{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "id": "K-7t0SXgWkh_" }, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "from sklearn.ensemble import RandomForestRegressor" ] }, { "cell_type": "code", "source": [ "data = pd.read_csv(\"DOGE-USD.csv\")\n", "data.head()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "zoONnED6XLhO", "outputId": "6cf83bf9-137f-46e7-882f-2248fd3253aa" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " Date Open High Low Close Adj Close Volume\n", "0 2017-11-09 0.001207 0.001415 0.001181 0.001415 0.001415 6259550.0\n", "1 2017-11-10 0.001421 0.001431 0.001125 0.001163 0.001163 4246520.0\n", "2 2017-11-11 0.001146 0.001257 0.001141 0.001201 0.001201 2231080.0\n", "3 2017-11-12 0.001189 0.001210 0.001002 0.001038 0.001038 3288960.0\n", "4 2017-11-13 0.001046 0.001212 0.001019 0.001211 0.001211 2481270.0" ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
DateOpenHighLowCloseAdj CloseVolume
02017-11-090.0012070.0014150.0011810.0014150.0014156259550.0
12017-11-100.0014210.0014310.0011250.0011630.0011634246520.0
22017-11-110.0011460.0012570.0011410.0012010.0012012231080.0
32017-11-120.0011890.0012100.0010020.0010380.0010383288960.0
42017-11-130.0010460.0012120.0010190.0012110.0012112481270.0
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "data", "summary": "{\n \"name\": \"data\",\n \"rows\": 1761,\n \"fields\": [\n {\n \"column\": \"Date\",\n \"properties\": {\n \"dtype\": \"object\",\n \"num_unique_values\": 1761,\n \"samples\": [\n \"2020-07-02\",\n \"2022-01-11\",\n \"2022-03-08\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Open\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.1013253618925643,\n \"min\": 0.001046,\n \"max\": 0.687801,\n \"num_unique_values\": 1534,\n \"samples\": [\n 0.11649,\n 0.007702,\n 0.005867\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"High\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.10915168814418758,\n \"min\": 0.00121,\n \"max\": 0.737567,\n \"num_unique_values\": 1537,\n \"samples\": [\n 0.329356,\n 0.007763,\n 0.00591\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Low\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.09369549203918358,\n \"min\": 0.001002,\n \"max\": 0.608168,\n \"num_unique_values\": 1526,\n \"samples\": [\n 0.079082,\n 0.006473,\n 0.056435\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Close\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.10137868294094772,\n \"min\": 0.001038,\n \"max\": 0.684777,\n \"num_unique_values\": 1543,\n \"samples\": [\n 0.06428,\n 0.286808,\n 0.221383\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Adj Close\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.10137868294094772,\n \"min\": 0.001038,\n \"max\": 0.684777,\n \"num_unique_values\": 1543,\n \"samples\": [\n 0.06428,\n 0.286808,\n 0.221383\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Volume\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3563999366.5691385,\n \"min\": 1431720.0,\n \"max\": 69410680685.0,\n \"num_unique_values\": 1760,\n \"samples\": [\n 52702701.0,\n 53434717.0,\n 1166163984.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 5 } ] }, { "cell_type": "code", "source": [ "data.corr(numeric_only=True)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 237 }, "id": "S6nEYDttXNMH", "outputId": "0082f5c5-e72e-4275-ae18-dab3bb830cc8" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " Open High Low Close Adj Close Volume\n", "Open 1.000000 0.993904 0.993707 0.992514 0.992514 0.554850\n", "High 0.993904 1.000000 0.986497 0.995104 0.995104 0.619321\n", "Low 0.993707 0.986497 1.000000 0.994575 0.994575 0.519991\n", "Close 0.992514 0.995104 0.994575 1.000000 1.000000 0.588678\n", "Adj Close 0.992514 0.995104 0.994575 1.000000 1.000000 0.588678\n", "Volume 0.554850 0.619321 0.519991 0.588678 0.588678 1.000000" ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
OpenHighLowCloseAdj CloseVolume
Open1.0000000.9939040.9937070.9925140.9925140.554850
High0.9939041.0000000.9864970.9951040.9951040.619321
Low0.9937070.9864971.0000000.9945750.9945750.519991
Close0.9925140.9951040.9945751.0000001.0000000.588678
Adj Close0.9925140.9951040.9945751.0000001.0000000.588678
Volume0.5548500.6193210.5199910.5886780.5886781.000000
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "summary": "{\n \"name\": \"data\",\n \"rows\": 6,\n \"fields\": [\n {\n \"column\": \"Open\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.1795194922860817,\n \"min\": 0.5548501036665978,\n \"max\": 1.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.9939040886453381,\n 0.5548501036665978,\n 0.9937074710789932\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"High\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.1530736580860577,\n \"min\": 0.6193209330200544,\n \"max\": 1.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.0,\n 0.6193209330200544,\n 0.9864972127200397\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Low\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.1935088349502361,\n \"min\": 0.5199906711621949,\n \"max\": 1.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.9864972127200397,\n 0.5199906711621949,\n 1.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Close\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.16649536220616812,\n \"min\": 0.5886775590054238,\n \"max\": 1.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.9951037913391725,\n 0.5886775590054238,\n 0.994574902415878\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Adj Close\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.16649536220616812,\n \"min\": 0.5886775590054238,\n \"max\": 1.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.9951037913391725,\n 0.5886775590054238,\n 0.994574902415878\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Volume\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.17707783703525545,\n \"min\": 0.5199906711621949,\n \"max\": 1.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.6193209330200544,\n 1.0,\n 0.5199906711621949\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 6 } ] }, { "cell_type": "code", "source": [ "data['Date'] = pd.to_datetime(data['Date'],\n", "\t\t\t\t\t\t\tinfer_datetime_format=True)\n", "data.set_index('Date', inplace=True)\n", "\n", "data.isnull().any()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "c1Cv9T_YXOlE", "outputId": "3256287f-75c8-458a-d193-e6b6c27e7a6d" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ ":1: UserWarning: The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", " data['Date'] = pd.to_datetime(data['Date'],\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "Open True\n", "High True\n", "Low True\n", "Close True\n", "Adj Close True\n", "Volume True\n", "dtype: bool" ] }, "metadata": {}, "execution_count": 7 } ] }, { "cell_type": "code", "source": [ "data.isnull().sum()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "7w-qZbhRXP3t", "outputId": "03523084-142d-44c9-cb43-11d7402d7921" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Open 1\n", "High 1\n", "Low 1\n", "Close 1\n", "Adj Close 1\n", "Volume 1\n", "dtype: int64" ] }, "metadata": {}, "execution_count": 8 } ] }, { "cell_type": "code", "source": [ "data = data.dropna()" ], "metadata": { "id": "K33zcNvaXRBj" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "data.describe()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 320 }, "id": "Wv7htK41XR-x", "outputId": "275b13d0-981c-44a3-89ac-b493065a1e21" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " Open High Low Close Adj Close \\\n", "count 1760.000000 1760.000000 1760.000000 1760.000000 1760.000000 \n", "mean 0.059575 0.063096 0.056126 0.059619 0.059619 \n", "std 0.101325 0.109152 0.093695 0.101379 0.101379 \n", "min 0.001046 0.001210 0.001002 0.001038 0.001038 \n", "25% 0.002550 0.002616 0.002500 0.002548 0.002548 \n", "50% 0.003476 0.003603 0.003356 0.003495 0.003495 \n", "75% 0.070633 0.075035 0.068478 0.070657 0.070657 \n", "max 0.687801 0.737567 0.608168 0.684777 0.684777 \n", "\n", " Volume \n", "count 1.760000e+03 \n", "mean 1.016258e+09 \n", "std 3.563999e+09 \n", "min 1.431720e+06 \n", "25% 2.307671e+07 \n", "50% 8.981855e+07 \n", "75% 6.565853e+08 \n", "max 6.941068e+10 " ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
OpenHighLowCloseAdj CloseVolume
count1760.0000001760.0000001760.0000001760.0000001760.0000001.760000e+03
mean0.0595750.0630960.0561260.0596190.0596191.016258e+09
std0.1013250.1091520.0936950.1013790.1013793.563999e+09
min0.0010460.0012100.0010020.0010380.0010381.431720e+06
25%0.0025500.0026160.0025000.0025480.0025482.307671e+07
50%0.0034760.0036030.0033560.0034950.0034958.981855e+07
75%0.0706330.0750350.0684780.0706570.0706576.565853e+08
max0.6878010.7375670.6081680.6847770.6847776.941068e+10
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "summary": "{\n \"name\": \"data\",\n \"rows\": 8,\n \"fields\": [\n {\n \"column\": \"Open\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 622.207219273755,\n \"min\": 0.001046,\n \"max\": 1760.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 0.05957455113636363,\n 0.0034765,\n 1760.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"High\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 622.20389855925,\n \"min\": 0.00121,\n \"max\": 1760.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 0.06309564886363636,\n 0.0036035,\n 1760.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Low\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 622.2119111547513,\n \"min\": 0.001002,\n \"max\": 1760.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 0.05612605625,\n 0.003356,\n 1760.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Close\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 622.2073650083192,\n \"min\": 0.001038,\n \"max\": 1760.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 0.05961943125000001,\n 0.0034945,\n 1760.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Adj Close\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 622.2073650083192,\n \"min\": 0.001038,\n \"max\": 1760.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 0.05961943125000001,\n 0.0034945,\n 1760.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Volume\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 24299765885.19182,\n \"min\": 1760.0,\n \"max\": 69410680685.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 1016258030.427841,\n 89818547.5,\n 1760.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 10 } ] }, { "cell_type": "code", "source": [ "plt.figure(figsize=(20, 7))\n", "x = data.groupby('Date')['Close'].mean()\n", "x.plot(linewidth=2.5, color='b')\n", "plt.xlabel('Date')\n", "plt.ylabel('Volume')\n", "plt.title(\"Date vs Close of 2021\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 258 }, "id": "NUabDOA8XTFH", "outputId": "99104e42-5e8a-4f62-c063-c49de891f64c" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Text(0.5, 1.0, 'Date vs Close of 2021')" ] }, "metadata": {}, "execution_count": 11 }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "iVBORw0KGgoAAAANSUhEUgAABlUAAAJBCAYAAADfmDO9AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAACalUlEQVR4nOzdd3iT5f7H8U+6aYECAgVqAdmiQj0gCCo4UBQc6FFwgj2KR8XjQNHD8QiiKE7kqCiI4gA9ojiPA1EUJ4oCDhRRlA0tu2V15/fH/UuTJ6tJmzSj79d15eqz8uSbNG3afPK9b5vdbrcLAAAAAAAAAAAAfiVEugAAAAAAAAAAAIBYQKgCAAAAAAAAAAAQAEIVAAAAAAAAAACAABCqAAAAAAAAAAAABIBQBQAAAAAAAAAAIACEKgAAAAAAAAAAAAEgVAEAAAAAAAAAAAgAoQoAAAAAAAAAAEAACFUAAAAAAAAAAAACQKgCAAAAIC7ZbDbdeeedkS6jVsrLy3XrrbcqJydHCQkJGjZsWKRLAgAAAOo1QhUAAAAgCj333HOy2WxVl7S0NLVp00aDBw/Wo48+qr1799b43F999ZXuvPNO7dmzJ3QF16Hvv/9el156qXJycpSamqpmzZpp0KBBevbZZ1VRURHp8kJq9uzZevDBB3X++efr+eef10033eT1uMrKSj333HM6++yzlZOTo4yMDB155JGaPHmyiouLvV7nmWee0eGHH660tDR17txZjz32mMcxr7/+ukaMGKEOHTooPT1dXbt21c033+z1uTNv3jxdeuml6ty5s2w2m0488cTa3HUAAAAgKiVFugAAAAAAvt1111067LDDVFZWpvz8fC1evFg33nijpk6dqrfffls9evQI+pxfffWVJk2apMsvv1xNmjQJfdFh9PTTT+vqq69WVlaWLrvsMnXu3Fl79+7VokWLdMUVV2jr1q3617/+FekyQ+bjjz9Wdna2HnnkEb/HHThwQHl5eTr22GN19dVXq2XLllqyZIkmTpyoRYsW6eOPP5bNZqs6fubMmbr66qv117/+VWPHjtXnn3+u66+/XgcOHNBtt91WddxVV12lNm3a6NJLL1Xbtm31008/6fHHH9d7772n5cuXq0GDBlXHPvnkk1q2bJmOOeYY7dy5M/QPBgAAABAFCFUAAACAKHbGGWeod+/eVevjx4/Xxx9/rDPPPFNnn322Vq1aZXljO559/fXXuvrqq9WvXz+99957atSoUdW+G2+8Ud99951WrlwZwQpDb9u2bQEFXykpKfryyy/Vv3//qm2jR49W+/btq4KVQYMGSZIOHjyo22+/XUOHDtX8+fOrjq2srNTdd9+tq666Sk2bNpUkzZ8/36PjpFevXho1apRefPFFXXnllVXb58yZo+zsbCUkJOjII4+s5T0HAAAAohPDfwEAAAAx5uSTT9Ydd9yh9evXa+7cuVXbf/zxR11++eXq0KGD0tLS1KpVK/3tb3+zdA3ceeedGjdunCTpsMMOqxpebN26dVXHzJ07V7169VKDBg3UrFkzXXjhhdq4caPfmubPny+bzaZPP/3UY9/MmTNls9mqAo/8/Hzl5eXp0EMPVWpqqlq3bq1zzjnHUoM3kyZNks1m04svvmgJVBx69+6tyy+/3O85VqxYoTPOOEONGzdWw4YNdcopp+jrr7+2HFNWVqZJkyapc+fOSktL0yGHHKLjjz9eH374oeW4X3/9Veeff76aNWumtLQ09e7dW2+//bbf23fYv3+/br755qohzLp27aqHHnpIdrtdkrRu3TrZbDZ98skn+vnnn6u+T4sXL/Z6vpSUFEug4nDuuedKklatWlW17ZNPPtHOnTt17bXXWo4dM2aM9u/fr3fffbdqm7chvLydU1LVvC8AAABAPOMvXgAAACAGXXbZZZKkhQsXVm378MMP9eeffyovL0+PPfaYLrzwQr388ssaMmRI1Zv15513ni666CJJ0iOPPKI5c+Zozpw5atGihSTpnnvu0ciRI9W5c2dNnTpVN954oxYtWqQBAwb4nYNl6NChatiwoV555RWPffPmzdMRRxxR1b3w17/+VW+88Yby8vL0xBNP6Prrr9fevXu1YcMGn+c/cOBAVR1t27YN7sH6fz///LNOOOEE/fDDD7r11lt1xx13aO3atTrxxBP1zTffVB135513atKkSTrppJP0+OOP6/bbb1fbtm21fPlyy7mOPfZYrVq1Sv/85z/18MMPKyMjQ8OGDdMbb7zhtw673a6zzz5bjzzyiE4//XRNnTpVXbt21bhx4zR27FhJUosWLTRnzhx169ZNhx56aNX36fDDDw/qPufn50uSmjdvXrVtxYoVkmTpgJJMB0pCQkLV/mDOCQAAANQbdgAAAABR59lnn7VLsn/77bc+j8nMzLQfffTRVesHDhzwOOa///2vXZL9s88+q9r24IMP2iXZ165dazl23bp19sTERPs999xj2f7TTz/Zk5KSPLa7u+iii+wtW7a0l5eXV23bunWrPSEhwX7XXXfZ7Xa7fffu3XZJ9gcffNDvudz98MMPdkn2G264IeDrSLJPnDixan3YsGH2lJQU+x9//FG1bcuWLfZGjRrZBwwYULWtZ8+e9qFDh/o99ymnnGI/6qij7MXFxVXbKisr7f3797d37tzZ73XffPNNuyT75MmTLdvPP/98u81ms69Zs6Zq28CBA+1HHHGE3/P5M2jQIHvjxo3tu3fvrto2ZswYe2JiotfjW7RoYb/wwgv9nvOKK66wJyYm2n/77TefxxxxxBH2gQMH1qRkAAAAIKrRqQIAAADEqIYNG2rv3r1V665zqxQXF2vHjh069thjJcnSZeHL66+/rsrKSg0fPlw7duyourRq1UqdO3fWJ5984vf6I0aM0LZt2yxDVM2fP1+VlZUaMWJEVY0pKSlavHixdu/eHfB9LSoqkiSvw34FoqKiQgsXLtSwYcPUoUOHqu2tW7fWxRdfrC+++KLqNpo0aaKff/5Zv//+u9dz7dq1Sx9//LGGDx+uvXv3Vj1OO3fu1ODBg/X7779r8+bNPmt57733lJiYqOuvv96y/eabb5bdbtf7779fo/vo7t5779VHH32k++67zzIvy8GDB5WSkuL1OmlpaTp48KDPc7700kt65plndPPNN6tz584hqRMAAACIJYQqAAAAQIzat2+fJWTYtWuXbrjhBmVlZalBgwZq0aKFDjvsMElSYWFhtef7/fffZbfb1blzZ7Vo0cJyWbVqlbZt2+b3+qeffroyMzM1b968qm3z5s1Tbm6uunTpIklKTU3V/fffr/fff19ZWVkaMGCAHnjggaohpXxp3LixJFlCpGBs375dBw4cUNeuXT32HX744aqsrKyaN+auu+7Snj171KVLFx111FEaN26cfvzxx6rj16xZI7vdrjvuuMPjcZo4caIk+X2s1q9frzZt2ngERI6hvdavX1+j++hq3rx5+ve//60rrrhC11xzjWVfgwYNVFpa6vV6xcXFlnDO1eeff64rrrhCgwcP1j333FPrGgEAAIBYlBTpAgAAAAAEb9OmTSosLFSnTp2qtg0fPlxfffWVxo0bp9zcXDVs2FCVlZU6/fTTVVlZWe05KysrZbPZ9P777ysxMdFjf8OGDf1ePzU1tWpOkSeeeEIFBQX68ssvde+991qOu/HGG3XWWWfpzTff1AcffKA77rhDU6ZM0ccff6yjjz7a67k7deqkpKQk/fTTT9Xej9oaMGCA/vjjD7311ltauHChnn76aT3yyCOaMWOGrrzyyqrH8pZbbtHgwYN91hspH374oUaOHKmhQ4dqxowZHvtbt26tiooKbdu2TS1btqzaXlpaqp07d6pNmzYe1/nhhx909tln68gjj9T8+fOVlMS/kgAAAKif+EsYAAAAiEFz5syRpKo39Xfv3q1FixZp0qRJmjBhQtVx3oawstlsXs/ZsWNH2e12HXbYYVWdJcEaMWKEnn/+eS1atEirVq2S3W6vGvrL/bZuvvlm3Xzzzfr999+Vm5urhx9+WHPnzvV63vT0dJ188sn6+OOPtXHjRuXk5ARVV4sWLZSenq7Vq1d77Pv111+VkJBgOWezZs2Ul5envLw87du3TwMGDNCdd96pK6+8smr4sOTkZA0aNCioOiSpXbt2+uijj7R3715Lt8qvv/5atb+mvvnmG5177rnq3bu3XnnlFa/hR25uriTpu+++05AhQ6q2f/fdd6qsrKza7/DHH3/o9NNPV8uWLfXee+9VG64BAAAA8YzhvwAAAIAY8/HHH+vuu+/WYYcdpksuuUSSqjpL7Ha75dhp06Z5XD8jI0OStGfPHsv28847T4mJiZo0aZLHeex2u3bu3FltbYMGDVKzZs00b948zZs3T3369KkagkySDhw4oOLiYst1OnbsqEaNGqmkpMTvuSdOnCi73a7LLrtM+/bt89i/bNkyPf/8816vm5iYqNNOO01vvfWW1q1bV7W9oKBAL730ko4//viqIcbc72fDhg3VqVOnqvpatmypE088UTNnztTWrVs9bmv79u1+78eQIUNUUVGhxx9/3LL9kUcekc1m0xlnnOH3+r6sWrVKQ4cOVfv27fXOO+/4HMbr5JNPVrNmzfTkk09atj/55JNKT0/X0KFDq7bl5+frtNNOU0JCgj744AO1aNGiRrUBAAAA8YJOFQAAACCKvf/++/r1119VXl6ugoICffzxx/rwww/Vrl07vf3220pLS5Nk5hxxzE9SVlam7OxsLVy4UGvXrvU4Z69evSRJt99+uy688EIlJyfrrLPOUseOHTV58mSNHz9e69at07Bhw9SoUSOtXbtWb7zxhq666irdcsstfutNTk7Weeedp5dffln79+/XQw89ZNn/22+/6ZRTTtHw4cPVvXt3JSUl6Y033lBBQYEuvPBCv+fu37+/pk+frmuvvVbdunXTZZddps6dO2vv3r1avHix3n77bU2ePNnn9SdPnqwPP/xQxx9/vK699lolJSVp5syZKikp0QMPPFB1XPfu3XXiiSeqV69eatasmb777jvNnz9f1113XdUx06dP1/HHH6+jjjpKo0ePVocOHVRQUKAlS5Zo06ZN+uGHH3zWcdZZZ+mkk07S7bffrnXr1qlnz55auHCh3nrrLd14443q2LGj38fBm71792rw4MHavXu3xo0bp3fffdeyv2PHjurXr58kM6fK3XffrTFjxuiCCy7Q4MGD9fnnn2vu3Lm655571KxZs6rrnX766frzzz9166236osvvtAXX3xRtS8rK0unnnpq1fpnn32mzz77TJIJlvbv31/1/RgwYIAGDBgQ9P0CAAAAoo4dAAAAQNR59tln7ZKqLikpKfZWrVrZTz31VPt//vMfe1FRkcd1Nm3aZD/33HPtTZo0sWdmZtovuOAC+5YtW+yS7BMnTrQce/fdd9uzs7PtCQkJdkn2tWvXVu177bXX7Mcff7w9IyPDnpGRYe/WrZt9zJgx9tWrVwdU+4cffmiXZLfZbPaNGzda9u3YscM+ZswYe7du3ewZGRn2zMxMe9++fe2vvPJKwI/NsmXL7BdffLG9TZs29uTkZHvTpk3tp5xyiv3555+3V1RUVB3n7X4vX77cPnjwYHvDhg3t6enp9pNOOsn+1VdfWY6ZPHmyvU+fPvYmTZrYGzRoYO/WrZv9nnvusZeWllqO++OPP+wjR460t2rVyp6cnGzPzs62n3nmmfb58+dXex/27t1rv+mmm6ruQ+fOne0PPvigvbKy0nLcwIED7UcccUS151u7dq3l+eJ+GTVqlMd1nnrqKXvXrl3tKSkp9o4dO9ofeeQRj9v3d86BAwdajp04caLPY92/DwAAAECsstntbn39AAAAAAAAAAAA8MCcKgAAAAAAAAAAAAEgVAEAAAAAAAAAAAgAoQoAAAAAAAAAAEAACFUAAAAAAAAAAAACQKgCAAAAAAAAAAAQAEIVAAAAAAAAAACAACRFuoC6VllZqS1btqhRo0ay2WyRLgcAAAAAAAAAAESQ3W7X3r171aZNGyUk+O9FqXehypYtW5STkxPpMgAAAAAAAAAAQBTZuHGjDj30UL/H1LtQpVGjRpLMg9O4ceMIVwMAAAAAAAAAACKpqKhIOTk5VfmBP/UuVHEM+dW4cWNCFQAAAAAAAAAAIEkBTRnCRPUAAAAAAAAAAAABIFQBAAAAAAAAAAAIAKEKAAAAAAAAAABAAAhVAAAAAAAAAAAAAkCoAgAAAAAAAAAAEICoCFWmT5+u9u3bKy0tTX379tXSpUt9HnviiSfKZrN5XIYOHVqHFQMAAAAAAAAAgPom4qHKvHnzNHbsWE2cOFHLly9Xz549NXjwYG3bts3r8a+//rq2bt1adVm5cqUSExN1wQUX1HHlAAAAAAAAAACgPol4qDJ16lSNHj1aeXl56t69u2bMmKH09HTNnj3b6/HNmjVTq1atqi4ffvih0tPTCVUAAAAAAAAAAEBYRTRUKS0t1bJlyzRo0KCqbQkJCRo0aJCWLFkS0DmeeeYZXXjhhcrIyPC6v6SkREVFRZYLAAAAAAAAAABAsCIaquzYsUMVFRXKysqybM/KylJ+fn6111+6dKlWrlypK6+80ucxU6ZMUWZmZtUlJyen1nUDAAAAAAAAAID6J+LDf9XGM888o6OOOkp9+vTxecz48eNVWFhYddm4cWMdVggAAAAAAAAAAOJFUiRvvHnz5kpMTFRBQYFle0FBgVq1auX3uvv379fLL7+su+66y+9xqampSk1NrXWtAAAAAAAAAACgfotop0pKSop69eqlRYsWVW2rrKzUokWL1K9fP7/XffXVV1VSUqJLL7003GUCAAAAAAAAAABEtlNFksaOHatRo0apd+/e6tOnj6ZNm6b9+/crLy9PkjRy5EhlZ2drypQplus988wzGjZsmA455JBIlA0AAAAAAAAAAOqZiIcqI0aM0Pbt2zVhwgTl5+crNzdXCxYsqJq8fsOGDUpIsDbUrF69Wl988YUWLlwYiZIBAAAAAAAAAEA9ZLPb7fZIF1GXioqKlJmZqcLCQjVu3DjS5QAAAAAAAAAAgAgKJjeI6JwqAAAAAAAACC+7Xdq3z3wFAAC1Q6gCAAAAAAAQp+x26fzzpUaNpKFDpcrKSFcEAEBsI1QBAAAAAACIU19+Kb3+ull+/33p3XcjWw8AALGOUAUAAAAAACBOff+9dX3JkoiUAQBA3CBUAQAAAAAAiFOJidb18vLI1AEAQLwgVAEAAAAAAIhTSUnWdUIVAABqh1AFAAAAAAAgThGqAAAQWoQqAAAAAAAAccp9+K+KisjUAQBAvCBUAQAAAAAAiFN0qgAAEFqEKgAAAAAAAHGKieoBAAgtQhUAAAAAAIA4xfBfAACEFqEKAAAAAABAPUGoAgBA7RCqAAAAAAAAxCn3EIXhvwAAqB1CFQAAAAAAgDjlHqrQqQIAQO0QqgAAAAAAAMQpOlUAAAgtQhUAAAAAAIA4RagCAEBoEaoAAAAAAADEKUIVAABCi1AFAAAAAAAgTjGnCgAAoUWoAgAAAAAAEIe+/Vb6+9+t2+hUAQCgdghVAAAAAAAA4tDw4Z7b6FQBAKB2CFUAAAAAAADi0Lp1ntsIVQAAqB1CFQAAAAAAgHqC4b8AAKgdQhUAAAAAAIB6glAFAIDaIVQBAAAAAACoJwhVAACoHUIVAAAAAACAeqK0NNIVAAAQ2whVAAAAAAAA6omSkkhXAABAbCNUAQAAAAAAqCfoVAEAoHYIVQAAAAAAAOoJOlUAAKgdQhUAAAAAAIB6glAFAIDaIVQBAAAAAACoJxj+CwCA2iFUAQAAAAAAqCfoVAEAoHYIVQAAAAAAAOqJykqpvDzSVQAAELsIVQAAAAAAAOoRhgADAKDmCFUAAAAAAADqEYYAAwCg5ghVAAAAAAAA6hGG/wIAoOYIVQAAAAAAAOqRsrJIVwAAQOwiVAEAAAAAAIgzdrvvfYQqAADUHKEKAAAAAABAnKms9L2PUAUAgJojVAEAAAAAAIgzFRW+9xGqAABQc4QqAAAAAAAAcYZQBQCA8CBUAQAAAAAAiDOEKgAAhAehCgAAAAAAQJxhThUAAMKDUAUAAAAAACDO+OtUKS+vuzoAAIg3hCoAAAAAAABxhuG/AAAID0IVAAAAAACAOEOoAgBAeBCqAAAAAAAAxBlCFQAAwoNQBQAAAAAAIM4wUT0AAOFBqAIAAAAAABBn6FQBACA8CFUAAAAAAADiDKEKAADhQagCAAAAAAAQZwhVAAAID0IVAAAAAACAOMOcKgAAhAehCgAAAAAAQJzx16lSXl53dQAAEG8iHqpMnz5d7du3V1pamvr27aulS5f6PX7Pnj0aM2aMWrdurdTUVHXp0kXvvfdeHVULAAAAAAAQ/Rj+CwCA8EiK5I3PmzdPY8eO1YwZM9S3b19NmzZNgwcP1urVq9WyZUuP40tLS3XqqaeqZcuWmj9/vrKzs7V+/Xo1adKk7osHAAAAAACIUoQqAACER0RDlalTp2r06NHKy8uTJM2YMUPvvvuuZs+erX/+858ex8+ePVu7du3SV199peTkZElS+/bt67JkAAAAAACAqEeoAgBAeERs+K/S0lItW7ZMgwYNchaTkKBBgwZpyZIlXq/z9ttvq1+/fhozZoyysrJ05JFH6t5771WFn78USkpKVFRUZLkAAAAAAADEMyaqBwAgPCIWquzYsUMVFRXKysqybM/KylJ+fr7X6/z555+aP3++Kioq9N577+mOO+7Qww8/rMmTJ/u8nSlTpigzM7PqkpOTE9L7AQAAAAAAEG3oVAEAIDwiPlF9MCorK9WyZUs99dRT6tWrl0aMGKHbb79dM2bM8Hmd8ePHq7CwsOqycePGOqwYAAAAAACg7hGqAAAQHhGbU6V58+ZKTExUQUGBZXtBQYFatWrl9TqtW7dWcnKyEhMTq7Ydfvjhys/PV2lpqVJSUjyuk5qaqtTU1NAWDwAAAAAAEMUIVQAACI+IdaqkpKSoV69eWrRoUdW2yspKLVq0SP369fN6neOOO05r1qxRpcvAoL/99ptat27tNVABAAAAAACoj/yFKuXldVcHAADxJqLDf40dO1azZs3S888/r1WrVumaa67R/v37lZeXJ0kaOXKkxo8fX3X8Nddco127dumGG27Qb7/9pnfffVf33nuvxowZE6m7AAAAAAAAEHWYqB4AgPCI2PBfkjRixAht375dEyZMUH5+vnJzc7VgwYKqyes3bNighARn7pOTk6MPPvhAN910k3r06KHs7GzdcMMNuu222yJ1FwAAAAAAAKIOw38BABAeNrvdbo90EXWpqKhImZmZKiwsVOPGjSNdDgAAAAAAQMi9/740ZIj3fXl50uzZdVsPAADRLJjcIKLDfwEAAAAAACD06FQBACA8CFUAAAAAAADiDHOqAAAQHoQqAAAAAAAAcYZOFQAAwoNQBQAAAAAAIM4QqgAAEB6EKgAAAAAAAHHGX6hSXl53dQAAEG8IVQAAAAAAAOIMnSoAAIQHoQoAAAAAAECcYaJ6AADCg1AFAAAAAAAgzrh3qhxxhHOZUAUAgJojVAEAAAAAAIgz7qFKo0bOZUIVAABqjlAFAAAAAAAgzriHKmlpzmVCFQAAao5QBQAAAAAAIM64hyqpqc5lQhUAAGqOUAUAAAAAACDOuE9UT6gCAEBoEKoAAAAAAADEGX/Df5WX120tAADEE0IVAAAAAACAOOMeqiQnO5fdu1gAAEDgCFUAAAAAAADijHuokpLiex8AAAgcoQoAAAAAAECcce9Gce1UIVQBAKDmCFUAAAAAAADiDMN/AQAQHoQqAAAAAAAAccY9VElKsu4rKJDOOkvq21f65pu6rQ0AgFiWVP0hAAAAAAAAiCWuoUpiorm47ps0SXrnHbM+fLi0fn3d1gcAQKyiUwUAAAAAACDOVBeqPPmkc33DhrqrCwCAWEeoAgAAAAAAEGdc501JSDAXb/sAAEBwCFUAAAAAAADiTHWdKgAAoGYIVQAAAAAAAOIMoQoAAOFBqAIAAAAAABBn/IUqDP8FAEDNEaoAAAAAAADEGfdQxXVOFW+dKnZ7+GsCACAeEKoAAAAAAADEGfeJ6qvrVCktDX9NAADEA0IVAAAAAACAOONv+C9vCFUAAAgMoQoAAAAAAECc8Tf8lzeEKgAABIZQBQAAAAAAIM4E26lSUhLeegAAiBeEKgAAAAAAAHHGdd4Uhv8CACB0CFUAAAAAAADijGunSkICw38BABAqhCoAAAAAAABxprzcuZyURKcKAAChQqgCAAAAAAAQZ5hTBQCA8CBUAQAAAAAAiDPBhip0qgAAEBhCFQAAAAAAgDjjHqowpwoAAKFBqAIAAAAAABBnXEMV5lQBACB0CFUAAAAAAADijOtE9cypAgBA6BCqAAAAAAAAxBmG/wIAIDwIVQAAAAAAAOIME9UDABAehCoAAAAAAABxJtg5VRj+CwCAwBCqAAAAAAAAxBn3OVUY/gsAgNAgVAEAAAAAAIgzDP8FAEB4EKoAAAAAAADEGUIVAADCg1AFAAAAAAAgzrjPqVLd8F/MqQIAQGAIVQAAAAAAAOKM+5wqdKoAABAahCoAAAAAAABxJtjhv159VbLbw1sTAADxgFAFAAAAAAAgzgQbqqxcKX39dXhrAgAgHhCqAAAAAAAAxJlg51SRpMmTw1cPAADxglAFAAAAAAAgzgQ7p4ok7dkTtnIAAIgbhCoAAAAAAABxJtjhvySpQ4fw1QMAQLwgVAEAAAAAAIgz7qFKIMN/JSWFrx4AAOIFoQoAAAAAAECccZ9TJZBOlX37wlcPAADxIipClenTp6t9+/ZKS0tT3759tXTpUp/HPvfcc7LZbJZLWlpaHVYLAAAAAAAQ3Woy/BehCgAA1Yt4qDJv3jyNHTtWEydO1PLly9WzZ08NHjxY27Zt83mdxo0ba+vWrVWX9evX12HFAAAAAAAA0c19ovpAhv8iVAEAoHoRD1WmTp2q0aNHKy8vT927d9eMGTOUnp6u2bNn+7yOzWZTq1atqi5ZWVl1WDEAAAAAAEB0o1MFAIDwiGioUlpaqmXLlmnQoEFV2xISEjRo0CAtWbLE5/X27dundu3aKScnR+ecc45+/vnnuigXAAAAAAAgJjCnCgAA4RHRUGXHjh2qqKjw6DTJyspSfn6+1+t07dpVs2fP1ltvvaW5c+eqsrJS/fv316ZNm7weX1JSoqKiIssFAAAAAAAgntGpAgBAeER8+K9g9evXTyNHjlRubq4GDhyo119/XS1atNDMmTO9Hj9lyhRlZmZWXXJycuq4YgAAAAAAgLrFnCoAAIRHREOV5s2bKzExUQUFBZbtBQUFatWqVUDnSE5O1tFHH601a9Z43T9+/HgVFhZWXTZu3FjrugEAAAAAAKJZTTpV9u+XKivDVxMAAPEgoqFKSkqKevXqpUWLFlVtq6ys1KJFi9SvX7+AzlFRUaGffvpJrVu39ro/NTVVjRs3tlwAAAAAAADiWU3mVLHbpYMHw1cTAADxICnSBYwdO1ajRo1S79691adPH02bNk379+9XXl6eJGnkyJHKzs7WlClTJEl33XWXjj32WHXq1El79uzRgw8+qPXr1+vKK6+M5N0AAAAAAACICna7teMk0OG/JDMEWEZGeOoCACAeRDxUGTFihLZv364JEyYoPz9fubm5WrBgQdXk9Rs2bFCCyyv/7t27NXr0aOXn56tp06bq1auXvvrqK3Xv3j1SdwEAAAAAACBquHapSIEP/yWZUOX/35IBAABe2Ox2uz3SRdSloqIiZWZmqrCwkKHAAAAAAABA3CkpkdLSnOsPPSRddllgYcn330s9e4atNAAAolIwuUFE51QBAAAAAABAaLl3qiQlBT781969oa8HAIB4QqgCAAAAAAAQR2oz/NfOnaGvBwCAeEKoAgAAAAAAEEfKy63rwYQqmzeHvh4AAOIJoQoAAAAAAEAcCbZTxXVoMEIVAAD8I1QBAAAAAACII8HOqdK2rXN506bw1AQAQLwgVAEAAAAAAIgjwXSq2GzSoYc61+lUAQDAP0IVAAAAAACAOBJMqJKYSKgCAEAwCFUAAAAAAADiiLeJ6n0N/5WYKGVnO9cZ/gsAAP8IVQAAAAAAAOKItzlVbDbvx7qHKvv2mQsAAPCOUAUAAAAAACCOeBv+y5fERCk93bqtpCT0NQEAEC8IVQAAAAAAAOJIsKGK+9BglZWhrwkAgHhBqAIAAAAAABBHvM2p4ktSkud+QhUAAHwjVAEAAAAAAIgj3uZU8YVOFQAAgkOoAgAAAAAAEEdqO/yX+/UBAIAToQoAAAAAAEAcYU4VAADCh1AFAAAAAAAgjgQzp0piInOqAAAQDEIVAAAAAACAOMKcKgAAhA+hCgAAAAAAQBxhThUAAMKHUAUAAAAAACCOMKcKAADhQ6gCAAAAAAAQR5hTBQCA8CFUAQAAAAAAiCPMqQIAQPgQqgAAAAAAAMQR5lQBACB8CFUAAAAAAADiCHOqAAAQPoQqAAAAAAAAcSSYUCUpiTlVAAAIBqEKAAAAAABAHHGfqD7YOVUY/gsAAN8IVQAAAAAAAOKIr06Vjh09j2X4LwAAgkOoAgAAAAAAEEd8hSovveR5bGIiw38BABAMQhUAAAAAAIA44itU6dNHGj7ccx+dKgAABI5QBQAAAAAAII74m1PFvSuFOVUAAAgOoQoAAAAAAEAc8dWp4r7sWKdTBQCAwBGqAAAAAAAAxJFgQxXmVAEAIHCEKgAAAAAAAHGkrMy6npzsXKZTBQCA2iFUAQAAAAAAiCO1DVWYUwUAAN8IVQAAAAAAAOKIe6jCnCoAAIQOoQoAAAAAAEAccQ1VkpMlm825zpwqAADUDqEKAAAAAABAHHEPVVy5ByhJSXSqAAAQDEIVAAAAAACAOBJMqMKcKgAABIdQBQAAAAAAII4EG6ow/BcAAIEjVAEAAAAAAIgjte1UIVQBAMA3QhUAAAAAAIA4wvBfAACED6EKAAAAAABAHHENVZKSrPvcA5SadKrY7dKzz0qjR0srVtS8TgAAYlFS9YcAAAAAAAAgVoR7TpUlS6S//c0sv/++tH695zkAAIhXdKoAAAAAAADEkXDPqTJhgnN582bpt9+CrxEAgFhFqAIAAAAAABBHwj2nSkmJdf3gweDqAwAglhGqAAAAAAAAxJHycudydaGKzRZ8p0pamnW9uDi4+gAAiGWEKgAAAAAAAHEkmE4Vb9uCDVUOHAi8NgAAYh2hCgAAAAAAQBwJNlQJtlMlNdW6vndv4LUBABDrCFUAAAAAAADiSDChirfhv6qbU8W9U6WoKLj6AACIZYQqAAAAAAAAccRfqOIeoHjbFuzwX4QqAID6hFAFAAAAAAAgjvgLVWw2z+ODnVMlJcW6TqgCAKhPCFUAAAAAAACinN0uzZ8vzZwplZT4P9ZfqOJNsJ0q5eXWdeZUAQDUJ0mRLgAAAAAAAAD+PfusdMUVZnnZMumpp3wfW9tQpbo5VUpLret0qgAA6hM6VQAAAAAAAKKcI1CRpFmz/B8bbKgS7PBfhCoAgPosKkKV6dOnq3379kpLS1Pfvn21dOnSgK738ssvy2azadiwYeEtEAAAAAAAIEaEe/gvQhUAQH0W8VBl3rx5Gjt2rCZOnKjly5erZ8+eGjx4sLZt2+b3euvWrdMtt9yiE044oY4qBQAAAAAAiH51HaowpwoAoD6JeKgydepUjR49Wnl5eerevbtmzJih9PR0zZ492+d1KioqdMkll2jSpEnq0KFDHVYLAAAAAAAQ3VxDlaQAZtO12azr48dLq1b5Pr6kxLpOpwoAoD6JaKhSWlqqZcuWadCgQVXbEhISNGjQIC1ZssTn9e666y61bNlSV7gOKOpDSUmJioqKLBcAAAAAAIB45a9TxW73fh33eVWuvtr3+Rn+CwBQn0U0VNmxY4cqKiqUlZVl2Z6VlaX8/Hyv1/niiy/0zDPPaFZ1s7L9vylTpigzM7PqkpOTU+u6AQAAAAAAolWww39JnkOAffaZ72MJVQAA9VnEh/8Kxt69e3XZZZdp1qxZat68eUDXGT9+vAoLC6suGzduDHOVAAAAAAAAkROKUMUf5lQBANRnAYysGT7NmzdXYmKiCgoKLNsLCgrUqlUrj+P/+OMPrVu3TmeddVbVtsr/nz0tKSlJq1evVseOHS3XSU1NVWpqahiqBwAAAAAAiC7790sHDzrXqxv+yzGfSm1ClYMHTZATaIADAEAsi2inSkpKinr16qVFixZVbausrNSiRYvUr18/j+O7deumn376Sd9//33V5eyzz9ZJJ52k77//nqG9AAAAAABAvXb22db1QIMO9zlV/HEPVSS6VQAA9UdEO1UkaezYsRo1apR69+6tPn36aNq0adq/f7/y8vIkSSNHjlR2dramTJmitLQ0HXnkkZbrN2nSRJI8tgMAAAAAANQnpaXSxx9bt9XF8F+SmVelWbPAzwEAQKyKeKgyYsQIbd++XRMmTFB+fr5yc3O1YMGCqsnrN2zYoIRgXtkBAAAAAADqIW9hR3WhSiiG/5LoVAEA1B8RD1Uk6brrrtN1113ndd/ixYv9Xve5554LfUEAAAAAAABRrLLSMwipSajiEIpOFQAA6gNaQAAAAAAAAGJMebnnttqEKrWdU4VQBQBQXxCqAAAAAAAAxBhvoUpZmec2OlUAAAgtQhUAAAAAAIAYU9NOlXPPta6PHGm+EqoAABAYQhUAAAAAAIAYU1HhuS2QUOXQQ6Wnn5ZOPFF69FGpa1fft2G3e26rrPQe6DBRPQCgvoiKieoBAAAAAAAQuEA7VbzNlXLFFebiyltIU1IipaVVfxsSnSoAgPqDThUAAAAAAIAYE2iosm9fYOfzFqoUFwd2GxKhCgCg/qhRqPL555/r0ksvVb9+/bR582ZJ0pw5c/TFF1+EtDgAAAAAAAB4CnT4r0DDjspKz20lJYHdRjC3AwBArAs6VHnttdc0ePBgNWjQQCtWrFDJ/7/CFhYW6t577w15gQAAAAAAALAKtFPFVwjizluoEkynyvbtgd0OAACxLuhQZfLkyZoxY4ZmzZqlZJfZzo477jgtX748pMUBAAAAAADAk7dQpazMc9tFFwV2vtoO//X224EHOAAAxLKgQ5XVq1drwIABHtszMzO1Z8+eUNQEAAAAAAAAPwIZ/mvCBCk7u+bnCyZUkaRjjpHs9sBuDwCAWBV0qNKqVSutWbPGY/sXX3yhDh06hKQoAAAAAAAA+BbI8F8XXxz4+Wo7/Jck/fij9N13gd8mAACxKOhQZfTo0brhhhv0zTffyGazacuWLXrxxRd1yy236JprrglHjQAAAAAAAHARSKiSkhL4+WraqWKzWdfz8wO/TQAAYlFSsFf45z//qcrKSp1yyik6cOCABgwYoNTUVN1yyy36xz/+EY4aAQAAAAAA6qXKSsnbFLaBDP9V21Dl7belDRukCy+UHNPqlpRYj5k5U7rqKue6tyAGAIB4EnSoYrPZdPvtt2vcuHFas2aN9u3bp+7du6thw4bhqA8AAAAAAKDeuvxyac4cz+2h7lTxNhfK1Knm6+efS089ZZbdQ5PGja3rhCoAgHgX9PBfDikpKerevbv69OlDoAIAAAAAABBiBw96D1Qk76FKWZl1PZhQxZ9Zs5zL7p0qTZpY1wlVAADxLuhOleLiYj322GP65JNPtG3bNlW6zWS23FtPKgAAAAAAAILiLTjxt682nSqBcg9VMjOt64QqAIB4F3SocsUVV2jhwoU6//zz1adPH9ncZyQDAAAAAABArfl7yyWQOVUc86CEQlmZOZ97aEKoAgCob4IOVd555x299957Ou6448JRDwAAAAAAAOR9nhOH6jpVbDYpMTF0tRQWSs2be3aqNGwoJSRIjoFMCFUAAPEu6DlVsrOz1ahRo3DUAgAAAAAAgP/nNuK6RXWhSkqK/06XYO3ebb66hyppaebiQKgCAIh3QYcqDz/8sG677TatX78+HPUAAAAAAABA/kOV6ob/CvV8Knv2mK/uoUpqKqEKAKB+CXr4r969e6u4uFgdOnRQenq6kt0G6Ny1a1fIigMAAAAAAKivajP8V6hDlZdeko45xjM0oVMFAFDfBB2qXHTRRdq8ebPuvfdeZWVlMVE9AAAAAABAGAQ7/FdZmXM51KHKtGnSBRd4dqokJxOqAADql6BDla+++kpLlixRz549w1EPAAAAAAAAFF3Df0nSpElS377O9dRUM28LoQoAoD4Jek6Vbt266eDBg+GoBQAAAAAAAP+vNhPVu43WHhL5+dbQxBGmuIYq7p0sAADEm6BDlfvuu08333yzFi9erJ07d6qoqMhyAQAAAAAAQO1F05wqkpSTYw1NUlPNVzpVAAD1SdDDf51++umSpFNOOcWy3W63y2azqcJb/ykAAAAAAACCEm3Df6WmEqoAABB0qPLJJ5+Eow4AAAAAAAC4qM3wX+EIVQoLpcaNneuEKgCA+ijoUGXgwIHhqAMAAAAAAAAugg1Vysqcy+EKVVq0cK57m1Plyy+lzp2lN96Qjjwy9DUAABBpQYcqn332md/9AwYMqHExAAAAAAAAMKJtTpXCwuqH/5KkNWukm2+WPvgg9DVEwksvSTNnSoMHS+PHSzZbpCsCAERS0KHKiSee6LHN5vJqwpwqAAAAAAAAtVebOVWSk0NfT6ChiiQtXBj624+EwkJp1CgTYn32mXTKKVLfvpGuCgAQSQnBXmH37t2Wy7Zt27RgwQIdc8wxWhgvr5gAAAAAAAARFm1zquzZY50zxdvwX/Hmyy+tj/XUqZGrBQAQHYLuVMnMzPTYduqppyolJUVjx47VsmXLQlIYAAAAAABAfRZtoUppqVRU5Fx3dKo4vsYj98Do4MHI1AEAiB5Bd6r4kpWVpdWrV4fqdAAAAAAAAPWavzlVvA3/5To0VzhCFUkqKHAu+xv+S/Jff6xwfxwJVQAAQXeq/Pjjj5Z1u92urVu36r777lNubm6o6gIAAAAAAKjXgu1UcX3DPz099PVI0rZtzuXqhv86cEDKyAhPHXXF/XF2Hf4MAFA/BR2q5Obmymazye72cYNjjz1Ws2fPDllhAAAAAAAA9VmwocqBA87lcIUqgU5UL0mffipNmSI1aCA9/7zUunV4agon1/sr0akCAKhBqLJ27VrLekJCglq0aKG0eJ6VDAAAAAAAoI75C1W8Df9Vm1BlzBhp+vTgrlNdqHLlldLWrWb5ppukl18O7vzRgFAFAOAu6FClXbt24agDAAAAAAAALuqyU2XCBGnjRjO819dfB3YdR5jSqJH3/Y5ARZLmzZNmzfJ9bLQqLbWuO0IVu12y2eq+HgBA5AUUqjz66KMBn/D666+vcTEAAAAAAAAw/E307h6qlJVZtwUbqrRsKb31llkONCxwdKoMHBjY8e++K114YXB1RZq3TpX77pOmTpXOPtsERYQrAFC/BBSqPPLIIwGdzGazEaoAAAAAAACEQDDDf+3fb10P15wqrhyhSocOgR3/yy/hqyVc3EOV/Hxp/Hiz/Mwz0vDh0mmn1X1dAIDICShUcZ9HBQAAAAAAAOEVzPBfr7xiXa9NqJKQ4P+2HRyhiiQtWiQNGuS/u6awsOY1RYr78F/uZs0iVAGA+iahNle22+2y+3u1BAAAAAAAQI0EGqosXSr9/e/W/bUJVZICnIG3YUPn8sknS2vW+D9+z54alxQx7p0q7hj6CwDqnxqFKi+88IKOOuooNWjQQA0aNFCPHj00Z86cUNcGAAAAAABQbwU6p8odd3jur4tQpXFj63qHDmY4LF/iMVRx7xgCAMS/oEOVqVOn6pprrtGQIUP0yiuv6JVXXtHpp5+uq6++OuC5VwAAAAAAAOBfoHOqeAsrIhGqSFKPHr6Pj8Xhv6oLVbZsqZs6AADRI8CXSafHHntMTz75pEaOHFm17eyzz9YRRxyhO++8UzfddFNICwQAAAAAAKiP/IUqrnN9ZGR47q9NqJKYaF1PS5OKiz2Pa9TIc9tRR/k+byx2qlQ3p8o330j9+0uzZ0vdutVNTQCAyAq6U2Xr1q3q37+/x/b+/ftr69atISkKAAAAAACgvvMXquzY4VwOdaji3qnSvLn344LtVInFUKW6ThVJWrJEuv/+8NcCAIgOQYcqnTp10iuvvOKxfd68eercuXNIigIAAAAAAKjv/M2p4vq51nCHKi1aeD/OW6jSrp3v88ZrqCJJzz3nf/9jj0lDh0rvvFPrkgAAERbw8F8rV67UkUceqbvuukvDhw/XZ599puOOO06S9OWXX2rRokVewxYAAAAAAAAEz1+niutcHpEKVbwN/2WzSSkp3ofNKioy9ykh6I/4Rk51w385NGzoe9+KFdL115vlzz+X1q2TmjWrdWkAgAgJ+GWsR48e6tu3r3bs2KGPP/5YzZs315tvvqk333xTzZs319KlS3XuueeGs1YAAAAAAIB6w1+osnu3dPCgWU5N9dwfqU4VyfdwYXa7tHdvzeuKhEA7VbKzfe+bO9e5vHev9OabtSoJABBhAYcqn376qY444gjdcsstGjJkiBITE/XII49o2bJlmjt3ro4++uhw1gkAAAAAAFCv+AtVJCk/33wtL/fcVxdzqnjrVJGkvDzf5461IcD8hSquj9P+/b6PS0mxrq9eXbuaAACRFXCocsIJJ2j27NnaunWrHnvsMa1bt04nnXSSunTpovvvv1/5jldyAAAAAAAA1Jq/OVUk5xBg3oaoSk6u+e26hyreujAyMqTERO/Xv+02qUMH79ctLKx5XZHgL1Q56yznsr9QxdFR5PDdd7WrCQAQWUGPYpmRkaG8vDx9+umnWr16tS644AJNnz5dbdu21dlnnx2OGgEAAAAAAOqd6jpVHKGKtzf+bbaa3657Z0WnTp7H+OpScez77Tdp/Xrpv/+17vvf/2peVyT4m1OlY0fnsr9QZft26/qPP9auJgBAZNVqarBOnTrpX//6l/7973+rUaNGevfdd0NVFwAAAAAAQL0W6PBfgU6mHqhHHnEuZ2VJp5zieYyv+VQcEhOltm1N8OA6Mf2TT0plZaGpsy746lRp3Ng610xpqfdh2CTPUMW9cwUAEFtqHKp89tlnuvzyy9WqVSuNGzdO5513nr788ssanWv69Olq37690tLS1LdvXy1dutTnsa+//rp69+6tJk2aKCMjQ7m5uZozZ05N7wYAAAAAAEBUqi5UcXRHhDpUGThQevhh6fzzpddeMwFCTo71mOpCFYc2baQhQ5zrmzdLGzaErtZw8xWqtGplhkBz5atbZds263qov18AgLqVVP0hTlu2bNFzzz2n5557TmvWrFH//v316KOPavjw4cpwfyUJ0Lx58zR27FjNmDFDffv21bRp0zR48GCtXr1aLVu29Di+WbNmuv3229WtWzelpKTonXfeUV5enlq2bKnBgwfXqAYAAAAAAIBoU12o4njD3/2N/4svrt3tJiRIY8dat3XrJm3c6Fz3N/yXuxtvlN55x7m+dat16Kxo5isAycryHqpkZnoe696pUlZm5supzRBtAIDICbhT5YwzzlC7du302GOP6dxzz9WqVav0xRdfKC8vr8aBiiRNnTpVo0ePVl5enrp3764ZM2YoPT1ds2fP9nr8iSeeqHPPPVeHH364OnbsqBtuuEE9evTQF198UeMaAAAAAAAAok11E9U7whT3N/5nzAh9LUcfbV33Fh744j5Z/datta+nrvjqVOnRwzNU2bfP8zi73TNUkaJ3CLQvv5SOPVa64AJp9+5IVwMA0SngUCU5OVnz58/Xpk2bdP/996tr1661vvHS0lItW7ZMgwYNchaUkKBBgwZpyZIl1V7fbrdr0aJFWr16tQYMGOD1mJKSEhUVFVkuAAAAAAAA0S7QThXXUOXMM4PrIgnU2LFSbq5zfdiwwK/burV1PR5ClaFDAxv+q7DQe4ASrUOA/eMf0jffSPPnS/ffH+lqACA6BTz819tvvx3yG9+xY4cqKiqUlZVl2Z6VlaVff/3V5/UKCwuVnZ2tkpISJSYm6oknntCpp57q9dgpU6Zo0qRJIa0bAAAAAAAg3Goy/FdKSnhqycqSvv5aWrRIatBAOvHEwK/buLGUliYVF5v1WApVfIUfJ54ouU8J7C1U8TWwSrSGKitWOJfvv1+6777I1QIA0arGE9VHUqNGjfT999/r22+/1T333KOxY8dq8eLFXo8dP368CgsLqy4bXQcABQAAAAAAiFI16VRJTQ1fPampZtL5k04Kbj4Qm83arRJLoYq3TpUHHjDBkrdOlYoK5/onn0hnneX9vNEaqgAAqhfURPWh1rx5cyUmJqqgoMCyvaCgQK1atfJ5vYSEBHXq1EmSlJubq1WrVmnKlCk60cvHJFJTU5Uazr8oAAAAAAAAwqAmc6qEq1Oltlq3ltauNcuxGqrk5UlTppiuHckzVDn9dBM8PfmkdMop/odIi9Y5VQAA1Ytop0pKSop69eqlRYsWVW2rrKzUokWL1K9fv4DPU1lZqRJfg1wCAAAAAADEoJp0qkRzqOKQnx+5OoLl+nZTs2bOQEWSGjb0fvzf/iY9/7zkb1pfOlUAIHZFtFNFksaOHatRo0apd+/e6tOnj6ZNm6b9+/crLy9PkjRy5EhlZ2drypQpkswcKb1791bHjh1VUlKi9957T3PmzNGTTz4ZybsBAAAAAAAQUtE0p0ptHXqoc3nNGjNMVmJi5OoJRGmptG+fc71BA+t+904VV65zk0jSjBnS1Vdbzx1tvHVG7dvnPTwCgPos4qHKiBEjtH37dk2YMEH5+fnKzc3VggULqiav37BhgxISnA01+/fv17XXXqtNmzapQYMG6tatm+bOnasRI0ZE6i4AAAAAAACEXHWhimPi97qaU6U2cnOdywcOSL/+Kh1xRMTKCcjKlVJ5uXP98MOt+/2FKkuWOJePOcYaKknRGap4G5Js61apc+e6rwUAolnEQxVJuu6663Tdddd53ec+Af3kyZM1efLkOqgKAAAAAAAgcuJpTpVevazry5ZFf6iybJl1vXdv67q/x9p1iLPmzT2PJVQBgNgV0TlVAAAAAAAA4F08Df91+OHW4bO++y5ytQTKNVRp1Ejq1Mm632aT2rat/jyxEqp4q2nLlrqvAwCiHaEKAAAAAABAFAokVLHbY6NTJSnJOgRYLIQqq1Y5l3NzpQQv76L95z/Vn6dFi9gIVbx1quzaVfd1AEC0I1QBAAAAAACIQoGEKq5zfkjRO6eKZB0+6/vvPWuPNoWFzuVWrbwfM2yY1LKl//PESqeKt1Bl927PbXv3Si+/LK1dG/6aACAaEaoAAAAAAABEIW9zqvTp41wuKfF8cz5aO1Uk67wqBw9aO0GikWuo0rix7+P87ZNiO1RxnRtGMs/JQYOkiy6SjjzSzLkCAPUNoQoAAAAAAEAUcu9UueUW6eijneslJdb5VKToDlXcJ3qP9iHAioqcy7UJVbwN/+UtwIg0bzU9/rg0c6Zz/Y8/pKVLzfKBA9K//103tQFANCFUAQAAAAAAiELuocr48dbhvWKtU6VbNzO5u8OmTZGrpTp2e+ChSqNG/s8VC50qlZW+a7r6audzcc8e674vvwxrWQAQlQhVAAAAAAAAopB7qGKzVR+qRPOcKomJUnKyc72iInK1VKe42Drni79QxfU+eRPtocptt5nvTf/+vo/ZvNl83bHDut3bnCsAEO8IVQAAAAAAAKKQe6iSkOAZqsTS8F+SefPeIZpDFdcuFcl/qOLafeMuMVFq184zeImWUGX7dumBB8yy+3129dtv5qt7qOLeuQIA9QGhCgAAAAAAQBRyn6ieUKXuuAcMmZm+j/UXqhx2mNSgQfR2qjg6UKozYYJ5PrqHKqWl1o4eAKgPCFUAAAAAAACikLdOlbQ057rdLu3daz0mlkKVaH4zPlSdKs2ama/RGqp4m5zem6++kp5/3jNUkaQNG0JbEwBEO0IVAAAAAACAKFTd8F+S5zwYDRqEt6baipVOlcJC63pNQ5V+/czXaA1V9u0L/NgnnvAeqmzbFrp6ACAWJEW6AAAAAAAAAHiqbqJ6d40aSX36hLem2oqVUCWYTpUEHx9ZzsiQxo0zy4mJ5vvnGNItWkIV904nf7791nt30a5doasHAGIBoQoAAAAAAEAUqm5OFXd//7uUnh7emmoryeWdqHgJVbKzreuvvy7l50sDBjj32WymW8UxB06gw26FWzChiiStWOG5jVAFQH1DqAIAAAAAABCFAhn+y1Xv3uGtJxT8daoUF1vnjImkF1+0rvsLVf71L+mZZ8z3KydHOvts6/10cA1VYrFTxZedO2t/DgCIJcypAgAAAAAAEIWCDVWaNg1vPaHgLVQpLTVdHY0bS3fc4dmhU9d++klauNC6rWFD38e3b28mcr//fumLL7wHKpJ1XpVYCFUaNpQef1w69VT/53B0qoQioAGAWECoAgAAAAAAEIWCnVOlSZOwlhMSroHDokVSVpa5T59/bobEmjzZhCsrV0auxo8+sq6npPgOShz69pVuvVVq29b3MbEWqqxaJY0ZIx1zjP9z/PyzNHCglJkp/e1voa0PAKIRoQoAAAAAAEAUcu/YqC5UibVOlT/+kLZt8zxm3z5pypS6q8lhwQLpqaek5cut2/v2Dc35k5Ody9ESquzb53ufo97q7v9rr0mffWaer88+K/34Y+jqA4BoxJwqAAAAAAAAUci1UyXh/z8WG+uhSlKA70S99JLnvCbh9Pbb0jnneN/3wguhuY1Y61RxhCqDB0udO0u//x7YOZculXr0qH1tABCt6FQBAAAAAACIQt5ClWbNfB+fmRneekKhumG0XNXl3CpXXOF9++jRZs6UUHANVT75JDTnrK1AQpXUVOm//5WaNzfrhx5qhm3zxb3TBwDiDaEKAAAAAABAFHINVWw287VNG9/Huw4vFa2CCVXy88NXh7sdO7xvP/zw0N2Ga6iyfr304YehO7ckFRdLmzYFd51AQhVJ6tVLWr3azLOydq3Urp3v6y1bFlwNABBrCFUAAAAAAACikGunhqNTJRa6UfwJJlRZsyZ8dQSqT5/QnWv9euv6ww+H7ty//246SHJypMmTqz9++XLpgQekH37wfYx7SNesmdStmxnCrajI9/V++imwmgEgVhGqAAAAAAAARCFvw385OlZiVTChyh9/hK8Od94e14YNpf79Q3cbu3db1z/4QCovD825L7tM2rnTLD/4oP+h07ZskU44QbrtNmnzZu/H2Gz+v1fjxjmXW7Uyt+lw8KC5AEC8IlQBAAAAAACIQt5ClVgXrZ0q6eme2554IrQh1rBhntuef15aubJ2592+XfrmG+d6UZFUWOj7+Icflg4c8H/O6uazufhi6W9/k/r1k+bOlQ45xLrfPUACgHgSJy/JAAAAAAAA8cXbnCqSlJFR97WESlJS4MfWZaeKt1DFPSiorX/8w3PblVdKRx0lvfBCzc/76aee23x1oEjSL7/U/LYc0tKkZ56RvvpKOuUUqUkT635CFQDxjFAFAAAAAAAgCvnqVPEWAIwfH/56QiFaO1W8BVWhDlVOPtl3B8moUdL06dLGjcGf132uFskM8eWLv3lUaqppU+s6oQqAeEaoAgAAAAAAEIW8TVQvSX37Wo875xzp5pvrpqbaCiZU+e47acgQacwYac+esJUkqW46VSSpcWOpZUvv+667Tho0SCopCe6c3oKY007zPrfK5MnS1q3BnT8Q7qFKuL9fABBJhCoAAAAAAABRyFenyv33O8OJ446T3nwzPAFAOFQXqhxxhHX9/ffN3CZ33hm2kiR5D1WaNw/PbbVp43vfb79JixYFdz5f3S233iotXWrd9vDDwZ07UHSqAKhPCFUAAAAAAACikK85Vbp3l5YvN5Ocv/9+3ddVG9WFKr16ed/+44+hr8VVcrLntszM8NxW69b+93/9dXDn8zdk2BdfOJd37w5fBwlzqgCoTwhVAAAAAAAAopCvThVJ6tFDGjlSatSobmuqrepClTPOsAZIDtu2haceh7Iyz23e6ggFf50qknT33cGFZf5CleJi5/Kff/o+rl+/wG/Pm0aNrN9bQhUA8YxQBQAAAAAAIAr5mlMlliUl+d9/zjnSlClSu3bW7du3h68mSSotDe/5XVUXqkhmLpm3367+uNJSqaDA9/6dO53Lf/zh+7i//7362/LHZrN2qxCqAIhncfKSDAAAAAAAEF/8darEquo6VRo0kG67TVq3TrrrLuf2HTukiorw1eWtUyVcqhv+y+F//6v+mK1bPSejdxVIqHLRRabrqbZc51VhonoA8SxOXpIBAAAAAADiS30LVXJzrestWzqXKyulXbvCUpIkz06Vq68O32316BHYcb/8Uv0x7o/JO+9Iffs613fsMF/37JH+9S/n9latpA0bpK++kubODc1QZ66hyvPPS2vX1v6cABCN4uQlGQAAAAAAIL74mqg+lvkLVV56ybruGqpI4Z1XxT1UmTAhfLfVv785f3Xhyu+/V38u946Qpk2lQw5xrjs6VR55xHpcly5STo6ZSyVUgZ37ZPWzZoXmvAAQbQhVAAAAAAAAolA8zqniK1RZt046/HDrNvdQpU8fa9AUSq6hyvXXBz5EV03YbNKkSdIPP1i3t2wpPfigc3379urnJnHf7y1UsdulF16wHnfTTZ7neuUV5/PsmWf83643J5xgXZ87V1qzJvjzAEC0i5OXZAAAAAAAgPgSj8N/eZuoPiPDc2J6yTNUOXBA+uST8NTlGqqkpITnNry5/HLz1WaTXntN6trVun/1av/X9xaqNG/uXF+zxjx31q1zbrvlFmnYMM9zXXCB9Ouv0qpV0t/+FuAdcDF+vHV940apc2fp9tuDPxcARLM4eUkGAAAAAACIL/EYqnjrVMnI8H5sixae2376KbT1OEQqVJk1S3rzTWnFCun4482wXK5cwxBvqutUcZeUJN1wg+/9nTtL3br5v01/5z73XM/t994rFRfX7JwAEI3i5CUZAAAAAAAgvtSXOVUaNPB+bGam1LixddvWraGvSZLKypzLdRmqJCVJ55wj9exp1l0ne5ekvXv9X981VGnQQEpN9R+q3HOPdOihNas1EK5dMq5++SV8twkAdY1QBQAAAAAAIArVlzlV0tK8H2uzSXfcYd1WXedGTdjt1k6V5OTQ30agGjWyru/b5/9411DFEci0auX92OHDpXHjal5bIHyFKl9/Hd7bBYC6FCcvyQAAAAAAAPGlvgz/5StUkcz8H/36OdfDEaqUl1vX67JTxV1amvV7XVRk5pLxxVuoMmiQ98f0qafC3/Hkbcg2SRozRhowgGHAAMSHOHlJBgAAAAAAiC+EKkaPHs7l9etDW49k7VKRIhuq2GzWbpU77zRzzhx3nLRjh+fx3kKVhg2lggLPYzMzQ1qqV746VSTp88+lZ54Jfw0AEG5x8pIMAAAAAAAQX+JxTpWkJM9t1YUq7do5lwsKpIMHQ1tTNIUqkglF3H31lZnU3mH/fulvf5M++MC5zXU+lsaNzfwpDv/+d+jr9MZfqCJ5DucGALHIy0sZAAAAAAAAIq2+z6nikJNjXc/Plw47LHQ1xUKoIkm//+5cnjNHevZZ6373Se7HjZPatjXDm114YWhr9OWQQ/zv373b1OMtXAOAWBEnL8kAAAAAAADxheG/DPfuh+OOk7ZsCV1NZWXW9UhOVC95TlbvsH27c9nbMFrNmlnXk5OlSy+VLr+8+sc4VHwFQq5WrAh/HQAQTnHykgwAAAAAABBf6kuokprq/zruocrWraEdzipWOlVcQ5UmTTz3DxgQlnKC0rWrdOih/o/58su6qQUAwiVOXpIBAAAAAADiSzzOqRKKThXJDH21a1doaoq2UCWQThX3Grt1k84+O3w1BSoxUfroIzP02FtvSaed5nkMoQqAWEeoAgAAAAAAEIXqS6dKdaGKr3k6mjeX9u6tfU3RFqoE0qniHig9+6z3xzYSunaVHnjAhDxPPSVdf711/1dfSbfdJnXpIl10kfTnn5GpEwBqKk5ekgEAAAAAAOJLPE5U722C8upCFV8hg90uvfde7WuKtlDFV6fK3r1SSYlZ3r3buf2SS6Rjjw1/XTXRrp30n/9I997r3LZliwldfv9devll6ZxzrM91AIh2cfKSDAAAAAAAEF/oVDH8DX22alXt6pGiL1TxN9m7o1vFNVRxn6A+GmVl+d63cqW0bl2dlQIAtRYnL8kAAAAAAADxhVCleqEIVcrKrOvJybU/Z21UF6rY7dZQpWnT8NdUWy1a+N9/xx11UwcAhEKcvCQDAAAAAADEFyaqr96vvwZ3/IIF0tFHS4MHmwnVpejrVPE1/Jdk5k7Zv98aBMVDqPLii9Krr9ZNLQBQW4QqAAAAAAAAUSge51TxFqqkptb8fKtXSxUV1R9nt0vl5dKoUdL330sLF0qnn25CmWgLVfx1qjzxhPTLL9Zt8RCqSNL//hf+OgAgFOLkJRkAAAAAACC+xOPwXzWZqF6SevTwvr2kpPr5OHbvNgFKcrK0bZtze0WF6ZCItlDFX6dKRYU0c6Z1WyzMqRJIqLJ2bfjrAIBQiIqX5OnTp6t9+/ZKS0tT3759tXTpUp/Hzpo1SyeccIKaNm2qpk2batCgQX6PBwAAAAAAiEXxGKrUdPivxx5zBjL9+1v3VTevyqWXms4Ub+69V1q/3rot0qFKdrb//bNnW9djoVOlUSPPx9Vmk3r2dK7/+Wfd1gQANRXxl+R58+Zp7NixmjhxopYvX66ePXtq8ODB2ub60QEXixcv1kUXXaRPPvlES5YsUU5Ojk477TRt3ry5jisHAAAAAAAIH+ZUcRowQPr5Z+nzz6V33rHu8xeq/PKL9N57vvdXVko33WTdlp5efT3h9Je/eG7Ly/N9fCyEKjab5zBtV1whnX++c33LFqm4uG7rAoCaiHioMnXqVI0ePVp5eXnq3r27ZsyYofT0dM12j93/34svvqhrr71Wubm56tatm55++mlVVlZq0aJFdVw5AAAAAABA+NSXOVUCnai+Sxfp+ONNiNCqlXO7v1Dl22+Dq69TJykrK7jrhFrjxp7bRozwfmxysnTYYeGtJ1TcQ5WRI6UOHazb3LuGACAaRfQlubS0VMuWLdOgQYOqtiUkJGjQoEFasmRJQOc4cOCAysrK1MzHAJIlJSUqKiqyXAAAAAAAAKIdw3/5dvjhzmV/ocqKFdbb2bxZKiiQ7r7b+/EjRkRHV1CDBtb1gQO9P069ekW+syZQ7vepXz/PQIghwADEgoi+JO/YsUMVFRXKcvsIQFZWlvLz8wM6x2233aY2bdpYghlXU6ZMUWZmZtUlJyen1nUDAAAAAACEG6GKb927O5eXLpXWrPE8pqRE+s9/nOs9ekht2kgtW0pDhng/7+WXB19LOLz7rnN5+HDzGA0c6Hnc8cfXXU21ddddzuXrrjNz5LRvbz1m06Y6LQkAaiSmX5Lvu+8+vfzyy3rjjTeU5uMVePz48SosLKy6bNy4sY6rBAAAAAAACF48zqnimGzeVWpq8Oe54ALncmWlNH265zGjR1vXXecq6dbN8/i33zbDf0WDk06SPvvMTEr/7LNm2/Dh3o+LFddfL82cKT32mHT//Wab+8Aze/bUeVkAEDQvL2V1p3nz5kpMTFRBQYFle0FBgVq5Do7pxUMPPaT77rtPH330kXr06OHzuNTUVKXW5NUZAAAAAAAggphTxbcBA6TcXOn7782646vDypXSnDnWbeec41z2NmTWWWcFX0c4nXCCuTicf740ZoxzMvdevaTBgyNTW02kpEhXXWXdlppqLiUlZr2wsO7rAoBgRfQlOSUlRb169bJMMu+YdL5fv34+r/fAAw/o7rvv1oIFC9S7d++6KBUAAAAAAKBOMfyXbzabdQiwLVus+x97zLr+8MPS6adbt11zjXN57Njga6hrjRtLkyaZ+968uelg8fZ4xpomTZzLhCoAYkFEO1UkaezYsRo1apR69+6tPn36aNq0adq/f7/y8vIkSSNHjlR2dramTJkiSbr//vs1YcIEvfTSS2rfvn3V3CsNGzZUw4YNI3Y/AAAAAAAAQolQxb82bZzLrqHKnj3SCy841wcO9B6a3H231KiRlJws3XprzWqoa7feauZ9ycys2bBp0SgzU3IMYlOb4b9WrTKXk0+2BjUAEGoRD1VGjBih7du3a8KECcrPz1dubq4WLFhQNXn9hg0blODyl8OTTz6p0tJSnX/++ZbzTJw4UXfeeWddlg4AAAAAABA28TinSrhClX37pL17pYYNpTPOcA6RJUn//7ldD4cc4pzbI5a0bBnpCkIrM9O5XNNOleXLpT59pIoKqWlTMz/O8ceHpj4AcBfxUEWSrrvuOl133XVe9y1evNiyvm7duvAXBAAAAAAAEGH1pVOlUaOancs1VJGc3Spff20993nn1ez8qBuhGP7riSdMoCJJu3dLF10k/fab1KBBrcsDAA9x8pIMAAAAAAAQX+JxovokLx/vDVWoMm6c9N131m3//nfNz4+64dqpUpPhvyoqTGeKq02bpNmza1UWAPgUJy/JAAAAAAAA8aW+dKrUdGgz91Dlf/+TLr3Uus19cnpEn9oO//X669L27Z7blywJ7jwbNkhDhphhw77/Pvg6ANQfUTH8FwAAAAAAAKzqw5wqyck1P1fr1tUf07Rpzc+PulGb4b/sdumf//S+r6Ag8PMcOGDm4vnlF7M+bpz04YfB1QKg/oiTzzkAAAAAAADEl/rQqdKqVc3PlZ5ufUPem+r2I/JcO1WKiqzPe1dbt0qffWbdv2mT9Oef3o/Pzw+8hldfdQYqkvTxx9bh9wDAVZy8JAMAAAAAAMSX+tCpkpVVu/O5DwHmflsNG9bu/Ag/11ClslLat890jrg+/x95RMrJkQYOlC6/3Ll940brubp1cy4HE6r89JN1vbLShDgA4A2hCgAAAAAAQBQqL3cu12aYrGhy8KB1vWXL2p3PX6jSpEn8hFHxzL2bKDNTysiQ+vQx4covv0hjx5oJ6SVp7lwTvEieocoxxziXd+yQysoCq2HDBs9tq1YFdl0A9Q+hCgAAAAAAQBQqLXUup6REro5QOnDAut6+fe3O5y9UYT6V2ODaqeJq2TJp/nzpt9+s2+126ddfzfKmTdZ9vXtb171NYO+Nt1DFcRsA4I5QBQAAAAAAIAq5fso+XjpVTjzRzIUimeG5fE0yHihCldjXtq3vfStWmHlW3DnmP3HtVGnSROrUyXqcYwgw9w4pd+4dL5L088/+rwOg/iJUAQAAAAAAiELxGKpkZEiffCLdcIO0YIGZJ6M2Wrf2vY9J6mND166+9+Xnew9VHIGHaxiSkyO1amU9bvNm6frrpUaNpL59PTulJNMR5m3+lG+/rb72eLN/v7R7d6SrAKJfUqQLAAAAAAAAgKd4HP5LMnNl9OkTmnM1bux7H50qscHRueTNn39KRx7puf2BB8xX1yG6vIUq55xjhguTpKVLpZkzpZtush6zZYvzGFfff286XBo0qPYuxIUVK6RTT5X27DGP0xVXRLoiIHrRqQIAAAAAABCF4rFTJdQaNfK9r7y87upAeKxdK/34o/d9DzzgHAZMkjp0kLKyTDeUg3tY8s47nufxNp+KZJ4/K1YEV28su+oqaedOqaJCuvLKSFcDRDdCFQAAAAAAgChEqFK9wYN9ByvNm9dtLai5ESO8b9++XXrlleqvb7NJo0aZeXpyc30f9/HHniGNr1BFkr7+uvrbjhfffRfpCoDYQagCAAAAAAAQZez2+B3+K5QaNpQWLpSuvVZ66y3pqKOc+846K3J1ITiTJzuf4/66j3y5+GKpd2+z7C9UkaTRo63r7pPUN2vmXP7mm+BrARD/mFMFAAAAAAAgylRUWNfpVPHt2GPNRZJ69ZKefFLq0kUaMiSydSFwnTqZcOP336UWLfxPXu/NJZc4l3v08NzfoIGZH0Uyc6vs3u2cc8e1UyUrS+rfX3rjDbNe006V334zQ40NHRr8fYkWdrvpAALgiU4VAAAAAACAKOM69JdEqBKo7GzT9TBypJTAu14xpWVL6bjjpM6dfR/ToYPpSnHVooV0yinO9XPOcXa7NG9uhhB79lnrdf74w7ns2qmSk+MM6CQTuGzZEtz9KCqS+vWTbr5ZGjBAKiwM7vrRorg40hUA0YuXFwAAAAAAgCjjOvSXxPBfqD9sNt9DePXuLb34ovn5uOEG6aSTpHnzrD8fWVnS559L994rLV5sgpUjj7SexzVUce1UadvWBCKuXnopuPpff13atcssb9smzZkT3PWjxf79ka4AiF4M/wUAAAAAABBl6FRBfXbnndKwYZ7b09LM1+Rkado039fv2dNcHA47zLr/11+dy+6dKv37m6+O7bNmSbfcEnjtjkDFYdWqwK8bTfbvN4EUAE90qgAAAAAAAEQZQhXUZ2efbcKMzEzr9gMHana+9HSpdWvn+p13mrCjsFDas8e5PSdHSkyUrrjCue2336SCgsBvy324r5kzpfLymlQdWXSqAL4RqgAAAAAAAEQZ91CF4b9Qn9hs0pVXSq+8Yt2+b1/Nz9mxo3V9yhQTmLjq1Ml8Pf546/Yffwz8djZvtq5XVEj//Gfg14+EkhLPbcGGKsXFJqy6+mrrkGpAPCJUAQAAAAAAiDLuc6rQqYL6qGlT63ptQpW+fa3rn34qrV5t3da1q/nao4d1+08/BX47mzZ5bgt2Xpa6tnev57ZgQ5WZM6VJk8zXv/89NHUB0YpQBQAAAAAAIMow/BcgdeliXa/Nm/W33WZd37BB+uAD53piotShg1lu0cJMeO8QTKji3qkiSVu3Sjt3Bn6OuhaKUOXGG53LCxbUqhwg6hGqAAAAAAAARBmG/wLMnCpTp5qOlTPPlP7615qfq0ULaelS67a5c53LHTpYf86OOsq5vHJl4LfjrVNFCi6YqWtFRZ7bajunit1eu+sD0YxQBQAAAAAAIMow/Bdg3HSTtGuX9L//SQ0a1O5cRx8tNW/ufV+3btZ1x/wqku+gxF1RkXXie1c//ST9/rs0YoSZdySaJoIPRaeKu+Li2l0fiGZJkS4AAAAAAAAAVgz/BYReUpKUlyc9+KDnPtcQRZLatHEub9smlZeb6/vzww++9/34o/TOO9LChWa9slJ66qnA6g43X6HKqlXmvg8YINlswZ1zz57ah2BAtKJTBQAAAAAAIMow/BcQHtde6z0cOeww67prqFJZacKF6ixbZl13DWqeftoZqEjSrFmBd8CEm7fhv95+W+reXTrxROnf/w7+nL46doB4QKgCAAAAAAAQZRj+CwiP9u09J613bHflGqpI0pYt/s/7ww9mqDKHQw6RzjjD/3Xeesv//rry44+e2z780Ll8773ma3Fx4MOCEaognhGqAAAAAAAARBmG/wLC5/LLPbe5d6q0bm1dry5UefRR6/rRR0s9evi/zp9/+t8fDt9+K61cKW3ebDpw9u2Tnnii+ustX24eo8xMafbs6o8nVEE8I1QBAAAAAACIMgz/BYSPe4AiBdap8vXX0mWXmY6UggITTlRUSHa79Ouv1uOHDJGOOsp/HevXB116rTz4oNSnj6nr0EOlfv1Mt0wgAcg550j5+eb+jhkjbdzo/3hCFcQzJqoHAAAAAACIMgz/BYRPYqLntoYNrevNm5u5V8rLzfo111j3T5tmPXbHDuv+664zP8cJCaYjxJt166SDB+tuQvenn7auL10qXXppYNd1nf+luFhq29Z0rfzrX9LYsZ7HE6ogntGpAgAAAAAAEGUY/gsIr5EjncsnneS5PyHBcwgwX9wDlXvuMT+zGRnSlCnmXA6uQ4ItWya1aCHNnx943TVVXi799ltoz1lYaOanmTPHc5/7YwLEE0IVAAAAAACAKMPwX0B4TZpkhsLq2tWEIN7k5NTs3K7Di916q7Rhg/TBB1JRkXTRRdZj9++Xxo0zQ4iF04YN1R+TkmKGBQvWjTd6bpswIbDbBGIRoQoAAAAAAECUYfgvILzat5e++cbMhdKvn/djvM29Eui5XWVnS6edJjVqJLVr53n8unXSqlU1u61Aff119ccMH27mSlmzRpo4MfBzFxV53+5tWDAgHhCqAAAAAAAARBmG/wIiz1eoMmeOdMstwV9Pkrp187793XcDrysYdrs0bJh0ySXW7d6GNhs61Hzt2FH6978993fvLg0cGPhtv/aaM8x58UXpqqvMkGdArCNUAQAAAAAAiDIM/wVEXocOntv69zcBxQMPSO+/L91+u3V/585SVpbvc+bmmvlckpKs2907ScrLTSjxzDPSvn01Kl+StGSJ9NZb1m2NGkkPPmjdNm6cdMEFznX3+iTpkUfMuZ57TvryS6l58+pv/5//NDVceqk0a5Z07rmenXhArPHy4wEAAAAAAIBIolMFiDxvHSdvvinZbGb59NPNJSNDevllqUsX6c47nfu9sdmk5583wcS55zoDD9dJ5IuKzHBh33xj1u+/X/rsM6lVq+Dvw6efem7r3l26+GKpSRMzofwFF0jp6Z7HJSWZcMdh0CApIUEaNcqsX3edub/V3X7//s71jRuln3+Wjj462HsCRA86VQAAAAAAAKIMc6oAkec+N8qgQVKLFp7HjR8v/fCD9Oqr0hFHBHZum03q2tW5vnKldP31ZriuV191BiqS9PvvZsL7mvA2WfxJJ5nbHzrUBCTeAhVJuukm5/Kjj5pAxdXtt3sPVZ55xn9Nv/zifz8Q7QhVAAAAAAAAooxrp0pSkv9PvgMIj7ZtpSOPdK5PmRLa83fpYl1/7DHTkfLrr57Hzp/ve0J4f3780XPbyScHdt177jHzx7z+uulKcZeUZCa0P+YY5zabTTrhBP/nXbkysNsHohXDfwEAAAAAAEQZ11CFLhUgMhISpDfekJ59VurbV+rdO7Tnd+1UcRgyRDpwwHP7wYNmqLDLLgv8/JWV0k8/Wbc1ayYdd1xg109ONnOhVOeNN8wE9n/8IeXlmXll/LnvPnM/qwtfgGhFpwoAAAAAAECUcR3+i1AFiJxOnUzHxtlnh/7c3kIVb4GKw3ffBXf+deukvXut215+2fdwXzWVnW06Yv74Q3r66cCuM2CA9Mknoa0DqCuEKgAAAAAAAFHGtVMlJSVydQAInxYtzIT0gXr0UemddwI/3n3oryVLpFNPDfz6wUhPlzp0cA5VOG5c9df5z3/CUwsQboQqAAAAAAAAUYbhv4D64e23pccfD/z4iy+W9u3zf8zdd5uA49xzrdtd54cJt7Fjpf79pcMOkxYulOx26YMPrMe88460bVvd1QSECqEKAAAAAABAlGH4L6B+SE2VxoyRevTwvj8317q+d68JLK64Qnr/fc/jly+XJkyQ1q61bu/YUWrYMCQlB6RVK+nLL6U//3R2x5x2mjVYqaiQvv227moCQoVQBQAAAAAAIMow/BdQv9x1l+e2xETvw2jNmiXNnm06UdzDkxdf9H5+X6FNXevWzbq+e3dk6gBqg1AFAAAAAAAgyhQXO5dTUyNXB4C6cc45Zg6UTz81gcmpp5pJ3y+6SDrrLO/XKSmR5syxbvM1+buvc9S1Jk2s64QqiEVJkS4AAAAAAAAAVq5zJtTlkD0AIueoo8zXAQOkvDzn9rfflqZPl667zvM6S5aYr/v3S2eeKa1Y4XlMZqY0YkTo662JRo1MB05FhVknVEEsolMFAAAAAAAgyuzf71zOyIhcHQCiwyWXeJ9facECaeJEMzn94sWe+202sy89PewlBsRms3ar7NkTqUqAmqNTBQAAAAAAIMrQqQLAVZMm0vnnS//9r+c+b/Ox9Okj3XefmaC+bduwlxeUJk2knTvNMp0qiEWEKgAAAAAAAFGGThUA7qZPNxO9r1njOZeKu/nzpZycuqkrWE2bOpcJVRCLGP4LAAAAAAAgytCpAsBd06bShAnSCy9IZWXS8cd7P27lyugNVCTr8F+EKohFhCoAAAAAAABRhk4VAP4kJUmvvioluL27e/bZUvfukakpUK6dKp99JtntkasFqAlCFQAAAAAAgChDpwqA6rRqJU2ebCawz842Icsrr5jJ4KOZa6giSbfcEpk6gJoiVAEAAAAAAIgiFRVScbFznVAFgC/jx0tFRdKmTWYi+9TUSFdUPdfhvyRp6tSIlAHUGKEKAAAAAABAFHEd+kti+C8A/qWlRbqC4LiGxkAsinioMn36dLVv315paWnq27evli5d6vPYn3/+WX/961/Vvn172Ww2TZs2re4KBQAAAAAAqAOuQ39JdKoAiC+dO3tuq6ys+zqAmopoqDJv3jyNHTtWEydO1PLly9WzZ08NHjxY27Zt83r8gQMH1KFDB913331q1apVHVcLAAAAAAAQfnSqAIhn55/vuc09TAaiWURDlalTp2r06NHKy8tT9+7dNWPGDKWnp2v27Nlejz/mmGP04IMP6sILL1RqLAwQCAAAAAAAECQ6VQDEs1atpPvus27buzcytQA1EbFQpbS0VMuWLdOgQYOcxSQkaNCgQVqyZEnIbqekpERFRUWWCwAAAAAAQLSiUwVAvOvSxbrOW7aIJRELVXbs2KGKigplZWVZtmdlZSk/Pz9ktzNlyhRlZmZWXXJyckJ2bgAAAAAAgFCjUwVAvGvc2LpOpwpiScQnqg+38ePHq7CwsOqycePGSJcEAAAAAADgk3uoQqcKgHjTqJF1nU4VxJKkSN1w8+bNlZiYqIKCAsv2goKCkE5Cn5qayvwrAAAAAAAgZrgP/0WnCoB4496pUlQkLVggbd4sjRjB7z1Et4h1qqSkpKhXr15atGhR1bbKykotWrRI/fr1i1RZAAAAAAAAEUWnCoB4596pMnOmdMYZ0pVXStdcE5magEBFrFNFksaOHatRo0apd+/e6tOnj6ZNm6b9+/crLy9PkjRy5EhlZ2drypQpkszk9r/88kvV8ubNm/X999+rYcOG6tSpU8TuBwAAAAAAQKi4zy3AJ7YBxBv3TpWFC53Lc+dKKSnSk0+ar0C0iWioMmLECG3fvl0TJkxQfn6+cnNztWDBgqrJ6zds2KCEBGczzZYtW3T00UdXrT/00EN66KGHNHDgQC1evLiuywcAAAAAAAg517kFMjKkpIi+ewMAoVddB97s2VK/fqZzxZfVq6WtW6UBA6SEuJ85HNHEZrfb7ZEuoi4VFRUpMzNThYWFauweiQIAAAAAAETYmDHSE0+Y5datpS1bIlsPAIRD48aenXnufvrJBDDNm1uHDFu8WDr5ZMluN8HLrFlhLTWqfPCB6eI5/XTp6qsjXU38CCY3IMMDAAAAAACIIq6dKnweFEC8cp9XxZujjpI6dJA6dpR+/925fcYME6hI0tNPS++/H54ao82+fdKFF0pvvWXmnvnmm0hXVD8RqgAAAAAAAEQRQhUA9UEwv9+2b5e6dJHeftuEKa+9Zt1/333OkCWeff+9tGePc/3OOyNUSD1HqAIAAAAAABBFCgudy5mZkasDAMKpRQvr+hFHSM8/7/8655wjZWdL5eXW7Z99ZuZV6dXLTG5/+unSzp2hrTfS7HZp7lzrtvXrI1NLfUeoAgAAAAAAEEXoVAFQH4wYYV0/5RTptNOk1FT/19u61fe+5culsjIz78g118RX98oTT0gzZ1q3uXatoO4QqgAAAAAAgJj33/+ayYrvvz/232QiVAFQH1x9tZlsXpJsNumyy6RWraQXX5TOOEPq21eaNEkaOrRm53/1VSkrS1q4MHQ1R9Itt3huy88386ygbiVFugAAAAAAAIDaeP996eKLnesbNkjTp0euntpyDVUY/gtAvEpMlN57z1y6dDHDf0nSX/9qLq62bDHDfrk65RTpwAFpyRLft7F9u3TFFWaYrIQYby8oLvbcZrdLS5c6wynUjRh/KgEAAAAAgPpu6VLr+jvvRKaOUHGdU4VOFQDxLDVVOvdcZ6DiS5s21mO6dZM+/FD6+GPp5ZdNCHPKKdIdd0hjx1qvu2mT9PXXoa+9LvnrwFy8uK6qgAOdKgAAAAAAIKa5hhCStHGj+URvWlpk6qmNp56SSkud64QqAGBMnOjsSnzsMTNkWFqamZvFfX6WoUNNyOIwf77Uv39gt1NRYbpoosmaNb73ffpp3dUBg04VAAAAAAAQ09w/wWu3S2edJVVWRqScGistlf7+d+s2QhUAMC64wAwDtnOnNGiQ/2NPPtnMyeLwySeB3cbzz0uHHCLl5vofVqyuvfCC733ffCOVl9ddLSBUAQAAAAAAMc69U0WSPvpImjmz7mupjU2bPLcxpwoAOLVoEXjYfNJJzuUff5T27vV/fGmpdP315jXlhx+kM880c7K4275devFFM09LdQ4elHbvNmF/sOx2aflyqW1b05nj6tFHncslJf47WRB6hCoAAAAAACCmeQtVJOnaa6X776/bWmpjwwbPbUkM3A4ANeI63Fdlpeno8Ofrr6WiIuf6rl1Sy5bSH3+Y6z/wgHTJJSbkuPRSqX176ZhjpD//9H6+OXOk5s2lZs2kXr2krVud+1auNPO/nH22mQ/mo4+kAwfM/CjHHCO1bi0lJ5vrbdxoPW+/ftJxx1m3HX64dNdd0ldfSS+9ZL4ifGx2e01ysthVVFSkzMxMFRYWqjE9tAAAAAAAxLxjjpG++877voQEads2M5xLtHvhBWnUKOu2336TOneOTD0AEMt27DCdLQ6TJkkTJvg+/oYbrB0gDkcfLQ0ZIt1zj/frdegg/fyzdR6vJ580wb67a681w1Oed57pYnGVnS1t3uy7PskMa/bCCyaoSU/3f+yHH1Y/TBqcgskN6FQBAAAAAAAxzX1OFVeVldKbb9ZVJbXj3qny738TqABATTVvLnXt6lz31b3xxx9mzpXp073vX7HCd6AimU6VJ55wrq9cKV13nfdjn3hCOuMMz0BFqj5QuflmaeFCE740aGC9b97Mnu1/P2qOUAUAAAAAAMQ01+G/jjzSc8ivV16p23qCsXWrNG2a9Omn1lClTRvp7rsjVhYAxAXXIcCWLJEqKqz7//UvqVMn0wHivi8Y//2v+VpSYobzqqys+bnctW1r5lZ56CEpMdG5/ZRT/F/vyy/NPDL79oWuFhiEKgAAAAAAIKa5hirnnSfdeqt05ZXObYsWmWFgQqWiwnwSuby8duex26VzzpFuuslMqOwa/rRtW7tzAwCsc48UFUmjR5tJ3w8eNJeHHgr+nMnJ0qxZ5ne3w4oV5nXhuOPMsI0ORx4pTZ7s+1xffuk57KMk3XmnCdrtdmn9ejMEmbu77jIdMddea84zcaJ1/4YNUuPGZgi0t94yk9nv3m2C/OOOk4qLg7nXcEWoAgAAAAAAYlZxsVRa6lzPzDRfhw93bquokN54o+a3MWGC1LGjeWOsvFzq00c66ijzppTrbQfihRfM5MbDh5s34b791my3263hEKEKANTescda1599Vrr+ehOmLF0qlZV5XmfxYmnkSOd6+/bSsGHS//5nugs3bDDB/YABzmMqKszrwrJl1nOdfrp0++0m0Elweye+Y0fTSfPcc+a1YPhw032yaJEJSHJy/N+3Qw4xAdH06eY8d95pwhV3xcWm/s6dzVwsN91khkJ79VX/54dvTFQPAAAAAABiVn6+1Lq1c/3pp6UrrjDhR+vWzg6VCy6QbrzRDINy8slSUlJg5//pJ6lHD+f6PfeYN8gc5syRLr3UuW63Szab93MVF0tZWebNNckMObNmjfdj586VLrkksBoBAN4dPFj9hO6uOneWVq/2/Xvc1fbtUsuW/o/56iupXz+z3KuXGcbLYcwY6fHHA68tEGVlUm6u9Msv1R/bt6/09dehvf1YxkT1AAAAAACgXnDt7pCkJk3M16Qk66eIX33VdJYMHux/KBZ3X3xhXXcNVCTpssuk88+X/vY3qV07E5q88473c61Z4wxUHOveHHOMdNFFgdcIAPCuQYPqgw8Hm80M6xVIoCKZYbX69vW+r1s3Mym9I1CRrJPXt2wpjR0b2O0EIzlZ+ugjqXt3/8e1aSMNGVL7YSzrK0IVAAAAAAAQs9xDFcfwX5LvN7smTTIdLnv3mjfQ3nzTdJh4E8hcLK+9ZoaU2bDBfHJ5xAjp1189j1u9uvpz2WzS6697DhMDAKiZdu0CO+7116WBA4M795NPmiDD4f77zST1q1ZJ11xjPTYvz3SQfPGFtG6d1KFDcLcVqNatzfwuzz9vgpPcXOdr45lnmvm71q0zQ1sG2rUJKx42AAAAAAAQs3btsq47OlUkM/eJL65Dhkmew3g5rF0bfE0HDkj/+Ie0cKFZ37LFfCq5ulDlsMOk774zY94DAEKjXTvn/FW+7N0rNWwY/LmPPlr65BNp9mzTCek6n5c3hx8e/G3UhM1m5oVxnRsGoUOoAgAAAAAAYlJZmTR1qnVbdrZzuVcv8yncQIY3ueyy0IUqkhl+5corpSVLzCeW/bngAmnUKNNZQ6ACAKFVXafKlCk1C1QcjjvOXFB/EKoAAAAAAICYNHas9OGHzvXkZDOniUOjRtK555r5VALhbZJ5f6HKeedJvXub8CY/X8rJkU49VaqoMPtnz67+Nv/yFzN0WEZGYDUCAIJTXahyxBF1UwfiB6EKAAAAAACISY8/bl3PyfGci+TqqwMPVS66yAQre/ZI6enSpk3S+vXO/ZddJg0YIH39tQlT/v53zxBm8mRp/Pjqb+v8883tDRkipaUFVh8AIHgnneR/f8+edVMH4ofNbvc1FVt8KioqUmZmpgoLC9W4ceNIlwMAAAAAAGrAbvcMUE46Sfr4Y+u2igrPiXhvuEH6z3+Cv82PPpJOOaX6ui66SJo3z7r92GOlTp2knTul9u3NcDOOiYMBAOG1YIH02WfS5ZdLbdpI/ftLP/0kjR4tPfVUpKtDNAgmNyBUAQAAAAAAUa+83LzxtX+/NGaMCUvc/60fOlR65x3P6x5xhPTLL871HTuk5s2Du/3LLpOef96zM8Wb3bulYcPMG3g2mzRnjnTJJcHdHgAgfOx2ads265CRqN+CyQ0Y/gsAAAAAAES9hx5yDqu1dq00bpznMbt3e7/us8+aTyVXVJg5Tw45JLjbzsuTZs0KLFCRpKZNpU8/NeFNgwbMlwIA0cZmI1BBzSVUfwgAAAAAAEBkuc5T8uSTJrBwd/313q/bp4+0ZIkJV157zWy74w7nfsdwXcnJZv2hh6TKSmnFCunbb82E84mJwdfcvDmBCgAA8YZOFQAAAAAAEHPcQ5WcHOm883wff8wx5uJw221SWZlUVCT9619Sdrb0l79IJSVmuDBJys0NedkAACDGEaoAAAAAAICY4x6qfPGFs9MkEBkZZrJ4V5061b4uAAAQ3xj+CwAAAAAARLWyMs9tW7ZY14OdeB4AAKAmCFUAAAAAAEBUKyjw3LZ0qXO5QQMpPb3u6gEAAPUXoQoAAAAAAIhqW7d6bnv9decyXSoAAKCuEKoAAAAAAIColp/vfz+hCgAAqCuEKgAAAAAAIKp561RxlZtbJ2UAAAAQqgAAAAAAgOi2bZv//f37100dAAAAhCoAAAAAACCq7dvnfz+hCgAAqCuEKgAAAAAAIKr5C1XatZO6dau7WgAAQP1GqAIAAAAAAKKar1Dl3HOlefOkBN7dAAAAdSQp0gUAAAAAAAD4s3ev57bbb5cmT677WgAAQP3GZzkAAAAAAEBUc+9UGTFCGjcuMrUAAID6jU4VAAAAAAAQ1VxDlSFDpJdfjlwtAACgfqNTBQAAAAAARDXXUKVhw8jVAQAAQKgCAAAAAACiGqEKAACIFoQqiHnl5dKsWdLzz0uVlZGuBgAAAAAQaoQqAAAgWjCnCmLedddJM2ea5eXLpf/8J7L1AAAAAABCi1AFAABECzpVENNWrTJdKg6PPiotWCDZ7eYCAAAAAIhtFRXSgQPOdUIVAAAQSYQqiGmTJnkO+XXGGVJCgpSYKB1/vLRpU2RqAwAAAADU3v791vVGjSJTBwAAgESoghj200/SK6/43m+3S19+KZ16qlRUVHd1AQAAAEB99+ef0rPPShs3Srt2SW+/La1bJxUUSJs3BzeygOvQXxKdKgAAILKYUwVR66efpPnzpS1bTNfJrl1SZqb0l7+Y5Vdesf4hnpoqlZR4nufXX6WbbpKeecasl5VJycl1cx8AAAAAoL7Ztk3q3Vvavdv3Mbm50pQp0uefS7/9ZrpPWrWSysuljAxz/c6dpe3bTQjjilAFAABEEqEKosrPP0srVph5UV58MfDrnX669O670i23SI884rl/9mxzzvJyaccO6W9/kx54wPlpqUMOMfs6dZIGDw48dLHbpe+/N5++ys6WunSR9u6VSkuldu0kmy3w+wCEUnGxlJJihsIDAAAA6tJrr/kPVCTzf9QZZ9Ts/IQqAAAgkghVEFFLl0r/+58ZpuuTT2p2joQE6e67zdepU6WzzzbzqGRlSaed5jxuyxbn8tNPm4s3rVpJ//iHdNVVJmzxFozY7dI330j/+pfvups2Nd0zrVpJLVua0KZFC6lZM+nEE00Ac8ghUk5Oze53qK1ebe5LSYkJlxo0MGFRixbmzfkWLcxj3KaNuV8//mj+mTniCNNJVFZm5rdJTY30PakfVqwwAWKPHtKoUeZ7kZYmrV9vntv/+Y/5nrRta57DXbqYn4umTaUBA8z3bd8+MzReebl5npaWmjCmuNg8D2w28zxo0sSc3/GzYLOZ50TXruZ6SUlmnRARAAAAUs3/twsUoQoAAIgkm90ezEimsa+oqEiZmZkqLCxU48aNI11OvfbZZ9LAgTW/focO0tFHS1dc4fsTTscea8KP2jj5ZBOC2O3S2rXSDz9If/wRunla/vIXE+Acdph5c7ugwAQXHTqYbpeUFOexBw9KFRUmxEhMNB01NXkje/du6ZdfpOXLzeOzerX03Xc1qz8pybxRv327CV26dDGt+tnZ5jHbt8/cn7ZtTRfP5s1mfcAA6cgjfddvt5vHuGFD8wb/3r3mtho3jtzwbbt2mceuXTtTi2SCi6Skug0Ufv5Z6tfPPCYOCQlmyITCwrqrw1VSkvleHXWU1KePeS4XF5tw8/DDzdANBw6Yn51GjUxI16KFGdohOdlcGjSQ0tMJZ+JVcbH5/cX32LfKSvO7NDPThKQAEA02b5YmTDAfvhg61PwN0rq19W/UYNntvBbUBbtdWrLEfFDq1FPNh7tqo6zM/A8xZ47pMmnYUNqzRzr0UPO3X0WFuRQXS++/b73uPfeYEQNSU81r3OLF5uKQlmb+bszPN38Xus+h4m79evP/BQAAQKgEkxtERagyffp0Pfjgg8rPz1fPnj312GOPqU+fPj6Pf/XVV3XHHXdo3bp16ty5s+6//34NGTIkoNsiVAmdigrzBu6uXc75Tpo2NW+AFxebAGLrVvMm9L595h+v9HTpww+lZcs8x8V1l5wszZ0rnXuu6WT54APzR/zxx0tXX23emK3O++9LjqdGmzbmj/TKytrf97pis5nHLDvbvCG9aZN1f8OG5g3+7Gxz/1q3Nt+X/fvN8Q0bmm2JieYfngMHpG+/lb7+Onoeh7Q088+VIyhKSHA+t8rKPI9PSDAdEs2aSc2bm6+pqeb5cuCACRoSE80b9h07mu1JSc6LY337dhNSpaSYbYmJ5vyJiab7whFYJSSY+X1eeskZ0DVtar4v+/aZOhMTzfOxcWNzCXQ5JcX8s+v4Lext2XW9slLauVOaONHzuRAvEhPN49OihXn+pqaa77PjcsghzkvLluZ7YLdbv8ful4QEc3F8P/2tb99uurB27DDPj8aNzW3Z7eZ7nphogiDH98X1+o7nr+vX9HRnl4/799NxfUeo5Pr8rO2wbXa7+fkpLXW+ceW4j74urtd1P5e356W/56pjeccO83v49ddNkF5RYb6nrVtL/fub+9qihXmsSkvNdVwfD28/u96+vwcPmt97rtd3vNm3dau5f6tWmVDc0XlXUWH9PiUnm/McPGheww4eNM+v/Hxz/caNze+U9HTzs+j4mXRdttvNm0plZearr2W73fy+qqw0583MNNtWrza37ZCaavY1b26ObdjQXBo1MvsqKpy/y9PSnL9Pq/te+7ukpjofD0fdlZXmcUtKcv6udnSopaeb6zi+747HRHKe0/XnzfW29uwxY+4nJJhzpKSY+5eZ6bw4OiEdtXi7eNtfVmb+NikrM7dVWWkenzZtzO2Vlpp9jut6+1nw9fPgrkEDU3dGhrkf+/eb16ZGjYJ77F1/nwT6OyshwXl/HffFsVxUZH4G7Xbn981xcdz/jAxTb3GxeXwaNDDfB8fFbrc+Vq7LFRXmNnbtMh/SWLfO3O/0dPO3YEmJ6XTs2NH589qsmfN5m5Rk/V67fr9dL5J5w9bx/Dv00NC/Ge/+nHXfV1npfMzLy83j4PjAx9q1Zl9Rkfm9kZBg/VmorDTbbTbzeCQnO7dXVHj/Her46mvZ3/6EBOfvFMdzu7rnk+PnOTnZ8/Vn0ybzd/e2bdbtqanmA0EtW5rL99+b50J6uvP3guvroePDKOXl0u+/m8eudWvzODieV+6vWa73zXH/kpPNc9XxOErmeZyZaW6jpMQ8rhkZzr+TGzY0z23Hdby9ltlsztcP14vjgzMVFaZ2yXl/HD9PjueM+3nr6uL+M1NWZn6/Ll1qfgc4Xh+TkkwIUVxs/n5NSTF/07o+V5OSnK8laWnmGEdYsnOn+TmvqPD9s+TLjBnS3/9u3Wa3S2+9ZTpaTjjB/M/n+HtcMq+J//2v+b3dvr15Lr75pvlf5qqrpEmTgq8DAADAn5gKVebNm6eRI0dqxowZ6tu3r6ZNm6ZXX31Vq1evVsuWLT2O/+qrrzRgwABNmTJFZ555pl566SXdf//9Wr58uY488shqb49QxbuLLjL/COXmmjcBHG9QFxaai+OfhcpKM4ngr7+aP9ZD/exx/FPXvbv5NJPr8F01tXy5+SP8tNPMPwfbt5shx7ZsMV0VgwaZN85sNjOM2KxZwZ2/e3dp/HjzeK1ebW6jpMT8w2izmX8aCwvNP5grV1Y/tjAQSuef7+wQysgwz8Vff410VaiOI2xxhDGSWXYNE8rLze8db2/KAUC8Skx0BpyON3/37TN/x3p7w9zbxTUM3b/fGeo6OMKVaPkAChDLDj/cfKCuQYNIVwIAAOBfTIUqffv21THHHKPHH39cklRZWamcnBz94x//0D//+U+P40eMGKH9+/frnXfeqdp27LHHKjc3VzNmzKj29ghVPNnt5lO7O3dG5vZbtTLBh+MT3a6fUIqEAwekhx+WnntO+vNP676WLaWePc3QXG3bmmHHevYM7lPlW7eaTpGSEtOO//TT5jYjJSvLzKHSubM0Zoz5xNqff5o3KTZuNJ/SPuww832pqDDbysvNp03Lysyb9evXm+MbNzafRv/tN/MGRWKi+QfK9dONjjeDERpjxpjOnU2bzBtDXbpIffuagNTX/DY7d5pw0fEJ+fJyE/a5fjLR8cnzAwdMgOr4lKPjFaOgwDyPbTbzfXZ8ov/zz00tju6hWOsOAwAAQPXatTN/Dzo6LI880vnBD0cXz3HHSf/8Z+2HHQMAAKgLMROqlJaWKj09XfPnz9ewYcOqto8aNUp79uzRW2+95XGdtm3bauzYsbrxxhurtk2cOFFvvvmmfvjhB4/jS0pKVFJSUrVeVFSknJwcQhUX69eblupwcv20dUaGdOaZZqLs9u2l0083oU40stvNsGObNkl//asJHEJt/35pzRrnECvNmpkQ4s8/zfdmzx5pwwbzj8kRR5jgqaLCBBoFBSbk2LzZXAoKzBvZGRkmpNqzx3xyUzLrdrsJT0480XTudOtmApPaDjVUneJiU2dGhhnqYfVq6dNPnUMslZRYh8JwDF3RtKl5fNLTTQdVebkJbH7/3dz/nTvN/XMMG5GWZo6rqDBzd7h/8rQ22rSRLrzQDLW2apV5LDMzzdBQ5eVm2I+iItMV4m25qMj7cGY1YbOZYe2efFLKyQnNOcPF0bX122/OLrSSEvMc37bNLDuGqnDtjlu/3jmUzc6d5rmyfbt1HhnEjlatzLAenTqZn9nvvzfDOTqGE3EM7yU5hxVyDGNUk2FGvGnWzMxhlZJink8OjvCwvNyEwA0aOIdBSksztScmmuff2rXW4XS8DWvlPpSbt2XJOUSZ4/eDYxi7jAwT2juGsdmxwzxmjvHl9+41X0tKnG9a2e3OoTeLi4P7pL77tpISz9+dCQmxG446/v5w/TsEoZeZaeZT277drDuC9YIC8zeM61B1iD2Jiaaze8wY8zdQerrpPNizx7xm79hhPqTTtav5Xjv+tnPMr+H4ne74fekYOtB1qDnH8GOOn9XKSu/DVJaVmd9zZWXOodYcw7FWVjqHQDxwwLy+rFpl6i8u9hzqz/VSWWkd2i7a+Bs60NuwZcnJzg9Ode1qPkjz/ffmcXEMRbtvn3lcXF/PysudryeOYfwcIUlGhjlfp07mf5K//MV871esMPNY8q81AACIdcGEKkl1VJNXO3bsUEVFhbKysizbs7Ky9KuP8Wny8/O9Hp+fn+/1+ClTpmgSA676VVEhXX65+efo11+d472npJg3qJs0Mcc5/plJTzefOsrONm9SNWtm/oguKDDXTU01l6ws09HhOr72nj3O8fNjgc1mQp9wysgw3S6uOnY0k4CGgut4+JGSlmbCHIdu3cwlnBwTpfsagz893YQ2rv9A22zmjYBt26xvOqanm38ea/u8dYy/7ngT1dGx4/pmgbdl1/WMDDO/QiBzCkWD1FTzyUX30RkPP7xm5ystNW8w79hhur4c8664f39d35T3NveFr2Wbzfw8dupkDSYTEsz3zvEGvGMMdccbha5fHcuO4bkcXT6u30fHV0dA6mtOBAfHGz6O+1Ve7pwLxFGL+yUpyTw2rvO5+Bsax3UeAfc5BXw9L/09Vx1vnvXoYd5sqWl4a7dbv5/evtcNGpjHwmazzvtQXm5eixxzdiAwjuel63xTju+B6xukJSXON0/dgybJd4jj+Llr2NCEVjabdY4KR7haWGjO42u+JF/z7DgujRo5h5ux283PYkGBdS4jxzkkZ43env++1h3zZezfb96gPHjQ3K9du8zPfzCBlvvj4/57ytd6YqLn/XF8wOL/2rv/sCrr+4/jr3P4jSJqiijCVzSzXIo/CCaR5hTzUlna1Jw61HW5iEulNTNnbQ0rSE0yt2WyknZZzmkpXtcMrhB1U/DScDnU1Mm6kFJQyxREfhzgfP/gOkcoy4Mi94HzfFyXf3C4z+H9AXzdN5/3+dyf7t2vrxBtPMHt5tZwXXDtWsNxPj7X9xKqqbn+r/H3yjbp3fj77ufXcC79odv62JpZtknaxvu6NP5Z2ybFvz0xXF3d8HOzWhuasUePNnw922bYVVUNx/XseeP9hG62x5DtjSg3+p217TfSeKLflq22vT3+7/8avjfe3g3XzLY3hzT+P+Hj0/Dcy5evX2/Y9huxZeO3M/RGjznyeYul4Xtpmwi3/Z42/v1pfNvIxvlq29OkMTe3hvOibaVBbOz3/6zbi8b7lDTeA6hxHjbOxMZ+6Hetuf8a56mz6t69ZW7XDAAA0NYY2lRpDb/97W/1zDPP2D+2rVTBdX37Sunp1z+2TUS19H1vbe/4Retyb/f/y2/M3b1hYutmbvR7HhLS8vVI1xuO3brdmdd3BZ6eDTkSGPjdRs2dYGscwziN95Lx9ja6Gtdgm/S+2WMtyfazvVMrV02mhnOCI+eF5rK9+QQ3ZpsUtq0Es/H1db3vXc+erfN1+FPn9phM11fPAAAAADdi6HRrt27d5ObmpvPnzzd5/Pz58wr8ntn3wMDAZh3v5eUlL96e2iy2dwYCAAAAAAAAAIDr7vBOCj/M09NTw4cPV05Ojv2x+vp65eTkaMT33PtoxIgRTY6XpOzs7O89HgAAAAAAAAAAoCUYfmOgZ555RnPmzFF4eLgiIiK0Zs0aVVRUaN68eZKkuLg4BQUFKSUlRZKUmJioUaNGafXq1Zo4caI2b96s/Px8paWlGTkMAAAAAAAAAADQzhneVHn88cd18eJF/f73v1dpaamGDBmirKws+2b0xcXFMjfa3TYqKkqbNm3SCy+8oGXLlql///7KyMjQ/a1xc30AAAAAAAAAAOCyTFar1Wp0Ea2prKxM/v7+unLlijp16mR0OQAAAAAAAAAAwEDN6RsYuqcKAAAAAAAAAABAW0FTBQAAAAAAAAAAwAE0VQAAAAAAAAAAABxAUwUAAAAAAAAAAMABNFUAAAAAAAAAAAAcQFMFAAAAAAAAAADAATRVAAAAAAAAAAAAHEBTBQAAAAAAAAAAwAE0VQAAAAAAAAAAABxAUwUAAAAAAAAAAMABNFUAAAAAAAAAAAAcQFMFAAAAAAAAAADAATRVAAAAAAAAAAAAHOBudAGtzWq1SpLKysoMrgQAAAAAAAAAABjN1i+w9Q9+iMs1VcrLyyVJwcHBBlcCAAAAAAAAAACcRXl5ufz9/X/wGJPVkdZLO1JfX69z587Jz89PJpPJ6HJwC8rKyhQcHKwvvvhCnTp1MrocAC6MPALgTMgkAM6ETALgLMgjAI6wWq0qLy9Xr169ZDb/8K4pLrdSxWw2q3fv3kaXgRbQqVMnToYAnAJ5BMCZkEkAnAmZBMBZkEcAbuZmK1Rs2KgeAAAAAAAAAADAATRVAAAAAAAAAAAAHEBTBW2Ol5eXXnzxRXl5eRldCgAXRx4BcCZkEgBnQiYBcBbkEYCW5nIb1QMAAAAAAAAAANwKVqoAAAAAAAAAAAA4gKYKAAAAAAAAAACAA2iqAAAAAAAAAAAAOICmCgAAAAAAAAAAgANoqgAA8D2sVqvRJQAAAAAAAMCJ0FSBUyktLdW5c+dUWVkpSaqvrze4IgCuqry8vMnHNFgAGMl2bQQAzoTrIwBGq62tNboEAC7IZOUqCE7AYrFowYIF+vjjj9W1a1f5+fkpKytL3t7eRpcGwMVYLBYtXLhQx48fV0BAgB599FHFxcUZXRYAF2WxWLRo0SIVFRWpe/fuSkhIUGRkpEwmk9GlAXBBFotFb7zxhvr166cpU6YYXQ4AF1ZTU6MXXnhBX331lTp37qwFCxaob9++RpcFwEWwUgWGO3v2rEaOHKnTp09r06ZNSkxM1BdffKGlS5caXRoAF/P555/rgQce0MmTJ7VkyRL5+/vr1VdfVXx8vNGlAXBBpaWlioyMVEFBgWJjY1VQUKD4+HitWrVKEit6AbSuzMxMhYWFacmSJfrwww917tw5SaxWAdD6tm7dqtDQUOXn56t37976+9//rvj4eOXl5RldGgAXQVMFhtu3b58qKyu1adMmjRgxQnFxcYqOjpafn5/RpQFwMZmZmerSpYs++ugjxcbG6p133tGiRYuUlpambdu2MYEJoFXl5uaqpqZGW7ZsUUJCgv75z39qypQpevHFF3X8+HGZzWYmMwG0ioqKCm3fvl0xMTFKTk7WqVOntGPHDkli5RyAVnXkyBGlp6dr4cKF2r17t5YvX66DBw+qsLBQRUVFRpcHwEXQVIHhLl++rNOnTyswMFCSVFJSooKCAnXt2lX79+83uDoArqSwsFC1tbXy9fWV1WqVyWSyT1gmJyfr66+/NrhCAK7A1sC9ePGivvnmGwUFBUmS/P399eSTTyo6OlpPPvmkJCYzAbQOX19fzZ07VwkJCVq6dKlCQkKUmZmpgoICSaycA9B6ampqNHDgQPstmi0Wi3r37q0uXbroxIkTBlcHwFXQVEGrOnTokKSmF90jRoyQv7+/IiMjNXXqVIWEhMjf3187d+7UhAkTtHz5clksFqNKBtBO3SiP/Pz85O3trY8++sg+UZmbm6ukpCQdO3ZMWVlZ33kOALSEDz74QLt27VJJSYnM5oZLdDc3NwUGBmrfvn324wIDA7V06VJ98sknys7OlsStdwC0vMaZJDU0cKOiojRgwABJUnx8vL788ktt375dVqvVnlsA0NJseWS75WBERIRee+019erVS5Lk4eGhK1euqKKiQg8++KCRpQJwIVz5oFVkZGQoKChIEyZMUFFRkcxms2prayVJYWFhysvLU1JSkk6cOKENGzZo79692rVrl9atW6eVK1fq/PnzBo8AQHtxozyqqamRJP385z9Xx44dNXPmTM2YMUN+fn46ffq0nnjiCU2ePFlbt26VJCYOALSYjRs3qkePHlq1apVmzpypadOmadu2bZKk8PBwVVVVKS8vz55TknT//fdr/Pjx2rhxoyRWqwBoOTfKpIyMDEkNbyqxNXFjYmI0YsQI7dmzR7t375ZEgxdAy/p2Hk2fPt2eR1artckb3S5fvqz6+nr179/foGoBuBpmhXDHvf/++0pOTtbIkSN133336dVXX5Ukubu724/p06ePvvnmG7m5uWn27Nn2k2N0dLRqamrsy8oB4HZ8Xx55enrKarXqvvvu09q1a/X666+rW7dueu+993Tw4EH16tVLNTU1CgkJMXgEANqL2tpavfHGG0pJSVFycrL27dunjIwM9evXT2+//bYqKys1dOhQRUdHa9u2bU02Xu3Ro4c8PDxo8AJoMT+USWlpaaqurpbZbJbJZLL/rbZw4UJVVVVpx44dqqiokNVq1X//+1+DRwKgrXMkj0wmU5O95fbu3StJ9tUrknTp0iUjygfgIvhLDHdMXV2dJOnuu+/WmDFjtGLFCv30pz/V3r177Sc82zGS7MvGL1y4YJ8k2Llzp4YNG6aIiIhWrx9A+9GcPAoODta8efP0pz/9SY8++qgkqbS0VMXFxbr77rsNqR9A+1NRUaGLFy9qzpw5mjdvnjw9PRUVFaWBAweqrKzMvjIlKSlJFotFaWlpOnv2rP35lZWV6tq1q1HlA2hnbpZJtrsMSLJPZN57772aMmWK8vPz9fLLL+uBBx7QrFmzmvyNBwDN1Zw8sq3WzcjI0MSJE+Xj46MjR45o3Lhxeumll1hBB+COoamCFnf69GlZrVa5ublJkiIjI/XSSy8pJCREEyZM0IABA7Rq1SpJDfcKt73TKSAgQJ07d9bYsWO1fv16/fKXv9Tvfvc7zZgxQ926dTNsPADarubkkbu7+3cuus+cOaOzZ89q8eLFqq+v12OPPdbqYwDQftgySWrYdH7q1KlavHixzGaz/XooODhYFRUV8vHxkdSwh8qyZcv05Zdf6sEHH1Rqaqri4uKUn59PJgG4Lc3JJA8PjybPtT1vzJgxys/P14oVKxQeHq7c3Fz7dRcAOOp28qiiokJlZWWKjIxUQkKCwsPDFRAQoJUrV3KLVAB3DE0VtJgtW7YoNDRUsbGx+vGPf6wNGzbYP2e7sP7Rj36kyZMnq6ioSOnp6ZKub/g8duxYJScnKzQ0VNu3b9elS5eUl5enp59+utXHAqBtu9U8atxUqays1Ntvv63BgweruLhYW7du5fZfAG7JtzPpnXfekSQNGTLE/gaTxqt0hwwZIk9PT/tqlalTp+pvf/ubHnnkEe3bt09ff/21/vWvfyk6OtqwMQFou241k769WuWtt95SRESERo8ercLCQq1fv16enp6GjAlA29QSeVRYWKg9e/Zo5syZ+vTTT3X06FG9995732m+AEBLcr/5IcDNZWdn67nnntOzzz6rfv366eOPP1Z8fLzq6uo0e/Zs+fj4qLa2Vu7u7ho3bpxyc3O1bt06TZs2TR07dlR1dbW8vLwUFRWljIwMlZeXy9/f3+hhAWiDbjePLBaLPDw85OPjo6lTpyomJkYjR440elgA2qgbZdJTTz2l+vp6/eIXv5C3t7dMJpOsVquqq6t17NgxPfvss5LUZHIyKChI69evV1VVlby9vY0aDoA27nYyqfGemJIUFRWlzZs3a/r06UYMBUAb11J5VFZWplGjRun555/X2LFjjRoOABdDUwW3xWq1ymQy6cCBA7rrrrs0f/58eXh46JFHHlFVVZXS0tLUrVs3TZkyxX7SCwoK0pQpU/Sf//xHr732mh577DE9//zzevPNNxUcHCyz2UxDBUCz3Yk8CgsLM3hUANqq5mSS7dYUly5dst++Qmq4Fca6deuUmppqf10aKgBuxZ3IpMGDB2vw4MGGjQlA29RSefTmm2/q9ddf10MPPaQ9e/YYOSQALojbf+G22E5wn332mfr16ycPDw9ZLBZJ0ssvvyxvb2/t2LFDpaWlkq5vBD169GhFRERo+fLlGj58uCwWiwICAowZBIB2gTwC4Eyam0mStGvXLgUHB6tnz55KTEzUwIEDdebMGVksFjZaBXBbyCQAzqKl8qi4uFgWi8V+S3kAaE00VdAs2dnZWrRokdasWaNDhw7ZHx8zZowyMzNVV1dnPyF26dJFcXFxOnDggE6dOiWpYS+DiooKpaWlaf369Ro1apT+/e9/KysrS15eXkYNC0AbRB4BcCa3mkknT56U1PCuzX/84x86duyY+vTpo5ycHB04cEAffvihPDw82GgVQLOQSQCcxZ3OI9ueKwDQmkgeOKSkpESxsbGaPXu2Ll26pA0bNmjcuHH2E+KoUaPUqVMnJSUlSbq+2fP8+fNVVlamTz/91P5aZ86c0ebNm5Wenq49e/Zo0KBBrT8gAG0WeQTAmdxuJh05ckSSVFlZqcrKSnXo0EF//vOfdezYMYWHhxsyJgBtF5kEwFmQRwDaM5OVdbu4iWvXrikhIUFVVVVKSUlRaGioJCkyMlIDBw5Uenq6ysvLtXbtWr3yyis6deqUgoOD7ffJfPjhh9W/f3/95S9/MXgkANo68giAM2npTDp8+LCGDx9u5JAAtGFkEgBnQR4BaO9YqYKb8vX1lZeXl+bOnavQ0FDV1tZKkiZMmKATJ07IarXKz89PM2fO1LBhwzR9+nSdOXNGJpNJxcXFunDhgiZPnmzsIAC0C+QRAGfS0pnEZAGA20EmAXAW5BGA9o6VKnCIxWKRh4eHJKm+vl5ms1mzZs1Shw4dlJaWZj/u7Nmzevjhh1VbW6vw8HDl5eXp3nvv1aZNm9SjRw+jygfQjpBHAJwJmQTAmZBJAJwFeQSgPaOpglsWHR2t+fPna86cOaqvr5ckmc1mFRYW6vDhwzp48KDCwsI0Z84cgysF0N6RRwCcCZkEwJmQSQCcBXkEoL2gqYJb8vnnnysqKko7d+60L8OsqamRp6enwZUBcDXkEQBnQiYBcCZkEgBnQR4BaE/YUwXNYuvB7d+/Xx07drSfCJOSkpSYmKgLFy4YWR4AF0IeAXAmZBIAZ0ImAXAW5BGA9sjd6ALQtphMJknSoUOH9LOf/UzZ2dn61a9+pWvXrmnjxo0KCAgwuEIAroI8AuBMyCQAzoRMAuAsyCMA7RG3/0KzVVVVadCgQfrf//4nT09PJSUl6bnnnjO6LAAuiDwC4EzIJADOhEwC4CzIIwDtDU0V3JKYmBj1799fqamp8vb2NrocAC6MPALgTMgkAM6ETALgLMgjAO0JTRXckrq6Orm5uRldBgCQRwCcCpkEwJmQSQCcBXkEoD2hqQIAAAAAAAAAAOAAs9EFAAAAAAAAAAAAtAU0VQAAAAAAAAAAABxAUwUAAAAAAAAAAMABNFUAAAAAAAAAAAAcQFMFAAAAAAAAAADAATRVAAAAAAAAAAAAHEBTBQAAAAAAAAAAwAE0VQAAAAC0aXPnzpXJZJLJZJKHh4d69OihmJgYbdiwQfX19Q6/zrvvvqvOnTvfuUIBAAAAtHk0VQAAAAC0eePHj1dJSYmKioqUmZmp0aNHKzExUZMmTVJtba3R5QEAAABoJ2iqAAAAAGjzvLy8FBgYqKCgIA0bNkzLli3Tjh07lJmZqXfffVeSlJqaqkGDBqlDhw4KDg5WQkKCrl69Kknau3ev5s2bpytXrthXvfzhD3+QJFVXV2vx4sUKCgpShw4dFBkZqb179xozUAAAAACGoqkCAAAAoF36yU9+orCwMG3btk2SZDabtXbtWh0/flx//etftXv3bi1ZskSSFBUVpTVr1qhTp04qKSlRSUmJFi9eLElasGCBDhw4oM2bN6ugoEDTpk3T+PHjdfr0acPGBgAAAMAYJqvVajW6CAAAAAC4VXPnztXly5eVkZHxnc/NmDFDBQUF+uyzz77zuQ8++EDx8fH66quvJDXsqfL000/r8uXL9mOKi4vVt29fFRcXq1evXvbHx44dq4iICCUnJ7f4eAAAAAA4L3ejCwAAAACAO8VqtcpkMkmSdu3apZSUFJ08eVJlZWWqra1VVVWVrl27Jl9f3xs+/+jRo6qrq9M999zT5PHq6mrdddddd7x+AAAAAM6FpgoAAACAduvEiRMKDQ1VUVGRJk2apKeeekqvvPKKunbtqv379+uJJ55QTU3N9zZVrl69Kjc3Nx0+fFhubm5NPtexY8fWGAIAAAAAJ0JTBQAAAEC7tHv3bh09elS//vWvdfjwYdXX12v16tUymxu2ltyyZUuT4z09PVVXV9fksaFDh6qurk4XLlzQQw891Gq1AwAAAHBONFUAAAAAtHnV1dUqLS1VXV2dzp8/r6ysLKWkpGjSpEmKi4vTsWPHZLFY9Mc//lGxsbHKzc3VW2+91eQ1+vTpo6tXryonJ0dhYWHy9fXVPffco1mzZikuLk6rV6/W0KFDdfHiReXk5Gjw4MGaOHGiQSMGAAAAYASz0QUAAAAAwO3KyspSz5491adPH40fP1579uzR2rVrtWPHDrm5uSksLEypqalasWKF7r//fr3//vtKSUlp8hpRUVGKj4/X448/ru7du2vlypWSpPT0dMXFxek3v/mNBgwYoMmTJ+uTTz5RSEiIEUMFAAAAYCCT1Wq1Gl0EAAAAAAAAAACAs2OlCgAAAAAAAAAAgANoqgAAAAAAAAAAADiApgoAAAAAAAAAAIADaKoAAAAAAAAAAAA4gKYKAAAAAAAAAACAA2iqAAAAAAAAAAAAOICmCgAAAAAAAAAAgANoqgAAAAAAAAAAADiApgoAAAAAAAAAAIADaKoAAAAAAAAAAAA4gKYKAAAAAAAAAACAA2iqAAAAAAAAAAAAOOD/AbHeGG6As3RZAAAAAElFTkSuQmCC\n" }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "data[\"gap\"] = (data[\"High\"] - data[\"Low\"]) * data[\"Volume\"]\n", "data[\"y\"] = data[\"High\"] / data[\"Volume\"]\n", "data[\"z\"] = data[\"Low\"] / data[\"Volume\"]\n", "data[\"a\"] = data[\"High\"] / data[\"Low\"]\n", "data[\"b\"] = (data[\"High\"] / data[\"Low\"]) * data[\"Volume\"]\n", "abs(data.corr()[\"Close\"].sort_values(ascending=False))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "nOJGiogCXUyz", "outputId": "b29895e2-ba97-4f65-9769-dc84c3e5344a" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Close 1.000000\n", "Adj Close 1.000000\n", "High 0.995104\n", "Low 0.994575\n", "Open 0.992514\n", "Volume 0.588678\n", "b 0.456479\n", "gap 0.383333\n", "a 0.172057\n", "z 0.063251\n", "y 0.063868\n", "Name: Close, dtype: float64" ] }, "metadata": {}, "execution_count": 12 } ] }, { "cell_type": "code", "source": [ "data = data[[\"Close\", \"Volume\", \"gap\", \"a\", \"b\"]]\n", "data.head()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 237 }, "id": "YG-STLA4XWJf", "outputId": "f6dae5db-b377-4aaf-c311-f0573c3e4a4c" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " Close Volume gap a b\n", "Date \n", "2017-11-09 0.001415 6259550.0 1464.73470 1.198137 7.499800e+06\n", "2017-11-10 0.001163 4246520.0 1299.43512 1.272000 5.401573e+06\n", "2017-11-11 0.001201 2231080.0 258.80528 1.101665 2.457903e+06\n", "2017-11-12 0.001038 3288960.0 684.10368 1.207585 3.971698e+06\n", "2017-11-13 0.001211 2481270.0 478.88511 1.189401 2.951226e+06" ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
CloseVolumegapab
Date
2017-11-090.0014156259550.01464.734701.1981377.499800e+06
2017-11-100.0011634246520.01299.435121.2720005.401573e+06
2017-11-110.0012012231080.0258.805281.1016652.457903e+06
2017-11-120.0010383288960.0684.103681.2075853.971698e+06
2017-11-130.0012112481270.0478.885111.1894012.951226e+06
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "data", "summary": "{\n \"name\": \"data\",\n \"rows\": 1760,\n \"fields\": [\n {\n \"column\": \"Date\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": \"2017-11-09 00:00:00\",\n \"max\": \"2022-09-04 00:00:00\",\n \"num_unique_values\": 1760,\n \"samples\": [\n \"2020-12-08 00:00:00\",\n \"2020-09-04 00:00:00\",\n \"2022-06-19 00:00:00\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Close\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.10137868294094772,\n \"min\": 0.001038,\n \"max\": 0.684777,\n \"num_unique_values\": 1543,\n \"samples\": [\n 0.06428,\n 0.286808,\n 0.221383\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Volume\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3563999366.5691385,\n \"min\": 1431720.0,\n \"max\": 69410680685.0,\n \"num_unique_values\": 1760,\n \"samples\": [\n 52702701.0,\n 53434717.0,\n 1166163984.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"gap\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 671007665.0051335,\n \"min\": 115.96931999999987,\n \"max\": 17853260000.35022,\n \"num_unique_values\": 1760,\n \"samples\": [\n 11752.702322999983,\n 10954.116985000017,\n 13019054.717376001\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"a\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.1474660717884617,\n \"min\": 1.0012287168685272,\n \"max\": 4.649299415045572,\n \"num_unique_values\": 1757,\n \"samples\": [\n 1.0335659687603855,\n 1.0457902511078287,\n 1.127043631786045\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"b\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6325954244.057025,\n \"min\": 1518264.2686567162,\n \"max\": 168327284560.88214,\n \"num_unique_values\": 1760,\n \"samples\": [\n 56447985.36042064,\n 57413691.567744285,\n 1419907156.943323\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 13 } ] }, { "cell_type": "code", "source": [ "df2 = data.tail(30)\n", "train = df2[:11]\n", "test = df2[-19:]\n", "\n", "print(train.shape, test.shape)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "35vsRHEOXXSu", "outputId": "59471739-9cb1-4930-bfc6-0fb2950ec2ae" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "(11, 5) (19, 5)\n" ] } ] }, { "cell_type": "code", "source": [ "from statsmodels.tsa.statespace.sarimax import SARIMAX\n", "model = SARIMAX(endog=train[\"Close\"], exog=train.drop(\n", "\t\"Close\", axis=1), order=(2, 1, 1))\n", "results = model.fit()\n", "print(results.summary())" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "s0d_2WPjXYm7", "outputId": "c0cbc928-a3bb-43de-d4b7-a55e6e502ada" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: No frequency information was provided, so inferred frequency D will be used.\n", " self._init_dates(dates, freq)\n", "/usr/local/lib/python3.10/dist-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: No frequency information was provided, so inferred frequency D will be used.\n", " self._init_dates(dates, freq)\n", "/usr/local/lib/python3.10/dist-packages/statsmodels/tsa/statespace/sarimax.py:966: UserWarning: Non-stationary starting autoregressive parameters found. Using zeros as starting parameters.\n", " warn('Non-stationary starting autoregressive parameters'\n", "/usr/local/lib/python3.10/dist-packages/statsmodels/base/model.py:607: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n", " warnings.warn(\"Maximum Likelihood optimization failed to \"\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ " SARIMAX Results \n", "==============================================================================\n", "Dep. Variable: Close No. Observations: 11\n", "Model: SARIMAX(2, 1, 1) Log Likelihood 47.663\n", "Date: Sun, 22 Sep 2024 AIC -79.326\n", "Time: 10:55:10 BIC -76.905\n", "Sample: 08-05-2022 HQIC -81.981\n", " - 08-15-2022 \n", "Covariance Type: opg \n", "==============================================================================\n", " coef std err z P>|z| [0.025 0.975]\n", "------------------------------------------------------------------------------\n", "Volume 7.491e-10 1.84e-10 4.077 0.000 3.89e-10 1.11e-09\n", "gap 1.13e-08 2.45e-09 4.615 0.000 6.5e-09 1.61e-08\n", "a -0.0073 5.05e-15 -1.44e+12 0.000 -0.007 -0.007\n", "b -7.541e-10 1.83e-10 -4.126 0.000 -1.11e-09 -3.96e-10\n", "ar.L1 -0 8.45e-15 -0 1.000 -1.66e-14 1.66e-14\n", "ar.L2 0 2.59e-14 0 1.000 -5.07e-14 5.07e-14\n", "ma.L1 -0.5015 1.87e-14 -2.68e+13 0.000 -0.501 -0.501\n", "sigma2 3.673e-07 5.67e-08 6.481 0.000 2.56e-07 4.78e-07\n", "===================================================================================\n", "Ljung-Box (L1) (Q): 0.15 Jarque-Bera (JB): 0.51\n", "Prob(Q): 0.70 Prob(JB): 0.77\n", "Heteroskedasticity (H): 0.40 Skew: -0.54\n", "Prob(H) (two-sided): 0.47 Kurtosis: 2.72\n", "===================================================================================\n", "\n", "Warnings:\n", "[1] Covariance matrix calculated using the outer product of gradients (complex-step).\n", "[2] Covariance matrix is singular or near-singular, with condition number 2.55e+29. Standard errors may be unstable.\n" ] } ] }, { "cell_type": "code", "source": [ "start = 11\n", "end = 29\n", "predictions = results.predict(\n", "\tstart=start,\n", "\tend=end,\n", "\texog=test.drop(\"Close\", axis=1))\n", "predictions" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "HzO3l0S7XZ_E", "outputId": "64677992-f312-45ff-f04b-70cce71e326c" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "2022-08-16 0.097293\n", "2022-08-17 0.083717\n", "2022-08-18 0.075957\n", "2022-08-19 0.069575\n", "2022-08-20 0.071583\n", "2022-08-21 0.072099\n", "2022-08-22 0.071244\n", "2022-08-23 0.072458\n", "2022-08-24 0.072406\n", "2022-08-25 0.071893\n", "2022-08-26 0.068140\n", "2022-08-27 0.071804\n", "2022-08-28 0.071866\n", "2022-08-29 0.071522\n", "2022-08-30 0.070720\n", "2022-08-31 0.071736\n", "2022-09-01 0.071452\n", "2022-09-02 0.072203\n", "2022-09-03 0.072785\n", "Freq: D, Name: predicted_mean, dtype: float64" ] }, "metadata": {}, "execution_count": 16 } ] }, { "cell_type": "code", "source": [ "test[\"Close\"].plot(legend=True, figsize=(12, 6))\n", "predictions.plot(label='TimeSeries', legend=True)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 355 }, "id": "rpTvpjYGXbLR", "outputId": "e0a3aee5-4295-47cc-e3a9-92f5d18f3e1f" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": {}, "execution_count": 17 }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ] } ] }