RNNs_for_Algorithmic_Trading.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "81f5a3f5",
   "metadata": {},
   "source": [
    "Link for blogpost : https://medium.com/@patelsaadn/rnns-for-algorithmic-trading-simplified-theory-and-python-implementation-6292055ba770"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "T9m-qjyauaJN",
   "metadata": {
    "id": "T9m-qjyauaJN"
   },
   "outputs": [],
   "source": [
    "#Importing Python Modules/Packages\n",
    "\n",
    "import os\n",
    "from pathlib import Path\n",
    "from math import *\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import pandas_datareader.data as web\n",
    "from datetime import datetime, timedelta\n",
    "import statsmodels.api as sm\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas_datareader as pdr\n",
    "import seaborn as sns\n",
    "\n",
    "from scipy.stats import spearmanr, norm\n",
    "from sklearn.metrics import mean_squared_error\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "import scipy\n",
    "\n",
    "\n",
    "import tensorflow as tf\n",
    "from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Dense, LSTM\n",
    "from tensorflow import keras\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "63t89LggIXyW",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "63t89LggIXyW",
    "outputId": "ec0f1e19-74a5-4212-9655-075ddba401c1"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
     ]
    }
   ],
   "source": [
    "from google.colab import drive\n",
    "drive.mount('/content/drive')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "9cc2cd29",
   "metadata": {
    "id": "9cc2cd29"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "TuOp7lRwJYFr",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "TuOp7lRwJYFr",
    "outputId": "07623e78-8cdf-40e6-a1b4-c7bc1a4868ca"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using GPU\n"
     ]
    }
   ],
   "source": [
    "gpu_devices = tf.config.experimental.list_physical_devices('GPU')\n",
    "if gpu_devices:\n",
    "    print('Using GPU')\n",
    "    tf.config.experimental.set_memory_growth(gpu_devices[0], True)\n",
    "else:\n",
    "    print('Using CPU')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "rPwIYNNJv3tR",
   "metadata": {
    "id": "rPwIYNNJv3tR"
   },
   "outputs": [],
   "source": [
    "# results_path = Path('/content/drive/MyDrive/HFT/data/results', 'univariate_time_series')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "cPALdnfNJYIb",
   "metadata": {
    "id": "cPALdnfNJYIb"
   },
   "outputs": [],
   "source": [
    "sns.set_style('whitegrid')\n",
    "np.random.seed(42)\n",
    "\n",
    "results_path = Path('/content/drive/MyDrive/HFT/data/results', 'univariate_time_series')\n",
    "if not results_path.exists():\n",
    "    results_path.mkdir(parents=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "aQ6rP3UGJYLT",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 481
    },
    "id": "aQ6rP3UGJYLT",
    "outputId": "5629cbdc-957f-4a1d-fba6-2b5db7360873"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "snp500 = web.DataReader('SP500', 'fred', start='2013', end='2024').dropna()\n",
    "ax = snp500.plot(title='S&P 500 Index Fund', figsize=(20, 8), c='b')\n",
    "ax.set_xlabel('Time')\n",
    "ax.set_ylabel('Price $')\n",
    "sns.despine()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "oriemd2fyTM2",
   "metadata": {
    "id": "oriemd2fyTM2"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "M8AwYFHNKtbe",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "M8AwYFHNKtbe",
    "outputId": "52a0ba2a-0c39-4145-c00a-4257b743e304"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    2519.000000\n",
       "mean        0.386143\n",
       "std         0.267904\n",
       "min         0.000000\n",
       "25%         0.161892\n",
       "50%         0.340853\n",
       "75%         0.567245\n",
       "max         1.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "snp500.head()\n",
    "\n",
    "scaler = MinMaxScaler() # The default scale for the MinMaxScaler is to rescale variables into the range [0,1]\n",
    "sp500_scaled = pd.Series(scaler.fit_transform(snp500).squeeze(), index=snp500.index) # transform(X) will Scale features of X according to feature_range.\n",
    "\n",
    "sp500_scaled.describe()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "poeQyXq6LAOd",
   "metadata": {
    "id": "poeQyXq6LAOd"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "BPmR_ogcLBbC",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "BPmR_ogcLBbC",
    "outputId": "bca03c91-d492-4a8b-aac2-8aeb21b5d09e"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    2519.000000\n",
       "mean        0.386143\n",
       "std         0.267904\n",
       "min         0.000000\n",
       "25%         0.161892\n",
       "50%         0.340853\n",
       "75%         0.567245\n",
       "max         1.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sp500_scaled.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "n2wFgmPjnNox",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "n2wFgmPjnNox",
    "outputId": "80737234-258e-4d9c-f428-0585541bf25c"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2519,)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sp500_scaled.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "05I3F8gkkYoH",
   "metadata": {
    "id": "05I3F8gkkYoH"
   },
   "outputs": [],
   "source": [
    "def data_for_rnn(data, window_size):\n",
    "    n = len(data)\n",
    "    y = data[window_size:]\n",
    "    print(\"previous data shape\", data.shape)\n",
    "    data = data.values.reshape(-1, 1) # make 2D\n",
    "    print(\"updated data shape\", data.shape)\n",
    "    X = np.hstack(tuple([data[i: n-j, :] for i, j in enumerate(range(window_size, 0, -1))]))\n",
    "    print(X.shape, y.shape)\n",
    "    return pd.DataFrame(X, index=y.index), y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "dbtBWSkclazE",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "dbtBWSkclazE",
    "outputId": "257ec90f-9bb8-4676-ade5-f693608e0b72"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "previous data shape (2519,)\n",
      "updated data shape (2519, 1)\n",
      "(2469, 50) (2469,)\n"
     ]
    }
   ],
   "source": [
    "window_size = 50\n",
    "X, y = data_for_rnn(sp500_scaled, window_size=window_size)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "C1Jnr3C9n48T",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "C1Jnr3C9n48T",
    "outputId": "d5a489d2-2de4-4618-928b-885ceef41f88"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DATE\n",
       "2013-03-25    0.003097\n",
       "2013-03-26    0.006808\n",
       "2013-03-27    0.006525\n",
       "2013-03-28    0.008473\n",
       "2013-04-01    0.006317\n",
       "2013-04-02    0.008799\n",
       "2013-04-03    0.003711\n",
       "2013-04-04    0.005644\n",
       "2013-04-05    0.003585\n",
       "2013-04-08    0.006593\n",
       "dtype: float64"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sp500_scaled.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "mWf4I9Hwla1q",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 693
    },
    "id": "mWf4I9Hwla1q",
    "outputId": "c711c894-e867-4220-cd98-5143e5e100a1"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "  <div id=\"df-9c893750-abc7-4c11-9dee-2a666fc8c279\">\n",
       "    <div class=\"colab-df-container\">\n",
       "      <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>40</th>\n",
       "      <th>41</th>\n",
       "      <th>42</th>\n",
       "      <th>43</th>\n",
       "      <th>44</th>\n",
       "      <th>45</th>\n",
       "      <th>46</th>\n",
       "      <th>47</th>\n",
       "      <th>48</th>\n",
       "      <th>49</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DATE</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2013-06-05</th>\n",
       "      <td>0.003097</td>\n",
       "      <td>0.006808</td>\n",
       "      <td>0.006525</td>\n",
       "      <td>0.008473</td>\n",
       "      <td>0.006317</td>\n",
       "      <td>0.008799</td>\n",
       "      <td>0.003711</td>\n",
       "      <td>0.005644</td>\n",
       "      <td>0.003585</td>\n",
       "      <td>0.006593</td>\n",
       "      <td>...</td>\n",
       "      <td>0.039186</td>\n",
       "      <td>0.034944</td>\n",
       "      <td>0.033457</td>\n",
       "      <td>0.033177</td>\n",
       "      <td>0.036391</td>\n",
       "      <td>0.032796</td>\n",
       "      <td>0.034655</td>\n",
       "      <td>0.027383</td>\n",
       "      <td>0.030357</td>\n",
       "      <td>0.027580</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013-06-06</th>\n",
       "      <td>0.006808</td>\n",
       "      <td>0.006525</td>\n",
       "      <td>0.008473</td>\n",
       "      <td>0.006317</td>\n",
       "      <td>0.008799</td>\n",
       "      <td>0.003711</td>\n",
       "      <td>0.005644</td>\n",
       "      <td>0.003585</td>\n",
       "      <td>0.006593</td>\n",
       "      <td>0.008295</td>\n",
       "      <td>...</td>\n",
       "      <td>0.034944</td>\n",
       "      <td>0.033457</td>\n",
       "      <td>0.033177</td>\n",
       "      <td>0.036391</td>\n",
       "      <td>0.032796</td>\n",
       "      <td>0.034655</td>\n",
       "      <td>0.027383</td>\n",
       "      <td>0.030357</td>\n",
       "      <td>0.027580</td>\n",
       "      <td>0.020673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013-06-07</th>\n",
       "      <td>0.006525</td>\n",
       "      <td>0.008473</td>\n",
       "      <td>0.006317</td>\n",
       "      <td>0.008799</td>\n",
       "      <td>0.003711</td>\n",
       "      <td>0.005644</td>\n",
       "      <td>0.003585</td>\n",
       "      <td>0.006593</td>\n",
       "      <td>0.008295</td>\n",
       "      <td>0.014169</td>\n",
       "      <td>...</td>\n",
       "      <td>0.033457</td>\n",
       "      <td>0.033177</td>\n",
       "      <td>0.036391</td>\n",
       "      <td>0.032796</td>\n",
       "      <td>0.034655</td>\n",
       "      <td>0.027383</td>\n",
       "      <td>0.030357</td>\n",
       "      <td>0.027580</td>\n",
       "      <td>0.020673</td>\n",
       "      <td>0.024870</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013-06-10</th>\n",
       "      <td>0.008473</td>\n",
       "      <td>0.006317</td>\n",
       "      <td>0.008799</td>\n",
       "      <td>0.003711</td>\n",
       "      <td>0.005644</td>\n",
       "      <td>0.003585</td>\n",
       "      <td>0.006593</td>\n",
       "      <td>0.008295</td>\n",
       "      <td>0.014169</td>\n",
       "      <td>0.015902</td>\n",
       "      <td>...</td>\n",
       "      <td>0.033177</td>\n",
       "      <td>0.036391</td>\n",
       "      <td>0.032796</td>\n",
       "      <td>0.034655</td>\n",
       "      <td>0.027383</td>\n",
       "      <td>0.030357</td>\n",
       "      <td>0.027580</td>\n",
       "      <td>0.020673</td>\n",
       "      <td>0.024870</td>\n",
       "      <td>0.031266</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013-06-11</th>\n",
       "      <td>0.006317</td>\n",
       "      <td>0.008799</td>\n",
       "      <td>0.003711</td>\n",
       "      <td>0.005644</td>\n",
       "      <td>0.003585</td>\n",
       "      <td>0.006593</td>\n",
       "      <td>0.008295</td>\n",
       "      <td>0.014169</td>\n",
       "      <td>0.015902</td>\n",
       "      <td>0.014513</td>\n",
       "      <td>...</td>\n",
       "      <td>0.036391</td>\n",
       "      <td>0.032796</td>\n",
       "      <td>0.034655</td>\n",
       "      <td>0.027383</td>\n",
       "      <td>0.030357</td>\n",
       "      <td>0.027580</td>\n",
       "      <td>0.020673</td>\n",
       "      <td>0.024870</td>\n",
       "      <td>0.031266</td>\n",
       "      <td>0.031091</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023-03-20</th>\n",
       "      <td>0.696321</td>\n",
       "      <td>0.723043</td>\n",
       "      <td>0.722125</td>\n",
       "      <td>0.730469</td>\n",
       "      <td>0.745941</td>\n",
       "      <td>0.750107</td>\n",
       "      <td>0.754998</td>\n",
       "      <td>0.752503</td>\n",
       "      <td>0.733421</td>\n",
       "      <td>0.724202</td>\n",
       "      <td>...</td>\n",
       "      <td>0.770153</td>\n",
       "      <td>0.751090</td>\n",
       "      <td>0.752823</td>\n",
       "      <td>0.730183</td>\n",
       "      <td>0.712754</td>\n",
       "      <td>0.710963</td>\n",
       "      <td>0.730481</td>\n",
       "      <td>0.722076</td>\n",
       "      <td>0.743074</td>\n",
       "      <td>0.729667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023-03-21</th>\n",
       "      <td>0.723043</td>\n",
       "      <td>0.722125</td>\n",
       "      <td>0.730469</td>\n",
       "      <td>0.745941</td>\n",
       "      <td>0.750107</td>\n",
       "      <td>0.754998</td>\n",
       "      <td>0.752503</td>\n",
       "      <td>0.733421</td>\n",
       "      <td>0.724202</td>\n",
       "      <td>0.746862</td>\n",
       "      <td>...</td>\n",
       "      <td>0.751090</td>\n",
       "      <td>0.752823</td>\n",
       "      <td>0.730183</td>\n",
       "      <td>0.712754</td>\n",
       "      <td>0.710963</td>\n",
       "      <td>0.730481</td>\n",
       "      <td>0.722076</td>\n",
       "      <td>0.743074</td>\n",
       "      <td>0.729667</td>\n",
       "      <td>0.740398</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023-03-22</th>\n",
       "      <td>0.722125</td>\n",
       "      <td>0.730469</td>\n",
       "      <td>0.745941</td>\n",
       "      <td>0.750107</td>\n",
       "      <td>0.754998</td>\n",
       "      <td>0.752503</td>\n",
       "      <td>0.733421</td>\n",
       "      <td>0.724202</td>\n",
       "      <td>0.746862</td>\n",
       "      <td>0.761363</td>\n",
       "      <td>...</td>\n",
       "      <td>0.752823</td>\n",
       "      <td>0.730183</td>\n",
       "      <td>0.712754</td>\n",
       "      <td>0.710963</td>\n",
       "      <td>0.730481</td>\n",
       "      <td>0.722076</td>\n",
       "      <td>0.743074</td>\n",
       "      <td>0.729667</td>\n",
       "      <td>0.740398</td>\n",
       "      <td>0.756159</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023-03-23</th>\n",
       "      <td>0.730469</td>\n",
       "      <td>0.745941</td>\n",
       "      <td>0.750107</td>\n",
       "      <td>0.754998</td>\n",
       "      <td>0.752503</td>\n",
       "      <td>0.733421</td>\n",
       "      <td>0.724202</td>\n",
       "      <td>0.746862</td>\n",
       "      <td>0.761363</td>\n",
       "      <td>0.760485</td>\n",
       "      <td>...</td>\n",
       "      <td>0.730183</td>\n",
       "      <td>0.712754</td>\n",
       "      <td>0.710963</td>\n",
       "      <td>0.730481</td>\n",
       "      <td>0.722076</td>\n",
       "      <td>0.743074</td>\n",
       "      <td>0.729667</td>\n",
       "      <td>0.740398</td>\n",
       "      <td>0.756159</td>\n",
       "      <td>0.735913</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023-03-24</th>\n",
       "      <td>0.745941</td>\n",
       "      <td>0.750107</td>\n",
       "      <td>0.754998</td>\n",
       "      <td>0.752503</td>\n",
       "      <td>0.733421</td>\n",
       "      <td>0.724202</td>\n",
       "      <td>0.746862</td>\n",
       "      <td>0.761363</td>\n",
       "      <td>0.760485</td>\n",
       "      <td>0.760261</td>\n",
       "      <td>...</td>\n",
       "      <td>0.712754</td>\n",
       "      <td>0.710963</td>\n",
       "      <td>0.730481</td>\n",
       "      <td>0.722076</td>\n",
       "      <td>0.743074</td>\n",
       "      <td>0.729667</td>\n",
       "      <td>0.740398</td>\n",
       "      <td>0.756159</td>\n",
       "      <td>0.735913</td>\n",
       "      <td>0.739523</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2469 rows × 50 columns</p>\n",
       "</div>\n",
       "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9c893750-abc7-4c11-9dee-2a666fc8c279')\"\n",
       "              title=\"Convert this dataframe to an interactive table.\"\n",
       "              style=\"display:none;\">\n",
       "        \n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "       width=\"24px\">\n",
       "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
       "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
       "  </svg>\n",
       "      </button>\n",
       "      \n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      flex-wrap:wrap;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "      <script>\n",
       "        const buttonEl =\n",
       "          document.querySelector('#df-9c893750-abc7-4c11-9dee-2a666fc8c279 button.colab-df-convert');\n",
       "        buttonEl.style.display =\n",
       "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "        async function convertToInteractive(key) {\n",
       "          const element = document.querySelector('#df-9c893750-abc7-4c11-9dee-2a666fc8c279');\n",
       "          const dataTable =\n",
       "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                     [key], {});\n",
       "          if (!dataTable) return;\n",
       "\n",
       "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "            + ' to learn more about interactive tables.';\n",
       "          element.innerHTML = '';\n",
       "          dataTable['output_type'] = 'display_data';\n",
       "          await google.colab.output.renderOutput(dataTable, element);\n",
       "          const docLink = document.createElement('div');\n",
       "          docLink.innerHTML = docLinkHtml;\n",
       "          element.appendChild(docLink);\n",
       "        }\n",
       "      </script>\n",
       "    </div>\n",
       "  </div>\n",
       "  "
      ],
      "text/plain": [
       "                  0         1         2         3         4         5   \\\n",
       "DATE                                                                     \n",
       "2013-06-05  0.003097  0.006808  0.006525  0.008473  0.006317  0.008799   \n",
       "2013-06-06  0.006808  0.006525  0.008473  0.006317  0.008799  0.003711   \n",
       "2013-06-07  0.006525  0.008473  0.006317  0.008799  0.003711  0.005644   \n",
       "2013-06-10  0.008473  0.006317  0.008799  0.003711  0.005644  0.003585   \n",
       "2013-06-11  0.006317  0.008799  0.003711  0.005644  0.003585  0.006593   \n",
       "...              ...       ...       ...       ...       ...       ...   \n",
       "2023-03-20  0.696321  0.723043  0.722125  0.730469  0.745941  0.750107   \n",
       "2023-03-21  0.723043  0.722125  0.730469  0.745941  0.750107  0.754998   \n",
       "2023-03-22  0.722125  0.730469  0.745941  0.750107  0.754998  0.752503   \n",
       "2023-03-23  0.730469  0.745941  0.750107  0.754998  0.752503  0.733421   \n",
       "2023-03-24  0.745941  0.750107  0.754998  0.752503  0.733421  0.724202   \n",
       "\n",
       "                  6         7         8         9   ...        40        41  \\\n",
       "DATE                                                ...                       \n",
       "2013-06-05  0.003711  0.005644  0.003585  0.006593  ...  0.039186  0.034944   \n",
       "2013-06-06  0.005644  0.003585  0.006593  0.008295  ...  0.034944  0.033457   \n",
       "2013-06-07  0.003585  0.006593  0.008295  0.014169  ...  0.033457  0.033177   \n",
       "2013-06-10  0.006593  0.008295  0.014169  0.015902  ...  0.033177  0.036391   \n",
       "2013-06-11  0.008295  0.014169  0.015902  0.014513  ...  0.036391  0.032796   \n",
       "...              ...       ...       ...       ...  ...       ...       ...   \n",
       "2023-03-20  0.754998  0.752503  0.733421  0.724202  ...  0.770153  0.751090   \n",
       "2023-03-21  0.752503  0.733421  0.724202  0.746862  ...  0.751090  0.752823   \n",
       "2023-03-22  0.733421  0.724202  0.746862  0.761363  ...  0.752823  0.730183   \n",
       "2023-03-23  0.724202  0.746862  0.761363  0.760485  ...  0.730183  0.712754   \n",
       "2023-03-24  0.746862  0.761363  0.760485  0.760261  ...  0.712754  0.710963   \n",
       "\n",
       "                  42        43        44        45        46        47  \\\n",
       "DATE                                                                     \n",
       "2013-06-05  0.033457  0.033177  0.036391  0.032796  0.034655  0.027383   \n",
       "2013-06-06  0.033177  0.036391  0.032796  0.034655  0.027383  0.030357   \n",
       "2013-06-07  0.036391  0.032796  0.034655  0.027383  0.030357  0.027580   \n",
       "2013-06-10  0.032796  0.034655  0.027383  0.030357  0.027580  0.020673   \n",
       "2013-06-11  0.034655  0.027383  0.030357  0.027580  0.020673  0.024870   \n",
       "...              ...       ...       ...       ...       ...       ...   \n",
       "2023-03-20  0.752823  0.730183  0.712754  0.710963  0.730481  0.722076   \n",
       "2023-03-21  0.730183  0.712754  0.710963  0.730481  0.722076  0.743074   \n",
       "2023-03-22  0.712754  0.710963  0.730481  0.722076  0.743074  0.729667   \n",
       "2023-03-23  0.710963  0.730481  0.722076  0.743074  0.729667  0.740398   \n",
       "2023-03-24  0.730481  0.722076  0.743074  0.729667  0.740398  0.756159   \n",
       "\n",
       "                  48        49  \n",
       "DATE                            \n",
       "2013-06-05  0.030357  0.027580  \n",
       "2013-06-06  0.027580  0.020673  \n",
       "2013-06-07  0.020673  0.024870  \n",
       "2013-06-10  0.024870  0.031266  \n",
       "2013-06-11  0.031266  0.031091  \n",
       "...              ...       ...  \n",
       "2023-03-20  0.743074  0.729667  \n",
       "2023-03-21  0.729667  0.740398  \n",
       "2023-03-22  0.740398  0.756159  \n",
       "2023-03-23  0.756159  0.735913  \n",
       "2023-03-24  0.735913  0.739523  \n",
       "\n",
       "[2469 rows x 50 columns]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "Ztnkw4_6la4M",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "Ztnkw4_6la4M",
    "outputId": "309751ef-a22e-420f-a2df-834db0e720f6"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DATE\n",
       "2013-06-05    0.020673\n",
       "2013-06-06    0.024870\n",
       "2013-06-07    0.031266\n",
       "2013-06-10    0.031091\n",
       "2013-06-11    0.025967\n",
       "dtype: float64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "xKABdTtsla7B",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 693
    },
    "id": "xKABdTtsla7B",
    "outputId": "816a5414-ff26-4d50-af51-d8c1f59e53b6"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "  <div id=\"df-a424af3a-9235-45c8-af19-7acf16ae2d86\">\n",
       "    <div class=\"colab-df-container\">\n",
       "      <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>40</th>\n",
       "      <th>41</th>\n",
       "      <th>42</th>\n",
       "      <th>43</th>\n",
       "      <th>44</th>\n",
       "      <th>45</th>\n",
       "      <th>46</th>\n",
       "      <th>47</th>\n",
       "      <th>48</th>\n",
       "      <th>49</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DATE</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2013-06-05</th>\n",
       "      <td>0.003097</td>\n",
       "      <td>0.006808</td>\n",
       "      <td>0.006525</td>\n",
       "      <td>0.008473</td>\n",
       "      <td>0.006317</td>\n",
       "      <td>0.008799</td>\n",
       "      <td>0.003711</td>\n",
       "      <td>0.005644</td>\n",
       "      <td>0.003585</td>\n",
       "      <td>0.006593</td>\n",
       "      <td>...</td>\n",
       "      <td>0.039186</td>\n",
       "      <td>0.034944</td>\n",
       "      <td>0.033457</td>\n",
       "      <td>0.033177</td>\n",
       "      <td>0.036391</td>\n",
       "      <td>0.032796</td>\n",
       "      <td>0.034655</td>\n",
       "      <td>0.027383</td>\n",
       "      <td>0.030357</td>\n",
       "      <td>0.027580</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013-06-06</th>\n",
       "      <td>0.006808</td>\n",
       "      <td>0.006525</td>\n",
       "      <td>0.008473</td>\n",
       "      <td>0.006317</td>\n",
       "      <td>0.008799</td>\n",
       "      <td>0.003711</td>\n",
       "      <td>0.005644</td>\n",
       "      <td>0.003585</td>\n",
       "      <td>0.006593</td>\n",
       "      <td>0.008295</td>\n",
       "      <td>...</td>\n",
       "      <td>0.034944</td>\n",
       "      <td>0.033457</td>\n",
       "      <td>0.033177</td>\n",
       "      <td>0.036391</td>\n",
       "      <td>0.032796</td>\n",
       "      <td>0.034655</td>\n",
       "      <td>0.027383</td>\n",
       "      <td>0.030357</td>\n",
       "      <td>0.027580</td>\n",
       "      <td>0.020673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013-06-07</th>\n",
       "      <td>0.006525</td>\n",
       "      <td>0.008473</td>\n",
       "      <td>0.006317</td>\n",
       "      <td>0.008799</td>\n",
       "      <td>0.003711</td>\n",
       "      <td>0.005644</td>\n",
       "      <td>0.003585</td>\n",
       "      <td>0.006593</td>\n",
       "      <td>0.008295</td>\n",
       "      <td>0.014169</td>\n",
       "      <td>...</td>\n",
       "      <td>0.033457</td>\n",
       "      <td>0.033177</td>\n",
       "      <td>0.036391</td>\n",
       "      <td>0.032796</td>\n",
       "      <td>0.034655</td>\n",
       "      <td>0.027383</td>\n",
       "      <td>0.030357</td>\n",
       "      <td>0.027580</td>\n",
       "      <td>0.020673</td>\n",
       "      <td>0.024870</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013-06-10</th>\n",
       "      <td>0.008473</td>\n",
       "      <td>0.006317</td>\n",
       "      <td>0.008799</td>\n",
       "      <td>0.003711</td>\n",
       "      <td>0.005644</td>\n",
       "      <td>0.003585</td>\n",
       "      <td>0.006593</td>\n",
       "      <td>0.008295</td>\n",
       "      <td>0.014169</td>\n",
       "      <td>0.015902</td>\n",
       "      <td>...</td>\n",
       "      <td>0.033177</td>\n",
       "      <td>0.036391</td>\n",
       "      <td>0.032796</td>\n",
       "      <td>0.034655</td>\n",
       "      <td>0.027383</td>\n",
       "      <td>0.030357</td>\n",
       "      <td>0.027580</td>\n",
       "      <td>0.020673</td>\n",
       "      <td>0.024870</td>\n",
       "      <td>0.031266</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013-06-11</th>\n",
       "      <td>0.006317</td>\n",
       "      <td>0.008799</td>\n",
       "      <td>0.003711</td>\n",
       "      <td>0.005644</td>\n",
       "      <td>0.003585</td>\n",
       "      <td>0.006593</td>\n",
       "      <td>0.008295</td>\n",
       "      <td>0.014169</td>\n",
       "      <td>0.015902</td>\n",
       "      <td>0.014513</td>\n",
       "      <td>...</td>\n",
       "      <td>0.036391</td>\n",
       "      <td>0.032796</td>\n",
       "      <td>0.034655</td>\n",
       "      <td>0.027383</td>\n",
       "      <td>0.030357</td>\n",
       "      <td>0.027580</td>\n",
       "      <td>0.020673</td>\n",
       "      <td>0.024870</td>\n",
       "      <td>0.031266</td>\n",
       "      <td>0.031091</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-12-24</th>\n",
       "      <td>0.364602</td>\n",
       "      <td>0.376510</td>\n",
       "      <td>0.371490</td>\n",
       "      <td>0.389656</td>\n",
       "      <td>0.389438</td>\n",
       "      <td>0.377017</td>\n",
       "      <td>0.376709</td>\n",
       "      <td>0.373053</td>\n",
       "      <td>0.368387</td>\n",
       "      <td>0.342399</td>\n",
       "      <td>...</td>\n",
       "      <td>0.336752</td>\n",
       "      <td>0.336463</td>\n",
       "      <td>0.340853</td>\n",
       "      <td>0.340690</td>\n",
       "      <td>0.325148</td>\n",
       "      <td>0.308555</td>\n",
       "      <td>0.308622</td>\n",
       "      <td>0.296579</td>\n",
       "      <td>0.284431</td>\n",
       "      <td>0.268824</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-12-26</th>\n",
       "      <td>0.376510</td>\n",
       "      <td>0.371490</td>\n",
       "      <td>0.389656</td>\n",
       "      <td>0.389438</td>\n",
       "      <td>0.377017</td>\n",
       "      <td>0.376709</td>\n",
       "      <td>0.373053</td>\n",
       "      <td>0.368387</td>\n",
       "      <td>0.342399</td>\n",
       "      <td>0.357597</td>\n",
       "      <td>...</td>\n",
       "      <td>0.336463</td>\n",
       "      <td>0.340853</td>\n",
       "      <td>0.340690</td>\n",
       "      <td>0.325148</td>\n",
       "      <td>0.308555</td>\n",
       "      <td>0.308622</td>\n",
       "      <td>0.296579</td>\n",
       "      <td>0.284431</td>\n",
       "      <td>0.268824</td>\n",
       "      <td>0.248695</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-12-27</th>\n",
       "      <td>0.371490</td>\n",
       "      <td>0.389656</td>\n",
       "      <td>0.389438</td>\n",
       "      <td>0.377017</td>\n",
       "      <td>0.376709</td>\n",
       "      <td>0.373053</td>\n",
       "      <td>0.368387</td>\n",
       "      <td>0.342399</td>\n",
       "      <td>0.357597</td>\n",
       "      <td>0.343194</td>\n",
       "      <td>...</td>\n",
       "      <td>0.340853</td>\n",
       "      <td>0.340690</td>\n",
       "      <td>0.325148</td>\n",
       "      <td>0.308555</td>\n",
       "      <td>0.308622</td>\n",
       "      <td>0.296579</td>\n",
       "      <td>0.284431</td>\n",
       "      <td>0.268824</td>\n",
       "      <td>0.248695</td>\n",
       "      <td>0.284517</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-12-28</th>\n",
       "      <td>0.389656</td>\n",
       "      <td>0.389438</td>\n",
       "      <td>0.377017</td>\n",
       "      <td>0.376709</td>\n",
       "      <td>0.373053</td>\n",
       "      <td>0.368387</td>\n",
       "      <td>0.342399</td>\n",
       "      <td>0.357597</td>\n",
       "      <td>0.343194</td>\n",
       "      <td>0.337836</td>\n",
       "      <td>...</td>\n",
       "      <td>0.340690</td>\n",
       "      <td>0.325148</td>\n",
       "      <td>0.308555</td>\n",
       "      <td>0.308622</td>\n",
       "      <td>0.296579</td>\n",
       "      <td>0.284431</td>\n",
       "      <td>0.268824</td>\n",
       "      <td>0.248695</td>\n",
       "      <td>0.284517</td>\n",
       "      <td>0.291009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-12-31</th>\n",
       "      <td>0.389438</td>\n",
       "      <td>0.377017</td>\n",
       "      <td>0.376709</td>\n",
       "      <td>0.373053</td>\n",
       "      <td>0.368387</td>\n",
       "      <td>0.342399</td>\n",
       "      <td>0.357597</td>\n",
       "      <td>0.343194</td>\n",
       "      <td>0.337836</td>\n",
       "      <td>0.350549</td>\n",
       "      <td>...</td>\n",
       "      <td>0.325148</td>\n",
       "      <td>0.308555</td>\n",
       "      <td>0.308622</td>\n",
       "      <td>0.296579</td>\n",
       "      <td>0.284431</td>\n",
       "      <td>0.268824</td>\n",
       "      <td>0.248695</td>\n",
       "      <td>0.284517</td>\n",
       "      <td>0.291009</td>\n",
       "      <td>0.290060</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1404 rows × 50 columns</p>\n",
       "</div>\n",
       "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a424af3a-9235-45c8-af19-7acf16ae2d86')\"\n",
       "              title=\"Convert this dataframe to an interactive table.\"\n",
       "              style=\"display:none;\">\n",
       "        \n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "       width=\"24px\">\n",
       "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
       "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
       "  </svg>\n",
       "      </button>\n",
       "      \n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      flex-wrap:wrap;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "      <script>\n",
       "        const buttonEl =\n",
       "          document.querySelector('#df-a424af3a-9235-45c8-af19-7acf16ae2d86 button.colab-df-convert');\n",
       "        buttonEl.style.display =\n",
       "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "        async function convertToInteractive(key) {\n",
       "          const element = document.querySelector('#df-a424af3a-9235-45c8-af19-7acf16ae2d86');\n",
       "          const dataTable =\n",
       "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                     [key], {});\n",
       "          if (!dataTable) return;\n",
       "\n",
       "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "            + ' to learn more about interactive tables.';\n",
       "          element.innerHTML = '';\n",
       "          dataTable['output_type'] = 'display_data';\n",
       "          await google.colab.output.renderOutput(dataTable, element);\n",
       "          const docLink = document.createElement('div');\n",
       "          docLink.innerHTML = docLinkHtml;\n",
       "          element.appendChild(docLink);\n",
       "        }\n",
       "      </script>\n",
       "    </div>\n",
       "  </div>\n",
       "  "
      ],
      "text/plain": [
       "                  0         1         2         3         4         5   \\\n",
       "DATE                                                                     \n",
       "2013-06-05  0.003097  0.006808  0.006525  0.008473  0.006317  0.008799   \n",
       "2013-06-06  0.006808  0.006525  0.008473  0.006317  0.008799  0.003711   \n",
       "2013-06-07  0.006525  0.008473  0.006317  0.008799  0.003711  0.005644   \n",
       "2013-06-10  0.008473  0.006317  0.008799  0.003711  0.005644  0.003585   \n",
       "2013-06-11  0.006317  0.008799  0.003711  0.005644  0.003585  0.006593   \n",
       "...              ...       ...       ...       ...       ...       ...   \n",
       "2018-12-24  0.364602  0.376510  0.371490  0.389656  0.389438  0.377017   \n",
       "2018-12-26  0.376510  0.371490  0.389656  0.389438  0.377017  0.376709   \n",
       "2018-12-27  0.371490  0.389656  0.389438  0.377017  0.376709  0.373053   \n",
       "2018-12-28  0.389656  0.389438  0.377017  0.376709  0.373053  0.368387   \n",
       "2018-12-31  0.389438  0.377017  0.376709  0.373053  0.368387  0.342399   \n",
       "\n",
       "                  6         7         8         9   ...        40        41  \\\n",
       "DATE                                                ...                       \n",
       "2013-06-05  0.003711  0.005644  0.003585  0.006593  ...  0.039186  0.034944   \n",
       "2013-06-06  0.005644  0.003585  0.006593  0.008295  ...  0.034944  0.033457   \n",
       "2013-06-07  0.003585  0.006593  0.008295  0.014169  ...  0.033457  0.033177   \n",
       "2013-06-10  0.006593  0.008295  0.014169  0.015902  ...  0.033177  0.036391   \n",
       "2013-06-11  0.008295  0.014169  0.015902  0.014513  ...  0.036391  0.032796   \n",
       "...              ...       ...       ...       ...  ...       ...       ...   \n",
       "2018-12-24  0.376709  0.373053  0.368387  0.342399  ...  0.336752  0.336463   \n",
       "2018-12-26  0.373053  0.368387  0.342399  0.357597  ...  0.336463  0.340853   \n",
       "2018-12-27  0.368387  0.342399  0.357597  0.343194  ...  0.340853  0.340690   \n",
       "2018-12-28  0.342399  0.357597  0.343194  0.337836  ...  0.340690  0.325148   \n",
       "2018-12-31  0.357597  0.343194  0.337836  0.350549  ...  0.325148  0.308555   \n",
       "\n",
       "                  42        43        44        45        46        47  \\\n",
       "DATE                                                                     \n",
       "2013-06-05  0.033457  0.033177  0.036391  0.032796  0.034655  0.027383   \n",
       "2013-06-06  0.033177  0.036391  0.032796  0.034655  0.027383  0.030357   \n",
       "2013-06-07  0.036391  0.032796  0.034655  0.027383  0.030357  0.027580   \n",
       "2013-06-10  0.032796  0.034655  0.027383  0.030357  0.027580  0.020673   \n",
       "2013-06-11  0.034655  0.027383  0.030357  0.027580  0.020673  0.024870   \n",
       "...              ...       ...       ...       ...       ...       ...   \n",
       "2018-12-24  0.340853  0.340690  0.325148  0.308555  0.308622  0.296579   \n",
       "2018-12-26  0.340690  0.325148  0.308555  0.308622  0.296579  0.284431   \n",
       "2018-12-27  0.325148  0.308555  0.308622  0.296579  0.284431  0.268824   \n",
       "2018-12-28  0.308555  0.308622  0.296579  0.284431  0.268824  0.248695   \n",
       "2018-12-31  0.308622  0.296579  0.284431  0.268824  0.248695  0.284517   \n",
       "\n",
       "                  48        49  \n",
       "DATE                            \n",
       "2013-06-05  0.030357  0.027580  \n",
       "2013-06-06  0.027580  0.020673  \n",
       "2013-06-07  0.020673  0.024870  \n",
       "2013-06-10  0.024870  0.031266  \n",
       "2013-06-11  0.031266  0.031091  \n",
       "...              ...       ...  \n",
       "2018-12-24  0.284431  0.268824  \n",
       "2018-12-26  0.268824  0.248695  \n",
       "2018-12-27  0.248695  0.284517  \n",
       "2018-12-28  0.284517  0.291009  \n",
       "2018-12-31  0.291009  0.290060  \n",
       "\n",
       "[1404 rows x 50 columns]"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X[:'2018']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "NKnE8p6acMMj",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "NKnE8p6acMMj",
    "outputId": "a6d172ed-734b-4628-8e62-e96de526a93f"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DATE\n",
       "2013-06-05    0.020673\n",
       "2013-06-06    0.024870\n",
       "2013-06-07    0.031266\n",
       "2013-06-10    0.031091\n",
       "2013-06-11    0.025967\n",
       "                ...   \n",
       "2018-12-24    0.248695\n",
       "2018-12-26    0.284517\n",
       "2018-12-27    0.291009\n",
       "2018-12-28    0.290060\n",
       "2018-12-31    0.296545\n",
       "Length: 1404, dtype: float64"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y[:'2018']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "n79Z0MXKla9Y",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "n79Z0MXKla9Y",
    "outputId": "4683d479-f91a-4c3a-bbfa-ab108f12a0b9"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "<ipython-input-23-10130eff6def>:5: FutureWarning: Indexing a DataFrame with a datetimelike index using a single string to slice the rows, like `frame[string]`, is deprecated and will be removed in a future version. Use `frame.loc[string]` instead.\n",
      "  X_test = X['2022'].values.reshape(-1, window_size, 1)\n"
     ]
    }
   ],
   "source": [
    "X_train = X[:'2021'].values.reshape(-1, window_size, 1)\n",
    "y_train = y[:'2021']\n",
    "\n",
    "# keep the last year for testing\n",
    "X_test = X['2022'].values.reshape(-1, window_size, 1)\n",
    "y_test = y['2022']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "PI16-m1Vla_7",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "PI16-m1Vla_7",
    "outputId": "964c0c5f-9350-42f9-fa85-5591cf7cbb6d"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(2161, 50, 1) (2161,) (251, 50, 1) (251,)\n"
     ]
    }
   ],
   "source": [
    "print(X_train.shape,y_train.shape,X_test.shape,y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "nRnCnaA7pQBN",
   "metadata": {
    "id": "nRnCnaA7pQBN"
   },
   "outputs": [],
   "source": [
    "n_obs, window_size, n_features = X_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "v2nsD1DXdaMR",
   "metadata": {
    "id": "v2nsD1DXdaMR"
   },
   "outputs": [],
   "source": [
    "# Define a Sequential model\n",
    "rnn = Sequential([\n",
    "    # Add an LSTM layer with 10 units or neurons, input_shape of (window_size, n_features), and name 'LSTM'\n",
    "    LSTM(units=10, input_shape=(window_size, n_features), name='LSTM'),\n",
    "    # Add a Dense layer with 1 neuron and name 'Output'\n",
    "    Dense(1, name='Output')\n",
    "])\n",
    "\n",
    "# Print the summary of the model\n",
    "print(rnn.summary())\n",
    "\n",
    "# Create an RMSprop optimizer with a learning rate of 0.001, rho of 0.9, and epsilon of 1e-08\n",
    "optimizer = keras.optimizers.RMSprop(learning_rate=0.001, rho=0.9, epsilon=1e-08)\n",
    "\n",
    "# Compile the model with a mean squared error loss function and the RMSprop optimizer created above\n",
    "rnn.compile(loss='mean_squared_error', optimizer=optimizer)\n",
    "\n",
    "# Define the path to save the model results\n",
    "results_path = Path('/content/drive/MyDrive/HFT/data/results', 'univariate_time_series') # Tested on colab, so created a repo in my GDrive\n",
    "\n",
    "# Define the path to save the best performing weights of the RNN model\n",
    "rnn_path = (results_path / 'rnn.h5').as_posix()\n",
    "\n",
    "# Create a ModelCheckpoint callback that saves the weights of the RNN model to rnn_path if validation loss improves\n",
    "checkpointer = ModelCheckpoint(filepath=rnn_path, verbose=1, monitor='val_loss', save_best_only=True)\n",
    "\n",
    "# Create an EarlyStopping callback that stops training if validation loss does not improve for 40 epochs, and restore the best performing weights\n",
    "early_stopping = EarlyStopping(monitor='val_loss', patience=40, restore_best_weights=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "oQIA9wI8ekNe",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "oQIA9wI8ekNe",
    "outputId": "6ddc86e7-9147-4d7b-a12d-5598f1ebcb04"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 0.0039\n",
      "Epoch 1: val_loss improved from inf to 0.00194, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 11s 15ms/step - loss: 0.0039 - val_loss: 0.0019\n",
      "Epoch 2/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 2.9483e-04\n",
      "Epoch 2: val_loss improved from 0.00194 to 0.00100, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 2.9483e-04 - val_loss: 0.0010\n",
      "Epoch 3/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 2.7101e-04\n",
      "Epoch 3: val_loss did not improve from 0.00100\n",
      "217/217 [==============================] - 1s 5ms/step - loss: 2.6828e-04 - val_loss: 0.0021\n",
      "Epoch 4/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 2.5109e-04\n",
      "Epoch 4: val_loss improved from 0.00100 to 0.00084, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 2.5109e-04 - val_loss: 8.4359e-04\n",
      "Epoch 5/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 2.3153e-04\n",
      "Epoch 5: val_loss did not improve from 0.00084\n",
      "217/217 [==============================] - 1s 5ms/step - loss: 2.3153e-04 - val_loss: 0.0014\n",
      "Epoch 6/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 2.2040e-04\n",
      "Epoch 6: val_loss did not improve from 0.00084\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 2.1752e-04 - val_loss: 0.0012\n",
      "Epoch 7/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 2.0222e-04\n",
      "Epoch 7: val_loss improved from 0.00084 to 0.00080, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 2.0377e-04 - val_loss: 8.0259e-04\n",
      "Epoch 8/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 1.9915e-04\n",
      "Epoch 8: val_loss did not improve from 0.00080\n",
      "217/217 [==============================] - 1s 5ms/step - loss: 1.9624e-04 - val_loss: 0.0021\n",
      "Epoch 9/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 1.8463e-04\n",
      "Epoch 9: val_loss improved from 0.00080 to 0.00079, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 1.8400e-04 - val_loss: 7.9376e-04\n",
      "Epoch 10/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 1.8287e-04\n",
      "Epoch 10: val_loss did not improve from 0.00079\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 1.8279e-04 - val_loss: 0.0012\n",
      "Epoch 11/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 1.7214e-04\n",
      "Epoch 11: val_loss did not improve from 0.00079\n",
      "217/217 [==============================] - 1s 7ms/step - loss: 1.8044e-04 - val_loss: 0.0012\n",
      "Epoch 12/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 1.6298e-04\n",
      "Epoch 12: val_loss improved from 0.00079 to 0.00066, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.6779e-04 - val_loss: 6.6109e-04\n",
      "Epoch 13/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 1.6846e-04\n",
      "Epoch 13: val_loss did not improve from 0.00066\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 1.6776e-04 - val_loss: 7.8268e-04\n",
      "Epoch 14/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 1.6209e-04\n",
      "Epoch 14: val_loss did not improve from 0.00066\n",
      "217/217 [==============================] - 1s 7ms/step - loss: 1.6160e-04 - val_loss: 0.0011\n",
      "Epoch 15/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 1.5219e-04\n",
      "Epoch 15: val_loss improved from 0.00066 to 0.00060, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 5ms/step - loss: 1.5275e-04 - val_loss: 6.0149e-04\n",
      "Epoch 16/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 1.5500e-04\n",
      "Epoch 16: val_loss did not improve from 0.00060\n",
      "217/217 [==============================] - 1s 5ms/step - loss: 1.5266e-04 - val_loss: 6.2962e-04\n",
      "Epoch 17/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 1.5246e-04\n",
      "Epoch 17: val_loss improved from 0.00060 to 0.00056, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.5228e-04 - val_loss: 5.6179e-04\n",
      "Epoch 18/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 1.4430e-04\n",
      "Epoch 18: val_loss did not improve from 0.00056\n",
      "217/217 [==============================] - 1s 5ms/step - loss: 1.4476e-04 - val_loss: 6.0192e-04\n",
      "Epoch 19/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 1.4786e-04\n",
      "Epoch 19: val_loss did not improve from 0.00056\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 1.4669e-04 - val_loss: 8.0307e-04\n",
      "Epoch 20/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 1.4478e-04\n",
      "Epoch 20: val_loss improved from 0.00056 to 0.00054, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 10ms/step - loss: 1.4478e-04 - val_loss: 5.4427e-04\n",
      "Epoch 21/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 1.4098e-04\n",
      "Epoch 21: val_loss did not improve from 0.00054\n",
      "217/217 [==============================] - 1s 7ms/step - loss: 1.3992e-04 - val_loss: 0.0011\n",
      "Epoch 22/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 1.3585e-04\n",
      "Epoch 22: val_loss did not improve from 0.00054\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.3471e-04 - val_loss: 6.3421e-04\n",
      "Epoch 23/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 1.2988e-04\n",
      "Epoch 23: val_loss did not improve from 0.00054\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.2988e-04 - val_loss: 5.6596e-04\n",
      "Epoch 24/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 1.3196e-04\n",
      "Epoch 24: val_loss did not improve from 0.00054\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.3221e-04 - val_loss: 5.5177e-04\n",
      "Epoch 25/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 1.2968e-04\n",
      "Epoch 25: val_loss did not improve from 0.00054\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.3068e-04 - val_loss: 0.0012\n",
      "Epoch 26/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 1.2760e-04\n",
      "Epoch 26: val_loss improved from 0.00054 to 0.00050, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.2771e-04 - val_loss: 4.9697e-04\n",
      "Epoch 27/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 1.2976e-04\n",
      "Epoch 27: val_loss did not improve from 0.00050\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.2973e-04 - val_loss: 9.4819e-04\n",
      "Epoch 28/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 1.2713e-04\n",
      "Epoch 28: val_loss did not improve from 0.00050\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.2713e-04 - val_loss: 5.5153e-04\n",
      "Epoch 29/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 1.2585e-04\n",
      "Epoch 29: val_loss did not improve from 0.00050\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 1.2673e-04 - val_loss: 5.7931e-04\n",
      "Epoch 30/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 1.2734e-04\n",
      "Epoch 30: val_loss improved from 0.00050 to 0.00048, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 1.2728e-04 - val_loss: 4.7932e-04\n",
      "Epoch 31/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 1.2184e-04\n",
      "Epoch 31: val_loss did not improve from 0.00048\n",
      "217/217 [==============================] - 1s 7ms/step - loss: 1.2159e-04 - val_loss: 5.7912e-04\n",
      "Epoch 32/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 1.2071e-04\n",
      "Epoch 32: val_loss did not improve from 0.00048\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.2270e-04 - val_loss: 5.1467e-04\n",
      "Epoch 33/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 1.2074e-04\n",
      "Epoch 33: val_loss did not improve from 0.00048\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.1950e-04 - val_loss: 5.5027e-04\n",
      "Epoch 34/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 1.1937e-04\n",
      "Epoch 34: val_loss did not improve from 0.00048\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.1894e-04 - val_loss: 5.6020e-04\n",
      "Epoch 35/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 1.1580e-04\n",
      "Epoch 35: val_loss did not improve from 0.00048\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.1562e-04 - val_loss: 5.4217e-04\n",
      "Epoch 36/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 1.1610e-04\n",
      "Epoch 36: val_loss improved from 0.00048 to 0.00045, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 11ms/step - loss: 1.1610e-04 - val_loss: 4.5220e-04\n",
      "Epoch 37/200\n",
      "207/217 [===========================>..] - ETA: 0s - loss: 1.1926e-04\n",
      "Epoch 37: val_loss did not improve from 0.00045\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.1614e-04 - val_loss: 0.0012\n",
      "Epoch 38/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 1.1691e-04\n",
      "Epoch 38: val_loss did not improve from 0.00045\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 1.1686e-04 - val_loss: 4.9667e-04\n",
      "Epoch 39/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 1.1204e-04\n",
      "Epoch 39: val_loss did not improve from 0.00045\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 1.1199e-04 - val_loss: 5.2651e-04\n",
      "Epoch 40/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 1.1558e-04\n",
      "Epoch 40: val_loss did not improve from 0.00045\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 1.1462e-04 - val_loss: 5.8662e-04\n",
      "Epoch 41/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 1.1338e-04\n",
      "Epoch 41: val_loss did not improve from 0.00045\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.1255e-04 - val_loss: 0.0013\n",
      "Epoch 42/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 1.1436e-04\n",
      "Epoch 42: val_loss did not improve from 0.00045\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.1445e-04 - val_loss: 5.0035e-04\n",
      "Epoch 43/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 1.1388e-04\n",
      "Epoch 43: val_loss did not improve from 0.00045\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.1258e-04 - val_loss: 7.4132e-04\n",
      "Epoch 44/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 1.0565e-04\n",
      "Epoch 44: val_loss improved from 0.00045 to 0.00045, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 1.1002e-04 - val_loss: 4.4828e-04\n",
      "Epoch 45/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 1.1197e-04\n",
      "Epoch 45: val_loss did not improve from 0.00045\n",
      "217/217 [==============================] - 1s 5ms/step - loss: 1.1055e-04 - val_loss: 5.6135e-04\n",
      "Epoch 46/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 1.0826e-04\n",
      "Epoch 46: val_loss improved from 0.00045 to 0.00042, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0759e-04 - val_loss: 4.2311e-04\n",
      "Epoch 47/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 1.0953e-04\n",
      "Epoch 47: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0950e-04 - val_loss: 8.0053e-04\n",
      "Epoch 48/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 1.0946e-04\n",
      "Epoch 48: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 1.0866e-04 - val_loss: 4.9306e-04\n",
      "Epoch 49/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 1.0800e-04\n",
      "Epoch 49: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 1.0682e-04 - val_loss: 9.1589e-04\n",
      "Epoch 50/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 1.0659e-04\n",
      "Epoch 50: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 1.0887e-04 - val_loss: 5.2045e-04\n",
      "Epoch 51/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 1.0469e-04\n",
      "Epoch 51: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0469e-04 - val_loss: 4.2951e-04\n",
      "Epoch 52/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 1.0718e-04\n",
      "Epoch 52: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0532e-04 - val_loss: 5.8709e-04\n",
      "Epoch 53/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 1.0307e-04\n",
      "Epoch 53: val_loss improved from 0.00042 to 0.00042, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 1.0280e-04 - val_loss: 4.2289e-04\n",
      "Epoch 54/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 1.0202e-04\n",
      "Epoch 54: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0198e-04 - val_loss: 4.8581e-04\n",
      "Epoch 55/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 1.0894e-04\n",
      "Epoch 55: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0787e-04 - val_loss: 6.4563e-04\n",
      "Epoch 56/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 1.0496e-04\n",
      "Epoch 56: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0496e-04 - val_loss: 0.0013\n",
      "Epoch 57/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 1.0426e-04\n",
      "Epoch 57: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0279e-04 - val_loss: 4.9065e-04\n",
      "Epoch 58/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 1.0232e-04\n",
      "Epoch 58: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 1.0213e-04 - val_loss: 0.0010\n",
      "Epoch 59/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 1.0369e-04\n",
      "Epoch 59: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 1.0365e-04 - val_loss: 4.8003e-04\n",
      "Epoch 60/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 1.0426e-04\n",
      "Epoch 60: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 1.0358e-04 - val_loss: 5.0648e-04\n",
      "Epoch 61/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 1.0463e-04\n",
      "Epoch 61: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0459e-04 - val_loss: 4.6647e-04\n",
      "Epoch 62/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.8888e-05\n",
      "Epoch 62: val_loss did not improve from 0.00042\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0018e-04 - val_loss: 4.9236e-04\n",
      "Epoch 63/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 1.0243e-04\n",
      "Epoch 63: val_loss improved from 0.00042 to 0.00040, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 1.0222e-04 - val_loss: 4.0202e-04\n",
      "Epoch 64/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 9.9585e-05\n",
      "Epoch 64: val_loss did not improve from 0.00040\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0171e-04 - val_loss: 8.3029e-04\n",
      "Epoch 65/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 1.0127e-04\n",
      "Epoch 65: val_loss improved from 0.00040 to 0.00040, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0225e-04 - val_loss: 3.9900e-04\n",
      "Epoch 66/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.8183e-05\n",
      "Epoch 66: val_loss did not improve from 0.00040\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.8848e-05 - val_loss: 4.5820e-04\n",
      "Epoch 67/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.9499e-05\n",
      "Epoch 67: val_loss improved from 0.00040 to 0.00039, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.9375e-05 - val_loss: 3.9153e-04\n",
      "Epoch 68/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.6681e-05\n",
      "Epoch 68: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.6681e-05 - val_loss: 4.6457e-04\n",
      "Epoch 69/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 1.0186e-04\n",
      "Epoch 69: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 1.0183e-04 - val_loss: 4.2524e-04\n",
      "Epoch 70/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 9.8942e-05\n",
      "Epoch 70: val_loss improved from 0.00039 to 0.00039, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.7249e-05 - val_loss: 3.8985e-04\n",
      "Epoch 71/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 1.0009e-04\n",
      "Epoch 71: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 1.0008e-04 - val_loss: 3.9857e-04\n",
      "Epoch 72/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 9.7392e-05\n",
      "Epoch 72: val_loss improved from 0.00039 to 0.00039, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.6862e-05 - val_loss: 3.8791e-04\n",
      "Epoch 73/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 9.9412e-05\n",
      "Epoch 73: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.9145e-05 - val_loss: 4.1197e-04\n",
      "Epoch 74/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 9.9159e-05\n",
      "Epoch 74: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.8763e-05 - val_loss: 3.9946e-04\n",
      "Epoch 75/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 9.9079e-05\n",
      "Epoch 75: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.9193e-05 - val_loss: 4.0301e-04\n",
      "Epoch 76/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 9.2912e-05\n",
      "Epoch 76: val_loss improved from 0.00039 to 0.00039, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.6015e-05 - val_loss: 3.8609e-04\n",
      "Epoch 77/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 9.6052e-05\n",
      "Epoch 77: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.6360e-05 - val_loss: 3.9334e-04\n",
      "Epoch 78/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 9.7497e-05\n",
      "Epoch 78: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 1s 7ms/step - loss: 9.7453e-05 - val_loss: 5.0787e-04\n",
      "Epoch 79/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 9.8064e-05\n",
      "Epoch 79: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.7799e-05 - val_loss: 6.4597e-04\n",
      "Epoch 80/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 9.4961e-05\n",
      "Epoch 80: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.6618e-05 - val_loss: 4.9697e-04\n",
      "Epoch 81/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 9.7545e-05\n",
      "Epoch 81: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.6320e-05 - val_loss: 3.9417e-04\n",
      "Epoch 82/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.3510e-05\n",
      "Epoch 82: val_loss did not improve from 0.00039\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.3510e-05 - val_loss: 6.7194e-04\n",
      "Epoch 83/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.5596e-05\n",
      "Epoch 83: val_loss improved from 0.00039 to 0.00038, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.5739e-05 - val_loss: 3.8050e-04\n",
      "Epoch 84/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 9.3073e-05\n",
      "Epoch 84: val_loss did not improve from 0.00038\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.3646e-05 - val_loss: 5.3537e-04\n",
      "Epoch 85/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.6376e-05\n",
      "Epoch 85: val_loss did not improve from 0.00038\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.6376e-05 - val_loss: 3.9216e-04\n",
      "Epoch 86/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.6262e-05\n",
      "Epoch 86: val_loss did not improve from 0.00038\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.6262e-05 - val_loss: 9.5517e-04\n",
      "Epoch 87/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.7215e-05\n",
      "Epoch 87: val_loss improved from 0.00038 to 0.00038, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.6801e-05 - val_loss: 3.7835e-04\n",
      "Epoch 88/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 9.6621e-05\n",
      "Epoch 88: val_loss did not improve from 0.00038\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.6764e-05 - val_loss: 4.0619e-04\n",
      "Epoch 89/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.5701e-05\n",
      "Epoch 89: val_loss did not improve from 0.00038\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.5701e-05 - val_loss: 4.9027e-04\n",
      "Epoch 90/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.5075e-05\n",
      "Epoch 90: val_loss did not improve from 0.00038\n",
      "217/217 [==============================] - 1s 7ms/step - loss: 9.5430e-05 - val_loss: 4.3283e-04\n",
      "Epoch 91/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.5008e-05\n",
      "Epoch 91: val_loss did not improve from 0.00038\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.4192e-05 - val_loss: 0.0012\n",
      "Epoch 92/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 9.6994e-05\n",
      "Epoch 92: val_loss improved from 0.00038 to 0.00037, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.6669e-05 - val_loss: 3.7482e-04\n",
      "Epoch 93/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 9.4923e-05\n",
      "Epoch 93: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.4765e-05 - val_loss: 3.8267e-04\n",
      "Epoch 94/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 9.3737e-05\n",
      "Epoch 94: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.4188e-05 - val_loss: 4.7149e-04\n",
      "Epoch 95/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.6062e-05\n",
      "Epoch 95: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.4931e-05 - val_loss: 5.0718e-04\n",
      "Epoch 96/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.3942e-05\n",
      "Epoch 96: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.6007e-05 - val_loss: 8.3156e-04\n",
      "Epoch 97/200\n",
      "207/217 [===========================>..] - ETA: 0s - loss: 9.2737e-05\n",
      "Epoch 97: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.5952e-05 - val_loss: 4.9604e-04\n",
      "Epoch 98/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.4514e-05\n",
      "Epoch 98: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.4313e-05 - val_loss: 8.6429e-04\n",
      "Epoch 99/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.5005e-05\n",
      "Epoch 99: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.4551e-05 - val_loss: 4.1645e-04\n",
      "Epoch 100/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 9.5076e-05\n",
      "Epoch 100: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.5036e-05 - val_loss: 3.8625e-04\n",
      "Epoch 101/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 9.2564e-05\n",
      "Epoch 101: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.3295e-05 - val_loss: 4.4306e-04\n",
      "Epoch 102/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 9.4019e-05\n",
      "Epoch 102: val_loss improved from 0.00037 to 0.00037, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.5392e-05 - val_loss: 3.7199e-04\n",
      "Epoch 103/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.4259e-05\n",
      "Epoch 103: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.3856e-05 - val_loss: 4.3069e-04\n",
      "Epoch 104/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.2899e-05\n",
      "Epoch 104: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2899e-05 - val_loss: 6.1231e-04\n",
      "Epoch 105/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 9.1313e-05\n",
      "Epoch 105: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.0526e-05 - val_loss: 4.7090e-04\n",
      "Epoch 106/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 9.8099e-05\n",
      "Epoch 106: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.6744e-05 - val_loss: 4.1717e-04\n",
      "Epoch 107/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 9.4653e-05\n",
      "Epoch 107: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.3500e-05 - val_loss: 6.3033e-04\n",
      "Epoch 108/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.1526e-05\n",
      "Epoch 108: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.1506e-05 - val_loss: 0.0014\n",
      "Epoch 109/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.4368e-05\n",
      "Epoch 109: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.3410e-05 - val_loss: 3.7240e-04\n",
      "Epoch 110/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.3766e-05\n",
      "Epoch 110: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.3766e-05 - val_loss: 5.7629e-04\n",
      "Epoch 111/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.2589e-05\n",
      "Epoch 111: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2589e-05 - val_loss: 4.2889e-04\n",
      "Epoch 112/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 8.8103e-05\n",
      "Epoch 112: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1557e-05 - val_loss: 4.3576e-04\n",
      "Epoch 113/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 9.4410e-05\n",
      "Epoch 113: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 5ms/step - loss: 9.3427e-05 - val_loss: 3.7856e-04\n",
      "Epoch 114/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 9.2447e-05\n",
      "Epoch 114: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.0999e-05 - val_loss: 5.9516e-04\n",
      "Epoch 115/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 9.5031e-05\n",
      "Epoch 115: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.4183e-05 - val_loss: 3.7543e-04\n",
      "Epoch 116/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.1957e-05\n",
      "Epoch 116: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2194e-05 - val_loss: 3.7545e-04\n",
      "Epoch 117/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.1681e-05\n",
      "Epoch 117: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1329e-05 - val_loss: 6.9997e-04\n",
      "Epoch 118/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.3210e-05\n",
      "Epoch 118: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.3210e-05 - val_loss: 4.1436e-04\n",
      "Epoch 119/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.1514e-05\n",
      "Epoch 119: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.1136e-05 - val_loss: 3.9519e-04\n",
      "Epoch 120/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 9.3936e-05\n",
      "Epoch 120: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2799e-05 - val_loss: 6.1015e-04\n",
      "Epoch 121/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 9.2896e-05\n",
      "Epoch 121: val_loss improved from 0.00037 to 0.00037, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.2454e-05 - val_loss: 3.6964e-04\n",
      "Epoch 122/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 9.3255e-05\n",
      "Epoch 122: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.3099e-05 - val_loss: 6.2808e-04\n",
      "Epoch 123/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.4137e-05\n",
      "Epoch 123: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.3869e-05 - val_loss: 4.2776e-04\n",
      "Epoch 124/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.1669e-05\n",
      "Epoch 124: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2536e-05 - val_loss: 7.7697e-04\n",
      "Epoch 125/200\n",
      "207/217 [===========================>..] - ETA: 0s - loss: 9.2510e-05\n",
      "Epoch 125: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1812e-05 - val_loss: 3.7439e-04\n",
      "Epoch 126/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 9.2618e-05\n",
      "Epoch 126: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1012e-05 - val_loss: 4.0331e-04\n",
      "Epoch 127/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 9.2361e-05\n",
      "Epoch 127: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.3016e-05 - val_loss: 9.3196e-04\n",
      "Epoch 128/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.2127e-05\n",
      "Epoch 128: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.2418e-05 - val_loss: 3.9668e-04\n",
      "Epoch 129/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 9.0428e-05\n",
      "Epoch 129: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.0389e-05 - val_loss: 3.7334e-04\n",
      "Epoch 130/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.1325e-05\n",
      "Epoch 130: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1317e-05 - val_loss: 3.7145e-04\n",
      "Epoch 131/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 8.8357e-05\n",
      "Epoch 131: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2484e-05 - val_loss: 4.8024e-04\n",
      "Epoch 132/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 9.0085e-05\n",
      "Epoch 132: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1971e-05 - val_loss: 3.8100e-04\n",
      "Epoch 133/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 9.2153e-05\n",
      "Epoch 133: val_loss improved from 0.00037 to 0.00037, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.2112e-05 - val_loss: 3.6562e-04\n",
      "Epoch 134/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.1865e-05\n",
      "Epoch 134: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2280e-05 - val_loss: 3.8350e-04\n",
      "Epoch 135/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 9.2316e-05\n",
      "Epoch 135: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2541e-05 - val_loss: 9.7636e-04\n",
      "Epoch 136/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.3146e-05\n",
      "Epoch 136: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2924e-05 - val_loss: 3.7754e-04\n",
      "Epoch 137/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.1503e-05\n",
      "Epoch 137: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.1503e-05 - val_loss: 3.8768e-04\n",
      "Epoch 138/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 9.0999e-05\n",
      "Epoch 138: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.0602e-05 - val_loss: 3.7651e-04\n",
      "Epoch 139/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.2112e-05\n",
      "Epoch 139: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.2112e-05 - val_loss: 3.7131e-04\n",
      "Epoch 140/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.0543e-05\n",
      "Epoch 140: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.0307e-05 - val_loss: 4.3089e-04\n",
      "Epoch 141/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.2110e-05\n",
      "Epoch 141: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2110e-05 - val_loss: 3.7098e-04\n",
      "Epoch 142/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 8.9641e-05\n",
      "Epoch 142: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.9690e-05 - val_loss: 4.0456e-04\n",
      "Epoch 143/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 8.8701e-05\n",
      "Epoch 143: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.0147e-05 - val_loss: 5.1968e-04\n",
      "Epoch 144/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 9.1549e-05\n",
      "Epoch 144: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1511e-05 - val_loss: 4.4207e-04\n",
      "Epoch 145/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 8.9004e-05\n",
      "Epoch 145: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.8500e-05 - val_loss: 3.6613e-04\n",
      "Epoch 146/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.1871e-05\n",
      "Epoch 146: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1694e-05 - val_loss: 3.6567e-04\n",
      "Epoch 147/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 9.0766e-05\n",
      "Epoch 147: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 7ms/step - loss: 9.1579e-05 - val_loss: 3.7102e-04\n",
      "Epoch 148/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 9.1825e-05\n",
      "Epoch 148: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.1794e-05 - val_loss: 3.9624e-04\n",
      "Epoch 149/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 9.1239e-05\n",
      "Epoch 149: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.0345e-05 - val_loss: 4.1668e-04\n",
      "Epoch 150/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 8.7884e-05\n",
      "Epoch 150: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.7845e-05 - val_loss: 5.4978e-04\n",
      "Epoch 151/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.2265e-05\n",
      "Epoch 151: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1031e-05 - val_loss: 3.6928e-04\n",
      "Epoch 152/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.1504e-05\n",
      "Epoch 152: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1504e-05 - val_loss: 4.1729e-04\n",
      "Epoch 153/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 8.6987e-05\n",
      "Epoch 153: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.9675e-05 - val_loss: 5.1307e-04\n",
      "Epoch 154/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 9.1064e-05\n",
      "Epoch 154: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.0637e-05 - val_loss: 5.8653e-04\n",
      "Epoch 155/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 8.7655e-05\n",
      "Epoch 155: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.8421e-05 - val_loss: 4.3915e-04\n",
      "Epoch 156/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 8.9769e-05\n",
      "Epoch 156: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.9769e-05 - val_loss: 3.8633e-04\n",
      "Epoch 157/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.4693e-05\n",
      "Epoch 157: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.3464e-05 - val_loss: 3.6674e-04\n",
      "Epoch 158/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 9.3945e-05\n",
      "Epoch 158: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.3533e-05 - val_loss: 4.5106e-04\n",
      "Epoch 159/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 9.0259e-05\n",
      "Epoch 159: val_loss did not improve from 0.00037\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.0244e-05 - val_loss: 4.8194e-04\n",
      "Epoch 160/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 9.0833e-05\n",
      "Epoch 160: val_loss improved from 0.00037 to 0.00036, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.0759e-05 - val_loss: 3.6356e-04\n",
      "Epoch 161/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.0572e-05\n",
      "Epoch 161: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.0077e-05 - val_loss: 5.4850e-04\n",
      "Epoch 162/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 9.1376e-05\n",
      "Epoch 162: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1417e-05 - val_loss: 5.2079e-04\n",
      "Epoch 163/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 9.0911e-05\n",
      "Epoch 163: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.0883e-05 - val_loss: 3.7738e-04\n",
      "Epoch 164/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.1955e-05\n",
      "Epoch 164: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1713e-05 - val_loss: 3.6529e-04\n",
      "Epoch 165/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 9.1152e-05\n",
      "Epoch 165: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1184e-05 - val_loss: 4.3005e-04\n",
      "Epoch 166/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 9.2952e-05\n",
      "Epoch 166: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2308e-05 - val_loss: 4.2054e-04\n",
      "Epoch 167/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.0830e-05\n",
      "Epoch 167: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.0675e-05 - val_loss: 4.1016e-04\n",
      "Epoch 168/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 8.9303e-05\n",
      "Epoch 168: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 8.8906e-05 - val_loss: 3.7278e-04\n",
      "Epoch 169/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 9.1722e-05\n",
      "Epoch 169: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.1037e-05 - val_loss: 4.0325e-04\n",
      "Epoch 170/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 8.9954e-05\n",
      "Epoch 170: val_loss improved from 0.00036 to 0.00036, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 8.9915e-05 - val_loss: 3.6258e-04\n",
      "Epoch 171/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.1486e-05\n",
      "Epoch 171: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1486e-05 - val_loss: 3.9261e-04\n",
      "Epoch 172/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 9.3125e-05\n",
      "Epoch 172: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.3005e-05 - val_loss: 0.0012\n",
      "Epoch 173/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 9.2759e-05\n",
      "Epoch 173: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2138e-05 - val_loss: 4.4681e-04\n",
      "Epoch 174/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 8.9580e-05\n",
      "Epoch 174: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 7ms/step - loss: 8.8934e-05 - val_loss: 3.6928e-04\n",
      "Epoch 175/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 8.8933e-05\n",
      "Epoch 175: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1057e-05 - val_loss: 4.5482e-04\n",
      "Epoch 176/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 9.0976e-05\n",
      "Epoch 176: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 7ms/step - loss: 9.0934e-05 - val_loss: 3.8315e-04\n",
      "Epoch 177/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 8.9881e-05\n",
      "Epoch 177: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 8.8906e-05 - val_loss: 7.1354e-04\n",
      "Epoch 178/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.0266e-05\n",
      "Epoch 178: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 8.9903e-05 - val_loss: 4.3468e-04\n",
      "Epoch 179/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 9.0943e-05\n",
      "Epoch 179: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.0567e-05 - val_loss: 3.6323e-04\n",
      "Epoch 180/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 9.0510e-05\n",
      "Epoch 180: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 3s 12ms/step - loss: 9.0777e-05 - val_loss: 0.0011\n",
      "Epoch 181/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 9.3229e-05\n",
      "Epoch 181: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 10ms/step - loss: 9.3188e-05 - val_loss: 3.7026e-04\n",
      "Epoch 182/200\n",
      "216/217 [============================>.] - ETA: 0s - loss: 8.8318e-05\n",
      "Epoch 182: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 11ms/step - loss: 8.8281e-05 - val_loss: 3.8979e-04\n",
      "Epoch 183/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 9.0561e-05\n",
      "Epoch 183: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.0259e-05 - val_loss: 3.6840e-04\n",
      "Epoch 184/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.2673e-05\n",
      "Epoch 184: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.2673e-05 - val_loss: 5.6742e-04\n",
      "Epoch 185/200\n",
      "215/217 [============================>.] - ETA: 0s - loss: 9.2601e-05\n",
      "Epoch 185: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 3s 15ms/step - loss: 9.2274e-05 - val_loss: 3.8375e-04\n",
      "Epoch 186/200\n",
      "212/217 [============================>.] - ETA: 0s - loss: 9.0362e-05\n",
      "Epoch 186: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.0002e-05 - val_loss: 4.1767e-04\n",
      "Epoch 187/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 8.9114e-05\n",
      "Epoch 187: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.1308e-05 - val_loss: 4.7727e-04\n",
      "Epoch 188/200\n",
      "208/217 [===========================>..] - ETA: 0s - loss: 9.3924e-05\n",
      "Epoch 188: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.2494e-05 - val_loss: 4.8312e-04\n",
      "Epoch 189/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 9.0105e-05\n",
      "Epoch 189: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.0105e-05 - val_loss: 3.7018e-04\n",
      "Epoch 190/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 8.8825e-05\n",
      "Epoch 190: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.8825e-05 - val_loss: 3.6774e-04\n",
      "Epoch 191/200\n",
      "209/217 [===========================>..] - ETA: 0s - loss: 9.0887e-05\n",
      "Epoch 191: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.9751e-05 - val_loss: 5.0591e-04\n",
      "Epoch 192/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 8.9875e-05\n",
      "Epoch 192: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.0001e-05 - val_loss: 0.0012\n",
      "Epoch 193/200\n",
      "211/217 [============================>.] - ETA: 0s - loss: 9.1462e-05\n",
      "Epoch 193: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 9.1426e-05 - val_loss: 4.0595e-04\n",
      "Epoch 194/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 8.8726e-05\n",
      "Epoch 194: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 8.8695e-05 - val_loss: 3.6355e-04\n",
      "Epoch 195/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 9.0290e-05\n",
      "Epoch 195: val_loss improved from 0.00036 to 0.00036, saving model to /content/drive/MyDrive/HFT/data/results/univariate_time_series/rnn.h5\n",
      "217/217 [==============================] - 2s 8ms/step - loss: 8.9862e-05 - val_loss: 3.6229e-04\n",
      "Epoch 196/200\n",
      "213/217 [============================>.] - ETA: 0s - loss: 8.9355e-05\n",
      "Epoch 196: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.8927e-05 - val_loss: 3.6608e-04\n",
      "Epoch 197/200\n",
      "217/217 [==============================] - ETA: 0s - loss: 8.9116e-05\n",
      "Epoch 197: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.9116e-05 - val_loss: 3.6831e-04\n",
      "Epoch 198/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 9.1028e-05\n",
      "Epoch 198: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 9.0965e-05 - val_loss: 3.6770e-04\n",
      "Epoch 199/200\n",
      "214/217 [============================>.] - ETA: 0s - loss: 8.9108e-05\n",
      "Epoch 199: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.9148e-05 - val_loss: 3.8532e-04\n",
      "Epoch 200/200\n",
      "210/217 [============================>.] - ETA: 0s - loss: 8.8836e-05\n",
      "Epoch 200: val_loss did not improve from 0.00036\n",
      "217/217 [==============================] - 1s 6ms/step - loss: 8.8748e-05 - val_loss: 3.6390e-04\n"
     ]
    }
   ],
   "source": [
    "lstm_training = rnn.fit(X_train,\n",
    "                        y_train,\n",
    "                        epochs=200,\n",
    "                        batch_size=10,\n",
    "                        shuffle=True,\n",
    "                        validation_data=(X_test, y_test),\n",
    "                        callbacks=[early_stopping, checkpointer],\n",
    "                        verbose=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "aPvLAsEpgOCb",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "aPvLAsEpgOCb",
    "outputId": "dbad807c-9ec2-4ca7-d5cc-acdace4810e4"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train RMSE: 0.0096 | Test RMSE: 0.0191\n"
     ]
    }
   ],
   "source": [
    "train_rmse_scaled = np.sqrt(rnn.evaluate(X_train, y_train, verbose=0))\n",
    "test_rmse_scaled = np.sqrt(rnn.evaluate(X_test, y_test, verbose=0))\n",
    "print(f'Train RMSE: {train_rmse_scaled:.4f} | Test RMSE: {test_rmse_scaled:.4f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "nspB4Gc_gPPt",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "nspB4Gc_gPPt",
    "outputId": "11938d01-7595-421b-91dc-e57d5d6a0d86"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "68/68 [==============================] - 1s 2ms/step\n",
      "8/8 [==============================] - 0s 3ms/step\n",
      "Train IC: 0.998533299020294 | Test IC: 0.9721980648833239\n"
     ]
    }
   ],
   "source": [
    "train_predict_scaled = rnn.predict(X_train)\n",
    "test_predict_scaled = rnn.predict(X_test)\n",
    "\n",
    "# Spearman rank correlation is a non-parametric test that is used to measure the degree of association between two variables.\n",
    "\n",
    "train_ic = spearmanr(y_train, train_predict_scaled)[0]\n",
    "test_ic = spearmanr(y_test, test_predict_scaled)[0]\n",
    "print(f'Train IC: {train_ic} | Test IC: {test_ic}')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "hNZYDTKBenSZ",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 666
    },
    "id": "hNZYDTKBenSZ",
    "outputId": "d85c32de-65c5-4486-ec6d-f63ee618594a"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=(20, 10))\n",
    "\n",
    "loss_history = pd.DataFrame(lstm_training.history).pow(.5)\n",
    "loss_history.index += 1\n",
    "best_rmse = loss_history.val_loss.min()\n",
    "\n",
    "best_epoch = loss_history.val_loss.idxmin()\n",
    "\n",
    "title = f'(Best Validation RMSE: {best_rmse} for window length of 50, testing on 2022 s&P500)'\n",
    "loss_history.columns=['Train RMSE', 'Validation RMSE']\n",
    "loss_history.rolling(5).mean().plot(logy=True, lw=2, title=title, ax=ax)\n",
    "\n",
    "ax.axvline(best_epoch, ls='-.', lw=1, c='r')\n",
    "ax.set_xlabel('Epochs')\n",
    "ax.set_ylabel('RMSE')\n",
    "sns.despine()\n",
    "fig.tight_layout()\n",
    "fig.savefig(results_path / 'rnn_sp500_error', dpi=300);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "C9APdl_gfw0x",
   "metadata": {
    "id": "C9APdl_gfw0x"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "MRf2-fnPfxVg",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "MRf2-fnPfxVg",
    "outputId": "2914d615-530f-4864-e6f8-52ac261d43f6"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train RMSE: 31.162661786164964 | Test RMSE: 62.09228035778334\n"
     ]
    }
   ],
   "source": [
    "train_predict = pd.Series(scaler.inverse_transform(train_predict_scaled).squeeze(), index=y_train.index)\n",
    "test_predict = (pd.Series(scaler.inverse_transform(test_predict_scaled).squeeze(), index=y_test.index))\n",
    "\n",
    "y_train_rescaled = scaler.inverse_transform(y_train.to_frame()).squeeze()\n",
    "y_test_rescaled = scaler.inverse_transform(y_test.to_frame()).squeeze()\n",
    "\n",
    "train_rmse = np.sqrt(mean_squared_error(train_predict, y_train_rescaled))\n",
    "test_rmse = np.sqrt(mean_squared_error(test_predict, y_test_rescaled))\n",
    "print(f'Train RMSE: {train_rmse} | Test RMSE: {test_rmse}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "d8EmLApu4kEG",
   "metadata": {
    "id": "d8EmLApu4kEG"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "hejVDQ_d4kAN",
   "metadata": {
    "id": "hejVDQ_d4kAN"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "3CLbZGDZfxYD",
   "metadata": {
    "id": "3CLbZGDZfxYD"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "QGQG-udJhycr",
   "metadata": {
    "id": "QGQG-udJhycr"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "834jqEtchyfs",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "834jqEtchyfs",
    "outputId": "ef32c4d8-7134-4ee3-9980-576ebcd8995e"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "<ipython-input-36-f9c4fb332678>:3: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  snp500 = snp500.join(train_predict.to_frame('predictions').assign(data='Train') .append(test_predict.to_frame('predictions').assign(data='Test')))\n"
     ]
    }
   ],
   "source": [
    "snp500['Train Predictions'] = train_predict\n",
    "snp500['Test Predictions'] = test_predict\n",
    "snp500 = snp500.join(train_predict.to_frame('predictions').assign(data='Train') .append(test_predict.to_frame('predictions').assign(data='Test')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "Rl2x6Ch-5MOA",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 597
    },
    "id": "Rl2x6Ch-5MOA",
    "outputId": "c520afe8-3ddf-4211-f021-ff82af4d0609"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Predictions')"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# fig=plt.figure(figsize=(20,10))\n",
    "fig, ax = plt.subplots(figsize=(20, 10))\n",
    "\n",
    "# ax1 = plt.subplot(221)\n",
    "\n",
    "snp500.loc['2014':, 'SP500'].plot(lw=4, ax=ax, c='k')\n",
    "snp500.loc['2014':, ['Test Predictions', 'Train Predictions']].plot(lw=1, ax=ax, ls='--')\n",
    "ax.set_title('Predictions')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "FIz3NZIy5Nfk",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 639
    },
    "id": "FIz3NZIy5Nfk",
    "outputId": "cc8f9219-23e0-47af-e05f-cdcd9fefdd9c"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x7f9f2ef26610>"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABJgAAAJcCAYAAAC1/R4oAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOzdd3gU1R7G8e+W7GbTe69AgNBDR3qT3kGxoAjqFQs2sPfesaOIiooVBBFQQbr0KjWUACG997ab3Z37x8CGJQEpgoK/z/PkMXPmzJkzw1yfy+spGkVRFIQQQgghhBBCCCGEOE/af7oDQgghhBBCCCGEEOLyJgGTEEIIIYQQQgghhLggEjAJIYQQQgghhBBCiAsiAZMQQgghhBBCCCGEuCASMAkhhBBCCCGEEEKICyIBkxBCCCGEEEIIIYS4IBIwCSGEEEL8TebNm8d111133tffeuutzJ8//2/s0V977733mDJlyiW9pxBCCCGuPBIwCSGEEOKKsnDhQkaOHElCQgJdunTh1ltvZevWrf90t2qpK9iZOXMmI0aM+Nvv9cgjj9CsWTMSEhJo3749t9xyC4cPHz7ndnr16sX69ev/9v4JIYQQ4vInAZMQQgghrhiff/45L730EnfccQfr1q1j5cqVXH/99Sxfvvyc27JarWdVdrmYOHEiO3bsYPXq1fj5+fHoo4/+010SQgghxBVEAiYhhBBCXBFKS0t59913eeqpp7j66qtxc3PDxcWFXr168fDDDwNgsVh48cUX6dKlC126dOHFF1/EYrEAsGnTJrp168aMGTPo3Lkzjz76KO+99x6TJ09mypQptG7dmvnz51NaWspjjz1Gly5d6Nq1K9OmTcNms9XZpxdeeIHu3bvTunVrRo4c6RhJtWbNGj7++GN+/fVXEhISGDp0KADjxo1jzpw5ANjtdj788EN69uxJp06deOihhygtLQUgLS2NRo0aMX/+fHr06EGHDh2YPn36Wb0nk8nEkCFDOHToUJ3nly9fzqBBg2jbti3jxo1zjHSaOnUqGRkZ3HHHHSQkJPDJJ5+c1f2EEEII8d8gAZMQQgghrgg7duzAbDbTt2/f09aZPn06O3fuZMGCBfz888/s3r2bDz/80HE+Ly+P4uJiVq5cyfPPPw+ogUv//v3ZunUrQ4YM4ZFHHkGv17N06VJ++ukn1q1b5wiFTtW8eXN++uknNm/ezODBg7n33nsxm81069aN//3vfwwYMIAdO3bw888/17p23rx5zJ8/ny+//JJly5ZRUVHBc88951Rn27Zt/Pbbb3zxxRd88MEHZzXtrby8nIULFxIfH1/r3NGjR3nwwQd57LHH2LBhA926deOOO+7AYrHw+uuvExYWxkcffcSOHTu47bbb/vJeQgghhPjvkIBJCCGEEFeEoqIifH190ev1p62zcOFC7rrrLvz9/fHz8+Ouu+5yCne0Wi2TJ0/GYDDg6uoKQKtWrejTpw9arZaysjJWr17NY489hpubG/7+/owfP57FixfXeb9hw4Y5+jRhwgQsFgtHjx49q+dZuHAh48ePJzIyEnd3dx544AF++eUXp2l6d999N66urjRu3JjGjRuzf//+07b32Wef0bZtW66++mrKy8t55ZVXatX55Zdf6N69O507d8bFxYWJEydSVVXFjh07zqrPQgghhPjvOv3/AxNCCCGEuIz4+PhQWFiI1Wo9bciUk5NDWFiY4zgsLIycnBzHsa+vL0aj0emakJAQx+8ZGRlYrVa6dOniKLPb7YSGhtZ5v08//ZS5c+eSk5ODRqOhrKyMwsLCs3qenJwcwsPDHcfh4eFYrVby8/MdZQEBAY7fTSYTFRUVp21vwoQJ3H///X95z5Pfj1arJTQ0lOzs7LPqsxBCCCH+uyRgEkIIIcQVISEhAYPBwLJly+jfv3+ddYKCgsjIyCAuLg6AzMxMgoKCHOc1Gk2ta04uCwkJwWAwsHHjxjOOlALYunUrM2fOZNasWcTFxaHVamnXrh2Kopz2Xqf2NT093XGckZGBXq/H39+frKysM157voKCgjh48KDjWFEUMjMzCQ4Ovij3E0IIIcSVQ6bICSGEEOKK4OnpyeTJk3nuuedYtmwZlZWVVFdXs3r1al577TUABg0axPTp0ykoKKCgoIAPPviAIUOGnPU9goKC6Ny5M6+88gplZWXY7XZSUlLYvHlzrbrl5eXodDr8/PywWq28//77lJWVOc77+/uTnp6O3W6v816DBw/miy++IDU1lfLycqZNm8aAAQP+Mti6EAMGDGD16tVs2LCB6upqPvvsMwwGAwkJCYA6Yio1NfWi3V8IIYQQly8JmIQQQghxxZgwYQKPPPIIH374IZ06daJHjx58/fXX9OnTB4A777yTZs2aMXToUIYOHUrTpk258847z+ker732GtXV1QwcOJB27doxefJkcnNza9U7sctcv3796NWrF0aj0Wkq3YlRVh06dGDEiBG1rh81ahRDhw7lxhtvpHfv3hgMBp588slz6uu5qlevHq+//jrPP/88HTt2ZOXKlXz00UcYDAYAbr/9dqZPn07btm359NNPL2pfhBBCCHF50SgnxmkLIYQQQgghhBBCCHEeZASTEEIIIYQQQgghhLggEjAJIYQQQgghhBBCiAsiAZMQQgghhBBCCCGEuCASMAkhhBBCCCGEEEKIC3Lx9rn9B/35558YjcZLdj+z2XxJ7ycEyHcnLj355sSlJt+c+CfIdycuNfnmxKUm35y4EGazmVatWtV57ooMmIxGI/Hx8ZfsfomJiZf0fkKAfHfi0pNvTlxq8s2Jf4J8d+JSk29OXGryzYkLkZiYeNpzMkVOCCGEEEIIIYQQQlwQCZiEEEIIIYQQQgghxAWRgEkIIYQQQgghhBBCXBAJmIQQQgghhBBCCCHEBZGASQghhBBCCCGEEEJcEAmYhBBCCCGEEEIIIcQFkYBJCCGEEEIIIYQQQlwQCZiEEEIIIYQQQgghxAWRgEkIIYQQQgghhBBCXBAJmIQQQgghhBBCCCHEBZGASQghhBBCCCGEEEJcEAmYhBBCCCGEEEIIIcQFkYBJCCGEEEIIIYQQQlwQCZiEEEIIIYQQQgghxAWRgEkIIYQQQgghhBBCXBAJmIQQQgghhBBCCCHEBZGASQghhBBCCCGEEEJcEAmYhBBCCCGEEEIIIcQF0f/THbjcFBYWMn78eADy8vLQarW4ubnh6urKnDlzMBgMZ7x+06ZNuLi40Lp161rn5s2bx549e3jqqacA+Omnn5g5cyYajQadTseQIUOYOHHiOfd5/vz5TJ8+HYBJkyYxYsSIWnX279/P008/TUVFBeHh4bzxxht4eHjw888/8+mnnzrqHThwgPnz5xMTE8O9995LSkoKOp2Onj17MmXKFAC2bNnCSy+9xIEDB3jrrbfo37+/4/rXX3+d1atXA3DnnXcycOBAADZs2MBrr72G3W7Hzc2NV155hejoaCwWCw899BB79+7Fx8eHadOmERER4dTnsrIytFotc+fOxWg0Ou51xx13kJaWxqJFiwBITEzk6aefxmw2o9PpeOaZZ2jRogWlpaVMnTqVjIwMbDYbEyZMYNSoUaSnp3P33Xdjt9uxWq3ceOONXHfddQBMnDiR3NxcbDYbbdq04emnn0an0/Hqq6+ycuVKXFxciIqK4uWXX8bLy4tdu3bx5JNPAqAoCvfccw99+/YF4IsvvmDOnDkoisKYMWMc35cQQgghhBBCCHHZUK5A+/btuyT3effdd5WZM2ee0/1OXFOXH3/8UXn22WcVRVGUVatWKcOHD1eysrIURVEUs9msfP/99+fcx8LCQqVXr15KYWGhUlRUpPTq1UspKiqqVW/kyJHKpk2bFEVRlDlz5ijTpk2rVWf//v1K7969FUVRlIqKCmXDhg2Ovl133XXKqlWrFEVRlNTUVCUxMVGZOnWq8uuvvzquX7lypTJ+/HilurpaKS8vV0aOHKmUlpYqiqIoV199tZKUlKQoiqLMnj1befjhhx2/P/nkk4qiKMqiRYuUe++9V1EURamurlYGDx6sJCYmKoqiKAUFBYrVanXca8mSJcoDDzygDBo0yFF2yy23OPq4atUq5cYbb1QURVGmT5+uvPbaa4qiKEp+fr7Srl07xWw2O34URVHKysqUnj17Ov48TvTbbrcrd999t7Jo0SJFURTljz/+UKqrqxVFUZTXXnvN0W5FRYWjPDs7W+nYsaNSXV2tHDhwQBk0aJDj/M0336wkJyfXevd1uVTfuRAnyDcnLjX55sQ/Qb47canJNycutf/0N2etvqjNm6utSoXF+tcVL2Nn+n5kitzfICkpiRtvvJGRI0cyceJEcnJyAPjyyy8ZOHAgQ4YM4f777yctLY3vvvuOWbNmMWzYMLZu3XraNmfMmMFDDz1EcHAwAAaDgWuuueac+7Z27Vo6d+6Mj48P3t7edO7cmT/++KNWveTkZNq1awdA586dWbp0aa06ixcvZtCgQQCYTCY6duzo6FuTJk3Izs4GICIigsaNG6PVOn9eSUlJtG3bFr1ej5ubG40aNWLNmjWO82VlZY5/BgUFAbBixQrHiKt+/fqxYcMGFEVh3bp1NGrUiMaNGwPg6+uLTqcDoLy8nM8//5xJkyY53V+j0VBeXg5AaWmp4x4nyhVFoby8HG9vb/R6PQaDwTEizWKxYLfbHW15eHgAYLVaqa6uRqPRANClSxf0enVgYKtWrcjKynK8rxPlZrPZUf/w4cO0aNHCcb5du3Z1vnshhBBCCCGEEOcp/wiseRM+7w+rX4f8pL+1+WqbnXVJeUyYtZVrPlrP/O1pZOUVUHlwFeblr2DZPAtb7qG/9Z7/RjJF7gIpisInn3zCrFmz8PPz45dffmHatGm8/PLLzJgxgxUrVmAwGCgpKcHLy4uxY8fi5ub2l1PdDh06RLNmzf7y/qdOYTshOjqad999l+zsbEJCQhzlwcHBjiDoZHFxcSxfvpw+ffrw22+/kZmZWavOL7/8wocfflirvKSkhJUrV3LzzTefsa+NGzfm/fffZ8KECVRWVrJp0yYaNGgAwIsvvsjtt9+O0WjEw8ODH374AYDs7GxCQ0MB0Ov1eHp6UlhYyNGjR9FoNEycOJGCggIGDhzIbbfdBsA777zDhAkTcHV1dbr/Y489xsSJE3n11Vex2+189913ANxwww1MmjSJrl27Ul5ezrRp0xzhWGZmJrfffjspKSlOgR+o0+R27dpFt27d6NevX63n/fHHHxkwYIDjeOfOnTz22GNkZGTw2muvodfradiwIW+//TaFhYW4urqyZs2as/pzF0IIIYQQQghxFioK4ee74dg69ThtCxz8Da7/HtwD/pZb7EotYtynm7Ar6vHTP+9l7eBiTItuc9Sxe0djHTcffUD9v+We/0YSMF0gi8VCSkoKt9xyCwB2u53AwEAAGjVqxJQpU+jduzd9+vS5KPcfOnQoQ4cOveB2XnzxRV588UU+/PBDevXqVWstqZ07d2IymWjYsKFTudVq5YEHHmDcuHFERkae8R5dunRh9+7djB07Fj8/P1q1auUIcmbNmsWMGTNo2bIlM2fO5OWXX+bFF188bVs2m41t27Yxd+5cTCYT48ePp1mzZvj4+JCSksJjjz1GWlqa0zXffvstjz76KP369eOXX37h8ccfZ9asWaxdu5b4+Hi+/PJLx59l27Zt8fDwIDQ0lIULF5Kdnc1dd91Fv379CAhQ/yX06aefYjabmTJlChs3bqRz586Oe02fPh2dTuf0Z9OyZUsWL17M4cOHefjhh+nWrRv169fn1ltvZeLEiZhMpjpHfgkhhBBCCCGEOE/5STXh0gnpW9XyCwiY/kwp5IetaWQUVXJ102A61fdnXVI+ANc3d8Prjwec6muLj2FJ2yEBkzg9RVGIiopiwYIFtc7NmDGDLVu2sHLlSj766CMWLlx41u02aNCAPXv20KlTpzPW+6sRTMHBwWzevNlRnp2dTfv27WvVr1+/Pp999hkAR48eZdWqVU7nT54ed7Inn3ySmJiYs16YetKkSY6paw8++CCxsbEUFBSwf/9+WrZsCcDAgQO59dZbAXXEVWZmJiEhIVitVkpLS/H19SUkJIR27drh5+cHQLdu3di7dy9ubm7s2bOHXr16YbVaKSgoYNy4cXz11VfMnz+fxx9/HIABAwbwxBNPAOri6rfffjsajYbo6GgiIiI4cuQILVq0cPQ7ODiYuLg4tm7d6rRoudFopHfv3ixfvtwRMM2bN49Vq1Yxa9Ysx1S4U9+1m5sbBw8epHnz5owZM4YxY8YA8NZbbzmNkhJCCCGEEEIIcQFO9x/wNef/H/b3ZhRz7YyNmK3qMiqrDuZyf584dqUWU2q24msEqoprXWe3VJz3PS8HMlTiAhkMBoqLi9mxYwcA1dXVHDp0CLvdTmZmJh07dmTKlCmUlpZSUVGBu7u7Yx2gM/nf//7H66+/Tm5uLqCOlJozZ06tekOHDmXBggW1ft59911AHTW0du1aiouLKS4uZu3atXTp0qVWO/n5atJqt9uZPn06Y8eOdZyz2+38+uuvtQKmadOmUVZWxmOPPXZW78pms1FYWAioO8AdOHCAzp074+XlRWlpKUePHgVg3bp11K+vprq9evVi/vz5ACxZsoSOHTui0Wjo0qULBw8epLKyEqvVypYtW2jQoAHXX389a9euZcWKFXzzzTfExMTw1VdfARAUFOQI2zZu3EhMTAwAoaGhbNiwAVB3Bjx69CgRERFkZWVRVVUFQHFxMdu3byc2Npby8nLHOltWq5VVq1ZRr149ANasWcPMmTOZPn06JpPJ8eypqalYrVYA0tPTOXLkCOHh4U7vPiMjg6VLlzJkyJCzep9CCCGEEEIIIf6Cfxw07O9cVq+nWn6etiYXOsKlExb8mUHPxuo6v9/ur6ay9e3OF+lc0AfUO+97Xg5kBNMF0mq1PPTQQ7zxxhuUlpZis9m4+eabiYmJYerUqZSVlaEoCjfddBNeXl707NmTyZMns3z5cp588knatm1bZ7vdu3cnLy+PW265BUVR0Gg0jBo16pz75+Pjw5133sno0aMBuOuuu/Dx8QHg8ccfZ+zYsTRv3pxFixbxzTffANC3b1+ne23ZsoXQ0FCnKXBZWVl89NFH1KtXz7EI94033siYMWPYtWsXd999t2Ntpvfee4/FixdjtVq54YYbAHWR7Ndff92x8PULL7zA5MmT0Wg0eHt789JLLwEwevRopk6dSt++ffH29mbatGkAeHt7M378eEaPHo1Go6Fbt2706NHjjO/i+eef56WXXsJqtWI0GnnuuecAuPPOO3n00UcZMmQIiqIwZcoU/Pz8WLduHa+88goajQZFUZgwYQKNGjUiLy+PSZMmYbFYUBSFDh06OAK5559/HovF4pgy2bJlS5577jm2bdvGJ598gl6vR6vV8swzzzhGX91zzz0UFRWh1+t5+umn8fLyOuc/ZyGEEEIIIYQQdXD1goGvqyHT4ZUQ2w3i+oKb73k3WXueCmg00Ds+CG83F6J93UgJDqOBXodu9/fgGQJNR+Cy/BnwnQm+Med9738zjaIoyj/dib9bYmIi8fHxV+z9hAD57sSlJ9+cuNTkmxP/BPnuxKUm35y41OSbu3D7MooZNX0DldU2R9k7Y1sxrFU4xZUWdqcVE0Q+DZeMg7BWUJ4PR1eB3QbXzob4y3fWypm+HxnBJIQQQgghhBBCCHGWmoR5893tHfnpz3Qyi6sY3TqCjvXUGSreJgNd4gKhsAIKkyHvoPPFNsul7/AlIgGTEEIIIYQQQgghxDloGelDy0if01fwjoAOd8D6d2vKDO4Q1OSi9+2fIgGTEEIIIYQQQgghxN9Jq1MDJo8g2DEbAhvDVfdA0JU7PVECJiGEEEIIIYQQQlweSrMgbSsUHlVDm/A24Ob3T/eqloNZpexMs+NiGkG7UdcQHuALesM/3a2LSgImIYQQQgghhBBC/PtVFsFvj8LeeTVlXadA94f/VeHN3oxirpuxkZIqKwCuLlq+u70jrSL/PX28GLT/dAeEEEIIIYQQQggh/lLeAedwCWDdNCy5h7Da7Ke/zmaB6qq/bt9Sru70doEW78p0hEsAVdV2vtmUcsHt/tvJCCYhhBBCCCGEEEL8+1nKa5fZbSSmZDN3s8KNHaJpFOKJ3a5QWGHBXa/gmrERZd27YC7B1uFO9A36gMnLuY3CY7BnHuyZCxHtod1ECGl23t1MK6yoVZZSUIHNrqDTas673X87CZiEEEIIIYQQQghxUSTllLI1uZDiymraRPvSIsIHg/48J1P5x4F7IJTnOopsIa3YXe6Hh0HPgh1pDGoRxu6MYrQaDX3cD+P6w3A0igKAPu0WyofORNdsBK6G43GIpRJWPA+756jH2XvgwGKYuAx8o86rm0NbhfPzzkynsuvbR1/R4RJIwCSEEEIIIYQQQoiL4HBOGdfN2ERumRkAjQY+H9+OHo2Czq9Bn0i48UdY+QqkbaQ8ug9rg2/kud8zeKKzOz28s/DN3ElKaTDv7NLRN3YJHA+XTjBtnc4+vy5EBPrh426EomR15NLJyrIhd/95B0wdYvx4c0xLpi07iNWmcHev+nRrGHB+z3wZkYBJCCGEEEIIIYQQf7utxwoc4RKoWc+bSw/SJtoXT1eXs2qjoNzMztQiEjNLqRfoTkJUQ4LHfMbBY2k8+ls623aU8VZvd4btvhtdibrO0QAXN6L6zkZf6FmrPZuLB8VVdvbtzWZwqzD0ihaDRgeK1ameXas/70WrPU0ujGoTQc9GgdgVCPA0nmdLlxdZ5FsIIYQQQgghhBB/u9Iqa62ygnILFusZFuQ+idlqY8aaI9wyayuvLTnAHbO38+zCfRRX6zla5cG2tHKCPY308CtEF9kWDB7qhdUVNDw8i5SgXuBiqmlQo6EwYRJrj5ZQVFnNvoxiDlsDyW9xu9N9LQFNKXCrd97PfYKfh/E/Ey6BjGASQgghhBBCCCHERdA6yhetBuwnzVKb0CUGf4+a0CW3tIo9GSXkl5mJ8XcnJsCNxMxSDuWUEehhJLfU7NTmL7uzmNgllkYhXtzW3p/x/on4rX8fNFroch8cXgHH1uNScJAfDincMvRHAjJWYakoJiWwB8/+4crAVkZ8TDoKCgupMHnxbcXV3Ni9KcG56yn2jmetvTlNbN5c+ZPa/l4SMAkhhBBCCCGEEOJv1zzCm1m3tOfNpQfIL7dwS+cYhrQMc5zPLzfz5II9/LYn21H25OB4Zqw5QnaJGix1jQugX9NgluytqaO1WYgxJ/NoVCLaijwIbAT7F8OKF6DPM5CykYz6Y1i0pYxGUQ35ZPdVVNsU0jZVMuXqCBqQSqvkefhmb6Q8th8loX0ZtMyPCN9ryC01E+2v46tu7pfsPV0pJGASQgghhBBCCCHEhakogJSNkLwWAhtCbHdc/GLp1jCQNtG+mK12/NwNTpccyCp1CpcA3ll2iGvaRTLzj6MA/HEoj/v7NnQETPEhnjQvXQNf3Y72xALejQdDw/5w8DdI3YSlzwv8kN2U/PJyskqqSC2oxGpX8DTqaeVTSac1k9EVJQPgnruf/lHbyO/9Eu+sy6F/02D+171+rb6KvyYBkxBCCCGEEEIIIc6f3Q5bP4MVz9eUBTeDG+aAVxjuRj3udSxFVFpZXauspMqKyUXnVOZjcqFzfX861w/gukYa9F+Nc94dbv8i6Pk4HPyNKo9IXsvrSrVWC5SzfH8OQ1qGMX9HOq4GHWHWNEe4dII+ZS3X9bEyoG1XfNxcMOid7y/OjgRMQgghhBBCCCGEOGdlVVb2Z5UQWJ1O9JrXnU9m74HsveAVVvfFQGygB0a9FvNJi363ifYlMbPEcezj5kLLCG92pRUx7890+gS64ltVVLsxmwVc3EgKGcRnP6bSOsqHV0c1x+Siw8OoJ9TLlYW7M3AzmWpfq9FgMBgJ8nI911cgTiK7yAkhhBBCCCGEEOKcVFXb+GzdUUZ/tIEdyXlgM9euZKs9QulkcUEezLqlHXFBHmg10K9pME8OboKvmwteJj3dGgbwybi23PPtDn7cnk5SThmf77JgDUlwbkjngiWoJSkj5vNNii/39o6ja1wgyxNzaBTqia+7gXaxfnx6czu8I5thje3pdLk94Sbwr3+hr+Q/T0YwCSGEEEIIIYQQ4pwczi1j2rKDAPyQpKV3w1F4HphbU8HkC4GNz9iGRqOhU/0AfrijE2VVVgI9jbi66GgS2pwp/Rrj6apnfVI+qYWVjmt+2FvKgIHP0sXwKtqUdeAdAUPeYZO9ObM3pbJkb5qjbq/GQXy1IYXZG48BEOBh4IPrW2Nt+hTRUYPxL96HLqYThvpdwaWOkU3inEjAJIQQQgghhBBCiHNSVG5BUaBttC+t6/uzJ+BuGnjVI/DoTxCaAJ3uAv96NReU50PqJkhZrwZPMV3ANwYAXzcDvm41i2ob9DqCvXTHf3eeeGWzK9z+WwUfjH4HbaNcosJCiIiIpkG5hYyiKqe6CVE+vLn0oOM4r8zCy7/uJ8DDwNqkcAI961G/wIP3Gvvj+fe+nv8kCZiEEEIIIYQQQghxTiL83LivdwP2ZJTwwcokvnEzcE+v6xl23e34+fiC7qS4wWaFLZ/AqpdrysLbwNhvwTP4jPdpFOJJ01Av9p60LtOoNhG8siKDQzllQCHf3e5Nx3r+XNs2kt3pxY56VdX2Wu3tSiviju71WZaYQ2pBJakFlRzLr6BZuPd5vwuhkoBJCCGEEEIIIYQQ5yTcx0R2qZlliTkAFJRbeHbhPpqGdaK9/ylRQ2Ey/PGmc1n6NsjZ5xQwlZmtJGaWkFFUSZi3ifhQL4K9XPnwxtasT8rnQFYpYb6ubDtWdDxcUv2+L5uO9fy5umkweeVmPl59BINeS8Mgj1r9TojyZd9JYZVGA3qt5sJfiJCASQghhBBCCCGEEMflJUHOXtDoIKSZYxpbrWplFhbvyqxVfjC7lPaxfs6F9mp1l7dTVFVVcjijmChfNwx6LV+uT+a1JQcc56f2a8itXeoR7e9OtL87FquNj1cfIdjLSP1Adw7nlgPqTnMAQV6uTO4Vx5i2keg0GtwMWu7tHcd7Kw5hV9RQ7Np2kTzy4y7HPa5vH0VsgPu5viVRBwmYhBBCCCGEEEIIAZm74MuhUFmoHnuFw7h5dS7W7W7QEe3vxu70EqfyAA9Drbr4REP8MEhcUFPm5s/8NA8e/WotHWL9eKh/I95YesDpsjeXHqRX42DiQ72w2RU2Hy3g1z2ZpBdV0bdJMD0aBfHd5hR6NgpyXKPVagj3qVmw+84e9enfLIRys5UofzcsVjuvjGzBrvQiOsT60yHWD6OL7jxeljiVBExCCCGEEEIIIcSVorIYqsvBIxi05xCcKAps+6ImXAIoSYf9v9YZMHmaXHh8YBNu+mwzFpu61lGbaB9aRPjUbtvgBn2fU9vZO5fqkNZsDr2e55ZUALDpaAEHskqxK86X2RUorqwGYF9mCTd/vgXb8Upzt6Uxtm0kP911FXHBXqd9LKOLjvhQ5/PXtHPjmnaRf/VGxDmSgEkIIYQQQgghhLjc2e1wbC0sfVJd86jlWOhwB/jFnuX1Vsj6s3Z5zt7TXtKhnh8/392ZQzlleBj1NAlT10yqk18M+xrdyWpLP/RGD15clOR0OqOokgAPA3llNVPp/N0NRPq6AXAwq9QRLp0wb0c6d/duUOtWeWVmDmSVUmmxUT/IQ6bAXSISMAkhhBBCCCGEEJe77D0weyTY1BE/bPoIzKUweBrojWpZZREx1Ydg2ffg1wBiOtcEUDoX6Hw/HFoCyWuh4Iha3qDvaW+p0WhoHOpF49DTjyBydK+kiolfbiOn1MzkXp61zqcWVPDxjW14/Kc97M8qpVGIJy+PaE64rzrdzcNYO77w9zDgqncepZVRVMkDP/zJxiMFAHi56vlqYgdaRvr8ZR/FhZGASQghhBBCCCGEuNzlHawJl07Y9R10m6qGSIoCO2ZjWvq447Q9uDmH+35KlTGIJrZEdBs+gILDEHc1xA8FaxUkLYPw1lh86rE/q5Tk/HL83Y00CfXC172O9ZZOI72wksziKgAyi6voWM/PEQL5uRu4rVt9moV7s+D6UJTccnSuGlwC7I7rW0R6cWOHKH7dk0V+uTrK6akhTQjwNDrdZ/uxQke7ACVVVt5ZdpAPb2yDq6y1dFFJwCSEEEIIIYQQQlzuDHVMAzP5gf74lLXCY7DyRafT2uzdlKfsIhs/mq+/Dqxm9cSOr6DFtVBVCgd/obzeADbneTHhi60ox2epjWoTwZOD4vFxqwmZ8krN6LSaOoMnb5MLRr0Ws9XOd1tSGdwilPv7xBEX5EnzCG8i/dwgbRvG2SOgqli9qNFAGPQWieXufL3xGDtSixjfOYZGIZ74uxloFu5d6z7HCipqle3JKKGsyioB00Wm/ac7IIQQQgghhBBCiAsU0gLCWjuX9X8ZvELV3+3V6oikU7goFuopqTXh0gl75kJwPABHCy2sPJBLk5Omwv24LY39WaUA5JeZmbXuKIPe+4PhH65j4c4Mys1Wp+ZiAtx5cnATx/GiXZnYFYWejQPVcMlSDsueqQmXAA78giV1K+M+3cTsTSnszSjhzaUHWZ6YTbMI7zp3f2sWXnu63qDmoec02kqcHxnBJIQQQgghhBBCXO68w+GaLyFjO5TlQnBTCGtVc94nClqMhZ3f1JQZvThgD6ehLqt2e67eYCnD5h3N1spQvt6Uwt09G7A3o8RRpbBCnaq2Yn8Ozyzc5yi/59sdfDmhPd0aBkJ1Famldo7kltEi3IsfJ3Uis6iKYG9X4kO8MBmOxxJVJZC1s1Y3bIWplFQ6L1Q+Z2sat3etT/0gj1r1W0X68OiAxrz1+0HMVju9Ggdy01Ux6LSas3iJ4kJIwCSEEEIIIYQQQlwJfCLVn7rojdDjEao9wnBJnEeFXxP2xE7g6aVm7mwTRqOgZrjk7HFUt111PzkWFzY2e4cXVpZjsyvYlZpd3PRaDbH+7qQWlPPFhuRat/MsPwYrZ8LB3zCFdqPArTfjl5dzQ4coHuzbqPaIIjd/aDTIOQADqn3jsNgsTmV6rRbtaQIjb5OB27rW4+qmwVisdiL83HA3SPRxKchbFkIIIYQQQggh/gt8o0mOGUtcl3s4ll/N1G/3UGq2MvegjZHXfEZw8W4oSccc1JKXd7oxb28hJZXqmkZto33wNqkRQqi3Ky+OaE5SbhnfbEoh0N3Iw1d50sUjA18PV3zcXXErXAdaHVjKCNj+LkND1pDb/XVeWpXCgGahdG4Q4Nw3vQG63A+FyZCy/ngg9jjWkFY0CNxHUm6Zo+rt3WKJ8nM77WNqtRpiA2qPbhIXlwRMQgghhBBCCCHElcRcBqWZYLOCbzQYasIYq9UKJh/iI+DHSVeRU2qm0mJl4bEigj07kdDEF5NBRy+lmB1ZFtw0Fp5vU0FE7gIqKwPocUN3Cj0aYNBrmTBrCwC/3BRJgxX3YXD3UXes2zFbvZlGCz0fh80z0GX9yYCOZbxj0JFVUnstKAACG8J130FxCuhN4BeLn1bHJze3ZfWBHPZlltC9YRAdYv1kytu/kARMQgghhBBCCCHElSJjJ+z7CTJ3QkhzNWBq2B+8wmpVDfAw8vvebB6dv9tR1iLcm3Edo3h0/h7eGNOCbtb1+C2+DQBXwNf0IQcHzmFbZRAALjoN7tlbMeTtheaPO+9Up9hh/bvQ+iZY/x4ZpdUMbB56xtFHmLzB1NypKDbAndiA2NNcIP4tJGASQgghhBBCCCGuBGW5sOheyNihHh9eDg36gGdYnQHTnvRickqruL9PHIdzy/l5Zwa70ovJKK6iUYgnkSYzPr+/6nxRZSG+hbuwGnoD4GbQYyzPVM/ZTtmJDtRd4fRGyqN7szDNnX4tg512oxNXDu0/3YHLTWFhIcOGDWPYsGF07tyZrl27ct999zFs2DAsFssZr929ezcvvPDCOd2vV69eFBQUAJCbm8v9999Pnz59GDlyJLfddhtHjx49q3ZSU1MZM2YMffv25b777quzrxaLhUcffZQhQ4YwdOhQNm3a5Dj3yy+/MGTIEAYNGsTrr7/uKM/IyGDcuHEMHz6cIUOGsHr1agDS0tJo0aKF41099dRTjmsmTpzI0KFDGTRoEE899RQ2mw2At99+myFDhjBs2DAmTJhAdnY2AD///DNDhgxhyJAhjB07lv379zva+uKLLxg8eDCDBg1i1qxZjvL9+/dz7bXXMmTIEO644w7Kymrm63788cf07duXfv368ccffwCQmZnJuHHjGDhwIIMGDeKLL75w1C8qKuKWW27h6quv5pZbbqG4uPi8+3XCZ599RqNGjRx/tkIIIYQQQoj/sNIsOLYBsnZD9Wmmj52N3P014dIJSctQyrLZnVZMZnElGo06tWxHSiHXzdjItGWHmLbsEJnFlVzbTl0gvF6gO/UDPVixLxNtdWWt25irKsguNnNDhyiKK6vJ8myqntC6gM7Fqa7iVw9LdA9+CL4PF3dfujUMwt0oY12uRBIwnSNfX18WLFjAggULGDt2LOPHj+ftt99mwYIFGAwGdT7raTRv3pwnnnjivO6rKAp333037du3Z9myZcybN48HH3yQ/Pz8s7r+jTfeYPz48fz+++94eXkxd+7cWnXmzJkDwMKFC/n888959dVXsdvtFBYW8tprr/HFF1+wePFi8vLy2LBhAwDTp09nwIAB/PTTT0ybNo1nn33W0V5UVJTjXT333HOO8nfeeYeff/6ZRYsWUVhYyG+//QbArbfeysKFC1mwYAE9evTggw8+ACAiIoLZs2ezcOFCJk2axJNPPgnAwYMHmTNnDnPmzGHBggWsWrWKY8eOAfD444/z4IMPsnDhQvr06cPMmTMBSEpKYvHixSxevJiZM2fy7LPPYrPZ0Ol0PPLII/zyyy98//33fPPNNyQlJQEwY8YMOnXqxNKlS+nUqRMzZsw4736BGmatW7eOsLDa/wVBCCGEEEII8R+TtRs+7Qef94ePu8Kql6Gi8PT1zeVwbD1s/woO/Q5lOTXnNHWvS1Sp8+SGmRsZ/sE6irXelFusvL7kAKXmmr+/bkkuJMzHRIsIL9YdyufnnRmEuWuwJ4xzbkznQnVgE1pH+/Bw/0bMvaMT2oi2VPR7C/YugF5PgXugWjcgDk372zHMm8BVEUYmdo3FoJcY4kp10f9kbTYbw4cP53//+x8AjzzyCL169XKMbElMTATUAOWFF16gb9++DBkyhL179zramD9/PldffTVXX3018+fPv9hdPmfvvPMOTz31FGPGjOH1119n165dXHvttQwfPpyxY8dy5MgRADZt2uR4D++99x6PPvoo48aNo3fv3nz55ZdnvMfGjRvR6/Vcd911jrLGjRvTtm3bv+yfoihs3LiRfv36ATBixAiWL19eq15SUhIdOnQAwN/fH09PT/bs2UNqairR0dH4+fkB0KlTJ5YsWQKARqNxjA4qLS0lKCjoL/vj4aGu5m+1WqmurnYk6CfKASora5L11q1b4+3tDUCrVq3IysoC4PDhw7Ro0QKTyYRer6ddu3YsXboUgOTkZNq1awdA586dHeXLly9n0KBBGAwGIiMjiY6OZteuXQQFBdG0aVNHP+rVq+cYQbV8+XKGDx8OwPDhw1m2bNl59wvg5ZdfZurUqY7nE0IIIYQQQvxHWcph+XNQlKweKwqsexsy/6y7vt0OO7+BzwfAz3fD16Pht0eh8nggFdAQQlo4XaLU68E2cwQlVVayS8y8+vsRCsss7MssqdW8udrGA30a8fOuDAI9jPSyr0Wbsw+6TYXQVtCgN4z8hBB7Lh3r+eNlMtA2xo8Af3+Gb4xjRvRr7HTrBF2nQLcpEN4Gfn8KynNoWL2fCN8zrL0kLnsXfVzal19+Sf369Z2mKD300EP079/fqd6aNWtITk5m6dKl7Ny5k2eeeYY5c+ZQVFTE+++/z48//ohGo2HkyJH06tXL8Rf7f4vs7Gy+++47dDodZWVlfP311+j1etavX8+0adN47733al1z9OhRvvzyS8rKyhgwYADXXXcdLi4udbQOhw4dcgQgpyorK+OGG26o89ybb76Jn58fXl5e6PXqH3dISIgjPDlZ48aNWbFiBYMHDyYzM5O9e/eSmZlJx44dOXr0KGlpaYSEhLB8+XKqq6sBuPvuu5k4cSKzZ8+msrKSzz//3NFeWloaw4cPx8PDg/vuu88pDJs4cSK7du2iW7dujuALYNq0afz00094enrWGbrNnTuXbt26AdCwYUPefvttCgsLcXV1Zc2aNTRr1gyAuLg4li9fTp8+ffjtt9/IzFTnBGdnZ9OyZUtHe8HBwbXeRVpaGomJiY56+fn5juAsMDCwzlFjZ9uvZcuWERQUROPGjev40xJCCCGEEEL8p1QWwNE1tcuLUuquX5gMvz/pXLZnLqXNb+bDI0EYXbTcNPBjfI/8jCb/MEqjAdgriwmzpHJba3++2l1JmcWKXVHo3zSE77akOjUV4u3KT3+mE+rlSn0/PaEpv6hh1xFPiL4KKotgz3xMegMkjHFcV1pl5WB2KS9lw21tNLRMex+KndvW2KvP/f2Iy8pFDZiysrJYtWoVd9xxR53r0JzsxCgRjUZDq1atKCkpIScnh82bN9O5c2d8fHwAdTTKH3/8weDBgy9m189Z//790el0gDqS5+GHH+bYsWNoNBpHGHOq7t27YzAY8PPzw8/Pj/z8fEJCQs753h4eHixYsOC05892nZ9Ro0Zx+PBhRo0aRVhYGAkJCeh0Ory9vXnmmWe4//770Wq1JCQkkJKi/gtv8eLFjBgxggkTJrBjxw4eeughFi1aRFBQECtXrsTX15c9e/Zw1113sXjxYscopU8//RSz2cyUKVPYuHEjnTt3BuD+++/n/vvv5+OPP2b27NlMnjzZ0b+NGzcyd+5cvvnmGwDq16/PrbfeysSJEzGZTDRu3BitVh2U9+KLL/Liiy/y4Ycf0qtXLwwGw1m9g/LyciZPnsxjjz3mNKLqBI1GU2vk0dn2q7Kyko8//pjPPvvsrPoihBBCCCGEuMJZLdDrSbCUQf4h2H18KRPviLrrW8qhjjWRqkoLmLW+gspqG5R6cY89CV14GzQ/TkCnKNQHptbrw/9G3IzbkR8wHk7ikU7dSCv0J7WwktFtIgj2NOLnbsAS5kXPxkG8t+IgRTGt8cn8E8ylcFCdxcJV96hrLWl1jvuHeBlpHu7F7vQS5iZWcHOnSUSse6ymg3ojRPz17BtxebuoAdNLL73E1KlTKS8vdyqfNm0aH3zwAZ06dWLKlCkYDAays7OdwpUTo2xOLa9rxMmpzGazY+rdxZSbm4vJZMJms1FQUOC45zvvvEP9+vW5++67yc7O5oknniAxMZFjx45RVlZGYmKi49oT11itVvbv309hofNcW4vFwqFDhzAYDGzZsqXO56qsrOTRRx+ts48PPvggERERFBYWsmfPHnQ6Hfv378fd3b3OtkaMGMGIESMAePjhh7Hb7SQmJhIaGupYR2nJkiV4enqSmJjI119/zVNPPUViYiKurq6UlZWxadMmRyCYlZWFTqfD39+flStX0qBBA6f7xcfHM3fuXMf0u5PLn3/+efr27QuoU95efvllnnrqKbKyshzT0Zo1a8aLL6rbYH711Vd4eXk5nmvq1KkApKenExgYSGJiIhqNhl27dtGwYUNAnc7Wrl07EhMTsVqtvPDCC7Rv357IyEhHO56enqxbtw4/Pz8KCgrw8PBwnDuXfp1Yi2nAgAGAOjJqyJAhvP766/j6+tb553cmVVVVl+Q7F+IE+ebEpSbfnPgnyHcnLjX55v47QgyVuBXsQVueTXVwKzRGD0w/3gjleWqFqE7QdgJW9OQQTPEp34VOp8PD5EFIWBu0GdtqThjc2Vbuz5CW3szdlkpPnyx0Fd6w9i11yt2JakeWEdB8BHj6QFUhXru+4O1+t/BHrgFj0WGaF+7CkFVE46jOfHrEl+GtIikIvg7vo7+hKc1QGwlsDC5ulEb2Iu2U/j09oAHP/ZrErvQSZha0YMqg6bjvmoXdMwxzq1tIL3XDWiTf+pXsogVMK1euxM/Pj2bNmjntRvbAAw8QGBhIdXU1Tz75JDNmzODuu+/+W+9tNBqJj4//W9usS2BgIG5ubhw7dozw8HDHPXU6HS1atCA+Pp5ly5ZhMBiIj4+npKQEDw8P4uPjHdeeuMZoNNKgQQMiIpyTaoPBQFxcHO3bt+fHH390rO8E6k5pZWVltG3b1rEm0ulcddVVHDt2jEGDBvHtt98ydOjQWu+osrISRVFwc3Nj3bp1eHp6cvXVVwNqGOLv709xcTErV67k7bffJjY2lpiYGPLy8ujWrRuHDx/GbrfTsWNHCgsL8fb2RqfTkZqaSm5uLl27dsXFxYXy8nKCgoKwWq18/PHHtG3blvj4eJKTk4mJiQFg69atxMfHEx8fT0ZGBm+99RZvv/02rVu3durziX5lZGSwfft2fvjhB7y8vBzldrudzz//nPHjxxMfH8/YsWN58MEHefjhh8nOziYvL4+hQ4ei1Wp5+OGHadGiBY888ojTPfr378/evXu5/fbbmTFjBgMGDDjvfp0Il0DdIbCucO1sJSYmXpLvXIgT5JsTl5p8c+KfIN+duNTkm7sC2W2Qsw/yD4ObHwQ1VUcefX0z5B0AwCWyPbgH1YRLACkbIGEc+ibD8VQMZGSVUlxZTYy/O4EeBn7bm807Px7iq2GvEbz1ddyTf6c6oCn7E57gmZVmHh8UQKi3K2Gu20DxcV78+4TCZNjwPgDa1jfhZs3HWFTBwG0Ta/qy/S3uHvoVV/2YjdKzAXfesgRd9i6wWcAtAHwi8PSrR11f7exbA8gqrsLTpMfDuyu0Ho1Oo8NNqyPub33J4p9ypkD8ogVM27dvZ8WKFaxZswaz2UxZWRlTpkzhjTfeANTgZOTIkY7pQsHBwY7RH6COfAkODiY4OJjNmzc7yrOzs2nfvv3F6vbf4tZbb+WRRx5h+vTpdO/e/W9pU6PR8P777/PSSy/xySefYDQaCQ8P57HHHvvri1FH89x///28/fbbxMfHM2aMOl92+fLl7Nmzh3vvvZf8/HwmTpyIVqslODiY1157zXH9iy++yP79+wG46667iI2NBdRF25944glmzZqFRqPhlVdeQaPRsGXLFt599130ej1arZZnn30WHx8f8vLymDRpEhaLBUVR6NChA2PHjgXU9aKOHj2KRqMhPDzcsSPdBx98QFFRkeNYp9Mxb948AO655x6KiorQ6/U8/fTTeHl5AbBo0SLHlLW+ffsyatQoQF2bacCAAQwcOBCdTsdTTz2FTqdj69atLFiwgIYNGzJs2DBADUO7d+/O7bffzn333cfcuXMJCwvj7bffPu9+CSGEEEIIIa5wScvhu+vAfnyHtmajIeFGR7gEgF/906y9lEqxzYXXluzn603qsiSuLlrev641ezOKCfA08EuWD1uq7qRP+3tILtWyYp2Z8Z2jeG7RPnJLzcT3DaJ/xhyo1wOOrKppW6tTp6qdsGM2uqbX0N6nRJ2qd4Ki4LvpNRbe9h1BgYHo3AzgF3VWj+5lcsHLdNK6wrqzW6pEXBk0inLSmLmLZNOmTXz22Wd8/PHH5OTkEBQUhKIovPTSSxiNRqZMmcKqVauYPXs2n3zyCTt37uSFF15g7ty5FBUVMXLkSMfucSNGjGDevHmOKVh1udT/FUD+q4P4J8h3Jy41+ebEpSbfnPgnyHcnLjX55q4wpdnwSU8oSa8pczHB2G/VEUoaLZRmqb+HtoBdPzhff/33rNO25YaZm5yKm4d7Mah5GPsyS+gQ60dGSSVtjBk0Kd2AyZKHpcEAntthok+4lXBtIc0iAzCUHkO7bz4cXoHiHYWm/W2wZaY6iuk4pc9zaA4thfa3QuExsJkh9wCkbYHbVoG7/8V7V+KydKZ/Z130XeRONWXKFAoLC1EUhcaNGztGf3Tv3p3Vq1fTt29fTCYTL730EgA+Pj7ceeedjB49GlBHz5wpXBJCCCGEEEIIIf4R5jLncAmgx6Mw7zYoz1WPg+Ih7moIbakGUkdXg1YPXe6HiPbkHnBexPvWrurskU1H84kL9iS3zMyoyHLq5e8ENzt4hcGfH/Bms2swLHscKgtBZyCv1xvsavgk1pip+Jp0tFv7P6dwicDGaPIPQeMBav9sxzeniu2uBk8SLolzdEkCpg4dOtChQweAOreeB3UK2NNPP13nudGjRzsCJiGEEEIIIYQQ4p+UU1oFQJCnq/MJzyCI7QFHV6nHwU0hY0dNuASQk4i92RhyfFoReE1fdEXH1KlrfvVA50KUX83GT0NbhrEtuZAdqUUArDyQy5AWIcT47oXlz4FiVyu2HIshZa06LW7vfLBZCFgxhbJOPzB5WQWuLlp+GPYOTQ98iC5tI0pMFzThbSA/CTZ/UhMuARxdjabjpL/zdYn/CO0/3QEhhBBCCCGEEOJyUFRh4asNyQx85w8GvvMHX25IpqjipPWLjJ4w4BWIuko9DmqqTjk7RVnOMa7/Po3t2TZ1qlxgI9CpaxfFh3nyysjmuBl01At0d4RLJ7TzKUe77KmacAlg53cQ1MR5jSWbhQDUsKqq2k6qoQG6MZ+Tf/1SKsI6wbJnwCMEio7VftCqotplQvyFSz5FTgghhBBCCCGEuBytP5zPkwv2Oo6fWrAXk4uO7g0DCfI6PpopKB5u+AFKMsDoBdu/UHeVO0l2QAdStlfww5ZU2sU47yptctHTrWEAn9zUhgqLrVYf/F2q1Glwp3JxhUNLa471rrj4hNO3iZbr20fTPtYPDHpyymzUj+kELm6Qugnq9YTDK065SYNzezFCICOYhBBCCCGEEEKIszJnW1qtsp93ZjBrfR0jmQIbqbuoaXTQaABoNOoopTbjqfCqj11RMFfXDpCO5JZxy+dbOJBVxp70YpqHO+9Inafxxx7QyPkirZ5qv7iaqW4Gd450e5u3tlkpqqgmLtgDd2PN+BJDZGuYsAQaD4b2t6shE4CbH4z6FIJbnN8LEv9pMoJJCCGEEEIIIYQ4C/UD3Fl5Slmgp5HFuzPp3jCQDvVOWRi76BisfAGiO0PXKaAocOAX4oNasPhqN/TRTWrdY+2hPK5qEMBHqw+TW2bm0f6N6VQvgB2phXSs50+WVWFLwiu02fEY+rxEcA8ktcur3POrlmtazSZMX4KrbwjTdypsOJqHXqvBZq9j8/jQFuAXC3mHoMfD0PtJdcqcd/jf98LEf4oETEIIIYQQQgghxFkYnhDO91tSKTVbAfA06mkY7Mm87emUHy9zYvRU10U6tk79Oc7g5kP89jexVPyJEvksGpeaxcKP5JXh6epCTqkZgE3JBVRZbGg1Gqw2O7/tzebTQjPXN3+djk0sNIkO44mVBfyZXsSf6QA6dNo8JvWoz+pDeYxICCfMx1S7bxWFsPoV2PTR8b56wQ1zJGAS502myAkhhBBCCCGEEGehWbg33/2vIw/1a8R9feK4o3s9PlyZhIdRT2ygR+0L/Oph73XKbulNhsGfX0PL6zBs/5yitP0ApBZUsGJ/NglRvui1Gkf1HSlFxId5seloAR+vOcKgFqHc2DGKJiFudHZNJmrZHXxk+ogfh7jg724AQFEUvFz1TOgcw6jW4bjo6virf9aumnAJwFwCix5QgychzoOMYBJCCCGEEEIIcWWoLIaKPDD5qusJXQRNw7yJsGdhTt6EtTyfngOaoQlLIDbAvXZlrY6j0aOIHBaAoSQZNFrI3AmHl6uBTmwXTNYi0nPy+WJLNtVWOy0jfQj2MjK0ZRg/78ygW1wg9QM9eGlEc3alFfL5uqM8O7gJI6t+R7tUDa/c+JM2yb/zTs9vGbfYwqAWoZitNtpG+9Is3KfuBynNrF2Ws1fdQc7N9+96XeI/RAImIYQQQgghhBCXv4w/YfGDkL4VAuNh8DSI7vT336fgCN5zx6jrKwFhGg3Wa78D+teqejCrBHdLETpzIVQUgEcwlGWrJ61mCGiE647PCbIrNPS/nXKfcB6fv4fhCeH0aRLMsFZhvLciibVJuTzQ1oVrA8t4ZEIM3r4uaKa/7Xyz6ko6afay9dpYzKHhGN198Pcwnv45fKJrl0V3BveA83sv4j9PAiYhhBBCCCGEEJe3smz44WYoSlaPcxPhm2vg9tXgX+/vu09RKqRtg1bXQ8Z2OLgEFAXNsqc54NqEBlGR6I5Pb9t+rABrURqx6yahy9lT00b3h6AwGVqOhepK2DQdF0WhZ7s4vlKuobLaxrebU9BpIdDDSHJ+OT/0rqDhmrvBXAo6A7aBb6JreSO4+ahtuJggdRO66lL8f7oeBk2DdhPO/CwhzaH/y/D702CzgF896P+qum6UEOdBAiYhhBBCCCGEEJe3wpSacOkEcwkUHj1zwKQooNGc/vzJMnfC16OhLEc9jrsaWlwD+xag0+lYtvsYGVWuRPiaiPJz48OVh3mhWTouJ4dLAJs/wT7iY7R758PObx3FgUd/JqzlCMfxztRi/N0N3NPalYbr/qeGSwA2C7qd36CENEez4vmadlvfBKbj0wKXPwsN+515wW6jB7T/H9Tvo74rnyjwCDq7dyFEHSRgEkIIIYQQQghxeXP1Ap1BHYlzMtNp1hLKPQC7f4TkNdB0BDQaoAYsp1NdCStfrgmXAA4thVGfgk809vICBvmmY9C6k7UnCXNUBGFuGnTWytptmUuw2MD1pHAJoDQgARfXmoXCj+aV07mBP9H6XHV63cnqdUez6hXnsh1fQY/Hjve3AhTb6Z/nBK0OAhv+dT0hzoIETEIIIYQQQgghLm9+9aHvc/DbIzVlV02GgEa165ZkwLfXQ0GSepyyAdK2wpB3wWBSy+w2dcSQwQN0eqgqhrRNzu00Hw1bPoWU9WiBGD6FltcTlrsf/tjOIwm3Uuo7BvSuYK1yXGZueh27q4JoGdQKQ86faqF7IH+Gj2Xm+hQeGxjPr7szMVvtdIj1QykqV4OyypN2d1PstZ9LUWoCtvZ3gNcZRi8JcRFIwCSEEEIIIYQQ4vKm00PCTRDWWl3fyCscQpqBsY6d3XL314RLJ+z+AbrcB8FNIfcg9i2fok1aCvV7Qbvb1PWJGlwNu76rucY/DnbPdW5n13fQbQpkbMdtx0yKYgeRN/IHvDe8hkvhIaqaXktJ03HoCSR/yCzITaSkvAIloBG3fZNGVXUlSTn76Vw/gHBfE62jfSkN8qDS6yNMP00ESxnoXCgJSMDLM9R5JzjvCHW639UvQNOR6ugkIS4hCZiEEEIIIYQQQlz+jO4Q1UH9ORONto4yDVVWOzmpKYQvvhVd1k61vOAIypE1aMYvwtLpXlyy96LJ3g1aHXb3IGq1dMrIIreKDD4takv7jh/Q0FfL8ytzWfThITSaQ4xKCKfcEszKAznc2tWAl6sLVdVmqm0Kqw7mMntie77ZlML0VYcJ9nTlvWGLsRenc6jcxM9bTLw7ajbuq59TR2BFd4E+T6sjuVxlkW7xz5CASQghhBBCCCHEf4KiKBS518M7qCnanL2OcnOz65mVqGVAwJGacOk4Tf5BrLmHKLK7ExTRBhoPAEBbVYTiGYamNKOmclRHyKpZ1LvQNZyZ65JJjg9Eq9GwaHfW8X6AuayQpxMqeTJgPyWGYjoMaMqBcncqLDY61vMjOb+CV387AEBJlZX+X5Xz4fWtiY0y8WpHE+6eRgj9Rp065+YHhjpGawlxCUnAJIQQQgghhBDiP2H1wVwOHTzKzR3uwpCzC/IPYYvuxlraYtS64e5S93VpJTZ8SzbBtlk1hXoj9HuFymNbMGVspDpuIDrPQLTLngYXE+ntn2CnJYIgrzR6xwfz4uL9jkvjg008FbSWwAVvABAGhNcbRFSv14mOCKfaZueV3/ZzqmX7s3nrmlY1BUYP9UeIf4E6xgYKIYQQQgghhBBXlvTCSp5buJeB+i0YFt4Ju+dARQG6P14jsvooesWGR+52iB/idJ2t0WB+OGZCe+qOcFYzmg3v8YXHRB71f5cB+/ryWlZbkoYvYu/QX1jlMYgZG7IY0jKMbzen0Czc23Hp/5pB4I53nJrzPLKYcOsxAPRaDQ0CawdHsf4ySkn8e8kIJiGEEEIIIYQQl05RKqRvh/IcCGoCYQlgcDuvpgrKzJRUWQn0MOLueua/3uaWVdHQ30B4ykK1oCJf/QFCctfSOqEjrnPfUAOmHo9AUQp4R2ALasH02bn0GtyMtlqdusPccalNbmf6ugKKK6sBSMqFoJAm1A90J6u0kIPZpfSKD2LT0UIeGxjPgawSMoqrMGmqwVZdq496awUAGo2GOzuHU1ZeztIDRVjtCn7uBvo2DT6v9yTEpSABkxBCCCGEEEKIS6MkE+ZOhLRNNWXDp0Or68+pGUVRWJeUz+M/7eZYfgVX1ffn6SFNaBTiddprgjxdKahSKA5ojnfmn07nqvyaUGrVY/WJQb/zO9DqwSMIyvOwDJ6Bohh4YK2G6X1m0/jwZ+jKs6lsczszD0dTXFnqaMfdoCPG342WkT5cVT+A4a3CqbLa+H5zKm8uPcC17SLxcXPB4K9BCW+LJn1rTSfc/MC/AVSVwOEVxKx/l/f1bpRedzc7dc2ICPShXh2jmoT4t5ApckIIIYQQQgghLo2s3c7hEsCSx6A4/ZyaOZRTxsQvtnAsXx3xs/5wPg/N3UVxpeW014T5mLinTyP2hI0G9wBHud2/IV7NB9CyQRTWPi+AzgXsVijJgNAEtOEJXNsukpRCM0MWKrwX8AzfNJvBN+ariIqIINDTCIC/u4H7+zakoMLMgaxSXPRa6ge40dTLwjfjWxDsZeTLDcf4fksqLh5+aIZ/CC2vA5Mv1O8DN8wD3xg4shLm3Azp29Ae+wPvH6+lm9tRCZfEv56MYBJCCCGEEEIIcWlYymqXVRWBteqcmknOK8dstTuV7UwrJqOoCm+T4bTXdY0LJNWvHdkRi/EuTcJoMKANboqrd7haoUEPuHUF5B0AoyeEtMDNK4ynh1gZ1zGa/DIzqw/m4oWRZmHefLjqMAOaheBlcqHcbGV/VgnH8ivIKTXz281RmHZ9Bbt+IC6oCcuvfYijxnZ4u7kQ7OUKBMCQd9Vpeq5e6i5wVgts/Kh2xxMXQUzXc3pHQlxqEjAJIYQQQgghhLg0Ahqpu69ZzTVlTUeCV3jNccERyN4HGg0ENQW/mFrNeJtqb/fm7aongmzY9RuUZatrO4W1rrW+U6S/O/g3BhrX7p9WC6Et1J+TuBn06LQaknLLCfAwUi/Qg8nf7mBgi1C8XF1IK6ygRYQ3u9KK2ZJcyFXRHhjWvAx75qgNlKTjkrKehretBK9GNQ3rDeAVWnOs0aph06mMnrXLhPiXkYBJCCGEEEIIIcSlEdwEbpwPvz8F+UnQfAx0uhNcXNXz2fvgy6FQnqsee4bCuPkQFO/UTKMQT0a1juDH7WmOsjnXR+I5bxzkJtZUHDkTWoyp3Y/SbMjdr06FC2gEPhEUlJvJKKzC3VVHtJ87Wq3GUX1LcgE3ztzkGDXVOMSTQS1C+WxdMm4GHW2jfTHotKw+qPZ7QjM9uhVzne9pKVfvGdiI09LpodNdcGgpKMdHaOldodHAM7xUIf4dJGASQgghhBBCCHF2FAUKjkJ1BXhHgsm77no2qxqQ6E+ZrqbRQExnNTSylIN7oBqqnLDr+5pwCaA0E/b+VCtg8nEz8PigxoxsHU5OqZlYfzcalK11DpcAlj4Gsd0o1vmSVlhBaZWVYHs20SvuQpu5Q63jFU7p6G+5dm4Rh3LKcHXR8uTgJoxMCMdk0FNutvL6kgNOU/L2Z5XSr2kIOq2GCouNNYfyGNQ8FJ1WQ5CnkZYxgeDiXntKoMtZ7JYX1Qlu+VUNmfQmaNAHwhP++joh/mESMAkhhBBCCCGE+Gvmctj5jTr6qLoCItrB0Pch6KSpZnY7pG2GjdOhNAva3wb1e4Obr3Nbrl51TwXL2K7+U6OFkBZgM8MpO76d4OdupHMDY03BrsralSoLKS4r474lKbSL9mXWhqPMb3ewJlwCKEmHbV+gKEMAqKq28/j8PTQO8aJNtC8VFitHcmuvHVVmtuKq11JuseHlqic2wJ0Pb2hDuI8rgV6u0Psp+PWhmgtCEyC4WZ3P4kTnAlEd1R8hLiMSMAkhhBBCCCGEqFt1FVQWgKs3ZP0Jv0ypOZe2BVa+CCNngItJLcv8E74YDLZq9Th1Iwz9AFrfeHb3a3EtmEvVdZmOrVVH8LS4Buw20OrOfG1gPOgMYDu+k5xHMErvZ8jJzeGapt5oyjP4uXcxQem7al3qmb2ZRv4jSTpp8FRKQQVton3xdzcysnUEM9YccbrG391AucWGRgNPDIqndbQvet1JG7XH9QPPEHXnPN9YiOnivN6SEFcYCZiEEEIIIYQQQtSWvQ9WvQxHVkFEe2hcxzpAB36B8jzwiVSPUzbWhEsnrH0TGg+qPYqpLg36qP9ccFdN2f5F6pSxyPZnvjakGYz7CZY/p46AajYCzZJHiasqokFwc+jxCJqU7c4jro7Lix7Ilu3OO9kFeaqjo7RaDTd2jKag3MK87Wl4urrw6IDGNArx5IPrE4j2d6dhsKdzuJR/GL67QZ2yZ/IFnRFunPPXzy/EZUwCJiGEEEIIIYQQzspyYc54yDugHh9epq6ddKrgZmA8aaqbrvbubuiMdY8+slRCdTm4+atrMwGY/GDnd8717FY1yKorYDKXqes0GTzU0UExneHGH7Fn70H7eX91zShAk70b/ngTvMKgLEcdKbV7jrpOVPxQrPEjKV2fTICHgTbRvrSI8KZpWM1zRfm58eKIZtzdswFGvZZQH3XEVkLUaUKzwytq1oOqLFT/uXkmDJ721yOxhLhMScAkhBBCCCGEEMJZYXJNuHRCzl6IHwqJP6vHBnfo/4rzQt9RncDoqU5zO6HnY7XXW0rdoo6Oyt2vhj1tbgbfmNP353hQ5CT3APz6MBxZCR5BMOgtaNifSo0rlZlH8Tv1mozt0KAXrHkDwhKg64PYozujjWxPiMGduXeEsmJ/Dgt3ZWDUa0kpqMDHrWaRcqNeR0yA++n7eLLsvbXL0reBtUp9b0JcgSRgEkIIIYQQQgjhzOCmTjNTanZOY/dcuG0VdJwEVcXg3wAC4pyvC2kG4xfD/sXqSKEmQyGyg3Od3APw1TB1FzmAtW+po5CGvAN6I1x1DyT/UVNfq4PGg8grNbPhSD5rDuYysJEn3f98BO2RlWqdshz4YRzctpKDtljMFW7UGu/kFQ7l+ervGTsgYwfaCX3A4E61zc6cbWnMWp8MwMHsMlbuz+WnuzpTP8ij9vux2yBnPxQeUXfCC2wCppNCtPq9YNvnztc0HyPhkriiScAkhBBCCCGEEMKZfwPofJ8a/pyQcBP4169797eThbZUf04nZ39NuHTCru+h61SyXcJIVppSf8R3+CZ+i8bVE23CjVQGtGTt/jyO5pVTZrZSkJ2K9sgK5zYUBWtuEhm6EH5P8SIu/gZ8E79Wz+lcULo9hOb3J2vqR3dxBGQZRZXM3njMqblSs5UD2aV1B0wHl6iBlt2qHneYBD0fVRdDB4i+Cro/DGunqXVajFUXLhfiCiYBkxBCCCGEEEIIZydGEsV0gYLD4B0F4a3/Olw6Gyd2nDuZwYMqdDz1816W7M1Gq4EmYbcxpk0EA3xC+Xh5Ep+vS8auQOsoH8KaB4BnqDry6ST7ivXo/DXMS6zA2ugarus2AA97CWavaBpGRuJ59YtojqxUn6tBb3X9J0Cn1WDUa7FabM5dPXnh7hOK02Hh5JpwCWDTdHW0VvRV6rF7AHR76PgOeHbwjVbfqRBXMAmYhBBCCCGEEELU5uanhjD0hsJjUJymhipeYefcVHGFhTKzlQBPI8aQZhDaCjL/rKnQ+ykOVPiwZK+6dpFdgT3pJRzMSsTP3cCna5MdVbenFLEw1Ivwq14k6vfb1OlqQGm9QcxN82Xbn4d4fFA8r/22n58PaAn0COKLCc3xCvaG4JugzU21+hfuY+KBvg15fnGioyw2wJ0moXUEalXFUJ5bu/zUMp1eHQkmxH+EBExCCCGEEEIIIepmt8PB3+CnSVBVBB7BMPozdQTQWVAUhQ1H8nlu4T6O5JYzqHkI9/SOo941X0DqJihMgYi2EN6GnMMV9GsaQqMQDxQFft+XTX6ZhT3pJbXaXXMwlyC3xowZ8yvm7IMUKh78lOHLV7vUqXdDW4byy+Su2Mxl1CvbjmHlbeqoojbjIaJdza51x2k0Gka3iSQmwJ21h/KoF+hO5wYBhPvWMdrKM1TdPS97z0kNaME39mzfqhBXJAmYhBBCCCGEEELULf8QzB0PVrN6XJYNc26G21eDd4SjWlGFhb0ZJeSWmonyc6NJmCeuLnoOZJcy/rMtWGzqYuHz/8ygzGzj3esSMLWIcVx/JLcMq10ht7SKJXuz0Gs1XNsuEqNOS7S/W61utYz0JszPk6lrS9BqGrI2KQ+oWdfJZNATF+wJe5er/T1h9w8wYQmEt6nVprebC73jg+kdH3zmd+LmC8M/hPmT1J31TL7qAuVB8X/5OoW4ktUxoVQIIYQQQgghhECdFnciXDqhPA9KMhyHJVXVvLH0ADfM3MSbvx9g/6EkslIOo1jNJOWUOcKlE35PzCazuNKpbE96Mb/uyWJ7ShEAVrvC15tSaBHlQ1W1jY71/Bx1g72M9GgYhNmmsDOtmOGtwjDqa/5qG+rtylX1A8BcDnt+VEcXnWCrhiNrLvCloC5iPn4R3LEO/vcHNBkGOpcLb1eIy5iMYBJCCCGEEEIIUTf3IDWgUU4KiQzu4BbgODyYXcrsjSk82cWDG6MKMe79BP7cihLdhXat7sFFp8HP3cB17aOw2RVcXXToteq6TG4GPS56LVabwsYj+bVufzCrlNmbjjGpe336NgmmpNJKmdnKEz/twcOo55tbOxAX5EmTMC/2Z5Vi1GtpHu5NlOUIrPsZtDro9SQkLYNj69RGT5ked97c/NQfIQQgAZMQQgghhBBCiNMJaAj9X4bfHgFFUQObIe+BX816QyUV1TQJcef6oGMYV02DgiMAaPbOIyhzFy/3nUGx3pdXfz3gGM20N6OYm1u4E2s7ClUldAuIY02sLz/tynK6fYi3K+VmG5XVNl797YDTObPVQnGlFTejniZh3jQJ81ZP5OyDLwapi3ED7J0PPR+DrN1gM0Ns94v0soT4b5OASQghhBBCCCEuV9VVkJ8E1ip1kWl3/7+3fRcjtB4PkR2hLAu8IyGgIenFVRzOKcWg0xHi7cqNTVwwlac7wqUTNAVJ9AgsZeTiYqepclGGUlrveBmXI7+rBToXnh/1HZuPuZJRXAVA5/r+BHoYsdkVFAX0Wg1Wu+LUvslFV7vPadtqwqUT/vwW+j4HIc0hrNWFvhUhRB0kYBJCCCGEEEKIy1F5HqydBhs/UEcXhTSHUTMhsPHfex8XV6dQJjGzhPGfbya7RF2bqV+TYKZ2CYEM1zovN+vdKakqdCobHJCDy+rfawps1bgtf5Qfbp7P3gI9Wg0YXbQUVlRzf584Vh/I5dp2kXy9KcVxydVNgokL9qh9Q7u1dpnNAo0Hg0fg2T+3EOKcSMAkhBBCCCGEEJejtK2w4f2a46zdsP49GPQ26C/OgtPVNjufrj3qCJcAluzLplWUD0F+jfBqMhz2/aSe8K+P0nUqPkd/YXkHE7td23DfahtFFdV42Ipqta0rPIzGUkGgVyAjP1zvKA/1dmVM2wiah3vTrWEgR3PLiQlwIyHSBx83Q+1OhrcGvas6quuEzveCsY4wSgjxt5GASQghhBBCCCEuRzn7apcd+h2qCsEj6KLcssJsZduxwlrlSTllTD3ixeOtbyY0tie6kjQIbYF2zs24K3bcgR4Gd97p/hX3rFQwBDes3Xb9wazP0uDmVknDYA8KK6rJLTWTWVzFu8uTeLh/I65tF0W/piE1F1ktkJMIhUfVZw5uCiEt4OZFsHkGFKdCo4GQugmOroEej4FnMFTkqwuV/91TCoX4D5OASQghhBBCCCEuRwFxtcuiOoGr99m3UXAUMnaApQyCm6nhjFaHvSSTArOGTIsJBYXkvArCfU00CfWkf7MQpq867GgiLsiDno2DyCv1ZqfGyK8VUbSIMNFmw10YTt59zlJOe+tWXh41jkMaK96DpuO+4jGoLMQS24fM1vezeEMBwxNMxAZ40N7DQIi3iQ9WJhHi7UpCpC9+7qeMWEpcCPMmqlMEATrcCV2ngN4IHSfBxumw6iWorlTfS+pGtSz/EAQ0gmHvQWSHc3jpQojTkYBJCCGEEEIIIS5HEe2g2WjYM1c99gqHbsfDlbORfwRmj4DCZPVYq4PrvseethXtpo/wM/lR3PoR3kmOomlUEJO/+5MnBsUzpk0EezOKWXMwjyahngxoHsq93/2Jza5gctHxQN+GVFmq0VuKa92yqrSQMi8rK44WkBXTmauuWYqbxsLnuy18/2Me17SL4r7vdzrq+7kbmNy7AS0ifGgd7ePcWOExWHx/TbgEsOlDiGwHP05U38XuH2rOJYyDFc9D5fERWHkH4Lvr4bZV4BN5du9MCHFa2n+6A0IIIYQQQgghzoNnCAx+CyYuw3zDT6SNWsA2czhFFZazuz5tc0241KC3On0s40+0niEQ2AhtWSb1i9bzTMtiYnR5DGgWwvI9qXiZM/lkdCy/3deFqf0aY7UpjEgIR6OBymobH65K4mCBFUu3J8DFVHM/jQalYT82Hy2kdZQPUX7uTP4lhwFfZ1GqGOnXLJTvt6Q4dbGg3EKIlyudGwRg0J+yY1xVce3d4kCdOqjYQXNKfRfXmnDphPI8KHK+pxDi/MgIJiGEEEIIIYS4XLl6k6hvxIS5W8gsPgiou6s9N6wZId517+rmUFGg/jOqI3gEq6N7Tuh0D7S+GVa/it+2WfTziqDXqM9QMvZj+GESis6FuF5PE6F1J8ZPy3qNF+G94vhs7VHe66mjTcGHGI8exNb3BbT5SSiZOylvfy8TlikUmQv4fV8WZWYrjw+K54XFicT4uxHmY2Lhzoza/dScpv9e4eqOebn7a8p0LupILIAjK6H5GNg9Rz3W6kGjVcOnE7Q6MPmc+T0JIc6KBExCCCGEEEIIcZmyWG18tPowmcU1O6Yt3ZfNsFbhDGoRevoLqyshqLH6e/1esPIl9XeNRj32i1VHH7W4Bky+4B6Ey0//g+pyaD4GTWkWuvm34tH9ETxSNxIZ1IJtfoNo2cdEl7U3gLkEAF3yH1T2eIbpIa+Qvk/hz4x0p26sS8qnVYQ3XRoEEBfsSXJeOS//WhMYuRl0NAn1qvsZ3P1h5AxYcDdk7VJHdA18E5Y9o55P2QjxgdDnGdAZIKQ59HzcOUjr8yz4115wXAhx7iRgEkIIIYQQQojLVGmVlS1HC2qVH8wuZRCnCZgKk2HZs+rIn77Pg71aLdcZoM/TkL0PsvfC1k9rrmlxDXiFwrH1sOED6PIAGDzBZoGk5egj2hNVtAWdm5cjXDrBtHEaY64bwpsbSokPNPJoGxuh1nTKdd7stin4BMYSE+AOwKg2Efh7GPhmcwr1AjwY1zGaRiGnCZgAQlvCTT9DWZa6iLdnqPocP/1PHaGVshHa3Qr1eqj1w1pDbFcoSlPXXQpqCnqXs3zbQogzkYBJCCGEEEIIIS5T3iYXescH8dVG53WEmoWfZic5RYEds2HvPPV49SvQ/xVw9VGDmK2fQ7NR8Mcbztft+gF6P62uV1SSDoeWQkxndUoaQEUePvYiNH6ta99To2XpvhyGJ9QnOmw/sSsnORbmbho3CHu7abjo1OWBAzyMjG4TybBW4ei1GjSa082PO4mbr/pzQsOr4fY1UJ6jTv3zjqg5Z/RQd42TneOE+NtJwCSEEEIIIYQQl0LBEXVETWkWRLSF8La161jNUJ4LRi9wPcPIneP0Oi03XxXLnvQSdqQWodXAhM6xtI7yca5os0L2HnXnNIOHOiJp1w9gKYelT2Id/jG6ynw0+UnqGkV2W821Gi1cNVmdPhfTFfzrQ1UpmItrFsj2iQGvWH7P9mCIyddpMe2MhPv5eEsF3zcuJXbTk067vrkcWgxpYyBdB4GN1B9wBE7nzSdSdoYT4hKTgEkIIYQQQgghLrbCY/D1NZB/qKZs5CfoXFvVHOcegNWvwv7FENwM+r2oLsD9FxoEefD5Le04VlCBUa8lNsAd46k7rh1eDt+OrVngOqYLtLgWdn0PVUVYLGbcCo+qI5Iq8sE3pmaHuXa3wv5FkJ/kaE7p+QQajRbWvwPtbkOpLERvqUKjbc+hAd/il7wY95IjpEQMYnpyGDmlFbhYK9Tw7FTZe2HN6+DiBuN+gigZXSTE5UgCJiGEEEIIIYQ4HasF0repI49MvhB9FQSex6LQmTudwyWApY/jO+on9feqElh4P6SsU4/Tt8LskXD7agiI+8vmfdwM+LgZ6j5ZlgOL7nfePS15LfR8DAB7WGsqy0txS/z5+DS5z9TpcIkLIW0zik+UOrLpJJp106i+fh5av3rotn2OJmM7LsCAwCbMqvcWis8tlGoLWbevnK0pZQR6GHHxjYD6feDwspqGtDrQG9XfqyvUtaFu+B6Mnn/5zEKIfxcJmIQQQgghhBDidI6sgm+vqZnW5REENy8+95CpurJ2WVUxOo5PRStOrQmXTrCUQ96hswqYzshSDqUZtcvdA+HGeZh9G5F15BD+uQfALQC6PaQukN12AvZuU6ksKcD91GutVVTZwHPRZKcpb7rcfVzfowh75lrcj83hrsAWZHefQFVAM4IDvKD/S/C7Cxz8VV0bqcMdsGVmTbt5iWApk4BJiMuQBExCCCGEEEIIUZeqElj+nFOAQlkOpG4694ApqIm6u5nNUlPW9lYKbSb8APQmdYpYdYXzdWexDtNf8giBRoPUaW4naDQQmgDhCZiAEK079j7Pol35AhxbB+4B0HUK2l+mkjPoW2KNzrvDWVvcQCnueHZ9EKqrYN9PUJwGgKEsHd3aF9Tfcw8QeeR3uHU54KWusTT6M3UdqvI8+HokmEtr+tV0NLgFXvgzCyEuOQmYhBBCCCGEEKIuNgtUFtQuPzkQOVshzeCmBbDiJSg6CgnjoNUNWDLL1PN+sdD3OfhlSs01jQZBYPz59f1kBhP0eUZduPvgr+AZAgPfgOCmjir+vr7qzmqd7wMUsFTAypeoDmvLYVso3qPn4vPnR2izd2NtPhZ9owEErX8Pdn8PBnd1al3aVpTSbHS5+5zvX1UEufshoMHx/riBfz3wCIQ+z8Kyp9VRS42HQMc7QCd/TRXiciT/yxVCCCGEEEKIU2XtUhefbn0TrHq5plyjVXeAO1cajbp+0w3fq9Pl3APU8szEmvMtx0JQPOQfVqfihbUGd//z6391hToqSqNRjwPijo8cysSqdyMfHzxsWtxP/hthUDwcXgF/vAmKHbtPDNvi7uW27/eh1WhYft80Yry06I2esOJ59Lu+Va8zl8LaaViHfkixRwP8546o3R9dHetDGT2h3URo0AdsZvCKVMMwIcRlSQImIYQQQgghhDhZ+jaYNUgNglpcA1dNVhe8dg9UF8YOSzj/tg3u6o/VDGW5eLuedM7oqe7uFtPl/NsvSIY9c2HfAqxRV1HU6Dq2V4VQL9CdBkGeJNmC+XB5Esv27aJZuDcP929Ey0hf9VqTD3SdQmHMQHYeSWNHqQ8f/VKGooBNUThWZCEmKAjK89Xd506hLUnj85zWjGs1meDNNaGcPTAe7UmjpWrxjT7/5xVC/GtIwCSEEEIIIYQQJ9vxdc2i3Lt+OB4sPQHNR4PR48LbzzsIq16FxJ8JDWgEA15VRzedGG10QmURpG2GlE3g30Ctc6YwxlyK8tsjaA7+CoA+axd+B38lteF07vu+lO9v78gzP+9jW0ohAOsP5zPus80sursLJoOOwopqAjwMlPs04t51ufSvrzCjp7r+1Ko8L0K8jqdhBjd16t7xNZdO0PpGMyo8kqW7+tO2RyyhBZsxhMRjbNgTvMMv/L0JIf7VJGASQgghhBBCiJOdEpxQnguHlkLb8RfetrkUfnkYjqwAQJO9G2aPhNtXQ1Djmnp2O2ybpa5PdEJYaxj7DXiF1t12QbIjXDpBW3SMG4JT2Fs/hK3HCh3h0gldotzwylqP9cgfuBqD2ebakuDYpvxyUyT+Kx7C9Y81AHSO7IRW/wHgBS4m6P4wpKxXd6gDCGkBkR2J9fMgrFtzsksaYjcMx83DeCFvSwhxGZGASQghhBBCCCFOljAODi05peyGv6ft4nRHuORgrYL8Q84BU2EyrH7FuV7GdsjZd/qASatTR0GdvOsd4Fp6jHsjyvi1OgqDTovFZgfA2+TCS01S8ZkzyVE3wjOCJconNDXuQZe6xlGuT90AiT9D1/vVgsh2cNtKyElUA6fg5uAdBoBRryPKz+3s34kQ4oqg/ac7IIQQQgghhBD/KrHdYPh08I0Fv3ow4iOI7vr3tO1iUtdaOpXRy/nYXq0GT6eqq+wEv3pUJ9ziXBbaCoqOEX3gM+p52bm/b5zj1LjmJnzWPe9UXVuaRlPtUTSnhmCghm52e82xTxS4+cGx9bBvnho2CSH+s2QEkxBCCCGEEEKczOQNra6Hhv3VYze/v69t32i4+iVYeE9NWcN+ENTEuZ53FDQZAXvn1ZS5ekNgo9O37eJKVacH0QQ2Qp+6HnxjwG6DDe9jjbyKltGBdHRzp0WED0k5ZXQPrYYDpbWa0djM2Or1QnvKdDsa9gPtSWMUkpbB9zfWHLu9Bbf8euY+CiGuWBIwCSGEEEIIIURd/s5g6WTNR0FAHOQnUaXzxDW2I3gEOtcxmKD30+oIqj1zIaSlOj3Nv8EZm/YMjKDKfBX6Xd/B4RXqmk8aDdruUwj29wGgc4MAOjcIALsde4dJaNe8VtOAzoA+pBn64GA49BscXq6WR10F8cNq6lUWwfLnnG9ekQ9pWyRgEuI/SgImIYQQQgghhPi72Cygdam9I1xZLpSkqaOQfGMhuhNEd+JoYiLxXiF1t+UXA72egE53gcEd9Ge3YLZrRAsY9j4cWQVVJdCgJ9qwNrUrarVo296C3eiFdttn2LyjMV/1IH7RrdEY9DD6c3VtKEUB//rOgZutumaB75NVn2EKnxDiiiYBkxBCCCGEEOK/Ke8Q5B0Eg4c6Re3UUUTnoiQD9i+GXd9BWBtofROENFPPZeyAuROg4Ih6r0FvqtPfXM4QGBUeg/RtUFkIwc0gLOHc+hPSrOb+Z+IVhrbzPdB6HDq9ETcXU805kzdEtK37Oo9AuOoe+O2RmjKtHsJbn1s/hRBXDAmYhBBCCCGEEP89qVtg9gh1ChlAvZ4w7APwDj/3tqzV8MdbsOUT9ThtK+z9ESYuA1cf+OluNVwCCIqH4lTY/QP4xeLpcnxUkN1es75RYQp8cy3kHl80W6OBa2ZD/OBz6laFxUphuQVvNxc8jC5nrmzyOae2AWg2Wl20fPMM8AyDLveri4oLIf6TJGASQgghhBBC/LeYy2D5szXhEsCRleqIofMJmIqPwbbPnMvK8yBnn7qGUs4etSygIUR1hBUvOKqFXTUZShvDjq+gfm9oOhJy9taES6BOUVvyuHqte8Bf9yfvMJWZiaSWa5hzzJPkKhNvdtPhXbgHNFoIaw3BTf66nb/iEQhtxkOzUaAznPUUPiHElemiB0w2m41Ro0YRHBzMxx9/TGpqKg888ABFRUU0bdqU1157DYPBgMVi4aGHHmLv3r34+Pgwbdo0IiIiAPj444+ZO3cuWq2WJ554gq5d/6YtQoUQQgghhBD/PZZSyD4etij2mvKS9L+4rgKy96ojkLzCILgpGD3VdrR6dce2k2l1YPJV65ZkQJNhsO5t5yrr34Wej0HKBvVn/yJod2vte5dng/Uv1jfKPwLJf0D+IUxu/jTaPYf7jUEUtn8Q72+ugeoKtZ7RE8YvhtCWZ27vbBk9/552hBCXNe1fV7kwX375JfXr13ccv/HGG4wfP57ff/8dLy8v5s6dC8CcOXPw8vLi999/Z/z48bzxxhsAJCUlsXjxYhYvXszMmTN59tlnsdlsdd5LCCGEEEIIIf6SpRK6PwJdHoA+z9TszBYUf/prbNWw40v4tA/MvQU+6webPlYXtfaJhk73ONf3jYWgpuAZAkPfrxndY6uuu+0TMv8Er3A1nDpZmwngGXr6/hUchdmjYOFkWP8eLHsGWlyLe9ZmQsv2gbWypq65FHb/ePq2hBDiPFzUgCkrK4tVq1YxevRoABRFYePGjfTr1w+AESNGsHy5uu3lihUrGDFiBAD9+vVjw4YNKIrC8uXLGTRoEAaDgcjISKKjo9m1a9fF7LYQQgghhBDiSlVwFL4eA789DH+8Acufg7YTYMBr6tSxupTnwtE1sPQJ5/KVL6qB0Ib3wS8WBr+tLt591WQY/Rn4RKr16vWE//2h/tM7wrkNV2+wW53LTN4w5kt14XGTLyTcBA36OI+2OlXGDig84ly2bRY0Hoy2LBt0p0xfK0o5fVtCCHEeLuoUuZdeeompU6dSXq5uX1lYWIiXlxd6vXrbkJAQsrOzAcjOziY0VE3k9Xo9np6eFBYWkp2dTcuWNUM3g4ODHdecjtlsJjEx8Yx1/k5VVVWX9H5CgHx34tKTb05cavLNiX+CfHdXvnoVf2IsSKopUOwo278id/CX5B9NB5ynyRlddEQlfYXeYKg9+kixo+QkojGXwsbp6mLcne4GvTuW5A0cLXPHbq8JhTQaf6KGzMC07BE0WbvUkVNd7ncKruxtJmCvKkefewDa3qIuDn5oKez8mpLrfiHd6l3nc9UvK8RwamFFPph8qApogumU6XVVjYZxVL71/yT595y4WC5awLRy5Ur8/Pxo1qwZmzZtuli3qZPRaCQ+/gzDW/9miYmJl/R+QoB8d+LSk29OXGryzYl/gnx3/wFbNtQq0pRlEeTrSVB0HVPQcg/C5g/VdZE8gqAsp+acqzcakx8suq+mbMlj0O9lDPkHadT5rrr7oH0BktdAUaq6FlTrm9R/trgO7bF1aL8aotbzCodOd0L+YfXQXoRXfMfa7VUWQ24TdVrdyetANR1BpV88eb4JhA2ahu6P10Gjgx6P4NqwN/Emr794WeJKJP+eExfiTOHkRQuYtm/fzooVK1izZg1ms5mysjJefPFFSkpKsFqt6PV6srKyCA4OBtSRSZmZmYSEhGC1WiktLcXX15fg4GCysrIc7WZnZzuuEUIIIYQQQohzEtJMHWmkKDVlbcaDRzBlVVb2Z5WQW2Ym0teNhsGeGOzV6hS2HbOh1xOw9VPIO6SusXT1C+qi3H71IPoqKE6Ho6tg30/Q49HT98EjGDZ8oPahw//AxR0aDQIXV9j2eU29knQ4uBRiuqqLd3ue8vcgm1UNqpY+pYZLwz9SR1KVpKuhVZPhmIKaEKnVQnR9iB+iPvvZ7EQnhBDn6KIFTA8++CAPPvggAJs2beKzzz7jzTffZPLkySxZsoRBgwYxf/58evXqBUCvXr2YP38+CQkJLFmyhI4dO6LRaOjVqxcPPvggt9xyC9nZ2SQnJ9OiRYuL1W0hhBBCCCHElSy0FVz3PSx9Esqy1WlobSdSXm1n+urDfLAyiRHxHoyOrsRS4YXB2xfa3Q5bZsD6d6Hnk2oQ5B8HScugQV813Elarq7D1O9llLxDlJltbNq8C8+AcNrH+qHRaKDaDPkH1TWdbpwHxWmw9HF1VJTOgNLpbjSn9jdjB7QcC3FXQ2Bj53NZu+Dr0TWjlhbcBQPfhIb9aodRAB6BF+GFCiGE6qKuwVSXqVOncv/99/P2228THx/PmDFjABg9ejRTp06lb9++eHt7M23aNADi4uIYMGAAAwcORKfT8dRTT6HT6c50CyGEEEIIIYSom96gBjAR7dWd1TxCQKvlUGohH6xMYlIbN+42LMLdJRJ++0Jdx6jDHTDuJ6iugAO/gF8DsFrAPRASF8K++WrbpZmQ8SeaUZ/i+cM1dIkbxhrdw6yz2mkdbsJtz9fw2yPqYt16V3Vh8RPhkM2CxuBWq7u26KtQEm5GH1AfXEzOJ7P3OE+Js1nUwCquz8V5d0IIcQaXJGDq0KEDHTp0ACAyMpK5c+fWqmM0Gnn33XfrvH7SpElMmjTpovZRCCGEEEII8R/i5gv4Og4LyixoNTAsMAt3fRgse0qdwuYTBQZ3+OkOKM2CsDYQ10/dfa7pMEhc4NxudQUUp0LXKbiWZuFWnMT8w2aa6apx++3hmql51ipY8Tx0fxRS1sORlZC+HXvr8Wh3fAGKgt0nlnWRk4gx1CPq1HAJwOBZu8w9QA2vADJ3wa4f1Cl9rcZCbI/jzy2EEH+/Sz6CSQghhBBCCCH+bSL93PAxGfCpSgdtUU0QlHAjLHtGXYcJIGMbrHkdQltAdRUYPMBc4tyY3ghFKVCSTus4I0b7AUxleud1n/wbQNsJsPsHqCpUf88/TEZITxK7DsFgr2RbqQ+rd2r4ss1p/toWnqCOpjqxK55Go64L5eYHOfvhi8FQVayeO/QbDHwD2t/2d70yIYRwIgGTEEIIIYQQ4r+nqkQd4ZOzF/SuNAhtyUfjWlOWWQpV+2rqKUpNuHRC1i5oeDX8+a26u9zat2rOBTeFzJ1qnfihuFXl0G7tndDrSdAZILI9aPVQv7c6ne1E6PTHmyi9n+KAtgG3LT0GaPEyVfD5+HZ4uxnqfgbfGLhxDqRtg8pCCG0JYQnH+7izJlw6YfUr6kLfniEX8uaEEKJOEjAJIYQQQggh/ntSN8LPk9V1kwCNbyxxA6ezyaURse5WdD5R6igkv9ja15p8Qeui7taWthl6P41SVYLGM1hd8Hv9e+q1wc3UuifuN/xD2PaFOj3O1UtdByp1k6NZzY7ZdL5lPD/dFUFJZTXR/m5E+7uf+Tn86qk/Z+PkEVRCCPE3k4BJCCGEEEII8d9Sng/7fnaESwAUHsU7bSV6fTfuSYzkjWGfYSrYhwYtNBkG+46vtaTRQOd7IbwNRHeBolQUSzmamC5w8FdI3wb1eqqjhPbOh+jO6nX1esGPt9bcL2Uj9HlGrX9ihJTJD1eDkVbBWshPgeICqPKCgDgw1rHe0pmEtACjl/P0ve4Py+glIcRFIwGTEEIIIYQQ4l+rwmwlKbeMwgoL0X7uxAT8xYies6EokHegVrE280/6VK7Cr/FU5mXHcd2RX9GFtVRHHPV8HGxmdQHtpBVgqYDwBOzhbdHEdodVL6qhEUDGDgiKhw6TYPMnakCUubN2P5KWQ2QHOLZODa56PHq8/WWwZy5k7Van1NXvo+585+J69s8YFA/jF8HO7yHvICTcALHdz/OFCSHEX5OASQghhBBCCPGvVFxp4YOVh5mx5ggAHkY9n97clg71/M+rvWqbnZT8CtAYqRfXH03qZucKIS1g/Xs0dplJZvNXsXjHYrJZIeNPOLjEUa180AccMvtiUcxEhwYRnPJHTbh0Qk4iNrcAdAVJ4BUOBrfaHTK4Y48fhrZeD4jtqu5Ql7sffnsYCpPVOrn7ISdRXRQ8pOm5PXBoS/VHCCEuAQmYhBBCCCGEEOfHVg0FR9TRPL7R6u5lf5eSTEhLpLOrmYyG7iw6WE6Z2cpj83cz545O+Lkb1XpWM1Tkg6tPrRDHbldILayg2mbH0+jC15uOMX31YaptCj+P7U7zVjei2fkNaLTQ4hooOgbWKtyKD+GhtVDSYASmhTeoO7yZy6CyiKoG/Xl5XxAmdy8qzFYeCUw+7SNYDD64jP4KXf4BNAFxsGM22CzqSY0W6vWgzKsBXgnX11xUmFwTLp2QtgVKM849YBJCiEtIAiYhhBBCCCHEuassga0zYdVLatAU0gJGfgJBjS+87ey98O31eBcl0x1IiBtBROub+Wh7BYdzyymuqFYDpuxEWP0qHFmhjv7pNgWirwKNhqqCdIqT/6SsqJiD9jAqPWN5d0USAFoNpBeW0ySsLfr4wZC2FQ4tUaekAeVNruPNNdnc0CGKNgO+Q5e9Cx9fE7u9o7l7bgklVXlAHjd3isYtJA52z4a4vnDod8cjWGO6Y6ssxjTvRrXAMxSGfahOn7OUqmszBTUhs8SI18nPbqhjCqBGo66nJIQQ/2ISMAkhhBBCCCHOXeYOWP5szXHWLlj1Moz4+NzWCjqV1QLr3oGiZEeR16H5DO/el0+0vjQL88bPwwjleTB3AuTuUysdWQE5e2Dst+AehGH+bQTbzASX5dDUXELywG/QaNTll8a39qW/1yE0iQvB1ReCmkBRKuhcKG12E1+VtWNXegn9y6vJ8I6kwDeYapvC1Hm7nLr6zeYUbu3SnchOd8LhFWrIlncIW1RnbAHxePx4U03l0kyYdyuM/wViOjuK7UWJzs8f2hJie8DRVTVlrW6AkObn/06FEOISkIBJCCGEEEIIce4KjtQuS/pdna7mHX7+7VYVQ/IftYp9y5JoHNKTF4Y3w9vkAmnJNeHSCWU5kL4Na0Aj9PV7qCOTQluCTxThe2fQNfY21hwp47YmVjQLn1TvBerOaj0fwxYYzy854aRnVDCpewi/7skiIcqH91YkcUvn2Fp90mk16uiiet3VkKqqBDyDKVk3E9/UNWAurv185Tlnfn43Pxj2HhxZrY52iuoIsd3qXsNJCCH+RbT/dAeEEEIIIYQQlyGvsNplYa3B9QKncpl81F3TTuEZ3YrPb2lP8whvtcDFpK5jdCprFbqUDbDqFXU3tm2zYOOHuES0omeMGtJ4VmbUhEsApVnw28NoLGV8uTmDjOJKiiur8XVzIcDdyIxxbSiprCbC1+R0q/FXxfB/9u47Pqoq///4a3pNZtJ7T0hCQu9VwIIi9t7ruq71u7bVn7pr2XV17W0ta++9Y6GIFClKbyEkIb33SSbTZ35/DEyIQQQlIPh5Ph55kDn33nPPvcyDDO+c87lJ1h1t5hiIzgJXJxErHw4W/c4+uu/Y1HqIyf3le2BNhZEXwOxHgrWhwuJ/+RghhDjIZAaTEEIIIYQQYt8lDochZ8LG94KvDRFw9N2gC/tt/ao0eMddhap+HQpTTDBIikjDmDkBo3mXpXeR2TDhWlj2eG9b4WkQkYHik7/07dPegl8XTpwliRcuTEURWBtsT5sIcQXQuAXq1uBWaKjrcLC5zsaz54/k03V1nPH8ck4bmUSjzcmpI5Owu3zUdjjITwgnLdKAUqn4yQUoQaWGiqUw5aZg4FYyn0B0Doqj7wnOdBJCiMOQzGASQgghhBBC7DtzHMx6CC79Bs7/EP60EJJG/eZuO3rcvLRVQfPYv+F390DbdtxR+aD8ye/GNToYfRmc8jxMvA5m3BFsX/s65J/Yr1+HysxVb6/lto830hmeS2D246A2wIb3QK0jcMrzLGwKo73HA0B5Sw9fbWqgo8fDi0srGJsexfOLt/PhmhpKm7p5e2UVgxMs/S8gPAGm3R78fslDwfBq5IUoTnomGGgJIcRhSmYwCSGEEEIIIX4dgyVYI2hfdTUGAyNTVL9Nm+tsjNWUE/v5+cGK3ID2i2vwKZWoRp7Xd2edKfgUO1sd+NyhZu/sJ1Gvf2uXcUbwrS0Z6KK5y0W3ywvfPwrtFcHtZd9CaxllmU8DkBppoLbD0edUjy0o4cWLxtBkc6JWKSlIDCczxrz76xtyenBZ25ZPISob8mZDTM4+3SIhhDjUSMAkhBBCCCGE+O06a6BmdfDpb3GFkDwa9D+Z4dPdCOvfgWVPgMYER/0DBh0LWlNoF4OvmyH25aFwaSfViqcgMg2PNYsyhwmPz0+2pgPDzpBoFwGFgrZjnsS67X1c0YMpjpvN3z63A6BTK9F3VaH4yXGKjkrGWzo4fkgSs4cmcP07a/tsb7O7MWpVnDIy+ZfvhcEK+bODX0II8QchAZMQQgghhBDiV3G4vWyp70LjamPw8htRly/s3XjU3TDxWlCqetuKvoB5f9/xogU+uBQu/BQyp4V2GaquQqXazX9TdGZY8ghqlY6NcdfSqo5jTmcn12Ucg7F8bp9dNXH5RCaPxjf+At78fjv//HBraFtsmA6vWv/T3gEoTE/klsJc2u1uLp6YzvNLykPbThuZRHbsz8xYEkIIIQGTEEIIIYQQYt/5/QE+WFPDnZ9s5t1jPH3DJQguXcufHVwiBuDqgh9f6N9R6YLegMltR7X8cUidALpwcNkgd1awoLgpFtxdKFw9nBrTzLcdSv7fhm5GTL6WaV4nuurFYIzEd+yDqOKGAKBSKjhpeBLheg2fb6gnNdJIvEXPJqeSiCGXErHxpd7rGXkx+qhU0swm0qKCXxOzoylr7iYt0sSwFAthes3+v5FCCHGYkIBJCCGEEEIIsc8qWu3884siAHQBZ/8dvK7g104qbfDJby3F4Pf1tocngqsLZ91mFO5udKXzoeZHmHR9cKnZ9kWw8L5gTaMJ18CKp1G5bBytCydj2iOct9jKqISbOWbSDSTFRrOiRc8VCjW6Hd3HhOk5c0wqI1KtPLGglM831HHqiGQmjrkSf+IglF21oLegbNgIG96F8VeBUkmEScu03Fim5cYGO3J3Q/168HkhMhOMEQNyX4UQ4lAlAZMQQgghhBBin3U5vWRG6Tk/X40+OhqicqC1pHeHzBlgTQ1+73FB/VpIHgWxecGC3MufAkMEZByBf8kj6Jc+AlNuDAZRzk749l448u9Q9Fmwj+HnwXf/BnewlhIuG9mLr2f+mR9y8qcOvix2cMPReh6bv41puTFsqO7ks/V1jEyL4OThieTGh3P/6UPpcnqIMurQVC2Gb24Fta43CCuZG5wxFZXZ92Jt9bDgHthZODx5HJz8X4jOHrgbLIQQhxgJmIQQQgghhBD7LFvXybsZcwj/8RXQmnFN/huKjiq0W97Dm3silYMu4tPFdUzNiWakYwXKd8/tPTgincA579ChS8TX2kL00keC7Vu/gJEX9i6l8/T0HqNQ9IZLO7nthNUs5rPjx/B/P8SxtcFGQaKFd36oZu7mRs4fn4ovEGDB1iYUCgWD4sIwaXf8F8i9o+9dZ1l5HODbzWysyu97wyWAmpWw7g048h/BcQkhhEB5sAcghBBCCCGEOPSYtn1E+Lr/gc8DjnZ0827Fl3EEzecv5Lza0zjylVqeWFDKnJVFKObd2ffg9grc3e0sKWnF2rGxt725GGy1weDmpGcgftguBymCs412pdaB341x1X+5cIiRLzc2MLMgjvdX13DV9CzmbaplnLaC433foi39iq7G3qLdRA8K1nnaVfYxYEntf7FVy/u3bfs6uGxOCCEEIDOYhBBCCCGEEPvK0QFrX+/XbKhbwZyeAlZWdobaYgwBFD2t/fbVOFuZVfce6tSxoFBCwB/cUPwVZB0JC/8Jphg44hZY8QxseA+m/b9gu88DKg1MuQnWvoHCY8dS0MXotAgmZEWxvrqDbzY38tjoVrIXXA6BAAC+jcPh7DfBmgzR2Xgv+AxlzUqUnh58Si2qvOOCT6v7qaRR/QuUZ0wDjenX3T8hhDgMScAkhBBCCCGE2DcaA0QNgtayvu0R6XT0ePo0vVvs4fLhF6Fd8Xhvo1KFMiIFZeVi6CiH6bfDsifA2UkgdxaKquXBmUy2WrA3w6hLIHkMNG+DM98IFgFXqmDdW9BRSWDwSSSn5fByfhh6jYpjC+Opqqkm88d7Q+ESgKphHdSvA2syPbWb0X56FcrmLQA488+kK3028bu73vQpkHNMsEYTBK991MWglAUhQgixkwRMQgghhBBCiH2j1gULcpcv6q2TFJkFiSOZ5VPxtFFD+46gqbLVgTvzKLQ+OxR9Hnwa3KhLYO3bcMStUDoPfvxfsPaSWocj6ziMn1zWey5bbTB8GnFBcElbRxUBZyeKVS9CwE8gJp/AhOuICA9D0dMMijCm5MRQpmhFuaGu/9idneDzol71Auod4RKAqeg9lFnT8QVaUUWkgymq9xhrCpz6PLSUBAuUR+VAWNwA3FghhDh0ScAkhBBCCCGE2Hdh8XDue9BZDWp9cNnaS8eSqA9jyay7+U95FsurezhpeCI+ox8qvodZD8GGd+GrW4JBTfEXwXpL390Hy56kJ3kqLzuO4Zzko4hs/8mSNEsyLP4PTL0F/9BzUQ07G7fHTaU3iqaGbkatugl98ccQnUvsjDtQZIykp+BsjBte6+1DoYSYPHDZ0FZ82++SDLXfw3d3gTEaTnsB4gbvsjECUsYOzL0UQojDgMzpFEIIIYQQQuyb8sXw3BR4dTZ8fn1wltH3j4LHDl0NmL/4MxektZAVa+b5xdt5r0wNp/4PHO0QkQ6m6FBX/u3f0XrU47TO+h8vRN3Ig0taWGI9EW/SjjBHoYShZ0HzVvD7CNhqUSUU0q0Kx7bpG3LmXcSE6ufRR6cFZ1PV/ABvnUlM/UJ0k67CN+qyYAAWmQXnvAsJQ0EXjid9ev/rsqRATys0bYYF9/Q+aU4IIcQvkhlMQgghhBBCHG6atkL1SnB1BWfdJI4IFsX+BYFAgI01nczb0ojd7eWYgnhGplrRqlW9O9nq4KM/BcMiCM5EmncnTLsNmopCu4U1r2VZ2ShsTi8ZqkYCi/+Loujz4DK3sVdA5VKoWoFTFc5zrcNo7Pbw6brgkrb/m9/NmEsfILFjHXTXQ9m3ULMKAEXiSPC5MMy/FXPZAgCUTUXBcGj0ZbDyWfA6oWEDKoBZD8CUG4J1o3ZZ9hYYewX+qmUoW4uDDYOOhY5K8HuDr8vmB8MmrfFX/RUIIcQfjQRMQgghhBBCHE6atsKrx4O9JfhaoYQLPobMab946IaaTs58bjkub/CJbp9vqOPxs0cwMat3xhHdTdDV0PfAQCAYNO3CoYvB6fZTEG9kYvO7wXAJwGWDJQ/BkX+Hmh9xj7qcicpY7vmitx5SQrieyNJPIDwKVr8K3Y3B08QNwZM6he7qYiJ3hEshndWgD+99rdJA8Zcw+MTgU+N+QpswGN9Fn9PTVILOZ0f143PBouGhQYwAveUX75kQQoggCZiEEEIIIYQ4nFR+3xsuAQT8sPDfwaewaU17PHTB1kZcXj9D4vTcNcpBSsdSlOWb8ZuORhlfENzJFAPm2GDQtJNCAWpD6KUvIpMV3hzcPjtn5usxrvu037kCfh89p7/D5jYFb24t5uaZuWiVCjbW2ZiRF4v2xw9g9XMw9k+gMQbPodTwvw1e0uhktkIZvLZdKXZUAEkaCR1VwXpLe6AKj8MYHhd8Ul1RQu8GvRVm3tc3sBJCCLFHEjAJIYQQQghxOOlp201bM3jdvQGTxwUtW6GrESxJED0IVBocbh9alZKHx3QyaP4lvcevfgwu/hKisoJLyE56Gj64NLgET6mGY++H1AkQnghqHd6YIaR3R/F6lp/CaCXU5EL1ij5DUqi0mN4/k0m6cMbMehRXxdcYe2o5csgZEB2Hd/CpKNe/BcueDB3TfcILPDG3nGEJBiYVXETEppdD2wIpE1BYUmH6/wvOsCqZBxOv27t7ZoqBY/8Noy4Cpy14nZEZe3esxwWtJcGn00WkB++nEEL8AUnAJIQQQgghxKHE54WWbcEZOuZYiMntOzMpfVJwtk8g0Ns27i9gjAh+7/XAujfgyxuD+yhVdMx8km/VU5iSE0NzayuZmx7oe05HO5QvgeVPw/q3gjODznw9eB5TLERlQ+MmWPcm1K5GlzmDCTNuh7gds56OvgtePwU8DgACSaNRdFQFzz/+KrRf/hWtszO475aP4cSn2B59FOrp/yV945MoA24qC65io68Ql3c7P1TbeSrqJM6aOpKYttWY00ehyZoGfjc0miG2ACb9H0Sk7f191Yfv+1PinDZY8Qwsuj84m8ocB+e8DUmj9q0fIYQ4DEjAJIQQQgghxKFk21fw/sW9xain3wETruoNmZJGwznvwbf/BGc7jL8aBp/Ue3zrNvjq5t4Ayu/DOv9GfKPf4fEfNNx3XBrqzzr7n7e7AbZ+HgxSmrbAG6fApfMgbjC0V8Kbp/XOniqeA21lcPGc4BPjUidQceqX9NRtIdZqIrp6Hmz+CMb8KVj02/mT8313H4GTJnH8/ChOzHsQtVLBZ4vs/PmI3kLlL67r4TVVNKcOv5R/DC1Ao93xX5uo7N9+j/dWw0b47r7e192N8MWNcOEnYLAeuHEIIcTvgPJgD0AIIYQQQgixl9qr4LNre8MlgIX/hOatva/VWhh0TDDc+dN3MP7K4EynnbqbwO/r26/HQbTSxurKDkptGvwTru27XaEMBia7BkGBALTseAJbW1n/pXnNW6G9IvTytVI9s+ZFcP+WaDxuF0y8NhhYOXazpM/vI9KgwePz8+5GG2+u76TL5aW8pZv7Tx2CWRcMk4YmWblsaiZG7UH6vXlnTf+2+rW7X6YohBCHOZnBJIQQQgghxKHC0RZcrvZTuxbc3kkftvs+LMmgMYSWqwFgiKDCbQG6sTk8KAtPBKUKVjxNwBiLZ+L1aFb+F8VP+zJEAuDTmFH9dJtS3Wfp3uScKF76vpyPi7r4x3lnonn/zOAGtS64n9se2tc35WYi45P534U6bvtoIw02J+MyIrliaia58eFMzI6mx+Ul0Wog3KD56ZkPnN3VW0oYAcbIAz8WIYQ4yCRgEkIIIYQQ4lARlgDW1GD9pZ2UqmDb3orKhtNfgU+uDIZV5li2THiUx+a7UCsVFCSFg8kKoy6iPf14XllZS/Nm+OvQPxFTsah39lPqBEgYRku3iw1tkYzMOxvr1nd6z3PE3yCyd7na6LQIHjp9CMnOYgwdxb37LX8apt0GdWvxdzdRnnYG1syZRCkVTM+L5bNrJtHt8hIbpsOsD4ZJqZHGfb93AyF+KBxxKyz+T3DpoCkGjn9IlscJIf6QJGASQgghhBDiUBEWB6e9GHyCW2c16K1w4hMQnbv3fSgUkHssXLEYb0c1dq+STzZpKEj0cvHEdJZsa2Z7s52xGZGsqHTydXEnQ1MsnD5Xxz+mvEOqvwaPOoyYnNHM2ezhnR9XkmAxoBvxf0QkziTM3YgzLJX07EJ81auw+3W0GVKIj7RyekwNvHo2HHFL73gc7TD3Dnw5x/Fy0r9YVuHiyYnRoc2x4Xpid3MZvwv6cJjyV8ifHVw+aE0Da8rBHpUQQhwUEjAJIYQQQghxKEkZC5d+DW3lwYApvjAYGu2LrkYCy59E/eMLWAJ+bs09nq2TbmX266vx76j9ffqoJML0Go7Mj+V/S7bj8QW49BuAONKjjBzX4+SZRdsBKKrvYnlZK1dOG8JjC3S8eryZ7LdORdNail6hgKFXsjL5PGaUPIHS74WuBkgcCXVrgidTqilJP5ePVnfy8BnDMekOof+mqPUQP+Rgj0IIIQ66Q+hfbiGEEEIIIQRt5bDgHtjyMagNMP3/wYgL9mlZlmf7YjQ/PB96rSyeQ2LUUKLNo2nqcgHwydo6HjhtKD5/gGtm5OD3B6jvdPLB6mqOHhzPK8sq+/Tp8Pjw+wNMSjczrvI5FK2lwQ2BAFHrnyEnYTyKrvpg26qXYOSFkHssAa0ZR+IEAupMXh9mIMqs+023RwghxMEhAZMQQgghhBCHikAA1rwKmz8Kvvb0wNw7ICYPso4MFu7WGqFxCzRvxaXUU63NYos9jMGJFrJjzcHjtn/Xr2vr9i+YlHYEH28KBkxef4DkCD0Pzd3GjxXBwuKD4sxcOyMHr8+PQavC4en7NDqlAo5J16Jbs7hf/xpbJZ3DLsdaf02wYc1rACgu/Axj2kjy98PtEUIIcfAoD/YAhBBCCCGEEHuppw02ftC/vWoFLPwnvDQTNn8ML0yHDy9F9/65pM79E801pZzy9Pesr27n/VXVtFsK+nXRFT8OL71PZMuNM/NDRXsoXALY1tiNzekhKdLAJZPS+xwfH65jYlYUs8flE0id2K//Nm0itdGTYfZjEJEOsQVw1hvBJX9CCCEOeTKDSQghhBBCiEOF1gRxhcEC37tS64JPMsucDiueBq+r95DmDRyRX8G8pEE8v7icbY1dDDp6IhEJo9DUrwbAb0mlOedsJnTHEBmup8ftY0JGFF9uqu83hDWV7ZQ2dePzB3jinOGsrmgnNdLIEbkxZMeGBXeacQc0bIAdS+I6Bp9PhW4Q4+MSIfsSGHwSKFRgsAzMfRJCCHHAScAkhBBCCCHEoUKjDz6BrfJ7cNmCbYkjwdEGPg+EJ0Ld2n6HJSpauH78WO5f3MrRg+M45a0y/jzqLo4v7MSiVfBVYzgPvdWC29fECUMTuG5GNif9dxkXT0xnflFTn76GJFuZu7mBpi4XZ45O5u6TCvuPM2EoXL4Ad3MpDoUemzGDo6Ij0Wt2/PfDGLm/74wQQoiDTAImIYQQQgghDiVJI+FPC6F5K2gMoAuHF48KbqtYCjnHwLo3+xxiVCuYMP80Xp7+AKfNc+EPwDOrutAcOYin55Th83eF9v18Qz3njE1lXEYknQ4P03Jj+K64GYCRqRGYdSqaulwoFZAVY+4/Pp8HOqpAoUCbMQmtSo3MUxJCiMOfBExCCCGEEEIcaqKzg18APa2QMQ3Kv4PWUsg9jkDhaSg2fwx6C4y9Aoq/BFstkZ9fxO1T3uPyb3q78vkD/fsPBHhqhpqe6tV4YjXYxhXQpEmkqLaLB77ZSnKEgXtOKiA/IRyai6F8CXQ3Qep4aNgEC+8BFDD+ahj/FwiL6+27pw2aisDVHbyGqKyBu09CCCEOGAmYhBBCCCGEOFA8DuisBbUerMm/ubvyFjuba13kjr+PtMGrUDeso8mUx3zFbCafejnpNZ/AqpfAHpyBhN9Hir8OiAKgpt3BoDgz2xq7Q33GmLWMUpWge+0kTD43AAnhSeRd+CnjMjKZNTQBo1ZFlFkHLSXw6gnQ3dg7qKPuApUW3Hb4/lGIzYdhZwW3dTXAlzdB0efB17pwOP9DKfQthBCHAXmKnBBCCCGEEAdCaxl89Gd4ejQ8NxnWvgnunl/dXUlTF0Ub15DbOh9qVzO/O4MfBt/B1C+juGNBK1+V+2DTR73h0g6xcQmE6YK/Z16yrYU7jx/MUflxhOvVTM6O5q1LhqNb9gjsCJcAFLZaKF+MTq0iJdIYDJcAalf3DZcA1r4Oecf3vt78Ue/3dWt7wyUI1pGa+3dw9S7RE0IIcWiSGUxCCCGEEEIMNJ8Hlj0FRZ8GXzva4dOrICweso/su29TEdSvh0AgWCw7rmC3XeqatzDrhwuCfQE5hgg2W95gULyZTbU2nl/nYOa0e8hceFWwL4DBJxORMYIvrjNQ0tSNw+1lW2MXM3JjmJwdxXfbmrBoAtBR0f+Ettr+bR5H/zanDbS71GZKHLlLH/2fSkfjhuAxurDdXqcQQohDgwRMQgghhBBCDDR7M2z6oH979UqIK+ytUVS/AV6dDc7O4GutGf9Fn+OPH45a1XfxQWT5p6FwCQBHO8nVn5Mffy6bam2093i46sc4Hpv9KcmBOlyaCKKyRoEpGo+9iwe/Kaa4IThz6IhBMSRY9NR1ONGarDDiQph3Z9+xZhzRf/wJw0CpBr+3t23IGbDlk+D34Ukw+MTebburt5Q7C0zR/duFEEIcUmSJnBBCCCGEEANNa4ao7P7tSnXwaXA7bf6oN1wCcHfTs+IV7vpsM8tKW3B7/aFNho6Sft2ZO0tItBpCr/1KNdWGXO6vLuTLnjwwx+D3B3hrZXUoXAJYtK2ZeIueB04bilXpCNZPGnN5sEZSeCLMuBMsKf3HnzAcLvwUMqcFr++4/wTDqeMfhnPegUu+CtZg2ilxBBzzr2ANKoCUCTD1ZlDrfukOCiGE+J2TGUxCCCGEEEIMNH04zLgD3jkHvK5gW9JI6KoHv693v7byfocabOUUu7p484cq/nfBKEw6NV9vauDa7FOILp3bZ9/A0LO4LDeDIUkWWrpdaFRKHvqmmJp2Bx/8ZSIAdpeXRdua+p2n3e5mRGpEcHneovshIgNGnBesE7X8KUgcDlGZfQ9SKiF9MiSOAp8LDNZge1z+T7vvvQ/jr4LcY4PL6yypYLDszR0UQgjxOycBkxBCCCGEEAdCyniY9RB0VIFKE/yz7FuYclNoF1/h6ah2Li/boSL9dDYs6CQQgIXFzazY3kZZczeuggRumHAnsWseBwIEptyMImsGFa12fP4AZr2a74qbOaYgnpkF8eQnhANg0qmZlhtLWXPfMGtkWkTwG5UuOLOqvRxWPNO7g8b489emNQCGn9++K6Vy97O5hBBCHNJkiZwQQgghhBAHgs4UXEqmt8K2b8AYA+e8C5YkAOo7HLxYnUj15PuDxb9NMdRNvIdnq1Nx7Vgap1Ur6XZ5AHhncw+nrB3J22Pex/GnZSgmX8/Sejjlv8v48xurufbttfS4vJw7NpXCpN5ZQkqlgnPGplKYGB5qO2l4ImMzIoMvorL6hF4A5B4HMXkDdmuEEEIc+mQGkxBCCCGEEPuZx+dnbVU7n6+vQ6VUMntYAiNSIlBZU2HURRA/JLgcrr0CDBEQFsePFW3ct7CBZ03ZnF/4IkcMiubKT2po7uoBQKdWMjItgpe/rwidp7bDwdOr4Zjxcbh63Nz7xWZ8/uAT4wIB+HJTAycOTyTB2nd2UXasmVcvHUtFqx2NSklmtAmzXhPcqNLAuCshZQw0bILITEgeDcbIA3HrhBBCHKIkYBJCCCGEEGI/W1PZzjn/W8GOrIfXV1Ty7hXjGZ1qhTWvwze39e48+GSY/Shb6m0AtNndPLHSzVflPq6ZnkVpUzceX4CMaBMNHQ5MWhV2d2/dpv87Mocos476Tge17c5+Y+ns8ex2jFFmHVHmnymubYyA7KOCX0IIIcRekIBJCCGEEEKI/eyNFZWhcAnA5w/w4ZoaRoe1wYK7++685RMYewXDkvsW0C5p6qaqzcE/TihgVUUb17y9FrfPz00zc6lq7aHe5uTUEUmMz4wCIMas44xRyby2ojLUh0IBOfFh4PNCT0vwaXY680BdthBCiD8wCZiEEEIIIYTYz3bWTNpJr1GSE6kOBj0+924O6GJ0egTnj0/lzZVVBAIwIsXKueNSUauUjM+K5vNrJtPe4yY6TEdsmL5fF2qVksunZODxB/hgdTUxZh3/OKGAYYZm+PIuKPoMonNh+u2QMWWArlwIIcQflQRMQgghhBBC7Gfnj09j7pZGAGbnGLkhs4qMkgehxgrHPwzLnoS27cGddWEQlUNMmJ7bZ+Vz7thUPD4/aVEmrEZtqM8Eq6FfLaWfSo0ycc9JBVw9PQuDRkWU1gsfXBcsKg5QtRzePgsu+gKSRg7EpQshhPiDkoBJCCGEEEIcNtp73LTb3UQYtUSYtL98wH7k9fkpqu+irLkLk07NO1eM4+XvK7gzcytx867r3bFsIZz4JHx5E8QNhZn/hOgsAAxaNYMTLX367XJ42FjbyfYWOwkWPcOSLYTpNeg0qt2OQ6NSkhxhDL6o2dQbLu3ktkPjZgmYhBBC7FcSMAkhhBBCiMPCmsp2bv1oA9sauxkUZ+b+U4cyMi1iv5/H6/NT3mKny+klOcJAbHhwudr3pa1c+uqPoae4jUmP4Lkz84h47699Owj48bRVorhqNWpDGOjDf/ZcPn+AN3+o4v6vthJuUHPtjBw+WlNLVVsPZ49J4ejBcaHz9+G0wcb3wVYXrLvk7u67XXVgwzchhBCHPwmYhBBCCCHEIa+23cGfXltFqz1Y32hbYzeXv7aKz66Z1DubZz+wu7y8+2M193+1FbfPT3KEgWfOG0VShIG7v9gcCpcAfqxop6rDSaTW1K+fFpea5dsDnDIyDMUezlfRaueRudsAuGxSBo/PL6Hb5QVgY20nzV0urjsyB6XyJ73UrII5N4AlBcb+CZY+2rstaRREZf3qeyCEEELsjvJgD0AIIYQQQojfqqa9JxQu7dRmd1PT7tiv5ymqt3HPF1tw+/w7zuvgzk830elwU9PW/1yl7T6YelPfRq2JEvNobv9kE5WtPXs8n8PtC53LHyAULu303OLt1Hfu5horlwb/7KyG6h/gyL/DpOvhuAfhqLsgftjeXbAQQgixl2QGkxBCCCGEOORZjBpUSkWfGURKBVgNmv16nt0FVuuqO/D6/JwyIpF3V9WE2hUKyIoxU2scRdex7xBb9y0eTTjlkZMoC2Tg8GzB5vTs8XzJEQaGJVtYX9PJTycpAWjUiv6zlwAi0nu/r/w++DX4ZJhwPZij9vJqhRBCiL0nM5iEEEIIIcQhLzPaxE3HDOrTduMxuWRE91+e9lvEhev6tWXFmHh1eSXHFsZz8vBElIrgfs+cN5IYs45PN7Zy7Cd+Tiw5juPXj+fszx2sre7giEFRJP3CU+GsRi0PnTGM2UMT8PoDxIb1Pf9Nx+SSYNlNH2mTIXqX+6E1wcRrJVwSQggxYGQGkxBCCCGEOORp1SoumJDOmPRI6jocJFoN5CWE/+yT1n6tgsRw/jw1k+cWbwcgTKfm/PFp3P/VVt5YUcWbl4/lhqNzMWiV6NQqHvh6K207lu7tOvuprLmbf55cyB4LMO2QExfGw2cOo63bzXGF8SwpaWF7SzdH5ccxNiNy9wdFZcL5H0HDRvA6ITY/+CWEEEIMEAmYhBBCCCHEYcGsUzM6/WcCl33U3uOmy+EhyqzDpOv9yBxu0HL9kTnMGpLAyvJW2uxuHl9QgssbrJP01spqnj5vJADrqzt4b1U1V0/P5qtNDX36n5oTzZVvrObEYYncNDMXnXrPQZhOrSLBaiDBamBwomXvLsKaEvwSQgghDgBZIieEEEIIIcQOKpWKFdtbOeu55Ux98Dv+/Ppqttbb+uxj1KkZlmKlsrWHZxdtp6Ont45SWlTvE+sCgQAeX4DSpm7OHpOCRqVAoYCZBfH0ePw02ly8uLSc8hb7Abs+IYQQYqBIwCSEEEIIIf6Q7C4vNkffItt2pYlLXv6RbY3dACwtbeGv762jo8fd7/izxqRg0vbOPArXq5k9NDH0OiPaxITMKL7YUM+66g4ePXM410zPprXbxavLKoDgk+FcHv8AXJ0QQghxYMkSOSGEEEII8Yfi9PhYWtrCEwtKsLt8XHlEJkcPjsNq1FJr86BUwPAUK7UdDpq7XBTVd1HT7sBq1PbpZ2iylQ//MpH1NZ14fD7MOg1lTV1YjRoSrQYsRi3/Pm0IX29sYH5RIw63j/dWVdNoc+3SRzipu8x6EkIIIQ5VAxYwuVwuzjvvPNxuNz6fj5kzZ3Lddddx66238sMPPxAWFgbA/fffT35+PoFAgH/9618sWrQIvV7P/fffT0FBAQAff/wxzzzzDAB/+ctfOOWUUwZq2EIIIYQQ4jC3tqqdy19dFXp98wcbePD0oUSZtUSEGbloYjobajo5tiCeSJOWF5Zux6zb/cfm1Cgjryyr4J0fq0NtM3JjefSsYViMWtKjTFw5LQutWsHj35Zw+ZRMlpe1srmuk7EZkVw9LZuInwRXQgghxKFowAImrVbLq6++islkwuPxcO655zJ16lQAbrnlFo499tg++y9evJiKigrmzp3L+vXrueuuu3j//ffp6Ojgqaee4sMPP0ShUHDqqacyY8YMLJa9LG4ohBBCCCHELuYXNfVre31FJSNTI+h0ePh4bS0QXB6XGmnk8bNH4PT4eH5xGT5/gIlZ0QxJsqBUKqho6ekTLgF8W9xEaXM3o9J6C46rlEpq2h38a04RI1MjmJoTQ7RZS3aseWAvVgghhDhABqwGk0KhwGQyAeD1evF6vSgUP/8c1gULFnDyySejUCgYPnw4NpuNpqYmli5dyqRJk7BarVgsFiZNmsSSJUsGathCCCGEEOIwNyzJwtXTs5mSE83Oj6dhejVpUUY+XVfbZ9+qth68Pj8n//d77vtyKw98Xczpzy5jTVU7AB6fb7fncHv71lWakhMdKgC+pqqdrzc1cNyQBNQqKYkqhBDi8DCgNZh8Ph+nnnoqVVVVnHvuuQwbNoy3336bRx99lKeffpoJEyZw0003odVqaWxsJD4+PnRsfHw8jY2N/drj4uJobGzc43ldLhdFRUUDdl0/5XQ6D+j5hAB534kDT95z4kCT95zYHYVCQSAQ+FXHqlQqGnxmnl1cSku3h5w4M7cdl8/Dc4uZkRdLm71/IW+Alm4Xzl0KcXt8AV5dVk6kvwMdakakWFlb3RHanh5lJFzR//375Kk5VHR68fgCZERo0dkbKSqq/1XXIg4f8m+dONDkPScGyoAGTCqVik8//RSbzcbVV1/Ntm3buOGGG4iJicHj8XDnnXfy/PPPc8011+zX8+p0OvLz8/drn3tSVFR0QM8nBMj7Thx48p4TB5q858Suup1eNtR2sLW+iwSLnuEpVhKshn3qY3tzN58sLGVmQQK1HU7iLTo6HW7+e+5I7vpiMzFmPccVJjBnY2/okxZpRPmTWfgKBTg8PtLSM1ApFTx8ZiTv/ljN/KJGJmZFc8GENAbFhe12DEP3/dLFYU7+rRMHmrznxG+xp3DygDxFLjw8nHHjxrFkyRIuu+wyIFij6dRTT+Wll14CgjOTGhoaQsc0NDQQFxdHXFwcP/zwQ6i9sbGRsWPHHohhCyGEEEKI34FAIMAHq6u56/MtobaJWVE8fvYIYsJ0e91Po82Jzx/g0fklffo5Mj+OSKOWNVXtXDA+jVtm5rK4pJnMaDPjMyOxGjWh/c8YlUxypBEFAZaWNDMsxUpmjJm/HZvHNdOzMerUqJQ/XxZCCCGEOFwN2KLvtrY2bDYbEJyCt2zZMjIzM2lqChZVDAQCzJ8/n5ycHABmzJjBJ598QiAQYN26dYSFhREbG8vkyZNZunQpnZ2ddHZ2snTpUiZPnjxQwxZCCCGEEAeJx+enze7G6+tbv6iqrYcHvi7u07asrJXiBts+9R8IwGfr6/r1Y+vx8NqlY3nq3BGYdCo+XVeL1xfg261N3PtFEdmxZp67YBSXTU6nodPBo/O28ci8Ei56+Ude+b4Cj8+PUqkgzKCRcEkIIcQf1oDNYGpqauLWW2/F5/MRCAQ49thjmT59OhdeeCHt7e0EAgHy8vK4++67ATjiiCNYtGgRRx99NAaDgfvuuw8Aq9XKVVddxemnnw7A1VdfjdVqHahhCyGEEEKIg6C4oYsXl27n+9JWjhgUw6WTMsiOCz5hze314/D0L6Ztc3j36RwqpYLdlW+yu71YjFoCAXh20fY+26bmRBNh1DGzIB6LQcOLSyv6bH9qYSnHD0sgJ3b3S+KEEEKIP4oBC5jy8vL45JNP+rW/9tpru91foVDwj3/8Y7fbTj/99FDAJIQQQgghDi9NNid/fn0VFa09ALz1QxVrq9t547JxRJl16DVKJmZFsaysNXSMUasiwqT5uS5DPD4/aqUChUJBotXAsGQL62s6Q9uTrAZMuuBH4pGpVkalWlld1QGASavir0cPwqBVAeDaTcjl9Qdwefz92oUQQog/mgNSg0kIIYQQQoifU95iD4VLOxXVd1HR2kOUWYfL62d0egTRZh1LSprJjDEze2gCPe6fn8HU0uViYXET7/xYTXaMifPGpzE02cpNM3P5aE0tqyrbKEi0MCLVStyOOk5JEUbunplKm28QDreP7FgzWbHmUJ+ZMWYiTdo+T5sblRpBSuS+FRsXQgghDkcSMAkhhBBCiINKp959WVD9jvZEq4FNtZ3Udzo5fkgCte0Olmxr4pZj8/H5A/3qHgUCAd5fXR2q27S6sp0vNtRz/2lDeHFpBbOHJXBUfiyb6zoZlx5JfqIldKzK3c2UvGQabE5UP3l6XEqkkVcvHcvj87expqqDo/PjuGJqBhaDdn/eDiGEEOKQJAGTEEIIIYQ4qLJizZwwLIHP19eH2s4Zm0JGjAkAo1bNnccP5vkl21lY3MT1Rw3i8/V1XPDiDxw/NIGLJqaTEW2itdtFWbMdjUrBfxeW9TmH3e2jrNnOuuoO1lV3MDErirtOGMyg+PA++/k0Jp5aWMqz35WhVSu5eWYus4clEq4PLscbkmThyXNG0uX0EGHUovmZcEwIIYT4o5GASQghhBBC7BOH20ejzYlRpyI2TP+b+wvTa7jj+HyOLUxga52NgqRwRqZFYNT2flTNiDFzz0mFbGvs4uznVtDlCi6Pe2VZBWXN3Vw0IZ2nF5aytrqDiyamo1bt+Wluy8pa2Vxv6xcwrW5w8/DcbUAwlPp/H28iNlzPUflxoX0MWlWoLpMQQgghgiRgEkIIIYQQe62suZsHvtrK3C2NxIbpuPekQqbnxaL9jTN54sINHD/EwPFDEn52H41KSV2HMxQu7bS5zsaGmg7WVncA8OXGes4Zm8p/v+udxRRl0uL1932EnNfX97XL4+PDdQ39zjt/S2OfgEkIIYQQ/UnAJIQQQggh9orT4+U/O8IlgKYuF1e+uZpPrprEsBTrARmDQdN/5lBOrJl1O8IlgOYuF5vrbNw5O59NtTbSo4xEmLTc92VRaJ+j8mNJjzb26UetUpIRZWDDLk+ZA0iPMu3fixBCCCEOQxIwCSGEEEKIvdJoczG3qLFPWyAA5S3dvypg8vj8VLTYsbu8pEQaiTLrfvGYvPgwJmRGsnx7W6htdHoEfj8sLmkJtS3a1sy0QTE8etZwAEqbuvi/o3JYXdlOQaKFUWkRFOxS3BtApVRw9sgE5hU10+P2ARBj1jE9P3afr00IIYT4o5GASQghhBBC7BWTVk1CuJ66Tmefdqux/1PUOnrcVLT2oFUpyIg2YdD2/djZ2Ong3VXVPLGgFK8/QFaMiafPHUleQni/vnYVHabj4TOHs6aqna31NgxaNcvLWsmONTM5O5qlpcGQaUZeLEcN7l3Wlh0bRnZsGN1ODwDmHUW7fypK0c3HV02kqL4LtVJBQZKFjGiZwSSEEEL8EgmYhBBCCCHEXokO0/HPUwr502ur8e2oZzQ9N6bfTKDtzd3c+N561lZ3oFDAuWNT+b+jcojZURB8c10nP5S38ci8ktAxZc12Hvh6K0+fN7JPce+f6nZ6aO12kRZpYlCsiXlbmvH5A3Q6PJw+KplxmZEkWQ0cPTiOsN2ESD8XLO3k8/nIjw8nN37PQZcQQggh+pKASQghhBDiMOf0+Nhab6O63UFMmI78hDAshv6zjvbG1JwYPr16EmXN3UQYNQyKC8Oo7S3w7fcHeG15ZajgdiAAb66sYlJ2NIMTwnG4vVz/zlqOLexfzHtJSQvtdvfPBkw17T3c+8UWvtkcXKZ35dRMSpu68fr9rKvu4OO1tQDcPDN3t+GSEEIIIQaOBExCCCGEEIcxvz/AJ2trufWjjaG2P03J4PqjBmHW7ftHQbVKSWGShawYE0tKW/jz66vx+PxcMyOHcemR1NscfFfc1O+4ldtbuf+rIk4cnkRpkx2tqv9T54YkWXB5/AQCARQKRb/t3xU3h8IlgOeXbOeJc0Zw/TvrQjOqzDo103Nj9vm6hBBCCPHbSMAkhBBCCHEYq2y1c/fnW/q0/W9JOccPSWB4asSv7ndVZTtXvLYagEnZUZQ2dfPUtyVkxZoZmRpBRWtPn/2tRi0NnS7cXj9mnZrNdTaOH5LAnI31O7ZruGJqJs8tKWNESgRTB8WQaDX06eOnwZU/AF9vquf9P49neVkbBp2KCZlR5P9CHSchhBBC7H8SMAkhhBBCHMa6XF4cHl+/9vYez2/q9+M1weVoOrWS8ZlRPDx3GwBb6rv427G5pEQYqG53AHDEoGiaupy4fX4WFDVy08xB3PXZFiZnR/PXowdhNWiINmm55YMNdLm8vPtjDTPyYnn0zGFYdikgPik7mvlFfUOm/PhwRqZFMjIt8jddjxBCCCF+GwmYhBBCCCEOY4kWA+nRRipaemcUGTQqUqOM+9RPR48brVqJUavG5vSgVQeXuI1Ki2BRcXOffR+Zt407jx+M3e3F7fUzKi2C81/8AYCZBfH4fAGeOW8kjTYXZr0Krz/ANe+sJRDo7ePbrU2UNXdj1mv4amM9Wxu6OGZwHFdMyeD5JeUAjE2P5IjcGBYUNWLQqBgUF0Z0mO7X3CYhhBBC/EYSMAkhhBBCHMaiw3Q8dc5I/t/HG9hQYyMl0sD9pw4lM9q0V8c3dTn5YkM9r3xfQWyYlv87KpdwvZqJ2dF8vLYWh9uHxdi3oLbHF2BLvY3vS1u5cEIa321r5qj8WOxuH2admsfml9Dj8TGrMJ6ZBfGUNHX3CZcAIowafP4A57+4kiabC4CvNjVw0zGD+OSqCbh9AdRKJee98AOdjuBsrElZUTx4xrB+S+uEEEIIMfAkYBJCCCGEOMwVJll4/bJxtHS5sRg0+zTL57N1dfxzThEAVW09XPjSSu6cPZgXFm/ngdOG0NLlIjZcz5KSllChbYNGxXE7wqNwvZpzX1jJpOxozhmTwnXvrAv1/fmGeqLNOsZmRDIkycLG2k4yok2cNSaFhk4nJU32ULi009MLyzh5RBIxZh3XvLU2FC4BfF/WyurKdgmYhBBCiINAAiYhhBBCiD8Ai0GLxaD95R130drt4sWl5X3a/AFQKuCssam8trwSq1HDOWNSeemi0fxY0Y7H52dMegQ3f7ABu8vLEbnRXD09m9eXV5IS2T/4WbC1ibEZEfx9dj5fbWogLcrE3Z9vxh+A64/M6be/PxAgEIBul5cNtR39tle02PfpGoUQQgixf0jAJIQQQghxiCht6ubLjfWsrmzjuMIEpuXGEG8ZuNk6GpUSq0FDfacz1BamU+P1B3hk3rZQ2+JtLdw8MxeDVoXGp+DuL7ZwzOA4wg0aihu7AHjkrKFsqbP1O0d2jIlwnYoEq4EzRidz12db2DERCq8/QIRR06cg+Z+mZpJkNRAAZhUm8PKyij79DUm27L8bIIQQQoi9JgGTEEIIIcQhoL7DwWWv/khla7BY96JtLZw/LpU7TxiMTq0akHOGGzTcfGwul76yKtR2/JAE3v6hus9+Xn+ABpuTj9fUcM/JQ8iKMVPd7mDRyioAFhQ1MS4jkqumZZEda6a0qRsAo1bFlEExKFUqLnxxJTlx4X2WvL38fTnXzcihqq2H0uYuTh+ZwrS8GJRKBQAXTkxje4udRdua0aqUXHtkNsNTrANyL4QQQgixZxIwCSGEEEIcAoobu0Lh0k5v/VDFxZPSyY4N26e+3F4fTV0uDBoVUWYdLo+P8hY7XU4vKZGGPrOiJmVF8fLFo1lV2Y7fDznxZjbWdfbrU61U4vEFqOtwcGReLHd+urnP9pXlbVwyKZ0LJ6TRbnfjCwRQKhQ8vqCEo/LjCKBgWWkLF09KZ2tDcNZTj9vHA99s5dOrJlGYZAkFSztlRJv577kjqe7oQatSkhZlQvWTfYQQQghxYOxVwPTqq69y2mmnYTKZuP322ykqKuLGG29k8uTJAz0+IYQQQgixB4Ff3qWPihY7//2ulI/X1pJg0fP32QXUtPdwzxfBpWnx4Xr+d+EohiRbAShrtrOpzsbwZAuPzi/hpe/L+etRg9i8y3I3k1aFxaDB4fHh8vpJCNfv9twdPR4WFDWxaFtzn/a2bjdmnZryFjtbG7q4dkY2X21qwGpQc+2MHPISwvqFS6Fz69XkxYfv410QQgghxP6m3JudPvzwQ8xmM0uXLsVms/Gf//yHhx9+eKDHJoQQQgghdhgUF0bqT4pk/+WILIwaFW1291714fb6eGphKe+tqsHjC1DV5uCK11fR7fKF6h412Jzc9fkWunYsVWvqcrK6sp2VFe0cUxDPaSOTKWnq4tEzh3Hu2BQuGJ/KNTOyeWVZObcdl09nj5v2HjfjMiL7nLswMRy1UtGvHeDI/Fg275gVNW9LI68uq+Dekwp47bJxHJEbi3aAlgAKIYQQYv/ZqxlMgUDwE8eiRYs46aSTyMnJCbUJIYQQQoiBl2g18NLFY/hiQz2rKtq5cEIam2o7Of7JpViNGm47Np9puTHoND8fxrT3eJizob5Pmz8ALq+vT9vqynbaetyEGTS4vQGyYsy880M1efFhHFMQh88foNHmZGJmFLEWPaVN3ZwzNpU3V1aiUirpdnk4Z2wqYzMi2Vpv46ThSZh1aqwmDUtLm7nxmEF8sb4ehQL+fEQWg+PDSY8ysr0luATwuCEJZMeaMWqlmoMQQghxqNirn9qFhYVceuml1NTUcOONN9Ld3Y1SuVeTn4QQQgghxH6SHRvG/x0VrLf0zHelPPFtKRBcevbnN1bz6iVjGJ8V1a/o95a6Tj5dX0dZUzfXzMhmbVU784uaQtvVqr6f64YlW7AatQBEmYJ/FiaGkxMXxn1fbgVAoYDbZ+Vjc3owGzQ8+XFpnz7a7G7+PCWD1dWd3Pj+elxePyatiofOGIZeq2JkqpVEi4GMGDMA7/55AhWtPejVKjJjTZgkXBJCCCEOKXv1k/tf//oXRUVFpKSkYDAYaG9v57777hvosQkhhBBCiN1os7t4Y0VVv/aFxc0sK23h0imZxO2og1Ta1MU5/1sZejrb/KIm/jw1k421nTTaXIxOs5Ji1aNQQCAAqREG7jqpgE21nYTp1WTFmtCrlZw5JoUb3lsfOlcgAA/NLebxs0YwJTuKx88azrKyVhKselIiDAxPsdLj8XPTe+tx+/wA2N0+bvlgA19cN5m0KFOfsceE6YkJ233tJiGEEEL8/u1VwKRUKomOjqa0tBSfz/fLBwghhBBCiAGjU6tIsOip7XD0aTdqVbywpJy8hHBOGZkMwJb6rlC4tNM7P1bz2FnDsDm85MWHEWZQ89nVk+h2+VAp4bJXVtFmd5No0XPJxDQmZUfj9PT/DOj0+NlS34nT62NIsoW3fqji3VXVAJw0PJGThiWGwqWdulxemrtc/QImIYQQQhza9ipgevDBB/nqq6/IyspCpeqdcj1mzJgBG5gQQgghhOirqN7GlxvrKWvq5vIpGayr7sC7ozp3okWPQqHA7fOzYGtTKGDa3WPmAgRYU9lOpFnHzR9uoKLVzglDE7l8cgY3vr+eGLOOP0/NpKa9h2a7hy31NtbXdPCP2YN5cG4xPe5g2BQfrqfN7uH9VVs5bVQyK8vbQuf4dF0dJw1PRKNS4PH1DsKsUxNj1g3cTRJCCCHEQbFXAdP8+fP5+uuv0Wq1Az0eIYQQQgixG9ubuzn3fyto7wnORlIq4LkLRlHeYkerVuJ0+3hwbjEAI1IjQsflxJoI16uxOb2htnPHpDIs1cKGGhuTsqJptDn5cE0NQ5MtbKrr5KZj8lhe1srQZAsBAszf0siUQTE8ubCUK6Zk8tiCEtKijFw8MZ0HvylmbHokC4ub+KllpS08ePow/vbhBlxeP3qNkofPHEZatMxeEkIIIQ43exUwpaSk4PF4JGASQgghhDhIttTZQuHSiBQrFqOWy15dhVIRfBLcVdOySLIa0GuUzMiLBaC0qZv7vy7mmhnZVLb2UNFiZ8qgGHJiTdz4/gY6ejwkW/XcdUIBG2s78fr8XDwxHQCn18fjC0pQKmD20EQijBq8Pj/p0SZuODqH6jYH93+1FZfXT2lzN8cWxLOp1tZnzJkxYZwwLJGCpHCau1zEh+vJkHBJCCGEOCztVcBkMBg4+eSTmTBhQp+Q6Y477hiwgQkhhBBCiF67rnSblhfLo/O2AcFwCeDFpeW8fMkYsmLMxIXrcXl9PP1tCYu2NVOYZGFjTQcatQoF8PL3FXTvmNF04cQM/vreOpweP0oFvHjhKL7b1srystZQ/5+tr2NYigWjVoVBq6Ig0cJT35aF6iudPSaFowfHs6SkmeLGbgAmZ0cxZVA0KqWCnNgwcmLDDsh9EkIIIcTBsVcB04wZM5gxY8ZAj0UIIYQQQvyM/IQwwg1qbA4vnp8UztaoFJw0PAm3109Hj5sIo4Y2u5t5RcFla2qlgtoOJ1dOy2JbQxdqpZK/Hj2I0qZuttTZcHqC/fkD8Mn6erY1dvU7/+Y6G5OyoxmeYiHGrGfOdZOpaXcQZdaSE2vGoFXzxuXjKGu2o1YqyIo1E2GU2e9CCCHEH8VeBUynnHIKbrebiooKADIyMtBoNAM5LiGEEEIIsYvs2DDevnw876+uIcasxaRVYd9RbPvmmXnM29LIvC2NODw+sqJMDE+1ctW0LHyBALEmLfeeXEBRfRepUUbKW+w8+E0x9586hK83NYTOUZgUjl6tYFiylaL6viFTYaKF4wrjiQs3AJATF0ZOXN9ZSTFhemLC9AN8J4QQQgjxe7RXAdPKlSu59dZbSUpKIhAIUF9fzwMPPCBPkRNCCCGEGGAen5/KVjsOtw+DVsWlk9Nptjn5xwkFPPFtCamRRnpcXoYmW/h0XS0mnZqsGDOVbQ7+800xseE6bj4ml2vfXodvx3q6c8amAPDysgrOG5vKxtpOrpqexcrtbRQ32rl2ejZLS1uoaXcAMCrNytGD40iwGg7afRBCCCHE79teBUwPPPAAL774IpmZmQCUl5dz44038tFHHw3o4IQQQgghfm+6HB7W13RS1NBJktXI8BQriQMUvLTb3bz0fXmwQLZFj0mrJt6ip7rNDgoFk7KjmZ4bw7qqDl5cWg5AS7ebB78p5uEzhwFwwtBE/jmnKBQuAbz9QzU3HjOIT9bWkR1r4r5Th3D9O2tDS+WufHM1j589nDC9BrVSyaA4M1Fm3YBcoxBCCCEOD3sVMHk8nlC4BMElch6PZ8AGJYQQQgjxe+T3B3jnx2r+9WVRqG1KdjSPnT18vwYwXQ4Pm+tt1HU48PoCrKvuYOuPwSVrmdEm7jmpgIfmbmNddQeJFgMLtjb162NjTSdx4ToMWhWdjv6f21xePycNTyQmTMe66qZQuATg8QW485PNfHX9FGLDZcmbEEIIIX6Zcm92Kiws5Pbbb2flypWsXLmSO+64g8LCwoEemxBCCCHE70pVWw8Pzyvu07aktIXi3RTF/rWcHh8vLC3nqjfXsKXehtvnZ2tDb//bW+x8X9pKRrQJgBXbW4nfTQgUadJw7tg0okxaUiONfbaplQoGx4fj8fpJjjSiUfX/SKhVK1EpFfvtuoQQQghxeNurgOnuu+8mOzub119/nddff53s7GzuvvvugR6bEEIIIcTvisvr7zPTZye7y7ffzlHW3M0T35Zgc3gYlmyhrLm73z4/VLRx1uhkZhbEMiUnmnPHpaJR9YZBMWYdEUYtjy3Yxgera7jnpALSdoRMVqOG/zcrjy831nLSiCQMGjXDU61EGPs+wOX6I3NkWZwQQggh9tpeLZHTarVccsklXHLJJQM9HiGEEEKI361kq4GpOTEsLmkOtYXp1GTFmH51n+urO/h8fR2tdjenjEjCqFERCIBWo8TrDzAixcp3xc19jhmeYuXeOUWcMiKJf84pIsGi5/+OGoTfHyBMr8brD/DPOUUEArC5zsb176zl1UvHoVaCUqFErVJwxqgUwgzBUGlMeiTPXzCK77a10NDp4OjBcUzOjv7V1ySEEEKIP549BkzXX389jz/+OCeccMJut3/++ecDMighhBBCiN8jk17N3ScV8MKS7Xy1qYHBCeHceMwgMmPMv6q/TbWdnPncclze4Kyoj9fW8vS5I4gP1+P1+/mxvJ3sWDMnDkvks/V1AEwbFIM/EGBydjSPzNsGQH2nkwe/KUatVPDIWcO47u11fc7T6fBS1+Fg1pCEnx3LmIwoxmRE/arrEEIIIYTYY8B0++23A/Dss88ekMEIIYQQQuykUqkO9hB2KyPaxN0nFnD9kTmY9WqM2r2aEL5b35e2hMKlnZ5fvJ0XLx7Nze9vIDXSyD1fbOGMUcn86+RCmrpcrK1q5+XvK7h2RjY97r5L87z+AArAqFX12xZl1v7qcQohhBBC/JI91mCKjY0F4K233iIpKanP11tvvXVABiiEEEKIPxavz8/qyjY+2+7lvwtL2VTbebCH1I9apSQ2XP+bwiUAnz/Qr83j80MgwJ+nZlKQEMYT5wxndWU7To+PxxeUsLikBYBtjV2MSrX2OVavUaJVKbliamaf9pOHJ5IbF/abxiqEEEIIsSd79alo2bJl/doWL17MzTffvN8HJIQQQog/tlWV7Zz3wspQ+PLEtyW89+cJDE22HtyB7SObw4PH599joewx6ZFoVAo8vt6g6YLx6Zz1/Eq6XV4ATh+VxJH5sUSatTx4+lDeX11DIBBgZGoEsWE6os06FmxtYlBcGHedOJjRaZGMTo9gUnY0la09xIbpGJwYjtUoM5iEEEIIMXD2GDC99dZbvP3221RVVfWpw2S32xkxYsSAD04IIYQQfyxen58Xl5b3mdnj9PiZt7nxdx8wOdw+KlrtKAhQ1ebg4bnFdDq8XDYlg5OHJxITpu93jD/g59bj8vihvA2b08sxg+PY2mgLhUsA325t5uIJ6ZS32HnmuzJGp0eiQMFDc4vx+AL8+9RCTh6RxLjMKCJNwRApyqwnyqxnTHrkAbt+IYQQQvyx7TFgOuGEE5g6dSqPPPIIN954Y6jdZDJhtVoHemxCCCGE+IPxE6Czx9OvvcPhPgij2Xt1HQ4emlvMR2tque24PP791dbQtn/NKUKrUnLRxPR+x/n8cO8XRRQkhmPUqvi+tJVGm7PPPm12N3HhOvQaFR5fgOVlrX22N3S6+Punm/nyuimhgEkIIYQQ4kDbYw2msLAwkpOTufDCC7FYLKH6S2q1mvXr1x+oMQohhBDiD0KrUnHxpLR+7cft4elnvweLipv5aE0tI1MjaO/pH4a9sqyC70uaeXJBCd9ubQrtkxsfxpj0CDbX2fixop3vS1s4cVhiv+PTok0cmR/LzIL4Pu0pkQY6HB48vgBOr6/fcUIIIYQQB8pe1WC66667+Pjjj0OvjUZjvzYhhBBCiP1hcnYMT54zgmcXlWHQqLh6ejajUiMO9rD2aH5RIwCzhsTT0u3qtz3arOX5JeUs2tYMwPVH5nDNjGycHh9/PTKHLfU2nF4/ceF6etw+njpnBPOLGqls7eG6I3MYkWJFp1Fxx/F5DEux8M2mBgbFh5ESYeSJBSUMS7GQGmE8oNcshBBCCLGrvQqYAoEACoUi9FqpVOL1evdwhBBCCCHErxNu0HDCsETywj0kJyVj0KoO9pD2yOZwMyzFyuqqdipbe4gya4k2a2npDs5SUikVnD0mle0t3QxNtqBWKdlc28HWehvfbm1i0bYWThgWT32rk4fmbgv1e+uxefzz5ALM+t5lbymRJq6als1RebE8v6ScF5eWc+LwRP4yLQuLFPEWQgghxEG0VwFTSkoKr732Gueccw4QLP6dkpIyoAMTQgghxB+b19nzuwiX/P4A1e09eH0BkiMM6DS9Y/J6/SwrayUj2kRapAGDVsUz35Xx5yMy8QfA7fWTEmHAalDz6rLKUPHuvx6dw7/mFLGivA2AI3JjeHNlVZ/zPjyvmCMHx5Kj7x8cDYoP556TCrj5mFwiTBq06oN/n4QQQgjxx7ZXAdPdd9/NP//5T5555hkUCgUTJkzg3nvvHeixCSGEEEIcVB09bt75sZqXlm5nfGY0BYlhzBqSSEqkkYqWblaWt9HQ6aS5y8XZY1KJDdfz3qpqnlhQikalQK1S8MTZI3hiYWmfJ8P5/YTCJQg+Pe+nPL4A3c6fnzFu1Koxavfqo5wQQgghxIDbq08lUVFRPProowM9FiGEEEKI3ywQCFDT7sDrD5Bo1aP7DbN71lS2s6qijTPHpPLlhnrKmruJMOlwe31c8fpqyprt5MaFcfbYFLa32GnrcXP/qUMoa+6m0eYi0WJAq1aypc7Wp99dKg8A4PUFCDeosTl6A6X0aCMpUldJCCGEEIeIPQZM//vf//jTn/7Evffe26cG00533HHHgA1MCCGEEGJfdTrcfLC6hofnbsPl9XP6qCSunZFD8q8MatZVdzA4MZwnFpSG2m75YAOPnzWcsmY7WpWS00Ylc/fnW0LbrUYN/z51CM8vLqfT4eH+U4cwITOKxSUtoX021XZyxKCYUNHvN1dWcufswby6rIJNdTbGZ0by99mDiQ7T/co7IYQQQghxYO0xYMrKygKgsLDwgAxGCCGEEOKXVLXa2d5ix6hVMSguDOsuxa3XVHZw7xdFodfv/lhDktXIdUfm/GK/3U4PbT1unB4/WrUSjUpBYWI4TV0uXrtkDCqVkh/LW/nvd9tZWd7KpZPSGZZiZXlZS59+Ono8bKmz4fYGl73VdzqZmB1NS7ebLfU2dGolGdFmIk1a8uLDKG7sYkJmFOMzozimII5Oh5dIowazXrOf7pgQQgghxMDbY8A0Y8YMAE455ZQDMhghhBBC/DF4fX5Kmrqpbe8hOkzHoLiwvaontKGmgwtf+oGOHg8AxwyO496TC4gLNwDwQ3lrv2M+WlPDRRPS9viUta31Nj5ZV4vd5eO9VdX4AwHOGZvKCUMTcPsCPPVdGT+Ut5EXH8Z/zx2BLxDg+SXbmVfUyInDEnni7OHc/MEGXDtCJZ8/wIUT0nhu8XYgwCtLKxibGcmFE9Jo6nLx8dpaylvshOnUpEYZ8QcC/FjRSmmTnbEZkVhTrft+U4UQQgghDqI9fpK78sor93jws88+u18HI4QQQog/hrlbGrn27bX4/AEAbjx6EJdNydhjyNTj9vLQN8WhcGlnP6ePSuaYgmDAlB5t6ndcfkI4+j08ja69x80tH65nRl4czy7aHmp/bXklKREGPt9Qz4aaTgBKmrppsbu5/ZNNobE/vbCMSyalc9W0LB6dX4JSAeEGDVWtdq6cmsHMgniOK0zg47W1bK7tpKHLSXmLHYAul5fNdTZmD03g5g824vMH+O93Zfx99mAunZyxt7dTCCGEEOKg22PAdOmllwIwd+5cWlpaOPHEEwGYM2cOUVFRAz86IYQQQhx2qtt6uPXDDaGABuDheds4IjeGocnWnz2uy+llQ21n//7ae0Lfj8uMIjfOTHFjNwBhOjVXHpG1x0LfdR0OPL4Am3bT91ebGgjTqzljVDLp0SZ6XB66Xd4+Ywf4bF0d95xUwKi0CGYNief15ZV0ODx8dd0UEqzB8Ou2hHD8/gBF9TbWVXXS3O0CYHpuDBWtPX3vx9xijimI+9W1o4QQQgghDrQ9Bkxjx44F4P777+ejjz4Ktc+YMYNTTz11YEcmhBBCiMNSR48bm9Pbr725y7XH4yKNWo7Kj+OD1TV92gfFhYW+T48y8colYylqsOHy+BkUF0ZWrHmP/aoUCrqdXpJ2E+bkxYeTFmnAqFNT1ebApFWh1/QPqywGDWqlEqNWxX1fbsXnD5AXb8b4k5lTSqWCgiQLH189ke0tdgxqFU6Pjwte+qHPfk6vH4+vb4glhBBCCPF79svFDgCHw0F1dTUpKSkAVFdX43A4BnRgQgghhDg8xYXrSbIaqO3o/SyhUSl+cbaORq3kyiOyKG+2s7qqHY1KwXVH5jA02dJnvwSrITRr6Jesr+7g3s+3cNmUDDp6PCRa9NR1OgGINGk5aUQi5c12bv1oY+iYW4/NJT5cR4OtNxC7YEIa62vaWbLjSXFKBdx6XP7P1n1KjjCGrre0qQuzTk23qzd0O3N0MklW/V5dgxBCCCHE78FeBUy33XYbF1xwASkpKQQCAerq6rj77rsHemxCCCGEOAzFhut58pwRXPv2Wmo7HFgMGv5z2lCydzPTyO8PUN3eg8fnJznCSHasmZcuGUN1Ww96jYr0KCNqlXKfx9DZ48bl83PLhxs4vjCBWLMOr8/PbbPycHr8dLu8pEQYWF3RzqvLK/oc++j8Ep48ZwRVbT00d7nIiw+jsdNJXnw4T587gm6nl9yEMAoTLbs/+U9kx4bx5uXjeOa7MrY22Dh1ZDKnjkxCu4dlfUIIIYQQvzd7FTBNnTqVuXPnsn17sPBlZmYmWu3PP4lFCCGEEGJPRqZF8PHVE2myubAaNbudveQ3WHnmuzKeXFiCy+vnhKGJ3HRMLqlRRixJexfe/FRDp5PVlW2UNdtJizRS0thF8tQMqtoc3P/1VgCSIwycOzYVg1ZNj8dHu93Tpw+X109pUzdZ0UZSI/TM3dLEEbkxTMiKJtqs+1XjGpZi5fFzhuN0+/b4tDshhBBCiN+rvfqVn8Ph4IUXXuCNN94gLy+Puro6Fi5cONBjE0IIIcRhLDZMT2GSpV+45PcHWLStmaWVPTw4txinx08gAJ+tr+P91dUEAr+uNpHfH2BJSTOvLa/kkXnb0KgUpEYa6XJ66XS4GZ0WAUBNu4P/fFPMg98UYdaqOH5oQp9+NCoFaVFGrnxrLWq1iofOHM4Jw5J+dbi0k06tknBJCCGEEIesvQqYbrvtNjQaDevWrQMgLi6Oxx57bACHJYQQQog/quLGLm79cANlzfZ+2z5dV0enw7Obo35ZY5eT+k4nK8vbiA/Xs6Gmk9tm5WHQqhmWbOWsMcmMSLECEGXSctGEDI4fmsiMvFjOH59KlEnL0KRw/nP6UGraeziuMJ5vNjX+lksVQgghhDhs7NUSuaqqKh577DHmzJkDgMFg+NW/PRRCCCGE2JPyFjttdjcxYf1nBBUkhmPQ/rraRBqlEqUi+H1cuI6hKVZueHc9drcPhQKumZ7NFVMzUSkVhOnVDE4Mx2LQkhJpZFJ2FPnx4ViNal7+vpJVle3kJ4Rx7Yyc33KpQgghhBCHjb2awaTVanE6nSgUwU9lVVVVUoNJCCGEEAPCatDg8vpxenzkxYeF2sMNaq6aloVuN8Wv6zsc1LT34PP//C/AosN0DE22khFt4urp2dzz+Rbsbh8AgQA8+W0pGrWCSJMGvUZFa7cbr88PQKRJx5AkC//+qphVle0AFNV38f8+3kh1W8/+vHwhhBBCiEPSXs1guvbaa7n88supr6/nxhtvZO3atfz73/8e6LEJIYQQ4jATCATY3mKnrsNBtFlHVoyp39PS8hLCmD00gZe+L+fsMSkcVxhPgtXAmPRIMqJNffa1OTx8ur6WB78O1mq6aGI6l05KJ9KkZX1NBz9WtBNh1DA2I5IEq4GsaBP3n1rI2qpOGmzOfuPTq1U8Pr+UJaUtaFVKrpmRxYUT0rEatXj8AWraHX327+jxUNXWQ0pk/yLlQgghhBB/JL8YMPn9fjo7O3nyySdZv349gUCA22+/ncjIyAMxPiGEEEIcRhZsbeKat9bg9PhRKRX844TBnDU6BZ2mN2SKNOm468QCTiiIpsevJCPaTH58WJ99dtraYOPx+SXYnF4AVpa3MijOjM8f4NaPNob2iwnTccPRg/hwVQ1XTc+ivNVOaqSRql1mH+XEmvlmcwNLSlsAcPv8PDKvhKHJVqblxhKmV6NWKvD+ZJZUmH6vfl8nhBBCCHFY+8UlckqlkhdeeIGIiAimTZvG9OnTJVwSQgghxD6rbuvhxvfW4/QEl535/AH+8dlmSpu6++0bbdaRqrVzyohkhqdY+4VLjTYnH66u4dlF2zl+aCK3HpvHnbPziQnTUdLUzYtLy0P76tRKzh+XSkOnk6RIA83dLowaJZdMSifarA3tc9PMXOZu6V+0e1NtJwAZUSZuOHpQn21/mpJBdoz5t90YIYQQQojDwF79ym3ixIm8+OKLzJo1C4PBEGq3Wq0DNS4hhBBCHGba7O5+T4ALBIJPdyvA0m9/tVqNzx/A6/NT2tRNU5cLk05Fm93N0pIW3lhZFdr38bOHUdXmYHBCOOlRJhZva0KtVKBQwGWTM3hjRRXN3S4g+CS6v88ezIKiRk4YlkiYXs2QRAtjMiIYlmztFzKl71iWp1EruXBCGqPSIqhp7yHeYqAgMRyjTmYwCSGEEELs1SeiL7/8EoVCwVtvvdWnfcGCBQMyKCGEEEIcfmLCdMSYdaGgB0C944ltdqcX0y5LzUqbuvi41Ev9mvVkxph4ZN42AgHQqBQ8cfYI3v6xOrTvsYXxzNvSxBcb6gGINmt58PShrK7swB8IUJAYzrs/efrtM4vKePOysbi8fkw6NelRJpRKBdfOyOGHijY6eoJB2JTsaEamRoSOM+s1jMuMIqHNwPrqDj5fX8fgxHAKEy27XcInhBBCCPFHsdcB01tvvcXq1atRKBSMHj2as88+e4/HuFwuzjvvPNxuNz6fj5kzZ3LddddRXV3NDTfcQEdHBwUFBfznP/9Bq9Xidru55ZZb2Lx5M1arlUcffZTk5GQAnnvuOT744AOUSiV33HEHU6ZM+e1XLoQQQogDKtFq4PGzh3P1W2to7/Fg0Kj4y7QsbvlgIxnRRu45oQC9Vk2Xy8O3W5sIKOD0UUk0dbm4fVYeb6yoIsFqIECwWPhOBYnhPDx3W+j15ZMzue7tdXS5gnWZ9BolNx2Tyz/nFIX2cbp9hOk1DLL2zswGGJJs4dOrJ7G92Y5eo2RQXBhRZl2ffarb7Fz2yipKdiztUyjgufNHcUxB/P6+ZUIIIYQQh4xfrMEE8Le//Y2ysjIuuOACzj//fEpLS/nb3/62x2O0Wi2vvvoqn332GZ988glLlixh3bp1PPTQQ1x88cXMmzeP8PBwPvjgAwDef/99wsPDmTdvHhdffDEPPfQQAKWlpcyZM4c5c+bwwgsvcPfdd+Pz+X7jZQshhBDiYJiYHc3n107mmfNGcsmkdN75oYryFjtJFgNvr6rm/dXVfLmxAa1aycTMaNZUttPa7SYQUPDPkwvJjDLx/OLtHD8kIdSny+sPfZ9o0VPRag+FSwBOj5/Vle3kxYeF2q6Ymkm8Rb/bMaZFmZieF8uErOh+4RLAxlpbKFyC4DK/f87ZQpvd1W9fIYQQQog/ir2awVRSUsKXX34Zej1+/HhmzZq1x2MUCgUmU7Bmgdfrxev1olAoWLFiBQ8//DAAp5xyCk899RTnnnsu3377Lddccw0AM2fO5J577iEQCLBgwQKOP/54tFotKSkppKWlsWHDBkaMGPGrLlgIIYQQB1dyhJGXllbw0vflRJu13Dk7H68vQHqUiZs/XI/N4SU71sxlkzLwBwjNPLrh6EG8+UOw7lJ+QhhXHpHJmqoO0qOMob7DDRra7O5+52zvcTOzIA6VUsG5Y1M5uiAOhULxq8Zv3yW82qml243L49/N3kIIIYQQfwx7FTANHjyYdevWMXz4cADWr19PYWHhLx7n8/k49dRTqaqq4txzzyUlJYXw8HDU6uBp4+PjaWwMFtJsbGwkISH420i1Wk1YWBjt7e00NjYybNiwUJ9xcXGhY36Oy+WiqKhoj/vsT06n84CeTwiQ95048OQ9J/aFQq2l1qVj3tYWIowapuVE4vEF2FjXRYRJx7iMSF5dXsFfpmXxn6+LiQnTMSErCpvDi8Wg4bSRSdTbHDy9sCzUp9vXG+C8/UM14Xo1w5KtpEQauG1WHk8uKGVbYxdnjk7uV6j79BHxjIhWMDs7Fb/bSWtNOa2/8tqSwsJRKRX4/L3L9M4alUR3cy1F9Z49HCkOBfJvnTjQ5D0nDjR5z4mBslcB0+bNmzn77LNJTEwEoK6ujoyMDE444QQAPv/8890ep1Kp+PTTT7HZbFx99dVs3759Pw17z3Q6Hfn5+QfkXABFRUUH9HxCgLzvxIEn77l9Y3d66XC4sRg0mPWagz2cA27u5gaueGN16PWrK6q5dkY2D8wtBWBcegSvXTqWN1dW4vL6iTBqae4KLjE7YVgiLy2t4KyxKX1CHI1K2SfYsTm9TMiK4ov19Wyo6eTmmYPIijGTEWXCatTy6Pxt+HwBrp6RzZEFCUQYtfvl2rw+Py9frOXfX22lvtPBOWNTOG9cGskRxl8+WPzuyb914kCT95w40OQ9J36LPYWTexUwvfDCC79pAOHh4YwbN45169Zhs9nwer2o1WoaGhqIi4sDgjOT6uvriY+Px+v10tXVRUREBHFxcTQ0NIT6amxsDB0jhBBC/B5tqu3kX19u4YfydkalRnDn7HyGJFsP9rAGXKfDQ2ePG6NOzZPflvTZ1uP24fT4+fvxg9lU10m8Rc/L35eHQqWtDTaunZHDd8XNWI0amrtd2F3ePk+d+2B1NbfMzOXZRWW093g4dUQia6s7mLdjttL6mk7CdGo+vWYSp45MZlpuDIEAu62j9FuoVUqmDophWIoVp8dHjFmHUvnrltsJIYQQQhwu9qrId1JS0h6/dqetrQ2bzQYEp+AtW7aMrKwsxo0bxzfffAPAxx9/zIwZMwCYMWMGH3/8MQDffPMN48ePR6FQMGPGDObMmYPb7aa6upqKigqGDh36my9cCCGEGAiNNidXvLaK5WVt+PwBfqho47JXV1Hf4TjYQxtQa6vaueDFFUx98DteWVrOiJQIZg9NIFzf+7usLqeHLQ2dHJkfyxsrKlle1sq03FgAPL4Aa6rauWpaFqWNXUzNiea9H6u5anoW2bFmALRKJYPizPzzpEKePGcEJw1PCoVLoXO4vJTuKMAdadLt93BpVxaDhrhwvYRLQgghhBDs5QymX6OpqYlbb70Vn89HIBDg2GOPZfr06WRnZ/PXv/6Vxx57jPz8fM444wwATj/9dG6++WaOPvpoLBYLjz76KAA5OTkcd9xxzJo1C5VKxd///ndUKtVADVsIIYT4TSpbe6jrdPZpa+pyUdnWQ4LVcJBGNbBq2nu47NVVtNndFCaFE27UsHBbM06Pj4snpbOxxsaSkmYKkyw89W0pXU4vj541nC11NuItem6eOYiXv69gW0MXM3JjCdOrGZJk5cWl27n/662cPSaFm44ZxJrKdsw6NUatmoxoEw6PD71GifMnxbX1GvmcIIQQQghxoA1YwJSXl8cnn3zSrz0lJYUPPvigX7tOp+OJJ57YbV9/+ctf+Mtf/rK/hyiEEELsd2F6NUoF7FI6CIUCwnQD9iP3oHJ5fBQ3dIWe3DZ7aCL3fbk1tP3phWXcPiuP2UPjeXjuNmo7HGxvsfNjRTtnjk7m5g82MLMgjifPGUGPy4teo6KkqZuP11YzODGcwYkWmrqc3PDeem44ehCj0yNDT3/z+wPccHQu933ZWwtgZKqVvPiwX3UtTo8PrUopM5KEEEIIIX6Fw/PTrhBCCHGQZMaYuGpaNk8tLA21/WlKBpkxpoM4qoFR3dbDI3OLSY8JLmHLjTOztT64PF6pgMsmZ2LQKmmyudCpVUSatNTuWCrYZnejUwdnGn2zuZFzx6by5aYG5hc1kRZl5JKJ6VS39xBh1GLUKnno9GEMS7GEwiUApVLBWWOSyY03s66qg7QoE6PTI4gN1+/TddR1OPhmcwMfrallSJKF88anUpBo2R+3SAghhBDiD0MCJiGEEGI/0qlVXD4lgwlZUdR1OEiw6ClMsmDQ/r5/5Fa22ilp7MasV5EQbiDeqg8FQDtVtNpZVdGO3eVhUHwYLV0uihq6aO/x8PCZQ6lpc9Dt8gJw8cR0FhQ1sr3FHjr+pmNyqWrrodPhAYIhFMCY9Aje+qGabzYHH+qxoaaTWz/ayFXTsmjpdnN0fiw58WH9xgNgMWg5YlAsRwyK/VXX7fH6eW5RGa8urwRgY20nX26q55OrJpEeffiFgkIIIYQQA+X3/WlXCCGEOARZjVomZUcf7GHstc11nZz/wkrOHZdGQ6eD5WWtDEmycM2MHIYkB2fy1LT3cPkrq8hLCMNi0HDfl1vxBwKcPCKJqTkx3PzBepweP7fMzMWsU2MxavuESwCvLa9g9tAE3lxZxZBES2hZ3bjMKJ7eZcYXgMvrR6FQMKswjtz48AG79toOB2+urOrT1tHjobihSwImIYQQQoh9IAGTEEIIcRip63CwprKdsuZuhiRZGJEaQYRJG9re4/ZS0thNc5eLlEgDMeFa/rd4O8OSraypamd5WWuwn04nKyva+PTqSaRFmajvcHDG6GTMejW3f7wp1N/7q2pIizSiVioBP88uLuPKI7IwavvPNuro8TAqNYIhSRb0GiWdPR4mZEaRZDUQrteEZjbtlB1tGNBwCYKzqFRKBd5di2YBKpXUYRJCCCGE2BfKgz0AIYQQQuwfbXY3zyws5evNDXh8AdbVdDB3SwMeb/Apa3aXlxeWlHPS099z+WurOP6JpSwsaqauw8HQFEsoXNqpo8fDqvI2Pllbyw3vr+fzDXXM29LY77yLtzVz9bQsdGolNoeXh+YWY9Sq0PwkpDl9VDIqFby3qoZ7vihidVUHf56ayaryVv52bG6ffUelWUk19w19BkJyhJFrZmT3aUuLMpI/wMGWEEIIIcThRmYwCSGEEIcwvz9AbYeDQCD4Z5RZi1aj4rnFZXh8AcakR5AXH8awlAhKm7p4ZN620LFef4C7v9jCXbMLKG3uRqtS4vb5+55AAS9/X051mwNnmJ/hKRH9xpAaZWJJaTMPnT6Ub7Y0Mm9LI3qNkofOGMYr31dQ0+HguIJ4JmZHccN76+lx+wD4bH0dXU4PFqOGBIuBd68Yz9aGLmLDdAxLsdJZXzGQtw4IFgo/b1wq2bFmFm5tIjc+jOm5sSRFGAb83EIIIYQQhxMJmIQQQohDVHOXkzdXVPHMojIAzhidwshUKze8tz60z48V7by/uobCJCst3e5+fdgcXnyBAN1OD2ePTeG1HcWuAYanWAkEYH1N547zuYgJ05Fg0VPf6QQg2qwlM9rEB6traOl2My03hvtPG8KikmamD4rljNHJWI0aPl5TS1WbIxQu7bSwuJkbjx5Ej9vL9LxYxmVGhbZ11u+/e7UnkSYdxxUmcFxhwoE5oRBCCCHEYUgCJiGEEOIQtaSkhccWlIRev7GikvQoI3qNEqendybS3M2N/N+Rg0iKMKD+Sb2h5AgDa6raKWns5rSRSTx4+lC2NXYRb9HT0OlkcUkL2bFmSpu6AXj621IunpROVoyJ+k4nbq+fx3eMYVtjN8cUxHPje+t55MzhtPW46XZ6CQRgWIqVKJOm3zWYtCpcXh95siRNCCGEEOKQJjWYhBBCiEPUJ2tr+7Ut3tbSr37Q8GQrYXo12TFmnj53BBZDMOhJjjDw56mZfLK2jlWV7dz28SY+XlPL9uZuXlhSjkKh4OtNDZw3LpVwffB3Um6fnx6XlzCdmsfml/Df78pw7ajxFBumo7PHgz8A21u6uW/OVh6au41752wh3KAhK8bMmLS+S+z+Mi2LE4YmkBVrHohbJIQQQgghDhCZwSSEEEIcogoSLSwuaenTlhljoqHTEXodYdRw7ZE56DTBp7rNLExgcKKFNrsbvz/A9lY7Lm/vsrVwvYZxWZEs2NpMZWsP18zIQq1U8NAZQ3F6/FS19bC4pIXyVjtnjk7mvVU1AGhVSi6fkslTC4OzmRQo8PqDwZPT4+eL9fUcVxjP4+eMYF11B3UdDvITwhmWbMWsl48jQgghhBCHOvlEJ4QQQhyiThqeyPurq0O1laLNWkakWGmw6Dl5RBIalZKcWDOpUaY+x6VEGqlqs9Pc5cbr8/PCRaOpa3dg1KlRKRVYjRpuOmYQLy4tZ0hSOM8v3k6kSUuUWce3W5tC/YzPjOSJs4djd/totDl5+ftybA4vyVYDbq+fXVbisb2lmwCQaDWQaJUC2kIIIYQQhxsJmIQQQojfgbLmbsqaujFqVeTGhxMTpuuzvcPhprzZjj8QINKopb3HEyyefdVENtd1oQDyEsJI+0mYtDvlzd043T421nbyfWkLR+REo1WrePq7zaFQ6Iajcnji7OFsruuiut1BXkI41W09ffpZWd7G5KxoxmRE0OPycsKwRPQaJUMSLVz11po++548PIloU99rEkIIIYQQhw8JmIQQQoiDbG1VO+e/sBL7jiesjc+M5JEzh4dm+tS293DnJ5tZvr2VW47N5ZnvymjqcmHQqPjnyYWcMCwBrVr1s/3XdTiobLXT7fTi9PpQK5V4fH5cXj9njEoiyqynqN7Gbcfl4/D4eHxBCY/ML+Gli0fTag/Ojlpd2c5pI5PZ2tAFQFy4jj9PzWJJSTNfb2ng9FEpDE4MhlDbGru44/jBPDy3mC6XlxOGJnLBhDSUSsUA30khhBBCCHGwSMAkhBBCHEQ9bi8PzS0OhUsAK7a3sa6qIxQwfV/WyrfFTZw1JoUXl5bT1OUCwOHxcdMH68mLD6MgydKv7/oOB2Ut3Xy5oZ5Oh5c5G+sBMGhU3HJsLiu2tzIjL487Pt7ExZMyKGvuRqmAh88YxkNziylp7GZEarDfNrubToeHs8ek8PHaWi6bnMH9X23F7QvWWdpUu5lbZuaiVipo6XaTFRvGl9dPwe31k2Q1hGpACSGEEEKIw5METEIIIcR+1GRzUt5qR6tSkh1rJkyv2eP+3U4vW+u7+rXXdvQuR/uhvA2AmDAdNe2OPvsFArC9xU52rJnVle28ubKKwqTgErs1le3kJ4Rz1OA4Ln1lVegYh8fH68srGZZi5cuN9dw8M5ebP9iAd8f6uHdX1XD7rHy6XF5aulz844TB/G/xdr7YUMc1M7J44LQh1LQ7QuHSTq+vqGRyTjTfbW1mem4MLq+f7c12mrpc5MaZiZAlckIIIYQQhy0JmIQQQoj9ZFtjF395YzVlzXYAjh+awJ3HDybeov/ZYyJNWmYPTeDV5ZV92gcnBGcOeX1+xmVG8sHqGmwODzFmHc3drj77ttpdrK5s59wXVjI8xYpOreSBr4tD28dnRnLC0AQ+31AfatveYmfW0ASKam2UNHUTb9GHwiufP8C66g5GpUUQE6blyW/LOLYwnqMGx+Hx+iiq78Ll7RsuAeg1KlweP+09bmo7nFzx+mp6dszMOrYwjntOLCQ2/OfvhRBCCCGEOHQpD/YAhBBCiMOB1+fnle8rQuESwJwN9fxY0bbH49QqJRdPyuCo/FgguHzt77PzibfoeHZRGWc+txyVQsGxBfF8sq6Wv58wGL0m+ONboYCLJ6bz2bo6qtqDM56OLYzjk3W1fc6xYnsbgxPCOWdsCtfMyObYwnhGp0XQ5fRw/LAEqtp6GJ8Zxf+blU+0WQtAt8tLRrSRj9bU8O9TCvnzEVlMyIziiNw4puTEMDI1Aqux7+ys00cls6CokSPz43hteUUoXAL4elMjG2s7f+XdFUIIIYQQv3cyg0kIIYTYD+wuL0tLW/q1b6rt5IRhiXs8NiPaxBPnjKC23YFWrSTSqOX6d9bybXEzAGuqOjhvXAovXjQGh8vL5VMyAdColMzfEgxuzhmbSrRZS05sWOhJcDslWPQkRxp5bUUl9Z1OhidbuWnmIMpburnhvfWh/XRqJdcfmcN/vinmtJFJ3PtFEXkJ4SRGGIgJ6515VJBkoQB4+0/j+a64mdqOHpKsBuZubsTu9pEaaeS74qZ+17mzdpQQQgghhDj8SMAkhBBC7AdmvYbpeTG8uqzvUrehydZfPLbJ5qS4oQuPz092rJnKNnsoXNrpzZXVHD80ET8B1lS2s6ysNbTNatSQFmnk6unZfLy2hlFpEayubA9tv3hiOje+tz5UM2ldTQf3frGFGXlxfc7h8vpp7/Hwj9mDWVPZzsNnDiM1yojVoN3tuPMTwslPCMfmdPPikgrW13QAUN1u58i8WL7c1NBn/8xo0y/eCyGEEEIIcWiSgEkIIYTYD2wOD1NzYog261Cg4LP1tQxPiWB0esQej6tstXPNW2tDy8eiTFqeOX8kAFqVksk50ejUSpaWtGB3eVlW2soRg6JJtBpYXtZKfkIYF4xPo83u4qPVtWys6+SaGdlkxpiobu1h9rAE9GpVv4LcxY3dnDYqpd94/IEAzy4qo9Xu5pLJGT8bLu0qXK/lqmlZHFcYT7fLS2qkEZvTS1O3i1UV7Rg0Km47Lo/C3TzpTgghhBBCHB4kYBJCCCF+o44eN//+qoj3VtWE2h48fSjHD03AqA3+qPX7A1S02mmzu4m36EmOMAKwrLS1T22iVrubD1bXcMfxefgDCuZsqMPh8XHltCyUKPhobQ33nVJIRrQZg1rFlgYb17+7jqfOGUFZSzcAT31byp+mZGBJtvDQ3G1cNS2r35jDdGqSrH0LbquVCmLMOhq7XBQmhv/iE/B2pdOoyEsID72ODYeXLxpDTYcDo0ZFapQRhUKx1/0JIYQQQohDiwRMQgghxG9U3NDVJ1wCuHfOFiZkRWHUqvH4/MzZUM+tH23A6fGTEmHg6fNGMjTZytZGW7/+1lZ1cOaoFE5/bnmo7cFvirn3pAJGpUVQ0+7kmUVldPR4QtsfnbeNowfH8em6OmLDdPj8AV76vgKA70tbmT00gS92eYrc5VMzmbOhnn+fOoTP1tVh1qs5Oj+W+UWNGDQq/nFCARbD3gdMuxNm0JD/G/sQQgghhBCHBgmYhBBCiN+ow+Hu12ZzeOl2egEobermxvfX4/MHuGRSOhqVkofnbmNabgyj0yL61W06aXgii7b1L5L93qoa/nVyAZVtjj7hEkCn08u5OdE0dbmIC9Mzd0tjaNuibc3MyIvloTOGUtPuQKVU8Pn6OnrcPjJjTPgCAeo7HcwrauLyyZn87dh8smLN++PWCCGEEEKIPwjlwR6AEEIIcahLizKhUfVd/jUs2ULCjiVo9R0OfP4AMwvi2VJn4/nF21m0rZl5WxrpcXm5fHIGGpUChQKOK4xnak40PW5/v/NYjRqeWVTGtoYudOq+P8I1KgWLS1rQqpSMz4okLlzXZ/u3W5tos7uJMmvx+wNcPCmdWUMSeHbRdn4ob2NznY1LJqYzLjNKwiUhhBBCCLHPZAaTEEII8Sv1uL2srepgXVUbD50xjAe+2kpdp5Ox6ZHcc1IBlh0FsmPD9SgUkJ8QxmPzS0LHj8+MwubysaSkhSumZqFUwKqKdoobu0mPNmLRq3H5/Dg9flRKBUcMiuG+L4vYaLVxwzGDaO12o1UrCfgD5CeE4Q9AeYuduZsaOH5IIuurO/H6AwAkWPQkWg2olQo8ngA5MWZiw/R09njw+QOcNiqZUWnWg3EbhRBCCCHEYUACJiGEEOJn+PwBGjodaFRKYsP1/bbPL2rkwW+K0atVNNicnDEqmZOGJ5EVY8K8o0B2o82JUaviyXNG4HT7OX9cKv5AgHiLgYwoI19sbKC4sYvixi4A0qOMrKtsZ/KgaB4+cxg9bh8Aeo2Sf87Zij8A3S4vBrWKd36swubwcvPMQTzxbSnbGoNFvo8eHItKCc9fOIrKlh6USgXp0UZyYsNItBpYV93OhS/9gM3hJSvGzLRB0WTGmNCqVQfozgohhBBCiMONBExCCCHEbtR1OHh1eQWvfF+BSafmtuPyOG5IAmZd8EdnW7eTNrubcRlR2F1eTh+VzBcb6hmWYmVYihWXx8f8okbu+mwLWrWS/zsqh9eWV1LT3sOsIQl0Ojw8v6ScmLDgUraRqVaOHhxHcUMXM4ck8Oi8bayt7iDRoufSyRnEW3Q02pwAnDYymUfnbwsFRCWN9lC4BDBvSxMzcuPYVN3JjMFxFCZZQtvsLi8PfL0VmyNYH6qsuZuy5m7GZ0Vz9OD+IZoQQgghhBB7Q2owCSGEELvx6bpanlu0HZfXT5vdzc0fbGBtVXto+/aWHv795VY+WF3DV5sa+PdXWzl+aAIer5/OHjc/lLdx9Vtrae52cc7YVG77aCMbaztp7/Hw5soqWrvdeHx+JmRFYdKqODI/jge+LsbrD/Cfr7eytroDgLpOJw98vZWGThfnjU0FwKBV0b6jyHduvJkNNR39xl/a3M11Rw/qEy4BdDm9bKrp/+S6ylY77fb+xcqFEEIIIYTYGxIwCSGEOGw12ZysqmijqN6G0+Pb6+M6e9y8+2N1v/Yftrf1fl/ehsvbtxD3VxvryYk3c927aylp6p1R5Pb5QrWQdvpyYz3TcmN4f1U1/zljKB+urgEgK8bMprq+AZDHF8Du8jJraDx/PSqH3Dgz4frgTKrihi6GpVj7jbUwKZxOh6dfe4RJw1H5sf3anR4/572wkm07luoJIYQQQgixLyRgEkIIcVgqqrdx+rPLOP3Z5cx6YgmPzt9Ge8/ezdDRa1RkRJv6te98KhzQLzAC8AUCrKnsYGJmNN0ub6hdpez/4zbSpKXT4WFbYzdb62y4fcGwqtvlJdzQfwV7vEXP/V8XY9armbOxgRuOGYROraSs2U5GtIm8+N4nvx1XEM/66g7Oem4ZC7c24d4lCNOpVVw1I5uRqVYAtColl0xKZ8X2VrbU23hsfgmufQjjhBBCCCGEAKnBJIQQYofihi5Km7oxalUMTgwnbjdFrQ8VDrePh74ppqrNAUAgAM8t2s6krGimDor5xeN1GhXXzMhmWVlraJZSaqSB8ZlRAHh9fiZmRfHEAkWfoOlPUzJptrnIijFR3+niztn5LC9rpaPHTVaMmbLm3llNl0xK5+mFpQxJsjAsJYJwg5Z/fVnEZ+vquOqIbB74ZiuBHV2fMCwBk1ZNcX0Xth4P/zqlkLz4MKZkx1Df6SA6TMfZY1KoauuhvtPJ+6uqeWVZAwCXvvojH1w5gVFpkaFz58SG8fIlY1he2srGOhtfb2oIje274iba7G4SrIbf8DcghBBCCCH+aCRgEkIIwY/lbZz/4spQmDI8xcrT544gKcJ4kEf263T0uFlW1tqvvaqtZ6/7GJUWyadXT6K4oQutWklBogWNChZubeLdH6txerw8de4IvthQT6fDwwUT0tCrVXh8fu78ZDP1OwpyH50fR0FiOGPTI2nqclHb4aAwMZzoMC1/PWoQ66rbeXdVFReNT+fmmbnM3dxAZZud/547kgabkySrgQ01HVS0dvP8haNYsq2ZT9fVYRibSmGShazY3plLKqWCa95aS8OOc0MwXFtf3dknYAKwGLRo1UqeXljap31YioVwg2av75MQQgghhBAgAZMQQvzh2Z1e/vNNcZ96QuuqO1hX3XHIBkwWo4YxGREs3tYCQEFiONPzYsmINuHy+tCpVXvVT15COHkJ4QBsru1kRXkrD35TjNMTvFffbWvhP6cN4bRRKTR3OXn5+woqWntC4RLAvKJGRqRZ8fmdbKrrpL3bhUapYG2VjzEZkUS265iSEEaL3c2IFAtqpYI2u4vmbhcrylrpcHg4ZUQSkUYND36zjTU7Co1/vqGej6+aSGZMb8CkVSuJDtP2CZgALD8TGA1JtnDqiCQ+WlsLQIRRw23H5WPSyccDIYQQQgixb+QTpBBC/MHZ3d4+S7d2arS5DsJo9g+jVs0tM/MobviR8ZlRaFVKnv2ujP8uLOWM0clcf+QgEvewBKzN7kKlUGAxagEIBAK8v7qacIMGp8ePSqng4onpxIfraOl2s63BhsvrZ+qgGD59b32//npcXo7Iicbh8lGrVjE1J4b3V9fw7o/VnDA0geXbW1lW2splUzLYUPP/2bvvwCqr+4/j77tHxs3eiwz2HoKAICggIm60auuo1lb9uXDbaltbra3WUbts7dBW657gBmU4QGRDIAmQhOy9b+7+/RG9GuNAIQHx8/qnvec+4zxPH540n5zzPa1ML0jglue3hqffrdnTxOI5g5kxOIGaVjdVrd20un3sqGnvFTBF2S1cN3cIF/z7Az6euZfqsjPuo3pLn5UYZecXJ47gnClZdHoC5CREkBX37QwVRUREROTgUsAkIvIdFx9p4+SxafzzndJe7cPSog9Ohw6Qkekunr9sGit21nPjs1vC7U98UMGwlGjOnzaozz4tXV5e3lLNn9/ehc1iZPGxg5men0BxXQfxkTYSImz8cFoOaTF2jAYjRbXtTM2P567Xi1i+o45fnjiciTmxLNlc3eu4GbFOlu2sZ3d9Jx5/kHd3N/DshgrMRiPjs2J4Zn0lNx43lN++uoMou4XYCGufIuKvbathULyTE8ak8beVu4GeKXGfNTU/gad/MpUtla1E2c2My4r93ILlH4t2WPpMnxMRERER+boUMImIfMeZjAbOm5pDQ4eXlzZXEWU3c/P8YYxJdx3sru23VJeD1cUNfdpf3FTF96dkYzb1Xt3trZ113Pzc1vDn65/ezG9OHc2VT2wIF9wemhzF9ccN4YcPr2NoShRd3gDLd9QB0NDhZXhqNLvqOyisbsdogFPHZxBhM7GyqIHt1W1cfWwBHn8Qs9FIRqyDotoOXA4LNW3d+AIhgqEQ5s8JjsxGA53eIDZzT5/TY+wMS+0bAlpMRsZnxzI+O/Yb3zcRERERka9LAZOIiJAdH8Fdp4/m6jmDsZmNXzp97NtmdGYMS7b0HlE0ITs2HC6VN3Wxp76D+Agrj7xb1mu7+aNSuev1T1ZzA9hR205RXc+Uwkk5cby4qSr83WNryrn62MFMGRTHnOHJuBwWcuIiWFfezPbqNgACoRBvbK/lB0dm8/jacuaOSCZECMNHmVJLl4/kaBt2izFc6+njvqwqqsdqMnDt3CEcNzJZ09lERERE5JChgElERACwWUxfOpXq26S5y0tJbQfd/gBT8+LJS4xgV30nACkuG6dPyABgS0Ur5/1rLU2dXs4+IpO4yJ6aS1Pz4pmal0B2vIOXNlVhNMCMgkTSYhx8UNqE96OC6FWtbgYlRLBxbwsAjZ1efv3ydu46fQzRdjONnR7uen0HO2p6AqnESBudngC17d0MTYniRzNySYy0kh3nJDHShs1sxOMP8tCqPVx17GBqW7tp7PQwMs1FY6eXmxcMoyApEus+FikXERERERkoCphEROSwUtXi5qfPbuGtonoAUqPt/P28CTR2+AiGghQkR5ER66TbF+D+ZUU0dXqBnlpUeUmRVDW7GZISxd2v72RoShSnj89gRHo0/kCIZreXMydlMiItmiNz45mYHUt6rJPrn94UHm20YFQqnR4/T6+r4MSxqeQkRFLV0s3oDBenjs9gV307l8zM45cvbcdgCPGv84/g/2bl0+UNcM8ZY3inpIHmLh/5iZGcOyWbYChEW7ef+EjrPq9+JyIiIiIy0BQwiYjIYaPL62dXfTtpMQ4um5VPl9fP8xsq+ceqPfz8xBFUt3bj8QXxBYK0u33EOC1kxTkpb+qi2xfkP++Wcv38YVz1+EYAdtS083+z86lr83DXaztx+wIAxEVYuWfRGM7/9wfER1i5/eSRVLV0gwHiI6zhouIriuuZkBXL38+dgC8Qor6tm3GZsZTUdbJ4zmCOGBTHyI9qXfkDQcqbuhieFk2qy4Hd8kmYFGm3DOyNFBERERH5mhQwiYjIt15Du4c3Cmv5z3tlpLrsHD00iQeWFRMIhrjk6HxsZgOX/28Dq4obsJgM/HhGHnERFjbubWVybhwnj0vjmQ8rOeuITAqr2/AGekYjfVxre82exnC4BNDU6WVtaRMJkVYaOrz8/MXtXHFMAW/vrOuz+tuH5c08/WElFx01iOkFiQAcO7zvNZhNRnITI/vnBomIiIiI9DPjV28iIiJyaHtmQwU3PbuF7dVtLNtRx69e2s55U3No7PTy+9d3EmEzs+qj1eR8gRB/fKuELm+QXfUdPLWugrd31jMhO4ahqVEMTo5keGoU0FPE2wDUtnn6nLOyxY3L0VOzqcPj57E1ZfzfrDwspr4rwGGAXXWd/Xb9IiIiIiIHmwImERE56Cqau3hufQW/faWQ17fV0NjZN9D5InVt3fx95e5ebd5AkC5vAJPRgMcfpKrF3We/6lY3MY6eqWebK1qZNSSJpz6ooKLZzSnjMjh6cCKxTgsldR3MHprYZ/8jcuLY09DxqeN1s66smYWj03ptZzEZyE+MxPx5wZOIiIiIyGFCU+RERA4x26taeW93Ix5fkCl58YzJiMFkPHzDicYOD9c+tYn3dzeF2y45Oo/Fxw7GYv7qv4OYTYZe9YrC7UYDwVAIgwESI+19vh+a2lOo22CAl7dUU9bUxZjMGD7Y08SEnDhOHJdGSpSN0sYufP4gV8zO5+H3yrCajVx6dB55SRGcOTGTV7fVkB0fwUlj03hlazUzCxK5+fhhbChvxmY2MSE7Fo/PH661JCIiIiJyOFLAJCJyCNla2cqZD75Hp7en3o/JaOCxiyYzOTf+IPes/xTVdvQKlwD+tnI3p41PJz8p6iv3j4uwccP8IazY2UCqy04wBO+W1BMMhQiF4EdHDSItxkZchDW8YtyUQXEYCHHVExsJAbedOByr2URLl48JOXG0ur2s3d3I6MwY9jZ1kRnn5MPSJn48I5cR6dE8uGI3f3l7F3edNpopefF0efxsqmjhJzPy+Ml/1+MNBClIisQXCPL8xkr+fu4E0mIc/XH7REREREQOCQqYREQOIcsKa8PhEkAgGOKh1XuYkB2L2XR4zmr2+AN92gLBULjQttcfZGtVK9ur2nA5LIzOcJEdH9Fr+3SXgw1lzTzd0InVZOTuM0bj8we545SRJEfbueWFbfxkZi4JkTYcFhPBYIjL/rcBgHMmZ/HY2r1sq2oDegp733X6GJ78oIKxWTE8v7GKaLuZGYMT2bC3hbd21hFps1DX7qG4roM/vFXMnKHJnD0li/ZuP75gT78NBjhtQgYefxBC0O72EeXQanAiIiIicnhSwCQicghp7vT1aWvs8BAIhjD3nQV2WMhPiiQx0kZ9h4dIm5kzJ2WSFuMgGAzh9QfYUN7M0i01fFjWzLaqNgYlRPDvCyaFQ6ZOj5+7XytiV0NPEe0zJ2Xy95V72FLZCoDdYuS+M8ayraaN5Gg7TquJf71bGj5/UrQ9HC4BBEPwh+XFnDA6FW+gZ0W4tm4/SzZXA5AZ52BithOA2AgLd546mqEpUeQmRuLxBThlbDrv7W5kwahU7nmjiNBHi8pdenQel83KJ8KmH70iIiIicvg5PP8cLiLyLTV3RHKftgum5WD7nBpDh4uMWCcP/3ASZ0zM4Kbjh/Lixip+tWQ75/7zA1aXNPDbV3fy/MZKsuKcXD1nMKWNnazd00TZR4FSU6eXd3c3Aj2jhsZmupg9NImrji3g6CGJdPuC/H31HiZmxbK6qB6PP8jw1Ojw+f0fjZT6tOqWbiLtZoam9J2iN3d4CquLG1gwOpXJufHMGZZMbmIkADaLicVzBnPrCcN5cOXucLgE8Oe3d1Fc134gb52IiIiIyCFDf0YVETmEjM+O5R/nTeSB5SV0evxccnQeMwqSDna3+t3wNBfXzxvCVY9vosPjB3qmrl3+2IbwlMFXttbQ2Onl6MFJ7Gno5NdLC/nr98czPC2a4alRbK9u58czcnl6fQXv7eqp6TSjIIEfTMlmyeYq3they8whSdS3eyhIiuTG+UNZs7spPGoqOdqGyWBgU0UrsREWIqxmNpW38POFw/nv++W0uX2cOSmDVJeDW04YxuTceJKj+xYPz4hz0tTlpcvbd+pfU4e3H++iiIiIiMjBo4BJROQQYreYOGZYMlNy4wkGQ9+Zmj0tXV7WlTWTEmPn/IwcQvSs/tb5mZBm7Z4mrpidj81iotXt45onN/Hnc8bzvUlZ/PvdUqxmUzhcAlhZ3MBP0qI5fXw6WfERvLurgZYuH2MyY3hxYxX5SRGMy4rhqQ/3UlLXMyJq9tBE5gxLpqyhkyiHmYwYB6eOT6OmtZvi2g6OHZbM2KzYL72eNJeDrDgH5U3ucJvNbCQr3nkA75qIiIiIyKFDAZOIyCHou1SnJxQK8dS6Cm5/uTDclpsQwUUzBvXZ1mExMSItmjtf3QlAbISVnTXt/P6NIh7/0WR+9sK2PvsU1XRw3rQcfvTwunDh8Je31nDz8cN4Zn0Fz6yvDIdLAMt31DMy3cWknFh213exrryZowoSmD/KQVKkjUj7V4d+CVE2/nj2eK57ejM7a9pJjrbxu9PHkJsQ+bXvj4iIiIjIt8F35zcYERE5JFU0u7n3zSIsJgNzh6cwKDGCiiY3TouJqXnxvLurMbztZbPy+NPyEvZ8VH/p+JEpvLurgUk5seysaWdCdiwfljX3Ov7EQbGsKqoPh0sfe2N7DceNSObFTdWf26fTxmVw1H5MTxydEcPjP5pCfbsHl9PyudPpREREREQOFwqYRETkgGtz+yht7MRkMJCTEPGlI7L8wRBGg4Gbjx/Gk+v2snRLNXmJkZwwOpW7Th/NpooWShu6MJsMlDd28eOj86hsceMLhJgyKI7H1u7lpvlDaer0MiItmqEpUeyo6SmmPSbDhT8Qwh8M9TlvIBiiqsXNkblx4cDqY6MzXKTFOvb7PsRGWImNsO73cUREREREDnVaRU5ERA6o8sZOLv/fek784zsseGA11z61ia2VrYRCfUMegPQYOz9bMIwHV+ymsLonGNpV38E1T20iEAJ/IMR9bxbzz9WlpMU4WPzkJl7YWMWuunYqW9ycPzWHX7y0jex4J7vrO7joqEFceUwBVx1bQHZ8BM9tqODIvHhMRkOv884dnkxshI3haa5eq8WdOCaVmYMTsZj0I1JEREREZF9pBJOIiBxQS7fUsKKoIfz5la015CRE0Nzp5ajBiX22t5pNZMY5qWnr7tXe6vZR3tjJo2vK8AaCnDo+nb+u2MXVcwazcW8LH5Q1EwwZOG18Oj9fOILbXy4kIdJGeoyTtBg726vaGJsVw4i0aO5Yup1fnTSClUUNdHh8nD4hg1a3j2UfVrCnoZOfHT+M7IQIEqNs5CVGfqdqYImIiIiIHAj6f9AiIt9xXV4/drMJ42dG+HwT/kCQN7bX9GnfWdPO5r0t5CdFkhrTd+pZUpQNs9HQayqbwdAzfW7uiBQm5sRjtxg5ZXwG/3mvjMqWntXZ9jZVsqehg+vmDaGotoOi2o5wzaaUaDtnTc4kPcbBwrHprCyq5+ghibR0+VhVXM/8UalcPrsAl8NCdryT3EQV4BYRERER+aYUMImIfEftbe5iyaZqXtpUxfisGL4/JZuhqdH7dUyzycj0ggTWl7f0as9LjOSJdeW0uH2fGzB5fAHOn5bDQ6v2hNsunDaI+98sZsPeFqJsZu48bRShUCgcLn1sU0UrXn+QYSlRFH5Uewmgpq0bo8FAZUs3f1xeAsCr22pJibYzPC2avIRIBilUEhERERE5IFRgQkTkO8jtDXD3azv57as72F7dxn/XlHPuv9ZS0dy138c+aUw6wz5V02h0hosQIWKdVhKjbEBPoNTq9gLQ0e3jj2/vYkN5C9fMHcz/zc7nmrmDSY+1s6u+A4B2j58Py5oZnBTV53wGA2ytauXqOYPDxzcZDZw/NYdVxQ3UtLoZk+EKb1/T1s3E7Fh2N3Ts97WKiIiIiEgPjWASEfkOqmju4sVNVb3a6to8FNe2kxHr3K9j5yVF8q8LJvFBaTN7GjrZVd/B0s3V/Omc8cRHWFlX2sQfl5dQ3tTFGRMzmJgdS2lDJztq2vmwrDl8nJPHphPtsNDW7ScvMZJAKMRzGyuZmhcfngYHcNr4DLZUtBICLp+djwGIdVrZWdtOty9AUpSNydNyKG9y4w0EcVpMvLS5Crslc7+uU0REREREPqGASUTkO8hoMGAyGPB/ZmU38wFaOS3F5eCE0XbKGrtocfv46fHDcFhMrNnTyHn//ACPPwjA1qo2CqvbOG5ECjs+Nb0NoCA5khc2VQIwb0QyD63agzcQ5KwjMpmUE0d1azdjMly4/QGe/GAvBclRFNW28+OZedS1dRMfaeWMiRmkuBzc+sJW/rd2b6/jD07W9DgRERERkQNFAZOIyHdQVryTH80YxF/e3h1uG54azZDkvlPQvimDwUBOQgQAexo6ueqJjUzMiQ2HSwA5CRF0+wL4g0HOn5rD/9aW47CauOzofMwmsJqMePxBEiJteAM9+/1v7V4sJgMxTiupMTZy4yO47aQRxDis5CQ4sVvMZH5mFNaPjsplb1MXq0sasVuMXDNnCGMyYg7YtYqIiIiIfNcpYBIR+Q6ymIxcOD2XUWkxrCyuZ0SaixkFCSRF2w/oedrcPlrdPt4paaCurZvkqN7H31Hdxqg0FyaTgVe31nDe1By8/iC+YJDnN1Rx4fRBmE0Gmru8zBycyIqiegB8gRC+QJDpeYk8uqaMFzdVER9p4xcLR3DssCRsFlOv8+QmRvLX70+gosWN3WwiK855QFbNExERhuihrgAAYs1JREFUERGRHgqYRES+oxIibRw/OpXjR6f2y/HX7mnk10sK2VLVyhE5cdx4/DDWlzWT5rJT1doNwPIddVx8VC5dvgD3vFFEycqeEVVRNjNXzSnggz1NFNd1MC0/gTMnZVCQFMkrW2sYneHiytn5/Pu9Mp7f2FNLqr7dw2WPreeZS45kQnZcn/5E2i0MTbH0y7WKiIiIiHzXKWASEZF90m6K5p/v7KHL4+fIvHhGZ8Rg+YKaTdsqW7nokXW0uf0ArNnTRH27hyMGxXLqhAwCgRD+QJBpBQks2VJNty/AKePSeWZ9T82ldo+fv769m7+eMw67zYw/ECQj1slxI1K5dFY+ETYTjR1ent9Y2efcJXUdnxswiYiIiIhI/1HAJCIiX6mwuo0LH91Ku6cnMDIa4L8XTmZqfsLnbr+1qjUcLn1sd0MnC0an8sDyEhwWEz+emcu1T22iocMLwDmTs7jymAJWFNUzKCGC4anRRDmsDE7pXRcqLsIKQITVRGask+K6jl7fxzqtB+SaRURERERk3x2Y5YJEROSwtrKoPhwuAQRD8Oe3d+HxBXptV9/ezWvbqun2BT97CCymT2oeuX0BQiHC4RLAo2vKefT9Mq46poCxmS6mF8T3CZc+zeW0cuvC4Zg/VUtpQnYMI9Nd3+gaRURERETkm9MIJhER+Uotbl+ftqZOL/5gCNtHn+vb3fz3/b385/0yLp+Vxynj0nhuQxUGA7gcFn44LYfcxEjGZLhw2sxkxTv7HLPd48dkNHDciBSSXY6v7NfUvAReuGwaxXUdRNnNjEhzkeI6sIXKRURERETkqylgEhGRPsqbumhz+0h12YmPtHH0kET+8vauXttcOH0QEbaeHyN1rW7e39PEf94vo6nTS1Wrh6xYJ3/7/gRa3D7KGjtJjrZjNMA1cwtIjLTjsJrJiLFT0dIdPubFM3KZmp+AaR9XeDMZDYxIdzFiAEYt7Wno4J2SRnbVdTA1P4FJObHEaDqeiIiIiAjQjwFTdXU1119/PY2NjRgMBs444wzOO+88HnjgAZ588kni4noKsC5evJiZM2cC8OCDD/L0009jNBr52c9+xlFHHQXAypUruf322wkGgyxatIiLL764v7otInLI6ez2s7elC5vZRFacc5/DF4BuX4Di2nYqW9ykuRwUpETisJjx+AJsr26jtKGTuAgrI9JdJETa8PoDvLylhp89v5UOj5+8xAju/944Rqe7+Ns5Y/jLyjJCwA+n5TAtP4Gyxk7au/28ub2Gpi4fTquJpk74+6rd/OioXN7Z1cDD75WF+zNvRArnTskiM85JpN3Cv394BK9vq2VbVRvzRqYwNS/+a13fQKlqcfOjhz+kpL6n3tO/3i3lxvlD+fGMXAyGQ6+/IiIiIiIDrd8CJpPJxI033siIESPo6OjgtNNOY9q0aQCcf/75XHjhhb22LykpYenSpSxdupTa2louuOACXnvtNQBuu+02/vWvf5GcnMzpp5/O7Nmzyc/P76+ui4gcMnY3dPDLF7ezoqgem9nIlccWcPYRWfs0csYXCPLUur3c8sK2cNsvFg7nnMnZvLK1hque2BhuP2F0KredNILK5m6ufnIjoVBP+676Tq5/ZjOXzsilvKmL648bwgelTeysbScE/GPVbo7MS6Cu3UNRbTtnTMzknjeKAHBaTTy0enevPr22rYbvT84i0m4BID8pivykL66zdKgorG4Lh0sfu//NYo4flUpWXN+pfiIiIiIi3zX9FjAlJSWRlJQEQGRkJLm5udTW1n7h9suWLWPBggVYrVYyMzPJzs5m8+bNAGRnZ5OZmQnAggULWLZsmQImETns+QNBHn6nlBVF9QB4/EF+9+pORqRFM3Nw0lfuv6ehk9uWbO/V9qulhYzNjOHnL27r1b5kczVnT86iudMbDpc+tr2qDYvZyKjMWH7473W4PyrsbTIa+OWJI3h/VyNv7azj/2bn82ZhHTccN4Tiug4yYx19jgVgPARHKH0VX6Bv0XJvIEgg+DkXKCIiIiLyHTQgNZgqKiooLCxkzJgxrF+/nkcffZTnn3+ekSNHcuONN+JyuaitrWXMmDHhfZKTk8OBVEpKSq/2j4OnL+LxeCgsLOyfi/kc3d3dA3o+EdBz910QskXy8taaPu0by5pICTUTDPYNPT6t2h+BL9A7AAkEQ9S2dtH6OUW7a5vaiXX2/bGQHG2jocNDaVlzOFz6+Fivb6vh+FGp7Kxtp7atm5PGpFFU18GErBiGJjsYmRbF1qr28D6p0XZcxoP37JrMFtpw0OIOEO804Qx0fOV9BEi2RxPtMNPm/mQlvdPHpeFrraWw3tOfXf5O03tODgY9dzLQ9MzJQNMzJ/2l3wOmzs5OrrjiCm6++WYiIyM566yzuPTSSzEYDNx///3ceeed/OY3vzmg57TZbAwbNuyAHvPLFBYWDuj5REDP3XdBty/AqPRqlu+o79WelxzNkCFpX7l/ZFMXLoelV5gUbTeTnxzN5EFxrNnTFG63mAwMz4wn1mnlvCOzw3WTrCYjFx2VS2ask80VbX3O4fUHiXFaGJ3hYs2eJkIYGJ0ezbT8BNJjndz3vXH8Y/Uelu+o44hBcVxydB7DU/u/IPfn8fqDPLehkp89vwlfIITTauLP54zn6GFfPRoM4NELI/jH6j1sq2rj1PEZnDgmlfRYTY/rT3rPycGg504Gmp45GWh65mR/fFk42a8Bk8/n44orrmDhwoXMnTsXgISEhPD3ixYt4ic/+QnQMzKppuaTv9TX1taSnJwM8IXtIiKHM7vFxFXHDmZdWXN45My0vHjGZcbu0/6ZcU4e/MEEFj+xkarWblKi7dxzxhhinFZ+eeIIfvfqDpbvrCc7zsmN84fS1OnhuQ2VFNd1sHjOYLyBIMNSonj6w704LSZyEyP6nOPcqTnc8vw26jt6RvEUVrdz4pg0Fo5JB3pqLN120kiunesj0m7GZjYdoLvz9e2q6+CmZzfz8ay2Lm+Aq5/YyEuXTydjH4KiURkx3L1oDN2+QLiGlIiIiIiI9Oi3gCkUCvHTn/6U3NxcLrjggnB7XV1duDbTm2++SUFBAQCzZ8/mmmuu4YILLqC2tpbS0lJGjx5NKBSitLSUvXv3kpyczNKlS/n973/fX90WETmkjM6I4aX/m05JXQcOq4khyVHER9pwe/1sqWxld30n8ZE2Rqe7SHbZAahrc/NBaTM7atoZmxnDYz+agtsXwGQw8PzGSq5+ciMjU6O5ck4Bl87KY1d9J0s3VzFvZAp/XdFTlPvdXY1AT6HuxXMG82FZz/Fumj+UV7bW4PEHOHFMGoFgMBwufeylzVVcPjufguSe4t0Wk5H4SFu/3qfi2nZK6jqwW0wMS40m5aN78Wk1bd18tmRSc5ePhnbPPgVMAGaTkUiT8UB0WURERETksNJvAdOHH37ICy+8wODBgznppJMAWLx4MUuWLGHHjh0ApKenc9tttwFQUFDA/PnzOf744zGZTNx6662YTD1/6b711lu56KKLCAQCnHbaaeFQSkTkuyA7PoLs+N6jh5Zuqebapz6pR3dUQTxXHjOYJZuqMRohMcrGf94v44HlJfxgSjbXzBnMDc9s5s0ddSwYlcqYDBeVTd2kuGwkR9sJGQzsru/sc+4ubwCPP0iqy86zGyoprmtnWn4CVpON3Q2djEjrO93NZDAMaCHvDeXNnPPQGrq8PfWhRqW7+PM548n8zOpuqS47JqOhV2HuuAgriVF9wygREREREfl6+i1gmjhxIjt37uzTPnPmzC/c55JLLuGSSy753H2+bD8Rke+SymZ3n9XhVhU3MjGnkX+/Vwr0jDz6v1n5/O61nfx3TRknjU3jte213HjcUJZsruLFTVXYzEZ+MCWb1Bg7UTYzgVAIm9mIx/9J0evMWAdjM134AyGeWLeXhg4vb++sx2k18diPppDqsjMiNZpt1Z/UZzp/ag6xzoGZQub2BrjvzeJwuASwpbKVD8ua+wRMuYmR/O600dz83BY8/iBRNjP3nTmW9FjHgPRVRERERORwNiCryImIyIHj9gV6rWb2MX/gk2CoyxugocNDcrQNAwYMBpieH897uxrYWtUTBnn8QR5avYdr5w5hTEYMf1hWxJ2njeK3r+ykpq2bgqRIfjAlm8v/t4G4CBuXz8rH5bQCIYalRjMkJRqAP31/PG/vrGN9WQt5SZEU17Zzxf828JtTR5EZ17du04HU5fVTVNvep72iuatPm9Vs5ORx6YzJjKGx00NKtL3PyDAREREREflmFDCJiHzLpMXYmT00sdfqcjazEfNH09JsZiOLJmQwMSeWWUOT8AeCGA3w/SnZXPn4xj7Hc/sCvL+nkSNy4ihr6OKG+UMIBqGm1Y03EOTnC0fgsltItHgYkZfeZ/+c+AjcngBbKlt5ZWs1vkDPFLS3dzbwgyP7N8CJdVo5eWw6f1mxq1f7mIyYz93eZDSQnxRJPpH92i8RERERke8aVSoVEfmWcVrN/GzBcE4dn47NbGR4WjQPnDWO4tp2Ul12bjhuKGv3NOGwmNlY3sI1T23muqc2E223MCw1us/xbGYjmbEOAiHIinPywLISrnlqE3e9XsSvlxayrLCWkekujN6Oz+2PPxDk9e217GnoDIdLAO/vbuy3e/Axo9HAWZOzOGVcGkYDRNrM3HbiCMZlxfT7uUVERERE5BMawSQi8i1T3+7BGwhy0bRBHJkbj8Vk4IPSJvY2u7lsVj5PrN3L1XMHs726jd+/UQTA6RMyuOyx9VxxTAG76jpo9/RMsZs1JImmTi/T8uLp9AawmI3sbuhd7HvJ5moun/3FiyuYTUYuOmoQJXUdBEMQIsS/3yllWn5C/92ET8mKc3LnaaO5fHYBVrNxn1eEExERERGRA0cBk4jIAKlt6yYUghTXN1+1bO2eRhY/uYmKZjcZsQ5+dvww7l9WjC8YYsGoVGKcFprdXoLBEGv3NIX3s5iMNHf5uPfNIq6eM5gYpwWjAYKhnmlj//tgLxvKm5mQFdvnnCEgGAr1af/YnoZO7nptJ6WNPXWPomxmfn7iCKbkxn3j6/y6bGYTuYma9iYiIiIicrBoipyISD9rdXt59P0y5t+/irn3ruCvK3bR0OH52sepaO7i0kfXMyrdxU9m5pIe46C8uQuTycAxQ5P401slLCusY0JWLO3dfpKibOF9u30BYp0W2tx+bluynZuf28L68mZSom28v6uJWKeFP509nnHZMWTH9x4BdOq49D5tn/ZOSUM4XAJo9/hZWVRHSvQ3D9JEREREROTbRQGTiMjX4PUHqG/vxuMP7PM+a/c08dPnt9LU6aWt28+dr+zg7Z11X/vcNa3dXDYrn7LGLh5atQer2cjQlGiOG5nCgyt34w+GeHlLNZMGxeKwmhieFk20o2eg6jPrK7h8dgEuhwUAAwZSXA5ufHYrEXYTR+bG09zlpaM7wL/Om8jls/OZlBPLL08cwTVzh2C3fPGA1931nX3adtS00+3b93skIiIiIiLfbpoiJyKyj3bWtPPXFSWsLm7kyPx4Lp2Zx9DPKZr9WS9vqenT9r+1ezlpbDoW077n/Gajgbtf20mntye4WVXcQKvbx4XTBoW38fiD3P16ET87fhgJkTZ+uXAEde0ebBYjWXFOvj8lCzCQ6rKzqqiOaXnxbCpv4aFVe4Cegt+P/PAIrpk7hGAwhPGjlem+zLT8eP75zp5ebaeNzyDSbtnnaxMRERERkW83jWASEdkHDe0eLn30Q57bUEV9h4cXN1bx4/+so669+yv3zfmc6WU58U7cHxXa/jJub4CSunYKq1opb+4Kh0sf21zRitNm6tXW0uXjnjeK2F3XTlu3jxFp0Ty3vpIf/nsdf3prF396qwSr2cgtC0cwrSCBD8qaw/t6/EFuf3k7bW7fPoVLABOz47hlwTAirCbMRgPnHpnNwjFp+7SviIiIiIgcHhQwiYjsg9LGTnZ9ZipYWZObPQ19p4d91ryRKcRFWMOfI6wmhqZGc+UTG6lsdn/uPh5fgPd2NfLo+2WUNnTyQVkTgUDfQtt2ixG7xcRlR+dh/igQcjks3HbSSN7b3cTPX9zOy1tqyIl3YjSAxWTgR0cNYtaQRDJinbS5fX2OWVLXSec+hF8fczkt/HD6IF67egbLrpnJLQuGkxbj2Of9RURERETk209T5ERE9oHdYvpa7Z82NCWap358JCuL62np8mE0wB+Xl9Dq9vH+7gZOm5AJQJvby5aKVvzBIGVNbm59YRs3HjeEPQ2d1LV7KGts5LgRyby6rTZ87CtmF/DY++WcNTmL0RkxdHj9uOwWUl02jhmexKyhSSRG2RifFcMVxwzGYIDMOGd4al5+UlSf/i4cnUpCpK1P+5cxGAxkxH5xIXARERERETm8KWASEdkHuQkRfH9KFv99vzzcdsbETPISI/dp/xSXncfWlFNc19GrfePeFo4bmUpJfTt+f4gPSpsYmxXLHS8X4rCYcFjNbK9u4+2dddS2efjpgqFMy0+gtt2Dw2KiucvDhJxYLnrkA0amuYhzWpg1NInfvlLI38+bRHyklagvqYU0Kj2au04fza+WbqfN7Wfu8GR+MjMPi1kDXEVEREREZN8pYBIR2QdOm5mrjh3MzMFJFNW2U5AUybisGCJtX/4abezwUNbURZTNxLHDkvsETCPTXLy6tZo/LC/he5MyMZkMNHV66fYF+c0pI3lyXQUZsQ4ibRZq8XD70h389rRRpETbiHFayUuMYFd9B/84dxL+YBCT0UC3L8hD508iOz7iK6/LYTWzaGImU/MS6PYHSHM5cFi/elSWiIiIiIjIpylgEhHZRwmRNuYMT2bO8OR92n5nTTuX/289RbUdGAxw35ljmZAVy4flPUW1TxqbSm5iBD99fitljT0FvEemRuMLBLlgajYb97bgclp4o7CWq44dzJ2v7ADg9qWFXHnsYLZUtFLX7mHh6FTGZcUSaf/mr/T0WNVMEhERERGRb04Bk4hIP/D4A/zp7RKKantGLIVC8Pjacn6xcDj1HR6sZiO1bR4e/6CCU8amkxHnoM3to9ntZX15C0flJ3DF4xu55YRhvFPSwIsbq7hx/lAqmrvIiHEyODmSC6cP2q8+ljV2UtbYRZTdTEFSJJFfMpVORERERETkyyhgEhHpB61dPlYV1TMsNYq5w5OZMiges8lAcX0HZqOBHWXt/PntXeHtj8qPZ2JOHPe+WQxA+kersP195R4WzxlMU6eP1i4fc4cnYzYaGJ8du1/9+7CsmQv+tZa27p7V4s6ZnMU1cwcTF/H1inuLiIiIiIiAAiYRkQOqtctLIBQi2mHm/Kk5OCwmXE4rv365kMoWN8ePTGFybjwPrdrTa7/haS7+umJ3+PN7uxqZPzKFV7bW8NtXd+K0mpiQFUtajI2TxmZgt3zz13er28cvXtwaDpcAHl1TznEjUjhqcOI3Pq6IiIiIiHx3KWASETkAurx+3t5Zzz1vFBEIBvn5CcPJiY/AbjVx+WMb8AaCADy2di+jM2LwBYO99jcZDfgCn7St2dPEaePT+fnC4XxY1szoDBeVLd38bdUeFoxO36++tnf72FrV1qe9tr17v44rIiIiIiLfXVqHWkTkAFhf1sylj66npK6D08ZncuOzW7nyiY1sq2oNh0sfe2Z9BQtHp/Zq21DezGnjewdHbxTWYgAWjErlhQ2VPPxuKT+ZkUdchHW/+hobYWV6XkKf9sxY534dV0REREREvrs0gklE5AB4Y3stABmxDsqbuqhp6xkNZDL2zfF313eyaGImSVF2Vpc0kJsYwdjMWCqbu7hw+iDe3dXA0JQoFk3MJMZh4f5lxRiNBn6/aAyzhu7/FLYIq5mbFwzj/x5bz676TqwmI9fOG8KINNd+H1tERERERL6bFDCJyGGpvKmLjeXNNHR4GZkezagMF479qFv0VZKi7EBPce49DR3h9vp2D0NTothR0x5uO29qDne+sgOT0cBfzhnPrS9s5eUtNQDER1j5wZQsLp6Rh9PW098/njUefyiEw2I6YP0dlhrNkz8+kopmNxE2MznxTswmDWoVEREREZFvRgGTiBx2Kpq7+NHDH7Cz9pOg54GzxrFwTFq/nXP2sCQeXLWLwuo2zp6cxQelzQA8uqaM847M4fxpOeyp7yTaYeG1bTU0dXrDff3h9Fzufm0nNW3djMuKYeGY9HC4BGAxG7H0Q5/jI23ER2rVOBERERER2X8KmETksLOtsq1XuATwqyXbmZIbR+JHI40ONJfdwm0njqCqtZukSBtnTMzgmfWVGACPL0BypI23d9Tx6rba8D7js2JIdTkYmeFixuAEujwBkqPtOKwHbqSSiIiIiIjIQFDAJCKHnS5foE9bc5cXjz/4OVt/c1srW3mnpAGHxUR9h4cHlpfwvSMyefKDvUQ7LFwxO59xWTEs3VLFj/7zIWdMzOTSo/PYXd/BEYPimDwonhHpPXWPIqxmiDqg3RMRERERERkwCphE5LBTkBSJxWTAFwiF284+IouU6K8eveQLBKlqcWMAMmKddHr8NHR00+0LEgKGp7nw+ANsqWjlnIfW4PEHOXV8Omt2NwHw8pZqLpw2iHvfLGZzRSt2i5GfHj8Mrz/E+7sbOXFsKrcuHE5ajFZsExERERGRw4cCJhE57AxPjeaRHx7B717byd6mLhZNzOTsyVlfWcS6prWbv6/axcPvlmEyGnjo3Al0+4OsKmpgb3MX80el0NLlY+nmKjyBYHhEVH27h7QYO5Utbtrcft7d1cj184awp7GTQfERTBoUx/eOyKLLGyDabsZgMAzEbRARERERERkwCphE5LBjNBo4Mi+B/1zowu0NkBBp26dQ591dDTitZi6fnU9SlJV2j59bX9hGQ0dPQe7cxEjueq2IOKeVnIRPRiC9U9LALScMZ3NFKx5/kDV7mmjs8PDwBUeQHvfJdi6HVmkTEREREZHDkwImETlsRdosRNq+fP21UChEXbuHgD8IoRDDUqOpaO4iOyGSD8uaw+ESQITNRH27h4YOD6eMT+e1jwp2B0Pw57d38fdzJ9LU6cVhMTEiPZr0WE2DExERERGR7wYFTCLynREMhmjq8uD2BImLslDa0ElNq4dQKESEzYTBaOTqJzbi8Qe598wxffY3fTQKKhSCV7fWcMNxQ1i6pZpgMMSlR+czPiuGSPuXB1oiIiIiIiKHIwVMIvKdsKG8mX+/U0pFi5sTx6SS5nLw7IZKXt1WA8AjFxzRU1vpo7pKj75fxoXTc4l1Wmju8gGwtaqNY4YmsWxHHRv3tlBY3cYvThzO/JEpxDhtB+3aREREREREDjYFTCJy2NtW1cpZf38f70fh0YyCRGrbWnhla014m2Cop1j3x9aVtTBzcBt3LxrDG9trKWvsYnp+AqFQkIk5sfgCIUamuxib6VK4JCIiIiIi33kKmETksOX1B3pqJrV7uGJ2AW5fAICRGdH8a3Vp720DAWYPTWJTRWu47fdvlPDwBZOAEMnRNu58ZQduX4Br5w5m0fgMUmMdA3g130xtWzdbK1tp7PQyKD6CkRnROCx69YuIiIiIyIGl3zJE5LC0p6GDPy4v4cVNVWTGOfn+5GweW1tORbOba+cMJi8pgtUlDeHtt1S2MiIlmstm5fH42r3YzEYunpmH3WJk3ohUnllfwYTsWKYXJDAhK+ZbES41tHu44enNvF1UH277/aIxnDYh4yD2SkREREREDkcKmETksOPxBbjn9SJe2lwNwO76Tu54uZArjy1gdXEDDquJWRlJrCpqYHdD50fbdFBU00EgFOKG44ZS197Nn98q4T8XHsHk3GiGpkbR7vYRabeQFnPoh0sAhTVtvcIlgF8u2caU3HjSvwUBmYiIiIiIfHsoYBKRw05NWzdLtlT3avMHQ1hNRiZkx/KrpYXEOMzc/71xdHp7ptGV1HUQ47BQ297N7S8XkpsYwQNnj2NwchQAqS4Hqa5vVyjT3u3r09bm9oenCoqIiIiIiBwoCphE5LDjsJhIiLT1KtoNkBHr5I/LNwPQ4vZz/TObOXFMOjuq25icG0+3P4A3EOCRH04iLzGSSLvlYHT/gMlLjMRqMuINBMNtRw9JJDXGfhB7JSIiIiIihyPjwe6AiMiBlhRt55cnjujVNiErBl8gSKfXH26rbfNQ1tjJ/FEprCttosvj5/wjBzEmM/ZbHy4BDE6O4uEfTmJoShQWk4ETx6ZxywnDibDqbwsiIiIiInJg6bcMEfnWcHsDlDZ2EAxBTnwEEbYvfoUdMzSJZy+dyoelzXT5ArR0ednb1MUJo9N4cVNVeLtVxQ1cMjOPsydnD8QlDCiDwcCReQk8fvEUOj1+EqJs2Mymg90tERERERE5DClgEpFvhZpWN8t21FHb2o0vECTGaWH+yBTMRhMWs4HEqN7TvmwWE2ajAYfVxANvFdPm7hm5dMnMPC6ekcuLG6vIT4rkymMKGJcdezAuacDEOK3EOK0HuxsiIiIiInIYU8AkIoe00oZOShs76fIGeH1bDe/vbuL0CekMT43m6Q8r2VHTzqgMF+OzYpk8KA6zqWfmb3WLmwsfXofbG+DC6YMAMBpg5pBExmTE8OMZuTitZhxWjegRERERERHZXwqYROSQtWZ3I4+8V0p+Us9KblNy40l1OThiUDx3vb6T8iY3AK9vr+XsI7KIj7AyNDUagLKmrnCR7/uXFQNgMMDk3HgMBgPxkbaDcEUiIiIiIiKHJwVMInLIKKlrp6S+nTinDQM9AVNTly8cEN08fygmo4E9DZ3hcOljT39YwXEjk8MBk8thwWiAYOiTbQxA9GFQvFtERERERORQo1XkROSAaXP7eHN7Ldc+uZEHlhWzo6Ztn/ctqmmjuKadGLuN+94s5oOyZhq7fLy3qxGAaLuZpi4vj64pJxTqu38gFMJq+uSVlpsQweWzC3pt83+z8slNjPhmFyciIiIiIiJfSCOYROSAWbqlmpue3RL+/K93S3nqJ0eSlxjZZ9vatm66vH5213dS1eImOdqOy2nlP++X8e6uRqbmxrNpb0t4+xFpLtaVNgPg8QdIiLTS0OENf3/quHTykz45j81i4sLpgzgyL56qFjdpLgfD06KxW1RzSURERERE5EBTwCQiB0Rdeze/f31nr7amTi87qtpIj3FQUtdOU6eXPQ1ddHT7yIpzEmU3YzT21EMyGuDNwlpWFNUD8PT6CmYPTWbjRyFTZYubIwbFsa6smX+9U8pVxxZQXNdBaUMnx49KZfaQJBI+s5JctMPClNz4Abl+ERERERGR7zIFTCJyQIRC4A0Ew5+PHpLIpJw4Spu6eHFTFRFWE1UtbuIibDitJhKjbLy/p4kHV+zG7Qtw3bwhlDd1kZsYweaKVkobu4iLsJCXGMGu+k7Km7q4eMYgVhbVU9fu4bev7uTI3DjuO3MsWfGa9iYiIiIiInIwKWASkQMiOdrO9XOHUN/hxeWwUNPq5q7XekY0WUwGvjcxk4k5sdz7ZjGljV3ce+YY7nuzOLy/PxDkrZ31/GzBMIprO3D7Atz7ZjHXzB1MarSdsqYuNle0cuH0QVhMBpKi7IzLiiU91nGwLllEREREREQ+ooBJRA6IYDBEhN3ML5ds5ycz8/jnO6UAXD47n8HJUWypaKG23cOc4Sk8tHo39e3eXvt3eQOkuuw8sLyEny8cTovbh8cfZGdNOyt21rNwTBrv726kucvHD6flMDEnDotJ6xSIiIiIiIgcChQwicgBUdrYyU3PbsEXCJEUZeOuRaOxW0w0tHv401vFFCRFEWG3sGZ3A/edMZbAZ5aC+8fqPfzp7HFsrmxje3UbR+TEUdrYidVk5MxJmRyZE8eZkzIxAGYFSyIiIiIiIocUBUwickA0dHiYnp/AWUdk0tTpY3d9J4+tKcfjD3LVsQU8sLyE8qYuMuMi2NPYSazTwqwhiby1s6eot9VsJMJuZs3uBorrOnnkvTKsJiO3nzKC9BgHqXHOg3yFIiIiIiIi8kUUMInI11be2El7t5/EaBsd3X4AomwmjsyLZ2tVO/5AkEAwxFXHFvCbV3bwr9V7OG18Ov98p5SZQxIxGgy0dfs5Mi+eU8al09btx2w0cNtL27l27hCaOr1UtrgZlhpNusvOsDTXQb5iERERERER+TIKmERkn3n9AV7eUsOG8iaOHpLMr5Zu5/3dTSRG2rj5+KFUNbv5x0e1l+IirNx+ykhumj+U0sYuCpIjmTs8GbvZRKTNzPMbK1lf3sKE7FhmFCTgD4a4aPogIm0mou1OJmbHkpcUicFgOLgXLSIiIiIiIl9JAZOIfCmvP0B9ezf17V7qOzwYDHDCmDT+uaqU93c3AVDf4WHxU5tYPGdweL8RadG8tKmKl7fUhNvOmZxFdryDR98vx24xAfBhWTMfljUDcOnReZwxKWsAr05EREREREQOBAVMIoextm4fRTXttLh9ZMc5yf8aI4LcHj/Fde38d00Z80aksHZPM/9YvQd/MES0w8xVxwxmZXE9nd4AAKEQePzB8P4Ts2O5983iXsd8bG05KS47a0ub+M2po3lvdyMf1/q2W4zMHpp0YC5cREREREREBpQCJpHDVEuXl3teL+KR98sAsJmNPHTuRI4anAjA3qYu9jZ34XJYyEuMxACUN3URCAbp8gYIhSDCZuKkMem0ewJ4/EGcVhNt3X7a3H4eWrWbk8am89ja8vA5LZ9a3e2zq8RBTwg1PCWaq+cMJspm5q/fn8DaPU04rSZmDU1ifFZs/94UERERERER6RcKmEQOUztq2sPhEvSMLrrx2S08f9lUShu7uOjhdbS6fRgMcMXsAmIdZrZWtbFwTBq/fXUHQ1KimJQdy4OrdlPW6CYx0sZVxw7mvmVFtLn9VLV2Ex9pDR9/5uBEUqNtmIwGAsEQBgwkR9uobfOEt8lLjGBlcT3rypq5/3tjyU+KYt6IlAG9LyIiIiIiInLgKWASOUzVfSrY+Vhli5v6dg83PrOZVrcP6BlVdP+yYv589jgWJkbyf49toN3j56bjh/FBaRPT8hJZNMHBB6VN/OmtEk4fn8E/3yklzWVnen48CZFWbGYTO2raqWnr5objhuAPhBicHMH4rNH8+91S1pe3MD0/ge9PycIfCHHprHySo+0DfUtERERERESknyhgEjlMZcU5+rSNy4qhvt3DSWPTMRoMPLqmjKl5cfxgSg5Gg4Gi2nZ+NCOX/MQI7np1J5srW8P7Xjh9EKWNnThtZqIdZi46Kpe2bj/dviB3v17EglGp5CbG8syHlYxMj+aOl3diNRu57Og8bpg3hEFJkdjMpoG8BSIiIiIiIjJAjF+9iYh8G3X7glx9bAGRtp4ceXByJKeNT+eHD6/jnjeKuH9ZEQ+cNZb4CDuXPbae+g4PHn+Q2AgrwRC9wiWAR9eUsXB0GkOSozhzYhZ/eXsXjR1eKprdJEfbefyDvXR6/IzNdPHA8hJ2N3Syo6adyx/fSGVrt8IlERERERGRw5hGMIkchlq7vPz8xa20uv2cPTmL8VkxpETb8fqDPHbRZDbubSEn3skb22rp8AS4/ZRRXPH4BtrcfgB+c+qoPsf0+IMMS4viVy8VUtPWzdlHZFHT1k20w0JTpxcAtzfA2zvr++z71o46jhmW3L8XLSIiIiIiIgeNAiaRw0wwGKKh00tVSzftHj+ZMXbinFbaPX7q2rpp7PSSGecgEAySEedkVXE9L22qDodLOfFOUl12ou1m2rr94ePOG5FCV7efCdmxDE6OZE9DJ5G2CDq9gXDAtKGsmYQoa58+JUTZBubiRURERERE5KBQwCTyLWUyfTLlLBQKsaWylbd31mMzGxiZGs2JY9PYXd9BaoyD3Q0dfFjewlPrKgAwGOBXJ43kgz2NxEdY2VnbGT7WnOEp/OWtEu5aNJpH3y9nd0Mn0/MTOGF0KrvqO5iYHYPbF+D4Uam0d/u467WdABgNMC4njkHxTt7aUY8/GAIg0mbmWI1eEhEREREROawpYBL5Fmnp8rJ2TxPLdtSSFeugzdoEIShv7sJhMZKb4GRbdTurdzdxRE4cJ41N469vlXD+9EGYjQbmDk+mstlNtMNCeWMn0woSeWVLDceNTGZ9eTMA3kCQoroOHnm3jItn5NLQ4SXKbuLapzZT09ZNlM1MIBSiyxvgz2eP5/aTR9Ht95McbSc7LoL8pEieuWQqa0sbsZpMTMqJZXia6yDfOREREREREelPCphEDhHVLW427m1hb3MXw1KiGZPpItrRe7rZ0x9W8OulheHPaa69nDkpk3vfLCbVZeeauUPYVtnKyuIGrjymgFAoxIiMGK5/ZjPnHzmI65/ZwkcDizh5bBpHFSRQkByF2Wjg/Kk5/G9tOW/vqOXiGbn89tWdVLS4OWVcOnmJEdS0dQPQ7vlk2lyH18fU3Hgy4iJ69XNMZgxjMmP650aJiIiIiIjIIUcBk8ghoLHDw/XPbGZVcUO47ab5Q/nRUbkYjQYAKlvc3PtGUa/9qlq7+Sgvorq1m1++uI3fnDqKdWXNuBxmLGYjDywv4bypOfx91e5wuATw/MYqpuTG0+r28vdVu7nnjNFMyxuL02pma2Urv1g4nB017ZiNRiwmI3mJkeyq7+h1/qEp0X3CJREREREREfnuMR7sDogI7Kxp7xUuAdzzRhFljZ/URgoGQ+G6Rp8W+lRTu8dPh8dPWoyd9BgnWypbAYiym2n8qBD3p1W0uEmItOFyWAhhYEtVG2tLm9lS1cZLm6pYs6cJkxFe3FjFLScMIz3GAYDDYuKu00czJDnqQFy+iIiIiIiIfMtpBJPIIcDtC/Rp8/iDeALB8Oe0GAc/mJLNQ6v3hNui7WZChLCZjUzIimVPYweRNjMTs+KoaOkiPrJn9baSug5Gp7vY/FHgBD1Fua0mI++VNnLDcUN5aOVuCmvaMRkNLJqQQUyElW3VbVhNJqYXJPDIu6UcNzKF6fkJ5CQ4yYmPwGAw9ONdERERERERkW8LBUwih4DcxEii7Wbauj+pbzSjIIGMj0YMlTV2srepi9lDk0iKtvHSpmqy4hwsGJXKroZObpg/lI3lLcwelkR6rIMFo1N4f3cTvlCI0eku3they60nDMdohI17W0mMtHHhUYP439pyzjsyh5VF9RTWtAMQCIZ4/IO9XDdvCPOGJ9PS5SU5ysGPZ+aREeskPdZxUO6RiIiIiIiIHLr6LWCqrq7m+uuvp7GxEYPBwBlnnMF5551HS0sLV199NZWVlaSnp3PffffhcrkIhULcfvvtrFixArvdzp133smIESMAeO655/jLX/4CwCWXXMIpp5zSX90WOSgGJUTwnwsnc88bRWytbGX+qBQunD4Ip9XMG9trWPzEJto9flwOC3eeOpKFo1Nw2npGL5XUdfDCxioAXA4Lr22rYUd1O7ecMJwVRfX8cHoOETYLHp+fny8cwXu7Gqlp6+avK3bhtJjIiXfyh+XFffrkDwQZlxmD3WomM8450LdEREREREREvkX6LWAymUzceOONjBgxgo6ODk477TSmTZvGs88+y5FHHsnFF1/M3/72N/72t79x3XXXsXLlSkpLS3n99dfZtGkTv/jFL3jqqadoaWnhj3/8I8888wwGg4FTTz2V2bNn43Jp2XM5vIzJjOGv359Ae7ePuAgrHR4/u+rb+elzW8Irt7W6fdzwzBbuOGUU1z61iV+eNDIcLtnMRlxOCx+UNgPgtBmpbnVz1RObMBjghNGpnHNEFsPTorGYjJw/NYf4CCu+QICxmTG8vbO+V3/ykiIpSIke2JsgIiIiIiIi30r9VuQ7KSkpPAIpMjKS3NxcamtrWbZsGSeffDIAJ598Mm+++SZAuN1gMDB27Fja2tqoq6tj9erVTJs2jZiYGFwuF9OmTWPVqlX91W2RfuP1B6hucdPR7evznS8QZG9zF+3dPpxWEy9tquKkP73DhQ9/yPeOyGJGQQIAdouRc6fm0NDhYfHcwcQ6LeFjxEdYqWpxA5AV52RFUQPry1uAnkLgL22qZm1pMxWNneQmRpAR46Ct20+E3cI5k7NI/KheE8BJY9M4YlBcP94NEREREREROZwMSA2miooKCgsLGTNmDI2NjSQlJQGQmJhIY2MjALW1taSkpIT3SUlJoba2tk97cnIytbW1X3o+j8dDYWFhP1zJ5+vu7h7Q88m3T7fVxcNra3ijsI4hKZEsnp1LotVPZZeB5u4gBoORZz7cy/en5NDlD3LNk5vC+/5hWQl3nDwSgwGOH5XKXa/tpKGjZ0W440emMC0/nndKGqlr95D90VS2EWnRrC9r6dOPyuYuRqWn0tDhoarFjcVkJOAPsb26jSuOzSfGYSHGEiTBFqCxYg+NA3J35NtC7zoZaHrm5GDQcycDTc+cDDQ9c9Jf+j1g6uzs5IorruDmm28mMjKy13cGg6FfVqGy2WwMGzbsgB/3ixQWFg7o+eTgqGjuori2A4vJQEFyFMnR9n3ar6Pbx48eWcd7u5sAWF/eysWPbeaXJ47guqc3Az0rut1zxlhWljRQ0+oJ7xttN3PT8cP4oLSJ9m4/nZ4A0/MTeP6jaXEvb63h9pNHMi4zlreL6oi0mzlrUiYfljUzIi2aXfUdvfoyMt2F1x+g66MpdyPSoimu7SAQDNHm9mM1Glk4Jmu/75UcnvSuk4GmZ04OBj13MtD0zMlA0zMn++PLwsl+DZh8Ph9XXHEFCxcuZO7cuQDEx8dTV1dHUlISdXV1xMX1TMNJTk6mpqYmvG9NTQ3JyckkJyezdu3acHttbS1HHHFEf3ZbpI8d1W2c/++14fBnRGo0fzpnPDkJEbS7feyoaae2rZvMOCdDU6KwWUzhfSua3eFw6WNd3gDlTV3hz8EQ3P5yIWdNysLrD4bbbz5+GL9eWkjHR4HQ+vIWLpmZR2acg71NPdPh/vN+GXefPorByZHUtnUzMsPFmMwYYp0WNu5tpvyj7Y4enMiMwQm0uQNE2My0uH1c/r8NtHX7+TjnffonUw/8zRMREREREZHDXr8FTKFQiJ/+9Kfk5uZywQUXhNtnz57N888/z8UXX8zzzz/PMcccE27/73//y4IFC9i0aRNRUVEkJSUxffp07rnnHlpbWwFYvXo1ixcv7q9ui/QRDIZ4dE1Zr5FF26rbWFVcT2KUjb+s2MWf394V/u63p45i0cRMmjq9VLS4MRnAYTHh9gV6Hdds7D16r77dQ5AQs4cm8crWGty+AN3+QDhc+tjD75Vyxex87nx1JwAnj02npL6Tq57Y1Gs7s9HAgz+YgMNiwmI2kp8YSWyENfx9dYub86cN4j/vlZIQaeOm44cyKl3F80VEREREROTr67eA6cMPP+SFF15g8ODBnHTSSQAsXryYiy++mKuuuoqnn36atLQ07rvvPgBmzpzJihUrmDNnDg6HgzvuuAOAmJgYLr30Uk4//XQALrvsMmJiYvqr2yJ9eALBcLHsT9ta2crojJhe4RLAz1/axpDUKNbuaSIh0oaBEFceU8Cdr+4IbzOjIJGSuk+mr511RCa5CRFgMNDi9nHp0fmECGGg7xRSs8lAcrSdWKeFU8dnEO0ws6ehC6OhZyTUx/zBEBFWE1PyEj73ulJjHFx9bAHnTM7Cbjbiclo/dzsRERERERGRr9JvAdPEiRPZuXPn53738MMP92kzGAz8/Oc//9ztTz/99HDAJDLQHBYTJ4xOY1tVW6/2owYn0tTp7bN9KATbKtv4zSs7MBkMXHlMATazkevmDaHT48dhNeGyW0iItPLe7kZOHJPG+7ub+N/avQBceUwB9y8r5qb5Q0mItJIQaQ0X9Qa4YOogmjs9/OioXMZkuNha1Uab28cPpw/ioVV7wttdOD2H0ZkxX3ptBoNhn2tJiYiIiIiIiHyRAVlFTuTb7oQxqRRWt/HS5ipMBgMXTBvElEHxtHb7sFuMdPuCxEVYuH7eUFrcPjq9fm6eP5Q3ttcyNjOGa5/ehMVkpLrVjdloxGoy8pOjc1k4Oo3MOCf/fKc0fC6j0UCE1US7x8+KonqunTuEbVVt1LV7GJfpIi8xgkAIjEb439oyXtlWR0FSJHkJEVw7dwgxTgs58U5GprtwWvVPXERERERERPqffvsU2QeZsU5+e9poLpuVj9loICvOicVsJD7SykPnTeKGpzfzswXDWPzkJpxWExazgYuPyiMtxsEflhVz8YxcfIEQWXFOSuo6aO7ykh7j4K0ddfgCwV7n+ufqPVx/3BAMBgN/XF5CXZuHY4YlMS0/gUAgiNVsoqyxk6xYO/NHp/Hy1lp21LSzo6ad/ORITh2Xg9Omf9oiIiIiIiIycPRbqMg+8vgDJEfbiHFaqWjuYkdNO75AkLzECF64bCr/eb+MK47Jp6LZzZTcOK5/eku4sPcHZc1cM2cwf1xewvbqT6ba3TR/KKFQ7/O0un3sbXYzNTeeKYPieLuonreL6jEa4PaTR7KtqpUJOXEkmzvJH5zD0iuOorypi6QoG4OToxQuiYiIiIiIyIDTb6IiX8Dt9bOrvpOObh/lzW7+/FYJIeCXC0fws+e3UNHSDdCzktw544i0W7h9aSEGA8RFWPusGvfwe6XMG5HSK2B66sMKFo5J5epjC/jrit10+wP89Phh1Ld7uPXFbSyakMFpEzKobHFjMhr4+6o9PHD2OEakuSgsLMRiMjIsNZphqdEDeWtEREREREREelHAJPI5Orr9/H3Vbv78dglXHTuYu17rKVifGGXjzR114XAJoL7dQ0ldB//4VIFtu8XU55hmoxF/sPdwpdYuH5Oy47j3jZ2ce2Q2YzJcvLOrkUfXlANw75vF2MxGLp2Vz+9fLwLA4w/2ObaIiIiIiIjIwWQ82B0QORTtqGljR3Ubt588kqQoGyPTe0YIpUTbqWjq6rN9jMNKe7cPgJFpLtJi7Lgcll7b/GRmLm9ur+3VtmB0Kq9tqyEQguU76rCYjTy5bm+vbTz+IIFgT6hUkBxJqlZ9ExERERERkUOMAiaRj/gDQfY2d1Ha0IHPH2RqXjyrSxrZVtXGBVMHcdKYNIpq2xmV4eq134+OGkSz28uJY9MAOHZ4Mrc8v5Ufz8jlnMlZzBuRwvXzhpAd5+SWE4YzOsNFeoyDH07LodPj5z/vl3H57HxGpLl4t6SRyM+poWQxGZkzPJlTx6VT2eIekPshIiIiIiIisq80RU4EqGpx84/Vu3nkvTImZsdy7PBkfrWkMPx9XISVX580kpc2V1HZ4uaiowbx8Lul/GBKNscMTeJHj3zIgtGpXDAtB6MBOjwBfvfaTpKjbbgcFt7YXsOls/KxmQwkRtkoSIpkyeZq6to92MxGPP4gz2+sJCHSyrlH5nD/suLwuXPinSRG2aht6+a3r+7kz+eMPxi3SEREREREROQLKWASAZ7bUMk/VpcCcPyoVP66Ynev75s6vTR2erjz1NGMSI9mSHIUswYnUdbUSZcvQLvHz+Mf7CUxysY1cwbjsJhw+wLUtnmobfOQFGWjzd0zha60oZNd9Z3hY589OYukKBsADR1e3ilp4Pp5Q+j0+rGYjHT7Avz0ua0EPqrflBHrGIA7IiIiIiIiIrLvFDDJd15rl7dX3aOMGAfdn1kBDqDV7cNq9NPtC7CutIlAKERFcxfNXV5mDk5kRVE99e0efv96EdfOG8zfVu6mts1DVpyT204awVWPb6Ct28+PZ+QRDIWoa/cwNjOG7HgHQ1Ki+cd5E/nPe2VE2c1MzIllfFYs26taueTRDQSCIewWI788cSRDkqMG8vaIiIiIiIiIfCUFTPKdVN/ezZbKVmpau8mIcXLF7Hz++NYukqJsPLuhkrMnZ/HA8pLw9jazkdzESMqbulizuwmzycCotGhSoh3srG3n9AkZxEVYWFZYR3qsnbzESK6YXUCk3UxmrINbntvCJUfn8/dVu/nLil2MyXBxzdwh2CxGxmS4sFvMHDMsmVlDkjAYwGAwADA6M5bnLp1KVYsbl9NKdpwTo9FwsG6biIiIiIiIyOdSwCTfOS1dXn69pJAXNlWF2y6cPoj5I5PJjo/gvjeLOaoggctm5bOyqJ7EKBtnTMzgV0u2U9nSDYDTauLG44ZS3+EhNyGCf71TSqzTzO8Wjaa+zcNFj6zDH+iZ0jY+K4acxCj+smIXJ45JI9phYURqNFNy47CaTb369nnhUVK0nSStHCciIiIiIiKHMK0iJ98p/kCQbVWtvcIlgP+8V4bBYGRPfQfzRqTw7IZKSuraiY+0EmE18eKmqnC4BNDlDbC5spXnN1aypbKNy2blceakLEJBuOWFbeFwCWB9eQsFyZG0dPl45L0y/ri8hLp2T59wSUREREREROTbSiOY5LC2q66D7dVthOhZje2FDZVEOvo+9t5AEKfVRLs7yNzhiVQ0dzE8NZqtVW3UtnVjMvXNYlu6vETbLTy/sZLlO2v5xcLhwOdPXwuFen/OSXAegKsTEREREREROTQoYJLD1raqVs7++xpaP1q9Ldph5tKZ+bR7fPxoxiCclp7Hv8PjZ11ZE2kuO7e8vYu/rtzNGRMyGJYahcthodsXwG4x8cGeJuaNSGFQYgRdHj+ZsU5+tXQ7AImRNgwYWFfWzKScWD4obQ73Y0J2DO3dPX2wmY1cMC0Hrz84wHdDREREREREpP8oYJLD1paKVs49MhuvP8hLm6qoau2muK6d4WnRtHT1BD5GA3h8Aa6bO4Tz/vUBgWDPUKMnP6ygpL6Ds47IYmdNO7OHJvHXH0zgnteLWLqlmhinhctn5zMoIZLdDR2cOSmL379exMwhiYzLimV0hottlW3MHJKI1x+krKmLy2fnEwiGWLqlmhSX42DeGhEREREREZEDSgGTHJaKa9t5/INyNu5tJcJq4oLpg1hVVE+XL0BKtJ1/vVNKRbMb6CnCPSbTRarLHm6DntpJJ45JY/WuBpq6vFS3drO9ug2Ali4fv15ayH1njqWy2c0TH+ylxe3j7COyaO7ykhnrJCu+Zxrc/cuKeXZ9Zfi4BgOMSosewLshIiIiIiIi0r8UMMlhoaPbx6aKFvbUd5EaY+OxtXvZuLcVgE5vgD8uL+G6eUPIiHXw1s76PkHSzMGJ5CVG9GrPiHXQ5Q2wt8nNSWPTeW1bba9zhkJQUtfBA8tLAFg8p4DhadEYDL3rMJ0xMZNgCB55r5SESCs3zR/GqAxXf90KERERERERkQGngEm+NWrbuqlv9xAXYSUt5pMpZl5/gH+/W8rdrxcBcOnReby1o67P/laTkZx4B39+q7VXu91iJNVlZ/bQJMZlxeLxBfnvmjJ+tmAYVrMRs9FAS6eX5GgbtW2eXvsmRdkYlhrF2UdkM29Ecp9wCSAtxsHVxxZwzuQs7GYjLqf1QNwOERERERERkUOGAib5Vlizu5ErH99ITVs3CZFW7l40hpmDEzEYDOxu6OTeN4vD21Y0u8lLjKS4rqPXMVwOM6WNXcwcksjO2vZw+5XHFHDnqztp6vQCPaHRgz+YQG1bN5v2NvHvCyZR3uRmYk4s1z61Gf9HdZrOnJTB8aNSOXV8BhG2L/+nZDAYSI62H6jbISIiIiIiInJIUcAkh7zKZjeXPLo+HAA1dHi55L/rWXrFdHITI+no9oeLcwO8tq2GG+cP5bev7qDb17Na2/wRKWyqaOXRNeVcenQekwfFsmZPM9nxTsqb3OFjA9S1e1heWMdLm6u4fHYB0Q4LZ09OJBAMMTQlmj2NncQ5rQxJiSJGo5FEREREREREFDDJoa+6tXcABOD2BahscZObGElWnJP0GAeVLT31kzz+II0dHm6cP5TGDi9Ws5H4CCs3P7cVgD+/vYu5w5P55YnDGZXm4rev7exzzj2Nnfz65FHEOM0MT+0pyG0yGhiaGs3QVBXoFhEREREREfk048HugMhXibKbsZl7P6pGAxiAFzdWUt3q5v7vjWVCdiwAI9KiyUuM5BcvbueB5SU88l4Zmyt61116fXstD79bBoYQxwxN6nPOhaNTmVGQwKSceMwm/TMRERERERER+TL6zVkOWR3dflYX1/P+7kbuOWMM+YmR4e+uPKaA25cWsrfZzf3LSqhodhMfYeGyWfkcPTgxPJoJoL7dQ3a8s8/xTxybBhhYOCaNS2bmYTMbsVuMLJ5TwPSCRGwW00BcpoiIiIiIiMi3nqbIySFrT0MHf12xixAQZTOzcEwqQ5KjwADv7mrk3Kk57K7vYGVRPaeNT2f5jnpe315HYqSNG+YP7XWs17fVcusJw/n7qt10dPs5f1oOiyZkkB7bEzxdO28IZ0/OwkDPqm9GY9/V4ERERERERETk8ylgkgHV1OnF7fWTEGXDZv78EUJ7Gjp5aVMVxXXtnDIugyc+2EtZZxeDU6KItJswGoxsrWzlkffKGJEWzU8XDMNAiNPGp/PEugrqOzy0dHm5af5QHly5m+YuLwlRVsZkxvCH743F5bBQkByFwfBJiGQyGsiM6zvKSURERERERES+mgImGRCBYIh3Sxr4xUvbKGvsYsHoVK48poDcT017A2js8HDV4xvYVNHKjfOHcu3Tmwh9tEBcYXU7fz57HL95dQd7m3qmwG2raqOypZg/fG8cVrOJS2bmsb68meLaDo4eksi9Z4zBbDKSFe8kM1YBkoiIiIiIiEh/UA0mGRA7a9q44N8fsKu+E38wxAsbq/jdqztxewO9tiup62BTRSsJkVb2NnWFw6WPlTe7w+HSx1q6fFS1uNld38F/3i8jBLyzq4FLHl2Pxx9kWn6CwiURERERERGRfqSASQbErvoO/MHeadFr22soqm2nucNDUU07q4vraejwAOANBPusHAeQGGnF/Dn1kewWIz84MhuzycDaPU1UNLuZPzKFMZkx/XI9IiIiIiIiIvIJTZGTARFtt/Rpi4+w8tKmKsZlxdDQ4eFvK/dwxex8xmXGsGFvC/GRNiJtZjo8fgAyYh10+4J8f0o2/363NHycMydm8L+1e9lW1cb3p2SR6nIwPC2awUmRuJzWgbpEERERERERke8sBUwyIIalRnNUfgKrShoAGJPh4kczcqlr8xBpMxMCqlvdvF1Uz8IxKZw7NZtuX4A/njWWD8qa8fiCHDEojque2MiYjBiunTuEbn8Aq8lIcrSdJ9ZVAPDXFbv55/mTmJQTdxCvVkREREREROS7RQGTDIikaDu/O30UL2+pwWIyUt3q5v8e2wCAzWzkZwuGcdtJI3l+QwV2i5nblxbS2OnluBEpzBmeTHOnB5PRQJc3wHu7G3lvd2P42LefPJLESBsWk4Fr5g3hiJzYg3WZIiIiIiIiIt9JCphkwMQ4bQRCITrdPv6yYne43eMPcv+yYhZNzOCsydlc8+Sm8HevbK3BaTVhNRmpbOnm2GFJvFlYF/4+wmpiSm48S69IxmQ0EB9pG9BrEhEREREREREFTDKAShs7WLuniaOHJPX5rqHDi8lopLXL1+e7JZur+cWJw0mJdpAR6yAj1smSzVUMSYnimrlDyEuKHIjui4iIiIiIiMgXUMAkA6ax00thdTunjEvHYIDQpxaVy4pzUt/mId3l6LNfdryTowoSyYh1AnDLCcO5dFYekTYzTqseYREREREREZGDre868CJfU3WLmze31/Ls+gq2VLTQ6fGxo7qNjXubae70hrcrrGrj/Gk5lDd1ceNxQ3FaTQCkuuxcMC2H+AgLJiOMznCF9zEbDdx6wohwuARgMhpIirIrXBIRERERERE5ROg3dPnGOj1+9jR0smJnHX9btYdWtw+T0cCdp47i5y9uo8sb4IrZeaTFONlc0cKEnDjuf7OY70/JYlB8BD9bMIwIqxm71US720d0UiQFyZH89PhhVDS78QeDDE+NZkSa66s7IyIiIiIiIiIHjQIm+dqaOjxsrWqlqLYDjz/I+vIWLpmZx5Pr9rK7oZM/vVXCvBEp1LR1s7O2gz8s30VchJXMOCcnjE7lD8tKsJgN3HXaaDo9AVq7vGTEOhmeFk2M0wrA5IN8jSIiIiIiIiKy7xQwyddS3tDBki01/O61neG2S47Ow+MPcN28ITy5bi+DEiIYnBxFhM3M5f/bAEBTpxeDwcALGys564gs7BYj/1hdyqIJ6ZwxKetgXY6IiIiIiIiIHACqwSRfqqyxk7V7Gtla2cK2imYKa9r5/RtFvbZ5cMUurGYTlzy6nrnDU3hjey03PruFkrqOXts9tW4vF0wbxMa9zby6tYaTx6Vx9NC+K8qJiIiIiIiIyLeLRjAJAG1uH6WNnZgMBnISIzAA7+1qZFNFCxaTke1VrcwdnoLZZCAQDPXaNxiCTq+fwcmRvLe7kb3NbgAKq9s4YlAca/c0AbCrvpOnP6zg4Qsm4bSZibJbBvoyRURERERERKQfKGASSmrbeXtnPf9+r5SKZjc/mJLFmMwYrnt6M6GPsqRFEzPo6PaTEmMnPsJK46dWh4txWvD4guQlRrKtqi3c/vr2Wn48I5cxGS7e393E1Lx4Fk3MINnlGOhLFBEREREREZF+pCly32EdHj/Prq/gnH+s4Q/Li5k9NIlTx6djt5j55Yvbw+ESwFPrKuj2B1j8xCb+b3Y+eQkRAOQmRHDlMQU8sa6cbVVtjM+O6XWOB1fuJjHKzoXTs7lx/lDyk6IG8ApFREREREREZCBoBNN32PqyZhY/uSn8+ZH3yvjxjFyiHGbaPf4+27d2+2n3+PnzWyVcM3cIFS1uYhwWVhXX0+b20+b2c/LYNCblxPJBaTMGAywYlYrLYWLyoAQMBsNAXp6IiIiIiIiIDBAFTN8BHl+Abn8Al8MabgsEQ6woqiMn3snCMWmEAK8/yLqyJo4fmUp2vJOyxq7w9haTAYuxJyCKi7Cys7adf71TCsDC0aksnjMYowHyEyNZNDGD5i4fwWCIxCgbqS4HRqPCJREREREREZHDlQKmw1goFOLDsmb+uLyE8qYuzpqcyQmj0mjs8LJsRy1pLgcLx6Tx4IrdeANBoh1mbj5+GMNTIslNjOSOlwsprusgMdLGLScMY8nmKm44bggldR2MzYzBYjLgC4R4aXM1UM3184YQBDLjIsiMO9hXLyIiIiIiIiIDRQHTYaywup1zHlqDxx8E4PalO2js8NLp8VPa2MVPZuTx/X+uCddaanP7+f3rRVw0fRC/f72IH0zJ4oJpORgNkBHnYHpBIre+sA2Ad0oa+emC4Wwob6ap08uJY9LIT4pgeKrrYF2uiIiIiIiIiBwkCpgOYxv2NofDpcxYJ5lxDl7cWMXxo1PZXNFKaVNnr0LeAPXtHto9fryBIP95v5xLjs7j/mXFnHdkNq9vrw1vV9PWzS9e3Ma/L5jEjIJETYETERERERGRw5rP56OiooLu7u6D3ZV+Z7fbycjIwGKx7PM+Cpi+RTq6fZQ1dmEyGRgUH4HNYgp/19zlpa3LR3yklUi7hW2VrbS5faS67CyeM5jC6jYSomz8eEYu/mCII3JiqWv3YjDQK2RKjLTR0d1T4NsbCLK3uYsTRqeCwUCXN9CnTw3tHoVLIiIiIiIictirqKggKiqKnJycw3oRq1AoRGNjIxUVFQwaNGif91PA9C1R1tjJL1/cxvKd9RgMcNakLK48toDkaDvrSptYuqWaGKeVqmY3Y7NcpLkctLp9XHlMATc/t4VZQ5Jo7/Zz92s7CYbgL+eMp9vr55KZefxt5W78wRARVhM/P3E4Nz+3JXzeZ9dXcunReUzIjiXWaeG+N4vD39nMRoalRh+M2yEiIiIiIiIyoLq7uw/7cAnAYDAQHx9PfX3919pPAdO3xIubqli+s+d/3FAIHltbzpTcOMZkxnDXazvIjIsIr+r2xLq9/OXscTR2eGlx+/AHQ4zOiOHu13eGj1dc20FuUgQbK1q4bFY+gVAIl91CYqSVc6fk8K939tDpDTB5UBx2i4n2bj9nT84iPsLGf98vIzveyY9n5jI8TQGTiIiIiIiIfDcc7uHSx77JdSpg+hZw+wK8urWmT/s7uxpIi3EwOTee/60p58i8WM6alI0/GCIQCnFUQQJvFtYRZTNT3+HptW+IEE+vq+CEManUt3uBEPGRFjz+IMePSmH+yBRq27ppdftIdtkZlxmDw2rmB0dmc+r4NCwmI1azqU+fREREREREROS7RwHTt4DdbGRKbjzbqtp6tY/JiMFuMZLmcrB4TgFGo5GfPreVdo+faLuZX5w4nONHpbBkcxVxEdZe+9a1e6huc/OrJYUcOyyJEOD1B5k8KJ70WCcAI9I/f0W4CNu+F/kSERERERERkf3X3NzM+eefD0BDQwNGo5G4uDgAnnrqKaxW6xfuu2XLFl544QV+9rOf9Vv/FDB9CxgMBs6cmMkb22uoaulmxuBExma6OHpIIk9/WMkflhXzwFnjuOapTeFC3G3dfjaUt1DW2MWdp42mptXNrCGJvPXRNLs3t9dy3/fGsr6smb3NbibnxjEpKy4cLomIiIiIiIjIN/f8hkruem0nVS1u0mIcXDdvCCePS//Gx4uNjeWFF14A4IEHHsDpdHLhhReGv/f7/ZjNnx/zjBo1ilGjRn3jc+8LBUyHsLq2bryBIMnRdganRPHkxUeyrbqNP79Vwn/eL2dQfAR/XF5CRqyD+nZPn1XeXE4rK98v591djZw7JYsrZ+dz8rh0Oj1+Gju8tLp9RDvMXDNxMInR9oN0lSIiIiIiIiKHl+c3VHLTs1tw+3p+T69scXPTsz0Lau1PyPRZN954I1arlcLCQsaPH8+CBQu4/fbb8Xg82O127rjjDnJzc1mzZg3//Oc/efDBB3nggQeoqqqioqKCqqoqzjvvPM4999z97osCpkOQ2+vntW21/Hrpdlq6fHxvUiY/nplHW7ePn/z3Q3yBEADF9R14A0EaO7zER1mxmY14/MHwccoaOhmT4WJTRSv/fLeMt4oaOGF0KkNSokiJtvPLl7Zx20mjFC6JiIiIiIiIHEB3vbYzHC59zO0LcNdrOw9owARQW1vL448/jslkoqOjg0cffRSz2cy7777LvffeywMPPNBnnz179vDII4/Q0dHB/PnzOeuss7BY9q8cjgKmQ9DmilauemJj+PN/15QT5bAwLtNFYqSNbn+Qpk4vTouZmYMTWFHUgMNk4spjCrj3zSJ8gRAWk4HJuXEsGJXK3a8XUVLfQX27B5vZiNvrJ9pm5m/nTqQgKergXaiIiIiIiIjIYaiqxf212vfHcccdh8nUswhXe3s7N9xwA2VlZRgMBnw+3+fuM3PmTKxWK3FxccTFxdHY2EhKSsp+9UMB0yFoS2Vrn7b1ZU1MzI5lWn4CDquJYSnRrCtrYkSai4xYJ/9dW8aZkzK598yxtLv9RNnNRDvMJEbZefRHk2n4KFxKiLIR4/ziwl8iIiIiIiIisn/SYhxUfk6YlBbjOODncjg+Oeb999/P5MmT+dOf/kRFRcUXTn37dEFwk8mE3+/f734oYDoEJUbZen22mAycMDqNCx9eF2678tgCXthYhT8YYlhKJJfNKmDJ5moGJUQQDIGxDU4bn0F2fAQAyZoGJyIiIiIiIjIgrps3pFcNJgCHxcR184b063nb29tJTk4G4LnnnuvXc32WcUDPJvtkfFYsw1I+mbo2syCR5zZU9trG6wtiMhoAKKzp4C8rdjEi1UUoBOkxdk4akx4Ol0RERERERERk4Jw8Lp3fnDqK9BgHBiA9xsFvTh11wOsvfdZFF13EPffcw8knn3xARiV9HRrBdAjKjHPy0PkT2V7VRqcnwLDUKK7438Ze27y+vZZzj8zm76v2ALCtqo1Wt48nfzyFtBjnQei1iIiIiIiIiHzs5HHp/RYoXX755Z/bPm7cOF577bXw56uvvhqAyZMnM3ny5M/dd8mSJQekTwqYDlHpMU7SPxUUXTwjl2ue2hT+vKehg+NHjWJ0RgxvbK9heKqLY4cnKVwSERERERERkQGngOlb4phhSdx35lj+sXo3MU4rl8zMY1R6DOOyjCwck3awuyciIiIiIiIi32EKmL4lYpxWTh6XztwRyZiNBqxm08HukoiIiIiIiIgIoIDpW8dp1f9kIiIiIiIiInJo0SpyIiIiIiIiIiKyXxQwiYiIiIiIiIjIftF8KxERERERERGRQ1xzczPnn38+AA0NDRiNRuLi4gB46qmnsFqtX7r/mjVrsFgsjB8/vl/6128B00033cTbb79NfHw8S5YsAeCBBx7gySefDN+AxYsXM3PmTAAefPBBnn76aYxGIz/72c846qijAFi5ciW33347wWCQRYsWcfHFF/dXl0VEREREREREDozNT8Ky26C1AlwZcMytMPqMb3y42NhYXnjhBaAnX3E6nVx44YX7vP/atWtxOp3fvoDp1FNP5fvf/z433HBDr/bzzz+/zw0oKSlh6dKlLF26lNraWi644AJee+01AG677Tb+9a9/kZyczOmnn87s2bPJz8/vr26LiIiIiIiIiOyfzU/CS1eAz93zuXVvz2fYr5Dps7Zu3cqdd95JV1cXsbGx/OY3vyEpKYlHHnmExx9/HJPJRH5+Ptdccw2PP/44RqORF198kVtuuYWJEycesH5APwZMkyZNoqKiYp+2XbZsGQsWLMBqtZKZmUl2djabN28GIDs7m8zMTAAWLFjAsmXLFDCJiIiIiIiIyKFr2W2fhEsf87l72g9QwBQKhfj1r3/Nn//8Z+Li4nj55Ze59957+c1vfsPf/vY3li9fjtVqpa2tjejoaL73ve997VFPX8eA12B69NFHef755xk5ciQ33ngjLpeL2tpaxowZE94mOTmZ2tpaAFJSUnq1fxw8fRmPx0NhYeGB7/wX6O7uHtDziYCeOxl4euZkoOmZk4NBz50MND1zMtD0zH1zPp8Pt9v91RsC9tYKDJ/THmqtoHsfj/FVfQmFQhQVFXHeeecBEAwGSUhIwO12U1BQwNVXX82sWbOYNWsWbrcbn8/3ta7B5/N9rWdlQAOms846i0svvRSDwcD999/PnXfeyW9+85sDfh6bzcawYcMO+HG/SGFh4YCeTwT03MnA0zMnA03PnBwMeu5koOmZk4GmZ+6bKywsxOFw7NvGroyeaXGfYXBl7PsxvoTFYsFoNFJQUMATTzzR5/uHHnqIDz74gLfeeot//OMfvPTSS1gsFiwWyz6f32Kx9HlWvixwMn69S9g/CQkJmEwmjEYjixYtYsuWLUDPyKSamprwdrW1tSQnJ39hu4iIiIiIiIjIIeuYW8HymSDH4uhpP0CsVitNTU1s2LAB6BlxVFxcTDAYpLq6milTpnDttdfS3t5OV1cXERERdHZ2HrDzf9aABkx1dXXh//7mm29SUFAAwOzZs1m6dCler5e9e/dSWlrK6NGjGTVqFKWlpezduxev18vSpUuZPXv2QHZZREREREREROTrGX0GLPwDuDIBQ89/LvzDAS3wbTQa+cMf/sDdd9/NiSeeyMknn8yGDRsIBAJcd911LFy4kFNOOYVzzz2X6OhoZs2axRtvvMFJJ53EunXrDlg/PtZvU+QWL17M2rVraW5uZsaMGVx++eWsXbuWHTt2AJCens5tt90GQEFBAfPnz+f444/HZDJx6623YjKZALj11lu56KKLCAQCnHbaaeFQSkRERERERETkkDX6jAMaKH3a5ZdfHv7vjz76aJ/v//e///VpGzRoEC+99FK/9Af6MWC65557+rQtWrToC7e/5JJLuOSSS/q0z5w5k5kzZx7QvomIiIiIiIiIyIEzoFPkRERERERERETk8KOASURERERERERkH4RCoYPdhQHxTa5TAZOIiIiIiIiIyFew2+00NjYe9iFTKBSisbERu93+tfbrtxpMIiIiIiIiIiKHi4yMDCoqKqivrz/YXel3drudjIyMr7WPAiYRERERERERka9gsVgYNGjQwe7GIUtT5EREREREREREZL8oYBIRERERERERkf2igElERERERERERPaLIXQYlj/fuHEjNpvtYHdDREREREREROSw4fF4GDt27Od+d1gGTCIiIiIiIiIiMnA0RU5ERERERERERPaLAiYREREREREREdkvCphERERERERERGS/KGASEREREREREZH9ooBJRERERERERET2iwImERERERERERHZLwqYvsBNN93EkUceyQknnBBue+CBBzjqqKM46aSTOOmkk1ixYkX4uwcffJA5c+Ywb948Vq1aFW5fuXIl8+bNY86cOfztb38b0GuQb5fq6mp+8IMfcPzxx7NgwQIefvhhAFpaWrjggguYO3cuF1xwAa2trQCEQiF+/etfM2fOHBYuXMi2bdvCx3ruueeYO3cuc+fO5bnnnjso1yOHvi965vSuk/7k8Xg4/fTTOfHEE1mwYAF/+MMfANi7dy+LFi1izpw5XHXVVXi9XgC8Xi9XXXUVc+bMYdGiRVRUVISP9UXPo8infdEzd+ONNzJ79uzwu66wsBDQz1c5cAKBACeffDI//vGPAb3npP999pnTe04GXEg+19q1a0Nbt24NLViwINz2hz/8IfTQQw/12ba4uDi0cOHCkMfjCZWXl4eOOeaYkN/vD/n9/tAxxxwTKi8vD3k8ntDChQtDxcXFA3kZ8i1SW1sb2rp1aygUCoXa29tDc+fODRUXF4d++9vfhh588MFQKBQKPfjgg6Hf/e53oVAoFHr77bdDF154YSgYDIY2bNgQOv3000OhUCjU3Nwcmj17dqi5uTnU0tISmj17dqilpeXgXJQc0r7omdO7TvpTMBgMdXR0hEKhUMjr9YZOP/300IYNG0JXXHFFaMmSJaFQKBS65ZZbQo8++mgoFAqF/vvf/4ZuueWWUCgUCi1ZsiR05ZVXhkKhL34eRT7ri565G264IfTKK6/02V4/X+VA+ec//xlavHhx6OKLLw6FQiG956TfffaZ03tOBppGMH2BSZMm4XK59mnbZcuWsWDBAqxWK5mZmWRnZ7N582Y2b95MdnY2mZmZWK1WFixYwLJly/q55/JtlZSUxIgRIwCIjIwkNzeX2tpali1bxsknnwzAySefzJtvvgkQbjcYDIwdO5a2tjbq6upYvXo106ZNIyYmBpfLxbRp0/QXL/lcX/TMfRG96+RAMBgMREREAOD3+/H7/RgMBt5//33mzZsHwCmnnBJ+hpYvX84pp5wCwLx583jvvfcIhUJf+DyKfNYXPXNfRD9f5UCoqanh7bff5vTTTwd6RozoPSf96bPP3JfRe076iwKmr+nRRx9l4cKF3HTTTeGpSrW1taSkpIS3SU5Opra29gvbRb5KRUUFhYWFjBkzhsbGRpKSkgBITEyksbER6PvcpaSk6LmTb+zTzxzoXSf9KxAIcNJJJzF16lSmTp1KZmYm0dHRmM1m4JP3GfQ8d6mpqQCYzWaioqJobm7Wcydfy2efuY/fdffeey8LFy7kjjvuCE9X0s9XORDuuOMOrrvuOozGnl+3mpub9Z6TfvXZZ+5jes/JQFLA9DWcddZZvPHGG7zwwgskJSVx5513HuwuyWGos7OTK664gptvvpnIyMhe3xkMhi/9q6vIN/HZZ07vOulvJpOJF154gRUrVrB582Z27959sLskh7nPPnNFRUUsXryYV199lWeeeYbW1lbVj5MD5q233iIuLo6RI0ce7K7Id8QXPXN6z8lAU8D0NSQkJGAymTAajSxatIgtW7YAPcluTU1NeLva2lqSk5O/sF3ki/h8Pq644goWLlzI3LlzAYiPj6eurg6Auro64uLigL7PXU1NjZ47+do+75nTu04GSnR0NJMnT2bjxo20tbXh9/uBT95n0PPcVVdXAz3Tm9rb24mNjdVzJ9/Ix8/cqlWrSEpKwmAwYLVaOfXUU7/wXaefr/J1rV+/nuXLlzN79mwWL17M+++/z+233673nPSbz3vmrr32Wr3nZMApYPoaPv4lH+DNN9+koKAAgNmzZ7N06VK8Xi979+6ltLSU0aNHM2rUKEpLS9m7dy9er5elS5cye/bsg9V9OcSFQiF++tOfkpubywUXXBBunz17Ns8//zwAzz//PMccc0yv9lAoxMaNG4mKiiIpKYnp06ezevVqWltbaW1tZfXq1UyfPv1gXJIc4r7omdO7TvpTU1MTbW1tAHR3d/Puu++Sl5fH5MmTee2114CeFWw+foZmz54dXsXmtddeY8qUKRgMhi98HkU+6/Oeudzc3PC7LhQK9XnX6eer7I9rrrmGlStXsnz5cu655x6mTJnC73//e73npN983jN399136z0nA858sDtwqFq8eDFr166lubmZGTNmcPnll7N27Vp27NgBQHp6OrfddhsABQUFzJ8/n+OPPx6TycStt96KyWQC4NZbb+Wiiy4iEAhw2mmnhf9Ri3zWhx9+yAsvvMDgwYM56aSTgJ7n8OKLL+aqq67i6aefJi0tjfvuuw+AmTNnsmLFCubMmYPD4eCOO+4AICYmhksvvTRc4O+yyy4jJibmYFySHOK+6JlbsmSJ3nXSb+rq6rjxxhsJBAKEQiGOO+44Zs2aRX5+PldffTX33Xcfw4YNY9GiRQCcfvrpXHfddcyZMweXy8W9994LfPnzKPJpX/TMnXvuuTQ3NxMKhRg6dCi//OUvAf18lf5z3XXX6T0nA+raa6/Ve04GlCEUCoUOdidEREREREREROTbS1PkRERERERERERkvyhgEhERERERERGR/aKASURERERERERE9osCJhERERERERER2S8KmEREREREREREZL+YD3YHRERERA4Xf/nLX1iyZAlGoxGj0chtt93G3XffTV1dHTabDafTyR133EFubi433ngja9euJSoqCoA777yTYcOGEQqFuP3221mxYgV2u50777yTESNGAPDcc8/xl7/8BYBLLrmEU0455aBdq4iIiMinKWASEREROQA2bNjA22+/zXPPPYfVaqWpqQmfzwfA3XffzahRo3jiiSf43e9+x1//+lcArr/+eo477rhex1m5ciWlpaW8/vrrbNq0iV/84hc89dRTtLS08Mc//pFnnnkGg8HAqaeeyuzZs3G5XAN+rSIiIiKfpSlyIiIiIgdAfX09sbGxWK1WAOLi4khOTu61zcSJEykvL//S4yxbtoyTTz4Zg8HA2LFjaWtro66ujtWrVzNt2jRiYmJwuVxMmzaNVatW9dv1iIiIiHwdCphEREREDoBp06ZRXV3NvHnz+MUvfsHatWv7bPPWW28xePDg8Od7772XhQsXcscdd+D1egGora0lJSUlvE1KSgq1tbV92pOTk/n/du4YpbEwigLwGQKiiJDGBLSwUlyBaQKC4AbEVaggatoUEXERFi5BsgAbIY1gYWcnlomNxMLG4p9iwJmBGUbmxZGB7+se3OKd9nDvPxqNPjARAMD7OZEDAJiA2dnZXFxc5ObmJtfX1zk4OMjR0VGSpNPpZHp6OouLi+l2u0mSw8PDzM/P5/X1Nd1uN2dnZ9nb2/vMCAAAf03BBAAwIbVaLa1WK61WKysrK+n3+0m+v8H0o0ajkSSZmprK1tZWzs/Pk3zbTBoOh29zw+EwzWYzzWbzp62o0WiUtbW1D04EAPA+TuQAACbg/v4+Dw8Pb993d3dZWFj47fzj42OSpJSSy8vLLC8vJ0k2NjbS7/dTSsnt7W3m5ubSaDTSbrczGAwyHo8zHo8zGAzSbrc/NBMAwHvZYAIAmICXl5ecnJzk+fk5tVotS0tLOT4+zv7+/i/nO51Onp6eUkrJ6upqer1ekmR9fT1XV1fZ3NzMzMxMTk9PkyT1ej07OzvZ3t5Okuzu7qZer/+TbAAAf/KllFI++ycAAAAA+H85kQMAAACgEgUTAAAAAJUomAAAAACoRMEEAAAAQCUKJgAAAAAqUTABAAAAUImCCQAAAIBKvgKvpaaQCCMoTQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax3 = plt.subplots(figsize=(20, 10))\n",
    "sns.scatterplot(x='SP500', y='predictions', data=snp500, hue='data', ax=ax3)\n",
    "ax3.text(x=.02, y=.95, s=f'Test IC ={test_ic}', transform=ax3.transAxes)\n",
    "ax3.text(x=.02, y=.87, s=f'Train IC={train_ic}', transform=ax3.transAxes)\n",
    "ax3.set_title('Correlation Plot')\n",
    "ax3.legend(loc='lower right')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "dKyBbok85Nh6",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "dKyBbok85Nh6",
    "outputId": "5ad832df-5b79-4310-949a-084709ea3493"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "<ipython-input-56-a4b0ee4c9093>:4: MatplotlibDeprecationWarning: Auto-removal of overlapping axes is deprecated since 3.6 and will be removed two minor releases later; explicitly call ax.remove() as needed.\n",
      "  ax4 = plt.subplot(sharex = ax2, sharey=ax2)\n",
      "<ipython-input-56-a4b0ee4c9093>:5: UserWarning: \n",
      "\n",
      "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
      "\n",
      "Please adapt your code to use either `displot` (a figure-level function with\n",
      "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "\n",
      "For a guide to updating your code to use the new functions, please see\n",
      "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
      "\n",
      "  sns.distplot(train_predict.squeeze()- y_train_rescaled, ax=ax2)\n",
      "<ipython-input-56-a4b0ee4c9093>:8: UserWarning: \n",
      "\n",
      "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
      "\n",
      "Please adapt your code to use either `displot` (a figure-level function with\n",
      "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "\n",
      "For a guide to updating your code to use the new functions, please see\n",
      "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
      "\n",
      "  sns.distplot(test_predict.squeeze()-y_test_rescaled, ax=ax4)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Text(0.03, 0.92, 'Test RMSE =62.09228035778334')"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAm0AAAE/CAYAAAAUpfTfAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAAsTAAALEwEAmpwYAABD3ElEQVR4nO3de1yUZf7/8dcww3AGQWVAQ0wl09Q8VWqlG4qY5FnbarUyXXe3XLVW22rLyk5b2dd01zz83HRba7fVNEsq85BpZVqtLqmUp1RUGFSQg8AMM3P//sBmIzyQMcDg+/l48JC557qvue6PSW/uw3WZDMMwEBEREZF6LaCuByAiIiIiF6bQJiIiIuIHFNpERERE/IBCm4iIiIgfUGgTERER8QMKbSIiIiJ+QKFNRATo0qULWVlZdT0MEZFzMmmeNhGp77p06eL9vrS0FKvVitlsBuDJJ59k8ODBP6m/MWPGMHjwYEaNGlWj4zybv/zlL8yfPx+r1erdZjab+fLLL33+2SLSsFjqegAiIheyfft27/fJyck8/fTT9OrVqw5H9NPcfPPNzJw584LtXC4XFovlgtt+ah8i0jDo8qiI+C2Px8PChQvp168f1113HZMnT+bUqVMAOBwOpk6dynXXXUf37t0ZMWIEJ06cYNasWXz55ZfMmDGDLl26MGPGDADatm3LoUOHAHjooYd48sknmTBhAl26dGHUqFEcPnzY+7mffPIJqampdOvWjSeeeILRo0ezbNmyizqGtm3b8vrrr9O/f3/69+/P1q1b6d27NwsXLuT666/n4Ycfxul08swzz3DDDTdwww038Mwzz+B0OgHO2l5EGiaFNhHxW//4xz9Yt24dS5cuZfPmzURFRXlD2MqVKykuLmbjxo1s3bqVJ598kuDgYO6//366d+/O9OnT2b59O9OnTz9r3++99x4TJ07kiy++oEWLFsyaNQuAvLw8Jk2axB/+8Ae2bt3K5ZdfXulM4MVYt24d//73v3nvvfcAOHHiBAUFBXz00Uc89dRTzJs3j//+97+sWrWKd955h6+//ppXXnnFu/+P24tIw6TQJiJ+61//+hf3338/cXFxWK1WJk6cyJo1a7yXCE+dOsWhQ4cwm8106NCB8PDwavfdr18/OnXqhMViYfDgwWRmZgKwadMmkpKS6N+/PxaLhTvvvJMmTZqct68PPviA7t27e7/GjBlT6f0JEybQqFEjgoODAQgICGDSpElYrVaCg4N59913ue+++2jcuDExMTHcd999vPPOO979f9xeRBom3fggIn7r2LFj3HfffQQE/O/3z4CAAE6ePMmQIUPIycnhgQceoLCwkMGDB3P//fcTGBhYrb5/GMSCg4MpKSkBIDc3l7i4OO97JpOp0uuzGTBgwHnvaYuPj6/0Ojo6mqCgIO/r3NxcmjVr5n3drFkzcnNzz9leRBomhTYR8VtxcXE8++yzdOvW7azvT5w4kYkTJ3LkyBEmTJjA5Zdf/rOfGG3atCl2u9372jAMcnJyflafJpPpvK9jY2M5duwYSUlJAGRnZxMbG3vO9iLSMOnyqIj4rdtvv52XX36Zo0ePAhX3m61btw6Azz//nG+//Ra32014eDgWi8V7Rq5JkyYXPSdbnz59+Pbbb1m3bh0ul4vXX3+dEydO1MwBnUNaWhrz5s0jLy+PvLw85s6dy6BBg3z6mSJS/yi0iYjfuvPOO0lOTuaee+6hS5cu3HrrrWRkZAAVN+dPmjSJbt26MXDgQK699lqGDBni3W/NmjVcc801PP300z/pM2NiYpg9ezYvvvgi1113Hfv27aNDhw7nvez6/vvv06VLl0pfJ0+erPZn3nvvvXTo0IHBgwczePBgrrrqKu69996fNG4R8X+aXFdE5GfweDz07t2bmTNn0qNHj7oejog0YDrTJiLyE23evJnCwkKcTifz588HoHPnznU7KBFp8PQggojIT7Rjxw6mTp2K0+mkTZs2zJ07V1NtiIjP6fKoiIiIiB/Q5VERERERP6DQJiIiIuIHLol72nbs2KHZwmuQw+FQPWuJal07VOfaoTrXHtW6dviqzg6H46wPN10SoS0oKIh27drV9TAajMzMTNWzlqjWtUN1rh2qc+1RrWuHr+r8/VrHP6bLoyIiIiJ+QKFNRERExA8otImIiIj4AZ/e07Zp0yaeeeYZPB4Po0aNYsKECZXedzqdPPjgg+zatYtGjRoxa9YsLrvsMj799FNeeuklysvLCQwMZNq0afTs2ROAMWPGkJub653I8tVXX6Vx48a+PAwRERGROuez0OZ2u5kxYwaLFy/GZrMxcuRIkpOTadOmjbfNsmXLiIyMZO3ataSnpzNz5kxefvlloqOjmTdvHjabjT179jBu3Dg2b97s3W/mzJl07NjRV0MXERERqXd8dnk0IyODxMREEhISsFqtpKWlsX79+kptNmzYwLBhwwBITU1ly5YtGIZB+/btsdlsACQlJeFwOHA6nb4aqoiIiEi957PQZrfbiYuL87622WzY7fYqbeLj4wGwWCxERESQn59fqc2aNWto3749VqvVu+2RRx5hyJAhzJ07F63CJSIiIpeCej1P2969e5k5cyavvvqqd9vMmTOx2WwUFxczadIkVq1axdChQ8/bj8PhOOecJ/LTlZWVqZ61RLWuHapz7VCda49qXTtqu84+C202m42cnBzva7vd7r3k+cM22dnZxMXF4XK5KCoqIjo6GoCcnBwmTpzI888/T4sWLSrtAxAeHs4tt9xCRkbGBUObJtetWZq0sfao1rVDda4dqnPtUa1rR4OZXLdjx44cPHiQrKwsnE4n6enpJCcnV2qTnJzMypUrgYrLoD169MBkMlFYWMiECRP4wx/+QLdu3bztXS4XeXl5AJSXl7Nx40aSkpJ8dQgiIiIi9YbPzrRZLBamT5/O+PHjcbvdjBgxgqSkJGbPnk2HDh3o27cvI0eOZNq0aaSkpBAVFcWsWbMAWLp0KYcPH2bu3LnMnTsXqJjaIyQkhPHjx1NeXo7H46Fnz57ceuutvjoEERERkXrDp/e09enThz59+lTaNnnyZO/3QUFBzJkzp8p+9957L/fee+9Z+1yxYkXNDlJERETED9TrBxHqi/z8fO6++24ATpw4QUBAADExMUDFXHM/fLL1bLZu3UpgYCBdu3at8t6KFSt44YUXsNlsOBwObrvtNu9n/eUvf+Gvf/0rH374IYmJiQAsWbKE5557juXLl9OxY0eWL1/O3//+dwAMw2DKlCn069ePhx56iG3bthEREQFASEgI//rXv37ysTudTp566im2bduGyWTi/vvvp0WLFixevJhly5ZhNpuJiYnh2WefpXnz5lX237lzJw8//DBlZWX06dOHP/3pT5hMJr755hsef/xxSkpKaN68OTNnziQ8PPycEyuXlpYyefJkDh8+jNls5qabbmLq1KkAHDt2jD/+8Y8UFRXhdruZOnWq95eFBQsWsHz5cgICAnj00Ue58cYbcTgc/OpXv8LpdOJ2u0lNTWXSpEkAVer25z//mXbt2rFo0SLeffddoGIOwv3797Nlyxby8vK4//77vceblZXFpEmTuPvuu8nMzOTxxx/H4XBgNpt54okn6NSpE+vWrWP27NkEBARgNpt55JFH6N69O0ePHmXixIl4PB5cLhejR4+mc+fOler529/+liNHjrB69eqf/HcpIiJ+zrgE7N69u8b6mjNnjrFo0aIa2+ett94ynnzyScMwDCMvL8+49tprjWPHjnn3u+WWW4y5c+d62//yl7800tLSjIyMDCM7O9vo27evUVhYaBiGYRQXFxuHDx82DMMw/vjHPxrvv//+Tz6+H5s9e7bxf//3f4ZhGIbb7TZOnjxp7N6929iyZYtRUlJiGIZhvP7668bkyZPPuv+IESOM7du3Gx6Pxxg3bpyxceNGwzAMY/jw4cbWrVsNwzCMZcuWGbNmzTIMwzB27dpl5OTkGIZhGN9++61xww03GIZhGCUlJcaWLVsMwzAMh8Nh3H777d6+Hn30UeP11183DMMw9u7da9x0003e7wcNGmQ4HA7j8OHDRt++fQ2Xy2V4PB6juLjYMAzDcDqdxsiRI43t27dXu27r1683xowZU2W7y+UyevXqZRw5csQwDMMYO3asd4wbN240Ro8ebRhGxd+Tx+MxDMMwMjMzjdTUVO9xORwOb5ubbrrJ+OSTT7z9r1mzxnjggQeMtLS0845Pfrqa/Bkh56Y61x7Vunb4qs7n6ldrj16knTt3Mnr0aIYPH864cePIzc0F4LXXXmPgwIEMGjSI+++/nyNHjvCvf/2LJUuWMGTIEL788stz9hkdHU1iYiLHjx/3buvXr593UuLDhw8TERHhfcL25MmThIWFERoaCkBYWBgJCQk1epxvvfUWv/nNbwAqnWHs0aMHISEhAHTu3LnSk8Lfy83Npbi4mM6dO2MymRg6dKj3WA4ePMg111wDwPXXX8+HH34IcM6JlUNCQujRowcAVquV9u3be+f9M5lMFBcXA1BUVERsbCwA69evJy0tDavVSkJCAomJiWRkZGAymQgLCwMqHm5xuVyYTKZq1yQ9PZ1bbrmlyvYtW7aQkJDgPeNoMpk4ffp0lXGFhYV5P6+0tNT7vdVq9Z61dTqdeDweb9+nT59m8eLF/O53v6v2OEVEpGHR5dGLYBgGTz/9NK+88goxMTG89957zJo1i+eee46FCxeyYcMGrFYrhYWFREZGcttttxEaGsq4cePO2++xY8dwOBy0bdvWuy08PJz4+Hj27NnD+vXrGThwoPe+viuvvJImTZrQt29fevbsSUpKSqUndF944QXmzZsHQJs2bXjppZcqfd6BAwcqXdr7oX/84x/e72fPns22bdtISEhg+vTpVdouX76c3r17V9n+4wmW4+LivEErKSmJ9evX069fPz744AOys7Or7H+2iZUBCgsL+eijj7jrrrsAmDhxIuPGjWPp0qWUlpayePFi7+dfffXV3v1+OMGz2+1m+PDhHD58mDvuuKNSu1mzZjF37lx69uzJ1KlTK31+aWkpmzdv5rHHHqsy3h+HuUceeYRx48bx/PPP4/F4Kl2eXrt2LS+99BJ5eXksWLDAuz07O5sJEyZw+PBhHnzwQW9Inj17Nvfcc493zV0REbn06EzbRXA6nezZs4exY8cyZMgQ5s2b5w0Dbdu2ZerUqaxatQqz2Vyt/t577z0GDRpE//79ueOOOwgKCqr0/sCBA0lPT2fdunWkpKR4t5vNZhYtWsScOXNo2bIlzz33HH/5y1+87z/44IOsWrWKVatWVQlsAK1atfK+/+OvyMhIXC4XOTk5dOnShZUrV9KlSxeef/75Sn2sWrWKnTt3Mn78+GrXD+CZZ57hjTfeYPjw4Zw+fbpKMPt+YuUZM2ZU2u5yuXjggQcYM2aM96xieno6w4YNY9OmTSxcuJAHH3yw0lmqszGbzaxatYqPP/6YjIwM9uzZA8ADDzzABx98wFtvvUVBQQELFy6stN9HH31E165dadSoUaXtTqeTDRs2MGDAAO+2f/7znzz88MN8/PHHPPzww/zpT3/yvpeSksIHH3zA3LlzmT17tnd7fHw87777Lh9++CErV67k1KlTZGZmcvjw4Up/9yIicunRmbaLYBgGSUlJvPnmm1XeW7hwIV988QUfffQR8+fP9968fj4DBw5k+vTpfP3114wbN47k5GSaNm3qff+mm27ixRdfpEOHDoSHh1fa12Qy0alTJzp16kSvXr145JFH+P3vf1+t47jQmbbo6GhCQkLo378/AAMGDGD58uXeNp999hnz589n6dKlZ30Y48cTLOfk5HgvfbZu3dq70sV3333Hxo0bK7U728TKAI899hgtW7b0PqwBFWf6Fi1aBECXLl1wOBzk5+dXa4LnyMhIrrvuOjZv3swVV1zhvYRptVoZPnx4pdU4oCIgpqWlVTnWTZs2cdVVV9GkSRPvtpUrV3qD2s0338yjjz5aZb9rrrmGrKws8vLyvGfVvq9dUlISu3fvJiQkhJ07d5KcnOydq3DMmDGVzoaKiEjDpzNtF8FqtZKXl8f27duBiol+9+7di8fjITs7mx49ejB16lSKioooKSkhLCzMe2/T+XTs2JHBgwfz2muvVdoeEhLC1KlT+e1vf1tpu91uZ9euXd7X33zzDc2aNav2cVzoTJvJZOKmm25i69atQMU9W61btwZg9+7dTJ8+nXnz5tG4ceOz9h8bG0t4eDg7duzAMAzefvtt+vbtC1Tcjwfg8XiYN28et912G8A5J1aGisuWxcXFPPLII5W2x8fHs2XLFgD279+Pw+EgJiaG5ORk0tPTcTqdZGVlcfDgQTp16kReXh6FhYVAxRIkn332Ga1atQLw3ptoGAbr1q2rNHlzUVERX3zxhfcYfuhsYS42NpZt27YB8Pnnn9OyZUsADh065F0zd9euXTidTqKjo8nJyaGsrAyAgoIC/vOf/9CsWTPuuOMOPvnkEzZs2MAbb7xBy5YtFdhERC5BOtN2EQICApgzZw5PP/20d5qJu+66i5YtWzJt2jSKi4sxDIM777yTyMhIbrrpJiZNmsT69et57LHH6N69+zn7/vWvf83w4cO9N/9/72xnd1wuF88//zy5ubkEBQURExPDk08+6X3/h/e0QfWmJ/mxqVOn8uCDD/Lss88SExPDc889R0FBAS+88AIlJSXeeffi4+OZP38+AEOGDGHVqlUAPP74494pP3r37u2992316tW88cYbQMWlwhEjRgDnnli5vLyc+fPn06pVK4YNGwbA6NGjGTVqFA899BCPPvooS5YswWQy8ec//xmTyURSUhI333wzAwcOxGw2M336dMxmM7m5uTz00EO43W4Mw2DAgAHcdNNN3uPNz8/HMAyuvPLKSvVcu3Yt119/vffBj++VlJTw2WefVbmU+9RTT/Hss8/icrkICgryvr9mzRpWrVqFxWIhODiYWbNmYTKZ2L9/v3fshmFwzz33eIOeiIiIyfj+V/4GTGuw1SzVs/ao1rVDda4dqnPtUa1rhy/XHj1bv7o8KiIiIuIHFNpERERE/IBCm4iIiIgfUGgTERER8QMKbSIiIiJ+QKFNRERExA8otImIiIj4AYU2ERERET+g0CYiIiLiBxTaRERERPyAQpuIiIiIH1BoExEREfEDCm0iIiIifkChTURERMQPKLSJiIiI+AGFNhERERE/oNAmIiIi4gcU2kRERET8gEKbiIiIiB9QaBMRERHxAwptIiIiIn5AoU1ERETEDyi0iYiIiPgBhTYRERERP6DQJiIiIuIHFNpERERE/IBCm4iIiIgfUGgTERER8QMKbSIiIiJ+QKFNRERExA8otImIiIj4AYU2ERERET+g0CYiIiLiBxTaRERERPyAQpuIiIiIH/BpaNu0aROpqamkpKSwcOHCKu87nU6mTJlCSkoKo0aN4siRIwB8+umnDB8+nEGDBjF8+HC2bNni3Wfnzp0MGjSIlJQUnn76aQzD8OUhiIiIiNQLPgttbrebGTNmsGjRItLT01m9ejX79u2r1GbZsmVERkaydu1a7r77bmbOnAlAdHQ08+bN49133+XPf/4zDz74oHefJ554gqeeeooPP/yQgwcPsmnTJl8dgoiIiEi94bPQlpGRQWJiIgkJCVitVtLS0li/fn2lNhs2bGDYsGEApKamsmXLFgzDoH379thsNgCSkpJwOBw4nU5yc3MpLi6mc+fOmEwmhg4dWqVPERERkYbIZ6HNbrcTFxfnfW2z2bDb7VXaxMfHA2CxWIiIiCA/P79SmzVr1tC+fXusVmuVPuPi4qr0KSIiItIQWep6AOezd+9eZs6cyauvvvqz+nE4HGRmZtbQqKSsrEz1rCWqde1QnWuH6lx7VOvaUdt19llos9ls5OTkeF/b7XbvJc8ftsnOziYuLg6Xy0VRURHR0dEA5OTkMHHiRJ5//nlatGhx1j5zcnKq9Hk2QUFBtGvXriYOS4DMzEzVs5ao1rVDda4dqnPtUa1rh6/qfK4g6LPLox07duTgwYNkZWXhdDpJT08nOTm5Upvk5GRWrlwJVFwG7dGjByaTicLCQiZMmMAf/vAHunXr5m0fGxtLeHg4O3bswDAM3n77bfr27eurQxARERGpN3wW2iwWC9OnT2f8+PEMHDiQm2++maSkJGbPnu19eGDkyJGcOnWKlJQUFi9ezNSpUwFYunQphw8fZu7cuQwZMoQhQ4Zw8uRJAB5//HEeffRRUlJSaNGiBb179/bVIYiIiIjUGybjEpjoTKeJa5bqWXtU69qhOtcO1bn2qNa1w5eXR8/Wr1ZEEBEREfEDCm0iIiIifkChTURERMQPKLSJiIiI+AGFNhERERE/oNAmIiIi4gcU2kRERET8gEKbiIiIiB9QaBMRERHxAwptIiIiIn5AoU1ERETEDyi0iYiIiPgBhTYRERERP6DQJiIiIuIHFNpERERE/IBCm4iIiIgfUGgTERER8QMKbSIiIiJ+QKFNRERExA8otImIiIj4AYU2ERERET+g0CYiIiLiBxTaRERERPyAQpuIiIiIH1BoExEREfEDCm0iIiIifkChTURERMQPKLSJiIiI+AGFNhERERE/oNAmIiIi4gcU2kRERET8gEKbiIiIiB9QaBMRERHxAwptIiIiIn5AoU1ERETEDyi0iYiIiPgBhTYRERERP6DQJiIiIuIHFNpERERE/IBCm4iIiIgfUGgTERER8QMKbSIiIiJ+QKFNRERExA/4NLRt2rSJ1NRUUlJSWLhwYZX3nU4nU6ZMISUlhVGjRnHkyBEA8vPzGTNmDF26dGHGjBmV9hkzZgypqakMGTKEIUOGcPLkSV8egoiIiEi9YPFVx263mxkzZrB48WJsNhsjR44kOTmZNm3aeNssW7aMyMhI1q5dS3p6OjNnzuTll18mKCiIyZMns3fvXvbu3Vul75kzZ9KxY0dfDV1ERESk3vHZmbaMjAwSExNJSEjAarWSlpbG+vXrK7XZsGEDw4YNAyA1NZUtW7ZgGAahoaF0796doKAgXw1PRERExK/4LLTZ7Xbi4uK8r202G3a7vUqb+Ph4ACwWCxEREeTn51+w70ceeYQhQ4Ywd+5cDMOo2YGLiIiI1EM+uzzqKzNnzsRms1FcXMykSZNYtWoVQ4cOPe8+DoeDzMzM2hngJaCsrEz1rCWqde1QnWuH6lx7VOvaUdt19llos9ls5OTkeF/b7XZsNluVNtnZ2cTFxeFyuSgqKiI6OvqC/QKEh4dzyy23kJGRccHQFhQURLt27S7uQKSKzMxM1bOWqNa1Q3WuHapz7VGta4ev6nyuIOizy6MdO3bk4MGDZGVl4XQ6SU9PJzk5uVKb5ORkVq5cCcCaNWvo0aMHJpPpnH26XC7y8vIAKC8vZ+PGjSQlJfnqEERERETqDZ+dabNYLEyfPp3x48fjdrsZMWIESUlJzJ49mw4dOtC3b19GjhzJtGnTSElJISoqilmzZnn3T05Opri4mPLyctatW8err75Ks2bNGD9+POXl5Xg8Hnr27Mmtt97qq0MQERERqTd8ek9bnz596NOnT6VtkydP9n4fFBTEnDlzzrrvhg0bzrp9xYoVNTdAERERET9RrcujEydOZOPGjXg8Hl+PR0RERETOolqh7Y477uDdd9+lf//+zJw5kwMHDvh6XCIiIiLyA9W6PNqrVy969epFUVERq1evZuzYscTHxzNq1CgGDx5MYGCgr8cpIiIickmr9tOj+fn5rFixgmXLltGuXTvuvPNOdu/ezT333OPL8YmIiIgI1TzTdt999/Hdd98xZMgQ5s+fT2xsLAADBw5k+PDhPh2giIiIiFQztN16661VngJ1Op1YrVY9zSkiIiJSC6p1efTll1+usu2Xv/xlTY9FRERERM7hvGfajh8/jt1up6ysjN27d3sXZy8uLqa0tLRWBigiIiIiFwhtn3zyCStWrCAnJ4fnnnvOuz0sLIwHHnjA54MTERERkQrnDW3Dhg1j2LBhrFmzhtTU1Noak4iIiIj8yHlD26pVqxgyZAhHjx5l8eLFVd4fO3aszwYmIiIiIv9z3tD2/X1rJSUltTIYERERETm784a22267DahYe1RERERE6k61pvx44YUXKC4upry8nLvuuosePXqwatUqX49NRERERM6oVmj79NNPCQ8PZ+PGjTRv3py1a9fyt7/9zddjExEREZEzqhXa3G43ABs3bmTAgAFERET4dFAiIiIiUlm1QtsvfvELBgwYwK5du+jZsyd5eXkEBQX5emwiIiIicka11h6dOnUq48ePJyIiArPZTEhICK+88oqvxyYiIiIiZ1QrtAEcOHCAo0ePei+VAgwdOtQXYxIRERGRH6lWaJs2bRpZWVlceeWVmM1mAEwmk0KbiIiISC2pVmjbuXMn7733HiaTydfjEREREZGzqNaDCElJSRw/ftzXYxERERGRc6jWmbb8/HzS0tLo1KkTgYGB3u3z58/32cBERERE5H+qFdp+//vf+3ocIiIiInIe1Qpt1157LUePHuXQoUP06tWL0tLSSk+RioiIiIhvVeuetn//+99MmjSJ6dOnA2C327nvvvt8OjARERER+Z9qhbbXX3+df/7zn4SHhwPQsmVL8vLyfDowEREREfmfaoU2q9WK1Wr1vna5XD4bkIiIiIhUVa172q655hrmz59PWVkZn376KW+88QbJycm+HpuIiIiInFGtM21Tp04lJiaGK664gjfffJM+ffowZcoUHw9NRERERL5XrTNtAQEB9OvXj379+hETE+PrMYmIiIjIj5w3tBmGwV//+leWLl2KYRhARYAbPXo0EydOrJUBioiIiMgFLo8uWbKE//znPyxfvpxt27axbds2li1bxvbt21myZEktDVFEREREzhvaVq1axUsvvURCQoJ3W0JCAi+++CJvv/22r8cmIiIiImecN7S5XK6z3sMWExOjaT9EREREatF5Q9sPF4f/Ke+JiIiISM0674MI33zzDV27dq2y3TAMnE6nzwYlIiIiIpWdN7RlZmbW1jhERERE5DyqNbmuiIiIiNQthTYRERERP6DQJiIiIuIHFNpERERE/IBCm4iIiIgfUGgTERER8QM+DW2bNm0iNTWVlJQUFi5cWOV9p9PJlClTSElJYdSoURw5cgSA/Px8xowZQ5cuXZgxY0alfXbu3MmgQYNISUnh6aef9i5kLyIiItKQ+Sy0ud1uZsyYwaJFi0hPT2f16tXs27evUptly5YRGRnJ2rVrufvuu5k5cyYAQUFBTJ48mQcffLBKv0888QRPPfUUH374IQcPHmTTpk2+OgQRERGResNnoS0jI4PExEQSEhKwWq2kpaWxfv36Sm02bNjAsGHDAEhNTWXLli0YhkFoaCjdu3cnKCioUvvc3FyKi4vp3LkzJpOJoUOHVulTREREpCHyWWiz2+3ExcV5X9tsNux2e5U28fHxAFgsFiIiIsjPz692n3FxcVX6FBEREWmIzruMVUPhcDi0JFcNKisrUz1riWpdO1Tn2qE61x7VunbUdp19FtpsNhs5OTne13a7HZvNVqVNdnY2cXFxuFwuioqKiI6OrnafOTk5Vfo8m6CgINq1a3cRRyFnk5mZqXrWEtW6dqjOtUN1rj2qde3wVZ3PFQR9dnm0Y8eOHDx4kKysLJxOJ+np6SQnJ1dqk5yczMqVKwFYs2YNPXr0wGQynbPP2NhYwsPD2bFjB4Zh8Pbbb9O3b19fHYKIiIhIveGzM20Wi4Xp06czfvx43G43I0aMICkpidmzZ9OhQwf69u3LyJEjmTZtGikpKURFRTFr1izv/snJyRQXF1NeXs66det49dVXadOmDY8//jgPP/wwZWVl9O7dm969e/vqEERERETqDZ/e09anTx/69OlTadvkyZO93wcFBTFnzpyz7rthw4azbu/YsSOrV6+uuUGKiIiI+AGtiCAiIiLiBxTaRERERPyAQpuIiIiIH1BoExEREfEDCm0iIiIifkChTURERMQPKLSJiIiI+AGFNhERERE/oNAmIiIi4gcU2kRERET8gEKbiIiIiB9QaBMRERHxAwptIiIiIn5AoU1ERETEDyi0iYiIiPgBhTYRERERP6DQJiIiIuIHFNpERERE/IBCm4iIiIgfUGgTERER8QMKbSIiIiJ+QKFNRERExA8otImIiIj4AUtdD0BEpK4UlDgpcrhwWsI5kl9SY/1GBFmICrXWWH8iIqDQJiKXsCKHi017TpCdk018nFFj/fa+oolCm4jUOF0eFREREfEDCm0iIiIifkChTURERMQP6J42EZEa5nJ7avTBhh/SQw4ily6FNhGRHyl1urEXllFYVs5phwu3xwCTiUCzicjgQKJCAomNCMJiPvvFitJyD9v35/lkbHrIQeTSpdAmIpc8h8tDxpFT7LEX8d2J0+SXlF9wnwATxEYEc3mTMJJs4bRqEo7VojtORMR3FNpE5JJkGAZfHcrnX18cZtfRAtxGHiGBZlo3DePaljHERQUTFWIlPNiCJcCEYYDT7aGorJy8006yC8o4eqqULw/lseXASayWADo0i6RLi2g6J0TV9eGJSAOk0CYilxS3x+C9r7OZ//F+dh0rJCTQTPvYYHq1bUZCTCgBJtM59w3BTFRIIJdFh9Lpsopt5W4PB0+c5uujBXx9tID/HD7Fukw7XVtE06VFIywBOvsmIjVDoU1ELhmb9hznufe/ITO7kFZNw3hoQFtCrBZOHLcT3zjsovoMNAeQZIsgyRbBoKub8fWRAv5zOJ+V24/y0be5JLeNpUuLaMwB5w6DIiLVodAmIg1eTkEZj63aydrddi6LDmH2bZ0Z1KkZxwpK2bTnRI19TqA5gK6J0dxzQ0v+/eUR1mXaWbH9KJ/sO8EtnZrRJja8xj5LRC49Cm0i0mB5PAb//OIwf37vG8o9Hh66+UrGXt+SIIvZp59rMpm4whZBUmw4u7MLee/rbF799Ds6NI9iUKd4IoIDffr5ItIwKbSJSIN04HgxD6/4mq3f5dGrdWOeG96RxIu8BHqxTCYTVzWL4gpbBJv3Huejb4+zP7eYWzrF0zmhEabz3D8nIvJjCm0i0qAYhsEb2w4z493dWC0BPD+iI7d2T6jTgBRoDiD5ShsdmkWxYvtRln11hH25xQzu3MznZ/1EpOFQaBORBqOgpJyHVmTw/s4cbkxqwkujriY2Mriuh+UVGxnMhN6t+OjbXDZk5nIkv5Tbr2tBXD0ao4jUXwptItIgfHUoj0n/3IG9sIyHb76SX9/YioB6+MRmgMlE3ytttGwcxptfZDFv4z4GdWpGt8RoXS4VkfNSaBOReq2gxEmRw3XO990eg9e3HuJvmw9iiwrilV91pX2zSI4VlF6wb0e5uyaH+pO0bhrO75Pb8OaXWazYfpTDeSUM7txM87qJyDkptIlIvVbkcJ1zWo7C0nL+/VUWB46fptNlUQzt3JwTxc5qT+PRpUWjGhzpTxcRHMg911/Oukw7G789Tl6Jk19dm0iIVfe5iUhVCm0i4pe+yS5k+X+OUO72MKJrc7q28M/LiwEmE/3bx9EkLIiV248yf9N+7urZkpgwLQovIpX59Dz8pk2bSE1NJSUlhYULF1Z53+l0MmXKFFJSUhg1ahRHjhzxvrdgwQJSUlJITU1l8+bN3u3JyckMGjSIIUOGMHz4cF8OX0TqoXK3h3f+e4zXPj9EVEgg993Uhm6JMX4Z2H6oa2I0Y69vSVFZOfM27uNwXkldD0lE6hmfnWlzu93MmDGDxYsXY7PZGDlyJMnJybRp08bbZtmyZURGRrJ27VrS09OZOXMmL7/8Mvv27SM9PZ309HTsdjtjx45lzZo1mM0Vlwz+/ve/ExMT46uhi0g9lVNYxptfHMZe6OD61o1JvSoOi7nh3APWqmk4v+3Tmte2HGLR5gPccW0LroyPrOthiUg94bOfdhkZGSQmJpKQkIDVaiUtLY3169dXarNhwwaGDRsGQGpqKlu2bMEwDNavX09aWhpWq5WEhAQSExPJyMjw1VBFpJ7zGAaf7DvBKx/to9jh5q6eLUnr1KxBBbbvxUYE89s+rbFFBrN06yH+m3WqrockIvWEz37i2e124uLivK9tNht2u71Km/j4eAAsFgsRERHk5+dfcN9x48YxfPhw3nzzTV8NX0Tqif3Hi5n/8X7e+zqb1k3DmZTchrZxEXU9LJ8KD7Iw7obLSWwcxr+/zGLrdyfrekgiUg/43YMI//znP7HZbJw8eZKxY8fSqlUrrrnmmvPu43A4yMzMrKURNnxlZWWqZy25lGvtdBv8KyOff399ikCzif5twrmiiZXiUycorqHPuLKJleycbFzl5WTnZNdQr//r9+ca0CqY911OVu04Rm7eKbo3D+VkjIminEM1MMradyn/91zbVOvaUdt19llos9ls5OTkeF/b7XZsNluVNtnZ2cTFxeFyuSgqKiI6Ovq8+37/Z+PGjUlJSSEjI+OCoS0oKIh27drV1KFd8jIzM1XPWnIp1towDDbuOc7T7+1m//HTpF5lo3tiDGFBNf/jKiQ0lPi4eLJzsomPi6/xfmvCuPh4ln2VxZbDBViDw7i1cQwJMQk10ndtuxT/e64rqnXt8FWdzxUEfXZ5tGPHjhw8eJCsrCycTifp6ekkJydXapOcnMzKlSsBWLNmDT169MBkMpGcnEx6ejpOp5OsrCwOHjxIp06dKCkpobi44nfskpISPv30U5KSknx1CCJSy74+UsCdr25j7OIvcHsMFo+9hsduae+TwOYvzAEmbu2ewLUtY/h4z3HmrN+HYRh1PSwRqQM++0losViYPn0648ePx+12M2LECJKSkpg9ezYdOnSgb9++jBw5kmnTppGSkkJUVBSzZs0CICkpiZtvvpmBAwdiNpuZPn06ZrOZkydPct999wEVT6fecsst9O7d21eHICK1ZEfWKf66YR/rMu1EhQTy2C3tGdMjEaslgCP5mvoiwGRiSOdmWMwmln11BKslgKeGdKiXy3SJiO/49NfXPn360KdPn0rbJk+e7P0+KCiIOXPmnHXf3/3ud/zud7+rtC0hIYF33nmn5gcqIrXO4XLz4S47Sz47yFeH8okMtvCHlCu4+/qWRAQH1vXw6h2TyURax3haNQ1j6eeHcbg8PD+iE2YFN5FLxqV7zUHkEnOhNTx/joggC1GhF57Bv9ztYdt3eazZlcM7/z3GqZJyWsSE8vig9ozqnkD4JXwZtDpMJhO/6d2KJuFBvLxuL06Xh5duvZrABjj1iYhUpZ+QIpeI863h+XP1vqLJOUPbiWIHn+47wbrMXDZ+m0tRmYsgSwCpV8Uxqvtl9GrdRGeLfgKTycSUflcQZDHz/Aff4HR5mHN7F6wWBTeRhk6hTURqTFm5m13HCtmRderMVz5ZeaUANAm3MrBDPP3a27ihTRMtiv4z/e4XrQmyBDBj9W5+u/QrXvlVV4IDVVORhkyhTUQuimEYnDztJCuvhK8O5bE3t5jM7ELK3RVPNsZHBdOlRSPG9Eike8sYOl/WSDfO17B7brgcqyWAR9/eya9f+5KFY7orDIs0YAptIlItLo+Ho/mlHDxxmoMnSzicV0JpuRuAkEAzVydEMe6GVnROaESXFo2wRQbX8YgvDaN7JBJkCeDBtzK4e/E2/nb3Nbo3UKSB0r9sETkrwzA4XuQgM6eIvfYisvJLvGfRmoYHcVWzSBKiQ7ksJoSR3S4jsXFYHY/40jWqewJWSwAP/Pu/3Pm3rSy551oi9QSuSIOj0CYiXoZhcOhkCbuzC8nMLuTkaSdQcanzmpYxtGwcRssmYVXO5OhBgro3pHNzgiwB/P6f2xm9aCuv3XMtjarxRK+I+A+FNhGhoLSc/xzO56tD+eSddmIOMNG6aRg3JDXhyrhIokJ01sYfDOgQz4IxAfx26X+4beHnLB1/HU3Cg+p6WCJSQxTaRC5RHsNgT04RW7/LY4+9CAO4vEkYfa+MpX18JEE/4UlEl9vjs5ULHGfum5PqSb7Sxt/u6s6vX/uS2xZ+zhvjryNW9xeKNAgKbSKXGJfbw3+PnGLT3hMcL3IQGWyhT9umdGsRTeOLPCtTWu5h+/68Gh5phS4tGvmk34bsxqSmLBl7Lfcs+YJbF2xh6fjruCw6tK6HJSI/k0KbyCWixOli057jfLb/BIVlLuKjgrm1ewIdm0fpnrQGqEerxvxj3HXcvXgbw1/5jCVjr6V9s8i6HpaI/AyaQlukgSsrd/O3T77jlws+54NdOTSNCGJsr5ZMvKkNnRMaKbA1YN0So1n+216YA0zcumALn+z1zYoYIlI7dKZNpIEqd3tY/tUR5qzfS3ZBGd0SG3FNYgwtNDXHJaVtXAQr7u3F2MVfcPfibbw4qhPDulxW18MSkYug0CbSwBiGwUff5vJ0eiYHjp+mc0IjZo66msTGoT5be1Tqt/ioEP7925785rWvuP/N/3LsVBn3/qI1JpPOsor4E4U2kQZkX24RM1ZnsmnPcVo1CeP/3dmdfu1iMZlMPnu6U/xDZHAgS+65hgeXZ/Dimm/5NqeI50d00rJXIn5EoU2kAThV4uTldXv5x+eHCLWaeTStHXf2bInVottW5X+CLGZe/mVnrrBFMPPDb9l/vJiFd3aneaOQuh6aiFSDQpuIH3O5Pby+9TCz1u2hsLSc269twQMpV1z01B3S8JlMJu67qQ3t4iOY/M8dDP7LJ8wb3Y1rL4+p66GJyAXo13ARP7Vpz3Funr2Zx9/ZRfv4SNIn3cgzwzoqsEm1JF9p4+2J1xMVGsgd/+9zFm0+gGEYdT0sETkPnWkT8TMHjhfzTHom67/JpUVMKAvGdKN/e5tuKr9E1OTqE0GWAF75VVeeSc/k6fRMPv72OC/f1lnBX6SeUmgT8RMFpeX8Zf1e/r7lIEEWMw/dfCVjr29JkEU3kl9KfLH6xICr4mgUamXNzhwGzN7My7/szPVtmtToZ4jIz6fQJlLPuT0Gb36RxUsffkteiZNbuyXwh9QriI3QepJSM0wmEz1bNWZE1+Y8nZ7J6L9t5Te9W3N/SpJ+KRCpRxTaROqZghInRQ4XAF/mwsT3Pmb/8dNcfVkUL4zsRNu4CJyun36JTAuvy4W0iQ3nnYnX89Tq3cz/eD9rd+fw/IhOdG+phxRE6gOFNpF6psjh4u3tx3jv62x2ZxfSKDSQ269tQYdmkdgLHdgLHRfVrxZel+oItVp4bngnBnSI55EVXzNqwRbu6tmSaaltCQvS/zJE6pL+BYrUI0Vl5byycT9vfpGF2WSiR0IoN3e5nECzHvSW2tXniqZ8eH9vXlzzLX/fcpC1u+08Pqg9KXroRaTOKLSJ1ANuj8Hyr7J4cc0eThQ76NqiEf3bx3G64IQCm9SZsCALTwy+ikFXx/PQW18z4R9f0at1Yx5Na0/7ZpF1PTyRS45Cm0gd23rgJDNW72bXsUK6JUbz3PAOHC9yAnC6oI4HJwJ0S4zhvck38saZiZzT/rKZX3ZP4A/929I0QtODiNQWhTaROpKVV8Jz72fy3tc5NIsKZs7tXRjUKZ6jp0o5XqSF3aV+CTQHcFevlgzt3JzZ6/fy2paDvPPfY9zZsyW/vvFyze0mUgsU2kRq2WmHi1c27uP/bf4Os8nE/f2uYELvVlq4W/xCVGgg0we1Z3SPFsxat5cFm/bz988OMqZnIr++sZXOvIn4kEKbSC1xewxW/OcIL6z5luNFDoZ2bsYfb76S+Cgt1i3+p1XTcP5yexcm923DXzfsY9HmA7y25SCjuiVwV69E2sRG1PUQRRochTaRWrBpz3Gee/8bMrML6ZzQiAVjutG1RXRdD0ukkotZIis40MzU1Lbcek0CS7cc4l9fHOYfnx+ie2I0I7tdRs/WjWkUEkhUqNVHoxa5dCi0ifjQ7mOFPPd+Jpv3niAhJoQ5t3fhlo7xBARoygSpf37uElk3JDWlc4tovjyYx9bv8nhoxdc0Cg1kaOdm3NmzZc0NVOQSpdAm4gPHTpXy0od7WLH9CJHBgTya1o4xPRO1JJA0eOFBFn7RNpYbk5qSmV3ItoN5vLblEEs+O0TbJkHcnhdMWqdmuvdN5CIotInUoMKycl75aD+LP/0OA5hwYyvu/UUbokID63poIrXKHGCiQ/MoOjSPon18BF8eyueNLft54t3dPLl6N50TGpHS3kZKOxttYsM1Ya9INSi0iVyEH64PCuBwuVm14xh//+wQBaXlpF5l49c3tiIuKpgiRzlFjvJq9601QqWhaRIRxPgbW3F9EwfmmMtYszOHtZl2XvjgW1744FsSG4dyY1ITrm/dpOIeON3/JnJWCm0iF6HI4WLTnhO4PB6+OpTPxm+PU1BaTqumYYzukUjzRiHssRezx178k/vWGqHSkF1hi+AKWwS/75tETkEZ6zLtbPgml5X/OcrSzw9jMsFVzSLpcXljuiZG07VFNHFRwXU9bJF6QaFN5CK43B6+OJjHR9/kcqq0nBYxoYzoehmtm4bpMo9INcVFBTO6RyKjeyRS7vaQceQUn+47ySf7TvDa54dY9Ml3ADSLCvYGuK6J0bSLj9D9oXJJUmgT+Qlcbg8rtx/l/9buIbugjMuiQxjapTlJuidH5Jy+n0rEaQk/75QitshghndtzvCuzSl3e9hjL2LX0UJ2Hitk23d5rM7IBsASYKJV0zCusEXQqXkU3S+PoV1cpCaolgZPoU2kGkqdbpZ/lcWiT77j0MkSrrCFk9I+kba2CIU1kQv4fiqR7Jxs4uOMn7RvXFQIcVEh9Gtno6C0nMN5JRw7VcqxU6Vs+CbXG+QCTNAmNpwOzaK4qnkUHZpF0r5ZJBHBeghIGg6FNpHzOFns4LUth/jH54fIO+3k6oRG/GlgO9rFR7B578m6Hp7IJSUqJJCOzaPo2DwKAMMwuDI+gpPFTnYeK2TX0QI+2XeCFduPeve5vEkY7eMrAly7+Ajax0dhiwzSL1vilxTaRM4i48gpXv/8MKv+e5Sycg99r4xlQu9WXHt5DCaT6SfPGi8iNc9kMtE4zIotMpj2zSKh+2VAxS9bFQ8CFbHHXsyOrFOkf53t3a9RSCBtYsNJsoVX/BkbTouYUCzmgEr9RwRZtJKD1CsKbSJnnHa4eOe/x3h96yF2Hi0kJNDM0M7NGXfD5STZtI6iSH10vlUcLm8SzuVNwkm9CsrK3eQUlJFdUEp2QRnZBWXsyDqFy1NxudYSYMIWGUxcVDDxUcHER4UwoltzhTapVxTa5JLmdHnYtOc472YcY+1uOyVON21tEcwYchVDuzQnUvfDiDQIwYFmWjYJo2WTMO82t8fgRLGjIsidqghymdmFfHUoH4D/t/kACTEhFZdX46O8l1ibNwrR5VWpEwptcsk57XDx+YGTfLjLzvs7syksc9EoNJDBVzdjVPfL6NoiWj+QRS4B5jNn12yRwXROqNhmGAZFZS6yC0oJCgzgaH4Zu7ML+XC3HePMMxThQRZan7msmnTmMmtSbEWY07rC4ksKbdJgfb9qgdtjcOB4MdsO5rHtuzz+m1WAy2MQajVzY1IT+rWz0b1lNIFn7mc5eqr0gn1r1QKRhslkMhEZEkhkSCC9Wsd473Mrcbo4cPw0e3OLOXjiNAdPnuajb3JZ/tUR775BlgASG4fSsnEYCTEhNG8UQrNGFX82Cg2s9Mug7peTi+HT0LZp0yaeeeYZPB4Po0aNYsKECZXedzqdPPjgg+zatYtGjRoxa9YsLrus4kbSBQsWsHz5cgICAnj00Ue58cYbq9WnXNo8HoNjBaXsPlbIpr3H+WzfSY6cKsXp8gAQFxlMz1aNSbJFkNg4lEBzAOVugy3nuCfmXLRqgUjDd7b75RqHBdE4LIhuiTFARZg7XuQgt9BBblEZuUUOtn6Xx4e7Ky9dZ7UE0DjMSsyZr+suj+Gq5lHERQYTFxlcJdSJnI3PQpvb7WbGjBksXrwYm83GyJEjSU5Opk2bNt42y5YtIzIykrVr15Kens7MmTN5+eWX2bdvH+np6aSnp2O32xk7dixr1qwBuGCf0rAZhkGRw0VOQVnFV2EZ2afKOHCimH25xRw4fprSM2fBzAEm4iKD6dqiEQnRobRqGk5UiO5RE5GaE2q1kNjYQmLjsErby90e8k87yTvt5ORpJ3klTvKKneQWOvg2p4jNe09Uah9kCah4ECIyGFtUMHGRQdgig2kaEUR0qJXoUCuNQgOJDrMSZjUr4F2ifBbaMjIySExMJCGh4kaBtLQ01q9fXylgbdiwgYkTJwKQmprKjBkzMAyD9evXk5aWhtVqJSEhgcTERDIyMgAu2Gd9YxgGhgEew8DgzJ8GFV8YeIyKNh4D+FE7l9ug3O2h3O3B5TFwuir+9G7zvm+cafOD73/wnutM+3LP99//qI3nB23cBi5PxXsAJhOYMOH2GLjP3NDhKi/H+nE+pjMNTFRMbBkQYCLA9P3XD1+D2WQiIMCE6QffB5ggwGQiyBKAOSAAp9tDuatiHE63B6fLwOFyU1TmorCsnMJSF4Wl5Tjdnip1bt4ohNax4Vx3eWNax4bR1hZBdGggW7/Lr6W/aRGR/wk0BxAbGUxsZNV1Uz2GQbv4iifScwoc5BSWYS/83y+iGUdO8WFBGQ5X1Z91FX2baBRqJTo0kEahVqJCAgm1mgm1Wgizmgm1mikuOMXlpw4SarUQajUTbDUTGBBAoNmExRyA1RyAxWwi0FyxLfDM64rtAQSc+dlvMv3v/wOmMz+zTZzZpuBY63wW2ux2O3Fxcd7XNpvNG7x+2CY+Pr5iIBYLERER5OfnY7fbufrqqyvta7fbAS7YZ11YtPkAL6759uxBrB7x/sMM+P4fauV/tJaA//3j/f5mWsMDBh7Kyj0UlpZjUHFZOzCw4mzW94foDaY/+PPHtThXgA0wmQg0m7BaKsb0/Z/ffx8ZbKF5dAhRIYFEBgdWzMsUFey9rBAbGURwYNXlazSXmojURwGmigcgLosOPWcbwzAoKC3nRLGTUyVO8kvKyS+p+D7vdPmZbRXbs/JKKC13c9rhptTp4rTzzD23X/202z4uxtmCXNPwIN6bfKOubPjAJfEggsPhIDMz02f9X98Erv9VS5/1Lz9kAI6Kr7ICTpfBd7nnbt0l0kfDOHW6VvruEhkJnK7xfmucn/ddo3X+Qb8+4Y99+6rOP+jbJ3zYd1HOaTJzqtc2DAgzwWVhZ140BQg881U/HTu4j2N1PYha4ot84XA4zrrdZ6HNZrORk/O//yLtdjs2m61Km+zsbOLi4nC5XBQVFREdHX3efS/U59l07tz5Zx6NiIiISN0KuHCTi9OxY0cOHjxIVlYWTqeT9PR0kpOTK7VJTk5m5cqVAKxZs4YePXpgMplITk4mPT0dp9NJVlYWBw8epFOnTtXqU0RERKQh8tmZNovFwvTp0xk/fjxut5sRI0aQlJTE7Nmz6dChA3379mXkyJFMmzaNlJQUoqKimDVrFgBJSUncfPPNDBw4ELPZzPTp0zGbK+5ZOlufIiIiIg2dyTCMena7vIiIiIj8mM8uj4qIiIhIzVFoExEREfEDCm1yXs8//zwDBgxg0KBB3HfffRQWFnrfW7BgASkpKaSmprJ582bv9k2bNpGamkpKSgoLFy6si2H7nffff5+0tDSuvPJKvv7660rvqc6+pTrWnIcffpiePXtyyy23eLedOnWKsWPH0r9/f8aOHUtBQQFQMQ/Z008/TUpKCoMGDWLXrl11NWy/k52dzZgxYxg4cCBpaWn8/e9/B1RrX3A4HIwcOZLBgweTlpbGnDlzAMjKymLUqFGkpKQwZcoUnE4nUDGP6ZQpU0hJSWHUqFEcOXLkfN3/dIbIeWzevNkoLy83DMMwXnjhBeOFF14wDMMw9u7dawwaNMhwOBzG4cOHjb59+xoul8twuVxG3759jcOHDxsOh8MYNGiQsXfv3ro8BL+wb98+Y//+/cbo0aONjIwM73bV2bdUx5q1bds2Y+fOnUZaWpp32/PPP28sWLDAMAzDWLBggfdnyMaNG41x48YZHo/H2L59uzFy5Mg6GbM/stvtxs6dOw3DMIyioiKjf//+xt69e1VrH/B4PEZxcbFhGIbhdDqNkSNHGtu3bzcmTZpkrF692jAMw3jssceM119/3TAMw1i6dKnx2GOPGYZhGKtXrzYmT55co+PRmTY5rxtuuAGLpeIh486dO3vnyTvXUmM/XL7MarV6lxqT82vdujWtWrWqsl119i3VsWZdc801REVFVdq2fv16hg4dCsDQoUNZt25dpe0mk4nOnTtTWFhIbu55ZsoWr9jYWK666ioAwsPDadWqFXa7XbX2AZPJRFhYxbqyLpcLl8uFyWTi888/JzU1FYBhw4Z5f25s2LCBYcOGARXLc27ZsgWjBp/3VGiTanvrrbfo3bs3cPZlyux2+zm3y8VRnX1LdfS9kydPEhsbC0DTpk05efIkULX2cXFxqv1FOHLkCJmZmVx99dWqtY+43W6GDBlCr1696NWrFwkJCURGRnpPaPywnudanrOmXBLLWMn53X333Zw4caLK9ilTptCvXz8A5s2bh9lsZvDgwbU9vAajOnUWachMJpMWGa9Bp0+fZtKkSTzyyCOEh4dXek+1rjlms5lVq1ZRWFjIfffdx4EDB+psLAptwpIlS877/ooVK9i4cSNLlizx/hCo6aXGLgUXqvPZqM6+VZ3l9uTnady4Mbm5ucTGxpKbm0tMTAxQtfY5OTmq/U9QXl7OpEmTGDRoEP379wdUa1+LjIzkuuuuY8eOHRQWFuJyubBYLJXqea7lOWuKLo/KeW3atIlFixYxb948QkJCvNu11FjtUJ19S3X0veTkZN5++20A3n77bfr27Vtpu2EY7Nixg4iICO+lPTk/wzD405/+RKtWrRg7dqx3u2pd8/Ly8ryzJpSVlfHZZ5/RunVrrrvuOtasWQPAypUrvT83zrU8Z03RighyXikpKTidTho1agTA1VdfzYwZM4CKS6ZvvfUWZrOZRx55hD59+gDw8ccf8+yzz3qXGvvd735XV8P3G2vXruWpp54iLy+PyMhI2rVrx9/+9jdAdfY11bHmPPDAA2zbto38/HwaN27M73//e/r168eUKVPIzs6mWbNmvPzyyzRq1AjDMJgxYwabN28mJCSEZ599lo4dO9b1IfiFL7/8kl/96ldcccUVBARUnHt54IEH6NSpk2pdw7755hseeugh3G43hmEwYMAAJk6cSFZWFvfffz8FBQW0a9eOmTNnYrVacTgcTJs2jczMTO/ynAkJCTU2HoU2ERERET+gy6MiIiIifkChTURERMQPKLSJiIiI+AGFNhERERE/oNAmIiIi4gcU2kRERET8gEKbiIiIiB9QaBMRERHxA/8f4DM8w+9l2SMAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 720x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax2 = plt.subplots(figsize=(10, 5))\n",
    "fig, ax4 = plt.subplots(figsize=(10, 5))\n",
    "\n",
    "ax4 = plt.subplot(sharex = ax2, sharey=ax2)\n",
    "sns.distplot(train_predict.squeeze()- y_train_rescaled, ax=ax2)\n",
    "ax2.set_title('Training Error')\n",
    "ax2.text(x=.03, y=.92, s=f'Train RMSE ={train_rmse}', transform=ax2.transAxes)\n",
    "sns.distplot(test_predict.squeeze()-y_test_rescaled, ax=ax4)\n",
    "ax4.set_title('Testing Error')\n",
    "ax4.text(x=.03, y=.92, s=f'Test RMSE ={test_rmse}', transform=ax4.transAxes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "pbiKgqxk5Nki",
   "metadata": {
    "id": "pbiKgqxk5Nki"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "dr5p7KTQh8Ms",
   "metadata": {
    "id": "dr5p7KTQh8Ms"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "LLgCrv8v5KTx",
   "metadata": {
    "id": "LLgCrv8v5KTx"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cIhiwZZKiAE8",
   "metadata": {
    "id": "cIhiwZZKiAE8"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "provenance": []
  },
  "gpuClass": "standard",
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}