Skip to content

Instantly share code, notes, and snippets.

@TatheerHussain
Created February 27, 2020 07:30
Show Gist options
  • Save TatheerHussain/800f6d0519ecd9ec0d6def4950278772 to your computer and use it in GitHub Desktop.
Save TatheerHussain/800f6d0519ecd9ec0d6def4950278772 to your computer and use it in GitHub Desktop.
CosDistance.ipynb
Display the source blob
Display the rendered blob
Raw
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "CosDistance.ipynb",
"provenance": [],
"authorship_tag": "ABX9TyNnL9xVw4vcybxT8N7dpkG7",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/TatheerHussain/800f6d0519ecd9ec0d6def4950278772/cosdistance.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"metadata": {
"id": "97l6HN7IjJak",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 996
},
"outputId": "aefeda3a-cf85-475f-bca5-2f103a2234ba"
},
"source": [
"from numpy import *\n",
"from numpy import dot\n",
"from numpy.linalg import norm\n",
"import numpy as np\n",
"import pandas as pd\n",
"import math\n",
"import matplotlib.pyplot as plt\n",
"\n",
"\n",
"def cosine_distance(a, b):\n",
" return 1 - cosine_similarity(a,b)\n",
"\n",
"\n",
"def cosine_similarity(a, b):\n",
" return dot(a, b) / (norm(a) * norm(b))\n",
"\n",
"\n",
"def find_end_points(point, angle, length):\n",
" '''\n",
" #Source - https://stackoverflow.com/questions/28417604/plotting-a-line-from-a-coordinate-with-and-angle\n",
" #\n",
" point - Tuple (x, y)\n",
" angle - Angle you want your end point at in degrees.\n",
" length - Length of the line you want to plot.\n",
"\n",
" Will plot the line on a 10 x 10 plot.\n",
" '''\n",
"\n",
" # unpack the first point\n",
" x, y = point\n",
"\n",
" # find the end point\n",
" endy = length * math.sin(math.radians(angle))\n",
" endx = length * math.cos(math.radians(angle))\n",
"\n",
" # plot the points\n",
" # fig = plt.figure()\n",
" # ax = plt.subplot(111)\n",
"\n",
" return ([x, endx], [y, endy])\n",
" # ax.plot([x, endx], [y, endy])\n",
"\n",
" # return fig\n",
"\n",
"\n",
"column_header = ['D0', 'D1', 'D2', 'D3', 'D4', 'D5', 'D6', 'D7', 'D8', 'D9', 'D10']\n",
"row_header = ['D0', 'D1', 'D2', 'D3', 'D4', 'D5', 'D6', 'D7', 'D8', 'D9', 'D10']\n",
"doc_term = array([\n",
" # D0 D1 D2 D3 D4 D5 D6 D7 D8 D9 D10 D11\n",
" [0.1, 0.1, 0.0, 0.1, 0.2, 0.0, 0.1, 0.9, 0.9, 0.3, 0.0, 0.8],\n",
" [0.1, 0.1, 0.0, 0.1, 0.0, 0.0, 0.1, 0.9, 0.0, 0.3, 0.0, 0.8],\n",
" [0.0, 0.0, 0.9, 0.0, 0.3, 0.1, 0.7, 0.0, 0.2, 0.7, 0.5, 0.5],\n",
" [0.0, 0.0, 0.9, 0.1, 0.0, 0.1, 0.9, 0.3, 0.8, 0.4, 0.1, 0.4],\n",
" [0.0, 0.0, 0.0, 0.0, 0.5, 0.9, 0.3, 0.7, 0.4, 0.6, 0.0, 0.3],\n",
" [0.5, 0.6, 0.0, 0.7, 0.3, 0.3, 0.9, 0.1, 0.0, 0.0, 0.0, 0.3],\n",
" [0.0, 0.0, 0.8, 0.0, 0.6, 0.6, 0.0, 0.1, 0.4, 0.9, 0.3, 0.1],\n",
" [0.35, 0.4, 0.0, 0.5, 0.5, 0.1, 0.7, 0.1, 0.5, 0.3, 0.8, 0.1],\n",
" [0.3, 0.3, 0.0, 0.2, 0.8, 0.7, 0.7, 0.8, 0.0, 0.6, 0.8, 0.0],\n",
" [0.0, 0.0, 0.5, 0.0, 0.2, 0.0, 0.0, 0.1, 0.0, 0.4, 0.5, 0.3]\n",
"])\n",
"\n",
"cos_similarity_list = []\n",
"pd_cols_cos_similarity = []\n",
"cos_distance_list = []\n",
"pd_cols_cos_distance = []\n",
"\n",
"for i in range(0, 11):\n",
" for j in range(0, 11):\n",
" cos_value = cosine_similarity(transpose(doc_term[:, [i]]), doc_term[:, [j]])\n",
" cos_distance = 1.0 - cos_value\n",
" cos_distance_list.append(asscalar(around(cos_distance,decimals=3)))\n",
" cos_similarity_list.append(\n",
" asscalar(around(math.degrees(math.acos(min(max(cos_value, -1.0), 1.0))), decimals=1)))\n",
" pd_cols_cos_similarity.append(cos_similarity_list)\n",
" pd_cols_cos_distance.append(cos_distance_list)\n",
"\n",
" cos_similarity_list = []\n",
" cos_distance_list = []\n",
"\n",
"df_cos_sim = pd.DataFrame(pd_cols_cos_similarity, columns=column_header, index=row_header)\n",
"print(df_cos_sim)\n",
"\n",
"df_cos_dist = pd.DataFrame(pd_cols_cos_distance, columns=column_header, index=row_header)\n",
"print(df_cos_dist)\n",
"\n",
"fig = plt.figure()\n",
"ax = plt.subplot(111)\n",
"ax.set_ylim([0, 1.75])\n",
"ax.set_xlim([0, 1.75])\n",
"\n",
"ref_doc = 0\n",
"for i in range(0, 11):\n",
" X, Y = find_end_points([0, 0], df_cos_sim.iloc[ref_doc][i], norm(doc_term[:, [i]]))\n",
" ax.plot(X, Y)\n",
" ax.annotate(\"\", xy=(X[1], Y[1]), xytext=(0, 0), arrowprops=dict(arrowstyle=\"->\"))\n",
" ax.text(X[1], Y[1], \"D\" + str(ref_doc) + \"-\" + \"D\" + str(i) + \"-(\" + str(df_cos_sim.iloc[ref_doc][i]) + u\"\\u00b0\" + \")\")\n",
"fig.show()\n",
"query = \"D\" + str(ref_doc)\n",
"rank_order = df_cos_sim.sort_values(query)\n",
"print (\"\\n\\nDocument Rank for the query \", query)\n",
"print(rank_order[query])"
],
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"text": [
"/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:71: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead\n",
"/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:73: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead\n"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
" D0 D1 D2 D3 D4 D5 D6 D7 D8 D9 D10\n",
"D0 0.0 4.0 90.0 14.6 50.6 64.8 41.9 64.6 74.6 72.1 56.9\n",
"D1 4.0 0.0 90.0 11.5 52.6 66.0 42.3 67.3 75.3 73.7 59.0\n",
"D2 90.0 90.0 0.0 86.4 66.1 71.8 59.5 81.4 57.6 41.7 61.7\n",
"D3 14.6 11.5 86.4 0.0 57.6 70.0 40.2 71.3 71.0 75.3 62.5\n",
"D4 50.6 52.6 66.1 57.6 0.0 29.5 48.9 53.8 60.8 31.9 36.1\n",
"D5 64.8 66.0 71.8 70.0 29.5 0.0 58.1 54.3 66.9 40.5 61.2\n",
"D6 41.9 42.3 59.5 40.2 48.9 58.1 0.0 63.0 56.4 53.5 50.5\n",
"D7 64.6 67.3 81.4 71.3 53.8 54.3 63.0 0.0 54.3 51.1 69.1\n",
"D8 74.6 75.3 57.6 71.0 60.8 66.9 56.4 54.3 0.0 50.3 69.2\n",
"D9 72.1 73.7 41.7 75.3 31.9 40.5 53.5 51.1 50.3 0.0 44.5\n",
"D10 56.9 59.0 61.7 62.5 36.1 61.2 50.5 69.1 69.2 44.5 0.0\n",
" D0 D1 D2 D3 D4 ... D6 D7 D8 D9 D10\n",
"D0 0.000 0.002 1.000 0.032 0.365 ... 0.256 0.572 0.734 0.693 0.454\n",
"D1 0.002 0.000 1.000 0.020 0.392 ... 0.260 0.614 0.745 0.719 0.485\n",
"D2 1.000 1.000 0.000 0.937 0.596 ... 0.492 0.851 0.463 0.254 0.526\n",
"D3 0.032 0.020 0.937 0.000 0.464 ... 0.236 0.679 0.675 0.746 0.538\n",
"D4 0.365 0.392 0.596 0.464 0.000 ... 0.343 0.409 0.512 0.151 0.192\n",
"D5 0.574 0.594 0.688 0.659 0.130 ... 0.472 0.417 0.608 0.239 0.519\n",
"D6 0.256 0.260 0.492 0.236 0.343 ... -0.000 0.545 0.447 0.405 0.364\n",
"D7 0.572 0.614 0.851 0.679 0.409 ... 0.545 -0.000 0.417 0.373 0.643\n",
"D8 0.734 0.745 0.463 0.675 0.512 ... 0.447 0.417 -0.000 0.362 0.644\n",
"D9 0.693 0.719 0.254 0.746 0.151 ... 0.405 0.373 0.362 0.000 0.287\n",
"D10 0.454 0.485 0.526 0.538 0.192 ... 0.364 0.643 0.644 0.287 -0.000\n",
"\n",
"[11 rows x 11 columns]\n",
"\n",
"\n",
"Document Rank for the query D0\n",
"D0 0.0\n",
"D1 4.0\n",
"D3 14.6\n",
"D6 41.9\n",
"D4 50.6\n",
"D10 56.9\n",
"D7 64.6\n",
"D5 64.8\n",
"D9 72.1\n",
"D8 74.6\n",
"D2 90.0\n",
"Name: D0, dtype: float64\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAD4CAYAAAD8Zh1EAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjMsIGh0\ndHA6Ly9tYXRwbG90bGliLm9yZy+AADFEAAAgAElEQVR4nOydd1gU1/fG36EJSJOmCAoioPRi16jY\nEBv23qMxthhjLDFGjSZCNPo1Ro2xa2Kixl5i7z2CiopGsWABVMCCiLTdeX9/IPuj7ALG3QVxPs+z\nz8POvXPuYWHfuXPvmXMEkpCQkJCQeP/RKWkHJCQkJCTUgyToEhISEmUESdAlJCQkygiSoEtISEiU\nESRBl5CQkCgj6JXUwNbW1nRyciqp4SUkJCTeSy5cuJBE0kZZW4kJupOTEyIiIkpqeAkJCYn3EkEQ\n7qtqk5ZcJCQkJMoIkqBLSEhIlBEkQZeQkJAoI0iCLiEhIVFGkARdQkJCoowgCbqEhIREGUESdAkJ\nCYkygiToEhISEmUESdAlJCQkygiSoEtISEiUESRBl5CQkCgjSIIuISEhUUYoUUHX1dWFn58fPD09\n4evri3nz5kEURUV7WFgYXFxcUKNGDezfv1+pjTVr1sDGxgb+/v5wdXVF69atcebMGUX7hAkTULNm\nTfj4+KBz58548eKFSn/Gjh2LEydOAACOHDmCgIAAeHl5YeDAgZDJZAAAkhgzZgxcXFzg4+ODixcv\nKrV14cIFeHt7w8XFBWPGjEFO7db4+Hg0b94cHTt2xKtXrwAAixYtwqpVq97ik5OQkJBQAskSedWq\nVYvly5dnDk+ePGGLFi04bdo0kuS1a9fo4+PD9PR03r17l87OzpTJZMzP6tWrOWrUKMX7I0eOsGLF\nirx+/TpJcv/+/czKyiJJTpw4kRMnTixggySTkpJYr149kqRcLqeDgwNv3rxJkpw6dSpXrFhBkvz7\n778ZHBxMURR59uxZ1q1bV6m9OnXq8OzZsxRFkcHBwdyzZw9JctKkSYyKiuLOnTu5ZMkSkmRqair9\n/PyU2pGQkJDIDYAIqtDVImfogiCsEgQhQRCEqEL6BAqCECkIwjVBEI7/lwuLra0tli1bhkWLFoEk\nduzYgV69eqFcuXKoVq0aXFxccP78+SLtNGvWDMOGDcOyZcsAAEFBQdDTy84SXL9+fcTGxio9b8uW\nLQgODgYAPH36FAYGBnBzcwMAtGrVClu2bAEA7NixAwMGDIAgCKhfvz5evHiBR48e5bH16NEjvHz5\nEvXr14cgCBgwYAC2b98OAJDL5dDR0YGOjo5i1m5sbAwnJ6di/X4SEhISqijOkssaAMGqGgVBsADw\nC4AQkp4Auv9XZ5ydnSGXy5GQkIC4uDhUqVJF0ebg4IC4uLhi2QkICMCNGzcKHF+1ahXatGmj9JzT\np0+jVq1aAABra2vIZDJFvvbNmzfj4cOHAFAsv+Li4uDg4KC0z+jRo/Hpp5/i119/Rb9+/RR9ateu\njZMnTxbr95OQkJBQRpEFLkieEATBqZAufQBsJfngTf8E9bj238mZ+eZm1qxZ0NPTQ9++fZWe8+jR\nI9jYZBcBEQQBGzZswBdffIGMjAwEBQVBV1dXLb45Ojoq1ulzY2trq/QiJCEhIVFc1LEp6gaggiAI\nxwRBuCAIwgBVHQVBGCYIQoQgCBGJiYkF2u/evQtdXV3Y2trC3t5eMSsGgNjYWNjb22Px4sXw8/OD\nn58f4uPjlY5z6dIluLu7K96vWbMGu3fvxh9//AFBEAAAgwcPhp+fH9q2bQsAMDIyQnp6uuKcBg0a\n4OTJkzh//jyaNGmiWH5R5Vdu7O3t8yztKOuTn/T0dBgZGRXaR0JCQqJQVC2u534BcAIQpaJtEYBz\nAMoDsAZwC4BbUTbta9rn2RRNSEhgq1atFJuiUVFReTZFq1WrVqxN0WPHjuXZFN27dy/d3d2ZkJBQ\n6EbDpEmTuHz5csX7J0+ekCTT09PZvHlzHj58mCS5e/fuPJuiderUUWov/6bo33//Xej4o0eP5vr1\n6wvto050dHTo6+tLDw8P+vj4cO7cuZTL5Yr20NBQVq9enW5ubty3b59SG6tXr6a1tTX9/Pzo4uLC\noKAgnj59WtEeGRnJ+vXr08vLi+3bt2dycrJKfz7//HMeP36cJPnRRx/R19eXvr6+tLOzY8eOHUmS\n69ato7e3N728vNigQQNGRkYqtbVw4UJWr16dAJiYmKg4LpfL2b9/fzZo0IBRUVEkyStXrnDgwIHF\n+9AkJEoBKGRTVB2C/hWAGbnerwTQvSibVq5WBUTlxx9/zCMq33//PZ2dnenm5qaIEslPjqj4+vrS\n1dWVQUFBPHXqlKK9evXqdHBwUAjEp59+qtTOiRMn2LdvX8X78ePHs2bNmnRzc+P8+fMVx0VR5MiR\nI+ns7EwvLy+Gh4cr2nx9fRU/h4eH09PTk87Ozhw1ahRFUVQ6bg7+/v5MSkoqtI860UaEUe3atXns\n2DGS5MqVK/nNN98o9SV3hFF+unTpwrVr11JHR4cuLi6sUaMGfXx8OGTIkDwRRrkvQIsWLWJMTAwd\nHR3zCPq4ceNYvnx5enp60tTUVHEBatGiBe/fv88ePXoo/k8cHR3z/D3zk/sCJIoiv/76a7q6urJm\nzZpcsGBBnr7nz5+nrq4uN23apNRWRkYGP/nkE7q6urJGjRrcvHkzSTIlJYUdOnRgs2bNGBcXR5Lc\ntWsXp06dqtIvibKPpgXdHcBhZK/HGwOIAuBVlE0rVyvt/PZvQaNGjfj8+XOtj3vx4kX269dPq2Pm\nFnSSvHPnDi0tLSmKIkNDQxkaGqpoCwoK4pkzZwrYyC/oZHaI59ixY0mSZmZmigvZgwcP6O7urtSX\npUuXcvr06QWOJycn08LCgsnJyQUuQE2aNKGpqSlJ1Reg/II+duxYNm3alAkJCRw0aJDiAjR58mTO\nnj07z9jjxo3jjBkzlPqb/wK0atUq9u/fXzEZybm7I0mZTMZmzZqxTZs2KgV92rRpnDJlCsnsu4gc\nn5csWcLdu3fzypUrnDRpEsnsi4efnx9TU1OV2pIo+xQm6MUJW1wP4CyAGoIgxAqCMEQQhOGCIAx/\ns2TzL4B9AK4AOA9gBUmVIY5vbDqmJ6cX1qVEmDdvHh48eKD1cZOSkvDdd99pfdzcaCLCyNPTEzt2\n7AAAbNq0Kc/eQ25yRxjlZvv27WjRogXMzMzyHLe1tUXDhg2RmZn5ViGuXl5eiIuLQ0hICMaNG6cI\ncb1z506eCCOS+Ouvv9C7d2+l/uYOcQWAJUuWYNq0adDR0VH4l8PChQvRtWvXPMfys2rVKkyePBkA\noKOjA2trawDKQ1wFQUBgYCB2796t0p7Eh0uRgk6yN0k7kvokHUiuJPkryV9z9fmRpAdJL5I/FWPc\nRakJqXj58uU7Oa9u6tWrBx8fH62P26pVKzg5OWl9XE2QIzxAtlD98ssvqFWrFlJSUmBgYKD0nNwR\nRrlZv369UlE9evQotm/fDgMDg7e6AOnq6qJ169Y4e/YsvL29AWRfgB49epRng/3kyZOoWLEiXF1d\nlfqb/wJ0584dbNy4EbVr10abNm1w69YtANnhq9u2bcOIESOU2gGgeHJ56tSpCAgIQPfu3fHkyRMA\nQN++ffHzzz9j9OjR+OyzzxTnSCGuEqrQ+qP/giDYAwgUdAUsWrRI28N/8LyWi8jMlV4hB01EGNWs\nWRMHDhzAhQsX0Lt3b1SvXh1A0RFGQPZdy/nz59GuXbs8x69cuYKhQ4dix44dihnxu0ASoijmiTBS\ndSHJIf8FKCMjA4aGhoiIiMAnn3yCjz/+GEB2KonZs2cX6qdMJkNsbCwaNmyIixcvokGDBhg/fjwA\nwMLCAnv37sXRo0fzPNdga2ur8vOX+LApiVwuXwE4qGugi/nz55e6WXpZZ9GDJ2j4z795jiUmJmL4\n8OEYPXo0BEFASEgINmzYgIyMDMTExODWrVuoW7cuRo0ahcjISERGRqJy5coFbB8/fhzLli3DJ598\nAgBISMh+JEEURXz//fcYPnw4AGD16tWIjIzEnj17AADu7u64fft2HlubN29G+/btoaOjg+PHsx8+\nfvDgAbp06YLff/8denp6RV6AUlJSEBgYWOQFqEKFCvDy8gKQLbBbt25Fz549FX2KugA5ODigS5cu\nAIDOnTvjypUrAICIiAj06tULTk5O2Lx5M0aOHKl4YjgHKysrGBsbK87v3r27yvxAOUghrhKq0Kqg\nC4JQGUBfAFsFHQFBQUFYvHixNl34oEnOkmFFbCJ8TIyRlpamSIzWsmVLBAUFYfr06QCy17579OgB\nDw8PBAcHY/HixSofrNq4cSP8/Pzg5uaG0NBQbNmyRTFDX79+Pdzc3FCzZk1UrlwZgwcPVmqjXbt2\nOHbsWJ5jGzZsQO/evbF//34cPXoUJDFz5kw8ffoUw4YNg6+vL8qVK6e4AIWFhSEmJgYxMTGIiIhA\n9+7dkZycjGfPnqF27dqFXoDMzMwUdwKHDh1CzZo188yIi7oAderUCUePHlXYzHlmISYmBvfu3cO9\ne/fQrVs3/PLLL+jUqVMeHwRBQIcOHRS//+HDh+Hh4aH0c8ohOjpacQGSkMiDqt1STbwAVALQBUAH\n/fL6vH//Pnft2qXeLWAJlfx49xErHrnEqy9LX4SEsgijqKgoTp8+nQcOHNBYiOuRI0dYr149RQK3\ngQMHKpKmqSJ/iOvz58/Ztm1benl5sX79+krj4wcOHJgnyiV3SOS9e/fYuHFjent7s3nz5rx//36h\n47dr145XrlwptI9E2QXvGrao7leOoEtoj8gbN6lrac0mYfOL7lwCnDt3jpcvX1a8P336NKtWrcoF\nCxYojYFXF9HR0Tx69Ohbn1dSIa6PHz9m8+bNtT6uROmhMEGXClx8AGzduhUN6taF/MUzdLRXHT5X\nkuREGN25cwf9+/dHYGAgHjx4gK5du6otj44yXF1dERgY+NbnlVSI64MHDzBv3jytjyvxflBkci6J\n9xeZTIbx48dj244dEKs4wSIzA86mxiXtlkqmT5+OxYsXo06dOtDV1UXFihWLzIFTUtSrV69Exq1T\np06JjCvxfiDN0Mswjx8/xuvXr9Hmu9nISnwCn+rVStqlQgkODsbmzZtx9uxZtGnTBnXr1i1plyQk\n3iukGXoZxsHBAfN+WQK7xs1Qe+gIVLhWeDhcSePl5YWGDRvC398f7u7uGl1qkZAoi0iCXsaZ/vdB\npN2JxqJdO/DswnnFE5KlDVEUMWbMGDx9+hR///03jh07hho1apS0WxIS7xWSoJdhUmRyLJsThlpD\nR6COdQWgdeuSdkklf/75J/766y+sXbsWVatWxYABKtPqS0hIqEAS9DLMjL2HkRZ9Awu3bStpVwrl\n9u3bGDduHAYMGICuXbuWtDsSEu8tAlmwXJvGBxWEDvrl9XdmvsrU+tgfCq9kctg1bYGajZsi/IcZ\nJe2OStLT09G8eXNkZGTgxIkTKF++fEm7JCFRqhEE4QLJ2srapBl6GWXG/iN4ffM6Fm7bWtKuqIQk\npkyZgps3b0piLiGhBqSwxVKOrq6uIueKr68v5s2bBzFXtsSwsDC4uLigRo0a2L9/PwAgVSbHrz+E\nwW/IcNS3tcSaNWtgY2MDf39/uLq6onXr1jhz5ozCRmRkJOrXrw8/Pz/Url1baS7xHLp164a7d+8i\nJSVFkXnRz88P1tbWGDt2bJ6+W7ZsgSAIiIiIUGpr06ZNWLBgAfT19dGtWzecPXsWABAfH4/mzZuj\nY8eOePXqFQBg0aJFWLVq1X/7ECUkPhRUPUKqyRekR/+LzX8pFTdh90HqWFnz9KPsyjdFlYpr1aqV\nIv/J33//zaZNmyr1JSoqip06dVLaFhAQoCjJRpIvX75k48aNWa9evTxl+nKIj4+nsbEx69SpQ7lc\nzoyMDMWj9JMmTWJUVBR37typyKuSmppKPz+/Yn1mEhJlGbxjxaJVgiAkCIJQVBWiOoIgyARB6Kam\na41EPmxtbbFs2TIsWrRIZaWe42fOYsnsMPh+PBwNK1krtZNTqWfZsmUAsjP+5aQxTk5OVpqZEAD+\n+OMPdOzYscDx6OhoJCQkoHHjxopjU6dOxaRJk2BoaFigv0wmQ79+/ZCVlYX9+/dDR0cHBgYGsLCw\nAKC8Uo+xsTGcnJwKvXuQkPjQKc6SyxoAwYV1EARBF8BsAAfU4JNEIRRVKu7nvQfw+voVLBz3eaF2\ncpeK++mnnzBhwgRUqVIF48ePR1hYmNJzVJWK27BhA3r27AlBEAAAFy9exMOHDwsUp8hhzpw5OHfu\nHFxcXPDFF1/A398fQ4cORWpqKgBg9OjR+PTTT/Hrr7+iX79+ivOkSj0SEoVTnBJ0JwA8K6LbZwC2\nAEhQh1MS/w0Zif3bt8Nn0DA0UjE7zyFn5gtk18ScP38+Hj58iPnz52PIkCFKz1FVKi4ndzmQ/YDQ\nuHHjVCaQOnPmDH744QcMGjQI0dHRGDFiBC5duoTy5cvjhx9+AAA4OjrixIkT2LVrF0xNTRXnSpV6\nJCQK5503Rd+UlOsMYEkx+g4TBCECwP8oaj9c8n1CFLOUHi+sVNzJy1eREfcAgZamb1Uqbu3atXkq\n5uQsa7Ru3Rp+fn4YOnQoAOWl4i5fvgyZTKaYuaekpCAqKgqBgYFwcnLCuXPnEBISgoiICLx48QKD\nBw9Gw4YNMXnyZDg4OCiSXHXr1k2q1CMh8Y6oI2zxJwCTSIo5t9yqILkMwDJBEDoIOsJONYxdZrlz\ndx6Sky/kOaasVFyfPn0wbtw43H74EPeuR8F7+FjM//or4OuvVNrOqdSTU2WncuXKOH78OAIDA3Hk\nyBFFceScqJkccir15C5onb/+prm5OZKSkhTvAwMDMXfuXAQEBKB3795IS0vD6tWrYWdnhypVquDm\nzZuoUaNGsSv1NGrUqPAPTkLiA0Ydgl4bwIY3Ym4NoK0gCDKS2ws/TUIVcnka4uP/gqVlI0WpuKys\nLOjp6aF///4YN24cgLyl4l5kZAL6Blg44QulNjdu3IhTp07h9evXqFatWp5SccuXL8fnn38OmUwG\nQ0NDxWZpfnJKxbVs2VJx7K+//lKUZiuM5cuXY+fOnfDy8oKdnR0AYOHChejbty8yMzPh7OyM1atX\nF2rj9OnT+Pbbb4scS0Lig0VV+Avzhhk6AYgqRr81ALoVo58UtlgIsXEbeOiwM589+6dY/VNlcpoF\ntqLPF5M06tfr169Zr169t64gdPXqVVaoUIFffvklRVH8T2NfvHiR/fr1+0/nSkiUJfCOYYvrAZwF\nUEMQhFhBEIYIgjBcEIThGrrGfNBkZWWhe7fPcOiQMSwsilfMIOzISby6fBELvlQ+O1cXRkZGmDFj\nBuLi4op9TmpqKgYMGICaNWti1qxZKGpZThVJSUn47rvv/tO5EhIfCkUuuZDsXVSfXH0HvZM3Hzgv\nX75Ex05BOHs2EbVqNSyW+L2Wi/g5LBQeA4Yg0L6ixn1s/RYZG0li/PjxiIuLw+nTp1GuXLn/PG6r\nVq3+87kSEh8KUi6XUsL9+/fRvn17GBo+g729AczMahbrvDlHT+FVZAQW/P6bhj18ezZv3ozffvsN\nS5cuhYuLS0m7IyFR5pFyuZQS2rZtiwEDuuPp00Q0aeKPly9TizwnTS7ipx/C4NF/CJprYXb+Nty/\nfx9jxoxBz5490adPn5J2R0Lig0AS9FJCeHg4qlRNRFYW0Lx5D7x48aLIc+YcO4OUi+cxf/w4LXhY\nfDIzMzFw4EDY2NhgwYIF0NGR/s0kJLSBtORSSjA01MXSpX+gb9/aaNy4HXR1KxTaP00uYn5YKGr2\n+xgtq1TSkpfFY8aMGYiMjMTRo0fzPOkpISGhWSRBLyVcivwdFyKSsXrVNDg51SiynubcE2fx8sI5\nbFq1QkseFo9Dhw5hwYIFmDVrFvz9/UvaHQmJDwqpYlEpYciQmkhOTsWmTfchCIUvUaTLRdi1CYGd\nWw1cX6Q8Z0pJkJSUhLp168LX1xebN2+Grq5uSbskIVHmkCoWlXISEyOwbdttbNnyXZFiDgBzT55D\ncvgZbFyh/InOkkAul2PIkCEQBAHLly+XxFxCogSQBL0UsHLVNDg7G6Fx49FF9k2Xi5gXFooafQah\nVRU7LXhXPBYsWIDDhw9j165dsLYuPNOjhISEZpAEvYTJzEzC2jVHMWZMJ+jpFb2B+L9T/yD5n9NY\nv3Tpf37qUt1ERERg5syZGDduHJo1a1bS7khIfLBIa+glzPbtEzFixHzcvHkNZmZuhfbNEEXYte2I\nis4uuL74f6VC0FNSUtCgQQPY2tpi3759MDAwKGmXJCTKNNIaeilFFGX49dc16NnTp0gxB4D5p8Px\n4twprPt1SakQc1EUMXr0aDx//hx79uyRxFxCooSRnvgoQa7/uwmnTz/FyJFTiuybIYr4MTQUrr0H\noo2jvRa8U46uri78/Pzg6ekJR0dHrF+/Hj/99BOqVq0KAAgLC4OLiwtq1KhRIJ96DmvWrIGNjQ38\n/f3h6uqK1q1b48yZM4r2b7/9Fvb29ooiHYWl5x07dixOnDgBIDt3zJQpU+Dm5gZ3d3f8/PPPefqG\nh4dDT08PmzdvVmpr/fr18Pb2ho+PD4KDgxV53ePj49G8eXN07NgRr169AgAsWrQIq1atKuanJiGh\nJVSlYdTkC1L6XJLkiJE+bN++EkWx6HS0P5w4R8HcgrtjHmrBM9WUL1+eJHnz5k1aWlrS3t6eU6dO\nJUleu3aNPj4+TE9P5927d+ns7Kw01e7q1as5atQoxfsjR46wYsWKvH79Okly+vTp/PHHH4v0JSkp\nifXq1VO8X7VqFfv370+5XE6SfPLkiaJNJpOxWbNmbNOmDTdt2lTAVlZWFm1sbJiYmEiSnDBhAqdP\nn06SnDRpEqOiorhz504uWbKEJJmamko/P78ifZSQUDd4l/S5Eprh2fOr2PTXNYwY+Qmya2yrJlMU\nMScsDC49+6NtCc7Oc0hPT8fAgQPh7OyMAwcOYPHixSCJHTt2oFevXihXrhyqVasGFxcXRTm7wmjW\nrBmGDRumsrCGKrZs2YLg4P+vX75kyRJMmzZNkWrA1tZW0bZw4UJ07do1z7Hc5HwhUlNTQRIvX75E\n5cqVAWSHZOro6EBHR0dRi9XY2BhOTk7F+v0kCpL7Ts/X1xfz5s2DKIqKdnXc6QHZf/eaNWvC09MT\nEydOVOlP7ju9HMaMGQMTExPF+xMnTiAgIKDQuzwgu5iMj48PPD09MWnSJMXxV69eISQkBM2bN1eU\nhty9ezemTZum0tZbo0rpNfmCNEPn/J8609vbiJmZz4vsO+fkPxTMLLjzzn0teFY45cuX59ixY2lp\naclr166RJM3Nzfn48WOOGjWKv//+u6Lvxx9/rHQ2nH+GTpLbtm1jcHAwyewZuqOjI729vTl48GA+\ne/ZMqS8DBgzgzp07Fe8tLS35/fffs1atWgwODmZ0dDRJMjY2lk2aNKFcLufAgQOV+kSSmzZtoqmp\nKStVqsTGjRsr7i7u3bvHxo0bs3379nz58qWi//fff8+5c+cW+ZlJFCTnTo/MvpNq0aIFp02bRlJ9\nd3pHjhxhixYtmJ6erhhHGfnv9EgyPDyc/fr1y+NnTEwML1++zP79+6v8H0pKSmKVKlWYkJBAMvt/\n9NChQyTJJUuWcPfu3bxy5QonTcouRiOKIv38/JiamlrIp5UXSDP00kVWVjJWr9qPQYOCoK9vUWjf\nTFHED2FhqN6zH9pXq6IlD1Ujk8mwbNkyzJ49u8gaoG8Dc0VbjRgxAnfu3EFkZCTs7Ozw5ZdfKj3n\n0aNHsLGxUbzPyMiAoaEhIiIi8Mknn+Djjz8GkD37mj17dqFJwrKysrBkyRJcunQJ8fHx8PHxQVhY\nGADA0dERJ06cwK5du/LkprG1tVVZhFui+Nja2mLZsmVYtGiRWu/0lixZgq+++kqRh1/V3Vn+Oz25\nXI4JEyZgzpw5efo5OTnBx8en0P+ju3fvwtXVVfF/2bJlS2zZskVhN/+dniAICAwMxO7du4v8/YpD\ncSoWrRIEIUEQhCgV7X0FQbgiCMJVQRDOCILgqxbPyjBHjsxHXFwGBg2aWWTfhecu4vmpY5g7aXyJ\nRrakp75CXFwcMjMz0bFjR4VY3r17F7q6urC1tYW9vT0ePnyoOCc2Nhb29vZYvHixYoNTlQBeunRJ\nUeO0YsWK0NXVhY6ODj755BPFl3nw4MHw8/ND27ZtAWRXUEpPT1fYcHBwQJcuXQAAnTt3xpUrVwBk\nx8n36tULTk5O2Lx5M0aOHInt2/OWvI2MjAQAVK9eHYIgoEePHgVu3wt8JunpMDIyKt4HKFEozs7O\nkMvlSEhIQFxcHKpU+f/Ji4ODQ7GrZAUEBODGjRsAsouKnzx5EvXq1UPTpk0RHh6u9JzTp0+jVq1a\niveLFi1CSEiIovbt2+Di4oKbN2/i3r17kMlk2L59u+I70bdvX/z8888YPXo0PvvsM8U5tWvXxsmT\nJ996LGUUJ2xxDYBFAFRVUIgB0JTkc0EQ2gBYBqCeWrwrg5By/PLLMnTv7g5LS59C+2aKIsLCQuHc\nvQ9CnKtqycOCyLKysHHmFKw+cxFA9sxHR0cHiYmJGD58OEaPHg1BEBASEoI+ffpg3LhxiI+Px61b\nt1C3bl00aNAAo0aNUmn/+PHjWLZsGY4ePQoge+ad82Xatm0bvLy8AKBAEWl3d3fcvn0bgYGBAIBO\nnTrh6NGjqFatGo4fPw43t+xQ0JiYGMU5gwYNQvv27dGpU6c8tuzt7XH9+nUkJibCxsYGBw8eVFxg\nVBEdHY1GjRoV9fFJaJHcd3oymQzPnj3DuXPnEB4ejh49euDu3bsFJka57/Ti4+OxadMmHDt27D+N\nX6FCBSxZsgQ9e/aEjo4OGjZsiDt37gAALCwssHfv3gLnqPNOr8gZOskTAJ4V0n6G5PM3b88BcFCL\nZ2WU27d34ciRJxg1alKRfRf/cwnPThzBnK8mlOjs/NT6NTh68w4uXr4MAGjatCk8PT3RsmVLBAUF\nYfr06QAAT09P9OjRAx4eHggODsbixYtV5nTZuHEj/Pz84ObmhtDQUGzZskUhoBMnTlSEDx49ehTz\n588vcL6uri62bNmC8ePHK9wrYjMAACAASURBVDbVJk6ciC1btsDb2xsDBgzAkydPitxU09PTg7+/\nP5o2bYoKFSqgdu3a8PHxQWRkJDw9PeHp6QkdHR1ERETkOTcsLAzLli3DN998o9I+AGzfvh0zZ85U\njGdjY6O4W1mx4v8zZT548ABBQUFwd3eHh4cH7t27V8DW/fv30aJFC/j4+CAwMBCxsbGKtvnz5yMg\nIAAbN24EkJ2TvkmTJpDJZCp9KwnSbz9H+p2Cuf41caeXc8cmCALq1q0LHR0dJCUlFXqnd+nSJdy+\nfRsuLi5wcnLC69ev37raVocOHfDPP//g7NmzqFGjhmJiofIzUeednqrFdebdxHQCEFWMfuMBrCik\nfRiACAC39Iz0ir0JUJb44ovabBVkTbk8s9B+mXKR1h260vnjERRFUUveFeTy8aP8okt7mpiY8Icf\nfigxP/KTs1nVqFEjRkdHa2RT7fr167xx4wabNm3K8PBwRb9r167R1dWVvXv3LtQ+STZo0EARCqls\nMziHpk2b8sCBAyTJlJQUpZtk3bp145o1a0iShw8fZr9+/RT9e/fuzaysLIaEhCj6f/vtt1y3bp3S\n8bRN1tM0Jv52jQ8nnWDCiit5NhsTEhLYqlUrxd8vKioqz9+vWrVqxfr7HTt2LM/fb8mSJYqQ2ps3\nb9LBwUHpd2nSpElcvny5Ur9z+5lDYRvr5P9vvj579oy+vr68efOmyr4kOXfuXIaFhRXaJzcoZFNU\nbYIOoBmAfwFYFcPeBxnlkpwczUp2ety69csi+84/e4GCmTk3R8do3jElpKenc05YKHUEgcbGxmzT\npg2zsrJKxBdl5HzRzp07x8uXL/POnTu0tLSkKIoMDQ1laGioom9QUBDPnDlTwIYygZ06dSrHjh2b\n51h+QQ8NDeXgwYMZExNTqP2bN28yMDCw0PHI7AtEo0aNivydPTw8+ODBA5LZ0RGmpqYkyZcvX7J3\n796UyWR5BD0yMpJt2rQp0q66uX37Nv/66y8uW7aMP8wKY88WnTm8fh/GfnOKyUfuU8yUU0dHh76+\nvvTw8KCPjw9//PFHxfMDZHYEkbOzM93c3Lhnzx6l46xevZrW1tb09fWlq6srg4KCeOrUKUV7RkYG\n+/btS09PT/r7+/Pw4cNK7Zw4cYJ9+/ZV2pZb0M+fP097e3saGxvT0tKSHh4eijZfX1/Fz7169aK7\nuzvd3d25fv36Ij+vdu3a8cqVK0X2y6EwQVfLo/+CIPgAWAGgDcmn6rBZFvlz/bcwN9NDm7aFL7dk\nicSs0FA4deuNLi6OWvIuG5lMhrVr12LmzJlgehogCDA0NMTq1auhp1f6MkXUq/f/2zW5N9Xq16+v\nOP62m2pLly4ttE9cXByaN28OJyenQu2fPn0aAQEBeY5t2bIFJ06cgJubG+bPn48qVaogOjoaFhYW\n6NKlC2JiYtCyZUv88MMPBZarfH19sXXrVnz++efYtm0bUlJS8PTpU1hZWcHb2xu1a9fGhAkTFP29\nvLxUbgRqkn379uHYsWPQeSXHpQuXcDvxPvo264qK42tDzzw74kQulxdqY8qUKZgypfAnqAcNGoRB\ngwapbDcwMMC6deuK9Ldx48aYPHkyXrx4AQuLvFFnOU8GA0CdOnXyLHPlJmdTHch+4ri4PHnyBGlp\nafD29i72OYXxzmGLgiBUBbAVQH+S0e/uUtlEJnuFlSt3YsCAQBiWsym075KISDw9fghzJk3U+tr5\nqVOnsHnzZnzcpSMSXiSDJKZPn46KFUtXEWpNQaovWV3+sMoOHTrg3r17uHLlClq1aoWBAwcCyL6I\nnjx5EnPnzkV4eDju3r2LNWvWFLA3d+5cHD9+HP7+/jh+/Djs7e0Voj958mRcunQpT0FuXV1dGBgY\nICUlRW2/U3HoH9wTbll2OHj8CKra2MPX0werD6xXiHlpZN68eXjw4IHWx33w4AHmzVNfkZrihC2u\nB3AWQA1BEGIFQRgiCMJwQRCGv+kyDYAVgF8EQYgUBCFCpbEPmFOnf8HtW2kYMuTbQvtlicT3oWFw\n7NITXV2dtOJbbgIDA7H4x9lYvHotdPX0oKuri6FDh2rdj7dFE5tqqiiu/fxhlVZWVoqY6KFDh+LC\nhQsAsmf4fn5+cHZ2hp6eHjp16oSLFy8WGLdy5crYunUrLl26hFmzZgFAgRllfnJi87WBLCUDf3y1\nBN61fXEx+jL+WvA7LifcxG/rfy+Vd3e5qVevHnx8Co860wR16tSBn5+f+gyqWovR5Asf2Bq6KIrs\n1r0KBw1yK7Lvz+cvUTAz58Ybd7TgWUEyXqeysWdNmpubs1atWnR2di4RP1RxN/EV+y4/R2MtbKrl\nkH8Nvbj29+7dm2dtNj4+XvHz1q1bFU8nymQy+vj4KJ4uHDRoEBctWlTAXmJiomKd+euvv1Zs+Kki\nKSmJNWrUKLSPOhBlcob/fpRNnOvQ1cqRW2esofx1FkeOHMlvv/1W4+N/aOBdN0XV/frQBP3evQM0\nNdVhePjSQvtlyUXadupBp4GflFhky5ShA2lsZEQbGxveunWLsbGxJeKHMu4mvmLdWQfpP/OAVjbV\ntm7dSnt7exoYGNDW1pZBQUFvZT81NZUeHh6Kv+VXX32l8DcwMJD//vuvou+BAwfo7e1NLy8vDhw4\nkBkZGSSzN2l37NhBMjs1gYuLC11dXTlkyBDFI+2q2LRpE8eNG1don3flUUQMhzbuTUsjc37fayJT\nY18o2l6+fFmiEVplFUnQS5ivJjdi06YVKJcX/gVcdP4yBVMzbvi3ZGbnhzdvpFE5AxoaGpaacLcc\nLt2OpdfnK+k/8wD/fZRc0u4UmzFjxvDgwYMlMnbnzp2LDJn7r6Q/SeH/Bn9Lm/KW7Fe3M++fvCGJ\nt5aQBL0ESU19wKpV9fnHHyMK7ZclF1mxS086DiiZ2XlSXCydKtrQxMSEQ4YMKRVfzpSUFG7YsIGt\n24UQgg7LWTm8V2JOko8fP1bMsLVJRkYG165dq3a78nQZ983bRK+KrqxTxZvHf/2bYqa86BMl1IYk\n6CXImjVDWK2aAV+/jiu03y8RVyiYmnH99Vta8uz/kWVlsUvjBjQzNaW3tzdTUlK07kN+duzYQTMz\nM34U2JzGlV2pa2jC0Pm/lLRbHyyiKDJ67yV28gminakNl302l1nP00rarQ+SwgRdyraoQeTydCxf\nvhn9+zeEkVFllf1kIjEzNAxVOnZDz5rVtehhNku//xZ7/rkACAJ+//33PDmgS4pWrVrhwNlIXEvM\ngp6xOYz0BYz6uG9Ju/VB8vJ2Ir7u+BnqdQlENbuqiPrnMj75+UvoWWgnekai+JTuWKL3nIiIFbh6\nNQUbNkwvtN/KyCg8Ofg3fj8XofW486unT2Lyj/8DBQHff/89fH1LR7LMe8/SEdx9ACiXYdLIQTh/\n/CDMzMxK2q0PCllKBtZ/twLfLJsFz8puOPnnAXiE1IGgU/L1bCWUI2TP4LU8qCB00C+vvzPzVabW\nx9YWJNF/gAtEuYg//iiY4S0HOQmHHv2gX84Q935fAR0tCnpq8gt8FOCHO4lP0bJlK2zatEllMi1t\ncj32GRq1DgFFEacP7MLyed+hadOm6Ny5c0m79kFAuYjwP47hy28nISHlKeaMnYEOX/aGjqE0/ysN\nCIJwgWRtpY2q1mI0+cIHsIYeF3eS5uY6PHVqfqH9ll2KomBqxt+uaiYaQRWiKHJ4lw4sb2xMZ2dn\nPn36VKvjq+LawyRauDeiec2GjHqQRJKlYoP2QyH+/F0O+agnrYwtGNrnK76Oe782oT8EIK2ha5/l\nK6bD3cME9esPU9lHTmJ6aBjsO3RBX09XLXoHbF2+BKt37wcBrFq1CpaWllodXxnXHj5Fw1YhAIAz\nB3fCs4oVAJRo6uAPhYwnrzBv0HT4BNZCliwLlw7+g6/WhcKosrTM9V6hSuk1+UIZn6GnpT1i9erl\nuHLloEL7rYi8RsHUjGuu3tCSZ9k8uPEvK1qY09DQUFHZvqSJepBE85oNaOHeiNceJmlt3PwPKM2d\nOzfPA0qhoaGsXr063dzcuG/fPqU2ch5Q8vPzo4uLC4OCgnj69OkC/ebOnUsAinS6yujatSvv3Ml+\nDqFp06Z0c3Ojr68vfX19FWlZ09PT2aNHD1avXp1169ZVZH3Mz/Pnz9m1a1fWqFGDNWvWVGSEjIuL\nY7NmzRgSEsLkpBfc8+MGVjK1YTXLKjy5fC/FLCkMsTQDKWxRu2zc+Bnt7fX56lWMyj4yUaRdj360\n7z2Qci0uKWSmp7G5nzdNTEzYvFkzZmYWnpddG1zNEXOPRrz2ULtLP9ooVkySDx48YFBQEKtWrapS\n0KOiotipUyfF+/wpB3JYvHgxP/30U5Lk+vXr2aNHD6X2BgwYoMjznZGRwefPswuST5o0iVevXOUv\n0+bTp3JNVja15eKRP9DXy0f5hyRRqpAEXYvI5Rls1tySEyfWL7TfysvXKZiacfXVfwvtp25mjvqU\nhuXKsVKlSnz48KFWx1bG1fuJNK9RnxYejXg99pnWx89fwEBTedW7du3KyMhIOjo6qhT0yZMnc/Xq\n1Yr3qgQ9tx9ZWVm0srIqsM/w4sULOjk5Kd1/+GzISA5p2ovlDYzZwqMRn914RJLs1KkT//nnH6W+\nSZQeChN0aQ1dzVy+vA4R4S8wYsQ0lX1EElNDw2DXrhMGeNbQmm+n/t6BsJVrQGTXBXVwKNlqgVfv\nJ6FRq/bQ0dXD2YO74G5foUT9ATRTrHjHjh2wt7cvMiQ0f7Fi4P8LY3/33Xc5k6E8funp6cHc3BxP\nn+YtQxATEwMbGxsMHjwY/v7+GDp0KJIfPcPaCYuw+a9N2Bq+F7V9ArD1zB5UqFEJgHqLFUuUDFIc\nkppZvPhHtGplB0fH1ir7rI26gUd7dmDFqXNaC1N8kfAYgz/5FBB08MnQIejYsaNWxlXF1ftJ+Cio\nPXT1DXDmwA7UrFzyYq5OcsT39evXCA0NxYEDB4o8J3/+9D/++AP29vZISUlB165d8fvvv2PAgAHF\nGl8mk+HixYtYuHAh6taqg55tusLL3RPlDYzx6+T/of0XvQqEIdra2iouQhLvJ9IMXY0kJkZg69Zb\nGDVqJARB+UcrkpgaNhuV2oRgoHdNrfglyuUY0acXHiWnwMPDA3PmzCnRyJEr9xOzxdzAAGdLSMwz\n0mSIPv+4wHF151W/c+cOYmJi4OvrCycnJ8TGxiIgIACPHz9G69at4efnp8g3nz9/ur29PQDA1NQU\nffr0wfnz5xXHc/ySyWRITk6GlZVVnvEdHByyX7DG0MDe2H/yEMqXL49Lly8hZHI/pTHlai1WLFEi\nFDlDFwRhFYD2ABJIeilpFwAsANAWwGsAg0gWzM7/AbB69XRUq2aIJk0+U9nn92vRiN+9DctPnoWu\nlkR15exZ2HbiDIxNTLBu3boS/dJGxiSgaesO0CtniLMHdsDNrvACDZrgWXwq9i69ipdJaUCu5+oS\nExMxfPhwjB49GoIgICQkBH369MG4ceMQHx+PW7duoW7dumjQoAFGjRql0v7x48exbNkyHD16FO7u\n7khISFC0OTk5ISIiAtbW1ti/f3+e89zd3XH79m04OTlBJpPhxYsXsLa2RlZWFnbv3o2WLVsCAEJC\nQrB27Vo0aNAAmzdvRvPmzQtcoC0EEwivRXgHBiDEvxU+7jcYehXKwchOdRhidHQ0GjVq9DYfpURp\nQ9XiOv9/A7MJgACoKBKNbCHfC0AAUB/AP8WwWeY2RTMykujubsjFi3uq7CMXRTr0GUS77n0p01Jk\ny/XwczQ3KU8DAwOuXLlSK2Oq4tLdJzR1rUNLrya8Gf+8RHw4vfcyF486xJUTTjIu+plW8qrnprBN\n0d9++41TpkwhSb569YoBAQH09vamh4cHx4wZo4iwSUtLY7du3Vi9enXWqVNHEeYYFxfH4NbB3D17\nPd1tq9PHrgZrOLrQ28ubHTt25LNnhW86+/v7MylJeyGjEv8NvGuUCwCnQgR9KYDeud7fBGBXhL0y\nJ+jbt09kxYp6TE5WHVO+9upNCqZmXHYpSis+paWksJZbdRobG7NP7955hErbXLzzhKYutWnp3ZS3\nHr0o+gQ1cf78ec6ZM4fdunWnlYUNAXBY56+Z8qzw3PQlwevXr1mvXj2loZFFIcpF/rs7gh28WtDe\nrCJXffETs5KL/ztevHiR/fr1e+txJbSPpgV9N4CPcr0/DKB2EfbKlKDL5VkMDrbhmDEBqvuIIh36\nDGalbn20MjsXRZGf9+5KI0ND1nBzY3JyyT3CnSPmVt6BWhVzkuzRowdHDB/FprXasZy+Ea0sbJiR\nVvKx96rYt28f79+//1bnvIh+wglth9PC0IxftvlUEYb4Nhw4cEDlA0oSpYtSI+gAhgGIAHBLz0hP\nS7++5omKWk8TEx3euLFZZZ9116IpmJpx6YUrWvFp19qVLKevz/Lly/PcuXNaGVMZ2WJei1Y+zXj7\nsXbFnCTv3XjMhl7BtLdyZt2Ahly6tPAygO8TWcnpXPXFT3Qwq8T2Xs15fVc4RbmU96asIy25aJiR\no3zYrn1FiqLyW2W5KLJqv49ZqUtvrczO4+/cZmVLS5YrV45zZs/W+HiqiLj9iCbVS07MD24+Rwdr\nF9b3aMW/tx6inZ0d09Le/6IMYpacZ1YeYANHf7rbVueuH/6kPD2rpN2S0BKaFvR2+TZFzxfDXpkR\n9OfPo2hjo8vdu79W2efP67comJrxlwjNz86zMjLYuk4AjYyM2KZNG2ZllcwXPfzWI5pUD6C1b3Pe\neazd5R5Zlpxzv1pBUyMLftxpPFOT07lq1Sr++uuvWvVDEzw8c4uDGnSjlbEF5/T/hq8fvSxplyS0\nzDsJOoD1AB4ByAIQC2AIgOEAhr9pFwAsBnAHwNWi1s9ZxgR9wYKu9PIyYmam8ggCURTp2H8oK3bp\nxSwt3A7P/nIMDQz06eDgwMePH2t8PGWE33pEE+eSEfOU52nsGzyKZsZWXDhjHeWyspFo6nV8Mn/o\n+zWtjC04uGF3xp67XdIuSZQQ7zxDV/errAh6ZuYL+voac968jir7bPj3DgVTMy4Ov6xxf/45uI/G\nhuVoaGjI/fv3a3w8ZZy/FU8TZ39a+7Xg3SfanT1GX3rAANcmrFbRnSd2X9Tq2JpCnpbFnaHrWNPG\nmQ2dAnh21QEpG+IHjiToGmL//hm0stLl06eRSttFUaTTwE9o26mHxmfnL58m0c2hMsuVK8eJEydq\ndCxV5Ii5jV9LxiRoT8xFUeSOtUdZ0aIqm/l3ZNyd9z+WWpSLvL4znO08m9HBrBJXf/nzW4UhSpRd\nJEHXAKIoZ8eOdhz2qafKPhtvZM/OF55XLvhq80UuZ7/WLWhkaMiGDRsyPV37X/x/ouNZvpofbfxb\naVXMszJknPHZzzQxtOBnfaYxPbX0hiQWl2c3HnFcm2GsYGTOie2G80X0k5J2SaIUIQm6Brh1awdN\nTHR45cpvSttFUaTToGG07dhd47Pz3/43hwb6+rS2tubdu3c1OpYyzkXHlYiYP3uSws5NB7GCiS1X\nzdv23ofsZb1I54rP/0d7s4oM8W7Jf3dHvPe/k4T6kQRdA4wbV4ctW1lRLlc+I9x08y4FM3Mu+Eez\na7m3L19kBVMTGhgYcP369RodSxk5Ym4bEKRVMb9y5jY9HevSzcGP4UeuF31CKUbMkvPU8n2sV9WP\nHrYu/HvOBikMUUIlkqCrmZcvb9HOTo+bt3yhtF0URVYb/CltQroxU4MzrPTUVNbzcKOhoSGHDBmi\n9WLKZ2/EsryTL21rtea9RO2IuSiKXP/LHlqb2bFtg95MjH1/ixiLosgHp29yQP0utDauwB8HTGX6\n45SSdkuilCMJuppZurQv3dzKMS1N+drm5ugYCmbm/EnDs/OJg/uxXLly9PLyYkqKdoXgzI1Ylnfy\noW3tYK2JeUZaFicMDqOJoTm/GjqHGWnv7yz2dVwyQ/t8RStjCw75qCfj/rlT0i5JvCdIgq5GsrJe\nsU4dE86aFaS0XRRFOn88gtYdump0dn5w458sZ2BAU1NTXr6s+ZDI3Jy5Ecvyjtli/uDpK62MmfDw\nBYPr9aS1WWVu+HWf1u9G1IU8LYs7vv+dNWyc+VG12jy35hDFMhIrL6EdJEFXI8ePz6GFhQ4fPz6r\ntH3LrezZ+f/ORGjMh4SH92lvY0V9fX0uWrRQY+Mo4/S/D2ns6M2KWhTzfw5H0dXel97V6vPqufdz\nJivKRV7bfp5tPQJZxbwS145fxKyXUhiixNsjCbqaEEWR3XtU5cBBrkpniKIosvqQkbRu34UZGkpV\nK8vKZLuG9ViuXDl27tzpP6Va/a+cvP6AxlW9WbF2Gz7UgpjL5SJXzNlMi/I27NZ8KF8kpmp8TE3w\n9Ho8v2g9lBWMzDmpwygpDFHinZAEXU3cu3eApqY6DA9XnhNk2+17FMwsOE+Ds/Ofpkykvr4+nZyc\niixYoE6yxdyLleq01YqYv07J4Mie39DE0ILfjV3MrEztXbjURdaLNC4fM4+VTW3ZySeI0XsvvbdL\nRRKlB0nQ1cTXX3/EJk0sKJMVvFUWRZEun4yiZdtOGpudXzpxlOUNDWlkZMTjx49rZAxlnLj2Rszr\ntmXsM82L+cNbiWzq2552FRy5a92J904ExSw5Tyzbw3pVfelZ0ZV75m6kPP39uyBJlE4kQVcDqakP\nWbWqPtetG660feed+xTMLPjjqX80Mv6r58/o4ViF+vr6nPHttxoZQxnHo+7RuIon7eq204qYH90Z\nTkfbGqxToxlvX4nV+HjqRBRF3j95g/3qdaZNeUvOGzSd6U+kMEQJ9SIJuhpYu/YTVqtmwNevC4qM\nKIp0HfYZLdt01MjsXBRFDglpy3IGBgwMDGRmpnYebz8edY9GVTxoV689455pdv1aJpNzwbTfaGZs\nyf7txjDl+fuVtzw19gVn9ZpESyNzDm3ci/Hh2n9iV+LDQBL0d0QmS2Ojj8z5zdSmStt33c2enf9w\nQjOVgTYuXkB9fT1WrFiRsbHambUeu/pGzOt30LiYv3qRzkEdvqCpUQX+b8pqyt6jMD756yxum7mW\nbtZObOxcm+d/OyKFIUpoFEnQ35Fz5xbR1FSHDx4cLtAmiiLdPh1Dy+AQpmtgdh5zPYpW5mY0MDDg\n9u3b1W5fGUeuxNDIwYOV64doXMzvRMWxbs0WrGrjysPbzmt0LHUiykVe3XqOwe5NWNWiMn+fuFgK\nQ5TQCpKgvwOiKLJf/+rs1ctR6ebc3zEPKZhbMEwDs/PMtDQ28vaggYEBR48epZXNwWwxd2flBiGM\nf65ZMd/z50lWtqzGj3za8v57FMqXFBXLz4M+ZgUjc04OGc3k24kl7ZLEB4Q6StAFv6kVehvAV0ra\nqwI4CuASgCsA2hZh770R9Pj4kzQ31+GJk/MKtImiyBrDP2eF1u01Mjuf+ukQ6uvrM8DfXyu1MHOL\n+aMXrzU2jixTztAvl9DE0ILDu0/m65QMjY2lTrKep/HX0T/SztSGXXxb89b+yPcuAkfi/eddS9Dp\nvikv5wzAAMBlAB75+iwDMOLNzx4A7hVh870R9JkzW7B+fTPKZAVnq3tjYimYW3DWceVPjb4Lx7Zv\npoGBPs3NzXnz5k2128/P4cgYGtnXpH3DjnysQTFPTkplj5bDaFHemkvD/qL8PUgPK2bKefzX3axT\nxZveldy4b94myjOkMESJkuFdBb0BgP253k8GMDlfn6UAJuXqf6YIm++FoKelPaKLSzmuWDGwQJso\niqw58gtWCGqn9tn50/g4VqloS319fa5auVKttpVxKPIuDe1r0L5hJ42K+bXzMfR1bsjqdl48u/+q\nxsZRF6Io8t7x6+xTpyNtylvyfx/PkMIQJUqcdxX0bgBW5HrfH8CifH3s3hSIjgXwHEAtFbaGAYgA\ncEvPSE97n8B/ZOPGMbS312dKSsEQtH33YilYVOB3R0+rdUy5TMZOTRrRQF+ffXr1olxDDynlkCPm\nDo0683GyZsRcFEVuWnaAtuYODKrTjY/va+8J1/9K6sPn/K7nBFoamXNY0z58dCGmpF2SkCCpHUEf\nB+BL/v8M/ToAnUJslvoZulyewebNLTlhQj2l7e6jvqBFy7ZMU3OI2i8zp1JPT48uLi5MTtZsru+D\nkXdpWLkGHT7qojExz0yX8etP59LE0JxfDvyeGa9Ld8pb+essbpmxmq5WjmxavR7D1x2lKCv9y0IS\nHw7aWHK5BqBKrvd3AdgWYrPUC/qlS6toYqLDu3d3F2g7cD+OgkUFzjxySq1jRp07TRMjIxobGzM8\nPFyttvOz/+KdbDFv3JVPkjWz4ZoUn8z2jfrRyrQS1y3cXao3EEW5yMubzzCo5kd0tLDnn5N/lcIQ\nJUol7yroem8EulquTVHPfH32Ahj05md3APEAhEJslnpBHzrUnZ0721MUC87APT77kuYt2qh1dp76\nMple1Z2op6fHH+fMVptdZWSLuRuraFDMLxy/wZpVAuhRtTYjT0VrZAx1kRQVyzEtB7OCkTmndBrD\nl3eTStolCQmVqCNssS2A6DfRLlPeHJsJIOTNzx4ATr8R+0gAQUXYK9WCnph4gZaWujx46LsCbQcf\nPKJgUYHfHjqptvFEUeTwbp2pr6/P1kFBzMrS3LLEvou3s8W8STeNiLkoF7lm/nZamlRkxyYD+KwU\nl1TLfJ7GX0bOZiUTG3bzb8PbB66U6rsICQlSDYKu7ldpF/TZs9vRP6A8s7IKllbzHDOe5i2C+VqN\ns/NtK36lvp4eK1euzISEBLXZzc/eiFs0tHNl1SbdNSLm6a+z+Hm/GTQxNOfUkfOZWUpD+8RMGY8u\n3sVaDl70savJA/O3SGGIEu8NkqC/BRkZSfTwMOTCRT0KtB16+Ig6FSw5/aD6UtfG3Y6mtYU5DQwM\neODAAbXZzc+eiFssZ+fCqk17MOGl+sX8UcwztqjVmRUtqnDb6sOlcqYriiJjjl5jr9odaFvekguG\nfseM97RohsSHiyTowWgPDQAAIABJREFUb8GOHV/R1laPz19cL9DmNWYCzZoFqW12npmRzqb+PtTT\n0+PECePVYlMZeyJusVwlFzoG9tSImJ/ae5nOlTzp5/IRb1y8r3b76uDV/Wec0f1LWhqZc3hgPz6+\neK+kXZKQ+E9Igl5M5PIsBrex5Wdj/Au0HY19TJ0KVpx68Jjaxps5ZgT19PRYr25dZmRo5vH3v89H\nK8Q8Uc1iLpfJufi7P2lubMVeQSOYnKS5h5L+K/LUTG6avpLVLasy0KU+L/x5XApDlHivkQS9mFy7\ntoEmJjr899+/CrT5fDGJZoGtmKqm2fmZPbtZzsCAFSpUYExMjFps5mf3+ZssV7E6nZr1UruYp75M\n59DOE2lqZMHZE5dTllm6UsaKcpGRf51mS7dGdKpgz/VfL2XWe5IzRkKiMCRBLyajRvmybVtbimLe\nDbJjb2bnU/YfVcs4LxKf0MmuIvX09Lhh/Xq12MzPrn80J+b3bjxmQ69gOlhV576NZ9RqWx0kXn7I\n0S0GsoKROad2HiuFIUqUKSRBLwbPn0fRxlaXu3Z/XaDN94uvaNa0FV/J3j0SQi6XsVuLQOrp6XHw\noIEa2Tzcee4Gy1V0plPz3kxKUe/DMQc3n6ODtQvre7RizL+P1Gr7Xcl4+pqLh4exook1u/u35e1D\nV0vl5qyExLsgCXoxWPBzN3p6GjEzM2+ekRPxCdSxtObX+46oZZyVs2dRT1eX7u41+eqV+mt07ngj\n5tVa9FGrmMuy5Jz71QqaGlnw407jmZpcep6iFDNlPLJoB/3tPehr585DC7ZJYYgSZRZJ0IsgMzOZ\nfn7G/HFuhwJtfuMm07RJC7XMzqMvRtDE2Jjly5fnlStX3tlefrafvU4DW2dWa9GXT9Uo5inP0tgn\neBTNjK24cMY6yktJiTVRFHnnyFX2rNWetiZWXDhsFjOSpDBEibKNJOhFcODADFpZ6TIp6VKe46fe\nzM6/2lOw9Nzbkp76ir6u1amnp8dFC39+Z3v5yRbzanRu2U+tYh596QEDXJuwWkV3nth9UW1235VX\n959xetdxtDQy58hm/fnkUukMl5SQUDeSoBeCKMrZsZMdhw3zKNDmP34KTRo3f+fZuSiK/KxPD+rp\n6TGkfXu1p8Td9kbMq7fqrzYxF0WRO9YeZUWLqmwe0Ilxd0rHxqI8NZMbv1lOZ8sqbO7agBc3nJDC\nECU+KCRBL4Tbt3fSxESHkZfX5Dl++lEidaysOWH3wXce4+91a6mnp8cqVarw2TP15gLfevoaDWyc\nWD2oP5+9Uo+YZ2XIOOOzn2liaMExfaYzPTVTLXbfBVEm8tLGk2zh1pDVKjhw4zfLKS8FfklIaBtJ\n0Avhyy/rsmVLK8rleWOUAyZ8Q5OPmvFV1rvNzh/fi6FNBQsaGBjwxAn1pQwg/1/MXVoPUJuYP3uc\nwk5NB7GCiS1Xz9tGsRSUiHty6T5HNhvACkbmnN51HFPulf4CGRISmkISdBWkpNxm5cp63LR5bJ7j\nZ54kUcfKhhN2v1tulazMTDarHUBdXV1Onzb1nWzlZ/OpqzSwcaRL64FqE/MrZ27T07Eu3Rz8GH6k\nYOoDbZORlMqFw2bR1sSKPWu1550jUhiihIQk6CpYtqw/XV3LMS3tSZ7jtSZNo0nDpkx5x9l52Pix\n1NXVZeOPGjEzU33LA5tOXqWBtSNdgwfx+at3f/pRFEWu/2UPrUzt2K5hHybGabZSUlHIM2Q8tGAb\n/Sq709/eg0cWbqeYKYUhSkiQ/9femcfHdL1h/Dkzk3Um+0IkspAEESS22JfGvsTaUvwsrX2ppVWU\n0qKtWkstraW20paqtUq1te9KEQRBkYg1iSSTdWae3x8z0oQskz24389nPubee8573ntzPXlzznvO\nkQQ9S9LSEli3rhVnzGyZ6fzxB08oc3DiBzv3Fsj+qT/30czMlI6Ojrx3716BbGXkmZj7th3A2ELo\nQ05JSuP4AV9QZW7DiQNnMyWp5LaI0+l0DP/jIt+q2Z5lVI5cMvQLpjyR0hAlJDIiCXoWHDo0l7a2\nMkZFZd7kuc7EaVQ2aFKg6Dw++gm9XMtRoVBw29atBXU1nU0HL9LU0V0v5okFF/MHd2LYJugtOlqX\n40/f7i3R7oy4W0/4cZcxtLOw4cjgfnx0/k6J+SIhUZopjB2L2gC4CiAcwMRsyrxl2Bz6EoCNudgr\nUUHX6XR8q4c7+/bzziRiJx48oczRmWO3/5Z/21ote7ZuQblczuFDhxSaSP5kEPNKbd8pFDE/se8i\nfcpVZzWvegw9ebMQPMwfmoRU/jh5OT3tXNnCtyHPbTpSKgZiJSRKKwXdU1Ru2HquQoY9Rf2eK+MD\n4BwAO8NxthtEsxQI+u3b+2hlJePJU0szna876RMq6zVmXAGi87UL5lAul7N6tWpMSiqcRbF+PHBB\nL+bt3y2wmGu1Oq6c/TNtlU7s/sZAxpbQBg86jY5/bzzI5t71WdHenZunrZLSECUkjKCggl4fwN4M\nx5MATHquzGwAA3OzxVIi6JMnN2bjxrbUaP7LDjn9KJoypzIcvXV3vu3eDL1AK6WSVlZWvHatcDZG\n/uHAeZo4lGel9gP5NKlggpcYn8LhPaZQZW7LGWOWMK2EBhrvn/2XQ5v1ob2FDT99830m3JbSECUk\njKWggt4dwMoMx/8DsPi5MtsMon4UwAkAbbKxNRjAGQDXFRaK4nsCGVCr79LDw5Tr1w/OdD5o8nRa\nBjXi03xG5ylJiQys7Eu5XM6VK5YXhqvceOA8TRzcWLlDwcX87vVHbFqjA13sPblrw6ES6S9PeaTm\nwoEz6Ky0Z8/aHXlr/yUpDVFCIo8Uh6DvArAVgAkALwB3AdjmYLPEIvR16wfT09OUiYkR6efOPIqm\nzLksR/3ya77tjuvXh3K5nN27dSuUqf0b/vqHJg5urNJxUIHFfP/20/RwrsQ6ld5g+IWI3CsUMtoU\nDfd99QtruFRhLTd/7l+yU0pDlJDIJ8XR5fINgAEZjv8EUCcHmyUi6BpNEhs1tuXkKU0yna83ZQYt\ngxoyNjV/KXu/b/6BCoWCnh4ejIuLK7CfG/46RxN7N1bpOLhAYq7RaLnw43W0trRn3/ajGR9T+PuJ\n5oROp2P47+fZPbAty6qcuHT4l0yNLl4fJCReNQoq6AoANw2R97NB0arPlWkDYK3hu6MhQnfIwWaJ\nCPrJk0tpZSXj7Tt/pJ87+ziGMueyHLllV75sPrkXQWd7e5qZmfH0qVMF9vH7P/8T87gCiHlCbDL7\ndxxLa0t7LpiyhppiXvI27uZjTu78Hu0sbDgquD8fXbhbrO1LSLyqFEbaYjsA1wzZLpMN56YDCDF8\nFwDmG9IWLwLomYu9Yhd0nU7Hvn292aOnR6Z+2wZTP6Nlnfr5is41aWlsUa8OZTIZZ332WYF9XP/H\nWZrYu9IvZEiBxPxGaCTrVg6mu5Mv/9xa8F8yeSEtPoUbJ31DD1tXtqrciP9sPiqlIUpIFCLSxCKS\n96KO0MZGxkOH56WfO/cklrIyLhy+eXu+bM6bNJ4ymYxvNGtGTQGX2F1nEPOqnYYWSMx3bzzMcvZe\nbFy9Pe9ce1ggn/KCTqPjmQ0H2LRiEL0d3Lnl09VSGqKERBEgCTrJ6TNaMCjIimlp/2371nDa57So\nXY8x+YjOzx8+RHMzMzo7O/PRo0cF8m3N73/TxK4cq3Yexvjk/PXja1K1/HzcMlpZ2HLYmx8xsRh3\nuL9/9l8ObtqL9hY2nNFjPNV3Y4qtbQmJ143XXtCTku7T29uMy1f8L/3cuSexlJUtx6E/bcuzvYTY\nGFYs70qFQsG9e/YUyLc1v5+hiV05+ncenm8xf/pYzTeDB9NW6cjlszZRW0xdHCmP1Fzw7nQ6K+3Z\nq04n/nvwspSGKCFRxLz2gr5p8xi6upowPv5G+rlGn3xBi1r1GJ3H6Fyn07FPhzaUyWQc+957BfLr\nu72nqbArx2pd8i/ml07dYo0KDehdrhpP/H6xQP4YizZFw73zf2a1spVY260aD3yzi7rU0rHPqITE\nq85rLehabQqDgx34wQdB6efORz+l3MWVQ3/K+8JZG5cspEwmY82AAKak5L9bI13Mu47Il5jrdDpu\nXv47nW3c2Krum7xfDLMtdTodr+/9h10DWrOsyonfjJzD1GJOhZSQeN15rQX9n39WU6WSMfzGzvRz\njad/SYuadfMcnd+5eoXWKhWtra3577//5tunlXtOUWHrwurdRjIhH2KemqzhR0PmUmVuw/f7f8aU\nxKJf8vZp+CNOChlJOwsbjm71Dh+HFv8EJQkJiddc0AcNqsLOXcpRp9N3CVyI0Ufng3/4JU92UpOT\nWMuvMuVyOTesX5dvf1b8phfzGt1H5UvMH997yg4Ne9PBqiy//3pXkfdZp8Ul8/sJS+luW45tqjTh\nxV9OSGmIEhIlyGsr6I8en6W9vZz79s1IP9d0xmyaB9bhkzxG5+MH9qdMJmPvt3vmW0RX7D5JhW1Z\n1uj+Xr7E/O+DYaxcvib9POrwn6OFs/hXdug0Wp5a9xebVKhDX0dPbp2+ltpi+EtAQkIiZ15bQZ89\npwMDA5VMTdVvqRYaG095ufIcuOHnPNk5sPUXKhQKelesSLU6f8vNZhRzdUoeB2K1Oq5ZsI32qjLs\n1KQfo+/H58sHY4k6c4sDG/ekvYUNZ/b8kOqI2CJtT0JCwnheS0FPSXlCv6oWXPR19/RzzWbOoXlA\nbT7Og6BG349iGUcHmpub88L58/ny5dtdJ6iwKcOAN0fnWcyTE9M4us+nVJnbcuqIBUxNKbpFrZIf\nxHP+gE/opLRnn7pdePtwmJSGKCFRyngtBX3Hzkl0cpYzJuYSSfKSITp/5/vNRtvQajVs3bA+ZTIZ\nv5o3N19+fLPrOBU2ZRj41pg8i3nUrWgG1+rCMrbluXX1n0UmrtpkDX+bs4n+ZXxYt3x1Hvp2t5SG\nKCFRSnntBF2rTWO7ds4cOSog/Vzzz+bSvEatPEXnC6dNpkwmY+uWLfO1JO43u45RYVOGNXuMZWIe\nI+sjv52nV1k/Bno3ZtjZ23lu2xh0Oh2v/XaOnau3oouVE1e8N49pUhqihESp5rUT9MtXfqJSKePl\nKz/pj2PjKXdzZ//1m4y2EXryOM3NzOhStixjYvI+lX3ZTr2Y1+o5Lk9irtVouWTGRtpYOvDt1sP5\n9HFints2hqfXH3JixxG0s7Dh2NYD+eTyvSJpR0JConB57QR95KgAtmvnTK1WH40HfzGfZtVr8mGy\ncYtFJSXE08ejPE1MTHhw//48t790h0HM386bmKvjkjmwy4e0srDllxNWUFME3R5pcclc+8Fiutu4\nsJ1fM4ZuPSmlIUpIvES8VoIeE3OJTs5y7tw5iSQZFpdAuZsH+6390aj6Op2OfTt3oBCCE8d/kOf2\nF28/Srm1M2v3+iBPYn7rShQb+Lemm0NF7vnpWJ7bzQ2dRsuTa/9kI6/a9HX04raZ66hNktIQJSRe\nNl4rQV/09Zv0q2rBlJQnJMkWX35FM/8APkg2bpr+phXLKJPJWLd2baal5U3wvt56mHJrZ9bp9QGT\n8rDF2r6fT9DN0Zv1q7birStReWrTGO6dusl3G/Wgg6UtP+81kYmRTwu9DQkJieLhtRH0tLQ4BgYq\nOXt2B5Lk1bgEyst78n9rfjCqfuSN67SxsqKtrS3vRUbmqe1FWw9Tbu3Eur3HGy3mmjQt505cSSsL\nW77beTzVT5Pz1GZuJN+P59x+U+mktGffel155+hVKQ1RQuIlpzB2LGoD4CqAcAATcyjXDQAB1M7F\nXpEI+r59M2hvL+ejx2dJki1nL6SZfw2jovO01FTW9q9KuVzOXzYbP3hKkgt/OZRnMY+PTmKvNiNo\nbenAxdM3UFuIW8Rpk9O4e/aPrFrGh0HuATy84jfq0qQ0RAmJV4GC7ikqN2w9VyHDnqJ+WZSzAnAI\nwImSEHSdTsvOXcpx0KAqJMlrcWrK3b3Y+7sNRtWfOHQwhRB8p+//ci+cgWdiHvS/CUaLedjZ26zp\n04ReZf146NdzeWovJ3RaHcN+/Zsh1VqwnJUzV46ez7RYKQ1RQuJVoqCCXh/A3gzHkwBMyqLcVwDa\nAzhQEoIefmMnVSoZz537jiTZes5CmlWtzvtJuUfnh3bvoEKhYCVfXyYnG9/t8dWWg5RbGS/mOp2O\n29fuZxlbd75RszMjbzw2uq3ciL32gBM6DKOdhQ3HtRnE6LDC74uXkJAoeQoq6N0BrMxw/D8Ai58r\nUxPAFsP3bAUdwGAAZwBcV1goCvUmP/ggiMHBDtRqU3g9Tk2Fhxd7rfo+13pPHz9iWScnWlhY8FpY\nmNHtLfhZL+b1+k40SszTUjT8dNQiqsxt+V6vaUwupP02054mc/X7i1jepizbV23OS9tPSWmIEhKv\nMEUq6ABkBhH3ZC6CnqFOoUbo8fE36Opqwk2bRpMk28xbTNMq1XKNznVaLds0bkiZTMZlXy8yur15\nmw/kScyj78ezc9P+tFM5c/W8rYUiuLo0LY9/9zsbeNZkJacK3PH591IaooTEa0CRdrkAsAHwGMC/\nhk8ygHs5iXphC/ryFX3p7W3GpKT7vJGQSIVHBb69cn2u9RbPmEYhBDu0bWv01P55mw5QbuXI+v0m\nGSXmF46Gs6pHXVZyC+Tpvy4b1UZuRJwI54AGb9LB0pazen/ExHtSGqKExOtCQQVdAeAmAK8Mg6JV\ncyhfrBF6WloCg4KsOH1GC5Jku/lLaFrFn1G5ROdhf5+mubkZXV3LMS4uzqi25mz6i3IrRzbo/1Gu\nYq7T6bhxya90sHJh+wa9+KgQcr+T7sdz9v+m0NHSjv3rd+fdY9cLbFNCQuLlojDSFtsBuGbIdpls\nODcdQEgWZYtV0A8dnkcbGxnvRR3hzYREKjwrssfytTnWSUlU08fTgyYmJjx5/LhR7cz+6S/KVQ5s\n0H8yk9NyFvOUpDSOH/A5VeY2nDhoNlMK2BWiTU7jri9/YBXniqzvEchjq36X0hAlJF5TCizohf0p\nLEHX6XTs0dODfft6U6fTsf2CpTStXJX3conOB3TtTCEEp02eZFQ7X/74J+UqBzYcMCVXMX9wJ4at\n675FR+ty/OnbvQWayKPT6nhl1xl29A+mq3UZrh63kGmFPPlIQkLi5eKVFfTbd/6glZWMJ08u1Ufn\nXt5869s1Odb5Ze0qymQy1g8KokaTex/4lz/8QbnKgY3e+ThXMT+x7yJ9ylVn9Qr1GXryZp7u5Xli\nrt7n+HZDaWdhww/aDZXSECUkJEi+woI+eUoTNmpsS40miR0WLqNJJT9GJmUfwd7/9xZtrK1ob2fH\nhw8e5Gp/lkHMG787NUcx12p1XPHlZtoqndj9jYGMfZS/bepIfRrid2O/opt1WXb0D+aVXWekNEQJ\nCYl0XklBT0yMoKenKdetG8RbCYlUVPBh929WZ1tek5bKutWrUS6X89ft23K1/8VGvZg3GZizmCfG\np3B4j8lUmdty5tilTMvDolwZ0aVpeWzV76zvEcgqzhW568sfqM3HRtISEhKvNq+koK9fP4QeHqZU\nq+8yZNG3NPH1Y0Ri9tH5RyOHUQjBoe++k6ttvZjbs8nAaUzJYfDx7vVHbFKjA13sPfnrhkP57i+/\ne+w6+9fvTkdLO87+3xQmRhmXdSMhIfH68coJukaTzMaNbTl5cmP+q06iSUVfdl26Ktvyx37fQ4VC\nwapVKjM1NecZmp9v2Ee5yp5NB32So5jv336aHs6VWKfSGwy/EJGv+0i895Szen9EB0tbvtPwLUac\nCM+XHQkJideHV07QT51aSisrGW/f3sfOi1fQxKcy72YTncfHRLOssxMtLS1560bOgjlz/V7KVfZs\nNvjTbMVco9Fy4cfraG1pz77tRzM+H3twapPSuOPz71nZqQIbetbiidX7pDRECQkJo3ilBF2n07Fv\nP2++1cOdt9VJNPGuxC5LVmZbtl2zJhRC8LtvvsnR7gyDmDcfkr2YJ8Qms1+HMbSysOOCKWuoyeOS\ntzqtjpd3nGL7qs1Z3qYsV7+/SEpDlJCQyBOvlKDfv3+MtrYyHjw4h12WrKSJdyXeySY6X/rFTAoh\n2KVjxxz7t6ev26MX86HTmZqNSIdfjGCdym/Q3cmXf249lWe/o8OiOK7NINqaW3NCh2GMvZZ7lo2E\nhITE87xSgj5jZkvWrWvFf+OjaeJTmZ0Xr8iy3LUL/9Dc3Jzl3dyoVmefRvipQczfGDozWzHfvfEw\ny9l7sXH19rxz7WGe/E2LTebK0fPpal2GIdVaSGmIEhISBeKVEfSkpAf08THj8uV92HXpKppU9OXt\nLKLzlMRE+nh50tTUlGdPZx9Nf7JmN+UqewYPy1rMNalafj5uGa0sbDnszY+YGG/cvqSkPg3x8Irf\nGOQeQD9nb/46+0cpDfElQiaTsUaNGvTz82P16tU5d+7cTAu4ff7556xYsSJ9fX25Z8+eLG2sXr2a\njo6ODAgIoLe3N1u1asWjR4+mX58yZQqrVavGGjVqsGXLlozMYdvDbt268caNGyTJjz76iG5ublQq\nlVmW/fnnnwmAp0+fzvJ6TEwMu3XrxkqVKrFy5co8dky/KXlkZCSbN2/OkJAQxsfHkyS//vprrlqV\nfcKBRPHzygj65p/Hslw5Ba8+ukoTnyoMWfRtluUGvNmVQgh+Nm1qtrY+WbObcqUdWwzPWsxjH6n5\nZvBg2ioduXzWJmqNjKp1Oh3vHLnKvvW60tHSjnP7TWXy/XjjblCi1JBRLB88eMDg4GBOnap/ny5d\nusTq1aszOTmZN2/eZIUKFbKcdbx69WqOGDEi/fivv/5imTJlePmyftXNp0//W7Bt4cKFHDJkSJa+\nhIaGsnPnzunHx48f571797IU9Li4ODZu3JhBQUHZCnrfvn25YoX+L9uUlBTGxMSQJCdMmMDQ0FDu\n2LGDy5YtI0mq1WoGBARkaUeiZMhJ0GV4SdDpUvHtN+vw9ts1MXnLMVCrwcJ3/vdCue3fr8PaLdvQ\nuH59TJw6LUtb01b/hhkjeuONfh9g96JJMJFnfgyXT/+LpkEtce7KcezZuh+DJrwJmUzk6mPSvTjM\n6vMRAlsFwURhggsH/sb7az6FWRlV/m5aolTg7OyM5cuXY/HixSCJ7du3o2fPnjAzM4OXlxe8vb1x\n6tSpXO00b94cgwcPxvLlywEA1tbW6dfUajWEyPod27BhAzp16pR+XK9ePbi4uGRZ9uOPP8aECRNg\nbm6e5fWnT5/i0KFDePfddwEApqamsLW1BQBotVrIZDLIZLJngRcsLS3h6elp1P1JlDwvjaBfDP0B\nJ07EoOu7U7B9/hy0Hf0+PJUWmco8iriLfiNGwc7WFtt27oRM9uLtTV39Kz4b1Rtv9B+PXxdNzCTm\nJPHzin1o1rIRyji64sjxgwhq6Z+rb7pkDbZ/th4BNQKw+/gf2L1sC1Yc2AiXOl4Fv3GJUkGFChWg\n1Wrx8OFDREZGonz58unX3NzcEBkZaZSdmjVrIiwsLP148uTJKF++PDZs2IDp06dnWefo0aOoVatW\nrrbPnj2Lu3fvon379tmWuXXrFpycnDBgwAAEBgZi4MCBUKvVAICRI0diyJAh+Oabb9CnT5/0OrVr\n18bhw4eNuj+JkuWlEfSlS2YjuEUZLDz8BExLxaJ3+2a6rtNq0aFDBySo1fhh3TrY2du/YOPj737F\n56P+hzcGfIjdCydkEvO0FC2mDJuPAe+9ib5dhmPnwY0o426Xo0/UEZe2nULHWi3x3pwJmNz/few/\nfwR1+74BIX9pHq1EMfIs8n3GZ599hrt376J3795YvHhxlnWioqLg5OSUo12dTodx48Zh3rx5OZbT\naDQ4e/Yshg0bhnPnzkGpVGLWrFkAAA8PDxw6dAg7d+6ElZVVeh1nZ2fcu3fPmNuTKGFeCtV58uQf\nbNlyFT0HjcC2BXPRevS4F6LzaeNG4/SFixg28B20zCJCmbJqFz5/rw+C3/kQu7/6EIoMgvskKg5d\ng/vh243z8M2cDZjz3SSYmity9Cn6ShTebzcYjXu1QvWKVXHxzHn0nTMCCiuzwrlpiSKBJMaMGYNV\nq1bhwYMHL1xLe/gQaQ8evlDv5s2bkMvlcHZ2hqurK+7evZt+LSIiAq6urliyZAkCAgIQEBCQrQCe\nO3cOVapUeeF87969sWXLFgBA69atERAQgIEDBwIALCwskJycnON9xcfHIzQ0FM2aNYOnpydOnDiB\nkJAQnDlzJlM5Nzc3uLm5ISgoCADQvXt3nD17NkfbycnJsLCwyLGMRCkhu871ovwgj4Oic+Z2ZECA\nJd/6dhUVXt68mZCY6frJv/ZRoVCwWlU/pqW9mEny0YqdlClt2ea9L5n23ADo3wfDWLl8Tfp51OE/\nR6/l6ktabBJXvDeP5ayc2aVGK1777VyB1jyXKH62bNnC7p060Vqlor+7O7vXqMEL3d9kWN0gXq5U\nmVGffZZpwPHhw4ds2bJl+qBoaGhopkFRLy8vowZFDxw4kGlQ9Nq1/963RYsWsVu3bln626NHD+7b\nt++F89lluZBk06ZNsx0UbdSoEcMMG6JPmzaNH3zwQbZ2SHLkyJH84YcfciwjUXygEHYsagPgKoBw\nABOzuD4OwGUAFwD8CcAjF3tGC3pqajSrVrXgzPk9aFrFn+3mL8l0PT42hi7OzlQplbx7+98X6k9c\nsT1LMddpdVyzYBvtVM7s1KQfo3PJRNGlanno290Mcq9B/zI+/G3uJmqT87eyokTxoYmJ4dPjx3ly\n3jyu7NGT42oEsK2DA71NTWkK0FQImstk/KN9e977eCqfrFvPpEuXXkhbnDNnTqa0xZkzZ7JChQr0\n9fXl7t27s2z7WdpijRo16OPjw1atWvHIkSPp17t27cqqVauyWrVq7NChAyMisl4TaN26dZw8eXL6\n8fjx4+nq6kohBF1dXTlt2rQX6mQU9MjISLZt2zb92rlz51irVi1Wq1aNnTp1YnR0dI7PMDAwkI8f\nP86xjETxUSBNmw69AAAdmUlEQVRBByCHfuu5CvhvT1G/58o0B2Bp+D4MwE+52DRa0Hfu+ohOznJ2\nX/o1FR4VMkXnOp2O7Zo3pRCC61e9OP1/wrfbKFPasu2Y2ZnEPDkxje/1/oQqcxtOHbGAqSnZC7NO\np+Ptw2HsU7cLnZT2nD/gEyY/kNIQSxua+HjGnznDvxct4po+ffhhrVrs6OTESmZmNBeC5U1M2Nza\nhkMrV+bXnTpxzciRrFqhArt1DMlV0EqaxMREBhm5IUthc/bsWfbp06fY25XInoIKen0AezMcTwIw\nKYfygQCO5mLTKEHX6TRs186ZA4bVpqlfdbadtzjT9aWzv6AQgm927vRC3Wdi3m7MnExiHnnzMd+o\n2ZllbMtz6+o/c+wuUUfE8rOeE2hvYcNBTd5m1JlbufosUbRo1Wqqz5/n+WXf8Pv+AzipTl12LlOW\nVc3MaSEEXRQKNray4iAfHy5o1577pkzh/d9+Y2pkZPrP+vz583R0dOTy5ctfmu6yPXv28Pbt28Xe\n7u+//85bt24Ve7sS2VNQQe8OYGWG4/8BWJxD+cUApmRzbTCAMwCuKywUuToeFraZKpWMHb78lAoP\nL4bH/zeFPzz0As3Nzenh7s7kpMwrHn64bCtllrZsN3YONRkmBB3e/Q+9yvox0Lsxw85m/59Dm5jG\nrdPX0tfRk00q1OGpdX9Rl8eFuCQKhjYpiYmhoby8ahV/GjSIH9evz+4u5Vjd3JxKmYzOCgUbqFR8\np2JFzmndmr99OIERO3Yy5c4d6rQ5/6wSExN59+7dYroTCYnCpdgEHUAfACcAmOVi06gIfdR7gWze\n2oVmVauz9ZyF6edTk5PpW8GLpqamDP3nXKY64w1i3n7c3HQx12q0XDJjI20sHfh26+GMe5J5UPUZ\nOq2OF345zjZVmtDdthy/n7CUaXHSaohFiTYlhYlXwnht3Xr+PHw4P2nUiD3c3FjTwoLWMhkd5HIG\nKZXs6+nFWcHB3DF2LP/dsoXJN29Sl8UAuITEq06xdLkAaAHgCgBnI2zmKuixT6/Q2VnBZh8Oo8Ld\ni9fj/ovOB/ToTiEEZ8+YnqnOB0t/oczSlh3GzUsXc3VcMgd2GU8rC1t+OWEFNdksjfs4NIKjW71D\nOwsbfhQyik/DHxnxaCWMRZeayuTr13nrp5+4bdR7nNmsGXu7u7O2pSVt5XLayGSsbWnJXu7unNG0\nKbeNeo83f/yRydevU5fLpiQSEq8TBRV0BYCbALwyDIpWfa5MoGHg1Cc3ezRS0L9e/BZ9qihp5l+D\nLWf/F51v37CeMpmMzRo1ytT/OW7xFsosbdnx/fnpYn7rShTrV21NN4eK3PPTsSzbSY1J4rIRs+li\n5cSuNVrz+t5/Xpp+1dKITqNh8s2bvP3LL9z1/vucFRzMfp5eDFIq6SCXUyWTMdDCgj1cXTmtYSNu\nHjaMV9etZ+KVK9SmGL/4mYTE60phpC22A3DNINqTDeemAwgxfP8DwAMA/xg+O3Kxl6Ogp6XFMbCm\nkrX6dqS8vCevGaLzR5ERtLG2pqODA2MNCwqR/4l5yAf/ifm+n0/QzdGb9au24q0rUS+0oUvV8uCy\nXazjVo3Vylbi3vk/U5tDtotEZnRaLVPu3GHkzl3cM3Ei57Zuw3cqVmRDlYplFApaChmrmZuzm4sL\np9Srzx8HDeKllSupvniR2sSsu7wkJCRyp8CCXtif3AR93x8zaGMnp5l/Dbb48iuSpFarYd2AGpTL\n5dy/b2962bGLN1NmactO47+iRqujJk3L2RNW0MrClu92Hk/1czsC6XQ6/nvwMnvV6URnpT0XvDud\nKQ8T8vFYXw90Oh1TIyP5YO9e/jFlCr9q356DfX3ZxNqa5RQKWghBPzMzdipThpPq1OX6/v15fuky\nJvzzD7UJ0nOVkChsXipB1+m07NLFlT6t6lDu5sGwOL0oTB4zigA4Zviw9LKjF22mzNKGnT9cSI1W\nx/joJL7dejitLR24ZPoGap/LTFHfjeH0t8bT3sKGg5v2YtTft/L3RF9BdDodU+8/4KM//+SBTz/l\n1506cXjlKnzDxoblTUxoJgQrmZmxg5MTx9esydW9e/PMwoWMO32amri4knZfQuK14aUS9Js3d9FS\nKaNpFX8GfzGfJHnywF9UKBSs4e+fPrnimZh3MYh52NnbrOnThF5l/Xjo18yZL1p1Krd8spreDu5s\nWjGIp7/fT53m9e0nT3v8mNGHDvPo519wWbduHOXvz5Z2dvQ0MaWZEKxoasq29g4cW6MGV/TowRNz\n5/Lp8ePUZOjmkpCQKBlyEnShv168CCE6mihNdqQmpL5w7cMP6+H7fY/w8LEGF0MvwUOmg7ePL+LV\nalwLu4Ky5Vwx5uufsXjSIHQaNQObPxuBXzccwuDR/VC1Qk2s37wS5So4ANCvhnhx6wmMn/Ihrt6/\nhS+GfYw3J/V/bRbQ0sTEIDEsDGHHjuHC6dO4fCUMYRERuJYQj4i0NLgoTOCjUqKyqyv8KlVC9dp1\nUKVhQ1j5VYHCwaGk3ZeQkMgCIcTfJGtndS3nJQWLmYSEW/h+4z94bO6BpsNHoLK1Eh1avIH7Dx9i\n4+rv9GK+aBMWfzQEnd+bgR+mDcOMMYsxb+VUvNN1DGavmAwzSxMAwJNLkfh0zBR8f3QrRrTuj593\nb4OV16spUtr4eCSGXcW148dw8dQpXL5yBVfu3sX1uDjcTk2Fk0IBH0tLVHYph/aNG2FirVrwa9gQ\nNv7+UDg5ZbuxgoSExEtGdqF7UX6QTZfLypX9aF3OjnLX8rwUG8+lc2ZRCMG3u3WhTqfjqK9+pMzS\nht0mfs3HUXHs3LQ/7VTOXDN/a/rGy6nRSVw6/EuWVTmxe2Bbhv9+4ZVJQ9QmJDDh3DmeX7qM6/v1\n56Q6ddipTBn6mZnRQgiWUyjYxNqag319+VX7Dvxjysd8sHcvU+/de2WegYTE6w5ehj50jUbN2vXs\nqCjvwWafzeXNy5dobm5OLw8PJiUlcsT8HyiztGH3jxbz3JFrrOpRh5XcAnl6v34pUl2qhvuX7GQt\nN39Wd6nMfV/98tKmIWqTkqi+eJGXVq7kjwMHckq9euzm4sJq5ua0FDKWUSjY0DDtfW6bNtwzcSIj\nd+1iyt27uU57f50ojo2eN23aRD8/Pwohsl2u9hmjR4/mwYMHM50bNWpUjsvgZufjDz/8wMDAQC5Y\nsCD9XHBwcKlfaEyi4LwUgn7o8DyaKs0od3Hl+cfR9KngRTMzM14+/w+Hz9+YLubff72LDlYubN+g\nNx9FPqVOp+Ot/ZfYs3ZHOivtuWjQTKY8UvNlQD/t/Qqvrl3HTUOHclrDRuzh6spACwtaZZz27uXF\nWcEtuOv993ln61am3LpFXQmsvPeyURwbPV++fJlhYWE5rj9Oko8fP2ZQUFCmc6dPn2afPn2yFfSc\nfOzUqRM1Gg179OjB+Hj96p9r1qzhzJkzjXk0Ei8xOQl6qehDJ4mvliyDVmmLRsNG46uRQxB+61/M\nnTkTX/9xGd9OGYquYz6Hx72nGDq/N0b1nYJPFo5B2sN4zOgxHgt3rcRbQR1x4fBZlAn0KOnbeQGm\npSH19m1EnjmDC0ePIfTiBVy5eQtXnzxGeHIyhBDwNjNDJUcnVPPxwdvVa6B6gwYoV7sWTN3dIUxM\nSvoWXnqebfRcp04dfPLJJ9lu9Fy/fv0c7WTc6HnBggVZ7j6UFVu2bEGbNm3Sj7VaLcaPH4+NGzdi\n69atWdbJyUcakhmEEOnfQ0JC0LhxY0yePNkonyRePUqFoEdGHsDO7XdAK3t09yiL0Z9swRuNG+G6\nqQeWTxmKjsM+RdyfB7E27Ci+W7QJXXs1wy9frMOkxZ/C3d4V+1btQOBbjSHkJTu4R60WqXfu4P7Z\ns7hw9CguX7iASzdu4NqjRwhPTkYqCR8zM/g6OKCypye6dOyAGvXrw612HZhV8ILM1LRE/X/VeX6j\n53r16qVfy+tGz99++22e2j569Ci6d++efrx48WKEhITAxcUl2zo5+di1a1fUrl0bffr0Sd//087O\nDikpKXjy5AkcpCyl15JSIegLv/0MWlNLBA0ejsmjRsLBwQEebd7B8qnD0aLPeFz6cTUszZU48PsR\naO5EoU3NN3Dj0W18MXwquk/qD7myeCNY6nRIi4jAo/PncfHIUYSe/weXr4fj6sMHCE9ORoJWB28z\nU/ja2aOKpwc6tGyFavXrwbNuXZhVrAiZuXmx+vsqcv36dVSsWBEyWfFvi/ssIs4LGTd6vnfvHjZv\n3owDBw7k24d+/fqhX79+L5x/tqGzJOivJyUu6ElJkfh25d+AXIH43dugVqvxRv8JWDNjNOq06odT\nGxehRVAnzPl0IuZ+9Ck2Ht+GkW0G4Jd524s8DZEkNPfuIfriRVw8ehQX/z6LK+HXEXb/Aa4nJeKp\nVosKpmbwsbVFFQ93BDdtgmp1g+DdoAHMvStCZmlZpP69rpDEoEGDEBUVhbFjx6Jv376wNOJZG7vR\n84oVKwAAu3fvztJOdhs9Z2TAgAE4d+4cypUrh927d2fa6PncuXMIDw+Ht7c3ACAxMRHe3t4IDw/P\nZCM7H3NC2tD59abEBf37n79AQmwyyrdshdCdOxDQqgd2rPgS3tVb4NLe9Zg0cDps0hJQr209NPUN\nwumdR1DhjaqFmjtNEpqHDxEbegmhRw4j9OxZXL52DWH3ohCelIjHGg08TE3ha22NKu7uGFivHvzr\n1IFvgwawqFQJcpWq0Hx5rdFpgVQ1kJao/zc1AUxRI1Udi4SnT5AQGw11XCwS4mLxcQcvnAoFVs6d\nig/Hvofgqs74ZWQgRFqivn6jsZlMP3r0CEOHDsXIkSMhhEBISAh69eqFcePG4d69e7h+/Trq1q2L\n+vXrY8SIEdm6ePDgQSxfvhz79+/P8VZWr16d6bhKlSoIDw9Hs2bN0L59e9y/fz/9mkqlekHMAWTr\nY3aQxP379+Hp6ZmjbxKvLiUq6FptCj6Z+ytgYoqI3b/CybMKLhz+DU5lfRF//SxmvTMVq7Z+A5LY\n8NkKNB/aETJTeb7bIwntkyeIv3IFlw4dxsW//8bla1cRFnkP19UJuK/RoLyJCXysrFClfHn0adcW\n1erUReWGDaCsXBlyG5tCvPuXmGyENyUhFuqnj5HwNCZdeBPin0IdH4+EhHgkJCRAnZiIBHUiEhKT\noE5KQUJSCtRJaUhITkNCihaH72hhJge0BHSGng2FDFCaACpTgWQNEJdCyATgX0YBhVwOjVaDa5HR\n0KUmQW5uhTVnEzF+ymCo1WqYmZnBxMQELi4uGDJkCMaNG4fo6GiMGTMGERERsLOzS4/M5fIX363F\nixfj1q1bOHLkCGJiYhAdHQ1ra2ssW7YMCxcuxLZt2zBq1Cg8evQI7du3R0BAACpVqoTdu3fD0tIS\na9asQc2aNdG+fXuMGTMGS5cuxYQJE9CjRw+kpqaiRYsWmdrbsWMHzpw5g+nTp6Nq1ap466234Ofn\nB4VCka2Pz/j7779Rr149KBQlHqdJlBAl+pM/dGYt7l26C1MbG9DUAk/u34WFuQ08ZaYo51YJ09d9\nhqm93segz0fD1CFv3ReamBiow8Jw+cgRXDpzBqFXwhAWGYHrCQmISEuDq4kJfJVKVHJzQ/cWwahW\npw78GjaCqkplKOzti+iOi5lnwpsuvglgSgJSEp6mC29CXCzUcTFIiI/LXngTU5CQnIKEpFSokzVI\nSNFCnUYkpAIJqYQ6Vf9dLtOL7jPxVZkCSlMBlZkCSnMTqCxMobIwg9LCHDZWKriWcYJSqYRKpYJS\npYLKygZtJq7GufXToLKxR6JWhqHTv0XjoFr4dOIYXL55D28PGYu7xw7j171/oVefPqhevTp+3zAf\njRo1ynDfa9BDfgaLFy8GAOzfvx9vv/022rdvD5lMhlmzZiE4OBj79u3DrFmzEBMTg7Zt277w+C5d\nuoTy5cvjzJkzAIC6devip59+QlBQENq1a4c9e/agS5cu6NKlS3qd3bt34+uvv8b169dx8uRJDBs2\nDCdPnkRgYCDu3LmDK1eu4N1330WPHj1gamqK4OBgDBkyJL1+SEgIQkJC0o8nT55sdNbK+vXrMXz4\n8Dy9IhKvFiUq6MOnrQCEDKnR0RCmFlBAhlqO7rgYeQm16oXg4tqzcA5wz9GGNi4OiVev4urRY7h4\n+jQuXbmMsLt3cT0uHrfTUuGsUMDXUolK5cqhY5MmqF6rFqo2agQrP7/SM+09N+GNjUFC/H/CmxAf\nD7WRwpuQSqjTMguvQmYQWlNAaaL/V2UqoDRTQGVhAqW5XnhVlgbhLesMlVKpF18rayhVVlBZ20Bl\nbQultR1UNvZQ2tjDRGkLmFgCpkrAVAWYWgIKCyAPA5fyKRtR+c0p6ccrK7XSpxouWIHtq3eiZ68+\nMLOyR+jly/D19cWCBQvQsGHDHG0+n2q4ffv29AHJfv36oVmzZvjyyy9fqLdhwwZ06tQJgH5QMy4u\nLj3rpG/fvti2bdsLvwi2b9+Ovn37QgiBevXqITY2FlFRUVCpVAgMDMzUJw4AnTt3xqRJk9C7d2+j\nn1F2+Pv7Izg4uMB2JF5eSk7QSYT9cQ7QagG5AnISjuaWMBECf67eiYDujTKlIWoT1Ei+fg3hx4/j\nwsmTuHTpMq7cvYNrT5/i39RU2Mvl8LG0RKWyLmhZrz7G1awJ/0YNYVetGhRlyhSOcGcU3lQ1kKY2\nCG8sEmKfQP1UL7wJT2OgTsgsvAnqRL34JiYhITFF392QnLXw6sVXL7wqUwGl6XORr7kh4jU3hdIg\nvLYZhFcf8VrpxdfKGiprO6is7aC0sYPSxgEmShu96JpYGoRXCZhYAKXhl9tzZJdqOHXqVNy+fRtR\nUVFG2cmYavjgwYP0dMGyZcviwYMHWdY5evQo3n77bQD6FEI3N7f0a9mlOUZGRqJ8+fIvlKtduzaa\nN2+Od955B+PHj0+/7u/vj9OnTxt1D7kxaNCgQrEj8fJilKALIdoAWAhADv2G0bOeu24GYB2AWgCe\nAOhB8t8cTOrSUnSAVqd3QsjhYmmHuaOmo+vYHkiNvI3Q71Yi9ORJhIaG4srt27geG4sbKSmwkcvh\nbW6BSmXLoFmtWhgREAD/Ro3gWL0GTMq5QMhkgFYDpKmBVH20i/sPMglvwtP/BteeCW9CfBzUarU+\n2lWroU5KziS8CckaqA3Cm5AKQ5dD1sKbHvmaK6AyN4EyQ1eDrZUKbmWd07saVFZWUKqsobK2gdLK\nFiobe6gMwquwtDZEu0rARFmqhdcY9u3bhxMnTmDUqFGwtbUt1razSzUUQmT7yz5jqmFhMGnSJEya\nNCnTOblcDlNTU8THx6fnk0tI5JdcBV0IIQewBEBLABEATgshdpC8nKHYuwBiSHoLIXoC+BJAjxzM\n/ims7cHYaABAlyqN4WuZjJ9XfYzP547CjdRUmAkBd1NTuNuo4OZgjdpVXFC2rBIKlQJJSEViUiIS\n1Dfw17lL2HH0O/3gmkF4E1K06d0LWQlvet9ueleDiT7qtXjW1WCRLrzp/bsqlUF4bfXia51ReG30\n3QvPuhpMLF9q4S0q/P39sXHjRnh7e2PUqFEYPXp0rsJeFKmGZcqUQVRUFFxcXBAVFQVnZ2cAQOvW\nrfHgwQPUrl0bK1euzJRq6OrqioiIiBfafp78pBqmpKTAXJqbIFEIGBOh1wUQTvImAAghfgTQCUBG\nQe8E4BPD958BLBZCCGYTFpFMNnPxQaWWbXDx9++x5eIf+vOGjwCQIgPC0pIQHp0EeewjyG8KyGUC\nMtmzf2WQyQRkMjmETAYhZBByMwiZJYRMAZjLIVPKoZKZQCVXADIFdEIBnZBBBzniIcNTw3cAgBZA\nguGTiTQAMYaPRGEgc/DAF/MX4dPpMxDw5hj4NO8GAPArZ52pXFGlGoaEhGDt2rWYOHEi1q5dm95P\nvnfv3kz1nqUaenp6wsXFBdbW1jhx4gSCgoKwbt06jBo16oW2QkJCsHjxYvTs2RMnT56EjY1NjrNB\nnzx5AkdHR5hIyztIFAK5bnAhhOgOoA3JgYbj/wEIIjkyQ5lQQ5kIw/ENQ5nHz9kaDGCw4dAfwCUA\njtDruC7DvyWJNYC4EvYhO0qrb3nxSwbADoANgHgAdwBk3OmkFoAk6H+vE/ouvIyd3GWhf2dgqJtV\nuw4A3PDf+5QC4B4AteG6HEBFAKaGtm9A/yv9eewBmBvqAoAlAC+Db3GG9gHgWb/MI8O/7tA/Ex2A\nfwEkZmHbEcBj6J+FEvq/fksDz/wqbUh+/YcHySz7Aot1UJTkcgDLAUAIcYbZ7LpRkpRWv4DS65ux\nfgkh2gFYD2ATgC9I3i4NfuVQ3wLAfgANSWYl+PnmmW9CiF8ATCR5rTDt55eX/R0rbkqbX8YIeiSA\n8hmO3QznsioTIYRQQB99PSkUDyVeJU4DqPHsL7nSDskkIcQ0AK74LxovNIQQpgC2lRYxl3j5MSZB\n+DQAHyGEl+EF7Algx3NldgB4tlJQdwB/Zdd/LvH6QvLRyyLmzyC5l2Shi7nBdirJdUVhW+L1JNcI\nnaRGCDESwF7o+x6/I3lJCDEd+oXWdwBYBWC9ECIcQDT0op8bywvgd1FSWv0CSq9vkl95p7T6JvmV\nN0qVX7kOikpISEhIvBwU/2LSEhISEhJFgiToEhISEq8IRS7oQog2QoirQohwIcTELK6bCSF+Mlw/\nKYTwLGqfjPRrnBDishDighDiTyFEsWxWmptfGcp1E0JQCFFsKVPG+CaEeMvw3C4JITaWBr+EEO5C\niP1CiHOGn2e7YvLrOyHEQ8M8jayuCyHEIoPfF4QQNUuJX70N/lwUQhwTQtQoDX5lKFdHCKExzJEp\nFX4JIZoJIf4xvPcHi8OvLMlu9+jC+EA/iHoDQAXoJ3GcB+D3XJnhAL4xfO8J4Kei9CkPfjUHYGn4\nPqy0+GUoZwXgEIATAGoXtV95eGY+AM4BsDMcO5cSv5YDGGb47gfg32J6Zk0A1AQQms31dgB+g36i\nUj0AJ0uJXw0y/Azblha/Mvy8/wKwG0D30uAXAFvoZ867G46L/L3P7lPUEXr6sgEkUwE8WzYgI50A\nrDV8/xlAsCj6NW1z9YvkfpLPZvidgD7/vqgx5nkBwAzo18tJLgaf8uLbIABLSMYAAMmHpcQvQj9z\nE9DPkbiHYoDkIeizvrKjE4B11HMCgK0QIvt1AorJL5LHnv0MUXzvvjHPCwBGAdgCoDjeLQBG+dUL\nwC80pLcW03ufJUUt6K4AMi4AHWE4l2UZkhoAT6Gful3SfmXkXegjqaImV78Mf5aXJ/lrMfiTEWOe\nmS8AXyHEUSHECcMqnaXBr08A9BFCREAf2b24CEvJkNf3sCQornc/V4QQrgC6AFhW0r48hy8AOyHE\nASHE30KIviXliLRXVS4IIfoAqA2gaSnwRQZgPoD+JexKdiig73ZpBn1Ud0gIUY1kbIl6BbwNYA3J\neUKI+tDPmfAnWdLrBpVqhBDNoRf0RrmVLSa+AjCBpK7o/4jPEwro1yAKBmAB4LgQ4gRLYAZwUQt6\naV02wBi/IIRoAWAygKYkU4rYJ2P8soJ+UbMDhhe6LIAdQogQkmdK2DdAH2GeJJkG4JYQ4hr0Al84\nOzjk3693AbQBAJLHhRDm0C+qVGJ/Ghsw6j0sCYQQ1QGsBNCWZGlZxqM2gB8N774jgHZCCA3JbSXr\nFiIAPCGpBqAWQhwCUANA8S/pUMSDCQoAN6Ffoe7ZgFXV58qMQOZB0U1FPXBgpF+B0A+2+RTXgIYx\nfj1X/gCKb1DUmGfWBsBaw3dH6LsTHEqBX78B6G/4XgX6PnRRTM/NE9kPprVH5kHRU8X4ruXklzuA\ncAANissfY/x6rtwaFNOgqBHPqwqAPw3voiWAUAD+xf3sSBZthM6iWzagOPyaA0AFYLMhIrhDMiRb\no8XnV4lgpG97AbQSQlyGfjna8Szi6M5Iv94HsEIIMRb6AdL+NPxPLEqEED9A3/3kaOi/nwbAxOD3\nN9D357eDXjwTAQwoap+M9Gsq9ONYSw3vvobFsKKgEX6VCLn5RfKKEGIPgAvQL5m8kmSOqZdF5msx\nvNcSEhISEsWANFNUQkJC4hVBEnQJCQmJVwRJ0CUkJCReESRBl5CQkHhFkARdQkJC4hVBEnQJCQmJ\nVwRJ0CUkJCReEf4P1zvbCpxCJ7IAAAAASUVORK5CYII=\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"tags": []
}
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment