diff --git "a/.ipynb_checkpoints/Time_Series_Forecasting-checkpoint.ipynb" "b/.ipynb_checkpoints/Time_Series_Forecasting-checkpoint.ipynb"
new file mode 100644--- /dev/null
+++ "b/.ipynb_checkpoints/Time_Series_Forecasting-checkpoint.ipynb"
@@ -0,0 +1,1402 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "lLC1wTwghgKr",
+    "outputId": "fadf5c4c-5ec6-496d-c0ee-3aadde7be24c"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[*********************100%***********************]  1 of 1 completed\n",
+      "\n",
+      "1 Failed download:\n",
+      "['AAPL']: ReadTimeout(ReadTimeoutError(\"HTTPSConnectionPool(host='query2.finance.yahoo.com', port=443): Read timed out. (read timeout=10)\"))\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Empty DataFrame\n",
+      "Columns: [Close_AAPL]\n",
+      "Index: []\n"
+     ]
+    }
+   ],
+   "source": [
+    "import yfinance as yf\n",
+    "import pandas as pd\n",
+    "\n",
+    "# Download Apple stock data\n",
+    "data = yf.download(\"AAPL\", start=\"2015-01-01\", end=\"2023-01-01\", auto_adjust=True)\n",
+    "\n",
+    "# Flatten columns (in case of MultiIndex)\n",
+    "data.columns = ['_'.join(col).strip() if isinstance(col, tuple) else col for col in data.columns]\n",
+    "\n",
+    "# Keep only the Close column\n",
+    "data = data[['Close_AAPL']].copy()  # Use the new name\n",
+    "\n",
+    "# Drop any missing values (just in case)\n",
+    "data.dropna(subset=['Close_AAPL'], inplace=True)\n",
+    "\n",
+    "# Show first 5 rows\n",
+    "print(data.head())\n",
+    "\n",
+    "# Save to CSV\n",
+    "data.to_csv(\"AAPL_stock_data.csv\", index_label=\"Date\")\n",
+    "\n",
+    "# Save to Excel\n",
+    "data.to_excel(\"AAPL_stock_data.xlsx\", index_label=\"Date\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "IcCo4MeeI_kC",
+    "outputId": "85159790-5809-4f8d-b8cc-4f03efe5d992"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                Close\n",
+      "Date                 \n",
+      "2015-01-02  24.261055\n",
+      "2015-01-05  23.577574\n",
+      "2015-01-06  23.579790\n",
+      "2015-01-07  23.910435\n",
+      "2015-01-08  24.829126\n",
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "DatetimeIndex: 2014 entries, 2015-01-02 to 2022-12-30\n",
+      "Data columns (total 1 columns):\n",
+      " #   Column  Non-Null Count  Dtype  \n",
+      "---  ------  --------------  -----  \n",
+      " 0   Close   2014 non-null   float64\n",
+      "dtypes: float64(1)\n",
+      "memory usage: 31.5 KB\n",
+      "None\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "# Skip the first 2 rows that are junk\n",
+    "df = pd.read_csv(\"AAPL_stock_data.csv\", skiprows=0, parse_dates=['Date'], index_col='Date')\n",
+    "\n",
+    "# Rename the column properly\n",
+    "df.columns = ['Close']\n",
+    "\n",
+    "# Ensure numeric\n",
+    "df['Close'] = pd.to_numeric(df['Close'], errors='coerce')\n",
+    "\n",
+    "# Drop missing values\n",
+    "df = df.dropna(subset=['Close'])\n",
+    "\n",
+    "print(df.head())\n",
+    "print(df.info())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000
+    },
+    "id": "UFUNbSQ1JKSP",
+    "outputId": "4172b22d-75f2-40b6-dbd4-4555f4f387ee"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ADF Statistic: -0.6303067985116851\n",
+      "p-value: 0.8639858434129919\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "from statsmodels.tsa.stattools import adfuller\n",
+    "from statsmodels.graphics.tsaplots import plot_acf, plot_pacf\n",
+    "\n",
+    "# Plot data\n",
+    "df['Close'].plot(figsize=(12,6), title=\"Apple Stock Closing Prices\")\n",
+    "plt.show()\n",
+    "\n",
+    "# Stationarity test\n",
+    "result = adfuller(df['Close'])\n",
+    "print(\"ADF Statistic:\", result[0])\n",
+    "print(\"p-value:\", result[1])\n",
+    "\n",
+    "# ACF & PACF\n",
+    "plot_acf(df['Close'], lags=40)\n",
+    "plot_pacf(df['Close'], lags=40)\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 716
+    },
+    "id": "KaLRag6iJPzo",
+    "outputId": "33bbb26e-dbcf-4182-9f2d-0d2e5953904b"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\Hp\\anaconda3\\Lib\\site-packages\\statsmodels\\tsa\\base\\tsa_model.py:473: ValueWarning: A date index has been provided, but it has no associated frequency information and so will be ignored when e.g. forecasting.\n",
+      "  self._init_dates(dates, freq)\n",
+      "C:\\Users\\Hp\\anaconda3\\Lib\\site-packages\\statsmodels\\tsa\\base\\tsa_model.py:473: ValueWarning: A date index has been provided, but it has no associated frequency information and so will be ignored when e.g. forecasting.\n",
+      "  self._init_dates(dates, freq)\n",
+      "C:\\Users\\Hp\\anaconda3\\Lib\\site-packages\\statsmodels\\tsa\\base\\tsa_model.py:473: ValueWarning: A date index has been provided, but it has no associated frequency information and so will be ignored when e.g. forecasting.\n",
+      "  self._init_dates(dates, freq)\n",
+      "C:\\Users\\Hp\\anaconda3\\Lib\\site-packages\\statsmodels\\tsa\\base\\tsa_model.py:836: ValueWarning: No supported index is available. Prediction results will be given with an integer index beginning at `start`.\n",
+      "  return get_prediction_index(\n",
+      "C:\\Users\\Hp\\anaconda3\\Lib\\site-packages\\statsmodels\\tsa\\base\\tsa_model.py:836: FutureWarning: No supported index is available. In the next version, calling this method in a model without a supported index will result in an exception.\n",
+      "  return get_prediction_index(\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA9oAAAH5CAYAAAB+sEb2AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8fJSN1AAAACXBIWXMAAA9hAAAPYQGoP6dpAACt9UlEQVR4nOzdd3hUZdoG8Ht6em8EEkLvHQQBBRakKMWKLqig7lpwUey6fio2sKyIwqqrIiDqYm+4ioBUUekdqaEmISE9mcnU8/0xM2fmTElmkpnMJLl/15UrM+ecOfOGZTH3PO/7vDJBEAQQERERERERUUDIQz0AIiIiIiIiouaEQZuIiIiIiIgogBi0iYiIiIiIiAKIQZuIiIiIiIgogBi0iYiIiIiIiAKIQZuIiIiIiIgogBi0iYiIiIiIiAJIGeoB1IfFYkFeXh5iY2Mhk8lCPRwiIiIiIiJq5gRBQGVlJTIzMyGX116zbpJBOy8vD1lZWaEeBhEREREREbUwZ8+eRZs2bWq9pkkG7djYWADWHzAuLi7EoyEiIiIiIqLmrqKiAllZWWIerU2TDNr26eJxcXEM2kRERERERNRofFm+zGZoRERERERERAHEoE1EREREREQUQAzaRERERERERAHUJNdo+8psNsNoNIZ6GNQCqNXqOlv8ExERERFRy9Asg7YgCCgoKEBZWVmoh0IthFwuR7t27aBWq0M9FCIiIiIiCrFmGbTtITstLQ1RUVE+dYUjqi+LxYK8vDzk5+cjOzubf9+IiIiIiFq4Zhe0zWazGLKTk5NDPRxqIVJTU5GXlweTyQSVShXq4RARERERUQg1u0Wl9jXZUVFRIR4JtST2KeNmsznEIyEiIiIiolBrdkHbjtN3qTHx7xsREREREdk126BNREREREREFAp+B+1NmzZh0qRJyMzMhEwmwzfffCM5X1VVhX/84x9o06YNIiMj0a1bN7z99tuSa/R6PWbPno2UlBRER0dj8uTJOHfuXIN+ECIiIiIiIqJw4HfQrq6uRp8+fbB48WKP5x944AH89NNP+Oijj3D48GE88MADmD17Nr799lvxmjlz5uDrr7/GypUrsWXLFlRVVWHixIlc3xoEI0eOxJw5c0I9DCIiIiIiohbD767jEyZMwIQJE7ye/+233zBjxgyMHDkSAHDnnXfiP//5D3bs2IEpU6agvLwcS5YswYoVKzBmzBgAwEcffYSsrCysXbsW48aNq99P0sTVtcZ3xowZWLZsmd/3/eqrr9gFm4iIiIiIqBEFfI328OHD8d133+H8+fMQBAHr16/H0aNHxQC9c+dOGI1GjB07VnxNZmYmevbsia1bt3q8p16vR0VFheSrucnPzxe/Fi5ciLi4OMmxN954Q3K9vbt6XZKSkhAbGxuMIRMREREREZEHAQ/ab775Jrp37442bdpArVZj/PjxeOuttzB8+HAAQEFBAdRqNRITEyWvS09PR0FBgcd7zp8/H/Hx8eJXVlaWX2MSBAFagykkX4Ig+DTGjIwM8Ss+Ph4ymUx8XlNTg4SEBHz22WcYOXIkIiIi8NFHH6G4uBh//etf0aZNG0RFRaFXr17473//K7mv69TxnJwczJs3D7fffjtiY2ORnZ2Nd999168/TyIiIiIiIvLO76njdXnzzTfx+++/47vvvkPbtm2xadMmzJo1C61atRKninsiCILX6dNPPPEEHnzwQfF5RUWFX2FbZzSj+9Orff8hAujQc+MQpQ7MH/Njjz2G1157DUuXLoVGo0FNTQ0GDBiAxx57DHFxcfjhhx9wyy23oH379hg8eLDX+7z22mt4/vnn8c9//hNffPEF7rnnHlx++eXo2rVrQMZJRERERETUkgU0aOt0Ovzzn//E119/jauuugoA0Lt3b+zZswf/+te/MGbMGGRkZMBgMKC0tFRS1S4sLMTQoUM93lej0UCj0QRyqE3SnDlzcO2110qOPfzww+Lj2bNn46effsLnn39ea9C+8sorMWvWLADW8P76669jw4YNDNpEREREREQBENCgbTQaYTQaIZdLZ6QrFApYLBYAwIABA6BSqbBmzRpMnToVgHV98oEDB/DKK68EcjiiSJUCh54LTZO1SJUiYPcaOHCg5LnZbMZLL72ETz/9FOfPn4der4der0d0dHSt9+ndu7f42D5FvbCwMGDjJCIiIiIKF8cLK7FgzVHcN7oTumbEhXo41EL4HbSrqqpw/Phx8Xlubi727NmDpKQkZGdnY8SIEXjkkUcQGRmJtm3bYuPGjfjwww+xYMECAEB8fDzuuOMOPPTQQ0hOTkZSUhIefvhh9OrVq9ap5Q0hk8kCNn07lFwD9GuvvYbXX38dCxcuRK9evRAdHY05c+bAYDDUeh/XLuQymUz8IISIiIiIqDm5dck25JXXYPupUmx/Mjh5g8iV3+lzx44dGDVqlPjcvnbavv3UypUr8cQTT2D69OkoKSlB27Zt8eKLL+Luu+8WX/P6669DqVRi6tSp0Ol0GD16NJYtWwaFInDV35Zg8+bNmDJlCm6++WYAgMViwbFjx9CtW7cQj4yIiIiIKDzkldcAAIoq9SEeCbUkfgftkSNH1tpJOyMjA0uXLq31HhEREVi0aBEWLVrk79uTk44dO+LLL7/E1q1bkZiYiAULFqCgoIBBm4iIiIiIKIQCvr0XNZ6nnnoK/fv3x7hx4zBy5EhkZGTg6quvDvWwiIiIiIhCTmcwY/0R9iGi0JAJvm70HEYqKioQHx+P8vJyxMVJGxrU1NQgNzcX7dq1Q0RERIhGSC0N/94RERERhZfHv9yHldvPSo6deumqEI2GmoPacqgrVrSJiIiIiKjJM5qlzX1dQ7ZKIWvM4VALx6BNRERERERN2qajRejxzGqMX7gJ728+6fEajTKIjZeLTwCnfg3e/anJYdAmIiIiIqIm7cHP9sBgsuDPgkq88MNhlFa7b3cbrQli0F7UH1h2JVBwIHjvQU0KgzYRERERETVpUWrpZkp6kwVKuXSqeKN0pnpnGPDFHY3wRhTuGLSJiIiIiKhJi49USZ4XV+thskiTtesa7qA58EXjvA+FNQZtIiIiIiJq0uIipRXtvLIat2uM5iCVtC2NFOCpSWHQJiIiIiKiJi0uQlrRPleqdbvGEKyKtsk91DfOPHUKZwzaRERERETUpEVrpBXtc6U6AEC3VnFIi9UAAEyNGbRN+uC8FzUZDNpERERERNSkWVwqyPaK9pD2Sfj5gctt1wBmS+2V5vxyHTYfK4LgT0XaY9DW+f56apYYtMOETCar9WvmzJn1vndOTg4WLlwYsLESEREREYUTk9k1aFuDbqv4CKgUjshTV0O0S+f/gluWbMOvx4v9eHNWtMmdsu5LqDHk5+eLjz/99FM8/fTTOHLkiHgsMjIyFMMiIiIiIgp7rgH6RFEVACAzIVIStA1mCyJU7vtpbzhSiD9yS8Tn206VYHinFB/f3EPQNrKi3dKxoh0mMjIyxK/4+HjIZDLJsU2bNmHAgAGIiIhA+/bt8eyzz8JkMomvnzt3LrKzs6HRaJCZmYn77rsPADBy5EicPn0aDzzwgFgdJyIiIiJqTlyDdo3R+rxLeixUCsfvv6/89Cfu/HCH23rtmUu34+0NJ8Tn0Wr3MO5VyUn3Y+FY0TbWAIbqUI+ixWgZFW1BAIzunQcbhSoKaGC4Xb16NW6++Wa8+eabuOyyy3DixAnceeedAIBnnnkGX3zxBV5//XWsXLkSPXr0QEFBAfbu3QsA+Oqrr9CnTx/ceeed+Pvf/97gH4eIiIiIKNysPVzo8XhaXARkMhlUChmMZgEf/X4GAHAgrwJ9sxK83i9K40dM2vtf92PhtkbbZAD+fQkgVwD3bgcULSMGhlLL+BM2aoF5maF573/mAeroBt3ixRdfxOOPP44ZM2YAANq3b4/nn38ejz76KJ555hmcOXMGGRkZGDNmDFQqFbKzs3HJJZcAAJKSkqBQKBAbG4uMjIwG/zhEREREROGkssbo9VyUrTKtUshhNJvF485lsCMFlW6vUyt8LJTpq4CjP7kf9zSdPJQq84Gy09bHebuArEtCO54WgFPHm4CdO3fiueeeQ0xMjPj197//Hfn5+dBqtbjhhhug0+nQvn17/P3vf8fXX38tmVZORERERNRc6U2eG5wp5DJxfbZGKY09NUZH6P5i51m31xq83NNN0Z+AxcPv3Z4apIWSrtTxuOJ86MbRgrSMirYqylpZDtV7N5DFYsGzzz6La6+91u1cREQEsrKycOTIEaxZswZr167FrFmz8Oqrr2Ljxo1QqVQNfn8iIiIionDlrZN4pFPTs0iVAqVwVL6dw7lS4V579Bbe3djXZ7cdDmT2BX5bbH0ebkH77B+Ox4YQLaltYVpG0JbJGjx9O5T69++PI0eOoGPHjl6viYyMxOTJkzF58mTce++96Nq1K/bv34/+/ftDrVbD7DRVhoiIiIiouTCarFt7RaoU0DlVqp27i7t2GneuaJdpDW739Dlo27uLa2KAcS8CebuB07+GX9Be87Tjcah6V7UwLSNoN3FPP/00Jk6ciKysLNxwww2Qy+XYt28f9u/fjxdeeAHLli2D2WzG4MGDERUVhRUrViAyMhJt27YFYN1He9OmTbjpppug0WiQkuLjVgVERERERGHOYKtoqxQydEqPx75z5QCACJWjUu0atE8XO8JmabX7Gu/zZToUVeqRGqup/c3NtpCutF2njLB+D6c12jUV0uDPoN0ouEa7CRg3bhxWrVqFNWvWYNCgQRgyZAgWLFggBumEhAS89957GDZsGHr37o1169bh+++/R3JyMgDgueeew6lTp9ChQwekpqaG8kchIiIiIgoo+9RxtVIOhdzRxEwyddxlu64X/3dYfFzqoaL9yR9nMOjFtaiopdEaAEeAVbgE7XCqaJ9YJ33OqeONghXtMDRz5kzMnDlTcmzcuHEYN26cx+uvvvpqXH311V7vN2TIEHG7LyIiIiKi5sRktk4dVynkUDoHbbV0jbY3ZVrvYXrHqRL8pWt6LW9u2y/bXtFW2PojndsODLytjpE3kvx90udG7qXdGFjRJiIiIiKiJssxdVwOpdzzdPHjhVXur7Otw/ZU0bbTGepYq+06dfzQN9bvez6uY9SNyP5hgB0r2o2CQZuIiIiIiJoso9Ma7YQox447zkH7iu7uVenzZToIgiBWtKPV7lVvvamOhsKuU8c7XuHP0BuHfYwR8dbvzlt9UdAwaBMRERERUZNldKpop8dFiMcjnZqhPXBFZ7xz8wAcf3ECuqTHAgBOF1ej2mAWK+I/zbnc7d51dh83uVS0Rzxm/R7bqj4/SnDYK9pxbazfq4tCN5YWhEGbiIiIiIiaLOdmaGlxji7hzuuyk6LVGN8zA0qFHNnJUQCAMyValFYbxNe2SYzE81f3lNxbb/Sxom0P2lFJthdWAYJQ3x8psOxjjG9t/V5yEjjzR/iMr5li0CYiIiIioibLYNtHWymXoUdmvHjcdUsvu+wkW9Au1orTxhOjVJDJZNAopPHIXu32yr5GW6G2ftfE2V5YCczPAo6t8edHCQ4xaNsq2hXngQ/GAoe/D92YWgAGbSIiIiIiarJMFsfU8f7ZCeJxb93E29oq2qdLtCjTWYNyYpQ1KGtU0nikN9YRtI0663dVpPW7JtZxzlAJfHy9Lz9CcJXkWr/HtZYeZ9AOKgZtIiIiIiJqspynjsdGOJqh7T9f7vF654q2vfO4RmmNRWqXinada7R1JdbvkbYp46oIx17a4cBQDRQetD52DdpKdeOPpwVh0CYiIiIioibLaHLsow0A1w+wTpG+8/L2Hq/PiLcG4YtVelhsy5Tltv231UrXoF3HGu3qYuv3qGTHMefHkCGkqi44HhuqHJ3HAcd0dwoKZagHQEREREREVF8Gp+29AGDeNb1w85C26N063uP1EUrr2m29yQKzLWnLZdbXapTSdd11VrS19qCd5DgWmWRdBw0ACpX7axqTc8MzmRyITgVqbJV+hcbzayggWNEmIiIiIqImy3l7L8Bale6blSBWqV3Z12HrTWYItiCqsAXtmAhpHbJKb6r9zfUV1u/OlWLn0C0PcV3T3qwNAPr8FYhKcTzn1PGgYtAOQ1u3boVCocD48ePdzp06dQoymUz8io+Px5AhQ/D999JmBsuWLUNCQoLkuUwmQ7du3dzu+dlnn0EmkyEnJ8ftnE6nQ2JiIpKSkqDT6eoc+9y5cyXjs3+tXbu27h88TG3YsAEymQxlZWWhHgoRERERuTCZpVPH62KvWhvNAoy2irYtZ6NX63jcP7oTLm1vnf5d7qWhmuPNbR297c3QAOnUcXmIK9r2PbRjWwHqKCAy0XGOFe2gYtAOQx988AFmz56NLVu24MyZMx6vWbt2LfLz8/HHH3/gkksuwXXXXYcDBw7Uet/o6GgUFhbit99+c3u/7Oxsj6/58ssv0bNnT3Tv3h1fffWVT+Pv0aMH8vPzJV+XX365T691ZTAY6r6IiIiIiFos16njddE4rcOuMVjXYCts1W+FXIYHruiMGUPbAgDKdLUEbbMJsNgq3s4N0Jwr2jIA1Rd9GldQmG3jF7cfi3Gcc/5wgAKOQTvMVFdX47PPPsM999yDiRMnYtmyZR6vS05ORkZGBrp27YoXX3wRRqMR69evr/XeSqUS06ZNwwcffCAeO3fuHDZs2IBp06Z5fM2SJUtw88034+abb8aSJUt8+hmUSiUyMjIkX2q19f/c+/fvx1/+8hdERkYiOTkZd955J6qqqsTXzpw5E1dffTXmz5+PzMxMdO7cGQBw/vx53HjjjUhMTERycjKmTJmCU6dOSd73gw8+QI8ePaDRaNCqVSv84x//EM8tWLAAvXr1QnR0NLKysjBr1izJ+54+fRqTJk1CYmIioqOj0aNHD/zvf//DqVOnMGrUKABAYmIiZDIZZs6c6dOfAxEREREFn+vU8bo4B22d0Rq07Wu07eIjrb+7lmprKfrYq9mAS9B2qmjXlAMLugO5m30aW8CZbRVtpa16fdlDjnOyEDdqa+ZaRNAWBAFaozYkX4JzAwIffPrpp+jSpQu6dOmCm2++GUuXLq31HkajEe+99x4AQKWqe2rKHXfcgU8//RRarRaAdUr5+PHjkZ6e7nbtiRMn8Ntvv2Hq1KmYOnUqtm7dipMnT/r18zjTarUYP348EhMTsX37dnz++edYu3atJBADwLp163D48GGsWbMGq1atglarxahRoxATE4NNmzZhy5YtiImJwfjx48WK99tvv417770Xd955J/bv34/vvvsOHTt2FO8pl8vx5ptv4sCBA1i+fDl++eUXPProo+L5e++9F3q9Hps2bcL+/fvx8ssvIyYmBllZWfjyyy8BAEeOHEF+fj7eeOONev8ZEBEREVFg+Ru0lQq5WMHW2iraruu5U2OtQftCeY3338Xt07IBR5AFHFt92Zn1wE9P+DS2gLOP0V7RTusG9J9hG1cd68+pQVpE13GdSYfBnwwOyXv/Me0PRKmifL7eXkEGgPHjx6Oqqgrr1q3DmDFjJNcNHToUcrkcOp0OFosFOTk5mDp1ap3379u3Lzp06IAvvvgCt9xyC5YtW4YFCxZ4DNAffPABJkyYgMTERHE8H3zwAV544YVa32P//v2IiXFMS+nevTu2bduGjz/+GDqdDh9++CGio6MBAIsXL8akSZPw8ssvi2E/Ojoa77//vlgF/+CDDyCXy/H+++9DZvvkbenSpUhISMCGDRswduxYvPDCC3jooYdw//33i+87aNAg8fGcOXPEx+3atcPzzz+Pe+65B2+99RYA4MyZM7juuuvQq1cvAED79o7tIJKSrP9YpqWlSda9ExEREVHoGW1rtF235qqNRimH1mB2qmhLz2clRUEuA6oNZhRV6vHjgQIs2ZKLpbcNQodU2++59oq2XAXInbqVR7kEbQCoLvR5bAFz5Cfg3DbrY+etvOwN2iwM2sHUIiraTcWRI0ewbds23HTTTQCsU7BvvPFGyVRvu08//RS7d+8WK7fvv/++GAjrcvvtt2Pp0qXYuHEjqqqqcOWVV7pdYzabsXz5cjH0A8DNN9+M5cuXw2yufT/BLl26YM+ePeKXvSJ8+PBh9OnTRwzZADBs2DBYLBYcOXJEPNarVy8xZAPAzp07cfz4ccTGxiImJgYxMTFISkpCTU0NTpw4gcLCQuTl5WH06NFex7R+/XpcccUVaN26NWJjY3HrrbeiuLgY1dXVAID77rsPL7zwAoYNG4ZnnnkG+/btq+NPkYiIiIjCgcHk3xptwDF9XGewhk2FyzRqjVKBrCRrsezkxWo8891BnCnR4vZl2x0X2YO287RxQFrdttOVWb9XFwMbXgJKT/s81nqpKgL+eyOw+TXrc+egbd9yzFJHozdqkBZR0Y5URuKPaX+E7L19tWTJEphMJrRu3Vo8JggCVCoVSktLxcoyAGRlZaFTp07o1KkTYmJicN111+HQoUNIS0ur832mT5+ORx99FHPnzsWtt94KpdL9r8Hq1avFddHOzGYzfv75Z0yYMMHr/dVqtWTatvPPIvOyFsT5uHMQBwCLxYIBAwbg448/dntdamoq5PLaPy86ffo0rrzyStx99914/vnnkZSUhC1btuCOO+6A0Wj9B+Zvf/sbxo0bhx9++AE///wz5s+fj9deew2zZ8+u9d5EREREFFomizVoK+v4ndCZtfO4EdVepo4DQLuUaJwu1iL3YrV4LL/MaV22fVq2yiVoe9rSyx5uv7kbOPYzsGsF8OBBn8frN/te2XZKVrQbW4uoaMtkMkSpokLy5S1YujKZTPjwww/x2muvSarBe/fuRdu2bT2GTLsRI0agZ8+eePHFF316r6SkJEyePBkbN27E7bff7vGaJUuW4KabbpKMZc+ePZg+fbrPTdFcde/eHXv27BGryADw66+/Qi6Xi03PPOnfvz+OHTuGtLQ0dOzYUfIVHx+P2NhY5OTkYN26dR5fv2PHDphMJrz22msYMmQIOnfujLy8PLfrsrKycPfdd+Orr77CQw89JK59t1fX66rkExEREVHjKtMaxIq2P1PH7ftlV9i6invacrtdirX44xy0BTit1zbZtr51rWhnX+p+M3vQPrnB+r3inM9jrRfXEO28zlwM2vzdNphaRNBuClatWoXS0lLccccd6Nmzp+Tr+uuvrzPcPvTQQ/jPf/6D8+fP+/R+y5Ytw8WLF9G1a1e3c0VFRfj+++8xY8YMt7HMmDED3333HYqKivz+GadPn46IiAjMmDEDBw4cwPr16zF79mzccsstHpuxOb8uJSUFU6ZMwebNm5Gbm4uNGzfi/vvvx7lz1n+k5s6di9deew1vvvkmjh07hl27dmHRokUAgA4dOsBkMmHRokU4efIkVqxYgXfeeUfyHnPmzMHq1auRm5uLXbt24ZdffhH3HG/bti1kMhlWrVqFoqIiSbdyIiIiIgqNnadL0fe5Nfhsh/X3QaWntOxFrC1ol9uCtsLDa9vbgva7mxy9jCR90Upyrd+jU6QvjEoCbv5Sekym8HCDIHKdFt5moOOxPWibOXU8mBi0w8SSJUswZswYxMfHu5277rrrsGfPHuzatcvr6ydOnIicnByfq9r27bU8sTcr87TmedSoUYiNjcWKFSt8eh9nUVFRWL16NUpKSjBo0CBcf/31GD16NBYvXlzn6zZt2oTs7Gxce+216NatG26//XbodDrExcUBAGbMmIGFCxfirbfeQo8ePTBx4kQcO3YMgLUB3IIFC/Dyyy+jZ8+e+PjjjzF//nzJe5jNZtx7773o1q0bxo8fjy5duoiN0lq3bo1nn30Wjz/+ONLT0926pBMRERFR4/v4d+k654SounfgsYuNsF5rD9qeZqG2S4lxOyaJyae3Wr97qmB3GA1c8x9rozTAEXwFi89jbBB7RTs6Fbh7C/CXpx3nOHW8UcgEf/efCgMVFRWIj49HeXm5GLTsampqkJubi3bt2iEiIsLLHYgCi3/viIiIiBrXG2uP4fW1R8XnS2cOwqiudfcrAoB7P96FH/bnIzspCmdKtJjcJxNv/rWf5JrzZToMe+kXyTG5DDg5/yrrk7cuBQoPAVNXAN0ne36j0tPAG70BVRTwZD7wbKIjbM8t9/yaQDi7HVgyBkjIBubsl57b9CrwywtA/1uByYscxy0WwI917i1RbTnUld9/kps2bcKkSZOQmZkJmUyGb775xu2aw4cPY/LkyeL62SFDhuDMmTPieb1ej9mzZyMlJQXR0dGYPHmyOAWYiIiIiIioLvZ11napsR66fXvhOnXc06zz5Gi12zGxQllTYQ3ZgOeKtp2927dJD5z5vREr2rYKutxDlV9h+3MyaB3H/vwf8FI2cHhV8MfWQvgdtKurq9GnTx+v031PnDiB4cOHo2vXrtiwYQP27t2Lp556SlLlmzNnDr7++musXLkSW7ZsQVVVFSZOnMhmU0RERERE5BOTWRpa0xoStD0kbbXCPSqJc4FryqzflRFATKr3N7IHbcEMfDDO5/E1mH1auKcO6Iltrd9LTzmOrfwrYKgEPp0e9KG1FH5v7zVhwoRat3Z68sknceWVV+KVV14Rj7Vv3158XF5ejiVLlmDFihUYM2YMAOCjjz5CVlYW1q5di3Hj3P8C6vV66PV68XlFRYW/wyYiIiIiombE6BK0kzxUoL2xr9G2k3tYo+0pfAPA2xtO4LbOBkQA7h3HXSl8XzceUPZGZ57eP9m2DW/xMesnBz7ukkT+CegkfIvFgh9++AGdO3fGuHHjkJaWhsGDB0uml+/cuRNGoxFjx44Vj2VmZqJnz57YunWrx/vOnz8f8fHx4ldWVlYgh01ERERERE2M0SxtNaX0UIH2JtZl2rnCj7D58k9/4uNfbWvD6wzavof/gDm8CvjoWutjjxXtdtbvNeWAtkR6ztP1VC8BDdqFhYWoqqrCSy+9hPHjx+Pnn3/GNddcg2uvvRYbN24EABQUFECtViMxMVHy2vT0dBQUFHi87xNPPIHy8nLx6+zZs3WOpQn2eKMmjH/fiIiIiBqXa0XbH24V7Tq2BuveStr46njeResDVRhWtH98zPHYU3BWRwFxbayPi49Lz6migzeuFiagH1lYLNa/7FOmTMEDDzwAwLq10tatW/HOO+9gxIgRXl8rCILHtvoAoNFooNH4tuZCpbL+ZdZqtYiMjPRn+ET1ZjAYAAAKhSLEIyEiIiJq/nadKcXBvPovJ02OkVaa69qCO0qtQHykSlzTrRRsy1rrqmjLQ/C7YXJ7oMLWaLrGS2fz5A7Wa4qPA9mDHcfVUcEfXwsR0KCdkpICpVKJ7t27S45369YNW7ZsAQBkZGTAYDCgtLRUUtUuLCzE0KFDGzwGhUKBhIQEFBYWArDuwewtwBMFgsViQVFREaKioqBUcroNERERUTCdKdbi2rc8Lzn11aXtk5EUrUZJta1YUkfSVipkSI5RO4K2xWA74XsDtkYT19rxuPiY52sSc4DcjUC5y0xhFYN2oAQ0FajVagwaNAhHjhyRHD969CjatrV2txswYABUKhXWrFmDqVOnAgDy8/Nx4MABSQO1hsjIyAAAMWwTBZtcLkd2djY/1CEiIiIKsnV/XnA7tvS2QX7dI0KlwA0D2uA/m04C8NwMzZlKIUdKtAYni6oBAGqxou3DDNrpXwAfX+/X+BrE3gitNhHx1u/6SulxVrQDxu+gXVVVhePHHXP5c3NzsWfPHiQlJSE7OxuPPPIIbrzxRlx++eUYNWoUfvrpJ3z//ffYsGEDACA+Ph533HEHHnroISQnJyMpKQkPP/wwevXqJXYhbyiZTIZWrVohLS0NRqMPf9GIGkitVkMuD2jLAyIiIiLyYMepUsnzR8Z1waguaX7fp32qYz1yXUFbKZchxmm6uUqwZQxfKtodA5NxfGY21H2NxrbmXO8y/Z5rtAPG76C9Y8cOjBo1Snz+4IMPAgBmzJiBZcuW4ZprrsE777yD+fPn47777kOXLl3w5ZdfYvjw4eJrXn/9dSiVSkydOhU6nQ6jR4/GsmXLAr6+VaFQcM0sEREREVEzsS23BD/sz5ccUynqN6MwzqkhWl1rtJUKuWRdt8pe0Vb5UNFu7BmP9j20a6OJtX7XVwEWs+M4K9oB43fQHjlyZJ0dlm+//XbcfvvtXs9HRERg0aJFWLRokb9vT0RERERELdT/XEI2YJ3WXR/OncfrWqOtUcqRHO2oXp+VtwYG3g6kda/lVSHiXNG2TxF3pYmxftdXSqePc412wHCuKxERERERNQlag3u1Nlpdv7ZTzntpe+uz89AVnZESo8aj47oixami/WVpLEacT8Sr+uR6vXdQ2ddop/UA/r7e8zViRdslaIeiS3ozxRbJRERERETUJGgNZrdjqXH16/zdJtEx7XvP2VKP18we3Qn/+EtHyGQyJMc43kcVvxslEauxIf9PXJ5v7fKtlCshl3mpY2rU7scKd0ueyhCgKebmKuv7DbgJMFcChXvcr9FftF5jKgMKdjjGZ6rwfH0j6Z7cHWqFhz+rJohBm4iIiIiImoQao3vQToutX9B2Ds5qpfdKrr3anRDlmGpuquwBTdpqnNHtx99+/lvdb5aZ4X7sx1t9H6w/FLb3+/M961etY9ICfzztGJ/xBPDjLcEZlw9+vu5ntIppFbL3DyQGbSIiIiIiahI8VrTrGbQB4Pt/DMebvxzDY+O71nmtc/M0iyENxrL+UCXsAgC0jmkNlVwFAV56WRUfdz+W3FF8WFcPLL+UnwPMeiC2lfc112aDYw/tmHSgyrZlmirK+roQUTSjqesM2kRERERE1CR4CtrOTcr81atNPN67daBP1zqv6QaAmoJrMKZzJ0zudgnG5oyt/cVzXZqSRcQDf1vlz1B999ZQoPAUcMvbQIdRnq8pPw+8bmvklhgBlNqazHUcA1z7ZXDG1cIwaBMRERERUZPgaep4XR3DA8W5SzkAQFBhStu/44qcdP9vVlMemEF5Yu86XttaZ3vXcQAozXU8trj/+VL9sOs4ERERERE1CToPQbuxuFa0gfrv4Q0AKD7RgNHUwt5FXBnh/Rp1rOOx8/RyfSXw7kjglxeCMrSWhEGbiIiIiIiaBKPJErL3VinkyIyXhld1PffwBgAUHWngiDyovghUFQCQAamdvV8nlwPdJlkfG7WO4+d3AHm7gU2vBn5sLQyDNhERERERBYWnqd4NYTCHLmgDwEvX9ZY8VysbEKe87N3dINVF1u+RiY69sr1J6RL49ycRgzYREREREQXcgp+PoPfcn7H3bFnA7mmwVbQfG98VESo5/j2tf8Du7QvXYK3ytaI9wVYhnvSG41gw1mmbjdbvvuxF7bxOuz6MOmDplcCGlxt2n2aKQZuIiIiIiALuzV+Ow2C24N/rPWxtVU/2ivbE3q1wYO44XNW7cbeiqnfQHnwn8NgpYMBMoPvV1mOBDtrVF4H8vdbHClXt1wINr2gf/Qk4/SuwYV7D7tNMses4EREREREFlPOUcbdu3Q1gNFv3m1Yr5VA2ZH10PbmuyfZr6nhkou17gvW7riwgYxIt7OVYb+1L0O44uvbzZhOgqCUuauIcj3Wljp+PALCiTUREREREAXa8sEp8rFYGZi2y2SLAbLEF7RCEbADQuATreo0jwrandmV+AEbkxLmpmdyHoK3U1F7VNunqeL1TY7iSXO/XtVAM2kREREREFFCH8ivEx8VVhoDc0+DUcVzVkCZkDeA2dbw+HyLYg/bOpUDBgQCMCoAgSJ/7skYbAK54zvs5Y00d7+nUmK7kpG/v14IwaBMRERERUUD9mV8pPi6uDlDQduo4HqqKdoxGOpW6QRVtANj8rwaOyMbkEoprm/LtrMt4YOqHgEJT9z1dCU4d5UtZ0XbFoE1ERERERAF12KmiXRKooO1c0VYEYWssHyRESSvF9aqsRyQ4HisjvF7mF32V9LkvU8ftuk8BZu/wcM9K92POLE5Bu+SU7+/XQjBoExERERFRwAiCgMMFjqB9sUofkPsabRVttUIOWTD2oPaBQi6TVLHrV9FOcDxWeqgk14fBJRT7++eTkA2k9ZAeq8yr/TXO09XLz/j3fi0AgzYREREREQXMhQo9yrRG8bneaKnlat/ZK9p+dfoOgpgIx7Rsn7f3cuY8dTxYFe3zu/y/R0ya9Hn5+dqvd546btB6v66FYtAmIiIiIqKAuX/lbgCODt0GswWCa7OuetDZtgyLUCkafK+GcF6nrZDXo7Ju394LCGBF2yVoW4yer6uNKlL6XFfi/VqLBfhkquO5kUHbFYM2EREREREFRLXehD9yrQFN6RRC7dty+epsiRb7zpVJjmkNJgBAlDq0QTs2wsdGY95oYh2Pfe0OXhfXina9uHxosPdToGC/50svHpU+Z9B2w6BNREREREQBUap1ND6Ldqr8Gs3+Be3LXlmPyYt/xdkSR4DTGqwV7SYftCMTHY9VUQ27l53rGu36cK2CFx0G3hnu+VrBZTmA89RxsxH46Hrg238AZ7dZq98tEIM2EREREREFhPPa7IQoR+drYz3DlnP38nAJ2jEaPzp6e6LUABm9rY89VbSPrwNOb/Xvnq4dwmMz/R+X2Y/u8M7rswHAqHM8PrEeOL4G2L0CWHIFsO9T/8fSDDBoExERERFRQDhXtEd1cTTXMpp8D9rO67lfWX0EMz7Yhiq9yWnqeAMryg3U4Io2AKTbOny7BtaqIuCja4GlE6RdvetinzreaRzwl6eA2/7n/5jMJs/HLWb3Y0aXPbaN1Y7xlp2Wntvxgf9jaQYYtImIiIiIqN6+2HkOP+zLBwCUOlW054zpLK7TNvmxRtt5mvnxwipsPFqEAc+vQXGVNcRHNvWp4wAgt/0MFpdw67ylltmPhmb2inJsOnD5w0BSO//H1PsGz8ddG60B7muyBYujIu4arNXR/o+lGQjtx0FERERERNRk5ZXp8PDnewEAY7qPR5mtoj2+RwYi1QooFTKYLIK4NZcvDGb3a/UmC1744TAAIC6igVO3G6hjWkzDbyK3xTDXKfUmp+nbFhMAH5qlnd0GrH/B+rgh24X1uwWIz7J2H//oOkeYrqmQbkkGSKeK25kNwM9PAYWHpMflLTNytsyfmoiIiIiIGuxEkaPamV9Wg9JqaxU2MdoahlUKOWqMFhg9hGdv9EYPU5WdtIoP0N7T9fTXS7Jx7EIVhnVMqf9NZB4q2pUXgFObHc993aJryRWOxw3pYi5XAB1HWx8/dhpY0A3QXnRf/w147jJ+fiew7T/ux0017sdaAAZtIiIiIiKql+OFjqCdV6ZDmc5akU2IsgY+lcK6UtWfqeOeKtrOWiWENmirFHI8f3XPht3EXuWtKQfObgfaDAS+uRs48YvjGm9rpmsTqH25lWpHaPcU+D1OJ/cSqA3VgRlTE8OgTURERERE9XLMKWhPX/KH2A8rMcpe0bau0V5z6AI6p8e6vd7VhYoaHCmQVlDjIpSoqHGEziu6pTd02KFnX6P9x9vWr2velYZswPeKtjNFgII24DS93UPgL8l1P+ap8g0A2mJrozSZzPP5ZorN0IiIiIiIqF6OXXCEK+cm2faK9oUKPQDg1dVHcLFKX+u9qvQmjPrXBsxcul1yPCfF0Uzrhat7Ii0utBXtgJC7NHTbt9J9S643+gB5e/y7b6Aq2gAgt0VFT13Hi4+5H9OXe75P2WlgXmtgw0uBG1sTwKBNRERERERu1v9ZiCmLt4hhev2RQhzKc+xrXa03SZ47S4xyXyt833931/p+m48WiXtlO4uPdDQ/i9E0kwm5MpegLVe5h29TDbBymn/3DWjQrqWiffG4+7Eaz38XAFi3/9owPzDjaiIYtImIiIiIyM1ty7Zj77ly3LF8B5b+movblm7H3R/tFM8fOF+Oag/BGHBMHZ82OFs8tvVEsWSPbFcH8twrohEqOSb3cVR6m03Qdu3ELVd63s6r4ryfNw7g9GxvQdtiBkpOul9vnzre7nLgyQKgxzXu15SfC9z4whyDNhEREREReXWmRItnvz8kPraHZW0t3cGToq0V7XnX9JIcd94j21WZVho0v541FAfmjkPXjDjxWHSzCdquFW2F58pxXQQBkDlFOl1Jw8YlGZM9aLv871x2BjB7WAagt1W0NXHWLcJuWAbEuKynP74ucOMLcwzaRERERETkM71tT+zatuHKcNqCa4xT8zKdlwo4YJ2KDgBPXtkNp166Cv2yE6FUyCX3CvXWXgHjWtFWqPxvflZ8wjodW3Dq0l59seFjs7N/GOAatL1V2e0VbVWk41iUyxZox9cGZmxNQDP5SIiIiIiIiBpDcbUBchmgqyVoR6kdMWPxtH7o+tRPAKyviYfK42uq9Nb7uVatU2M1WD3ncpRUGySN0Zo0mUu9U670fzuv5ZPcQ2/boQ0bl+uYAODiUeva73aXWZ9728bLqLO9zul/36gk6TX+Nndrwhi0iYiIiIjIjUIug9nD/tfT3/sdp4q1GNUl1e3cpD6Z6NMmXnIsQqVAbIQSlTUm/LA/HxcqavDQ2M7QKKXTp+0V7WiNy7RqAF0y6t4arEnxtEbbXtFWqAGzoe57uIbsGz8GulwZmPEBjoZtq5+wfr93O5Da2fO0cQAw2Y47f4gQ7VLRNukCN74wx6BNRERERERuVArPQftUsRYAsP5Ikdu5RX/t5/FekSoFKmtMeH6Vda13j8w4TOnbWnJNtcEWtNUtIKIoXKr6zs3QfA3arrpNbPi4XMfk7MIBa9A2eQna9gAudwrarlPHTQbg6GrgwkFg+APNem9trtEmIiIiIiI3KkXgokKUWlql3n2mzO2ai5XWoJYQ5XlqebPiug2XTAbA9qGGocpxPK5Now3JjWvDtmrbByvePgQw2Y47V7Sjkl2uqQE+mQqsexY4vTUw4wxTLeDjIiIiIiIi8pfax6DdLzsBMgCPje/q9ZpIlyr1nrNlkucl1QbklVvX/ja7aeKeKFyCtsJ933EA0uqwM3/Xc9eHa0VbW2z9bvKyRtvsw9Rx52nn+lr23W4GWNEmIiIiIiI3Mh+n9fZpk4CvZg3D4PbJXq9JiZEGyUN5FdCbHM3UDtr20G6XEo3YiBZQ0XYN1s7Pr1rgqGR7C9Sua53TugdubHauQds+td1UV0XbqRLu2gzNmWtDuGamef90RERERETkt2MXKnGxystaXFjXXD8/pQdGdE7F/aM71Xm/jDjptlwGswWnbWu9AeDAeWt1s0dmHFoE1w8xjE7Bud8twPTPrY+9bfklWSctA65fGtDhAXAP2vax2KvS6b2Adpc7rvNU0XZdo+3Mvh1YM8WgTUREREREomq9CVe8vqnWa/51Qx/ccmkOlt9+CRKjvUx7dpLhYf9r5z217RXtHpnxbtc1Ty5B2zk4K1SOZmle10Pbpm/LlcAjx4E079P26811jba9ov3bW9bvaV2BGd87thQTx+T0OnWM9/sbqgMzzjDFoE1ERERERKL3Np/0eHzupO6IUiuwdOYgXNW7lV/39BS09SaL+Ph8mbWi26657JPtL/tUcJnCWu0Wq8Tepo7bgrkq2n0ddKB4CtrVF4HKPOvz42tt19k+FPDUDE3l/r+7yLnpWzPkd9DetGkTJk2ahMzMTMhkMnzzzTder73rrrsgk8mwcOFCyXG9Xo/Zs2cjJSUF0dHRmDx5Ms6dO+fvUIiIiIiIKMAWrj3m8fj1A7NwYO44jOqa5vc9XaeOA5Cs0S6ssAbH9DiN23XNkuvU8dLT1u/2tdr2796mjtunmrt2Lw8k16njVReAX15wPO8wWnqdOHXc6WdTRXq/v0Hr/Vwz4HfQrq6uRp8+fbB48eJar/vmm2/wxx9/IDMz0+3cnDlz8PXXX2PlypXYsmULqqqqMHHiRJjNZg93IiIiIiKiULiyV4b4WKOUQy6v377H6Z6CttGCGqMZVXoTCiut047TPFzXLLkG7fM7rN/tYVWcOm4EBPe9zB0V7SD+ebkG7T9XATud1oKPf8n6XeFa0XaqhCtrCdqWRuicHkJ+b+81YcIETJgwodZrzp8/j3/84x9YvXo1rrrqKsm58vJyLFmyBCtWrMCYMWMAAB999BGysrKwdu1ajBs3zt8hERERERFRELROcAQlZT1DNgC08rRG22jGxEVbcKGiBkazNUzGRrSU3Ye9/FkKtun0YsgVAIsZULj8uRhsjcRUUUEZnXQMHrQbAcSkSq/z1Ayttg8CmnnQDvgabYvFgltuuQWPPPIIevTo4XZ+586dMBqNGDt2rHgsMzMTPXv2xNatnjct1+v1qKiokHwREREREYUzg9Ma5KYqWuMIW75u9+VJkoeGabP/uxvHC6tQWeMIXJEqhdt1zVLbYbWfVzhtceZp+rh9T+vauno3VG1BOzrV8dg+Vntwdg7aLbiiHfCg/fLLL0OpVOK+++7zeL6goABqtRqJiYmS4+np6SgoKPD4mvnz5yM+Pl78ysrKCvSwiYiIiIgCZsXvp9H1qR+x7vCFUA/Fb/Z10i9d2wsxmsBUmGUyGR4d3wU3DGhT63UqRQvp1RybDjx8DLj8Ec/n5U5B297tu/Q0sOlVYM9/gWpb0I72vnd5g9W2/tu5AZvcZd9z5yZqtd2jmQftgM7N2LlzJ9544w3s2rXL70+8BEHw+ponnngCDz74oPi8oqKCYZuIiIiIwtZT3xwAALy76SRGd0sP8Wj8Y7EtCe7VJh4Xq7xsL1UPs0Z2BAB8vpNNkAEAMWmAJtbzOYWHoL12LnDwK+vjzralvFFBDNqKWrZtc66ku3Ynd65o15YJLc27P1dAPzLavHkzCgsLkZ2dDaVSCaVSidOnT+Ohhx5CTk4OACAjIwMGgwGlpaWS1xYWFiI93fM/QhqNBnFxcZIvIiIiIqJwJDg1r9IamlaYEAQBVbap3NFqJS7vlIJHx3fBBzMHBuw90mJbSGdxX8i8TJWXKxyB1T51vLrIcf7sH9bvCW2DN7bagrZzJV3hUtGWuUTMqxYAQ+8Duk60PrdXwL11VG8mAlrRvuWWW8QGZ3bjxo3DLbfcgttuuw0AMGDAAKhUKqxZswZTp04FAOTn5+PAgQN45ZVXAjkcIiIiIqJG5xyuzRYPHaPDWO7FauiMZmiUcmQmREImk4mV6ED5/O5LMeLVDQG9Z5PlWg2WnFNZG4zZK9r2Lb0AQFdi/Z7WPXhjq23ad1QtU8ddg/agO6zfDVogbzeQuwnY+BKnjruqqqrC8ePHxee5ubnYs2cPkpKSkJ2djeRk6fQFlUqFjIwMdOnSBQAQHx+PO+64Aw899BCSk5ORlJSEhx9+GL169XIL6URERERETU2x03TrBvQPC4k9Z8sAAD1bx0OtDM566bbJ0RjTLQ1rDxcG5f5NimvV2Pm5wha07ZVfU43769O6BnFsKu/nnNdo11XRtlNHATnDHNX4Zh60/f5/z44dO9CvXz/069cPAPDggw+iX79+ePrpp32+x+uvv46rr74aU6dOxbBhwxAVFYXvv/8eCkUL6TJIRERERM1WUZVefGw0N63O47vPlAEA+mUlBPV9pg9xTHm+fVg7xGiUuHlIdlDfMyypXLpyz1jleOy8lzYgrWgDgDoGiA9i3yqf12i71G69BW3X65v5Gm2/K9ojR46UrDupy6lTp9yORUREYNGiRVi0aJG/b09EREREFNaKnYK2ydy0po7bK9p9sxOC+j6pMY5pyV1bxWLXU1dApWhi5f9AcJ6ePehvQPZgx3O5S9B2rWindgnulAmz0xrqKf8Gvr3X8Ty6lqCtr2MrZjFoN++KdkvZEZ6IiIiIqFEUVzumjhuaUEW7xmjG4XxrSOob5Ip2WpwjYEarlUGbph72lBGOxxHx0nMKl6ZhrhXt1G7BGxcAGKocjzN6Sc9FJDgeu04dF+r4O28P2ubm3Qythf6NJiIiIiIKjuImOnW8sEIPk0VAhEqO1gmRdb+gAZKjHUHbYG7eU4hr5VzR1rjsrCQGUlvl11NFO5j0TkHbdYq63ClGRiZKz9VVqbY3gGvmFW0GbSIiIiKiAHLee7opTR3XGa2BN1qthCzIXdwUcsf9EyJrWQvc3NVa0bb9uZgNgCC4V7Rj0oI7Nn2l43FUkvfrelwDxLV2PK9r7bVYqW/eH7AwaBMRERERBdBFp4p2U5o6rjVYK4wRqsZpULx4Wj/ceXl7jOic2ijvF5YkQdulou08ddxsAODyoY06JqhDw7D7rN/73WL9Pnmx9fv0L6TXxaQBDxx0PK+zos012kRERERE5KdSraOi3ZSmjuts+39HqRsnaE/snYmJvTMb5b3ClvPUcdeKtvPUcddqNgBoghy007oBT5wH1NHW5/1vsX554jwDgkEbAIM2EREREVFA2QMr0DSnjjdW0CYASqe18AltpeecK9qe9tBWaNyPBVp9wnxdU8JbyBptBm0iIiIiogByni5usgiwWATI5eG/dZXW9gFBY00dJwDJHYA+fwXiMoGUTtJz9iBtqvFc0a5rv+pQqTNot4yu4wzaREREREQBpDdKp4tXG0xQKeRhH2Dta7RZ0W5EMhlwzTuez9mnktdUOCraUcmAttj6OC5Mp90LdQRtVZT1u8nDhwfNSJh+DEJERERE1DS5NkCbsvhXdH3qJ/y4Pz9EI/LNrtNlAICspKjQDoSsxKBdDujKrI/lSmDm/4CbPgESsry+NKTqmhKuibV+ry4GTm9ttpVtBm0iIiIiIj+dK9XieGGlx3OuFe2TF6sBAPd8vAt7z5YFe2j1tvdcGQDgsk4tuAt4OLEH7YtHgR8fsT6uugDkDAO6XhW6cdXF16BdcQ5YOgFY91zwxxQCDNpERERERH4QBAHDX16PMQs2ocypw7id3uR96uz+8+XBHFq9CYKAk0XWDwS6pMeGeDQEwBG0d68ACvaHdiz+qGuNtsZlG7OtbwZvLCHEoE1ERERE5IeKGkfF7lyp+zpTg8n7ll6nbNXtcFOlN4lT3tPiGqGbNdXNdbsvAIjJaPxx+KrNIOv3fjfXfp2mZXyQw6BNREREROSHokrHVktag3v1Tl9L0H5/Sy7MlvDb8qtMa10nq1GGf9O2FsNT0L5xReOPw1czfwD+sQPoPK726zSxgFzVOGMKIQZtIiIiIiI/FFbqxcelLlPHzRYBpjqC9Bc7zwZkHIIQuMBuD9qJUeqA3ZMayFPQjm3V+OPwlVLjvkWZJ3KFdVuzZo5Bm4iIiIjID0VOQdt1jbbztPFoL9tkfbXrfIPeXxAEfPzHafSa+zMWrTuGf3yyC4fyKhp0z6Iqa5U+Iar5VxqbjMgE92Mx6Y0+jKBI7hjqEQQd99EmIiIiIvKDc9AuqZZuTeTcCC1ao0S109TyV6/vjUe+2IeSavcGav6896AX14rPX1tzFABQWWPC8tsvqdc9jxRU4rPt5wAAXTJaxvrZJsG1oh2VAiibyYyDlM6hHkHQMWgTERERUZNRVKlHjEaJSC/V4sYag51rRdu+Plshl7mNcUQX67ZZx4uqUK03IVrj/6/i728+6fH47yeL/b4XYJ3qfuWbm8V1471ae5iuTKHhGrTjwnjauL9aQNDm1HEiIiIiahLs1dwh89eFfBx2rmu07VPHNUo5lHKZ5FxabARaxUdAEIAD9dzmy9v6b73JgkKnJm2+qqwxSpqzMWiHEdegHc7rs/3FoE1EREREFB52ni4FAJTrjHVcGVxFVY6gXVzlWtG2ThVXK+WSjuSPju8CwBFk67OftiAIOHqh0uv5dYcL/b6n659lDwbt8OG633RsGG/t5a/MvkB0qu2JDDCbaru6SWLQJiIiIqImQaVwVIgD2XHbX4UVjqB9waWKXGN0VLTzyx3nZo20Nn/qalsDfbIe+2l/uycPm49d9Ho+r8x9T++6OAftmUNzEFOP6ewUJHKX5RHNqaItVwAPHbFV7QWgYG+oRxRwDNpERERE1CQoFY5fXWvbqzrYnCva+WXSoG0w24O25zXkcZHWrt5avf8VvCVbcms9v+iX4/hsu39bh9mDdpf0WMyd3MPvMVGQJeY4HjenoA1Yw3b2UOvj01tDO5YgYNAmIiIioibBec1zjdFcy5XBYzRbJF3Di6sNKKysweF86/ZaeltFW610/JodF+GoEkeprY+du5H7ql1KdJ3XPLfqkM/3KyivwS1LtgEAMuIj/B4PNYIZqxyPxanWzUjbS63fm2HQ5twQIiIiImoSnGeLaw1mJEQ1/hiWbz0lPo7VKFGpN2HIvHWwCMAXd18qrtHWOAXtdqkx4uNojbXSXV2PinZSdN1bO7VPrTuM2z3+1T7xcbdWcbVcSSGjinQ89rSvdlPXdpj1+8mNgMUCyJtPHbj5/CRERERE1KwZzY7p4roQVbRf+OGw+DjHVmG2N+3+evd5seu4WinHUxO7IyVGjddu6C2+JroBFW3XKv7GR0biySu7YdbIDuKx7CTfP304mFchPu7WivtnhyWFyvFY0wz/N2rVB1BFAcZq4JUc4MLBUI8oYBi0iYiIiKhJkATtegTVQMtOlobag3kVKLOtedYo5bhjeDtsf3IMOqY5AlKUraJdnzXazl3M7xvdCW2To/H3y9vjbqegbTL71iROEATJNmWsaIcpuXPQbob/GylUAGxLQmrKgei0kA4nkBi0iYiIiKhJMDqFSIM5dM3Q7Nq6VI/3nC3Do19Yp2Pbm6HJZNK9tGM11uBUUeP/FmVagzWcT+iZgXtHOcJ1XIQKr1xnrZr/dLAAe8+W1Xkv1+7l7X1Y/00hoI4Cel4PdJssbYzWnBidOvDHNJ916AzaRERERNQkmCyOcG2xhGZ7r1a2pmHPT+mBtsnep2k7N0NzlhJrXWd9oULv989gr2iP75nh1tVcpXQE+in//rXOe32565z4uHurOElHdwoz1y8BblwBuHxoQ+GN/48iIiIioibB4LSllzlEQdve5Kxbqzhk1bIeWuMtaMdoxMff7j3v13vbg7a9c7kzlZ9B2fn612/s69driahuDNpERERE1CSYnMJ1iHK2uH+3RqlA22Tv06297aPtHHC35Zb69d46MWi739s1aAtC7X9AFqfzndJiarmSiOqDQZuIiIiImgTnZmiWOoJksIhBWyVHqzjve097mzoOADcOzALg/0xgrdG6RjvSQ9BWuwTtUm3ta8AvVNQAABZM7QO5nFOSiQKNQZuIiIiImoRQTx1/f/NJlFQbAFiDbW0B1dvUcQDo2draPbq4Su/1Gk+0et8r2vYg7U1BufV8Ri0fFhBR/TFoExEREVGT4Lyll7mRK9q/nSiW7KGtUVl/jb6kXZLH62sL2sm2ddrFVQa/xmBfox3tcY22NPQX+Bq04xm0iYKBQZuIiIiImoTiakcwrWsNcqD9fKhA8jzCyxpsu9qCtr0hWnG1ARuPFuGBT/egXFf7VG9BEKAzWoO2p6njrtX1j38/jfNlOo+V/8oaI6ptoZ1Bmyg43D8OIyIiIiIKQ6VaR9Bu7G20V247Kz6O1SiREKVyuyYjLkKsJEd4CMN2yTHWLb4uVukx44NtAID4SBXmTu7h9TVVepP4OEbj/it8x9QYRKsVYoBee7gQaw//ApVChqEdUvDSdb3QKj4SALD+SJF4H08dzImo4VjRJiIiIqImoaTaOWg3bkXbec/sDmkxkHnoZOY8XXts93Sv90qJtla0K2sc4fl8ma7W97dXvNVKOSJU7iE+MVqNHf93Be4Z2UFy3GgWsPFoES6d/4t4j/v+uxuANLwThUzXidbv3a8O6TACjUGbiIiIiJqEkhBOHdc4hduOXrbDGt4xBQBw06AsdEyL9XqvuEgllC5Tvetq/G0PyfGR7pV0u0i1AlmJ3vf23n2mFKXV/q0LJwq6a94BrlsCTPl3qEcSUJwrQkRERERh79TFahzMqxCfN3YzNJPTXPWBbRPFx3ERjl+nn5vSA7vOlOHqvpm13ksmkyE5Ro0LFY6u4/I69vryJWgDQEa8ptZ7fLnrXK2vJ2p0mlig1/WhHkXAMWgTERERUdgb+a8NkueNPXXcZLa+X1ZSJK4f0EY8/sykHiioqMEdw9uhfWoM2qd6rna7SonR+BW0jxdW2V6nrvW6tFjvzc32nC3D0l9Pic+frWVNOBE1DKeOExEREVFYs29F5czS2BVti7Wi/er1faB02rM6KykKq2Zfhmv6tfH2Uo8G5Ui3BbPn7GMXKjHspV+w4vfTkvN/5JYAAC7rlFrrfaM9NEqz23O2THz8wcyBmDE0x/cBE5FfGLSJiIiIKKzdtWKH2zFLI3cdN9kq6K77VdfX+J4Zkuf2ivbLP/2J82U6PPXNAcn5k0XVAICuGd7XfgNApIdGaXa7z5QBsHZN/0tX783aiKjhGLSJiIiIKKztPVfudqzx12hb308pD8yvz8nR0ing9qnwnn4si0VA7kXr1PEOdUxNj1C5j2/64GzJ80p2GycKOgZtIiIiIgpbBpPn0rWlkdZoF5TX4Jc/L8Bga4amqKs9uI/USumv4VqDNfx62rorr1yHGqMFKoUMbRIja72v8+tTYzUY3yMD947qiOha9vUmosDzO2hv2rQJkyZNQmZmJmQyGb755hvxnNFoxGOPPYZevXohOjoamZmZuPXWW5GXlye5h16vx+zZs5GSkoLo6GhMnjwZ586xAyIRERERSR3Mc69mA4AvObtca8TV//4VS3/Nrff7j/zXety+bAeKKq2Ny1SKwNSpXO+jNZgBADqjWTxm73RunzbeNjlasj7cE41TgL/r8vZ455YByEyIxP/uvywg4yYi3/j9L0V1dTX69OmDxYsXu53TarXYtWsXnnrqKezatQtfffUVjh49ismTJ0uumzNnDr7++musXLkSW7ZsQVVVFSZOnAiz2ex2TyIiIiJquc6UaAEAl+Qk4c/nx2NcD+vaYl+mjr+98QT2nC3Ds98fqtd7G80W1BilFXVlgNZou1a07QHbvo0XAPx2shgWi4ATRfZp49F13lfm1L3cufreNjka6XHWrb/UAfqwgIi883t7rwkTJmDChAkez8XHx2PNmjWSY4sWLcIll1yCM2fOIDs7G+Xl5ViyZAlWrFiBMWPGAAA++ugjZGVlYe3atRg3blw9fgwiIiIiao6MtrXRURoFIlQKMTz6MnW8osZY5zW1OVJQ6XZMGaCp464V7WrbuuniKseWX7cs2YbnpvQQK9q+bh1m57pl2PLbL8GLPxzGg1d0rs+QicgPQf84q7y8HDKZDAkJCQCAnTt3wmg0YuzYseI1mZmZ6NmzJ7Zu3erxHnq9HhUVFZIvIiIiImr+7NOn7QHXHh592Ue7Ieu41x66gImLtrgdr2vqtq80rhVtgxmCIKCwUi85vviX4zhpa4TWPqXuirazhCiV5HnXjDisuGMw+mUn1mPEROSPoAbtmpoaPP7445g2bRri4uIAAAUFBVCr1UhMlP4fPD09HQUFBR7vM3/+fMTHx4tfWVlZwRw2EREREYUJo0Xa7dsetH3ZR9uXMO7NwnVHPR5XBamirTWaUaEziWu17fQmizh9PsfHoP30xO64slcGruzVKiBjJSL/BS1oG41G3HTTTbBYLHjrrbfqvF4QBMmaEmdPPPEEysvLxa+zZ88GerhEREREFIbM9oq2bW20OHXcl6DdgC3ASqs9TzsPVNdx1/toDWZ8vdu9ObBcBuSV1QAAshKjfLr37cPb4a3pAwLWuI2I/BeU//cZjUZMnToVubm5WLNmjVjNBoCMjAwYDAaUlpZKXlNYWIj09HSP99NoNIiLi5N8EREREVHzZxIr2q5Tx+t+bUOmjrs2K7ML1NRxVwaTBXM9NG2zCI7KfEqM2u08EYWngP9LYQ/Zx44dw9q1a5GcnCw5P2DAAKhUKknTtPz8fBw4cABDhw4N9HCIiIiIqAmzN0OzB1x7zvWlou2cs02+JHMnelsX8G6tHAWeSJUCkR72uQ4m5y7kwQr5RBR4fncdr6qqwvHjx8Xnubm52LNnD5KSkpCZmYnrr78eu3btwqpVq2A2m8V110lJSVCr1YiPj8cdd9yBhx56CMnJyUhKSsLDDz+MXr16iV3IiYiIiIgAR0BWKaQVbV+q1c5Tx8t0RqTEaHx+X73J+r4vX9cL+eU1SIpWI1qt9FrpJiJy5nfQ3rFjB0aNGiU+f/DBBwEAM2bMwNy5c/Hdd98BAPr27St53fr16zFy5EgAwOuvvw6lUompU6dCp9Nh9OjRWLZsGRSKxv2EkIiIiIjCm33quOua5tfWHMXs0Z1qfa3Z7AjaX+48h7tGdPD5fe1BOy5Chd5tEnx+nT9uH9YOO06XYN+58qDcn4hCx++gPXLkSAi1TNWp7ZxdREQEFi1ahEWLFvn79kRERETUgpgs9u29rJXki1UGAEBcRN2/xtaYHB28Pe2JbWc0W/B/Xx9A+9RoMYwbbEE7mBXspyd1BwDkPP5D0N6DiEKDc1+IiIiIKGyZzNJmaPeMbA8AiNbUHbS1ekfQLqrSe73u+715+HTHWcz/8U9YLAIsFgEG25R11/2uG8MlOUmN/p5EFFh+V7SJiIiIiBqLazO0+EgVAEBnNHt9jZ3WaBIfV+g8b9d19EIlHvxsr/i8qEovvgcAaBqh+dl7tw7E3z/cAQDIiIvA4un98PHvZzC4XRJiI1R4bc0R3DAgK+jjIKLAYdAmIiIiorBltkibocVorCG4qsYEQRAgk3nf19q5ol3uIWgLgoCnvjkgOXa+TIcIpSNcN0ZFOy3W0aRtYu9WSIuNwANXdBaPLbvtkqCPgYgCi0GbiIiIiMKW0aUZWqxtbbbJIkBvsiCilopztcFR0XYN2udKtbjhnd+QX14jOb71+EWkx0UAsE5XV8q9B/lAca6gq9jVnKhZ4P+TiYiIiChsObb3sv7aGqVWwF7ErqwxeXsZAEBrcFS0y3RGscEZAOw4VeoWsgHgXz8fxZliLQCgTWJkrRXzQIlzCtrBfzciagwM2kREREQUtlyboclkMsTYGqFV6b0HbUEQJEFbEIDCSkewNpotnl4GADhbYg3aWUlR9R+4H5w7qPuy9pyIwh+DNhERERGFLb2HbbZibUG7ssZzgzMAMJgtMNumnSdGWSvG50t14nmjWbolbfvUaPFxbnE1AKBtcuMEbXujNwDQGRi0iZoDBm0iIiIiClta2zrraLWj6htjqwC/sfYYBEHw/DqnRmjtU2MAADe++ztqbBVjg0kaaOeMcTQf23OmDADQNikajU3LoE3ULDBoExEREVHYsgfPSLWj6Zl96vi6Pwvx04ECt9fklenERmhqpRwZ8RHiuS3HLgKAuE+2454KJEerAQA7T5cCALIbqaLtjEGbqHlg13EiIiIiClv2NctRzkE7wtE87HhhleT6ldvO4PGv9ovPo9QKRDl1Jl+0/jh2nilFtFrarVyjVCA1VoPiaoMYwrMbaY22M4uXCj0RNS2saBMRERFR2Kq2NTyLcpo6bl+jDQCusdQ5ZAPW7cCctwDbe7YMb284gV226eF2CrkMqU77WSdHq9ExLaaBo/fd0xO7IyVGg39e2bXR3pOIgocVbSIiIiIKW/bmYFEepo4D1m7itYnRqJBomxLuzLVjeWqsBqkxjqA9qU+muKVYY7h9eDvcNiynUbYTI6LgY0WbiIiIiMJSSbUBeba9rmMj3JuhAcDra4/i4c/3er1HbIQStw3NcTtepjUAAMZ0S8fS2wahQ2oMUpwq2u1SGr8RGkM2UfPBoE1EREREYed4YRVuX7YdAJAZHyEJvs4VbQD4Yuc5CIIgbuflzGS2IDFaja9nDZUcP3rBura7e2YcRnVJAwBJRTs9TgMiovri1HEiIiIiCjuLfzmGPWfLAADtUqMl1V7n6rad0Szgi53n3I7XGK2NzbxVqDVO+3M7r9FOi4vwdDkRkU9Y0SYiIiKisHPyYrX4uFtGnOScRqVwvRx6kxnrDl9wO/7XwdkAgIQo96o2AKid1mEnxzjWcmcwaBNRA7CiTURERERhw2IRUFSlh9xWwR7WMRl3jegguca5Cm1XY7TA7KEzWo9MR0jvl53odl6lcFTKI50CvHN1m4jIXwzaRERERBQ2HvliH77c5ZgC/o9RndxCr6egrTeZ4WGJttt6bldqpSNc98lKQP/sBGQnRTVqx3Eian4YtImIiIgobDiHbMDzemxvFe3zpVqfrnWmdjqvUsjx1axhvg6ViMgrflRHRERERGHLU0Vao3Rfo11jNONcqc7teHoda62dp44TEQUKK9pEREREFLYi1e6hemCO+1rrvDId9CYL5DLggTGdkR4XgRFdUhHhoXGas7oq3kRE9cGgTURERERhy1MQjo1Q4bZhOVj66ynx2MajRQCAtNgIzB7dyef7qxm0iSgI+C8LEREREYUtT9PEAeC6/m0kzz/+4wwAIMpDBbw2aoV/1xMR+YJBm4iIiIjClreKc8/W8fjloREY2FY6jVzm55JrrtEmomBg0CYiIiKisKWQew/C7VNjkBEvbXYmqyNpp8SoJc85dZyIgoH/shARERFR2PC3OVlcpEryvK769NKZl0ieM2gTUTDwXxYiIiIiChvKWirYnrjus13X1HHX672tASciaggGbSIiIiIKCyazBXqTxa/XRLps3yWro6atdFmTHe9SESciCgQGbSIiIiIKC/vOl8NkEfx6jWtFuq6KtlIu/fWXQZuIgoH7aBMRERFRWDhRWAUA6N4qDgUVNRjXI6PO1/i7ptu5uZpGKecabSIKCgZtIiIiIgoLZ0u0AIC+2Ql4bnIPKBV1h2CNyr+gHKNx/PqbFqfxb4BERD5i0CYiIiKisHC2VAcAyEqM8ilkA0CE29Tx2ueOR6oV+PKeS7H64AVc1imlfgMlIqoDgzYRERERhYUztop2dlKUz69xrWj7MpV8QNskDGib5N/giIj8wEUpRERERBQW6hO0XSVHqwM1HCKiemPQJiIiIqKQ0xnMKKrUAwCykiJ9fl2Z1ih53ibR99cSEQULgzYRERERhdy5Ums1OzZC6deWWykxjoZmfbISMGdM54CPjYjIX1yjTUREREQhZ582npUYVWdDM2dju6fjgTGdMTAnEcM6srkZEYUHBm0iIiIiCrm8MmvH8dZ+Tv2Wy2W4f0ynYAyJiKjeOHWciIiIiEJOb7IAACJVijquJCIKfwzaRERERBRyFkEAACjkvk8bJyIKVwzaRERERBRyZmtBG3I/1mcTEYUrBm0iIiIiCjlHRTvEAyEiCgC//ynbtGkTJk2ahMzMTMhkMnzzzTeS84IgYO7cucjMzERkZCRGjhyJgwcPSq7R6/WYPXs2UlJSEB0djcmTJ+PcuXMN+kGIiIiIqOkyWzh1nIiaD7+DdnV1Nfr06YPFixd7PP/KK69gwYIFWLx4MbZv346MjAxcccUVqKysFK+ZM2cOvv76a6xcuRJbtmxBVVUVJk6cCLPZXP+fhIiIiIiaLHvQ5tRxImoO/N7ea8KECZgwYYLHc4IgYOHChXjyySdx7bXXAgCWL1+O9PR0fPLJJ7jrrrtQXl6OJUuWYMWKFRgzZgwA4KOPPkJWVhbWrl2LcePGNeDHISIiIqKmiM3QiKg5CegqmNzcXBQUFGDs2LHiMY1GgxEjRmDr1q0AgJ07d8JoNEquyczMRM+ePcVrXOn1elRUVEi+iIiIiKj5sAdtVrSJqDkIaNAuKCgAAKSnp0uOp6eni+cKCgqgVquRmJjo9RpX8+fPR3x8vPiVlZUVyGETERERUYjZu46zok1EzUFQ+jrKXD6JFATB7Zir2q554oknUF5eLn6dPXs2YGMlIiIiotBzVLRDPBAiogAIaNDOyMgAALfKdGFhoVjlzsjIgMFgQGlpqddrXGk0GsTFxUm+iIiIiKj5EJuhMWkTUTMQ0KDdrl07ZGRkYM2aNeIxg8GAjRs3YujQoQCAAQMGQKVSSa7Jz8/HgQMHxGuIiIiIqGURt/fiGm0iagb87jpeVVWF48ePi89zc3OxZ88eJCUlITs7G3PmzMG8efPQqVMndOrUCfPmzUNUVBSmTZsGAIiPj8cdd9yBhx56CMnJyUhKSsLDDz+MXr16iV3IiYiIiKhlYddxImpO/A7aO3bswKhRo8TnDz74IABgxowZWLZsGR599FHodDrMmjULpaWlGDx4MH7++WfExsaKr3n99dehVCoxdepU6HQ6jB49GsuWLYNCoQjAj0RERERETQ330Sai5kQmCLaPD5uQiooKxMfHo7y8nOu1iYiIiJqBJ77aj/9uO4MHr+iM+0Z3CvVwiIjc+JNDg9J1nIiIiIjIHxYLp44TUfPBoE1EREREIWcWOHWciJoPBm0iIiIiCjlHRTvEAyEiCgD+U0ZEREREIWNvF8SKNhE1JwzaRERERBQSn+84i97P/ozfThSz6zgRNSsM2kRERETU6PafK8cjX+xDZY0JT397gPtoE1GzwqBNRERERI2qXGvEpMVbxOdagxkWi/WxnEGbiJoBBm0iIiIialTHCislz8+X6WA0W5O2glPHiagZYNAmIiIiokZ1pkTrdqyixgiAXceJqHngP2VERERE1KhKtUa3YzVGa0WbzdCIqDlg0CYiIiKiRnPsQiWeX3XI7bjWYALAZmhE1DwwaBMRERFRo3n8q/3i46EdkqFWWn8dvVhlAADER6pCMi4iokBi0CYiIiKiRlGtN2Hn6VLx+eQ+mYhWKwAA5TrrdPKEKHVIxkZEFEgM2kRERETUKIptVWsAePm6Xri6X2uxom2XFM2gTURNnzLUAyAiIiKilqFKb12HnRKjwY2DsgEAKpc244lRnDpORE0fK9pERERE1CiqbQ3PYjQK8ZhrRTsugkGbiJo+Bm0iIiIiahR5ZToAQLTGMalSJZf+Oipn13EiagYYtImIiIioUTz59QEAwMG8CvFYcbXB2+VERE0WgzYRERERNQr7Gu1IlWPq+MUqvfj4knZJjT4mIqJgYNAmIiIioqDTGkyQ2WaFf3nPUPG4877ZK+64pLGHRUQUFAzaRERERBR0RwoqIQhASowa3TPjxOMr7xyC/tkJWHbbIGiUilruQETUdHB7LyIiIiIKipJqA/69/jhuGNgGh/MrAQDdWsVJrunWKg5fzRoWiuEREQUNgzYRERERBcUz3x3E93vzsGRLrnisu0vQJiJqjjh1nIiIiIiCYs/ZUrdjrhVtIqLmiEGbiIiIiIJCIXPfE3t4p5QQjISIqHExaBMRERFRUOiMZsnzf93QBykxmhCNhoio8TBoExEREVFQRKikXcQ7pcWEaCRERI2LQZuIiIiIgiLVpXrdgUGbiFoIBm0iIiIiCopTxdWS5zEabnhDRC0DgzYRERERBVxFjREXqwyhHgYRUUjwY0UiIiIiCgiT2YIHPtuLflkJbufS49gEjYhaDgZtIiIiIgqIH/bn4/u9efh+b57k+FW9WuHBsZ1DNCoiosbHoE1EREREAVFS7T5VPEIlx7+n9w/BaIiIQodrtImIiIgoIIxmi9ux56f0DMFIiIhCi0GbiIiIiALCaBYkz6/q3QrXD2gTotEQEYUOgzYRERERBYTJJWj3z06ETCYL0WiIiEKHQZuIiIiIAsJkkU4dj9EoQjQSIqLQYtAmIiIiooBwnToeo1GFaCRERKHFoE1EREREAWFyaYY2KCcxRCMhIgotBm0iIiIiCogak1l83CYxEmlxESEcDRFR6DBoExEREVFAaPWOoH1559QQjoSIKLQYtImIiIgoIKoNJvFx+5ToEI6EiCi0Ah60TSYT/u///g/t2rVDZGQk2rdvj+eeew4Wpy6UgiBg7ty5yMzMRGRkJEaOHImDBw8GeihERERE1Ii0BkdF+6rerUI4EiKi0Ap40H755ZfxzjvvYPHixTh8+DBeeeUVvPrqq1i0aJF4zSuvvIIFCxZg8eLF2L59OzIyMnDFFVegsrIy0MMhIiIiokZgMFlwulgLAJh3TS+0io8M8YiIiEIn4EH7t99+w5QpU3DVVVchJycH119/PcaOHYsdO3YAsFazFy5ciCeffBLXXnstevbsieXLl0Or1eKTTz4J9HCIiIiIqBF88GsuzpRokRilwoSeGaEeDhFRSAU8aA8fPhzr1q3D0aNHAQB79+7Fli1bcOWVVwIAcnNzUVBQgLFjx4qv0Wg0GDFiBLZu3erxnnq9HhUVFZIvIiIiIgofe86UAQDuGdkBidHq0A6GiCjElIG+4WOPPYby8nJ07doVCoUCZrMZL774Iv76178CAAoKCgAA6enpktelp6fj9OnTHu85f/58PPvss4EeKhEREREFiL0RWkqMJsQjISIKvYBXtD/99FN89NFH+OSTT7Br1y4sX74c//rXv7B8+XLJdTKZTPJcEAS3Y3ZPPPEEysvLxa+zZ88GethERERETdb+c+V46psDKK02hGwM1Xpr0I7WBLyOQ0TU5AT8X8JHHnkEjz/+OG666SYAQK9evXD69GnMnz8fM2bMQEaGdc1OQUEBWrVydKMsLCx0q3LbaTQaaDT8dJSIiIjIk2nv/Y5KvQnHCiux8s5LG/39q/Qm7LJNHY9WM2gTEQW8oq3VaiGXS2+rUCjE7b3atWuHjIwMrFmzRjxvMBiwceNGDB06NNDDISIiImp2KmqM2Hm6BCeLqjBx0WZU2qrJv58swS9/XoDJbKnjDoG14jfH8r8ojaJR35uIKBwF/CPHSZMm4cUXX0R2djZ69OiB3bt3Y8GCBbj99tsBWKeMz5kzB/PmzUOnTp3QqVMnzJs3D1FRUZg2bVqgh0NERETU7Mz97iC+2nXe47nbl+3Ao+O7YNbIjo02nt1nSsXHgiA02vsSEYWrgAftRYsW4amnnsKsWbNQWFiIzMxM3HXXXXj66afFax599FHodDrMmjULpaWlGDx4MH7++WfExsYGejhEREREzY63kG33n40ngx609SYz1Ao59CYLfj1+UTzeq3VCUN+XiKgpkAlN8GPHiooKxMfHo7y8HHFxcaEeDhEREVGjynn8h1rPq5VyHH1hQtDe/2yJFpe9sh4A0CcrAXvPliEzPgK/Pv4Xr81tiYiaOn9yKLtVEBEREYU5s0XA86sOoahKj7WHLtR5vVIe3LDrXFHfe7YMADChVyuGbCIiGwZtIiIiojBWYzTj7x/uwOZjF71e88N9wxGjUeL9zblY8ftptIqPCMpY8st1KK4ywGA2u5278/L2QXlPIqKmiEGbiIiIKIy9se5YrSEbANqlRCNKrcRNl2Rhxe+nUVFjCvg4BEHAsJd+gcVl0eF9f+mIm4e0RVpccMI9EVFTxKBNREREFMZWHyio85oIpXVLrbgIFQCgssYY8HGcKKpyC9kZcRF4cGyXgL8XEVFTF/B9tImIiIgocC5U1IiP7xvdCZku08Kj1ArIbWuy4yKtQbvGaEGN0X16d0NsOupeVf/39P4BfQ8iouaCQZuIiIgoTNUYzag2OAKzWiFDcoxGck2UWiE+jotQQq2w/npXXG0I6Fi2npAG7cs6pWBA28SAvgcRUXPBoE1EREQUppzDbYxGiSl9WyM5Ri25xuw0n1smk4nniyr1AR1LfnmN5LlKwV8jiYi84b+QRERERGFq6/FiAMB1/dtg/9yxyEqKwpD2yZJr0mKlU8lTY60V74sBDtoVLuu+r+7XOqD3JyJqTtgMjYiIiChMlWit0787psWIe1TfMbwdqmpMiI9U4dcTF3Flz1aS16TYppZfrApw0NaZxPfvkBqDSb1b1fEKIqKWi0GbiIiIKEyV2tZZJ0c7pourFHI8PM7a6fvvHvauTgnC1HGLRRA7md91eXtu5UVEVAdOHSciIiIKUyW2oJ0Yra7jSgdx6niVHpuOFmHc65uw52xZg8ZRUWMUt/aydzYnIiLvGLSJiIiIwpR96niSH0HbMXXcgFs/2IYjFypx29JtDRrHqWItACAtVoMIlaKOq4mIiEGbiIiIKMz8dqIYl73yC86W6ABIp47XxR60i5zWaJdqjd4u98np4moAQE5ydIPuQ0TUUnCNNhEREVGYuWP5dmid9s/2Z+q4PWhvyy0J2HjOlVoDf5vEyIDdk4ioOWNFm4iIiCjMOIdsAIiL8L02khgd+DXU58usQbs1gzYRkU8YtImIiIjCTITK8SvamgcuF7f28kW0OrATFnUGM3KLrFPHWycwaBMR+YJTx4mIiIjCiMFkgcFkAQBs++dov7fSilQHrlmZwWTBsJd/Ebufs6JNROQbVrSJiIiIwsjp4mpYBCBKrRC36vJHVACD9vkynRiyATZDIyLyFYM2ERERUZiwWAS8t/kkAKBnZrxfU8btIpSBC9p6k2OtuFwGZCVFBezeRETNGYM2ERERUZj48LdT+GzHOQDA1EFZ9bqHXO45nNcYzR6P16ayxiQ+HtUlrV7jISJqiRi0iYiIiMLEluPFAIBW8RG4rn/rgN7beQq4N2sPXUDO4z/gs+1nAQCVNY79t1+8pldAx0NE1JwxaBMRERGFiRNFVQCA127oU69p43Y9W8e5HXv4870wW4RaX/e3D3cAAB79ch8EQUCFzlrRHtohGRnx/jVlIyJqyRi0iYiIiMKA1mBC7kXrNlod0mIadK/RXdPdjm09UYwvd53z+R5FlXr88mchACAuIvB7cxMRNWfc3ouIiIgoDHzyxxkAQGqsBmn16DbuTK30XEs5X6qr9XWxEUpxXfYN//kNp4u1AACzUHslnIiIpFjRJiIiIgoxg8mCtYcvAABuHty2QdPGAUCl8Px6k8VS6+taJzj2ybaHbAAortI3aDxERC0NK9pEREREIXS8sApjFmwUn1/dL7PB91Qp5E6PZTCarRVpk7n2yrTe5DmIaw3+dywnImrJWNEmIiIiCqGPfj8tPu6YFoO2ydENvqdz0G4V76hS/2fTyVoboum9bAHWIbVha8aJiFoaBm0iIiKiEFp/pFB8/K8b+gTknmpJ0JZ2C99/vtzr6zxVtK/ono5nJnUPyLiIiFoKTh0nIiIiCpHci9U4XayFSiHD7qfHIkYTmF/NVErHGu1Mp3XXgPeqNQDUeDj3zs0DoJA3bM04EVFLw4o2ERERUYjsOl0KAOiXlRiwkA0ACrnjV7xUlw7mJi9TxwVB8FjRZsgmIvIfK9pEREREIXLOtt1WTkpUQO/bLysBSdFqZCVGIj1OOnXcYPbc8OxgXgVMFgEapVwM3F0zYgM6LiKiloJBm4iIiKiRXazS4x+f7MLvJ0sAAG0SAxu0s5KisOPJMZDLZfjvtjOSc0YvncVX7csHAPylaxp+PFAAAA3eZoyIqKXi1HEiIiKiRiIIAgRBwPKtp8SQDVgbjgWa3DblO0Il/XXP6GGLL0EQsGpfHgBgUh/H9mKcNU5EVD+saBMREREFUV6ZDqsPFuC6AW1w339340RRFVq7NCgL5hTtCKVC8tzoYer44fxKnCvVIUqtwKguaRjRORUbjxZhxtCcoI2LiKg5Y9AmIiIiCpILFTW47u2tyC+vwbPfHxKPny3RiY/7tIkP6hTtNJc12nqTe2fxXWesTdkGtE1EpFqB/9wyAMcuVKFn67igjYuIqDlj0CYiIiIKAkEQMHjeulqviY1QYvG0/kEdR//sBMnzGqN7RbuwUg8AaJtsXSseoVKgV5v4oI6LiKg54xptIiIioiA4Vayt85o3b+qHrKTANkJzJZPJ8Lfh7cTnOpe9sgVBwJvrjgEAYiNUQR0LEVFLwaBNREREFGCCIOBvy7d7PDdnTCfxsese142hxiVoV+pN4uOSKkNjD4eIqFli0CYiIiIKsK92nceJomoAwJhu6Xj3lgFonxqNhTf2lYRr+1TtYHNeAm6vaO84VYK8Mh0qdEbxnMni3pGciIj8xzXaRERERAG24vfTAICHruiM2aOtFeyxPTIAADtPl4rXhWKqdo3BjAPny3H9O78BAH64b7h47p6R7Rt9PEREzRGDNhEREVEAfbvnPPacLQMAjOuZ4XZ+QNtE/OeWAeiYFtNoY3Lual5jtGDHKcce3uW2ina7lGh0TAveNmNERC0JgzYRERFRgBw4X445n+4BAKgVcq9Tw8f1cA/gjUVnNEMudwTvae/9AQBIjGIjNCKiQOEabSIiIqIA+fFAPgTbMuev7x0KjVIR2gHZOO/S/d3ePBhM7lt8xUUyaBMRBUpQgvb58+dx8803Izk5GVFRUejbty927twpnhcEAXPnzkVmZiYiIyMxcuRIHDx4MBhDISIiImo0pVrrNOw5YzqhR2b47kP98R9n3I7FM2gTEQVMwIN2aWkphg0bBpVKhR9//BGHDh3Ca6+9hoSEBPGaV155BQsWLMDixYuxfft2ZGRk4IorrkBlZWWgh0NERETUaMq01u2xEqPUIR5J7fLLdW7H4riHNhFRwAR8jfbLL7+MrKwsLF26VDyWk5MjPhYEAQsXLsSTTz6Ja6+9FgCwfPlypKen45NPPsFdd93ldk+9Xg+9Xi8+r6ioCPSwiYiIiBqktNqA/+0vAAAkhPl65xqjp6njbN1DRBQoAa9of/fddxg4cCBuuOEGpKWloV+/fnjvvffE87m5uSgoKMDYsWPFYxqNBiNGjMDWrVs93nP+/PmIj48Xv7KysgI9bCIiIqJ6EwQBl72yXnyeEGYV7fEeup+74tRxIqLACXjQPnnyJN5++2106tQJq1evxt1334377rsPH374IQCgoMD6SW96errkdenp6eI5V0888QTKy8vFr7NnzwZ62ERERET1tvZwIar0JvF5QpiF1n7ZifjXDX1qvYZTx4mIAifgc4QsFgsGDhyIefPmAQD69euHgwcP4u2338att94qXue8nyNg/STY9ZidRqOBRqMJ9FCJiIiIAmL9kULJ83Bco90+NbrW8+w6TkQUOAGvaLdq1Qrdu3eXHOvWrRvOnLF2t8zIsE5dcq1eFxYWulW5iYiIiJqC7bklkufxYbhGW7DvO+aF3EvBg4iI/BfwoD1s2DAcOXJEcuzo0aNo27YtAKBdu3bIyMjAmjVrxPMGgwEbN27E0KFDAz0cIiIioqA6XVyNY4VV4vPkaDViNeHXWKx7q9q3G4uLCL8xExE1VQEP2g888AB+//13zJs3D8ePH8cnn3yCd999F/feey8A65TxOXPmYN68efj6669x4MABzJw5E1FRUZg2bVqgh0NEREQUVE9/exAAoFbK8eU9Q/Hd7OGQy8OvOhypVmDV7OGSY09PtM5CzEmOwqUdkkMxLCKiZingH10OGjQIX3/9NZ544gk899xzaNeuHRYuXIjp06eL1zz66KPQ6XSYNWsWSktLMXjwYPz888+IjY0N9HCIiIiIgsZiEbDxaBEAoEdmHAa0TQzxiGrn2ll8SPtknHrpqhCNhoio+QrKHKGJEydi4sSJXs/LZDLMnTsXc+fODcbbExEREQWV2SIg92I1CsprxGOLp/UP4Yh8o1FKJzOqFOFXeSciag64GIeIiIjIT8u2nsLzqw6Jz6/um4nWCZEhHJFvNEqF5LlSEfBVhEREhCCs0SYiIiJq7vafK5M8v2FgVmgG4ie1S0VbGYZryYmImgMGbSIiIiI/lWqN4uMx3dIwtIk0EnMN2q7PiYgoMDh1nIiIiMhPZVoDAOC9Wwfiiu7pIR6N7xRyGRRyGcwW657arGgTEQUHP8YkIiIKAzVGM3aeLhEDEIW34mpr0E6MUtVxZfhRO63L5hptIqLg4L+uREREYeDJrw/gurd/w8d/nA71UKgWNUYzvt1zHudKdQCArKSoEI/If73bxIuP2XWciCg4GLSJiIjCwJe7zgEAFv1yPMQjodq8ue4Y7l+5R3yeFqsJ3WDqaWiHFPGxUs5fBYmIgoH/uhIREQWRIAhY8ftpjF+4Cbcs+QMms8XtGudjiVEqCAKnj4daRY0RFpdp/H8WVOCtDSckx2SyplcRHt0tTXzMijYRUXCwGRoREVEQHb1Qhae+OQAA+LOgEj8dLMDPBy9g+uBsDG5v7VS9al++5PrhL6/Hj3MuQ1xE01v/2xycLdFi9Gsb0Tc7AX/pmoa+WQkY0j4Z4xdullw3umualzuEt56t4zF3UndEqZVN8oMCIqKmgEGbiIgoiA6cL5c8/8cnuwEA3+3Nw6mXrsK5Ui0e/XKf5JrzZTpsOlqEib0zG22c5HAwrxwGswXbckuwLbcEAPDStb0k19wypC0eHtclFMMLiJnD2oV6CEREzRqnjhMREQXR0QuVXs8JgoAtxy7CYLIgJ1naVCtao4QgCDhbosW6wxcgCAL0JjOnlTeCCp3J7djjX+2XPL9xUBbiIznjgIiIPGNFm4iIKIiO2IJ2l/RY8bHduVKdGOB6tI7HjYOy8fJPfwIAblu6HamxGhRV6gEA79zcH49+sQ8juqRh0V/7NeJP0PKU64x1XtMhNaYRRkJERE0VK9pERERBdLTAGq6nD8l2O3fZK+vFx0UVetwzsgP6Zyc4jtlCNgDc/dEuVNSY8P3evOANlgDUHrTjIpT4x6iOiFQrGnFERETU1LCiTUREFGAVNUZEqhSo0BmRV14DAJjStzWe/vag19c8Ot663tds4dTwULtQYf3fbM6YTvhL1zS8vuYoqvVmzL+uFyvZRETkEwZtIiKiAMov12HkqxvQPTMOl7RLAgB0zYhFfKQKL17TE09+fcDtNd/cOwx9sxIAACYG7UZVYzRDpZBDIbd2315z6AK+sO1p3iU9Fr3bJGDpbZeEcohERNQEceo4ERFRAO05Uwa9yYLdZ8rwn40nAQD3jOwAAJg+uC2W334J1j88En+9xDqVfObQHDFkA6xoB8Pxwipc/e9fsfbQBcnxg3nl6PnMalz/zlax2dw/PtkFQQDS4zQY2jElRCMmIqKmjkGbiIgogM6X6STPb720Lab0bS0+H9E5Fe1SojH/2l449dJVmDu5h+T67plx4uMBbRM9vkdzCuPf7D6PfefKgvoej325D3vOluFvH+6QHH/os70wWQTsPlMGndGM/LIa6E0WAMBP91/OruJERFRvnDpOREQUQOdKrUG7XUo07hnRAdf0b13HK6SevLIbThdrcU2/1rh5SFuU64yY8cE27DlbJl5jMFmaRTOu134+gkW/HAcA/Pn8eESoAvszGUwWlGoN2Hm6VHJ86/GLWLjuGP4scHSBf/zL/dh+yrpndofUaCRGqwM6FiIiallY0SYiIgqg08XVAIA7hrfD1EFZUCn8+09tcowGX94zFDcPaQsAiI9UYenMQYh2CtYbjhTCYKu8NmX2kA0Aq/blB/z+T369H4PnrXM7Pu39P7Att0Ry7Lu9eci3Na7LTIgM+FiIiKhlYdAmIiJqILNFwK/HL2L1wQJsPnYRANA+JTpg90+MVmPtQyPE5/d8vAu3fvBHwO7fmCwWAQ99thf/981+yfFV+wK7bVmZ1oDPd57z+P51kclkAR0LERG1PJw6TkRE1ADVehP+/uEObD1RLB7rn52Awe2TA/o+reIjEaVWQGswAwB+P1lSxyvC0/GiKny5yz0AF9iqyfWhN5mx6ehFdM2IRVqcBje//we2n3JMFx/eMQVbjls/ACnRGuq83+iuafUeCxEREcCgTURE1CBLtuRKQjYALJrWX9wuKpASIlVi0AaAyhojYiOaTsOukmoD3lh7zOO5Uh8CsDcL1x7D2xtOeDw3dWAbvHxdbwx6cS0uVhnwz6/2e7wOAGb/pSP6ZydiaMfAfkhCREQtD6eOExERNUDuxWrxcUqMBtueHI3WQVrj2y9b2oU8r6z+VeBQeOzLffhhv+e12Bcq9Cis9P/nMVsEfOWhQm43sG0SZDIZWsVb/zf52WWLrxGdUwEANw3KwgNjOmNU1zRolE2/0RwREYUWK9pEREQNUFJtrcS+en1v3DAwK6jvNTAnURJUz5Vq0SUjNqjvGQh7z5ZJun/Pu6YXzBYLnvr2oOS6NYcuYPrgtj7ds6C8BhEqOeb/709cqNC7nR+Uk4jYCBUm980EAGQlRWL/+XLJNSM6p+KNm/ribIkOvdrE1+dHIyIi8ohBm4iIqAHsQTupEbaDGtg2SfL8TIk26O/ZUD/uz8c9H++SHLuqdytU1hgBW9CePjgbH/9xBofzK3y65/ubT+KFHw5Ljl3SLknsJL5q9nD0bC0NzlmJUZLnfxveDk9e1Q0ymQwJUdzKi4iIAotBm4iIqAHKdNagnRAV/LXS3TPjcHnnVGw6WgQAOF0c3kFbEAS89NOfkmNJ0WrERSgRH6nCv27og2i1AgazxRa0K73cSco1ZAPW9dUms4AotcItZANAm0THdP6bBmXh/yZ29/OnISIi8h2DNhERUQPobM3JojXB/0+qQi7Dh7dfgo9+P43/++YAzoZ5RfuP3BLxw4Cc5Chc2iEZ1/RrI26fdf2ANgCAPwuslezjhVW13q+yxojKGpPHc0M7pNTagK5NkqOi3btNgs8/AxERUX0waBMRETWAvQt4pKrxGmhl20JjuE0d/3bPeby57hjeuXkAOqXH4hVbNfvGgVl4+freXl9nbx5XrjOiSm9CjJcPLf763u84cN4ayuUyQKWQQ2+y4Mf7L6uzy3uWU0U7JzmqliuJiIgajl3HiYiI6uFsiRY7T5dCZ7QFbXXjB+1jhVX442RxHVc3nvtX7sGJomo8/MU+nLpYjV1nygAAd45oX+vrYiNUiIuwhuu8Mp3Ha4oq9WLIBoCclGhsfGQUvpo1FN1axdU5tjZOa7TT4iLqvJ6IiKghGLSJiKjF0pvMePjzvXj62wMwmS0+v04QBNyy5A9c9/ZWCIL1WGNWtFsnRkKttP4n/MZ3f8cBl27aoZZXpsMhW2OzPm3i0SE1ps7XZNqq2tPe+x2l1e57ai/fekp8nBStxivX9UZGfAT6u2x55k2ESoGHx3bGbcNy0CE12qfXEBER1RenjhMRUYv1ze7z+GKndQ/mD387jfdvHYgx3dO9Xl9SbcD+8+V4f/NJnHJpRNaYQVulkCMzPkIcwx+5JR4bgIVKUaUeb6w9BgDomlF3tRmwNiv7s6ASF6sMeOjzvfhg5iDxnM5gxvtbTgIA3ripL67ono4otf+/wvzjL538fg0REVF9MGgTEVGL5BwG7f724Q7seuoKt626ci9WY9S/NtR6P6WicSeJGc2C+PhcaejXamsN0iZlRy5UIiVGjbtHdvDp9Rnxjuncv/xZCLNFENdd55frUGO0IEajxOQ+mWIzNSIionDFqeNERNSsvfTjn5j6zm/YfKwI1XoTdp0pxRtrj+Hpbw8gr7wGaoUcXTNixesnLdqCcq1RfC4IAu5fubvW92gV3/hrfk0Wx1T3P33cFitYBEHAze//4Xb86Uk90C7Ft2naZosged577mpxOn9RpR4AkBqrYcgmIqImgRVtIiJqtoxmC97ZeAIAcMuSbR6veeLKrrhtWDs8/e0BfPjbaZwv02HJr7l48IrOKKyowZxP92DfOcca6L9f1g5DO6ZgVJc0bD9Vgnc2nMCNg7Ia5edxlhytwYUKawD9s6ACgiCELISuPlggNj6z0yjlmNwn0+d7dEyLlTyvNphxoqgaXTJiUVRl/TlTYtSeXkpERBR2GLSJiKjZqmtfZsDavRoAHp/QFT8eKEBRpR5vrjuGMd3SMHnxr5Jrs5Ii8eAVXcQO44NykjBoZlLgB+6Df93QB7M+3olTxVqUao0o0xqRGK3G3O8O4uTFaiydOajOLa8C5bcT1s7nCrkMX9x9KQwmi9jczFc3D8lGUaUen/xxGhW2vbLzy3XokhEr7sXd2s97EhERhQqnjhMRUbMkCAI+2JILAEiL1YjHs5Ii8evjf8Fb0/tj5tAcDO+YAgCIUivx2g19xOtcQ/bcSd2x4eFRjbqNV226Z8ZhwyOjxCZslTUmlGuNWLb1FDYdLcKRgsabTr7XVvFfMLUP+mUnYnD7ZGQl+bdXtUapwOMTuuLdWweKx86WWrf6OnbB+rN0So/1+FoiIqJww4o2ERE1Sx/9fhqf2zqKL5jaF8M7pcBiESC3VXlbJ0Tiyl6tJK+5rFMKpg5sg892nHO738Q+mY1WIfZHtEYJndGMihojFq93NHcz+LFdWUNcqKgRtxfr3Sahwfcb0j4ZwzumYMvxizhTXA3Aul84AHRMq3ubMCIionDAoE1ERGFJEAS8vzkXepMZ947q6Pf64y3HLwIA7hnZAcM7WavW8jqCskwmw8vX9caqffnQGszok5WA6we0Qd82CUiJ0dT62lCJ0ShwsQr4dPtZyQcEVTWmWl4VOOv/LITJIqB3m3jkJPtXxfZmXI90bDl+Ee9tzsV7m3PF477sx01ERBQOGLSJiCgsffzHGbz4v8MAgNHd0tGtlW/7MduV66ydw/19nUwmw0/3X45lW0/hnpEdkBobngHbLlpj/U/5L38WSo5X1hg9XR5wO0+XArDOBghUM7Yp/Vrjk21ncTi/QnI8NUw/7CAiInLFNdpERBQ0xwsr8eBne7DxaFGd15rMFkx773dMfec3lGkNeHvDCfHctPd+hyAIXl97sUqPJVtyUVhZIx4r11kruvGRKr/HnZ0chacndQ/7kA04gvb5Mp3keKU+eBVtk9mCdYcv4MFP94jT8we2DVxTuLgIFX6YPRzDOiaLx2QyIDaC9QEiImoaGLSJiCgoThRV4e6PduGrXecx44NtWHvoQq3X//JnIbaeKMa2UyXo+9waSXAs1RrdKrbOFv9yHM+vOoS/f7hTPGZf31ufoN2UZMR53sP7d1sn8IY4V6qFzmCWHNt5ugQdn/wRdyzfga92nxeP98tOaPD7OZPLZXjjpn7ic0Goe+o/ERFRuGDQJiIi0ZGCSqw7fEFSPTaYPDfVOnWxGle9uRnvbDzhVm0urTZgyuJfJdtr3fXRTpwr1Xp97/9uO+PxeOd067rcOZ/uQbnWfTr0xSo9lm09BQDYe7YMgLVLdbUtIDb3LaH+fll7yfNr+7cGAKzalw+zxfssgLpsOlqE4S+vxzVvObqvrz5YgOve/s3j9QlRgd/jOiVGg+v6twHARmhERNS0BD1oz58/HzKZDHPmzBGPCYKAuXPnIjMzE5GRkRg5ciQOHjwY7KEQEVEtjGYLblnyB+5YvgO3L9uOMq0BT3y1D53/70fc9O5vbiH5juXbcTCvAi/9+CdmLN0OQRBQYzRjwhub0e/5Nahymbpstghid2pn+eU6aA0mbPVQge2RGYeVd14KwLp91bd7z4vB32i2oLLGiIEvrJW8RhAEnLNVw7OToprE9O+G6NpKuuXV7L90AmDtOl5cpYfeZPb0sjrZZxD8WVCJu1fsxMyl23DXip2SazLjrdX0Gwdm1es9fPHydb3w3JQeeOX63kF7DyIiokAL6mKn7du3491330Xv3tL/OL7yyitYsGABli1bhs6dO+OFF17AFVdcgSNHjiA2lntkEhGFwuJfjqOwUg8AWH+kCPP+dxhf26YG/36yBA98ugef3z0UepMZMz7YhhNF1eJrNx0twq4zZfizoELSwGr64GzMGtURr60+gq92n5e8BrBOTR7x6gax8qqQy/DC1T2RER+BYxcqMbF3JpKi1bi8cyo2HS3C098exL/XH8eP91+Om979DUcvVMFVRY0JlbaO2829mg0AKoUcU/pmYuPRInx+16VolxKNWI0SlXoTLpm3Dh3TYvDznMv9nnZ9tsTxwcpPBwsk51bccQku65SK08XV2HL8Iq7t1yYgP4snSoUct16aE7T7ExERBUPQgnZVVRWmT5+O9957Dy+88IJ4XBAELFy4EE8++SSuvfZaAMDy5cuRnp6OTz75BHfddVewhkRERF7sO1eGN9ZZ92C+rFMKNh+76LaX9PZTpVj6ay4qdCb8frIEgLVifLFKD63BjOve3ipeq1bI8dSk7pg6sA00SgU62Kb9vrr6CO4Z0UEMfUcKKiXTmyNVCvz1kmwAwKguaeLxyzulYJOtodqFCj0W/XLMLWRHqhTQGc0o0xpQYes4HhfZMppnLbyxL4xmAWqldaKa3mkP7eOFVSjVGpDsR8duvcmM30+6zzD4S9c0XNE9HZd1SgUAtE2ORtvk6AaOnoiIqPkJ2tTxe++9F1dddRXGjBkjOZ6bm4uCggKMHTtWPKbRaDBixAhs3brV9TYAAL1ej4qKCskXEREFzi7bFk0jOqdi3jW9JOcuaefoJv3s94fw+tqj4vM3buqLlXcOcbvfxkdH4pYhbaFRKgAA3TMdW2xttu1vDQDF1QbxcZRagWcn9/A4Ptf9k/fY1mLbrbxziNj0rEJnQoVta6vYiObdCM1OJpOJIRsA+rZJkJy/WGWAP9YcuoBqgxkpMRpsfnQUXr2+N46+MAEfzBwkfhBCRERE3gUlaK9cuRK7du3C/Pnz3c4VFFinn6Wnp0uOp6eni+dczZ8/H/Hx8eJXVlbw1oIREbU0lTVGzP3+EACgXUo02iRKp1sP75gC11nHcRFKHHx2HPplJ6J3mwSM6Jwqnls1ezhaxUvvMbJzKpKjrc2yZnywDQfzrGu1S2xB+9p+rXHw2XG4boDnKciue2HvPlMmPo6PVGFQTpIYtMt1RhTbgmViVMsI2q5euKYnHh3fRXw+buEmbHX6gKM2giDgxR+s+5eP6pKKrKQo3DAwSxLkiYiIqHYBn1N39uxZ3H///fj5558REeF5yxHA+um7M0EQ3I7ZPfHEE3jwwQfF5xUVFQzbREQB8tUuxxZNqbEayGQy/Htaf+w8XYq/XdYOreIjcGWvDBzMq0BFjQlbj1/EbcPaifs3A8Dy2y/B8q2nkBKjQc/W8W7vIZPJsPLOIbji9U0AgCe/PoBv7h2GgvIayft6k+aloVlmfAS+/cdwKOQyMWh/tfsctHprA7DMFrBG25PO6bHonB6Lbbkl2HDEOuX+2e8PYfUDl9f52rMlOuTb/neZMTQnmMMkIiJqtgIetHfu3InCwkIMGDBAPGY2m7Fp0yYsXrwYR44cAWCtbLdq1Uq8prCw0K3KbafRaKDRNO+usUREoXL0QqX4eHjHFADAVb1b4arejn+jO6bFomOatVnlLUPaerxPXaGsU3osWidE4nyZDvtt3cdPXrQ2R2uXUvs6X9dGXrEaJa7u1xrPTOoOpcJaac1MsH646/zBQZvEqFrv29w9Nr6rGLRjI3z7T7592n16nOcPTYiIiKhuAZ8HNnr0aOzfvx979uwRvwYOHIjp06djz549aN++PTIyMrBmzRrxNQaDARs3bsTQoUMDPRwiombts+1nMfWd3zw2rvJFjdGM7/fmAQDuGdkBfbISAjg6d8tuGwTAutXXe5tO4qAtcHdKr3uP5GcmdcegnETsfXos9j87Ds9f3VMM2QDw1MTubq8Z0j7J7VhL0q1VHGaN7ADA96Ctte0/HqVuGY3kiIiIgiHg/xWNjY1Fz549Jceio6ORnJwsHp8zZw7mzZuHTp06oVOnTpg3bx6ioqIwbdq0QA+HiKjZMJot2HW6FAPaJkKpkOP7vXl49Mt9AIDbl23Hgql90D41Bp3Tfd8mcePRIlTUmJAZH4GHx3ap+wUNFBfpWDP94v+s64DVSrlPldPbhrXDbcPaeT2fHKPBazf0wUOf7wUATBuc3WKaodWmf3YiAN8bomkN1q3RIlWKoI2JiIiouQvJx9WPPvoodDodZs2ahdLSUgwePBg///wz99AmIvLAbBGwbOspbMstxuqDF3DToCxM7puJp789IF6jNZhx90e7AAAzh+bgqYndofCyb7LOYMZbG45jcLtkca/kgTlJXq8PpPhI9+Dbt02C2J28oa4b0Aa928Tj95PFmDqIvTwAIMW2vv1ilR5bj1/E77klWHf4Am66JFtcBiAIAoqq9Mgvq8HMpdsBWLvAExERUf3IBEEQ6r4svFRUVCA+Ph7l5eWIi4ur+wVERE3Ym+uOYcGaox7PJUer8dWsoRjx6gbJ8V6t47Hor/2Q42Ht84s/HMJ7m3MRo1Hi+gFtsGzrKdw2LAfPTPK8tVYgCYKAIfPX4UKFXjw2a2QHPDq+a9Dfu6U6V6rF8JfXux3vlBaDNQ+OAAC8uvpP/Hv9Ccn5jmkxWGs7T0RERP7lUO7VQUQUxiprjF5DNgC8e+sAtE2OxuQ+mZLj+8+X4wXbFk3Ozpfp8N7mXABAld6EZVtPAYC49VawyWQyXN4pVXJsUE7LXkcdbCkxnpuJ6k0WlFYbsO9cmVvIBoDjhVXBHhoREVGzxU4nREQNsPFoEc6X6nBF93SkOm1BZbYIMJotUCnk9Z6SfaZYi8tfda9E2r09vT8GtLWG1H9e2Q3tU6OhUsjx6mrr7g72vaoB4GyJFl/vPu81tLdObLxtsK7p1xqf7zwnPu/fNrHR3rslilApEKtRolJvkhwvrKzBmAUbUVztee32PbYmakREROQ/Bm0ionoq0xrwt+XbYTQLePGHQ1h556WIi1SiVXwkbnhnK/aeswbdR8Z1wb2jOvp9/9UHC9yOfXH3pcgrr4HFImB8zwzxeEZ8BOaM6QwAuHlIW/R59mfkl9fgb8t3YO3hC273aRUfIe6VDADjemS4XRMsQzumYObQHCzbegqRKoXHddsUWCmxGjFoj+ySig1HilBjtKDG6AjZ8ZEqlOusW3stntYP4xvx7wQREVFzw6BNRFRPty2zhmwAqDaYMWnxFo/Xvbr6iF9BO/diNR7+fC9qjGbx2MvX9UJljQkDfZhmHR+pEoO0a8ieOTQH1w9ogy4ZsTh6oRLpcRFepxYH09zJPTC+ZwbaJrfsfa4bS2qMBrm2PctbJ3ievXD/6E7onhmHMq0B43u28ngNERER+YZBm4ioHgrKa7D7TJlP1yrkMgiCAJms9inkgiBgzaELuHPFTsnx6we0wY2Dsv0a36CcJHxn2x/b7q+XZOOZSd3FcfTIrHtLrWAa0j45pO/fkgzIScS2UyUAgEwPQVsuA4Z1TEGXDO7+QUREFAgM2kRE9fDV7nMej6998HKYLcCqfXkY1yMDExdtgdkiQGc0I0rt/Z9cg8mCf68/jjfWHXM7V5+p1Xde3l4M2v+8sivuvJzrbVuyKX0z8fYGa8OzJJfGd8tuG4SuGXHIiI8IxdCIiIiaJQZtIiI/CYKAL23NvF65rjcq9SY8v+oQFt7YFx3TrBXBLhldIAgC1Eo5DCYLCiv0yEnx/k/unE9343/73ddkA9b11P7q2Toeq2YPxw/78/2uhlPz0zUjDn3axOPIhUoMbudYfjCsYzJGdE6tc7YFERER+YdBm4jIT/et3IMTRdb1rhN6ZSA2QoWr+2Yi2WWts0wmQ4/MOOw+U4ZxCzdhyYxB2HriItqnxmBQTiKyEqMgl8tQrTdh7aFCAMDNQ7Jx3+hOOF2sxYOf7YFWb8ZVveu3XrZn63j0bB3a6eEUPv575xDoDGbEOc2QuG1oO4ZsIiKiIGDQJiJyYW9CFqFSuJ3be7YM39umZGcnRSE2whpaXEO23Y0Ds7D7TBn0JgtuXvKH5NyskR1w76iOmP/jYRjMFmQlReL5KT0hk8mQFhuBTY+MgskiQKWQB/LHoxYqSq1ElFoJQRAcxzTuf8eJiIio4Ri0iYhsVm47g58OFmDDkSK0SYzEazf0wcCcJCjkMpgtAv62fDvWHykSr39kXJc67zmpTyYe/2q/x3NvbTiBt2zrZgH36qJMJoNKwWojBZZMJkPb5CicKdGiT5uEUA+HiIioWZIJzh9tNxEVFRWIj49HeXk54uLiQj0cImriaoxmlGmNGPbyLzBbpP8kZiVF4skru+Pxr/ahTGvdY1gmA9Y+OAIdUmN8uv/BvHJc9aZ166/B7ZKQFhchVsXt3preH1f24pZK1Dj0JjNMZgHRGn7eTkRE5Ct/cij/C0tELYrRbIFSLoNMJsOhvArc9O5vqKgxSa4Z0TkVm48VwSIAZ0t0uPsjx3ZbSdFqPDOpu88hG7Buo3V551Qczq/A4mn9kRClwl2Xt0ep1oA31h7D0I4pDNnUqDRKBZixiYiIgocVbSJqMUa/tkFsYubNlL6ZeOOmfhAEAVP/8xu2nyoVz904MAsvX9+7Xu9tsQiwCAKUXG9NRERE1CSxok1E5GTfuTL8mV9Za8hWyGV46dpeGN8zA4B1Hevndw/FqYvVUMhl2HG6BJP7tK73GORyGeTgemsiIiKiloBBm4iarZ2nS/Cv1Ufx28liyfHHxnfFyaIqtE+NwaUdktE3K8HrPXJSogEAWUlRwRwqERERETUjDNpE1CydKdbipnd/h9HsWB3TvVUcZgxtixsHZYdwZERERETU3DFoE1Gzc75Mh+vf2SqG7G/uHVZr1ZqIiIiIKJDYlYeImhW9yYzbl25HYaUeAPDvaf0ZsomIiIioUTFoE1Gz8v7mXBy5UAkAeOnaXriqN7fNIiIiIqLGxaAdpsq0Bjz02V5sOlrU4Hv9dCAfv7s0g7Jb8ftp3L9yN1b8dgq5F2vf9sib44VV+GzHWTTBneKomZn6n9/w6uojAID/u6obbrqEa7GJiIiIqPFxjXaYWrj2GL7cdQ5f7jqH4y9OqPfeu2sPXcDdH+2CRinH3mfGIkKlEM9tP1WCp745AAD4dk8eAOCafq3x3JQeiI1Q+XT/ar0J1/z7V1TqTdAo5ZjSt/7bHxE1RI3RjG25JQCAWy9ti9uHtQvxiIiIiIiopWJFOwyV64xYtvWU+LzrUz9h1b48v+9TWWPEM98dBADoTRa8teH/27vzsCjLvQ/g3xmWGZZhEHAYEFTcMFFzyUAytwSpTDtW7+ty8Nirp8Vss8XTqfeglal1Ttar5VIezBbN0o6mhUsiZuKSjooQKCIqyyibM+zDMPf7BzI5ASIyMzjw/VzXXJfzPPc8z33741F+c2/nUFZthBACb/wnBY+tSm7wme80uZj2yWEs230Gh6/rBddV1qDW1LDHevX+LJRWGwEASVbofSe6VfrKGvOfF04Mg1TKPauJiIiIqG2wR/s2k67VY/LHBy2OGU0Cc7/SoNYkEN1Pjc+Ss7Fy3zm8/sAduH+A2tz7fOR8MVycJPCUOSPEzwOz1v2K3KuV5uv8309n8X8/nYWvhyuKyg0AALWXHF193HEkuxgKmTNKq41IydUhJVeHD386a1GPEb388PbD/eEpd4afpwy1JoGvj140n78+0SGyN921nz9vdxdIJEyyiYiIiKjtSIQDTqzV6/VQKpXQ6XTw8vJq6+pYzYGzhZjx78Oo7zi+M0iJkzk6izIP3RmI70/+3rvt5+mKiB6+SMvTI6uJOdauzlIYjKZGz2W98wCkUgmEEJBIJEhMv4JXvj2JwjLDDevaV61AL5Untp/KNx/zcHVC6psxN9NUIqv6eF8mVuzNRIWhFl193LH/1TFtXSUiIiIiamdakoeyR/s28u2xSzAJYGCQEoseHoABQUoAwNYTuXh+4wkAsEiyAaCwzGCR7DZmRkQ3fHrgfIPjr4wPNQ+vre8BHNNXhZ9eGo2E0/lI15Yi/pdsKN1czL2F9dK1pUjX1q3sPLirNzQXr6LcUIsF21Lx2gN9IXN2gj2UVtVAKpHAQ8Yf5Y7kdK4OVytqcDS7GCcuXbWYtuDj4dqGNSMiIiIiYqJ9W9FcugoAeDk61JxkA8DEOwMRqlYg5oOfb/j5YB83RIT4Ymp4V0z++CC83V2w68WRcJZKkZCqRXm1EbrKGsyL6oORfTpjQBdlo9dRurngv4fVrdYc91AYAMBkEvjr+l9xMkeHx+4Kwsp95wAAvh6uWP8/d2P+5lP4IUWLdQezcTLnKjY+EWHzZLu0qgZj/pmEwrJqzI/pi9jh3eDJhPu2UlVTa7EAX2sZa014d2cG1uzPavT81Lu74iFu50VEREREbYxZyW2iqKwaF4oqAAB3BntbnJNIJOirthyakPbmeKzZn4UP9tTNo341JhSPR4bAzbUuqdH8bxRqhYCfpwwA8POrYyCRSGAwmuDq3PI18KRSCT79y10AgNQ8vTnRXjx5ABRyFyyfOgRCHMePp7XQXLyKTb/mICZMjV8yCzHxzkCrLkwlhMCBzELErj1iPrY0IR2peTosnzoYW0/kwcVJisFdvRHo7Yazl0tRbTQhLNCLc3dtqKqmFpNW/AInqQT9u3ghQ1uK03l6bHpyOIZ269Ti6x27UIz1yRdw8FwRVAoZwkN8cbXCgC2aXHOZQcHeGBikhIfMGZMGBTZ4ToiIiIiI2gIT7TYmhMD3p/Lx3AYNAKBnZw8o3RrfWmvjExHYdjIPbzx4B9xdnfHCuD54alRPSCWSBslzpz8Mn61PMG8lyf7jNXqpPM3Huvq6AwCcpBKs/PNQfLI/C4t++A0rEzOxaEcaqmrq5oY/PNg6235pdVWIXpYEfZWxwbnf8vX4TpOLeZtOmo95yZ3NZYd174QvZ0e06u+gIxNCYEdKPsIClQjx82hw7pkvjyPjct10grR8vfnczlRtixLtwrJqzFh7xOIaBaXVSM37/f38mL74670hcJJK+OUJEREREd12mGi3oU2/XsKr356yOBbVT91k+Ygevojo4WtxzJrDcm+W3MUJb00Kw2V9NUL9FRbnYod3w6cHspCnqzIfe+HrE/goMRNLHx2IIV0bT7h2pWohc3HCqD6db3jv3b9dtkiy/xzRFU/c2xMj30vEuYJyfHHogkX568sezS7BV4cvYCb3V74lxy9exdyv6r4Q8nZ3wczI7ghQyhETFoDPkrPxU/oVAEBnhQyh/gocyCwEAGw5nouZkd0R6O3W7D0OnC3En9cetjg2opcfMi6XoqC0GjJnKSJ7+mLWiJBb3lueiIiIiMjWmGi3oT8m2f87oR9iI7q1UW1aJnZ490aPy12cENnTD99dN7wXAM5eKcOSH9Ox6cnhDT6z9sB5vLU9DQDg6iTF0G6dsOSRAejm69GgbPEfVkN/7r7e8PWQIdjHDZeKK3H84lUAwMODAhHUyR0rEjMtyq9IzGSifYvOXOutBoCrFTXmaQvzN6eYj/9jQj/8z4i6v9/CsmrcuzQRhWXVGPVeIg69dh+83V3hdG0awW/5enyUmImgTu4YFOyNsX1V+PCnM+ZrPXdfb8yL6mN+X2mohdxFyh5sIiIiIrrtMdFuQ24uTqisqYW3uwuS/3afeX61o2tq6Puv2cVIy9Nj06+XMLirNx4aGIi96VfMSTYAGGpNSM4qwuPxR/HjC/daLKhWbazFsj1nLK7p6yGDk1SCp0b1xOvfnTYffzWmLwK93RAd5o8n1h+Du6sTsgrLUVhmwNnLpej9h574tvD10YuoNpoQG9HNIZLH3JLKG55/dGgQHr+nu/m9n6cM70zujxe/PomaWoGhb++BVFIXGy+5CxZ+n4rq67adu36Y/6NDg/Dc2F4W128vzwcRERERtX9MtNtAebURq/dnobKmFgDwzZPD21USMeXuYCSdKUBXH3cknSmAj4crXJ2k0Oqr8Oiqg6gw1GLdQZi3LGtMVmE5Pk++AC+5CxZcS8hqTb9v+f7IkCCE9/Ax945evwhWj84eCFDKAQADg7xx6O/3odJQi7sX7UFptRFRy/bj0Gv3QX2tjL2UVxvx8jcn8eNpLfqqFebt0foFeOGu7j52rcv1LhZVIF9XiQ1HLqKkogZ+njJMuTsYw66rU61JIKekbrG+1+7viwcGBCDzShkSTmtRVm3EpEGBiOrn3+ALgz8NDsKZy2XmxfNMAljyY7pFmQFdlEjJ1ZmT7Ht7++Gfj91pyyYTEREREdmURAghmi92e2nJRuG3g41HLmLB96l4dmxvPDOmFxb/8BtWX7c90bE3xsH32urg7YkQAidzdOirVmDG2iM4kl3cZNlPZ9wFhdwZlTW12H+mEP/+peG+3/Xu76/Gyj8PtThmMgm8veM39FR5YHp448Pvz1wuRfSy/QCAKcOCsWBi3dZl1TUmKN0b74W3luJyA4a8tbvRc0+P7on5MX1tev+mrE46h3d3Zlh8iVFv0Z/6Q19pxH80uThfWA5DbV3v84ppgzFhYOBN30MIgfEf7MeZy2UNzp2Mi4aX3BlzN2iw41Q+XJ2k2PBExC2tUk5EREREZEstyUPZo21DJeUGrDuYjQ9/qpvL+t7ODBzKKkJ5teWK2d7uro193OFJJBIMurZVWXOJ7LAQH/OQ80pDbZOJ9rg7VHj30YENjkulEvzjoX43vEcffwU6K2QoKK3GxqOXsPHoJQCAzFmKXS+ObHROeGsJIXA6V4+zV0qbLLNy3zkEKOWY0cS8d1vZcjwHi6/rXVa6uWB4D18kpGoBwGIo/vW6+ri36D4SiQRfzApHxuVSiy3ZXo7uY475R9OG4F+P1UJfVQOVwr4jDYiIiIiIrI2Jtg19+NNZrDuYbXHs57OFDco5WXGP6duVdxPztt+aFIbRoSqLed0jevuZ//zvmXfhxxQtnhzVA85SKbr7tS4ZXj51MKasOWRxrNpowts7fsPH04fAxUorWesqazD3q+MN4n1nsDeeGd0TB88VITzEB98cy8He9CuI25YKD1dnTB7SxebztYUQWPh9mvlnc3gPX7wSE4pQfwU8ZM6oNtbi5W9O4fuTeQ0+6ySVoM8tzG9Xecmh8pLjzNv3Y/wH+5FTUoGY/gEWZeQuTm2yij4RERERkbUx0bahWSNCGiTa9aL7+UPlJUP/QKV9K9VGvK/r0e7k7oLhPX0xaVAXjA9ruJ2ZQu6C7CUPmt+P7etvtXrcEeAFZ6kExj8Mld6ddhmPrDyIbXNHtOr6BqMJrs5SbD+V1+iXKrNGhCA6TI3oa+0O7+GLIW/thhDAS9+chK6yxrxqt618cyzH4ufyxag+FtuuyZydsHzqYDw1qgfOXi5DWKAXoq4NuY/u59+qZNjVWYrNT0fiaoUBPTp7Nv8BIiIiIiIHxETbhoJ93DF5SBdsOZ6LXipPjLvDH6uSzsHb3QWLJw9ol/OymzK0Wyd88nPdcHCF3AUfTx/azCdsQ+nmgjUzhsJYKxAdpoZWV4UJyw+gsKwap3J0KCk3oJPHrQ3lf2t7Gr44dAEPDgjAlmvbm0X29MWfI7rhVI4OtSYTYv7wxYKPhytOLYjGa5tTsCMlH0lnCmyeaF/fU/1SVB8M6974fOiwQCXCApWoNQl093WHvsrY7PD8m+Hj4QqfW/w7JiIiIiJyBEy0bSzuoTAMCvbGPb38oPaSw1kqwfgwdYdKsgFgfJgadwYpcTJHZzE0vC1c30OuVsrx6xvjcM+Svci9WonMgjIM86hbbXt9cjZO5+qwcGL/ZleFP1dQhrUH6r5I2HLdHuL/eKgf+qq98MCAgKY+Ci+5C/40uAt2pOTjaoWhyXKbj+VgVdI5hKoVePyeEPTs7IGfzxbi/v5qODcz5L20qgbrky+gwmDEhaK61cM/n3U37u3d+YafA+qGi+947l4Ya4XNF40jIiIiImoPmGjbmNLNxWKRq5fHh7ZdZdqQRCLBR9OHIOG0FlPu7trW1Wmgl8oTuVcrMf/bU8gqLMfH04fgH1tTAQCbfs3Bkb/fB5WX5SJdVTW1kDlLIZFIsOra9lX13FycEP/4MIttx26kk0ddAltSUdPoeZNJ4L2dGdDqq3D2Shm2n8o3n5sW3hV/u79ub+rG/JpdjMfXHUVpleUifJ1asAifh4z/VBARERER3Sz+9kx2E9TJHbPv7dHW1WhUL5Unks4UIKuwHAAw58vjFueX783Ei1F9IHeRwt3VGcculGDKmmSMCVVhXD9/fHMsBwCwcGIYRvbpjAClvEVzmetXni9pokf70PkiaPVVjZ776vBFfHX4Ij6cMgihagX6qBQorTbCxUmCjxPPYUViZqOfu9Uh8kREREREdGNMtIkA9FbdeGGuzw9dwOeHLiBQKcfns8Mx+7OjqKkV2JV2GbvSLpvL9e+iRMgtrIyuUtRNJSitMmJP2mWE9/CB4loP9aGsIkz75DAAYOrdwRjZuzPiD2bjgf5qlBtq8d7ODADA8xtPAADG3eGPxIwrDfbG3vDXCBSVV2PuVxrIXaTwZaJNRERERGQTTLSJULdYm0QCOEslqKkVTZbL01Xhvn8lNXpu8uAu5n3DW0ohd4FKIcOV0mrMXv8rQvw8MKpPZzhJJea539193fHcfb0RoHTD/dfN+e6t8sQTnx8zv9/z2++Jv5NUgqdH9UR4Dx8M7+kLAPD1kEEqAbfSIiIiIiKyEYkQoums4hYsXrwYW7ZsQXp6Otzc3BAZGYmlS5ciNPT3uclCCCxcuBBr1qxBSUkJwsPD8dFHHyEsLOym7qHX66FUKqHT6eDldXNzYImac66gDGovOTxkzqiqqcWBs4X44vAF7MsoaLT8K+NDYTCa8OXhC1gz4y6LLbJuxQsbNfjPiYZ7V9fbM28UejXR8378Ygk+/TkLP6RozcfenBSGUH8Fwnv4tqpeRERERETUsjzU6ol2TEwMpkyZgmHDhsFoNOL1119HSkoK0tLS4OFRN6R26dKlWLRoEdatW4c+ffrg7bffxv79+5GRkQGFQtHsPZhok738klmIx+OP4r+GBSFA6YZeKk/klFTC3dUJU4YFQyKRWO1eWl0VVu7LxJ7frqCm1oQrpdXmcwfmj0FQJ/cbft5kEnj525PYcjwXMyO7Y8HEm/viioiIiIiImtemifYfFRQUQKVSISkpCSNHjoQQAoGBgXjhhRcwf/58AEB1dTX8/f2xdOlSPPnkk81ek4k22VNNrQkuzWyfZQtPf3EMP57W4rmxvTAv+uZWqxdCIDVPj14qTw4NJyIiIiKyopbkoTbPHnQ6HQDAx6dub+Lz589Dq9UiOjraXEYmk2HUqFE4ePBgo9eorq6GXq+3eBHZS1sk2QCw9NGB+G5OJF6M6nPTn5FIJOjfRckkm4iIiIioDdk0gxBCYN68eRgxYgT69+8PANBq6+aQ+vv7W5T19/c3n/ujxYsXQ6lUml/BwcG2rDbRbcFL7oLBXTtZdXg6ERERERHZnk0T7blz5+LUqVPYsGFDg3N/TB6EEE0mFK+99hp0Op35denSJZvUl4iIiIiIiKi1bLa917PPPott27Zh//79CAoKMh9Xq9UA6nq2AwJ+36LoypUrDXq568lkMshkMltVlYiIiIiIiMhqrN6jLYTA3LlzsWXLFuzduxchISEW50NCQqBWq7F7927zMYPBgKSkJERGRlq7OkRERERERER2ZfUe7WeeeQZfffUVtm7dCoVCYZ53rVQq4ebmBolEghdeeAHvvPMOevfujd69e+Odd96Bu7s7pk2bZu3qEBEREREREdmV1RPtlStXAgBGjx5tcTw+Ph4zZ84EALz66quorKzEnDlzUFJSgvDwcOzateum9tAmIiIiIiIiup3ZfB9tW+A+2kRERERERGRPt9U+2kREREREREQdCRNtIiIiIiIiIitiok1ERERERERkRUy0iYiIiIiIiKyIiTYRERERERGRFTHRJiIiIiIiIrIiJtpEREREREREVsREm4iIiIiIiMiKmGgTERERERERWRETbSIiIiIiIiIrYqJNREREREREZEXObV2BWyGEAADo9fo2rgkRERERERF1BPX5Z30+eiMOmWiXlpYCAIKDg9u4JkRERERERNSRlJaWQqlU3rCMRNxMOn6bMZlMyMvLg0KhgEQiaevqNEmv1yM4OBiXLl2Cl5dXW1eHmsA4OQbGyTEwTrc/xsgxME6OgXFyDIyTY3CEOAkhUFpaisDAQEilN56F7ZA92lKpFEFBQW1djZvm5eV12/6w0O8YJ8fAODkGxun2xxg5BsbJMTBOjoFxcgy3e5ya68mux8XQiIiIiIiIiKyIiTYRERERERGRFTHRtiGZTIa4uDjIZLK2rgrdAOPkGBgnx8A43f4YI8fAODkGxskxME6Oob3FySEXQyMiIiIiIiK6XbFHm4iIiIiIiMiKmGgTERERERERWRETbSIiIiIiIiIrYqJNREREREREZEVMtImIiIiIiIisiIl2MxYvXoxhw4ZBoVBApVLh4YcfRkZGhkUZIQQWLFiAwMBAuLm5YfTo0UhNTbUos2bNGowePRpeXl6QSCS4evVqg3t1794dEonE4vW3v/3Nls1rF+wZIwDYsWMHwsPD4ebmBj8/P0yePNlWTWtX7BWnffv2NXiO6l9Hjx61dTMdnj2fpzNnzmDSpEnw8/ODl5cX7rnnHiQmJtqyee2GPeN0/PhxREVFwdvbG76+vnjiiSdQVlZmy+a1C9aIUXFxMZ599lmEhobC3d0dXbt2xXPPPQedTmdxnZKSEsTGxkKpVEKpVCI2NrbJ/8PIkj3jtGjRIkRGRsLd3R3e3t72aF67Ya84ZWdnY9asWQgJCYGbmxt69uyJuLg4GAwGu7XVkdnzeZo4cSK6du0KuVyOgIAAxMbGIi8vzy7tvFlMtJuRlJSEZ555BocOHcLu3bthNBoRHR2N8vJyc5l3330X77//PlasWIGjR49CrVYjKioKpaWl5jIVFRWIiYnB3//+9xve780330R+fr759cYbb9isbe2FPWO0efNmxMbG4vHHH8fJkyfxyy+/YNq0aTZtX3thrzhFRkZaPEP5+fmYPXs2unfvjrvuusvm7XR09nyeHnzwQRiNRuzduxfHjh3DoEGDMGHCBGi1Wpu2sT2wV5zy8vIwbtw49OrVC4cPH0ZCQgJSU1Mxc+ZMWzfR4VkjRnl5ecjLy8M///lPpKSkYN26dUhISMCsWbMs7jVt2jScOHECCQkJSEhIwIkTJxAbG2vX9joqe8bJYDDgsccew9NPP23XNrYH9opTeno6TCYTVq9ejdTUVCxbtgyrVq1q9vd3qmPP52nMmDHYtGkTMjIysHnzZpw7dw6PPvqoXdvbLEEtcuXKFQFAJCUlCSGEMJlMQq1WiyVLlpjLVFVVCaVSKVatWtXg84mJiQKAKCkpaXCuW7duYtmyZbaqeodhqxjV1NSILl26iE8//dSm9e8obPksXc9gMAiVSiXefPNNq9a/o7BVnAoKCgQAsX//fvMxvV4vAIg9e/bYpjHtmK3itHr1aqFSqURtba35mEajEQDE2bNnbdOYdqq1Maq3adMm4erqKmpqaoQQQqSlpQkA4tChQ+YyycnJAoBIT0+3UWvaL1vF6Xrx8fFCqVRave4diT3iVO/dd98VISEh1qt8B2LPOG3dulVIJBJhMBis14BWYo92C9UPW/Dx8QEAnD9/HlqtFtHR0eYyMpkMo0aNwsGDB1t8/aVLl8LX1xeDBg3CokWLOFTlFtgqRsePH0dubi6kUikGDx6MgIAA3H///Q2GYtLNsfWzVG/btm0oLCxkD9wtslWcfH19cccdd2D9+vUoLy+H0WjE6tWr4e/vj6FDh1q3ER2AreJUXV0NV1dXSKW//7rg5uYGADhw4IA1qt5hWCtGOp0OXl5ecHZ2BgAkJydDqVQiPDzcXCYiIgJKpbJV/3Z2VLaKE1mXPeOk0+nM96GWsVeciouL8eWXXyIyMhIuLi5WbEHrMNFuASEE5s2bhxEjRqB///4AYB7i6O/vb1HW39+/xcMfn3/+eWzcuBGJiYmYO3cuPvjgA8yZM8c6le8gbBmjrKwsAMCCBQvwxhtvYPv27ejUqRNGjRqF4uJiK7WgY7D1s3S9tWvXYvz48QgODr71CndQtoyTRCLB7t27odFooFAoIJfLsWzZMiQkJHDuYgvZMk5jx46FVqvFe++9B4PBgJKSEvMQyvz8fCu1oP2zVoyKiorw1ltv4cknnzQf02q1UKlUDcqqVCpOw2ghW8aJrMeecTp37hyWL1+Op556ykq17zjsEaf58+fDw8MDvr6+uHjxIrZu3WrlVrQOE+0WmDt3Lk6dOoUNGzY0OCeRSCzeCyEaHGvOiy++iFGjRmHgwIGYPXs2Vq1ahbVr16KoqKhV9e5IbBkjk8kEAHj99dfxyCOPYOjQoYiPj4dEIsE333zTuop3MLZ+lurl5ORg586dDeb10M2xZZyEEJgzZw5UKhV+/vlnHDlyBJMmTcKECROYwLWQLeMUFhaGzz77DP/617/g7u4OtVqNHj16wN/fH05OTq2ue0dhjRjp9Xo8+OCD6NevH+Li4m54jRtdh5pm6ziRddgrTnl5eYiJicFjjz2G2bNnW6fyHYg94vTKK69Ao9Fg165dcHJywowZMyCEsF4jWomJ9k169tlnsW3bNiQmJiIoKMh8XK1WA0CDb2GuXLnS4NualoqIiAAAZGZmtuo6HYWtYxQQEAAA6Nevn/mYTCZDjx49cPHixdZUvUOx57MUHx8PX19fTJw48dYr3EHZOk579+7F9u3bsXHjRtxzzz0YMmQIPv74Y7i5ueGzzz6zTiM6AHs8T9OmTYNWq0Vubi6KioqwYMECFBQUICQkpPUN6ACsEaPS0lLExMTA09MT3333ncXQSLVajcuXLze4b0FBQat/D+lIbB0nsg57xSkvLw9jxozB8OHDsWbNGhu0pH2zV5z8/PzQp08fREVFYePGjfjhhx9w6NAhG7To1jDRboYQAnPnzsWWLVuwd+/eBr9YhISEQK1WY/fu3eZjBoMBSUlJiIyMbNW9NRoNgN8TPGqcvWI0dOhQyGQyi20KampqkJ2djW7durW+Ie2cvZ8lIQTi4+MxY8YM/rLTAvaKU0VFBQBYzP2tf18/eoSa1hb/N/n7+8PT0xNff/015HI5oqKiWtWG9s5aMdLr9YiOjoarqyu2bdsGuVxucZ3hw4dDp9PhyJEj5mOHDx+GTqdr9e8hHYG94kStY8845ebmYvTo0RgyZAji4+Mb/D9FTWvL56m+J7u6utpKrbEC26+35tiefvppoVQqxb59+0R+fr75VVFRYS6zZMkSoVQqxZYtW0RKSoqYOnWqCAgIEHq93lwmPz9faDQa8cknn5hX2tVoNKKoqEgIIcTBgwfF+++/LzQajcjKyhJff/21CAwMFBMnTrR7mx2NvWIkhBDPP/+86NKli9i5c6dIT08Xs2bNEiqVShQXF9u1zY7InnESQog9e/YIACItLc1ubWwP7BWngoIC4evrKyZPnixOnDghMjIyxMsvvyxcXFzEiRMn7N5uR2PP52n58uXi2LFjIiMjQ6xYsUK4ubmJDz/80K7tdUTWiJFerxfh4eFiwIABIjMz0+I6RqPRfJ2YmBgxcOBAkZycLJKTk8WAAQPEhAkT7N5mR2TPOF24cEFoNBqxcOFC4enpKTQajdBoNKK0tNTu7XY09opTbm6u6NWrlxg7dqzIycmxKEPNs1ecDh8+LJYvXy40Go3Izs4We/fuFSNGjBA9e/YUVVVVbdL2xjDRbgaARl/x8fHmMiaTScTFxQm1Wi1kMpkYOXKkSElJsbhOXFzcDa9z7NgxER4eLpRKpZDL5SI0NFTExcWJ8vJyO7bWMdkrRkLUbRX10ksvCZVKJRQKhRg3bpw4ffq0nVrq2OwZJyGEmDp1qoiMjLRDy9oXe8bp6NGjIjo6Wvj4+AiFQiEiIiLEDz/8YKeWOjZ7xik2Nlb4+PgIV1dXMXDgQLF+/Xo7tdKxWSNG9duuNfY6f/68uVxRUZGYPn26UCgUQqFQiOnTpze79SHVsWec/vKXvzRaJjEx0X4NdlD2ilN8fHyTZah59orTqVOnxJgxY4SPj4+QyWSie/fu4qmnnhI5OTl2bvGNSYS4jWaMExERERERETk4TjogIiIiIiIisiIm2kRERERERERWxESbiIiIiIiIyIqYaBMRERERERFZERNtIiIiIiIiIitiok1ERERERERkRUy0iYiIiIiIiKyIiTYRERERERGRFTHRJiIiIiIiIrIiJtpEREREREREVsREm4iIiIiIiMiK/h/ifbvN4KSlCQAAAABJRU5ErkJggg==",
+      "text/plain": [
+       "<Figure size 1200x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from statsmodels.tsa.arima.model import ARIMA\n",
+    "\n",
+    "train = df['Close'][:-200]\n",
+    "test = df['Close'][-200:]\n",
+    "\n",
+    "model = ARIMA(train, order=(5,1,0))  # (p,d,q) — tune using AIC\n",
+    "model_fit = model.fit()\n",
+    "forecast = model_fit.forecast(steps=len(test))\n",
+    "\n",
+    "plt.figure(figsize=(12,6))\n",
+    "plt.plot(train.index, train, label='Train')\n",
+    "plt.plot(test.index, test, label='Test')\n",
+    "plt.plot(test.index, forecast, label='ARIMA Forecast')\n",
+    "plt.legend()\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 564
+    },
+    "id": "4-SnQaMTJUfH",
+    "outputId": "7c33dfe8-2248-49aa-cb06-86e9a9a563f7"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA+0AAAIhCAYAAAA7GltoAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8fJSN1AAAACXBIWXMAAA9hAAAPYQGoP6dpAADMBElEQVR4nOzdd3hTZRsG8DvN6p5AB5Q9yhIUGQIyBNlLUFREQXAiKAoO/BRBEQQFUZAPVLAKKqCAAn7KHiKICILsWXZLGd0j83x/pDnNyWrSJiRt79919SJn5kkp1ec87/u8MkEQBBARERERERGR3wnwdQBEREREREREZB+TdiIiIiIiIiI/xaSdiIiIiIiIyE8xaSciIiIiIiLyU0zaiYiIiIiIiPwUk3YiIiIiIiIiP8WknYiIiIiIiMhPMWknIiIiIiIi8lNM2omIiIiIiIj8FJN2IiIq0aeffgqZTIZmzZrd1vft0qULunTp4tF7btiwAT169EBCQgLUajUSEhLQpUsXfPDBB5Lzpk+fjp9++smj723t/PnzkMlk+Oijj0p1vUwmk3xFRESgS5cu+OWXX1y6fvv27ZDJZNi+fXup3r+sdDod4uLiIJPJ8OOPP9o9Z8qUKZLPqFQqUbNmTTz99NNIS0uzOb927dro16+fZJ/52pEjR9p9j3fffVc85/z583bPGTx4MGQyGcaOHevWZ7T+OzJ/ValSxa37lEdXr17FlClTcPDgQV+HQkRUrjFpJyKiEi1ZsgQAcPToUezdu9fH0ZTewoUL0atXL4SHh2P+/PnYsGEDZs6cicaNG9skjbcjafeEBx98EHv27MEff/yBzz77DGlpaejfv79Liftdd92FPXv24K677roNkdpav349rl27BgBYvHix03N/++037NmzB7/++iseeeQRLFmyBN26dYNOp3PpvcLCwvDDDz8gJydHsl8QBCQnJyM8PNzhtenp6Vi/fj0A4Ntvv0VhYaFL72lm/juy/NqwYYNb9yiPrl69iqlTpzJpJyIqI4WvAyAiIv/2999/49ChQ+jbty9++eUXLF68GG3btvV1WKUyY8YMdOrUySZBf/zxx2E0Gn0UVdnExsaiXbt2AID27dvjnnvuQf369TF37lz07dvX7jU6nQ4ymQzh4eHitb6wePFiqFQqdO7cGRs3bsTly5dRo0YNu+e2atVKrE53794dN27cwFdffYVdu3aha9euJb7XwIEDsWrVKixfvhxPP/20uH/r1q1ISUnB008/jS+++MLutd988w10Op34b2D16tUYNmyYy5/T8u/IkwwGA/R6PdRqtcfvTURE/oOVdiIicspcAf3ggw/Qvn17LF++HPn5+ZJzzMO8Z82ahffffx81a9ZEYGAg7r77bmzZskVyrnm48z///IPBgwcjPDwcERERGD58OK5fv15iPFqtFtOmTUNSUhLUajWqVq2KJ5980qVrb968ifj4eLvHAgKK/5Mok8mQl5eHr7/+WhzObDlM/8iRIxg4cCCioqIQGBiIli1b4uuvv7a5Z2ZmJiZMmIC6detCrVajWrVq6NOnD06cOOEwRp1OhxEjRiA0NFSs7rqjXr16qFq1Ki5cuACgeAj80qVLMWHCBFSvXh1qtRpnzpxxODx+79696N+/P2JiYhAYGIh69eph/PjxknNOnz6NYcOGoVq1alCr1WjcuDE+++wzl+O8evUqfvvtN/Tv3x+vvvoqjEYjkpOTXb7+7rvvBgCxUl+SiIgIPPDAA+KoEbMlS5agQ4cOaNiwocNrlyxZgtjYWHz99dcICgqyuUdZXbx4EcOHD5d8L2fPni15kGT5b2zatGmoU6cO1Go1tm3bBsD0cG3AgAGIjo5GYGAg7rzzTqxcudLmva5cuYJnnnkGiYmJUKlUSEhIwIMPPih+HwsLCzFhwgS0bNkSERERiI6Oxj333IOff/7Z5l4//PAD2rZti4iICAQHB6Nu3boYNWoUANPPXevWrQEATz75pPjvaMqUKR793hERVQZM2omIyKGCggJ8//33aN26NZo1a4ZRo0YhJycHP/zwg93z58+fj99++w1z587FsmXLEBAQgN69e2PPnj025z7wwAOoX78+fvzxR0yZMgU//fQTevbs6XS4s9FoxMCBA/HBBx9g2LBh+OWXX/DBBx9g06ZN6NKlCwoKCpx+nnvuuQerVq3ClClTcOjQIRgMBrvn7dmzB0FBQejTp484nHnBggUAgJMnT6J9+/Y4evQoPv30U6xevRpNmjTByJEjMWvWLPEeOTk56NixIxYtWoQnn3wS69atw8KFC9GwYUOkpqbafd/MzEz07NkTGzduxI4dO2zmZrsiIyMDN2/eRNWqVSX7J02ahIsXL2LhwoVYt24dqlWrZvf6DRs24N5778XFixcxZ84c/Prrr3jrrbckyfGxY8fQunVrHDlyBLNnz8b69evRt29fvPjii5g6dapLcSYnJ8NgMGDUqFHo3r07atWqhSVLlkAQBJeuT0lJAQCnyba10aNH488//8Tx48cBmL7fq1evxujRox1es3v3bhw/fhxPPPEEYmJiMGTIELE67ypBEKDX6yVf5s95/fp1tG/fHhs3bsR7772HtWvXonv37pg4caLd+fOffvoptm7dio8++gi//vorkpKSsG3bNnTo0AGZmZlYuHAhfv75Z7Rs2RIPP/yw5EHIlStX0Lp1a6xZswavvPIKfv31V8ydOxcRERHIyMgAAGg0Gty6dQsTJ07ETz/9hO+//x4dO3bE4MGD8c0334j32rNnDx5++GHUrVsXy5cvxy+//ILJkydDr9cDME29+OqrrwAAb731lvjv6KmnnnL5+0ZEREUEIiIiB7755hsBgLBw4UJBEAQhJydHCA0NFe69917JeSkpKQIAISEhQSgoKBD3Z2dnC9HR0UL37t3Ffe+8844AQHj55Zcl9/j2228FAMKyZcvEfZ07dxY6d+4sbn///fcCAGHVqlWSa/ft2ycAEBYsWOD085w5c0Zo1qyZAEAAIAQFBQndunUT5s+fL2i1Wsm5ISEhwogRI2zu8cgjjwhqtVq4ePGiZH/v3r2F4OBgITMzUxAEQXj33XcFAMKmTZscxmP+vn344YdCSkqK0KRJE6FJkybC+fPnnX4OMwDCmDFjBJ1OJ2i1WuH48eNC7969BQDCZ599JgiCIGzbtk0AIHTq1MnmevOxbdu2ifvq1asn1KtXT/L3aK1nz55CjRo1hKysLMn+sWPHCoGBgcKtW7ecxm00GoX69esL1atXF/R6vSAIxT8XW7ZskZxr3p+WlibodDohIyNDWLlypRASEiI8+uijNveuVauW0LdvX5vv0wsvvCAYjUahTp06wsSJEwVBEITPPvtMCA0NFXJycoQPP/xQACCkpKRIrh01apQAQDh+/Ljke/b22287/YyW723v64svvhAEQRDeeOMNAYCwd+9eyXXPP/+8IJPJhJMnTwqCUPyzUq9ePZuf1aSkJOHOO+8UdDqdZH+/fv2E+Ph4wWAwiJ9FqVQKx44dcyl2QRAEvV4v6HQ6YfTo0cKdd94p7v/oo48EAOLPuz3mf5dfffWVy+9HRES2WGknIiKHFi9ejKCgIDzyyCMAgNDQUDz00EP4/fffcfr0aZvzBw8ejMDAQHE7LCwM/fv3x86dO22q2o899phke+jQoVAoFOJwX3vWr1+PyMhI9O/fX1K1bNmyJeLi4krsgl6vXj0cOnQIO3bswNSpU9G9e3fs27cPY8eOxT333ONSg7GtW7eiW7duSExMlOwfOXIk8vPzxVEFv/76Kxo2bIju3buXeM8DBw6gXbt2iI2NxR9//IFatWqVeI3ZggULoFQqoVKp0LhxY+zevRvvvvsuxowZIzlvyJAhJd7r1KlTOHv2LEaPHi35e7RUWFiILVu24IEHHkBwcLDk76FPnz4oLCzEn3/+6fR9duzYgTNnzmDEiBGQy+UAiodQOxp6HhcXB6VSiaioKAwdOhStWrWyOyXBGXMH+aVLl0Kv12Px4sUYOnQoQkND7Z6fm5uLlStXon379khKSgIAdO7cGfXq1UNycrLLfRCGDh2Kffv2Sb4GDRoEwPTz1KRJE7Rp00ZyzciRIyEIArZu3SrZP2DAACiVSnH7zJkzOHHihPjvyfrvIzU1FSdPngRg+pns2rUrGjdu7DTeH374AR06dEBoaCgUCgWUSiUWL14sjlAAIA59Hzp0KFauXIkrV6649L0gIiL3MWknIiK7zpw5g507d6Jv374QBAGZmZnIzMzEgw8+CAB2k6u4uDi7+7RaLXJzc52eq1AoEBMTg5s3bzqM6dq1a8jMzIRKpYJSqZR8paWl4caNGyV+roCAAHTq1AmTJ0/G2rVrcfXqVTz88MPYv3+/S3OVHc2LT0hIEI8DpmHPjpqqWdu0aROuXbuGp556CpGRkS5dY2ZOCP/++2+cPHkSN2/exNtvv21znqO5/JbMfQGcxX3z5k3o9XrMmzfP5u+gT58+AFDi34O5T8IDDzwg/lxFRESgY8eOWLVqFTIzM22u2bx5M/bt24cNGzZgyJAh2LlzJ8aNG1fiZ7Jm7n8wffp0HDhwwOnQ+BUrViA3NxdDhw4V48zKysLQoUNx6dIlbNq0yaX3rFq1Ku6++27Jl7mpnqs/T2bW55qnLUycONHm78P84Mb89+HKz+Tq1asxdOhQVK9eHcuWLcOePXuwb98+jBo1SvJQq1OnTvjpp5+g1+vxxBNPoEaNGmjWrBm+//57l74nRETkOnaPJyIiu8zzi3/88Ue7a2h//fXXmDZtmlgpBWB33ey0tDSoVCqbamZaWhqqV68ubuv1ety8eRMxMTEOY6pSpQpiYmLw22+/2T0eFhZW4ueyFhISgkmTJmHFihU4cuRIiefHxMTYnZN+9epVMUbAlKhdvnzZpRheffVVnD17Fk888YSYBLnKnBCWRCaTuXQvAE7jjoqKglwux+OPP44XXnjB7jl16tRxeH1WVhZWrVoFoLhaa+27776zGSnQokUL8Xt7//33o2fPnvj8888xevRoh/exJzExEd27d8fUqVPRqFEjtG/f3uG55ocL48ePt2nEZz7es2dPl9/bHld/nsys/x7NxydNmoTBgwfbfY9GjRoBcO1nctmyZahTpw5WrFgheS+NRmNz7sCBAzFw4EBoNBr8+eefmDFjBoYNG4batWvjnnvucfo+RETkOibtRERkw2Aw4Ouvv0a9evXw5Zdf2hxfv349Zs+ejV9//VXSLG316tX48MMPxaHVOTk5WLduHe69915Jcg+Y1rtu1aqVuL1y5Uro9XpJl3Zr/fr1w/Lly2EwGEq17FxqaqrdqqZ52K+5ugkAarXabmO7bt26Yc2aNbh69ark/G+++QbBwcHi0l69e/fG5MmTsXXrVtx3331O4woICMCiRYsQGhqKkSNHIi8vD88//7zbn6+sGjZsiHr16mHJkiV45ZVX7C4lFhwcjK5du+Kff/7BHXfcAZVK5dZ7fPfddygoKMB7772Hjh072hx/6KGHsGTJEpuk3ZJMJsNnn32GJk2a4K233nJ7zfMJEyYgKCgIDz30kMNzjh8/jj179mDIkCF2G8JNmzYNP//8c4kPmkrSrVs3zJgxAwcOHMBdd90l7v/mm28gk8lKXM6uUaNGaNCgAQ4dOoTp06c7Pbd3795YunQpTp48KSby1mQyGVQqlSRhT0tLs9s93kytVqNz586IjIzEhg0b8M8//+Cee+4Rf35KahBJRETOMWknIiIbv/76K65evYqZM2faTaKbNWuG+fPnY/HixZKkXS6X4/7778crr7wCo9GImTNnIjs7225H8dWrV0OhUOD+++/H0aNH8fbbb6NFixYYOnSow7geeeQRfPvtt+jTpw9eeukltGnTBkqlEpcvX8a2bdswcOBAPPDAAw6vb9q0Kbp164bevXujXr16KCwsxN69ezF79mzExsZKhko3b94c27dvx7p16xAfH4+wsDA0atQI77zzDtavX4+uXbti8uTJiI6OxrfffotffvkFs2bNQkREBABTdXbFihUYOHAg3njjDbRp0wYFBQViV3h7ydjs2bMRFhaGMWPGIDc3F6+++qrDz+Itn332Gfr374927drh5ZdfRs2aNXHx4kVs2LAB3377LQDgk08+QceOHXHvvffi+eefR+3atZGTk4MzZ85g3bp1NvOwLS1evBhRUVGYOHGi3XnzTzzxBObMmYNDhw6hRYsWDu/ToEEDPPPMM1iwYAF27dpl9wGAIz169ECPHj2cnmOusr/22ms2880B0wOpLVu2YNmyZXjppZdcfm9rL7/8Mr755hv07dsX7777LmrVqoVffvkFCxYswPPPP+9Sd/xFixahd+/e6NmzJ0aOHInq1avj1q1bOH78OA4cOCCu9vDuu+/i119/RadOnfDmm2+iefPmyMzMxG+//YZXXnkFSUlJ6NevH1avXo0xY8bgwQcfxKVLl/Dee+8hPj5e0sdi8uTJuHz5Mrp164YaNWogMzMTn3zyCZRKJTp37gzA1EMiKCgI3377LRo3bozQ0FAkJCRIHnYREZELfNwIj4iI/NCgQYMElUolpKenOzznkUceERQKhZCWliZ2tp45c6YwdepUoUaNGoJKpRLuvPNOYcOGDZLrzN3A9+/fL/Tv318IDQ0VwsLChEcffVS4du2a5Fzr7vGCIAg6nU746KOPhBYtWgiBgYFCaGiokJSUJDz77LPC6dOnnX6uRYsWCYMHDxbq1q0rBAcHCyqVSqhXr57w3HPPCZcuXZKce/DgQaFDhw5CcHCwAEASx+HDh4X+/fsLERERgkqlElq0aGG3Q3ZGRobw0ksvCTVr1hSUSqVQrVo1oW/fvsKJEycEQZB2j7dk7mQ+efJkp58HRV3RnTF3O//hhx8cHrPsHi8IgrBnzx6hd+/eQkREhKBWq4V69erZdPtPSUkRRo0aJVSvXl1QKpVC1apVhfbt2wvTpk1zGMuhQ4cEAML48eMdnnPixAkBgDBu3DhBEIp/Xq5fv25z7rVr14TQ0FCha9eu4j5n3eOdsewer9VqhWrVqgktW7Z0eL5erxdq1KghNG/e3Ol9XXnvCxcuCMOGDRNiYmIEpVIpNGrUSPjwww/Fru+C4PhnxezQoUPC0KFDhWrVqglKpVKIi4sT7rvvPnHlB7NLly4Jo0aNEuLi4gSlUikkJCQIQ4cOlfzb++CDD4TatWsLarVaaNy4sfDFF1+Ifw9m69evF3r37i1Ur15dUKlUQrVq1YQ+ffoIv//+u+T9vv/+eyEpKUlQKpUCAOGdd95x+r0gIiJbMkFwcUFUIiIiB86fP486dergww8/xMSJE52eO2XKFEydOhXXr1+3ma9LRERERFLsHk9ERERERETkp5i0ExEREREREfkpDo8nIiIiIiIi8lOstBMRERERERH5KSbtRERERERERH6KSTsRERERERGRn1L4OgB/YDQacfXqVYSFhUEmk/k6HCIiIiIiIqrgBEFATk4OEhISEBDguJ7OpB3A1atXkZiY6OswiIiIiIiIqJK5dOkSatSo4fA4k3YAYWFhAEzfrPDwcB9HQ0RERERERBVddnY2EhMTxXzUESbtgDgkPjw8nEk7ERERERER3TYlTdFmIzoiIiIiIiIiP8WknYiIiIiIiMhPMWknIiIiIiIi8lOc0+4iQRCg1+thMBh8HQpVcHK5HAqFgssPEhERERERk3ZXaLVapKamIj8/39ehUCURHByM+Ph4qFQqX4dCREREREQ+xKS9BEajESkpKZDL5UhISIBKpWIFlLxGEARotVpcv34dKSkpaNCgAQICOIuFiIiIiKiyYtJeAq1WC6PRiMTERAQHB/s6HKoEgoKCoFQqceHCBWi1WgQGBvo6JCIiIiIi8hGW8FzEaifdTvx5IyIiIiIigEk7ERERERERkd9i0k5ERERERETkp3yatO/cuRP9+/dHQkICZDIZfvrpJ8nx3NxcjB07FjVq1EBQUBAaN26M//73v5JzNBoNxo0bhypVqiAkJAQDBgzA5cuXb+OnqDy6dOmC8ePH+zoMIiIiIiKiSsOnSXteXh5atGiB+fPn2z3+8ssv47fffsOyZctw/PhxvPzyyxg3bhx+/vln8Zzx48djzZo1WL58OXbt2oXc3Fz069evUq+nLpPJnH6NHDmyVPddvXo13nvvPc8GS0RERERERA75tHt879690bt3b4fH9+zZgxEjRqBLly4AgGeeeQaLFi3C33//jYEDByIrKwuLFy/G0qVL0b17dwDAsmXLkJiYiM2bN6Nnz56342P4ndTUVPH1ihUrMHnyZJw8eVLcFxQUJDlfp9NBqVSWeN/o6GjPBUlEREREREQl8us57R07dsTatWtx5coVCIKAbdu24dSpU2Iyvn//fuh0OvTo0UO8JiEhAc2aNcPu3bsd3lej0SA7O1vy5SpBEJCv1fvkSxAEl2KMi4sTvyIiIiCTycTtwsJCREZGYuXKlejSpQsCAwOxbNky3Lx5E48++ihq1KiB4OBgNG/eHN9//73kvtbD42vXro3p06dj1KhRCAsLQ82aNfH555+7/L0kIiIiIiIi5/x6nfZPP/0UTz/9NGrUqAGFQoGAgAB8+eWX6NixIwAgLS0NKpUKUVFRkutiY2ORlpbm8L4zZszA1KlTSxVTgc6AJpM3lOrasjr2bk8EqzzzV/b6669j9uzZ+Oqrr6BWq1FYWIhWrVrh9ddfR3h4OH755Rc8/vjjqFu3Ltq2bevwPrNnz8Z7772HN998Ez/++COef/55dOrUCUlJSR6Jk4iIiIiIqDLz60r7p59+ij///BNr167F/v37MXv2bIwZMwabN292ep0gCJDJZA6PT5o0CVlZWeLXpUuXPB263xs/fjwGDx6MOnXqICEhAdWrV8fEiRPRsmVL1K1bF+PGjUPPnj3xww8/OL1Pnz59MGbMGNSvXx+vv/46qlSpgu3bt9+eD0FERERERFTB+W2lvaCgAG+++SbWrFmDvn37AgDuuOMOHDx4EB999BG6d++OuLg4aLVaZGRkSKrt6enpaN++vcN7q9VqqNXqUsUVpJTj2Lu+mSsfpJR77F533323ZNtgMOCDDz7AihUrcOXKFWg0Gmg0GoSEhDi9zx133CG+Ng/DT09P91icRERERET+JC2rEPlaPepWDfV1KFRJ+G3SrtPpoNPpEBAgHQwgl8thNBoBAK1atYJSqcSmTZswdOhQAKYmbEeOHMGsWbO8EpdMJvPYEHVfsk7GZ8+ejY8//hhz585F8+bNERISgvHjx0Or1Tq9j3UDO5lMJv79EBERERFVNO1mbAEA7H+rO2JCS1cIJHKHT7PP3NxcnDlzRtxOSUnBwYMHER0djZo1a6Jz58549dVXERQUhFq1amHHjh345ptvMGfOHABAREQERo8ejQkTJiAmJgbR0dGYOHEimjdvLnaTJ9f8/vvvGDhwIIYPHw4AMBqNOH36NBo3buzjyIiIiIiI/INlY+gz6blM2um28GnS/vfff6Nr167i9iuvvAIAGDFiBJKTk7F8+XJMmjQJjz32GG7duoVatWrh/fffx3PPPSde8/HHH0OhUGDo0KEoKChAt27dkJycDLncc0PJK4P69etj1apV2L17N6KiojBnzhykpaUxaSciIiIiKqI3FiftOoNrKzsRlZVPk/YuXbo4XcYsLi4OX331ldN7BAYGYt68eZg3b56nw6tU3n77baSkpKBnz54IDg7GM888g0GDBiErK8vXoRERERER+QWtvngaqM7AKaF0e8gEVxf/rsCys7MRERGBrKwshIeHS44VFhYiJSUFderUQWBgoI8ipMqGP3dERERE/uWVFQdx/mYeDlzMBAAserwVejaN821QVK45y0Mtlf+OakRERERERF6kNxix+p8rkn0aPSvtdHswaSciIiIiIrKw4WgaNh27hg71YzCwRXVo7QyFz9fofRAZVUYBJZ9CRERERERUeTy7dD9+3H8ZL684hLd+PiKZy25mL5H3hEu38nHf7O1Yuue8V+5P5Q+TdiIiIiIiIge+23vRftLupeHxczefxrnreXj756OYu/kUMvK0XnkfKj+YtBMRERERETlhb/66t5Z8E1B837mbT+P1Vf965X2o/GDSTkREREREVMTe4lr2hsJ7a8m38EClZHv32ZteeR8qP5i0ExERERERFdEb7STtdivt3knag1VyyTZX6CYm7UREREREREX0doa9385GdDKZdNvOMwSqZJi0ExERERERFbGXjJv3hajkqBUTDADQ6b2TTVtX+i3nuFPlxKSdiIiIiIioiL1h73+l3AIA1IgKxsCW1R2eZykrX4dec3fik82n3Xp/jU56X1baiUl7BSSTyZx+jRw5stT3rl27NubOneuxWImIiIiI/Im9ZPzDDScBAEEqOVRymcPzzFKzCrBo51mcSMvBx5tPufX+Gr1Bss057aTwdQDkeampqeLrFStWYPLkyTh58qS4LygoyBdhERERERH5PWfD3l/q1gCnruUAMC0Dt+FoGlrVikKVULV4zpErWeg3b1ep37+QlXaywkq7uwQB0Ob55svFp2xxcXHiV0REBGQymWTfzp070apVKwQGBqJu3bqYOnUq9Hq9eP2UKVNQs2ZNqNVqJCQk4MUXXwQAdOnSBRcuXMDLL78sVu2JiIiIiCoSRw3mBrZMQNekalDKTSnUmn+u4Nml+zFm2QHJeUv3XCjT+1/P0Ui2jf5Yac+8CKx5Drh51teRVAqstLtLlw9MT/DNe795FVCFlOkWGzZswPDhw/Hpp5/i3nvvxdmzZ/HMM88AAN555x38+OOP+Pjjj7F8+XI0bdoUaWlpOHToEABg9erVaNGiBZ555hk8/fTTZf44RERERET+ZvlfF+3uD1GbUielQlr3/Ov8Lcn2v1eySv3eBy9lYteZG5J9/pizY/0rwJlNwL8rgXdulXw+lQmT9krm/fffxxtvvIERI0YAAOrWrYv33nsPr732Gt555x1cvHgRcXFx6N69O5RKJWrWrIk2bdoAAKKjoyGXyxEWFoa4uDhffgwiIiIiIq/4cleK3f1BStP66Wq588HKx1OzS/3eP+6/VOprb6ubZ0x/Cgbn55FHMGl3lzLYVPH21XuX0f79+7Fv3z68//774j6DwYDCwkLk5+fjoYcewty5c1G3bl306tULffr0Qf/+/aFQ8EeFiIiIiCq+Hk1isfHYNZv9YtKu9N4M41PXcgEAtWKCceFmPgAgMljptfcrNX2hryOoVJiJuUsmK/MQdV8yGo2YOnUqBg8ebHMsMDAQiYmJOHnyJDZt2oTNmzdjzJgx+PDDD7Fjxw4olX74C4OIiIiIyIOqR9lv2hxYlKybk3d36A1GKEqo0AOmZeIA4L2BzXA6PRfvrT+GULWfpWy6QiAnteTzyGP87CeAvO2uu+7CyZMnUb9+fYfnBAUFYcCAARgwYABeeOEFJCUl4fDhw7jrrrugUqlgMHAYDBERERFVTOal3NrXi8HuszfF/YFFyXqQyv2kXeti0m5ughekkqN9vRgAtt3kfS7jvHRbEEyFTfIado+vZCZPnoxvvvkGU6ZMwdGjR3H8+HGsWLECb731FgAgOTkZixcvxpEjR3Du3DksXboUQUFBqFWrFgDTOu07d+7ElStXcOPGDWdvRURERERU7piXfLOuqJuTdXuV9l5zd6JQ57iw9fCiP3HgYkaJ763VmxJ0lTwA6qKGdxon9/WJq9Ju+Rwq731M2iuZnj17Yv369di0aRNat26Ndu3aYc6cOWJSHhkZiS+++AIdOnTAHXfcgS1btmDdunWIiTE96Xv33Xdx/vx51KtXD1WrVvXlRyEiIiIi8jhzpT3QOmkv2rbeDwAn0nJw9rppPrq9ovPhK1kYvGB3ie+t0ZsSdJUiQHyfHI3e2SW330/PS7e1+b6JoxLh8PgKbuTIkRg5cqRkX8+ePdGzZ0+75w8aNAiDBg1yeL927dqJS8AREREREVU0WgdJe6CTpB0wDWM3GIUyLdGmKaq0qy2SdgA4fS0HDWLDSn9jTxEEQBYACBZD9o+sAto+47uYKgFW2omIiIiIiIqYK+3hQdL6ZlAJc9oLdQZxeHtpmZN2lSJAMgx/3SEfrV5lzaiXJuwAcHytb2KpRJi0ExERERERFdEZTKXy6pHSLvLmyndCRCAeuLM67m1QBe8NbIqQoiS+QGsQq/QA0Lx6hFvvKwhC8Zx2RYDk4UB0iMr9D+INlvPXe800/WnQ+SaWSoRJOxERERERURFzpT06RCUu8wYUL/kmk8nw8cMtsXR0Wzx+T200r2FKzgt0BvFaAFj1fHsEu9Fp3vywAADUCtN1j7ROBADkaf2kGZ1eW/w6sqbpT4PGN7FUIkzaiYiIiIiIipgTb6U8ABFBSnG/o2Hx5mHsBRbD45VyGVSKAMRHBErOFZxMeDc3oQMgdo4PKVqjfeXfl7Bq/2V3P4rnmSvtchWgLBqJcPUfYPtM38VUCTBpJyIiIiIiKmKueCvlAfjv8FbifntLvQHFyXyhzoCfDl4BYFqyDQBUCuk1lsPnrVnOhzdfH1qUtF+4mY8JPxzCjVwfV7XFpF0NKNTF+7dP9008lQSTdiIiIiIioiLmSrtKIUPV0OLE1FHXePP+Aq0Bv5+6AaB4OLu5Ym7mrFFdTqFpabdglRwBAaZ14+pWDZGcU+DrYfKX9pr+1OaYEne6LZi0ExERERERFSke4h6AyODi4fHm6rc1y+HxAkxV+llD7jBdY5W0a5wk7TfzTPPFLZvO9b8jQXKOvTXgbyvLNdoVftIcrxLgOu1ERERERERFLOe0hwUq8WrPRtDqjYhy0MHdMmk3FuXkoYGmNMu60u4sac+wk7QHBMgQpJSjQGeqsOsNZVgE3tMUgSWfQx7BpJ2IiIiIiKhI8Zx2U1n7ha71nZ4vzmnXGmAsajQXUFQSt07anQ1vz8g3Je2RwdKHAwZjcaKuczIn/rao0Qa4/JfptZyV9tuFw+OJiIiIiIiK6C0q7a4ItKi0G8Sk3XSsbZ0YyblZBY7XNC8sqqaHWHWpNwiWSbuPK+0xRQ8wur4lbURHXsWkvYLbvXs35HI5evXqZXPs/PnzkMlk4ldERATatWuHdevWSc5LTk5GZGSkZFsmk6Fx48Y291y5ciVkMhlq165tc6ygoABRUVGIjo5GQUFBibFPmTJFEp/5a/PmzSV/cD+1fft2yGQyZGZm+joUIiIiIrJDa9E93hXFw+ONMBfF5UVZ+9Od6uLQ5B5oEh8OAMgq0Nq9B1A8dN66Ou9XlXbzmuzq0OIl38ycLGdHZcOkvYJbsmQJxo0bh127duHixYt2z9m8eTNSU1Oxd+9etGnTBkOGDMGRI0ec3jckJATp6enYs2ePzfvVrFnT7jWrVq1Cs2bN0KRJE6xevdql+Js2bYrU1FTJV6dOnVy61ppW6/iXJBERERERIJ3T7grz8PgCrQFGo3R4PABEBCsRE2oaSr5oxznxHGvFSbv9LvUA8PLKg/i5aFk5n9AXJe1yFRAYIe0gL/j4gUIFxqTdTYIgIF+X75Mvwc2nV3l5eVi5ciWef/559OvXD8nJyXbPi4mJQVxcHJKSkvD+++9Dp9Nh27ZtTu+tUCgwbNgwLFmyRNx3+fJlbN++HcOGDbN7zeLFizF8+HAMHz4cixcvdukzKBQKxMXFSb5UKtMvvcOHD+O+++5DUFAQYmJi8MwzzyA3N1e8duTIkRg0aBBmzJiBhIQENGzYEABw5coVPPzww4iKikJMTAwGDhyI8+fPS953yZIlaNq0KdRqNeLj4zF27Fjx2Jw5c9C8eXOEhIQgMTERY8aMkbzvhQsX0L9/f0RFRSEkJARNmzbF//73P5w/fx5du3YFAERFRUEmk2HkyJEufR+IiIiI6PYQl3xzs9JeqLOY0x4gbfNeNcyU3O5NuYU/U27avY+maHi8Wun4fc9dz8NLyw86HWbvVYai9zXPZx/1q+0x8jg2onNTgb4Abb9r65P33jtsL4KVwS6fv2LFCjRq1AiNGjXC8OHDMW7cOLz99tuQOVgrQqfT4YsvvgAAKJVKu+dYGj16NDp16oRPPvkEwcHBSE5ORq9evRAbG2tz7tmzZ7Fnzx6sXr0agiBg/PjxOHfuHOrWrevy57GUn5+PXr16oV27dti3bx/S09Px1FNPYezYsZKHE1u2bEF4eDg2bdpkeuCSn4+uXbvi3nvvxc6dO6FQKDBt2jT06tUL//77L1QqFf773//ilVdewQcffIDevXsjKysLf/zxh3jPgIAAfPrpp6hduzZSUlIwZswYvPbaa1iwYAEA4IUXXoBWq8XOnTsREhKCY8eOITQ0FImJiVi1ahWGDBmCkydPIjw8HEFBQdYfjYiIiIh8SKy0K1xbX00yp90ondNu9uJ9DbD6gKlCfjNXi58PXkH1yCDcXTtaPKfQwfB4e85ez8VdNaNcis9jjMbi4fHm+exVLabLGvW3N55KhEl7BWaubANAr169kJubiy1btqB79+6S89q3b4+AgAAUFBTAaDSidu3aGDp0aIn3b9myJerVq4cff/wRjz/+OJKTkzFnzhycO3fO5twlS5agd+/eiIqKEuNZsmQJpk2b5vQ9Dh8+jNDQUHG7SZMm+Ouvv/Dtt9+ioKAA33zzDUJCQgAA8+fPR//+/TFz5kzxwUFISAi+/PJLsTq/ZMkSBAQE4MsvvxQfXnz11VeIjIzE9u3b0aNHD0ybNg0TJkzASy+9JL5v69atxdfjx48XX9epUwfvvfcenn/+eTFpv3jxIoYMGYLmzZsDgOTBRHS06RdztWrVJH0CiIiIiMj3BEEQm70pAkoxPL6o0i63KpLVrhKCLo2qYvvJ6ziemo0F288CAE6810tM+s2VdvO2Mxdv5uOumlHQG4zQ6I0IUXs5rTv6k2mNdl2+aVuulP4JMGn3IibtbgpSBGHvsL0+e29XnTx5En/99Zc4d1yhUODhhx/GkiVLbJL2FStWICkpCadOncL48eOxcOFCMbksyahRo/DVV1+hZs2ayM3NRZ8+fTB//nzJOQaDAV9//TU++eQTcd/w4cPx8ssvY+rUqZDLHf9iatSoEdauXStuq9Wmp3rHjx9HixYtxIQdADp06ACj0YiTJ0+KSXvz5s3FhB0A9u/fjzNnziAsLEzyPoWFhTh79izS09Nx9epVdOvWzWFM27Ztw/Tp03Hs2DFkZ2dDr9ejsLAQeXl5CAkJwYsvvojnn38eGzduRPfu3TFkyBDccccdzr6NREREROQHLLuzuzo8PrCoMl6oN4hz2e2NbDUPo0/LLhT3nbqWgztqRAJw3IjOnhyNKUHu9cnvOJOei0OTeyAiuOSRsqW2bXpxwg4Uz2UPsEgnmbR7DZN2N8lkMreGqPvK4sWLodfrUb16dXGfIAhQKpXIyMgQK94AkJiYiAYNGqBBgwYIDQ3FkCFDcOzYMVSrVq3E93nsscfw2muvYcqUKXjiiSegUNj+SG3YsEGcR27JYDBg48aN6N27t8P7q1Qq1K9vuzamIAgOh/lb7rdM6gHAaDSiVatW+Pbbb22uq1q1KgJKeKJ64cIF9OnTB8899xzee+89REdHY9euXRg9ejR0OtM8nqeeego9e/bEL7/8go0bN2LGjBmYPXs2xo0b5/TeRERERORbemNxMzVXh8dbrtNurpLLrcfHo7iCnm0xH91y3XZHjehqRAXhcoZ05SVd0bln0k19lfacu4lezeJcirdUqjUGbpws3jbPaZfJAJkcEAxM2r2IjegqIL1ej2+++QazZ8/GwYMHxa9Dhw6hVq1adhNWs86dO6NZs2Z4//33XXqv6OhoDBgwADt27MCoUaPsnrN48WI88sgjklgOHjyIxx57zOWGdNaaNGmCgwcPIi8vT9z3xx9/ICAgQGw4Z89dd92F06dPo1q1aqhfv77kKyIiAmFhYahduza2bNli9/q///4ber0es2fPRrt27dCwYUNcvXrV5rzExEQ899xzWL16NSZMmCD2CjBX/Q0Gg801REREROQ7vx1Jw2s//ituu7/km8XweDuXmpP2zcfTxX3meexAcQJv3Yju26ds+2lZL/1m5xmBZ6lCpdtqi1Gr5mo7G9F5DZP2Cmj9+vXIyMjA6NGj0axZM8nXgw8+WGKiPGHCBCxatAhXrri2nERycjJu3LiBpKQkm2PXr1/HunXrMGLECJtYRowYgbVr1+L69etuf8bHHnsMgYGBGDFiBI4cOYJt27Zh3LhxePzxx+02wrO8rkqVKhg4cCB+//13pKSkYMeOHXjppZdw+fJlAKb14WfPno1PP/0Up0+fxoEDBzBv3jwAQL169aDX6zFv3jycO3cOS5cuxcKFCyXvMX78eGzYsAEpKSk4cOAAtm7dKq5pX6tWLchkMqxfvx7Xr1+XdJ0nIiIiIt95btl+rP83VdxWuJgJSxrRFSXtzobHWyrUFRdyMvJNyxNHBqsk59SKCcHC4XdJ9lkn7Y5GoHqMuYoeHAN0eROo3qr4mDlpZ6Xda5i0V0CLFy9G9+7dERERYXNsyJAhOHjwIA4cOODw+n79+qF27douV9vNS67ZY24UZ2+OeNeuXREWFoalS5e69D6WgoODsWHDBty6dQutW7fGgw8+iG7dutnMp7d33c6dO1GzZk0MHjwYjRs3xqhRo1BQUIDw8HAAwIgRIzB37lwsWLAATZs2Rb9+/XD69GkApuZ7c+bMwcyZM9GsWTN8++23mDFjhuQ9DAYDXnjhBTRu3Bi9evVCo0aNxCZ11atXx9SpU/HGG28gNjZWspQcEREREfkHtSLA5URYHB6vM8JgsN+IDgAC7SzlZi9pjwlR2ZzXq1k8Tk7rhYSIQACA1iBdCtrbhXYYi6ronV4FurwOyC2mxJpfGzmS1FtkgruLf3vQzp078eGHH2L//v1ITU3FmjVrMGjQIMk5x48fx+uvv44dO3bAaDSiadOmWLlyJWrWrAkA0Gg0mDhxIr7//nsUFBSgW7duWLBgAWrUqOFyHNnZ2YiIiEBWVpaYuJkVFhYiJSUFderUQWBgYJk/M5Er+HNHREREdHvVfuMX8XVEkBKH3unh0nV5Gj2avrNBvC6rQId1YzuieQ1pAe3TLacxZ9Mpyb6ZQ5rj4dY1ceRKFvrN2wUA+N+L96JJgjQnMXtv/TEs3pWC57vUw6s9GqHum/8DACwZeTfuS3I82rTMVj4BHPsZ6PMR0OZp6bFZdYH8m0BSP+CRomm4x9YCBRlAqxHei6kCcJaHWvJppT0vLw8tWrRwWB09e/YsOnbsiKSkJGzfvh2HDh3C22+/LUlixo8fjzVr1mD58uXYtWsXcnNz0a9fP84ZJiIiIiKiUnGlg7tZsEoOc2E9p9BUkbbX21hl556FOtMw97WHinsk1Yh2vGKUeZ79mgNX0G3ODnG/zNu1dkPR0PcAO33MQ4qaV+cUTy3AyseBdS8CGRe8G1cl4dPu8b1793baOfw///kP+vTpg1mzZon7LNe8zsrKwuLFi7F06VJxGbNly5YhMTERmzdvRs+ePb0XPBERERERVUjWzeCckclkCFUpkKPRw1g0hjnAzvB4e43tPtp4EsPb1UK+1pQUD727BsIDHS/dppKb7mu5bJwpBpfDLR3z8Hi5ndj6fAh83Q/QFPVqshzIXZgJoJaXg6v4/HZOu9FoxC+//IKGDRuiZ8+eqFatGtq2bYuffvpJPGf//v3Q6XTo0aN46EpCQgKaNWuG3bt3O7y3RqNBdna25IuIiIiIiAiwXXatJKGB0lqovSXf7FXacwr16PLRNmiKKu61YkJszrHkqKO9VxvRHVkFnN5oeh1gJ2lXF3WW1+SY/pR0kff6bPtKwW+T9vT0dOTm5uKDDz5Ar169sHHjRjzwwAMYPHgwduwwDQVJS0uDSqWSrDkOALGxsUhLS3N47xkzZiAiIkL8SkxM9OpnISIiIiKi8sNe0zhnQtTSpN1e43m1RcL9Vt/G4utLtwrENdoD7XSYt6R0MGzfa6mxQQ/8aLGsc4Cd+NRFc7G1RZV2yy7yMr9NN8sVv/0uGo2mH9yBAwfi5ZdfRsuWLfHGG2+gX79+NktsWRMEwenTpkmTJiErK0v8unTpUonx+LBfH1VC/HkjIiIi8h1354iH2iTtdobHK4r3dWlUTXLM3EW+pLn0rq4d7zEGjXTb3vB4lUWlXRCKh9IDTNo9xG+/i1WqVIFCoUCTJk0k+xs3boyLFy8CAOLi4qDVapGRkSE5Jz093ela3Wq1GuHh4ZIvR5RK0w9mfn5+aT8KkdvMP2/mnz8iIiIi8o5tJ9Jx97RNkn1avdHB2fZ1byxNwu0Oj5cXV6mDVdKKdUFR0l5Spd3eEHsA4vrwHicZ6g77jejMw+MhANq84qZ1wG2YbF85+LQRnTMqlQqtW7fGyZMnJftPnTqFWrVMzQxatWoFpVKJTZs2YejQoQCA1NRUHDlyRNK8rizkcjkiIyORnp4OwLTOt1fnjFClJggC8vPzkZ6ejsjISMjl7s2nIiIiIiL3vLnmMG7kaiX7GsSGOjjbvhe61sdn286Kybe9SrvlrhCVNA3LKTQluiVV2tvViba732C4XUm7nYKSMthUUReMxUPkzTh61CN8mrTn5ubizJkz4nZKSgoOHjyI6Oho1KxZE6+++ioefvhhdOrUCV27dsVvv/2GdevWYfv27QCAiIgIjB49GhMmTEBMTAyio6MxceJENG/eXOwm7wlxcXEAICbuRN4WGRkp/twRERERkXcYjQJSs6Sd2KcNaoa+zePduo9MJkO1cDUu3DSNlgywU2nXGYqr90FWlXbzUnElVdobxIbhzT5JmP6/E5L9Xqu0G62Sduvh8oDpaYQqDNBkmTrIK4uX54bAZbg9wadJ+99//42uXbuK26+88goAYMSIEUhOTsYDDzyAhQsXYsaMGXjxxRfRqFEjrFq1Ch07dhSv+fjjj6FQKDB06FAUFBSgW7duSE5O9miFUiaTIT4+HtWqVYNOpyv5AqIyUCqVrLATERER3QY7Tl232fdI60QoSjF33HKpNnuN6PQW1XDrYe7ZLlbaAUBuZxF4o9FblXbpCASxQ7w1dagpadfmSJvVGZm0e4JPk/YuXbqU2HBr1KhRGDVqlMPjgYGBmDdvHubNm+fp8GzI5XImU0REREREFYAgCHgyeZ/Nfnvz0V0RZrHsm9zO8Hi90fE8+es5pgp2RFDJ/YyUctt7e29Ou166rSuwf55lMzqVxdQCVto9wm8b0REREREREXmLef65JZU8oNT9qyyTdnv3aBAbVuI94iMCSzxHYafSbrgdlfbImkCzIfbPE9dqz5Uu+ebkQQW5zm8b0REREREREXlLgdY2aXdleLojllVye9X6u2pGYeHwVqgVE2z3+gAZEBOqLvF9FHbubfT2nPaweOClfx13g1cXPZDQ5kqb17HS7hGstBMRERERUaWTby9pV5Y+PerWuHjJaUe1+l7N4tA43v5y08EqhUtD8xX2hsd7q6BtTsDlSufLt4nD47Olzes4p90jmLQTEREREVGlU2hneLxaUfr+VV0bmdZqjwxWIjTQ/QHN9uaq22OvSZ73GtEVJeD2lnqzZK60Z12WzoMXODzeEzg8noiIiIiIKh1zpV2lCIBWb0ouyzI8XqUIwKHJPWAUBChd6D4fIAMsc23rjvKO2Bse771GdEVz2uUq5+cVZJj+3PUxUP/+4v0cHu8RrLQTEREREVGlY25EZzkX3d7Qc3dEBCsRFVJCglskWCWtn7qS6AMOknZvVdrNQ93lJdR6z+8qfn14pcX1TNo9gUk7ERERERFVOuZGdJZd3wNK2Tm+NAKV0qH4KheTdnvJ/Vs/HRGXjfMofVGlvaTh8dWaFL8++Vvx66zLwP5kx0vFkUuYtBMRERERUaWjKRoSH6b2TdI+umMdybarw+MdNav7+/ytMsdkIyPF9GdYvPPzBi0ofq3JLn697kVg3UvAtumej60SYdJORERERESVjrao5XqQqrji7Ur3dk95plNdSXXd5eHxDobw67wxRP7mGdOfsU2dnxdTH5AVfR91+bbHT23wbFyVDJN2IiIiIiLye59tO4N1h6567H66okq7yqJjfI2oII/dvyTyABk6NqgibrvaPb5e1VDx9Qtd64mvzZ/Ho/RFQ+5VIc7Pk8mKO8iXVm468Od/gUv7ynafCojd44mIiIiIyK/9ezkTH244CQDo3yLBI/c0V9pV8gAsf6Yd9p67hSGtqnvk3q6yrLS7Ojw+NjwQXzxxN27mavBIm5r493IWfj99A3qjF5J2y3XaSxJRAyjMtH/MlWkHm6cCB5eZXk/OAAJYXzZj0k5ERERERH4tp7B47e9CncGmiVtp6MxJu0KGdnVj0K5uTJnv6S7LRN3V4fEAcH+TWPF1SFEXeq3Bg8Pjc68DK58ALu42bZfUiA4AHkoG5t9dhvdMK36tywfUoY7PrWT4+IKIiIiIiPyaZaH2Zp7WI/c0r83uatd2b7BM2ksbh3mOu97gwUr7zg+LE3bAtUp7lQZle0+5uvi1vXnxlRiTdiIiIiIi8mvm5dkA4Fauh5L2oiTXnQq3p0mSdheHx1szx+/J+f7Q5Ei3XUnay8xipIA27za8X/nBpJ2IiIiIiPxankXSfiPPM+uR6/SmJFFZymTZE6qFFVeXLacAuGPXmRsAgAMXMz0RkokyULotV7l23cPLHBxwYU67sfjvmJV2KSbtRERERETktwRBwA9/XxK3b3qs0m5KEn05PP6pe+uKr3WlHN5+PcczDzEklMHS7QAXW6E17g9MybJzwIX59oJF0q5l0m6JSTsREREREfmtXWdu4PfTN8TtW56qtBc1bivtsHRPCFUXJ8NeWGW99ASrBwjuDo/v/4l0W5Pr3nvqODzeEpN2IiIiIiLyW/9ellZuswp0HrmvPzSik/CnrN1mTruLw+PNEu6UbuffLPkaIyvtjvjJTygREREREZGU3mDEt39esNrnmexWozcliWofVtr9ltaqMu7q8Hgz6+H1+gLA2TryeTeAlB3F25zTLsGfUCIiIiIi8kv/3X4WV7MKAQCx4aambVoPLW2WpzEl7UGqsq/5XuFYD2d3d3i8ddIOOB/y/uOT0m12j5dg0k5ERERERH7pu78uiq+rRwYBcL9h26Vb+eg1dydW7b8s2Z9f1JE+RO1mFdlLhFKOj48K9sJybNaVdneHqwdG2O6bUQO4uNf++Sk7pduWlfaCDGDv57bnVCJM2omIiIiIyC+FBRYn1InRpuqtu8Pjp647ihNpOZjwwyHJ/nytaYm14HJeaV84vJXT40ZjKR4GWFfarZP4kqhC7O9f/7Jr11tW2nd8CPz6KvB1f2BRp0pZhWfSTkREREREfskyQW9QLRSA+8PjczXF659n5euQVjTc3lxpD1b5SaW9lFP1G8SGia+tE/StJ66hxdSN+O1Imns31RY1oqvaGIiqAzTs5d71Mgfrsjvab/P+Fon55b+KX6ceAq7sdy+WCoBJOxERERER+Y3swuLu8K1qRYmvzcm1u5V2eUBxotji3Y1oN2MLvvojxe8q7aVtrye3SIQNVpn/qOS/kaPR47llbia65qR5yJfAi/8A6lD3A5PZSTXV4a5dazk8PvWQ1bEC92Mp55i0ExERERGRX/j54BXcMWUjlu45DwBQK03pykvdGkBZ1OXd3TntAXaqu1PXHUNGvunhgL8k7aUll1sk7aUZCm/t5lkg77rptTLI9eq4tX5zgdjm0n1hca5dq9cABh3w2yTAoJUeq4Sd5Zm0ExERERGRX3hp+UEAwNs/HwUA6PSmJFSlCICyqGLuiaQdAK7naAAA1cIDSxOqxzzWtiYA4JX7G5bqeoXFSAJ9WZN2XQGwoF3xtrvrs1tqNQJ4fhfw3B9AaKxpn6vz0Y064Pc5wJ8L7MRYWPqYyikm7URERERE5Besq97m+esqeQCUcnOl3b3ENMBJoVgmA6qFqd0L0sOmDWqGQ5N7oEP9KqW63vKhhLnSnlWgQ59Pfnf/ZrnXpJVthQe+N3HNgJ7TTa9drZIb9MCts/aPVcJKu390XSAiIiIiokovWKUQG8St/PsSrmSa5i8r5TIoioaBF+oMbt1T7iRrr1c1VHwY4CsymQwRZVi2zbLSPmLJX+hYvwra1o3GsdRs929WmCXdLkul3VJAUdopuDhKwqgHDBr7xzinnYiIiIiIyDf0xuKk7rUf/8VfKbcAACqFHKqi5Hpvyi0s3pVS4r3OXc/F0EV7sPl4umS/ZTX/h2fv8UTYPhVgkbQfvJSJ+dvO2J1CsPvsjZJvVpAp3fZEpR0oTtqNeufnmRl1jpPzU7+ZloEzuvfwpjxj0k5ERERERF637/wt/Hs5U9wWrDqdn0nPQWa+DvYo5TJJRfy99cdKrLg/vvgvMem3FB5YXNWOCvFQJdnHFFajCexNIRj2xV5o9CUkuoWZ0m25j5J2g95x0n7+d2DbNGD7DM/EVg4waSciIiIiIq/KKdThoYV7MGD+H9DqjVh94DJavrsJe87eFM9ZtOOcw+tVigBEWg0hn7f1tNP3NA+tt2a9LFpFEGCVtDvqIn/pVglDyzW51jcuS1gW9yka3WAvabdXMTfqiueuN+gBNOpje87OD4G8m7b7KyAm7URERERE5FU5hcXJ2q9HUvHKykPIKtDhww0nxP3pOQ7mMAOIClbhrppRGNgyQdx3Jj3X4fl6O8PDn763Dn587h7PLIvmZ2wr7fbnjl/KKKGJm7eavIlJu50E3XoePWBa7s1cab9nLDB0KfDSv7bn3XL8oKciYSM6IiIiIiLyKq2+OIn84vfiRCsuoni5NWfD3dvXi0FAgAzPda6Hnw9eBSAd5m4tV1P8kGDh8FZomRgpvldCZCBu5WlR1cdd4z1JbrWsnd5Bh32NzkkjOF0BkHnBk2EVE4fH2/k73vCm7T6jvvgBgjIYkCuAqFq25+Ve81yMfoxJOxEREREReZXGImm/nFE8RDtYVZyOFOrtJ5SRwUooiuazJ8WFIUAGGIXi5eDsMVf2A5UB6NUsTnJsxgN34L1fjuHhuxPd/yB+KkcjHXZu2dDPlf3QFQDzWgHZVzwdmomzOe15dhrkGfWAvmjpOYWTvgOVJGnn8HgiIiIiIvIqywZols3mrmUXYux3B/DzwSso1NqvtL/eK0l8LZPJMG1QcwBAvtaAa9mFuHAzz+Yac9IeqratxjevEYGVz96DIa1qlO7DlAPaokq79Wp3jobN49ox24S92zueC8ictN88A8xvDfzxafExfaHt+QYdIBT9PMjktsfNKsma7ay0ExERERGRVxU6GJb9+2lTlXX9v6k2xx5pnYjRHeugfrVQyf4glanuuO1EOtrN2AJBAJaMvBv3JcWK5+QUmh4MhAdWznRHUzTVIFApF9e9B+x3lQdgSqYtdXwZuPcVzwVkntMOAbhxCtj0NtDhRdMug9b2fKOueE33AIukXRYgXetdX2iq1AdFe65pnh+quJ+MiIiIiIj8QolLjdkRHaJCg9gwyKzmawcpTUmc3ijA3Aj+6JVsyTnmOe2hlTVpL5pqYP5emTma6w6N9Pvn8TXQnVXL9XYaEBr0xTHILFLWAKuREym/Ax/WA9aOLXuMfoxJOxEREREReZXTBmgODL7L/vD1IJVtIp5htb67eXh8WCVP2gOtk3ZHc9qth6in2enUXhYBdv4etEVD2x1W2oseMFgm/Nb3Sdlh+vPgt2WP0Y9Vzp9iIiIiIiK6bTQOmszZs3ZsB4SqFahbNdTu8aS4MJt9mQXSxM/cmC1UXTnTHfPIhtpVgiXr1Wsd/T1YJ+33ve3ZgOwl7fpCQBXsZE57UayWIy3s3acSYKWdiIiIiIi8ytlyboCpYVqADGhePQLNq0c4TNgBIDY8EH2aSzvCZ9pU2k3bYU6WhavIzCMb6lQJwaaXO6FulRAApikFdlkPUa9xt2cDspdsmzvJ6+1V2g0Wjegsh8c7GWZfgVXORxVERERERHRb7Dt/CxN+OOT0nCUjWyM+Igix4WqbOez2RAVLlwHL1xYvJSYIAmb9dhIAK+2KgAA0iA1DmzrROHcjD3pH3eMtq92Pr/F8QPaSbfOw+OzLpj9HrAcKM4EVwx03oquklfbK+amJiIiIiOi2eHnFQafH9/2nO6qGqd26p/Vcbcvh96eu5Yqv61UNceu+FYW5W7+iaM03hdz0p8Pu8bqipL3Ta0C9+zwfkL1k26ADDv9YvB0WDwRHFx8Th8dbVtorZ/rq0+HxO3fuRP/+/ZGQkACZTIaffvrJ4bnPPvssZDIZ5s6dK9mv0Wgwbtw4VKlSBSEhIRgwYAAuX77s3cCJiIiIiKhEVzMLcDmjwGZ/TIgK3z7VFt+MauN2wg4AgUppGmO5pFxadnHVeFjbWm7fuyIwT0dQyE3fJ0XRcmglNqJTuP934RK7lXYdcPA76Tnm7vBGnYPu8U6SdnvD7CsInybteXl5aNGiBebPn+/0vJ9++gl79+5FQkKCzbHx48djzZo1WL58OXbt2oXc3Fz069cPBoOHlykgIiIiIiK3ZOQ7TqQ61K+CTg2rluq+MkiH0FsuKXcty5SAdm5YFfKAkofaV0S/HkkDUPxwQ1lSpd08p10R6J2A7CXbS3oCZ7cUb0fWBORF5xn0FpV2y+HxTua02+tCX0H4dHxB79690bt3b6fnXLlyBWPHjsWGDRvQt29fybGsrCwsXrwYS5cuRffu3QEAy5YtQ2JiIjZv3oyePXt6LXYiIiIiInLOcl3wl7o1wCdbTnvmvlYN1TQ6I9JzCjHjfyfEfdEhKuvLKh3zNAJlUcVd53BOe9FoCK9V2u2knQW3il8P/ca20g7zkm8uVtqNesfHyjm/nhRgNBrx+OOP49VXX0XTpk1tju/fvx86nQ49evQQ9yUkJKBZs2bYvXu3w6Rdo9FAoynukJidne354ImIiIiIKrk8iwZxlv3lXOg159SljHzJ9pXMAry5+gg2H78m7gtSVZ5O4yEqOfK0tiON1Yqi4fFFSbveUaU9P8P0Z1CUV+Irset7UNFcdnlR0m5ZNXe1EZ2x4o609usl32bOnAmFQoEXX3zR7vG0tDSoVCpERUl/uGJjY5GWlubwvjNmzEBERIT4lZiY6NG4iYiIiIg86fu/LuL7vy76Ogy35WuKE6nHJPPLy5a1D2tTEwDQoFrx0nCWCTsABCkrT9L+89gOGNm+ts1+sdJeNE1AMqfdaAA0RU378m+Y/gyp4p0A5SVU8JXBpj/tJeWurtNu1Dk+Vs75bdK+f/9+fPLJJ0hOTnZp2QdLgiA4vWbSpEnIysoSvy5dulTWcImIiIiIvOJEWjYmrT6MSasPIyu/fCUm5kp7+3oxpWo450iH+lWwfWIXfDnC8XrilSlpr18tDFMGNEWVUOmUAPOcdnOlXasvqrTrCoB5dwEzqgMb3wLyipL2YG8l7SVMVVAUHbebtLu4TnsFHh7vt0n777//jvT0dNSsWRMKhQIKhQIXLlzAhAkTULt2bQBAXFwctFotMjIyJNemp6cjNjbW4b3VajXCw8MlX0RERERE/uhMevESZpad0cuDvKJKe0jReunTBjWDWhGAeY/eWeZ7164S4jQxr0zD480CrAqXaoV5TrtVpf3WOSDjvOn12e2m9dEBLw6PD3BeJTdX4s3D4y1ZNqK77y3Tn/W62R5n0n77Pf744/j3339x8OBB8SshIQGvvvoqNmzYAABo1aoVlEolNm3aJF6XmpqKI0eOoH379r4KnYiIiIjIY7QWa5BfK2dJe35RpT2kKIEe3q4Wjk7tiXvqxXjk/s6q94LgYP52Baaw6pZf3D3eak67zuLnSJtbnPCqvLiuvbNqu1hpt5e0W6SsDe4HXj0LDF8F3DMW6DIJUBVNkajAc9p92oguNzcXZ86cEbdTUlJw8OBBREdHo2bNmoiJkf5jViqViIuLQ6NGjQAAERERGD16NCZMmICYmBhER0dj4sSJaN68udhNnoiIiIioPNNYJO3OllDzR7kaUzIYrC5OO8xDtT1BJpNhxTPt8PDnf9ocu5pVvh5weIL19zawqNKuEJd8K/pZMneLB4qr7IB3k3aZk793c6XdXjXeeki8ed59z/dNf+5dZPrTUL6mjrjDp0n733//ja5du4rbr7zyCgBgxIgRSE5OdukeH3/8MRQKBYYOHYqCggJ069YNycnJkMsr33AYIiIiIqp4LCvtDtfZ9lP5RR3NQ9XeSzva1o3BUx3r4MtdKZL9jWLDvPae/srcLd6sQdH3QBlQVGk32qm0FxRNNQ5Q2B+e7inORj6Yl5oLCDAl94JFwzxnyT5QnOhX4OHxPk3au3Tp4tawlfPnz9vsCwwMxLx58zBv3jwPRkZERERE5B+kSbuDdbb9VJ650u7l+eWW35etEzpj56nreKRN5VshSq0sTnD73REvTh9QKpxU2s2UXqyyl8Ry6HyAEjAUL89dYtJuftDApJ2IiIiIiHxBoy+eq1uekvabuRp8u9e0TF2Iyrtph9bi+1K3aijqVg11cnbFZR4ODwCN44ubbSuKKu3iz4/OztQBVbBXYwMsirVh8UBOavG2wqI3gdzNpN08fL4Cz2n320Z0RERERERUfofHJ+8+L76OCS1hya8yEpcyq+QsK+3mjvGWr8VGdHYr7V5O2i1HWKutVu+ynMtuPUS/pOW/xeHxFXdOO5N2IiIiIiI/pimnw+Nv5JqqpUFKOXo3i/fqe2nL0ffFm9QWlXZzdd3ytc7enHaz+BZejU0iqpZ02zIxT2zr3r0qwZx2Ju1ERERERH7M3MwNAHT68pOcFhTFPaFHQ6+vmf5853oAgAdb1fDq+/g7y0Z0kkp70X7x58depX3IYq/Ghir1TX8qAoHObxTvr9NZel6/j4u7ybsigHPaiYiIiIjIR3I1eiz984K4LVZKywHzw4ZApfdXdWqSEI7DU3p4tUt9eWCZtFsu/6YsWr9db3Qypz3Ay/XcgQuAQ98DjfoANVoBr5ww7Q+NlZ4XngB0fg3Y+p5r9xXntDNpJyIiIiKi2+zc9VzJdnkaHl+gMyXt3u4cbxYW6MXlysqJ/RczxNeW33dzAn/uep5ph71Ku7fF32H6Mgt3MmXC3nrtJZ1rqLhJO4fHExERERH5KY3VcPjyODw+6DZU2snk8XamueLhgQrcl1RN3C82ojMK2HTsmv1Kuz8JcONnphLMaWelnYiIiIjIT2mtknR9ORwe7+357FRsZPs66FC/CprEh0Nm0dytSUJxt/Yz6bm43xeVdne4U2k3r/FuuUxcBcNKOxERERGRn7Jcox0ArmYW4I1V/+Ifi2HQ/shgFJCWbarmhgWyTni7qBQBaJoQIUnYAVNX+Ufb1ARQNMVCX5TgtnwMiKkPDP7idofqnDtJuzrU9Kcm1/l55Rj/BRERERER+SnrSvvGY9cAAMv3XcILXevh1Z5JvgirRCfTcnArT4swtQLNq0f6OhwCoBLXajeaGsIBpmXeBi3wYVQOyNyoLZvXfF/3InB+FzD485LXdi9nWGknIiIiIvKhc9dzMfCzP7DxaJrNMes57ZY+23bWm2GVyclr2QCAxgnhUCmYcvgDhTwA9wUcQJ/jrxfvvH7CdwE541alPaz49eGVQPYVz8fjY/wXRERERETkQ/9ZcwSHLmXimaX7bY5pdM4bz+Vp/LP5VmqWaWh8YlSwjyMhM4VchiWqj5CUsa14Z9XGvgvImbA418+1TNoBwGiwf145xuHxREREREQ+lKd1nHhrSljiLeVGHppVj/B0SGWWVaADAEQGcxk2f6GS26nXthpx+wNxRYMewD1jTcP3SxIcLd2ugF3kWWknIiIiIvKhEJXjOppG57xq2G/eLsz433FPh1RmWflFSXsQk3Z/oQiwSv0ClIBC7ZtgSiKTAT3fB+4YWvK5LR6Vbuv8vDN+KTBpJyIiIiLyoRC1k6S9aE673SppkV8Op5Y5hvX/XsW3ey8gPacQl27ll/l+mfmstPsbpcKqOZu/JuzuCq0GyC0+i77iLf3G4fFERERERD5kuSSaIAiS5brM3eND1HJo84uHyj/UqgbOXM/FPxczyzSv/Ux6Lvp++rv4cOA/a44gWCXH1gldEBcRWOr7mofHh7PS7jeU1pV28/rmFUGAoniddn9fg74UWGknIiIiIvKhELVcfJ1jlYBrxKRdWmsTAMx79E4AQJ629I23us/ZYdOhPl9rwKbj10p1v+Op2eg0axv2nLsJAIgMrkCJYTmnkFtV2ita0m6mK/RdHF7CSjsRERERVUoHL2Xiv9vP4M0+jVErJsRncQRYVNYz8rQIDyyuTmv0poQ81Cppz8zXifu0eiN0BiOUTobQu+vizbxSXfff7Wdx0WJ4Pee0+w+1zID9ajUmVquCmnodwgJUwJaxvg7LM2JCAEPRQ4hji4CLP6FltZZ4qvlTvo3LQ5i0ExEREVGlNOizPwAAF27m47fxnXwWh86iQ/ytPK3kAYJ5eLx10j7ozgQEWzSwy9PoPVrV3nI8Hf/p28Tt68KDpHFGMGn3G2ohH5OrRuOGQo4biqLRHZd3+DYoT1ErIKa2mSeAzBNQVaCRBEzaiYiIiKhSO3s916fvr9UL4uvrOdImWvaGx0eHqNC3eTxkMhlU8gBoDUbkaQ2IdHNJ9C9/P+fw2LkbedDoDVAr5A7PsUdn8VmClHJUDasgzc4qgOvGG7ioND1EubugEP0DIiDr+h8fR+UhRj2w9T0g74Zpu+kgJDR62LcxeRCTdiIiIiKq1PRGoeSTvMiy0j7j1xPo1LAqApWmZFmstFs0q2tfL0ZsVmduUFeaZnTTfnG+VNycTacwqXdjt+6ZXWhqQNemdjSmDGjqtDM+3V4J4UkYcaEOmgbtQ++8fCChOtDgAV+H5Tk1uwMza5teC6FAfFufhuNJbERHRERERJWa4NucXZK0p9zIw4ajaeK2OKfdYii85VB5c1Jclg7y1sxT7BftOIejV7Ncvi6rQIcjRec/1q4mmiSEeywmKrta0cHoH5RvStgBIKSabwPytKAo4P53Ta812b6NxcOYtBMRERER+cjyvy7i1yNpkn0vLT+IQZ/9gYs38+0Oj5e8VpmTdvc6yAtOnlQEKYuHxFt3lnem60fbcemWabkty2Z65B9aJEaiUbiueEffj3wXjLeoix4UFbr+sKk8YNJOREREROQD52/k4Y3Vh8XtqODiRPfgpUxsOXFNHB4fb7FmuuVr83JxuW5W2q2T8TlDW+COGhHoe0c88i2WkLNZ29uJW3la8bV1QzryE5qc4teRNX0Xh7cEFiXtJ/8HpDuf/lGe8F8TEREREZEPXM4oEF+3qR2NulVDsHzfJXFfgc4gJteJ0cH4amRrXM0qwKCW1cVzzFX3fK17SXuB1druHepXweC7agAA9Ia/seGoaZ12rcG1Cr7W6iEAK+1+yjJpr4jUFlMy1o4Dntrsu1g8iJV2IiIiIiIfCFIV/6/4oDurw2K5dgDArN9O4mauqZu8WhmArknV8FjbWnaHx7tbac+zSPJHtq+N2PDi6v0nj9wpvj6Zlgu9oeQh8l/uknai51JvfqrVSNOf9bv7NAyvUVisVtC4v+/i8DAm7UREREREPmA5RL1v83icTLOtgp6/aWoaplbY/9/26FDTWtQ3c7V2jztirrRHBisxZUBTybFApRyN400VyzfXHMbor/8u8X6zfjspvo4MVnp0zXjyoM6vAcNXAw997etIvENukbSHJfguDg9j0k5ERERE5APmpL1JfDgigpUwOOli7yhprxpqSlI+2XIap6+5PvTZPG89RGV/tqxKXlz233Hqusv3BYCN4ztB5SBe8jG5EqjfDVCH+joS71BYPCyyrLqXc/zXRERERETkAxqdKWkPUpmayRmdrBevVsjt7q8SWpykLPvzgsvvbU7aze9tTevsCYITVcPUqGYx1J7otrKstCsqzs8hk3YiIiIiIh8wr8FurqJbz2m35KjS3u+O4iHAeVrXl30r0JnmtAc7SNpzNcVLg6nkJacMVcNMydKCx+5yOQYij7OsrrPSTkREREREpSUIAtKyCgEUJ+TTBjVzeL6j4eZRISq83a8JANsO7s6Y13W3XJPdUr7Fuu9agxEGJ6MAAEBX1KzOctk6ottObjk8npV2IiIiIqIKwVmF21s+3XIGM349AaB46PsdNSIdnu9oeDxQnNC7k7SbG9FZdqK3lG9VtS/p3oU686gBx3ESeZ2k0l5xmiEyaSciIiKiSk3ug6z9482nxNeuNG1zNDze8phGb8DZ67m4lVdyJ3nzuu6O5rQX6KRJe6HO8dB7QRBQWDQ/P9BB5Z7otrCstMsqTqpbcT4JEREREVEpBATc3qQ9p1An2bY3rzw+Qjq011lib07az17PQ7fZO3DXe5tKjME8/z3YQZLdqWFVyfad721Ck8m/YflfF20a5v1++ob4OlDJ9IJ8qALNY7fEf1VEREREVOkIQnHiqbjNSXvKjTzJtr01zcMDi+eGq+QBTivY5kZxF2/luxxDdoHpwUFEkP056FMHNMX47g0k+/K1Bryx+jDqvvk//Hs5EwCQmlWAJ5b8JZ4T7GAJOaLbwrJ7vJzD44mIiIiIyi29RbX4dg+P11ktp2aveVt4UHHyW7dqCOROHiyoS1Hdziohaa9TJQTjuzdElVD7lctHP/8TALBg21lx38vdGzqNk8jrAgKANs8CTR8Aqib5OhqP4aMwIiIiIqp0zN3Ogds/PF5vkDZ1i7STtDdNiECuxoDLt/Ix9O5Ep/dTyW2r8Fq90emQenPSHu4gaTerFqbGjVyNzX7z8Ppsi6H+TRPCnd6L6LboM8vXEXgck3YiIiIiqlQuZ+Rj4Pw/xO3bPTzeevm0xvHFya5KEQCt3ohezeIwZUBTl+5nLznP1+qhctI9+2auqVmdo0q7WUJkEI6lZts9tu7QVfx88Kq4HRdRcZbYIvInTNqJiIiIqFJ5d90x3LTosH67m8fripL26BAV1o/riITIIPHY7jfuw4WbeWhVK9rl+1UJtU3O87UGRAYD/17OxL+Xs/BY25qQFX1Qjd6AAxczAJRcHbd3b7PVBy6Lr5++tw6aVY9wOWYich2TdiIiIiKqVDYeuybZtip8e515eHxiVJAkYQeAKqFqh/PIHalbNRRN4sMlFXHzOusDikYURIeo0Kd5PAAgT2MQ5/TXqxrq9N5KueMh9ttOXgcAvDeoGR5vV8utmInIdWxER0RERESVhmXXeDPr4ereZk6YPdm0zXKIPQAUaKXrqu89d7P4WNGa6ypFQInz+QXYfm+sL4kL57B4Im9i0k5ERERElUauRm+zz2gnkfcmfVH3eIWTKra7rDvI52v1kgcUORaf25zQBzlZRs7Mqmce+t4Rj17N4iT7QuysM09EnuPTpH3nzp3o378/EhISIJPJ8NNPP4nHdDodXn/9dTRv3hwhISFISEjAE088gatXr0ruodFoMG7cOFSpUgUhISEYMGAALl++DCIiIiIia6fTc232GV2stF/NLMDPB6/YdH93VXahDr3m7sS0X44BAJRyz1XaVXLrpN0gdngHALWiOLEu1LmTtBd/1m0Tu+DDB+/AW32bSM5Ru3AfIio9nybteXl5aNGiBebPn29zLD8/HwcOHMDbb7+NAwcOYPXq1Th16hQGDBggOW/8+PFYs2YNli9fjl27diE3Nxf9+vWDwWCwuScRERERVW5T1h4VX9/boAoAwOBipf3+OTvw0vKD+HrPhVK991e7zuNEWg5SswoBAIoAz/2vuHUH+XytAZn5xc32LIe0m4fHB7lQIbd8PlGnSgiCVQokRAbh1LTe4v7SPsQgItf4tBFd79690bt3b7vHIiIisGnTJsm+efPmoU2bNrh48SJq1qyJrKwsLF68GEuXLkX37t0BAMuWLUNiYiI2b96Mnj17ev0zEBEREVH5YR6a/mibRIy7rwHaf7AVRhdzTnPlevvJdIzuWMft9z53Q1rl9+RSc9ZV+3ytXjKv/du9F6GUB2DKgKbi/kAXKuSOpg5YPiRoGBtWmpCJyEXlak57VlYWZDIZIiMjAQD79++HTqdDjx49xHMSEhLQrFkz7N692+F9NBoNsrOzJV9EREREVPHpizL0/nckiI3g3J3TritFZXnTsWuSNc0BQOHR4fHSBLxAZ0ChThpn8u7zyMzX4oklfwEAApUlpwLOmvQdnHw//njjPkSFOF4WjojKrtwk7YWFhXjjjTcwbNgwhIebumOmpaVBpVIhKipKcm5sbCzS0tIc3mvGjBmIiIgQvxITE70aOxERERH5B8vO7eb12V0dHm/mbrf5nEIdxny732a/JxvRKRXWlXaDOAzekuWDg4bVSq6QP3R3DQBAi8RIm2ORwSpUt1qyjog8r1wk7TqdDo888giMRiMWLFhQ4vmCIEAmc/zkctKkScjKyhK/Ll265MlwiYiIiMhPWXZulxf9/6Ig2F8KzhGdwb2k/ejVbLvX5BTadrIvLZtGdBo9rmUX2py3N8W09Ft0iArvP9CsxPve26AqNr/SGSueaeeZQInIbT6d0+4KnU6HoUOHIiUlBVu3bhWr7AAQFxcHrVaLjIwMSbU9PT0d7du3d3hPtVoNtVrt1biJiIiIyP+Ym6Yp5TLJOukGo+DycHV3h8fbq3gDwM5T1926jzPWjeiOpebg061nbM47m54HAOjZNM7lSn/9aqFlD5CISs2vK+3mhP306dPYvHkzYmJiJMdbtWoFpVIpaViXmpqKI0eOOE3aiYiIiKhykg6PL07S3Rnx7u7weK3efpLvyfXNrSvtm49fs3veyWs5AIDwQL+v3RFREZ/+a83NzcWZM8VPAFNSUnDw4EFER0cjISEBDz74IA4cOID169fDYDCI89Sjo6OhUqkQERGB0aNHY8KECYiJiUF0dDQmTpyI5s2bi93kiYiIiIjMzEm7Uh4gqbS704zOUeXcEU1R0n5P3Ri0rRuNtQevIjJYiVd7Jrl1H2fcHWqv9OB8eiLyLp8m7X///Te6du0qbr/yyisAgBEjRmDKlClYu3YtAKBly5aS67Zt24YuXboAAD7++GMoFAoMHToUBQUF6NatG5KTkyGXe+7JJRERERFVDOah7YoAmTinHQC+3n0ez3Sq67QvktmFm/luvaemKMlXKwMwvntDjO/e0K3rXdE4PrzkkyyUpgM+EfmGT5P2Ll26OG364UpDkMDAQMybNw/z5s3zZGhEREREVAEZHFTaZ/x6Al0aVUOjONfWHE/LKkRcRKDdY3kaPfam3ESH+lWgVsjFSrta4b3qdof6Mfjiibvx0z9X8Mvh1BLP1zgYsk9E/ofjYoiIiIio0jB3j5cHyKBSBOC1Xo3EY7kandNrEyyS9JQbeQ7Pe2P1YYxK/htzNp0CUDynXa3w3khQmUyG+5vEokVihEvns9JOVH4waSciIiKiSkNnLBoeX9QpfkyX+qhbNQRAcULviN6iAV1Wgf0E/3qOBusOmdZCX7TjHIDiqrZ1h3dveOKe2qgaVrxK0pT+TdC5YVVx2zy64IE7q3s9FiLyDLaNJCIiIqJKwWAUYJ59qQwoTqAVRYlsSV3hLY9n20na9QYj+nz6u81+jb5oTvttSNoDlXJMHdAUY749AADo0TQOI9rXhtZghFohR4HWgNSsAtStymXciMoLVtqJiIiIqFLQG4uHhMst1mQPKGo+Zyihn5Ll8RV/X5IcO3Y1G7M2nMT1HI24z/ww4HZW2i3fFzDN3ZfJZOLQ/CCVnAk7UTnDSjsRERERVQqWw98llfaiBF5fUqXd4vr9FzKQVaBDRJASADDtl2PYffam9P2MAo6nZqNAa6q0B3twXXZnAiw64Fuv305E5U+p/hXr9Xps3rwZixYtQk5ODgDg6tWryM3N9WhwRERERESeYpm0Kywq7eal34wlJO3WSb3lEHnrhN1s0Y6zyNea1lAPVt2eeplllEpFyUvYEZF/c/s3x4ULF9CrVy9cvHgRGo0G999/P8LCwjBr1iwUFhZi4cKF3oiTiIiIiKhMdBbD4y2HkJubs5VYabc6Xli0/joANKgWitPptgWsQKUcuRpT0h5ymyrtlpSstBOVe27/K37ppZdw9913IyMjA0FBQeL+Bx54AFu2bPFocEREREREnmIeph6klEMms03aS2pEZzknHgAOXsoUX2utllCrV9SRfvm+S8gpvL2VdkuWDyeIqHxyO2nftWsX3nrrLahUKsn+WrVq4cqVKx4LjIiIiIjIk/IdzC2/eCsfAMSO6/YYjQKsc/pXf/xXfG1ei91s7H31xdd7zpmGzgerb0+lXbBomGf5cIKIyie3H/cZjUYYDAab/ZcvX0ZYWJhHgiIiIiIi8jTz3PIgq6T9WrbG3ukAgKV/XsCJ1GzERwTaPX7qWg5qx4RAZ1Vp739HAl5ecQhAcUIf4oNKOxGVf27/5rj//vsxd+5cfP755wBMT+9yc3PxzjvvoE+fPh4PkIiIiIjIE8yVdleTZ0EQ8PZPRyT7ZDLAcmW4Hh/vRPfG1cRl3cwU8gC0SIzEIYsh9InRwaUL3E1c0o2oYnE7af/444/RtWtXNGnSBIWFhRg2bBhOnz6NKlWq4Pvvv/dGjEREREREZWZO2q0r7Y5kF+ht9s14oDneWH1Ysm/z8XSo7azBrrZoAtfvjnjUr3Z7kun61ULx1ZOtUS1MfVvej4i8y+2kPSEhAQcPHsTy5cuxf/9+GI1GjB49Go899pikMR0RERERkT9JzykE4Hy99K93n8fAlgmIDFYhNbvA5nhooAL1qobg7PU8yX7z8Pia0cEY29U0n73Aorv8pD6Nyxy/O7o2qnZb34+IvKdUE2uCgoLw5JNP4sknn/R0PEREREREHpev1WPnqesAgHpOho+/s/Yosgp0eLFbA9zK09ocD1UrsPLZe9Bq2mbJfnOTurVjOyAy2NSwObOg+PrqkSxuEVHpuN09fsaMGViyZInN/iVLlmDmzJkeCYqIiIiIyFMKdQZ0/nA7Nhy9BgDo2KCK0/PXHboKAHjn56M2x8IClYgJVeOxtjXtXquyGCafla8rbchERCK3k/ZFixYhKSnJZn/Tpk2xcOFCjwRFREREROQpqVmFuJ5T3CE+IcJ51ds85/10eq7NsUZxptWSHro70e61Sot57NmFtnPiiYjc5XbSnpaWhvj4eJv9VatWRWpqqkeCIiIiIiLylFyL5Ll9vRgkxZd+meJQtWl2acvESCwd3UZyTCYDFAFcF52IPMvtpD0xMRF//PGHzf4//vgDCQkJHgmKiIiIiKisBEHA1HVHMX/baQBAw9hQfPd0O0k13B5X027r+6jkAZDJiq8e0ML0/8aD76ruetBERFbcbkT31FNPYfz48dDpdLjvvvsAAFu2bMFrr72GCRMmeDxAIiIiIqLSOHQ5C1/9cV7cNlfJXRWqViBX43iIu1IuTe9VVkn89MHN0btZHLqwkzsRlYHbSftrr72GW7duYcyYMdBqTR0xAwMD8frrr2PSpEkeD5CIiIiIqDTyrRLusEClW9dr9AanxxUBVpV2q7XaQ9UK9G5uO62UiMgdbiftMpkMM2fOxNtvv43jx48jKCgIDRo0gFqt9kZ8RERERESlIreaX24UBLvn1a0SgnM3bNdd1xmk568f11GybTM8XuH2zFMiohKVap12AAgNDUXr1q09GQsRERERkcdYzi8HgGvZhXbPW/ZUW7T/YKu4bRAEfL7znLi9/63uiApWIcDqIYBVob3EufJERKXhUtI+ePBgJCcnIzw8HIMHD3Z67urVqz0SGBERERFRWegMRsl2iIM57QmRQWiZGImDlzIBAEeuZOPIlWzxeHSIyuYBAABYF+5ZaScib3ApaY+IiBB/UUVERHg1ICIiIiIiT9DqpUm7s67wk3onYfyKg0jNklbjZw5pbjdhB2yH27PSTkTe4FLS/tVXXwEwLZsxZcoUVK1aFcHBwV4NjIiIiIioLKwbydmf0W7Stm4MVj57D+6dtU2y31n1PFApd/lcIqLScus3iyAIaNCgAa5cueKteIiIiIiIPEJjVWkvSbid7vIqudzOmSb1qoZKttWstBORF7j1myUgIAANGjTAzZs3vRUPEREREZFHWCftDprHi0IDbQehllQ9H9a2pvhaqXA2AJ+IqHTcfhw4a9YsvPrqqzhy5Ig34iEiIiIi8gh3K+3yABmC3BzyrrToKB+mdm8deCIiV7i95Nvw4cORn5+PFi1aQKVSISgoSHL81q1bHguOiIiIiKi0LlitvV5CoR0AoFYGoEBXPBdeVcKQd7nFum8RQUzaicjz3E7aP/74Y4cdNImIiIiI/MU/RUu4md1bv0qJ1wQq5AB04nZJlXaFvPj/iyOCmbQTkee5nbQ/+uij0Ov1CAkJ8UY8REREREQecfZ6LgDg88dbIT1Hgwdb1SjxGrVSmqSrS0jaLSvxrLQTkTe4PKf9xo0b6Nu3L0JDQxEeHo727dvj3Llz3oyNiIiIiKhUtHojMvNNFfM2daIxvF0tmyXa7LFO0kuqtPduHoe6VUOgVgTg7lpRpQ+YiMgBlyvtkyZNwv79+zF16lQEBgZi4cKFePbZZ7Fp0yZvxkdERERE5LYCbfG89GCV64NL1QppYh+ocJ7oN02IwNYJXaAzGKHkkm9E5AUu/wbbsGEDlixZgj59+gAA+vTpg2bNmkGn00Gp5FAgIiIiIvIf+To9AEARICuxWm5JHiDt3VQlTOXSdUzYichbXP7tcvXqVdx5553idlJSElQqFa5eveqVwIiIiIiISiu/qNIepCp5SLwl6w7z7lTpiYi8weWkXRAEKBTSX1oKhQJGo3vrXxIREREReZt5eLz1uusl4RpJRORvXH50KAgCunXrJknc8/Pz0b9/f6hUxcOGDhw44NkIiYiIiIjcZF5rPdjNSnvf5vE4eCkTwSo5tr/axQuRERG5x+Wk/Z133rHZN3DgQI8GQ0RERETkCVPWHgUABLk5vP3pTnXxcJtEhKkVkMlYdyci3ytT0k5ERERE5I/My71VCXWtkZyl8EA2WSYi/8E2l0RERERU4RiMppZyr/dK8nEkRERlw6SdiIiIiCocg2BK2gM4xJ2Iyjkm7URERERU4RiLKu3W664TEZU3TNqJiIiIqMIxV9rl/L9dIirnfPprbOfOnejfvz8SEhIgk8nw008/SY4LgoApU6YgISEBQUFB6NKlC44ePSo5R6PRYNy4cahSpQpCQkIwYMAAXL58+TZ+CiIiIiLyN+Y57RweT0TlnXtrYAD49NNP7e6XyWQIDAxE/fr10alTJ8jlJa+JmZeXhxYtWuDJJ5/EkCFDbI7PmjULc+bMQXJyMho2bIhp06bh/vvvx8mTJxEWFgYAGD9+PNatW4fly5cjJiYGEyZMQL9+/bB//36XYiAiIiKiiqeo0M6knYjKPZkgmH+luaZOnTq4fv068vPzERUVBUEQkJmZieDgYISGhiI9PR1169bFtm3bkJiY6HogMhnWrFmDQYMGATBV2RMSEjB+/Hi8/vrrAExV9djYWMycORPPPvsssrKyULVqVSxduhQPP/wwAODq1atITEzE//73P/Ts2dPue2k0Gmg0GnE7OzsbiYmJyMrKQnh4uDvfDiIiIiLyQ43f/g0FOgN+f60rEqODfR0OEZGN7OxsRERElJiHuj08fvr06WjdujVOnz6Nmzdv4tatWzh16hTatm2LTz75BBcvXkRcXBxefvnlMn2AlJQUpKWloUePHuI+tVqNzp07Y/fu3QCA/fv3Q6fTSc5JSEhAs2bNxHPsmTFjBiIiIsQvdx4uEBEREZH/E7vHsxEdEZVzbiftb731Fj7++GPUq1dP3Fe/fn189NFHmDRpEmrUqIFZs2bhjz/+KFNgaWlpAIDY2FjJ/tjYWPFYWloaVCoVoqKiHJ5jz6RJk5CVlSV+Xbp0qUyxEhEREZF/EbvHc3g8EZVzbs9pT01NhV6vt9mv1+vFRDkhIQE5OTlljw6mYfOWBEGw2WetpHPUajXUarVH4iMiIiIi/1NcafdxIEREZeT2r7GuXbvi2WefxT///CPu++eff/D888/jvvvuAwAcPnwYderUKVNgcXFxAGBTMU9PTxer73FxcdBqtcjIyHB4DhERERFVLoIgiI3oWGknovLO7aR98eLFiI6ORqtWrcSK9d13343o6GgsXrwYABAaGorZs2eXKbA6deogLi4OmzZtEvdptVrs2LED7du3BwC0atUKSqVSck5qaiqOHDkinkNERERElYvRos0yu8cTUXnn9vB4cyJ94sQJnDp1CoIgICkpCY0aNRLP6dq1q0v3ys3NxZkzZ8TtlJQUHDx4ENHR0ahZsybGjx+P6dOno0GDBmjQoAGmT5+O4OBgDBs2DAAQERGB0aNHY8KECYiJiUF0dDQmTpyI5s2bo3v37u5+NCIiIiKqAAwWWTsb0RFReed20m6WlJSEpKSkMr3533//LUnwX3nlFQDAiBEjkJycjNdeew0FBQUYM2YMMjIy0LZtW2zcuFFcox0APv74YygUCgwdOhQFBQXo1q0bkpOTuUY7ERERUSVltFjRWM6knYjKObfXaTcYDEhOTsaWLVuQnp4Oo9EoOb5161aPBng7uLo+HhERERH5vzyNHk3f2QAAOP5uLwSpWMwhIv/jah7qdqX9pZdeQnJyMvr27YtmzZqV2MmdiIiIiOh2MgiWw+N9GAgRkQe4nbQvX74cK1euRJ8+fbwRDxERERFRmRgt5rSzezwRlXduP3tUqVSoX7++N2IhIiIiIiozy0Z0nNNOROWd20n7hAkT8Mknn8DNqfBERERERF710z9XsP7fq5Il3ziVk4jKO7eHx+/atQvbtm3Dr7/+iqZNm0KpVEqOr1692mPBERERERG5IjNfi/ErDgIAdrzaBQCr7ERUMbidtEdGRuKBBx7wRixERERERG7be+4mHv3iT3H7Rq4WAOezE1HF4HbS/tVXX3kjDiIiIiKiUnl88V+SIfHbTqQDYOd4IqoY+KuMiIiIiMo1rcEo2Z6/7QwAVtqJqGJwqdJ+1113YcuWLYiKisKdd97ptKHHgQMHPBYcEREREZG7okNUuJWnRQDntBNRBeBS0j5w4ECo1WoAwKBBg7wZDxERERGRy9KyCm32VQtTm5J2VtqJqAKQCVy7DdnZ2YiIiEBWVhbCw8N9HQ4RERERuSArX4eus7fjVp5Wsj8+IhCpWYWICw/En29281F0RETOuZqHuj2n/dKlS7h8+bK4/ddff2H8+PH4/PPPSxcpEREREVEpbDp+TZKwTxvUDABwLdtUfY8KUfkkLiIiT3I7aR82bBi2bdsGAEhLS0P37t3x119/4c0338S7777r8QCJiIiIiOw5mZYtvh7UMgFhgaaZn+ZO8lHBSl+ERUTkUW4n7UeOHEGbNm0AACtXrkTz5s2xe/dufPfdd0hOTvZ0fEREREREduVq9ACACfc3xNxH7oRSLv1fW7WCCyURUfnn9m8ynU4nNqXbvHkzBgwYAABISkpCamqqZ6MjIiIiInIgp9CUtIeoTRV2lVXSXukbNxFRheB20t60aVMsXLgQv//+OzZt2oRevXoBAK5evYqYmBiPB0hEREREZE9eUaU9tChpV1pV1rlOOxFVBG4n7TNnzsSiRYvQpUsXPProo2jRogUAYO3ateKweSIiIiIibzIaBWw7eR2A40o7c3YiqghcWqfdUpcuXXDjxg1kZ2cjKipK3P/MM88gODjYo8EREREREdlz8Va++DqgKDlXKaRZesPYsNsZEhGRV7idtAOAXC6HXq/Hrl27IJPJ0LBhQ9SuXdvDoRERERER2ZevNYivuzSqBgBQK+SSc8beV/+2xkRE5A1uD4/Py8vDqFGjEB8fj06dOuHee+9FQkICRo8ejfz8/JJvQERERERURgU603z2WjHBCFKZkvUGsaGoEmpqmNyneRyCVaWqTxER+RW3k/ZXXnkFO3bswLp165CZmYnMzEz8/PPP2LFjByZMmOCNGImIiIiIUKgz4EauBgCQpzFV2i0Tc7VCjnXjOmDh8Fb4YMgdPomRiMjT3H78uGrVKvz444/o0qWLuK9Pnz4ICgrC0KFD8d///teT8RERERERAQD6z9uF0+m52PV6V2QV6AAAISrpkPj4iCDERwT5IjwiIq9wO2nPz89HbGyszf5q1apxeDwRERERec3p9FwAQMeZ28R9QVZJOxFRReP28Ph77rkH77zzDgoLC8V9BQUFmDp1Ku655x6PBkdERERE5Ex8RKCvQyAi8iq3K+2ffPIJevXqhRo1aqBFixaQyWQ4ePAgAgMDsWHDBm/ESERERESVnEZvsNk3uV8TDGyZ4INoiIhuH7eT9mbNmuH06dNYtmwZTpw4AUEQ8Mgjj+Cxxx5DUBDnDxERERGR55kbz5nFhKgwqmMdH0VDRHT7lGodjKCgIDz99NOejoWIiIiIyK7cQr1kOyyQy7kRUeXg0m+7tWvXunzDAQMGlDoYIiIiIiJ7cjQ6yXYok3YiqiRc+m03aNAgl24mk8lgMNjONyIiIiIiKgvr4fHBSibtRFQ5uNQ93mg0uvTFhJ2IiIiIPCVXo8eu0zegNxiRa1VpV8hlPoqKiOj24iNKIiIiIvJLo5L34a+UWwhUBqBQZ5Qca1UrykdRERHdXi6v075161Y0adIE2dnZNseysrLQtGlT7Ny506PBEREREVHl9VfKLQCQJOwd6sfgt/H34pX7G/oqLCKi28rlpH3u3Ll4+umnER4ebnMsIiICzz77LD7++GOPBkdEREREZCkuPAhJceGQyTg8nogqB5eT9kOHDqFXr14Oj/fo0QP79+/3SFBERERERNba1I7GyPa1fR0GEdFt5fKc9mvXrkGpVDq+kUKB69eveyQoIiIiIiJr3z3dFgq5yzUnIqIKweXfetWrV8fhw4cdHv/3338RHx/vkaCIiIiIiCwFKgOYsBNRpeTyb74+ffpg8uTJKCwstDlWUFCAd955B/369fNocEREREREABCi4qJHRFQ5ufzb76233sLq1avRsGFDjB07Fo0aNYJMJsPx48fx2WefwWAw4D//+Y83YyUiIiKiSioi2PE0TSKiiszlpD02Nha7d+/G888/j0mTJkEQBACATCZDz549sWDBAsTGxnotUCIiIiKqPPQG6brs8RGBPoqEiMi33BpnVKtWLfzvf/9DRkYGzpw5A0EQ0KBBA0RFRXkrPiIiIiKqhPJ1Bsl2XHiQjyIhIvKtUk0OioqKQuvWrT0dCxERERERAKBAK03aH7+nlo8iISLyLbbgJCIiIiK/k6fRS7ZbJkb6JhAiIh/z66Rdr9fjrbfeQp06dRAUFIS6devi3XffhdFYPMdJEARMmTIFCQkJCAoKQpcuXXD06FEfRk1EREREZZVvUWlfPaa9DyMhIvItv07aZ86ciYULF2L+/Pk4fvw4Zs2ahQ8//BDz5s0Tz5k1axbmzJmD+fPnY9++fYiLi8P999+PnJwcH0ZORERERGXx2bYzAICmCeG4qyb7JxFR5eXXSfuePXswcOBA9O3bF7Vr18aDDz6IHj164O+//wZgqrLPnTsX//nPfzB48GA0a9YMX3/9NfLz8/Hdd9/5OHoiIiIiKo2MPC1+PZIGAGhdO9rH0RAR+ZZfJ+0dO3bEli1bcOrUKQDAoUOHsGvXLvTp0wcAkJKSgrS0NPTo0UO8Rq1Wo3Pnzti9e7fD+2o0GmRnZ0u+iIiIiMg/ZBboxNcvdmvgw0iIiHyvVN3jb5fXX38dWVlZSEpKglwuh8FgwPvvv49HH30UAJCWZnoCa70+fGxsLC5cuODwvjNmzMDUqVO9FzgRERFROXY9RwOVIgARQUqfvL+5CV1ceCCiQ1Q+iYGIyF/4daV9xYoVWLZsGb777jscOHAAX3/9NT766CN8/fXXkvNkMplkWxAEm32WJk2ahKysLPHr0qVLXomfiIiIqLzJ0+jR/oMtaD9jCwRB8EkMlzPyAQBBKrlP3p+IyJ/4daX91VdfxRtvvIFHHnkEANC8eXNcuHABM2bMwIgRIxAXFwfAVHGPj48Xr0tPT7epvltSq9VQq9XeDZ6IiIionDmTnov1/16FziBAZzCgx8c78c3oNoiPCLqtcTy37AAAIOVG3m19XyIif+TXlfb8/HwEBEhDlMvl4pJvderUQVxcHDZt2iQe12q12LFjB9q359IgRERERCXRGYx4Yslf+M+aw+g+Zwfmbj4tHjudnot7Zmy97fEQEVExv6609+/fH++//z5q1qyJpk2b4p9//sGcOXMwatQoAKZh8ePHj8f06dPRoEEDNGjQANOnT0dwcDCGDRvm4+iJiIiI/N/JtBzsPHXd6TnZhTqEB96e+e2Hr2SJr5smhN+W9yQi8md+nbTPmzcPb7/9NsaMGYP09HQkJCTg2WefxeTJk8VzXnvtNRQUFGDMmDHIyMhA27ZtsXHjRoSFhfkwciIiIqLyIadQX+I5F2/mo1n1CK/FcOBiBiatOoyBdybAYCieR5/8ZBuvvScRUXkhE3zVYcSPZGdnIyIiAllZWQgP5xNdIiIiqtg0egP2pWTg0OVM7Dx1HXtTbjk9//PHW6FH0zivxVP7jV9s9g2+qzrmDG3ptfckIvI1V/NQv660ExEREZFnGY0Cpqw9hu//uujwnMhgJcZ2rY9pvxwH4Fo13tOae7GyT0RUnjBpJyIiIqpEJvxwCGv+ueLw+IOtauCjh1oAAP44cwPbTl5HdqHO43GkZhXgya/2oadVBT8iSIlFj7dCm9rRHn9PIqLyiEk7ERERUSXiLGEHgBCLtdHjipZ6u56j8Xgc87eewYm0HJxIyxH3/f5aVyRGB3v8vYiIyjO/XvKNiIiIiLxn/biONvuCVMU1nfAg0+sF288iT+PZIfL27lclVO3R9yAiqgiYtBMRERFVEtb9hxvH2zY+sqy0d0uKFV9fvJXvsTj0BiN+OnhVsq9pQjiCLN6biIhMmLQTERERVRLJu89LtuUBMptzLBPnNnWiUT3SNES+UGfwWBxHrmbb7GvNOexERHYxaSciIiKqJD7Zclp8vW6s7dB4ANAbpdV4cxJfqDN6LI7MfK3NvvBAtloiIrKHSTsRERFRJVCgNSAz39QF/q83u6F5DdOSamO71pec17p2lGQ7UGn638VCvecq7dlWS8jFhqvRu3m8x+5PRFSR8JEmERERUSVwq6i6rZTLUDWsuOHbxJ6NML57AwgALt3KR92qoZLrAhVFlXatB5P2AtPDg55NY7Ho8bs9dl8iooqISTsRERFRJXAr15S0R4eoIJNJ57Ir5KZqunXCDgCByqKkXW/A3nM3YRAEtK9XpUyxZBUl7eGByjLdh4ioMuDweCIiIqJKwFxpjwpWuXWdOWnPLtDj4c//xLAv9iKnUFemWK5mFgAAqoVziTciopIwaSciIiKq4P4+fws//XMFABAT6m7SbvrfxQyL5nHmSnlpnb+ZBwCoHRNSpvsQEVUGHB5PREREVIEJgoAHF+4Rt3M17s1NN1faVx24LO7TGQRHp7vkcoap0l4zOrhM9yEiqgxYaSciIiKqwHI10k7t52/kuXW9udJ+6VaBuC9fq3d0eomMRgGpmYUAgISiNeCJiMgxJu1EREREFZj1UPZvRrVx6/qgokq7pfwydJK/kaeB1mCETAbERQSW+j5ERJUFk3YiIiKiCsy8NjsArHq+PVokRrp1faCdpD1PU7pK+4WbeRj+5V4AQGxYIJRy/q8oEVFJ+JuSiIiIqAL7/q+LAID61ULRqlaU29erFbb/u1jaSvvzyw7g1LVcAEBCJKvsRESuYNJOREREVIGdu26aw16nSuk6tadlF9rsu5GrKdW9jqVmi685n52IyDVM2omIiIgqqE82n8aeczcBAK/3alSqe9irqk9ddwyC4H4HeaVcJr6uzqSdiMglTNqJiIiIKqACrQEfbz4FAIgJUaFuldBS3cdotE3ODUYBx1NzSrz238uZOG5RXa8aqhZf169WuniIiCobJu1EREREFdCtfK34+ofn7kFAgMzJ2Y6N69bA7v6bec6HyKdlFWLA/D/Q+5Pfse7QVQDF3eL7No/HwJbVSxUPEVFlw6SdiIiIqAK6lWtK2mPD1ahbtfRV7XpVQ8W12i09vvgvp9ddySxe133c9/8AAHIKTV3nh7WtCZWdBndERGSLvy2JiIiIKqDp/zsOAIgKVpX5XmqF7bJvJbEu7L/w3QGcTjd1jg8LVJQ5JiKiyoJJOxEREVEFdPRqFgCgc8OqZb5XadZTL9QZJdu//Jsqvg4LVJY5JiKiyoJJOxEREVEFciItG4MX/IHsoqHoY7rWL/M9VXL358Nr9I7Xcg9npZ2IyGVM2omIiIgqkDHfHsCBi5kAAJUiwCMJstLB/POV+y45XPpNozfa3Q+w0k5E5A4m7UREREQVhMEo4Nz1PHG7Z9M4yGSl6xpvydHw+NdW/YtjFku6WSrU2a+014oJZhM6IiI3cGwSERERUQVxJcPUsV0mA45M6YkQtWf+V8/ZnPasAp3d/fYq7VXD1NgwvpNHYiIiqiz4mJOIiIiognh55UEApo7xnkrYAedz2o0ORsHbS9pb1IhAoNL9TvRERJUZk3YiIiKiCiK1aG30ro2qefS+MaFqh8cMDua0F2pNw+Mtl3cb372hR+MiIqoMmLQTERERlXOXbuXji53ncDWrEADwWq9GHr3/tEHNMOH+hvjwwTtsjhkclNpv5WsBANUjg8R9seGBHo2LiKgy4Jx2IiIionJu3Pf/4OClTABAtTA1qjqpjJdGQmQQxnVrAAB49cd/JccMDobHpxQ1xKsSqgaQA0BadSciItfwNycRERFROWI0CjAIAjR6Iz7fcRYJkUFiwg4AfZrHIyCg7B3jXWUw2g6PX/rnBfx2NA2AqVv8rjOm/ZzPTkTkPibtREREROVEVr4O7WZsQWy4GipFAE5dy7U5p27VkNsak9HOnPa1B6+Ir5++ty6CVXLJMHkiInIdk3YiIiKickBvMKLFuxsBAOdv5ts9p0ZUEAbdWd2rcbzWqxFm/XayOC47lfazRUPj//fivahdJQT/6dvEqzEREVVkbERHREREVA4s2H7W6XGVIgC/v9YV4YFKr8Yxpkt9ybbRKmnPLtThVp6pCV10iMqrsRARVQZM2omIiIj8nNEoYM6mU85PEgCZ7PbNZTezntM+5eej4uvIYO8+QCAiqgyYtBMRERH5uU+2nBZf31EjAvKiRnMd6seI+wN89H911uu0mxvQAWw8R0TkCUzaiYiIiPzYlcwCMWmvFqbG2rEdsWH8vZg15A7MfqileF6zhAifxGc0Clj/71XcP2cHTl3LQYsakT6Jg4ioomLSTkREROTHvvz9nPh6zQsdAAD1q4VhaOtExEUE4rNhd6F59Qh8+FALn8SnNwoY+90/OJ2eiwkrD+GORNPDg9a1o3wSDxFRRcPu8URERER+6sDFDHz1x3kAwKCWCXaXTet7Rzz63hF/myMrZrnk2+ErWYiLCAQA3F072lchERFVKKy0ExEREfmpkUv+El8Pb1fLh5E4diNHI9nedOwaAEAZcPub4hERVUR+n7RfuXIFw4cPR0xMDIKDg9GyZUvs379fPC4IAqZMmYKEhAQEBQWhS5cuOHr0qJM7EhEREfk/vcGI7EI9AGDeo3f6beX6061n7O5Xyv3+fzOJiMoFv/5tmpGRgQ4dOkCpVOLXX3/FsWPHMHv2bERGRornzJo1C3PmzMH8+fOxb98+xMXF4f7770dOTo7vAiciIiIqo6wCnfi6d7M4H0ZSOgom7UREHuHXc9pnzpyJxMREfPXVV+K+2rVri68FQcDcuXPxn//8B4MHDwYAfP3114iNjcV3332HZ5999naHTEREROQRGfmmpD0sUFEuE2ClnMPjiYg8wa//C7B27VrcfffdeOihh1CtWjXceeed+OKLL8TjKSkpSEtLQ48ePcR9arUanTt3xu7dux3eV6PRIDs7W/JFRERE5C80egO6z9kBAIgMVvo4mtLh8HgiIs/w69+m586dw3//+180aNAAGzZswHPPPYcXX3wR33zzDQAgLS0NABAbGyu5LjY2Vjxmz4wZMxARESF+JSYmeu9DEBEREblpya7z4usQlf8NjFz+TLsSz2HSTkTkGX7929RoNOKuu+7C9OnTceedd+LZZ5/F008/jf/+97+S82Qy6fArQRBs9lmaNGkSsrKyxK9Lly55JX4iIiIidxmNAmb+dsLXYTjVrm5MiecoODyeiMgj/Dppj4+PR5MmTST7GjdujIsXLwIA4uJMTVmsq+rp6ek21XdLarUa4eHhki8iIiIif3DxVr5k23Id9PKEc9qJiDzDr5P2Dh064OTJk5J9p06dQq1apnVK69Spg7i4OGzatEk8rtVqsWPHDrRv3/62xkpERETkCb8cTpVs14oJ8VEkzjVNkBY9WtSIkGxzeDwRkWf49W/Tl19+GX/++SemT5+OM2fO4LvvvsPnn3+OF154AYBpWPz48eMxffp0rFmzBkeOHMHIkSMRHByMYcOG+Th6IiIiIvd9uMFUsKhfLRT3JVXDhB4NfRyRfV+OuFuybd3hPimOIxmJiDzB/zqbWGjdujXWrFmDSZMm4d1330WdOnUwd+5cPPbYY+I5r732GgoKCjBmzBhkZGSgbdu22LhxI8LCwnwYOREREZH7rmQWiK9f75WE+5s4nu7na/ERQXi8XS0s/fMCAEARIMOG8Z1w9nou7m1QBWGB5bPrPRGRv/HrpB0A+vXrh379+jk8LpPJMGXKFEyZMuX2BUVERETkBRdvFs9n71C/5GZvvqZSFFfXlfIANIoLQ6M4Fk6IiDzJ75N2IiIioopu1m8nsDflFvZfyABgStiD/XCpN2uWSTu7xRMReYf//9eAiIiIqALL0+ixYPtZyb7WtaN9FI171JZJe4Bft0oiIiq3+NuViIiIyIdu5Wkl232bx+Olbg18FI17LCvtKgUr7URE3sBKOxEREZEPZebrAAChagUm92+CAS0SIJOVjwRYrZCLr1lpJyLyDibtRERERD6UkW+qtNeICsLQuxN9HI17LCvt6TmFPoyEiKji4iNRIiKiCkYQBLyy8iAmrT7s61DIBalZpmXeqoapfRyJ+9rXK+5wf+xqtg8jISKquFhpJyIiqmDO38zH6gNXAACv92qEyGCVjyMiewRBwIvLD2LdoasAgHpVQ30ckfssY84u1PswEiKiiouVdiIionImPbsQX+w8h2vZ9ocjn03PFV9fzeSQZX919Gq2mLADQJ0qIT6MhoiI/BWTdiIionJk2Z8X0Gb6Frz/v+N4b/0xZOZrcTItR3LOvgu3xNdvrjmMI1eybneYZOGvlFuYtPowrmYWIKOoU3x2oQ795u2SnFceh8cDwLxH74QiQIZPHmnp61CIiCokDo8nIiIqR349kiq+Xv9vKo6nZuPs9Tz88mJHNE2IwF8pt7BoxznxnIOXMtFv3i6c/6CvL8IlAB9tPIm/Um7h+78uQiYDvn+6HYxGQXJO98bV0L1xrI8iLJv+LRLQo2mspJM8ERF5DpN2IiKicuRkWq5k++z1PADAA5/txqn3e+OjjSd9ERY58VdK8cgHQQAe+fxPm3O+HNH6dobkcUzYiYi8h8PjiYiIyombuRrcyNUAAJRy6TreWoMRF2/miwnisLY1JcdbvbcJm49dQ5cPt2HOxpM4djUb760/Jg7XJiIiIv/ESjsREVE5ceqaqcpeMzoYCZGB+PPcLcnxoYv2iK9f6tYAHepVwQvfHQAA3MzT4qlv/gYAfLr1DD7degYAoNEbMG1Q89sRPjnwas9Gvg6BiIj8GCvtRERE5cTJNNM62A1jw/Bom5o2x9MsusnHhKiQFB9W4j1TbuR5LkCyoTcYEVA0KOLJDrURpCweRv5qz0b44om78Vznej6KjoiIygNW2omIiPzY3+dv4bNtZ9ChfhX8czETANCsejgGtqyOl5YftHvNuPvqQyEPQIiq5P/Mx4YFejBasvbvlSwYBSBYJcfbfZvg9V5JuJGrQdUwNeeBExGRS1hpJyIi8mPztp7BtpPXMe2X4/jlsKlzfIf6VQAAHz/cAnfVjMSglgni+WpFAEZ1qAMACFKVnBSGBym9EHXFdiY9F9tPptvs33X6Bt7+6QiuZBYAAH4/fR2DF+wGADSJD0dAgAyBSjlqRAUzYSciIpex0k5EROTHzAmgWbUwNVrUiAQAPHBnDTxwZw0IgoD/9G2CU9dyEB8RiKgQFQAgVF3yf+YVAbISzylPMvO1CAtUQu7Fz9V9zg4AwNqxHXBH0d8FAAxfvBcAkKfRY87DLfHHmZvisRe61vdaPEREVLExaSciIvJTgiDgcka+uN23eTze6tcYKoV0oJxMJkPVMDWqhqkl++UBMiTFheFEWg4WDm+FmFAVVu2/jOX7LonnaA1G736I2+iNVf9i+b5LuKNGBH5+oQNkMs8n7gaL9dUPXc7CHTUicTItBwcvZYj7b+Rpse1kOjYcTQMA/KdPY3RNqubxWIiIqHJg0k5EROSnbuZpUagzQiYDTrzXq1RDqlc8ew/OXc9Fy8RIyGQytK4djexCHf532JRQanQVI2m/eDNffBjx7+Us3MjV2jzEKAu9wYhpvxxH8u7z4j5BEHAzV4Oec3dKzt156v/t3XlcVFX/B/DPsA37ICg7Crgr4J6K5r6QmpblL9M0Sys1SysfW7S0Mk17NM0Ws0WtJzVNS1vccckNN1AUQUVR9n3fhmHO74+BgXEGBWGGAT7v14tX3HPv3HuOhwm+c875nlQcv56qPvZoZlVn9SAioqaHa9qJiIiM1PkY1ZZuLnaWD70GWmZljm4tm2mMOr/7WEf197+ej8WUH0KQU1RSu8rWk0J5KYIjkxFyO12j/E563WbFPxqVqhGwA0B6nhwx6QW6X1CJuwODdiIiengcaSciIjIiSqXA/N8uYdfFeHXZwHYt6vQZXo7W+PgJP7z/xxUAwL830rDh2C3Mb4D7hX97PBprDt3QKq+8/V1tFJWUYu3hG/jmaLTWuZTc4mrdw13GDP1ERPTwGLQTEREZkRk/nUdwpGZm8teG1n0SM5t7Msun5NZNkGtIpUqBPZcSdJ7LyJc/9H3f+DUMp6LT0NHNHoBqlL2ch4MVXujnjaV/X8PWs3fvOwW/Xxsn+Da3hbM9g3YiInp4DNqJiIiMRH6xQitgX/qEHzybWdf5s4bckxht+/k4LAjqgOa2dbcOXJ+KSkox7suTuJWqexp8yK0MTO3rXeP73knPx++hqlkOyTmpWudfH9oGPs1t1cdfHNYe5S/3v+m99ZIMj4iImhYG7UREREai8ujwV5O6o7evo96CaAdrC7RuYYPoSkHvmVvpGBPgfp9XGY+TN9MQlZwLADCRAJWSugMA/rmS+FD33Xsl6b7n27vao4unDBamJlqZ9/8zsj0ik3KRmS/H8vH+DNiJiKhOMGgnIiIyEuVBu5vMEqMD3PT+vMwCzeRzBfJSvT+ztr46chOf7Y9ST+8f2dkF307pCe93/ta4Tgggu7AEMivzB97zz0sJ2HMpAYevJWsF/wBw4u3BSMwugqmJBF29HAAAowPc1CPyANCtpQOm9/eBpfnDJQwkIiKqCrPHExERGYmMAlXQ7mBtYZDnPd3DU+O40MiDdiEEPtsfBQDIL6tr+dKBH57vCTtLM6x/rgc8yrK1B0cmP/CeN5Jz8drWUByM0AzYpwV6w6e5DbbM6A3PZtbo5e2I7i2bqc9bVcoJsP65Htg1K5ABOxER6QWDdiIiIiORV6QAANhbGmYi3LxhbbF2YleM6OQCAMiXKwzy3Ie1s1JGfUCVTO8xP1cAwNCOLri8eASC/FzR3tUOAPDGr5egKL3/PvRnbmdolUkkwAv9vHFk/iAEtmmu83WVP+Do18aJU+GJiEhvOD2eiIjISBSWqAJBKwvDjNhaW5hhXFcPXLiTqXq+kY20H4xIhoO1OXp5OyKvWIEP91wFADjbSbHlpT7wcrTS2L++PHCe8aiPOqFfvrwUMivtMYqMfDkW/HYZp6LTtM7tnfsoWjnZ3LduSdkV2fbtLB88BZ+IiOhhMWgnIiIyEuVBs7WBgvZy1haqPweMaU17QlYhXvrpPADg9vJR2BpyF7nFqpkA217uA98WtlW+tq+vE0xNJChVChSVlOpc1/7bhVgculYxfX5Gfx/cySjA2C7u6OBq/8D61WZLOSIioprg9HgiIqI6IlcocSQypcYj1nGZBRjx+TGsOqBar23otdHlSd1+OHEbfZcfRmxGgUGfr0taXrH6+/R8Oc7cSgcALBzV8b4BO6Aacbcq+zeMy9TdlsjEXI3jAe1a4LupPfF4l+plz583rC0AYGIvr2pdT0RE9LAYtBMREdWRd3eF44VN5zBt41lcis2q1mtKlQJbQu7ienIecsrWtBt6pL18DTgAJGYXIUTHOm9Dqzzqv+C3yzhcNt3dz0NWrdfnlY3KP/XNaRSVaH6IEpGQg11lmd9bOVnjvVEd8Ghb3WvXq/KYvxtOvD0Yy570r9HriIiIaorT44mIiOpAobwUOy/GAQBCbmdg3Fcn8d8JXbQytAOqqdU/nriN9ceiodCxx5iVgUfa27nYaRznFZVUcaXhZBdW1KF8fbq5qQSd3B88df1e/VcEI+S9YTA1Ua1531XWTwCwa1YgnGylD1XH8sz1RERE+sSRdiIiompSKgV2XYzTmHIthICiVImRa45rXT9/xyXIFZrZy4UQGPjZEXx55KbOgB0ALMwM++vZ0VZzi7nyUer6IoTAKz9f0Cp/6VHfau27fq+0PDnCYjPVx6llU++nBXo/dMBORERkKBxpJyIiqqYDEUl4c/sl9fFT3T3Vo+vl3hzeDlIzEyzfGwkAGLr6KI7OHwxTEwkUpUr8diEOuUWaQfEzPb0wrps7Jn0XAhMJMKSDs/4bU4mdVPPPgdx6DtrXHr6hVebb3AYLgjo89D2f+uY0Yj4dDQBIzVUF7V29HB76fkRERIbCoJ2IiKiazt7O1Di+N2AHgNeHqhKUJeUUYePJGMRmFOLQtWQM6eCM8V+fQnh8tvpabydrHP3PYPVxxEcjUVyiRDMbC6376tO9e4yX7xcvVyjxd3gCAls3h4u9pUHqIoTAplMx6uMFQe3x7/U0rHw6oEb3eWWAL346fUe9jV5liWXbtTnbcZSdiIiMH6fHExERVYMQQuee3gCwaHRHWFuY4sluHuqyxY93Vn//ys8X0HbhXo2AfUIPT/w8vbfGfawtzAwesJc79c4Qdeb08unxG45H441fL+Hp9acMVo+7GQXIKlCtZ7+waBhmD2qDrS/3gZdjzdaPvzuqIy4tHqFVXqwoxZ30fABAa+f7Z6EnIiIyBhxpJyIiqoZP90YiMikXUjMT7JjZFwcjkmFpboqne3jCxd4Szz7SUivr+9tBHbBiX6TO+302oYshql1t7g5W6N/GCX9eSlCPtP8dngQAiM0oNFg9LtxRzWbo4imr9XpzCzMTrJ3YFXO3hQEA8osViM0sgFIAdpZmHGknIqIGgUE7ERE1GdGpeWjpaA1z05pNNMvMl+Pb47cAAKP93RDg6YAATweNa2yk2r9SZw1qjZ7ezTBh/WmN8o/Hdda61hjYSlVJ3nKLFfh0bySuJeYYvA6/l23F1q9NzbZgq8q4rh74YPdVZBeWYNL3IQhs7QQAaONsq7UsgIiIyBgxaCcioibh59MxeH/3Vbwy0BfvPtaxRq9NK8s2DgALR9fstT1aNkMXTxnkpQJ75vSr8QcGhmRnqfqzILdIgfXHog3+fKVS4GLZSHv5VP26MKBdC/x5KQGXYrNwKTYLAODhYFVn9yciItIn4/3LgYiI6B6Z+XJEp+ZV69rswhJ8/+8tJOcUISopF+/vvgoA+PbYLShKlfd9rVIpNK4p3zO8paN1jadsm5hIsHtOf+yd+6hRB+wAYFsWtNfHCHtaXjFup+cjX65KHOfbwqbO7r18vD+m9/fRKGtmXT+5A4iIiGqKI+1ERNQgFJWUYvjnx5GWV4xB7Vvg+6k9YXafIPh/Z+7gs/1RWPr3NTzft5XGuTYL9yL4rYHwbaGdiEwIgSe+Pon0PDn+eLUfWthJ1UH7w+wR3pA43ieQvRyXpbUkoC7cSM7F+G9OaWyDZ2NhCqmZ6X1eVTO2UjO8P6YTjl1Pxc0U1Yc+JpwZT0REDYRxf+RPRERNxt30Auy5lAAhhNa5kFvp6PD+PvU09aNRqfh0r+4Eb4Aq8F4XXLHX9+bTd7Su2XUxXnc9MgpwOS4b8VmFOBiRrHr+7QwAgIN14w7aWzlZo1kVbfz3hu7M+dW1OyweMzafw61KMyXOx2Rg+OfHtfatd9DTKPiyJ/3V32eWZagnIiIydg0qaF++fDkkEgnmzZunLhNCYMmSJXB3d4eVlRUGDRqEq1ev1l8liYgIABCTlo8hq47i1V8u4mZKHhSlSqw7fAMLfw/H/qtJWtc/vf4UXt8aCp93/8HKfZEoKilFQlYhluy5imc2nNG6/lR0epXPDo5MQVGJ9hT4FU/5Y0bZNOkvj9zUOp9VIMek70LUx+llHxJEl43O+nvIHtDqhk0ikWD+yPYaZW8MawcAiMusXQb5udvCcOhaCtYF30RRSSmuxGfj6XsS9JVrrqes7o/4OOKDMZ3gaGOBlwf46uUZREREda3BTI8/d+4cNmzYgICAAI3ylStXYvXq1di0aRPatWuHpUuXYvjw4YiKioKdnV091ZaIiL48chO3UvNxKzUfp6LT8M5jHbDq4HUAwPbzsTj2n8Fwd7CCUinwS8gdpORWJHv7+mg0OrrZ4/StdGwJuasu93K0wisDWmPRH1dwKy0PSqWASaV5zidupOH7E7c0RoXNTCRQCoF2LnYI8nODv0chvj9xGwDw7q5wPPuIF9wdrPBl8E1sOhWj0YbUsqA9p0g1KtvYg3ZAtW6/3PwR7WBftiQgIjEH7/0ejhf7eaONc81+v5ZUyg/we2i8OkN8uef6tMSYAHd8ujcSpUqB+SPa1aIF9/difx+80M+bmeOJiKjBaBBBe15eHiZPnozvvvsOS5cuVZcLIbBmzRosXLgQ48ePBwBs3rwZLi4u2LJlC1555ZX6qjIRUZN24GoSfrsQpz7OLCjBqgPX1cclpQL9VgQj8uMgvPnrJfwdnqh1j3/CE7H3SsWI/JPdPLD6/7qgVCmw6I8rKCpRYuu5u5jcu2K9+ueHrqv3+QaA90Z1wMsDWmvcV2ZlDjtLM+QWKbD17F1sPXsXbZxt1WudAcDURIJSpUB6nhwAkFOomr5tZ9m4p8cDQGDr5lg0uiOKFUrMeNQH+6+qlgiUZ14Pj8vGn6/1r9E9k7KLqjw3LdAbS8aqtsD749V+D1/xGmDATkREDUmDmB7/6quvYvTo0Rg2bJhG+e3bt5GUlIQRI0aoy6RSKQYOHIhTp05Veb/i4mLk5ORofBERUd1ZXTaibmdphqDOrgCgHkn3clRttSUE8MgnhzUC9tPvDsHMgaogu3LAHvlxED5/piskEgnMTE3gJrMEACz8/YrGGunUSqP1gGqrL108m1lrHFcO2AHgkyf8AFSMsJf/196qQXzWXSumJhLMeNQXrw5uA6mZqdYa9/D47BrfMz6rYmp9+Uj+t1N6IOyD4eqAnYiIiHQz+qB927ZtuHjxIpYvX651LilJ9Qedi4uLRrmLi4v6nC7Lly+HTCZTf3l5edVtpYmImrDknCJEJuUCAP47oQuk5pq/aipPMS/Pyg4AW1/qAzeZFbp4ak5Bf3Vwa1iam95T1kb9/ZWEig9elWVJ7BaN7ojvp/ZEB1d7nXXs6Fb19O6gzq5oXratW3ZhCYQQ6nraN4GR9nt18XJAG2fNLPu7w3Qn8dMlPa8YE8tyEvRr44TjCwYj5tPRGNnZVW8J54iIiBoTow7aY2NjMXfuXPzvf/+DpaVlldfdO81NCHHfqW/vvvsusrOz1V+xsbF1VmcioqZu0ncVSeP6+Dph1qCK6emLRnfEsif9EeApQ2d3e5iVrUcf1tEZfVs7AQCC/FzVScIszU3wmJ+b1jOe69MKYwJU5a9vDUVkUg6EqJjOPqyjC4Z1ctF6XbnWOrZ6KzemixtkZaPLl+OykVlQgoKyvcNdZVX/Lmqs7C3NcejNgdj+Sl912dxtYSiQK+7zqgrbzlX8ju3eslmd14+IiKixM+p5fhcuXEBKSgp69OihListLcXx48fx5ZdfIioqCoBqxN3NreKPupSUFK3R98qkUimkUv1kpiUiauqiU/PV39tbmkFmZY8rH46EpZmJel/1PXNUa6JTcotgJzWHlUXFSLpEIsF7ozri9aFtYWYi0RplL/do2+b467Jqav2l2Cw42ligsKQUJhLAzeH+wbWHg5VW2cjOLnh/TCd4NrPGjeTciuesCAYAuNpbVlmXpqCLl+YMiLRcOVo6PfjPiNtpqp+H0f5u6kz0REREVH1GPdI+dOhQhIeHIywsTP3Vs2dPTJ48GWFhYfD19YWrqysOHjyofo1cLsexY8cQGBhYjzUnImqYQu9m4uczdxCdmvfgi3WonCX8PyPbq2c92UrN1AF7Zc52lhoBe2W2UrP7Bsn/19MLUjPVPROyihBVNiXfs5k1pGb3D647ulVMm585sDX+XTAYayd2U691b93CFn18HQEA+WWj7C2drLVv1IRIzUxxYVFFbpnyzPoPUlj279fLu5lGpn8iIiKqHqMeabezs4Ofn59GmY2NDZycnNTl8+bNw7Jly9C2bVu0bdsWy5Ytg7W1NSZNmlQfVSYiarC+//cWlv59DQDgLrPEyXeG1DjL9rrDNwAAVuammDWw9QOurh2JRIKJvbyw+fQdrC17LgD0bPXgKdjtXe3wx6v9UCBXoI+Pk1YwaWIiwaYXHkGH9/epy1o5Nu2gHQCcbKXo6uWAsNgspFUzaC+fRm8tNeo/OYiIiIyWUY+0V8eCBQswb948zJ49Gz179kR8fDwOHDjAPdqJiKqgVArkFSvw4Z9XMWPzeRTIFcgvVmDl/ij1NQnZRfB59x+sOhAFUZbcrSqlSoHkHNWWXn+WTVd3sZcaZFS1fA/xynxb2FTrtV29HBDYunmV9bQ0N8U3k7sDUG0TNzpAe219U9TcVpU8rjxov3AnA39dToCi0iyLcjFp+TgSlQoAsK5iRgURERHdn0Q86K+xJiAnJwcymQzZ2dmwt9edaZiIqLH48M+r2HgyRn3sJrNEYtk+2q2crNHL21Fjj3UA+GZydzzmrztoffmn8zh4LRkbpvTEm9vDkFukwO+zA9HNAEnHfgm5g4W/X9EoW/qEH57r06qKV1BtvbPzMradi4W7zBIJlfZfX/9cdwT5uUEIgZX7o3DhTibO3s5Qn/9xWk8M6VB1vhkiIqKmprpxaIMfaScioupLyyvWCNgBqAN2ABjbxR1zh7bVet2sXy4iqdJ15TLz5TgQkQwhgJ/P3EFukWoqtE/z6o1219aT3Ty0yppxGzG9Kt8OL+Gen4e0ssz9x66n4puj0RoBO4AmncSPiIioNhi0ExEZkdyiEhQrSvVy7zO30tFz6aEqzy99wg+vD20LDwcr9NCxLvxUdJr6eyEEQu9motvHFYlAj19PVX9vqP3MrS2010mXT98m/ajq3zciMQdTfgjBi5vO6TxvoSMRIRERET0Ys8IQERmJgxHJmPm/C7C2MMX653qgX5vmAFSj2cv+uYbjN1IxLdAHLz3qozMT+4NM3HBGq6yvrxOScorweICbxpTy32b2RbFCidTcYqw5dAM7L8YhMikXRyJTcCstHx//FVHlc7p4ygyaJfzryd0x+5eL6uOe3o4Ge3ZT1NxOc8tUL0crxGYUYkvI3SpfM6O/D/doJyIiekgM2omIjIAQAm/vvIxSpUBukQKTvw+BpbkJ7C3NkZJbkaV7xb5IeDazwuNd3Kt974SsQly8m6lVviCoPWYPaqPzNRKJan90L0drdGvpgJ0X47Dh+C1sOH5L69r/jGyPQnkpUnOLkZZXjM8mdKl23erCKH83bJjSAz+fuYNVE7rAlNuK6VX59PhyDlYWiEWh1nUfjeuMD3ZfxUfjOmNqX28D1Y6IiKjxYdBORGQEdpyPQ0a+XKOsqESJohLtbbVi0vKrfd+8YgX6rQhG5ZSjO2f1hZ+H7IF7mZfr7K47Mcr0/j54f0ynatdFn0Z0dsWIzq71XY0moa2zrcaxg7XupRBT+3ozWCciIqoDDNqJiIzA3+GJOsudbCxQWFIKRxsLKJUCCdlFyCiQ67z2XmsOXceaQze0ypvbSqsdsANAgKcDrMxNUViiWmv/55z+sLU0Q0vuW94kOdlK8cpAX3x7TDXrovLMBjMTCd4Y3g4BnrL6qh4REVGjw6CdiKielSoFjpUlcVs1oQve2nEJAHBu4TC0sJNCqRSQSIDv/72NT/65ho0nY/DuYx1hYaZ7XbtcocT8HZew51KCzvMyHXub34+piQRH5g/C8M+PoYunA/w87CGRcAp6U9bF00H9faG8InHiSwN88epg3UsuiIiI6OEwaCciqkdKpcDzP55VH3dyt8dnTwdAIpGgRVnCr/Kkbq2cKka2D0QkYUyAO0TZvPfKQfTBiGSNgP3Jbh74PTQeANC6hU2Ng3YAcJVZInzJyBq/jhqnIR2c8XzfVmjlZIODEcnq8reDOtRjrYiIiBonBu1ERPXop9MxOHFTtZWalbkp2rvYoaOb7jXkQzu6qL+fsyUUc7aEqo+7t3TAjpmBMJEAm0/HAAD8POyx+9X+MDWRYOkTfvj5zB0MbNeCo+RUa5bmpvhwnB8AYHcVMzqIiIiobjBoJyLSk+jUPCRlF2HnxTi89KivRjBeVFKKH07c1sjGvmNm3/tulWZqIsH4bh7YVTZqXtnFu1lo/d4/GmWLH++sXm9sIzXDzIGta9skIi0BHjJcis2q72oQERE1WgzaiYj0YG94ImZV2jt818V4jOvqjqVP+EEAmLctDMGRKerzn473h5/Hg5N3LRrTSWfQfq/Xh7ZFL+5XTgbwn6D2aGZtXqNtCImIiKj6JEJU3gioacrJyYFMJkN2djbs7XVPSyUiepC8YgUOX0vG3G1hMDORQKGs3v9eWzlZY/+8AbA0r15G95/P3MH7f1wBAPw4rScORiRj54V4yEuVAIAB7Vpg07Re9x21JyIiIqL6Vd04lCPtREQPoVhRiinfn0VGgRy9vB3Ro1UzzC/L+g5AHbCvndgVIzq54r3fw9XJ4Mp1a+mATS88AhsLU5iZ6s4Er8szPb2QXSCHuakJBrRtgSEdXLB8fACUSoGo5Fx0cLXjunUiIiKiRoJBOxHRQ9gdloCzMRkAgJspedh69q7WNf3bNMeQDs6wsjDF6v/rApmVOSIScnA2JgMz+vtg0ZhOD/VsCzMTzBnSVqvcxERSZRI7IiIiImqYGLQTEVWTEAI7LsRh7aEbiM8q1DpvKzXDE93c4dPcFs/1aQmpWcV0d4lEgiVjOxuyukRERETUCDBoJyKqhhM30vDcDyFa5d9O6YEhHZyhFEIjSCciIiIiqgsM2omIHqBUKbDm0HWNsoWjOqJ/2+acjk5EREREesWgnYjoPtLzihG09l+k5hYDAPbPG4D2rnb1XCsiIiIiaiqqn66YiKgJWvZPpDpgH9S+BQN2IiIiIjIojrQ3EblFJUjNLYZvC1u9PudUdBpyChUY0K45rC3440UNV4FcgTlbQhEcmQIA+PgJPzzT06uea0VERERETQ1H2puIN34Nw5BVx3AoIrlW9/knPBFtF/6DgzrucygiGZO+C8HM/11Apw/249j1VAghanT/9Lxi9F1+GG9uD6tVPYlqa+fFeHXA7u8hw5Q+rWBhxv9lEhEREZFh8S/QJkBRqsSha6rgY8ZP55FXrHio+yTnFGH2LxdRUirw0k/n1eVKpcAfofGYUakMAJ7/8Sz8lxxAbEYBCuWl1XrGjJ/OIzG7CLsuxqunJBPVh+TsIvX3G6b2qMeaEBEREVFTxvnLjVxesQJ+i/drlPkt3o8FQe0xe1AbAMDWs3fhbCfF0I4u973Xe7vCNY6D1hzH2K7u+OtSIiISc6p8/qMrjwAAhnZwhqW5KYoVSphIgM+e7gKZtbn62qsJ2Qi9m6U+js8qRAs7abXbSlSXcopKAACvD2kDN5lVPdeGiIiIiJoqBu2NWHBkMmb/clHnuZX7onD2dgZm9PfFu2XBeCsna6z+vy4QAkjNLcasXy6ihZ0UqbnFaGZtjsyCEo17RCblInJflEbZjpl9UVRSClupGe5mFGDutjD1ucNlU43LHfjoAKzMTTGkgzNeGuCL9UejNc6ncaSd6oFSKRAam4XdYQkAAHsr8we8goiIiIhIfySipouOG6GcnBzIZDJkZ2fD3r5x7LksVyjR/eOD6qnwL/bzwWP+rjgYkYwNx2+przM3laCktG5+BPbOfVRrz+qsAjnmbgvDseupNb6fhakJji0YxFFOMgghBFLzirE1JBafV9qTfeVTAfi/XkxAR0RERER1q7pxKEfaG6lriTnqgP2PV/uhq5cDAKCXtyM6u9urR8BrGrCvndgVXwbfxI2UPHVZKydrjO/miQ46tsJysLbA5hcfKXuWEnfS85FVUILIpFws+uOKzmf8Z2R7fLY/CvJSJfouD8bZ94bC2d6yRvV8GNGpeVhz6AZG+7tiSAcXJh1rIrafj8X6Y9G4lZqvdc7cVIJO7o3jgzwiIiIiapgYtDdSoXczAaj2lS4P2MuN6+qBklKB+Tsuqcv+nNMfj395QuO632b2RUc3e+QVK7BibySa20nxeIA7+vo64fStdMiszJFdWIJxXT2qVSdzUxO0cVYF9j1aNYPUzAQ9vR0xccNpJOeopsJ/MKYTXuzvg/isQmwJuQsAeGTZYRx6cwBat7CFRCJ5qH+PBzlzKx0vbDyHwpJS/HkpAR4OVvj79f5wsLZATlEJrM1NYWbKIN6QSpUCV+KzoVAq0d7VHptPxcCzmVW1f97ulVtUgpspeWhuK8XNlDwMat8Cb+24hF0X47WudbGX4reZgZBZm8PektPjiYiIiKj+MGhvhA5fS8aKsrXm3bya6bxmcPsWkJqZoFihxF+v9YefhwwrnvLHjvNxmNDTE8/0aqm+1kZqhtXPdFUfO9tbPnTgVE4ikWBC2Z7Xluam6vJpgd4AgE+e8IONhSm++/c2AGDVgeuISs5FB1c7fD257jJ5X4rNwheHb2itt4/PKsS/N9JwMyUPaw/fAAA809MLBSWlCLmVDkcbC3w3tSe8HK3rrC5NkRBC5wcxSqXAyDXHcbPSjI5yo/zdYF6DD1Byi0qwLvgmfjhxG6XKqmeWPN+3FXr7OuExP1e9fThERERERFRTDNobkd8uxGFveKJGANqtpYPOa51spQj9YDhMTSSQmqmC5md6tdQI1g3lkyf88dwPIZgzuA1MTFTBkkQiwcLRnSCRSLDh+C3svZIEALiVmo+DEcmwtzRDb1+nKu9ZVTB4r4//isD5O5nqY9/mNvD3lGF3WAKuJuTgxxO31ed+PR+r/j4ltxhv7biE7a/0rXF7SeW747ew9vANDGjXHCM7u+LxAHd1/286FaMzYAeAqKRc+HnIqvWM0LuZePLrU/e9pr2LHfa81k/9PiAiIiIiMiZMRIfGkYguq0COrh8d1Cjr4GqHPXP6N4i12Zn5cjhYm2sF2teTczHi8+M6X3Nk/iD4NLfRKt948jaW743Ei/18MKKzC3yb28DB2kLnPfosO4ykHNV+3JbmJrj4/nD8eOI2/nvgus7r73XozYFo42xbrWtJU8f396GwpFSr3MbCFPlyVflofzesndgV+68m49UtFTsh/DitJ4Z00NyiUK5QQkCgpFTAVmqG1Nxi9PrkkPr8zIGtEeTnCicbC1xNyEHo3UzYW5njxX4+sLJgwE5EREREhsVEdE1MTHqBxvGu2YHwc5c1iIAdAJrZ6A6qW95n+vnflxMw41Ff3M0oQFtn1Xr3X0Lu4MM/IwAA649FY/0x1TZyk3q3xLIn/TVeH5tRoA7YAdVSAmsLM0zq3QrfHI1WB47+HjL8+Vp/yBVKtFu0V+Meaw/fwLpnu9W8wXqQXVACeyuzBjO129xUgsIS7fLyf3c7SzO881gHmJmaYHSAG1o6VuRdeHHTeSx5vBPkpUq82M8HsZmFGP3Fvygoe21QZ1cMbN9Cfc+xXdzxzmMd1MdejtYI8nPVY+uIiIiIiOoGg/ZGQKkUCL6WrD7++/X+6OxevenDxs7S3BQdXO0QmZSrde7Y9VRsCbmLhGxV4P3jtJ5Y+LvujPS/X4zHR2M7IzazEH9eSkBJqRIhtzPU5yUS4NneqqUBjjYW6OLlgFPR6QAqPjiwMDPB0fmDEJ2ah/1Xk7D9fBz+vJSAYR2da73G/2EIIfDzmTuIzSiAi70llv59DZN7t8Qn93w4UR8K5AqEx2VDQPXv5+6guW1fUUkpcopUuxssfcIP3/97S+ODp1mDWmPByPYaH0D4e8rw28y+eHr9aQDAkrIPZ45EpuL0rXSN+++7moR9V1VLKt4Y1g5zh7Wt8zYSERERERkCp8ej4U2P//NSAi7ezcSYADd0b9kMz288h+Nl+6D39nHEr41snXVsRgGSc4oQn1WIczEZGNnZFVN+OHvf17w8wFdjP3oA8HK0QmxGoda1rw5ujdmD2sBGWvEZ1pfBN9RT5C99MAIya80M4nGZBRjy32OQlyoBADc+eaxGydFq60ZyLoZXsWxg+yt98YiPo8HqUtnBiGR8cfgGwuOzNcrfGNYOrw9tg6sJOTgYkQx5qRLfHI2GrdQM4UtGQCKRQAiBYoVSIzGhLlN/PKv+eb/Xs494wdHGAl8diVaX6eo/IiIiIqL6Vt04lEE7GlbQnphdiL7Lg9XHf73WH2PWVWzV5tvcBsHzB9VDzQznfgFruZhPR6u/937n7yqv83CwwsE3B8DaQnPSiRACMekFcLaTagTzlR2/noqpP6o+PHiuT0uUKoGrCdmYO7QthnZ00fmauvLMt6c1ZgpU1tfXCVtf7qPX5+uyJeQu3vs9vEavae9ih/1vDKjRa/KKFZi7NVQr4//htwaidQtbCCGw/2oyDkQk4fEAdwzu4Fyj+xMRERERGQLXtDdCj64M1hopHn9PZux8ucKQVaoXDxo1vTej+5gAN/x1OVF97OFghV7ezdDS0Rov9vfRCtgBVfZ6XUnuKhvQroU6adr/ztxVl0/ffB63lo1SZ0KvC6m5xTh+PRU7L8bBRmqmFbCbmkjQ0tEat9PycfpWOtYcuo5Zg1obLCP6zgtxGgH78E4uGN7JBWO7uGPkmuO4c0/OhXLtXe1q/CxbqRl+mNYLBXIFHl93AtGp+QBUH1gBqr4L8nPlmnUiIiIiahQYtDcguqZ2l0/PLrf48c6Gqk69kVnpDtpfH9IGE3p6ae2d/vE4P4zyd8Owji4oVQqYmkjqLEHfE9088EvIXa3yUV/8iw1TeqKlU93s4/7urss4dC1FqzxqaRCEUK3JNzMxQdcPDyC3WIE1h27gSnwOvpvaQ++J6b46chOf7Y9SH4e+P1wjseCRtwZh+/lY/HDiNrq3bIbMAjkORKhyMPh5PPzMFmsLM/z12qNYsucqRgW4NZgEfERERERENdEwUosTACD4rYHq74M6a44ibnmpN0LeG4pR/m6GrpbBSc1MYVZpFPvT8f44+c4QvDmivVbADqgy04/yd4OFmQmsLEzrNKP+2C7uaG5rAXtLM43+iUzKxU+nYx76vkqlwNpDN/De7+EIi83SGbA/5ucKqZkpLM1NITUzhamJBOcWDcMof9XPxqFryVpry+taZr4cqw9WbI83c2BrrZ0ATEwkmPhISxx8cyBWPB2AAM+KJIn+Hg61er6VhSlWPB2Age1aPPhiIiIiIqIGiCPtDYhvC1tM7OWFi3cz8c5jHSA1N8HusAR4OVqhq5eDzmnejdWq/+uCudvCAADuDlbwuCc7uaH09nXC+UXD1cch7w3FjM3nER6fjRspeepyIQROR6dDIpGgb2unB9732PVUfH5IFQxvKRvJd5dZ4uQ7QyCRSFAgV8BKR8I2S3NTfD25B8Z9dRKXYrOQmF2EAE/dzzgSlYK76QUI8JShW8tmNWk2hBBIyC5CTFo+SpWqtBi/zeyLHq0efJ9nH2mJxOwiNLO2QO96SphHRERERNRQNJ0or5H49KkA9fdrJ3bD0if8YG1hBtM6XD/dEIz2d8O2s7GwMDNBb1/jCfxc7C3xweOdMGH9adxMUW0N52hjgUJ5qTpp3ftjOmF6f58q71FSqsTbOy9rlX/weGf1FPAHfUDjWLbuP6tArvP8mVvpeGHjOfXxwlEd8fmh63CytcD653rcd8vAy3FZeHHTOaTlVdy7i5cDenpXrx+cbKVGsS0dEREREVFDwKC9gbOzbJpbWZmZmtRLhvTqaNPCFgAQn1WIV36+AAAYWimD+cd/RWgF7UejUnD2dgbeHN4OcZmFSMktBqDaKi2zQI4X+/nUaH18M2vVFPXMghKd53eHJWgcf/LPNQBAQUYhRn9xAu881gEzB7bWuEYIgRM303Rut2fWxD40IiIiIiIyFAbtRHXs3jXdALS2J/N+52/4edjjq0nd4dnMGtPKRr2/Plqxv3jrFjaYO6xtreqQVhb8V5aSU4StZ1VT7heN7ojP9kehWKGZ0PDTvZH4dG8knn3ECwPbOeO3C3E4dC1Z45qne3jitwtxAABpHeYJICIiIiKiCgzaifTgER9HnK1iH/VyV+JzMPCzo+jlrXsdeBdPh4d+vnfZ9mffn7iNS3FZWDuxG8xMJfjzUiI+/isCAOBkY4Fpgd4Y2dkV+XIF2jnb4cLdTExYf1p9n61nY7H1bKzW/ZeP98ezj7TE0z088dGfEXh5gO9D15WIiIiIiKomEUKI+q5EVZYvX45du3YhMjISVlZWCAwMxIoVK9C+fXv1NUIIfPjhh9iwYQMyMzPRu3dvfPXVV+jcufpbn1V3U3ui6jp7OwNbQu5gQLsWcLKVYueFOCTnFGntr16V/03vjZ7ezWCpI9lcdZyPycDTlYJvXVZN6IKnemhnqTsUkYxvjkXjwp1MjXIPByu8P6YT9z8nIiIiIqoD1Y1DjTpoDwoKwsSJE9GrVy8oFAosXLgQ4eHhiIiIgI2NaiRxxYoV+OSTT7Bp0ya0a9cOS5cuxfHjxxEVFQU7O7tqPYdBOxlK3+WHkZhdpFXuLrPEu6M6wtlOCktzU3TxcqjVc5RKgYkbzuBsjO4PCXbOCnxgpvefTsfgg91XAQBfPNsNY7u416pORERERERUoVEE7fdKTU2Fs7Mzjh07hgEDBkAIAXd3d8ybNw9vv/02AKC4uBguLi5YsWIFXnnllWrdl0E7GcqFOxm4k16AJ7t5qDPBlyqFXrL/CyGQVVACeakSXx+5ic2n7wAAenk3w46ZgdW6x++hcYhIyMHbQR1gZsp160REREREdaW6cWiDWtOenZ0NAHB0VG0tdfv2bSQlJWHEiBHqa6RSKQYOHIhTp05VGbQXFxejuLgiQVdOTo4ea01UoUcrR/Ropbk1mr6265NIJOqEdO+P6QR5qUBOYQle7O9d7Xs82c0TT3bTS/WIiIiIiKgaGkzQLoTAm2++if79+8PPzw8AkJSUBABwcXHRuNbFxQV37typ8l7Lly/Hhx9+qL/KEhkZM1MTLB/PvdGJiIiIiBqaBjPfdc6cObh8+TK2bt2qda58mnE5IYRWWWXvvvsusrOz1V+xsdrZsYmIiIiIiIjqW4MYaX/ttdewZ88eHD9+HJ6eFdmuXV1VWayTkpLg5uamLk9JSdEafa9MKpVCKpXqr8JEREREREREdcCoR9qFEJgzZw527dqF4OBg+Pj4aJz38fGBq6srDh48qC6Ty+U4duwYAgOrl2iLiIiIiIiIyFgZ9Uj7q6++ii1btmD37t2ws7NTr2GXyWSwsrKCRCLBvHnzsGzZMrRt2xZt27bFsmXLYG1tjUmTJtVz7YmIiIiIiIhqx6iD9m+++QYAMGjQII3yjRs3Ytq0aQCABQsWoLCwELNnz0ZmZiZ69+6NAwcOVHuPdiIiIiIiIiJj1aD2adcX7tNOREREREREhlTdONSo17QTERERERERNWUM2omIiIiIiIiMFIN2IiIiIiIiIiPFoJ2IiIiIiIjISDFoJyIiIiIiIjJSDNqJiIiIiIiIjBSDdiIiIiIiIiIjxaCdiIiIiIiIyEgxaCciIiIiIiIyUgzaiYiIiIiIiIwUg3YiIiIiIiIiI8WgnYiIiIiIiMhImdV3BYyBEAIAkJOTU881ISIiIiIioqagPP4sj0erwqAdQG5uLgDAy8urnmtCRERERERETUlubi5kMlmV5yXiQWF9E6BUKpGQkAA7OztIJJL6rk6VcnJy4OXlhdjYWNjb29d3dagK7KeGgf1k/NhHDQP7qWFgPzUM7Cfjxz5qGBpKPwkhkJubC3d3d5iYVL1ynSPtAExMTODp6Vnf1ag2e3t7o/7hIxX2U8PAfjJ+7KOGgf3UMLCfGgb2k/FjHzUMDaGf7jfCXo6J6IiIiIiIiIiMFIN2IiIiIiIiIiPFoL0BkUqlWLx4MaRSaX1Xhe6D/dQwsJ+MH/uoYWA/NQzsp4aB/WT82EcNQ2PrJyaiIyIiIiIiIjJSHGknIiIiIiIiMlIM2omIiIiIiIiMFIN2IiIiIiIiIiPFoJ2IiIiIiIjISDFoN6Dly5ejV69esLOzg7OzM5544glERUVpXCOEwJIlS+Du7g4rKysMGjQIV69e1bhmw4YNGDRoEOzt7SGRSJCVlaX1LG9vb0gkEo2vd955R5/NazQM2U8A8Pfff6N3796wsrJC8+bNMX78eH01rVExVD8dPXpU671U/nXu3Dl9N7PBM+T76fr16xg3bhyaN28Oe3t79OvXD0eOHNFn8xoFQ/bRxYsXMXz4cDg4OMDJyQkvv/wy8vLy9Nm8RqMu+ikjIwOvvfYa2rdvD2tra7Rs2RKvv/46srOzNe6TmZmJKVOmQCaTQSaTYcqUKVX+DiNNhuynTz75BIGBgbC2toaDg4MhmtdoGKqfYmJiMH36dPj4+MDKygqtW7fG4sWLIZfLDdbWhsqQ76WxY8eiZcuWsLS0hJubG6ZMmYKEhASDtLO6GLQb0LFjx/Dqq6/izJkzOHjwIBQKBUaMGIH8/Hz1NStXrsTq1avx5Zdf4ty5c3B1dcXw4cORm5urvqagoABBQUF477337vu8jz76CImJieqvRYsW6a1tjYkh+2nnzp2YMmUKXnjhBVy6dAknT57EpEmT9Nq+xsJQ/RQYGKjxPkpMTMSMGTPg7e2Nnj176r2dDZ0h30+jR4+GQqFAcHAwLly4gK5du2LMmDFISkrSaxsbOkP1UUJCAoYNG4Y2bdogJCQE+/btw9WrVzFt2jR9N7FRqIt+SkhIQEJCAv773/8iPDwcmzZtwr59+zB9+nSNZ02aNAlhYWHYt28f9u3bh7CwMEyZMsWg7W2oDNlPcrkcEyZMwKxZswzaxsbAUP0UGRkJpVKJb7/9FlevXsXnn3+O9evXP/BveDLse2nw4MHYvn07oqKisHPnTkRHR+Ppp582aHsfSFC9SUlJEQDEsWPHhBBCKJVK4erqKj799FP1NUVFRUImk4n169drvf7IkSMCgMjMzNQ616pVK/H555/rq+pNir76qaSkRHh4eIjvv/9er/VvKvT5fqpMLpcLZ2dn8dFHH9Vp/ZsKffVTamqqACCOHz+uLsvJyREAxKFDh/TTmEZKX3307bffCmdnZ1FaWqouCw0NFQDEjRs39NOYRqy2/VRu+/btwsLCQpSUlAghhIiIiBAAxJkzZ9TXnD59WgAQkZGRempN46Wvfqps48aNQiaT1XndmxJD9FO5lStXCh8fn7qrfBNhyD7avXu3kEgkQi6X110Daokj7fWofGqGo6MjAOD27dtISkrCiBEj1NdIpVIMHDgQp06dqvH9V6xYAScnJ3Tt2hWffPIJp+I8JH3108WLFxEfHw8TExN069YNbm5ueOyxx7SmnFL16Pv9VG7Pnj1IS0vj6OBD0lc/OTk5oWPHjvjpp5+Qn58PhUKBb7/9Fi4uLujRo0fdNqKR01cfFRcXw8LCAiYmFX96WFlZAQBOnDhRF1VvUuqqn7Kzs2Fvbw8zMzMAwOnTpyGTydC7d2/1NX369IFMJqvV/zubKn31E9UtQ/ZTdna2+jlUfYbqo4yMDPzyyy8IDAyEubl5Hbagdhi01xMhBN588030798ffn5+AKCewuni4qJxrYuLS42nd86dOxfbtm3DkSNHMGfOHKxZswazZ8+um8o3Ifrsp1u3bgEAlixZgkWLFuGvv/5Cs2bNMHDgQGRkZNRRC5oGfb+fKvvhhx8wcuRIeHl5PXyFmyh99pNEIsHBgwcRGhoKOzs7WFpa4vPPP8e+ffu41rMG9NlHQ4YMQVJSEj777DPI5XJkZmaqp4gmJibWUQuahrrqp/T0dHz88cd45ZVX1GVJSUlwdnbWutbZ2ZlLTWpIn/1EdceQ/RQdHY1169Zh5syZdVT7psEQffT222/DxsYGTk5OuHv3Lnbv3l3HragdBu31ZM6cObh8+TK2bt2qdU4ikWgcCyG0yh7kjTfewMCBAxEQEIAZM2Zg/fr1+OGHH5Cenl6rejc1+uwnpVIJAFi4cCGeeuop9OjRAxs3boREIsGOHTtqV/EmRt/vp3JxcXHYv3+/1looqh599pMQArNnz4azszP+/fdfnD17FuPGjcOYMWMYENaAPvuoc+fO2Lx5M1atWgVra2u4urrC19cXLi4uMDU1rXXdm5K66KecnByMHj0anTp1wuLFi+97j/vdh6qm736iumGofkpISEBQUBAmTJiAGTNm1E3lmwhD9NF//vMfhIaG4sCBAzA1NcXUqVMhhKi7RtQSg/Z68Nprr2HPnj04cuQIPD091eWurq4AoPXpUEpKitanSDXVp08fAMDNmzdrdZ+mRN/95ObmBgDo1KmTukwqlcLX1xd3796tTdWbFEO+nzZu3AgnJyeMHTv24SvcROm7n4KDg/HXX39h27Zt6NevH7p3746vv/4aVlZW2Lx5c900opEzxHtp0qRJSEpKQnx8PNLT07FkyRKkpqbCx8en9g1oIuqin3JzcxEUFARbW1v8/vvvGlNAXV1dkZycrPXc1NTUWv8t0pTou5+obhiqnxISEjB48GD07dsXGzZs0ENLGi9D9VHz5s3Rrl07DB8+HNu2bcM///yDM2fO6KFFD4dBuwEJITBnzhzs2rULwcHBWn+k+Pj4wNXVFQcPHlSXyeVyHDt2DIGBgbV6dmhoKICKQJGqZqh+6tGjB6RSqcb2FSUlJYiJiUGrVq1q35BGztDvJyEENm7ciKlTp/IPpxowVD8VFBQAgMZ66fLj8lktpFt9/G5ycXGBra0tfv31V1haWmL48OG1akNTUFf9lJOTgxEjRsDCwgJ79uyBpaWlxn369u2L7OxsnD17Vl0WEhKC7OzsWv8t0hQYqp+odgzZT/Hx8Rg0aBC6d++OjRs3av2eIt3q871UPsJeXFxcR62pA/rPdUflZs2aJWQymTh69KhITExUfxUUFKiv+fTTT4VMJhO7du0S4eHh4tlnnxVubm4iJydHfU1iYqIIDQ0V3333nTpbcmhoqEhPTxdCCHHq1CmxevVqERoaKm7duiV+/fVX4e7uLsaOHWvwNjdEhuonIYSYO3eu8PDwEPv37xeRkZFi+vTpwtnZWWRkZBi0zQ2RIftJCCEOHTokAIiIiAiDtbExMFQ/paamCicnJzF+/HgRFhYmoqKixPz584W5ubkICwszeLsbEkO+l9atWycuXLggoqKixJdffimsrKzE2rVrDdrehqou+iknJ0f07t1b+Pv7i5s3b2rcR6FQqO8TFBQkAgICxOnTp8Xp06eFv7+/GDNmjMHb3BAZsp/u3LkjQkNDxYcffihsbW1FaGioCA0NFbm5uQZvd0NjqH6Kj48Xbdq0EUOGDBFxcXEa19D9GaqPQkJCxLp160RoaKiIiYkRwcHBon///qJ169aiqKioXtquC4N2AwKg82vjxo3qa5RKpVi8eLFwdXUVUqlUDBgwQISHh2vcZ/Hixfe9z4ULF0Tv3r2FTCYTlpaWon379mLx4sUiPz/fgK1tuAzVT0Kotg976623hLOzs7CzsxPDhg0TV65cMVBLGzZD9pMQQjz77LMiMDDQAC1rXAzZT+fOnRMjRowQjo6Ows7OTvTp00f8888/Bmppw2XIPpoyZYpwdHQUFhYWIiAgQPz0008GamXDVxf9VL4dn66v27dvq69LT08XkydPFnZ2dsLOzk5Mnjz5gdthkooh++n555/Xec2RI0cM1+AGylD9tHHjxiqvofszVB9dvnxZDB48WDg6OgqpVCq8vb3FzJkzRVxcnIFbfH8SIYxohT0RERERERERqXFRBREREREREZGRYtBOREREREREZKQYtBMREREREREZKQbtREREREREREaKQTsRERERERGRkWLQTkRERERERGSkGLQTERERERERGSkG7URERERERERGikE7ERERERERkZFi0E5ERESYNm0aJBIJJBIJzM3N4eLiguHDh+PHH3+EUqms9n02bdoEBwcH/VWUiIioiWHQTkRERACAoKAgJCYmIiYmBnv37sXgwYMxd+5cjBkzBgqFor6rR0RE1CQxaCciIiIAgFQqhaurKzw8PNC9e3e899572L17N/bu3YtNmzYBAFavXg1/f3/Y2NjAy8sLs2fPRl5eHgDg6NGjeOGFF5Cdna0etV+yZAkAQC6XY8GCBfDw8ICNjQ169+6No0eP1k9DiYiIGhAG7URERFSlIUOGoEuXLti1axcAwMTEBF988QWuXLmCzZs3Izg4GAsWLAAABAYGYs2aNbC3t0diYiISExMxf/58AMALL7yAkydPYtu2bbh8+TImTJiAoKAg3Lhxo97aRkRE1BBIhBCivitBRERE9WvatGnIysrCH3/8oXVu4sSJuHz5MiIiIrTO7dixA7NmzUJaWhoA1Zr2efPmISsrS31NdHQ02rZti7i4OLi7u6vLhw0bhkceeQTLli2r8/YQERE1Fmb1XQEiIiIybkIISCQSAMCRI0ewbNkyREREICcnBwqFAkVFRcjPz4eNjY3O11+8eBFCCLRr106jvLi4GE5OTnqvPxERUUPGoJ2IiIju69q1a/Dx8cGdO3cwatQozJw5Ex9//DEcHR1x4sQJTJ8+HSUlJVW+XqlUwtTUFBcuXICpqanGOVtbW31Xn4iIqEFj0E5ERERVCg4ORnh4ON544w2cP38eCoUCq1atgomJKi3O9u3bNa63sLBAaWmpRlm3bt1QWlqKlJQUPProowarOxERUWPAoJ2IiIgAqKarJyUlobS0FMnJydi3bx+WL1+OMWPGYOrUqQgPD4dCocC6devw+OOP4+TJk1i/fr3GPby9vZGXl4fDhw+jS5cusLa2Rrt27TB58mRMnToVq1atQrdu3ZCWlobg4GD4+/tj1KhR9dRiIiIi48fs8URERAQA2LdvH9zc3ODt7Y2goCAcOXIEX3zxBXbv3g1TU1N07doVq1evxooVK+Dn54dffvkFy5cv17hHYGAgZs6ciWeeeQYtWrTAypUrAQAbN27E1KlT8dZbb6F9+/YYO3YsQkJC4OXlVR9NJSIiajCYPZ6IiIiIiIjISHGknYiIiIiIiMhIMWgnIiIiIiIiMlIM2omIiIiIiIiMFIN2IiIiIiIiIiPFoJ2IiIiIiIjISDFoJyIiIiIiIjJSDNqJiIiIiIiIjBSDdiIiIiIiIiIjxaCdiIiIiIiIyEgxaCciIiIiIiIyUgzaiYiIiIiIiIzU/wPyYMu9VGgmtAAAAABJRU5ErkJggg==",
+      "text/plain": [
+       "<Figure size 1200x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "from statsmodels.tsa.arima.model import ARIMA\n",
+    "\n",
+    "# Read CSV with correct date parsing\n",
+    "df = pd.read_csv(\"AAPL_stock_data.csv\", parse_dates=['Date'], index_col='Date')\n",
+    "\n",
+    "# Rename column if needed\n",
+    "df.columns = ['Close']\n",
+    "\n",
+    "# Ensure numeric and drop any missing values\n",
+    "df['Close'] = pd.to_numeric(df['Close'], errors='coerce')\n",
+    "df = df.dropna(subset=['Close'])\n",
+    "\n",
+    "# Resample to daily frequency and forward fill missing values\n",
+    "df = df.resample('D').ffill()\n",
+    "\n",
+    "# Split train and test\n",
+    "train = df['Close'][:-200]\n",
+    "test = df['Close'][-200:]\n",
+    "\n",
+    "# Fit ARIMA model\n",
+    "model = ARIMA(train, order=(5,1,0))\n",
+    "model_fit = model.fit()\n",
+    "\n",
+    "# Forecast\n",
+    "forecast = model_fit.forecast(steps=len(test))\n",
+    "\n",
+    "# Plot\n",
+    "plt.figure(figsize=(12,6))\n",
+    "plt.plot(train.index, train, label='Train')\n",
+    "plt.plot(test.index, test, label='Test')\n",
+    "plt.plot(test.index, forecast, label='ARIMA Forecast')\n",
+    "plt.title(\"Apple Stock Price ARIMA Forecast\")\n",
+    "plt.xlabel(\"Date\")\n",
+    "plt.ylabel(\"Closing Price\")\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "6cmWlsw9JuLP",
+    "outputId": "deaf96c5-a5ff-4985-d28e-6ff7e28b3d27"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: tensorflow in c:\\users\\hp\\anaconda3\\lib\\site-packages (2.20.0)\n",
+      "Requirement already satisfied: absl-py>=1.0.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (2.3.1)\n",
+      "Requirement already satisfied: astunparse>=1.6.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (1.6.3)\n",
+      "Requirement already satisfied: flatbuffers>=24.3.25 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (25.9.23)\n",
+      "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (0.6.0)\n",
+      "Requirement already satisfied: google_pasta>=0.1.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (0.2.0)\n",
+      "Requirement already satisfied: libclang>=13.0.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (18.1.1)\n",
+      "Requirement already satisfied: opt_einsum>=2.3.2 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (3.4.0)\n",
+      "Requirement already satisfied: packaging in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (23.2)\n",
+      "Requirement already satisfied: protobuf>=5.28.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (6.32.1)\n",
+      "Requirement already satisfied: requests<3,>=2.21.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (2.32.2)\n",
+      "Requirement already satisfied: setuptools in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (69.5.1)\n",
+      "Requirement already satisfied: six>=1.12.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (1.16.0)\n",
+      "Requirement already satisfied: termcolor>=1.1.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (3.1.0)\n",
+      "Requirement already satisfied: typing_extensions>=3.6.6 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (4.15.0)\n",
+      "Requirement already satisfied: wrapt>=1.11.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (1.14.1)\n",
+      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (1.75.1)\n",
+      "Requirement already satisfied: tensorboard~=2.20.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (2.20.0)\n",
+      "Requirement already satisfied: keras>=3.10.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (3.11.3)\n",
+      "Requirement already satisfied: numpy>=1.26.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (1.26.4)\n",
+      "Requirement already satisfied: h5py>=3.11.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (3.11.0)\n",
+      "Requirement already satisfied: ml_dtypes<1.0.0,>=0.5.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorflow) (0.5.3)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (2.0.4)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (3.7)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (2.2.2)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (2025.1.31)\n",
+      "Requirement already satisfied: markdown>=2.6.8 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorboard~=2.20.0->tensorflow) (3.4.1)\n",
+      "Requirement already satisfied: pillow in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorboard~=2.20.0->tensorflow) (10.3.0)\n",
+      "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorboard~=2.20.0->tensorflow) (0.7.2)\n",
+      "Requirement already satisfied: werkzeug>=1.0.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tensorboard~=2.20.0->tensorflow) (3.0.3)\n",
+      "Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from astunparse>=1.6.0->tensorflow) (0.43.0)\n",
+      "Requirement already satisfied: rich in c:\\users\\hp\\anaconda3\\lib\\site-packages (from keras>=3.10.0->tensorflow) (13.3.5)\n",
+      "Requirement already satisfied: namex in c:\\users\\hp\\anaconda3\\lib\\site-packages (from keras>=3.10.0->tensorflow) (0.1.0)\n",
+      "Requirement already satisfied: optree in c:\\users\\hp\\anaconda3\\lib\\site-packages (from keras>=3.10.0->tensorflow) (0.17.0)\n",
+      "Requirement already satisfied: MarkupSafe>=2.1.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from werkzeug>=1.0.1->tensorboard~=2.20.0->tensorflow) (2.1.3)\n",
+      "Requirement already satisfied: markdown-it-py<3.0.0,>=2.2.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from rich->keras>=3.10.0->tensorflow) (2.2.0)\n",
+      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from rich->keras>=3.10.0->tensorflow) (2.15.1)\n",
+      "Requirement already satisfied: mdurl~=0.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from markdown-it-py<3.0.0,>=2.2.0->rich->keras>=3.10.0->tensorflow) (0.1.0)\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip install tensorflow"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "BxOrU-i6J0z4",
+    "outputId": "b91c6e1b-3985-4369-9de0-6868ec873464"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\Hp\\anaconda3\\Lib\\site-packages\\keras\\src\\layers\\rnn\\rnn.py:199: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
+      "  super().__init__(**kwargs)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "\u001b[1m65/65\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 66ms/step - loss: 0.0018 - val_loss: 6.9563e-04\n",
+      "Epoch 2/10\n",
+      "\u001b[1m65/65\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 55ms/step - loss: 1.8511e-04 - val_loss: 0.0010\n",
+      "Epoch 3/10\n",
+      "\u001b[1m65/65\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 57ms/step - loss: 1.6209e-04 - val_loss: 8.2369e-04\n",
+      "Epoch 4/10\n",
+      "\u001b[1m65/65\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 56ms/step - loss: 1.8279e-04 - val_loss: 5.5513e-04\n",
+      "Epoch 5/10\n",
+      "\u001b[1m65/65\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 55ms/step - loss: 1.6396e-04 - val_loss: 9.0062e-04\n",
+      "Epoch 6/10\n",
+      "\u001b[1m65/65\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 54ms/step - loss: 1.3207e-04 - val_loss: 4.7759e-04\n",
+      "Epoch 7/10\n",
+      "\u001b[1m65/65\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 53ms/step - loss: 1.2545e-04 - val_loss: 5.0669e-04\n",
+      "Epoch 8/10\n",
+      "\u001b[1m65/65\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 54ms/step - loss: 1.2764e-04 - val_loss: 4.2861e-04\n",
+      "Epoch 9/10\n",
+      "\u001b[1m65/65\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 54ms/step - loss: 1.2959e-04 - val_loss: 4.0455e-04\n",
+      "Epoch 10/10\n",
+      "\u001b[1m65/65\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 53ms/step - loss: 1.4660e-04 - val_loss: 5.4251e-04\n",
+      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 46ms/step\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "import tensorflow as tf\n",
+    "from tensorflow.keras import Sequential\n",
+    "from tensorflow.keras.layers import LSTM, Dense\n",
+    "\n",
+    "# Scale data\n",
+    "scaler = MinMaxScaler()\n",
+    "scaled = scaler.fit_transform(df[['Close']])\n",
+    "\n",
+    "# Create sequences\n",
+    "def create_sequences(df, seq_len=60):\n",
+    "    X, y = [], []\n",
+    "    for i in range(len(df)-seq_len):\n",
+    "        X.append(df[i:i+seq_len])\n",
+    "        y.append(df[i+seq_len])\n",
+    "    return np.array(X), np.array(y)\n",
+    "\n",
+    "seq_len = 60\n",
+    "X, y = create_sequences(scaled, seq_len)\n",
+    "\n",
+    "# Train-test split\n",
+    "split = int(0.8 * len(X))\n",
+    "X_train, X_test = X[:split], X[split:]\n",
+    "y_train, y_test = y[:split], y[split:]\n",
+    "\n",
+    "# LSTM model\n",
+    "model = Sequential([\n",
+    "    LSTM(50, return_sequences=True, input_shape=(seq_len,1)),\n",
+    "    LSTM(50),\n",
+    "    Dense(1)\n",
+    "])\n",
+    "model.compile(optimizer='adam', loss='mse')\n",
+    "model.fit(X_train, y_train, epochs=10, batch_size=32, validation_split=0.1)\n",
+    "\n",
+    "# Forecast\n",
+    "pred = model.predict(X_test)\n",
+    "pred = scaler.inverse_transform(pred)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "sqjLrn3MKbwv"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ARIMA RMSE: 12.955494218221505\n",
+      "ARIMA MAPE: 0.08013550160453459\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from statsmodels.tsa.arima.model import ARIMA\n",
+    "from sklearn.metrics import mean_squared_error\n",
+    "\n",
+    "# ---- Robust metrics (handles NaNs, shape, zeros for MAPE) ----\n",
+    "def safe_metrics(y_true, y_pred, eps=1e-8):\n",
+    "    y_true = np.asarray(y_true, dtype=float).ravel()\n",
+    "    y_pred = np.asarray(y_pred, dtype=float).ravel()\n",
+    "\n",
+    "    # align lengths if off-by-one happened\n",
+    "    n = min(len(y_true), len(y_pred))\n",
+    "    y_true, y_pred = y_true[:n], y_pred[:n]\n",
+    "\n",
+    "    # drop NaNs/Infs\n",
+    "    m = np.isfinite(y_true) & np.isfinite(y_pred)\n",
+    "    y_true, y_pred = y_true[m], y_pred[m]\n",
+    "    if y_true.size == 0:\n",
+    "        return np.nan, np.nan\n",
+    "\n",
+    "    rmse = np.sqrt(mean_squared_error(y_true, y_pred))\n",
+    "    mape = np.mean(np.abs((y_true - y_pred) / np.maximum(np.abs(y_true), eps)))\n",
+    "    return float(rmse), float(mape)\n",
+    "\n",
+    "# ===== Example: proper train/test split and ARIMA forecast =====\n",
+    "if \"Close\" not in df.columns:\n",
+    "    raise ValueError(\"❌ 'Close' column not found.\")\n",
+    "\n",
+    "y = df[\"Close\"].astype(float)\n",
+    "\n",
+    "# Use a fixed-size holdout (e.g., last 60 points)\n",
+    "test_size = 60\n",
+    "train, test = y.iloc[:-test_size], y.iloc[-test_size:]\n",
+    "\n",
+    "# Fit ARIMA on TRAIN only; forecast exactly len(test) steps\n",
+    "model = ARIMA(train, order=(5,1,0), enforce_stationarity=False, enforce_invertibility=False)\n",
+    "res = model.fit(method_kwargs={\"warn_convergence\": False})\n",
+    "\n",
+    "forecast = res.forecast(steps=len(test))      # <-- length matches test\n",
+    "# If you get a pandas Series for both, the indices should be aligned already:\n",
+    "# test.index, forecast.index\n",
+    "\n",
+    "arima_rmse, arima_mape = safe_metrics(test.values, forecast.values)\n",
+    "\n",
+    "print(\"ARIMA RMSE:\", arima_rmse)\n",
+    "print(\"ARIMA MAPE:\", arima_mape)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "id": "5BpmMJkaMf1G"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "LSTM RMSE: 4.381223059835496\n",
+      "LSTM MAPE: 0.022886644352858705\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error\n",
+    "import numpy as np\n",
+    "\n",
+    "# Ensure y_test and pred are aligned and scaled back\n",
+    "# Reshape y_test before inverse scaling\n",
+    "y_test_inv = scaler.inverse_transform(y_test.reshape(-1, 1))\n",
+    "\n",
+    "# Align y_test_inv and pred to have the same number of samples\n",
+    "# Take the last 'len(pred)' elements of y_test_inv\n",
+    "y_test_aligned = y_test_inv[-len(pred):]\n",
+    "\n",
+    "lstm_rmse = np.sqrt(mean_squared_error(y_test_aligned, pred))\n",
+    "lstm_mape = mean_absolute_percentage_error(y_test_aligned, pred)\n",
+    "\n",
+    "print(\"LSTM RMSE:\", lstm_rmse)\n",
+    "print(\"LSTM MAPE:\", lstm_mape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "id": "v3cNcUXsMuJG"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\Hp\\anaconda3\\Lib\\site-packages\\statsmodels\\base\\model.py:607: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n",
+      "  warnings.warn(\"Maximum Likelihood optimization failed to \"\n",
+      "C:\\Users\\Hp\\anaconda3\\Lib\\site-packages\\statsmodels\\base\\model.py:607: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n",
+      "  warnings.warn(\"Maximum Likelihood optimization failed to \"\n",
+      "C:\\Users\\Hp\\anaconda3\\Lib\\site-packages\\statsmodels\\base\\model.py:607: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n",
+      "  warnings.warn(\"Maximum Likelihood optimization failed to \"\n",
+      "C:\\Users\\Hp\\anaconda3\\Lib\\site-packages\\statsmodels\\base\\model.py:607: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n",
+      "  warnings.warn(\"Maximum Likelihood optimization failed to \"\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ARIMA Rolling RMSE: 0.7900705786191281\n",
+      "ARIMA Rolling MAPE: 0.009881837288304923\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from statsmodels.tsa.arima.model import ARIMA\n",
+    "from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error\n",
+    "\n",
+    "def rolling_window_arima(series, window_size=200, forecast_horizon=1):\n",
+    "    errors_rmse, errors_mape = [], []\n",
+    "\n",
+    "    # Ensure input is a numpy array\n",
+    "    series = np.array(series)\n",
+    "\n",
+    "    for i in range(window_size, len(series) - forecast_horizon):\n",
+    "        train = series[i-window_size:i]\n",
+    "        test = series[i:i+forecast_horizon]\n",
+    "\n",
+    "        try:\n",
+    "            model = ARIMA(train, order=(5,1,0))\n",
+    "            model_fit = model.fit()\n",
+    "            forecast = model_fit.forecast(steps=forecast_horizon)\n",
+    "\n",
+    "            rmse = np.sqrt(mean_squared_error(test, forecast))\n",
+    "            mape = mean_absolute_percentage_error(test, forecast)\n",
+    "\n",
+    "            errors_rmse.append(rmse)\n",
+    "            errors_mape.append(mape)\n",
+    "        except Exception as e:\n",
+    "            # Optional: print errors for debugging\n",
+    "            # print(f\"Iteration {i} failed: {e}\")\n",
+    "            continue\n",
+    "\n",
+    "    # Handle case where no errors collected\n",
+    "    if len(errors_rmse) == 0:\n",
+    "        return np.nan, np.nan\n",
+    "\n",
+    "    return np.mean(errors_rmse), np.mean(errors_mape)\n",
+    "\n",
+    "# Example usage\n",
+    "arima_rmse_roll, arima_mape_roll = rolling_window_arima(df['Close'], window_size=200)\n",
+    "print(\"ARIMA Rolling RMSE:\", arima_rmse_roll)\n",
+    "print(\"ARIMA Rolling MAPE:\", arima_mape_roll)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "id": "5rfxUys8nYqw"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Processed window 1/2719\n",
+      "Processed window 20/2719\n",
+      "Processed window 40/2719\n",
+      "Processed window 60/2719\n",
+      "Processed window 80/2719\n",
+      "Processed window 100/2719\n",
+      "Processed window 120/2719\n",
+      "Processed window 140/2719\n",
+      "Processed window 160/2719\n",
+      "Processed window 180/2719\n",
+      "Processed window 200/2719\n",
+      "Processed window 220/2719\n",
+      "Processed window 240/2719\n",
+      "Processed window 260/2719\n",
+      "Processed window 280/2719\n",
+      "Processed window 300/2719\n",
+      "Processed window 320/2719\n",
+      "Processed window 340/2719\n",
+      "Processed window 360/2719\n",
+      "Processed window 380/2719\n",
+      "Processed window 400/2719\n",
+      "Processed window 420/2719\n",
+      "Processed window 440/2719\n",
+      "Processed window 460/2719\n",
+      "Processed window 480/2719\n",
+      "Processed window 500/2719\n",
+      "Processed window 520/2719\n",
+      "Processed window 540/2719\n",
+      "Processed window 560/2719\n",
+      "Processed window 580/2719\n",
+      "Processed window 600/2719\n",
+      "Processed window 620/2719\n",
+      "Processed window 640/2719\n",
+      "Processed window 660/2719\n",
+      "Processed window 680/2719\n",
+      "Processed window 700/2719\n",
+      "Processed window 720/2719\n",
+      "Processed window 740/2719\n",
+      "Processed window 760/2719\n",
+      "Processed window 780/2719\n",
+      "Processed window 800/2719\n",
+      "Processed window 820/2719\n",
+      "Processed window 840/2719\n",
+      "Processed window 860/2719\n",
+      "Processed window 880/2719\n",
+      "Processed window 900/2719\n",
+      "Processed window 920/2719\n",
+      "Processed window 940/2719\n",
+      "Processed window 960/2719\n",
+      "Processed window 980/2719\n",
+      "Processed window 1000/2719\n",
+      "Processed window 1020/2719\n",
+      "Processed window 1040/2719\n",
+      "Processed window 1060/2719\n",
+      "Processed window 1080/2719\n",
+      "Processed window 1100/2719\n",
+      "Processed window 1120/2719\n",
+      "Processed window 1140/2719\n",
+      "Processed window 1160/2719\n",
+      "Processed window 1180/2719\n",
+      "Processed window 1200/2719\n",
+      "Processed window 1220/2719\n",
+      "Processed window 1240/2719\n",
+      "Processed window 1260/2719\n",
+      "Processed window 1280/2719\n",
+      "Processed window 1300/2719\n",
+      "Processed window 1320/2719\n",
+      "Processed window 1340/2719\n",
+      "Processed window 1360/2719\n",
+      "Processed window 1380/2719\n",
+      "Processed window 1400/2719\n",
+      "Processed window 1420/2719\n",
+      "Processed window 1440/2719\n",
+      "Processed window 1460/2719\n",
+      "Processed window 1480/2719\n",
+      "Processed window 1500/2719\n",
+      "Processed window 1520/2719\n",
+      "Processed window 1540/2719\n",
+      "Processed window 1560/2719\n",
+      "Processed window 1580/2719\n",
+      "Processed window 1600/2719\n",
+      "Processed window 1620/2719\n",
+      "Processed window 1640/2719\n",
+      "Processed window 1660/2719\n",
+      "Processed window 1680/2719\n",
+      "Processed window 1700/2719\n",
+      "Processed window 1720/2719\n",
+      "Processed window 1740/2719\n",
+      "Processed window 1760/2719\n",
+      "Processed window 1780/2719\n",
+      "Processed window 1800/2719\n",
+      "Processed window 1820/2719\n",
+      "Processed window 1840/2719\n",
+      "Processed window 1860/2719\n",
+      "Processed window 1880/2719\n",
+      "Processed window 1900/2719\n",
+      "Processed window 1920/2719\n",
+      "Processed window 1940/2719\n",
+      "Processed window 1960/2719\n",
+      "Processed window 1980/2719\n",
+      "Processed window 2000/2719\n",
+      "Processed window 2020/2719\n",
+      "Processed window 2040/2719\n",
+      "Processed window 2060/2719\n",
+      "Processed window 2080/2719\n",
+      "Processed window 2100/2719\n",
+      "Processed window 2120/2719\n",
+      "Processed window 2140/2719\n",
+      "Processed window 2160/2719\n",
+      "Processed window 2180/2719\n",
+      "Processed window 2200/2719\n",
+      "Processed window 2220/2719\n",
+      "Processed window 2240/2719\n",
+      "Processed window 2260/2719\n",
+      "Processed window 2280/2719\n",
+      "Processed window 2300/2719\n",
+      "Processed window 2320/2719\n",
+      "Processed window 2340/2719\n",
+      "Processed window 2360/2719\n",
+      "Processed window 2380/2719\n",
+      "Processed window 2400/2719\n",
+      "Processed window 2420/2719\n",
+      "Processed window 2440/2719\n",
+      "Processed window 2460/2719\n",
+      "Processed window 2480/2719\n",
+      "Processed window 2500/2719\n",
+      "Processed window 2520/2719\n",
+      "Processed window 2540/2719\n",
+      "Processed window 2560/2719\n",
+      "Processed window 2580/2719\n",
+      "Processed window 2600/2719\n",
+      "Processed window 2620/2719\n",
+      "Processed window 2640/2719\n",
+      "Processed window 2660/2719\n",
+      "Processed window 2680/2719\n",
+      "Processed window 2700/2719\n",
+      "Processed window 2719/2719\n",
+      "✅ Rolling LSTM RMSE: 1.9061913541153364\n",
+      "✅ Rolling LSTM MAPE: 0.030438538947571786\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from numpy.lib.stride_tricks import sliding_window_view # Import the function\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "import tensorflow as tf\n",
+    "from tensorflow.keras import Sequential, Input # Also import Input\n",
+    "\n",
+    "# Scale data\n",
+    "# scaler = MinMaxScaler()\n",
+    "# scaled = scaler.fit_transform(data[['Close_AAPL']]) # 'data' might not be available here\n",
+    "\n",
+    "# Create sequences\n",
+    "def _make_seq_xy(arr_2d, seq_len, horizon=1):\n",
+    "    \"\"\"\n",
+    "    arr_2d: shape (N, 1)\n",
+    "    Returns X: (N-seq_len-horizon+1, seq_len, 1), y: (N-seq_len-horizon+1, 1)\n",
+    "    \"\"\"\n",
+    "    if arr_2d.ndim != 2 or arr_2d.shape[1] != 1:\n",
+    "        raise ValueError(\"arr_2d must have shape (N, 1)\")\n",
+    "    if len(arr_2d) <= seq_len + horizon -1: # ensure enough data for at least one sequence and its horizon target\n",
+    "        return np.empty((0, seq_len, 1)), np.empty((0, 1))\n",
+    "\n",
+    "    # X: (N-seq_len+1, seq_len)\n",
+    "    X = sliding_window_view(arr_2d[:, 0], seq_len)\n",
+    "\n",
+    "    # y: (N-seq_len, 1) - target is the value right after the sequence\n",
+    "    y = arr_2d[seq_len:]\n",
+    "\n",
+    "    # Adjust X and y to align for the given horizon\n",
+    "    # We want sequences ending at time t, and targets at time t + horizon\n",
+    "    # So, X should end at N - horizon, and y should start at seq_len + horizon - 1\n",
+    "    if horizon > 0:\n",
+    "        X = X[:-horizon]\n",
+    "        y = y[horizon-1:-horizon+1] # Need to adjust indexing here\n",
+    "\n",
+    "    X = X[..., None] # (N-seq_len-horizon+1, seq_len, 1) -> add channel\n",
+    "\n",
+    "    # Recalculate y to ensure it has the same number of samples as X\n",
+    "    y = arr_2d[seq_len + horizon - 1: len(arr_2d) - (horizon - 1 if horizon > 1 else 0)]\n",
+    "    y = y[:len(X)] # Trim y to match X length in case of remainder\n",
+    "\n",
+    "    return X, y\n",
+    "\n",
+    "\n",
+    "def _make_dataset(X, y, batch_size=64, shuffle=True):\n",
+    "    ds = tf.data.Dataset.from_tensor_slices((X.astype(np.float32), y.astype(np.float32)))\n",
+    "    if shuffle:\n",
+    "        ds = ds.shuffle(min(len(X), 2048), seed=42)\n",
+    "    ds = ds.batch(batch_size).prefetch(tf.data.AUTOTUNE)\n",
+    "    return ds\n",
+    "\n",
+    "def build_lstm(seq_len=60, units=32):\n",
+    "    model = Sequential([\n",
+    "        Input(shape=(seq_len, 1)),\n",
+    "        LSTM(units, return_sequences=True),\n",
+    "        LSTM(units),\n",
+    "        Dense(1)\n",
+    "    ])\n",
+    "    model.compile(optimizer=\"adam\", loss=\"mse\")\n",
+    "    return model\n",
+    "\n",
+    "def rolling_window_lstm_fast(\n",
+    "    data,                    # np.array shape (N,1) or (N,) values\n",
+    "    seq_len=60,\n",
+    "    window_size=200,\n",
+    "    horizon=1,\n",
+    "    base_epochs=5,           # more epochs for the very first window\n",
+    "    update_epochs=1,         # tiny updates for subsequent windows\n",
+    "    train_every=10,          # retrain every k windows instead of every step\n",
+    "    batch_size=64,\n",
+    "    units=32,\n",
+    "    use_global_scaler=True,  # FAST (may leak scale info across time)\n",
+    "    verbose=False\n",
+    "):\n",
+    "    \"\"\"\n",
+    "    Returns: (avg_RMSE, avg_MAPE) over all rolling steps\n",
+    "    Much faster than rebuilding a model per step.\n",
+    "    \"\"\"\n",
+    "\n",
+    "    # Ensure 2D (N,1)\n",
+    "    data = np.asarray(data)\n",
+    "    if data.ndim == 1:\n",
+    "        data = data.reshape(-1, 1)\n",
+    "    if data.shape[1] != 1:\n",
+    "        raise ValueError(\"data must be a single column array of shape (N,1)\")\n",
+    "\n",
+    "    N = len(data)\n",
+    "    if N < window_size + seq_len + horizon:\n",
+    "        raise ValueError(\"Not enough data for the requested window_size/seq_len/horizon.\")\n",
+    "\n",
+    "    # Scaler(s)\n",
+    "    global_scaler = MinMaxScaler()\n",
+    "    if use_global_scaler:\n",
+    "        scaled_all = global_scaler.fit_transform(data)\n",
+    "    else:\n",
+    "        scaled_all = None  # we’ll fit a scaler per window\n",
+    "\n",
+    "    # Model (built once)\n",
+    "    model = build_lstm(seq_len=seq_len, units=units)\n",
+    "\n",
+    "    errors_rmse, errors_mape = [], []\n",
+    "\n",
+    "    total_steps = (N - horizon) - window_size  # number of rolling positions\n",
+    "    # Train on the very first window\n",
+    "    start = window_size\n",
+    "    end = start  # for progress reporting\n",
+    "    subset = data[start - window_size:start]  # (window_size, 1)\n",
+    "\n",
+    "    if use_global_scaler:\n",
+    "        subset_scaled = scaled_all[start - window_size:start]\n",
+    "    else:\n",
+    "        scaler = MinMaxScaler()\n",
+    "        # fit scaler only on the training portion inside the subset to avoid leakage\n",
+    "        fit_end = len(subset) - horizon\n",
+    "        scaler.fit(subset[:fit_end])\n",
+    "        subset_scaled = scaler.transform(subset)\n",
+    "\n",
+    "    X, y = _make_seq_xy(subset_scaled, seq_len, horizon=horizon)\n",
+    "    if len(X) == 0:\n",
+    "        return np.nan, np.nan\n",
+    "\n",
+    "    # Split into train/test for the first window\n",
+    "    X_train, y_train = X[:-horizon], y[:-horizon]\n",
+    "    X_test,  y_test  = X[-horizon:], y[-horizon:]\n",
+    "\n",
+    "    # Train base\n",
+    "    ds_train = _make_dataset(X_train, y_train, batch_size=batch_size, shuffle=True)\n",
+    "    cb = [tf.keras.callbacks.EarlyStopping(monitor=\"loss\", patience=2, min_delta=1e-5, restore_best_weights=True)]\n",
+    "    model.fit(ds_train, epochs=base_epochs, verbose=0, callbacks=cb)\n",
+    "\n",
+    "    # Evaluate first window\n",
+    "    pred = model.predict(X_test, verbose=0)\n",
+    "    # Inverse-transform for metrics\n",
+    "    if use_global_scaler:\n",
+    "        pred_inv = global_scaler.inverse_transform(pred)\n",
+    "        y_inv    = global_scaler.inverse_transform(y_test)\n",
+    "    else:\n",
+    "        scaler.inverse_transform(pred) # Need scaler here\n",
+    "        y_inv = scaler.inverse_transform(y_test)\n",
+    "\n",
+    "    errors_rmse.append(np.sqrt(mean_squared_error(y_inv, pred_inv)))\n",
+    "    errors_mape.append(mean_absolute_percentage_error(y_inv, pred_inv))\n",
+    "\n",
+    "    if verbose:\n",
+    "        print(f\"Processed window 1/{total_steps}\")\n",
+    "\n",
+    "    # Walk forward\n",
+    "    for step, i in enumerate(range(window_size + 1, N - horizon), start=2):\n",
+    "        subset = data[i - window_size:i]\n",
+    "\n",
+    "        if use_global_scaler:\n",
+    "            subset_scaled = scaled_all[i - window_size:i]\n",
+    "        else:\n",
+    "            scaler = MinMaxScaler()\n",
+    "            fit_end = len(subset) - horizon\n",
+    "            scaler.fit(subset[:fit_end])\n",
+    "            subset_scaled = scaler.transform(subset)\n",
+    "\n",
+    "        X, y = _make_seq_xy(subset_scaled, seq_len, horizon=horizon)\n",
+    "        if len(X) == 0:\n",
+    "            continue\n",
+    "\n",
+    "        X_train, y_train = X[:-horizon], y[:-horizon]\n",
+    "        X_test,  y_test  = X[-horizon:], y[-horizon:]\n",
+    "\n",
+    "        # Only retrain every `train_every` steps with tiny epochs (warm start)\n",
+    "        if (step - 1) % train_every == 0:\n",
+    "            ds_train = _make_dataset(X_train, y_train, batch_size=batch_size, shuffle=True)\n",
+    "            model.fit(ds_train, epochs=update_epochs, verbose=0)\n",
+    "\n",
+    "        pred = model.predict(X_test, verbose=0)\n",
+    "\n",
+    "        if use_global_scaler:\n",
+    "            pred_inv = global_scaler.inverse_transform(pred)\n",
+    "            y_inv    = global_scaler.inverse_transform(y_test)\n",
+    "        else:\n",
+    "            # Need scaler here\n",
+    "            pred_inv = scaler.inverse_transform(pred)\n",
+    "            y_inv = scaler.inverse_transform(y_test)\n",
+    "\n",
+    "\n",
+    "        errors_rmse.append(np.sqrt(mean_squared_error(y_inv, pred_inv)))\n",
+    "        errors_mape.append(mean_absolute_percentage_error(y_inv, pred_inv))\n",
+    "\n",
+    "        if verbose and (step % 20 == 0 or step == total_steps):\n",
+    "            print(f\"Processed window {step}/{total_steps}\")\n",
+    "\n",
+    "        if step >= total_steps:\n",
+    "            break\n",
+    "\n",
+    "\n",
+    "    if not errors_rmse:\n",
+    "        return np.nan, np.nan\n",
+    "    return float(np.mean(errors_rmse)), float(np.mean(errors_mape))\n",
+    "\n",
+    "# ===== Example usage (keeps your original interface) =====\n",
+    "if \"Close\" in df.columns:\n",
+    "    lstm_rmse_roll, lstm_mape_roll = rolling_window_lstm_fast(\n",
+    "        df[['Close']].values,\n",
+    "        seq_len=60,\n",
+    "        window_size=200,\n",
+    "        horizon=1,\n",
+    "        base_epochs=5,       # try 3–5 to get a decent base fit\n",
+    "        update_epochs=1,     # keep tiny for speed\n",
+    "        train_every=10,      # retrain every 10 steps (tune for speed vs accuracy)\n",
+    "        batch_size=128,      # bigger batch often faster on GPU\n",
+    "        units=32,            # smaller than 50 for speed\n",
+    "        use_global_scaler=True,  # fastest; set False to avoid scaling leakage\n",
+    "        verbose=True\n",
+    "    )\n",
+    "    print(\"✅ Rolling LSTM RMSE:\", lstm_rmse_roll)\n",
+    "    print(\"✅ Rolling LSTM MAPE:\", lstm_mape_roll)\n",
+    "else:\n",
+    "    print(\"❌ Error: 'Close' column not found in data.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "id": "ia9hsAicy4TW"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   Model     RMSE    MAPE Rolling RMSE Rolling MAPE\n",
+      "0  ARIMA  12.9555  0.0801       0.7913       0.0099\n",
+      "1   LSTM   4.3812  0.0229       1.9062       0.0304\n"
+     ]
+    }
+   ],
+   "source": [
+    "import warnings\n",
+    "warnings.filterwarnings(\"ignore\")  # silence statsmodels convergence warnings\n",
+    "\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error\n",
+    "from statsmodels.tsa.arima.model import ARIMA\n",
+    "\n",
+    "# -----------------------------\n",
+    "# Utility: safe fetch a variable if it exists\n",
+    "# -----------------------------\n",
+    "def _get_if_defined(name, default=np.nan):\n",
+    "    try:\n",
+    "        return eval(name)\n",
+    "    except NameError:\n",
+    "        return default\n",
+    "\n",
+    "# -----------------------------\n",
+    "# Rolling-window ARIMA\n",
+    "# -----------------------------\n",
+    "def rolling_window_arima(series, window_size=200, forecast_horizon=1, order=(5,1,0)):\n",
+    "    \"\"\"\n",
+    "    Walks forward one step at a time.\n",
+    "    For each position: fit ARIMA on the last `window_size` points; forecast `forecast_horizon`.\n",
+    "    Returns mean RMSE/MAPE across all steps (ignores steps that failed to fit).\n",
+    "    \"\"\"\n",
+    "    errors_rmse, errors_mape = [], []\n",
+    "\n",
+    "    series = np.asarray(series, dtype=np.float64).ravel()\n",
+    "    if len(series) < window_size + forecast_horizon:\n",
+    "        return np.nan, np.nan\n",
+    "\n",
+    "    for i in range(window_size, len(series) - forecast_horizon + 1):\n",
+    "        train = series[i-window_size:i]\n",
+    "        test  = series[i:i+forecast_horizon]\n",
+    "        try:\n",
+    "            model = ARIMA(train, order=order, enforce_stationarity=False, enforce_invertibility=False)\n",
+    "            model_fit = model.fit(method_kwargs={\"warn_convergence\": False})\n",
+    "            forecast = model_fit.forecast(steps=forecast_horizon)\n",
+    "            rmse = np.sqrt(mean_squared_error(test, forecast))\n",
+    "            mape = mean_absolute_percentage_error(test, forecast)\n",
+    "            errors_rmse.append(rmse)\n",
+    "            errors_mape.append(mape)\n",
+    "        except Exception:\n",
+    "            # skip windows that fail to converge\n",
+    "            continue\n",
+    "\n",
+    "    if not errors_rmse:\n",
+    "        return np.nan, np.nan\n",
+    "    return float(np.mean(errors_rmse)), float(np.mean(errors_mape))\n",
+    "\n",
+    "# -----------------------------\n",
+    "# Holdout ARIMA (single fit)\n",
+    "# -----------------------------\n",
+    "def holdout_arima(series, test_size=60, order=(5,1,0)):\n",
+    "    \"\"\"\n",
+    "    Fit ARIMA on all but last `test_size` points; forecast next `test_size`.\n",
+    "    Returns RMSE, MAPE on the holdout.\n",
+    "    \"\"\"\n",
+    "    series = np.asarray(series, dtype=np.float64).ravel()\n",
+    "    if len(series) <= test_size + 5:  # need a bit of room to fit\n",
+    "        return np.nan, np.nan\n",
+    "\n",
+    "    train, test = series[:-test_size], series[-test_size:]\n",
+    "    try:\n",
+    "        model = ARIMA(train, order=order, enforce_stationarity=False, enforce_invertibility=False)\n",
+    "        model_fit = model.fit(method_kwargs={\"warn_convergence\": False})\n",
+    "        forecast = model_fit.forecast(steps=len(test))\n",
+    "        rmse = np.sqrt(mean_squared_error(test, forecast))\n",
+    "        mape = mean_absolute_percentage_error(test, forecast)\n",
+    "        return float(rmse), float(mape)\n",
+    "    except Exception:\n",
+    "        return np.nan, np.nan\n",
+    "\n",
+    "# =========================================================\n",
+    "# Compute metrics\n",
+    "# =========================================================\n",
+    "if \"Close\" not in df.columns:\n",
+    "    raise ValueError(\"❌ Error: 'Close' column not found in data.\")\n",
+    "\n",
+    "close_series = df[\"Close\"].astype(float).values\n",
+    "\n",
+    "# ARIMA metrics\n",
+    "arima_rmse, arima_mape = holdout_arima(close_series, test_size=60, order=(5,1,0))\n",
+    "arima_rmse_roll, arima_mape_roll = rolling_window_arima(close_series, window_size=200, forecast_horizon=1, order=(5,1,0))\n",
+    "\n",
+    "# LSTM metrics:\n",
+    "# If you already computed these earlier (e.g., from your LSTM code), they will be picked up.\n",
+    "# Otherwise, they will default to NaN and the table will still render.\n",
+    "lstm_rmse        = _get_if_defined(\"lstm_rmse\",        np.nan)\n",
+    "lstm_mape        = _get_if_defined(\"lstm_mape\",        np.nan)\n",
+    "lstm_rmse_roll   = _get_if_defined(\"lstm_rmse_roll\",   np.nan)\n",
+    "lstm_mape_roll   = _get_if_defined(\"lstm_mape_roll\",   np.nan)\n",
+    "\n",
+    "# =========================================================\n",
+    "# Performance comparison table\n",
+    "# =========================================================\n",
+    "results = {\n",
+    "    \"Model\": [\"ARIMA\", \"LSTM\"],\n",
+    "    \"RMSE\": [arima_rmse, lstm_rmse],\n",
+    "    \"MAPE\": [arima_mape, lstm_mape],\n",
+    "    \"Rolling RMSE\": [arima_rmse_roll, lstm_rmse_roll],\n",
+    "    \"Rolling MAPE\": [arima_mape_roll, lstm_mape_roll],\n",
+    "}\n",
+    "\n",
+    "df_results = pd.DataFrame(results)\n",
+    "\n",
+    "# Optional: nice formatting (4-decimal precision)\n",
+    "df_results_fmt = df_results.copy()\n",
+    "for col in [\"RMSE\", \"MAPE\", \"Rolling RMSE\", \"Rolling MAPE\"]:\n",
+    "    df_results_fmt[col] = df_results_fmt[col].apply(lambda x: f\"{x:.4f}\" if pd.notnull(x) else \"NaN\")\n",
+    "\n",
+    "print(df_results_fmt)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "id": "SUqnlUkYcTcA"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: huggingface_hub in c:\\users\\hp\\anaconda3\\lib\\site-packages (0.35.3)\n",
+      "Requirement already satisfied: filelock in c:\\users\\hp\\anaconda3\\lib\\site-packages (from huggingface_hub) (3.13.1)\n",
+      "Requirement already satisfied: fsspec>=2023.5.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from huggingface_hub) (2024.3.1)\n",
+      "Requirement already satisfied: packaging>=20.9 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from huggingface_hub) (23.2)\n",
+      "Requirement already satisfied: pyyaml>=5.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from huggingface_hub) (6.0.1)\n",
+      "Requirement already satisfied: requests in c:\\users\\hp\\anaconda3\\lib\\site-packages (from huggingface_hub) (2.32.2)\n",
+      "Requirement already satisfied: tqdm>=4.42.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from huggingface_hub) (4.66.4)\n",
+      "Requirement already satisfied: typing-extensions>=3.7.4.3 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from huggingface_hub) (4.15.0)\n",
+      "Requirement already satisfied: colorama in c:\\users\\hp\\anaconda3\\lib\\site-packages (from tqdm>=4.42.1->huggingface_hub) (0.4.6)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests->huggingface_hub) (2.0.4)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests->huggingface_hub) (3.7)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests->huggingface_hub) (2.2.2)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests->huggingface_hub) (2025.1.31)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "93e8b85b39384a07bf68e19f7eba097d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "!pip install -U huggingface_hub\n",
+    "from huggingface_hub import login\n",
+    "login()  # paste the token here\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Env tokens cleared.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "\n",
+    "# Remove the env vars for this Python session\n",
+    "os.environ.pop(\"HF_TOKEN\", None)\n",
+    "os.environ.pop(\"HUGGING_FACE_HUB_TOKEN\", None)\n",
+    "\n",
+    "print(\"Env tokens cleared.\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Logged out (cleared cached token).\n"
+     ]
+    }
+   ],
+   "source": [
+    "from huggingface_hub import logout\n",
+    "logout()  # clears cached token (if any)\n",
+    "print(\"Logged out (cleared cached token).\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3b7eba9ce212438890c7dde7e20d233f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from huggingface_hub import login\n",
+    "\n",
+    "login(token=os.getenv(\"HF_TOKEN\"))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Note: Environment variable`HF_TOKEN` is set and is the current active token independently from the token you've just configured.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "✅ Authenticated as: azima4361\n",
+      "Sample files: []\n",
+      "📦 Repo ready: https://huggingface.co/azima4361/DataSynthis_ML_JobTask\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No files have been modified since last commit. Skipping to prevent empty commit.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "✅ Folder uploaded. Commit: 94fbd6e0c72e4f3fd0d9f10e757d75da73b9f74f\n",
+      "🔗 Open: https://huggingface.co/azima4361/DataSynthis_ML_JobTask\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Robust HF login + folder upload (Windows-safe)\n",
+    "\n",
+    "import os, getpass, sys\n",
+    "from pathlib import Path\n",
+    "from huggingface_hub import HfApi, login\n",
+    "\n",
+    "# --- 0) TOKEN: Use env var if set, else prompt once ---\n",
+    "HF_TOKEN = os.getenv(\"HF_TOKEN\")\n",
+    "if not HF_TOKEN or not HF_TOKEN.startswith(\"hf_\"):\n",
+    "    tok = getpass.getpass(\"Paste your HF token (starts with hf_): \").strip()\n",
+    "    if not tok.startswith(\"hf_\"):\n",
+    "        raise RuntimeError(\"Invalid token format. Get one from https://huggingface.co/settings/tokens (Read+Write).\")\n",
+    "    os.environ[\"HF_TOKEN\"] = tok\n",
+    "    HF_TOKEN = tok\n",
+    "\n",
+    "# --- 1) Log in (doesn't touch git creds) and bind API to token ---\n",
+    "login(token=HF_TOKEN, add_to_git_credential=False)\n",
+    "api = HfApi(token=HF_TOKEN)\n",
+    "\n",
+    "# --- 2) Verify the token actually works; get your username ---\n",
+    "me = api.whoami()            # raises if token invalid/unauthorized\n",
+    "username = me[\"name\"]\n",
+    "print(f\"✅ Authenticated as: {username}\")\n",
+    "\n",
+    "# --- 3) Define the local folder to upload (Windows path!) ---\n",
+    "# Replace this with your real path. Use raw string or Path.\n",
+    "local_folder = Path(r\"E:\\Career\\Data synthis\\DataSynthis_ML_JobTask\")  # <-- EDIT THIS if needed\n",
+    "\n",
+    "if not local_folder.exists() or not local_folder.is_dir():\n",
+    "    raise FileNotFoundError(f\"Folder not found: {local_folder}\")\n",
+    "\n",
+    "# Optional: quick sanity check of contents\n",
+    "some = list(local_folder.rglob(\"*\"))[:5]\n",
+    "print(\"Sample files:\", [str(p) for p in some])\n",
+    "\n",
+    "# --- 4) Choose your repo. Prefer your own namespace unless you have rights elsewhere ---\n",
+    "repo_name = \"DataSynthis_ML_JobTask\"\n",
+    "repo_id   = f\"{username}/{repo_name}\"          # safer than hardcoding someone else's handle\n",
+    "\n",
+    "# NOTE: If this should be a dataset instead, set repo_type=\"dataset\".\n",
+    "repo_type = \"model\"\n",
+    "\n",
+    "# --- 5) Create repo if missing (idempotent) ---\n",
+    "api.create_repo(repo_id=repo_id, repo_type=repo_type, exist_ok=True)\n",
+    "print(f\"📦 Repo ready: https://huggingface.co/{repo_id}\")\n",
+    "\n",
+    "# --- 6) Upload the folder ---\n",
+    "# You can ignore patterns to skip junk files or huge artifacts if needed.\n",
+    "res = api.upload_folder(\n",
+    "    folder_path=str(local_folder),\n",
+    "    repo_id=repo_id,\n",
+    "    repo_type=repo_type,\n",
+    "    path_in_repo=\"\",  # optional subdir inside the repo\n",
+    "    # ignore_patterns=[\"*.tmp\",\"*.log\",\"__pycache__/*\",\".ipynb_checkpoints/*\"],\n",
+    ")\n",
+    "print(\"✅ Folder uploaded. Commit:\", getattr(res, \"oid\", res))\n",
+    "print(f\"🔗 Open: https://huggingface.co/{repo_id}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No files have been modified since last commit. Skipping to prevent empty commit.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "CommitInfo(commit_url='https://huggingface.co/azima4361/DataSynthis_ML_JobTask/commit/94fbd6e0c72e4f3fd0d9f10e757d75da73b9f74f', commit_message='Upload folder using huggingface_hub', commit_description='', oid='94fbd6e0c72e4f3fd0d9f10e757d75da73b9f74f', pr_url=None, repo_url=RepoUrl('https://huggingface.co/azima4361/DataSynthis_ML_JobTask', endpoint='https://huggingface.co', repo_type='model', repo_id='azima4361/DataSynthis_ML_JobTask'), pr_revision=None, pr_num=None)"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from huggingface_hub import HfApi\n",
+    "\n",
+    "api = HfApi(token=os.getenv(\"HF_TOKEN\"))\n",
+    "api.upload_folder(\n",
+    "    folder_path=\"/Career/Data synthis/DataSynthis_ML_JobTask\",\n",
+    "    repo_id=\"azima4361/DataSynthis_ML_JobTask\",\n",
+    "    repo_type=\"model\",\n",
+    ")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}