2wexnFJXRPlTShwrn/d+Les4MLOPy4OtcG3qFWlfAu9EjGhK/9W4Eau2T5gYPHswXvvAFHn74Yb7yla8AcOSRRzYZa3fJJZfwyCOPcNttt/HII49w6aWXArBw4UIefPDBhtk5k3HOsW3bNsaOHZvR2JXotYM+AkREpA2lwKi4xyXA1rjH/YCjgfnmzfA1HHjOzC5J4ViRHqVg4EJ6Df8H0doDqNs2FZwxwnZxUfBdJgbWsd/14tXIibxWOIy3h77JgkB/qkuvgWifFud6JHIehdRzUmAVUwIfMDWwlDsKHuUOHmVR9DC+XPcdKml5nPRst956Kw8++GDD4wsuuIBrrrmm4fFtt93WkAyOHj2aZ555BoBNmzY1aaUbO3YsFRUV1NXV8Y9//IPZs2czYcIEFi9ezKmnntowuUumKNETERHJvPeA8WY2DtiCN7nKVbGdzrm9wNDYYzObD3zbObfIzKqBx83sPuAgYDywMIuxi+SJKIXDXqbX0NcIVx1G9ZarGevK+a/Qs1wSeJt9FPFw5AIeDl/YkJyFakdRNOIZ+o59iP2bv4yrbzneqY4C3owew5vRY7iLL1FiOzkv8B63hZ7gfwr/m+vqvksthdl+spJnqqqqGn4+8MAD2b9/f8PjMWPGMGTIENasWcP48eMZMmQIc+bMaXGOd999l5tuuqnh8caNGxNe69FHH+XrX/965oL3KdETERHJMOdc2MxuBl7GW17hT8655Wb2Y2CRc+65Vo5dbmZP403cEgZucs5FshK4SL6weooOepqC/suo+/QUard9hh+EnuD64MvUUcDvIxfz+/DF7KFfk8PCFROprh9A75JH6TP2IapLryVaPabVS5W6YTwcuZCdbgC/KvwNDxT8hpvqv0E0t5PTS567++67KSsrY/z48UnL3HPPPSmd6+ijj2b69OmZCq2BEr00aMF0ERFJlXNuFjCr2bY7kpSd0uzxXcBdicqKdHe7q3fTZ8wfCBSVUrP9IurLz+SK4Dy+GnqRJ8NTuDf8RXYxIOnxkepx7Nv4dfqM/jN9Rv8PNVs/T7jyuDav+1z0DIbUV/DDgkf5qfsT3w//GxqwI8kcfvjhHH744Rk519e+9rWMnKc5fVWRhliiZ1oxXURERCTj1u9Zz9WzribQaxs1W66mvnwyB1sZd4QeZUHkaL4X/mqrSV6Mqx/K/o1fJ1JTQu+SJygcMo8Ecxq18OfIBfwmfAlXhebyzdDMDDwjkdxRi56IiIiI5Nzi7Yu5Ze4tFAQK2P/JDURrRlFAmAcKfkMtBdxa/x+4NNooXKQv1Zv+jaIRM+l1wMtY4W5qyz5HW+0c94S/yBAq+Ebo75S7/jwSOa+Dz0wkN9Si1w5qzxMRERHJnH31+/jOa99hcNFgHr/ocaI13sSz3wo9w7GBDXy3/mvsYFD6J3YF1Gy9gtpdUygcuIiCAYtTOMi4PfxvzI6cyA9Df+XiwNvpX1ckD6hFT0RERERy6rdLf8uO6h3MmDqDkcUjgaWcFljOvwef5/HwNGZHT+rA2Y26necR7LORwgNepL7yqIRLL8SLEOSW+lv4a+Hd3FfwEHvqi3kjekwHYpCOGHvbCxk938a7L2qzTHFxcZOZN//yl7+waNEiHnzwQX73u9/Rp08frr322oTHzp8/n8LCQk4//fSMxdweatFLg+ZiEREREcmsNZ+u4bGVj3HZ+Ms4dtixAAygivsKfssGN5yfhL+UgasYtdsuxYI19Drg5ZSOqKWQr9Xdyjp3EL8vuI9jbH0G4pDu4MYbb0ya5IGX6L311ltZjCgxJXrtob6bIiIiIh3mnOOud++iuLCYb5zwjdhGflbwR4ayl2/U30Q1RRm5VrR2BPXlp1EwcCGBos0pHVNBX66ru40K+nJnwSMZiUO6vjvvvJN7770XgF/96ldMmDCBY489liuuuIKNGzfyu9/9jvvvv5+JEyeyYMGCnMWprpsiIiIikhPPr3+exdsXc8dpdzCoyB+Dt3QGFwUXcnf9FXzkDs7o9Wp3nUtowIcUDf8n+zd+nVTaPHYwiIfDF/CDghkcZpv52I3KaEySn6qrq5k4cWLD4/Lyci655JIW5e6++242bNhAr1692LNnDwMHDuTGG2+kuLiYb3/729kMuQW16ImIiIhI1lXUVfDfi/6bY4Yew2XjL/M27l4Hs77D25EJ/CFyceYvGi2idvtFBHuXUjBwYcqHPRuZTK0LcWVwbuZjkrzUu3dvli5d2vDvxz/+ccJyxx57LFdffTWPPfYYoVB+taEp0RMRERGRrHto6UOU15Rz+ym3E7AAROrhb1+DYAHfqv8Pop1UTQ1XHEd438HekgvBqrYPAD6lPy9HT+JzwQX0oq5T4pKu6YUXXuCmm25i8eLFnHjiiYTD4VyH1ECJXhqc03QsIiIiIh21qnwVT6x6gi8c/gWOGnqUt/GN+2HLYvjMA5QxpBOv7k3MQqCWwgNeSvmoxyPTGWD7uTDwbifGJl1JNBpl8+bNTJ06lV/84hfs2bOHqqoq+vXrR2VlZa7D0xi99jDNxiIiIiLSLlEX5a537mJA4QBuOf4Wb2O4Ft79HRx+IRz1r0Bmp9NvEUPdgdSXn0nhkNep33MS0eoxbR7zTvRI1keHc2VoLn+vm9yp8UlTqSyHkAuRSIQvfelL7N27F+cc3/zmNxk4cCCf+cxnuPzyy/nnP//Jr3/9ayZPzs37RYmeiIiIiGTNP9f+k6U7l/Lj03/MgF4DvI2rnof9u+Gkr2Ytjtpd0wn1X0rR8H+wf8PNQLCNI4wnItO4veBxDrVS1rqSbIQpORK/hh7A9ddfz/XXXw94s27GvPHGGy2OPeyww/jwww87M7yUqOumiIiIiGTF3tq93L/4fo4bdhyXHnpp447Ff4GBo+HgqdkLJtqL2u0XEywqo2BQat0xn42cRZ0LcmVwXicHJ9JxSvTSoBF6IiIiIu336yW/Zm/dXn5w6g+8CVjAm2lzw+twwrUQyG7VNFx5DOGqQ+k1bDYWbHtMVbk/Kctlwdc1KYvkPSV67WAaoiciIiKSlhW7V/D06qe54vArOGLwEY073v8rWBAmfikHURk12y+FQD29DngxpSMej0xnoO3jgkDqyzNI+jQJYsdfAyV6IiIiItLp/rjsjxQXFnPT8Tc1bgzXwdIZcNj50H9ETuJydcOoLz+d0IAlWOjTNsu/Ez2SDdEDuTKkNfU6S1FREbt37+7RyZ5zjt27d1NUVNTuc2gyFhERERHpVNv2bWPuprlcO+Fa+hf2b9zx8YuwbyeceF3uggPqys+gYPCbFAx6h7qdF7Ra1hHgycg0vlfwBIfYFta5kVmKsucoKSmhtLSUnTt35jqUnCoqKqKkpP2T/ijRExEREZFO9dTqp3A4vnjEF5vuWPwI9B8Jh56Tm8B8LjyQcOVRFA5aSN2u6eAKWy0/M3IWt4ae5srgXH4aviZLUfYcBQUFjBs3LtdhdHnqupmOntt6LCIiItIuNeEaZn48kyklUxhZHNf69eknsG4uHH8NBNpa2qDz1ZefhgWrKRiwtM2yuxnA7OgkLgsu0KQskreU6LWD5mIRERERSc2LG15kT+0erj7y6qY7ljzqzXB3fC4mYWkpUj2OSM0ICga9SSrf7j8emc4gq+K8wHudH5xIOyjRExEREZFO4Zzj8VWPc+jAQzlp+EmNOyJhWPKY12Vz4KjcBdiEUVd+OsGi7QT7rG+z9NvRCWyMHshVmpRF8pQSPRERERHpFO/veJ9V5au4+sirsfj1qdbMhsoyOPH6nMWWSLhiItFwHwoGvdVmWW9SlqmcGljJwbY1C9GJpEeJXhqcBumJiIiIpGzGyhn0L+zPRQdf1HTH4r9A8XAYf15O4krKFVC/52RC/VZgBeVtFp8ZOZt6F+SK4LwsBCeSHiV6aejBS3mIiIiIpKWsqoy5m+Zy2WGX0TvUu3HH3lJY+4o3Ni+YfxPA1396KmAUDnqnzbK7GMDs6IlcHnwNwrWdH5xIGpTopSHqJ3qm2VhERKQNZna+ma02s7VmdluC/Tea2TIzW2pmb5jZBH/7WDOr9rcvNbPfZT96kY6LLalwxeFXNN2x5DFwUTghP5cliC21UDDwPbC2Z9R8IjKdwVYFq17IQnQiqVOil4ZY100LXSFwAAAgAElEQVTTvJsiItIKMwsCvwEuACYAV8YSuTiPO+eOcc5NBH4B3Be3b51zbqL/78bsRC2SOTXhGp5d8yxTR03loOKDGndEI/D+o3DINBg0NmfxtaW+/PSUl1p4M3oUe1xfWDcnC5GJpE6JXhrUdVNERFJ0MrDWObfeOVcHPAlcGl/AOVcR97AvWq1VupGkSyqsnQMVpXDCdbkJLEWR6rEpL7XgCPBu9EjYsCA7wYmkSIleGnQHFhGRFI0ENsc9LvW3NWFmN5nZOrwWvf+M2zXOzJaY2WtmNjnRBczsBjNbZGaLdu7cmcnYRTrEOceMlTMYP2g8kw6c1HTn+49A32Fw+IW5CS5lRl35GWkttcCeT7xF4EXyhBK9NDi/SU9j9EREpA2J7hQtvi90zv3GOXcI8F3gB/7mMmC0c+544FvA42bWP8Gxf3DOTXLOTRo2bFgGQxfpmMXbF7P609VcfUSzJRUqymD1izDxKggV5i7AFIUrjiMa7kvB4DfbLPtW9Cjvh41q1ZP8oUQvDeq6KSIiKSoF4leBLgFaW2jrSeCzAM65Wufcbv/nxcA64LBOilMk4x5f9TgDeg3gwoObtdotexpcJO+7bTaILbVQvLLNpRY+diXQZ6i6b0peUaKXBqdMT0REUvMeMN7MxplZIXAF8Fx8ATMbH/fwImCNv32YP5kLZnYwMB5ou++YSB6ILanwufGfa7qkAsCqWTD8WBhySG6Ca4fUl1owGHum16Kn+qLkCSV6adCfrYiIpMI5FwZuBl4GVgJPO+eWm9mPzewSv9jNZrbczJbiddGMNXOcBXxoZh8AM4EbnXNtr9wskgeSLqmwbxdsfrcLjM1ryoUH+EstLGx7qYVxk6FiC5TrexnJD/m3SmUe0xc0IiKSKufcLGBWs213xP38jSTHPQs827nRiWReTbiGmWtmMm3UtKZLKgB8/DLg4PALchJbR9SXn0FB/2UUDFhC/Z5Tkhcce5b3/4bXu1SrpXRfatFLQ1STsYiIiIgkNG/zPPbW7uWKI65oufPjF6HfQTDiuOwH1kGR6jFEaoZTMHBR6wWHjofi4ZqQRfKGEj0RERER6bBZ62dxQJ8DOGn4SU131NfA2rlea16X/LbcqN97AsHem7GCXa0UM6/75gaN05P8oEQvDfqbFREREWlpT80e3tjyBheOu5CANateblwA9fu63Pi8eOGK43DOKBjwQesFx06GfTtg18fZCUykFUr00uA0HYuIiIhIC69seoWwC3PhuATJ3OpZUFjstXZ1US48gMj+sYT6L6XV6fliz3HD61mJS6Q1SvTSEG34u+6K3Q5EREREOses9bMYN2AcRww+oukO57xF0g+ZBqFeuQkuQ8IVEwn22kmgVytLYg4aBwNGKdGTvKBELw3quikiIiLS1LZ921i8fTEXjrsQaz4Gr2wpVJZ1ydk2m6uvPBrngq133zTzum9ufAOi0ewFJ5KAEr00qOumiIiISFMvbXgJh0vSbfNFsACM/5fsB5Zpkb5Eqg7zu2+2ksSNmwzV5bBjRdZCE0lEiV4a1KInIiIi0tQLG17gmKHHMLr/6JY7V8+CUadA36HZD6wT1FdMJFBQQbDPhuSFxvrj9LTMguSYEj0RERERaZd1e9axqnxV4ta8PZth27Ju0W0zJlx5JC5aSKh/K903B46CQWM1Tk9yLueJnpkFzWyJmT2f61jaEo1qwXQRERGRmFkbZhGwAOePO7/lzo9f8v7vwssqtOAKCVdOoKD/MrBw8nLjzoKNb0I0kr3YRJrJeaIHfANYmesgUqGemyIiIiIe5xyz1s/ilOGnMLR3gq6Zq2fBkENh6PjsB9eJ6vcejwWrCfZtZa28sWdB7V7Y9mH2AhNpJqeJnpmVABcBf8xlHKnSGD0RERERz7JdyyitKuXCgxO02NVUwIYF3arbZkxk36FEw30p6L80eaGG9fQ0Tk9yJ9cteg8A36GVqYvM7AYzW2Rmi3bu3Jm9yBLQrJsiIiIinlkbZlEYKGT66Oktd66bC9H67tVts0GQcMUxhPqthEBt4iL9hsOQ8ZqQRXIqZ4memV0M7HDOLW6tnHPuD865Sc65ScOGDctSdMliyenlRURERPJCOBrmpQ0vcfaos+lX2K9lgdUvQu/BUHJy9oPLgnDFRCxQT6i4lSUUxk2GT96CSH32AhOJk8sWvTOAS8xsI/AkMM3MHsthPG1yyvREREREWLhtIbtrdieebTMShjUvw2HnQTCU/eCyIFI9mmjdQAoGtNZ98yyoq4KtrZQR6UQ5S/Scc99zzpU458YCVwBznXNfylU8qYilecr3REREpCebtX4WxQXFTC6Z3HLn5neh+tNuOT6vUYD6iokE+67BglWJizSsp6dlFiQ3cj1Gr0tpTPCU6YmIiEjPVBOu4dVNr3LOmHPoFezVssDqWRAshEOmZT+4LApXTMQsSqj/ssQF+g6FAyZoQhbJmbxI9Jxz851zF+c6jrbEJmNRi56IiIj0VAu2LGBf/b7E3Tad8xK9cWdBrwRj97qRaO1wIjUHEmpt9s2xk2HTOxBOMmmLSCfKi0Svq/DXS1eiJyIiIj3WrPWzGFI0hJOHJ5hoZdcaKF/fzbttNgpXTCTU5xOsoDxxgXFnQbgatrQ696BIp1Cil4ZYgqdlFkRERKQnqqir4PXS17lg3AUEA8GWBVbP8v4/rGckevUVxwFQ0D/JwuhjzwBM3TclJ5TopUFdN0VERKQnm/PJHOqidYm7bYK3rMKI42DAyOwGliOufjCR/WOSd9/sPQiGH6P19CQnlOilwzX5T0RERKRHeWHDC4zqN4qjhx7dcue+Xd6Mmz2kNS+mvmIiwaJtfPzpx4kLjDsLNi+E+ursBiY9nhK9NGh5BREREempymvKeW/be5w/9nzMrGWBj18CXI8ZnxcTrjgG54yXN76cuMDYMyFSC1vez25g0uMp0UtD1J+NRWP0REREpKeZv3k+URfl3DHnJi6wahb0L/G6bvYgLlJMZP9Y5m6am7hAyUne/1sWZS8oEZTopUXL6ImISKrM7HwzW21ma83stgT7bzSzZWa21MzeMLMJcfu+5x+32szOy27kIonN2TSHg/oexBGDj2i5s24/rJvrteYlau3r5sKVR7F2z1o+qfik5c6+Q2HgGM28KVmnRC8NTmP0REQkBWYWBH4DXABMAK6MT+R8jzvnjnHOTQR+AdznHzsBuAI4CjgfeMg/n0jO7Kvfxztb32Ha6GmJu22un+8tI3BEkklaurlwlffnnbxVbxKUKtGT7FKil4bGWTeV6omISKtOBtY659Y75+qAJ4FL4ws45yriHval8XvES4EnnXO1zrkNwFr/fCI588aWN6iL1jFt9LTEBVa/AL36w5gzsxtYnnD1gzly8JHM2TQncYGRJ0JFKVRuy25g0qMp0UuDWvRERCRFI4HNcY9L/W1NmNlNZrYOr0XvP9M5ViSb5myaw6BegzjhgBNa7oxGYPVLMP5cCBVmP7g8MW30ND7Y+QE79+9suXPkJO//Uo3Tk+xRopeGWEueGvRERKQNiQYptbh7OOd+45w7BPgu8IN0jjWzG8xskZkt2rkzQcVSJEPqI/UsKF3AlFFTEi+SXroI9u+Cw3tmt82Y6aOnAzBv87yWO0ccC4GQJmSRrFKilwbX7H8REZEkSoFRcY9LgK2tlH8S+Gw6xzrn/uCcm+ScmzRs2LAOhiuS3Lvb3qWqvqohkWlh9QsQKPBa9HqwQwceyuh+oxN33yzoDQcerRY9ySolemlo6LqpJj3ppipr6nng1Y8JR6K5DkWkq3sPGG9m48ysEG9ylefiC5jZ+LiHFwFr/J+fA64ws15mNg4YDyzMQswiCc3ZNIc+oT6cetCpiQusmuWtFVc0ILuB5RkzY/ro6SwsW0hFXUXLAiWTYOsSr6urSBYo0UtDw2QsOY5DpLO8tW43D7y6htXbK3MdikiX5pwLAzcDLwMrgaedc8vN7Mdmdolf7GYzW25mS4FvAdf5xy4HngZWAC8BNznnVDOUnIi6KPM2zePMkWfSK9irZYFda2D3GjjiouwHl4emjZ5G2IVZULqg5c6Rk6CuCnauzn5g0iOFch1AVxJV303p5qJRjUMVyRTn3CxgVrNtd8T9/I1Wjr0LuKvzohNJzYc7P2R3ze7ks22uesH7//ALshdUHjt22LEM7T2UOZvmcNHBzZLfEn9Cli2L4MDmq62IZJ5a9NLQOOumasHSPUUbuifnNg4REckPczbNIRQIcVbJWYkLrJ4FI46DASXZDSxPBSzA1FFTeWPLG9SEa5ruHHyI171V4/QkS9Silxa1dkj3FvsSI6o3uYhItzD2thc6cLSj7yH/S7TuYI654/UWe4eyl4W9FvJA+DJ+1aHrdC/TR0/nmY+f4Z2yd5gyakrjjkDAW09vixZOl+xQi14anFo7pJuLtegp0RMRkUCv7QQKdxOuPCrh/mnB9wmY45XoiVmOLL+dPPxk+hX0Szz75shJsGMF1FZlPzDpcZTopUFdN6W7a1grMsdxiIhI7oX6Lcc5I1yZeDzZuYHFlLqhrHSjsxxZfisIFjC5ZDLzN88nHA033TnyRHBRKPsgN8FJj6JELw1q5ZDuTkuIiIhITKjfcqLVo3GRfi329aaGyYFlvBI5EbDsB5fnpo+ezp7aPSzZsaTpjvgJWUQ6mRK9NDRMuqk6sHRTsS8z9B4XEenZrKCcYNFW6pO05k0OLKPI6pkdnZTlyLqGM0eeSWGgkLmb5jbd0XcoDByjCVkkK5TopaGx66ZI99Q4Ri+3cYiISG6FilcAJB2fd25gMXtdH96LHp7NsLqMPgV9OO2g05izaU7LXjIlkzQhi2SFEr00OM26Kd1c7GakbsoiIj1bqN9yIjUH4uqHttgXIMq04BLmRo8nrAnck5o+ejpl+8pYWb6y6Y6Rk6BiC1SU5SYw6TGU6KWhse6rSrB0T5pZVkRELFhFsM/GpK15J9rHDLFKf3yeJHP2qLMJWKDl7JsapydZokQvDU7jl6Sbaxyjpze5iEhPFSxeiZlL3m0zuJhaF+K16HFZjqxrGVw0mBMOOKHlOL3hx0KgQOP0pNMp0UuDa/a/SHej97iIiBT0W060biDR2oMS7HWcG1jE29Gj2EfvrMfW1UwfPZ21e9ayqWJT48aCIhh+tMbpSadTopcGTT0v3V1UY/RERHq2QC3BvmsJVx1FomUTDrUtjAts1yLpKZo6eipAy+6bIyfB1iUQjeQgKukplOilQa0dkklPL9rMs4tLcx1GE5p1U0SkZwv1XY0Fwkm7bf5LwGuF0vi81IwsHsmRg49MPE6vrgp2rspNYNIjKNFLg9YYk0z6zswPufWZD3IdRhNOY/RERHq0UL8VRMN9iewfm3D/ucHFLI0ezA4GZTewLmza6Gl8sPMDdu7f2bhxpJ8oa5yedCIleunQOnrSzWnWTRGRnixCqHgVkaojSFRFLLEdHB9Yy+zISdkPrQubNnoaAK+Vvta4cfAhUDRAM29Kp1Kil4bGdfRUC5buqaHVWl9niIj0OME+G7FgDeGqIxPuvzz4OlFn/D1yZpYj69rGDxzPQX0P4rXNcYleIOC16m15P3eBSbenRC8Nyu+ku2sYoxfNbRwiIpJ9oeIVuGiIcNX4FvuMKJcFFvBG9GjKGJKD6LouM2PKqCm8XfY21eHqxh0jJ8GOFVBblbvgpFtTopcGdWuT7s5p1k0RkR7KEeq3isj+Q8D1arH31MBKRgV2MjNydg5i6/rOHnU2tZFa3i17t3FjySRwUShbmrvApFtTopcGdWuT7s5pHKqISI8UKNxBoHA34crk3TYrXG9ejk7KcmTdw0kHnkTfgr7M3zy/caMmZJFOpkQvDQ3LK6gWLN1UVLNuioj0SKF+KwESjs/rSzUXBBbyfOQ0ainMdmjdQkGwgDMOOoPXSl8j6vzxEX2HwqCxmpBFOo0SvTSo66Z0d/oyQ0SkZwoVryRSPRIXHtBi34XBd+ljtTyjbpsdMmXUFHZV72L5ruWNG0dOgtLFuQtKujUlemlR103p3qINY/RyHAhQH4ly+9+XsW1vTa5DERHp1ixYRaD3JsJVRyTcf3nwddZFR7DEHZrlyLqXySMnE7AA80vnN24smQSVW6Fia87iku5LiV4aomrRS1kk6lj8SXmuw5A0xd7b+TAZy9xVO5jx7iZ++NxHuQ5FRKRbCxavwswRrprQYt8Y28YpgVV+a55lP7huZGDRQI4/4Phm4/T8MY8apyedQIleGlzDZCzSlt+9to7Lfvs2b6/bnetQJA359B6vC3tjGEIBfUyJiHSmUPFKovX9idYc1GLfZcHXiWjtvIyZUjKFjz/9mK1Vfgve8GMgUKBxetIpVINKg2vxgySzZnslAGV7q9soKfmksdU692/y+oiX6BWG9DElXZOZnW9mq81srZndlmD/t8xshZl9aGZzzGxM3L6ImS31/z2X3cilR7F6QsVr/ElYmrbYBYhyWXABC6LHsp3BuYmvm5kyagpAY6teQREMP1rj9KRTqAaVhsap53NfCc53Zt7NIg/yBUlD46ybOQ6Exha9gqC6CknXY2ZB4DfABcAE4Eoza94vbgkwyTl3LDAT+EXcvmrn3ET/3yVZCVp6pGCf9VigLuGyCqcFljPSdmsSlgwaO2AsY/uP5bXS1xo3lpwEW5dANJK7wKRbUqKXBs1ImLpY1VwvVdeST2P06iKxRE8fU9IlnQysdc6td87VAU8Cl8YXcM7Nc87t9x++A5RkOUYRQv1W4qIF3kLpzXw++Bp7XR9ejZ6Qg8i6rymjprBw20Kq6qq8DSMnQf0+2LEyt4FJt6MaVBryoTtbl+FnenrNuhaXhy166ropXdRIYHPc41J/WzL/BrwY97jIzBaZ2Ttm9tnOCFAEHKHilYT3jQdX0GRPP/ZzfuA9/hk5Q2vnZdjZJWcTjoZ5a+tb3oaS2IQs7+UuKOmWVINKQ2PXTWlLINZ1M8dxSHqiedSiVx/xYlCiJ11Uoj7HCf+wzOxLwCTgnrjNo51zk4CrgAfMrEVzi5nd4CeDi3bu3JmJmKWHCfTaSqBgL+HKlrNtXhR8hyKrZ2bkrBxE1r1NPGAiA3oNaBynN/hg6D1YM29KxqkGlYbY2Dy1UrWtoeumXqsupfE9nuNAiGvRU9dN6ZpKgVFxj0uAFgtlmdk5wO3AJc652th259xW///1wHzg+ObHOuf+4Jyb5JybNGzYsMxGLz1CqN9KnDMiCdbP+3zwNT6OjuRDd3AOIuveQoEQk0dOZsGWBYSjYTDzxumpRU8yTDWoNKhFL3XW0HUzt3FIo8qaej7asrfVMtE8mnCoLuINStcYPemi3gPGm9k4MysErgCazJ5pZscDv8dL8nbEbR9kZr38n4cCZwArsha59Bih4pVEq0fhIsVNth9sWzkxsEZr53WiKaOmsKd2Dx/s/MDbUHIS7FoN1XtyG5h0K6pBpaEh0ct9HTjvGeq6mW+++sgiLv71G0SiyX8rsS6brRTJmlx03dxbXU9tuOfNera7qrZhOQvJDOdcGLgZeBlYCTztnFtuZj82s9gsmvcAxcAzzZZROBJYZGYfAPOAu51zSvQkoyy0l2DvLf6yCk1dHnydsAvwD62d12nOOOgMQoEQr232Z9+MjdPbomUWJHOU6KUhmkeLSee72BrXqSbFe/fXM/a2F/jb+6WdF1QPt2Sz9y1hq4lMJ36ZUV2XXgLVuLxC9j6mjvvRbL7yl57VdaY+EuXEn77K9/62LNehdDvOuVnOucOcc4c45+7yt93hnHvO//kc59yBzZdRcM695Zw7xjl3nP//w7l8HtI9hYpXAbQYnxcgyueCC5gfPY6dDMxFaD1CcWExJx14EvM2z/M2jDwBMCV6klE5S/TMbJSZzTOzlWa23My+katYUtW4YLpSvbZ5LXrxk3ps3VNN6af7E5b+pHwfAH96c0Pnh9ZD9fITptYSrsYWvcy+xzfu2seRd7zE0+9tbruwL9bCFMhyr6E31+7O7gVzrNZPqJ//sMXwMRHpxkL9VhCtG0y07oAm2ycHljHcPmWm1s7rdGePOpuNFRvZuHcjFA2AYUdonJ5kVC5b9MLArc65I4FTgZsSLCabXzowRu+T3ftYVtr6+KjuxBJUzk+/ey5n/nxe68dpLECniXWBrAkn76LXMEavlUTvoy172VVVm3R/Imt2eGsFzV6xLeVjYi16+dCNtDuLvc6BRH+0ItI9WR3BPuv8bptN//Y/H5zPp66YudEW8/9Ihk0ZNQWgcfH0khO9RE8NCpIhOUv0nHNlzrn3/Z8r8cYwtLbGUM61Z0bCipp6vvrIIs6+Zz6fefCNToos/6S7YLo+0zpfQ6JXn7xFL5UJhy7+9Rtc9KsFaV27PbOvxhZM18ytnSuW6AWV6In0GKG+a7BAmHBl0/F5w9nN+YH3mBk5izoKkhwtmTKyeCTjB41v7L5ZchJUfwrl63MbmHQbeTFGz8zG4k0d/W6CfXmzTlB7ZiRcs72SV1du76SI8pe1c8F01TU7T7JELxyJNszG2dB1s41mtO0V6bXoNZ4t9V9wfUOil9alJE2xMZv62xPpOYL9VuIiRUT2j2uy/ZrQKxiORyLn5SiynmdKyRSW7ljKnpo9XqIH6r4pGZPzRM/MioFngf9yzlU0359P6wTFkpZ0Kp7hSM+spTYsmJ7i0++Zr1J2xdajq6lv2nXznpdXc/Gv32DtjsrG93iGrx17H6STTNSFO2e8YDI9teWwoetmtgdDikiORAkVryJcdRgQbNhaRC1XBecyOzqJUqd1GbNlyqgpRFyEBVsWeGP0CouV6EnG5DTRM7MCvCRvhnPub7mMJRWxamA69cFID608xqqMqVbSY5VsVTU7T7IWvQ9Kvdk4d1XVNbRaZ3pcXOz3m04uEeu6ma0xeq0tO9GdxSZj0d+eSM8QKColEKoiXNV0WoTPBt9kkFXx5/D5OYqsZzp66NEMKRrijdMLBL3ZN5XoSYbkctZNAx4GVjrn7stVHOloz4Lp+VJ5XL2tkldWZK8LqaXZohd3YOaDESDFMXoN41Az+76NnS2dyXbq/C6F2Vq8PZzFv9VvPbWUmYvzYymRWk3GItKjhPqtwLmA36IX4/hy8CU+io5loTsiZ7H1RAELcPaos3ljyxvUR+q97pvbl0Nd4lnKRdKRyxa9M4BrgGn+QrFLzezCHMbTpsYWvdQrhNmsPLbmvAde52t/XZT166Y8GUunRiGQvOtm/Nu5cdbNxOdoa+xeW9LJJWILpmerUTxbXUQB/rZkC99+5oOsXa81jWP0lOiJ9ASh4pVE9o+FaJ+GbWcEPuLwQKnfmqfPgmybOmoq++r38d7297xELxqGsvy4R0jXFsrVhZ1zb9DFPk3a08rR0YpxRz00fy2HDCvO+nXTnYylYQxXJ8UjyVv04n9Dsd9XsqSnvV2R23NYbDKWbP0N5Uvre7Y1Lq+Q40BEpNNZwW6CRdup2XZxk+1fCb7ETtef/42elqPIerZTRpxCUbCIeZvmcfrRN3gbS9+DMfp9SMfkfDKWrsS10dqRSK5b9H7x0mr+/dHFWb9uuuvh9dSJMLKpV8M6eom7bhptd09ubzIU636Z3mQsGqOXDeq6KdJzhPqtAPDXz/OMszKmB5cwI3KOllTIkd6h3px60KnML52P6zsUBo7ROD3JCCV6aWgYv5RGR8Pmlccv/P5tVpa1mFy022ls0UutfOx1Ul2z0Y7KGm5+/H321YYzcr7GFr3EC6abWePyCkl+ce394qJx1s10xuj5yytkqWOvEr0cByIinS5UvIJIzYG4+iEN264LvkytCzEjfE4OI5Npo6axbd82VpWv8rpvlmZ/uI10P0r00tCeFr3mlceFG8r5yfMrMhhVfopVGlOtpDckep0VUAqcc3zoz0CZ7esmct/sj3n+wzL+uXRrRq7TOEYv+WQsbY3Ra28yFE1hVtU/LljPI29tbHhc201b9PItoYwl1BqjJ9LNBfcR7PNJk9k2+7OPzwdf4/noaexkYA6Dk8klkzGM+Zvne4le5VbYuyXXYUkXp0QvDdE2urUlkqhSl6g+NePdT9i2t6Z9geWhWKUx1TptPixD8Y+lW7jkwTd5cVlZVq+b7Klnut4dDKQw62ZDopdkjF6HJ2NJ/qR++sJKfvjc8obHsUQvW916s/UejI09zBexyVgCuhuIdGuhvh9jFiVc2ZjofT44n75Wy5+0pELODe09lOOGHce8zfMaF07folY96Zhue2u/87nlHPr9WRk9Z+OC6R2bdbP5+LVte2u4/e8fZWVWTOccMxeXcvUf3+nU68SeYaKXKtHkGuGGrpu5a1XYXF4NwPKt2e1am+0FwVtP9GJdNxPvD0ezl6TEllfI1uuTrZa2fEv06pKM0Xv+w6089s4nuQhJRDpBqN8KovX9iNaMBCBAlOuDs3k3egTL3bgcRyfgLZ6+snwl2/oNg2AvjdOTDuu2id5f3trYaROhpNei17JS1zyXiVW891bXN2ybubiUsbe90GqlvD0iUceKrRUs/uTTjJ63hVa6btYneE1yPTspQN9e3iS0VRkaE5eqtp56psaoRRsSvWavf1wrXrThy4zE52j3ZCztmFW1sxZvTyZbiV44kvv3erxkk7Hc/PgSfvCPj3IRkohkmoUJ9V3tT8LiVf3ODSxmVGCnWvPyyNTRUwGYX/YWjDhO4/Skw7ptotcZGiq/aY3Ra7tMLCENxc2GcPeLqwCoqKlPeEx7haNeZb6zK7WBVhZMT1TRzYcxesW9ggAZm/ykNfGtwm21WGWqQSv2K0/25UHUNb61k07GkkaSsmVPdcO12jPrZuw9ka1evfnaoheNOvbXdd57snGMXqddQkRyLNhnHRasazI+7yuhF9kcHcYr0Uk5jEzijes/jjH9xzR239y6BCKZrQdKz6JELw2Ns26mLlGLXssyfqIX9EZVrSYAACAASURBVGpaY297gV1VtQAUZHjgTCTqCEejnV6pbey62bK7a2uJXi7FWvT2dWKlOib+6SZPZDJb844lb9VJEj2vRc//uY1zpOLCXy7gr29v9I7z/wzSmcK/MdHrXl0369JM9O547iMm3PFy0vj27K+jsgNfCMXG6OXBMFkR6SShfitx0QIi+w4B4CjbyCmBVTwS+ReiqgrmDTNj6qipLNy2kKoRR0G4BrarZ4W0n/6609CeemDCMXrNKruxb/iDCZK6TNe9whFHJOq33nRiza758grxL0OirpuxiTBy2aoQS0KqajPbXTaR+IQp2SQgmX4tYpdJtrxCpEnXzY4tr+CcY291Pbuq6rzH/vZ0nlLsdcnaGL3430knJn3pdt186r3N3nFJvjSa+ONXOP3uue2OJ9aiF/u/uXzoVi0iHeEIFa8gXHUYOG+dvC+HXmKf68XTkSm5DU1amDJqCuFomDdC/gZ135QOUKKXhvZMxpJKhTFWpiDYshqc6UpuOBptqLh1pDK7sqyCVduST1oSm3AmdoX47mqtd93MXaYXiyE7XTcbf872ZCO1SRZMj8T13UwWU6rvmVi5FslDO7puZivPiH9fduaEKemeO/Y30VrngMqa9r9nY2P0kiWSHW3h3lVVq2RRJIcCRVsIFFQ0LJI+lL18JvAWMyNnUUHfHEcnzU0cNpGBvQYyf/cyKD5QE7JIhyjRS0M7huilVDGOVbCCCVYs7kgSkCghDUddQ8tFR6aTv+CXCzj/gQVJ9zdv0Yt/HRJVdPOh62bstU410Xti4Sae/7B9a9zF/15dG/X+TL0ysWvur0s2Rq/tyVhSbY2Kvbfau0RCfGKQrS6F8b+TdLtXpqO+nZOxdNbyD7FkPFlcHZmcaNveGib99FV+NXdNu88hIh0TKl6Bc0ak6ggArgzOoZeF+UtEk7Dko2AgyFklZ/H6ltepHzlJLXrSIUr00tEwO2HqhyReXqGpWAWrIBBo+c13B+p2iXKncNRlpEWvLbHnGKucxicI8a9JJOrYsqe6MZYcdt2MVfRTrdh+72/LuPnxJe26Vioteg0vRYYq+LGXuHkiGxt76nXpbb0VLdX3TKxxqGH8l789UYvt7qraFueNf4+09mXHJ7v3sWHXvpRiakuTLyOSdGPMhLRbC/2XLNJJs3XGkvH45xyfmFd1oLVwR6W3NuiclTuSlvlk9z7W7qhq9zVEpHWhfiuJVI/BRYoJEOWK0DxejxzDBjci16FJEtNGTaOyrpIlQ0ugfB3sL891SNJFdftEL5Pj0Bpb9DrWdbP52KvGMXrWolLbkVws0bUjkbgWvU5M9GJnjiWV8d3CwnEV3XteXs0Zd89l657cLhb/9yWl/O39LUB2um7G/56TJnoZH6PnXad5N7/4VteGBdOTvMdTbVWKlWvouukf1rzR+tN9dZz401e55+XVTbY3afFs5Zpn3zOfqffOTymmtjRtde68v432dgvtrDUMG1r04s4fP46zsgN/D41duFv/HZ5z32vtvoaIJLe1aivBorKGRdKnBJYy0nbzeGR6jiOT1px20GkUBgqZZ97EfGrVk/bq9oleJnOZ1rq1bdy1L+FkBgkTPf9/5xw7K2sbKn6hoLWoSHek62aiY+vjZtzszLWvG1uGYole4kr0/NXeN/2xb/5z1aD3zac+YMGaXQDsy8JkLPG/maytE9dGi2WTWTeTtuil9qZpHA8YbXLt5slr+X5vspaXl29LeDzkZh29ZBOTZEK6SWQsOU6UZKeTNFbVhjn3vtf4aMveJttjra7xccUv59CR8X/Nu3CLSHbN2zwPoGF83lXBOexwA3k1ekIuw5I29Cnow6kHncq8PatwFtA4PWm3bp/oZbLVyiWpBJfvq2PKvfP54XMtp8Bt7fpvrdvNqf9vDqWfVgPeOnrNz92R6BO26EUb19DrrBYCiGslSpDoJbpuw2QsebCWVybGZ81dtZ3N5fuT7k+1xQoSvwfqI9FWz5/4mt7/VbXhhNeMONewPdnkGamO0YsdH0uY2ppsp3k88UlNphaMb0uTRC8PJ2NJ9PecbLxlItsralizo4pV2yqbbK+N+x3Ffm/x5+1I180YJXoiuTF/83witcNwdcMYwW6mBpbydOT/s/fm8XZUZbrws6pq77PPnOFkPklICENCSAKEMMgQIKAI7YQIiEps70Xtz9bbw3c/7Ba1VW47tK3tbWe7iS2OjahIIJJAgDBESJgSpgRO5jk5yRn3WLW+P6rWqnetWlV7nwxsTlLP75dfzqldw6ppn/dZz/s+76WowKm+cYq6YuHkhdgxsBOvjzs9JXopDhvHPdE7mo6GcQGnCISEIkSR1F5hx0G/Nm13j69mObYVTd08AqJqUgD89gr+8i3dg7HNs48UYtgydZMEtyZFYygB65uBI035/csla3Dlt+LT0agBS9wtDt0Woyv84+/W4eKvrxxS/zRxTq7Hjb30XI9XNRyq2XVTS93kMYpeHK/36qHoUTOWt1KNXgDTtc8P4b0Ja3PV4xfJuYr0TYXoFQ+/R59U9A57DylSpDhc9JZ6sWb3Gpm2eaOzEgzAr9zL6zuwFDVhYedCAMDKUWOBHWuPbRpWiuMWKdEbAkJFT91nUnqS6fgiuBW25SKociwWCeaOZPgmglDxPDmm933vSdz6s7WHf4AEUIMP/7hE0SOBrjg/kU5Yz/YKFHp6Y89gGT9bvQWex/Hk6/trIshx/eoAtcVBtWfUJKI9+PKeYD+1f/HT45hUGuq6GTemWvvo6a0c4giiaTnnXDlOPRqmH9v2CkM7H/H9Ylb0alfbTOo64E84CQjFduBopW6KGj3OcfHXH8Z133/ysPc1HMEYewdj7DXG2OuMsdsMn/8tY+xlxtiLjLGHGGNTyWe3MMY2Bv9ueXNHnuJ4wBM7nkCFV+D2z4QNFzfYK/GYNwfb+Zh6Dy1FDRjTNAZndpyJR5AHir3A/g31HlKKYYjjnugdk9RNbXlSuqEp1U2sLwieMP/wFT3tmEcwF2469wpJ3QSAxzbsO+z9A/FBeNgoXSh6NHUzus3RSA87mhCNvgW++8jruP336/H9R9/AB3/yZ/zj76JpurVi2frdWPB/HpK/xz2jYYAfJR3ietaaSrmte1CpPTQZbPium/7PsTV6tZqxiNRNV9To+cv1d8WUIll2uarovUmTmG8e0Rtq6qYP03szFCXclYpeuJ/dPQXsOJTH5FGNcn8V11OUwiNpr0AnwbZ157F2y8HD3tdwA2PMBvBdAFcDmAXgJsbYLG215wDM55zPAXA3gK8H244C8AUA5wFYAOALjLGRb9bYUxwfWLl1JUblRsHNT8Fl1vMYzw7iF6maN6xw2eTLsC6/C3ttG9iRGrKkGDqOe6J3NNO+wobp6nKRimmsezJGqf76guBRRU9X4UzjX7O5G0ue2IS7Vm+RaZ8mmIJy1+NGhehwEadOiPMIzVho6mb0mhyJs9+xwL6+ovJ7e2MGALDiFV9Je21PfLP4arjj/peV36txJ9M1Ftczrvm5jou/vhLPbzskf6fEWuzd8zh5xmMUuFr76AlFL1A1xfPANKYnzo3uteJ59a/RO4apm7XUxlKiJa6ZSaEfSuq1uKR0cuDZrT7xOm/aaADAuXeswIVffVhxnj0SRa+ai+txjgUAXuecd3HOSwB+BeDddAXO+UrOuSi2XQ2gM/j57QCWc867OecHASwHkDY9S1Ezym4Zj+94HJd0XgLAwgfth7Cbj8RDqQnLsMLCyQsBAI+2jQS2PV3fwaQYljj+id7RVPTk/3p6ZTRYFUhKdZOKXpAm5RjbK0S3f/8PnsIX//gyPvf79bj1Z/EzPKZ4sux6R/WaxBENcQRp/EIVPTcaxIs6oLeCGQsQJXotDX7huiBLSaJMUqqh63Fs684ry6qmbpqUWVetgUsCHU/G9i+wSaXxzVjEmMz7qjV1U5xTqOgFRE9bT5B+egnKrqo618V181gqepXkE3p6Uzdmfn4Znnzdr/k9lore+h09cCyGuZ3tctnevqKy3yOpn01yKj4BMAnANvL79mBZHD4G4IGhbMsYu5UxtoYxtmbfviPLzkhxfGHt3rXoK/fhssmXYRL2YaH1An7tLoQLu95DSzEEzBgxA50tnXhkxBhg61P1Hk6KYYjjnuiJAPPvfvMCvnzfy1XWjscfX9iJXYF6FnHG1NIUKYw1ejJ1U1P0bBZN3awSIPXm440S4twtj6bbZlwdWlJ7BXH8/f1FWWMmFKZ6EL2KIajf368SPZ2QJJHlpHRhE8GKI3pSgYlJwQVqq9Gj42nL+cpkb74cGQut0YvtozfEGr2I62ZMD0mKiuspkxRHs842CVRFPJZ99KqRyE37/ebhP1u9RVl+pK6bphq9QtlDLmOjKas68In9Zh0L3QNF3PfizpqPQxGX7n6CwPRtZrwUjLEPAZgP4BtD2ZZz/iPO+XzO+fwxY9K6qxQhVm5diQa7AedPOB83OCsBAL+pLKzvoFIMGYwxLJy8EKtZAYMHNgJ9u6tvlCIFwXFP9ESQ+Ntnt+M/Ht902Pv5618+J3/W/9omBb/GGr3g/4EgmBKEz9QwvZoRRdaJv4UmPldxec01T4cGS9hyYCBxnbjUsZAQieNGXTfnf2UFthzws5ZEelg9TKUKBrKkK3p64J9Uq6Z/1l+sYObty7Dytb1GBS7u8Qkb28dflFqUJxrYixTUf/rjy5j9hT8prp2eR81Y4vYVPV5Pvox/vv8VhbSJ/RR1102YUzf18dLjmC719oODRz29kr7HtabEHg5MEwsUzYF6vEbUsyWYseTLtadVmlw3Pc5hMX+SiUJ8J41qyuJPL+3Bp37xHF7dPfR0ZVeb8DnBsB3AZPJ7J4AIY2aMLQLwjwDexTkvDmXbFClM4JzjkW2P4IIJF6DJyuAG+xE84s3FDqSTAcMRl0+5HCXu4qnGHLD58XoPJ8Uww/FP9I4BcdBjlqT0JGPDdKHoiRq9YrwDYzUBJYnoGdsreFxZnqSgvf3bj+HSbzySePw4RUla+RNL/3AMXiRIF2SkVrOPo4miRlZHNmUMRE8db5KiR5+5z/1+HWZ/4U/Il118e8VGI4GII/OyNUXCsWohO3T71oDo7e711WlaC+Z6Yepm3G0wBexfX/YqfvhYF+59PoxDxeUKFT3z/sqa4gf4JFu4ivpjUY/ZVyjjoq+txO2/P3xDHBN0k5JjhWpqobhm4hk82qmbZdevxRT/LIsha6vfI2K/I5uzctlQWjkIyOflhOR5eAbAKYyxaYyxLIAbAdxLV2CMnQXgh/BJ3l7y0Z8AXMUYGxmYsFwVLEuRoio2HNyAnQM7/fquDcswjh3CL9wr6j2sFIeJs8aehbZsGx5ubQc2r6r3cFIMMxz3HTOHShxWdx3A6OYsThnXmrCWuY7OFI8nHX9Aq9HzeBiMXX76WDz86t6qJgZ6gKYc29gw3VOWWwlMb09vMfYzgVhFL/hfkJWy4mjIcWiwZNjq6NZU1gpd0RvXlsO+mNRNgaT7StWou1ZvlT8zmIlZtXq4JGfNWogeNVBpy6mvvGWF99/l8S1E5JgMYxHXhl6jSOpmTB89sQ19Jm/+yZ/RQ1KS9evTG6i/y1/Zg6MJOoZN+5OV7CNBucrsE5084ZyHZiyGe0LJF13XBDrpMu2z9+OC6aMxY2wLLMaQ0b5HBkoVZB0LLQ1hPY9tDT2vWrzPpqfpvd97Au8/p9PwyfEBznmFMfYp+ATNBvCfnPOXGGNfArCGc34v/FTNFgD/Hdy7rZzzd3HOuxljX4ZPFgHgS5zz7jqcRophiBVbV4CB4dLJlwJ334pdfBRWevPqPawUhwnHcnBp56V4pLQU5U2PIVPvAaUYVjgBFL3qxOHgQAkn3bYUv3tuO2780Wpc+a3HEtePKnryk8i6xobpwRy9rNELFD1OzDBEUFVNkaSKXvdACSuIEmIKDMsuV5YfaUlcnKLnRRS9cL2Ky3FgwEz0dAL1ZvRQ08nq2LacoUZPS92sUdHTYUq1jEtrM5ln6KilRo8SzwbHQgN5ZjweOm2qqZu11+jJXmlkGTVj8bywXYK+WzEBQO97j1Z3qo9FpD7S5U++sR+fvGvtET0v4twmtOfQte8YEr0qZiyUvFc8LskxJdmux/GV+17GG2Sc1eon9ZrPp7oOwI1J3cyXXDRnbeQyR2bcELbriI7tua2HjqhNyXAA5/x+zvmpnPOTOed3BMs+H5A8cM4Xcc7Hcc7nBf/eRbb9T875jODfnfU6hxTDD8s3L8fZ485GR6EfeOPh1ITlOMCiqYvQCw/P5HcCvWkWd4racVwQvYrrxae/1RD4dQWz9//11JYqa/rQ9+jGBLGA2Y4+0kevFNanifE6VvwsPkXWCb+8P/Gztfgf/7UGPYNlZVz6WOMUvWLFxRv7+hOPp0NPexQQhxD/U6JU8TwcjCF6dMj3PLsd5//zQ1Vrmo4UlOgxBoxuzuKgpjjWmrr5xOv78fZvx08UmBW9GPVMpm4m1OgNMXXTYkzWgAH+Myc+dXmoH8c9dkNtmA74ZC+uVkukbiZNyETIoRvd5qN3PoMH1u+ONQcqlN2qdXdijDPGthxbRY/WMhrOm46z7HpyMoZe0+e3HcRPHt+EXz4dKsbV7k04cRBVDPXMgIGii6asgwby/XI4NZE0XXQoiFP8U6RIkYyuni680fMGrpx6JbD2pwBj+FXlsnoPK8UR4sKJF6LRbsDypkZgU5q+maJ2HBdEb8Y/PoC/++8XjJ/V4hIogs+kNEYKnVSGToVRGBU9WaPnBtuH+xHjrTVNKktm4rd0+8GpII6mc/9fv34eL+0kpgrkMJ+9Zx2u+Oaj6C2oikoS0SrEtVcQ52RQpcoJih4NfLd157Gnt4iDg/HOokcDlBzYjGFkUxYHB9Rj6kSvHPNcffaedbL+TQdjMUQv5vKarp2Oklu9bkonek3ZMHinSppbgxmLaSxW8C1CXwu632IlbOmhby6uaxJJ0cmhuF90sWzMHZPqfPrty3D5vzxq/GywVMGPHnsDh4Ln7JSxrdjdW5CK+9EGTd00pQDTZ4Sqfy5RX437NbynnHP84fkdKFZco+um5/nPfGNWne3PlytoytrIZcI/EYdD9MR4a1Ge6bv/6Ia0VUCKFIeDFVtWAAAWdS4EnrsLOOXt2I3R9R1UiiNGzsnh0s6FeLi5Ge6m5KyzFCkojpsavXue3YF//cA8eB7HN5e/JpfXIkCIlCi7VqKn/S7itlrbKwgMlHR7+3C8SYqexcL1aOqm+HlQ1vxVP3l6xsuDtM/efFna8AN+kObE1AIWYxQUacYiZ/Rp6qYXUcwEKJEQgWn3QAljWhuqnIkZhbILzhEJZCmoKmlZDKOaM+gvVlCsuFLR0IPo0hDqqOK2E4hX9ETtm6aCkbHUpOiR9S0LaM5SRS/cN+c8TLUbUnuF6LnT/ZYqHjEs0s6lBjKrXx6hwJpIUtJ+dhzKG5e/73tP4tXdfbhguh8MdbT6BiR9hUqk7cDRgELePA49O5KSopLryQmoF7cdwi3/+TR+8T/PQ6MhpdJUP/nIa/vwmV89j49fOh0LTholjykgXDenjGpStvMVPTV1s3gYyroriZ5q+mOax3I5hxU8S8eyYX2KFMczVmxZgTlj5mDctjXAwF5g/keBF4/NpFWKKE66bekx27fTOhqNnRYeeHk5PrX66B5n81evOar7S/HWwbBX9GhA+ZX7XsZz2w7huyvfCD+vgexIRY9cjaEEnkmum3E1epzziGMeJ33M7GAwpmFQ4wSaciWWi1YFtaiZlNsK0tabV/8oJM3GV1P0zK6bHAf641I3o2ShO0b9qwWX/8sjmPn5ZYnr0HOwGZNOg4cGy7jxR0/hpNuWJpKtikKW4o/DYA6W6TlzzmXLg7gaPfrcDDV1kzGGJmKwQY/teuEJxJ1Hkossj1mv5HrSdTMudTOx5jFG0VNrTVnV/ZiQL7l4dXcfgJBYi3dqqPuqFSbTGgpF0XM9eX2XrtsFAFjd1W1U/E0mL4fy/ruzp6cgj1XRJlMYYxhF3DUBf7KoKescsaInDqWQ14pnPG+1vUVK9FKkGCq29W3DK92v4MopVwJr7gTaJwMzFtV7WCmOEir9p8HyLKxrKWEi9td7OCmGCYY90aPBzU8e34QNe/qUzw83dTOpRkRXJdwYtcI/viFgYX4go4+NNqwWip5pnwrRc6KkTzTCroXk0nMWRiF66uYL2w7F1jfFKXq6gkPVhnKNip7Yx5EQvZ012OQrqZsWw6imrDzu6q5uOWYKxTDDjY45DtVcN//j8U0484sPYldPntTo6UQvJOJDbZhua6mbVEV2iaJXrW6QThBIzsFVAiHHWHZjU0JNrps69I+EokeXS8OSIZKzrv1hTWopuI/CrOZYET1ac2kaL72nP3qsC/uDSZEdB31FcmJ7LtKPEKheB+fJdzHcf6HswrIQcescKLpobrCRO8IaPTFZU9KJnuH5otciVfRSpBg6HtryEABg0YjTgK6VwNkfAazUhOW4AW9AdmAqVjQ34nzrpXqPJsUwwbAnenpAYCJPOln62eot+P4jb0S2oYFGErnQQxSxf1OYZQoWl764C9d8J1pM6/FwfdtmcpkO6pBHiZogfQNFoejFnoKEKVm1V3M9/OiSZ/D536tfKoKIVmuvYLq2wnWzvTGD1pyDzpGN8jPXQBa6j4IxQ1JtEyWxjIW9w6hhjE70lPPRGlAnwRTA0rHdH6g2Ow7mjeYZgB+Ey/3VcJPp2C0GJR3RJY6Y1HWTnsYzm7ux8rW9yljoc8MQfVbpkH1Fz6wUhjV68eeh3zupwFKiR84naftHXtuLO5a+LH+nrpXi3mSqKHrL1u/GsvW7I8foK9RWS1rSUjcpvr1iA5Y8uVn+Tn/uC97r5gbHTJQCU6pP3rUWT76xPxhX+Lk4FH12Dw2WjSnrPfkyGrOOkrp5eIqegci6rrEulRpXpYpeihRDx/KtyzFz1Ex0vv4oAAbMu7neQ0pxlHGodz72Og6mND1X76GkGCY4/omeF501v/336/G1Za+G6xjSC3WzkOaEGi8RRxtdN2OCxTcM9u0+KfV/rlXRo/vPaqmbScGzgKnvlm5vDwDPbj2o/C5IpehB9y9/eg33vhBa/obtFRAZS9nzsK+viNPHt2LdF98ua6MALTAVqZsxaZ5DgQiSTdCdGkUa2wGF6MUTOFXRix8DY6yqomexkDRJkqwdW1H0YhRVCt1llT7LnBgAueT5owH69T94Ch+98xns7S0QRS98bmTqZqyi50VU7417+lCqePK6Jl03/SNxv+gxxHj29Baw8Bsr8fre/sj6ALD4zmfw41Wb5O9vkPUE6RTPdpw6+JNVXfjJqi5lmVBid2p1gDsP5Q2TBJ7xZwD49oqNxmNS9OTLxobuZZejt1DBA+t343/+dI3yGWPMmAp8cLAsnzk64dKbLwftFUjq5uHU6MWkppq+m+iyVNFLkWJo2D2wGy/uexGLplwBvPhrYNrFQPukeg8rxVFGuX8WbA4cat1W76GkGCYYtkRvX18RF3/9Yby2OzlV0+Xc6EZHIeILmtKkK3qKI6cWu8QZTQBDSyXjPNyXqMGhWx/oL+Kk25ZiX1/Y442eb0ZP3RyCojdAiJBoSE2hN1QWwbAgGv++8nV8+pfP4cXth0AH7hnISqHkYn9fURqsKC6QtH4oGH9cmudQcP+Lu3D9D540PguKKslDokePm/QMlTW7+iRU66NnEVOXuNRNSlxqU/RUQtRE2iu4JF1YUfTI9pNG+ATgrtVbSD+86JjpNooZC2l/4nGOXT15XPmtx/CVpS9XfTfFNhRh6iY5r+D/rn0D2HxgUGkTopseUdD1BLkQz3acOltyvch1Fwrftu5BfPHel/D63j70Fsq48KsP4wv3qmq42l4hdmix+Nzv1+MTd62NLK94nlQVGwIlTlX0os/TocGSJOq/uvV8TB/TDMCfGGnUzFiOpEaPwndhjS5X6zqru8mmSJEixENb/bTNK3MTge4uYM4NdR5RimMCrxEdg6OwuplhEttTff0UJzyGFdGjKYXL1u/Ctu48vv/oG8o6ptTNuAbFurU7DYgjfdQ8DwtPG4Przu40uG4OLXUzDrS9gnTd9HyiunFPH7Z0D0b3TyK5TBCg9gszllpcN4MgjzYI11M3ASCjNVQWv+W11M11O3rkudD/xWz9xPYcdvcWsI8QvVwM0RPbxrViKJTdmnvs3XbPOjyz+WBEcfH3o+5jRKPvONqdkLpJoZLT+GvOUN11U9wP+izoRI+ecy3Bt1KjZ6nqNO2rSBVlSuSE0rOzJ1T0PB4ltfRXJWgn9agPvboXX77PT51cu+VgVaJHHWYFBNFTDh9ct/5i1IhosBhPGroHShjflpPjZAxwAiMkk4ulWK9U8fCTVV046balyJdc+e4fHCxjyZOb8eiG/SgEpjnCzTYcf1TRG0rqZxwqLpdGSqLOUIyLgZj7aN9zoaLXhI9dNE1+1px1JGEU5z1UmMhyvKKnqsApUqSoHcu3LMeMETMw7Y3HACcHzPyLeg8pxTFCvncedmQcnNG4ut5DSTEMMKyIHq3VsgIipAcE+ky753GjGx0QBvImQwg9OKy4HLMmtGFEUybBjCV6jKESPbG6aGfgceD/u/tFXPmtx5AvRQNW1fHR/7lfNmCvfmxxHfsKVNGLBpx6ewWxa73XmCCZ0uBDIyuTRzWha98A+oqVUNHLELt/6roZ/BzXXP3025fhxh8N7YvOZGJBFT0O/1xbGhzFfTRusgCoPXUTiKvRC3+Wih5JOdZr9MoaiSqUXWw9EJ0EkOMj2/t99MLrzTl1Rg3bKpiUoJ58WSPi/v+CnL64/RBe2dUbHJME7RVXqrN9hQruX+erXxnbqmog4thW5H1Lqt8SyjQ9fn9C2m7F42gI0hPLrgebMammxyp6FQ/FiocfPNoVnFNZUSyB4J4JaDJtsgAAIABJREFUgxjtO4lOIonredeft+LMLz4YO84kiEmYsuvJtOsGR/tqZ+Z62ULZUxw8qXLfmLWRc2pP3Vy7pRuf/uVzyvdOHNGLa41xx9KX8e7vPnFYaaIpUpyo2J/fj2f3PItFky8D1v8WOO1qINde72GlOEbY2XchLM7htKaGLCmqY1gRPRrvioBYV5R0cxDXi0/dFCmQ4nNKCKmFPQ/S6Bzb7/IUUfSECmLQ9IZG9EjqpkyH47jnuR3B59F9eUpA7Y+/fyjtFYL/6XU01eg5mp27GIsIovX6QK6tt2bzQbTlHEwd3YSNQV3UmJZqqZvJih4ArNni1w6u3XJQScOLg4n0U7IqAvZcxlbaLsRNFgBaA+ojTd20xHquJHi6skSJw8HBEk6/fRku+cbK2AbfFS11k6bjKWYsMa6bYllPvqxa8wc/i3fx98/vxNX/tiqyPe2jR5GxWVVFL2OxyASKacJDT0F2lXc5nui5HpfPbqnikx7xrMelXRcrHorl8P5YFouYD63auB/fC9q8iOt/oL+Id/3743hxe4/clzjGgy+p5i6mPnNxaA5Scf0aPUH0ojXFCgkloPWWtF1L8xBTN6/7/lO494WdyveHsUbPNaduVjyOH6/a5Lv8popeihQ14+GtD4ODYxFrBQYPpGmbxzm424Jp+QZsajkEIP2uTJGM4UX0SMQniJBO7AY0Jc7j8SlYIl1RBDB0PUp8RDCWsRgYM/TRi3EUpNvWAs7DoFvW6HH6efL+xXnI9LWaUjf941Biq/fRA6I1emLXA1orB721g+txvLSzBw+/uhefXDgDnSPDxsxC0WvMmvu6iVOLU/Qorvv+k7jim49Gluv9xkwuobTmURy9MWvJ1DsgOcilxCvpkjNmVqN0sxQgMDARtaN66ib5fdXGsJeO3pfRvH8/fVPA41zpdWhqgyC2740oev7PJk6i90QzBfyOZVUleo5tweMcg6UKbv7Jary8s9d4D8Vz3B+8/3S3A4brItt+eFzW5JVcn+gJlTtuokTU6InvC85J30hC9IRjpiD396/fjRe398D1ODpassr6Sg0wgJaG2hu1NwcKbcX1ZNq1OCdueJ/054m+IvQ9b2rQXDdrVNlKVd6HuNRNSkBTRS9FitqxYssKTGmdglNffwxoHAWcfEW9h5TiGKOpbzq2Zy1Manil3kNJ8RbHsCJ6NGgQcZHesFufvfc4V4IGGpSL/lSyVo98lif7oS0PGGMR5c5kYCE/q0L0aIqVr+j5P4t0LBpsmoJiz0T0CrWnbkpFLwiGW3NOTOqmWdEbKLpS8QRI2qdUhkKH0StmjsWE9pzchyR6GbWvm35u3QOlqiYnAr96eqvSLkAP1k1Ea08vIXrB6o0ZWyFOcW0kALW2s5b2Cnq9o/pcMzlOqehFavTC36l6Ekea6HLbYkr6qse5VFdczuV9M6VuHho0Ez0dPYNl5bNiTKqeY7OqqZsZm2Hdjh58+b5X8MTrB/DPD7wSeeeB8PuAKnr//vBGPPTKHsVoKBw75Ho60XOqEb2Kh2LZI/WKPKLoUYhlLaRRfUegZodET92mMcHlV4cghWWPSyMlPXWTIXTd1Ce+KMmkz2ZT1lb6dBbKLv7xd+uwUetVCkT75AnEuW7GKXr0WClSpKiOnmIPntn9DBZ1XgL22gPAGe8FnGy9h5XiGGNn74VgnGN825P1HkqKtziGFdFTFD3Zx03rMVZKTt2k9TpS0XPD2X0BGuSL7TNWkLqpxS4ymDkMRU9Xs0LXTf/WUPMQGkCdPWUEHIupil4wzr5iBRXXUyzm4yBivHzZvy7j23IxZix6jV5A9EoVhZz1FyrYvH8Au3sLcr29wc9jWxukg6M4FpCQuhkco+R6RlXGhNvuWYc/b/KbnJtInSklbE9faFUvQvbGrKOouvpzRlEL+QH8YLtYcZUm1Po2IswuVtzYGj2hhlCCDERVR8/jWN11IKIYUvHI9cLxq330oimacambeoeOrv39ETMWE1HP2lZV5caxLPQVKvjl01sBAOPacsZ7IXYv6lMrHse/PLgBH/vpGiPRq5C0WJGuyLn/vSKIDz2HXz69FX943k+hLlZcFN1QlXK9UNIzERtxzeglEJMccYqeqZY0Ds0BgayQGj3xvtLRmNrIAGGdLhAaOgH+e0lH8equPvz8z1vxqV9E+zdt3BuSP9qX0thHL86MhRDQQ4NHZkyTIsWJgpXbVqLCK7iqkgEq+TRt8wTB5sopOKPgord1a72HkuItjmFL9AQKGgEYLEYVPRpA0LTEA/1qjR4NgJTUzWB7x2YAO7o1esLhT+xHnKNQFWh9Gg2K3zajA3M627UUOX/MA8UKvrbsVXxz+YbEYwO+grRmczcefMl3BhzRlDEqQ3Eq1ECxooyhr1DBwn95BGuD2jnX49jXV0TWsdDemMFZU0bixnMn4wcfOhujWwypm5Q0kZ/1XnpquqR6jYW5RtGg/JiW7estojVQRUJFz1IIwmCpEiE0ArR+rxYzlqymtnzsp2vwXNCnUMTcNN1RV2CECiYC/CmjmoLl6n37+Z+34MYfrcYDpLk3Y2pNVjR1019OjyjGkS+7itIiTlsnKV37BmpL3bRZVddUXUluaXCMao94BgZMrpuGSQIxdo9z5X7YjMlj0u+bz96zDp/51fMAQtdNcR9cL3zzk2o56SSTIHqCBFqapBf3rJmg1OgFRE88C+K6MGLGoo+RHrqBTOi05jLKcyDaVJjGRlPm6QSL0YzFNdds0vt6NFqqpEhxImDFlhWY2DwRszY+CoyYCkxeUO8hpXhTwDClfzR2N5TBMvvqPZgUb2EMM6IX/iyCXz2NS++Zpadu0rREQebKQWAigiOLqYYPIjDyzViiTM9U1yTHmRD4ZR1LCXho82qhWFKVhqpRjmXBsayIcgL4YxeqVjUwAO//wVOSDLQ0OMbz0IP5kOi5KtErqjPxrsext6+IMS0NYIyhMWvjq9fNwTtmT5DrUGWKpvjRa9OtBX70nk777P3KZ4IgmhS9A/0lnHvHCvy560Aw/gr6ihVMDJRGccTGjI1DefVZ0ZU4AUrEqvbRMxA9ALKeS63RiyrN/vECRS8gyG+b0RHsW11vc+DESU1qLMYwNiAZgJre6vFwssLkfgqoEw9yuRb47+4tRMxYTHzOr9GrlrqpXqvefDlR0TMRPZPrpnjOKh5X0hypomdS4yuuF3k/aFuKpFpO6mw7RqZuht85FEPgebJGr+x68vtNPPuywT0QO3GgpG46lOg5yvN8IJhsoeT7X5dvwEm3LVW+51SiFx3vP9yzztirk9bKpkQvRYrq6C/148mdT+KK8eeDbX7MV/OGMkuUYlij0DcHADCu7ak6jyTFWxnDiujRoEME+nqgqM/eux6wgTRVp2mJ+ZJK8MQ+RzZllf2IwEiascTV6Bktw+PPpzlrK4EhDRhFMEWDpiLZmWMzWJYfvK3f0YNXd/fKfQ2WXEW1SYK+WnODk1hnRMcK+EE0DfL6tQCOc2BvXwFj2xoQB2r3r6Zuhut0DxTpJomufCK4NSk/a7Z0Y19fUaqde4PgcsKInLJeY9bGIRJsFsqeVAqjx6tR0WP+M2YietuCHonivpXckOjp1160V2jOOrAYcP70Uf5y7WETzxC9DrbFcO2cCfjLt02T46V99EKlK9wPPT4NxgVZ0mtBdWJXrLiH7bqpu7325MtGVTZ8HoUZC1X0DESPXNusRvRkewVTfZlhvL6i56+bRPQo4RQ1eg++vAc/e2pzNHVzCMGaUPQqniczFsQ9rxjqR/VrHmfG0pbLYG7nCPm7SHW3SRbCdx7aCCDaN1HA9F3SX6zIDAKKvQrRS1M3U6Sohse2P4ayV8aVRRfgHjDnA/UeUoo3Ec+XzsHsYhGZtvX1HkqKtzCGF9EDaYUQEyDq9Tj3vbgTt92zTv5OZ5KFGihq9IRS0N6UUVI3ZRNzO7lGzxTj6/VVFE1ZRyV6HmmvYFD06M8Zm/mKHue49v8+jnd8exUhepWa7dlpLVDWtpB1LMVyX0An1GKcg6WKYqzQpxE9l3Ps7S1iXKtKpChiXTe9sH6qe0AN/EwB95xOv2+QCG4FSaaBvCCI4qz3BPWDE9qD2sHg8LmMHakTqkXRS67RCxQ9O/rabT8oajGDsZfDGj1dFXaDc586ugnnTRuNUc1+4b1+TTJBQE4VMJG6ec2c8QCAQ/mSfNZdj8vJCt2tsS3nkwlRbwmEREi/FWVXNV8pxaZuWkZidNOCyco6gN+0fd7kEejJl82pm8H/4v2nz6vuxEvHTmv0AFRtrxDX8F6cblKPPzoJMjK4Zz98tAu3/+GlSOrmUCBMXmh7BV3R88dpPoc4M5a2xgxGNmex+avXYOaENrnPjGGs9B2g16BWEyXAnxASOJzm7ClSnGhYvmU5xjSOwdyNjwATzwY6Tqn3kFK8idjCx2FBP3Ao1wvmHKz3cFK8RTGsiB4QKnZxRE9X9F7a2av8TlM3i2XzvkY0ZtTUzeBzRyp6KkQsM9T2Ck1ZWwbnFgvqpQSpFETPNVv8O5YFK8aMJV92ZfuJaqAxW9axYDEGzqNN5vVr5HF/jGWXYzAwcmnK2ujTaySD1M0kRU8leuFyakOvK3qmQPD86aP9sXoeTvvcA/hh0NBapMkBYbquCG5F8D06CLylGUvGjty7XIyid+8LOwlBij1NMBafurlX9nQMSap4FrZ157GrJzTlEeP62nVzsOQvz5UqTFm7JiZFT5y3+P9Tv3hOXkuX9NHj2n0Q9ZQ0dVMqetpJl10v4gYb1wNSv8a/+fgF+MwVp4bnEDygY1sbML4th558OdI7k45BEL1q9V4u53hjX79R0TOZsQgY00A91JS6KbadP3WkYkoERFOjhwKp6LlcTrQI1VNMNNEaPX1CgB5b76Mnl2vXSAe93tUUPcDcMmVvb9GwZooUKUwYLA/i8R2P4/IxZ8HavS41YTkhwdDSfxIAwElVvRQxGHZEryDJmTmA0ImenvolAqGmrB3W6OlErykryQsQBtaO7VvT67PUSYYrSS0OmkivrJYGB5yHREeYtNAURZqy5it6TNl/2eWwA/JlsrMXpImCpoiVXQ82Y3A1AxvxmYA4/9ZA5RHpYiMaM5FAt1jxnQAp2dLRlDG7bnqco60xA4tFe/uZlJP2xgwA/x4XKx5+++x2AMBoct7inovTFvsRZJO2V9BhakINAHev3Y4/vrgr9vwo4lI3/bG48joXK55iVHLH0rBXjnj2GxwbDY6ttAegEAQwrxA98X80WPdICiJNT/Y4N/Z1E7cqklrqhhMWVtA70ET0ypojLhAoanZUYXJs38ynJ1829nmUNXqlKNETKYcU9z6/E1d881Hs7i3AsS15XRxyfKnUk7HT1FUBasZiSisV6CtUMHNCG+7+5IWRSYNIjd5hmLFUPI8QXQ/7+opEKQ6/iyKpm2QoNHWTfjdQkxbdIAdQnzHVdVNd74cfPgeAmXx319AvM0WKFD6e2PkECm4BVw0WAGYDs99X7yGlqAM2FOfitGIJra3P1nsoKd6iGHZETyhtcTPnej2OHpT0BYreyKasTGkzK3oi4Hbx7w+/7u/LsoyKnimI/Y/HN2HGP9yfqOjRGfPWXEZpryDGTYN3RdGzLdiaoifGDqgEUQSRN583FQumjVLWpwFlyfVgWQyuFzVsUA1H/P9bAqInLN3bm6JEUtyPpL5g+meyDx7nsBhDLmNHAmjT/Rfphd1aYC/UOiAkAIz5xxG/ixYP4ixN441T9Oh+k+C3VzCnbgLAYJESPRceB64/pxOMqUGwIIDiGRH70yc/wtYZpEYvWGhSZajrJhV0PY8rLTAE3vbVh33XVe35p66KjRk7NnWz4vrulboZCp2cEambjsXQ3uQTPRNJEEMQ7zQ95wP9JdnKQ2DNltCsyCF1eY5lhYoeV1OAAbWOTMBP3aylRq8s3V2p2y4QNV8ZQsajvDcVl0uiV6y4OPeOFfivp7bI9dyYMcaZsVDQyQnTOeZjFD363Zh1LFw1axwcixnvoUmpTZEihRnLtyzHyIaROHvDo8DJlwMtY+s9pBR1wFPeLCwaHES5cReY01t9gxQnHIYf0YtR4QQitWTaakINGNWclcG5rg61N2Vkw/Q7n9iMe1/YCcBXF0w1eiai9+X7XkbFoFhQtGiKntpHL7lGz7GYr75pJziiySd61I1UBMsWY4nKgd9HLOpUCqiEU4yxtcE/liR6jVHVR4zZRCwEGhxLGRe1+7cthgbHijgtmmr02gKS263V1nUoqZuiRo/h9NuX4e/++wUAoXOhCNhzJkXPsExAEOxqiEvdBPznUNSL+g25PYxqzuKiGR1qX0ctvVeoMHoALn6njyfTUjcpKGGhz7TLuVSNdOzvL0brOQmxa8w6Pmk1vAZll6NU8aQSC4j2BuH1EYqebTG0N2ZQrHiROlAgapBEr9f+/hImamY7/aRuj6Zrqg3T/UFTEm9S9BSH0YT3vb9YkZMjGs+LkJz3n9MZux8dguh5nMv0UJMzqbhP+nPCYlI3Kegza2pXUVAyD2KInm2BMYa2xoxRvUuJXooUtaHoFvHY9sdw+chZcHq2pWmbJzC287E4s78BYIDT+lK9h5PiLYjjjujp0GtqRI3eqOYs2VcYjGRshuasg8GyC865JDFAQJiMAXL88eM+G9mUwWcWhYXTrTkn6KMXHMsyuG4qZiwWbJtFlJIRgapGFT1hnmCxaCNm/XebMb/3oKFGb+2Wg3hh2yE5xhaZulkOziFKdkpSfYp/1BhjaosFYvdvWb6ipytmRUNQ2BYcX6/nE+QXCPssMqYG5Y26omcgdSbyJ5BEZCl29xQUhZGiUHZlEC5q9CzLfx6pyVDF9WBbTAboIgjX3wmT8iJr9Ay3w+Ok3pQsdz0YFT3Afx+jqZuhGUtj1m+KbkolrngeegsV2VNOjIsqesLh0bGYJPIm6O8ZJQ3dA0XZPkOA9ttUFD07/FlcTkpiTIqeb2Lj/5zkBttfqMjJHV3Ro+T117eej/+1qHZTBfFcFiseippCGo4xnEDRJ8No0kMs0bNVovfAul146o0DcllcjR69L0IRb8s5xoboeQOBTJEiRRSPbnsUA+UBvL2/H8g0A6e/s95DSlFH7CzMxLRSBZm25+o9lBRvQdSV6DHG3sEYe40x9jpj7LZatimUouQsCTrRE+YbI5oyMiijJhZZ20Jj1gbnfuBE41PHCmkRrdup1hTdhAtndOCMie3y96YGv2eVmHUXAW6somcLRS8mddOk6FksEuDr27Ngn6bUzeu+/yTe/d0n5Cy9MJT48Srf9KTVoPqI+6TXSupoJC0WPKIqWQxB6mbtit5BzaGTqlEioNbt60XzcVmjZ0rdjFHiAP88k+oxAWBPXwG7ewuYO3mE8fNXd/fhQJB2Wqz4rpuOxdDc4CgqihssF8gY0nwBM9ET8brJrMdP3YzWpXmcS8UTiKo7xtRNoeglpm5y9BXKCtHTUzfFJIVtWQpBFmm6dIwUdCLA44iYn9DvBduylJRWW1P08oqiV4AOj4e1jcWYCSgeqG1ickSfGKATSq25zJDaK4jaUTGJZZpIcL2w/1+SGUvGMR9XvecVfPLnz+KmH6+WyyjRe+qNA9I8iN538U61NWYifTEB//uWsdonTVKkOFFxX9d9GNPYgQUbHwNmXgtkm+s9pBR1xGpvFt7d3we7aStY5kD1DVKcUKgb0WOM2QC+C+BqALMA3MQYm1Vtu6Eqen0FNegXKY0tDQ4xdiFEz7GkepEvuUpKmHDdBNR0uCRL/TjogbZjsUDRU4kRDdbpOP2G6SwSZLeL1E2q6AVEgLFoyp4+djsweBHH+vYN83DtnAmaGYv//2njW7H4wpPwatCnsCVnTu8T+03CNWeOx6njWoIx+ctcj8NmInVzCDV6WloYJSkiwNdH05hRx25SsJIUPdfjeGzjvtjPAaBr3wAAxBK9T9y1VipGhbIXpNIyNDfYCjEpu1wxzcjGpG6aDGsEgTARCS/BdTOXCdNr6bXJl6KKXqnCpRrmp26azVjyZRfFiqcY9diMKc+KqEN0LIbOkSFZo+RQHy8QTS8c356L/dyxmGxv4FgmRS9c1+QMSV034xS9kuunnApFT79X1A04LrUXML9H4rtCpqUbTJcqhpYpAvRZ0BvUm8Y0aGhXQa/Rspd24x3fXgVAnTAQ72F7Y8ZYg5gvucjYllFNH66oNpnJGLuEMfYsY6zCGHu/9pnLGHs++HfvmzfqFG9lHCocwqodq/DO9tNhF3rS3nkp8JQ3C9f0+714M+3P13k0Kd5qqKeitwDA65zzLs55CcCvALy72kZDJXq68lcou7AtP1VQ7IvOcDc4tgxk/fTNcFu/j54fFNG9VlNyTBAB23vmTQQQba8gPqfKHFULMrYfnLra+Y0UqZtU0bNojZ4aKLoeV7JR7YA8UqfRrG0Za/QYgOljwpnE1gSilzE49VH807tn4wPzJ8sxif8ti6EhY6NQ8fDbtdtx5xObAJiJnlDudKLX1BAGjv0kdVPAYog0QzfW6CUE4IWyi8V3PhP7uYBjMcya0FZ1PWFiEyp61AXW05wph566GWfGYqrR84L7IK4JdUkdNBA9mrqZc6xYoicMOTqU1E2mEA/x7No2Q+fIJrm8I8HFFYjWe43V+jgOKIpeSO6qKXr7DbVl1HUzrkavUPLTKoUqPGV0Eya05/Dh86cCUF1lk56zJsNzaQfPQqjoRa+N6/HYzAP6KMQp79edHdYMDhrSpvXrLRRKejmkomdI8Rb7EL08jwfUOJm5FcBiAL8w7CLPOZ8X/HvXMR1simGDB7c8iIpXwbXde4HmscC0hfUeUoo6Yyc6cKg8EaflrSB9c+gxaYrjF/GR+bHHJADbyO/bAZxXbaPlDz+K/c8W8erOVgDxTbjjsH3nHoA7eO2V9ciXmnDnnUuwbUc7AJ8gFfIDePqpJwC04Re/vhvPH8oB8APMZfcvxesDWQDNWPLTn8ralqe6GwH4atSSJUuCI41JHMemrjewZMnzmAdg3unAL7cVcahsY9XjOwC0YsXyBwGMwO59ByBu0+tdmwH4QdzKh1agq68BvQNZZJiFMvcHs+nV9QCaFYJbyA8AsPHsmjXYOZiR+wCAgcE8wBmExvXS+vUoVxrx29/9HsAorHr0EWzqz6JnIAvAD9TuuuvnADqwds0aNNgcQCsA4LX1L8jroOPxVavQ80Jyn6w1wXX8+S9+gSabY9fudljMV0sOAfi7Db5ixjc8ivW9DQBUwnTP3b8B0IHt+3tA5zAOrnsE05rasGUwAy84zx3bt8vrYIPjgaVLAYwE4N/D1wcyAFTlbWvXBohnQccfHn4SQPX0mSxz8auf/wzVno/te/YDcPDcc8+Cc4ay24yf3LkEDgNe2t2CcrFBPmtFDwDG4MnVT4NtfFTu42XDO/Ls2jVYsnkVuksWgNHKZzt27kKx5ACwsGfvPrn/QqkDr778MuDmAFgo5fshnsllKx5GV18D6DO1dfsOeAc2g6EJ+/fuRsFlqHAG/etmV3cfAAubXg6fmz/87h6Mynry+mzevAlADls3b8IffvOiXN6/f2fk3Ch2BtdPYM3jD0HcXwDoGSxCPPMvvvA8ioVGABb27t6N3/z6VwA68ORTq+G+9gg2kWdhy+4DEO+BwAPLluHQoRYADrZs2wHxXUJx589/CWA01r/4ApbsfAoA8PEJwIbtewC0oydfkuP5/T13o9UJrwEFd4uR4z+0fDmAEXj1jS0Asji4e1vk2nRt3oLujAvT87tt21YsWRL2YBqZGYULRg2S7zIfnz8NeKK7EQ/ti77j61/ZEDnmkiVL8Oy+Joj3omf/XixZsgS7drUAaIzso79QQtbiGJ8toxvJRH6YQE5mAgBjTExmvixW4JxvDj5LO8SnqAlLu5ZiRts0nLb+MWD+xwC7nmFcircKlnnn4sb+B/FPYzxYuR3wCrUbeqU4vlHPqVPT1HFkGoIxditjbA1jbA0ASWhqLNGLoMwZbMaRYQAHg8sBlxPzB8bhMH/nFc5QdC3lMxMOZyhM24oF+xFLxcR6haxWIeP00zABHpyPQM42qDjBXhmLXnSX+9eh0fLwsakHYTEe9PMLDVxsBuTJdRBHYyzcNwA0WPFXwqrhKlksNGHxj+PrpxkrvO8A8Gp/Fn/c3WrY3v9/0FXvZ7PNccuUHozLRd0aAcBhPOJGmjE8nUnnt69U2x/buGdIR8kLrj+AbHBcsczl6n7EhAN9jk2/A6GSaX759KdSLPe3E+9Fhhy77LGIEYrLGTj3753DOCpc3W+L42J0toJ8cJ9anPCZ1cclfregqrB0GxP0DMpWbX36LlmMy2fPYlweU0wK0GevvxL9yvQQvhOmaw4AheBcHe3+h9dSfWbjYHouEbyH4no2G66Nb7RjHpt+1z9zcjcWjIzWIloMyMaMLc6Dhq6dCZ7jnG3ehxt8ly0YmTd+PgxhmsycNITtc8HfvtWMsfeYVqB/H/ftS04dTzH8sb1vO57d+yyuyU0Ac0vA3BvrPaQUbxE84C7AVYMDsDyGTHtqypIiRD2J3nYAk8nvnQB26itxzn/EOZ/POZ8PAPPOOReLFy/GpMlTaz5QS4ODuZ2+8Ulzazty2SwuPG8+AOD6m27GyNEdct2OkSNx1aIrAADXXHstxnaGx7nuve/BOWefBQD48Ic/gsWLF2Px4sU455z5cp1bbrkFixcvrjqmmaefJrdfvHgxpp00FSNGjMD5F1wAAPiLa64GAOSaQkIzZtx4+fMVi67ErJmnI9PQANvJ4L1nTcLHL52Ov//QtZFjjWj3z/28BQswZcpk5TPP8gnKp6+ahds/+SHMmzsXnDGMPeNCAMA7rroSs2fNVALjm276oNzf5Qsvkcuvuuzi2PO98orLlfM1/bswOPcPfOAGLF68GKM7xqBz0kRMnzoZbSNGyXS93+wA4NDcAAAgAElEQVRoV4JvAPjXD8zFh2/2x8VJ0NzRmsNHP+rvf9K4sM/QlMnhdWhtbsR73xNmRi1evBh/fcv1OGfqSPzTu86Qyy8675zIed1+rZ+JVWkcHfnMhLaWlpqeDzvrKx7nn7cAl1/s34t3ve96LF68GNOnz0Bba4u8bh9bfAsAYPbcebjlllvw7us/iMWLF2PCpMmR/Z63YAEWL16MGz5wfeSzMWPHwnH8tLrRHR1y/8yyMHfOmWht8ZWcyRPGyW3OOvc8dE6eEo7bYhjZMQazZs9GxrExY/pJaGlrR1t7qI5eMXsyzj2lE4LcvO+dV8rPbvjA9cr1Ofnk6QCA0089RVl+4Tnz5PFMyDSG6qrFgFtv+aBxPQA479z5aG321z9pymR85EM3AwDOmT8fixcvxkWXXibXrRjI0hWLrkR7m/+OtY00PwcLr/Jd8d52wXnKM//ed10TWfejH/5Q7DMyaoSqYr973kR8/uM3wXFsNLT41/jS886ObDdxUidOPf004z6nT5tW9d0U/y675G3GfYyfNEX5vTFjY/HixThzzhy57PQZ/nEWnD3XuA8AaG9pwRf/6mbc+ynzcYYZaprMTMCU4O/eBwF8mzF2cmRn5O/jmDHJWQIphj/u33Q/AOCdOzYCY2cBE+LfpRQnFl7jk7G/Mg5zBm04bS8ASF2MU/ioJ9F7BsApjLFpjLEsgBsBVC04F7VjtdboAcAFJ4/Gl949G4BfS5WxrdCSnFjaA6q9esXjiplLXFBJFY1ay/V0MxaLCTMWcazAYIOcp96fyrYCh0yPY2xrAz579cyISQUQKiEWi5pwiHMXNXQWY+AcuOP+V/zlFovUzIh6K4up5g0tMb3WgGjjehNkbRSpE7NJe4VxbeZ0ro6WLN53dmfEsh4IaxYBte6OXoaGjBWpTRrVnMVvP3khLjw5DNxbGqK1RedP9xvQb9zbX+30ACQbbVAIV8KMzWSN4UBgglH2VDMWxhgyNsN3HtqIaZ+9H2d9eTm2Hxw01otZ8lkw1+iFrpvhco+rdVzUkTRfdpX6u6asLfvo2RZDgx3U6JEXw++VF+6QtuXQ3zFZUxisL+6H3ixeB7XqH9WcTawRtS1L7p/W6InvGrEv07sF+DWM1Wr0RM2afv9zmej4k54R/Rn/txvPQtbxXUNFm5NRRtdNjrivTNOzEIe4Nhu0bycQ1svSY+YCd9Ck8xP3aU6n2bBomKGmycw4cM53Bv93AXgEwFlHc3Aphhc457iv6z6cM+oMTNy+1lfzhvDupjjewbDMW4AP9++B5fTDbn693gNK8RZB3Yge57wC4FMA/gTgFQC/4ZxX7fYozEcqJHA8eUxybVRz1paBYaHiSTMWwA9UFTdL25LBlOtxpb9VJmj4C6gNmmmgq/efi4Me0LLAjEUExCbXTfqz60G2VxBBNQA0ZaNkK+ydFm2YLiAMIPRx+ddDXSaJnmaFbzq23I+pcVtknGL/4XEsxpDL+A3T48i9NOwwnBwleqrJRbhu1rZig13a/8/kKiqs7WtFtTYT/j4tSbRmT2qXQfNAYMhScb3IfnTCs7unYHTdTOqj9/y2Q9KtVWmYHrifim2SXDdbGhzfjCXYJutYKGlmLJbFFKJKTXz0+yB+E+d750fPxQtfuEoSgrgJBOo6O7q5wdhOQsCxmPzcsSz5HIl3UZCYsTFEj5rYFCvmWVTxPaIbrZgcJpMcauNOw7aYNGPpMLpueooDZq3H09Ec847rPfB6C2V856GNyn0Xhkdx5ById/0cpjisyUwAYIyNZIw1BD93AHgbSG1fihMPL3e/jE09m3AtbwKYBZyZum2mUPGAuwAL8wNw3EyavplCoq5/VTnn93POT+Wcn8w5v6OWbQTBo6Tn4lOSU1aaGhxJBnRFr1D2lFn4DJnRL7ueYmtPg0rPA77xp1ext6+gqBU18jyjcsFpe4XgWDRwVIkeh20zVAJFTxAS26DAieCZGVw35XnbcUSPRYIvcbqMMWTIsZJUu1oIjhibuJ6uh4Do2ShU3NjeidSCX0czcdykzpqUkFuMxRJRuk+TqyhVZJIUzXCs1V85+jzPmdQug2tha192eWQ/ulKbCZQ0HaKNQDUVR8Tn4l5YFpOOs42a62ZE0XN9YmfbfmuMYkVtmG4zFntdoxMgTFne4Nhob8zI+xXnUEnf6Y7WbCKZsUl7BZuQPrELQWLiiJ7Hw3w8k9Opvw//e0R/N5NaCfzVwkimXiwsFjoMjxqi6+ZQRIFYRa/sKZNIpYqHf12+AS/t7JHLxL1KVvSOH6IXN5nJGPsSY+xdAMAYO5cxth3A9QB+yBgTk50zAaxhjL0AYCWAr3LOU6J3AmNp11JkrAyu7HoGmL4QaJtQ7yGleIthHZ+GvbwD5/ZbcFpfAliyAV6KEwPD7q+qCFbKroeLZnTg5S+9HRNHJLtvNmVsGeiJ9goiQM+XXUW1c+wwrUxX9BzLkkHRc9sO4rsr38Df/voFJYiteJ5ihR8HnZSI9goydZOFip4YOw1eZ09qg82YVLno/pq1YIymbloxAa8IsHQCYLI7F8oAA5AhBKlaMF0Noa19kLrpcdiWHyAWy15sEC3Pj/Q5FGgggXROIyjyfBCmBupQlCcDkaOK3tlTR2LjHVcb9xPur/p1mDrad0acPKoRjm1JsiomHSqeF9mPriQ5NkOp4kUUXPF7ksIF+M9iqeLh509vleuLTWjqpt5ewVf0eFTRI7fOslisUhpNaQ7Ox6CAA7URg9HNDcEkh/lzVdFj8jkS7RUEYY5N3eRcEuO4Z3QgeN50NSsXQ5wA4H+/43TcMD9aZ2k8h2C/jsUizeQBf4JM77kpMLTUTfNkRqHsGidL+knPPfGuJCp6x0lrBQHTZCbn/POc83uDn5/hnHdyzps556M552cEy5/knJ/JOZ8b/P8f9TyPFPVFxavggU0P4NJRZ6D90FZg7k31HlKKtyQY/uSei4/17wCzynBa07mhFPVtrzBkMIT1W2WXB83NnappgU0NjgyMPe4HQ2ImffvBQRwaDOvwMnaYulVx1Rq9jB2qGoI07OsrKnV5rsdx5hcfVI7vkzh1TDrhsoI0TKGgyPQxDjRnLAyUXNmMef0/vR0tDQ4ci8kAkxKptsYMDpJzkul6CYqeIHN6MOwrelpdX0AuLaZ+lqTa1aJkJdboVdzY+idG0jAzlqX1RTQrbjTVzOM8lvhQldKUuklJcNa2qhKPWpTNQtnFqv99mRyvVPRk6iaPEGdd7fQ8n/xNaG/EjkOhiyFN49XHRdOhOQe+ufw1/PDRLrm+2IKqOoWySvSaGxzs7Cn4abcWQ4Pj96ukY3AIIc86lkKWdcItxqs/P+KYtdR+jg5SGW2LwTOowrQuT+zPZkw+h/mSC4uFStn4thxyGQubDwzKsYhUbpOKCoR9+xo0BY8qem+bMVr2koxDDFeT16nBsYw9IOl3S3TbxEMqoD0pKcQEml7/ny9F+wMmvSPZGu5nihQnGp7e9TT25/fjGjYWyLYAp0dN11KkAIAH3HPx0dIDyJUbUWl/DpXetLT3RMewmj5lARkCfEWvWp2OQFPWVgJjx2Yy4Hph2yEAoYFBxrakSlUoq+mCNg1Qg2DltT19+M5DG+U6euNgsU8dUYVCTd2k2wgFRRAYQUpsQnDp/vSGxIqiF3OpYlM3LStCpAvBOVpMnYFPUgYOK3WTc7AgdZNzYLBoVkr1hu8UNJBupkRPu09xiqOqlEaJnkPqFJMaXcv1ayC8+ZKLyaOaMDJ4JkMzFqLoVZncKHu+Aqqr3eJs6Ol+/f1zMHeyan7BwXH/ul3yd//ZD1I3yXUYLFW01E21Ro9OlNB9iWdKV590wi1+1Z8fQUqT1CEB4dYaX4cZToDYpN5TmrGUXTRmbLQ1+mMd357D2VPDnnw1KXpFs6JHJ5bmdI7Au+ep7vu1im1it45tGZ/DistjW9IMpUYv3ozFM34PD1BFT9TonSCpmylSHC3c13UfWjOtuHjjE8Cs9wBZcz/XFCnW8lOxn4/ABX0W7OaNYHZfvYeUos4Ydn9VK0G0UnK9WHKiozFjKwGEbVkydfP5gOjNmuDbljtkdn9QMxhwLEsGypWY2XGa6ilgCkb1oFOkbgoVgZ6TmKEXQaSI8eluVUVPDZ6pohd3pbJOfO2Wnk4ljC4sxhTCkVijdziumwFZEIHrQMlsdEH3rBMCqm7EKXrg8USUEjNTEGpbYapvLWmZtayjk9BQ0fOXV1xe9XpWXD/1ckJ7tDG1GLeAYzEcDFw+BVyPY1t3qMLZ5NnRa/RURU+4bvrHmDwqGpBQJViva4zjr/o7Lo5ZCzGY3uGbNcXdY5sYsIh1bIuFZixlF7mMLd1BRzdnlfo534zF/znue2EwpkYPAHIJSlfNRI+knuqqIaAaPUWPceSpm/mSa7y+NI1dfA+mRC9FitoxWB7Eiq0rcFXbKWgo9aW981IkgsPCn9z5uHVgCxjjQauFFCcyhtVfVVo3U3Y9GThUU4saM6qil7GZTBd7aWcvOlqy0qkuY1syiB4MAu6rZ4/HX8ydiFwmrNGLMzYwKRimupNojR5TlAEngegNVdETHyWmbtp2sE9NEcvakXQqoegxBmScGlM3a3DdFEF/b94PDt0gddMUuFLQQFWk/gnloXNkSHSatZRDAY742kV6TqZToGTXFMDqdX21XIeTOlQX2RxxiAX89grVlMHfPbcDe/uKGNmkPgviqaXPgW0x9Ayqz22vNmFB6x+rpW6WXR6kbgKLLzwJ9/31Rcq+bCsk/q3as6oreqb3AQjfv2rtKp647XK8Y/Z4eQ4miLo8f2zh/1TRy2Vs+R6Nas5ixthWrPrflyljSYKYpDCpbeL7wawI+wd9z7yJuPsTFyhuvxS0PUTOpOiR1hk6hpS6GaPo5csubMvCyr9fiIntoYpMJ77Ee5wSvRQpascj2x5BvpLHtQf3Au1TgKnHRY/JFMcQD3gLMLsyiObCCGTan6/3cFLUGcPqryoD6aNX4UTRC09jbmc7JrSr6WoNGStiGiJI4mDJRXtjRgZ6tI+eqC+5+JQx+L83nQXGwhq9uODuK0tfiSwzqTiRGj3Lr8fTa/SAMACUqZsyGA23t8kv7Y1h8GwxSFnAsuJn78M+euGyr183B5NGNBpSN0NFj36WlLpZS3qYuG+7enwlyfP8oZsC1wntOfztladGlovxfHDBFHzrhrn4yAUnyc9o6uagVqMXR1IVJdhwfo6i6EXHqdf1VVP0fvaxBfibRep52ZavaualouchU+V6/jIwUYka6fj/R4heXiV6BwdUhc9m4bND9zlYchWTj+asjRJJ3XRsC7MnteN/XDRNpmlaJHVTdzLVnxNPKtzqeSSlblLCNKEtF3Hu1OE7bfo/mxS9YtlDY9aWpGVUMCkk3mF/giaZ7Im0YxOZmzzSVz1Nz4a4TedMHYn5J42K3T9V9BySDiqQ5Lo5FDOWjG3Fpss6FsO0jmac2dkul1GFU7puJtXoObWPJUWKEwH3dd2HCY1jcXbXamDuDfFpDylSBPizNxPdvAWX9HHYjdvBsvvqPaQUdcSw+8YQwUrF86SaJIKza+ZMwB8+dRFmjG1RtmnM2IrJQ8ayFCUq69hyHxnSN06QARrYVlP0ntt6KLKslho9izFUXE/2wqIEio7JYtRy3qzoieD5M1ecgq5/vkZT9IzDlqoCJaDTg/6EIpAX5y4cHhlTg7YktaqWlMUJI3z1bVdPAUBokmIylxjRlMX4Np8YmlI3cxkb7z2rUwl4W2Jq9DhPJgGmnwWog6RR0csNTdG7aEaHcT+NWVuOuZbUTYE49YSeis1YJOVQ/90mZiyU0/h99MLfRWpfseIqz9Lnrp2Fy08fK48Xl7qpT0SIZy/SyzEhdVPskyp14rgm0HRtm5ixqIqehRvPnYxr50zAJy45Wdmf6yFGZwsxkJC6OXNCa+x2csSif2ecGYs2fn1y5NBgSb5XkW2H2HS5MUbVC9Nfzc9cQ00N04fdn6QUKY4ZDuQP4MmdT+KdDRNgcQ+Yk6ZtpqgOFzaWu/PxicEucM6QaUt76p3IGFZ/VRkJvkqVaI1eXLiSy9hKoGhbam+4LFHxMoqiZyJ6/me1Nkb392+u7aKwGMPBwTJ+vGqT/zvZJEtm6BXiQYN1slzUUOlperSP3qKZ43DxKR2RMdqa0gMAe4IAcVqQUqjU6BHCbNsMJ40Oa7LodatF0WtpcNDa4GB3cDzRCN6kgmQdK5HsmLZpTuhzV8v4YltTBMtN91m35K9G0OIU16aMLSceyp5XUwooAHQPlPHrW8/HaeN8MiFS/6oRWNO4dKIP+CSI1n6J1L5C2TO0SgifYUGO9dRNHSaFGwiJqCktWtxnnTQkkXmLKGJimVATC4EZy4imLP79g2dLkxxxC1wenxYpYJo0Ejh9vF8f3LVvIH4HVfZPG74DUXfPg4NlrNvRE9kOGDrR09u3CMh+ljHP+Mlj/e+PJEWv1uc6RYoTAcs2L4PLXVy7cwPQeS7QMaPeQ0oxTPCAdy6mewNoHxwbpG9WLzFIcXxiWP1VZRDGBxyFSlijp8cpeuDSmFWJnmOrTcWzjkUCvdBlUs7Ck8BE7CbOdMGEOBMPdczx55BxQvKppNwpalq4XPTmKhJ3TPH/2DafeLznrIm47LSxcpusQdET12FqQPDE+rRGjwZmNmO479MX45o5fiPXhipGJiZMGJHDzsCKX1j0mxS9BpqeRq6dUIBMAXUc0eOIb69AEd+CwazoffryGfjKe85Ulpmug7heScgRRc/1alf0Nu3vx3nTR2P+Sb5LpOALTCP0k0aYTVvoOqcFhITWB+qpm+IaSLt9CqIsi+fV1ISeQrxmuiI8L3AJnae5hQKU6KnbxDurWhE1yraYNH4SNXo6xPPgJaRFCsj2Ck50P5ecOgYAcMbEtshn0om2yteNPhFUiwNseIyaVwVQXdHTr/PkUY146rOXS0Kb2F4hTd1MkUJiaddSnN46FTP2vJaasKQYEp70ZqOXN2Jhnwsr2w2rcWu9h5SiThhWRA/MJ1j7+oooVTxMCow29MluPXDJObbSGsEhNXqAanFOa/QGDQYKtMdercgYghc9GNKVHEro1ECULjerMkLRCwlZSBL/+vJT8LXrzsQ1Z05QrlPGoOgJDvcXcybg0f93oUy9y0sCqV5H22JoaXCkGcNQFT0AGN/eiN29InXTv5c0sBS7yTohIad7FgqQiejpaYICnMerdRRx56C33BD426tOw6imrLJMJx8r/34h/u2GeVWP3ZS1SY0er1n5WDRznDJG01NrWwx//OuLcNOC+B5uNmP42nVn4q6PnYerA3OTOZ3tyJdURU88R4WKF1WKSM/HjFT0/HvysYumKat+5opT8JELpsbW6L1j9nj8+R+uwCVElRYQilNWI1VxypXuQCqWuVLR88xEzxKpm7zqxI9sr2B4LmeMbcHazy3CzedNjXwWcwljx0JTl2tFLc8+RdyEiUx/1+6VzZji/pqmbqZIUR1berdg3f51uJY3A3YWOON99R5SimGEEjJ4yDsbf5XfAO5l0vTNExjD6q+qr+h56NrvpzhN09wJ5XoRRc8CI6TEttTG1lknJFK0Hi4xdTOmebcJpuAl2l5BJ37q9rJGL6bmiAb+uksjVfSyjoUbzp0CxpgS4EozFjJUSaQYw9TRzYpaI8Zsct0UY6TXrZY+egAwsT2HnYdI6iZjSv86QdZo6ia938mKnjn4pRMFI5riUwnjiILsfWg4pt4AXHfLbG/M1NRbrzETEj3aQ1LgvWdNimzz4fOnSgIV31jDJwmjmrOyxYgJlsXQlHVw0Skd6GhpwOavXoNFM8eh5HooVjzMmzwCP/rwOfIdKxoUvZC0MeK66d/P26+dhc1fvUau+zdXnoovvXu23Mb0/IxryxlJiiAiultsrKJnM/kMUPdKodIVYhQ9asbiVpn4MWUHUIxuaUgkXNXMXg5H0ZMp70MU0eKcNwUZ19Vm/bySxpYSvRQpfCztWgoGhqs3rwVOfQfQFG/GlCKFCcvcBZiEfozonwSn7UUA5l7EKY5vDKu/qgx+8LUphuiFypW6nW4CIOrwxHoZ25KkKWMzGewZFb1gvXIQBFKHyzjUZsaifk6Dr6zDlEbOcixVFb2wls7fZ3wAJlM3DTV6ch0RxIt+flrqptif2IdC9GoM4NqbMrJFhef5qZuUoEmiR8gvHaW03U8w6dBxwcmjAQA//PA5kVYAAqePb1WuB73volzTWIupXXPdLVP8ev+nL8bdn7jAeGzAb1Iu2n1UDKmb37phHr5/89nKspacE635MxCGkBzEq0Cm2yees4FSBdM7mnHVGeMl8c+X3UiA71FFT7puVqvRU8eow0S+xfOiE+/4PnpM1i4qih4heo2Z+Mkaj1dX9MR3SS2mRBRi7Wr5AzL1PLhRtRA9ea5DZHpxvfTEuZmMptT1DDW3thX7WYoUJxpcz8W9b9yLBe0zMLZvHzD3pnoPKcUwxKPeHAzyBizqK8FyBuG0vlrvIaWoA4bXX1XmB/Jd+/qRdSxMjGkGrQe3YjZeBD9UvQP8IEO2V7CSFT0RhwhF7x1njJefPfg3lxjHI4KY/+eyk6VZSbS9QnLqpmNFgyhTyhkQtikYH/wvdqUHXDTAC9VO8z4Bv00FENb+MaYGrnrgqDpy1hZMNmcdFCseKq4nXTdpqphoV0BTbCmSUjdNAeo33j8Hd7x3NgDg7WeMR+fIaIPvNZ9bhHv+6kKFjC//20tw76fUfkYmRU/PsNQJr1DaZk1sS7TPb8xYKBBFz5S6qddO0aA5MXUz+LBBIzNU3TQRKnG8gWJFPr8ydbPsQuc04th+2wX/wzjyLSAVvRiCpJOUrBOq9fr9TuqjJxU9MaHCQqJXrUbP9ar30nM9jgbHGlJzciD8LhPji1P29O+Har0ngfD9HKoZS7yip5JNudxwj3SI91pXYVOkOBHxxM4nsKN/B67Pu0DTaGDGonoPKcUwRAENeMSbi48XX4VXHoHMiNX1HlKKOmBYET0GX83YtH8QJ41uigRuIgjSQwURkOqzxuL3rGPJbanr5mA5aokepm766+dIcBxnLCHI0PvO7sSswHBBJz56rEV/pTWEcYobTRE8b/po/Pgj8/F3V52qbKNPltPrZ6rRi1P0CoGi5zsxRtc/ktRNEUQOBCYflmVO3aRjptdOpG6a1ClTgHna+NZEJQsAOloa0JRV1bGxrTnM6fSNQAQZaTAqt5qqpAWyrMY3sCnryOfRr9GLXk+d2NCgWSpDBp4gxqRfh46W0DHURKrFvSq7nCjiguh5kW3EO0ZbUlQ3YzG7bgro703OCdX5Fi1VN0658hU9H/GKnil1MxxjkguvbXgfhoqqit5hpG6K+z5UM5Y4cm6ajAKi98g8CROosKmilyIFfv3ar9GRG4XLX38KmP1+wMlW3yhFCgOWuQswgR3C2EPT4LS8nvbUOwExrP6qskDR68mXMLq5IXY9fYZa9JTK6ooeSeUUAbBjhyYfg8JAwdA0WzQvpzP9NA2Nti7IkJnzuFS0pJq9rBMqIHGKmx5cXTlrnAzcBUHR67Ro4CsCWaUGUCd6hho9ZX+WGjgqzcZrjCZFEDlQrMDz/GNQMt1CrnHYViPct7i+tboOHg07d/HsiOvz35+4AN+56SwA0SBaN6qoVU3JZWzkS/7J+a6b8cGyPJai6MUfR4xBV/RGEkXPRJIo+ZHknih6+rmFil6Ywlo1dVO8lzH3KfKuZ2z5XOjEN8l1k2vKoSB6nsdRKHtGhcwmkz5Jgp4zBPKlQyqxGkPP2Az/8M7TI2MZihmLTWpwh4K/vGgaJo+KZlNQQyvTcgFT+qrMtkgVvRQnOHb078Cq7avwvtZTkXGLwLw0bTPF4eNhbx6K3MF7+wbAuYXsiD/Xe0gp3mQML6IH3/K8VPESZ8f1uEW3v3e0oDTrWEpjZuHQaep9Fbpu+kE3DQCbyM//572hrb4glDZjxj5mQHKNHnXdpIFtEilL2rdpG72+zj9uNaKn7U8oh6RfWng+NSp6AdEbLFXgcg7bUrcVKg2HOWBMMmMBgO/dfDauJe0MhlozZYI0Ywmep3NPGoV3zZ0IQPQuDNeNGFXUeHjfjKWCsuuh5HpGhSkpdVPAlPonSFROU/RoD0BT2iM9nnRcJHWckXRLUqN39tSRuHr2eJw+Pr5ZOBCmRCbV11HkMrY8rm6+k9RHT070EFXK5VzWo5qut9hfyXUjn1GIa1JNOTZBn5wRd+9Xt56PW4PG7XQsuqL35ffMxjVnmtt3iMej1kkYgVPHteLq2eE+xebiOdJJuU7GTbWsgpgOxc04RYrjEXdvuBuMMVy/8w2g4zRgQnVX5hQp4tCPJqzyzsT78DwqfWcgM2ItwEr1HlaKNxHDiugBfuBXrHjG2XFpxhITuEiiZwtFLwxORaBHGycPlkypm/7/wnyBqk2WgTgBUPr9yVqgqq6b4e/UddMx1MT5P8ffSmoaoSw3XCcag+kBYIMt3DxVkxd9f3oa2VDQLOu+XL+PnnYMmcbJqSIRfu4m1OgBwDvPnIAzJ7XL349GqpinKXo66L3Rj5fkhknRFPTR6837RjXtjdH0uc6RjbL1AWCuGTSF0WJ4uqJHzY5MyiNVzMS9biGpmLrq7pHUzXFtOXz/Q+ckNrGn28QpPfojlstYsYpeYo2ePA9Lrut6XE5qmMxYRBP5UiXZgVe8s0eSuqlDbzeht1cQpPJtJ49Ge4yTrPgOOozXVHkeBEkztYABotfdNOkj9lEegptxihTHG0puCfdsvAeXdszD+O1rgfkfHbotbooUGpZ5C9DJ9uOkg51gdj5w4ExxomBYET3GgIrn27lTJU0EUIIkfOEvZuED8zsj2wvCJQLvDFH0ZBAafKfaFgtdN+3wWCKYKbvxtWD+MShRCwmQCChrCX7kTLlNXDePQNHT08ukCbKOREMAACAASURBVAcJQBNdNzVFL+7vj9jH4ahlIvDvL1b8/nbaQSiRSKr7i7OxB1SziFobjycjrO80wUogz7X+DW/M2vA4sK+/CADG4L3BsfE94ryp1OjJFMDovsX7ML4tpyyf1tFCxm0YE03dDA7QOTJM6RNmQAJxkxxJqLaN/h7lMrZctzmr1+iZj+EreprrZmDGIlqUxKVC2oxVJ3paBsFQYOn3TVMe5Tjk5EqgzmbC7zjxvkb2LVKfDyOQpKcinoNwMko9z2qtIYDwO6iUEr0UJzBWbFmB7kI3bujPA9kWYN7N9R5SiuMAD7gL0Mub8Ffl5+EWxyI7MjVlOZEwvIgefMWmVPGUoGnRzHH4uytPxT9cMxP4/9m78zi3yrL/458r22ztdKbtdF+hCzsUSllEFoGWRUAeQFll04r7T9BHFAVFUUBFcXkeQQFBWcQdFGQV9EGWllWgLAXBlkJXOtNOp+1M5v79kXMyZzJJJpPJzJmk3/frldckJycnVzInOefKfd/XTapQxpUn7t7j8Tm7bgZb9NK/SkfSrXbdum760yukx+j1Pnaoa4xe7oIx2XKWYOtitnn0gl3t8iU9lqNFz38LgwUxck3ZAL2P0cvcbmarQyH8Fjt/ioXMGPyTSofLmyTln5S55/+mP3pr0etW4CY91UXqdqFj9PzX/XZzao7BXNN6ZLYEp5fnnUcv9XdCQw0Pff7g9IT3vbXoBbtu+tsYVddVNCAzceytsEo2vT0mGNfukxs4dd6U9H5Xm9FamKvVO5jsB7tAdmvRy1FpMhKxXpMT/3mLadHzX17Pz272HgGZLXqJWO5EL1t38EIF9+neWvR6S4RT8abem/YOdd2UbdevX/41k+smsN9LD6aSvOrcc5uKFKqVGm5LHsJRkUXUvrsL0ZrlRKqXhx2WDJKySvSwVJfJLR3Jbt3MohHj04fOpL6Xwg4J7+TH7wYWrL7pn0j5J8rBE6ngCZqfaKW7bhbUohcYo+edx/SY0y7LyZa/KBrpqgQaPMHKlaBl6moVyOi6ma5OGNhOxrQOQdGIMawqxrrWrd3i6/l82U/4ClHrjatq2dyRfs6gYAtqrvcytV6+RK/v1UDz8fedXC023ccqen8zbvfGTzTeSSd6vVdhyzpGL2t8XetNG13HCu85golevqqbkL11aHxmi16ebeXid8XN9T4F99cT95zIyfOmpP8fmS16ObcRyV1102/Ry9VyHzVLj+PLpauqaem+bnu26Hl/vecKtuj508Rk6hpL2/fn7/aDU7x7l/jMVvLCEr3U+9vbeEeRSvXKu6/w1Kqn+GB8HJHOdpi3MOyQpILc2DEfw3FG60pcZ5y4WvW2GWWV6PkTpm9pzz5Grzfp6RXSXTe9hC9L181gUYZuRUvSlfZ6Vt0EePbi+Tx7yfxuY4r8RNGs64SykBY9XzTQoheMJZjo5euC2DVGL/vyYOXD4Il6tgaQqaNq0xPW527RKz7R85PODV6il6s0ezBnzfYs+Vv0gl03S9Ci18u4wGz7zwf2mNjtdm/8pKq3Fr2grPPoZZswPSOGU+ZNBnqvuhlM9IL3+1fH5uq6WUyLXo73KbjYTz78xCvXxN6ZUlU3u8cW9YqxbPbGo+Zq0YtGeu+6mS7GkqP1P5/0PHre7Vxdv7sKoXRv0YtFLf0aMmUrwFSo4P/Df5/TMWR8pnpLhKErWVSLnmyrbn/5dhKRBB9Y+ijMOBxGzwg7JKkgb9HE3Z3zONsexjXvSrz+WYhsCjssGQTlleiZV4wlmb/qZi6JWPdkqVuLnncu0jXnnNe9M5bZqpX6m6vr5ojaOCNq4t1OhNJj9Cw4l1jma+t5shUcn5RZVQ+6t8TlS6pyFWNJF9Coyt4ymK2r27RRdemxi7216BVTjMVPHtJdNzOeJNjtsqtFr+d28u0fwe6FxYybypQ5vUKmYIuZ/5ZcceJuPPXVwwt+j/wfFN5pbgMKS/T8/R3g5L0nE48aC3Ye12O9zEIn3zp+V1697MiMpL9nnMEfOYKvw/9cZXbd9NOUviQWnb0kh93GqXrb3eK1wmVW3czbopdROTWz62Z1jv9txHq2WGXODeh/NusKTDyzxZyZn/f4oSjj+2F6Ux1Nw6uoiUfZ3JG/Ra+YMXrB931sfaroTq559AoZd3fcnIn8154TuWDBrD7HIlLuWttb+fPrf2bBiNk0bFgJ+54XdkhSga7vOJJ628ShLREs0k58xFNhhySDoKwSPUh1mdza0VlUqfLMIiH+iXk8FklPe5DZopd58u5voz09YXruX/p9wZNH/8Q1c8xUtpPfYMXBzMnIoXtLXN7xcOZvr/ti/wRsWLcuoMGYem5q2ujavDFnxthXtYnuLXo9u252tej5Lzlb6ftgAZ1MwSIhpSjG4r+tucb7ZatkGo9GGFlX+CS4fvKw/N3CE71gPDPHDufVy45i8sjaHutlJtNm1uO1ZEu0qmKR9D4S3Be+d9LuTBtVy5jhmVU3c28rl8wu1fli9/c7P7HJbNHr+ZlL/e1edbMrWSlkjF40YmzOSPQ+sMdEnvva/PRtv4Urc57DQnzi4BmcuNckzthvat71ohnfW8fuPoFFFx1GPBrhuyftzmE7junxmK5xon0Oq9v/cEJDTbdlxYzRq0vEuOqDezBmeOaPAyKV7y+v/4XW9lY+tGoZjJoJ270v7JCkAj3lZvF05ww+1/EIyU2TiTc+TvYBHVJJyirRMyM93qSQrpuXHb8LP/Imroaelen81pyqaKQrAfNbo/xkMJo90evozF+MJXgiVJeIYZY64Ut33cw4ucp2stU1WbRlPYkKJqGFtOhldtvb6CVTwwMtesET9mwn11NH5S/QAV0n3wUU2+v52IhRE4+mW/Qyx/v5iXUsauw0vp7PHDqTH506p8d28rXoBVuaBmOM3iGzx6Sfp5jWE4DG2lRS+ObaTdTEowW1aBdaaKaQxCv7GFJLxxHcxjG7T+ChLxySs/pin1r0Orv/ANMzrq7rXS162btVZz6t//6Y0WMevUiBVTcjZry2amO3ZdXxSLfxwv4PS5nFYQoxoibOd0/aPd3qnquCZSTjuy1o+6ZhXH1yz89Itl4ChQom2GO9z5M/brmYMXol+BiKlCXnHL9++dfsMGwKuy1/Dvb5WPZxEyIlcF3HkUyPrGRm8ziiVauJ1r4WdkgywMrq28QwWr257QpJ9E7bZyrHeBNXQ8+kwT/Ri8csMEbPXyd7pbyuCdPzT68QPBE6Ya9JXH/W3gyrinVV3SygGEvwvmDZ96zPl6/qpvc38xxx45bUezmswKIuQLdWmt5Ovl2RvxTVVUXTLXr+tvz/1eE7jeWs/adxyTE7Y2acf/gsxo+o6bGNfIlQQ232MYnF6q3r5uUn7MZJ3nQfxYyHgq5E7631bQW15kFpE71c6/j7fyHbKKYYS5+6bmaM0cv8jsh86791/K6MqktQFYum99X0DypRv0Uv94Tp/vO/tT7VyuoXr8lct6vrZt9b9HLJ3G9zdZv0ZUtUo/348SH4vvvfCWu9Ik2xjB/SCum6WYrPoUg5enb1s7zy7it8cGsEq6qH3U8OOySpYHd3zuMtN4rzN72I66j1WvWkkpVZokfX3HZFjNFLJ3GBIiwAiWi0a7yXt26uMXqFdt2MRCx9YtlYG+eQ2d27TmWe1uQ7z0m16HlTNOR42flb9FJ/M8foTRmV6sa319TGwLr5T7gSWQp89Hg+7wkzu4oWqq4q1qPr5v+evif7bjeS+uo4Xzt2Z5oyugVmypv4lviksrcWPSAwBrS45wgmpw05JsDOVOj4w4ISvRzvmd/SVEgC21XwpKCwAHr8AJMpuDzddbM9+3dEZtfNE/aaxJPeOMl0i156PG3h8+hBKsnz16nqkej5XTf73qKX6chdxwPQkJHs99Y6l225/94Vs08GHzPGa9Fb15qa47Gr9T31upMFfBFUaouemR1hZi+b2VIzuzDL/Qea2VNm1mFmJ2bcd6aZvepdzhy8qGUw3fbybdTFajl66aMw5wyoGh52SFLBkkS5sWM+B0WWUN88k9jwF7BYS9hhyQAqq0QP6zppKGaMnn+C2dWi1/W3M6NISq5Jjv0Tkt66bvrbiFj3xKJrzFH3dfOdKOequpm5Ti5+16q6jK5jh8wewwMXHMRxXgXI3uKAruQYChs3VYzaRIwWv+um97oOnj2G2xbu1+v4v2K6ofWXnyTE8/z40FvC0pvqeDS9r9UX2qIXK+y5CnnPcoW9XVOdt43en6eY96Av0yuku252FNZ1M6grCe2qXpl0Ll3Ypbcu2jtNqGerNzYws0WvvdOvAtr/Fr0vzJ/N0189nMaM8Z3FTGnSr3n0srTordvoteh5O0OucY0Af/zke/jdx/dL3y72czGUmVkU+AlwJLATcIqZ7ZSx2n+As4BbMh47ErgE2AeYB1xiZo1IRVm3eR33vnEvx1ZPoDbZAfM+EnZIsg24Lfk+Wl0VZ21cg1kn8YYnwg5JBlD/f2IeRMFTgWKqbmYWNElPmB7rGqOXWTEys1XAX+5X3cw1CbO/bmYrQlfLYWbXzXxxR9JjBnMVXckXx/nzZ7F90zDm7zS2x33bNw3rEXM+we6A/ntVl4jSGpiryw+lmDF6kDqp7uq62bcTwPvPP4iX3h7cX6diUWNrsntF0ExdY0CLf57G2gRvN29mUkPPrqrZFNp1s5DkINd+MWvscP7x6pqCxmG5jM9YIXqbMN26FbpJ/fW/G/IlGj1i8/7GAt8RHUmXHhOcu+U+9XdcfTX/Wt7cbd2po2qZNqqONRtTLV3FjNHr+XzWI8mDQItenn3w2/+1KzuOr+cDP3kktS1v1eJa9PJ03fRiyNXdFWCPyQ05t1dB5gFLnXOvA5jZbcBxwIv+Cs65N7z7Mj9AC4D7nHPrvPvvA44Abh34sCWfaRf+pWTbSox8mKqx7Ry+5CnuS87ho1cuAZaUbPsi2bRQx2+SB3EmD/KTje8h3vAEHZ0dxCJllRJIgcrrvxo4F+hP1810C0xgeoVJjamT51F1XqnwQBLYbRvpRC9/kQjwWhgi3bOdXFMC5Gupika6Xm+u87h8J3hVsSgf3Hty7kAzniufYDLjh/zPLx3a7UQ/V/GXQiUCkzz3tXVw+ui6bhN95/K7j+/PS+/0PSH80SlzeoyR+815+/HX59/J21WymEIkmWrSCUTvrw8K77pZSEy5Eq3ZY1PdjJZmFCTJxh8H15e3ID1Gr5Cum971H50yh98/tZyZY4ZlfUzW2DL+P4lohI7OTjZ3JIlFelYhzXzOukQ0/RmoSaTWffgLhwAw//sPp9cZKIXMXXnKvCnpdZOdLtB1s38tev740YNnN3WLIVdynE2F1p6YCCwL3F5OqoWu2MdOzLGulKVO4o2P07hpJHt3/IdTk0eEHZBsQ25IHsGHo/fxvpYI909o4eFlD3Po1EPDDksGQFklesFWsGImH86cTy44vcLnDpvFnlMaOWDmaKDnxMOZ2/AnTM+foBnmMlr0/JPdjHXzjRuLRiKMHlaV3mY2pageCX0bo+evm5n4+DEWW7S3Kh5Nj7Pqz1QN+ew1tbHb2MRCBYv7+HaeMIKdJ4zI+7jMrsHFaPFaOYNTXORTyha9XPvFnCmplhl//8wnV2t2Pl8+agc+/5vnsk4LARldN73XMaGhhk+9b2aPdfsyNjMWNdqTjratnXlbptq95K6uKtY1t2bGd8bWjtJ13cwlmu6J0Pv/3E/0+tV1M2Ns5GNfOrTH2NG+tKhWaItethdV6NdiQY81s4XAQoApU6YUHpmELlr3KpHEOs5YZ7zSOZF/du4cdkiyDXnTjeOBzj25cPNi7mufyq9f/rUSvQpVVr+jBo98xY3RS23BH/cTbNFLxCIcHujaGM3xq7R/gtPR2XsLTTQwLYKvq0Wv8K6bsYjR5J1Ib9qaY/LjQUr04oUUYylFi56X6JVgPvMhIbNrcDFa2lLjFgtt0cvXlTSokGQ61/41c+xw/vTJ9/D5BbN73Ua+Ce5zed8OY3nqq4fnbB0Kbqu315Hv3szY4tEI7clO2tqTPYqrBPn7aW1VLJ3QVSdyJXoD/7taIUl75njfYn58yHyvx42o7vE/ypcg99heZSZ6y4FgV4pJwIpSPtY5d61zbq5zbm5TU1PRgcrgS4z6B9GOGs5qe5NfJI8g/zeUSOldlzySsbaB2c1jePTtR3l53cthhyQDoKxOo4PnAsWM0fMf7590J9LFWHpuyz8Zymyt8k+K/F/vex1bl7HC5w6fRWNtnF0m1nffbr7pFSLG6OGp7lHrvHEwPr9Fpb8FUHy9jtELFmPJcWBKJ3re7b5MDA6pbqrpFr0KOQGsr0md5Pfl5DeTX6Z+2qgCW/SK+Izkkm//2n1yQ0Hd9HK1ZvdHcH/tz2cgs1upn+htaU+mu2Jm40+/UJeIpv8/PVr0kn6r38C16PVl6orMlry+tLB2baP3dfry2a3QqpuLgJlmNt3MEsDJwB0FPvYeYL6ZNXpFWOZ7y6QCRGreJFa3lAXrY2xytfwh+Z6wQ5Jt0GOdO/JC51S+vOEV6uJ1XPPcNWGHJAOgrLpuBhUzRs8/EezMbNHLsi3/ZMg/Qfd1dd30u+LlH1uX2XVz3+1G8fTF83usm+88JxYxRtamKme+u6l7onfjOfN4Y01rybo49radeOD+XC0B/nvX6WDJpUf0uQBJtuI45e5LR+7IdqOHcdiOPQviFOqy43fhun/8m4bawhLnQsfoFaIUY6hytWb3R3D/6C3JKaTqpp/0xP2um+3JHolbkN+iV1cVSyd0mV0WtwxCi17mhO/5ZLboFTPfZb7PZTEN+ZU4j55zrsPMPkUqQYsC1zvnXjCzS4HFzrk7zGxv4A9AI3CMmX3dObezc26dmX2DVLIIcKlfmEXKX9XoB6Cjhq9seImbk0fSRnXYIck2ybiu40iuSvyUU8eey8/fvJ/X1r/G9g3bhx2YlFCZtegFxuj1o+umP16qax69nm+D/1z11dnHn7UX0HUzFokUPHYumefsKGK5W/Tqq+PsNqkh28OK0lurSLaqm5n8l+ycoyYR7VNRBuj+/whjuoSBUFcV45wDpvcrIT9tn6k8+PmDC16/0DF6hSjF/6GYrpu9CYbV248Cebtu+usEWvSSnY5NW5MFjTWrS8TSry9zKobBGKPnK6xFz5uTsx//iP5MyZFNhXzMe3DO3eWcm+Wc2945d5m37GLn3B3e9UXOuUnOuTrn3Cjn3M6Bx17vnJvhXW4I6zVIaUWqlxEb9gr7ra+n1nXyq+ThYYck27A7O/dnlWvgjBWvUx2r5trnrg07JCmx8kr0AteL67rpjdFzvbfobfbGwmXOWZaeMN07eYuacddn3svDXzi4xzayjdHLxW9lPHq38Tz91e5f/LGIpYtd+NU+B0pvLTfB7oC5Xlp/WxeDhXYqpUUvDKVMkkvRNXggum4Gf/wZXp2/xSxfq9EhXsVIv4Kk/92wcUtHQT9U1Aa6ZWZ2z/Vb+ga0Ra8PrXLx9FQt3mOL+Erx94dsu1hwc789bz/+7lUfzUefc9lWJEY/CMlqvrXhWf7U+R6WO42tlPC0E+MXHfNpfO1vnDzuAP76xl95s+XNsMOSEiqrRK+/0ytknths11THmOFVPcbhAbRuTVU4rM84efRPnv0J081SkyVnK5DRl0TPLxAzqi7RY56saMTSJ6ADrfdiLF339zZherHz6HWv7FncNqQ0/H9xKbrWpbvjDtA/dZY31UMu+Z71wiN35NEvvY8mb044fz/fsLm9oERvWGCOvMz1/c/BgI7R60O32GhG181i+P/DbM/X6FXf3G50HXOnjWRKAWNKlejJtiBStYL48CW8d30t9S7JVR0nhh2SCNcnj4SGKXz45UdIRBL87LmfhR2SlFBZJXrBU4FiEr3j56SmITpyl3EAHDJ7DE9cdFjWrlmbcrbopf76Y/TynSz1KdHLMyYtuJ2dxtf3uL+Ueu26Gem9tc1fXMzYH+jewlopXTfLVVfZ/lJ03Sx9i15Qb638+XbtaMQYP6JrIvqYt5+3tHVQU8BULsFumbkSw3xj/UqlkPc2lpGk9adFL9vz7TapgRvPmceXj96x4O0pz5NtQWL0g1gywWUb/sXNycNY7saEHZIIm6mCI65g9KqXOHH4DP78+p9ZtmFZ7w+UslC2iV4xXTdnjBnOG5cfzXZNvU+k3Lol1aLXo+qm33Wzs7Pb7WyiZgWP0fO7bmY7ofa38cSXD+U35+1X0PaK1VtrS/D+XKv6BS2KbtELdg9Vohcqf/8uTdfNlIEovJFZxTa7rufNnPMtk99FudAWvbpEsEWv+3fTTefM46S9Jg2ZfTndopdRHbeYbeT6Vx40q6lP46iHynsjMlAiiZXE65/noOYEic4YP+n4QNghiXTZ4SiYdQRnL/kHUYtw3b+uCzsiKZHyqrrZz2IsfeEnermKsaSrbvbSStBZ4FmUPy9ftsTQPwkaUz/wlbn60nKTe3qF1N+SJHr6qb/PvrBgNvcvWVmSbflvfymqbnYOQDEWgH/89yEFTdjuu/rkPViw87i86/hTr7RuTRY0JUZdoOtmZnGnA2c1ceCsgR2Hk24tLeC99Vsr01U3i/iglrJLL6iLtlS+xOgHsc4Yl254ieuSx7KGEWGHJNLdEZcz5n/25fhIA7977U98bLePMX7Y+LCjkn4q2xa9QieDLlZruutm9ukV2pMOs/wnOtGIESswTr8SaLZftgttFSyFvrTc5Fy1n103g0l8qeYH3JZ88pAZ/OETpZmXKVLCrpsMUNfNySNrC6qM6e9K1fHeK8HGApltIS16wR8nwpgqIN1aWsC6vbXGFaJrLr7itxGkH3SkklliNbH65zi0OQrJWn7W8f6wQxLpaeR0OOB8zn39GXCO65+/PuyIpATKK9Gz4PXBOTHoMUYvMGF6b0lIamxdYW+xX4wl2zYHs1tTn0qi54irtF03i9uGlIZfWKPY/2WQPwZuIKtP5uPvrYW8lmB12b5ODxKGvhRjiUWt3wla1xi90nw3Kc+TSlY16m9EXISvtLzGTzqOYwO9FygSCcV7Psv4+ikct8Xx+1d/z6pNq8KOSPqprE6j/XOBxl7G15TSsIyTUv8EpyPZ2euv0LFI4WP0/EQv9Ba9PjxXzjF6/ey6WRWcR09ngKG6beF+fP3Ynbt1TSzWlSftxtUn78HscfmrYw6Url2p9x0zHti5M8fc5XL7x/bj0uN27n3FAVTIxyUaMSJmXT/IFPE8kRK0CnaLSZ9zqVAWX0tsxDMc3uLYmmzgl5o3T4ayeDUc9R3OXbmMZGc7NzyvKTzLXVklen6qlzn9wEA42JtXKzPx6irG4no9yYlHC58w3e+6me2EZzArT/blhCtn1c1+xhBs0StFgiHZPf7lQ7n//IPyrjNlVC1n7j+tJM9XXx3nuD0mlmRb/VFQi17gx4ZCxugBzJs+kg/vN63IqPqnT/PoRSKpRC/dxNn350t3/+z7Q7NS102pVIlRDxFx8MWWZfyg4wS2MDhTJYkUbebhTJ5xJEe3tvHbV37D2ra1YUck/VBWZ9H+ucBgzCl37RlzafPG6QX5iV9HsrPXLl2fXzCr4FatdNfNLKn3YCZ6fekmmuvcLF22vQTTK2Sb41BKY2x9NWMHdraOIaUvLViFdt381bn7sL5ta39D67d0180C1o1GjEikf0man5iVKkFToieVyGLriTc8xYKWDja0j+G3yQPDDkmkMEd8m4/+dD/+XFfNjS/eyPl7nR92RFKkMmvRSxmMRC8RizAiSxdRP+nqdL2fnOw1dSRzp40s6PmSQ6QYS1/kGp/jvy2FVhzNFJwjMdv/QKQYfelSHOy6ma/QywEzR/P+3Sb0N7R+S7+kgsfoda1XzA8y6R+f+vnVlN5MWR6JRPJLjHqICJ1c0Pw23+34IEmG/nhfEQAapjDtPedzxMZWbnvxZtZvXh92RFKksjq8+q1egzlGL1Mw5ypl/pVM5inGMkR/7c49j15KMWXboXuLXuYYSZFipRO9QsboBfbB2gIqeg4VBbfo9fM7Jd+E6X3aTqS0LYMiQ4XFmok3LGbBhnZWtU/h7s55YYck0jf7fYqFNLA5uZWbNFavbJVlojdyEMbo5RI8ISllNUx/nq19thvV477YEC09mXOMXvqEujjBecg0kbKUSl8qRAZb0csh0evLbyqxSKrqZn+KJvlfSf2tfhwpUcIoMtRUjfkrUZJ8tnklV3acjPZyKTuxKrY/4rssaG3lly/eyIqNK8KOSIowNDOIHPyWnkK7Qw6E4Hi5UlaKO3BWE69ediR7TG7ocd8QzfPyJHqlm15BpGT60nWzWzGWcmhVLnzC9NQYvf5V3SzVPHpdXeFLMH+HyBARrXmd+IinObW5jTe37MD/de4Sdkgixdn+fZzftD+WbOfKhy8MOxopQlmdUY+oiXP/+Qdx+E5jQ4shmNyUei6/eLZKLAzdFr1c42pK2XVTpFT6UmQyUWZdN7uKsRQwRs+ruumPPSxmDHC662Y/vwO/cdwujKiJF1zZVGToS1I17k8Mb4/zmebVXNnxIdSaJ+Vs/LE/YeGWKA+seZp/LP1L2OFIH4VyRm1m3zGzl8zsOTP7g5n1bMbKYcaYYQMZWq+C50Q58rKSG8yqm33Ra4tekdutiumkTwZOIT9ABJOfuqqhvz+ef/gsFuw8lmP36L0wTNTrunnB/Fl86pAZfGBO36e8SM+j1+dHdnfCXpN49pL5xAbry1RkgMVH/pNo9Uq+vvZt/tB+CM+6GWGHJNI/1SM48/3XM629g28/8lW2tLeFHZH0QVhH1/uAXZxzuwGvAF8KKY4+M7N0sjdYBQSGaqKXK6quFr3itlulFj0ZAH1pferWdbMMCgKNqa/mmjPmMqyAeSdjXjGW4dVxPr9gds6eBPmUqkVPpJJYrIWq0fezRyvsuinB5R2nhB2SSEnEJ83lToqGtgAAIABJREFUSzM+yDLa+cVdC8MOR/oglDNq59y9zrkO7+ZjwKQw4ihWqeeQ6s1gJ3o///BcHrgg/0TakPv1p9+fIuNW100ZCH3ZG7t13aywboU1iShV8f59xrq+A0sRkUhlqBpzF1HbymXrVnBJ+1m0UBd2SCIls/9BX2N+bCQ/W/c0by35Q9jhSIGGwhn1OcDdue40s4VmttjMFq9evXoQw8rNT2AGa+jcYCd6h+00lu2beu8imyvP3XlCPeceMJ0fnzKnqOf3q24m1J1LSmh3r9DRpMbaXtcNdt3MN49eOfr4wdtz9cnFfTZ9XVU3SxCQSAWI1r5GfMQznN3cwpIte3CPplOQSmPGF466gYgZV/zjItjwTtgRSQEG7EzazO43s+ezXI4LrHMR0AHcnGs7zrlrnXNznXNzm5qaBircPvG7LZWy6mY+Q3XC9JwtehHjq+/fickjez+hzsZvTdlt0oiiYxPJdM57pnHv5w5kr6mNva4bnEev0roST2qsZc8pvb8H+XRNizA0v5tEBleqAMuoduPU9Zu5uP2ssAMSGRDjGrfjvB1O429VUf7+21Mh2dH7gyRUAzb4xDl3WL77zexM4P3Aoa7Y8owhGexJfofqZMIDlX/WVcW46Zx57D6p4Bo9Ir0yM2aNHV7QuvFAc73GofXkf2HrrRGB+MhHiFat4pKVq/lh+8msJLwpoEQG2hl7X8Af3/gr3964gn3+9k2qDvta2CFJHmFV3TwC+CJwrHNuUxgx9Id/cjNYJznl1qJXCgfOamJEbXzAti+STzw6ND9zQ4X/25zeJdnWWayZ6tH3s1/rVuo2TuLm5KFhhyQyoOLROF8+6HKWx+Nc//x18Op9YYckeYTVJ+nHwHDgPjN7xsx+GlIcRfFb9AZr7FyxRU0Gmn7Nl0o1VCvdDhXpefv0JSDbuKoxdxGzrXxx7Tq+3P5R3JAofSAysPYdvy8LphzGdQ0NLPvTx6B5edghSQ5hVd2c4Zyb7Jzbw7ucF0YcxYoOctXNoUoneVKptG/nN6a+itHDElx8zE5hhyISmmjtUuIjnuWjzc3csfkYlrqyKiAu0i+fn/dFIrFqrhwWh9tOha1l10Fvm6Cfnopg23iid8NZe3PUruPCDkNEQlIVi7L4K4ezYGd9D+RjZkeY2ctmttTMLsxyf5WZ/dq7/3Ezm+Ytn2ZmbV6Pl7Lr9bJNsHZqxv2Rce2dHPjuMP43eWzYEYkMqnF14/j4Hp/goZoEDza/An88Dzo7ww5LMijRK4Jf9X+wplcYag7ZYQz/c9peYYchIjJkmVkU+AlwJLATcIqZZTaBngu865ybAXwfuCJw32vl2utlW1A19s9Y1RouXruGS7Z+hK1oTLlse07f8XRmNc7ikvGTeOflP8PDl4cdkmTYRlOV/hns6RVERKTszAOWOuded85tBW4DjstY5zjgRu/6b4FDTf2Gh7xY/dMkGh/nrPUtvLHhAJ50s8MOSSQU8Wic7x30PdqjMS6YvgPtD18B//pt2GFJgBK9IvjHYR2PRUQkh4nAssDt5d6yrOs45zqAZmCUd990M3vazB42s/cOdLBSmEhiJTXjf8+ubR0cs7aGb3ecGnZIIqGaNmIaX9//6zyX3MBV03aCP34Cli8OOyzxKNErwmBX3RSRwXfTOfO473MHhh2GlK9sB4jMOWNzrfM2MMU5Nwc4H7jFzOp7PIHZQjNbbGaLV69e3e+AJb9N7ZuomfQrhnd2cMWqtXy6/bNsojrssERCt2DaAk7b8TR+ZRu5d+TYVHEWVeIcEpToFaFrwvSQAxGRAXPgrCZmFjjBukgWy4HJgduTgBW51jGzGDACWOec2+KcWwvgnHsSeA2YlfkEzrlrnXNznXNzm5qaBuAliM85x9ce/RrRxGp+sPodfrTlw7zspoQdlsiQccFeF7Db6N24eEQNb3RuhltPhq2tYYe1zVOiVwS/x+a2WnVTRER6tQiYaWbTzSwBnAzckbHOHcCZ3vUTgQedc87MmrxiLpjZdsBM4PVBiluyuP3l27n733fziXfXs7x1b25PHhx2SCJDSjwa57sHfZdYLMEF03egbdWL8PuFqsQZMiV6RdA8eiIiko835u5TwD3AEuB259wLZnapmfm1+K8DRpnZUlJdNP0pGA4EnjOzZ0kVaTnPObducF+B+F5Y8wJXLLqCA7YkOfTdOr7Sfg7Ze92KbNvGDxvP5e+9nFc3vcO3dj0UXvoz/O2ysMPapsXCDqAcpbtuKk0WEZEcnHN3AXdlLLs4cH0zcFKWx/0O+N2AByi9at7SzPkPfY7RnZ18e806PtR+icblieRxwMQDWLjbQq557hr23Hk+x//juzByOsw5PezQtklKVYowWBOmJ6L694iIiISh03Vy0f9dxKrWlXzvrbdoOOJKjcsTKcDHd/84+4zfh8u2/JuXp+8Pd3wGXrk37LC2SWrRK0J6wvQBTvQe+/KhtLUnB/Q5REREpKfrn7+eh5c/zJfWvMuuOxwPc86A2+/q/YEiZWbahX8p+TYteji105dwgtvEz90kdrv5dE7dehHPuBkl2f4blx9dku1UOjUZFSE9YfoAl90cWZdgYkPNgD6HiIiIdHfbS7dx9VNXc+TmJKckxsLRV3VVYhORXrnkMDa/dSrEm1k4bhz/thFcn7iS7Syz+LAMJCV6RYhoegUREZGKdOtLt3LZ45dxsKvhstVrsQ/eBFXDwg5LpOwk26bRtvw0OqtXcdq4qbREotyUuJwxvBt2aNsMJXpFiKjqpoiISMW59aVb+dbj3+LgSD1XvfEy8WN+CGN3DjsskbKV3LgTbctPo6N6DSeMnUEsspFfJK5kOJvCDm2boESvCJpeQUREpLKkk7zYSK567XniR1wOu38o7LBEyl4q2TudLdXrOHbsDoyNvsU18atI0B52aBVPiV4R/GkVBnqMnoiIiAw8P8k7pGosV736DPGDLoR9Px52WCIVI7lxR9qWn86mqmaOGbsjO8eXcFX8fzE0ofpAUqJXBL8lTw16IiIi5e2WJbekkryayXzvpUXE9zkPDr6w9weKSJ8kN+5I21un01K1kWPG7sh7449zceyXgAs7tIqlRK8IfkueWvRERETK1y1LbuHbT3yb9w3bju+9+Ajx3U+BBd/WL7kiAySV7J3BukQb/zV2Jv+VuJdvxa4jiqYTGwhK9IqgYiwiIiLlq9N18rPnfpZK8kbM5rv/eoj47KPh2B93jc8QkQGR3LgDbW+dwcpEOx8YO4uDqx/mf+JXU8XWsEOrOPo2K4LfkKc8T0REpLysbVvLJ+7/BD98+occOWp3vvvsg8SnvRdOvB6isbDDE9kmJDfuQNvyD7M63sn7J0wlOuxFbkpcTj2tYYdWUZToFSHddVOZnoiISNl4/O3HOfHOE1n0ziK+sv1JXPH0vcTH7w6n3Arx6rDDE9mmJFtn0/rvT7N561g+N240941exS+rLtU8eyWkRK8I6ropIiJSPjo6O/jx0z/mo/d+lGHxYdwybj4feuD72Kjt4fTfQdXwsEMU2Sa59tFsevPjbF37Hn49YhiXTuzgh8O+xna2IuzQKoISvSK0tacGjEZUjEVERGRIe6f1Hc6951yuee4ajpk6n19viDD7kf+BXU6Ac++F2pFhhyiybXMxtqw6hk3LPszS2DA+M7GahSO/xR62NOzIyp4SvSJMaqwF4KBZo0OORERERHJ5eNnDnHTnSSxZt4Rv7XA2lz35Z2rffBTe/wP4r5+pJU9kCElu3ImW1z9H++aJXDZmGDtO/BEHRx8PO6yyplHHRfjyUTvwucNmMqZe/flFRESGmv+0/IcfP/1j7n7jbmY3zuY7w3Zh+l+/CY1T4SP3w/jdwg5RRLJwHQ28++YnaWj6C38Z9U8mTP8NZ699mDvf/ShraAw7vLKjRK8Iw6vjDK+Ohx2GiIiIBKzatIprnr2G37/6e+LROB/d4XQ+9uoTVD31fdjpA3Dsj6C6PuwwRSSvKOtXH0t162zaxt3Gb8etY0bjZcxZsycPtHyITqJhB1g2lOiJiIhIWWve0swNz9/AzUtupqOzgxNmHM/HEuNp+vsPoHUVHPVd2PsjmhdJpIxs3jSbN1//KhPq/05z0z0snfgcc0Y+R/OqY4Gjww6vLCjRExERkbLU1tHGLUtu4brnr2Pj1o0cNfkQPtlRw+RHboLW1dC0A5z8K5gwJ+xQRaQoEVa0HAwtB7BX4+2sGf0M66bewadufZRPH/IdZo/bK+wAhzQleiIiIjKopl34l349PpJYSWzEU8QbniQS20jtxsl8cl0N57z+S6J0cn/nHvwi+RH+b9ku8MMVgEq1i5S3GE++eyrD1x/Fe0f/nKcaV3LSX8/kwGHTOHaXszho5jFURavCDnLIUaInIiIiQ55FNxKrf5b4iKeI1rwFLkJT6yg+1tzGh7Y+Qour4abkfG5KHs6bblzY4YrIANjgGrhr9ed59oR6bnrwC/yx+TUefvzrDH/8Gxw5eg7HzPk4u4+fh6mbNqBET0RERIYq66B+2DMMG/E4G4ctx5lj6hY4YU0zx7ZuYFTnG7zWOZ6vJM/mD8kDaKUm7IhFZBCMmPZePn3OY3zined5fNGPuWPFP7hj1SJuv+9JpkVqOGbKYbx/zieYUD8p7FBDpURPREREBo9zNNLCWFvPOFvHaGumkQ002kZG0MKm6nd5q3Yj/67eypIaaIsYVR1JTmhu5cANji1bJvGS25lvdU5liZvCEjcFp2mBRbZJ0XG7sP8xP2X/ziStS+/n3meu4Y71L/KjN+7kR2/cyYxIDXsP3469J+zP3FnH0tgwLeyQB5USPRERESkd56B1Dax5GVa/BGtfhw0roOVt2PA2bHiHp6u3ANAOvJRIsKimiieqa3iquoq2SKrL1ZgtcXZsqaN+40TWt+7KbZ3T+BENgLpkiUiGSJS6WQs4ftYCjt+6ibeeu4W/vvRrnmh7mz92/Itbm1+AJT9jZhL2TjSx9+hd2HPywYwcNROGjYXaURCpvGkblOiJiIhI3zkHLW/B6pdhzSuppG6197dtXdd6sRq21o/njfomXh+3Pa9NnsWdb6/l3cQWNiU2gjkAklvGkGzejmTrdiQ3TWdDcjivhfTSRKSMJWqZOPcjnDv3I5wLtLes4IWld7Fo+T9Y1Pwqf+hYzS0r/wYr/8aojiTbt7ezXXsH21s12yca2L5mLCOHT4TakVBVD1XDIDEs9bdqOCSGp65Xj0hdEsOG7NQtSvREREQGgJkdAVwNRIGfO+cuz7i/CrgJ2AtYC3zIOfeGd9+XgHOBJPAZ59w9gxh6d8l2WPdvr4XuZVjzaur6mldh60Y6gXWRCKvqGlnVOJlV2+3JyurhrIxFWeXaeXvLOpZtWE7SvQ1bILI1QkdVI8ktk+ncMIbOzRNIbpqOSw4P7SWKSHnpe+Xe8cAHvesdDK95ldG1LxCpWsWrifU8XbeR9mgnsBE6NzJi3VKmrmxnbLKDsR0djO1IMiaZuoztSNKUTFLtvB+pnNFCHS2ulmbvbwt1rHPDWcsI1rrhrHUjWEs9t/2/Y6CuCWoaITLwXc6V6ImIiJSYmUWBnwCHA8uBRWZ2h3PuxcBq5wLvOudmmNnJwBXAh8xsJ+BkYGdgAnC/mc1yziWLjcc5R4froL1jK+1bW2jf3ELHlmbat26gfctGtrStZfOGt2lrXcXmTavZvGktmze/S9uWFja3t7IxYrREIqlLopaWqmo2TJlEC46W5BaSdHrPtA42rSPSFmF09WjG1I5hRsNM5k9bwPYjtmf7hu2ZWj+VHb7yQLEvRUSkn2JsaNuRDW07BpY5LNZCpGolkcQqtlatYm1iDZFYC5GaZoi099hKtDNKVTJGdWeE2iQM64T6zk4aOjcxsrOZkW4L4zrb2I5Oqjsd1c6x6PrvUNPpqAISVSOI1zQSrxlJvGYksdpRxOuaiNc2Eakd2dWKmAi0KCbqUi2KBb9SERERKbV5wFLn3OsAZnYbcBwQTPSOA77mXf8t8GNL1QQ/DrjNObcF+LeZLfW292iuJ3tl7Yu87xe7kQSSOO9v6tKJo6OYbkUJIBEHGogRoT5eR311I/VVDYyoGs7keD31VfXUJ+ppqm1iTO0YxtaOZUztGEZVjyJageNdRKRSGa5jBMmOESRbZ2Xc5yCyhUisBYs1Y/GW1PVoK5ujbTRH27BIGxZrw/zr0SRQ413y2QysgC0rYAvwbmppxDmiQNT7G3EQwxFxEMUV/KrKKtF78skn15jZm2HHUYDRwJqwgyiC4h485RgzKO7Bti3HPbUUgYRoIrAscHs5sE+udZxzHWbWDIzylj+W8diJmU9gZguBhd7NjX87+18vlyb0QVOu+3dQub+Gco8fyv81lHv8UP6voRzjL+gYWVaJnnOuKewYCmFmi51zc8OOo68U9+Apx5hBcQ82xV3WsjWhZf4Mm2udQh6Lc+5a4Nq+hzY0VMJ+Uu6vodzjh/J/DeUeP5T/ayj3+PPRxDMiIiKltxyYHLg9CViRax0ziwEjgHUFPlZERCQvJXoiIiKltwiYaWbTzSxBqrjKHRnr3AGc6V0/EXjQOee85SebWZWZTQdmAk8MUtwiIlIhyqrrZhkp1640invwlGPMoLgHm+IuU96Yu08B95CaXuF659wLZnYpsNg5dwdwHfBLr9jKOlLJIN56t5Mq3NIBfLI/FTeHsErYT8r9NZR7/FD+r6Hc44fyfw3lHn9O5lzhlVtERERERERk6FPXTRERERERkQqjRE9ERERERKTCKNErgJldb2arzOz5wLLdzexRM/uXmd1pZvWB+3bz7nvBu7/aW/6Qmb1sZs94lzFDJW4zOy0Q1zNm1mlme3j37eWtv9TMfuhN6FsOcQ/l9ztuZjd6y5eY2ZcCjznCi3upmV04kDGXOO43vOXPmNniIRZ3wsxu8JY/a2YHBx4zaPt3CWMe7H17spn9zfufv2Bmn/WWjzSz+8zsVe9vo7fcvPdyqZk9Z2Z7BrZ1prf+q2Z2Zq7nlG2DmX3D20eeMbN7zWxC2DH1hZl9x8xe8l7DH8ysIeyY+srMTvI+151mVjYl5gf7WFlq2Y4H5STXcaGcmFm1mT3hHWNfMLOvhx1TyTnndOnlAhwI7Ak8H1i2CDjIu34O8A3vegx4Dtjduz0KiHrXHwLmDsW4Mx63K/B64PYTwH6k5na6GziyTOIesu83cCpwm3e9FngDmEaqaMNrwHZAAngW2Gmox+3dfgMYPUTf708CN3jXxwBPAhE3yPt3CWMe7H17PLCnd3048AqwE3AlcKG3/ELgCu/6Ud57acC+wOPe8pHA697fRu9642C9Dl2G3gWoD1z/DPDTsGPqY/zzgZh3/Qr/M1BOF2BHYPZgf6/0M+ZBP1YOwGvocTwop0uu40LYcfXxNRgwzLseBx4H9g07rlJe1KJXAOfc30lVRAuaDfzdu34fcIJ3fT7wnHPuWe+xa11I1dL6GHfQKcCtAGY2ntSB+FGX+iTcBHxgYCJOKUXcYehj3A6os9TcWTXAVqAFmAcsdc697pzbCtwGHFcGcQ+6Psa9E/CA97hVwHpg7mDv36WIeaBiy8c597Zz7inv+gZgCTCR1L55o7fajXS9d8cBN7mUx4AG771eANznnFvnnHuX1Os9YhBfigwxzrng90cdWSaGH8qcc/c65zq8m4+RmvOwrDjnljjnXg47jj4a9GNlqeU4HpSNPMeFsuEdozZ6N+Pepay+g3qjRK94zwPHetdPomty21mAM7N7zOwpM/vvjMfd4HVR+epAdhHLI1fcQR+iK2GaSGryXt9ywvkg9zVu31B9v38LtAJvA/8BvuucW0fqvV0WePxQe79zxQ2pL8d7zexJM1s4mMEG5Ir7WeA4M4tZal6yvbz7hsL+3deYfaHs22Y2DZhD6pfPsc65tyF10CfV8gi59+Ohsn/LEGJml5nZMuA04OKw4+mHc0i1ZMvA03fJEJJxXCgrZhY1s2eAVaR+iCy715CPEr3inQN80syeJNVkvdVbHgMOIHXAOgA43swO9e47zTm3K/Be73LG4IYM5I4bADPbB9jknPP7jGc7gQzj146+xg1D+/2eBySBCcB04AIz246h/37nihvgPc65PYEjvcceOMgxQ+64ryd1IrAY+AHwT1Lzkw2F97uvMUNI+7aZDQN+B/y/jJaYHqtmWebyLJcKZmb3m9nzWS7HATjnLnLOTQZuBj4VbrQ99Ra/t85FpD6fN4cXaW6FvIYyo++SIaIPx4UhyTmXdM7tQao1fp6Z7RJ2TKWkCdOL5Jx7iVQ3TcxsFnC0d9dy4GHn3BrvvrtI9cF+wDn3lvfYDWZ2C6mT5puGSNy+k+neKrac7l1RJgErBjLGbIqImyH+fp8K/NU51w6sMrNHSHXLW0b3Vpuh9n7nivt159wK77GrzOwPpN7vv/fYeAhxe12rPuevZ2b/BF4F3iXk/buImEPZt80sTupgfrNz7vfe4pVmNt4597bXNXOVt3w52ffj5cDBGcsfGsi4JXzOucMKXPUW4C/AJQMYTp/1Fr9XVOj9wKFeF/Ahpw//g3KR6ztGBlGO40JZcs6tN7OHSA0nKMsCOdmoRa9I5lW5M7MI8BXgp95d9wC7mVmtN47pIOBFr/vVaO8xcVIHhUHfkfLE7S87iVRfdyDdHWuDme3rdQ/7MPCnQQ2avsddBu/3f4D3WUodqYIVL5EqzDHTzKabWYJUAnvHUI/bzOrMbLj3mDpSicuQeb+9z2Odd/1woMM59+JQ2L/7GnMY+7b33lwHLHHOXRW46w7Ar5x5Jl3v3R3Ah739ZF+g2Xuv7wHmm1mjpSp0zveWyTbKzGYGbh5L6nuwbJjZEcAXgWOdc5vCjmcbMiSOlduyPMeFsmFmTeZVyjWzGuAwyuw7qFeDXf2lHC+kWoreBtpJ/Yp0LvBZUhWGXgEuByyw/unAC6ROvq70ltWRqpr3nHff1XjVOIdQ3AcDj2XZzlzvtbwG/Dj4mKEa91B/v4FhwG+82F4EvhDYzlHe+q8BFw2l/TtX3KQqnz3rXV4YgnFPA14mNVj8fmBqGPt3KWIOad8+gFS3qOeAZ7zLUaSqCj9AqqXxAWCkt74BP/He038RqORHqqvqUu9y9kDvJ7oM7Qup1oDnvX3rTmBi2DH1Mf6lpHpi+J+Lsqoa6r2G473voy3ASuCesGMqMO5BPVYOQPw9jgdhx9TH+LMeF8KOq4+vYTfgae81PA9cHHZMpb74JxQiIiIiIiJSIdR1U0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERERGRCqNET0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERERGRCqNET0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERERGRCqNET0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERERGRCqNET0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERERGRCqNET0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERERGRCqNET0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERESkLZvaGmR0Wdhwi5UCJnkiZMrOvmdmvwo5DRES2LWZ2qpktNrONZva2md1tZgeEHZeIdKdETyQH71fDlWZWF1j2ETN7KMSwCmZmDWb2v2b2jpltMrN/mdmZBTxuJzO7w8yazWyDmT1oZvsORswiIjK0mdn5wA+AbwFjgSnA/wDH9XE7sUKWDRYzi4b13CIDRYmeSH4x4LP93YilDNrnzcwSwP3AVGA/YATwBeBKM/tMnsdtDzwC/AuYDkwA/gjcZ2bzBjpuEREZusxsBHAp8Enn3O+dc63OuXbn3J3OuS+YWZWZ/cDMVniXH5hZlffYg81suZl90czeAW7Itsxb9/1m9oyZrTezf5rZbjniyfl83v3/7bU4rvB+qHVmNsO77xfej6F3mVkrcIiZHW1mT5tZi5ktM7OvBbY1zXv82d5975rZeWa2t5k958X644F670WKoURPJL/vAJ83s4Zsd5rZ/ma2yGv9WmRm+wfue8jMLjOzR4BNwHbesm96B66NZnanmY0ys5u9A8siM5sW2MbV3gGlxcyeNLP3Fhj3GaR+ZT3JOfdv70D8V+AzwDfNbHiOx30NeNQ5d5Fzbp1zboNz7ofAr4ArCnxuERGpTPsB1cAfctx/EbAvsAewOzAP+Erg/nHASFI/Qi7MtszM9gSuBz4GjAKuAe4IJnCFPJ+ZHQGcDxwGzAAOyvL4U4HLgOHA/wGtwIeBBuBo4ONm9oGMx+wDzAQ+RKpl8yLvOXYGPmhm2Z5HJBRK9ETyWww8BHw+8w4zGwn8BfghqYPRVcBfzGxUYLUzSB3MhgNvestO9pZPBLYHHiX1K+ZIYAlwSeDxi0gdwEYCtwC/MbPqAuI+HLjbOdeasfx3QC2pA2Oux/0my/LbgfcW+NwiIlKZRgFrnHMdOe4/DbjUObfKObca+Dqp452vE7jEObfFOdeWY9lHgWucc48755LOuRuBLWQ/buV7vg8CNzjnXnDObfLuy/Qn59wjzrlO59xm59xDzrl/ebefA26lZ4L4DW/de0klhrd6z/8W8A9gTo73RmTQKdET6d3FwKfNrClj+dHAq865XzrnOpxztwIvAccE1vmFd5DpcM61e8tucM695pxrBu4GXnPO3e8dOH9D4CDhnPuVc26t9/jvAVXA7AJiHg28nbnQe441QOZryfs4b1mUVMIpIiLbprXA6Dxj6SbQ9aMm3vUJgdurnXObMx6TuWwqcIHXFXK9ma0HJmdsp5DnmwAsC9wXvJ51mZntY2Z/M7PVZtYMnEfquBi0MnC9LcvtYVmeRyQUSvREeuGcex74M3Bhxl2ZBxi82xMDt7MdWAo+SJjZBWZ1IrMsAAAgAElEQVS2xOsaup7UWLvMg042a4DxmQu9g/NoYLWZneZ1H91oZnfne5y3zHn3i4jItulRYDOQ2Z3Rt4JUouab4i3zuSyPyVy2DLjMOdcQuNR6P6b25fneBiYF7ptcwHPfAtwBTHbOjQB+CliWx4mUBSV6IoW5hFR3kmASl3mAgdRB5q3A7WwHtYJ44/G+SKr7SaNzrgFoprCDzv3AkRaoGOo5AWgHnnDO3eycG+Zdjgw87qQs2/sg8Jhzbmsxr0VERMqf1xPlYuAnZvYBM6s1s7iZHWlmV5Lq6vgVM2sys9Heun2dBuhnwHle65qZWZ1XJCXb2PJ8z3c7cLaZ7Whmtd59vRkOrHPObfYKkJ3ax9hFhhQleiIFcM4tBX5NqpiJ7y5glqXmE4qZ2YeAnUi1/pXCcKADWA3EzOxioL7Ax/4SWE5qTN8070C8gNR4wiu9g3U2Xwf294rIjDSz4Wb2aeBsuo8dFBGRbZBz7ipSRU6+Qur4tAz4FKkKzd8kNbb9OVLVm5/ylvVl+4tJ/bD6Y+BdYClwVo7Vcz6fc+5uUse8v3nbeNR7zJY8T/8J4FIz20AqMby9L7GLDDXmXNENDiIVzczeAD7inLvfuz0ZeJVUy9bB3rIDgKtJVfRaCnzWOfd/3n0PAb9yzv08sM1uy8zsm8Ak59xZ3u3DgJ8652ZYak6fa0m1sLUC3yd1EPqIc+5+r+zzDOfc6TniHwl8m1QXm1Gkxth9GbjCOdeZ53XvAlwOHAjUARuAU7yDpoiISNkxsx2B54GqPMVkRCqKEj2RbYCZxUkVfnkLOMsV+ME3s0nAY6Qqol03gCGKiIiUlJkdT6o6dh1wI9DpnMs1vlCk4qjrpsg2wKv4eQLwGoVV7fQftxw4EhhvZqokJlIgM7vezFaZ2fM57jcz+6GZLfUmW94zcN+ZZvaqdzlz8KIWqTgfI9W99DUgCXw83HBEBpda9ERERErMzA4ENgI3Oed2yXL/UcCngaNITcB8tXNuH6/L9WJgLqliTk8Ceznn3h204EVEpCKoRU9ERKTEnHN/B9blWeU4Ukmgc849BjSY2XhgAXCfc26dl9zdBxwx8BGLiEilyTXh5ZA0evRoN23atLDDEBGRAfbkk0+ucc41hR3HAJpI93k2l3vLci3vwcwWAgsB6urq9tphhx2KCmTVhi2sbMmcwxrG1lczZnhVUdsUEZGBU+gxsqwSvWnTprF48eKwwxARkQFmZm+GHcMAyzYfpsuzvOdC564lVZmXuXPnumKPjw8sWcmnb32aTVuT6WW1iSg/OmUOh+44tqhtiojIwCn0GKmumyIiIoNvOTA5cHsSsCLP8gFz8Owx7DG5AUtuBddJbSLKHpMbOHj2mIF8WhERGWBK9ERERAbfHcCHveqb+wLNzrm3gXuA+WbWaGaNwHxv2YCJRoxfnrsPTa/eScPyR/jRKXP45bn7EI1ka1wUEZFyUVZdN0VERMqBmd0KHAyMNrPlwCVAHMA591PgLlIVN5cCm4CzvfvWmdk3gEXepi51zuUr6lIS0YhRu/51ate/ru6aIiIVQomeiIhIiTnnTunlfgd8Msd91wPXD0RcIiKy7VDXTRERERERkQqjRE9ERERERKTCKNETERERERGpMEr0REREREREKowSPRERERERkQqjRE9ERAbVzTfDtGkQiaT+3nxz2BGJiIhUHk2vICIig+bmm2HhQti0KXX7zTdTtwFOOy28uERERCqNWvRERGTQXHRRV5Ln27QptVxERERKR4meiIgMmv/8p2/LRUREpDhK9EREZNBMmdK35SIiIlIcJXoiIjJoLrsMamu7L6utTS0XERGR0lGiJyIig+a00+Daa2HqVDBL/b32WhViERERKTVV3RQRkUF12mlK7ERERAaaWvREREREREQqjBI9ERERERGRChNqomdmDWb2WzN7ycyWmNl+YcYjIiIiIiJSCcIeo3c18Ffn3IlmlgBqe3uAiIiIiIiI5Bdaomdm9cCBwFkAzrmtwNaw4hEREREREakUYXbd3A5YDdxgZk+b2c/NrC5zJTNbaGaLzWzx6tWrBz9KERERERGRMhNmohcD9gT+1zk3B2gFLsxcyTl3rXNurnNublNT02DHKCIiIiIiUnbCTPSWA8udc497t39LKvETERERERGRfggt0XPOvQMsM7PZ3qJDgRfDikdERERERKRShF1189PAzV7FzdeBs0OOR0REREREpOyFmug5554B5oYZg4iIiIiISKUJdcJ0ERERERERKT0leiIiIiIiIhVGiZ6IiIiIiEiFUaInIiIiIiJSYZToiYiIDAAzO8LMXjazpWZ2YZb7v29mz3iXV8xsfeC+ZOC+OwY3chERqQRhT68gIiJSccwsCvwEOBxYDiwyszucc+n5Yp1znwus/2lgTmATbc65PQYrXhERqTxq0RMRESm9ecBS59zrzrmtwG3AcXnWPwW4dVAiExGRbYISPRERkdKbCCwL3F7uLevBzKYC04EHA4urzWyxmT1mZh/I8biF3jqLV69eXaq4RUSkQijRExERKT3LsszlWPdk4LfOuWRg2RTn3FzgVOAHZrZ9j405d61zbq5zbm5TU1P/IxYRkYqiRE9ERKT0lgOTA7cnAStyrHsyGd02nXMrvL+vAw/RffyeiIhIr5ToiYiIlN4iYKaZTTezBKlkrkf1TDObDTQCjwaWNZpZlXd9NPAe4MXMx4qIiOSjqpsiIiIl5pzrMLNPAfcAUeB659wLZnYpsNg55yd9pwC3OeeC3Tp3BK4xs05SP8heHqzWKSIiUggleiIiIgPAOXcXcFfGsoszbn8ty+P+Cew6oMGJiEjFU9dNERERERGRCqNET0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERERGRCqNET0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERERGRCqNET0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERERGRCqNET0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERERGRCqNET0REREREpMIo0RMREREREakwSvREREREREQqjBI9ERERERGRCqNET0REREREpMIo0RMREREREakwSvRERETk/7N35/FRVff/x1+fhB2kIKhFIOCC1h0t1brUVnBBq+K+oUJRERAFja1a+mv7tWJtS9gRjKAgxBW1olIRcW2tVlRcABVEAgjKjkBYk8/vjzvRSTIJE8jMncy8n4/HPGbunXvPfGYgyzvn3HNERCTNKOiJiIiIiIikGQU9ERERERGRNKOgJyIiIiIikmYU9ERERERERNKMgp6IiEgCmFlXM/vczBaa2Z0xnu9pZqvMbE7kdn3Ucz3MbEHk1iO5lYuISDqoE3YBIiIi6cbMsoExwBnAMuA9M5vm7vPKHfqEu/cvd+7ewJ+AToAD70fOXZeE0kVEJE2oR09ERKTmHQ8sdPdF7r4deBzoFue5ZwEz3X1tJNzNBLomqE4REUlTCnoiIiI1rzWwNGp7WWRfeReb2cdmNtXM2lbnXDPrbWazzWz2qlWraqpuERFJEwp6IiIiNc9i7PNy288D7d39aOAVYFI1zsXd8929k7t32mefffaoWBERST8KeiIiIjVvGdA2arsNsDz6AHdf4+7bIpsPAj+N91wREZFdUdATERGpee8BHczsADOrB1wBTIs+wMxaRW2eD8yPPJ4BnGlmzc2sOXBmZJ+IiEjcQp91MzIz2Wzga3c/N+x6RERE9pS77zSz/gQBLRt4yN3nmtndwGx3nwbcYmbnAzuBtUDPyLlrzewvBGER4G53X5v0NyEiIrVa6EEPGEDwV8ymYRciIiJSU9x9OjC93L4/Rj2+C7irknMfAh5KaIEiIpLWQh26aWZtgF8D48OsQ0REREREJJ2EfY3ecOB3QEnIdYiIiIiIiKSN0IKemZ0LrHT393dxnNYJEhERERERqYYwe/ROBs43s8XA40BnM5tS/iCtEyQiIiIiIlI9oQU9d7/L3du4e3uCaadfdferw6pHREREREQkXYR9jZ6IiIiIiIjUsFRYXgF3fx14PeQyRERERERE0oJ69ERERERERNKMgp6IiIiIiEiaUdATERERERFJMwp6IiIiIiIiaUZBT0REREREJM0o6ImIiIiIiKQZBT0REREREZE0o6AnIiIiIiKSZhT0RERERERE0oyCnoiIiIiISJpR0BMREREREUkzCnoiIrJbCgqgfXvIygruCwrCrkhERERK1Qm7ABERqX0KCqB3bygqCrYLC4NtgO7dw6tLREREAurRExGRahs06IeQV6qoKNgvIiIi4VPQExGRaluypHr7RUREJLkU9EREpNpycqq3X0RERJJLQU9ERKpt8GBo1KjsvkaNgv0iIiISPgU9ERGptu7dIT8f2rUDs+A+P18TsYiIiKQKzbopIiK7pXt3BTsREZFUtcsePTM7yMzqRx7/ysxuMbNmiS9NREREREREdkc8QzefBorN7GBgAnAA8GhCqxIREREREZHdFk/QK3H3ncCFwHB3vxVoldiyREREajcz62pmn5vZQjO7M8bzt5nZPDP72MxmmVm7qOeKzWxO5DYtuZWLiEg6iOcavR1mdiXQAzgvsq9u4koSERGp3cwsGxgDnAEsA94zs2nuPi/qsA+BTu5eZGZ9gb8Dl0ee2+LuHZNatIiIpJV4evR+A5wIDHb3r8zsAGBKYssSERGp1Y4HFrr7InffDjwOdIs+wN1fc/eiyOY7QJsk1ygiImlsl0Ev8tfHO4APIttfuft9iS5MRETSVEkJvPgijBsXdiWJ1BpYGrW9LLKvMtcB/4rabmBms83sHTO7INYJZtY7cszsVatW7XnFIiKSVuKZdfM8YA7wUmS7o64XEBGRatu6FcaPhyOPhHPPhREjoLg47KoSxWLs85gHml0NdAL+EbU7x907AVcBw83soAqNuee7eyd377TPPvvURM0iIpJG4hm6+WeCISjrAdx9DsHMmyIikqYKCqB9e8jKCu4LCvagsdWr4S9/CVZVv+EGqF8fpkyBjz+G7OwaqjjlLAPaRm23AZaXP8jMTgcGAee7+7bS/e6+PHK/CHgdODaRxYqISPqJZzKWne6+wazMHydj/lVSRERqv4IC6N0biiJXjxUWBttQzQXSFyyAYcNg4kTYsgXOOQdyc+G008BidXillfeADpHr2r8GriDonfuemR0LPAB0dfeVUfubA0Xuvs3MWgInE0zUIiIiErd4evQ+NbOrgGwz62Bmo4C3E1yXiIiEZNCgH0JeqaKiYP8uucO//w0XXgiHHgoTJsBVV8HcucF1eZ07Z0LII7IsUX9gBjAfeNLd55rZ3WZ2fuSwfwBNgKfKLaNwGDDbzD4CXgPuKzdbp4iIyC7F06N3M8Gwkm3AYwQ/tP6SyKJERCQ8S5ZUbz8AO3fCs89CXh68+y7svXeQDG+6CX7844TUmercfTowvdy+P0Y9Pr2S894GjkpsdSIiku52GfQiUz8PitxERCTN5eQEwzVj7a9g0yZ46KFgiObixXDQQTBmDPToAY0bJ7pUERERqUSlQc/MnqeKa/Hc/fzKnhMRkdpr8OCy1+gBNGoU7P/e8uUwalSwRML69XDyyTB0KJx/fjpPsCIiIlJrVNWjNyRpVYiISMoonXBl0KBguGZOThDyuncnmClz6FB49NFgaYSLLgomWPn5z0OtWURERMqqNOi5+xvJLERERFJH9+5RM2y6w8yZcOaQ4L5xY+jTBwYOhAMPDLVOERERia2qoZtPuvtlZvYJMYZwuvvRCa1MRETCtX07PPZYMMHKJ59Aq1Zw771w443BZCsiIiKSsqpaXmFA5P5c4LwYNxERqcUqXRR93Tq4775gZ8+eQY/eww/DV1/BXXcp5ImIiNQClQY9d18RedjP3Qujb0C/5JQnIiI1oXyo69cvmHClsDDIcYWFMPj6r/jsrAHQtm0Q6I48El56Kbgur2dPqF8/5HchIiIi8YpnwfQzYuw7u6YLERGRxCgoqBjqxo37YVbN43mXJ7mUT7YezIEvj4WLL4Y5c+Dll+GsszJigXMREZF0U9U1en0Jeu4ONLOPo57aC/hPogsTEZGaMWhQ2aUSAMyL6cY0csnjFP7Den7EP/gto7mZZZNah1OoiIiI1Jiqlld4FPgX8Ffgzqj9G919bUKrEhGRGrNkyQ+PG1JETyZyK8PowEK+oj0DGM5D9GITe9GuXXh1ioiISM2panmFDcAG4Eozywb2ixzfxMyauPuSys4VEZHUkZMDWwq/pT+j6ctYWrKGdzmey3iSZ7iQ4siPggqLoouIiEittctr9MysP/AtMBN4MXJ7IcF1iYhITZg3j1faX08h7RjEYP7NKZzCW3Ru+A4t+15Km3Z1MIN27SA/P2rtPBEREanVqhq6WWogcKi7r0l0MSIiUgPc4bXXgvXvpk/n4AYN+KJLL26cP5A3VhxCTg7kD1aoExERSWfxBL2lBEM4RUQkle3YAU8+GQS8Dz+EffaBu++Gvn05pGVLXgu7PhEREUmaeJZXWAS8bmZ3mdltpbdEFyYiInHasAGGDIEDD4Srr4YtW3jnugc5tOESsv70/2jfqeUPi6GLiIhIRoinR29J5FYvchMRkZAVFMCYO5ZwydcjuMEeZC/fyNv1T+NexvHuyrP5bnIW27cHxxYWBuvogYZrioiIZIpdBj13/79kFCIiIrEVFARr4RUWQnY2HFP8Prnk8SZPAvCEX04euXy47bjghBgL4BQVBW0o6ImIiGSGXQY9M9sH+B1wBNCgdL+7d05gXSIiGS063JkBXsKvmU5ucR6n8TrfsRfDGchIbmEpOXG1uUSL4oiIiGSMeIZuFgBPAOcCfYAewKpEFiUikmnKBzv3YH99tnKNT+Y2hnIYn7GEtuQyhPFcz3f8qFqvkRNfHhQJ3brN2ynaURx2GUnhpV/sKSQFSxKpcfH8P3fi+2KIry1oXD+bffdqsMtja0o8Qa+Fu08wswHu/gbwhpm9sacvbGZtgUeAHwMlQL67j9jTdkVEapOCAhgwANZELWDjDi1YTT/upz+j2ZdVvM9xXEUBT3EpO6lb7dfRYuhSm6zZvJ1VG7eFXYaI1HIlJc6cpetZvGYz7Vs0pmPbZmRlWWj1tGxSL+WC3o7I/Qoz+zWwHGhTA6+9E8h19w/MbC/gfTOb6e7zaqBtEZGUFivgAXTgC25lGD2ZSEO28gK/Jo9cXudXQPw/nOrWhaZNYe3aoCdvsNbNExGRDFJS4tz7r/ksXLmJ7TtLqFcni4P3bcLvzz4s1LCXTPEEvXvM7EdALjAKaArcuqcv7O4rgBWRxxvNbD7QGlDQE5G0VlAQzIJZVFS6xzmFf3M7QziP59lOPSZzDUO5jc84rNJ2Sod4tmsH55wD06cH1+Ep2ImISKabs3Q9C1duYtvOEgC27Sxh4cpNzFm6nuPaNQ+5uuSIZ9bNFyIPNwCnJaIIM2sPHAu8G+O53kBvgBxdYCIiaWDQoCDkZbOTi3iG2xnC8bzHalpwD39gDDexkv3KnFMa6rKzobg4CHcKcyIiIrEtXrOZ7ZGQV2r7zhIWr9msoFfKzB6GilciunuvmijAzJoATwMD3f27GK+TD+QDdOrUSZcHi0itFD3ZShM2cgsPcSvDaE8hX9CBvtzPJHqwhUYVzm3RAkaMUKgTERGJV/sWjalXJ+v7Hj2AenWyaN+icYhVJVc8QzdfiHrcALiQ4Dq9PWZmdQlCXoG7P1MTbYqIpJrSoZrNir7mr4yiD+Noxgbe4hQGMpznOY8Ssr8/PisLSkrUaycSplSbxEFEqqdj22YcvG8T5i5ZDdl1qF+3Dgfv24SObZuFXVrSxDN08+nobTN7DHhlT1/YzAyYAMx396F72p6ISKrKv+kjxhblcSWPkUUJT3MxeeTyP04oc5x67kRSgyZxEKn9srKM3599GDcOyKW4yX7079M74/5gk7Ub53SAOFfnrdrJwDVAZzObE7mdUwPtioiEzx1eeokVR53BGxs6chHPMIabOJiFXM6TFULelCmwerVCnkgqiJ7EwSk7iYOIVK2kxPmgcB3PfLCMDwrXUVIS3pVXWVlGvTULaVj4H45r1zzUkFdS4ryzaA0jZy1g1vxvKU7C5xLPNXobCa7Rs8j9N8Ade/rC7v5vqjNXuIhIbbBtG/+9+VGaTxzKT3Z8itOKO7iPfHqzntgXf7drp4Ankko0iYPI7lFveGyln8uXqzaxbUcJDetl07FtMyZfdwLZCfxcdtmj5+57uXvTqPtDyg/nFBHJeGvXMueye/mmYXtOfLAX23cY1zKJ9izm79xRacjTQubpy8y6mtnnZrbQzO6M8Xx9M3si8vy7kRmoS5+7K7L/czM7K5l1yw+TOETLtEkcYkmlnhpJTeoNj630c9m6I/hcirYXM2fpel7/fGVCX7fKHj0zawh0Bw6P7JoNTHX37QmtSkSklnhu6JesHDScq7Y+REeKmMGZXMMjvMLp7GrQgiZbSV9mlg2MAc4AlgHvmdk0d49eK/Y6YJ27H2xmVwB/Ay43s8OBK4AjgP2BV8zsEHcvTu67yFyaxKGiVOup0WQ5qUm94bHF+ly2bC9m3vLv6HLYfpWctecq7dEzs6OA+cAvgMVAIXAW8B8za2Zm9ySsKhGRFFVQAC1bwon2X6baJZybewg9tj7Ak1zGUXxMV2bwCmdQVchr1Ci4Jm/xYoW8NHY8sNDdF0X+OPo40K3cMd2ASZHHU4EukYnKugGPu/s2d/8KWBhpL+0Vlziz5n/LlHcKQ+0xKp3Eocm8f9Lwq7e4pXOHjB96lko9NaWhc+SrC5j6/jJGvrqAe/81Xz2MKUC94bHF+lwa1svm8P2bJvR1q+rRGwnc4O4zo3ea2enAp8DcRBYmIpJqbupTzIoHnuM58jiZt1lHM/7GHYymPyvYP642srMhP18BLwO0BpZGbS+DcjPwRB3j7jvNbAPQIrL/nXLntq7qxRat2szlD/x3jwpecfjlAHvczu5ydz77ZiObtu2kxMEMGtbNJmfvhgT5N/m2tg3+yV74ZDkvfFIjK0vVWqs2biuzHhkEYW/i218l/bPZuHUnX6/fgvsPdcxb8R13PPMxezWIZ+UwSRR3D6458xLAsCwjO8t4/uOvQ/sa+q5j8AP37hfCiy7lP5esLKNOlvHAG1+S/+aihL1uVV8NrcqHvEihr5jZDoL19ERE0t7jEzbzv34TuXX7MA7mSxZxADczkof5DZtpEnc7jRop5GWQWMmkfHdDZcfEcy5m1hvoDdCk1UHVra+Cjsd03OM29sT6LTu+D3kQTFy7ZUcxm7YVh/bLe4fDjwzldWNZMO9TILyaGtTNxozvwxUEYbx+3ezKT0qQrTuKy9QBQV3bdoTzfyXsf5tS7s4XCxdBdj32378VTepnJ/2PJGZGzt4N2bStHtt2FFO/bnYodUQL+98Ffvhctu6oz85ip1H9bJo1rJvwz6Wqr4YsM6vv7tvKFdoA2OHuRQmtTEQkZE+P+YYvbx3NdTvGcgVreYcTuJP7eJYLyyxwHg9dj5dxlgFto7bbAOX/nF16zDIzqwP8CFgb57m4ez6QD9CpUyd/4sYTa6z4MIyctYBhM78ou9PhxANbcNFxbcIpKoXc9OhdAPzxd9NCef1Uukbvg8J1jHx1QZkexvp1suh50gFJvw6spMS5ccYEipvsx7lHnRnatYKl/z4lDZpBdh1WbdzGjxpqtstU07JJPTrst9cet/Nkn/iOqyroPQI8bWb93X0xQGRGsJHA5D2qTkQklc2dy8KbhnLuG1Ooyw7+yQXkkcvbnER1VoXRAugZ7T2gg5kdAHxNMLnKVeWOmQb0AP4LXAK86u5uZtOAR81sKMFkLB2A/yWt8pAcsX9TGtbLpmj7D3PO6NqeQEmJs73FwRQ32Y8PCteFEiZKr1tMhQlQSifLKR86kz1ZTmm42nT4BZBdh5GvLggt/JZeQ0mdekDZaygzeRKUTFdp0HP3e8ysP/CmmTWK7N4MDHH3UUmpTkQkWdzh1Vf5OjeP1h/9i/1pyHiuZzgDWUiHuJtp0gTGjVO4y3SRa+76AzOAbOAhd59rZncDs919GjABmGxmCwl68q6InDvXzJ4E5gE7gZsyYcbNXx26Lx3bNmPO0vVs2V4c2i/vqSaVwkRWlnFcu+ahB4dUCZ2pFK4026XEUuVAZncfDYw2s70i2xuTUpWISLLs2AFPPAF5eTBnDtnsxx/4C2Ppy1pa7PL00mtWNDRTynP36cD0cvv+GPV4K3BpJecOBjJqhcXsLGPydSfw+ucreWvBavZpUl9T5pNaYSKVpELoTKVwVTqrY/RwVvWIS1xXrCrgiUja2bCBD/rk8+MnR7B/ydfM4zDyGE8B3dlGg7ia6NsX7r8/wXWKZJDsLKPLYfvRrkVjVm3ctusTMkAqhQkpK5XCVaoMZ5XUojloRSSzFBbCiBHsGPsgx23dxCw6cz35vERXvPKlRcvQ8EwRSZZUChNSViqFq1QZziqpRUFPRDLD7NkwZAglT02luMR4gsvJI5c5HBt3E1lZ8MgjCngikjypFCakrFQLV6kwnFVSyy6DXmQillwgx91vMLMOwKHu/kLCqxMR2RMlJfDiizBkCLz5Jpuzm3J/ya2M5BaWlZm9ftfq1YOHHlLIE5HkSrUwIWUpXEkqi6dH72HgfaB0gZ5lwFOAgp6IpKYtW4Kut2HD4PPPWZqVwzDyGF98PRtpWu3mtEyCiIRJYUJEdkc8Qe8gd7/czK4EcPctFuby9iIilVm1CsaMYevQMTTYuJrZ/JQ8HmVqySXspG61m9NkKyIiIlJbxRP0tptZQ8ABzOwgQFNhiUjq+PxzGDo06MXbupWZnMsQbudNTqU6C5yXUg+eiIiI1HbxBL0/AS8Bbc2sADgZ6G9DAfQAACAASURBVJnIokREdskd3nwzWP/u+efZSn0e4VqGchuf85PdalI9eCKpoVmjutTRNWi7xcMuQCrlnnn/OrXhHcf/z7LrA3fVVpMGyZ0Hc5ev5u4zzewD4OcEfxof4O6rE16ZiEgsO3fC1KlBwJs9m7XZLRnJn7iffqxi391qUj14IqmlZZP6tGxSP+wyRERqtUqDnpkdV27Xish9jpnluPsHiStLRKScjRth/Hg23TuCJqsL+YIO5DGOR4qvZSsNd6vJLl3glVdquE4RERGRFFBVj15eFc850LmGaxERqeCZkcsovH0kv9mRTzM28AG/YAgjeYFz417gvDwteC4iIiLprtKg5+6nJbMQEZFo0++dw4Y/5nFJ8eNkUcJTXEoeuczmZ7vdpoZoioiISKaIZ8H0BkA/4BSCnry3gHHuvjXBtYlIpnHntTtewofkcY7PYhONGU1/RjCAQtrvVpMNGsD48Qp3IiIiklnimfrlEWAjMCqyfSUwGbg0UUWJSIbZto3JXQs47vU8TmMeX7M/v+Nv5NObDTTbrSazsuDGGzWLpoiIiGSmeILeoe5+TNT2a2b2UaIKEpHM8dtea6j38DhuZhTX8C1zOIZreIQnuJwd1NutNjXBioiIiAhxzWTwoZn9vHTDzE4A/pO4kkQknRUUwFGNvmS09efPD+cwmD/wIcdyOjM5lg+ZwjW7FfKaNIEpUxTyRERERCC+Hr0TgGvNbElkOweYb2afAO7uRyesOhFJGwUFkN/zbW7ZmcdHPMsO6lJAd4ZyG3M5strtmUGfPhqaKSIiIhJLPEGva8KrEJH0VVxM/jn/5KiXh/AG77CW5vyVuxhNf76hVbWa0rIIIiIiIvHZZdBz90Izaw60jT5eC6aLSJU2b+a9fg/T4pFh9GYRX3Ig/RnFw/yGIhpXqynNnCkiIiJSPfEsr/AXoCfwJcHyCqAF00Ukhn794NmxK+jPaPoylp+xjrc5kd/yd/7JBZSQXa321IMnIiIisnviGbp5GXCQu29PdDEiUnsUFECvXrA98p3hCD4llzyG8Sh12cGzXEgeufyXk6rVrq69ExEREdlz8QS9T4FmwMoE1yIiKaxfPxg7tvxepwuzuJ0hdGUGm2nEg9zAcAbyJQdXq30tiyAiIiJSc+IJen8lWGLhU2Bb6U53Pz9hVYlISogd7qAu27mCx8klj2P4mG/Yj0Hcwzj6sJYWcbeva+9EREREEiOeoDcJ+BvwCVCS2HJEJGzlh2RG+xHruZEHuIWRtGY5czmcXkyggO5sp361Xkc9eCIiIiKJE0/QW+3uIxNeiYiE7vTTYdasivvbsZiBDOc6JrAXm3iFLlzHBGZwFmDVfp2+fXUNnoiIiEgixRP03jezvwLTKDt0U8sriKSR1q1h+fKy+37G/8glj0uYSglZPM4V5JHLR3SsdvsapikiIiKSPPEEvWMj9z+P2qflFUTSQKxhmkYJ5/E8ueRxKm+xgaYM4XZGcTNf0ybutrU0goiIiEh44lkw/bRkFCIiyVHZ8MwGbKEHk7iVYRzKFxSSw0CGMYHr2MReVbapJRFEREREUks8PXqY2a+BI4AGpfvc/e5EFSUiidG8OaxfX3bfPqzkJsbQj/vZh9W8Rycu53Ge5mKKK/kWoWGYIpUzs72BJ4D2wGLgMndfV+6YjsBYoClQDAx29yciz00EfglsiBze093nJKN2ERFJH1m7OsDMxgGXAzcTzLpwKdAuwXWJSA05/fSgx82sbMg7lM94gN4sIYc/cTdvcxKn8gbH8z+e5PIKIa9LF3APblu2KOSJVOFOYJa7dwBmRbbLKwKudfcjgK7AcDNrFvX8b929Y+SmkCciItW2y6AHnOTu1wLr3P3/gBOBtoktS0T2VGnAKztM0/klrzON8/iMw7iGyUykJ4fyGRfwHG9xKuVn0ezbNwh3WgpBJG7dCJYmInJ/QfkD3P0Ld18QebwcWAnsk7QKRUQk7cUzdHNL5L7IzPYH1gAHJK4kEdldla2BV4cdXMJUbmcIP+UDVtGSP/Fn7qcfqyv53bJZM1i3LuZTIlK1/dx9BYC7rzCzfas62MyOB+oBX0btHmxmfyTSI+ju22KeLCIiUol4gt4LkeEk/wA+IJhx88GEViUicalqcXOAvfiO6xnPQIaTw1I+5xB68wCTuYatNKy0XS1mLlI1M3sF+HGMpwZVs51WwGSgh7uXRHbfBXxDEP7ygTuACtfFm1lvoDdATk5OdV5WREQyQDyzbv4l8vBpM3sBaODuG6o6R0QSr7LZMwHasJRbGElv8vkR3/E6v+QmxvAiv8arGLGthcxF4uPup1f2nJl9a2atIr15rQiGZcY6rinwIvAHd38nqu0VkYfbzOxh4PZKasgnCIJ06tTJd++diIhIuqo06JnZz4Cl7v5NZPta4GKg0Mz+7O5rk1SjiETp1w/Gjo39XEc+JJc8LucJDOcpLiWPXN6nU8zjNTxTJCGmAT2A+yL3z5U/wMzqAc8Cj7j7U+WeKw2JRnB936eJL1lERNJNVZOxPABsBzCzUwl+YD1CMN1zfuJLE5HyWreuGPKMEs5mOrPozIccRzeeYxQ3cxBfchWPVRryunRRyBNJkPuAM8xsAXBGZBsz62Rm4yPHXAacCvQ0szmRW8fIcwVm9gnwCdASuCe55YuISDqoauhmdlSv3eVAvrs/TTCEU1M9iyRRrGGa9dlKdwrIJY/Dmc8yWvNb/s6D3MAGmsVsR9feiSSeu68BusTYPxu4PvJ4CjClkvM7J7RAERHJCFUGPTOr4+47CX5g9Y7zPBGpIbEC3t6soS9juZlR7MdKPqQjVzOZJ7mMHdSL2Y4CnoiIiEhmqSqwPQa8YWarCZZYeAvAzA4mGL4pIgkSK+AdzAJuZRg9mUgjtjCds8kjl1fpTPm170ppchURERGRzFRp0HP3wWY2C2gFvOzupTN6ZQE318SLm1lXYASQDYx39/tqol2R2ij2UgnOSbzN7QyhG8+xg7pM4WqGchvzOKJCG4cfDnPnJq1kEREREUlRVQ7BjJ7uOWrfFzXxwmaWDYwhuFB9GfCemU1z93k10b5IbVDZEgnZ7ORCniWXPH7Ou6xhb+7l94ymP9/GXLpLvXciIiIi8oMwr7U7Hljo7osAzOxxoBugoCdprar17xqziV48xECGcyBfsZCDuInRTKQnRTSucLwZTJ4M3bsnuGgRERERqVXCDHqtgaVR28uAE0KqRSThqlr/rhXLuZlR9GEczVnPfziJXPKYxvmUkB3zHE2wIiIiIiKVCTPoxZo9wiscZNabyIyfOTk5ia5JpMZVFfCO5BNyyeMqHiWbYp7lQvLI5R1OrLQ9BTwRERER2ZUwg94yoG3UdhtgefmD3D2fyALtnTp1qhAERVJV5UM0nTOYSS55nMXLbKYR4+jDcAbyFQdW2p4mWhERERGReGWF+NrvAR3M7AAzqwdcAUwLsR6RPdavX3DdnFnFkFeX7VzLJD7iGF7mLI7mY37PYNqylAGMrDTkdekC7gp5IiIiIhK/0Hr03H2nmfUHZhAsr/CQu+tXWamVqppgpRnruJEHuJlRtGY5n3AkPXmYx7iS7dSvtE3NoikiIiIiuyvMoZu4+3Rgepg1iOyp5s1h/fqK+9vzFQMZznVMoAmbeZkz6MVDvMyZxLpEtUEDGD9eM2iKiIiIyJ4LNeiJ1FaxFzcPHM+75JLHxTxNCVk8ylUM5TY+5pgKx+q6OxERERFJBAU9kThVNTwzi2LO43luZwin8B/W8yP+wW8Zxc0sp3WF4+vUgYkT1XsnIiIiIomhoCdSharCHUBDiujBJG5jKB1YyGLaMYDhPEQvNrFXheM1PFNEREREkkFBT6QSrVvD8goLfgT25VtuYgz9uJ+WrOF//IzLeIJnuIjiGF9WWvtORERERJIpzOUVRFJO9PIIsULeT5hPPjdQSDv+wD38m1P4BW9yAu/yFJeVCXkNGsCUKcHSCAp5IiIiIpJM6tGTjNevH4wdW9URzq94ndsZwq+ZzhYa8DC/YRi3soBDKhzdrBmsW5ewckVEREREdkk9epKRonvuKgt5ddjBlTzK+/yU1+jMz3iPP/J/5LCEfoyNGfK6dFHIExEREZHwqUdPMkpBAfToAcXFlR/TlA1cz3gGMpy2LGM+P+EG8pnC1WylYcxztLi5iIiIiKQSBT1Je7semhloyxIGMIIbeJCmbOQ1fkVfxjKdc/Bynd8KdiIiIiKSyhT0JK3FE/KO431yyeMyngTgSS4jj1w+4KcVjp0yRUsjiIiIiEjqU9CTtFZZyDNKOIfp5JLHabzOd+zFCAYwggEsJafC8U2awLhxCnkiIiIiUjtoMhZJOwUFQTAzq/hcfbZyHeOZyxG8wHkczEJu5x+0ZSm3k1cm5EUvj7Bxo0KeiIiIiNQe6tGTtHH66TBrVuznWrCaftzPTYxhP1byAcdyFQU8xaXspO73x6nnTkRERETSgYKepIXWrWMvcN6BL7iVYfRgEo3YwoucwxBu53V+BQRdfnXqwMSJCnciIiIikj40dFNqtYKCIKiVDXnOKbzFs1zAZ/yEXjxEAd05nLmcy4u8zmmAYRbMnrljh0KeiIiIiKQX9ehJrVV+qGY2O7mIZ8gljxP4H2vYm3v4A2O4iZXs9/1xXbrAK6+EULCIiIiISJIo6EmtdMQRMG9e8LgJG+nFQwxkOAewmAUcTF/uZxI92EKjMuftv79CnoiIiIikPw3dlFqlX79gNs1582B/vuav3MkSchjBQJbRhgt4lp/wGePoWyHkdekCX38dUuEikjHMbG8zm2lmCyL3zSs5rtjM5kRu06L2H2Bm70bOf8LM6iWvehERSRcKepLyopdLGDsWjuJjJtKDrziA3/IPZnIGJ/AOp/IWz3EBJWR/f26TJj8skaCePBFJkjuBWe7eAZgV2Y5li7t3jNzOj9r/N2BY5Px1wHWJLVdERNKRgp6kpOhwd/XVsHmzcyYzmMGZfMwxXMzTjKUvB7OQy3mS/3FCmfMPP1zr34lIaLoBkyKPJwEXxHuimRnQGZi6O+eLiIiUUtCTlFJQAPXrl4Y7qMc2ejCRjzmaGXTlSD7lTv5KW5YykBEs5oAKbXTpAnPnhlC8iEhgP3dfARC537eS4xqY2Wwze8fMSsNcC2C9u++MbC8DWie2XBERSUeajEVSQkEB9OoF27cH281Zy408wM2MYn9W8DFH0YOJPMaV7CD25SpaD09EksXMXgF+HOOpQdVoJsfdl5vZgcCrZvYJ8F2M47ySGnoDvQFycnKq8bIiIpIJFPQkVP36BdfdlTqARQxkONcxgcYUMYMz6clEZnIGpQucx7L//ppoRUSSx91Pr+w5M/vWzFq5+wozawWsrKSN5ZH7RWb2OnAs8DTQzMzqRHr12gDLKzk/H8gH6NSpU8wwKCIimUtDNyUUpUM0S0PeCbzDU1zCAjrQh3E8xaUczUd0ZQYzOZOqQp5m0xSRFDMN6BF53AN4rvwBZtbczOpHHrcETgbmubsDrwGXVHW+iIjIrijoScIVFEDLlsHEKqW3q6+GnduLuYBn+Tcn8w4n0oVZ/J3f0Z7F/IaJfMLRlbZpBn37ajZNEUlJ9wFnmNkC4IzINmbWyczGR445DJhtZh8RBLv73D2yOih3ALeZ2UKCa/YmJLV6ERFJCxq6KTWuoABuvDGYTCWWhhTRk4ncxlAO5ksWcQC3MIKH6MVmmlTZdt++cP/9CShaRKSGuPsaoEuM/bOB6yOP3waOquT8RcDxiaxRRETSn4Ke1JjyE6qUtx/f0J/R9GUsLVjLO5zAXfyVZ7mQ4ir+KzZoAOPHa5IVEREREZF4KehJjSg/qUq0w5nLbQzlaqZQlx08RzeGcDtvcxJVXXvXpAmMG6eAJyIiIiJSXQp6skcqD3hOZ14llzzO4V8U0ZAJXMcwbmUhHapsU8MzRURERET2jIKe7JbKhmnWYQeX8wS55HEsc/iWffl/3M1Y+rKGllW2qYAnIiIiIlIzFPSkWiqbaKUpG+hNPrcwkrYsYx6HcR3jKaA722hQZZsaoikiIiIiUrMU9GSXCgpgwABYs6biczkUMoARXM94mrKRVzmNG3mAl+iKx1i9o0ULGDFCoU5EREREJJEU9KRSVS2T8FNmk0sel/IUAI9zBUO5jQ857vtjzKBPHw3HFBERERFJNgU9qaCygGeU8GteJJc8fsUbfMdeDONWRnILy2hb5lhdbyciIiIiEh4FPQGqHp7ZgC1cw2RuYyg/4XOW0JbbyGM817ORpmWP1Zp3IiIiIiKhU9CTSpdIaMkq+nE/NzGGfVnF+xzHlTzKVC5hJ3XLHKsJVUREREREUoeCXoaLFfIO4XNuZRg9mERDtvI855JHLm/wS8ovcK6AJyIiIiKSehT0MlhBQRDSAs4veItc8ujGNLZSn0e4lmHcymccVuFczZ4pIiIiIpK6FPQyQEEBDBoEhYXBTJjuPzyXzU4u5mluZwg/YzaracH/8Ufupx8r2a9MO+q9ExERERGpHRT00ly/fkE4Kw13pfdN2Mh1TGAgw2lPIV/QgT6M5RGuZQuNyrShgCciIiIiUrso6KWhqmbQbM0ybmYUN/IAzdjAm/yCAYzgec6rsMC5hmeKiIiIiNROCnpppKqAdwxzyCWPK3icLEqYyiXkkct7HF/hWK2BJyIiIiJSuynopYmCAujdG4qKovc6ZzGD2xnC6cxiE40Zw02MYACLOSBmOy1aKOSJiIiIiNR2CnppoKAAevSA4uJgux7buIpHySWPI5nL1+zPHdxHPr1ZT/NK22nUKBiqKSIiIiIitZuCXi0XPdlKc9bSh3HczCha8Q0fcTTXMonHuYId1It5flYWlJRAu3YweLCuxxMRERERSQcKerVU9PV4B/IltzKM3/AwjSniJc7iGiYziy5EL3CuyVVERERERDKDgl4tEWstvBN5m1zyuJBn2UkdpnA1Q7mNuRxZ5lwFPBERERGRzKKgVwtET7SSRTEX+D/JJY+T+C9rac5fuYvR9OcbWn1/TnY2TJqkcCciIiIikokU9FJYdC9eIzZzEw9zK8M4iEUs4gD6M4qJ9GQzTcqcZ6aQJyIiIiKSybJ2fUjNM7N/mNlnZvaxmT1rZs3CqCNsBQXQvn0wIUrLlsGt9HGTJnD11bCtcAX3MIiltGU0N7OSfbmYqXRgAWPoHzPk9emjkCciIiIikslCCXrATOBIdz8a+AK4K6Q6QlM6HLOwMLjebs2a4Fb6uP3mT5lALxbTnrv4K69xGifxH07ivzzDxZSQXaHNFi1g8mStgyciIiIikulCCXru/rK774xsvgO0CaOOMJT24l19dfnFzQGcLrzCdM7mU47iCh7nQW7gEL7gEp7mv5wUs80WLWDKFFi9Wj15IiIiIiKSGtfo9QKeqOxJM+sN9AbIyclJVk0JET2pSrS6bOdyniCXPDryEd+wH4O4h3H0YS0tKrSTnR0sjq6170REREREJJaEBT0zewX4cYynBrn7c5FjBgE7gYLK2nH3fCAfoFOnTp6AUpNm0KCyIe9HrKc3+dzCSNrwNXM5nF5M4FGuYhsNKpzfqBHk5yvYiYiIiIhI1RIW9Nz99KqeN7MewLlAF3ev1QGuKqUzZy5ZElx/B9COxQxgBNcznr3YxCt04QYe5CW6Er3AeTSthSciUjuY2d4EI1XaA4uBy9x9XbljTgOGRe36CXCFu//TzCYCvwQ2RJ7r6e5zEly2iIikmbBm3ewK3AGc7+4VrlSrraJn0WzfHvr1KzvhSife4zGu4EsOoj+j+ScX0JEPOYNXeK/F2bRoYZgFoa5Fi2AGzXbtdP2diEgtcycwy907ALMi22W4+2vu3tHdOwKdgSLg5ahDflv6vEKeiIjsjrCu0RsN1AdmmhnAO+7eJ6RaakT56+8KC2HcOMBLOI8XuJ0hnMpbbKApeeQyklv4mjY0agRTNBxTRCSddAN+FXk8CXid4I+blbkE+Fc6/eFTRETCF0rQc/eDw3jdRCp//V0DtnCtP8JtDOVQvqCQHG5lKBO4jo00DXrrcjSZiohIGtrP3VcAuPsKM9t3F8dfAQwtt2+wmf2RSI+gu29LQJ0iIpLGUmHWzbSwZElwvw8r6cf93MQY9mE179GJK3iMqVxCceTjbtcOFi8Or1YREdkzVU04Vs12WgFHATOidt8FfAPUI5iM7A7g7hjnps2s1CIiUvMU9HZT9CQrOTlw/I8+o9f6oVzLIzRgG9M4jyHczr/5BR41wUqjRkEvnoiI1F5VTThmZt+aWatIb14rYGUVTV0GPOvuO6LaXhF5uM3MHgZur6SGtJmVWkREal4ok7HUdqXX4xUWOr/wNxhVeB7vrD+Ma3mESfTgJ8ynG9N4v9Gp9OlrtGv3w8QqWh5BRCTtTQN6RB73AJ6r4tgrgceid0TCIRZcxH4B8GkCahQRkTSnHr3d8Kff7+D8oqnkkkcn3mcVLfkzf+Lx5v3Y2nRflizR9XciIhnsPuBJM7sOWAJcCmBmnYA+7n59ZLs90BZ4o9z5BWa2D8F6O3OAWj1ZmYiIhENBrzq++w7Gj2fWkhG0Ywmfcwg3Mo5HuJatNMTWQ8nasIsUEZEwufsaoEuM/bOB66O2FwOtYxzXOZH1iYhIZlDQi8fSpTByZDDu8rvv+Kb+qfTfNpoX+TUeNfpV18KLiIiIiEgqUNCryocf8lX/PNq8/QSGM73RpdS9O5e1B3bi1d4QveKRJlkREREREZFUoclYyispgenToUsXOO44Wr79HKO4mYP4km5Fj3HJfZ2AoHNPk6yIiIiIiEgqUo9eqa1bg+k0hw6FefOgdWvubfZ3/r7+BjbQ7PvDioqCZRUWL1awExERERGR1KQevTVr4J57oH17uP56qFsXJk+GRYv4w4bflgl5pUoXRxcREREREUlFmdujt3AhDBsGDz8MW7bA2WdDbi507hyMxySYXKWwsOKpmnRFRERERERSWWb16LnDf/4DF10EhxwC48fDlVfCp5/+cF1eJORBMLlKo0Zlm9CkKyIiIiIikuoyI+gVF8PUqXDiiXDKKfD66/D73wfddRMmwBFHxDyte3dNuiIiIiIiIrVPeg/d3LQpGJo5bBh89RUcdBCMHg09e0LjxnE10b27gp2IiIiIiNQu6Rn0VqyAUaNg3DhYtw5OOgmGDIFu3SA7O+zqREREREREEiq9gt4nnwTLIxQUBMM1L7wwmGDlxBPDrkxERERERCRp0iPo/fvfwRIJM2YEs6XceCMMHBgM1RQREREREckw6RH0PvgAPvoomA6zTx/Ye++wKxIREREREQlNegS93r2DXrz69cOuREREREREJHTpEfQaNAi7AhERERERkZRR69fRKyiA9u0hKyu4LyhIzrkiIiIiIiKpqlb36BUUBKM2i4qC7cLCYBt2vfbdnpwrIiIiIiKSymp1j96gQT8EtVJFRcH+RJ4rIiIiIiKSymp10FuypHr7a+pcERERERGRVFarg15OTvX219S5IiIiIiIiqaxWB73Bg4P10aM1ahTsT+S5IiIiIiIiqaxWB73u3SE/H9q1A7PgPj8/vslU9uRcERERERGRVFarZ92EIJjtbjjbk3NFRERERERSVa3u0RMREREREZGKFPRERERERETSjIKeiIiIiIhImlHQExERERERSTMKeiIiIiIiImlGQU9ERERERCTNKOiJiIjUIDO71MzmmlmJmXWq4riuZva5mS00szuj9h9gZu+a2QIze8LM6iWnchERSScKeiIiIjXrU+Ai4M3KDjCzbGAMcDZwOHClmR0eefpvwDB37wCsA65LbLkiIpKOFPRERERqkLvPd/fPd3HY8cBCd1/k7tuBx4FuZmZAZ2Bq5LhJwAWJq1ZERNJVnbALqI73339/k5nt6odnumoJrA67iBBl8vvP5PcOmf3+M/m9tzOz3u6eH3YhCdIaWBq1vQw4AWgBrHf3nVH7W8dqwMx6A70jmzX18zGT/89VRp9JRfpMKtJnUpE+k9hq4nNpF89BtSroAZ+7e6XXO6QzM5udqe8dMvv9Z/J7h8x+/5n83iF4/0BKBj0zewX4cYynBrn7c/E0EWOfV7G/4s4gBNfo55Pp/+di0WdSkT6TivSZVKTPJLZkfi61LeiJiIiEzt1P38MmlgFto7bbAMsJ/srbzMzqRHr1SveLiIhUi67RExERSb73gA6RGTbrAVcA09zdgdeASyLH9QDi6SEUEREpo7YFvZQcwpMkmfzeIbPffya/d8js95/J7x1q6fs3swvNbBlwIvCimc2I7N/fzKYDRHrr+gMzgPnAk+4+N9LEHcBtZraQ4Jq9CUksv1Z+5gmmz6QifSYV6TOpSJ9JbEn7XCz446GIiIiIiIiki9rWoyciIiIiIiK7oKAnIiIiIiKSZmpV0DOzv5jZx2Y2x8xeNrP9w64pmczsH2b2WeQzeNbMmoVdU7KY2aVmNtfMSswsY6bqNbOuZva5mS00szvDrieZzOwhM1tpZp+GXUuymVlbM3vNzOZH/t8PCLumZDGzBmb2PzP7KPLe/y/smjJBJn+vqUwmfx1WxcyyzexDM3sh7FpShZk1M7Opkd/R5pvZiWHXFDYzuzXydfOpmT1mZg3CrinZYv0eY2Z7m9lMM1sQuW+eyBpqVdAD/uHuR7t7R+AF4I9hF5RkM4Ej3f1o4AvgrpDrSaZPgYuAN8MuJFnMLBsYA5wNHA5caWaHh1tVUk0EuoZdREh2Arnufhjwc+CmDPq33wZ0dvdjgI5AVzP7ecg1pTV9r6lUJn8dVmUAwQRC8oMRwEvu/hPgGDL88zGz1sAtQCd3PxLIJphZONNMpOLvMXcCs9y9AzArsp0wtSrouft3UZuNqWQR2XTl7i9HZmoDeIdgfaWM4O7z3f3zsOtIsuOBhe6+yN23A48D3UKuKWnc/U1gbdh1hMHdV7j7B5HHGwl+aWgdiSwPxwAAB65JREFUblXJ4YFNkc26kVtGfa8PQUZ/r6lMJn8dVsbM2gC/BsaHXUuqMLOmwKlEZsd19+3uvj7cqlJCHaChmdUBGpGB64FW8ntMN2BS5PEk4IJE1lCrgh6AmQ02s6VAdzKvRy9aL+BfYRchCdUaWBq1vYwM/yUjE5lZe+BY4N1wK0meyNCwOcBKYKa7Z8x7D4m+1+xCJn4dVmI48DugJOxCUsiBwCrg4ciQ1vFm1jjsosLk7l8DQ4AlwApgg7u/HG5VKWM/d18BwR+TgH0T+WIpF/TM7JXIeN7yt24A7j7I3dsCBQRrEKWVXb3/yDGDCIaUFIRXac2L571nGIuxTz0bGcTMmgBPAwPLjWhIa+5eHBmi3wY43syODLumNKfvNVXI1K/D8szsXGClu78fdi0ppg5wHDDW3Y8FNpPg4XipLnLdWTfgAGB/oLGZXR1uVZmpTtgFlOfup8d56KPAi8CfElhO0u3q/ZtZD+BcoIun2SKI1fi3zxTLgLZR223IwKEPmcrM6hL8clng7s+EXU8Y3H29mb1OcI1Dxk3Kk0T6XlMJfR2WcTJwvpmdAzQAmprZFHfP9F/glwHLokYeTCXDgx5wOvCVu68CMLNngJOAKaFWlRq+NbNW7r7CzFoRjFxJmJTr0auKmXWI2jwf+CysWsJgZl2BO4Dz3b0o7Hok4d4DOpjZAWZWj+BC5mkh1yRJYGZGcL3HfHcfGnY9yWRm+5TOKGxmDQl+Ycio7/Uh0PeaGDL56zAWd7/L3du4e3uC/yOvKuSBu38DLDWzQyO7ugDzQiwpFSwBfm5mjSJfR13I8AlqokwDekQe9wCeS+SL1aqgB9wXGcr3MXAmwcxPmWQ0sBcw04IlJsaFXVCymNmFZrYMOBF40cxmhF1TokUm3ukPzCD4Bvmku88Nt6rkMbPHgP8Ch5rZMjO7Luyakuhk4Bqgc+RrfU7kr+iZoBXwWuT7/HsE1+hpGvcEyvTvNVXI5K9DqZ6bgYLI962OwL0h1xOqSO/mVOAD4BOCvJEfalEhqOT3mPuAM8xsAXBGZDtxNaTZ6D8REREREZGMV9t69ERERERERGQXFPRERP5/e/casvccx3H8/ZlhjsuhPDJqzpPdzGlKOcUDmpyaEjElHhhleUIje4SiNBLRIg9QCAk1Z8KanewBjTmkFDJEUfP14P8b/5brvu9tN3Lt/aqr69f3+l//3+Guuz79/v//JUmSNGQMepIkSZI0ZAx6kiRJkjRkDHqSJEmSNGQMehoqSfbpPQb76yRftfaGJP/q79okGek/ijvJnCRb9SOqST5Lsu/f1KcmeSTJJ+31WJK9tmXcA/ofOJcktyZZMNF9SpIkaesZ9DRUquq7qhqpqhHgfuDu1h4Bfp/o/pJMHuXjEeDPcFRVz1bVRP9eykPAp1U1vaqmA+uAJRPcB/w7c5EkSdIEMehpe7JDkgeTrE3ycpJdAJJMT/JikuVJ3kxyWKsfkGRpktXtfVqrL0lyV5JXgduT7Jbk4STLkqxIcm6SnYDbgLltR3FuksuTLG7n2C/J00lWtddJrf5MG8faJFeNNpkkBwGzgEW98m3AzCSHJjklyfO94xcnuby1F7bxfpjkgSRp9deS3J7k/SQfJzl5rLlsNqZBa3lR62tVkje2/E8nSZKkLWHQ0/bkYODeqpoBbAAuaPUHgGurahawALiv1RcDj1TVUcBjwD29cx0CnFFVNwA3Aa9U1XHAqcCdwI7AQuDxtsP4+GZjuQd4vapmAscAa1t9XhvHscD8JPuMMp8jgJVVtXFTobVXAIePsRaLq+q4qjoS2AU4p/fZ5Ko6HrgeuKWqfhtjLn2D1nIhcFab75wxxiZJkqRtNNplZ9KwWV9VK1t7OXBgkt2Bk4An26YWwM7tfTZwfms/CtzRO9eTvYB1JjCnd5/aFGDaGGM5DbgM/gxnP7T6/CTntfb+dOH0uwHnCFAD6mM5NcmNwK7A3nRB87n22VPtfTlw4DjO1XU6+lq+DSxJ8kTv/JIkSfqHGPS0Pfm1195It5M1CdjQ7uMbSz9U/dxrB7igqj7qH5zkhC0ZXJJTgDOA2VX1S5LX6ELjIGuBo5NMqqrf2zkmAUcBH9CFzf6u/ZR2zBS6nbZjq+rLJLdu1s+mddrIlv2PGLiWVXV1W4+zgZVJRqpqUICVJEnSNvLSTW3XqupHYH2SiwDSmdk+fge4uLUvAd4acJqXgGt797kd3eo/AXsM+M5S4Jp2/A5J9gSmAt+3kHcYcOIYY19Hd5nmzb3yzcDSqvoC+Bw4IsnOSaYCp7djNoW6b9su3IWj9TOOuWwaz8C1TDK9qt6rqoXAt3S7lZIkSfqHGPSkLsRdmWQV3S7Zua0+H7giyWrgUuC6Ad9fRHdP3uokH/LXw1FepQtaK5PM3ew719FdPrmG7hLJGcCLwOTW3yLg3XGMfR5wcJJ1Sb6hC4dXA1TVl8ATwGq6ewxXtPoG4EFgDfAMsGwc/Yw2l75Ba3lnkjVtfd4AVo2jT0mSJG2lVP3dLT6S/m+SHAq8QPcwlBf+6/FIkiTpv2PQkyRJkqQh46WbkiRJkjRkDHqSJEmSNGQMepIkSZI0ZAx6kiRJkjRkDHqSJEmSNGQMepIkSZI0ZP4AIaOEiM5b0HsAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 1080x864 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "results.plot_diagnostics(figsize=(15, 12))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 466
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1008,
     "status": "ok",
     "timestamp": 1558260492623,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "CRT4fVfOIaV_",
    "outputId": "6d46c29f-394d-43ca-aebb-cac385bd532e"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                 Statespace Model Results                                 \n",
      "==========================================================================================\n",
      "Dep. Variable:                                co2   No. Observations:                  526\n",
      "Model:             SARIMAX(1, 1, 1)x(1, 1, 1, 12)   Log Likelihood                -133.890\n",
      "Date:                            Sun, 19 May 2019   AIC                            277.780\n",
      "Time:                                    21:12:17   BIC                            298.843\n",
      "Sample:                                03-01-1958   HQIC                           286.046\n",
      "                                     - 12-01-2001                                         \n",
      "Covariance Type:                              opg                                         \n",
      "==============================================================================\n",
      "                 coef    std err          z      P>|z|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "ar.L1          0.3182      0.092      3.442      0.001       0.137       0.499\n",
      "ma.L1         -0.6254      0.077     -8.162      0.000      -0.776      -0.475\n",
      "ar.S.L12       0.0010      0.001      1.732      0.083      -0.000       0.002\n",
      "ma.S.L12      -0.8769      0.026    -33.812      0.000      -0.928      -0.826\n",
      "sigma2         0.0972      0.004     22.632      0.000       0.089       0.106\n",
      "===================================================================================\n",
      "Ljung-Box (Q):                       36.21   Jarque-Bera (JB):               187.89\n",
      "Prob(Q):                              0.64   Prob(JB):                         0.00\n",
      "Heteroskedasticity (H):               0.65   Skew:                             0.40\n",
      "Prob(H) (two-sided):                  0.01   Kurtosis:                         5.90\n",
      "===================================================================================\n",
      "\n",
      "Warnings:\n",
      "[1] Covariance matrix calculated using the outer product of gradients (complex-step).\n"
     ]
    }
   ],
   "source": [
    "print(results.summary())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "3IM7or1rIaWC"
   },
   "source": [
    "The summary attribute that results from the output of SARIMAX returns a significant amount of information, but we'll focus our attention on the table of coefficients. \n",
    "\n",
    "The coef column shows the weight (i.e. importance) of each feature and how each one impacts the time series. \n",
    "\n",
    "\n",
    "The P>|z| column informs us of the significance of each feature weight. \n",
    "\n",
    "Here, each weight has a p-value lower or close to 0.05, so it is reasonable to retain all of them in our model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 363
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1181,
     "status": "ok",
     "timestamp": 1558260538133,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "sdSQpYMmkDen",
    "outputId": "d9817265-c10f-42f0-8361-a625cb2f7a4e"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "lag   p-value          Q    c-value   rejectH0\n",
      "1       0.000     53.819      2.706      True\n",
      "2       0.000    105.308      4.605      True\n",
      "3       0.000    156.832      6.251      True\n",
      "4       0.000    208.435      7.779      True\n",
      "5       0.000    260.137      9.236      True\n",
      "6       0.000    311.936     10.645      True\n",
      "7       0.000    363.830     12.017      True\n",
      "8       0.000    415.823     13.362      True\n",
      "9       0.000    467.915     14.684      True\n",
      "10      0.000    520.106     15.987      True\n",
      "11      0.000    572.397     17.275      True\n",
      "12      0.000    624.788     18.549      True\n",
      "13      0.000    624.862     19.812      True\n",
      "14      0.000    624.862     21.064      True\n",
      "15      0.000    624.862     22.307      True\n",
      "16      0.000    624.862     23.542      True\n",
      "17      0.000    624.863     24.769      True\n",
      "18      0.000    624.863     25.989      True\n",
      "19      0.000    624.863     27.204      True\n"
     ]
    }
   ],
   "source": [
    "h, pV, Q, cV = lbqtest(results.resid, range(1, 20), alpha=0.1)\n",
    "print ('lag   p-value          Q    c-value   rejectH0')\n",
    "for i in range(len(h)):\n",
    "    print (\"%-2d %10.3f %10.3f %10.3f      %s\" % (i+1, pV[i], Q[i], cV[i], str(h[i])))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "CfI7vEWKIaWD"
   },
   "source": [
    "# Validating Forecasts"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "R4j7voxzIaWE"
   },
   "source": [
    "We have obtained a model for our time series that can now be used to produce forecasts. We start by comparing predicted values to real values of the time series, which will help us understand the accuracy of our forecasts. The get_prediction() and conf_int() attributes allow us to obtain the values and associated confidence intervals for forecasts of the time series."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "mN2BlfRVIaWF"
   },
   "outputs": [],
   "source": [
    "#The code requires the forecasts to start at January 1998\n",
    "#The dynamic=False argument ensures that we produce one-step ahead forecasts, \n",
    "#meaning that forecasts at each point are generated using the full history up to that point.\n",
    "pred = results.get_prediction(start=pd.to_datetime('1998-01-01'), dynamic=False)\n",
    "pred_ci = pred.conf_int()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 140
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 52655,
     "status": "ok",
     "timestamp": 1557987545614,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "GERFrYKxIaWH",
    "outputId": "9b9860bb-032e-42b1-d9ad-d1c36c8b7622"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "date\n",
       "1998-01-01    365.340\n",
       "1998-02-01    366.200\n",
       "1998-03-01    367.375\n",
       "1998-04-01    368.525\n",
       "1998-05-01    369.140\n",
       "Freq: MS, Name: co2, dtype: float64"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y[y.index >= '1998-01-01'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 230
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 52654,
     "status": "ok",
     "timestamp": 1557987545615,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "bm0i9t_TIaWJ",
    "outputId": "b08abbff-4a32-4258-82c4-4e196ec4b00a"
   },
   "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>lower co2</th>\n",
       "      <th>upper co2</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1998-01-01</th>\n",
       "      <td>364.453366</td>\n",
       "      <td>365.675241</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1998-02-01</th>\n",
       "      <td>365.373503</td>\n",
       "      <td>366.595377</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1998-03-01</th>\n",
       "      <td>366.404744</td>\n",
       "      <td>367.626619</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1998-04-01</th>\n",
       "      <td>367.908502</td>\n",
       "      <td>369.130375</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1998-05-01</th>\n",
       "      <td>368.389524</td>\n",
       "      <td>369.611398</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             lower co2   upper co2\n",
       "date                              \n",
       "1998-01-01  364.453366  365.675241\n",
       "1998-02-01  365.373503  366.595377\n",
       "1998-03-01  366.404744  367.626619\n",
       "1998-04-01  367.908502  369.130375\n",
       "1998-05-01  368.389524  369.611398"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred_ci.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "mib0bbAiIaWL"
   },
   "source": [
    "We can plot the real and forecasted values of the CO2 time series to assess how well we did."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 412
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 52655,
     "status": "ok",
     "timestamp": 1557987545616,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "6gVOB46BIaWM",
    "outputId": "e38ed62f-8e54-49c8-afaa-894e0f167025"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1296x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = y['1990':].plot(label='observed')\n",
    "pred.predicted_mean.plot(ax=ax, label='One-step ahead Forecast', alpha=.7)\n",
    "ax.fill_between(pred_ci.index,\n",
    "                pred_ci.iloc[:, 0],\n",
    "                pred_ci.iloc[:, 1], color='k', alpha=.2)\n",
    "ax.set_xlabel('Date')\n",
    "ax.set_ylabel('CO2 Levels')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "DlMuwXV_IaWO"
   },
   "source": [
    "Compute the MSE (Mean Squared Error), which summarizes the average error of our forecasts. \n",
    "\n",
    "For each predicted value, we compute its distance to the true value and square the result. \n",
    "\n",
    "The results need to be squared so that positive/negative differences do not cancel each other out when we compute the overall mean."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 52655,
     "status": "ok",
     "timestamp": 1557987545617,
     "user": {
      "displayName": "Bhavesh Bhatt",
      "photoUrl": "https://lh5.googleusercontent.com/-Dxy3HXzth_c/AAAAAAAAAAI/AAAAAAAAHvk/4kcnA5cyAC4/s64/photo.jpg",
      "userId": "01561702845917398436"
     },
     "user_tz": -330
    },
    "id": "QlHwycYdIaWO",
    "outputId": "238e7e2a-cdd0-4f56-b411-24dc3a18c219"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The Mean Squared Error of our forecasts is 0.07\n"
     ]
    }
   ],
   "source": [
    "y_forecasted = pred.predicted_mean\n",
    "y_truth = y['1998-01-01':]\n",
    "\n",
    "# Compute the mean square error\n",
    "mse = ((y_forecasted - y_truth) ** 2).mean()\n",
    "print('The Mean Squared Error of our forecasts is {}'.format(round(mse, 2)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "bO8jnqNmIaWS"
   },
   "source": [
    "The MSE of our one-step ahead forecasts yields a value of 0.07, which is very low as it is close to 0. An MSE of 0 would that the estimator is predicting observations of the parameter with perfect accuracy, which would be an ideal scenario but it not typically possible."
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "SARIMA.ipynb",
   "provenance": [
    {
     "file_id": "1m9smVZYvT2mhk_b2sx6ovDdWnvOTKk0K",
     "timestamp": 1557984821190
    }
   ],
   "version": "0.3.2"
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}