{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#| hide\n",
    "!pip install -Uqq nixtla hierarchicalforecast"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#| hide \n",
    "from nixtla.utils import in_colab"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#| hide \n",
    "IN_COLAB = in_colab()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#| hide\n",
    "if not IN_COLAB:\n",
    "    from nixtla.utils import colab_badge\n",
    "    from dotenv import load_dotenv"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Temporal Hierarchical Forecasting with TimeGPT"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this notebook, we demonstrate how to use TimeGPT for temporal hierarchical forecasting. We will use a dataset that has an hourly frequency, and we create forecasts with TimeGPT for both the hourly and the 2-hourly frequency level. The latter constitutes the timeseries when it is aggregated across 2-hour windows. Subsequently, we can use temporal reconciliation techniques to improve the forecasting performance of TimeGPT."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/tutorials/23_temporalhierarchical.ipynb)"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#| echo: false\n",
    "if not IN_COLAB:\n",
    "    load_dotenv()\n",
    "    colab_badge('docs/tutorials/23_temporalhierarchical')"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1. Load and Process Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "from utilsforecast.evaluation import evaluate\n",
    "from utilsforecast.plotting import plot_series\n",
    "from utilsforecast.losses import mae, rmse\n",
    "from nixtla import NixtlaClient"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "nixtla_client = NixtlaClient(\n",
    "    # api_key = 'my_api_key_provided_by_nixtla'\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/electricity-short-with-ex-vars.csv')\n",
    "df['ds'] = pd.to_datetime(df['ds'])\n",
    "df_sub = df.query('unique_id == \"DE\"')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((1632, 12), (48, 12))"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train = df_sub.query('ds < \"2017-12-29\"')\n",
    "df_test = df_sub.query('ds >= \"2017-12-29\"')\n",
    "df_train.shape, df_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABrMAAAFpCAYAAAA/c9NNAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAA0JtJREFUeJzs3Xd4VNXWx/HvzKT33iu9995UQLCDoqiggr33/l7ler0o9t4r9i5gQ0Ckd+mdUNJ775nJzLx/BHJFWgJJJgm/z/PkwZzZ55w1cSaZs9fZaxnsdrsdERERERERERERERERkWbI6OgARERERERERERERERERI5FySwRERERERERERERERFptpTMEhERERERERERERERkWZLySwRERERERERERERERFptpTMEhERERERERERERERkWZLySwRERERERERERERERFptpTMEhERERERERERERERkWZLySwRERERERERERERERFptpTMEhERERERERERERERkWZLySwREREREWl0M2fOxGAwkJiY6OhQ6iQxMRGDwcDMmTNPOHbq1KnExcU1ekwiIiIiIiKnKyWzREREREREmoFDCbRDX87OzgQFBTFkyBD+7//+j+Tk5CP2Wbx48WH7/PPr66+/dsAzERERERERaVhOjg5ARERERERav6uvvporrrgCV1dXR4dSJ7GxsVRUVODs7Nzk577yyis577zzsNlsFBQUsG7dOl555RVeffVVPvzwQ6644ooj9rnrrrvo37//EdsHDx7cFCGLiIiIiIg0KiWzRERERESk0ZlMJkwmk6PDqDODwYCbm5tDzt2nTx+uuuqqw7YlJSUxZswYpkyZQufOnenZs+dhjw8fPpxLL720KcMUERERERFpMiozKCIiIiIiRzhWH6gnnngCg8FQ+73BYOCOO+5g9uzZdOvWDVdXV7p27crvv/9+2H5H65llt9uZPn06UVFReHh4cNZZZ7F9+3bi4uKYOnXqMc95vGMCzJ07l+HDh+Pp6Ym3tzfnn38+27dvr9fzP1bPrEPP083NjW7dujFr1qx6HfdkxcbGMnPmTMxmM88991yTnFNERERERKS50MosERERERE5JcuXL+fHH3/ktttuw9vbm9dee40JEyaQnJxMYGDgMfebNm0a06dP57zzzuO8885jw4YNjBkzBrPZfNKxfPbZZ0yZMoWxY8fy7LPPUl5ezttvv82wYcPYuHHjURN0dTV//nwmTJhAly5dmDFjBnl5eVx77bVERUUdMbagoACr1XrCY3p4eODh4VGn8w8ePJi2bduyYMGCIx4rKSkhNzf3iO2BgYFHTQSKiIiIiIi0JEpmiYiIiIjIKdm5cyc7duygbdu2AJx11ln07NmTr776ijvuuOOo++Tk5PDcc89x/vnn8/PPP9cmXP71r3/x9NNPn1QcpaWl3HXXXdxwww289957tdunTJlCx44defrppw/bXl8PP/wwoaGhLF++HF9fXwDOOOMMxowZQ2xs7GFje/fuTVJS0gmP+e9//5snnniizjF069aNOXPmUFxcjI+PT+3266677qjjMzIyCAsLq/PxRUREREREmiMls0RERERE5JSMHj26NpEF0KNHD3x8fNi/f/8x9/njjz8wm83ceeedh60cuueee046mbVgwQIKCwu58sorD1ulZDKZGDhwIIsWLTqp40JNUmjTpk088sgjtYksgLPPPpsuXbpQVlZ22PgvvviCioqKEx63TZs29YrDy8sLqFmJ9fdk1rRp0xg+fPgR4wMCAup1fBERERERkeZIySwRERERETklMTExR2zz9/enoKDgmPscWrXUvn37w7YHBwfj7+9/UnEkJCQAMHLkyKM+/vfkT30dK16Ajh07smHDhsO2DR069KTPdTylpaUAeHt7H7a9e/fujB49ulHOKSIiIiIi4mhKZomIiIiIyBGO1WfpaH2gTCbTUcfa7fYmjcVmswE1fbOOVlrPyanpLn9ycnLq1DPLy8urdrVVXWzbto2QkJBTSsyJiIiIiIi0NEpmiYiIiIjIEfz9/SksLDxie136QNXFoR5TCQkJh5Xay8nJOWJF16GVWoWFhfj5+R0zlkOlDkNCQhp8ldLf4/2n3bt3H7Gtf//+Dd4za9WqVezbt4+rrrqqTuNFRERERERaCyWzRERERETkCG3btqWoqIgtW7bQo0cPoKZv1KxZsxrk+KNHj8bZ2ZnXX3+dMWPG1K6+euWVV44aC8DSpUu56KKLACgrK+OTTz45bNzYsWPx8fHh6aef5qyzzsLZ2fmwx3NycggODj6peMPDw+nVqxeffPLJYX2zFixYwI4dO2qTXYc0dM+spKQkpk6diouLCw8++GD9n4CIiIiIiEgLpmSWiIiIiIgc4YorruDhhx/m4osv5q677qK8vJy3336bDh06HNEf6mQEBwfzwAMPMGPGDC644ALOO+88Nm7cyNy5cwkKCjps7JgxY4iJieH666/nwQcfxGQy8dFHHxEcHExycnLtOB8fH95++22uvvpq+vTpwxVXXFE75tdff2Xo0KG88cYbJx3zjBkzOP/88xk2bBjXXXcd+fn5vP7663Tt2rW2l9Uhp9Iza8OGDXz++efYbDYKCwtZt24dP/zwAwaDgc8++6w2ufh3y5Yto7Ky8ojtPXr0OOp4ERERERFpPHa7nerq6jqVHj+dOTs7H7Ns/T8pmSUiIiIiIkcIDAxk1qxZ3HfffTz00EPEx8czY8YMEhISGiSZBTB9+nTc3Nx45513WLRoEQMHDmT+/Pmcf/75h41zdnZm1qxZ3HbbbTz++OOEhYVxzz334O/vz7XXXnvY2EmTJhEREcEzzzzD888/T1VVFZGRkQwfPvyIsfV1zjnn8N133/HYY4/x6KOP0rZtWz7++GPmzJnD4sWLT+nYf/fVV1/x1Vdf4eTkhI+PD+3bt+eee+7hlltuISYm5qj7vPbaa0fd/u9//1vJLBERERGRJmQ2m8nIyKC8vNzRoTR7BoOBqKioOvURNtgbqiuziIiIiIhIA4iLi+PMM89k5syZjg5FRERERESkzmw2GwkJCZhMJoKDg3FxcaktqS6Hs9vt5OTkUF5eTvv27U+4Qksrs0RERERERERERERERE6R2WzGZrMRHR2Nh4eHo8Np9oKDg0lMTMRisSiZJSIiIiIicojZbCY/P/+4Y3x9fXF3d2+iiEREREREpLUxGo2ODqFFqM+qNSWzRERERETktLFy5UrOOuus4475+OOPmTp1atMEJCIiIiIiIiekZJaIiIiIiDQriYmJjXbsnj17smDBguOO6dq1a6OdX0REREREROpPySwRERERETlt+Pv7M3r0aEeHISIiIiIiIvWgwo0iIiIiIiIiIiIiIiLSbGll1j/YbDbS09Px9vauV/MxERERERERERERERFpXux2OyUlJURERGA0an1PS6Vk1j+kp6cTHR3t6DBERERERERERERERKSBpKSkEBUV1aTntNvtVFisTXrOQ9ydTXVesPPpp59y7733kp6ejqura+328ePH4+3tzWeffdZYYdaZkln/4O3tDdS8sH18fBwcjYiIiIiIiIiIiIiInKzi4mKio6Nr5/6bUoXFSpdp85r8vAA7nhyLh0vdUkCXXXYZd911Fz/99BOXXXYZANnZ2fz666/Mnz+/McOsMyWz/uFQptLHx0fJLBERERERERERERGRVkBthY7N3d2dSZMm8fHHH9cmsz7//HNiYmI488wzHRvcQUpmiYiIiIiIiIiIiIiINDB3ZxM7nhzrsHPXx4033kj//v1JS0sjMjKSmTNnMnXq1GaTBFQyS0REREREREREREREpIEZDIY6l/pztN69e9OzZ08+/fRTxowZw/bt2/n1118dHVatlvFTFBERERERERERERERkUZzww038Morr5CWlsbo0aOJjo52dEi1jI4OoK6sViuPP/448fHxuLu707ZtW/773/9it9trx9jtdqZNm0Z4eDju7u6MHj2ahIQEB0YtIiIiIiIiIiIiIiLS/E2aNInU1FTef/99rrvuOkeHc5gWk8x69tlnefvtt3njjTfYuXMnzz77LM899xyvv/567ZjnnnuO1157jXfeeYc1a9bg6enJ2LFjqaysdGDkIiIiIiIiIiIiIiIizZuvry8TJkzAy8uL8ePHOzqcw7SYMoMrV65k3LhxnH/++QDExcXx1VdfsXbtWqBmVdYrr7zCY489xrhx4wD49NNPCQ0NZfbs2VxxxRVHPW5VVRVVVVW13xcXFzfyMxEREREREREREREREWl+0tLSmDx5Mq6uro4O5TAtZmXWkCFDWLhwIXv27AFg8+bNLF++nHPPPReAAwcOkJmZyejRo2v38fX1ZeDAgaxateqYx50xYwa+vr61X82pBmRzVm218cnKRH7dkoHNZj/xDiIiIiIiIiIiIiIi0iwVFBQwa9YsFi9ezO233+7ocI7QYlZmPfLIIxQXF9OpUydMJhNWq5WnnnqKyZMnA5CZmQlAaGjoYfuFhobWPnY0jz76KPfdd1/t98XFxUponUC5uZo7vtzIn7uyAege6cu/zu/MoDaBDo5MRERERERERERERETqq3fv3hQUFPDss8/SsWNHR4dzhBaTzPr222/54osv+PLLL+natSubNm3innvuISIigilTppz0cV1dXZvdcrnmLKekius/WceW1CJcnYw4m4xsTSviivdWM7pzKI+e14m2wV6ODlNEREREREREREREROooMTHR0SEcV4tJZj344IM88sgjtb2vunfvTlJSEjNmzGDKlCmEhYUBkJWVRXh4eO1+WVlZ9OrVyxEhtzr7c0qZ+vE6kvPL8fdw5oMp/YkN9ODVPxL4cm0yf+zMYtHubCYNiOH6YfHEBXk6OmQREREREREREREREWnhWkzPrPLycozGw8M1mUzYbDYA4uPjCQsLY+HChbWPFxcXs2bNGgYPHtyksbZG65MKmPD2SpLzy4kJ8OCHW4fQN9afIC9X/ju+G/PuGcHozqFYbXY+W53EmS8sZtybK/ho+QGySyodHb6IiIiIiIiIiIiIiLRQLWZl1oUXXshTTz1FTEwMXbt2ZePGjbz00ktcd911ABgMBu655x6mT59O+/btiY+P5/HHHyciIoLx48c7NvgWbt72TO76aiNV1TZ6Rvny4dT+BHkdXpqxXYgXH0zpx6p9eby1eC8r9uayOaWQzSmFTP91B0PbBXHt0DhGdgo9xllERERERERERERERESO1GKSWa+//jqPP/44t912G9nZ2URERHDzzTczbdq02jEPPfQQZWVl3HTTTRQWFjJs2DB+//133NzcHBh5y1ZUbuGB7zZTVW1jVKcQXp/UGw+XY79sBrcNZHDbQHJKqvhlSzqzN6WzOaWQZQm5rNibyy93DqdLhE8TPgMREREREREREREREWnJDHa73e7oIJqT4uJifH19KSoqwsdHSReAJXty+GNHFv++sAtOpvpXpkzMLeOh77ewNjGfO0e24/4xHRshShERERERERERERGRwzXlnH9lZSUHDhwgPj5ei2zqoD4/rxbTM0sc54wOwfx3fLeTSmQBxAV5csWAaADmb89qyNBERERERERERERERKSVUzJLmsTITiGYjAZ2Z5WQlFfm6HBERERERERERERERKSFUDJLmoSfhwsD4wMAWLBDq7NERERERERERERERJqLM888k3vuuafBjjd16lTGjx/fYMdTMkuazNldQgGYr2SWiIiIiIiIiIiIiIjUkZJZ0mQOJbP+Sswnr7TKwdGIiIiIiIiIiIiIiDQeu91OmdXqkC+73V7nOKdOncqSJUt49dVXMRgMGAwGEhMT2bZtG+eeey5eXl6EhoZy9dVXk5ubW7vf999/T/fu3XF3dycwMJDRo0dTVlbGE088wSeffMKcOXNqj7d48eJT+lk6ndLeIvUQ5e9B1wgftqcXs3BXNhP7RTs6JBERERERERERERGRRlFus9F26VaHnHvfiO54mkx1Gvvqq6+yZ88eunXrxpNPPgmAs7MzAwYM4IYbbuDll1+moqKChx9+mIkTJ/Lnn3+SkZHBlVdeyXPPPcfFF19MSUkJy5Ytw26388ADD7Bz506Ki4v5+OOPAQgICDil56NkljSps7uEsj29mAU7spTMEhERERERERERERFxMF9fX1xcXPDw8CAsLAyA6dOn07t3b55++unacR999BHR0dHs2bOH0tJSqqurueSSS4iNjQWge/futWPd3d2pqqqqPd6pUjJLmtSYLmG88kcCyxJyqDBbcXepW2ZYRERERERERERERKQl8TAa2Tei+4kHNtK5T8XmzZtZtGgRXl5eRzy2b98+xowZw6hRo+jevTtjx45lzJgxXHrppfj7+5/SeY9FySxpUp3DvYnydye1oIKlCTmM7dowWVkRERERERERERERkebEYDDUudRfc1NaWsqFF17Is88+e8Rj4eHhmEwmFixYwMqVK5k/fz6vv/46//rXv1izZg3x8fENHs+ppeZE6slgMHB2l1AAFuzIcnA0IiIiIiIiIiIiIiLi4uKC1Wqt/b5Pnz5s376duLg42rVrd9iXp6cnUDPfP3ToUP7zn/+wceNGXFxcmDVr1lGPd6qUzJImN6ZLzWqshTuzqLbaHByNiIiIiIiIiIiIiMjpLS4ujjVr1pCYmEhubi633347+fn5XHnllaxbt459+/Yxb948rr32WqxWK2vWrOHpp5/mr7/+Ijk5mR9//JGcnBw6d+5ce7wtW7awe/ducnNzsVgspxSfklnS5PrH+ePn4UxBuYX1SQWODkdERERERERERERE5LT2wAMPYDKZ6NKlC8HBwZjNZlasWIHVamXMmDF0796de+65Bz8/P4xGIz4+PixdupTzzjuPDh068Nhjj/Hiiy9y7rnnAnDjjTfSsWNH+vXrR3BwMCtWrDil+NQzS5qck8nIyE4h/Lghjfk7shjYJtDRIYmIiIiIiIiIiIiInLY6dOjAqlWrjtj+448/HnV8586d+f333495vODgYObPn99g8WllljjEoVKD83dkYrfbHRyNiIiIiIiIiIiIiIg0V0pmiUOM6BCEq5ORlPwKdmeVODocERERERERERERERFpppTMEofwcHFiePtgAOZvz3JwNCIiIiIiIiIiIiIi0lwpmSUOM6ZLKAALdyqZJSIiIiIiIiIiIiIiR6dkljjM4LaBAOzIKKaq2urgaERERERERERERERETp3dbnd0CC1CfX5OSmaJw0T5u+Pv4YzFamd3pvpmiYiIiIiIiIiIiEjL5ezsDEB5ebmDI2kZzGYzACaT6YRjnRo7mIaUlpbGww8/zNy5cykvL6ddu3Z8/PHH9OvXD6jJ4v373//m/fffp7CwkKFDh/L222/Tvn17B0cuR2MwGOge5cfSPTlsSS2iR5Sfo0MSERERERERERERETkpJpMJPz8/srOzAfDw8MBgMDg4qubJZrORk5ODh4cHTk4nTlW1mGRWQUEBQ4cO5ayzzmLu3LkEBweTkJCAv79/7ZjnnnuO1157jU8++YT4+Hgef/xxxo4dy44dO3Bzc3Ng9HIsPSJ9Wbonh62pRY4ORURERERERERERETklISFhQHUJrTk2IxGIzExMXVK+LWYZNazzz5LdHQ0H3/8ce22+Pj42v+22+288sorPPbYY4wbNw6ATz/9lNDQUGbPns0VV1zR5DHLiXWP8gVgS5qSWSIiIiIiIiIiIiLSshkMBsLDwwkJCcFisTg6nGbNxcUFo7Fu3bBaTDLrp59+YuzYsVx22WUsWbKEyMhIbrvtNm688UYADhw4QGZmJqNHj67dx9fXl4EDB7Jq1apjJrOqqqqoqqqq/b64uLhxn4gcpntkTTJrT1YJlRYrbs4nro0pIiIiIiIiIiIiItKcmUymOvWCkrqpW8qrGdi/f39t/6t58+Zx6623ctddd/HJJ58AkJmZCUBoaOhh+4WGhtY+djQzZszA19e39is6OrrxnoQcIdzXjSAvF6w2OzszlEgUEREREREREREREZHDtZhkls1mo0+fPjz99NP07t2bm266iRtvvJF33nnnlI776KOPUlRUVPuVkpLSQBFLXRgMhtrVWVtValBERERERERERERERP6hxSSzwsPD6dKly2HbOnfuTHJyMvC/pmpZWVmHjcnKyqp97GhcXV3x8fE57EuaVvcoPwC2pCqZJSIiIiIiIo5ht9vJKak68UARERERaXItJpk1dOhQdu/efdi2PXv2EBsbC0B8fDxhYWEsXLiw9vHi4mLWrFnD4MGDmzRWqZ8eh1ZmKZklIiIiIiIiTSy/zMx7S/cx8sUl9H/qDz5cfsDRIYmIiIjIPzg5OoC6uvfeexkyZAhPP/00EydOZO3atbz33nu89957QE25unvuuYfp06fTvn174uPjefzxx4mIiGD8+PGODV6Oq3tUTTIrIbuEcnM1Hi4t5mUpIiIiIiIiLZDdbmftgXy+XJvM3K2ZmK222sdemLeb87qHEe7r7sAIRUREROTvWkzWoH///syaNYtHH32UJ598kvj4eF555RUmT55cO+ahhx6irKyMm266icLCQoYNG8bvv/+Om5ubAyOXEwn1cSPE25Xskip2pBfTLy7A0SG1KvtzSvlufSquTkbuGtkeo9Hg6JBEREREREQcJr/MzJSP1h7Wt7l7pC+TBsbww/pU/koqYMZvu3jtyt4OjFJERERE/s5gt9vtjg6iOSkuLsbX15eioiL1z2pCN3yyjj92ZjPtgi5cNyze0eG0eOZqG/O2Z/LlmmRW7c+r3f7chB5M7B/twMhEREREREQcx263c9Nn61mwIwsPFxPjekUwaUBsbcWQbWlFXPjGcux2+OamQQxsE+jgiEVERORUac6/dWgxPbOkdese6QfUXDjIycsvM/PM3F0MnrGQO7/ayKr9eRgM0CnMG4Cn5+4kv8zs4ChFREREREQc4+t1KSzYkYWzycB3twxmxiU9ahNZAN0ifblyQAwA//5pO9V/Kz8oIiIiIo6jZJY0Cz0OXjxsUTLrpKUVVjDh7ZW8s2QfeWVmQn1cuWtkO5Y/PJKf7xxGpzBvCsstPDN3p6NDFRERERERaXL7c0p58ucdADw4tiNdI3yPOu6BMR3xdXdmV2YJX61NbsoQRUREROQYlMySZqFbZM1FxL6cUkqrqh0cTcuzP6eUy95eyYHcMiL93Hn36r6seHgk943pSKSfO84mI09d3A2Ab/9KZV1ivoMjFhERERERaToWq417v9lEhcXKkLaB3DCszTHHBni6cP+YDgC8MH+PqluIiIiINANKZkmzEOztSoSvG3Y7bNfqrHrZnl7ExHdXkV5USZtgT767ZTBju4bhZDr87d03NoArB9T0y/rXrK1YVC5DREREREROE6/+kcDm1CJ83Z15cWJPjEbDccdPGhBDpzBviiosvDB/dxNFKSIiIiLHomSWNBuH6pRvVTKrztYn5XPFe6vJLTXTNcKH724eTISf+zHHP3xOJwI8XdiTVcqHyw+c8vkrLVY+XZXI/O2ZFFdaTvl4IiIiIiIiDW3tgXzeXLwXgKcv7k6477GvmQ5xMhl54qKuAHy1Nln9nUVEREQcTMksaTa6Hyw1uCVVFwl1sTwhl6s+WEtJZTX9Yv358sZBBHq5HncfPw8X/u+8zkDNnYmpBeWnFMNjs7cxbc52bvpsPb2fXMAlb63gpfm7WbM/D3O1DXO1jXJzNUXlFnJKqsgoqsBcrRVhIiIiIiLSNIorLdz7zSbsdpjQJ4rze4TXed9BbQK5sGcEdjs88dN27HZ7I0YqIiIiIsfj5OgARA7pHuUHoDvejsFitbExuZAle7JZsieHbWnFAIzoEMy7V/XF3cVUp+NM6BPJt3+lsPZAPk/8tIMPpvQ7qXh+2pzO9+tTMRggNsCDxLxyNiQXsiG5kNf+3HvM/dqFeDHrtiF4uzmf1HlFRERERETqwm63869Z20grrCA6wJ0nLupS72P833md+GNHFn8lFbB8by7D2wc3QqQiIiIiciJKZkmzcWhl1v7cMoorLficZsmOSouVP3ZmUVBuqV3VZK62UVVtZV9OKSv35lFSVX3YPhf3juSZCd1xdapbIgvAYDDw1PhunPvqMv7YmcW87ZmM7RpWr1hT8sv5149bAbjjrHbcP6YjqQXlrNybx/K9uazYm0veUZokGwywN7uUx2Zv45XLe2EwHL9OvRxfSn45c7dlEBPgwZB2Qafde0ZERERE5HjeWryPnzenYzIaeOXyXid1Q124rzuX9Yvi01VJfL46ScksEREREQdRMkuajQBPF6L83UktqGBbWhFD2gY5OqQmU2mxMvXjtazen3/ccf4ezgxvH8wZHYIZ3iGIEG+3kzpf+1BvbhzRhrcX7+OBbzcTeZM73Q4mE0+k2mrj7q83UlJVTZ8YP+4e1R6AKH8PJvb3YGL/aGw2OwXlZpxMRlxMRpxMBpyMBtYnFXD5e6uZsymdYe2CuKxf9EnFf7orKDPzxqK9fLYqCbO1pmyjyWigV7QfI9rXvDZ6RPriZFIlWRERERE5Pc3fnsnz83YD8MRFXekbG3DSx7pqUCyfrkrij53ZZBZVEuZ7ctdhIiIiInLylMySZqVHlC+pBRVsTT19klnVVht3fLmR1fvz8XJ1Yli7IFycjLg4GXE2GXF1MhLk5cLw9sF0i/TFZGyY1Ux3j2rP+sQC1ibmc/WHa/j6psF0DPM+4X6vLkxgQ3Ih3m5OvHpF76MmTIxGw1H7d/WLC+De0e15Yf4eps3ZTp9Yf9oGezXI8zkdVFqsfLTiAG8v3kdJZc0qvT4xfhRWWNifU8b6pALWJxXw8h97CPJy5d8XduGCHuFaASciIiIip5Ud6cXc880mAK4ZHMvVg2JP6XgdQr0ZEB/A2gP5fLU2mXvP7tAAUYqIiIhIfSiZJc1K90g/ftuayZbTpG+WzWbn4R+28sfOLFycjHwwpR+D2gQ2ybndnE18OLUfV324ls0phVz14Rq+vXkw8UGex9xn1b483lhU0w/r6Yu7Ex3gUe/z3npmO1buy2Plvjzu+HIjs24bgptz3csknk4qLVZSCypIKShnb1YpH604QEZRJQCdw3145NxOjGgfhMFgILWgnGUJuSxLyGF5Qi65pVXc+dVGftuawZPjuhHsfWRyEaCq2kpCVilxQZ54uepPgoiIiIi0bLmlVdz46V+Um60MbRfI4xfUv0/W0Vw1KJa1B/L5el0yd4xsh7OqIIiIiIg0KYPdbrc7OojmpLi4GF9fX4qKivDx8XF0OKed5Qm5XPXhGmICPFj60FmODqdR2e12/vvLTj5acQCT0cA7V/Xl7C6hTR5HYbmZK95bza7MEiJ83fj2lsFE+R+ZpCooM3Puq8vILK5kYr8onru050mfM6u4kvNeXUZemZmpQ+J44qKup/IUWpUFO7J4b+k+kvPLySquOuLxCF83HhjbkfG9IjEeY5WeudrGG4v28taivVTb7Ph7OPOfcd248OAqLZvNztrEfOZsSuO3rZkUVVgwGQ10i/BhYJtABsYH0C8uAF/3hu/BlV1cybKEXAa1DSTSz73Bjy8iIiIip6+qaiuT31/DX0kFxAd5Mvu2ofh6NMxnWnO1jSHPLCS31Mzbk/twbvfwBjmuiIiIND7N+bcOSmb9g17YjlVUbqHnk/MB2DTtbPw8XBwcUeN5fWECLy7YA8CLl/VkQt8oh8WSW1rFxHdXsT+njNhAD769eTChPm4UV1rYkV7MtrQift2awcbkQtoEefLLXcPwcDm1VTyLdmdz7cfrAHjv6r6M6RrWEE+lRbNYbQx55k9ySv6XxPJ0MREd4EF0gAeD2gQyeWBMnVeybUsr4sHvt7AzoxiAsV1DiQ/y4qdNaaQfXOEF4OFiotxsPWxfgwFGdgzh9Um9T/n/dWG5mbnbMvlpUzqrD+Rht0N8kCdz7x6uVXkiIiIiUm92ux2rzY7Fasdis2GptmGx2nl+3m5+2JCKt5sTs24bSruQhi1p/vy8Xby5aB9D2wXyxQ2DGvTYIiIi0ng05986KJn1D3phO94Zzy8iKa+cz68fyLD2rbNv1merk3h89jYApl3QheuGxTs4IsgsquSyd1eSkl9BuK8bziYjyfnlh41xMRn58bYhdIv0bZBzPvXrDt5fdgA/D2d+u2s4Eaf5Sp1ft2Rw+5cbCPZ25f1r+hET4IG/h/Mp9bwyV9t4a/Fe3vizZpXWId6uTpzbPYzxvSIZ2CaQzOJK1h7IY83+fNYeyGd/bhlwaq/PdYn5vLtkH0v25GCx/u/cLk5GzNU27hzZjvvHdDzp5yYiIiIirUNRhYUv1iRRVGHB1WSs7SHsYjJitdes7s8oqiSzuJKs4koyiyqpqrYd9Vgmo4GPp/ZnRIfgBo8ztaCc4c8twm6HP+8/gzbq/ysiItIiaM6/dVAy6x/0wna8O7/ayM+b0xnePogPp/THxal11SLfl1PK6JeWYLfDXSPbcV8zmsxPyS9n4ruravsyAUT6udM1wodukb6M6RpKp7CGe1+Yq21c+s5KtqQWcUmfSF6a2KvBjt0SXfHeKlbvz2+U18WO9GJe+WMPRoOBi3pFMLJTyHFXRX2+OonHZm8j0s+dxQ+eWe+eAKkF5Yx8cQnmg5MMncK8uahXBBf2iGBrWhG3fbEBZ5OB3+4aTvtQ71N6biIiIiLSchWWm7nqwzVsSys+peM4GQ34uDvzyDmdmNg/uoGiO9INn6zjj53ZXD8svsH6cYmIiEjj0px/66Bk1j/ohe1429KKuOydVVRYrFzUM4JXLu91zN5ALdFLC/bw2sIEhrcP4tPrBpzSqpvGkFZYwR87smgb7EXXCB/8PRu31OP6pHwmvL0KDxcTfz02+pRL2rVUe7NLGP3SUowGWP7wSIevUqu0WBn27J/klpp55fJejO8dWa/97/1mE7M2ptE7xo9nJ/Sgw98SVna7nRs++YuFu7LpF+vPtzcPblXvcRERERGpm8JyM5M/WMP29GICPV0Y3zsSi9WGubrmq8pqwwCEeLsR7utGqK8bYT41Xz7uTjibjAe/DE12XXWoXLqPmxNr/m807i4qmy0iItLcac6/dTg9Z42lWesW6cvbV/Xhhk/+4qfN6QR4uvDvC7s0u6TPybDb7fyyJR2AS/pENsvnFOnnzpQhcU12vj4x/sQEeJCcX86CHVmM61W/pElr8fnqZABGdQ51eCILwM3ZxLVD43l+3m7eWbKPcb0i6vx63ZZWxKyNaQA8eVG3wxJZAAaDgSfHd2PVS0v4K6mAr9elMGlgTIM/BxERERFpvgrKahJZOzKKCfJy4csbBx3xubE5OqN9MNEB7qTkV/DzlnQm9mu8VWAiIiIi8j+tq36btBpndgzhxYk9AZi5MpG3Fu9zcEQNY0dGMftzynBxMjK6c6ijw2kWDAZD7aqfHzekOTgaxyg3V/PD+lQArh4U6+Bo/ueqgbF4uJjYlVnC0oTcOu1jt9uZMXcnAON6RdA96uj91SL93Lnv7A4AzJi7k+ySyqOOExEREZHWJ7/MzKS/JbK+aiGJLACj0cDkgTWf2b9YneTgaEREREROH1qZJc3WuF6R5JeZ+c/PO3h+3m4CPF24ckDLXr3xy5YMAEZ2DMHbzdnB0TQfF/eO5LWFCSxLyCGnpIpgb1dHh9Sk5mxKp6SqmthAD4a1C3J0OLV8PZy5ckAMHy4/wDuL93FGHZpoL9mTw4q9ebiYjDxwgr5fU4fEMXtTGtvSivnvLzt5/credYprX04pX69Nxt/ThX6xAfSI8j1u/y8RERERaT7yy8xMen81uzJLCPJy5asbB7a4HqqX9Y3ipfl72JxaxJbUQnpE+Tk6JDkJO9KLeXXhHgrKLdhsdmx2OzZ7zQ16bs4mekX70S8ugL6x/gQ0cvl9EREROTEls6RZu3ZoPHmlZt5YtJd/zdqKv4cz53QLd3RYJ8Vut/Pz5poSgxf0bJnPobHEB3nSK9qPTSmF/Lw5neuGxTs6pCZjt9v5bFXNHZ1XDYxtdr2jrhsWzycrE1m1P4/NKYX0jPY75lirzc6M33YBMGVILNEBHsc9tpPJyDOX9OCiN5bz8+Z0JvSJ5MyOIcccX2mx8uaivby7ZD9mq612u4vJSLdIH/rFBXBGh2CGNqOEoIiIiIj8j8Vq4+oP19Qmsr6+aSDtQlpWIgsg0MuV87qHMXtTOi8t2MMbk/rg5Xrs6RWL1cYP61NxcTJySZ+oJoxUjuXnzek8+P1mKi22Y45ZcyCfd5fuB6BNsCf9YwOYPChGyUsREREHabFlBp955hkMBgP33HNP7bbKykpuv/12AgMD8fLyYsKECWRlZTkuSGkQ94/pwJUDorHZ4a6vN7E+qcDRIZ2UzalFpBZU4OFiYmSnY0/Yn64uPlhqcPam06vU4MaUQnZkFOPiZOTSvs3vwjbSz52LekYA8N7BC7lj+WFDKruzSvB1d+aOs9rX6fjdIn25dmhN8vKx2dtYeyCfSov1iHGLdmVz9stLeP3PvZitNoa3D+LcbmEEe7tittrYkFzIe0v3M/mDNXyw7PhxioiIiIhjfL8+le3pxfh7OPP1TYNaZCLrkGuHxmM0wOLdOYx9eSlL9+Qcddy6xHwueG05j/y4lfu+3cyuzOImjlT+zmqz88zcXdz51UYqLTXXFW9N7sM7V/Xh3av78v41/fhwSj+eu7QHV/SPpl2IFwD7c8r45q8ULn93tUqki4iIOEiLXJm1bt063n33XXr06HHY9nvvvZdff/2V7777Dl9fX+644w4uueQSVqxY4aBIpSEYDAamj+9ObqmZBTuyuPmzv5h9+1Ci/I+/6qO5ObQqa1TnUDxcWuRbr1Fd0COc//6ygy2pRezNLq29aGjtPj9YZ//CHhH4N9PSFTed0YYfN6Yxd1sGibllxAV5HjGmwmzlxfm7AbjjrHb4etS9jOZ9Z3fg922ZpBZUMPHdVTibDHSN8KVvrD+9ov34bWsGc7dlAhDm48a/L+zCOd3CMBgM2O12kvPL+SuxgCV7cvhpczoz5u6ia4Qvg9sGNswPQEREREROWVW1ldcXJgBw58j2Lf7zfs9oPz67fiCP/LiFlPwKrvloLZf2jeLx87vg6+FMXmkVM+bu4vuDvXEP+W1LBp3CfBwU9emtqNzCnV9vrE083nxGGx4a2wnTMapjTOwXDUBBmZkNyQW8MH8POzOKeXfJfh6/oEuTxS0iIiI1DHa73e7oIOqjtLSUPn368NZbbzF9+nR69erFK6+8QlFREcHBwXz55ZdceumlAOzatYvOnTuzatUqBg0aVKfjFxcX4+vrS1FRET4++oDZnJRVVXPZO6vYkVFMpzBvvr91yHFLOTQnNpudIc/8SWZxJe9d3ZcxXcMcHVKzdP3MdSzclc0dZ7XjgbHH77fUGhSUmRk4YyHmahuzbhtC7xh/R4d0TFM/Xsvi3TlcNSiG6eO7H/H4m4v28vy83UT5u7Pw/jNwdapfD6vdmSW88sce/koqIKek6ojHTUYD1w2N4+7RHY75vrfb7dz/7WZ+3JhGkJcLP985jHBf93rFISIiIiKN45OVifz7p+2E+bix+MEzW03P03JzNc/P283MlYnY7RDs7crEflF8vjqZogoLAFcOiKZjqDdP/LyDNsGeLLzvDAyG5lVevLHYbHYKys2UVlVTWlVNWZWVsqpqyszVmAwG3F1MuDub8HBxwt3FiLPJSLnZ+rfxNV/ebs4MiA8gyOvk+ivvySrhxk//IimvHDdnI89d2rO2AkVdLUvI4eoP1+LqZGTpQ2cR6uN2UrGIiEjT05x/69AyMgF/c/vtt3P++eczevRopk+fXrt9/fr1WCwWRo8eXbutU6dOxMTEHDeZVVVVRVXV/yZOi4u15L+58nR14oMp/Rj35gp2ZZZw91cbee+afse8i6o5WZ9cQGZxJd6uTpzRMdjR4TRb43tHsnBXNrM3pXHf2R2aXf+ohvbd+hTM1Ta6RvjQ6zi9qJqDm0e0ZfHuHL77K5V7RneovYi0WG0k5ZXz9uJ9ADw4tmO9E1kAHcO8efuqvtjtdlILKvgrKZ+/EgvYmFxIiI8rD5/Tic7hx/+wYTAYeOri7uzMLGFnRjG3fr6Bb24edFLxiIiIiEjDqTBbeWPRXgBuH9mu1SSyADxcnPj3hV25oEc4D36/hf05Zby5qOazcedwH566uBt9Yvwprarm6bm72J9Txq7MkhN+tm3psksq+XZdCl+tTSGtsKLBjts+xItBbQIZ3Dawzsmt9Un5TPloHaVV1UT5u/Pe1f3oElH/n/+wdkH0j/NnXWIBby3ay3/GdTuZpyAiIiInqUUls77++ms2bNjAunXrjngsMzMTFxcX/Pz8DtseGhpKZmbmMY85Y8YM/vOf/zR0qNJIIvzcef+aflz+7ioW7srm2d938X/ndXZ0WCd0qMTgmK5hmlg/jtGdQ/FydSK1oIL1yQX0jwuo0352u52Mokoi/FrOKhybzc4Xa5IBuHpQbLO/M3NQmwB6RvmyObWIye+vwWQ0kF1SSV6ZmUPre7tH+nJhj/rd3fhPBoOB6AAPogM8uLh3/XuIubuYePeqvlz4xnI2pRTyn5938PTFR64kExEREZGm8/nqJHJKqoj0c+fyg6XbWpu+sQH8dtdwXv8zgbnbMrlqYCzXDI7FyVTTqtzL1YkzOwQzf0cWv27JaJXJLLvdzqr9eXyxOpl52zOptv2vEJC7swkvNye8XJ3wdK1ZiWW32yk3W6mwWKk0Wym3WDFX2/BwccLL1YSnqxOerjX7pBdWsCuzhITsUhKyS/nsYLn28b0ieOri7ngeo3rD2gP5XPvxWsrMVgbEB/DOVX0JOMny7gaDgXtHd2DSB2v4am0KN5/RtkVdg4qIiLR0LSaZlZKSwt13382CBQtwc2u4pdyPPvoo9913X+33xcXFREe3zg/XrUWvaD+ev6wnd321kfeW7qdtsCeX949xdFjHVG218dvWDAAu6Bnu4GiaN3cXE+d0C+P79an8uCGtTsmslPxyHvp+C6v253HlgBievrhbs08MASzZk0NSXjnebk5c1OvUEkBNwWAwcMsZbbn1iw3szio57DFnk4FIP3eeHNe1Waymiwn04NUrenHtzHV8uSaZXlF+TOyv3+siIiIijlBWVc3bS2pWKt09qj0uTkYHR9R43JxNPDi2Ew+O7XTUx8/vEc78HVn8tjWD+8d0aBHXLXU1f3smz/xes/LskD4xflw1KJbzuoc3yGq8gjIzaw7ks3p/Hqv357Ers4TZm9LZmlbEO1f1pX2o92HjV+3L47qZ66iwWBnWLoj3r+mHu8upxTG4bSAD4wNYcyCfNxft5SndOCciItJkWkwya/369WRnZ9OnT5/abVarlaVLl/LGG28wb948zGYzhYWFh63OysrKIizs2P2JXF1dcXU9uZrL4jgX9YxgX3Ypry5M4F+zthEb6MmgNoGODuuo1hzIJ7fUjJ+HM8PaBTk6nGbvkt6RfL8+lV+3pPPERV2OuZLNZrPzxdpkZvy2k3KzFYCv1ibj4WLisfM7N+sLQ6vNznPzdgNweb9oPFxaxq/ic7qF8cak3pRVVRPi40aotxuhPq74e7g0iyTW353ZMYT7RnfgxQV7eGzONjqFe9Mjys/RYYmIiIicdmauTCS/zExcoAeX9Il0dDgONapzKK5ORvbnlrEzo+SkSt01NwVlZp74eTtzNtVUI/F0MTG+dySTB8Y2+PPz93ThnG5hnNOtZo5nfVI+t3+xkX05ZVz0xgqemdCdcb1qXmMr9uZy/SfrqLTYGNEhmPeu7tsgCTWDwcC9Z3fgivdW8+1fKdxyRluiAzxO+bgiIiJyYi3mlqhRo0axdetWNm3aVPvVr18/Jk+eXPvfzs7OLFy4sHaf3bt3k5yczODBgx0YuTSWu0e15/we4VTb7Nz2xQZSC8odHdJR/bKl5kP9ud3CcDa1mLecwwxsE0iYjxvFldUs2pVz1DGpBeVc/dEaHp+9jXKzlQFxATx8Ts3djx8uP8CrCxOaMuR6m70xjZ0ZxXi7OXH7We0cHU6dGQwGLugRweX9YzirYwhdInwI9HJtdomsQ24/qx2jO4dirrZx+5cbqLRYHR2SiIiIyGmluNLCe0v3A3D36Pa1JfdOV16uTpx5sIfyr1vTHRzNqZu/PZOzX17KnE3pGA1w8xltWPOv0Tx1cfcmSdT1jQ3gl7uGMbRdIBUWK3d/vYnHZ2/jjx1ZXDezJpF1VseGS2QdMqhNIEPbBWKx2nnzYC84ERERaXwt5pOkt7c33bp1O+zL09OTwMBAunXrhq+vL9dffz333XcfixYtYv369Vx77bUMHjyYQYMGOTp8aQRGo4EXL+tJt0gf8svM3PTpeirMzWuy2mK1MXdbTc+2U+0ldLowGQ2MO1h2b/bGNKCmYfS+nFKWJeTwzpJ9jH15KSv25uHmbGTaBV34+qZB3HpmW564sAsAr/yRwAfL9jvsORxPpcXKi/NrVmXddmY7/E+yXrucmNFo4KXLexLm40ZKfgWfrUpydEgiIiIip5UPlx2gqMJCuxAvLup5eq/KOuT8g9eFv23NxG63n2B081RQZuburzdy02fryS2tol2IFz/cOoRHz+2M1zF6VzWWIC9XPr1uIHeOrLlJ8LPVSdzw6V9UVdsY3TmUdxo4kXXIvaM7APDd+lSS8spOMFpEREQaQotJZtXFyy+/zAUXXMCECRMYMWIEYWFh/Pjjj44OSxqRm7OJd6/uR6CnCzsyinnw+83N6oJg+d5cCsstBHm5MrCZlkFsjsb3rrnQXbAziz7/XUDnab8z6sUlXP3hWp6Zu4sys5V+sf7MvXsE1w2Lr10ZNHVoPA+O7QjA9F938uWaZIc9h2P5aMUB0osqifB149qhcY4Op9XzcXPmvrNrLjTfWLSXogqLgyMSEREROT0UlJn5aPkBoGbi39RMV/M3tVGdQnB1MnIgt4wdGcWODqfe0gsrOOfV/63GuuWMtvxy5zB6x/g7LCaT0cD9Yzry8bX98fNwBmBs11DemtznmGXrT1W/uABGdAjGarPz+p9anSUiItIUDPbmNPPfDBQXF+Pr60tRURE+Pi2/fvXpYu2BfCa9v5pqm52Hz+nErWe2PWLMzoxinp+3GxeTkWcv7YGvu3ODnNtut7MxpZD527MoqrBQabFSYbZSWW1lb3YpqQUVTBkcy3/GdWuQ850uxr2xnM2pRbXfe7qYiPR3J9zXnVGdQ5g8MPaoF8R2u51nf9/NO0v2YTDAK5f3qq2b7mh5pVWc+fxiSqqqeWliTy7pE+XokE4LVpudc19dyp6sUm45oy2PnHv0htwiIiIiUn92u52lCbnszS4lq7iSzKKar6T8MrKKq+gU5s1vdw1vtqWpHeGWz9bz+/ZMbjuzLQ+d03I+m9psdiZ/sIZV+/OID/LkpYk9HZrEOpqs4ko2JhcyqnNIo5f535hcwMVvrcRogIX3n0l8kGejnk8cr9JqY0FeMT293Ylxd3V0OCJSD5rzbx2adv23SCMZEB/AExd15bHZ23hu3i46hXtzVscQAIrKLby0YDefrU7CdjB1m5hXxqfXDyDE2+2kz1lUbuHHjal8vTaF3Vklxx17sZIW9fbh1P5sSysi1MeNCD93fNycMBhOfAFsMBh4+JyOlFVV89nqJO7/djOdw33oEOrdBFEf3+t/7qWkqpou4T6MbyYJttOByWjg4XM6cf0nf/HxigNcMziWCD93R4clIiIi0uKVVFp44LvNzNueddTHDQZ45NxOSmT9w/k9wvl9eya/bc3gwbEd63Sd0xx8tOIAq/bn4e5s4qOp/Ztl8ibUx41zuoU1ybl6x/gzslMIf+7K5r2l+5hxSY8mOa80Pavdzg9ZBTy7P4O0KguuRgO3RYdwR2wInqbGWf0nIiJH0sqsf1CWtmV79MetfLU2GW83J2bdNpR1ifk8P283+WVmoKbUwIbkQnJKqogJ8ODz6wcSE+hRp2NbbXbSCytIyC7h580Z/LY1g6pqGwCuTkbO6x5OfJAn7s4m3FxMuDkZcXcxEe3vQc9ov8Z6ynIMNpudGz79iz93ZXNutzDevqqvQ+NJzC1j9EtLqLbZ+fz6gQxrH+TQeE43drudy99dzdrEfCb2i+K5S3s6OiQRERGRFm1vdik3f/YX+3LKcDEZGd0lhHBfd8J83AjzrfmKDfAgxOfkbyBsrcqqquk7fQGVFhu/3DmMbpG+jg7phHZmFDPujRWYrTaevrg7kwbGODqkZmHVvjyufH813q5OrHtsdKP05xLHsdvt/JFXzFP7M9hVVgmAh8lIubVmLijS1Zlp7SK4KNivxSSlRU5XmvNvHbQyS1qV/1zUlYSsEv5KKuDcV5disdbkajuEevHEhV0Z0i6IpLwyrv5wLcn55Ux4ZyWfXjeAzuGH/xIzV9tYtT+PdQfy2ZdTyv6cMg7klWE+mLw6pFOYN5MGxjCuV2SDlS2UhmE0Gnjk3E4s2p3N3G2ZbEsrcuhF4nPzdlFts3NGh2AlshzAYDDwyHmduOStlXy/PpUbhrdpFqv1RERERFqiedszuf/bzZRWVRPm48bbV/VpduXmmjNPVyfO6hjC3G2Z/Lo1o9knsyotVu79ZhNmq43RnUO4ckC0o0NqNgbGBxDp505aYQXztmc2mxL3cur+Kipj+r50VheVAeDrZOLOmBCujwrmz/xi/r03jdRKCzdvT+ITvzyeah9JZy9VABERaUxamfUPytK2fNkllVz0+goyiyvxdnXinrM7cM3g2MPqZWcXV3LNR2vZlVmCt5sTH03tT5dwH5bsyWHe9kz+3JVNSWX1Ecd2MRmJDfSgX5w/l/ePoWeUr+6+aebu/WYTszamcWbHYGZeO8AhMWxILuCSg7XUf7t7OJ3C9LvFUW79fD1zt2UyunMIH0zp7+hwRERERFoUq83Oywv28MaivUBNufc3J/Uh2Fu9Y+rrly3p3PHlRmIDPVj8wJnN+rpy+i87+GD5AYK8XPj9nhEEeen/99+9NH83r/25lxEdgvn0Osdcc0rDSSirZMb+DH7Lrenh7Wo0cENUMHfGhODn/L81ARVWG28mZ/NGchaVNjsmA9wVE8p9cWE4q7SqSLOjOf/WQcmsf9ALu3VIyitj/vYsxveOPOaFVVGFhRs+Wce6xAJcnGoSXX9feRXk5cpZHYPpGOZN22Av2gR7EuXvgUkfSlqUpLwyRr1YU97v+1sG0y8uoEnPb7XZmfjuKtYnFai8XTOwL6eUMS8vxWqz8+3NgxkQ37SvBxEREZGWqtxczR1fbuTPXdkAXDc0nkfP63TYTYNSd+Xmavr8t/mXGlyxN5fJH6wB4MMp/RjVOdTBETU/ibllnPnCYowGWPnIKMJ8VVqzJcqoMvPCgUy+ysjHBhiBy8MDeCAujEg3l2Pul1Jp5om9afyaU5P86uXtwRtdYmjnodeBSHOiOf/WQZ86pVWKDfTkxhFtjnuHoK+7M59eN5CRnUIwV9swV9uIDfTgphFt+OHWwaz9v1E8f1lPbhjehrM6hRAb6KlEVgsUG+jJZf1qymA8P283TZ2/f+rXnaxPKsDd2cR9Z3ds0nPLkdoGe3FF/5rXw4y5O5v89SAiIiLSEhWWm7nqgzX8uSsbN2cjr1zei2kXdlEi6xR4uDgxslMIAJ+uSsRma36fS4vKLdz/7WYAJg2MUSLrGOKCPOkf54/NDrM2pjk6HKmnpIoqntqXzuDVO/niYCLrnCAfFg3oxMudYo6byAKIdnPhw27xvNMlFl8nE5tKyjl73W5mpuXqelNEpIFpZdY/KEt7+rFYbSzcmUVckCcdQ72bdXkHOTnphRWc+fxizFYbn18/sMl6Vn2+OonHZm8D4M1JfTi/R3iTnFeOL7u4kjOeX0yFxcobk3pzQY8IR4ckIiIi0mxlFlVyzUdr2JNViq+7Mx9N7U/fWPXHagh/7Mjihk//AqBvrD/PTuhBuxAvB0dVY1NKIdN/2cFfSQXEB3ny613D8HBR2/Vj+XptMo/8uJV2IV4suHeE5hXqwGa3k2+x4u1kxNXYdInxfEs1ywtKWVZQwpL8EpIrzbWPDfD15LE24QzwO7n3YXqlmbt3JbOsoBSAkQHevNwphlBX9VgXcTTN+bcOSmb9g17YIq3Tf37ezscrEukZ7cfs24Y0+sXFsoQcpn68DqvNzgNjOnDHyPaNej6pn5cW7OG1hQl4uTrxw61D6Bjm7eiQRERERJqdA7llXP3hGlILKgj1ceWz6wfSIVSfmxrSF2uSmPHbLkqrqnFxMnLP6PbcNLwNTg5a9bYltZCXF+xh0e4cAFydjHxz82B6Rfs5JJ6WorjSQv/pf1BVbWPO7UPpqZ/XYbaXVrCmsJSkCjMHKqpIrDCTXFlF5cEViQHOJkJdnGu+XJ0JdXE6+O/h39cn6VVhtXGgooqE8kr2llWxt7yS3WWV7Cyr5O8ToU4G6OfjyW0xIZwd6HPKcwU2u52P0nKZvi+dSpsdT5ORayICuSU6REktEQfSnH/roGTWP+iFLdI65ZRUMeK5RVRYrLx/TT/O7tJ4JTL2Zpdw8VsrKams5pLekbw4safuzGtmzNU2rv5wDWsO5BPp586s24cQ4q2a5iIiIiKHbEsrYurHa8ktNRMX6MFn1w8kOsDD0WG1SmmFFfzfj1tZsqcmgdQt0ofnJvSkS0TTzUlsTS3ilT/2sPBgTzSjAS7uHcVdo9oRG+jZZHG0ZHd/vZE5m9K5ZnAsT47r5uhwmo2MKjMDVu3E0gDTj94mI/7OTvg7mwhwdsLPyYS3k4kyq40CSzVF1VYKLVYKq63kW6o51hk7erpxhr83w/29GOznhZeT6ZRj+6fdZZXcvTOZTSXlALgYDFwRHsDtMSHEuh+7JYaINA7N+bcOSmb9g17YIq3Xs7/v4u3F++gU5s1vdw3H2Ag90PLLzIx/cwXJ+eX0i/XnixsH4toIH4zl1BWWm7nkrZXszy2jZ5QvX980GHcX/b8SERER2ZhcwDUfrqWkqpquET7MvHbAcfsRy6mz2+38uCGNJ3/ZQVGFBYA2QZ50j/Kle6QvPaP96Brh0+Cl/srN1Tz9204+X50M1CSxxveK5M5R7YkPUhKrPpbuyeGaj9bi6+7M2n+N0nXgQV9m5HHfrhTCXZ25KMSPeHdX4t1diXN3IcLVhRKrlawqC1lmC5lVFrLN1WQe/L5mezVZVRbMJzF96edkop2HK+083Gr/7e3j0WQrpOx2OwvzS3gtKYu1RWUAGIFxIX7cGxdGB0/dUCnSVDTn3zrUKZl1ySWX1PvA77zzDiEhIScVlCPphS3SehWWmxn+7CJKqqp54bKeXNo3qkGPX1Vt5aoP1rAusYCYAA9m3TaEQC9d9DdnibllXPzWCgrKLZzTNYy3JvdplCSniIg4XrXVRpnZirPJoL4vIidw8Vsr2JhcyMD4AN6f0g8fN5XGairZJZU88dN2ftuaecRjRgN0DPNhUJsABrUJZGB8AH4eLid9rk0phdz7zSYO5NZMso/rFcFdo9rTNrh59O1qaaw2O0Of+ZPM4krentyHc7urZzLArdsTmZVdyL2xoTzc5uR+Jna7ncJqK3mWagosVgr+9m+J1Yq3yYSvswl/Jyd8nU34OZkIdnEm0NnUbKqkrC4s5bWkLP7MLwFqklpXhgfwQHwY4a4n/z4WkbrRnH/rUKdkltFoZOLEibi7u9fpoF9++SU7d+6kTZs2pxxgU9MLW6R1e21hAi8t2ANAl3AfxveO4KKekYT5ntwdUXa7nW1pxfy6NYNft6aTkl+Bt5sTs24bQrsQ9RNoCdYl5jP5/TWYrTZuHtGGR8/r7OiQRETkJJVUWlizP58V+3LZkFRAQbmFsqpqSquqqaq2AeBkNHDFgGjuGtmeEB/dES3yT5tTChn35gpcTEZWPDJSK7IcJL/MzNa0IramFrI5tYitqUVkFlceNsZggM5hPgxqE8jITiEMahNQp15bFquNNxft5fU/92K12QnzceOFy3oyrH1QYz2d08Yzc3fxzpJ9jO4cwgdT+js6HIez2e10X7GdPEs1s3q3Y7CfEqVbS8p5MTGT33OLAXAzGrgxKpg7YkLwdT7yZhub3Y6xmSTkRFoyzfm3DnVOZmVmZtZ5pZW3tzebN29WMktEmp0Ks5VHftzCb1szsFhrfv0ZDDC4TSAX9Iggyt8dX3dn/Dyc8XV3xtvNGaMBzFYbFWYr5Qe/CsvNLNyVza9bMkjOL689vrerE29f1VcXgi3MnE1p3P31JgBmXNKdKwfEODYgERGps305pczakMaKfblsSS3CaqtbGSJ3ZxPXDYvjphFt8XXXqhORQ+77ZhM/bkzj4t6RvHx5L0eHI3+TVVzJX4kFrNqfy+r9+ezNLj3scX8PZ8Z0CeOc7mEMbRuEi9Phia0Ks5V9OaX8a/Y2NqcUAnBhzwimj+uGr4d+DzaEvdkljH5pKSajgdWPjjrtk8HbSysYtW43HiYju4Z1w8V44mTr6WJdURnT96Wz5mD5QT8nE5PCA6m02cisspBRZSHTbCHbbOGsAB8+79Hy5lhFmhPN+bcOdUpmLVmyhKFDh+LkVLdyHMuXL6d///64ura8P9p6YYucHgrKzPy6NYM5m9JYl1hwzHEGA5gMBqqPMzHm5mxkVKdQzu8Rzpkdg1W6qIV69Y8EXv5jDyajgd/uGk7HMK2sExFp7nJKqhj5wmJKqqprt8UFejCkXRCD2wQS4eeOp6sJTxcnPF2d8HQ1sSGpkOfm7WJjciEAvu7O3HZmW6YMicPNWf1N5PSWU1LFkGcWYrHamXP7UHpG+zk6JDmOnJIq1hzIY3lCLgt2ZJFXZq59zNvNib6x/pRUVpNbWkVuSRVlZuthj08f341xvSIdEXqrNu7NFWxOKeSx8ztzw/DTOwHxVnI2T+5LZ1SAD1/0PL1/Fkdjt9tZkFfMU/sz2F1Wedyxywd2op2HVpSLnCzN+bcOdUpmnU70whY5/aTkl/PT5nRW7M0lv8xMcYWFwgoL5X+72DvE2WTA3dmEp6sTvaL9uKBHBGd1UgKrNbDb7dzwyV8s3JXNFf2jeWZCD0eHJCIiJ/DKH3t45Y8E2gR7cssZbRnSNpAof48T7me321mwI4vn5+0m4eDKhjbBnnxxw0DCfetWWl3kVNjtdt5dup8Qb1cu6dOwfVxPxaGS3L2i/Zh9+1BHhyP1UG21sTYxn7lbM/l9eyY5JVVHHefiZGRYuyCmj+9GhJ9+3zWGz1Yl8vic7XQO92Hu3cMdHY5DXbl5H4vyS/hPuwhujq5btafTkdVu54esAlYXlhLk7ESYqzMRri6EuTrz333prCgs5bE24dwRG+roUEVaLM35tw71TmadccYZXH/99Vx22WV17qHVkuiFLSKHmKttFFVYqLbZ8HBxwsPFhHMdatBLy7UuMZ/L3lmFm7OR1Y+OOqWG2iIi0riqqq0MfWYRuaVVvHZlby7qGVHvY1htdmZtTOP5ebvIKq4iOsCdL28YRHTAiRNiIqdiQ3IBl7y1EqMB1vzf6GZRisxcbWPYs3+SXVLFq1f00oqdFsxqs7M+qYA9WSUEeLoQ5OVKkJcLQd6ueLs6YVD/nUZVWG5mwFMLMVttfHHDQIa2Oz1L0FdabXRevpUKm51F/TvS2av1zSE2hZlpuTyyJ5X+Pp783Le9o8MRabE059861HtWtnfv3jzwwAOEhYVx4403snr16saIS0TE4VycjAR7uxLuW9NHS4ms1q9frD9dwn2otNj4Zl2Ko8MREZHj+HVLBrmlVYT5uHFut7CTOobJaODSvlH8eNtQYgM9SMmvYOK7qziQW9bA0YocbsGOLABsdvhlS7qDo6nx+/ZMskuqCPZ25dxu4Y4OR06ByWhgQHwAVw2K5bzu4QyID6BNsBc+bs5KZDUBPw8XLutXs+Ly/m83U/C38o+nk7+Ky6iw2QlxcaKTp8rjnayxQTWT7n8Vl5Fjtjg4GhERx6r3zOwrr7xCeno6H3/8MdnZ2YwYMYIuXbrwwgsvkJWV1RgxioiINAmDwcDUIXEAfLoqCetxeqWJiIjj2O12Pl6RCMDVg2NP+YaTSD93vr15MG2DPckoqmTiu6tIyCppgEhFju5QMgtg9sY0B0byPzNXHABg8sAYXJx0E5fIqfjX+Z1pE+xJZnElD/2whdOxw8eygpoyviP8vZVEPQXhri708vbADszPLXZ0OCIiDnVSn1CdnJy45JJLmDNnDqmpqUyaNInHH3+c6Ohoxo8fz59//tnQcYqIiDSJi3pF4O/hTFphBX/s1E0aIiLN0fqkAramFeHqZOTKATENcsxQHze+uXkwncK8ySmp4or3VrMjXZNG0vAO5JaxN7sUJ6MBk9HA5tQi9ueUOjSmLamFbEguxNlkYNLAhnlPiZzOPFyceO2K3riYjCzYkcXnq5McHVKTW5Jfc1PIcH9vB0fS8p1zcHXW77lFDo5ERMSxnE5l57Vr1/Lxxx/z9ddfExISwtSpU0lLS+OCCy7gtttu44UXXmioOEVERJqEm7OJy/vH8M6SfXyyMpGxXU+udJXU3/qkfBJzy7mkT6Tu3hRp5ux2O4t355BfZnbIe/bQqqzxvSIJ8Gy4/oZBXq58deMgrv5oDdvSirny/dUMbReIxWrHYrVRbbVjttoA8HQx1fbU9HSt+XdM1zB6Rfs1WDzSspRWVfP12mTGdAkjJvDYfdcW7MgEYFCbQExGA0v25DB7Uzr3nd2hqUI9wsyViQCc1z2cEG+VAxNpCN0ifXn43E7895cd/PfXnfSPD6BT2OnRp6XQUs3mknIARgR4OTialm9skC/PHMhkaUEJZdVWPJ1Mjg5JRMQh6r0yKzs7mxdffJFu3boxfPhwcnJy+Oqrr0hMTOQ///kPH3zwAfPnz+edd95p0EBnzJhB//798fb2JiQkhPHjx7N79+7DxlRWVnL77bcTGBiIl5cXEyZMUOlDERGpt6sGxWA0wMp9eexRmakmUW6u5tqP13H/d5uZMXfXaVmKRaSl2JlRzKT313DtzJr37LQ525v0PZteWMHv22uSAdcOi2vw4/t7uvDFDYPoHeNHUYWF37ZmsmBHFot357B8by5rD+Sz9kA+i3bn8OvWDL5bn8rMlYm8tXgft32+Xr+/TlOVFivXzVzH9F938sB3m4879lCJwbO7hDK+dwQAczalOey1k1taxS+bMwBqyy2LSMO4bmgcZ3YMxlxt466vNlJpsTo6pCaxvKAUO9Dew5Vw14a76eR01cnTjTh3F6psdhYX6PpURE5f9V6ZFRUVRdu2bbnuuuuYOnUqwcHBR4zp0aMH/fv3b5AAD1myZAm33347/fv3p7q6mv/7v/9jzJgx7NixA09PTwDuvfdefv31V7777jt8fX254447uOSSS1ixYkWDxiIiIq1blL8HY7qE8fv2TD5ZmchTF3d3dEit3i+bMyiurAbgvaX78XV35vaz2jk4KhH5u7zSKl5csIev1yZjs4OLkxGL1cZnq5OwY+e/47o1yQqtQz0NB7cJbLQ73H3dnfnihoH8uiWDcrMVZ5MRJ5MBl4P/ApSbrZRXVVNmtlJurubdJftJL6okvaiSSD/3RolLmieL1cYdX25g7YF8ANYm5rM9vYiuEb5HjM0rrWJ9UgEAo7uE4ufujLvzNpLyytmUUkjvGP8mjR3gqzXJmK02ekb5OuT8Iq2ZwWDghct6cs4ry9iTVcr0X3cwfXzrv7ZYejDhckaASgw2BIPBwNggX95NyWFuThHnB/s5OiQREYeodzJr4cKFDB8+/LhjfHx8WLRo0UkHdTS///77Yd/PnDmTkJAQ1q9fz4gRIygqKuLDDz/kyy+/ZOTIkQB8/PHHdO7cmdWrVzNo0KAGjUdERFq3KUPi+H17Jj9uSOOhczrh6+7s6JBOid1uZ2NKISv35nJe93DaBDevch9frE0GoGe0H5tTCnl+3m583J25elCsgyMTkWqrjZkrE3l1YQIlB5PO5/cI59FzO7FqXx4P/bCFz1fXvIefvKgbRmPjJbTKzdV8dfD3xbVD4xrtPFDT7+SyftF1Hr90Ty5b04rYmFygZNZpxGaz89D3W/hjZzauTkY6hXmzObWIT1Ym8tylPY8Yv3BXNjY7dI3wqX2djOkaypxN6czemNbkySSL1cbna2p6+Uxt5PeUyOkqyMuVlyb25JqP1vL56mQ6hHpzbrdwgr1dHR1aozmUzBqhflkN5tyDyayFecVU2+w4NeLnLRGR5qreZQZPlMhqKkVFNU0PAwICAFi/fj0Wi4XRo0fXjunUqRMxMTGsWrXqmMepqqqiuLj4sC8REZFBbQLoGOpNhcXKd3+lODqck5aQVcIL83ZzxvOLueStlbwwfw9TP15HWVW1o0OrtS2tiM0pNU3nP5zSjztH1qzImjZnG3M2pTk4OhF5e/E+pv+6k5LKarpG+PDtzYN5c1Ifovw9uKxfNM9f2hODAT5fnczjc7ZhszVeqbRZG9MoqrAQHeDOqM6hjXaek9E7xg+ATcmFDo1Dmo7dbufJX3Ywa2MaTkYDb1/Vh2kXdgVg9qZ08svMR+zz9xKDh4zvHQnAL1sysBzsydZUftyQSlZxFUFeLpzXPbxJzy1yOhnRIZibRrQBYNqc7fR/6g+GPvMnt36+nneW7GPtgfxWU6Y2qaKKxAozJgMM8WteN9C1ZP19PQlwNlFQbWVNUamjwxERcYg6JbP69OlDQUFBnQ86bNgw0tIab/LJZrNxzz33MHToULp16wZAZmYmLi4u+Pn5HTY2NDSUzMzMYx5rxowZ+Pr61n5FR9f97ksREWm9DAYDUw72jThU0qol+WZdMue+uoyzX17KG4v2kpxfjoeLCT8PZ5Lzy3nqt52ODrHWlwdXWYztGkaQlyv3nd2BKYNjsdvhvm8388cO9b8UcRSrzV77Hn1gTAd+umMYA+IDDhtzad+o2oTWF2uSeayRElp2u52ZKxIBmDI4DlMzuyO5V7QfABtTCh0ahzSs79enMvblpdz3zSa++yuF1ILy2sdeXZjAzJWJALxwWU9GdgqlT4wfPaJ8MVfbalcRHlJhtrIsIQc4PJk1vF0QgZ4u5JWZWZ6Q2/hP6m/xvLRgDwA3j2iLq5Opyc4tcjp6YExHbj6jDe1DvDAYIK2wgrnbMnlm7i4mvruq9vdJS7esoCbR0tfHEy/9XmkwJoOBswNrytf+nlvk4GgcI7PKwrP7M1iUV9xqkr8iUj91KjO4adMmNm/eXLsKqi7jq6qqTimw47n99tvZtm0by5cvP+VjPfroo9x333213xcXFyuhJSIiAIzvHcEzc3eSnF/O4t3ZzW4VwLF8sGw/03+tSVY5mwyc0SGEcb0iGN05lI0pBUx6fw1frknm7C6hnNUxxKGxllZVM2djzQ0wkwbGADWJxH9f2JWSymp+3JjGbV9u4JNrBzC4baAjQxU5La3al0dGUSW+7s7cOKLNMRNIl/aNwgA88P1mvlyTTHGFhf+O64a/58k1fd+WVkRqQQVgx2YHux2S88tJyC7F08XExP7N7/P6ofJw29KKMFfbcHGqdxEMaWbKqqr57y87KKqwsDurhB8P/r2KDnCnY6g3f+zMBuA/F3WtXV1lMBiYOiSO+77dzOerk7hpRBucTTWvheV7c6m02Ij0c6dL+P/6vTmZjFzYM4KZKxOZvSmNszo1zd/mj1YcIKu4ikg/d64erLK+Io3NxcnIo+d25tFzO1NaVc3W1CK2pBby565s1hzIZ+62TK4dGu/oME+ZSgw2nnODfPkmM5/fc4t5sp29SXqVNhd/5BVz184k8i1WAHp4u3NvbChjg3wxnkY/B5HTXZ17Zo0aNarOWe/G/GV6xx138Msvv7B06VKioqJqt4eFhWE2myksLDxsdVZWVhZhYWHHPJ6rqyuurq23TrGIiJw8DxcnLu8fzfvLDvDh8gOM7BTS7C8YZm1MrU1k3XJGW24e0eawyeQhbYO4bmg8H604wMPfb2HePSNOerK5IczZlEaZ2UqbIE8Gt/lfsspoNPDspT0orqzmj51Z3PvNJhY/eCZuzrq7U6Qp/bAhFYALe4afcNXGhL5RGAzwwHeb+WVLBqv35/HvC7tyQY/wev3u/HRVItPmbD/m45f2jcLHrfn1MYwL9MDPw5nCcgu7MovpEeXn6JDkFH21NpmiCguxgR5c0COcVfvy2JxaREp+BSn5FQDcO7pD7UruQ87vEc7Tv+0ko6iS+duzOL9HTfm+BTtqKoac3SX0iPfEuF41yaz527Moq6rG07Xe7a3rJb/MzDuL9wHwwNgO+vsq0sS8XJ0Y3DaQwW0DObdbOCOeX8SGpAJKq6rxauT3f2Oy2e0sr01mqcRgQxsR4I270UBKpZkdZZV09Wr9PTrNNhtP78/gnZSalc3x7i5kVlWzpaSCa7cl0tHTjXtiQ7kw2I88SzU7yyrYVVrJzrJKEsoraePuysNtwol2O/Y1b2m1lbdSskmvtPBk+0h8tKJQpNmq01/IAwcO1PvAf080NQS73c6dd97JrFmzWLx4MfHxh9+t0rdvX5ydnVm4cCETJkwAYPfu3SQnJzN48OAGjUVERE4f1wyOY+bKRFbuy2Pe9izO6XbsGyQcbdHubB78bgsA1w2N5+FzOh51AvmhczqyZE82+3LKeHzONt6Y1KepQwVq/rZ/uaamBNOkgTFHxOpsMvLGpN6c9cJiMooq+XptMlNbwd2qIi1FaVU1v2+rmXy/pE/dPttf0ieKuCBPHvlhC3uySrnzq43M3pjG9Iu7Ee574gmX7elFTP+lJiHfLdIHd2cTBgwYDGAwgK+7M7cf7KvX3BgMBnpF+7F4dw6bUgqVzGrhqqqtfLCs5jr41jPacsWAmtXDpVXVrEvMZ/X+PCJ83bnmKCuaXJ1MTBoQw2t/7mXmygOc3yMcq83OwoMruf5eYvCQXtF+xAV6kJhXzvwdmVzcu2Gvp//p9T8TKKmqpku4D+N6RjbquUTk+GICPYgN9CApr5zV+/IYfZTfES3FttIK8i1WvExGevt4OjqcVsfDZOSMAG9+zy3m95yiVp/MSqyo4ubtiWwuqbmB5PrIIB5vG0Gp1cb7qTl8lJrD7rJKbt2RxD3GZKqOUuZ6Q3E5v+QUckdMKLfHhOBu+t/KeZvdzjeZ+czYn0G2uaandJbZwmfd2+B0EuWs1xeVsa20gm5e7nT1csfNpFX6Ig2tTsms2FjHlxy4/fbb+fLLL5kzZw7e3t61fbB8fX1xd3fH19eX66+/nvvuu4+AgAB8fHy48847GTx4MIMGDXJw9CIi0lJFB3hw84i2vLFoL0/8tJ1h7YOa5d2SG5MLuO3zDVTb7IzrFcFj53c+5koIN2cTL1/ei4vfWskvWzIY0zWdi3pGNHHEsCW1iO3pxbg4GZlwjIlyN2cTt5/Vjsdmb+Otxfu4YkCM7h4XaSJzt2ZQYalZOdn7YD+ouugT488vdw7n7cX7eGNRAgt3ZbPmpaU8fE5HJg+MxXiMyYGyqmru/HIjZquN0Z1DeP+afs1+New/HUpmbUwu5BrdT9eizdmYTmZxJaE+rlzc53/JHi9XJ87qGHLCMr2TB8Xy1uJ9rEssYFtaEVXVVvLKzHi7OR3Rdw5qkqHjekXy6sIEZm9Mb9RkVnJeOZ+vTgLg0fM6HfM9KSJNZ3j7IJLyklmakNOik1lL8mtWZQ3x88JZv1saxdggX37PLWZebhH3x9fcaFlutfF7bhHfZ+ZTYLHyUqdoOrfwRNesrAIe3J1CqdWGn5OJVzrFcE5wTc8wN5ORR9uEc1t0MB+n5fJeag75FitGoI2HK5083ejk6U68uwufZ+SxqrCMFxIz+SYzn/+0i+DcIF/WFJUxLSGNLaU1ibI4dxeyqqpZlF/CE/vSmN6+7n+Hq212njmQwRvJ2bXbnAzQxdOdXj4e9PLxwNNkpMxqo9xqo6zaRrnNhhG4OToYP+fmN78g0ly1mHfL22+/DcCZZ5552PaPP/6YqVOnAvDyyy9jNBqZMGECVVVVjB07lrfeequJIxURkdbmjpHt+GlzOsn55bw0fw/TLuzi6JAOsze7lOtmrqPCYmVEh2Cev7TnCSemekT5cefIdrzyRwKPz97GgLgAwnzdmijiGl+sqZlIO69b2HFLHU7sF83bi/eRVljBF2uSuX6YVmeJNIVDJQZrygfWb0LKxcnI3aPbc173MB7+YQsbkgt5fM52lu/N5aWJvY5aQm3anO3szy0jzMeN5y/t2eISWfC/vlmbUgodG4icEqvNzjtLa0rw3TCszQlLbB5NqI8b53UP56fN6XyyMpEAr5q/c2d1DKntofVP43vXJLOWJeSQU1JFsHfjlMN/fv5uLFY7w9sHMbx9cKOcQ0TqZ0T7YD5fncyyhFxHh3JKavtlBahfVmM5O9AXIylsKa1gdlYBi/NL+DmnkDKrrXbMBRsSeLtLLGOCfB0Y6ckps1p5LCGNrzLyARjo68lbXWKJPEqZQF9nJ+6JC+Om6BBSKs3EuLkctvIK4JJQf37KKeQ/e9NJqTRz3bZE2nu4klBeBYC3ych9cWFcFxXEH3nFXL8tkQ9Sc2nv4caUyKATxpteaebWHUmsKSoDoL+PJ/srqsizVLOltIItpRV8mp53zP23llbwWff4Fvm5V8QRDPa6NsI6TRQXF+Pr60tRURE+Pj4n3kFERE4LS/bkMOWjtRgN8NMdw+gW2TwuDDKKKpjw1krSiyrpGeXLlzcOqnOfDYvVxoS3V7IltYjBbQKZ2D8Km62m3ILdXvPvgPgA2gQ3fL374koLA59aSIXFyne3DKZ/3JF3qf/d12uTeeTHrQR5ubD0obPwcGkx9+OItEgp+eUMf24RBgMsf3gkkX4nf3evzWbn01WJPP3bLsxWG53CvHn/mn5EB3jUjpm1MZV7v9mM0QBf3TiIgX/rodeSFJVb6PnkfAA2Pn62Q3sSysmbuzWDW7/YgK+7MyseGXnSK7I3JBdwyVsrcXEyEuzlSlphBa9f2ZsLj7MaetybK9icUsiIDsFc2T+aMzoGN+jfvC2phVz0xgoMBvjlzmF0jWgen2dETncllRZ6PbkAq83OsofOOuxvZEtRUm2ly/JtWOx2VgzsRFuPpr1R7nQyfkMCqw8mTw6JcXNhQqg/64rKWF5YigF4vG0Et0YHt5hEyY7SCm7enkhCeRUG4N64UO6LDTupkn//VGa18npSNm8lZ2O22zECV0UE8mB8GMEu/+vF+mpiFjMOZGAywDc92zLM/9iJ2T/zirljZ1Jtac2XOsVwUYgfdrud1CoLG4vL2VRczpaScqzY8TCa8HQy4mky4mY08mVGHlU2O/9tF8mN0bq5pLFpzr910EyQiIhIHZzRIZgLeoTzy5YM/jVrKz/eNhSTg0tnFJabmfLRWtKLKmkT5MlHU/vXq2G8s8nISxN7cv5ry1m1P49V+4+8Y8zVycjMawcwuG3DTizP3phGhcVK+xAv+sX6n3D8hL5RvLl4Lyn5FXy+OombRrRt0HhE5HCzNqYBMLhN4CklsgCMRgNTh8bTI9qPmz5dz67MEsa9uYK3J/dhYJtADuSW8disbQDcPapDi01kAfh6ONMm2JP9OWVsSi08YSk6aX7sdjtvL6lZlTVlcOwplRbuHe1HzyhfNqcWkVZYgbPJwJkdjz9Zdd3QOO7+ehNL9+SwdE8Ork5GhrcPZmzXUM7oGEywl+tJT0ra7XZm/LYLgIt7RSqRJdKMeLs50yfGj3WJBSxNyGHyQMe3+6ivJfklWOx22rq7KpHVyCaGB7C6qAwfJyMXBftzWZg/A3w9MRgMWGx2/i8hlc/S83hyXzp7yip5rmMULsbm27/JbrfzSXoe/96bRpXNTpiLM290iTluIqm+PE0mHmkTzhXhAfyYVcDYIN+j9hy7KzaEPeWV/JBVwA3bEvm1b/sjXs9FlmreSsnh1aQsALp7ufNe1zjiPWpWVBsMBqLdXIh2c+GiEL9jxtTew5X/S0jjv/vSGeTnSXfvlpfEFmlqSmaJiIjU0bQLurBkdw6bU4v4Yk0S1wyOc1gsFWYrN3zyF3uySgn1ceXT6wcQ6FX/ckTtQrx5aWIvvl6XDNR88DYawGgwkFFUyc6MYm74ZB1f3DiIXvXomXM8drudL9fUnG/SwJg6Tco5m4zcObI9D32/hXeX7GfywNh6Je5EpO7sdjs/HioxeIx+diejT4w/P985lBs//YttacVM/mAN/76wC9/8lUKZ2crA+ADuGNmuwc7nKL2i/difU8bGZCWzmquiCgsWq42go/zdXLkvjy2pRbg5G5kyJO6UzmMwGJg6NI57v9kMwKA2gXi7OR93n3G9IokO8GDu1gzmbc8iOb+cP3Zm8cfOmgkzDxcTkX7uRPm7E+nvTqSfB+1DvOge5Uuoz/EnjxfvzmHV/jxcTEbuG9PhlJ6biDS8Ee2DWZdYwLI9uS0ymbUgrxiA0UFa8dDYrgwLoL+PJ9FuLrj9o6yes9HAcx2i6OjpxrSENL7OzCexoor/to/E02TCyQAuRiPOBgNuJgOeJsf2I84xW3hkTyq/5hQBMCrAh1c7xxDUSJU44txduS8u7JiPGwwGXuwYTWJFFeuLy7lmywFe6xzDjrIK1heVs764rLZEIcDUyCCeaBtxxP+Hurg2MoglBSXMyy3mlu1JzO/XAc+TKG0scjqpd5nBNm3asG7dOgIDD79jsrCwkD59+rB///4GDbCpacmhiIgcz6erEpk2Zzverk78cf8ZJ5w4agzVVhs3f7aehbuy8XFz4rtbhtAxrOHr0ldarFw3cx0r9+Xh6+7MtzcPbpDzrEvM57J3VuHmbGTNo6Px9Tj+xN4h1VYbo15aQlJeOQ+f04lbz9TqLJHGsD4pnwlvr8LDxcS6f41u8MRxhdnKg99v5pctGbXb/D2cmXv3iCbv3dcYPludxOOztzGiQzCfXjfA0eHIP/y+LYOHvt9ChcXK9cPacOfIdoe9xid/sJoVe/OYOiSOJy7qesrnq6q2MvSZP8ktNfPfcV25uh43wtjtdnZlljBveybztmexM6P4uONDvF3pEeVLt0hf2oV4kVlUyYHcMg7klrE/p4zM4koAbhrRhv87r/OpPC0RaQSbUgoZ/+YKvN2c2Pj42TidxOS4o9jsdrqv2E6epZrvex2/NJs0nT/zirl5eyIlf+un9U99fTy4INiPC0L8iD5KX6rGUGG1MS+3iO+zCliUX4zVDs4GA4+1DeemqOZRFjHHbOGcv/aQVmU56uPx7i480iaccSEnrjJyPPmWakat201GlYUrwwN4uVPMKR1Pjk1z/q1DvZNZRqORzMxMQkIOv8swKyuLmJgYqqqqjrFny6AXtoiIHI/VZueSt1awObWIC3qE88akPscdn1ZYwZ87s1ixN48RHYKZNPDUPpza7XYe+n4L361PxdXJyOc3DDxhv6lTUVZVzeQP1rAppZBgb1e+u3kwcUGeJ328ZQk53PXVRgrKLVzaN4oXLutZr/1/3JDKfd9uxs/DmWUPnXXCO9xFpP4e/XErX61NZkKfKF6cWL/3aF3Z7XbeXLSXF+bvAeCjqf0Y2Sm0Uc7V1LalFXHB68vxcXNi07QxGB1cklZqVFqs/PeXHXxxcGXwIaE+rvzfeZ25qGcEW1KLGPfmCpyMBhY/eCZR/g1T7mfpnhz+3JXNI+d2ws355O+4rrRYSS+sIK2wgrSCClILKkgpKGdXRgkJ2SXY6nBl3yvaj5nX9sfPQ/3cRJobq81O3+kLKCy38MOtg+kb23if8RvahqIyztuQgLfJyI5h3XHW375mY3dZJffvSmZ/RRXVdjsWmx2L3U71Uf5m9PL24IJgX0YH+dDW3a3B/z+uKSzlm8x8fs4uPCzB1sfHg6fbR9HLp3mV2dteWsGlG/disdvp7eNBXx9P+vh40MfHs0FXjq0sKGXCpr3YgXe6xDI+9NQSZHJ0mvNvHer8zvvpp59q/3vevHn4+v6vvrbVamXhwoXExcU1aHAiIiLNjclo4KmLu3PRG8v5ZUsGJZVriQ/yJCbAg9jAmq/iymoW7sxi4c5sdmWW1O77+/ZMDAa4csDJJ7Sem7eb79anYjIaeGNSn0ZNZAF4ujox89r+XPHeanZlljD5gzV8f+tgwn3r10PHZqvpQfLC/N3Y7dA90peHzulY73gu6hnBG4v2sj+njE9WJnLHyPb1PoaIHFulxcovW9IBmNA3stHOYzAYuGNke4a2C6LCYmVI26BGO1dT6xjmjZuzkeLKag7kldE22MvRIZ32ErJKuOPLjezOqvmbfMsZbekd48dTv+4kOb+cu7/exOerk2p7YV7UK6LBElkAIzoEM6LDqTd2d3M20SbYizZHeU2Vm6vZmVHMltQitqYWcSCvjDAfN9oEexIf5EWbYE/aBHkqiSXSjJmMBoa2C+LXLRks3ZPbopJZh0oMnhngo0RWM9PR041f+h5ZWtZmt5NltjA3p4hfcopYXVjKppJyNpWUM31/Bs4GA/HurrT3dKWDhxsdPN04K8AbP+f6J3GSK6p4LCGN+Xn/W2Ec6erMpWEBXBrqT3vP5rkyv6uXO1uGdsNoAFMjrhYb4u/FPbGhvJyUxYO7U+jt40Gse/1bCIicDuq8Mst4sFGgwWDgn7s4OzsTFxfHiy++yAUXXNDwUTYhZWlFRKQunpm7i3cONog/HqMB+sb6E+ztym9bMzEa4K3JfTinW3i9z/nh8gP895cdADw3oQcT+0fX+xgnK7ukkonvrCIxr5y2wZ58e/PgOvfoKqqwcP+3m2v7fVzRP5onLup60nenz9mUxt1fb8LX3ZllD5+Fj1ZntXr7ckp548+9XDc0nu5RvifeQU7az5vTufOrjUT6ubPsobO0qugkXfbOStYlFvDCZT25tG/D9R2T+rHb7XyzLoUnft5OpcVGkJcLL03sVZtYqrRY+WDZft5ctI8Ki7V2vwX3jqB9qEpkiUjT+2ZdMg//sJU+MX78eNtQR4dTZ6PX7WZbaQWvdY5hYljLScLJ/+SYLfyWU8TP2YWsLy6nwnZkacJQFyc+6hZPX9+6Veqostl4JzmHV5IyqbDZcTLApaEBTAwLYJCfJ8ZmUE6wuai22bl4417WFZfR18eDn/q0b9QE2ulIc/6tQ53T6baDv8Ti4+NZt24dQUGt5+5JERGR+nr4nI6M6hzCnqwSkvPKScorJym/nOS8MowGAyM6BjOqUwhndgwhwNMFu93Ooz9u5et1Kdz11SZmXud8wpUIRRUWVu3LZWlCLssTcknOLwfgoXM6NmkiCyDE243PbxjIxHdWsS+njLu+3shn1w084UT3rsxibvlsPYl55bg4GXnyoq5ccQor0wAu6BHBG3/uJSG7lK/WJHPzGeqd1ZrlllYx5aO1pBZUsD+nlNm3D20WdfRbqx82pAJwce9IJbJOQe8Yf9YlFrAppUDJLAd6acEeXv9zLwDD2wfx4sSehHj/7+5vN2cTd4xszyV9onj6t538siWDS3pHKpElIg4zvH1Nsn1TSiFF5ZY695Z1pPRKM9tKKzAAIwM0QdxSBbs4MyUyiCmRQdjsdtKqLCSUVZJQXklCWRXLCkpIqjRz8ca9PNMxiknhgcc93rL8Eh5NSGVveU07mqF+XszoEEWHZroKy9GcjAbe6hrLqHW7WF9cztcZ+UyOOP7PWOR0VO+1oQcOHKj978rKStzc9EtIREROPwaDgf5xAUeU+Tu0evmfk+0Gg4Hp47tRUG5m3vYsbvp0PV/fNIhukYevMknJL2fOpjQW7spmc0rhYf0vnIwGbj2zLbc6KHkT5e/Bp9cP4MLXV7Bibx4frTjADcPbHHP81tQiLn9vFeVmK5F+7rx9VR96RPmdchwmo4Frh8bzf7O2MntTupJZrVilxcpNn/5FakEFAJtTi1ifVEC/Ri6vebrKLq5k6Z4cAC7p03glBk8HvaL9ANiYXOjQOE5nK/fl8saimkTWg2M7cusZbY+ZoI3wc+eNSX34z0VV+Lo3/4ljEWm9IvzcaRfixd7sUlbuy+Xc7odXc9hZWsE7KTnEuLlwf3yYg6I83B8HS8f19fFo0D5C4jhGg4FoNxei3VwYGViToCyttnLXzmR+yy3ivl0pbC2p4Ml2kYeVlTTbbCzKL+HLjDzm5da8LoJdnHiibQSXhPrrhrQTiHZz4f64MP69N51nDmQwLsQPL6eT77Up0hoZ67uDzWbjv//9L5GRkXh5ebF//34AHn/8cT788MMGD1BERKQlMRgMx/yQ7mQy8uoVvRncJpDSqmqmfLSW/TmlFJSZ+Wx1EhPeXsnw5xbxwvw9bEyuSWS1CfZk6pA4PpzSj03/HsP9Yzo69CKgXYg3j13QGYDnft/Nrszio47LKq7khk/XUW62MjA+gJ/vHNYgiaxDzusehrPJwM6MYvZklZx4B2lx7HY7D36/hQ3Jhfi4OXHGwbJgHyw7cII95WTN2ZSOzQ59YvyO2pNH6q53jB8AuzJLqDBbjz9YGlxhuZn7vtmM3Q5XDojm9rPa1WmlYaCXK06mel8ii4g0qOHta6o3LE3IPeKxAxVVfJOZz0dpuZiPUgbOEQ71yzo7UKWgWzMvJxMfdIvjoYNJ1I/Tcrls015yzBY2FJfxf3tS6bVyO1O2HmBebjFG4LrIIJYP6MSEsAAlsuro2sgg4t1dyDFX83pytqPDEWl26v1Jffr06cycOZPnnnsOF5f/NY/t1q0bH3zwQYMGJyIi0tq4OZt475q+dIv0Ia/MzMVvraT/U3/w+OxtrE8qwGCAoe0CmXFJd1Y8MpI/7z+TJy7qyqjOoXi5No87HScNiGFUpxDMVhv3fL2JSsvhE7UVZis3fvoXWcVVtA/x4v0p/QjwbNiG834eLpzRIQSAnzalN+ixpXl4+Y8Eft6cjpPRwDtX9+Vf59ckUeftyCQpr8zB0bU+dru9tsTgBJXFO2Xhvu6E+rhitdnZmlbk6HBOK3a7nf+btZXM4krigzx5/IIujg5JRKReDvX1W7on54ie9WMCfQlzcSbPUs1vOY7/+1JhtbG8oObGsrODVGKwtTMaDNwXF8Yn3ePxMhlZXVRG35U7OG99Ah+l5ZJvsRLi4sQt0cH8OaAjT3eIwte5eVzDthQuRiPT2kYA8E5KNimVZgdHJNK81DuZ9emnn/Lee+8xefJkTKb/LXXs2bMnu3btatDgREREWiNvN2dmXjuA+CBPiiosVNvsdI3w4V/ndWbVI6P44oZBXDkghkg/d0eHelQGg4FnL+1BkJcLuzJLeGHe7trHbDY7D3y3mS2pRfh7OPPhlP74uDVOyaZxvWo+5M/ZnHbEhb60bLM3pvHawgQAnrq4G0PaBtEh1JszOgRjt8PHKxIdG2ArtD29mF2ZJbg4Gbmge4Sjw2kVekf7A7AppcDBkZxevl+fym9bM3EyGnjl8l54qOSViLQwA+MDcDEZSSus4EDu4TfwOBkNTI6oKbf8SfqRK7ea2orCUipsdiJdnemsXkinjbFBvvzWtwNt3F0x2+24Gw1MCPXnqx5t2DC4K0+0i6STZ/O8lm0JzgnyZbCfJ1U2OzP2Zzg6HJFmpd7JrLS0NNq1a3fEdpvNhsViaZCgREREWrsgL1e+uXkQT47ryoJ7R/DrXcO5cUQbwnxbxkVgkJcrz07oAcAHyw+wYm/NxfQrCxP4dWsGziYD717dj5hAj0aLYXTnUDxcTKTkV7AxpbDRznO6yympwmprumThX4n5PPT9FgBuHtGGy/vH1D52w/B4AL79K4Wicn3ubEiHVmWd3Tm0RTSbbwl6HSw1qL5ZTScxt4wnftoOwL1nd6Dnwd5lIiItiYeLE/3iam6IONTL8u8mhwdiBFYVlrGnrLKJozvcgtya1WGjA31URu4008HTjfn9OvBljzZsHdqNN7vEclagD051KOsrx2cwGPhPu0gMwI9ZBWwoUlUKkUPqnczq0qULy5YtO2L7999/T+/evRskKBERkdNBiLcb1wyOo32ot6NDOSmjOocyeWBNouH+bzfz2eqk2tU0T1/cnQHxAY16fncXE2O71tRsV6nBhrc+qYBrP15L/6f+4LqZ66i2Nn5fhpySKm7+bD1mq40xXUJ5+JxOhz0+rF0QncK8KTdb+WpdcqPHc7qwWG2176EJfSMdHE3r0ftgImWTku1NwmK1cc83mygzWxkQH8AtZ7R1dEgiIiftUKnBZUfpmxXh5sKYgyX9PnXg6iy73c4fh/plBalf1unIy8nEyEAfvJxMJx4s9dLD24OJYTXX09P2qhKJyCH1TmZNmzaNO+64g2effRabzcaPP/7IjTfeyFNPPcW0adMaI0YRERFppv51fmfaBHmSWVzJ47O3ATWraS7rF90k57/oYKnBX7akN0my5XSwen8ekz9YzYS3V7Jod83dwEv25PDC/D2Nfu4nftpOXpmZTmHevHJFL4z/uLPTYDBw/bCa1VkzVyRi0f/zBrF4dw55ZWaCvFwY0T7Y0eG0Gt2jfDEZDWQUVZJZ5Ng7508Hry9MYFNKId5uTrx8eS9MujNcRFqw4e2DAFi1Pw9z9ZGfd66JqHn828x8yh30eWhnWSVpVRbcjQaG+nk5JAaR1uzRNuG4G438VVzOTzmFjg5HpFmodwHxcePG8fPPP/Pkk0/i6enJtGnT6NOnDz///DNnn312Y8QoIiIizZSHixOvXNGLS95aSbXNzujOITz0j9U0jWlYuyACPF3ILTWzcl9e7V2scmzphRX8siUdi9WO0WDAZKxp5gwwf3sWaxPzgZqeDJf0iaRTmA9P/rKDd5bso2eUL+d2D2+UuH7flsmvWzMwGQ28cFnPY/a5uahXBM/+vpvM4kp+25rBuF5aSXSqfjxYYnBcr0icTPW+102OwcPFiY6h3uzIKOalBbuJC/I87PH4QM9Gez+dbjalFPLGor0APHVx92bbc1JEpK46h/kQ5FXzGXd9UgGD2wYe9viZAd7EuLmQXGlmTnYBV4YHHuNIjWdBbs2qrOH+3rjr84NIgwtzdeaOmBCeT8xk+r4Mxgb64qb3mpzmTqob7vDhw1mwYEFDxyIiIiItUI8oP96c3If1SQXcNap9k94N72wycn73cD5bncScTelKZp3Air253PHlBgqO02/KxWTksn5R3HJGW6IDanqeZRZX8t7S/Tzw3WbahXg1eGnMonILj8/538q+bpHHLlXj6mRiyuBYXlywh/eX7eeinhHq0XAKCsvNLNyZDcCEPlEOjqb16RPrx46MYr79K/Woj388tT9ndQpp4qhal2qrjX/N2orNDhf1jOCinhGODklE5JQZjQYeOqcTPm7OdI868nOR0WDg6ohAntqfwSdpeY5JZuXV9Ms6+2DJQxFpeLfGhPB5Rh4plWbOWLsLF6MBs82OxW6nymbH02Tkg25x9PBuvF7VIs3JSSWzRERERP5ubNew2v5VTW1crwg+W53EvO2ZPGXphpuzarb/k91u58PlB3j6t53Y7NApzJueUX5Y7XZsNnvNv3aI9HNn6pA4wnzdDtv/obEd2ZpaxKr9edz82Xpm3zEUHzfnBovv6d92klNSRZtgT+4a1f6E4ycPiuWNRXvZllbMmgP5DGrT9BM4rcXPm9MxW210DvehS4QmoxrabWe2w2QwUGGxHrY9MbectYn5TP91B8PaB+Gsu2xP2qerktieXoyPmxPTLuzi6HBERBrMxBOU7b4iPIDnDmSyqaSczSXl9GzCyezMKgvri8sBGB2ozw8ijcXDZOTxthHctiOJpErzEY/nWeCm7Yks6NcRb/Uuk9NAvZNZ/v7+R7371WAw4ObmRrt27Zg6dSrXXnttgwQoIiIicjx9YvyJ9HMnrbCCP3dlc57Kdh2mwmzl0R+3MHtTOlCz+uapi+uX9HMyGXljUm8ufH05+3PLuP/bzbx7Vd/DelrZ7XYyiyvx93Cp17GXJ+TyzV8pGAzw3IQeddo3wNOFCX2j+HJNMh8sO6Bk1in4fkMaABP6qFxjY4jwc+c/47odsb2owsJZLyxmX04ZX61N5prBcU0fXCuQVVzJSwtq+vk9fG4ngrxcHRyRiEjTCXZx5oJgX2ZlF/JZWh49OzVOMqvQUs364nK2l1awrbSC7SUV7K+owg5093In3NWlUc4rIjUuCfUnzt2FkmobLkYDLgYDzgevw67bdoDECjMP7k7h7S6xqlghrV69k1nTpk3jqaee4txzz2XAgAEArF27lt9//53bb7+dAwcOcOutt1JdXc2NN97Y4AGLiIiI/J3RaOCiXhG8vXgfczalKZn1N6kF5dz82Xq2pxdjMhp47PzOTB0Sd1IXOYFerrx9VV8ue2cVC3Zk8dKCPfSJ9WNzShFbUgvZklpEXpkZb1cnXpjYs04r9crN1Tzy4xYArhkUS7+4gDrHc93QeL5ck8wfO7O44r1VnNkxhDM7BtMx1FsXcXW0N7uUzSmFmIwG9R5rYr7uztw7uj2Pz9nOywv2MK5nJL4eDbfa8XTx5C87KK2qple0H1f2j3F0OCIiTe6ayCBmZRfyQ1YB09pF4NOAKzMKLNW8mZzNh6k5VNjsRzwe5uLM3bGhDXY+ETm2Pj6eR93+bpc4xm1MYHZ2IcP9vZkcoZv8pHUz2O32I/8iHceECRM4++yzueWWWw7b/u677zJ//nx++OEHXn/9dd577z22bt3aoME2heLiYnx9fSkqKsLHR0ulRUREWoJdmcWc88oyXExG1j02Gl93TQpnl1Ry7ivLyCszE+jpwpuT+zTICqZv1iXz8A8n/ox384g2PDi2I07HKZ/25M87+GjFASL93Jl37wi8XOt3n9UTP21n5srEw7aF+7pxRodgrh0aT8ewhu3t1do89/su3lq8j5GdQvhoan9Hh3PaqbbaOOfVZezNLuXG4fH863yVyKuPJXtymPLRWowG+PnOYXSNOHavPRGR1sput3PG2t3sKa/k6faRXBd16v1jS6utvJuSwzsp2ZRYbQDEu7vQy9uDrl7udPN2p6uXO8Eu+rwt0hy8kZTF9P0ZuBsNzO3XgU6e7o4OqVnSnH/rUO/i7PPmzWP06NFHbB81ahTz5s0D4LzzzmP//v2nHt1JevPNN4mLi8PNzY2BAweydu1ah8UiIiIija9TmA8dQ70xW23M25bp6HCahZ82pZNXZqZNsCc/3TmswUrxXd4/hmuHxmEwQNtgTy7pHckTF3Zh1m1D2PafsdwwLB6Ad5fuZ9IHa8gurjziGDabnT93ZfH/7d13fFR19v/x951JJr0SUggJEDoCUpRiQUSkKYoF17WB66JiW8VdldXF3l37WvCr6FpxZcW2KqCIgigKAtICoYZAEkJIJr3MzPePyQwEQkiGSWaSvJ6PRx5LZu7cOfP75nec+zn3nM+cH7dLkh6+oG+jC1mSdN95J2jJ30bq/vNO0Jk92ys40KS9heX64JdM/WH2chWWVh3fh23FbHaHPv7NNWKwo4+jaZsCzCbdfU5vSdKbP+7QjrwSH0fUcpRX2TTrk3WSpKmndKGQBaDNMgxDVyU7v+P9e89+NeR+dZvDoSX5Rfo8t0Bf5xXqm/1WLckv0rIDRXp5V66G/LRBT+7IVpHNrj5hwfp3vy76cWhvvXxCZ93UKUEjYyMpZAF+5IbUeJ0ZG6Eyu0PXrd+p0poiNNAaNXrVIDY2Vp999pluu+22Wo9/9tlnio11joYpKSlRRIRv7oSdO3euZsyYoVdeeUVDhw7Vs88+q7Fjxyo9PV3x8fE+iQkAADS98wZ00JNfp+vDXzM1uHOMOkSFKMTSdjfBXbQxR5J05bBOSo727t159048Qfec00dm05Hj/O45t48GdYrRHR+t1Yrt+TrnhaV68Y8DlRwToqVb8vRDRp6WZeSpoKbQdOGgZI3s6fl3tE7twjTllDBNOaWzyqts+mnbfj3w+QZt21eil5ZkaOb43h6fuzVbvnW/9haWKzI4QGf15juyr5zZM14jerTX95v36bEvN+mVKwf7OqQW4aXFGdq5v1SJkcGaMaaHr8MBAJ+anBCjh7fu0aaScv1rV67+1LG9QuvojHc4HPomv0gP1Rxbn64hQfpbl0SdFx8tE+ObAb9mMgw93ztVZ/2SrvSScs3akqWneqX4OiygSTR6zOBrr72m6dOna8KECe49s3755Rf973//0yuvvKJrrrlG//znP7VixQrNnTu3SYKuz9ChQ3XyySfrxRdflCTZ7XalpKTo5ptv1l133XXE8RUVFaqoqHD/brValZKSQsshAAAtTGZ+qU5/YnGtx2LDLOoQHaykqBCFWcwKMJsUYDJkNhkKNJsUG2bRtSPSFBzYuopeBaWVGvzQItnsDv1wx5lKiW2aDcHrs21fsaa/s0rpOUV1Ph8eFKBRveL14Pl9vb5X0LebcvSnN3+VJcCkxX8d2ehiXkFppW6du1rZheUyGYYMQzIM54ViqMWs+8/r2+JHGN7y/m/6dM0eXT40VQ9f0M/X4bRpm3OKNO7Z72V3SB9cO8xrXZTetnzrfi3amKM7x/WSJaDRAz68Zuu+Yo1/9gdV2ux66fJB7JMIAJL+vnm33sjKkyTFBJg1JTlOf0qOU3yQ8zvWamupHti6Rz8WFEuSogLM6hUWrGqHQ1UOh6rtzv8NNZs0NTlOkxNiFVDHTUsA/NcP+UW6ZM1WOSS90qeTJiXE+Dokv8KYwdah0cUsSVq2bJlefPFFpaenS5J69uypm2++WaeccorXA2yMyspKhYaG6qOPPtKkSZPcj0+ZMkUFBQX65JNPjnjNfffdp/vvv/+Ix/nDBgCg5Xlm4Wb97/e9yiooU2mlrUGv+ce5fXRNzWi81mL+b1m6de5q9UyI0Ne3jfBZHKWV1br743X6+LcsmU2GBqRE67RucTq9e5xOTIlWYD37aR0Ph8OhS2f/pJ+35+uiQR31z0tObNTrXXt5HU1aXJg+u/k0hXkwGtEfLE7P1dVzfpEkzb/xVA1IifZtQNDdH/+ud3/epb7Jkfr0xtNk8rMFRJvdoVMf+1bZ1nI9/8eBOu/EDj6LZeqcFfoufZ/O6NFeb159sgw6BgBAlXa73t6zX7Mz92lneaUkyWIYuigxRmU2u+bnFkiSgkyGrklur1s6xSs6sGV+jwFwdI9v26tnduYo3GzSopN7qnNIkK9D8hsUs1qHRv2Xq6qqStddd53+8Y9/6P3332+qmDyWl5cnm82mhISEWo8nJCRo06ZNdb5m5syZmjFjhvt3V2cWAABoeW47u4duO7uHHA6HrGXVyioo056CMu0tLFN5lV3Vdodsduf/bthj1YINOVq4IbvVFbMW1owYHN3Ht+PjQi0BevqSE/XXsT0VERygyODm2V/BMAzNnNBbk/61TP/9bbeuOa2L+nRo2AVLZn6p3vlppyTpgfNPUOd2YbI7HHJIstkcumf+Om3LK9F9n67Xk5MbVyTzB7nWcv31wzWSpKuGd6KQ5SdmnN1Dn67eo3VZVv33tyxdPNi/9jFblpGn7Jr977bmFvssjtLKav2wxdl58I9z+1DIAoAaFpNJ13Rsr6nJcfpyX6FeyczVr9ZSvb83X5JkSLo4MUZ3dklSx2CLb4MF0GRu75yoHwuKFWcJUExA65o+AkiNLGYFBgZq3rx5+sc//tFU8TS7oKAgBQVRpQYAoDUxDENRoYGKCg08ahEjM79UCzbk6JcdB1RQWqno0NZxYV9Zbdf36fskSaN7Jxzj6KZnGIbX9+xqiAEp0Tqnf5K+WLtXj3+1SW/9aUiDXvfMws2qtNl1ard2unJYpyMWy8OCAnTZ//2k/6zcrdO6x+n8AclNEX6TsNsdmvHhGu0vqVSvxAj9fQL7ifmLduFBumlUNz365SY99uVGjeoVr9gw/8lJH63c7f73trwSn8Wxfo9VNrtD8RFB6hYf7rM4AMBfmQ1D58ZH69z4aP1aWKI3s/Jkl3RjarxOCG/+72MAmleAydC7/dMUZjZx0w9apUbPdpk0aZLmz5/fBKEcv7i4OJnNZuXk5NR6PCcnR4mJiT6KCgAA+KOU2FD1SoyQze7Q4vRcX4fjNSu256uoolpx4UE6sWO0r8PxqTvG9lSg2dCSzfu0LCPvmMdv2GPVx6uzJEl3jutV5wXg8K7tdPOZ3SRJd3+8Trv2l3o36Cb06vfbtDQjT8GBJr142cBWt1dcSzf11M7qkRCuvOJKzfpkna/DcSssq9LX67Pdv2/b57vOrDWZBZKkE+koBIBjOikqTC/26aSX+nSikAW0IeEBZgpZaLUaXczq3r27HnjgAV188cV69NFH9fzzz9f68SWLxaLBgwfrm2++cT9mt9v1zTffaPjw4T6MDAAA+KOz+zg7lxZtaD3FrEWuEYO94/1u353m1qldmC4f2kmS9OiXG2W3179V7BNfb5LDIZ3bP0n96ykE3nJWd53UKUbFFdW6+YPfVGWzezPsJvHbrgP65wLnfrf3TTxB3eIjfBwRDhcUYNZTk0+U2WTo87V79eXve5v0/RwOh176LkMvf7e13uO+WLtXFdV2RYc6x4RuzyuRB9sue8Wa3YWSxHhMAAAAoA1qdDHr9ddfV3R0tFauXKnZs2frmWeecf88++yzTRBi48yYMUOvvfaa3nrrLW3cuFHTp09XSUmJrr76al+HBgAA/IxrDN+SzftUUW3zcTTHz+FwaOEGVzHL9yMG/cHNo7opPChA67Ks+mztnqMe9+PWPH2Xvk8BJkN/HdOz3nMGmE169tIBigwO0JrMAv1zwWZvh+1V1vIq3fLBb6q2O3RO/yT94WT2h/VX/TtG6/oz0iRJ//hknfJLKpvsvX7LLNATX6Xr8a826bt6ulM/WpkpSZp2eprMJkOllTblWCuaLK76uDqz+neM8sn7AwAAAPCdRheztm/fftSfbdu2NUWMjfKHP/xBTz31lGbNmqUBAwZo9erV+uqrr5SQwIIOAACorV9ylOIjglRcUa2ft+X7Opzjtim7SFkFZQoONOnUbnG+DscvtAsPchcHnvw6vc6ipcPh0ONfbpIkXTY0VZ3jwo553o4xoXr8ov6SpFeWbNUPW/Z5MeqDSiurlV1Yrh15JdqUbdXqzAL9tG2/tuQUNej1DodDd3+8Tpn5ZUqODtEjF/Rj7Iifu+Ws7uqZENHk4wbf+nGH+9+P/G+jquvoMMzILdaqXQUymwxNPqmjUmKcY6q25TX/qMH8kkrtyneO9eyfHN3s7w8AAADAtxpdzGoJbrrpJu3cuVMVFRX6+eefNXToUF+HBAAA/JDJZOismg4m13i+lmxRTVfWad3iFGJhPySXP53WRfERQdp9oExT3/hFK7bXLlx+uS5ba3YXKtRi1s2jujf4vOP7JemyoamSpNs/XOP17r5lGXk68f4FGvboNxr51Hca9+wPmvSvZbp09k86+5nvtXZ3wTHPsWhjrj5bs0dmk6Hn/zhQUSGBXo0R3tcc4wZzi8r1v5rzhlrM2pxTrLm/Zh5x3LxVuyVJI3u0V3xEsLrUFHq37SvxekzH4vp77xIXpqhQ/o4BAACAtsajYtbu3bv10ksv6a677tKMGTNq/QAAALQkZ/eJl+QsBPlqHxhvObhfFh3phwq1BOj+805QgMnQ8m37dcmry3Xp7OX6MSNPVTa7nvrauZfUn09PU/uIoEad+x/n9FFEcIByiyq0Pc97C/x2u0MPfr5BVTaHzCZDYRaz4sItSo4OUUigs1C5JefY3TGrMw9Iki4cmKzBnWK8Fh+aVr+OUZp+RldJ0j3z12l/sXfH+r338y5V2RwalBqtv411jtV8esFmFZVXuY+x2R36b00x6+LBHSVJae3DJfmmmLUm07lf1omMGAQAAADapIDGvuCbb77Reeedp7S0NG3atEl9+/bVjh075HA4NGjQoKaIEQAAoMmc0jVOIYFm7Sks1/o9VvVNbpkLpbnWcq3Z7VzsHdU73sfR+J/x/ZK0ODlKLy/Zqv/8mqmftuXrp20/KzU2VLvyS9UuzKJpp3dp9HlDLGalxYVpze5C7dpfql6JkV6J99M1e7Qpu0gRwQFaeseoWp0oN723Sp+v3avCsqp6zuBkLauWJCVFBXslLjSfm8/qpoUbcpSeU6RZn67Xvy7zzrVWZbVd7/68S5I05ZTOmtAvSW8v36lteSV6+butumNcL0nS0ow85VgrFB0a6M4pae2dnVnbfTBm0NWZdWJKdLO/NwAAAADfa3Rn1syZM/XXv/5Vv//+u4KDgzVv3jxlZmbqjDPO0OTJk5siRgAAgCYTHGjW6d2d+0u15FGD32zKlSQNSIlWfASFi7qkxIbqkQv6acnfztSU4Z1kCTC59+C5eVQ3RQR7NrosJTZUktznOl6V1XY9vXCzJOn6M7oeMVLNNSrQWn7sYpar4BXJeMEW59Bxg1+s3atnF22WzX783aNfrc/WvqIKtY8I0vi+SQo0mzRzQm9J0v8t3a7dB5x/xx+tdHZlTRqQrKAAZzege8ygF7sQG8LhcGhNTTGrf8foZn1vAAAAAP6h0cWsjRs36qqrrpIkBQQEqKysTOHh4XrggQf0+OOPez1AAACApja6T8vfN8u1X9bZfRgxeCwdokN0//l9tfSOM3XdGWmaekpnXTa0k8fnS60pZmV6qZg195dd2pVfqrjwIF19aucjnncVphrUmVVT8GKvrJapX8co3XqWcx+3Zxdt0VVv/Kxca/lxnfOtH3dIki4fmipLgPNycHTveA1Pa6fKarue+CpdhaVV+np9tqSDIwYlqWvNmMHM/FKv7xFXn6yCMuUVVyrAZOiEDt7pfgQAAADQsjS6mBUWFqbKykpJUlJSkrZu3ep+Li8vz3uRAQAANJNRveJlGNK6LKv2Fpb5OpxGK62s1tIM5/cw9stquPjIYM0c31v3nXeCe1HfE65i1k4vFLNKK6v1/LcZkqRbzuqmUMuRU8GjGlHMojOr5bv5rO765+QTFWoxa1nGfk14/gct2bzPo3OtyyrUyp0HFGg2dNnQVPfjhmHo7nN6yzCcIy4f+mKDKqvt6pUYUat4FB8RpDCLWXaH94q3DbG2ZoRqr6QIBdfsGQcAAACgbWnwVfsDDzygkpISDRs2TEuXLpUkTZgwQbfffrsefvhh/elPf9KwYcOaLFAAAICmEhcepMGpMZKkRRtzfRxN4y3dkqeKartSYkPUIyHc1+G0OaleHDM4Z9kO7SuqUEpsiC49ObXOYyJrxiG69sOqj6uYRWdWy3bR4I767ObT1CsxQnnFlZryxgo99uUmVdnsjTqPqytrfN+kI8aR9k2O0kWDnF1Y/6kZMXjx4I4yDMN9jGEY6lKzb9bWfc03anBNZoEkRgwCAAAAbdmRt3oexf3336/rr79eTz/9tIqLi92PFRcXa+7cuerevbuefvrpJgsUAACgKY3uk6Bfdx7Qwg05unKY5yPnfME1HvGsXgm1Fp7RPFx7Zu3OL5Pd7pDJ5Nn/DQpLq/TqEufUgxln9zhqt5h7z6yGjBmsKXhFergfGPxH1/bhmn/jqXr4i416+6edemXJVn26OkuJUcGKCglUZEigokICFR0SqNF9Eo4o/OSXVOqTNXskSVNO6Vzne/x1TE99sXavyqpsMpsMnT8g+Yhj0uLCtS7Lqu3NuG/W6ppi1gCKWQAAAECb1eBilsPh3Gw4LS3N/VhYWJheeeUV70cFAADQzEb3TtBjX27S8q15KiqvUkQLWvxfuoURg76UFBWsAJOhSptdOUXlSooK8eg8Ly/ZKmt5tXomROi8E48sIri4i1nl9RezHA6Hu+AVFdpy/p5xdMGBZj04qa9O6dpOd8xbqz2F5dpTeOQeWs9/m6Fz+iXpr2N7qkucs5Pqg192qbLarn7JURqUGl3n+ROjgnX9GV31zKLNGt07Xu0jgo44Jq2mM2vbvmLvfbB62OwOrctyjhk8MSW6Wd4TAAAAgP9pcDFLEnf6AgCAVqtr+zB1iQvT9rwS/bAlTxP6Jfk6pAaprLZrr9W5mN0rKcLH0bRNAWaTkmNCtHN/qXbtL/WomJVjLdebP26XJP1tbE+Z6+nuigxxfoU/1p5Z5VV2VdaMoWPMYOsyvl+Shndtp417i1RYViVrWZWs5VUqLKvStrwS/e/3vfri9736en22/jgkVTeN6qZ3lu+U5OzKqu+67uZR3dQrKUJDOsfW+byrOLatmcYMbt1XrJJKm0ItZnWLZ4wqAAAA0FY1qpjVo0ePYxa08vPzjysgAAAAXzAMQ6N7x+u1H7Zr0YacFlPMyrGWy+GQLGaT2oVZfB1Om5UaG+osZuWXamhau0a//vlvtqi8yq5BqdE6q3d8vce6ClPHKma5OrfMJkNhFnOjY4J/iw61aHjXuv/WNmVb9fiXm7Q4fZ/e/mmnPvhll6psDsWGWXRu//pzm8lkaOwJiUd9vmt7Z0GpucYMuvbL6pscVW+RFwAAAEDr1qhi1v3336+oqKimigUAAMCnRvdO0Gs/bNe36bnHtfdRc8qu6cpKjAqmi96HXPtmZeaXNvq1WQVlmvtLpiTpznG9jvl/R9f+V6WVNlXZ7Ao01723lqvYFRkcwN9GG9MrMVJzrh6i5Vv367EvN2rNbueYvktPTlFw4PEVNl2dWftLKlVYWtXkIyzX7C6QJJ3YketQAAAAoC1rVDHr0ksvVXx8/XeKAgAAtFSDO8UowGSooLTquPY+ak57CsokOfdtgu+k1hSzdnlQzPq/H7ap2u7Q8LR2DerqijxkZKC1rErtwo/c10g6WMxixGDbNbxrO82/8VR9uS5bv2cV6oYzux33OcOCApQQGaQca4W25hVrUGqMFyI9ujWZ7JcFAAAAQKr7Ns46cDcnAABo7QLMJnWIdhawMvPLfBxNw2QXOjuzKGb5lqfFrAMllfpghbMra/rIrg16jdlkKCLIeU+atbz6qMdZXZ1ZFLPaNMMwNKFfku4c10vhQY26l/Go0uJqRg028b5Z5VU2bcq2SpJO7BjdpO8FAAAAwL81uJjlcDiaMg4AAAC/kBLrKmY1vsPGF/a6ilnR/t9F1podLGY1rgj61vIdKquy6YQOkTq9e1yDXxfZgH2z6MxCU0lr7xw1uC2vuEnfZ+Neq3uvr44x5DgAAACgLWtwMctutzNiEAAAtHodo2v2PjrQUopZjBn0B649s/KKK1RaefRuqUOVVlbrrR93SJKuO6NroyYhNKaYRWcWvM21b9b2vKbtzFqTWSDJuV8Wk0IAAACAtq3BxSwAAIC2wNWZtftAyxgz6O7MagH7e7VmUSGB7g6oho6o/PCXTB0orVJKbIgm9E1s1PtFBteMGaynmGUtq645lmIWvKtre+eYwW1NPGZw7W72ywIAAADgRDELAADgEK4OmxY3ZpDOLJ9rzL5ZVTa7XvthuyTp2tPTFGBu3NfyKMYMwodcYwa355XIbm+6cfSrdxdIYr8sAAAAABSzAAAAaukY4yxItITOrMpqu/KKKyRRzPIHqe2cfzs79x+7W+WLtXuVVVCmdmEWTT4ppdHvRTELvpQcHaJAs6GKarv2FDZNriwsq3J3fvXvGNUk7wEAAACg5aCYBQAAcIiUGOe4vr2FZaqy2X0cTf1yrOVyOCRLgEmxYRZfh9PmpTawq8/hcOiVJVslSVef2lnBgeZGv5drHyxreT1jBstde2YFNPr8QH0CzCZ1aufszmqqUYPrspwjBlNiQ9QuPKhJ3gMAAABAy9Eiilk7duzQNddcoy5duigkJERdu3bVvffeq8rKylrHrV27VqeffrqCg4OVkpKiJ554wkcRAwCAlqp9RJCCAkyyO6S9BeW+Dqdeh44YNAzDx9GgoWMGv0vfp03ZRQqzmHXlsM4evZer26q+PbPozEJT6hLnKmYVN8n5V2cWSJL6M2IQAAAAgKQWcZvmpk2bZLfb9eqrr6pbt25at26dpk2bppKSEj311FOSJKvVqjFjxmj06NF65ZVX9Pvvv+tPf/qToqOjde211/r4EwAAgJbCMAx1jAnR1n0lyjxQ6h4d54/21oz3SoxkxKA/aGgx6+Warqw/DklVVKhnhaaDxazqox5jpZiFJnTovllNwTWus2dCRJOcHwAAAEDL0iKKWePGjdO4cePcv6elpSk9PV0vv/yyu5j17rvvqrKyUm+88YYsFotOOOEErV69Wk8//TTFLAAA0CgdY0KdxaxjFCV8zdWZ1SE6xMeRQDpkzOCBMtntDplMR3bLrdp1QCu25yvQbOia07t4/F6u0YH17ZnlKmZFBlPMgvd1jQuXJG1romJWjtW5HyDFegAAAABSCxkzWJfCwkLFxsa6f1++fLlGjBghi+XgfhFjx45Venq6Dhw4cNTzVFRUyGq11voBAABtW0qsszi0+0CZjyOpX3ZNMSsxisVef5AUFSyzyVBltV25RRV1HvPmsh2SpPMHJCspyvMipKvbqr5iFmMG0ZS6tG/aPbNyrM78lkB+AwAAAKAWWszKyMjQCy+8oOuuu879WHZ2thISEmod5/o9Ozv7qOd69NFHFRUV5f5JSUlpmqABAECLkRLj6rDx786sPQXOYlsHFnv9QoDZpOSaLrm6Rg1W2+xanJ4ryTli8Hi4uq2s5XUXs6psdpVU2iRRzELTSKvZM2tPYZnKq2xeP7+rmEVnFgAAAADJx8Wsu+66S4Zh1PuzadOmWq/JysrSuHHjNHnyZE2bNu24Y5g5c6YKCwvdP5mZmcd9TgAA0LKluMbF+fmYwWzXYu9xdPjAu+rbN2vVrgIVlVcrJjRQA1Kij+t9jtWZVVR+cC+tiOAWMVkcLUxsmEVRIYFyOLy/b1Z5lU0HSp1/2wmRQV49NwAAAICWyadXtrfffrumTp1a7zFpaWnuf+/Zs0dnnnmmTjnlFM2ePbvWcYmJicrJyan1mOv3xMTEo54/KChIQUFcIAEAgIM6xjiLQ5l+PmZwT4GzmJVEZ5bfSKmnmPVdTVfWiB7tZa5jP63GcBWzrGVVcjgcMoza53MVucKDAhRgbpHDGODnDMNQl7gwrc4s0Pa8EvVOivTauffVjOkMCjDRWQgAAABAko+LWe3bt1f79u0bdGxWVpbOPPNMDR48WHPmzJHJVPuifPjw4br77rtVVVWlwEDnBc/ChQvVs2dPxcTEeD12AADQernGDO4rqlB5lU3BgWYfR3Skymq78oqdC74Us/xHaj1dfYvT90mSRvZs2Pff+kTWLPDbHVJxRbUigmsv+FtrilmRdGWhCaW1dxaztu0r9up5XV2nCZHBRxRqAQAAALRNLeI2zaysLI0cOVKpqal66qmntG/fPmVnZ9faC+uyyy6TxWLRNddco/Xr12vu3Ll67rnnNGPGDB9GDgAAWqLo0ECFBzmLALv9tDvLtZ+MJcCk2DCLj6OBy9HGDGYXlmvjXqsMQxrR/fiLWcGBZlkCnF/l6xo16Hoskq4WNKGu7cMlSdv2eXfMIPtlAQAAADhci7hVc+HChcrIyFBGRoY6duxY6zmHwyFJioqK0oIFC3TjjTdq8ODBiouL06xZs3Tttdf6ImQAANCCGYahjjEh2pRdpMwDpeoWH+7rkI6wt/DgiEE6F/zH0YpZSzY7Rwz27xitduHeGXEdGRyovOIKWcuqpcMGEbiKWYxoQ1PqEhcmSdrm5T2zsmvyWzz7ZQEAAACo0SKKWVOnTj3m3lqS1L9/f/3www9NHxAAAGj1OsaEalN2kXbXMS7OH+wtdHaMMWLQv7iKWfuKKlRaWa1Qi/Pr9nc1IwbP9MKIQZeokADlFVfU2ZllLaczC00vrb2zmLUlp0glFdUKC/LO5SWdWQAAAAAO1yLGDAIAADS3lNgQSf47ZvBgZ1aIjyPBoaJCA937VGXmO/92qmx2Ld2SJ0ka2TPee+9VU6iqb8wgnVloSt3jI9S5XahKKm1656edXjtvjtW5H2ACxSwAAAAANShmAQAA1CElxtlhk3nATzuzCujM8lep7WqPGly584CKKqrVLsyi/slRXnsfV9eVqwvrUBSz0BzMJkM3jeouSXr1+20qraz2ynmzazqzEshvAAAAAGpQzAIAAKhDSs24OFd3jb85dM8s+JfD981yjRgc0aO9TCbv7W/mKlRZ6xozWOYsKkQGU8xC05o0oIM6tQtVfkml3l7une6sXFcxK4I9swAAAAA4UcwCAACoQ8cY5/g+v+3MYsyg3zpYCHUVs3IlSSO9uF+WdLBQVXcxy9WZ1SK2yEULFmA26aYzu0mSZnuhO8vhcLg7sxIp1gMAAACoQTELAACgDq6CREFplYrqGOPma65iFou9/ufQzqy9hWXalF0kkyGN6O7dYlaD9swKpTMLTe+Cgcnq1C5U+0sqj3vvLGt5tcqr7JLYMwsAAADAQRSzAAAA6hAeFKCYmkLA7gP+NWqwotqmvOIKSVKHaDqz/M2hxSzXiMEBKdGKCbN49X3qK2a59tFizCCaw6HdWa8uOb7urJyarqyokEAFB5q9Eh8AAACAlo9iFgAAwFEcPi7OX+RanYWsoACTu+AG/5F6yN/Nt5tcIwbjvf4+kTUjBK3lRxYO3J1ZIfx9oHlcMDBZqbHH353lKmYl0pUFAAAA4BAUswAAAI7CtW+Wv3Vm7SlwxpMUFSzDMHwcDQ7XITpEJkOqqLa798s6swmKWQ0aM0gxC80kwGzSTaOOf++s7JoRqvGRQV6LDQAAAEDLRzELAADgKFJiajpsDvhXZ1a2lf2y/Fmg2eQe/1hlcygu3KITOkR6/X1cIwSthxWzHA6H+7FIilloRq7urLziSr370y6PzkFnFgAAAIC6UMwCAAA4io7ucXH+1pnlXOztEMV+Wf7KNWpQks7oES+TyfsddJFH6cwqrqiW3eH8N51ZaE6Bh+6d9f1Wj7qzcmrGqCZQzAIAAABwCIpZAAAAR5HiHjPoZ51Zhc7iGp1Z/qtTu4PFrJE92zfJexxtzKDrd0uAScGB5iZ5b+BoLhiUrJTYEOUVV+qDFZmNfr2r8zSB/AYAAADgEBSzAAAAjqJjzZjB3QfK5HA4fBzNQXtq9pRJiqYzy1+l1HRmmQxpRPemKWa5OrMqqu0qr7K5H7eWObthXGMIgeYUaDZpyvDOkqQft+Y1+vW5rmJWBHtmAQAAADiIYhYAAMBRdKzpzCquqFZBadUxjm4+2a5iFmO4/FbvJOceWcPS2ikqtGmKShFBATJqphdayw/+fbo6s6JCAprkfYFjOaFDlCQpPaeo0a9lT0AAAAAAdaGYBQAAcBTBgWbF13QHZPrRqMG9NWMGk6JZ7PVXI3u01ytXDNYzfxjQZO9hMhmKCHIWrKxlRxazItkvCz7SMzFCknO/weKKhu+bZbM7tK+IPbMAAAAAHIliFgAAQD1c3VmZ+WU+jsSpotqmvOJKSVJSFGMG/ZVhGBrXN7HJF+RdXV+FZQcLBq4urSiKWfCR2DCL2tfcCLClEd1ZecUVsjuc4znjwhkzCAAAAOAgilkAAAD1cO19tNtPOrNyCp1dC0EBJsU00fg6tByugtWhnVnWMopZ8L1eNd1Z6dkNL2bl1IwYbB8RJLPJaJK4AAAAALRMFLMAAADqkRLjLGY195jBjNxi7S+uOOJx94jBqGAZBou9bV1kcE0xq449s1zPAb7QI6GmmNWIzizXfoCJjBgEAAAAcBiKWQAAAPVIiW3+MYOfr92js59Zoote/lEV1bZaz+2tWexlxCCkg91XhXRmwc/09KQzq2a/rHiKWQAAAAAOQzELAACgHh2buTPrx615mjF3jRwOacf+Ur33865azx8sZrHYi4PdV4WlR3ZmUcyCL/Ws6cza3IjOrBw6swAAAAAcBcUsAACAerjGDGYdKJPD4WjS99qwx6rr/r1SlTa7Ordzvu+L32aouKLafYx7zGA0i72QokLrGTMYEuCTmABJ6p4QLsOQ8oorlVfHyNS6ZNfsmZUQGdSUoQEAAABogVpcMauiokIDBgyQYRhavXp1refWrl2r008/XcHBwUpJSdETTzzhmyABAECrkRQdLJMhVVTbta+oYQuynsjML9XUOStUVFGtoV1i9cUtpystLkz7Syr1fz9scx/n6sxKZMwgdJQxg+XVtZ4DfCHUEqDUWGdRfnMDRw3muItZFOsBAAAA1Nbiill33HGHOnTocMTjVqtVY8aMUadOnbRy5Uo9+eSTuu+++zR79mwfRAkAAFqLQLPJvT9VU40azC+p1JQ5K5RbVKFeiRGafdVJCgsK0O1jekqSXvt+m7uzwdWZ1YExg5AUGezsvrKWHezeO9iZRTELvuUaNbipkcWsRPIbAAAAgMO0qGLWl19+qQULFuipp5464rl3331XlZWVeuONN3TCCSfo0ksv1S233KKnn37aB5ECAIDWpGNMTTErv8zr5y6rtOmat37Rtn0l6hAVrDevHuLuqJnQL1H9O0appNKmF7/NkCRlF7LYi4Mi6+rMchWzgilmwbd6JjZu36wcq7NoT2cWAAAAgMO1mGJWTk6Opk2bprfffluhoaFHPL98+XKNGDFCFovF/djYsWOVnp6uAwcOHPW8FRUVslqttX4AAAAOlVIzKmt3E3Rm/f3j3/XbrgJFhQTq39cMqVWkMgxDd47rJUl69+ed2rqvWHnFlZKkDowZhOouZrn+zZhB+JqrmNWQzqzyKpv7b5diFgAAAIDDtYhilsPh0NSpU3X99dfrpJNOqvOY7OxsJSQk1HrM9Xt2dvZRz/3oo48qKirK/ZOSkuK9wAEAQKuQEuMsZi3L2K+i8qpjHN1wudZyfbI6S5L02lUnqVt8xBHHnNotTqd1i1OVzaGZ836XJAUFmBQdSqECBwtW1pq/y/Iqmyqq7c7n+BuBj7nGDG7JKZLd7qj3WNeIweBAk3t8JgAAAAC4+LSYddddd8kwjHp/Nm3apBdeeEFFRUWaOXOm12OYOXOmCgsL3T+ZmZlefw8AANCyndY9TpK0fNt+jXnmey3akOOV885fnSW7QxqUGq0hXWKPetwd45x7Z63YkS9J6hAdIsMwvBIDWraowzqzXEUtw5DCLRQE4Fud48JkMZtUUmlTVkH9Y1rdI1Qjg8lvAAAAAI7g0yvc22+/XVOnTq33mLS0NH377bdavny5goKCaj130kkn6fLLL9dbb72lxMRE5eTUXlhy/Z6YmHjU8wcFBR1xXgAAgEMN7hSjd64Zqr9//Lt25Zfqz//+Vef0S9K95/VRfIRn47AcDoc+WrlbknTx4Po7w/t3jNY5/ZL0xe97JTkXewHp4L5YReXVstkdtfbLMpkoCMC3As0mpbUP06bsIqVnF7lHttYlp8i5X1Y8+Q0AAABAHXxazGrfvr3at29/zOOef/55PfTQQ+7f9+zZo7Fjx2ru3LkaOnSoJGn48OG6++67VVVVpcBA50X9woUL1bNnT8XExDTNBwAAAG3Gad3j9PWtI/TsN5v1fz9s1xe/79UPW/bpnnP66JKTGz+meF2WVZtzimUJMOmc/knHPP72MT301fps2ewOJUWz2AunyJCDX+eLy6vZLwt+p1dihLOYlVOk0X0SjnpcziGdWQAAAABwuBaxZ1Zqaqr69u3r/unRo4ckqWvXrurYsaMk6bLLLpPFYtE111yj9evXa+7cuXruuec0Y8YMX4YOAABakRCLWTPH99YnN56qfslRspZX6455a7V0S16jzzVvlbMra+wJiQ0qPKS1D9dlQ1IlSX2SIhv9fmidggLMCg50fqUvLKuStaxaUu0iF+BLPRKd+2alZxfVe5xrz6yESKZmAAAAADhSiyhmNURUVJQWLFig7du3a/Dgwbr99ts1a9YsXXvttb4ODQAAtDJ9k6P08Q2n6Nyajqov1+1t1Osrq+36ZHWWJOmiQckNft29E/vovT8P1ZXDOzXq/dC6uYqh1vIqOrPgd3rVFLM259RfzMp2F7PozAIAAABwpBZ5y2bnzp3lcDiOeLx///764YcffBARAABoawLMJl04KFmfr92r79L3yeFwyDAatkfRt5tydaC0SvERQTq9+7FHLh/6nqd0i/M0ZLRSUSGByrFWqLDsYDHLtZcW4Gs9EpzFrK37ilVlsyvQXPf9lDkUswAAAADUo9V0ZgEAADS34WlxsgSYlFVQpozc4ga/7qOVzhGDFwxKltnUsAIYcDSuwpVzzCCdWfAvydEhCg8KUJXNoe15JUc9LsdaIUlKjKKYBQAAAOBIFLMAAAA8FGIxa1haO0nSd+n7GvSa/cUV+i49V5J08aCOTRYb2g73mMEyxgzC/xiGoR4J4ZKkTUfZN8vhcBwcMxhBMQsAAADAkShmAQAAHIeRPZxjAr/bnNug4z9ZvUfVdodO7Bil7jXjt4DjERlysDPLPWaQYhb8SE/XvllHKWYVllWpstouSYqPDGq2uAAAAAC0HBSzAAAAjsPIns5i1ort+SquqD7m8a4RgxcNpisL3hF1SDHLWk4xC/6nZ03h/midWa6urJjQQAUHmpstLgAAAAAtB8UsAACA49AlLkyd2oWqyubQjxl59R67YY9VG/ZaFWg2NLF/h2aKEK2dq3BlLWfMIPxTD1dnVk7dxSzXflkJkYwYBAAAAFA3ilkAAADHwTCMQ0YN1r9v1rxVzq6s0b0TFBNmafLY0DZEBgdIkgrLqlVYVl3rMcAfuDqzduWXqqSODtacwpr9sihmAQAAADgKilkAAADHaWSveEnSd5ty5XA46jymymbXJ6uzJEkXDWLEILzH1YVlLauSlc4s+KF24UGKC3fuhbUlt/iI53OsrmIW+2UBAAAAqBvFLAAAgOM0PK2dggJM2lNYXudCrSQt3pSrvOJKtQuz6IyafbYAb6i1ZxbFLPipXjWjBtOzrUc859ozK5HOLAAAAABHQTELAADgOAUHmjUsrZ0kZ9HqcJXVdj3xdbok6eLBHRVo5isYvMe1Z9aB0koV1Yxwi6SYBT/TI8FVzDp6Z1Y8xSwAAAAAR8FKCgAAgBecWdNt9V36kftmvfbDNmXkFisu3KIbzuzW3KGhlXN1Ye0pKDviMcBfuDuzco7szMqxVkiiMwsAAADA0VHMAgAA8IKRPZ37Zv26M19F5VXuxzPzS/XCt1skSXef05siA7zO1YVVZXPu1xZqMdP9B7/TI/HonVnZ7j2zKGYBAAAAqBtXuQAAAF7QOS5MXeLCVGVzaFnGfvfj93+2XuVVdg1Li9WkAck+jBCt1eEF0shgCqbwPz0SwiVJecUV+mR1ljJyi1Rls6vaZldesbMzKyEqyJchAgAAAPBjAb4OAAAAoLU4o0d7bc8r0ZLNuRrXN1EL1mdr0cZcBZgMPTSprwzD8HWIaIXCLGaZTYZsdmdnFt1/8EehlgClxYVpW16J/vLBaklSgMlQSmyoHA7JbDLULoxiFgAAAIC60ZkFAADgJSMP2TerpKJa93+2QZI0bUSausVH+DI0tGKGYSgy+OA9ahSz4K+euLi/LhyUrBM7RinUYla13aHteSWSpE7tQmU2UfAHAAAAUDc6swAAALxkWFo7BQeatLewXH/54DdlFZQpOTpEt4zq7uvQ0MpFhQTqQKlzr7bIEL7iwz+d1DlWJ3WOlSQ5HA7tKSxXRm6xduSVaEiXWB9HBwAAAMCfcaULAADgJcGBZg1Pa6fF6fu0aGOuJOn+805QiMXs48jQ2kUe0o0VSWcWWgDDMJQcHaLk6BCd0aO9r8MBAAAA4OcYMwgAAOBFZ/aKd/97dO8Eje6T4MNo0FYcOlqQMYMAAAAAgNaGYhYAAIAXndkzXmaToZBAs+47r4+vw0EbUaszK5hiFgAAAACgdWHMIAAAgBelxIbq/WnDFB4UoI4xob4OB23EoQUsOrMAAAAAAK0NxSwAAAAvG9Il1tchoI2JYs8sAAAAAEAr1qLGDH7xxRcaOnSoQkJCFBMTo0mTJtV6fteuXTrnnHMUGhqq+Ph4/e1vf1N1dbVvggUAAACaSWTIwXvU6MwCAAAAALQ2LaYza968eZo2bZoeeeQRjRo1StXV1Vq3bp37eZvNpnPOOUeJiYn68ccftXfvXl111VUKDAzUI4884sPIAQAAgKZ1aAGLYhYAAAAAoLVpEcWs6upq/eUvf9GTTz6pa665xv14nz4HN1VfsGCBNmzYoEWLFikhIUEDBgzQgw8+qDvvvFP33XefLBaLL0IHAAAAmlztMYMt4is+AAAAAAAN1iLGDK5atUpZWVkymUwaOHCgkpKSNH78+FqdWcuXL1e/fv2UkJDgfmzs2LGyWq1av379Uc9dUVEhq9Va6wcAAABoSSKD6cwCAAAAALReLaKYtW3bNknSfffdp3vuuUeff/65YmJiNHLkSOXn50uSsrOzaxWyJLl/z87OPuq5H330UUVFRbl/UlJSmuhTAAAAAE2DMYMAAAAAgNbMp8Wsu+66S4Zh1PuzadMm2e12SdLdd9+tiy66SIMHD9acOXNkGIb+85//HFcMM2fOVGFhofsnMzPTGx8NAAAAaDYxoc6R2hazSSGBZh9HAwAAAACAd/l0oP7tt9+uqVOn1ntMWlqa9u7dK6n2HllBQUFKS0vTrl27JEmJiYlasWJFrdfm5OS4nzuaoKAgBQUFeRI+AAAA4BdSYkN09amdlRwdIsMwfB0OAAAAAABe5dNiVvv27dW+fftjHjd48GAFBQUpPT1dp512miSpqqpKO3bsUKdOnSRJw4cP18MPP6zc3FzFx8dLkhYuXKjIyMhaRTAAAACgtTEMQ/dOPMHXYQAAAAAA0CR8WsxqqMjISF1//fW69957lZKSok6dOunJJ5+UJE2ePFmSNGbMGPXp00dXXnmlnnjiCWVnZ+uee+7RjTfeSOcVAAAAAAAAAABAC9UiilmS9OSTTyogIEBXXnmlysrKNHToUH377beKiYmRJJnNZn3++eeaPn26hg8frrCwME2ZMkUPPPCAjyMHAAAAAAAAAACApwyHw+HwdRD+xGq1KioqSoWFhYqMjPR1OAAAAAAAAAAAwEOs+bcOJl8HAAAAAAAAAAAAABwNxSwAAAAAAAAAAAD4LYpZAAAAAAAAAAAA8FsUswAAAAAAAAAAAOC3KGYBAAAAAAAAAADAbwX4OgB/43A4JElWq9XHkQAAAAAAAAAAgOPhWut3rf2jZaKYdZiioiJJUkpKio8jAQAAAAAAAAAA3lBUVKSoqChfhwEPGQ7KkbXY7Xbt2bNHERERMgzD1+HAQ1arVSkpKcrMzFRkZKSvwwHQQpA7AHiC3AHAE+QOAJ4gdwDwRFvPHQ6HQ0VFRerQoYNMJnZeaqnozDqMyWRSx44dfR0GvCQyMrJNJmgAx4fcAcAT5A4AniB3APAEuQOAJ9py7qAjq+WjDAkAAAAAAAAAAAC/RTELAAAAAAAAAAAAfotiFlqloKAg3XvvvQoKCvJ1KABaEHIHAE+QOwB4gtwBwBPkDgCeIHegNTAcDofD10EAAAAAAAAAAAAAdaEzCwAAAAAAAAAAAH6LYhYAAAAAAAAAAAD8FsUsAAAAAAAAAAAA+C2KWQAAAAAAAAAAAPBbFLMAAACAFqi6utrXIQBogdasWSOr1errMAAAAIBGoZgFAIAP5ebm6r333tOyZct04MABX4cDoAXYs2ePhgwZolmzZvk6FAAtSFZWli655BINHDhQb7/9tq/DAQAAABqFYhbgJVarVTk5OZIku93u42gAtAR33XWXunXrpldffVXjxo3TLbfcoh07dvg6LAB+7LbbblPnzp2VmJiom266ydfhAGghZsyYodTUVJWVlSkmJkYRERG+DglAC5GTk6NPP/1Ua9asoSscQIOxToqmQDEL8IKHHnpI3bp104svvihJMpn4/1oAji4rK0vjxo3T4sWL9fnnn2vhwoV66aWXtHr1aq1bt87X4QHwQ7t27VJycrI+/fRTLV26VJ9++qk6dOjg67AA+LmvvvpKUVFRWrx4sRYvXqzPPvtMJ510kv73v//5OjQALcCsWbOUlpam5557TiNGjNANN9ygDRs2SGJxGsDRsU6KpsJfEnAciouLdcMNN2j+/Pnq3Lmzfv31Vy1btkyS5HA4fBwdAH9yaE6oqqrShAkT9Prrr2vEiBGyWCy66KKLZBiGevTo4cMoAfiTQ/NGQECAkpOTNWTIEA0ZMkSrVq3SHXfcoaefflqLFi1SeXm5DyMF4E8OzR3Z2dl69dVX9dtvv2nEiBGqrKxU586dVVRUxL5ZAOr1wQcf6Ouvv9Znn32mBQsW6N///rd27typqVOnSmJxGsCRWCdFU+O/PEAjHZp8g4KClJqaqr/+9a964YUXlJeXp48//lhlZWUyDINEDUCSVFlZKZvN5v69Q4cOuvLKK9W3b19JUkFBgS699FJVVFToscce08cff0z+ANq4w/NGUlKSHnjgAc2dO1djx47VBRdcoE2bNunNN9/U5Zdfrttuu428AeCI3DFlyhRdeumlkiSbzSaLxaKEhARt2bJFkZGR5A0Abq584Prfjz/+WB06dNCoUaNkNpt1/vnna8iQIfr111/17LPP1joWQNvFOimaE8UsoBEOvzgMCAjQDTfcoEsvvVRDhw7V+PHjtWzZMn311VeSJMMwfBUqAD/x0EMPady4cTr//PP1wgsvKD8/XxaLRTExMZKkzMxMderUSaWlpfr73/+ukpIS3X333Zo5c6aPIwfgK4fnjf3798swDA0fPlzXXXed8vPz9dFHH2nu3Llau3at7r77bi1fvlyvvPKKr0MH4EOH544DBw7IMAz39Yuri2LUqFHau3evNm3axPUKAEm11zoMw1BxcbGqq6vVuXNnVVZWuo8LDAxU7969NWvWLBUVFZFDgDaurKxM+/fvd/9uNptZJ0WTopgFNFBdC9KGYSgiIsJ9Z8FNN92koKAgffLJJ9qzZ48k7lQC2qpVq1bp5JNP1gcffKArrrhCERERmjNnjh566CH3MQ6HQykpKVqyZIkWLVqkKVOmaO7cubr44ou1YMECxv8Abcyx8kZUVJRuu+02vfDCCxo8eLCCgoIkSVdccYUSExO1YcOGWjfdAGgbjpY7HnjgAUnOhSXp4AKSzWZTXFycdu/e7bOYAfgP11rHpEmT3J0U4eHh6tu3r5YsWaIHH3xQeXl5mjVrlp5//nn9/e9/V2xsLDfRAG3cAw88oKFDh+r888/X5Zdfrl27dslkMik8PJx1UjQZilnAMRxrYckwDBmGIbvdrvj4eF1xxRX6/fff9emnn7qfJ1EDbUtxcbHef/999erVS8uWLdOf/vQnffDBBzrnnHOUkZGhgoKCWscPGDBA0sEvdRkZGYqMjFRgYCD5A2gj6ssbW7du1YEDByRJ3bt317Bhw2QymWQymWS32xUbG6sdO3aosrLSvWgNoG04Vu44/DuHJJ166qnat2+f9u3bJ0my2+3NHDUAf3D4Wkd4eLjmzJmjBx98UJJ09913a9SoUfrwww/Vu3dvzZ07Vx999JEuv/xydevWTRUVFT7+BAB8YdmyZRo4cKA+/PBDzZo1S+eff762bdumu+66S5KzE5x1UjQVillAPRqzIO260/HPf/6zOnXqpK+//lq//fab5s2bp1mzZvnoEwDwBYfDoS5dumj69OmKiopSdXW1JGdXRXp6uiIjIyUd2WJvGIZWrVqlvXv36qqrrlJISAht+EAbcay8ERUVJenIvGEymfTNN98oMjJSU6ZMafa4AfhWQ79zHMpms+m0007TkiVLJB0cPwig7ahvrWP79u3Ky8uTxWLRE088oSVLlmjBggVKT0/XyJEjJUmbN29WQECAbz8EAJ9YuHChhg0bpp9++kkXX3yx7rjjDvXv31/h4eHuYxwOB+ukaBL8lweoh+vi8IILLnBfHAYEBNR5cei668BkMumGG27Q9OnTdfbZZ8tqteof//iHDz8FgOYWERGh6667zt0h4VokKiws1IABA45YNEpPT1dubq7mzZunOXPm6I9//KP++Mc/NnvcAHynsXlj48aNys3N1X//+1+9/fbbmjp1qk4++eRmjxuAbzU2d0hSWFiYcnJyFBcXp4qKCvfIUgBtx7HWOlz7+5pMJiUmJioxMdH92nnz5ikxMVF/+MMffBU+AB+6/vrrVVpa6i5eVVRUKCMjQ2effbbS09PVs2fPWqONXftosU4Kb6CYBdSjsReHJpNJO3fu1H/+8x9t3bpVU6dO1VNPPaXY2Nhmjx2A7zgcjlqjvlxf5FatWqURI0a4j3E9vm7dOr399tuyWq1auHChhgwZ0vxBA/CpxuaNtWvX6vXXX1dZWZm+/PJLDR06tPmDBuBzjc0drgXru+66S3369KGQBbRRx1rrOHxscUFBgX744QctWLBAb775pm6++WalpqbWyi8A2oZDi9vvvfeepk+fro4dO+qjjz7S7NmzddFFF+nJJ5+U5Ny3k3VSeBPFLKAejb04lKS3335bH3/8sX7++WfukAZaqfz8fFVXVys6OloWi8V9t5F0cJHIxdWxWVhYqJ9//ll33nmnJGc+2blzpzp16qTx48dr4MCBSktL88nnAdD0vJ03zj33XA0aNEjdu3f3yecB0Dy8lTsyMzOVkpLiXrCmowJo2xq71mGz2bRixQr9/vvvWrRoETfRAJAkWa1WvfHGG5o4caJKSkr0/fff64ILLtCf//xn9ezZUxLrpPAuhmOjTcvPz1dubq4qKyslOb+guVRXV9cqUtntdhmG4b44HD58uKSDF4cu99xzj3Jzc0nQQCvkcDj0l7/8RaeccoomTJigs846S5mZmTKbze7N0wMCAuRwOPTMM89IOniX4zfffKPo6GiNGDFCWVlZuuSSS3TyyScrNzdXoaGhFLKAVqqp8kZYWBiFLKAV83buGDx4sPbt28f+WEAb4a21jl27dkmSYmNjdeedd+q7776jkAW0YsfKHYe77rrrdNFFF8lisSgmJkZ9+vRRVFSUVqxY4T6GdVJ4E99k0SY11cUhgNZr5cqVGjp0qFasWKF//etfmj59uioqKjRlyhRJB3PE//3f/ykpKUkffvih9uzZ4379pk2bNHDgQD3yyCPq3r27CgoKtHLlSsXHx/vk8wBoeuQNAJ5oqtzRvn17n3weAM3H22sdJ510knJzc2UYhnt/HACtjye5Q9IRY0a///579erVS+PHj2/W+NF2UMxCm8PFIQBPfP7550pMTNTnn3+us846S9dcc41efPFFrVixQtu2bZMkffbZZ3rppZf08MMPa+nSperQoYP79Z988onmzZund955R/Pnz9eCBQuUkpLiq48DoBmQNwB4gtwBwBPcRAPAE8ebO/Ly8rRnzx7dd999mjVrli6++GLFxsbK4XD45POgdWPPLLQ5rovDOXPmqF27dpKkfv36adSoUdq2bZvS0tJqXRxOnTq11izpTz75RL/88ovWr1+v+fPna8yYMb76KACagWv/iYkTJ2r48OHuvCE5N0hOTEx0b54+ceJEjRo1SmFhYbXOUVJSotGjR+uWW27R5Zdf3qzxA2h+5A0AniB3ADgerHUA8MTx5I5NmzbpP//5j/79738rODhY77zzjs4880xffhy0chSz0GZwcQigod5//32deOKJ6tOnj/supEGDBrmfd224npubq4CAgFr55PC84Xrs4YcfbvrAAfgMeQOAJ8gdAI4Xax0APOGN3NGpUyedcsopGjhwoM4999xmjR9tE2MG0aq9//772rBhgyTVujh03WHk2rywsReHfLkDWqfvv/9e/fr10+WXX653331XZWVldR7nyifffvutTj31VAUHB7vnSANoW8gbADxB7gBwPFjrAOAJb+eOkJAQnXXWWRSy0GwoZqFV4uIQQGPt3r1bb731lkaPHq2ZM2fq5Zdf1po1a+o81mQyyeFw6JdfftHYsWPdj61Zs0YFBQXNGDUAXyJvAPAEuQOAp1jrAOAJcgdaC4pZaHW4OATgicjISE2YMEHXXHONHn74YbVv317PPffcUXPBb7/9poKCAo0YMUIbN27UqFGjNHz4cGVnZzdv4AB8hrwBwBPkDgCeYK0DgCfIHWhNKGah1eHiEIAnIiMjddFFF6lv376SpH/961+aO3eulixZIofD4T7O9e+1a9cqNDRUjz76qPr166ekpCTl5OSoV69ePokfQPMjbwDwBLkDgCdY6wDgCXIHWhOKWWh1uDgEcLzsdrtGjx6tcePG6dFHH1VWVpb7OcMwJElff/21Nm/erLVr12rFihV69913FRER4auQAfgYeQOAJ8gdABqKtQ4AniB3oDWhmIVWjYtDAC4ZGRkaMWKE3n77bUmq9aXNtcmpi2sm9CuvvKJffvlFH3/8sfuxzMxMSdJ1112n//73v1q8eLEGDRrUHB8BQDMjbwDwBLkDQFNjrQOAJ8gdaOkoZqHF4eIQQGNUVlbqqquuUq9evbR06VKtX79ekvOLms1mkyQFBASourpaGzdudP9us9mUmpqqW2+9Vc8884zmzp2rMWPG6O9//7vKyso0cuRITZo0yVcfC0ATIm8A8AS5A8DxYK0DgCfIHWhLKGahxeDiEEBjPfbYY4qJidHOnTuVkZGhiRMnuuc822w2mc1mSdLzzz+vqKgo/e9//1NVVZUk5yanknTrrbdqx44duvzyy2WxWPTcc88pJCTENx8IQJMjbwDwBLkDgKdY6wDgCXIH2iKKWWgRuDgE0Fivv/663n//fb355ptasmSJOnfurMGDB2vp0qWSJLPZrIqKCk2fPl0PP/ywXn31Vc2YMUOBgYGSnF8A33vvPaWlpemkk07SqlWr9Pnnnys2NtaXHwtAEyJvAPAEuQOAp1jrAOAJcgfaKopZ8HtcHAJoDFeL/AUXXKDVq1dr8uTJ7ufCwsIUEhKirVu3SpIsFotmzJihLVu26IorrnDPiHadJzg4WP/617+0YsUKDRgwoFk/B4DmQ94A4AlyB4DjwVoHAE+QO9CWGY5DB2kCfsRut8tkMik/P18xMTG1Lvj++c9/6s0339T8+fPVtWtXORwOZWRkKCEhQZGRkUecZ/78+crLy9O1117b3B8DQDNZsWKFhgwZUusuJBeHwyHDMLR06VKdccYZ2rVrl5KTk30UKQB/Qd4A4AlyB4DjwVoHAE+QOwA6s+CHVqxYIenghoWxsbHuBO16bOjQodqwYYOCg4MlOe8q6N69+xEJWnK2z1544YUkaKCVmj9/vpKTkzV+/Hjt2LFDZrPZfae0iyuHJCUlKSUlRQsXLvRFqAD8BHkDgCfIHQCOB2sdADxB7gAOopgFv8HFIYDGevfdd/XII49oxIgR6tOnjx577DFJB2dAHy44OFgWi0VlZWXNGSYAP0LeAOAJcgcAT7HWAcAT5A7gSBSz4Be4OATQGDabTZLUrVs3nXXWWXr88cd13nnn6bvvvtN3331X6xgXh8Oh5ORkJSQk6KeffpKkI74IAmi9yBsAPEHuAHA8WOsA4AlyB1A3ilnwKS4OATTGli1b5HA43PtTDB06VA8++KBSU1M1YcIE9ezZU08++aQk56anh24LaRiGHA6HBg8erIyMDJWUlBz1iyCA1oO8AcAT5A4Ax4O1DgCeIHcA9eMbNXyCi0MAjfHhhx+qS5cumjhxooYNG6Y33njD/Zwrj5xwwgmaNGmSduzYoTlz5khSrdwhOfNHRUWFTjzxRAUGBjbfBwDQ7MgbADxB7gBwPFjrAOAJcgfQMPxlo1lxcQigsRYuXKg777xTf/vb3/Tcc8/ptNNO0/XXX6/XXntNZWVlMgxD1dXVkqQxY8Zo+PDhevnll1VcXCyTyaSqqipJB+9eev755/XSSy/JYrH47DMBaFrkDQCeIHcA8BRrHQA8Qe4AGifA1wGg7Tj04rBr165asGCBrr/+etlsNl1xxRUKCQlRdXW1AgICNGbMGC1btkwvv/yyJk+erPDwcFVVVSkwMFA2m01ms1nPP/88CRpoxRwOhwzD0PLly9WuXTtNmzZNgYGBGjt2rMrLyzV79mzFxcXpggsuUECA8z9nycnJuuCCC7RmzRo99dRTuvDCC3X33XfrpZdeUkpKiiSRN4BWjLwBwBPkDgDHg7UOAJ4gdwCNR2cWmpzrboFDLw7Hjh2rf/7zn5o2bZpmz56tr776SpKOuDh0OBx66qmntHbtWl144YXKzMx035lAggZaN8MwJEkbNmxQ165dFRgY6L7j+aGHHlJwcLA++eQTZWdnSzp4F/SZZ56pIUOG6IEHHtDgwYNVVVWl+Ph433wIAM2KvAHAE+QOAJ5grQOAJ8gdgOcoZqHJcXEIoCEWLlyoW265Rc8++6xWrFjhfvyss87Sl19+KZvN5s4fMTExuuqqq7R8+XKlp6dLcrbgl5SUaPbs2Xr11Vd1xhlnaNWqVfrqq68UFBTkq48FoAmRNwB4gtwBwBtY6wDgCXIH4DmKWfA6Lg4BNMbevXs1ceJEXXHFFcrPz9cbb7yhMWPGuPPHGWecocjISN1///2SDt7FNG3aNFmtVv3222/uc+3cuVMffPCB5syZo8WLF6tfv37N/4EANDnyBgBPkDsAHA/WOgB4gtwBeA/FLHgNF4cAGqu0tFQzZ85UWFiYfvrpJ73zzjtau3atevbsqZdfflmSlJSUpOnTp+upp55SZmamLBaLO3/07NlT69evd5+vT58++umnn3TllVf65PMAaHrkDQCeIHcA8BRrHQA8Qe4AvI9iFryCi0MAnggNDVVQUJCmTp2qLl26qLq6WpI0YcIEbdy4UQ6HQxEREbrssss0aNAgXXLJJdq5c6cMw9CuXbuUm5urSZMm+fZDAGhW5A0AniB3APAEax0APEHuAJoGxSx4BReHADz14osvaty4cZIkk8n5n6XNmzerf//+7lnSXbp00dy5c5WXl6eRI0dq8uTJGj58uJKSknTSSSf5LHYAvkHeAOAJcgeAxmKtA4AnyB1A0zAcrpIvcJyqqqoUGBgoSbLb7TKZTLr88ssVFham2bNnu4/LysrSyJEjVV1drZNOOkk//vijevXqpffee08JCQm+Ch+AHznttNM0bdo0TZkyRXa7XZJz0SkjI0MrV67Uzz//rBNPPFFTpkzxcaQA/AV5A4AnyB0AjoW1DgCeIHcA3kcxC02Ki0MAjbVt2zadcsop+uKLLzR48GBJUmVlpSwWi48jA+CvyBsAPEHuAOAp1joAeILcARyfAF8HgNZr27ZtysjIUN++fSU5k7Pr4rBbt27q1q2b/vCHP/g4SgD+wuFwyDAMLV26VOHh4e5Fpfvvv1/Z2dm6//77FR8f7+MoAfgT8gYAT5A7ABwP1joAeILcARw/9syC17ma/eq6OPzLX/6i3NxcX4YHwE+59qpYsWKFLrroIi1cuFBdunTRSy+9pAsuuIBFJQBHIG8A8AS5A4AnWOsA4AlyB+A9jBlEk7npppsUFham0aNH69prr1VpaanefvttjRkzxtehAfBT5eXl6tevn7Zu3SqLxaL7779fd955p6/DAuDHyBsAPEHuAOAp1joAeILcARw/illoElwcAvDU2Wefre7du+vpp59WcHCwr8MB0AKQNwB4gtwBoLFY6wDgCXIH4B0Us9BkuDgE4AmbzSaz2ezrMAC0IOQNAJ4gdwDwBGsdADxB7gCOH8UsNBkuDgEAAAAAQGvCWgcAT5A7gONHMQsAAAAAAAAAAAB+y+TrAAAAAAAAAAAAAICjoZgFAAAAAAAAAAAAv0UxCwAAAAAAAAAAAH6LYhYAAAAAAAAAAAD8FsUsAAAAAAAAAAAA+C2KWQAAAAAAAAAAAPBbFLMAAAAA+KWpU6dq0qRJzf6+b775pgzDkGEYuvXWW+s9tnPnznr22WcbdN6RI0e6z7t69erjjhMAAAAA2ooAXwcAAAAAoO0xDKPe5++9914999xzcjgczRRRbZGRkUpPT1dYWJjXzvnf//5XW7du1ZAhQ7x2TgAAAABoCyhmAQAAAGh2e/fudf977ty5mjVrltLT092PhYeHKzw83BehSXIW2xITE716ztjYWFmtVq+eEwAAAADaAsYMAgAAAGh2iYmJ7p+oqCh38cj1Ex4efsSYwZEjR+rmm2/WrbfeqpiYGCUkJOi1115TSUmJrr76akVERKhbt2768ssva73XunXrNH78eIWHhyshIUFXXnml8vLyGh1zbm6uJk6cqJCQEHXp0kXvvvturecdDofuu+8+paamKigoSB06dNAtt9zi0f/7AAAAAAAOopgFAAAAoMV46623FBcXpxUrVujmm2/W9OnTNXnyZJ1yyilatWqVxowZoyuvvFKlpaWSpIKCAo0aNUoDBw7Ur7/+qq+++ko5OTm65JJLGv3eU6dOVWZmphYvXqyPPvpIL730knJzc93Pz5s3T88884xeffVVbdmyRfPnz1e/fv289tkBAAAAoK1izCAAAACAFuPEE0/UPffcI0maOXOmHnvsMcXFxWnatGmSpFmzZunll1/W2rVrNWzYML344osaOHCgHnnkEfc53njjDaWkpGjz5s3q0aNHg9538+bN+vLLL7VixQqdfPLJkqTXX39dvXv3dh+za9cuJSYmavTo0QoMDFRqair7YwEAAACAF9CZBQAAAKDF6N+/v/vfZrNZ7dq1q9X9lJCQIEnujqk1a9Zo8eLF7j24wsPD1atXL0nS1q1bG/y+GzduVEBAgAYPHux+rFevXoqOjnb/PnnyZJWVlSktLU3Tpk3Txx9/rOrqao8+JwAAAADgIDqzAAAAALQYgYGBtX43DKPWY4ZhSJLsdrskqbi4WBMnTtTjjz9+xLmSkpK8GltKSorS09O1aNEiLVy4UDfccIOefPJJLVmy5Ii4AQAAAAANRzELAAAAQKs1aNAgzZs3T507d1ZAgOeXP7169VJ1dbVWrlzpHjOYnp6ugoKCWseFhIRo4sSJmjhxom688Ub16tVLv//+uwYNGnQ8HwMAAAAA2jTGDAIAAABotW688Ubl5+frj3/8o3755Rdt3bpVX3/9ta6++mrZbLYGn6dnz54aN26crrvuOv38889auXKl/vznPyskJMR9zJtvvqnXX39d69at07Zt2/TOO+8oJCREnTp1aoqPBgAAAABtBsUsAAAAAK1Whw4dtGzZMtlsNo0ZM0b9+vXTrbfequjoaJlMjbscmjNnjjp06KAzzjhDF154oa699lrFx8e7n4+OjtZrr72mU089Vf3799eiRYv02WefqV27dt7+WAAAAADQphgOh8Ph6yAAAAAAwF+8+eabuvXWW48YIegNO3bsUJcuXfTbb79pwIABXj8/AAAAALRGdGYBAAAAwGEKCwsVHh6uO++802vnHD9+vE444QSvnQ8AAAAA2go6swAAAADgEEVFRcrJyZHkHB0YFxfnlfNmZWWprKxMkpSamiqLxeKV8wIAAABAa0cxCwAAAAAAAAAAAH6LMYMAAAAAAAAAAADwWxSzAAAAAAAAAAAA4LcoZgEAAAAAAAAAAMBvUcwCAAAAAAAAAACA36KYBQAAAAAAAAAAAL9FMQsAAAAAAAAAAAB+i2IWAAAAAAAAAAAA/BbFLAAAAAAAAAAAAPit/wdyMA/DrNgNugAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 1600x350 with 1 Axes>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plot_series(df_train[['unique_id','ds','y']][-200:], forecasts_df= df_test[['unique_id','ds','y']].rename(columns={'y': 'test'}))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2. Temporal aggregation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We are interested in generating forecasts for the hourly and 2-hourly windows. We can generate these forecasts using TimeGPT. After generating these forecasts, we make use of hierarchical forecasting techniques to improve the accuracy of each forecast. \n",
    "\n",
    "We first define the temporal aggregation spec. The spec is a dictionary in which the keys are the name of the aggregation and the value is the amount of bottom-level timesteps that should be aggregated in that aggregation. \n",
    "\n",
    "In this example, we choose a temporal aggregation of a 2-hour period and a 1-hour period (the bottom level)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "spec_temporal = { \"2-hour-period\": 2, \"1-hour-period\": 1}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We next compute the temporally aggregated train- and test sets using the `aggregate_temporal` function from `hierarchicalforecast`. Note that we have different aggregation matrices `S` for the train- and test set, as the test set contains temporal hierarchies that are not included in the train set."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from hierarchicalforecast.utils import aggregate_temporal"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Y_train, S_train, tags_train = aggregate_temporal(df=df_train[['unique_id','ds','y']], spec=spec_temporal)\n",
    "Y_test, S_test, tags_test = aggregate_temporal(df=df_test[['unique_id','ds','y']],  spec=spec_temporal)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "`Y_train` contains our training data, for both 1-hour and 2-hour periods. For example, if we look at the first two timestamps of the training data, we have a 2-hour period ending at 2017-10-22 01:00, and two 1-hour periods, the first ending at 2017-10-22 00:00, and the second at 2017-10-22 01:00, the latter corresponding to when the first 2-hour period ends. \n",
    "\n",
    "Also, the ground truth value `y` of the first 2-hour period is 38.13, which is equal to the sum of the first two 1-hour periods (19.10 + 19.03). This showcases how the higher frequency `1-hour-period` has been aggregated into the `2-hour-period` frequency."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>temporal_id</th>\n",
       "      <th>unique_id</th>\n",
       "      <th>ds</th>\n",
       "      <th>y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2-hour-period-1</td>\n",
       "      <td>DE</td>\n",
       "      <td>2017-10-22 01:00:00</td>\n",
       "      <td>38.13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>816</th>\n",
       "      <td>1-hour-period-1</td>\n",
       "      <td>DE</td>\n",
       "      <td>2017-10-22 00:00:00</td>\n",
       "      <td>19.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>817</th>\n",
       "      <td>1-hour-period-2</td>\n",
       "      <td>DE</td>\n",
       "      <td>2017-10-22 01:00:00</td>\n",
       "      <td>19.03</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         temporal_id unique_id                  ds      y\n",
       "0    2-hour-period-1        DE 2017-10-22 01:00:00  38.13\n",
       "816  1-hour-period-1        DE 2017-10-22 00:00:00  19.10\n",
       "817  1-hour-period-2        DE 2017-10-22 01:00:00  19.03"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y_train.query(\"ds <= '2017-10-22 01:00:00'\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The aggregation matrices `S_train` and `S_test` detail how the lowest temporal granularity (hour) can be aggregated into the 2-hour periods. For example, the first 2-hour period, named `2-hour-period-1`, can be constructed by summing the first two hour-periods, `1-hour-period-1` and `1-hour-period-2` - which we also verified above in our inspection of `Y_train`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>temporal_id</th>\n",
       "      <th>1-hour-period-1</th>\n",
       "      <th>1-hour-period-2</th>\n",
       "      <th>1-hour-period-3</th>\n",
       "      <th>1-hour-period-4</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2-hour-period-1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2-hour-period-2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2-hour-period-3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2-hour-period-4</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2-hour-period-5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       temporal_id  1-hour-period-1  1-hour-period-2  1-hour-period-3  \\\n",
       "0  2-hour-period-1              1.0              1.0              0.0   \n",
       "1  2-hour-period-2              0.0              0.0              1.0   \n",
       "2  2-hour-period-3              0.0              0.0              0.0   \n",
       "3  2-hour-period-4              0.0              0.0              0.0   \n",
       "4  2-hour-period-5              0.0              0.0              0.0   \n",
       "\n",
       "   1-hour-period-4  \n",
       "0              0.0  \n",
       "1              1.0  \n",
       "2              0.0  \n",
       "3              0.0  \n",
       "4              0.0  "
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "S_train.iloc[:5, :5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3b. Computing base forecasts\n",
    "\n",
    "Now, we need to compute base forecasts for each temporal aggregation. The following cell computes the **base forecasts** for each temporal aggregation in `Y_train` using TimeGPT. \n",
    "\n",
    "Note that both frequency and horizon are different for each temporal aggregation. In this example, the lowest level has a hourly frequency, and a horizon of `48`. The `2-hourly-period` aggregation thus has a 2-hourly frequency with a horizon of `24`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Y_hats = []\n",
    "id_cols = [\"unique_id\", \"temporal_id\", \"ds\", \"y\"]\n",
    "# We will train a model for each temporal level\n",
    "for level, temporal_ids_train in tags_train.items():\n",
    "    # Filter the data for the level\n",
    "    Y_level_train = Y_train.query(\"temporal_id in @temporal_ids_train\")\n",
    "    temporal_ids_test = tags_test[level]\n",
    "    Y_level_test = Y_test.query(\"temporal_id in @temporal_ids_test\")\n",
    "    # For each temporal level we have a different frequency and forecast horizon\n",
    "    freq_level = pd.infer_freq(Y_level_train[\"ds\"].unique())\n",
    "    horizon_level = Y_level_test[\"ds\"].nunique()\n",
    "    # Train a model and create forecasts\n",
    "    Y_hat_level = nixtla_client.forecast(df=Y_level_train[[\"ds\", \"unique_id\", \"y\"]], h=horizon_level)\n",
    "    # Add the test set to the forecast\n",
    "    Y_hat_level = Y_hat_level.merge(Y_level_test, on=[\"ds\", \"unique_id\"], how=\"left\")\n",
    "    # Put cols in the right order (for readability)\n",
    "    Y_hat_cols = id_cols + [col for col in Y_hat_level.columns if col not in id_cols]\n",
    "    Y_hat_level = Y_hat_level[Y_hat_cols]\n",
    "    # Append the forecast to the list\n",
    "    Y_hats.append(Y_hat_level)\n",
    "\n",
    "Y_hat = pd.concat(Y_hats, ignore_index=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Observe that `Y_hat` contains all the forecasts but they are not coherent with each other. For example, consider the forecasts for the first time period of both frequencies."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>unique_id</th>\n",
       "      <th>temporal_id</th>\n",
       "      <th>ds</th>\n",
       "      <th>y</th>\n",
       "      <th>TimeGPT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DE</td>\n",
       "      <td>2-hour-period-1</td>\n",
       "      <td>2017-12-29 01:00:00</td>\n",
       "      <td>10.45</td>\n",
       "      <td>16.949448</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>DE</td>\n",
       "      <td>1-hour-period-1</td>\n",
       "      <td>2017-12-29 00:00:00</td>\n",
       "      <td>9.73</td>\n",
       "      <td>-0.241489</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>DE</td>\n",
       "      <td>1-hour-period-2</td>\n",
       "      <td>2017-12-29 01:00:00</td>\n",
       "      <td>0.72</td>\n",
       "      <td>-3.456482</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   unique_id      temporal_id                  ds      y    TimeGPT\n",
       "0         DE  2-hour-period-1 2017-12-29 01:00:00  10.45  16.949448\n",
       "24        DE  1-hour-period-1 2017-12-29 00:00:00   9.73  -0.241489\n",
       "25        DE  1-hour-period-2 2017-12-29 01:00:00   0.72  -3.456482"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y_hat.query(\"temporal_id in ['2-hour-period-1', '1-hour-period-1', '1-hour-period-2']\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The ground truth value `y` for the first 2-hour period is 10.45, and the sum of the ground truth values for the first two 1-hour periods is (9.73 + 0.72) = 10.45. Hence, these values are coherent with each other.\n",
    "\n",
    "However, the forecast for the first 2-hour period is 16.95, but the sum of the forecasts for the first two 1-hour periods is -3.69. Hence, these forecasts are clearly not coherent with each other. \n",
    "\n",
    "We will use reconciliation techniques to make these forecasts better coherent with each other and improve their accuracy."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3c. Reconcile forecasts\n",
    "\n",
    "We can use the `HierarchicalReconciliation` class to reconcile the forecasts. In this example we use `MinTrace`. Note that we have to set `temporal=True` in the `reconcile` function."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from hierarchicalforecast.methods import MinTrace\n",
    "from hierarchicalforecast.core import HierarchicalReconciliation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "reconcilers = [\n",
    "    MinTrace(method=\"wls_struct\"),\n",
    "]\n",
    "hrec = HierarchicalReconciliation(reconcilers=reconcilers)\n",
    "Y_rec = hrec.reconcile(Y_hat_df=Y_hat, S=S_test, tags=tags_test, temporal=True)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4. Evaluation "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The `HierarchicalForecast` package includes the `evaluate` function to evaluate the different hierarchies."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We evaluate the temporally aggregated forecasts _across all temporal aggregations_."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import hierarchicalforecast.evaluation as hfe\n",
    "from utilsforecast.losses import mae"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "evaluation = hfe.evaluate(df = Y_rec.drop(columns = 'unique_id'),\n",
    "                      tags = tags_test,\n",
    "                      metrics = [mae],\n",
    "                      id_col='temporal_id')\n",
    "\n",
    "numeric_cols = evaluation.select_dtypes(include=\"number\").columns\n",
    "evaluation[numeric_cols] = evaluation[numeric_cols].map('{:.3}'.format).astype(np.float64)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>level</th>\n",
       "      <th>metric</th>\n",
       "      <th>TimeGPT</th>\n",
       "      <th>TimeGPT/MinTrace_method-wls_struct</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2-hour-period</td>\n",
       "      <td>mae</td>\n",
       "      <td>25.2</td>\n",
       "      <td>12.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1-hour-period</td>\n",
       "      <td>mae</td>\n",
       "      <td>18.5</td>\n",
       "      <td>6.16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Overall</td>\n",
       "      <td>mae</td>\n",
       "      <td>20.8</td>\n",
       "      <td>8.12</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           level metric  TimeGPT  TimeGPT/MinTrace_method-wls_struct\n",
       "0  2-hour-period    mae     25.2                               12.00\n",
       "1  1-hour-period    mae     18.5                                6.16\n",
       "2        Overall    mae     20.8                                8.12"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "evaluation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As we can see, we improved performance of TimeGPT's predictions both for the 2-hour period and for the 1-hour period, as both levels see a significant reduction in MAE and RMSE."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Visually, we can also verify the forecast is better after using reconciliation techniques. For the 1-hour-period forecasts:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAB58AAAFpCAYAAACrnO/TAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAA8URJREFUeJzs3Xd8k+X6x/FPku69B3TRMsresqegCDgRVBTFgR73OCrqcf08KuLee+ARcYuoiArI3kM2lFHaUqB7r6RN8vujECmzQNtQ+L5fr5DkmdcT0iTPc933dRvsdrsdERERERERERERERERERGR02B0dgAiIiIiIiIiIiIiIiIiItL4KfksIiIiIiIiIiIiIiIiIiKnTclnERERERERERERERERERE5bUo+i4iIiIiIiIiIiIiIiIjIaVPyWURERERERERERERERERETpuSzyIiIiIiIiIiIiIiIiIictqUfBYRERERERERERERERERkdOm5LOIiIiIiIiIiIiIiIiIiJw2JZ9FREREREREREREREREROS0KfksIiIiIiL1bsqUKRgMBlJSUpwdSq2kpKRgMBiYMmXKCZcdP348cXFx9R6TiIiIiIiIiMiZTslnERERERGRM8DBhPfBm6urKyEhIfTu3ZvHHnuMtLS0I9aZP39+jXUOv3399ddOOBIREREREREROVe5ODsAERERERE5+40bN46rr74ad3d3Z4dSK7GxsZSXl+Pq6trg+77mmmsYPnw4NpuN/Px8Vq1axeuvv84bb7zBJ598wtVXX33EOvfccw/du3c/YnqvXr0aImQREREREREREUDJZxERERERaQAmkwmTyeTsMGrNYDDg4eHhlH136dKF6667rsa01NRULrjgAm644QZat25Nx44da8zv168fV155ZUOGKSIiIiIiIiJyBJXdFhERERGRIxxrHOOnn34ag8HgeG4wGLjrrrv46aefaNeuHe7u7rRt25bff/+9xnpHG/PZbrfz7LPPEhUVhZeXF4MGDWLz5s3ExcUxfvz4Y+7zeNsEmDVrFv369cPb2xtfX19GjBjB5s2bT+r4jzXm88Hj9PDwoF27dkyfPv2ktnuqYmNjmTJlChaLhRdffLFB9ikiIiIiIiIicrLU81lERERERE7L4sWL+fHHH7njjjvw9fXlzTffZNSoUaSlpREcHHzM9Z588kmeffZZhg8fzvDhw1m7di0XXHABFovllGP54osvuOGGG7jwwguZPHkyZWVlvPfee/Tt25e///77qAn12vrzzz8ZNWoUbdq0YdKkSeTm5nLjjTcSFRV1xLL5+flYrdYTbtPLywsvL69a7b9Xr14kJCQwe/bsI+YVFxeTk5NzxPTg4OCjJu5FREREREREROqDks8iIiIiInJatm7dypYtW0hISABg0KBBdOzYka+++oq77rrrqOtkZ2fz4osvMmLECH755RdHgvQ///kPzz///CnFUVJSwj333MMtt9zChx9+6Jh+ww030KpVK55//vka00/WxIkTCQ8PZ/Hixfj7+wMwYMAALrjgAmJjY2ss27lzZ1JTU0+4zaeeeoqnn3661jG0a9eOGTNmUFRUhJ+fn2P6TTfddNTl9+/fT0RERK23LyIiIiIiIiJyOpR8FhERERGR0zJkyBBH4hmgQ4cO+Pn5kZycfMx15syZg8Vi4e67767RM/e+++475eTz7NmzKSgo4JprrqnRC9hkMtGjRw/mzZt3StuF6iTuunXreOSRRxyJZ4ChQ4fSpk0bSktLayz/5ZdfUl5efsLtxsfHn1QcPj4+QHVP50OTz08++ST9+vU7YvmgoKCT2r6IiIiIiIiIyOlQ8llERERERE5LTEzMEdMCAwPJz88/5joHewW3aNGixvTQ0FACAwNPKY4dO3YAMHjw4KPOPzRZe7KOFS9Aq1atWLt2bY1pffr0OeV9HU9JSQkAvr6+Naa3b9+eIUOG1Ms+RURERERERERqS8lnERERERE5wrHGCT7aOMYmk+moy9rt9gaNxWazAdXjPh+t1LSLS8Od/mRnZ9dqzGcfHx9Hb+ba2LRpE2FhYaeVSBcRERERERERqS9KPouIiIiIyBECAwMpKCg4YnptxjGujYNjJO/YsaNG6ens7Owjekwf7AldUFBAQEDAMWM5WPo7LCysznsBHxrv4ZKSko6Y1r179zof83nZsmXs2rWL6667rlbLi4iIiIiIiIg0NCWfRURERETkCAkJCRQWFrJhwwY6dOgAVI97PH369DrZ/pAhQ3B1deWtt97iggsucPRufv31148aC8DChQu55JJLACgtLeXzzz+vsdyFF16In58fzz//PIMGDcLV1bXG/OzsbEJDQ08p3sjISDp16sTnn39eY9zn2bNns2XLFkdy+qC6HvM5NTWV8ePH4+bmxkMPPXTyByAiIiIiIiIi0gCUfBYRERERkSNcffXVTJw4kcsvv5x77rmHsrIy3nvvPVq2bHnE+ManIjQ0lAcffJBJkyYxcuRIhg8fzt9//82sWbMICQmpsewFF1xATEwMN998Mw899BAmk4lPP/2U0NBQ0tLSHMv5+fnx3nvvMW7cOLp06cLVV1/tWGbmzJn06dOHt99++5RjnjRpEiNGjKBv377cdNNN5OXl8dZbb9G2bVvHWMwHnc6Yz2vXrmXq1KnYbDYKCgpYtWoVP/zwAwaDgS+++MLRGOBQixYtoqKi4ojpHTp0OOryIiIiIiJSf+x2O1VVVbUaikdEpDEwmUy4uLgcc2i0Qyn5LCIiIiIiRwgODmb69Ok88MADPPzwwzRr1oxJkyaxY8eOOkk+Azz77LN4eHjw/vvvM2/ePHr06MGff/7JiBEjaizn6urK9OnTueOOO3jiiSeIiIjgvvvuIzAwkBtvvLHGsmPHjqVJkya88MILvPTSS5jNZpo2bUq/fv2OWPZkDRs2jO+++47HH3+cRx99lISEBD777DNmzJjB/PnzT2vbh/rqq6/46quvcHFxwc/PjxYtWnDffffxr3/9i5iYmKOu8+abbx51+lNPPaXks4iIiIhIA7JYLOzfv5+ysjJnhyIiUqe8vLyIjIzEzc3tuMsZ7Ha7vYFiEhEREREROaG4uDgGDhzIlClTnB2KiIiIiIhIrdlsNnbs2IHJZCI0NBQ3N7da9RIUETmT2e12LBYL2dnZWK1WWrRogdFoPOby6vksIiIiIiIiIiIiIiJymiwWCzabjejoaLy8vJwdjohInfH09MTV1ZXU1FQsFgseHh7HXFbJZxEREREROWdYLBby8vKOu4y/vz+enp4NFJGIiIiIiJxtjtcjUESksartZ5uSzyIiIiIics5YunQpgwYNOu4yn332GePHj2+YgEREREREREREziJKPouIiIiIyBklJSWl3rbdsWNHZs+efdxl2rZtW2/7FxERERERERE5myn5LCIiIiIi54zAwECGDBni7DBERERERERERM5KGnhAREREREREREREREREREROm3o+H8Zms7Fv3z58fX0xGAzODkdERERERERERERERE6R3W6nuLiYJk2aYDSqP56ISH1T8vkw+/btIzo62tlhiIiIiIiIiIiIiIhIHdmzZw9RUVENuk+73U55pbVB93mQp6up1h3s/ve//3H//fezb98+3N3dHdMvu+wyfH19+eKLL+orTBE5Cyn5fBhfX1+g+ovIz8/PydGIiIiIiIiIiIiIiMipKioqIjo62nHtvyGVV1pp8+QfDb5fgC3PXIiXW+1SQKNHj+aee+7h559/ZvTo0QBkZWUxc+ZM/vzzz/oMU0TOQo0q+bx3714mTpzIrFmzKCsro3nz5nz22Wd069YNqG5F9NRTT/HRRx9RUFBAnz59eO+992jRokWt93GwJZCfn5+SzyIiIiIiIiIiIiIiZwENs3lsnp6ejB07ls8++8yRfJ46dSoxMTEMHDjQucGJSKPTaJLP+fn59OnTh0GDBjFr1ixCQ0PZsWMHgYGBjmVefPFF3nzzTT7//HOaNWvGE088wYUXXsiWLVvw8PBwYvQiIiIiIiIiIiIiInIu8XQ1seWZC52275MxYcIEunfvzt69e2natClTpkxh/PjxStqLyElrNMnnyZMnEx0dzWeffeaY1qxZM8dju93O66+/zuOPP86ll14KVI9TEB4ezk8//cTVV1/d4DGLiIiIiIiIiIiIiMi5yWAw1Lr0tbN17tyZjh078r///Y8LLriAzZs3M3PmTGeHJSKNkNHZAdTWzz//TLdu3Rg9ejRhYWF07tyZjz76yDF/9+7dZGRkMGTIEMc0f39/evTowbJly465XbPZTFFRUY2biIiIiIiIiIiIiIjIueSWW25hypQpfPbZZwwZMoTo6GhnhyQijVCjST4nJyc7xm/+448/uP3227nnnnv4/PPPAcjIyAAgPDy8xnrh4eGOeUczadIk/P39HTd9mIqIiIiIiIiIiIiIyLlm7NixpKen89FHH3HTTTc5OxwRaaQaTfLZZrPRpUsXnn/+eTp37sytt97KhAkTeP/9909ru48++iiFhYWO2549e+ooYhERERERERERERERkcbB39+fUaNG4ePjw2WXXebscESkkWo0yefIyEjatGlTY1rr1q1JS0sDICIiAoDMzMway2RmZjrmHY27uzt+fn41biIiIiIiIiIiIiIiIueavXv3cu211+Lu7u7sUESkkWo0yec+ffqQlJRUY9r27duJjY0FoFmzZkRERDB37lzH/KKiIlasWEGvXr0aNFYRERERETmSzWZn/Z4C3p2/k9lbMk+8goiIiIiIiDSI/Px8pk+fzvz587nzzjudHY6INGIuzg6gtu6//3569+7N888/z5gxY1i5ciUffvghH374IQAGg4H77ruPZ599lhYtWtCsWTOeeOIJmjRpovIQIiIiIiJOkltiZtGOHOYnZbFwRw55pRYADAb4+PpunN863MkRioiIiIiISOfOncnPz2fy5Mm0atXK2eGISCPWaJLP3bt3Z/r06Tz66KM888wzNGvWjNdff51rr73WsczDDz9MaWkpt956KwUFBfTt25fff/8dDw8PJ0YuIiIiInLusNrsrE8vYH5SNguSstiwtxC7/Z/5Pu4uRAV6si2jmHu++psf7uhNYoSGvhEREREREXGmlJQUZ4cgImcJg91+6KUgKSoqwt/fn8LCQo3/LCIiIiJyEn5Yk86zM7eQX1ZZY3rrSD8GtAxlYKtQusQEYjDADZ+uZOmuXJoGeDLjrj6E+Gg8MRERERERqXsNec2/oqKC3bt306xZM3WKE5GzTm0/4xpNz2cRERERETlzfb0yjUd+3AiAn4cL/VqEMqBVKANahhLud+QJybvXduGyd5aQklvGbV+sYdqEHri7mBo6bBERERERERERqUNGZwcgIiIiIiKN27QV/ySex/eOY+0TQ3nn2i6M6RZ91MQzQICXG5+M746vhwtrUvN59MeNqCiTiIiIiIiIiEjjpuSziIiIiIicsi9XpPLY9OrE8019mvHUxW1wMdXuNCMh1Id3r+2CyWjgx7V7eX9Bcn2GKiIiIiIiIiIi9UzJZxEREREROSVTl6fyn+mbALi5bzOeGNkag8FwUtvo1yKUpy9uA8CLf2zjj80ZdR6niIiIiIiIiIg0DCWfRURERETkpH2xPJXHf6pOPN/StxmPjzj5xPNB43rFcX2vWOx2uP+bdWzeV1iXoYqIiIiIiIiISANR8llERERERE7KF8tSeOJA4nlCv2b85zQSzwc9ObINfZuHUGaxMuHz1WQVV9RFqCIiIiIiInKaxo8fz2WXXebsMESkkVDyWUREREREau1/y1J4YsZmAG7tH89jw08/8QzgYjLyztguxId6s6+wglv/t4aKSutpb1dERERERESOzWAwHPf29NNP88YbbzBlypQGiScjI4N7772X5s2b4+HhQXh4OH369OG9996jrKzMsVxcXJwjRm9vb7p06cJ33313xLyj3caPH98gxyJyrnJxdgAiIiIiItI4fL40had+rk483zYgnkeGJdZJ4vkgfy9XPrmhO5e9s4R1ewqY+MMGXr+qU53uQ0RERERERP6xf/9+x+NvvvmGJ598kqSkJMc0Hx8ffHx8GiSW5ORk+vTpQ0BAAM8//zzt27fH3d2djRs38uGHH9K0aVMuueQSx/LPPPMMEyZMoKioiFdeeYWrrrqKpk2bsmrVKqzW6sbMS5cuZdSoUSQlJeHn5weAp6dngxyPyLlKyWcRERERETmhKUt28/QvWwD414AEJg5rVS9J4WYh3rx3XReu/2QlM9bto3tcENf1jK3z/YiIiIiIiNQ3u91OlaXSKft2cXOt1TlbRESE47G/vz8Gg6HGNKguu11QUMBPP/0EwMCBA2nfvj0mk4nPP/8cNzc3nn32WcaOHctdd93F999/T3h4OG+99RYXXXSRYzubNm3ioYceYtGiRXh7e3PBBRfw2muvERISAsAdd9yBi4sLq1evxtvb27FefHw8l156KXa7vUZcvr6+REREEBERwTvvvMPUqVP55ZdfmDRpkmOZoKAgAMLCwggICKjdiycip0XJZxEREREROSabzc7kP7bxwYJkAG4fmMDDF9ZP4vmg3gkhPHJRIs/O3MrLfyYxskMkAV5u9bY/ERERERGR+lBlqeTdW19yyr7v+PAhXN3r7zzq888/5+GHH2blypV888033H777UyfPp3LL7+cxx57jNdee41x48aRlpaGl5cXBQUFDB48mFtuuYXXXnuN8vJyJk6cyJgxY/jrr7/Izc3lzz//5Pnnn6+ReD7U8c5DXVxccHV1xWKx1Nchi0gtacxnERERERE5qjJLFf+ausaReL5vSIt6TzwfNL53HIkRvhSUVfLq7O31vj8RERERERGpvY4dO/L444/TokULHn30UTw8PAgJCWHChAm0aNGCJ598ktzcXDZs2ADA22+/TefOnXn++edJTEykc+fOfPrpp8ybN4/t27ezc+dO7HY7rVq1qrGfkJAQR+nviRMnHjUWi8XCpEmTKCwsZPDgwfV+7CJyfOr5LCIiIiIiR8gorOCW/61i094i3ExGXhrdgUs7NW2w/buYjDx1cVuu+Wg5U5encs15MbSO9Guw/YuIiIiIiJwuFzdX7vjwIaftuz516NDB8dhkMhEcHEz79u0d08LDwwHIysoCYP369cybN++o40fv2rXLUR77cCtXrsRms3HttddiNptrzJs4cSKPP/44FRUV+Pj48MILLzBixIjTPjYROT1KPouIiIiISA2b9hZy8+eryCwyE+ztxofXd6Vr7NEvBNSnXgnBjGgfycyN+/m/Xzbz1YSeDdLrWkREREREpC4YDIZ6LX3tTK6uNZPbBoOhxrSD5242mw2AkpISLr74YiZPnnzEtiIjI6moqMBgMJCUlFRjXnx8PACenp5HrPfQQw8xfvx4fHx8CA8P1/miyBlCZbdFRERERMThj80ZjH5/GZlFZlqE+fDTnX2ckng+6NHhibi7GFmenMdvGzOcFoeIiIiIiIicui5durB582bi4uJo3rx5jZu3tzfBwcEMHTqUt99+m9LS0lptMyQkhObNmxMREaHEs8gZRMlnERERERHBbrfzwYJd/GvqGsorrfRrEcIPd/QmOsjLqXFFBXpx+8AEAJ6buYVyi9Wp8YiIiIiIiMjJu/POO8nLy+Oaa65h1apV7Nq1iz/++IMbb7wRq7X6PO/dd9+lqqqKbt268c0337B161aSkpKYOnUq27Ztw2QyOfkoRKQ2lHwWERERETnHWapsPPLDRibN2obdDuN6xvLZ+O74edTvGGG1dVv/BJoGeLKvsIL3F+xydjgiIiIiIiJykpo0acKSJUuwWq1ccMEFtG/fnvvuu4+AgACMxupUVUJCAn///TdDhgzh0UcfpWPHjnTr1o233nqLBx98kP/+979OPgoRqQ2D3W63OzuIM0lRURH+/v4UFhbi5+fn7HBERERERE5KldVGYXkl+WWVFJRZKLNYsdrsVNnsWG02rDaostkOmWZnxrq9LE/Ow2iAJ0a2YXzvuDOuZNlvG/dzx5drcXcxMvffA4gKdG6PbBERERERaRwa8pp/RUUFu3fvplmzZnh4eNTrvkREGlptP+NcGjAmERERERE5jlJzFW/+tYPNe4twMRlwMRpxNRlwMRlxNRpwMRkwHZhmNBgOJJktjkRzfqmFooqqU9q3t5uJt8Z2ZnBieB0fVd24qF0EveKDWZacy/O/beXda7s6OyQRERERERERETmMks8iIiIiImeAtWn5PPDNOlJyy+pke34eLgR6u+HpasLVZMRkNOBiNFTfH0hiH3zu6+HCrf3jSYw4cyv/GAwGnrqkDcPfWMRvGzNYuiuH3gkhzg5LREREREREREQOoeSziIiIiIgTVVptvPXXTt6ZtxOrzU4Tfw/uHNwcV5ORKqudKpvNcV9ptTse2+x2/DxcCfRyI8DLlUBvNwK9XAnwciPA0xUXk9HZh1bnEiP8GNczls+XpfJ/P29h5j19z8rjFBERERERERFprJR8FhERERFxkuTsEu7/Zh3r0wsBuLRTE565tB3+nq5OjuzMdf/Qlvy8fh9JmcV8uSKNG3rHOTskERERERERERE5QN0EREREREQamN1u58sVqYx4czHr0wvx83DhzWs688bVnZV4PoEALzf+fUErAF75M4m8UouTIxIRERERERERkYPU81lEREREpAFlF5t55IcNzN2WBUDvhGBeHt2RJgGeTo6s8bjmvBi+XJHG1v1FvPJnEs9d3t7ZIYk0qIpKK5VWGzY7YAeb3Y6dA/f26gYudsDPwxVPN5OToxUREREREZFziZLPIiIiIiINZPaWTB75YQO5pRbcXIw8fGErburTDKPR4OzQGhWT0cDTF7fhqg+XM21lGmN7xNC2ib+zwxKpd/sLy3nx9yRmrNtbnXg+AYMBogI9aR7qQ4twX5qH+tA83IfmYT74eajKgoiIiIiIiNQ9JZ9FRERERBrAF8tSeGLGZgASI3x54+rOtIrwdXJUjVeP+GAu7tiEX9bv484v13L/0JaMaB+Ji+nkRxay2+2sTStg+t/pnNcsmEs6NqmHiEVOXam5ig8W7OLDRclUVNpOuLzBAAbAZoc9eeXsyStnXlJ2jWXC/dxpEeZL26Z+/Kt/AoHebvUUvYiIiIiIiJxLlHwWEREREalnm/cV8t9ftwIwvnccjw5PxN1FpXBP16MXJbJsVw4puWXc+/U6Xvw9iVv6NeOq7tF4uZ34VMdcZWXmhv1MWZrChvRCAL5dnU7PZkGE+XnUd/giJ2Sz2flhbTov/ZFEVrEZgPPigvjPiNa0ivDFaDBgMFB9z4Gks+GfSgq5JWZ2ZpWwI6uEnQduO7KKySwyO26Ld+awLq2AaRN6YlIVBhERERERETlNJ98t4AzxwgsvYDAYuO+++xzTKioquPPOOwkODsbHx4dRo0aRmZnpvCBFRERE5JxXZqni7q/+xmK1MaR1OE9d3EaJ5zrSJMCTOQ8M4MELWhLs7cbegnL+75ct9H7hL179M4mcEvNR18sqquDV2dvp88JfPPDtejakF+LmYiTU1x1LlY1PFu9u4CMROdLy5FwueWcxD32/gaxiMzFBXrx/XRe+ua0nHaMD8HA14eZixNVkxGQ0YDQaaiSeAYJ93OkRH8x1PWN5+pK2TL2lByseG8L6py7gxzt6M+mK9ni7mVixO4/3F+xy0pGKiIiIyJlu/PjxXHbZZc4O44zz9NNP06lTJ2eHcdaYMmUKAQEBdb7dlJQUDAYD69atq7NtGgwGfvrppzrb3tmmUSafV61axQcffECHDh1qTL///vv55Zdf+O6771iwYAH79u3jiiuucFKUIiIiIiLw9M+bSc4uJcLPg5eu7HBEckhOT4CXG3cNbsGSRwbz3OXtiAv2oqCskjf/2kmfF/7iP9M3kpJTCsDfafnc+/Xf9H7hL96cu4OcEgsRfh48dGErlj0ymMmj2gMwdXkqBWUWZx6WnMNSc0u57YvVXP3hcjbtLcLX3YXHhicy+4H+DGsXWSefIf6ernSJCeSa82L4v0vbAfDq7O2sTcs/7W2LiIiISONiMBiOe3v66ad54403mDJlSoPEk5GRwb333kvz5s3x8PAgPDycPn368N5771FWVuZYLi4uzhGjt7c3Xbp04bvvvjti3tFu48ePd2ynvLwcb29vdu7cyZQpUzAYDLRu3fqIuL777jsMBgNxcXGOaQ8++CBz586t1XEdTIAe79ZQr/GZIC4ujtdff93ZYZzRGvI1mj9/PgaDgYKCgjrZXqMru11SUsK1117LRx99xLPPPuuYXlhYyCeffMK0adMYPHgwAJ999hmtW7dm+fLl9OzZ86jbM5vNmM3/9IgoKiqq3wMQERERkXPGz+v38e3qdAwGeO2qThpTtR55uJq4tkcsV3eP4c/NGby/YBfr0wv5ckUa01am0SzYm+QDSWiAbrGBjO8Tx4VtI3A9ME70oFZhJEb4si2jmM+XpnLvkBbOOhw5TE6JmYXbs0nOLqW80kpFpZXySivmSpvjcUWllYpKGxVVVlyNRtxcjLi7VN//89iEm8mIu2v1/3nFgW38s76V8kob5gOPLVY7MUGetIrwIzHCl1YRviRG+BLgVfd/yxWVVl6fs4NPFidTabVjNMDYHjHcP6QlwT7udb6/g0Z1acrC7dn8vH4f9379NzPv6Yefh2u97U9EREREziz79+93PP7mm2948sknSUpKckzz8fHBx8enQWJJTk6mT58+BAQE8Pzzz9O+fXvc3d3ZuHEjH374IU2bNuWSSy5xLP/MM88wYcIEioqKeOWVV7jqqqto2rQpq1atwmq1ArB06VJGjRpFUlISfn5+AHh6ejq2MXv2bGJjY2nevDmLFy/G29ubrKwsli1bRq9evRzLffLJJ8TExNSI92Rem+jo6Bqv9csvv8zvv//OnDlzHNP8/f0dj61WKwaDAaOxUfYhlQZypr5PzqxoauHOO+9kxIgRDBkypMb0NWvWUFlZWWN6YmIiMTExLFu27JjbmzRpEv7+/o5bdHR0vcUuIiIiIueOtNwy/vPjRgDuHtScXgnBTo7o3GAyGriofSQ/3dmHr2/tyeDEMOx2SM4pxc1kZFSXKH65qy/f396bkR2aOBLPUN3i/85BzQH4bOluSs1VzjqMc57VZufvtHxenb2dS99eTPfn5vDAt+t5e95OPlm8my9XpPHj2r3M3LifuduyWLorl7VpBWzZX0RydilJmcVs3FvI6tR8lu7KZX5SNn9szuSX9fv4YW0601akMe2Qbfx1yDa27i8iOaeUfYUV5JSYWZtWwFcr03jq581c/eFyOj0zmx7Pz+GGT1cy6bet/Lg2nbTcshMf1HFs2lvIJW8v5v0Fu6i02unfMpTf7+vPs5e1r9fEM1S/75+9vB1RgZ7sySvniZ82Ybfb63WfIiIiIucKu91OqdXqlFttf9NFREQ4bv7+/hgMhhrTfHx8jii7PXDgQO6++27uu+8+AgMDCQ8P56OPPqK0tJQbb7wRX19fmjdvzqxZs2rsa9OmTVx00UX4+PgQHh7OuHHjyMnJccy/4447cHFxYfXq1YwZM4bWrVsTHx/PpZdeysyZM7n44otrbM/X15eIiAhatmzJO++8g6enJ7/88guhoaGO+IOCggAICwurcZwHzZgxo0ZC28XFhbFjx/Lpp586pqWnpzN//nzGjh1bY/+Hl90++Dq9/PLLREZGEhwczJ133kllZSUmk+mI19XFxcXx/PfffycyMpKff/6ZNm3a4O7uTlpaGqtWrWLo0KGEhITg7+/PgAEDWLt2bY04CgoKuO222wgPD8fDw4N27drx66+/OuYvXryYfv364enpSXR0NPfccw+lpaXURlxcHM8++yzXX389Pj4+xMbG8vPPP5Odnc2ll16Kj48PHTp0YPXq1TXWO94+Bw4cSGpqKvfff7+j1/eh/vjjD1q3bo2Pjw/Dhg2rkbS32Ww888wzREVF4e7uTqdOnfj9999rrL9y5Uo6d+6Mh4cH3bp14++//z7uMdrtdkJDQ/n+++8d0zp16kRkZGSN43F3d6/R+/4gi8XCXXfdRWRkJB4eHsTGxjJp0qQTvLLV+3366aeJiYnB3d2dJk2acM899xz3NTpYmvzw98nAgQNrDFMMcNlll9Xo5W82m5k4cSLR0dG4u7vTvHlzPvnkE1JSUhg0aBAAgYGBR1QHOBWNqufz119/zdq1a1m1atUR8zIyMnBzczuiHnx4eDgZGRnH3Oajjz7KAw884HheVFSkBLSIiIiInJZKq417vv6bYnMV3WIDued89aBtaAaDgZ7xwfSMDyYpo5it+4vo2yKEkBMk8oa3j+SVP5NIyS3jq5Vp3NIvvoEilvxSCwt3ZDNvWxYLd+SQV1qz9HnbJn50iQnEy92Ep6sJD1cTHi5GPN2qH7u7mPB0M+HuYsRqs2OusmKpsmGustW4t1htmCttAHi4GvFwrd6e+4HHB597uBoxGgwk55SSlFFEUkYx2zKKSc8vJ7PITGZRNgu2ZwNgNMCVXaO4f2hLIv09jzi2Y6my2vhgYTKvz9lOpdVOiI87k65oz9A24XX3wtaCn4crb1zdmTEfLGPGun0MaBnKFV2iGjQGERERkbNRmc1GwsKNTtn3rv7t8TaZ6m37n3/+OQ8//DArV67km2++4fbbb2f69OlcfvnlPPbYY7z22muMGzeOtLQ0vLy8KCgoYPDgwdxyyy289tprlJeXM3HiRMaMGcNff/1Fbm4uf/75J88//zze3t5H3efxhqBxcXHB1dUVi6X2QyjZbDZ+/fXXI8buvemmmxg4cCBvvPEGXl5eTJkyhWHDhhEefuLf6fPmzSMyMpJ58+axc+dOrrrqKjp16sSECRNOuG5ZWRmTJ0/m448/Jjg4mLCwMJKTk7nhhht46623sNvtvPLKKwwfPpwdO3bg6+uLzWbjoosuori4mKlTp5KQkMCWLVswHfi/37VrF8OGDePZZ5/l008/JTs7m7vuuou77rqLzz77rFav02uvvcbzzz/PE0884fh/7d27NzfddBMvvfQSEydO5Prrr2fz5s0YDIYT7vPHH3+kY8eO3HrrrUe8LmVlZbz88st88cUXGI1GrrvuOh588EG+/PJLAN544w1eeeUVPvjgAzp37synn37KJZdcwubNm2nRogUlJSWMHDmSoUOHMnXqVHbv3s2999573OMzGAz079+f+fPnc+WVV5Kfn8/WrVvx9PRk27ZtJCYmsmDBArp3746Xl9cR67/55pv8/PPPfPvtt8TExLBnzx727Nlzwtf1hx9+4LXXXuPrr7+mbdu2ZGRksH79eoATvkaHv09q4/rrr2fZsmW8+eabdOzYkd27d5OTk0N0dDQ//PBDjQoBh1YHOBWNJvm8Z88e7r33XmbPno2Hh0edbdfd3R139/ptSS4iIiIi55ZXZ29n3Z4C/DxceP3qTriYGl3BobNKqwPlkmvDZDTwrwEJPPLjRj5alMy4XrG4u9TfBZtzXZXVxsyN+/nfslTWpuVzaOcMX3cX+rUMYWCrMAa2DCXMr+7OA09Gu6b+0LGJ43lxRSXbM0tIyigmKaOITfuKWJOaz7er05mxbh839mnG7QMT8Pc8funqlJxSHvh2HWvTCgAY1jaC5y5vV+89nY+la2wg953fgldmb+eJnzbRJSaQuJCjX/QTEREREenYsSOPP/44UN3J74UXXiAkJMSRKHvyySd577332LBhAz179uTtt9+mc+fOPP/8845tfPrpp0RHR7N9+3by8/Ox2+20atWqxn5CQkKoqKgAqivjTp48+YhYLBYLr7zyCoWFhY5hWWtj+fLlAPTo0aPG9M6dOxMfH8/333/PuHHjmDJlCq+++irJyckn3GZgYCBvv/02JpOJxMRERowYwdy5c2uVfK6srOTdd9+lY8eOjmmHH8+HH35IQEAACxYsYOTIkcyZM4eVK1eydetWWrZsCUB8/D+NqCdNmsS1117r6BXbokUL3nzzTQYMGMB7771Xq3zb8OHDue2224B//l+7d+/O6NGjAZg4cSK9evUiMzOTiIiIE+4zKCgIk8nk6Ll++Gvw/vvvk5CQAMBdd93FM88845j/8ssvM3HiRK6++moAJk+ezLx583j99dd55513mDZtGjabjU8++QQPDw/atm1Leno6t99++3GPceDAgXzwwQcALFy4kM6dOxMREcH8+fNJTExk/vz5DBgw4KjrpqWl0aJFC/r27YvBYCA2NvaEr+nB9SIiIhgyZAiurq7ExMRw3nnnAZzwNTr8fXIi27dv59tvv2X27NmOCtKHvk8OrRBweCffU9Foks9r1qwhKyuLLl26OKZZrVYWLlzI22+/zR9//IHFYqGgoKDGC3PwzS4iIiIi0hAW78jh/QW7AJg8qgNRgUe2ipUz2+VdmvL6nB1kFFXw49q9XHNezIlXkpNSUWnl+zXpfLgwmbS8f8qWJUb4MrBVGINahdIlNrBGWfQzha+HK11jA+kaG+iYtjYtnxd+28bKlDzeX7CLr1amcdeg5ozrFYuHa83GC3a7nWkr03hu5lbKLFZ83F34v0vackWXpsftydEQ7hjUnEU7c1i5O497v/6b7/7VGzeXM+//QERERKSx8DIa2dW/vdP2XZ86dOjgeGwymQgODqZ9+3+O9WAv4aysLADWr1/PvHnzjjpG8q5duxzJr8OtXLkSm83Gtddei9lsrjFv4sSJPP7441RUVODj48MLL7zAiBEjan0MM2bMYOTIkUcdL/emm27is88+IyYmhtLSUoYPH87bb799wm22bdvW0esYIDIyko0ba9f73c3NrcbrCtU5rscff5z58+eTlZWF1WqlrKyMtLQ0ANatW0dUVJQj8Xy49evXs2HDBkfPYag+J7HZbOzevZvWrVufMK5DYzr4/3qs/+uIiIjT2qeXl5cj8QzVr9/B91BRURH79u2jT58+Ndbp06ePo8fw1q1b6dChQ42k+qFjd0P1/1FqaioA/fr1Y9asWQwYMIB7772X7OxsFixYwMCBAx3J55tvvpmlS5fy8MMPHzXm8ePHM3ToUFq1asWwYcMYOXIkF1xwwTGP8aDRo0fz+uuvEx8fz7Bhwxg+fDgXX3wxLi7HT90e7X1yIuvWrcNkMh0zgV7XGk3y+fzzzz/iD/TGG28kMTHRUaPc1dWVuXPnMmrUKACSkpJIS0s74o0lIiIiIlIfckrM3P/tOux2GNsjhovaR554JTnjuLuYmNA/nv/+uoX3F+xidNco9V6vI0UVlUxdnsqni1PIKam+cBTo5cqNfZpxZdcomgScXmkvZ+kSE8g3t/Xkr21ZTP59G9szS3jut61MWZrCA0NbclnnppiMBrKKKpj4wwbmJVWX6+4ZH8TLozueMY1UTEYDr1/ViYveWMT69EJenb2dRy5KdHZYIiIiIo2WwWCo19LXzuTqWrPSj8FgqDHtYMNKm616yJuSkhIuvvjio/ZcjoyMpKKiAoPBQFJSUo15B3tnHq0M8EMPPcT48eMdY0ifbGPOn3/+mRdeeOGo86699loefvhhnn76acaNG3fChOBBR3tdDr4GJ+Lp6XnEMdxwww3k5ubyxhtvEBsbi7u7O7169XKUFz9ReeSSkhJuu+02x1jCh4qJqV1D66P9v57o//pU93m016+245fX1m+//UZlZSXwz+vXvn17goKCWLBgAQsWLOC5554jIiKCyZMns2rVKiorK+ndu/dRt9elSxd2797NrFmzmDNnDmPGjGHIkCE1xpA+mujoaJKSkpgzZw6zZ8/mjjvu4KWXXmLBggVHvA6HOtr7xGg0HvE6HTzGQ4+zoTSa5LOvry/t2rWrMc3b25vg4GDH9JtvvpkHHniAoKAg/Pz8uPvuu+nVqxc9e/Z0RsgiIiIicg6x2ew8+N16sovNtAz34cmRbZwdkpyGa86L5u2/dpCaW8ZvmzK45JCyy3Lysoor+GxJClOXpVJsrgKgaYAnE/o1Y0z3aLzcGs2p6TEZDAbObx3OwFZh/LA2nddmb2dvQTn//m49Hy1K5rLOTflgwS7yyypxczHy8IWtuKlPM4xG5/Z2PlyTAE8mj2rPv6au5YOFu+jXIoQ+zUOcHZaIiIiINHJdunThhx9+IC4u7qiJXG9vb4YOHcrbb7/N3Xfffcxxnw8VEhJC8+bNTymeHTt2kJqaytChQ486PygoiEsuuYRvv/2W999//5T2UReWLFnCu+++y/Dhw4HqIWpzcnIc8zt06EB6ejrbt28/au/nLl26sGXLllN+nU5Fbfbp5uaG1Wo9qe36+fnRpEkTlixZUqMH75IlSxzlqlu3bs0XX3xBRUWFo/fzwfLqBx2tLLbBYKBfv37MmDGDzZs307dvX7y8vDCbzXzwwQd069btuO9JPz8/rrrqKq666iquvPJKhg0bRl5e3jF79B/k6enJxRdfzMUXX8ydd95JYmIiGzdupEuXLif1GoWGhrJ//37Hc6vVyqZNmxg0aBBQnVy32WwsWLDAUXb7UG5ubo716sJZ1Xz/tddeY+TIkYwaNYr+/fsTERHBjz/+6OywREREROQc8OmS3cxPysbdxchb13Q5otSuNC5ebi7c2KcZAO/O21nnLa3PFXsLyvnP9I30nTyP9+bvothcRYswH14d05H5Dw1kfJ9mZ0Xi+VAmo4Ex3aKZ9+BAHrkoET8PF7ZlFPPCrG3kl1XSJtKPX+7qyy394s+4xPNBw9pFcs15MdjtcP8368grtTg7JBERERFp5O68807y8vK45pprWLVqFbt27eKPP/7gxhtvdCS83n33XaqqqujWrRvffPMNW7duJSkpialTp7Jt27Ya5axP14wZMxgyZAheXseuQjRlyhRycnJITHReNaAWLVrwxRdfsHXrVlasWMG1115boxfrgAED6N+/P6NGjWL27NmOHri///47UF2afOnSpdx1112sW7eOHTt2MGPGDO666656i7k2+4yLi2PhwoXs3bu3RjL9RB566CEmT57MN998Q1JSEo888gjr1q3j3nvvBWDs2LEYDAYmTJjAli1b+O2333j55Zdrte2BAwfy1Vdf0alTJ3x8fDAajfTv358vv/zyuOWqX331Vb766iu2bdvG9u3b+e6774iIiDjh2MlTpkzhk08+YdOmTSQnJzN16lQ8PT0dyfGTeY0GDx7MzJkzmTlzJtu2beP222+noKDAMT8uLo4bbriBm266iZ9++ondu3czf/58vv32W6A6IW8wGPj111/Jzs6mpKSkVq/ZsTTq5PP8+fN5/fXXHc89PDx45513yMvLo7S0lB9//FHjPYuIiIhIvbLb7azbU8Dk37cB8MTINrSK8HVyVFIXbugVh7ebiW0Zxfy1LcvZ4TQ6SRnFXPLWYr5ckYalykaXmAA+vr4bf9zXnyu6RJ2R4znXJQ9XE/8akMDChwdxa/94wv3cuXNQAj/d2adRfEY8MbI1CaHeZBWbefj79WqAISIiIiKn5WCPVavVygUXXED79u257777CAgIcIy5nJCQwN9//82QIUN49NFH6dixI926deOtt97iwQcf5L///W+dxTNjxgwuueSS4y7j6elJcHBwne3zVHzyySfk5+fTpUsXxo0bxz333ENYWFiNZX744Qe6d+/ONddcQ5s2bXj44YcdCf0OHTqwYMECtm/fTr9+/ejcuTNPPvkkTZrUX3Wv2uzzmWeeISUlhYSEBEJDQ2u97XvuuYcHHniAf//737Rv357ff/+dn3/+mRYtWgDg4+PDL7/8wsaNG+ncuTP/+c9/jlrq/WgGDBiA1Wpl4MCBjmkDBw48YtrhfH19efHFF+nWrRvdu3cnJSWF33777ahjiR8qICCAjz76iD59+tChQwfmzJnDL7/84njPncxrdNNNN3HDDTdw/fXXM2DAAOLj4x29ng967733uPLKK7njjjtITExkwoQJlJaWAtC0aVP+7//+j0ceeYTw8PDTbpxgsOsMsoaioiL8/f0pLCzEz8/P2eGIiIiIiBOVW6z8uSWDzKIK8ssqKSizkF9aSX6Z5cCtksKySizW6nGNLmwbzvvXdT3pcabkzDVp1lY+WJBMl5gAfri9t/5va2l7ZjHXfLic3FILbSL9eOriNpzXLEivXyOzZV8Rl72zBIvVxjOXtuX6XnHODkmk0UnNLWXl7jy6xQXRLOTE5UNFRKTuNeQ1/4qKCnbv3k2zZs0cJX/lzJOTk0NkZCTp6emEh4c7OxyRRqO2n3FnV30zEREREZE6YLPZ+WFtOi//mURmkblW63SMDmDyqA5Krp1lbu7bjM+WpLA2rYAVu/PoGe/cVu+NwY7MYsZ+VJ14bt/Un6k398Dfy9XZYckpaNPEj0cuSuSZX7fw/G9bGdY2gjA/XUQVOZFScxUzN+7n+zXprNyd55jer0UI43rGMjgxDJezvPqDiIjImSwvL49XX31ViWeReqLks4iIiIjIIZbuzOHZmVvZsr8IgKYBnpzXLIgAL1cCvdwI9HIlwMut+rH3wWlueLppjOezUZivB2O6RTF1eRrvzNup5PMJ7Mgs5pqPlpNTYqFdUz8lns8CN/aJ49cN+1ibVsCbf+3g2cvaOzskkTOS3W5n5e48vluTzm8b91NmqS51aTBAYoQf2zKKWLQjh0U7cmji78HYHjGM6R5NmK8adIiIiDS0li1b0rJlS2eH4XSLFi3ioosuOub80x3391z35Zdfcttttx11XmxsLJs3b27giBqOym4fRmW3RURERM5NO7OKmfTbNuYeGNvX18OFuwc35/pecXi4KrF8LtuTV8bAl+djtdn55a6+tI/yd3ZIZ6SdWcVc/eEKckrMtG3ix5e39CDAy83ZYUkdWJ6cy9UfLsfFaGDuvwcQG6zSwSIH7Sso54c16Xy/Np3U3DLH9GYh3lzZNYorujQl0t+TPXllfLkijW9X7yGv1AKAq8nAsHaRjOsZS/e4QFVPERGpJyq7LXJ05eXl7N2795jzmzdv3oDRnH2Ki4vJzMw86jxXV1diY2MbOKLTV9vPOCWfD6Pks4iIiMi5JafEzOtztvPVyj1YbXZcjAau6xnLPee3IMhbiTOp9sA36/jx771c1C6C967r6uxwzjiHJp7bRPoxbYISz2eb6z9dycLt2VzWqQmvX93Z2eGIOFVFpZU/Nmfw/Zp0Fu/M4eCVNW83EyM7NGF0tyi6xh49mWyusjJrYwb/W1Y9pMNBLcN9uKF3HFd2jcLdRY3eRETqkpLPIiJ1Q8nnU6Tks4iIiMi5oaLSyqdLdvPuvF2UmKsAGNomnEcvSiQ+1MfJ0cmZZkdmMUNfW4jBALPv70/zMF9nh3TG2JlVwtUfLncknr+8pQeBarhx1tm0t5CRby3GYIDf7ulH60idL8u5xW63s25PAd+tSeeX9fsorqhyzOsZH8TortFc1D4CL7faj3C3eV8hU5en8dPfeymvrC7THeHnwb8GxHP1eTGqvCIiUkeckXyOi4vD09OzXvclItLQysvLSUlJUfL5ZCn5LCIiInL2W7ozh0d+3EhaXnV5zHZN/fjP8Db0StB4vnJst/5vNX9uyWRUlyheGdPR2eGcEXZmlXDNR8vJLjbTOtKPaUo8n9XunLaWmRv2c35iGJ+M7+7scEQaRFZxBdPX7uX7NensyPpn3MOmAZ5c2TWKUV2iiAn2Oq19FFVU8v3qdD5alMz+wgoAQn3dua1/PGN7xJxUQltERI7UkNf8rVYr27dvJywsjOBgnV+KyNklNzeXrKwsWrZsicl07IaSSj4fRslnERERkbNXYXklk37byter9gDVvYseHtaKyzo1xWjUOItyfOv2FHDZO0swGQ28eXVnhrWLwHQOv292ZVf3eM4uNpMY4cu0CT1Vqv4sl5xdwtDXFmK12fn+X73oFhfk7JBE6kV2sZlVKXn8sCad+duzsdqqL515uBq5qF0ko7tG0TM+uM5/O5irrHy/Jp135+1ib0E5AMHebtzSL55xvWLxcVcSWkTkVDT0Nf/9+/dTUFBAWFgYXl5eRx2GQUSkMbHb7ZSVlZGVlUVAQACRkZHHXV7J58Mo+SwiIiJydvpjcwZP/LSJrGIzANf3iuXhYYm6kCsnZfxnK5mflA1AXLAXt/SL58quUedUadTMogp+Wb+PDxYmK/F8Dnr0xw18tXIP58UF8c1tPXUxVRo1q81OSm4pW/YVsWV/keM++8BvhYO6xAQwuls0IzpE4ufhWu9xVVptTF+7l7fn7XRUaQnwcuXmPs24oU9cg8QgInI2aehr/na7nYyMDAoKCup9XyIiDSkgIICIiIgTngcq+XwYJZ9FREREzi7ZxWae/nkzMzfuByA+xJsXRnXgvGbqsScnr6iiko8XJvP5slQKyyuB6l5p43vHMa5XLAFeZ2cCtqiikt83ZjBj/V6W7srl4FmkEs/nnv2F5Qx4aT6WKhuf3didQa3CnB2S1IOKSivZxWayis1kF1eQVWwmq8hM1oHHuSUW3F2MBHi54u/pRoCXKwGervh7ueLv6UqAlxsBnq4Hprvh6+HitAojVpud7GIz+wvLySisYH9hBck5JWzeV8S2/cWOsZYPZTBU/14Y2iaCK7tG0TzMxwmRQ5XVxox1+3h73k5255QC4OvhwsgOTRjRPpKe8UG4mIxOiU1EpDFx1jV/q9VKZWVlg+1PRKQ+ubq6HrfU9qGUfD6Mks8iIiIiZwe73c6Pa/fyzK9bKCyvxGQ0cFv/eO45v8U51UtV6kepuYpvV+/h40W7HaVRvdxMXNU9mpv7NiMq8PTG/zwTmKuszNuWzYx1e5m7LQtLlc0xr1tsIJd2asLlXaJUPeAc9NzMLXy0aDdtIv349e6+GrbgLPLGnB18tnQ3BWV1e6HcYKA6Ke3pin+NxHR1strXwxVvdxe83U34uLvg4+6C9yH3vh4umIwGSs1VlFqslJmrKDFXUWaxHphWRanZSom5isyiCkeSObOoOll+sGz20Xi4GkmM8KNNEz/aRPrRtokfrSJ8z6hxlq02O79u2Mdbf+1k5yHjTgd5u3Fh2whGdoikRzMlokVEjkXX/EVEGpaSz4fRF5GIiIhI47cnr4zHpm9k0Y4cANo28ePFKzvQtom/kyOTs02V1cbMjfv5YEEyW/YXAWAyGhjZIZLh7SNpFuJNTJBXo2rwsG5PAV+vTOO3jfspqqhyTG8R5sNlnZtySccmRAc1/uS6nLr8Ugv9X5xHsbmKN6/pzCUdmzg7JKkD+aUWejw/F4u1uqGJm8lIqK87YX7uhPm6E+brUX3v506IjzuWKhsF5ZUUlFVSUG6h6ODjskoKyispLLNQUF5JmeXInsUNzWQ0EOHnQYR/9S060MuRbG4W4o2pkTSgsNnsLNmVw28b9/P7pgzyD2kkEOztxoXtIhjRXoloEZHD6Zq/iEjDUvL5MPoiEhEREWnc1qTmM+6TFZRZrLi5GLl/SEsm9Gumi7BSr+x2O4t35vDBgmQW78ypMc9ggEg/D+JCvIkL8aZZcPV9XLAXMcFeuLucGYnp1Sl5vDF3h6PRBkCEnweXdmrCJZ2a0CbST+P7isObc3fw6uztxAV7MfuBAbjqM7bRm7JkN0//soU2kX5Mm9ADf0/XOvmbN1dZKSyvpNCRlK48kLS2UHggYV1yoCdzSUV1L+YScxWljuc1k9duLka83Ux4uVX3jPZyN+HtVt1r2tvNhVA/dyL9PIjw9yTS34NIfw+CfdwbTYK5tqqsNpYl5x4zEX1R+whGd42mQ5S/PrtF5Jyna/4iIg1LyefD6ItIRBpaldVGRZUNF6OhUfWKEhE5E1VabQx/YxE7skroGhvIS1d2ID7UOeM0yrlr095CvliWytaMInbnlFJ8SO/hw5mMBuKCvUiMqC7z2irCl8QIX6IDvRqklLHdbmd5ch5vzt3BsuRcR0yXdmzC6G7R9GgWpJLKclQl5ioGvDiP3FILz1/enrE9YpwdkpymEW8uYvO+Ip6+uA3j+zRzdjgONpudskorVqsdL3eTGjocxfES0S3DfRjdNZrLOjcl1NfdiVGKiDiPrvmLiDQsJZ8Poy8iETldVpud3TklbNlfzNb9RSRlFFNQZqGi0kZFlRVzpY2KSmv1rcrmGH/MxWhgYKswruzalMGJ4bi56KKKiMjJ+mDBLibN2kawtxt//Xsg/l6uzg5JznF2u528UgspuWWk5JSSklvK7pxSUg88LzYfPTHt5WaiZXh1IrpVhC8dovxp19S/znpJH+yp/dbcnaxMyQPA1WTgyq5R3D6gOTHBKqstJ/bZkt383y9bCPdzZ8FDg9SQshHbvK+QEW8uxs1kZMVj5xPo7ebskOQUVVltLN2Vy49r05m1KQNzVXUZ9YPnm6O7RTE4MUxJfBE5p+iav4hIw1Ly+TD6IhKRk1FUUcm2A0nmLfuK2JpRnWw+eIJ/qgK9XLm0U1NGdYmiXVOVuBQRqY19BeWc/8oCyiutvHRlB0Z3i3Z2SCLHZbfbyS42sy2jmG0ZRWzLKCYpo5gdWSVYjvJbws3FSIem/nSNC6RbbBBdYwMJOskEkd1uZ/72bN6cu4O/0wqqt2syclX3aP41MIGmAZ51cWhyjjBXWRn88gL2FpTz6EWJ3DYgwdkhySl6+ufNTFmawoj2kbxzbRdnhyN1pLC8kl837OO71ems21PgmB7i48ZlnZpycccmmIwG8sss5JdVl0LPL6088Lx6WmGZhR7xwTw2vLXzDkRE5DTpmr+ISMNS8vkw+iISkdp6Z95OXv4ziaN9inq5mWgV4UvrSD9aR/oR5uuOh6sJDxcjHq4m3F2NeLiYqqe5Vk/bk1fGD2v38uPadLKKzY5ttQr35cquUVzauQlhvh4NeIQiIo3L7VPXMGtTBt3jAvnm1l4qFSyNVpXVRkpuqSMZvXV/EX+nFZBbajli2fhQb7rGBNItLpAW4b6UmqsoKq+iqKKSovJKiioqKSyvdExLzy9nZ1YJAO4uRsb2iOG2/glE+Os3hpya79ek8+B36/H3dGXhw4Pw91TFicbGXGWl5/NzyS+r5LMbuzOoVZizQ5J6sCOzmO/WpPPj2r3klJhPvMJhZtzZh47RAXUfmIhIA9A1fxGRhqXk82H0RSQitbExvZBL31mMzQ5N/D1oHelHmyZ+jmRzbNCpj9NYZbWxeGcO369J588tmY6eTyajgQEtQ7m1fzw944Pr8nBERBq9+UlZjP9sFSajgZn39CUxQr/j5Oxit9tJyS1jdUoea1LzWZ2a70ginyxPVxPjesVyS79matgmp81qszPs9YXsyCrhrkHNefDCVs4OSU7Sbxv3c8eXawn3c2fpI+djUuOtOmGx2ZifV8xPWQWsLSplQKAvd8eGE+Xh3JLmlVYbC5Ky+W7NHpbuzMXTzUSglxuB3q4EerkR4OVGoNfBx67M2pTBX9uyuKRjE968prNTYxcROVW65i8i0rCUfD6MvohE5ESsNjuXv7uEDemF9X4CXlhWya8b9/H9mnRHaUyA8b3jmDgsEU83jasnIv94+ufN/LphP9/c1pOEUB9nh9NgKiqtXPj6QlJzy7i5bzOeGNnG2SGJNIj8Ugt/78lndUp1Mnpvfjm+Hi74ebji53nw/sDNwwU/T1f8PV3pHhd00uW6RY7n900Z/GvqGjxdTSx4eKAaNTQyN362knlJ2dwxMIGHhyU6O5xGzWq3szS/hOlZ+czMLqSwylpjvqvBwFURQdwdG0asp7uTojw5m/YWMvKtxbgYDSyaOIhIfw3PICKNj675i4g0LCWfD6MvIhE5kf8tS+HJGZvx9XBh7r8HNNjFtV3ZJXy0MJmvV+0BoFmINy+P7kjX2MAG2b+InNn25JUx4KV52Oycc+M1vjFnB6/N2U64nztzHhiAr4dKvoqINCS73c5l7y5l/Z4COkb587+beuDvpc/ixiCzqIJek+Zis8Nf/x5A/DnUeK2u2Ox21hSVMT0zn1+yC8i2VDnmhbu5cElYAF39vJm6L5fFBdUVK0wGuDI8iHtjw4n3OvOT0GM+WMbK3XncPjCBiWqgICKNkK75i4g0LKOzAxARaUyyiip46fckAB6+sFWD9upICPXhhVEd+Pym84jw82B3Timj31/K5N+3YT6sRb2InHv+tywF24EmhTM37mfr/iLnBtRAUnNLeWf+TgAeH9FGiWcREScwGAy8OKoDQd5urE8v5JqPlpN3lDHK5czzw9p0bHboFhuoxPNJKLPa+Cu3iKd27KX7si1cvHYHn+7NIdtSRaCLiXFNgvm+UwJre7flvy2iuCw8kO87N+fnzs0ZFOSL1Q7fZOTRd8VW7tySyvbSCmcf0nHd3LcZANNWpFF2SHJdRERERORolHwWETkJ/525lWJzFR2j/BnbI9YpMQxoGcof9/fnis5Nsdnhvfm7uOStJWzaW+iUeETE+UrMVY6qCHHBXgC8Pme7M0NqEHa7nad/3oylykbf5iGM7BDp7JBERM5ZrSJ8+WpCT0J83Nmyv4irP1xGdrHZ2WHJcdjtdr5fnQ7AmG7RTo7mzGaz29lUXMbbqZmMXreTxEUbGbshmQ/Ss9lrrsTbZOTK8ECmdohnfZ+2vNQqmr6BvpgMNcfPPi/Ah686JvBblxYMCfbDBvyQmc+Aldu4bXMKi/OLSa+wUGU7s4oUDmkdTkyQF4Xllfywdq+zwxERERGRM5zKbh9GJThE5FgWbs/m+k9XYjTAz3f1pV1Tf2eHxO+bMvjP9I3kllpwMRq45/wW3DEwAReT2haJnEumLNnN079sIT7Em/fHdeXC1xdit8Ovd58Zn1X15eAYo64mA7/f1/+cGudaRORMtTOrhLEfLSer2ExCqDfTJvQk3E9jQJ+J1qTmMeq9ZXi6mlj1+BB83F2cHdIZJdNcyYL8YhbkVd9yKmv2+G3q7sqAIF8GB/lxfrAfnqdwDra+uIzXUzKZlVOzIbHJABFurkR5uNHUw42m7q409XAjysONeE93p5Tq/mzJbv7vwO/NOQ8MwGg0nHglEZEzhK75i4g0LJ1ZiIjUQkWllSdnbALght5xZ0wyZ1i7CLrHBfKf6Zv4fXMGr87eztytmTx3eXvCfN2pstmx2uwH7m1U2exUWaunWe12XI1G3F2NuLsY8XA14e5ixN2l+l4XE0QaB5vNzmdLUwC4sU8cLcN9ubRjE35at4/X52zn4xu6OzfAelJmqeKZXzYDcFv/BCWeRUTOEM3DfPj2tl6M/Wg5u7JLGfPBMqZN6EnTAE9nhyaH+XZVda/n4e0jlXg+oLjKyi/ZBXy7P4/lhaU15nmZjPQJ8GFAkC8Dg3xJ8HTHYDi9c6aOvl581r4ZW0rKeSs1kzVFZewzW6iyw15zJXvNlXBYHAB3RIfxZPMmp7XvkzW6WzSv/rmd5JxSFmzPZlBiWIPuX0REREQaD51diEidstvtrE7NZ9qKNFan5jGhXzzjesae9km5s703fxcpuWWE+7nzwNCWzg6nhmAfd967rgs/r9/HEz9tYn16ISPfWnza23UzVSelY0O8+OKmHgR6u9VBtCJyqHKLlWdnbmFNaj7vXNvllBKof23LIjW3DD8PF67oEgXAPee34Of1+5izNYv1ewroGB1Qx5E735tzd7KvsIKmAZ7cOai5s8MREZFDxIV4881tvRj78XJSc8u46oNlfDWhJ9FBXs4OTQ4os1Tx64Z9AIzpFuXkaJyrymZnYX4x32XkMSunkIoDJa8NQAdfTwYG+TEg0Jdu/l64GeunwlQbH0/eaxsHgNVuJ9tSxd4KC+lmC+kVleytsLDXbCG9wsLmkgre3ZNFuLsLt0U3XALYx92Fq7pH8/Hi3XyyeLeSzyIiIiJyTI0m+Txp0iR+/PFHtm3bhqenJ71792by5Mm0atXKsUxFRQX//ve/+frrrzGbzVx44YW8++67hIeHOzFykXNDYXkl09emM21lGtszSxzTn5yxmb+2ZfHilR0I822c5faSs0t4b/4uAJ66uC2+Hq5OjuhIBoOBSzs1pUezYB7/aRNzt2ViNBgwGQ24GA+9Nzqem4wGqqw2KqpsmCutmKtsNcYWs1htWKw2Nu0t4pcN+7i+V5zzDlDkLLQzq4Q7v1xLUmYxAI/+uJFvbu150o11Pl2yG4BresTgfaDXUnyoD5d3juKHtem8Nmc7U248r26Dd7KdWcV8vCgZgKcvaYunm8nJEYmIyOGig7z45tZeXPvxCnbn/NMDulmIt7NDE2DWxgxKLVZig704r1mQs8Nxii0l5XybkcePmflkWf4pqd3Cy50xEUFcER5IU4+Gb4BrMhiIcHclwt2Vrhz59/JOWhb/3bWPp3buI8LdlUvDAhsstht6x/Hpkt0s3pnDtowiEiNUulbOXHa7nZzKKvZUVDfiSK+obsDhZTJycVgAHXw8G31HCRERkTNVoxnzediwYVx99dV0796dqqoqHnvsMTZt2sSWLVvw9q7+MX777bczc+ZMpkyZgr+/P3fddRdGo5ElS5bUej8a/0Gk9ux2O+v2FDBtRRq/bNhHRaUNAE9XExd3jCQmyIs3/9qJpcpGoJcrk67owLB2EU6O+uTY7Xau+2QFS3bmMqBlKFNu7N4oTk7sdvspxVlltWGuqr5VVFr5amUab/21k34tQvji5h71EKnIuWnGur08+uNGyixWQn3dKa6opKLSxqtjOjp6L9fG1v1FXPTGIkxGAwsfHlSjpGlqbimDX1mA1Wbnh9t70zW24S5M1ie73c7Yj1awLDmXIa3Dztqy4iIiZ4usogrGfryCnVklhPm6M21CD5qH+To7rHPeVR8sY8XuPP49tCV3n9/C2eE0CLPNxrqiMpYVlPBLdgGbSyoc84JcTVweFsjoiCA6+p7ZCSm73c7jO/byyd4c3AwGvu6YQO/Ahht+5I4v1/DbxgzGdIvixSs7Nth+RY7GZrezp8LClpJytpVWHEg0H6gYYLZgth37sndzL3cuDwvk8vBAp4yjLg1L1/xFRBpWo0k+Hy47O5uwsDAWLFhA//79KSwsJDQ0lGnTpnHllVcCsG3bNlq3bs2yZcvo2bNnrbarLyKREysxVzFj3V6+XJ7Glv1Fjumtwn25tmcMl3Vuit+B3sHbM4u57+t1juXGdIviyYvbNpoxxWas28u9X6/D3cXIn/f3Jzb43OqpkZxdwuBXFuBqMrDmiaGO/1cROTUVldVltqcuTwOgd0Iwb1zdme/W7OHF35MI8XFj7gMD8feq3d/aw9+v59vV6YzoEMk7Y7scMX/i9xv4ZvWes6oByaGfy3MeGKASriIijUBOiZnrPl7Btoxigr3deHtsFzpG++Pl1jjOCc42abll9H9pHgYDLJk4mCZnyHjc5VYbWZZKsixVZJorHY+zLJVkmquwY6e5lwfNvdwd96FuLsdMFJdarawtLGNZYQnLCkpYW1RWIxHlajBwQYgfo8ODGBzsW28lteuD1W5nwqYUfsspxN/FxIwuzUn0bpj/xzWpeYx6bxluLkaWPjKYEB8l7Zyl3GpjZ1kFFTY7nX29cDGeuY0m6kJRlZWtJeVsKa2ovi8pZ2tpBaVW2zHXMQAR7q5EubsR5eFKUw839lRY+OOQEvsAnXy9GBUeyKVhAYS567rH2UjX/EVEGlajPdMrLCwEICioujzUmjVrqKysZMiQIY5lEhMTiYmJOW7y2Ww2YzabHc+LioqOupyIVCssr2TEm4tIzy8HwM3FyMj2kVzbM4YuMYFHnPi3DPdl+p29eW32Dj5YuItvV6ezPDmP167qSNfYM7u8W2FZJf/9dQsAdw9ufs4lnqG6dG9CqDe7sktZkJTNxR2bODskkUYrLbeMO6atYdPeIgwGuHtQc+4d0hKT0cAtfeP5YU06u7JLefnPJP57WbsTbi+nxMxP66rHarypT7OjLnPX4Ob8sDadRTtyWJWSR/e4M/tz90T2F5bzf7/887msxLOISOMQ4uPOVxN6Mu7TFWzaW8Q1Hy0HIMLPg7gQL5qF+BAf4k2zEG/iQryJCfLCzaXxJAIbm+/X7AGgb/OQek882+128iqt/ySVLZVkmQ9JKlsqyT6QbC4+TgLpoL/yims893MxOhLRLbw8aOrhxpaScpYXlLCuuIyqw7pbhLi60DPAm/6BvowMCyDItXFeFjMZDLzTJpar1u9iZWEp165P5teuLYh0r/8y4V1iAukYHcD6PQV8uTyNe4ecGz3nnanKZmd3uZltpRVsK63u4butpILd5WYO/tWEurlwaVgAV4QF0tnP64zuvV8b2ZZKNhSXs6G4jPXFZWwsLmevufKoy7oZDLTy9iDRx4M4D3eiPKoTzVEebkS6ux61YUlJlZVZOYX8mJnPwvxi1hWXsa64jKd27qVfoC+XhAXg42Kk1GqjtMpGidVKidVGqdVGSZW1errVSlsfTx6Jj8S9ETVeERERaQiN8le2zWbjvvvuo0+fPrRrV31xNiMjAzc3NwICAmosGx4eTkZGxjG3NWnSJP7v//6vPsMVOat8tDCZ9PxywnzdubV/PFd2jSLA6/gnuO4uJh65KJGBrUL597frScsrY/T7y7hrUHPuPr8FrqYz80f6S39uI6fEQkKoNxP6xzs7HKcZ2iaCXQt2MXtLppLPIgek55cxb1sWcSHeJEb4Eep7/B4ff2zO4MHv1lNcUUWglyuvXdWJga3CHPPdXIz897J2jP1oBVNXpDK6WxQdogKOu80vl6dhqbLRMTqALjFHXzY6yIsx3aOZtiKN12ZvZ9qE2lWCORNZqmzc8eVa8kottIn0O6c/l0VEGqNAbze+vKUnj/64gWW7cskvqySjqIKMogqWJ+fVWNZogIRQH965tgstw1Wiuy5ZbXa+X5MOwOhu0fW2n43FZTyfvJ/F+SVUnkTBPXejgTA3V8LdXAhzcyXM3ZUwNxfC3VyxYWdnmZmdpWZ2llWQVmGhqMrG2qIy1haVHXV7Tdxd6RXgQ88Ab3r6+9Dcy73RJ+UO8jQZmdK+GZes3cHOMjPXrk/mpy4t8HMx1et+DQYDN/WJ496v1/HF8lT+NTAe93re57mouMrK88n7WVlYwo5SM5Zj/B0FHnjtsy1VfJyew8fpOTTzdOPy8ECuCA+kuZcHUP23bwCMh/WOttntpJZbHElti83O0GC/Bk1g51VWVSeZi8rZUFLGuqKyYyaam7q70trHkzbeHrTx8aS1jyfxnu64nmSvbx8XE6MjghgdEUS2pZKfswr4MTOfNUVlLMgvZkF+8Yk3AizMLyGtwsIHbeLO+p7nIiIiJ6NRlt2+/fbbmTVrFosXLyYqqnpcxGnTpnHjjTfW6MUMcN555zFo0CAmT5581G0dredzdHS0SnCIHEV2sZkBL82jzGLlg3FdubDtyY/fXFRRyVMzNjP9770AdIzy55UxHc+4cd/W7Sng8neXYLfDVxN60ish2NkhOc3Bsmq+Hi6sfWLoGdtYQKShVFRaGf7GIpJzSh3TQnzcaR3pS2KEL4kRfiRG+tI8zAejwcDkWdv4ePFuALrGBvLWNZ2P2cvovq//5qd1++gQ5c/0O/pgOsYFDHOVlT4vzCOnxMwbV3fi0k5Njxnv3oJyBr00H4vV1qg/z57+eTNTlqbg5+HCr3f3IyZYvZ5FRBqzgjILu3NKj3ors1gBuKJLU14d08m5gZ5lFu3IZtwnK/HzcGHlf4bg4Vq3ScPUcjOTd2fwY2Z+jelBriZCD00qux1IKru7EnoguRzm5oKfi6nWCa9yq42UcjM7yqqT0TvLzOwpt5Dg5e5IOMd4uJ01yeZjSSs3M3LtDrIsVfQL9OHLDvH1XkK80mqj/4vz2F9YwUtXdqjXhgznIovNxrUbklmUX+KY5mUykujtccjNk0RvD0LdXKiyw/y8IqZnFTAru5By2z9VBFp7uuOTa2Hz6v0Ee7vRqW0YEU19KXKFbaUVbC8111j+oKburowMDeDisAC6+HlhrOXfUUmVlTVFZawsLCG13ILFbsdis2G22bHY7FTa7ZhtNiwHnpdabWRYjkw0G6gek7mDrxcdfT1p7+tFa28PAuq5WkFquZnpmfnMyyvGQHWS2sdkxNtkxMdkwtvFiLepeprZZuPZXfux2O2MiQjk9cSYWr9O0vBUdltEpGE1up7Pd911F7/++isLFy50JJ4BIiIisFgsFBQU1Oj9nJmZSUTEsRNk7u7uuLtrfBqR2nhn3k7KLFY6RgdwQZvwU9qGn0d1j7/BiWH8Z/pG1qcXcsFrCxnWLoIJ/eLpHBNYx1HXtGVfEd+u3oO5ygbYsdupvh18TPXz1al52O3VF7waa6KmrnSKDiTEx42cEgsrkvPo2yLE2SGJONXLfySRnFNKgJcrgV5upOSWklNiZtEOM4t25DiWczEaCPByI6ekupHbhH7NeHhY4nEbcDw2ojVzt2axIb2QaSvTGNcz9qjL/bp+PzklZiL8PBjePvK48TYN8OTq86L537JUXpuznZ7xPRvdRdgZ6/YyZWkKAK9d1UmJZxGRs0CAlxudY9yO+P1vt9tZtiuXsR+v4LeN+3nq4rb4e2r8zbry3erqXs+Xdmpap4nnXEsVb6RmMmVvjqOH5hXhgdwTG0a8p3u9JEM9TUZaH+j5eC6L8XTnyw7xXPb3Thbll3D/tj281bp+k2CuJiPX94pj8u/b+GTxbq7sGtXofl+eqWx2O/dv28Oi/BK8TUZeaRVNFz8vojzcjvl/6mqAoSH+DA3xp7TKyh+5RXy1N4fFBaVsLTeDF9A/gjJgD1WQW7NxiIfRQEsvD1r5eFBpszM7t4i95ko+SM/mg/RsmhySiO7q54XdDiajAbvdTrq5klWFpawsLGVVYQlbSyo4cQH9I8V7utPR1/NAstmL9r6e+DqhR32spzv3xUVwX1ztOltEe7hxy+YUvs3Ix8dk4rkWTfW3ICIiQiNKPtvtdu6++26mT5/O/Pnzadas5tiGXbt2xdXVlblz5zJq1CgAkpKSSEtLo1evXs4IWeSskp5fxpcrUgF4+MJWp/1j+uKOTegWF8gTP21iztYsftuYwW8bM+gWG8iE/vEMaR1+zB5/p2rZrlxu/nyVoyfFifh7uvLY8NZ1GkNjZDIaOD8xnG9W72H2lgwln+Wctjolj0+WVPdifnVMRwYnhlNmqWJ7Zgnb9hexLaOYrQfuC8srySkx4+vhwiujO3JBLapFhPl68OCFrXjq5828+Ps2hrWNOKKkt91u59MDMVzfO7ZW1QjuGNicr1ftYeXuPJbuyqVP88bzd7w9s5hHftgIwF2DmnN+61Nr/CQiIo2DwWCgV0IwrcJ9Scos5uf1+47ZGEtOTmFZJb9vrh6WbHS3qBMsXTtlVhsfp2fzVmqmY8zm/oE+PJ7QhA6+aizWUNr7evFJuziu25DMD5n5RLq78nhC/Q6ZdM150bw5dwfbMopZlpxL74TG8/vyTPZc8n5+yMzHxQCftItjYNDJ9dC0mK0krc1g49IU3ABrhCdezXwp8jRV9+StslORZ8ZeZMFQXImhpIpYTzeGdohkZFQgiRG+5JZXMn1vLrNyClldUcE+cyUfpmfzYXo2JrMVMsvx93fHGuBG4VEKakZ7uHGevzeJ3h54moy4GQy4GQ24G424GQ24GQzkFJlZsDWL1btzubRFGI8NSKzza0AN4aLQAN5IjOHurWl8ujcHPxcTj8Qfv3GwiIjIuaDRJJ/vvPNOpk2bxowZM/D19XWM4+zv74+npyf+/v7cfPPNPPDAAwQFBeHn58fdd99Nr1696Nmz8Y5vKHKmeH3ODiqtdvo0D66zpEWkvycf39CdbRlFfLxoNzPW7WV1aj6rv1hDsxBvbu7bjCu7RtVJi/z5SVnc9sUazFU2zmsWRN/mIRgAgwFHIt1gAAOGA/fQt0UIIT6qjAAwtE118nnO1iyevsSulrxyTiq3WHno+w3Y7TCqSxSDE6uToF5uLnSKDqBTdIBjWbvdTkZRBcnZpSRG+BJ8Ep8l1/WM5dvVe9i8r4hJs7YeUW505e48Nu8rwsPVyDXdY2q1zQh/D8aeF8OUpSm8Ons7vROCG8XfcYm5in9NXUN5pZU+zYO5f2hLZ4ckIiINwGAwcFX3aJ75dQvfrDp2JRA5OT9v2IelykZihC/tm/qf1raqbHa+ycjjpd0ZjpK57Xw8eTwh8qSTZVI3Bgb58UqrGO7dlsbbaVl4m4zcEhVab71HA7zcGNW1KVOXp/Hp4t1KPteBj9OzeSctC4BXE2NO6m+pqKKSTxbt5pPFuykxVwHQJSaAhy5oRe/mIeRVVuFlNOJhMlJusTI/KYtfN+xnbn4mqWVlvDNvF+/M24W3m4nSQxrsG4zgGuyBNcITW5gHVncTxPiQB9Vl42x2wuxGBoX5MyQigO7+3kS4H71ahbnKyu+bMvh8RRord+c5pn+SXkJaZimvX9UJb/f6vVS9JjWP3TllxAV70SzEmyDv0y/Nf2VEEKVWGxO3p/N6aiY+JiN3xarBrIiInNsazZjPx/oh8NlnnzF+/HgAKioq+Pe//81XX32F2Wzmwgsv5N133z1u2e3DafwHkSPtyCzmwtcXYrPDT3f2qZFgqUuZRRV8vjSFqctTKaqoPlkK8nZjXM9YxvWKPeVE8B+bM7hr2loqrXbOTwzjnWu71PnYZme7ikornZ+ZTXmllZn39KVtk9O7WCXSGP331y18sng34X7u/Hn/gHotAfp3Wj5XvLcUux2+vrUnPeP/Kf9/2xer+WNzJmN7xPD85e1rvc2sogr6vTgPc5WNz286jwEtQ+sj9Dpjt9u5c9paftuYQaS/B7/e3fekkvgiItK45Zda6PH8XCxWG7/e3Zd2p5ksFbj07cWsTy/k8RGtuaVf/Clto9RqZXpmAR/syWJHWfXQItEebjzSLILLwwM13ukZ4LWUDCbvru6w4WYwMCDIlxGh/lwY4k9gHY+Xuyu7hPNfWYDBAH/9eyDNQryPWMZut5OcU8rSXbmsTskjOtCLWwfE4+ehcvqH+iWrgFs3p2AHHouP5J5aJi/LLFVMWZrCBwuSKSyvbgjSJtKPBy9syaBWYSdMrJaaq5i7LYtf1+9j/vZsLFXVFQwCvFxpGuBJVKAnTQO8iAr0JDTAgww32FhhJjevjG1bc8jZU4LBVn1puV+LEMb1jGVwYhguh1RnSs4u4auVaXy/Jp38suoYjQY4v3U4naIDeGPuDixVNlpH+vHJDd1oElD3pfQ3pBfw0h9JNYZJAvD1cCE+xJtmId7EHbiPD/EhJsgLDNUJc3OlDXOVlYpKG+YqG+ZKa/V9lZUW4b4khPoA8HZqJs8m7wdgcssobmiqBhlnEl3zFxFpWI0m+dxQ9EUkcqR/fbGG3zdncGHbcD4Y163e91dqruLb1Xv4ZPFu0vPLAXB3MXJLv2bcMbD5SbWEnbFuLw98ux6rzc6I9pG8dlUn3Fzqfryxc8Gt/1vNn1syuW9IC+4bot6Hcm5ZlZLHmA+WYbfDZ+O7MygxrN73+dj0jUxbkUbLcB9m3tMPV5ORtNwyBrw8D7sdZt/fnxbhvie1zWd/3cLHi3fTMTqAn+7ofUb3fv54UTLPztyKq8nAN7f1osthY4KKiMjZ7+6v/uaXA2W3/3tZO2eH06glZVQ3KHYxGljx2Pkn3aBre2kFn+/N4duMPEd57UAXE/fFhTO+aQju9TCms5wau93OR+nZfL43l13lZsd0FwP0DfBlZFgAw0L8CXGrm0T0TVNW8de2LK7vFcszl1b/ne7JK2PZrlyW7sph6a5csorNNdYJ8XHj4WGJXNklCmMjLLVc15YVlHD1+l2YbXbGNw1hUi3GDa6otDJtRRrvzt9JTokFgBZhPjwwtCUXto04pde1uKKSjMIKIgM88anFdRerzc7C7dl8sTyVeUlZHLzC3MTfg7E9YogO8uLrlXtYlpzrWCfS34Oru8dwVfdoIvw9AFiTms9tX6wmp8RCqK87H1/fjY511OlhZ1YJr85O4reN1Q0yXE0GOscEsje/nH2F5ZzuVXGjAV4d04nLOjcF4IXk/byemokBeKt1DFdGBJ3mEUhd0TV/EZGGpeTzYfRFJFLT+j0FXPrOEgwG+OO+/rQ8yUTH6aiy2vhjcyYfLtzF+vRCAML93HnkokQu7dj0hCdT367aw8Qfq0vkXtG5KS9e2aFG61s5Od+u3sPD32+gbRM/Zt7Tz9nhiDSYcouVi95YSEpuGVd2jeLl0R0bZL8FZRYGv7KAvFILjw1P5Nb+CTzzyxY+XbKb/i1D+d9N5530NrOLzfR/cR7llVZeHt2RSzo2OSMb5Kzcncc1Hy3HarPzzKVtub5XnLNDEhERJ1iyM4drP16Br4cLKx8bgqebqhedqid+2sQXy1MZ1jaC98d1rdU6lTY7v+cUMmVvDksKShzTm3m6cUOTEK6JDMK/jnvSSt2x2+1sK61gZnYhv2YXsK20wjHPCPQM8GFEqD8XhPgT7eF2yvs5+Hfq6Wri4o6RLN2V62hEfpCbi5GuMYF0iwtk5sb9JGeXAtAxOoD/u6RtvVVXawy2lZZz6dqdFFZZuSjEn4/bxWE6TuLZUmXjuzV7eGvuTjKKqv9PY4O9uG9ICy7p2NRp4ybvySvjyxVpfLMqzdG7+SCDAQa1CmPseTEMbBV61Osy6fll3DxlNUmZxbi7GHllTEdGdjj1ccv3FZTzxpwdfLdmDzZ7dQyXd2rK/UNbEh1UPR59RaWVtLwykrNL2Z1Tyu6cElJyykjOKSWnxOyI3d3FiIerCXcXI+4uJjxcq+8tVTaSMosxGGDyFR0Y0z0au93O4zv28sneHEwG+LhtHBeFBpzycUjd0TV/EZGGpeTzYfRFJFLTuE9WsGhHDld0aXrEuKMNxW638+eWTJ6buZW0vDIAOscE8NTFxz5J/XxpCk/9vBmAsT1iePbSdmpRfZpyS8x0f24ONjsseWQwTeuhFJbImehgwjfCz4M/7u9fr+W2D/fd6j089P0GvNxMzLizD5e/u5QScxVTbuzOwFan1vt60qytfLAgGai+kNK+qT9dYgPpHB1Al9hAwv086vIQTlpWcQUj31xMVrGZSzs14fWrOp3RPbRFRKT+2Gx2Brw8jz155bw6piNXdIlydkiNUlFFJT2fn0uZxcq0W3rQu/nxS8HuN1uYui+XqftyybRUD4dkBC4I8WN80xD6B/qqvHYjtKvsQCI6q4ANJTWTw628PTg/yI/zg305z98H15M4d7bb7Vz0xiK2ZRQ7prkYDXSMDqB3QjC9EoLpEhPoGPrKUmVjytLdvDFnh2Ns4THdonjowkRCfc+tIVb2VVgYuXYH+8yVdPfz5ttOCXgeo8G81Wbnp7/38vrc7ezJq/7/a+LvwT3nt2BU1yhcz5CG9hWVVmZt2s+Xy9PILbVwcYdIrjovplbXD0rMVdzz1d/8ta163OsHhrbk7sHNT+pcIK/UwrvzdvK/5amOEuJD24Tz4AWtaBVR+84UFZVWjAYDribDMfdvs9l5YsYmvlyRBsB/L2vHuJ6x2Ox27tuWxrcZ+bgZDEztEE//oIbryCFHp2v+IiINq1bJ5yuuuOKkN/z+++8TFlb/JSnrmr6IRP6xdFcOYz9agavJwF//HuhoHeosFZVWPl2ym7f/2knZgZPUK7tG8fCFrQg7JFny/oJdvDBrGwA3923G4yNaK3FRR0a/v5RVKfn83yVtuaF3nLPDEal3K3fncdWHB8pt39idQaeY8D1VNpudqz5cxqqUfIK83cgrtdA8zIfZ9/c/5c+14opKnpqxmXlJWUf0SgBoGuBJ55gAusQE0q6pP2G+7gT7uOHj7lLvn6VVVhvXfryCFbvzaBnuw0939sGrjkpCiohI4/T2Xzt4+c/tnNcsiG9v6+XscBqlKUt28/QvW074G6LKZuepnXuZsi8H64ErRaFuLlwXGcy1TYKJOo3esXJmSS0381t2IbNyClldWIrtkHm+JiP9g3w5P9iP84P8CHc/ccPLlbvzeGfeThIjfOmVEEz3uKATDpeVVVTBC79v48e1e6v36+7CfUNbcn2v2DMmkVqfCiuruPTvnWwrraCFlzszurQg6CiVBGw2O79t2s9rs7ez60CP8RAfd+4alMA1PWJwdzm7KkJYbXae/20rnyzeDcClnZoweVQHR+OFw9ntdrKKzezKLmH5rlw+XZJCibm60UyPZkE8PCyRrrH1N3yP3W7nv79u5dMl1fE+PqI1t/SLp8pm57YtKczMLsTTaKR3QPW40Ac/fg9+CjvuDdDVz5s7Y8KO2/NdTp2u+YuINKxaJZ+NRiNjxozB07N2vdymTZvG1q1biY+PP+0AG5q+iESq2e12rnhvKX+nFdQYu+lMkFlUweRDTlK93UzcNbgFN/WN4915u3hj7g4A7h7cnAeGtlTiuQ59uHAXz/+2jb7NQ5h6Sw9nhyNyUqqsNvLKLIT6uNfqc+HQctuju0bxUgOV2z7ctowiRry5GKut+ifbc5e349oesae9Xbvdzu6cUtamFbA2LZ+1qflszyzGdoxfhm4uRkK83Qj2qU5GB3u7E+LjRoiPO00DPYkL9iY22OuEFxqPF88Ls7bxwcJkfNxdmHFXHxJCfU7jCEVE5GyQUVhB7xfmYrPDX/8eQLy+G06KzWZnyKsLSM4p5b+XtmXcMYayKK2ycuvmVObmFQHQ09+b8U1DGB7qj5vGcz6r5VdWsSCvmLl5RfyVW0xuZVWN+e19PBkdEcjNUaH1khRbk5rHUz9vZtPe6vdeizAfHhvemmYh3piMBkxGAy6OeyMm0z/PG2uS2myzcc36ZJYWlBDm5sKvXVoQ41mz13e5xcqC7Vm8MXcnW/dXvzYBXq7cPiCB63vFnfXDEHy1Mo0nftpElc1O55gA3ry6M8UVVSTnlJCcXUpydgm7DpTLPphsPqhdUz8eujCR/i1CGuR6kN1u58U/knhv/i4AHrqwFXcOao7ZZmP8xt3Myys+wRb+MSYikNcSY5SArge65i8i0rBqnXzOyMiodU9mX19f1q9fr+SzSCM2e0smE/63Gk9XEwseHkiYr3PLsB7N32n5PP3LFtbvKQBw9AqEf37sS93anVPKoJfn42I0sPbJofh5NFz5YZFTdbBE3Rtzd5CWV0abSD/G9Yrl0k5Njtur9v9+2cxnS1KcUm77cM/N3MJHi3bj7+nK8kfPr7eLTSXmKjbsOZCMTitgR1YxeSUWR0nE2gj1dScu2Iu4YG/iQqoT0nHB3vh5uJJZXEFGYQWZRdX3GUUHHhdVkFlkdpTGe+/aLlzUPrJejlFERBqfm6esYu62LG4bEM+jF7V2djiNyqId2Yz7ZCU+7i4sf+x8fI7SSCzbUsl1G5JZX1yOp9HAu21iNUbpOcpmt7O+uJy5uUXMzS1iXXEZBy8a9vD35q3WMUckSeuC1Wbn29V7eOmPJMc5fW2E+7nTLTaIrrGBdI8LonWk71HHEz4T2O121hWX83tOdenzXeVmfExGfurcnHa+XpirrPydVsDSXbks35XL33vyqTxQgsDX3YVb+sVzU984fM+hc/ClO3P419Q1FFVUHXc5k9FAdKAnCaE+XN6lKcPbRTb4sGt2u5035+7ktTnbAbjn/BbcP6QFlXY7c3KLKKqyOv6W7I5/HHdkWSp5OSUDq10J6Pqia/4iIg2rVsnnBQsW0KdPH1xcateTZfHixXTv3h1398Y3Vou+iESqT/yGv7GIpMxi7hiYwMPDEp0d0jHZbHZ+WreXF2ZtI6vYDMCTI9twU99mTo7s7DXk1QXszCrhzWs6c0nHJs4OR+SYjlai7lC+Hi6M6hLFdT1jaR5WsxeVs8ttH67MUsUrf26nT/NgBieGN/j+yy1WckvN5JZYyCk5cH/geXaxmT35ZaTklB61jPfJMBkN3Hd+C+4+v0UdRS4iImeDPzdncOsXawjxcWPZo+c32t6OznDL56uZszWT8b3jePqStkfM31VWwdj1yaRWWAhyNfFF+3i6+ns7IVI5E2VbKvk5q4BJyfspsdrwMRmZ1DKKK8MD66VHaWFZJa/N2c6vG/ZhrrRRZbNjtdmpstmOWZ3nUF5uJjpFB9AtLohusYF0jglwarK20mZnWUEJs3IK+T2nkP3mf34re5uMPBYWQsX+MpbuymF1Sj7mKluN9Zv4e3BZ56bc2j+eAK9zs+x9cnYJt36xhp1ZJQR4uRIf4k18qA8JoT7Eh3qTEOpNTJA3bi5nxvfCe/N3Mfn36mHgbhsQzyPDEmv9tzIjK587tqRitcNVEUG8mhitBHQd0jV/EZGGVavk87lEX0Qi8NPfe7nvm3X4ebiw6OHB+Hud+S1rS81VfLUyjZggLy5oG+HscM5qL8zaxvsLdnFxxya8dU1nZ4cjcgS73c6crVm88mcS2zKqS5wFeLnyrwEJXNKxCTM37GfqilRSc8sc6/ROCGZcz1iGtAmn0mrjojcWkZpbxphuUbx4pXPKbTdGhWWVpOaVkpJbnYxOyS0l9cDjEnMV4X4eRPh5EO7vQYSfe/Vz/wPT/DwI83M/68atExGR01dptdH7hb/ILjbz/nVdGdZOv/drY09eGf1fmofdDnMeGHBEY7vVhaVcvzGZvEorsR5uTOsYT4LXmVfxSpwvtdzM3VvTWFlY3aDzkrAAJreMIvAoYxTXF5vNjtV+MBltp7LKRlJmMWtS81mVksea1HyKD+shazRAizBfooM8ifT3JDLAgyb+nkT6e9AkwJNwP486T1qWVlmZl1fM7zmFzM4torDqnwpC3iYjXT09qdpXyrYNWZSV1my4GeLjTq+EYHofuMUEeWkYMarP74oqqpxaiepkfLp4N8/8ugWA8b3jeOriNkpAnwF0zV9EpGGddPJ5wIAB3HzzzYwePbrWY0A3JvoiknOdpcrGkFcXkJZXptLVclRrUvMZ9d5SfN1dWPPE0DOmhbGI3W5n0Y4cXvkzifXphcCxS9TZbHYW7czhi2Wp/LUt09GTItzPnbhgb1bsziPSv7rctsrLi4iION/k37fx3vxdDGoVymc3nufscBqFSbO28sGCZPq1COGLm3vUmDcru4Dbt6RSYbPTydeLLzo0I9RNv3nk2Kpsdt5Oy+TllAyq7BDp7sobiTH0D/J1dmhA9e/7HVkljkT06tQ89uSVH3cdg6E64dvE34MBLUO5dUDCUUvT19aivGJu2ZxSI+Ec4urC0GA/QkusrFqzn79T8h3z/D1d6RUf7Eg4Nw/zUbL5LPHlilT+M30TAGN7xPDspe1qXQr8p8x87txanYC++kAC2qj3xWnTNX8RkYZ10snn++67j2nTpmE2mxkzZgw333wzPXv2rK/4Gpy+iORc98XyVJ74aRMhPu4sfHjgccdDlXOTzWbnvOfnklNi5oubz6Nfi1BnhyTCqpQ8Xvo9iZUpeQB4upq4sU9crUrUpeeX8dXKNL5euYfcQ8aY+/ym8xjQUu9vERGRM8HunFIGvTwfowEWTxxMk4CzrzF8XaqotNJz0lwKyir56PpuDG3zz7Adn6Zn8/iOvdiAIcF+fNA2Fm+TKo9I7awrKuPOLansKq8e9uq2qFAejY/E4wwsh59ZVMHmfYXsLaggo7Cc/QUV7CssZ39hBfsLK7AcVuY6xMedhy5syZVdozGd5JjBM7MLuH1zKha7nWgPN0aE+tPH24utW7P5cnkamUXVr5erycCI9pGM6xVL5+jABh+bWBrOd6v3MPGHDdjscFOfZjx5cZtar6sEdN3TNX8RkYZ1SmW3q6qq+Pnnn/n888+ZNWsWzZs356abbmLcuHGEhzf8OIR1SV9Eci4rt1gZ8NI8sorN/N8lbbmhd5yzQ5Iz1CM/bODrVXu4vlcsz1zaztnhyDnu2wMn9XY7uLkYGdczltsHJhDi435S2zFXWfl9UwY//b2X7s2CuGOgKj+IiIicSa7+cBnLk/N4YGhL7jm/hbPDOaN9u3oPD3+/gaYBnix8eBAmowGb3c7zyft5Oy0LgOsig3mhZRQuSn7JSSq1Wnlm5z4+35cLQKK3B++2iaWNT+NpFGK328kttbC/oIKkzGLe/msHKQeG5WkT6cfjI1vTOyGkVtuati+XB5P2YANGhvpzh38g05an8vP6fY4Ed4iPO9f2iOHaHjGE+am8/bni4LB2AK+O6cgVXaJqv25mdQluG0pA1wVd8xcRaVinPeZzVlYWH374Ic899xxWq5Xhw4dzzz33MHjw4LqKsUHpi0jOZe8v2MULs7YRFejJX/8eqHLKckxzt2Zy8+eraeLvwZJHBqs0mDjNN6vSeOTHjdjtcGmnJjx6UWsi/HUxR0RE5Gx08CJ+0wBPFj08qFY9Blel5LF0Zy4392t2WuV0GxO73c7ItxazeV8Rj1yUyL8GJGCx2bh/2x5+yKwu+TuxWQT3xYbrd7ycltk5hdy/bQ85lVW4GQzcHxfOnTFhuBkb37UES5WN/y1L4Y25OxxjR1/QJpzHhrcmLsT7mOu9k5bFf3ftA6CDzYTntiLW7ylwzO8Y5c+NfZpxUfsI3F1UYeBc9OqfSbz5107cXIx8/69edIgKqPW6SkDXHV3zFxFpWKf1a3DlypU89dRTvPLKK4SFhfHoo48SEhLCyJEjefDBB+sqRhFpAIXllbw3fxcA9w9pqcSzHFef5iF4uprYV1jB5n1Fzg5HzlFfrUxj4g/ViecbesXy+lWdlHgWERE5iw1rF4Gfhwt7C8pZsivnuMtabXZen7Odqz5YxmtztvPczK0NFKXzrU0rYPO+ItxdjFzVLZpSq5UbNu7mh8x8XAzwemI098dFKPEsp21oiD/zzmvFhSF+WOx2Ju/O4PxVSSwvKHF2aCfNzcXILf3iWfDQIMb1jMVkNPDnlkyGvraA52ZuobC80rFsldXG2tQ8rpi32ZF4NiUXkzQ7jfV7CnAxGri0UxOm39GbGXf15bLOTZV4PofdN6Ql5yeGYamycdsXa8gpMdd63cvCA3m3TSxG4OuMPP6dtAeLzXbC9URERJztpHs+Z2Vl8cUXX/DZZ5+xY8cOLr74Ym655RYuvPBCx4nL4sWLGTZsGCUlje/HplpBybnq5T+SeHveTlqE+fD7ff1PenwjOffc+r/V/Lklk3vPb8H9Q1s6Oxw5x0xbkcZj0zcCcGOfOJ4c2UYXUEVERM4BT83YxOfLUhnRIZJ3xnY56jKZRRXc+/XfLE/Oc0wzGODXu/vStol/Q4XqNPd+/Tcz1u1jdNco/nNZW67bkMzqojI8jUY+bRfHoGBd65C6ZbfbmZFVwOM79pJTWd1r+NrIIB5PaEKga+OsOLAjs5hnZ25lwfZsAIK83RjdLYodmSWs2J1HQYIP1ujqHtEuSYVE5FjolRBC74Rgzk8MU2ltqaGoopLL3l5Cck4p5zUL4stbeuB6EuOkT8/M584DPaA9jQY6+3nTM8Cbnv4+dPXzwluNG05I1/xFRBrWSSef3dzcSEhI4KabbmL8+PGEhoYesUxRURGXXnop8+bNq7NAG4q+iORclF1sZsBL8yizWHn/uq4Maxfh7JCkEfhu9R4e+n4DbSL9+O3efs4OR84hXyxP5YmfNgFwU59mPDGytRLPIiIi54gt+4oY/uYiXE0GVjw2hCBvtxrzF2zP5oFv1pFbasHLzcRzl7dj7tYsft2wn/OaBfHNrT3P6t8NWcUV9HnhLyqtdj6/vSdPZ2aztbQCfxcTX3aIp5v/scsHS93L3ZvN9hVb2Je0h6CmIcR2SCAqMRY3D7cTr9wIFVRW8eyu/UzdXz0WdLCrC880b8IV4YGN9u9uflIWz87cys6s6g42dgNUdgjCFuEJdjujXL24t2UTWoT5NNpjlIaxM6uYy95ZSom5ivG943j6krYntf6MrHwe276X3AMNPA4yGaC9jxc9Arzp6e/Nef4+BLs1zkYf9UnX/EVEGtZJJ58XLVpEv35nb5JBX0RyLnr6581MWZpCx+gAfrqjt06YpFbySi10e3Y2NjssnjiIqEAvZ4ck54D/LUvhyRmbAZjQrxmPDVfiWURE5FxzyduL2ZBeyOMjWnNLv3gAKq02XvlzO+8vqB5KqHWkH++M7Ux8qA97C8o5/5X5VFTaeGdsF0Z0iHRm+PXqzbk7eHX2dtokBJLbLoDUCgthbi580zGB1j6ezg7vnFCYXcD25ZvZvmILOXuyjphvcjER2TKauPbxxLSLJyQ67Kz7PbuioISHktLZXlYBwIBAXya3iiLO093JkZ2aKquNr1ftYWlqHuvDXNiFFTeDgXfbxDIyLMDZ4Ukj8ufmDG79Yg0AL13ZgdHdok9qfZvdzo4yMysKSlhRWMryghL2miuPWK6FlzvfdEygyVna0OVU6Jq/iEjDOunk89lOX0RyrknPL2PwywuwWG18eUsP+jQPcXZI0oiMeX8ZK1PyePriNozv08zZ4chZbsqS3Tz9yxYAbusfzyMXJZ51F+pERETkxL5ckcp/pm+iRZgPf97fn32FFdw9bS1r0woAGNczlv+MaI2H6z9lSF+fs53X5+ygaYAncx4YgKfb2VeitNJqo+/kv9hvs+LRN5Iiu41YDze+7ZRAbCNN+jUWpQXFbF+5le3LN5NxYAxgAKPJSGz7BOI6JJCTnkXqxmSKsgtqrOsd4ENMu3jiOiQQ2SIK7wAfjMbal+M9U1lsNt5Ly+bV1AzMNjseRgP3x0Zwe0wobo3s+Cw2G7vKzPw7aQ9ri8rwMhmZ0q4Z/YN8nR2aNEKvzt7Om3N34OZi5LvbetExOuC0trenwlIjGb2jzIyPyUhSv/aYdL7soGv+IiINq1bJ5y5dujB37lwCAwNrtdG+ffvyzTff0LRp09MOsKHpi0jONQ99t57v1qTTOyGYaRN6OjscaWQ+WpjMc79tpU/zYL68Re8fqT+fLt7NM79WJ57/NSCBicNaKfEsIiJyjiquqOS85+ZSXmnl3vNbMGVpCoXllfh6uPDiqA5c1P7Ins3lFivnvzKffYUV3D+kJfcOaeGEyOvXzA37uf23TVR2DcbuYqS1twdfd0wg3N3V2aGdVex2O6X5xeTuzSZnTzYpG3aSvi0VDlxdMxgMRLWOpWXPtjTv2gqPQ3qc2+12CjLzSd24i9SNu0jfmkaVpWavRaPJiE+gL74h/vgG+eMb7Hfg5o9fSPVzV/fG05txd5mZidv3sDC/umx1iKsLA4J8q2+BvmfU+7OoysrO0gp2lJnZUVbBzrIKdpaZSSk3U3Xg/zfQxcSXHePp4qcS9nJqbDY7t36xmjlbs4j09+Dnu/oS6lt3DYRyLVXsKqvgvACfOtvm2UDX/EVEGlatks9Go5G//vqLoKCgWm20d+/ebNiwgfj4+NMOsKHpi0j+v737Do+qTP8//pmSSe89JCGE3nuzICKL2BF/9sZ+FRW7665l3UVhdVdX197XuoqKbUVdC6iIihQFpCcQWgLpCellMjPn90eSgVATSDKT5P26rlxJzpw5c49y8px57nPfT1eSkV+uKU/8IJch/ffGEzQ8uXk3mACNdhRW6tTHvpfVbNKqv/5Oof7eM3GAzuOVH7frwf9tliTdOLGn/nQ6iWcAALq6P36wVh+u2u3+fWhSmJ69dLiSIg6/FMxna7N1y7tr5Odj1nd3TlRCWOdqQz35rRXaEOcjWc0aFRKgt4ekKsyHdT+PR1VZpYr2FKh4d4EK9xSoaHeBivYUyF5Ve9C+8b0S1WfcAPUe3V+BzUz6OOwOZW/N0q7127Vr/TYVZxfKcB15ms5kNmno5NE68aJTZe0g/38Nw9DHeXt1f0a2Cg9Yr7ZfoJ87ET0uLEgBlvatik6rrNYj23O1uqxSeXbHYfcLsJg1JMhfD/dNVL/AzvW3A+2vvKZO5z23VNsLKjWmR4TmXTtWPu38b7+rYc4fANpXs5PPJpNJze3QbTKZtHXrVpLPgJeb9fYqfbkhV1MGxOrlq0Z5Ohx0UJMfX6KM/Ar97byBmtg35oj7RgX5dsoWh2g7+7favmVSL/3hd31IPAMAAK3aVawLXlgmSZp5cg/96fR+slkPnrivcxmqcjoV6mOVYRi6+KXlWrmzWOcOTdDTlw5v77DbzPPp2Zq7O08ym3RCSKDeGpaqQAvX3S1lGIbytmdr89L12rYqXZUlFYfcz2Q2KTwuUhHdohSXmqDeo/srJDrsuF/f5XKpsqRC5UVlKi8qbfgq2+97mWob1lGOTo7V1FnTFJHQcZbOsrtc+rW0Skv2luv74jKtK6/W/jONNpNJY8MCdUp4sKbFhiuxDderrXA49djOXP17d4Gc+wURa7Oqd4CfegX6qVeAr3oH+Kl3gK/ifX34HIJWlZFfoWnPLVVFrUNXj++uOecN8nRInRpz/gDQvpqVfN61a1eLD5yYmChLB/ygw0CErmLd7hKd++xSmUzSV7dNUN841irCsXnkqzS98P22Zu0bFuCjN34/RsOOc00jdA1fbcjRrHmrZRjSrZN66Q4SzwAAYD/fbs5TWICPRnY/fJe2Z3fl6aXdBZrbq5umxYRpY3aZznn2JxmG9MEN4zU6pXkd3rxNpdOptIoabayo1m/lVXonu1gySYnVhn6eOrTDranraWVFpUr7eYPSlq7X3pyiJo+FRocpMjFakYnRiugWrchu0QqPj/RY1fGO37Zq0Sufq7q8Slabj065/HcaeMqwDnmdXFzn0I97y7WkuP5rT+2+FuQmSSeHB+mS+EidERUq/1aqCjUMQwvyS/RARrZyG1qenxkVqhuTY9Qn0E8h1o43l4mOa9GmPM38z6+SpNtO660eUYFyuAw5nC45XIacLkN1TpecLkMOlyE/H4vOH95NEYEdp/W+t2DOHwDaV7OSz10JAxG6iitfXaEftxZq+vBuevziYZ4OBx3YzsJKXf7KChVX2o+4n9NlyO50KS7ET5/ecqJigv3aKUJ0RKt27dVl/16uWodLV4xL1t/OG9QhJ9QAAIDnuAxDU1dt0bryaknShPAgPdwnSf/+Kl3vrszSwIQQfXrzSbKYvfcawzAMZdfWaWNFtTZVVGtjRY02VVRre3WtDpzMsWRV6oMT++qEnh2nEtaT7NW1yvg1TZuXrtfuzfuKLqw2q3qO7Kf+Jw5SfO8k2dqw+vZYVZaU6+uXP1PWxh2SpF6j++m0358pvw7cDtowDG2rrtX3xeX6oqBUP+9XdR5sMWtabLgujovQyJCAY/5csLWyRn/euls/Nqw/neJv00O9E3VaJPN/8Jwnv9miJ7/Z2uz9U6MDNe/asYoP7bjnuycw5w8A7Yvk8wEYiNAVLNtWpEv/vVw+FpO+u3PiEddFA1pLeU2dpj23VNsKKjWqe7jemTnukK0RgZ2FlZr+ws8qrrTrtH4xeunKkbKy/hUAADgGtS6XXsjM15O78lTjMmQzmXRNfKQ+eG+jKqodeuSCwbp4dHK7xlTucOrZzHx9W1Qmu8uQ0zDkaPhyGpJT+7bVuQxVH2YN4AirRclWq5wldqVtKlR/s4++vv3kDnfDnuEyZGqnGwAMw9Duzbu08Ye12rYqTY791vhN7N9d/U8crF6j+snm79su8RwPw2Vo9VfL9fOH38vldCkoIkRTZ01Ttz5Jng6tVeyqrtX7ucWan1us3TX7KqJ7B/jqorgIXRgXoThfn2Ydq9Lp1JM78/RiVoHqDEN+ZpNu7R6rG5Ni5MfnDHiYy2Xome8y9PO2QvlYzLKYTfKxmGQxm2Q1m2Vt+NnHbNYPWwuUU1qjxHB/vXPtOCVHMp/XXMz5A0D7Ivl8AAYidHaGYWj6Cz9rTWaJrhrfXXNZUwbtaFtBhaY9u1TltQ5dMS5ZD04b7OmQ4GWKK+2a/vxS7Syq0uBuoZp//TgF2DzT0hAAAHQeO6trde+W3VpcXC5JipRZZb/mK7bW0Hd/nKgQv+YlsY6Hw2XonZwiPbIjV0V1jqM/oYFZ9fEG2w1ZyutUXVSt4pxKuWqcTfZ76PxBunxs91aO+tgYLkNVZZWqLClXZWmlqkorVVVaoaqyxp8rVdnwe21ljUJjwhXfK1HxvbspvleiIhOjZW7F1uH2Grs2L12ndd+sUnF2oXt7WFyE+p80RP3GD1JIVGirvV57ytuRrS9f+ESleXtlMpk05ryTNObck2TuJElVl2Ho55IKvZdTrP8VlLhvxjBL6h3opygfq6JtVkXZrIrysSrK5lP/u0/9tvXl1bo/Y4+7pffvIkP0YO9u6t4BbjAADrR7b5WueGWFdhZVKS7ET29fO1a9YoI8HVaHwJw/ALQvks8HYCBCZ/fNpjxd+59f5edj1g9/OlUxIbQ+Rvv6Li1P17z5qwxDenj6YF0ypn0rTeC9auqcuuzfy7U6s0Tdwvz135tOoD07AABoNYZh6LOCUs3euse91qs5p0ozQkP197MGtulrf19cpgcyspVWWSNJ6hXgqz+kxCnWZpXVZJLVZJLZZJLVJO2ttOv7zfn6dlOedhRWylTrlMl18DFtFrMSw/2VFBGgAQkhumNyn3brLFRbXauyghKVF5epoqis/ntx/ffyojJV7i2X0+E8+oEOw+ZnU1zPborvnaj4XomK65kg34CWXxfuzS3Sum9WadNP62SvrpUk+fjZ1G/8IA04eYhiUxM6XKX4odira/X92wu1+ad1kqT43ok6/frzFBod5tnAWlm5w6nP8ks0P7dYK0orW/TcJD+bHurdTVM66E0GQKP8shpd/soKbc2vUGSgTW9dM1YDEpjDPhrm/AGgfZF8PgADETozl8vQmU//qLTccs2a2FN3T+3n6ZDQRT3z7Vb9a9EW2SxmvXf9OI1IDvd0SPAwp8vQTfNW66uNuQrxs+rjG09Qr5hgT4cFAAA6oXKHU//ckaNXdhfWr5tc59IfkmN0Z99usrRyIjK9skZzMvbou4aK63CrRXf2iNPVCVHy2a/VdGWtQ19vzNXHq/do6bZCNc7U2KxmDUwIUfeIACVHBCip4Ss5IkCxIX7tul614TKUtXmn1n27StvXbJFxmHbgbiYpICRQgaFBCggNVEDj9ybbAuUb4Kei3QXKyditnK27lbttj+w19oOOFR4XqYiEKIXHRyoiPlLhDV8HJqUNl6Gd6zK09ptftWv9dvf2sLgIDZ08Sv1PGiLfTlr1mr5so75780vZq2tlMpmU0DdJvUb1U6+RfRUU0bnmuLJq7NpRVavCOocK7XUqtDsafq7/XmCv324ymXR9YrRu6R6rgE5SDQ4UV9p15asrtDG7TCF+Vr35f2M0nHmVI2LOHwDaV4uTz6mpqfrll18UGRnZZHtJSYlGjBih7du3H+aZ7ee5557To48+qtzcXA0dOlTPPPOMxowZ06znMhChM/tkzR7dPv83BftZ9dNdkxQa0Pat5YBDcbkM3diQaIwJ9tXnt5xEFX4X97fPN+nVn3bIZjHrrWvGaGxq5NGfBAAAcBzWlVfpwqVpKvWtT0hZTFKo1aJwq1VhPhaFWa0K97EozMdSv93HqnCrRTE2H8X4+ijGZlWY1XLIytkiu0OP7szVW9mFchqS1SRd0y1ad6TEKsynfkkRp8vQsm1F+nj1bn21MVdV9n2VwmNSIjR9RDedMTheof6e/dxWU1mtzT+t17rvVqkkt9i93T84QMERIQqKDKn/HhHS5PfAsCBZrJYWv57L5dovGb1HORm7VZq/97D7B4YF1Sei4yLlH+yv9GUbVVpQUv+gSeoxtJeGTh6t5IE92m1taU8qLSjRN6/9T7s37WyyPb5XN/Ua3V+9RvZVSCeriD4Sl2HI3Amq24EDlVbX6fevr9TqzBIF2ix6bcZoPkcfAXP+ANC+Wpx8NpvNys3NVUxMTJPteXl5Sk5OVm1tbasG2FLz58/XVVddpRdffFFjx47Vk08+qQ8++EDp6ekHxXwoDETorOqcLp32ryXKLK7Sn07vq5tO7eXpkNDFVdQ6dP5zS7U1v0IjksP07nXj5HsMk1Po+F5fukNzPtskSXrqkmE6b1g3D0cEAAC6iq355Zr84SrV9gqRfFpeFWkzmRRtsyrG5qMwi1nlpbXKLKhUYZhVroYW2CEldeqWU6tApyGLySSLuf4rq7hauWU17mOlRAbo/OGJOn94NyVHBrTaezxWeTtytP67VUpfvlEOe/0a1TY/m/qfNESDJ41QZLfodoulsqRChVn52ptTpOKcQu3NKdLenCJVllQccn/fAD8NnDBUQ04bqdCYrlkNWFZQooxV6cr4JU05GbubPBaTEldfET26n8LjSFahczMMQ9XlVSorLFV5Ualk1HdCCI+LkNXWsYsyKmsdmvmfX/XztiL5+Zj10pWjdEqf9vvb3JEw5w8A7avZyedPP/1UkjRt2jS9+eabCg3dt0aK0+nUt99+q0WLFik9Pb1tIm2msWPHavTo0Xr22Wcl1d8xm5SUpFtuuUX33HPPUZ/PQNT2Sqvq5DIMmUySSSbJpIafJZPJJJMki9kkPx+SUK3p7eW79JdPNigqyFc/3DVRATarp0MCtLOwUuc++5PKahy6dEyy/jF9sKdDQjv7emOubnh7lQxDumtqX904kRtjAABA+3rof5v08k87ZPI1q39SmEb0ilTfpDBZ/S0qqXOqpM6hEodTJQ6niuwO5dvrVGCv33YkpjK7rOmlshTbD7tPiJ9V5wxN0PQRiRqRHObx9Ycd9jptXblZa79dpbzt2e7tUUkxGnLaSPUdP0g2P5sHI2yqtrrWnYjem1Oo8qJydeubpL7jB8nHt2MnlVpTRXGZtq1KV8av6dqTnqn9pwJDosOUPCBFSQN7KLF/dwWEBHowUqDlDMNQVVmlSnKL6xPMDUnmsqIylRfV/9x4A00TJikkMrShhX+UwuMjFBFf39o/IDRQJpNJLqdL9ppa1dXUNXy3y15jl726VnW1dTJbzO6OD0FhwTJ7oLV7TZ1TN85bre/S8mWzmPXMZcN1+sC4do/D2zHnDwDtq9nJZ7O5fvA0mUw68Ck+Pj5KSUnRv/71L5199tmtH2Uz2e12BQQE6MMPP9S0adPc26+++mqVlJRowYIFBz2ntra2SbV2WVmZkpKSGIjaQJ3TpVlvr9I3m/OPuq/ZJF0yJll/O29Qu65h1VntKqrUBS8sU2FFreacO1BXn5Di6ZAAt+/T8/X7N36RYUgPnT9Il4/t7umQPM7pMnTre2vkchl67rIRMnfSv4OrM/fq0peXq9bh0mVjk/XQtEEen3AFAACdS/aWLKUv36gTLpgo38BDL/NSXlOnG+et1o9bC5ts7xcXrNMHxun0gXHqHx/c5DolI79C767K1Mcbc1VU55Dha5FhMysuJlDJ8cEaHxGkCQEBklF/bec0DDlchlyufd8DfK0alxrh8e4/LpdLuzfvUtrPG7RtVbrs1fVzJGaLWb3H9NeQSSMV3zuR67ROoqqs0p2I3r15p1xOV5PHo5JjlDSgh5IGpKhb32SvutkAXZvD7lBJfrH25hRrb05h/ffcIu3NLZK96iidOE1SYGiQQqLqi6mKc4pUW1lz2N19fH3kchly1h0iaX24lzCZFBgWdNASBEHhwTI3dMJoLMJpeIL7R5lMCgoPVlRSzDH9rbU7XLp9/hp9sT5XFrNJj180lI5iByD5DADtq8Vtt3v06KFffvlFUVFRbRXTMcvOzla3bt30888/a/z48e7td911l5YsWaIVK1Yc9JwHHnhAc+bMOWg7A1Hr+/sXm/XyDy1bE/zsIfF64uJh8vHAnYOdxbaCCl327+XKK6tV75ggfX7rSR6f3AAO9NziDD36dbp8LCa9O3OcRqVEeDokj/p49W794f21kqSvbj9Z/eI633hUWevQKY8uVmGFXaf2jda/rxolK3/rAQBAKzJchub99RUV7c5XQGigTr50svqOG3jYif3skmot3JirrzfmaeXOYjld+6ZLkiMCNGVArLpHBuiT37K1ate+NYijgmyaPiJRF45MVO/Y4DZ/X63BMAzl78xV+rIN2rJiU5P21cFRoRo8cbgGnjKMKthOzl5dqz1bspS1cYeyNu1UYVbTYgGzxay4nt3UZ9wADTl1ZJdYMxveoaaiWnk7cpS3I1t5O3JUmJWvssIS6XCz2CYpJCpMIdFhCokMUXBkqEKiQhUcWf8VFBEsq8++DoCNrbj3dU4oUnHD97KCkoMKryxWi3x8bfLxt8nmV//l42uT0+FUeXGZKorLDrqR41gEhAaq++CeShnSU8mDesgv0L/Zz3U4Xbrro3X6ePUemUzSgptO1JDEsOOOqbMg+QwA7avFyef91dTUyM/v0HcOe8KxJJ+pfG4fX22ob6sqSS9cPkK/GxArQ5JhSEbDlWPjv0TDqK+EvPW9NapzGpoyIFbPXDachOkxSM8t1+WvrFBhRa36xAbp7WvHKibYe85ZoJFhGLrpndX6Yn2uooN99dnNJykutGv+W611OHXav5Zo995qSdLD0wfrkjHJHo6q9X2xPkc3zlutbmH+WnjHBAX6shQAAABofVmbd2rxm19pb06RJClpQIpOvXrqUde53Vtp1zeb8/T1xjz9uLVAtY6mSQWL2aRT+8boolGJOrVfTIe5Ybo0f6/Slm1Q+rKN7v8mkuQb6KfeY/qr3/hBSuidRJKxi6oqq9TuzbuU2ZCMLisocT+W2L+7psw8V8GRzJWhddXV2pW/M7c+2by9Ptlcmr/3kPvaAnwVHhdZ/5XQ8D0+QmExEbK20vJyjjqHyotKZbFYGpLNvrIcZU7ScNW3/m5MRJcXl6miqP57ZUmFDJerYd5zvznQholQQ5JchvbmFqmuts59TJPJpLie3ZQypKe6D+mpmO5xR/3b7HIZmv3pBtksFv317P50rNgPyWcAaF8tTj67XC499NBDevHFF5WXl6ctW7YoNTVVf/3rX5WSkqJrrrmmrWI9qmNpu30gBqLWt6uoUmc//ZPKax269qQe+svZA5r1vMVp+br+7VWyO1ya2DdaL14xknWgW2DDnlJd+eoK7a2q04D4EL197VhFBNIuC96rstahC174WWm55eofH6L3Zo5TaEDXW6ft9aU7NOezTe7fLxmdpIcvGOLBiNrGne+v1Uerd2vmyT1031nNGxcAAACOhaPOodVfLtfKT5fKWeeQxWrRyLPGa/TZJzYrWVFld2hJeoG+3pir3XurNXlArKYP76aYkI5zs2Rp/l4t/Pdnyt6S5d5m8bEqdXhv9Rs/SN2H9DxqcgVdT2lBibb9mqZlH/8gh71OtgBfTbr6DPUdN9DToaGDcjqcKszKd1c0523PUfGegoMqjSUpNCZcsakJiu0Rr5jucQpPiFRASGCnTag66hzK3pKlXeu2aee6bSrObroUREBooLoPSlW3ft3VrW+SQmPCD/nfovG/ZWf973SsmPMHgPbV4uTz3Llz9eabb2ru3LmaOXOmNmzYoNTUVM2fP19PPvmkli1b1laxNsvYsWM1ZswYPfPMM5Lqk+XJycm6+eabdc899xz1+QxEraumzqnpz/+sTTllGtk9XO9dN65Fd4T/tLVQ1/7nF9XUuXRCz0i9cvUoBbTSnYyd2ZrMvbrqtZUqr3FoaFKY/vP7MV0yiYeOJ7OoStNf+FmFFbUanhymt64Zq6AuVBFbUevQKf9crKLK+lbUi9ML1C8uWF/dPsHTobUqp8vQmIe+UVGlXe/OHKfxPY9ceQQAANAaSvP3avF/vtKu9fXLQYXGhuvUK6eq++BUD0fWtgqz8vXfR99RVWmlTCaTkgakqO8Jg9RzZF/5+vt6Ojx0AHtzi/X1SwuUtz1bktR3/CCdeuXph11HHZDqq4H35ha5q5nzdmSrIDNPzjrnQfsGhgW5E82xPeq/+wU1v+V0Z1RWWKpd6+sT0Vmbdqquxt7k8cCwICX0TlJC3yR165OkyKQYmc0dowuHJzDnDwDtq8XJ5169eumll17SaaedpuDgYK1du1apqalKS0vT+PHjtXfvoduitJf58+fr6quv1ksvvaQxY8boySef1Pvvv6+0tDTFxsYe9fkMRK3r3o/X6d2VWYoMtOl/t558TG10V+4o1u9fX6lKu1OjU8L12ozRCvYjkXo4/PdCR5eWW6ZLXl6ukqo6jU+N1Ou/H92huh4YhnHMdxg/+c0WPfnNVqVGBeqta8fqxIe/k9kkrX/g9E7Vlnp15l5Nf/5nBftZtfqvv+swbSoBAEDHZxiGMn5N05K3F7rXOe4zdoAmXDZZgWEdY73mlsjeulufPj5ftVU1ikqK0Tl3XKSQyFBPh4UOyOlw6pfPlmrlgp9kGIaCIkJ0+nXnKrF/d0+HBi9RW1Wj3G3Zyt6apZytu5W3PVv2AxKmkuQb4FefZE7dl2gOimAO9kicDqeyt2Ypc/0O7dmSqfwdOXI6mibxbQG+iu+VqG59kpTQN1lxqQl0tNgPc/4A0L5aPJO9Z88e9erV66DtLpdLdXV1h3hG+7r44otVUFCg2bNnKzc3V8OGDdNXX33VrMQzWteHq3br3ZVZMpmkpy4Zfszrt47pEaG3rh2rq19bqV927tUVr66kkvcwlmYU6to3f1V1nZNKcXRY/eJC9Obvx+iyfy/Xsu1Fumnear145UivT1DaHS5d9u/lKqyo1fzrxyu2hW0YCytq9e8f6qtw7pzSV93C/BUf6qec0hqt213aqaqDv92cJ0k6pU+01/9/BQAAnYvJZFLv0f2VPChVyz9eorWLftWWFZu0c902DZo4XAm9ExXXM6FTJKJ3rd+mz5/+SA57neJ7JercP1wkv8CuXUmIY2exWjTu/AnqPjhVX7+4QKUFJfrokbc18ozxGjd9gqw+zD10JYZhqKywVDlbd7uTzYW78xuXNHaz2qyK7h5Xn2RuSDaHxR66XTQOz2K1KKl/ipL6p0iSHPY65W3P0Z70TO3ZkqWcjN2yV9Vq17pt2rVumyTpmidvVVB4xx/LAAAdU4srn0eOHKk77rhDV1xxRZPK57lz52rRokX68ccf2yrWdsFdUK0jLbdM055bqpo6l+6Y3Ee3Te593MdkDeMjY41sdDbLtxfp6tdWqtbh0tlD4vXUJcNlMXvvB9SXlmzTP75MkySNSA7Te9eNl83a/MTqnM826vWlOzW4W6g+vflEmUwmzXp7lb7ckKt7zuinG07p2Vaht7upT/6gtNxyPXnxME0b3s3T4QAAgC4sf2eOvnvjS+XtyGmyPSgiRPE9uymuZ4LienZTTEqcrLaOcwP0lhWb9PVLC+RyutR9cKrOuuUC+fjy+Rmtw15dqx/eWaSNP6yVJEUnx+r0689TZGK0hyPDsXA5XSrJK1bRngKVF5XJ6XDK5XDK6XDIWeeU07HfV51DdbV25e/MdXeP2F9IdJgSeicqvlei4nt1U2RijMzccNzmXE6XCjLzlL0lS3u2ZKpyb4Uunj3D02F5Feb8AaB9tTj5vGDBAl199dW69957NXfuXM2ZM0fp6en6z3/+o88//1y/+93v2irWdsFAdLCiilqFBdianfQpr6nTec8u1fbCSk3oE603ZoyWuZUSRmm5ZbrilRUqrLCrT2yQ3r52rGKCvXuNIZfLUJ3LJbvDpTqn0fDdJavFpPjQ1rnr/KsNubrl3dWqcxr63YBYPXvZcPnSWgedwPfp+Zr5n19V5zR00ahEPTx9SKv9PWlNOaXVOu1fS1Rld8pqNsnhMnT52GQ9dP7gZj0/q7hKp/1riexOl96+ZqxO6h0laV9Ce+rAOL145ci2fAvtZk9Jtbud+Kq//E7h3EQEAAA8zOVyaevKzdq9aadyt2eraHeBDpwqMVvMikqMUUxKnIIiQhQYFqSA0MCG70EKCAk8antTw2WortYue3Wt7DV21dXWyXC55HK65Gr43vR3QzIMRXePVVhsRLPfz/rFq/Xdm19KRn1L8SnXnUvrVbSJjF/T9O3rX6imoloWq0WJA1KU1L+7EvunKLp7LOvPehnDMFReXKairHwV7SlQ0e4CFe7O197sooNaODeH2WJWTEpcfaK5d5ISenfrFF0j0Dkx5w8A7avFyWdJ+vHHHzV37lytXbtWFRUVGjFihGbPnq0pU6a0RYztioHoYDP/86vWZJbo7CHxOmdovEYkH749jmEYuvndNfrfuhzFh/rpf7ee3OrVyRn5Fbr8leXKK6tVz+hA/e/Wk72mwtfhdOnej9dr4aY81TnrE84O1+FPsbnnDdRV41OO6zVXbC/SZa+skNNl6Owh8Xri4mG0sUWn8uX6HN30zmq5DGnGCSm6/5wBXtei66Z5q/W/9Tka2T1cN53aU9e8+asMQ3p4+mBdMib5qM//w/u/6ePVe3RSryi9fe1Y9/YV24t08cvLFRfip+V/Pq0t30K7eWv5Lv31kw0anRKuD244wdPhAAAAHMReY1f+jhzlbt+j3Iw9yt2efcgKvwP5BwcoIDRQAaFBkmG4k8z26lrV1dgPufZpc8X2iFffEwapz5gBCgwLOuQ+hmHo1/8t088fLJYkDZ40QhOvPJ0EINpUZUm5Fr3yuXat395ku2+An7r1S1Zi/+5K7NddUYkxMnnhjcQdTVVZZX3iOKtARbvrk8gVe8slk0lmk0kym2Q2m2UymWQym+q/N3x+Ls3fe9i/Q1abjyIToxUaHSarzSqL1SqLj0UWa+OXVWarRRYfi6w+VkUkRCm2R3yH6giBro05fwBoX8eUfO7MGIiasjtcOumR75RfXuve1i3MX2cPjdc5QxI0MCGkSRLojaU79MBnm2Q1m/T+DeM1Ijm8TeLaVVSpac8t1d6qOs27dqxO7BXVJq/TUo9+nabnFm874j4Ws0kmSQ6XoXOHJujpS4cf12s+8OlGvfHzTk3uH6OXrhzl1W2JgWP10arduvOD+pZut0zqpTun9PVwRPv8sKVAV722UmaT9PktJ2tAQoie/W6rHlu4RTaLWe9dP+6IfwvTcst0xlM/yjCkT28+UUMSw9yPVdkdGnT/13IZ0vJ7T1NcqHd3emiOGa+v1PfpBbp7aj/Nmth5WokDAIDOyzAMVRSXK3fbHhXuzldVSYUqSytUWVqpqpIKVZVVyuV0Nft4JrNJNn9f+fj6yGyxyGw2y2wxy2Q2y2wx1X9v2OZyOpW3I0dGw03NJpNJiQNS1HfcQPUa1Ve+AX7uGH+a/51Wf7lckjTm3BM1bvopXnfTJjonwzBUmJWvrE07tXvzLu1Jz5S9urbJPv7BAerWL1lJA1LUfVCqQmPaZr6oM3A6nKosrVB5UZn2ZhfWVyg3VCpXl1Ue17HNFrPC4yMV2S1akYnRikqMUWRitEKiwrg5AJ0ac/4A0L6sng4A3s1mNeunuydpaUahPlubra835mpPSbVeWrJdLy3ZrtToQJ0zJEHnDE1QWU2dHvpisyTpvrP6t1niWZK6RwZqfM9IfbE+VxuzS70i+bxkS4E78fzw9ME6oWeUfKwm2Sxm+VjN9d8tZlnMJi34bY9ue+83FZTXHuWoR9d4jBN7RZF4Rqd1wchEVdkd+uuCjXrmuwwF+lq9Yg3kWodTD3y6UZJ09QkpGpBQ/wHmplN7acOeMn21MVez3l6lz2456bBLBDz6VboMQzprcHyTxLMkBdis6hMbrLTccv2WtVdTQ+Pb9P20tSq7Qz9vK5IkndY/xsPRAAAANI/JZFJwZIiCI0PUe0z/gx43XIZqKqtV2ZCUriqtlMlkks3fJpufb/13f1/5+Nnk6+8ri4+1RUnhqrJKbV25WenLNionY7eyNu5Q1sYdWvyfL9VjaG/1HT9QO9dmuNffPfnSyRoxdexRjgq0HpPJpOjkWEUnx2rE1LFyOV3K35Wr3Zsbk9FZqi6vUsYvacr4JU2SFBoTruSBPZQ8qIeS+qfIN7Dj32jbXHW1dSrIzFNFcZkqistUXlymiuLyhu9lqiqtPKj1v5tJCo0OV2RitDuBHBodJqn+JgCXy5BcRsPPLhmGIaPh9+DIEIXHRdKGHwAAtLkWJ5/Dww/dctlkMsnPz0+9evXSjBkz9Pvf/75VAoTn2axmndovRqf2i1FNnVOL0/L12bpsfbs5X9sLKvXUt1v11LdbZbOaVec0dNbgeM04IaXN4xoQH6Iv1udqU3ZZm7/W0eSUVuuO+b9Jkq4Yl3zUNrvRQb6SpIKK1ks+Rwf7HvexAG925fgUVdqdevjLND38ZZr8fSy6uh3+1hzJKz/u0PbCSkUH++qO3/VxbzeZTHrsoqHKeK5CGfkVumneas27dpxs1qYtD3/ZWaxv0/JlMZt055Q+Bx5ekjQ8OUxpueVak1WiqYM6dvJ5aUaR7A6XkiL81Tvm0O0iAQAAOhqT2ST/4AD5BwcoKqn1b7ALCAnU0MmjNHTyKJUWlCh9+Ual/7xBxdmFyvg1TRm/1ifzTCaTJl9zlgacPLTVYwBawmwxKy41QXGpCRp11glyOpzK256trE07lblxh3K37VFp/l6tz9+r9YtXy2Q2KS41QcmDUpU8KFVxqQkyd7LlxKrLq7Tjt63atnqLMjdsl8PuOOL+ZotZQeHBTaqUIxOjFZEQJR/f1l3eDgAAoLW1OPk8e/ZsPfTQQzrjjDM0ZswYSdLKlSv11Vdf6aabbtKOHTs0a9YsORwOzZw5s9UDhmf5+Vh0xuB4nTE4XuU1dfpmc54+W5ujH7YUyO5wqUdUoB6+YHC7tPYamBAqSdro4eSzw+nSre+uUXGlXQMTQvSXswYc9TlRDYniwlZIPjceIyqI5DM6vxtO6amKGoeeXZyh+z/dqK825OqPp/fVyO7t37Itq7hKz3y3VZJ035n9FeLXdK2rIF+rXr5ypM57dql+2blXD/5vk+aeN8j9uGEYeuTL+onCi0YlKTX60MnYYUlhendlln7LLGmbN9KOvkvLkySd1i+WFpAAAADHIDQ6TGPOOVGjzz5BhVn5Sl+2UenLN6qmolpTbzhPPUd6z/I0QCOL1aKEPklK6JOksdNOlr26VrvTdilzww5lbtyhvTlFysnYo5yMPVrxyY/y8bO520FHJUYrMjFGkUnR8g8K8PRbaZGyghJtW71F21anKzs9q0k1c2BYkEJjwhUUEaLgiBAFRQS7vwdFhCggOJA22AAAoMNqcfL5p59+0oMPPqgbbrihyfaXXnpJCxcu1EcffaQhQ4bo6aefJvncyQX7+ej84Yk6f3ii9lba9fO2Io3uEa7gAxIwbaWxve22ggrV1Dnl5+OZtkH/WrRFv+zcqyBfq567bESz4misfC6pqpPd4TqoGrIlqHxGV3PnlD6yWkx6fvE2LdtepAte+FmT+sXozil93DeltIe/fb5JNXUuje0RofOGJRxyn9ToID15yTBd8+av+s+yXRrULVQXjUqSJH2Xlq9fd+2Vr9Ws207rfdjXGZZUn1hfv6dUTpfRYdvru1yGvt2cL0ma1I+W2wAAAMdj/zbHJ154qpxOp6w+rKyGjsHm76vU4X2UOry++1NZYakyN2xX5sYdytq4UzWV1crJ2K2cjN1NnhcQGuhOSkcmxig0OkwBoYHyDwmQX4B/qydrayqqVZxTpL05hdqbU6SKvRXysVll9bXJ5udT/93XRz5+Nvn42urXcbdalL0lS9tXb1FBZl6T40V3j1XPEX2VOqKPopJiuCEXAAB0Wi3+ZPL111/rkUceOWj7aaedpjvvvFOSdOaZZ+qee+45/ujQYYQH2nTWkPZtBxsT7KvIQJuKKu1Kzy3X0KSwdn19SVqcnq8Xvq9f5/mRC4YoJSqwWc8L9feRj8WkOqehospaxYf6H9Pr19Q5VV5b36qJ5DO6CpPJpNsn99GFo5L0zLdb9cGq3fouLV/fpeXrrMHxuuN3fdSrjVs6L07L18JNebKaTfrbtEFHnDQ4rX+s7pjcR098s0V/+WSD+sYGa1C3UP3zq3RJ0u9P7KG40MOvb9YrJkiBNosq7U5tzS9Xv7iQVn8/7WFjdpnyy2sVaLNobGqEp8MBAADoNExmk6xmEs/ouEKiQjVo4nANmjhcLpdLxXsKVbS7QEV78lWYVaCiPQUqKyhRVWmlMkvrq6UP1Nj+PiA0UAHBgfIPCVRASID8ggNk9bHKarM2fPeRxcciq4+PrD5WWWxWWawWVZZUqDi7Psm8N6dIxTlFqi6rPK73ZTKZ1K1vslJH9lHP4X0U0rA2MwAAQGfX4k8nERER+uyzz3THHXc02f7ZZ58pIqJ+MrmyslLBwcGtEyFwGCaTSQMSQvTj1kJtzC5r9+RzTmm1/tCwzvNV47u3KPluNpsUGeir3LIaFZQfe/K5serZZjUr2JfJBnQt3cL89fAFQ3T9KT315Ddb9OnabP1vfY6+3JCj84cn6vbJvZUU0fpt2WrqnLr/042SpP87qYf6xB59vLtlUi9tyC7Vok15uuHtVfr9iSlKzytXiJ9Vs07pecTnWswmDUkM07LtRfots6TDJp+/bWi5fXLvaPlaPdOpAgAAAIB3M5vNikqKaVg/faB7u726VsXZhSrcXaCi3fkq2l2gir3lqiqrVG1ljQyXoarSSlWVHl/C+EBBESGKiI9UeEKkgiNC5axzqK62TnW1dtlr7HLU1slea1ddw8919jqFx0eq54g+6jGst/yDO1arcAAAgNbQ4mzVX//6V82aNUuLFy92r/n8yy+/6IsvvtCLL74oSVq0aJFOOeWU1o0UOITG5POmnNJ2fd06p0u3vLNGe6vqNKhbiO47q3+LjxEdvC/5fKwKGtZ7jg7ypV0TuqweUYF66pLhmjWxpx5fuEULN+Xpo9W7teC3Pbp4dJJGp0QowGZRoK/V/d3fZ9/vvlZzi86fF5dsU2ZxlWJDfHXrEdpl789sNunxi4bqvOeWantBpf7+Rf1az7Mm9lJowNGXKhiW3JB8zirRJWOSmx2rN/kuraHldn9abgMAAABoGZu/r+J6dlNcz24HPeZ0OFVdXqXqskpVlVWqqqzx5ypVV1TJWeeQw+6Qo84hZ8N3R12dnHVOOex1ctQ5FRAcoPD4SIXHRyoiIcr9s83P5oF3CwAA0LG1OPk8c+ZMDRgwQM8++6w+/vhjSVLfvn21ZMkSnXDCCZLkbr8NtLUB8fUVgBuzy9r1df+1cIt+3bVXwQ3rPB9LFV9UUP0HmMKK40g+s94z4NYvLkQvXzVKa7NK9NjCdP24tVDzVmRq3orMIz7PYjYpKdxf04Z30/8bmajE8MPfmZ5ZVKXnG1rt//XsAQpqQceBYD8fvXzlKE17bqkqah2KDfHVjBNSmvXcYQ2dHX7LKmn263mTvLIardtdf5PQqX1JPgMAAABoPRarRUHhwQoKpwsjAACAN2hR8rmurk7XX3+9/vrXv+rdd99tq5iAZhuYECpJSsspl9NlyGJu++rf79Ly9OKS+uTTP//fEHWPbN46zwdqTBgfT+VzY+I6KojkM9BoaFKY3rpmrFZsL9LbKzJVXFmrKrtTVbVOVdodqrI7VVnrUK3DJUlyugztLKrSk99s1VPfbtUJPSN10agknT4wTn4++24sMQxDD3y2UXaHSyf1itJZg1u+zn2vmCA9c9lw/e2zTbpraj/525p340pj8nlLXrkqax0K7GBt9hc3VD0PTQrjZhkAAAAAAAAA6MRaNHvt4+Ojjz76SH/961/bKh6gRXpEBcrfx6LqOqd2FlWqZ3RQm75edkm1/vD+WknSjBNSdMYxJJ8aNSZgCivsx3wMKp+BwxubGqmxqZGHfdzpMlRld6iy1qnl24v0waosLc0ocn8F+1l17tAEXTQqSUMSQ/XN5nx9l5YvH4tJc84beMyt7k/tG9Pi6t/YED/Fh/opp7S+gnh8z8O/L2/0bUPy+bR+VD0DAAAAAAAAQGdmbukTpk2bpk8++aQNQgFazmI2qV98fVultm69Xed06ZZ316ikqk5DEkN175n9jut4jdXKx7XmM8ln4JhZzCYF+/koLtRP04Z307xrx+nHu07V7ZN7q1uYv8prHJq3IlPnPbdUU5/8UX/5ZL0kaebJqW1+o8uhdNTW2zV1Tv20tVCSdBrrPQMAAAAAAABAp9bivp29e/fW3LlztXTpUo0cOVKBgU1bDt96662tFhzQHAPiQ7Qms0Sbsst07tCENnudZ77L0KpdexXsZ9Wzlx7bOs/7a82229EN60cDOD5JEQG6fXIf3Tqpt5ZtL9IHv2bpyw25Ss8rlyR1C/PXzZN6eSS2YUlh+nJDrn7L2uuR1z9Wy7YXqbrOqbgQPw2ID/F0OAAAAAAAAACANtTi5POrr76qsLAwrVq1SqtWrWrymMlkIvmMdjcgoT6ZsTG7tM1eY2N2qZ5fnCFJ+vv5g5UcGXDcx2ysfG5MIB8LKp+BtmE2m3Riryid2CtKc6rr9Pm6bP20tVDXnpyqAJtn1lturHxem9V2f+vawneb61tuT+ofc8ytygEAAAAAAAAAHUOLZ9B37NjRFnEAx2xgQqgkaVN2mQzDaPXkRp3TpT9+sE4Ol6EzBsXpnFaqrm6NyueCCpLPQFsL9ffR5WO76/Kx3T0ax+DEUFnMJuWW1Si3tEZxoX4ejac5DMPQd6z3DAAAAAAAAABdRovXfAa8Td/YYJlNUlGl/bgSuYfz/OJt2pxTpvAAH809b1CrHbcxYVxe61BNnbPFzzcMQ4Xldkn7qqgBdF4BNqv6xNavcd9RWm+n55VrT0m1/HzMOrFXlKfDAQAAAAAAAAC0sWPqHbp79259+umnyszMlN1ub/LY448/3iqBAc3lb7MoNTpIGfkV2phdppiQ1qsGTMst07OLt0qSHjh3YKtWGAf7WmWzmmV3uFRQXqukiJa18q60O1XdkLQm+Qx0DcOSwrQ5p0xrsko0dVC8p8M5qm8bWm6f2DNKfj4WD0cDAAAAAAAAAGhrLU4+f/vttzr33HOVmpqqtLQ0DRo0SDt37pRhGBoxYkRbxAgc1cCEEGXkV2hTTplObaXWrvXttteqzmnodwNidW4rtdtuZDKZFB3kqz0l1SqoaHnyubHKO9BmUaCvZ9agBdC+hiWF6t2V0m+ZJZ4OpVm+3ZwnqX69ZwAAAAAAAABA59fittv33nuv/vjHP2r9+vXy8/PTRx99pKysLJ1yyim68MIL2yJG4KgGxIdIkjZml7baMV/+Ybs27ClTqL+PHpo2qNXXkpakqIZK6sJjaBde2LDecxTrPQNdxrCkcEnS+j2lcroMD0dzZEUVtVqTVSJJmsR6zwAAAAAAAADQJbQ4+bx582ZdddVVkiSr1arq6moFBQVp7ty5euSRR1o9QKA5BiaESpI2ZZe1yvG25JXrqW/q223PPntAq7by3l90Q7vsgoqWJ58bK5+jabkNdBm9YoIUaLOoyu7UlrxyT4dzRIvTC2QY9TcHxYf6ezocAAAAAAAAAEA7aHHyOTAw0L3Oc3x8vLZt2+Z+rLCwsPUiA1qgf3ywJGlnUZUqah3HdSyH06U/fbhOdqdLk/rFaPqIbq0R4iFFuyuf7UfZ82Du5DOVz0CXYTGbNCQxTJL0W0NVsbf6Lq2+5fZkWm4DAAAAAAAAQJfR7OTz3LlzVVlZqXHjxumnn36SJJ155pm688479dBDD+n//u//NG7cuDYLFDiSyCBfxTVUJ2/OOb7q51d+2qG1WSUK9rPq7+cPbpN2242ig2ySpIKKmhY/1912m8pnoEsZlhwmSVrrxclnu8OlH7bU35A2qX+sh6MBAAAAAAAAALSXZief58yZo8rKSj3++OMaO3ase9tpp52m+fPnKyUlRa+++mqbBQoczcCE+nWfj6f1dkZ+hR5ftEWS9NezBigutG3abTdqrFouOIY1n6l8BrqmYUlhkry78vmXncWqqHUoKsimId1CPR0OAAAAAAAAAKCdWJu7o2EYkqTU1FT3tsDAQL344outHxVwDAYkhOjbtHxtzC49puc7XYbu+nCt7A6XJvSJ1oWjEls5woM1Vi0XVtB2G0DzDG9IPm/JK1dlrUOBvs0eytvN9+n5kqRT+8bIbG677hEAAAAAAAAAAO/SojWf27L98JHs3LlT11xzjXr06CF/f3/17NlT999/v3vt6Ubr1q3TySefLD8/PyUlJemf//ynR+KFZ7grn4+x7fbrS3dodWaJgnyt+sf0tm233eh4Kp9puw10TTEhfkoI9ZPLkNbtPrabbdpaWm65JGlUSriHIwEAAAAAAAAAtKcWlUv16dPnqAm54uLi4wroUNLS0uRyufTSSy+pV69e2rBhg2bOnKnKyko99thjkqSysjJNmTJFkydP1osvvqj169fr//7v/xQWFqbrrruu1WOC9xkQX9/adUtuheqcLvlYmn9vxY7CSj36dbok6c9n9le3MP82ifFAjcnnxkRyS1D5DHRdQ5PClF2aq9+ySjS+Z6SnwznIzqJKSVKPqCAPRwIAAAAAAAAAaE8tSj7PmTNHoaHtv3bj1KlTNXXqVPfvqampSk9P1wsvvOBOPs+bN092u12vvfaabDabBg4cqN9++02PP/74EZPPtbW1qq3dl/grKzv29YLhWYnh/gr2taq81qGM/Ar1jw9p9nP//PF61TpcOrFXpC4dk9SGUTbVWLVcZXe2qH2uYRjuVt0kn4GuZ1hSmL7ckKvfsvZ6OpSD1Dqc2r23WpLUIyrQw9EAAAAAAAAAANpTi5LPl1xyiWJiYtoqlhYpLS1VRESE+/dly5ZpwoQJstls7m2nn366HnnkEe3du1fh4Ydu/fmPf/xDc+bMafN40fbMZpP6J4Ro5Y5ibcoua3byecOeUi3bXiQfi0kPTx/Sru3lA32tCrBZVGV3qqC8ttnJ57Jqh+xOlyQpMtB2lL0BdDbDGtZ9/i2rxKNxHEpmUZUMQwrytSoqiL9PAAAAAAAAANCVNLsvsafWez6UjIwMPfPMM7r++uvd23JzcxUbG9tkv8bfc3NzD3use++9V6Wlpe6vrKystgka7WJAQ8J5Y3bzK9jnrdglSZo6KF5JEQFtEteRNFY/t6T1dkFFjSQpxM8qPx9Lm8QFwHsNTgyVxWxSXlmtckqrPR1OE9sLG1tuB3rVtQMAAAAAAAAAoO01O/lsGEarv/g999wjk8l0xK+0tLQmz9mzZ4+mTp2qCy+8UDNnzjzuGHx9fRUSEtLkCx3XgIT6/3+bckqbtX9ZTZ0W/JYtSbpibHKbxXUkjW2zG9dwbo6CclpuA11ZgM2qPrHBkqS1Xlb9vHO/5DMAAAAAAAAAoGtpdtttl8vV6i9+5513asaMGUfcJzU11f1zdna2Tj31VJ1wwgl6+eWXm+wXFxenvLy8Jtsaf4+Li2udgOH1BjYmn7PLZBjGUavuPlmzR1V2p3rHBGlMj4gj7ttWoo+p8rl+38aqaQBdz7CkMG3OKdOarBJNHRTv6XDcdjQkn1NIPgMAAAAAAABAl9OiNZ9bW3R0tKKjo5u17549e3Tqqadq5MiRev3112U2Ny3aHj9+vO677z7V1dXJx8dHkrRo0SL17dv3sOs9o/PpHRMsH4tJZTUO7d5bfcQ22oZhaN7yTEnS5WOTPdYeNiq4fk3UllU+1+9L5TPQdQ1PCtO7KzP1W2aJp0NporHtdirJZwAAAAAAAADocprddtuT9uzZo4kTJyo5OVmPPfaYCgoKlJub22Qt58suu0w2m03XXHONNm7cqPnz5+upp57SH/7wBw9GjvZms5rVO6a+Fe2mnCOv+/zrrr1KzyuXv49F549IbI/wDik6yE/Svmrm5miskib5DHRdw5LDJEnr95TK6Wr9pTGOFW23AQAAAAAAAKDr8mjlc3MtWrRIGRkZysjIUGJi0yRh41rUoaGhWrhwoW666SaNHDlSUVFRmj17tq677jpPhAwPGpAQok05ZdqYXabTBx6+5fq85bskSecOTVCov097hXeQfZXP9mY/p7HymbbbQNfVMzpIQb5WVdQ6tCWvXP3jQzwdkipqHcpv+PtE220AAAAAAAAA6Ho6RPJ5xowZR10bWpKGDBmiH3/8se0DglcbEL9v3efDKaqo1Rfr6yvnLx+X3C5xHU7jms8tqXym7TYAi9mkwd1CtWx7kdZklnhF8rmx6jky0ObRm3oAAAAAAAAAAJ7RIdpuAy0xMKE+AbP5CG23P1y1W3anS0MSQzUkMaydIju0xgRyYQvWfHa33abyGejSxvSIkCS99MM2VdY6PByNtIOW2wAAAAAAAADQpZF8RqfTvyH5vKekWnsrD25l7XIZemdlpiTp8rGerXqW9rXOLqiodbeRPxoqnwFI0v+d1EPdwvy1q6hKcz7b6OlwSD4DAAAAAAAAQBdH8hmdToifj5Ii/CUduvr5p4xC7SqqUrCfVecMTWjv8A7SmEC2O1wqqzl65aLLZaioIalO8hno2kL9ffSvi4bKZJLe/3W3vlyf49F4GpPPrPcMAAAAAAAAAF0TyWd0SgPjQyVJGw+x7vO8FbskSReMSFSAzfPLnvv5WBTsWx9HYTPWfd5bZZfTVV8hHRFoa9PYAHi/camRmnVKT0nSPR+vV25pjcdiaUw+p5J8BgAAAAAAAIAuieQzOqUBDa23Nx1Q+ZxbWqNvNudLki7zgpbbjRormAuase5zQUOCOiLQJh8LpzAA6fbJfTS4W6hKq+t05we/yeVqXgv/1mQYhrYXVEiSekSTfAYAAAAAAACArojMFTqlgY3J5wMqn9/7JVNOl6ExPSLUJzbYE6EdUlRLks+N6z0H0XIbQD2b1awnLxkmfx+LlmYU6dWfdrR7DHur6txLB3SPIPkMAAAAAAAAAF0RyWd0So2VzxkFFaqpc0qSHE6X3luZJUm63IuqnqV9ieTmtN1u3CcqmJbbAPbpGR2kv549QJL06Nfp2phd2q6vv6Owvuo5IdRP/jZLu742AAAAAAAAAMA7kHxGpxQX4qfwAB85XYa25JVLkr5Ny1duWY0iA22aOijOwxE21aK221Q+AziMS8ck6XcDYmV3unTbe7+5b75pDzsKqyTRchsAAAAAAAAAujKSz+iUTCaTBiaESpI2NrTenrciU5J04agk+Vq9qyovKqi+irk5lc/u5HMwyWcATZlMJj1ywRBFB/sqI79C//hic7u9dmPlc48oks8AAAAAAAAA0FWRfEanNWC/dZ93FVXqhy0FMpmky8Z4V8ttqWWVz4UVdklSFJXPAA4hItCmxy4cKkl6c9kuLU7Lb5fX3VFYKUlKiST5DAAAAAAAAABdFclndFoD4huSzzllemdlfdXzhN7RSo4M8GRYh+ROPlP5DKAVnNInWr8/MUWS9KcP1zarq8Lxamy7nUrbbQAAAAAAAADoskg+o9Ma2FD5vDmnTB/8uluSdMW47p4M6bAaq5gLy+1H3ZfkM4DmuHtqP/WNDVZhhV13f7hOhmG02Wu5XIZ2NlQ+94gKarPXAQAAAAAAAAB4N5LP6LR6RAXK12pWld2p4kq74kP9dGrfaE+HdUiNieTCilq5XEdOEDVWMNJ2G8CR+PlY9NSlw2SzmvVtWr7eblj3vi3kldeous4pi9mkxHD/NnsdAAAAAAAAAIB3I/mMTstqMatfQ+ttSbp0TLKsFu/8Jx8ZWJ9IdrgMlVbXHXa/OqdLxVX11dFUPgM4mn5xIbpnaj9J0j++2Kxqu7NNXqdxvefkiAD5eOnfWQAAAAAAAABA22OGGJ1a47rPFrNJF49O8nA0h2ezmhUW4CPpyOs+F1faZRj17yc8wNZe4QHowGackKK4ED9V2Z1ak7m3TV5jh7vlNus9AwAAAAAAAEBXRvIZndq41AhJ0pmD4xUb4ufhaI4suqGNduOazofS+FhEoE0Ws6ld4gLQsZnNJvffwuU7itvkNXYU1CefUyJJPgMAAAAAAABAV2b1dABAWzp3aIKignw1Ijnc06EcVVSQr7bmV7jXdD6UxqroaNZ7BtACY1Mj9clv2VqxvahNju+ufI4m+QwAAAAAAAAAXRnJZ3RqJpNJJ/aK8nQYzdK4hnNzKp9Z7xlAS4ztUV/5vCarRDV1Tvn5WFr1+DuK6pPPqbTdBgAAAAAAAIAujbbbgJeIamy7fYTK58aq6CgqnwG0QI+oQEUH+8rucOm3rJJWPbbD6VJmUZX7dQAAAAAAAAAAXRfJZ8BLUPkMoK2YTCZ39fOK7a277vPuvdVyuAz5Ws2KC/Fr1WMDAAAAAAAAADoWks+AlyD5DKAtjUuNlCSt2NG66z43ttzuERUos9nUqscGAAAAAAAAAHQsJJ8BLxEVZJMkFVbYD7vPvrbbtnaJCUDnMS61vvJ5deZe2R2uVjvujoJ9yWcAAAAAAAAAQNdG8hnwElQ+A2hLPaODFBVkU02dS+t2l7TacXcU1iefU0g+AwAAAAAAAECXR/IZ8BLRQfUJ5eLKWjldxiH3aUw+x5B8BtBCJpNJYxrWfV6+vfVab+8sovIZAAAAAAAAAFCP5DPgJSICbTKZJJchFVce3Hq71uFUWY1DkhQVRPIZQMuN7dG47nNxqx1ze0Pb7VSSzwAAAAAAAADQ5XW45HNtba2GDRsmk8mk3377rclj69at08knnyw/Pz8lJSXpn//8p2eCBI6B1WJWZGD9Ws6Har3duBa0j8WkUH+fdo0NQOcwLrU++bxq117VOY9/3eeaOqeyS6sl0XYbAAAAAAAAANABk8933XWXEhISDtpeVlamKVOmqHv37lq1apUeffRRPfDAA3r55Zc9ECVwbBormgsrDk4+u9d7DvKVyWRq17gAdA69Y4IUHuCjKrtT6/eUHvfxMourZBhSsJ/VffMMAAAAAAAAAKDr6lDJ5y+//FILFy7UY489dtBj8+bNk91u12uvvaaBAwfqkksu0a233qrHH3/cA5ECxya6YS3nQ1Y+N2yLYr1nAMfIbN637vOK7cffenv/ltvcFAMAAAAAAAAA6DDJ57y8PM2cOVNvvfWWAgICDnp82bJlmjBhgmy2fZVXp59+utLT07V3797DHre2tlZlZWVNvgBPOWLlc8W+ymcAOFaN6z4v31503MfaUViffKblNgAAAAAAAABA6iDJZ8MwNGPGDN1www0aNWrUIffJzc1VbGxsk22Nv+fm5h722P/4xz8UGhrq/kpKSmq9wIEWak7lczSVzwCOw9jU+srnX3cWy3Gc6z7vKKyQJPUg+QwAAAAAAAAAkIeTz/fcc49MJtMRv9LS0vTMM8+ovLxc9957b6vHcO+996q0tNT9lZWV1eqvATRXY1VzwREqn6OofAZwHPrHhSjU30eVdqc2Zh9ft4+dhVWSSD4DAAAAAAAAAOpZPfnid955p2bMmHHEfVJTU/Xdd99p2bJl8vVtmnQbNWqULr/8cr355puKi4tTXl5ek8cbf4+Lizvs8X19fQ86LuApUcH1beMP2XabymcArcBsNml0SoS+2ZynFTuKNDQp7JiPtb2wcc3noFaKDgAAAAAAAADQkXk0+RwdHa3o6Oij7vf000/rwQcfdP+enZ2t008/XfPnz9fYsWMlSePHj9d9992nuro6+fj4SJIWLVqkvn37Kjw8vG3eANDKooP8JB2m7XYFyWcArWNcakPyeXuxrpvQ85iOUV5T5/67lBIV0JrhAQAAAAAAAAA6KI8mn5srOTm5ye9BQfUVVj179lRiYqIk6bLLLtOcOXN0zTXX6O6779aGDRv01FNP6Yknnmj3eIFjta/y2X7QY40JadpuAzheY3tESpJW7iiW02XIYja1+BiNLbejgnwV7OfTqvEBAAAAAAAAADomj6753JpCQ0O1cOFC7dixQyNHjtSdd96p2bNn67rrrvN0aECzNa75XFxpV53T1eQx2m4DaC0DEkIU7GtVea1Dm3OObd3n7YUVkqRU1nsGAAAAAAAAADToEJXPB0pJSZFhGAdtHzJkiH788UcPRAS0jvAAmyxmk5wuQ0UVdsWF1rfhrrI7VGl3SiL5DOD4Wcwmje4Roe/S8rV8e5EGdQtt8TF2NKz3TMttAAAAAAAAAECjTlP5DHQGZrNJkYGNrbf3rftcWF7fhtvPx6xAm8UjsQHoXMb2iJAkrdhRfEzP39mQfO4RFdRqMQEAAAAAAAAAOjaSz4CXaaxsbmyzLUkFFTXux0ymlq/NCgAHGpu6b91nl+vgbiJHs8OdfKbtNgAAAAAAAACgHslnwMtENaz7XLBf5XNBQ+Vz45rQAHC8BiWEKNBmUWl1ndJyy1v0XMMwtJ3kMwAAAAAAAADgACSfAS9z6Mrn+p+jSD4DaCVWi1kjUxpbbxe16LlFlXaV1zhkMkndI1nzGQAAAAAAAABQj+Qz4GUOmXxu+LnxMQBoDeNSG5LP21u27nPjes8Jof7y82EdegAAAAAAAABAPZLPgJdprG4u3K/tduPPJJ8BtKaxPRrWfd7ZsnWfG1tup0bTchsAAAAAAAAAsA/JZ8DLHKnymbbbAFrTkMRQ+ftYVFxp19b8imY/b0dD8jklkuQzAAAAAAAAAGAfks+Al4kKsklqWvlM220AbcHHYtbI7uGSWrbuc2Pb7R5RJJ8BAAAAAAAAAPuQfAa8TMwhKp9puw2grYzt0fJ1nxsrn3vQdhsAAAAAAAAAsB+Sz4CXiQ7ykySV1ThUU+eUYRj7Kp9puw2glY3rWb/u84odRTKMo6/77HIZ+5LPtN0GAAAAAAAAAOyH5DPgZUL8rbJZ6k/Nokq7ymsdqnW4JLHmM4DWNyQxVL5Wswor7NpWUHnU/XPLalTrcMlqNikx3L8dIgQAAAAAAAAAdBQknwEvYzKZ3Os+F5TXqrCh6jnY1yp/m8WToQHohHytFo1Irl/3efn2o6/73Fj1nBwZIKuFywgAAAAAAAAAwD7MGgNeKKphbefC8lp3y+0o1nsG0EbGpjas+7zj6Os+b6flNgAAAAAAAADgMEg+A16ocW3ngopaFVSw3jOAtjW2R8O6z9uPvu7zzsbkcxTJZwAAAAAAAABAUySfAS8U3VDlvH/b7WgqnwG0keHJYbJZzcovr9XOoqoj7tvYdrtHNMlnAAAAAAAAAEBTVk8HAOBgUQ1VzoUVtap1OBu22TwZEoBOzM/HomFJYVq5o1gzXl+p1KhAJYT5KyHMX/GhfvU/h/orLtRvX/KZymcAAAAAAAAAwAFIPgNeaP/K55o6Z5NtANAWzhwUp5U7irWrqEq7jlL9LJF8BgAAAAAAAAAcjOQz4IWaVj67JJF8BtC2ZpzYQ6f0jVFmcZVySqqVXVKt7NIaZZdUK6e0RntKqmVv+HuUFOGv2GA/D0cMAAAAAAAAAPA2JJ8BL9S08rk+2dOYkAaAttIjKvCwFc2GYai40q6c0holhQfIbDa1c3QAAAAAAAAAAG9H8hnwQodKPlP5DMCTTCaTIoN8FcmNMAAAAAAAAACAwyD5DHihqCCbJKnS7lR1w5rPVD4DAAAAAAAAAADAm5k9HQCAgwX5WuXnU396uoz6bZENCWkAAAAAAAAAAADAG5F8BryQyWRqUukcFuAjX6vFgxEBAAAAAAAAAAAAR0byGfBS+6/xTMttAAAAAAAAAAAAeDuSz4CXit4v4RxN8hkAAAAAAAAAAABerkMln//3v/9p7Nix8vf3V3h4uKZNm9bk8czMTJ111lkKCAhQTEyM/vSnP8nhcHgmWOA4Re1X+bx/FTQAAAAAAAAAAADgjayeDqC5PvroI82cOVN///vfNWnSJDkcDm3YsMH9uNPp1FlnnaW4uDj9/PPPysnJ0VVXXSUfHx/9/e9/92DkwLHZv9qZttsAAAAAAAAAAADwdh0i+exwOHTbbbfp0Ucf1TXXXOPePmDAAPfPCxcu1KZNm/TNN98oNjZWw4YN09/+9jfdfffdeuCBB2Sz2TwROnDMqHwGAAAAAAAAAABAR9Ih2m6vXr1ae/bskdls1vDhwxUfH68zzjijSeXzsmXLNHjwYMXGxrq3nX766SorK9PGjRsPe+za2lqVlZU1+QK8QZM1n0k+AwAAAAAAAAAAwMt1iOTz9u3bJUkPPPCA/vKXv+jzzz9XeHi4Jk6cqOLiYklSbm5uk8SzJPfvubm5hz32P/7xD4WGhrq/kpKS2uhdAC2zf8I5KojKfQAAAAAAAAAAAHg3jyaf77nnHplMpiN+paWlyeVySZLuu+8+XXDBBRo5cqRef/11mUwmffDBB8cVw7333qvS0lL3V1ZWVmu8NeC4UfkMAAAAAAAAAACAjsSjaz7feeedmjFjxhH3SU1NVU5OjqSmazz7+voqNTVVmZmZkqS4uDitXLmyyXPz8vLcjx2Or6+vfH1J7MH77J9wjgn282AkAAAAAAAAAAAAwNF5NPkcHR2t6Ojoo+43cuRI+fr6Kj09XSeddJIkqa6uTjt37lT37t0lSePHj9dDDz2k/Px8xcTESJIWLVqkkJCQJklroKPwt1n0xyl9VGl3UvkMAAAAAAAAAAAAr+fR5HNzhYSE6IYbbtD999+vpKQkde/eXY8++qgk6cILL5QkTZkyRQMGDNCVV16pf/7zn8rNzdVf/vIX3XTTTVQ2o8O6eVJvT4cAAAAAAAAAAAAANEuHSD5L0qOPPiqr1aorr7xS1dXVGjt2rL777juFh4dLkiwWiz7//HPNmjVL48ePV2BgoK6++mrNnTvXw5EDAAAAAAAAAAAAQOdnMgzD8HQQ3qSsrEyhoaEqLS1VSEiIp8MBAAAAAAAAAADHiDl/AGhfZk8HAAAAAAAAAAAAAADo+Eg+AwAAAAAAAAAAAACOG8lnAAAAAAAAAAAAAMBxI/kMAAAAAAAAAAAAADhuJJ8BAAAAAAAAAAAAAMeN5DMAAAAAAAAAAAAA4LhZPR2AtzEMQ5JUVlbm4UgAAAAAAAAAAMDxaJzrb5z7BwC0LZLPBygvL5ckJSUleTgSAAAAAAAAAADQGsrLyxUaGurpMACg0zMZ3O7ThMvlUnZ2toKDg2UymTwdDo6grKxMSUlJysrKUkhIiKfDAbo0zkfAO3AuAt6D8xHwDpyLgPfgfAS8Q1c8Fw3DUHl5uRISEmQ2sxIpALQ1Kp8PYDablZiY6Okw0AIhISFd5kIJ8Hacj4B34FwEvAfnI+AdOBcB78H5CHiHrnYuUvEMAO2H23wAAAAAAAAAAAAAAMeN5DMAAAAAAAAAAAAA4LiRfEaH5evrq/vvv1++vr6eDgXo8jgfAe/AuQh4D85HwDtwLgLeg/MR8A6ciwCAtmYyDMPwdBAAAAAAAAAAAAAAgI6NymcAAAAAAAAAAAAAwHEj+QwAAAAAAAAAAAAAOG4knwEAAAAAAAAAAAAAx43kMwAAAAAAAAAAAADguJF8Bo6Bw+HwdAgAAHiVtWvXqqyszNNhAAAAAAAAAPAgks9AC2RnZ2vMmDGaPXu2p0MBIKmgoEBOp9PTYQBd2p49e3TRRRdp+PDheuuttzwdDgAAACBJysvL04IFC7R27VoZhuHpcAAAALoMks9AM91xxx1KSUlRXFycbr75Zk+HA3RpOTk5mj59um699VatX7/e0+EAXdYf/vAHJScnq7q6WuHh4QoODvZ0SECXlZubq4ceekivv/66li1bJklMtAMekpeXp08//VRr166laxbgIXPnzlVKSooefPBBjRkzRrfeequ2bt0qSXK5XB6ODuh6ysrKlJeXJ4lzEAC6ApLPwFFkZmaqW7du+vTTT/XTTz/p008/VUJCgqfDArqcxgn0Dz74QIMHD5bT6dTNN9+s2NjYJo8DaHtfffWVQkNDtXjxYi1evFifffaZRo0apS+++MLToQFd0pw5c9SrVy/98MMPeuyxx3ThhRfql19+kclkYnwE2tns2bOVmpqqp556ShMmTNCNN96oTZs2SWKyHWgvv/32m+bPn6958+ZpyZIlev7557V27Vpdc801kiSzmelQoD09+OCD6tWrl5599llJnIMA0BXwlx44hP0n6axWq7p166YxY8ZozJgxWr16te666y49/vjj+uabb1RTU+PBSIGuw2QySZLeeecd3XHHHVqwYIFOPPFEhYaGNnkcQNvYf2zMzc3VSy+9pDVr1mjChAmy2+1KSUlReXk56z4D7ezLL7/UggUL9OGHH+rrr7/W/Pnz1bt3by1YsEAS4yPQnt577z19/fXX+uyzz7Rw4UL95z//0a5duzRjxgxJTLYDbeXAG62++OILVVZWavr06QoICNA111yjBx54QGvXrtUTTzwhiZtBgPZQUVGhG2+8UZ988olSUlL066+/aunSpZIoIACAzo5PPsAB7HZ7kzVk4+PjNXfuXM2fP1+nn366zj//fKWlpemNN97Q5ZdfrjvuuIMLJqCNHHhuLV++XOvXr9ett96qNWvWaPr06Zo+fbpuuOEGff/994d8DoDjd+DYePXVV+uSSy6RJDmdTtlsNsXGxmrr1q0KCQnhPATaUOP51fi9sePA1KlTJUmDBg2S2WzWmWeeedBzALSuA8/H//73v0pISNCkSZNksVh03nnnacyYMfr111/15JNPNtkXQOuorq5WUVFRk23R0dEKCgrS3r173dtOOukk3X777br//vtlt9u5GQRoI/uPc76+vkpOTtYf//hHPfPMMyosLNR///tfVVdX06EHADo5rrSA/Tz44IOaOnWqzjvvPD3zzDMqKiqSyWTS+PHjdf3116u4uFgffvih5s+fr3Xr1um+++7TsmXL9OKLL3o6dKDTOTDZJUnBwcHau3evFi5cqJtuukkpKSmaMGGCtm7dqrPPPls7duygwgtoZQeOjXv37pXJZHKfn40Td5MmTVJOTo7S0tI4D4E2sv/YaDKZ5HK51KtXLxUUFGjRokXavXu3Lr74Yv3666+6//77NWvWLPc5C6B1HXg+VlRUyOFwKCUlRXa73b2fj4+P+vfvr9mzZ6u8vJzzEWhFc+fO1dixY3Xeeefp8ssv165duyRJfn5+8vX11Xfffefe12az6dJLL1VMTIweffRRSdwMArS2A28GsVgsuvHGG3XJJZdo7NixOuOMM7R06VJ99dVXkujQAwCdGclnQNLq1as1evRovffee7riiisUHBys119/XQ8++KAkKTQ0VHfccYeeeeYZjRw5Ur6+vpKkK664QnFxcdq0adNBSTIAx64x2TVt2jQ988wzKi4uliTV1tZq1KhR+uc//6nU1FQ98sgj+vOf/6zPP/9cgwYN0l133SWJFmpAazjc2Dh37lxJ9RMJ0r4JA6fTqaioKO3evdtjMQOd2YFjY1FRkcxms6ZOnapJkybpiSeeUM+ePVVYWKiPPvpIZ599tn788Ud3u18m2IHWc+D5WFhYqKCgIA0aNEhLlizR3/72NxUWFmr27Nl6+umn9ec//1kRERHctAy0kqVLl2r48OF6//33NXv2bJ133nnavn277r77bknSRRddJJPJpC+//FJ79uxxP6979+4aP368MjMz5XA4SHwBrejAm0EyMzNlNpsVFBTkvg69+eab5evrqwULFig7O1sS16gA0FmRfEaXV1FRoXfffVf9+vXT0qVL9X//93967733dNZZZ2nbtm3uNk29e/fWuHHjZDabZTab5XK5FBERoZ07d8put7sn4QEcuwOTXUFBQXr99df1t7/9TZI0ePBgRUZG6pdfftGwYcPk4+Mjp9Mpf39//fGPf9T333/vnowHcOyONjaWlJQc9JwTTzxRBQUFKigokMRNIEBrOdzY2HiTZN++ffXmm2/quuuu08knn6wPP/xQkydP1m233abnnntOX3/9tbKysphgB1rB0a5V77vvPk2aNEnvv/+++vfvr/nz5+vDDz/U5Zdfrl69eqm2ttbD7wDoHBYtWqRx48Zp+fLl+n//7//prrvu0pAhQxQSEiKHwyFfX1/dfPPNWrJkiRYsWOB+nr+/v3bt2qXq6mpZrVYPvgOg8zjczSD33HOPpPpOWY0de2JiYnTFFVdo/fr1+vTTTyWJ9tsA0EkxO48uzzAM9ejRQ7NmzVJoaKgcDoek+mrn9PR0hYaGSjq4FYzZbNa3336rkJAQXX311e0eN9DZHC3ZVVhYKB8fH1177bWKi4vTJ598Imlf9eWWLVvUq1cvWa1WPrgAx+loY2NISMhBz3E6nTrppJO0ZMkSSeImEKAVNPcmSUlKS0uT1WpVeHi4e9vWrVuVkJCgmpoaT4QPdCpHOh937NihwsJC2Ww2/fOf/9SSJUu0cOFCpaena+LEiZLqr1VJdgGt44YbbtCf/vQnBQUFSarvkJWRkaHU1FRt3bpVkjRjxgydfPLJeuWVV/T000+rrKxM69atU1VVlc444wxPhg90Koe7GaTx/JTqP182zqtee+216t69u77++mutWbNGH330kWbPnu2p8AEAbYRZQXR5wcHBuv7663XCCSdI2jdZXlpaqmHDhh00eb5582YtWbJEt912my688EKddNJJGj16dLvHDXQ2R0t2hYWFSapfV/a2227T1q1bdeeddyo9PV3btm3T999/r4kTJyo0NJTqLuA4tXRslKTAwEDl5eWpoqKCyi6glTT3JkmpPjFWU1OjTz75RA6HQxkZGXr//fc1ceJE9ezZ01NvAeg0jnY+Nt74YTabFRcXp+HDh7uf+9FHHykuLk4XX3yxR2IHOpu4uDilpqZKkt555x3FxMQoNzdXH374oc466yzdcccdkqQHHnhAF1xwge68805NnjxZ48ePV79+/XT++ed7MnygUznSzSDp6emS6gt6TCaTe8nCG2+8URs2bNDvfvc7XXrppbLZbB6LHwDQNrjtFl2eYRhNWmY3Jq1Wr16tCRMmuPdp3L5u3Tq9+uqrqq6u1pdffqmxY8e2f9BAJ9SY7Go8Hw9MdlmtVjkcDlmtVt1www1KSEjQ7bffroULFyozM1NnnHGG7rvvPk++BaDTaOnY2Hhu3nPPPRowYIB8fX3bP2igEzra2Gg2m+V0OmWxWHTZZZcpPT1dF110kSZNmqRly5bprLPO0lNPPUUnAqAVHO18PHAZppKSEv34449auHCh3njjDd1yyy1KTk5uMn4COH5lZWV67bXXdM4556iyslI//PCDzj//fF1//fXq16+f7rvvPk2bNk07d+5UUlKShgwZ4umQgU4lLi7O/fM777yjWbNmKTExUR9++KFefvllXXDBBXr00Ucl1Xeu27Vrlz744ANt27ZNM2bM0GOPPaaIiAhPhQ8AaCMkn9HpFRcXy+FwKCwsTDabzT1BJ+2bLG/kcrlkNptVWlqqFStW6O6775ZUP+m+a9cude/eXWeffbZGjBih3r17e+T9AJ1Vc5JdjY+Hhobqyiuv1OTJk7Vnzx4FBgaqf//+7R800EG11tiYlZWlpKQk9wQ8FV1A62rO2Nh4/g0YMEDPPPOMrrzySmVlZenhhx/WsGHD2j1moLNq6Y1ZTqdTK1eu1Pr16/XNN99w0zLQTC25TpWk66+/3n3e2Ww2DRgwQKGhoVq5cqX69esnSRo4cKAGDhzYvm8E6IIOdzPItddeq759+0qS3nrrLf33v//VihUr6CQJAJ0Yt8Cj0zIMQ7fddptOOOEEnXnmmTrttNOUlZUli8Uil8slSe61YZ944glJ+ybvvv32W4WFhWnChAnas2ePLrroIo0ePVr5+fkKDAwk8Qwcg+LiYuXn58tut0uSu92SVD+JsH8FiMvlkslkcie7xo8fL2lfsqtxn/j4eI0aNYrEM9BMrT02jhw5UgUFBVRVAseotcbGzMxMSfWVJ+eee65uuukmEs9AC7X2+RgREaG7775b33//PYlnoBmO5TpV0kGdBH744Qf169dPZ555ZrvGD3RGRxsbD3T99dfrggsukM1mU3h4eJObQRr95S9/UX5+PolnAOjkmClEp7Rq1SqNHTtWK1eu1HPPPadZs2aptrZWV199taR9E+mvvPKK4uPj9f777ys7O9v9/LS0NA0fPlx///vf1bt3b5WUlGjVqlWKiYnxyPsBOjKSXYB3aKuxMTo62iPvB+jIWntsHDVqlAoKCjz2foCOrC3Ox/z8fJlMJvf6lwCO7HivUwsLC5Wdna0HHnhAs2fP1v/7f/9PERERMgzDI+8H6Oha+2aQM844o13jBwB4HjP36JQ+//xzxcXF6fPPP9dpp52ma665Rs8++6xWrlyp7du3S5I+++wzPf/883rooYf0008/KSEhwf38BQsW6KOPPtLbb7+tTz75RAsXLlRSUpKn3g7QYZHsArwHYyPgHRgbAe/BTcuAdzie69S0tDS98MILOuWUU9zXqnfeeafMZjPrqwPHgJtBAACtgTWf0ak0rkt5zjnnaPz48YqMjHQ/Vlpaqri4OPn6+kqSzjnnHE2aNEmBgYFNjlFZWanJkyfr1ltv1eWXX96u8QOdTeMkwuuvv+4+HwcPHqxJkyZp+/btSk1NbTKJMGPGjCZr6S1YsEC//PKLNm7cqE8++URTpkzx1FsBOizGRsC7MDYC3oPzEfCs1rhO7d69u0444QQNHz5cZ599drvGD3RGxzM2pqWl6YMPPtB//vMf+fn56e2339app57qybcDAPAQks/o8N59910NHTpUAwYMcN99N2LECPfjDodDVqtV+fn5slqtTT7MHPihpXHbQw891PaBA50YyS7AsxgbAe/D2Ah4D85HwHNa+zrV399fp512WtsHDnRy3AwCAGhNtN1Gh/XDDz9o8ODBuvzyyzVv3jxVV1cfcr/GDzPfffedTjzxRPn5+bnXJwHQet59911t2rRJkppMIjRWgDgcDklqcbKLyTyg+RgbAe/C2Ah4D85HwLO4TgW8T2uPjY03g5B4BgCQfEaHtHv3br355puaPHmy7r33Xr3wwgtau3btIfc1m80yDEO//PKLTj/9dPe2tWvXqqSkpB2jBjonJhEA78DYCHgPxkbAe3A+Ap7HdSrgXRgbAQBtjeQzOqSQkBCdeeaZuuaaa/TQQw8pOjpaTz311GE/iKxZs0YlJSWaMGGCNm/erEmTJmn8+PHKzc1t38CBToZJBMB7MDYC3oGxEfAenI+Ad+A6FfAejI0AgPZA8hkdUkhIiC644AINGjRIkvTcc89p/vz5WrJkiQzDcO/X+PO6desUEBCgf/zjHxo8eLDi4+OVl5enfv36eSR+oLNgEgHwHoyNgHdgbAS8B+cj4B24TgW8B2MjAKA9kHxGh+dyuTR58mRNnTpV//jHP7Rnzx73YyaTSZL09ddfa8uWLVq3bp1WrlypefPmKTg42FMhA50GkwiAd2JsBDyHsRHwHpyPgPfhOhXwLMZGAEB7IPkMr5SRkaEJEyborbfekqQmFz8Oh6PJvo1rjbz44ov65Zdf9N///te9LSsrS5J0/fXX6+OPP9bixYs1YsSI9ngLQJfDJALQthgbgY6HsRHwHpyPQNvhOhXomBgbAQBtheQzvIrdbtdVV12lfv366aefftLGjRsl1V/wOJ1OSZLVapXD4dDmzZvdvzudTiUnJ+v222/XE088ofnz52vKlCn685//rOrqak2cOFHTpk3z1NsCOiwmEQDPY2wEvAtjI+A9OB8Bz+I6FfA+jI0AAG9A8hle4+GHH1Z4eLh27dqljIwMnXPOOe71Q5xOpywWiyTp6aefVmhoqL744gvV1dVJkszm+n/Kt99+u3bu3KnLL79cNptNTz31lPz9/T3zhoAOjEkEwDswNgLeg7ER8B6cj4DncZ0KeBfGRgCANyH5DK/w6quv6t1339Ubb7yhJUuWKCUlRSNHjtRPP/0kSbJYLKqtrdWsWbP00EMP6aWXXtIf/vAH+fj4SKq/kHrnnXeUmpqqUaNGafXq1fr8888VERHhybcFdEhMIgDegbER8B6MjYD34HwEPI/rVMC7MDYCALyOAXiQ0+k0DMMwioqKDJfL1eSxxx57zBg0aJCRkZFhGIZhuFwuY8uWLUZpaekhj/PRRx8ZL730UtsHDXRir7zyijFkyBDj/fffd2+bM2eO0bNnT/fvNTU1xg033GDExMQYb7311kHn7rx58wyr1WqMHj3aWLNmTXuFDnQajI2Ad2FsBLwH5yPgWVynAt6HsREA4I1MhrHfwg9AO1m5cqXGjBnT5O67RoZhyGQy6aefftIpp5yizMxMdevWzUORAl2Dy+WS2WxWcXGxwsPDZTKZ3I/961//0htvvKFPPvlEPXv2lGEYysjIUGxsrEJCQg46zieffKLCwkJdd9117f02gA6NsRHwLoyNgPfgfAQ8i+tUwPswNgIAvBltt9GuPvnkE3Xr1k1nnHGGdu7cKYvFIpfL1WSfxoul+Ph4JSUladGiRZ4IFegSVq5cKal+wkCSIiIi3Odg47axY8dq06ZN8vPzk1R/jvbu3fugDyxSfbum6dOn84EFaAHGRsC7MDYC3oPzEfAsrlMB78PYCADoCEg+o93MmzdPf//73zVhwgQNGDBADz/8sKR9a4scyM/PTzabTdXV1e0ZJtAlMIkAeAfGRsB7MDYC3oPzEfA8rlMB78LYCADoSEg+o805nU5JUq9evXTaaafpkUce0bnnnqvvv/9e33//fZN9GhmGoW7duik2NlbLly+XpIMuqAAcGyYRAM9jbAS8C2Mj4D04HwHP4joV8D6MjQCAjobkM9rM1q1bZRiGez2gsWPH6m9/+5uSk5N15plnqm/fvnr00UclSRaLRfsvP24ymWQYhkaOHKmMjAxVVlYe9oIKQPMwiQB4HmMj4F0YGwHvwfkIeBbXqYD3YWwEAHRUXAmi1b3//vvq0aOHzjnnHI0bN06vvfaa+7HGDzEDBw7UtGnTtHPnTr3++uuS1OSDi1T/4aW2tlZDhw6Vj49P+70BoJNhEgHwPMZGwLswNgLeg/MR8CyuUwHvw9gIAOjoGHnQqhYtWqS7775bf/rTn/TUU0/ppJNO0g033KB///vfqq6ulslkksPhkCRNmTJF48eP1wsvvKCKigqZzWbV1dVJ2nfX3tNPP63nn39eNpvNY+8J6KiYRAC8A2Mj4D0YGwHvwfkIeB7XqYB3YWwEAHQWVk8HgM7BMAyZTCYtW7ZMkZGRmjlzpnx8fHT66aerpqZGL7/8sqKionT++efLaq3/Z9etWzedf/75Wrt2rR577DFNnz5d9913n55//nklJSVJEhdIwDHafxKhZ8+eWrhwoW644QY5nU5dccUV8vf3l8PhkNVq1ZQpU7R06VK98MILuvDCCxUUFKS6ujr5+PjI6XTKYrHo6aef5nwEWoixEfAujI2A9+B8BDyL61TA+zA2AgA6Eyqf0SpMJpMkadOmTerZs6d8fHzcd8A++OCD8vPz04IFC5Sbmytp312xp556qsaMGaO5c+dq5MiRqqurU0xMjGfeBNAJNN7tuv8kwumnn65//etfmjlzpl5++WV99dVXknTQJIJhGHrssce0bt06TZ8+XVlZWe47a/nAArQcYyPgHRgbAe/B+Qh4B65TAe/B2AgA6IxIPuOYLFq0SLfeequefPJJrVy50r39tNNO05dffimn0+n+8BIeHq6rrrpKy5YtU3p6uqT6VjGVlZV6+eWX9dJLL+mUU07R6tWr9dVXX8nX19dTbwvo8JhEADyHsRHwToyNgPfgfAQ8g+tUwHsxNgIAOiOSz2iRnJwcnXPOObriiitUXFys1157TVOmTHF/eDnllFMUEhKiOXPmSNp3997MmTNVVlamNWvWuI+1a9cuvffee3r99de1ePFiDR48uP3fENDBMYkAeB5jI+BdGBsB78H5CHgW16mA92FsBAB0BSSf0WxVVVW69957FRgYqOXLl+vtt9/WunXr1LdvX73wwguSpPj4eM2aNUuPPfaYsrKyZLPZ3B9e+vbtq40bN7qPN2DAAC1fvlxXXnmlR94P0JExiQB4B8ZGwHswNgLeg/MR8DyuUwHvwtgIAOhKSD6j2QICAuTr66sZM2aoR48ecjgckqQzzzxTmzdvlmEYCg4O1mWXXaYRI0booosu0q5du2QymZSZman8/HxNmzbNs28C6ASYRAC8B2Mj4B0YGwHvwfkIeAeuUwHvwdgIAOhqSD6jRZ599llNnTpVkmQ21//z2bJli4YMGeJeo6RHjx6aP3++CgsLNXHiRF144YUaP3684uPjNWrUKI/FDnQWTCIA3oWxEfA8xkbAe3A+At6D61TAOzA2AgC6GpPReAsVcIxOOukkzZw5U1dffbVcLpek+g81GRkZWrVqlVasWKGhQ4fq6quv9nCkQOdRV1cnHx8fSZLL5ZLZbNbll1+uwMBAvfzyy+799uzZo4kTJ8rhcGjUqFH6+eef1a9fP73zzjuKjY31VPhAp8fYCLQ/xkbAe3A+At6L61TAMxgbAQBdCclnHJft27frhBNO0P/+9z+NHDlSkmS322Wz2TwcGdD1MIkAeAfGRsB7MDYC3oPzEfA8rlMB78LYCADorKyeDgAdk2EYMplM+umnnxQUFOT+0DJnzhzl5uZqzpw5iomJ8XCUQNexfft2ZWRkaNCgQZLqP6w0TiL06tVLvXr10sUXX+zhKIHOjbER8C6MjYD34HwEPIvrVMD7MDYCADoz1nzGMWlcG2jlypW64IILtGjRIvXo0UPPP/+8zj//fD60AO2ksXnFoSYRbrvtNuXn53syPKBLYWwEvANjI+A9OB8B78B1KuA9GBsBAF0BbbdxzGpqajR48GBt27ZNNptNc+bM0d133+3psIAu6eabb1ZgYKAmT56s6667TlVVVXrrrbc0ZcoUT4cGdCmMjYD3YGwEvAfnI+B5XKcC3oWxEQDQmZF8xnH53e9+p969e+vxxx+Xn5+fp8MBuiQmEQDvwtgIeB5jI+A9OB8B78F1KuAdGBsBAJ0dyWccF6fTKYvF4ukwgC6PSQTAezA2At6BsRHwHpyPgHfgOhXwHoyNAIDOjOQzAHQCTCIAANAUYyPgPTgfAQBoirERANCZkXwGAAAAAAAAAAAAABw3s6cDAAAAAAAAAAAAAAB0fCSfAQAAAAAAAAAAAADHjeQzAAAAAAAAAAAAAOC4kXwGAAAAAAAAAAAAABw3ks8AAAAAAAAAAAAAgONG8hkAAAAAAAAAAAAAcNxIPgMAAADwSjNmzNC0adPa/XXfeOMNmUwmmUwm3X777UfcNyUlRU8++WSzjjtx4kT3cX/77bfjjhMAAAAAAMDbWD0dAAAAAICux2QyHfHx+++/X0899ZQMw2iniJoKCQlRenq6AgMDW+2YH3/8sbZt26YxY8a02jEBAAAAAAC8CclnAAAAAO0uJyfH/fP8+fM1e/Zspaenu7cFBQUpKCjIE6FJqk+Ox8XFteoxIyIiVFZW1qrHBAAAAAAA8Ca03QYAAADQ7uLi4txfoaGh7mRv41dQUNBBbbcnTpyoW265RbfffrvCw8MVGxurf//736qsrNTvf/97BQcHq1evXvryyy+bvNaGDRt0xhlnKCgoSLGxsbryyitVWFjY4pjz8/N1zjnnyN/fXz169NC8efOaPG4Yhh544AElJyfL19dXCQkJuvXWW4/pvw8AAAAAAEBHRPIZAAAAQIfx5ptvKioqSitXrtQtt9yiWbNm6cILL9QJJ5yg1atXa8qUKbryyitVVVUlSSopKdGkSZM0fPhw/frrr/rqq6+Ul5eniy66qMWvPWPGDGVlZWnx4sX68MMP9fzzzys/P9/9+EcffaQnnnhCL730krZu3apPPvlEgwcPbrX3DgAAAAAA4O1ouw0AAACgwxg6dKj+8pe/SJLuvfdePfzww4qKitLMmTMlSbNnz9YLL7ygdevWady4cXr22Wc1fPhw/f3vf3cf47XXXlNSUpK2bNmiPn36NOt1t2zZoi+//FIrV67U6NGjJUmvvvqq+vfv794nMzNTcXFxmjx5snx8fJScnMz6zgAAAAAAoEuh8hkAAABAhzFkyBD3zxaLRZGRkU2qi2NjYyXJXZG8du1aLV682L2GdFBQkPr16ydJ2rZtW7Nfd/PmzbJarRo5cqR7W79+/RQWFub+/cILL1R1dbVSU1M1c+ZM/fe//5XD4Tim9wkAAAAAANARUfkMAAAAoMPw8fFp8rvJZGqyzWQySZJcLpckqaKiQuecc44eeeSRg44VHx/fqrElJSUpPT1d33zzjRYtWqQbb7xRjz76qJYsWXJQ3AAAAAAAAJ0RyWcAAAAAndaIESP00UcfKSUlRVbrsX/86devnxwOh1atWuVuu52enq6SkpIm+/n7++ucc87ROeeco5tuukn9+vXT+vXrNWLEiON5GwAAAAAAAB0CbbcBAAAAdFo33XSTiouLdemll+qXX37Rtm3b9PXXX+v3v/+9nE5ns4/Tt29fTZ06Vddff71WrFihVatW6dprr5W/v797nzfeeEOvvvqqNmzYoO3bt+vtt9+Wv7+/unfv3hZvDQAAAAAAwOuQfAYAAADQaSUkJGjp0qVyOp2aMmWKBg8erNtvv11hYWEym1v2cej1119XQkKCTjnlFE2fPl3XXXedYmJi3I+HhYXp3//+t0488UQNGTJE33zzjT777DNFRka29tsCAAAAAADwSibDMAxPBwEAAAAA3uKNN97Q7bffflBL7dawc+dO9ejRQ2vWrNGwYcNa/fgAAAAAAACeROUzAAAAABygtLRUQUFBuvvuu1vtmGeccYYGDhzYascDAAAAAADwNlQ+AwAAAMB+ysvLlZeXJ6m+lXZUVFSrHHfPnj2qrq6WJCUnJ8tms7XKcQEAAAAAALwFyWcAAAAAAAAAAAAAwHGj7TYAAAAAAAAAAAAA4LiRfAYAAAAAAAAAAAAAHDeSzwAAAAAAAAAAAACA40byGQAAAAAAAAAAAABw3Eg+AwAAAAAAAAAAAACOG8lnAAAAAAAAAAAAAMBxI/kMAAAAAAAAAAAAADhuJJ8BAAAAAAAAAAAAAMft/wNsGaYFpu+fpQAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 1600x350 with 1 Axes>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plot_series(Y_train.query(\"temporal_id in @tags_train['1-hour-period']\")[[\"y\", \"ds\", \"unique_id\"]].iloc[-100:], forecasts_df=Y_rec.query(\"temporal_id in @tags_test['1-hour-period']\").drop(columns=[\"temporal_id\"]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "and for the 2-hour period forecasts:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1600x350 with 1 Axes>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plot_series(Y_train.query(\"temporal_id in @tags_train['2-hour-period']\")[[\"y\", \"ds\", \"unique_id\"]].iloc[-50:], forecasts_df=Y_rec.query(\"temporal_id in @tags_test['2-hour-period']\").drop(columns=[\"temporal_id\"]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Also, we can now verify that the forecasts are better coherent with each other. For the first 2-hour period, our forecast after reconciliation is 6.63, and the sum of the forecasts for the first two 1-hour periods is 1.7 + 4.92 = 6.63. Hence, we now have more accurate and coherent forecasts across frequencies."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>unique_id</th>\n",
       "      <th>temporal_id</th>\n",
       "      <th>ds</th>\n",
       "      <th>y</th>\n",
       "      <th>TimeGPT</th>\n",
       "      <th>TimeGPT/MinTrace_method-wls_struct</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DE</td>\n",
       "      <td>2-hour-period-1</td>\n",
       "      <td>2017-12-29 01:00:00</td>\n",
       "      <td>10.45</td>\n",
       "      <td>16.949448</td>\n",
       "      <td>6.625738</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>DE</td>\n",
       "      <td>1-hour-period-1</td>\n",
       "      <td>2017-12-29 00:00:00</td>\n",
       "      <td>9.73</td>\n",
       "      <td>-0.241489</td>\n",
       "      <td>4.920365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>DE</td>\n",
       "      <td>1-hour-period-2</td>\n",
       "      <td>2017-12-29 01:00:00</td>\n",
       "      <td>0.72</td>\n",
       "      <td>-3.456482</td>\n",
       "      <td>1.705373</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   unique_id      temporal_id                  ds      y    TimeGPT  \\\n",
       "0         DE  2-hour-period-1 2017-12-29 01:00:00  10.45  16.949448   \n",
       "24        DE  1-hour-period-1 2017-12-29 00:00:00   9.73  -0.241489   \n",
       "25        DE  1-hour-period-2 2017-12-29 01:00:00   0.72  -3.456482   \n",
       "\n",
       "    TimeGPT/MinTrace_method-wls_struct  \n",
       "0                             6.625738  \n",
       "24                            4.920365  \n",
       "25                            1.705373  "
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y_rec.query(\"temporal_id in ['2-hour-period-1', '1-hour-period-1', '1-hour-period-2']\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Conclusion"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this notebook we have shown:\n",
    "- How to create forecasts for multiple frequencies for the same dataset with TimeGPT\n",
    "- How to improve the accuracy of these forecasts using temporal reconciliation techniques\n",
    "\n",
    "Note that even though we created forecasts for two different frequencie, there is no 'need' to use the forecast of the 2-hour-period. One can use this technique also simply to improve the forecast of the 1-hour-period.\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "python3",
   "language": "python",
   "name": "python3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}