{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Homework #4\n", "### Assignment\n", "Following the example provided in the lecture, perform a complete data exploration task on the supplied covid19_cases.csv, trying to extract and plot significant information about the geographical incidence of the virus and focusing on an area of your particular interest.\n", "\n", "### Add below your solution" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '29/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '28/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '27/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '26/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '25/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '24/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '23/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '22/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '21/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '20/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '19/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '18/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '17/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '16/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '15/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '14/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '13/11/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '31/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '30/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '29/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '28/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '27/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '26/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '25/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '24/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '23/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '22/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '21/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '20/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '19/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '18/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '17/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '16/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '15/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '14/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '13/10/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '30/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '29/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '28/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '27/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '26/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '25/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '24/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '23/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '22/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '21/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '20/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '19/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '18/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '17/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '16/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '15/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '14/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '13/09/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '31/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '30/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '29/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '28/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '27/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '26/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '25/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '24/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '23/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '22/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '21/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '20/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '19/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '18/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '17/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '16/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '15/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '14/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '13/08/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '31/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '30/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '29/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '28/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '27/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '26/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '25/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '24/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '23/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '22/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '21/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '20/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '19/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '18/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '17/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '16/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '15/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '14/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '13/07/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '30/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '29/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '28/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '27/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '26/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '25/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '24/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '23/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '22/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '21/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '20/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '19/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '18/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '17/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '16/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '15/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '14/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '13/06/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '31/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '30/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '29/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '28/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '27/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '26/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '25/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '24/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '23/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '22/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '21/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '20/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '19/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '18/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '17/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '16/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '15/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '14/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '13/05/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '30/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '29/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '28/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '27/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '26/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '25/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '24/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '23/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '22/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '21/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '20/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '19/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '18/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '17/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '16/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '15/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '14/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '13/04/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '31/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '30/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '29/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '28/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '27/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '26/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '25/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '24/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '23/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '22/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '21/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '20/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '19/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '18/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '17/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '16/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '15/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '29/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '28/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '27/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '26/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '25/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '24/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '23/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '22/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '21/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '20/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '19/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '18/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '17/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '16/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '15/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '14/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '13/02/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '31/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '30/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '29/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '28/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '27/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '26/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '25/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '24/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '23/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '22/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '21/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '20/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '19/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '18/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '17/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '16/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '15/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '14/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '13/01/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '31/12/2019' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '14/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n", "C:\\Users\\GRCDNL71D14D969B\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\datetimes.py:1063: UserWarning: Parsing '13/03/2020' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.\n", " cache_array = _maybe_cache(arg, format, cache, convert_listlike)\n" ] }, { "data": { "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
dateRepdaymonthyearcasesdeathscountriesAndTerritoriesgeoIdcountryterritoryCodepopData2019continentExpCumulative_number_for_14_days_of_COVID-19_cases_per_100000
585902020-06-28286202060ZimbabweZWZWE14645473.00Africa1.44
585912020-06-272762020100ZimbabweZWZWE14645473.00Africa1.49
585922020-06-262662020210ZimbabweZWZWE14645473.00Africa1.50
585932020-06-25256202050ZimbabweZWZWE14645473.00Africa1.43
585942020-06-242462020130ZimbabweZWZWE14645473.00Africa1.44
.......................................
586852020-03-25253202000ZimbabweZWZWE14645473.00AfricaNaN
586862020-03-24243202001ZimbabweZWZWE14645473.00AfricaNaN
586872020-03-23233202000ZimbabweZWZWE14645473.00AfricaNaN
586882020-03-22223202010ZimbabweZWZWE14645473.00AfricaNaN
586892020-03-21213202010ZimbabweZWZWE14645473.00AfricaNaN
\n", "

100 rows × 12 columns

\n", "
" ], "text/plain": [ " dateRep day month year cases deaths countriesAndTerritories \\\n", "58590 2020-06-28 28 6 2020 6 0 Zimbabwe \n", "58591 2020-06-27 27 6 2020 10 0 Zimbabwe \n", "58592 2020-06-26 26 6 2020 21 0 Zimbabwe \n", "58593 2020-06-25 25 6 2020 5 0 Zimbabwe \n", "58594 2020-06-24 24 6 2020 13 0 Zimbabwe \n", "... ... ... ... ... ... ... ... \n", "58685 2020-03-25 25 3 2020 0 0 Zimbabwe \n", "58686 2020-03-24 24 3 2020 0 1 Zimbabwe \n", "58687 2020-03-23 23 3 2020 0 0 Zimbabwe \n", "58688 2020-03-22 22 3 2020 1 0 Zimbabwe \n", "58689 2020-03-21 21 3 2020 1 0 Zimbabwe \n", "\n", " geoId countryterritoryCode popData2019 continentExp \\\n", "58590 ZW ZWE 14645473.00 Africa \n", "58591 ZW ZWE 14645473.00 Africa \n", "58592 ZW ZWE 14645473.00 Africa \n", "58593 ZW ZWE 14645473.00 Africa \n", "58594 ZW ZWE 14645473.00 Africa \n", "... ... ... ... ... \n", "58685 ZW ZWE 14645473.00 Africa \n", "58686 ZW ZWE 14645473.00 Africa \n", "58687 ZW ZWE 14645473.00 Africa \n", "58688 ZW ZWE 14645473.00 Africa \n", "58689 ZW ZWE 14645473.00 Africa \n", "\n", " Cumulative_number_for_14_days_of_COVID-19_cases_per_100000 \n", "58590 1.44 \n", "58591 1.49 \n", "58592 1.50 \n", "58593 1.43 \n", "58594 1.44 \n", "... ... \n", "58685 NaN \n", "58686 NaN \n", "58687 NaN \n", "58688 NaN \n", "58689 NaN \n", "\n", "[100 rows x 12 columns]" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "\n", "# suppress scientific notation for floating point values\n", "pd.set_option('display.float_format', lambda x: '%.2f' % x)\n", "\n", "filename = 'covid19_cases.csv'\n", "dmds = pd.read_csv(filename,parse_dates=['dateRep'])\n", "data = dmds.copy()\n", "data.tail(100)" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 58690 entries, 0 to 58689\n", "Data columns (total 12 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 dateRep 58690 non-null datetime64[ns]\n", " 1 day 58690 non-null int64 \n", " 2 month 58690 non-null int64 \n", " 3 year 58690 non-null int64 \n", " 4 cases 58690 non-null int64 \n", " 5 deaths 58690 non-null int64 \n", " 6 countriesAndTerritories 58690 non-null object \n", " 7 geoId 58430 non-null object \n", " 8 countryterritoryCode 58582 non-null object \n", " 9 popData2019 58582 non-null float64 \n", " 10 continentExp 58690 non-null object \n", " 11 Cumulative_number_for_14_days_of_COVID-19_cases_per_100000 55826 non-null float64 \n", "dtypes: datetime64[ns](1), float64(2), int64(5), object(4)\n", "memory usage: 5.4+ MB\n" ] } ], "source": [ "data.info()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Only some columns contain numerical data where statistical information may be relevant:" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "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", "
casesdeathspopData2019
count58690.0058690.0058582.00
mean1061.0224.7741254230.29
std6037.24126.85153797500.57
min-8261.00-1918.00815.00
25%0.000.001324820.00
50%14.000.007813207.00
75%245.004.0028608715.00
max207913.004928.001433783692.00
\n", "
" ], "text/plain": [ " cases deaths popData2019\n", "count 58690.00 58690.00 58582.00\n", "mean 1061.02 24.77 41254230.29\n", "std 6037.24 126.85 153797500.57\n", "min -8261.00 -1918.00 815.00\n", "25% 0.00 0.00 1324820.00\n", "50% 14.00 0.00 7813207.00\n", "75% 245.00 4.00 28608715.00\n", "max 207913.00 4928.00 1433783692.00" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.loc[:,['cases','deaths','popData2019']].describe()" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "dateRep 0\n", "day 0\n", "month 0\n", "year 0\n", "cases 0\n", "deaths 0\n", "countriesAndTerritories 0\n", "geoId 260\n", "countryterritoryCode 108\n", "popData2019 108\n", "continentExp 0\n", "Cumulative_number_for_14_days_of_COVID-19_cases_per_100000 2864\n", "dtype: int64" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.isna().sum()" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " dateRep day month year cases deaths countriesAndTerritories \\\n", "37781 2020-03-19 19 3 2020 0 0 Namibia \n", "37782 2020-03-18 18 3 2020 0 0 Namibia \n", "37783 2020-03-17 17 3 2020 0 0 Namibia \n", "37784 2020-03-16 16 3 2020 0 0 Namibia \n", "37785 2020-03-15 15 3 2020 2 0 Namibia \n", "\n", " geoId countryterritoryCode popData2019 continentExp \\\n", "37781 NaN NAM 2494524.00 Africa \n", "37782 NaN NAM 2494524.00 Africa \n", "37783 NaN NAM 2494524.00 Africa \n", "37784 NaN NAM 2494524.00 Africa \n", "37785 NaN NAM 2494524.00 Africa \n", "\n", " Cumulative_number_for_14_days_of_COVID-19_cases_per_100000 \n", "37781 NaN \n", "37782 NaN \n", "37783 NaN \n", "37784 NaN \n", "37785 NaN \n" ] } ], "source": [ "whichCountries = data.countriesAndTerritories[data.geoId.isna()].unique()\n", "for i in whichCountries:\n", " print(data[data.countriesAndTerritories == i].tail())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now check if NA can be used as geoId for Namibia:" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "(data.geoId == 'NA').sum()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now we can fix those values by arbitrarily inserting NA as geoId code for Namibia:" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [], "source": [ "data.loc[data.countriesAndTerritories == 'Namibia','geoId'] = 'NA'" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(['Cases_on_an_international_conveyance_Japan', 'Wallis_and_Futuna'],\n", " dtype=object)" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.countriesAndTerritories[data.countryterritoryCode.isna()].unique()" ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(['Cases_on_an_international_conveyance_Japan', 'Wallis_and_Futuna'],\n", " dtype=object)" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.countriesAndTerritories[data.popData2019.isna()].unique()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Given that we don't have any information about the listed territories or the missing cumulative cases, we decide to drop those entries containing Nan values:" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [], "source": [ "data.dropna(inplace=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The number of remaining valid entries is:" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "55826" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.index.size" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The number of recordings for each country can be displayed by" ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "South_Korea 322\n", "Sweden 322\n", "Japan 322\n", "Mexico 322\n", "Canada 322\n", " ... \n", "Comoros 198\n", "Lesotho 186\n", "Solomon_Islands 32\n", "Marshall_Islands 19\n", "Vanuatu 6\n", "Name: countriesAndTerritories, Length: 212, dtype: int64" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.countriesAndTerritories.value_counts()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "From the cleaned dataset we can summarize the number of cases and deaths by country and derive the percentage of deaths over the total number of cases in the given timeframe:" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "data": { "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", "
casesdeathspercdeaths
countriesAndTerritories
Afghanistan4584417633.85
Albania367207852.14
Algeria8121223932.95
Andorra6482761.17
Angola150793432.27
............
Vietnam1341352.61
Western_Sahara76010.13
Yemen215961528.49
Zambia175543572.03
Zimbabwe98142742.79
\n", "

212 rows × 3 columns

\n", "
" ], "text/plain": [ " cases deaths percdeaths\n", "countriesAndTerritories \n", "Afghanistan 45844 1763 3.85\n", "Albania 36720 785 2.14\n", "Algeria 81212 2393 2.95\n", "Andorra 6482 76 1.17\n", "Angola 15079 343 2.27\n", "... ... ... ...\n", "Vietnam 1341 35 2.61\n", "Western_Sahara 760 1 0.13\n", "Yemen 2159 615 28.49\n", "Zambia 17554 357 2.03\n", "Zimbabwe 9814 274 2.79\n", "\n", "[212 rows x 3 columns]" ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ "aggdata = data.groupby('countriesAndTerritories')[['cases','deaths']].sum()\n", "aggdata['percdeaths'] = aggdata['deaths']/aggdata['cases']*100\n", "aggdata" ] }, { "cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [ { "data": { "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", "
casesdeathspercdeaths
continentExpcountriesAndTerritories
AfricaAlgeria8121223932.95
Angola150793432.27
Benin2968431.45
Botswana9979300.30
Burkina_Faso2717652.39
...............
OceaniaNew_Zealand1694251.48
Northern_Mariana_Islands9300.00
Papua_New_Guinea64471.09
Solomon_Islands900.00
Vanuatu00NaN
\n", "

212 rows × 3 columns

\n", "
" ], "text/plain": [ " cases deaths percdeaths\n", "continentExp countriesAndTerritories \n", "Africa Algeria 81212 2393 2.95\n", " Angola 15079 343 2.27\n", " Benin 2968 43 1.45\n", " Botswana 9979 30 0.30\n", " Burkina_Faso 2717 65 2.39\n", "... ... ... ...\n", "Oceania New_Zealand 1694 25 1.48\n", " Northern_Mariana_Islands 93 0 0.00\n", " Papua_New_Guinea 644 7 1.09\n", " Solomon_Islands 9 0 0.00\n", " Vanuatu 0 0 NaN\n", "\n", "[212 rows x 3 columns]" ] }, "execution_count": 39, "metadata": {}, "output_type": "execute_result" } ], "source": [ "aggdata2 = data.groupby(['continentExp','countriesAndTerritories'])[['cases','deaths']].sum()\n", "aggdata2['percdeaths'] = aggdata2['deaths']/aggdata2['cases']*100\n", "aggdata2" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The following plots reports the top ten territories by cases and by number of deaths:" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "aggdata.cases.sort_values(ascending=False)[:10].plot(kind='barh', figsize=(16,5))" ] }, { "cell_type": "code", "execution_count": 41, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "aggdata.deaths.sort_values(ascending=False)[:10].plot(kind='barh', figsize=(16,5), color='red')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Detail figures for a specific territory can be found in the aggregated dataset. It is possible to suppress the default scientific notation with the set_option command:" ] }, { "cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "cases 1564532.00\n", "deaths 54363.00\n", "percdeaths 3.47\n", "Name: Italy, dtype: float64" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "aggdata.loc['Italy']" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's plot the time series related to the number of deaths over the selected timeframe for my country of interest, which is Italy:" ] }, { "cell_type": "code", "execution_count": 43, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 43, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAABRkAAAGuCAYAAAAUBgFYAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOz9d7wkV33mjz/V8eY44U5SHiGhESAkIRDZEuDFMsasjW1gbdYsZr9gvLJhsVnsXdm7ln7GJtiSzRqMAZNkgy0DCwZEsEBIQtIoIAml0YxGk+6km1PH+v1RfU6dqq6qru463V1d/bxfL72YudPTc+m6Fc5zns/zGKZpmiCEEEIIIYQQQgghhJAWSXX7GyCEEEIIIYQQQgghhPQ2FBkJIYQQQgghhBBCCCGRoMhICCGEEEIIIYQQQgiJBEVGQgghhBBCCCGEEEJIJCgyEkIIIYQQQgghhBBCIkGRkRBCCCGEEEIIIYQQEgmKjIQQQgghhBBCCCGEkEhQZCSEEEIIIYQQQgghhEQi0+1voF1Uq1UcPXoUo6OjMAyj298OIYQQQgghhBBCCCE9hWmaWF5exvbt25FKBXsVEysyHj16FLt27er2t0EIIYQQQgghhBBCSE9z6NAh7Ny5M/A1iRUZR0dHAVgfwtjYWJe/G0IIIYQQQgghhBBCeoulpSXs2rVL6mxBNC0y/uAHP8Cf//mfY+/evTh27BhuueUWvP71r5d/bpom/viP/xgf//jHMT8/jyuuuAJ//dd/jYsuuki+plAo4L3vfS+++MUvYn19HVdddRX+5m/+xqGIzs/P43d+53fw1a9+FQDwute9DjfeeCMmJiZCfZ9iRHpsbIwiIyGEEEIIIYQQQgghLRImirDp4pfV1VU897nPxU033eT55x/84Afx4Q9/GDfddBPuuecezMzM4FWvehWWl5fla6699lrccsstuPnmm3H77bdjZWUF11xzDSqVinzNm970JjzwwAP45je/iW9+85t44IEH8J/+039q9tslhBBCCCGEEEIIIYS0GcM0TbPlv2wYDiejaZrYvn07rr32Wvz+7/8+AMu1uHXrVvzZn/0Z3vGOd2BxcRGbN2/GZz/7WfzKr/wKADs/8Rvf+AZe85rX4NFHH8Wzn/1s3HXXXbjiiisAAHfddRde9KIX4bHHHsOznvWsht/b0tISxsfHsbi4SCcjIYQQQgghhBBCCCFN0oy+1rSTMYgDBw5gdnYWr371q+XX8vk8Xv7yl+OOO+4AAOzduxelUsnxmu3bt2PPnj3yNXfeeSfGx8elwAgAL3zhCzE+Pi5f46ZQKGBpacnxHyGEEEIIIYQQQgghpP1oFRlnZ2cBAFu3bnV8fevWrfLPZmdnkcvlMDk5GfiaLVu21L3/li1b5Gvc3HDDDRgfH5f/sVmaEEIIIYQQQgghhJDOoFVkFLjDIE3TbBgQ6X6N1+uD3uf9738/FhcX5X+HDh1q4TsnhBBCCCGEEEIIIYQ0i1aRcWZmBgDq3IYnTpyQ7saZmRkUi0XMz88Hvub48eN173/y5Mk6l6Qgn8/LJmk2ShNCCCGEEEIIIYQQ0jm0ioxnn302ZmZmcOutt8qvFYtF3HbbbbjyyisBAJdeeimy2azjNceOHcPDDz8sX/OiF70Ii4uLuPvuu+VrfvzjH2NxcVG+hhBCCCGEEEIIIYQQEg8yzf6FlZUV7Nu3T/7+wIEDeOCBBzA1NYUzzjgD1157La6//nrs3r0bu3fvxvXXX4+hoSG86U1vAgCMj4/jbW97G97znvdgenoaU1NTeO9734uLL74YV199NQDgwgsvxM/+7M/i7W9/O/72b/8WAPBbv/VbuOaaa0I1SxNCCCGEEEIIIYQQQjpH0yLjvffei1e+8pXy97/3e78HAPiN3/gNfPrTn8b73vc+rK+v453vfCfm5+dxxRVX4Nvf/jZGR0fl3/nIRz6CTCaDN77xjVhfX8dVV12FT3/600in0/I1n//85/E7v/M7soX6da97HW666aaW/48SQgghhBBCCCGEEELag2Gaptntb6IdLC0tYXx8HIuLi8xnJIQQQgghhBBCCCGkSZrR19rSLk0IISQZVKuJ3IcihBBCCCGEEKIZioyEEEI8+eLdz+Di676Fuw/MdftbIYQQQgghhBAScygyEkII8eT2faewWqzgB0+c7Pa3QgghhBBCCCEk5lBkJIQQ4kmhVAUAHJpf6/J3QgghhBBCCCEk7lBkJIQQ4kmhXAEAHJ5f7/J3QgghhBBCCCEk7lBkJIQQ4slGyRIZD83RyUgIIYQQQgghJBiKjIQQQjzZqI1Ln1guSMGREEIIIYQQQgjxgiIjIYQQT8S4NAAcXeDINCGEEEIIIYQQfygyEkII8UQ4GQHgEHMZCSGEEEIIIYQEQJGREEKIJ+qI9GE2TBNCCCGEEEIICYAiIyGEEE9UkfHQHJ2MhBBCCCGEEEL8ochICCHEk0LZHpemk5EQQgghhBBCSBAUGQkhhNRhmqZLZKSTkRBCCCGEEEKIPxQZCSGE1KEKjACdjIQQQgghhBBCgqHISAghpA41jxEATq0UsV6s+LyaEEIIIYQQQki/Q5GREEJIHcLJmE4ZGM1nANDNSAghhBBCCCHEH4qMhBBC6hBOxoFMCjsmBwEwl5EQQgghhBBCiD8UGQkhhNSxUbKcjAPZNHZNDQGgk5EQQgghhBBCiD8UGQkhhNQhnYzZNHbWnIyH6GQkhBBCCCGEEOIDRUZCCCF1iEzGfCaFXZN0MhJCCCGEEEIICYYiIyGEkDqEkzGvOBmZyUgIIYQQQgghxA+KjIQQQuqwx6VT2FlzMh6ao5OREEIIIYQQQog3FBkJIYTUsVEblx7IpLFzynIyzq+VsFIod/PbIoQQQgghhBASUygyEkIIqaMgx6VTGBvIYnwwC4C5jIQQQgghhBBCvKHISAghpA7VyQgAu2puxsNzzGUkhBBCCCGEEFIPRUZCCCF1FJRMRgDYOcGGaUIIIYQQQggh/lBkJIQQUodd/GI5GUXD9CE2TBNCCCGEEEII8YAiIyGEkDoKtXHpfMa6TeyaYsM0IYQQQgghhBB/KDISQgipw+1k3DqWBwCcXCl07XsihBBCCCGEEBJfKDISQgipY6NUczLWRMapYUtknFstdu17IoQQQgghhBASXygyEkIIqUM4GcW49NRwDgAwt0KRkRBCCCGEEEJIPRQZCSGE1CEyGcW49KYRS2RcLpRRKFe69n0RQgghhBBCCIknFBkJIYTUYWcyWreJsYEs0ikDADC/Wura90UIIYQQQgghJJ5QZCSEEFLHhnAyZiwnYyplYHLIcjOeXmX5CyGEEEIIIYQQJxQZCSGE1CEzGbP2bWJa5DKy/IUQQgghhBBCiAuKjIQQQuoouJyMgFL+QpGREEIIIYQQQogLioyEEELqKMhMRkVkrJW/nGbDNCGEEEIIIYQQFxQZCSGE1OEufgHscWlmMhJCCCGEEEJaYd+JFfzv//dTnFzmmiKJUGQkhBBSx0bJGpfOc1yaEEIIIYQQoolP3r4fn7z9AP75vsPd/lZIG6DISAghpI5COcDJyHFpQgghhBBCSAssrJUAAMeXNrr8nZB2QJGREEJIHcLJ6MhkHM4DoJOREEIIIYQQ0hqrRcvMMM81RSKhyJhATixv4NFjS93+NgghPYppmtioORnzipOR49KEEEIIIYSQKKwVygCA01xTJBKKjAnkP3/qHlxz4+04QfsxIaQFipUqTNP6tZrJOC3apflAQAghhBBCCGkB4WSkcSGZUGRMILOLG6hUTZxgWxMhpAUK5ar89YCHk3FxvYRSpVr39wghhBBCCCEkiNWak5EiYzKhyJhAylXLgkQRgBDSChsla3fRMIBc2r5NTA7lYBjWr+fX+FBACCGEEEIIaY61oj0ubYrxKZIYKDImkGpNZBRiIyGENENBlL5k0jCEqgggnTIwOcRcRkIIIYQQQkhrrBYsQ0OxXMVabXTaTbFcxT/dewh/8a3HpQGC9AaZbn8DRD8Vk05GQkjrFDxKXwRTwznMrRYxt0KRkRBCCCGEEBKeStXEuiIazq0WMZy3ZanVQhlfvPsZ/N0PD2C21jHx/DMn8DMXbO3490pagyJjAhEOxnKFTkZCSPNsKE5GNyKXkeUvhBBCCCGEkGZYd7kST68WsWtqCABQrlTx2r/6IQ6eXnO85tQy1x29BMelE4gYl65wXJoQ0gJiJGHAw8k4PcxxaUIIIYQQQkjzrNVKXwRzq3ZZ7bHFDRw8vYZMysCf/ceLcc1ztlmvYRZ8T0GRMYFwXJoQEgXpZMzSyUgIIYQQQgjRw0qdyFiSvxbj0dsmBvArl5+BLaMDAFg42WtQZEwY1aoJUdDE4hdCSCvITMaMv5Px9Iq96zi7uIE79p1iOxwhhBBCCCHEF3fRi+pknF2siYxjgwCAyaEsAGBBESJJ/NEuMpbLZfzhH/4hzj77bAwODuKcc87Bn/zJn6BatV11pmniuuuuw/bt2zE4OIhXvOIVeOSRRxzvUygU8O53vxubNm3C8PAwXve61+Hw4cO6v93EUVEW+XQyEkJaQTgZ8wFORnVc+ne+eD/e9Hc/xsNHljrzDRJCCCGEEEJ6jlWXk1GdjjpeczJuHbccjJNi3UEnY0+hXWT8sz/7M/zf//t/cdNNN+HRRx/FBz/4Qfz5n/85brzxRvmaD37wg/jwhz+Mm266Cffccw9mZmbwqle9CsvLy/I11157LW655RbcfPPNuP3227GysoJrrrkGlQrry4NQcxhZ/EIIaQU7k9FDZBzJA7AfCArlCu4/NA/AfjAghBBCCCGEEDd1TsYVW0A8VnMyzoxZ643JIUtkXKDI2FNob5e+88478Qu/8Av4uZ/7OQDAWWedhS9+8Yu49957AVguxo9+9KP4wAc+gDe84Q0AgM985jPYunUrvvCFL+Ad73gHFhcX8clPfhKf/exncfXVVwMAPve5z2HXrl34zne+g9e85jW6v+3EUFWcjOUqnYyEkObZqI1LDwSMSwsn42PHllGqMAeWEEIIIYQQEsxq0elkVPMWRSbj1rGak7E2Lj2/xnHpXkK7k/ElL3kJvvvd7+KJJ54AADz44IO4/fbb8drXvhYAcODAAczOzuLVr361/Dv5fB4vf/nLcccddwAA9u7di1Kp5HjN9u3bsWfPHvkaN4VCAUtLS47/+hHVyViik5EQ0gKFJsalf3JkUf5ZkSIjIYQQQgghxAcxLm0Y1u8d49Iik3G8lsk4TCdjL6JdZPz93/99/Nqv/RouuOACZLNZXHLJJbj22mvxa7/2awCA2dlZAMDWrVsdf2/r1q3yz2ZnZ5HL5TA5Oen7Gjc33HADxsfH5X+7du3S/X+tJ3COS3PBT0g/sVYs49qb78c3H/a+ToYljJNxfq2IStXETw4tyD8rlHnNIYQQQgghhHizWrDWGTM1t6Ka8y6cjDPjznHp+bUSCyZ7CO0i4z/+4z/ic5/7HL7whS/gvvvuw2c+8xn8xV/8BT7zmc84XmcI6bqGaZp1X3MT9Jr3v//9WFxclP8dOnQo2v+RHsUhMrJdmpC+4vYnT+FfHziKv/n3fZHeRxS/eGUyih1F07R2FR9SnYwUGQkhhBBCCCE+rNXGpXdNDgGwMxlN08SJJatpWoxLT9TGpStVE0sbZfdbkZiiPZPxv//3/44/+IM/wK/+6q8CAC6++GIcPHgQN9xwA37jN34DMzMzACy34rZt2+TfO3HihHQ3zszMoFgsYn5+3uFmPHHiBK688krPfzefzyOfz+v+v9NzONulKTIS0k8srFt5JadXoo0UFGrFL3kPJ2M2ncLYQAZLG2UcWVjHE8ftwi5mMhJCCCGEEEL8WK0Vv+ycGsTdTwPLhTIK5QpWNsoyemnLqCUyDmTTGMqlsVasYGGtiPHBbLe+bdIE2p2Ma2trSKWcb5tOp1GtlZCcffbZmJmZwa233ir/vFgs4rbbbpMC4qWXXopsNut4zbFjx/Dwww/7iozEguPShPQvSzWRcXE9WjiyGHv2cjICwHStYfqHT56Capimk5EQQgghhBDix1otk3Hb+ADSKWtKdWGtJJulN43kkFOMDmJkWh2rJvFGu5Px53/+5/Gnf/qnOOOMM3DRRRfh/vvvx4c//GH85m/+JgBrTPraa6/F9ddfj927d2P37t24/vrrMTQ0hDe96U0AgPHxcbztbW/De97zHkxPT2Nqagrvfe97cfHFF8u2aeKNo/iF49KE9BVijGClUEaxXHXcoJtho+ZkHMh6//3p4RwOnFrFbY+fdHydIiMhhBBCCCHEj5VaJuNIPovJoSxOrRRxeqWI4zKPccDx+omhLI4srGOBDdM9g3aR8cYbb8Qf/dEf4Z3vfCdOnDiB7du34x3veAf+5//8n/I173vf+7C+vo53vvOdmJ+fxxVXXIFvf/vbGB0dla/5yEc+gkwmgze+8Y1YX1/HVVddhU9/+tNIp72dNcSiqqzxK1Uu+AnpJ5YUB+PCelGOGjSLLTJ6X29Fw/TeZ+YdX+e4NCGEEEIIIcQPkck4nE9jajiHUytFzK0W7dKXMef6xS5/oZOxV9AuMo6OjuKjH/0oPvrRj/q+xjAMXHfddbjuuut8XzMwMIAbb7wRN954o+5vMdGomYxlZjIS0lcsbdgi4+JaKYLIaImFXpmMADA9Yt3shXP6vC0j2HdiBQWKjIQQQgghhBAfRCbjUC4jjQunVws4XhuX3uoWGYfthmnSG2jPZCTdRXUvsviFkP5iad1uXYtyIy6Ua8UvDZyMgkvPsAq6OC5NCCGEEEII8UNkMo7k05getnLe5wOdjFn5GtIbUGRMGKqRqMxxaUL6CtXJGGWkQDgZ/cel8/LXOyYGZXYKRUZCCCGEEEKIH6qTcXLYEhDnVouy+KU+k5Hj0r0GRcaE4Sh+oZORkL5CzWRcjOBk3Kg5GQf8xqUVJ+Nzdo7LgplmMhmrVRMnljda/h4JIYQQQgghvcVqQc1ktIwLp1f9i1+mak5GFr/0DhQZE0bVkclIVxEh/cTyhjouHd3JGGZc+uKd4zK7sRkn4w3/9ihe8KffxT1Pz7X8fRJCCCGEEEJ6B1H8MpTLSOPC3GoRs4s+49LDdDL2GhQZE0ZZcTKqvyakXzm9UsDVH74Nf/39fd3+VtqOs106eiajn5NRFRmfs2NCOhmLTWxsPHliBQCwr/a/hBBCCCGEkGSzWrDWGcNK8cvRhXUs1cwSW33GpeeYydgzUGRMGM5xaToZCXnw8AL2nVjB1x482u1vpa1UqiaWC7aTcSHCbl+hQSbjllE7k/HiHePIpoWTMfzGhrhW0XFNCCGEEEJI8qlUTayXaiJjPi1FxsdmlwEAQ7k0RvMZx9+ZqomMHJfuHTKNX0J6Cee4NJ2MhIjzoJDwUpIVZVQaAOZXI2Qy1m7+viLj2AB++5XnYXwwi/GhLHLp5p2M4rjQcU0IIYQQQkh8WVwv4Y/+9WFcdeEW/MLzdrT8PkJgBIDhvO1kFOu0mfEBGIbh+DsTol16rQjTNOv+nMQPiowJQxUW2S5NiO2Y21BuaklEbZYGgIX1KJmM1meV9xmXBoD3vuZZ8tdyXLoc/jOumMLJSJGREEIIIYSQuPLxHzyFrz54FD89thRJZFyrTV2lDGudoZZJAvV5jICdyVgoV7FeqmAoRwkr7nBcOmGoTka2SxNii1nrCRcZF10ZjFFGCsRuop+T0Y09Lh1+Y0OOS9PJSAghhBBCSCxZXC/hH+44CACynKVVVkSzdC4DwzBk3qLAS2QczqWRTVvuxXmOTPcEFBkThprJWOHinZC+dTIGNbAdXVjHe/7pQTx8ZLHuz8qVqhT+BrLhbhHC8djMxkaZmYyEEEIIIYTEmn+442mZ+75SKGN5o3Whb61orceG8paRIZdJYXTAdia6S18AwDAMTNbEyHmWv/QEFBkTRsVk8QshKmIcd6NUhWkmV3hfWq81so1ZpSxBTsZb7j+Cf77vMD5221N1f7ahuBHDOhntcenw15xqTWQscTOEEEIIIYSQ2LFaKOOTPzrg+NrxpdbdjKvCyaiUu6gj09s8REYAUmRk+UtvQJExYVQcmYxcvBOiCu9JLn8RTsYzpoYA1HJLit7uzVMrBQDAo0eX6v5MdXyKQpdGZFspfqldnyrMjiWEEEIIISR2fP7HB7GwVsLZm4ZxzuZhAMDsYqHl9xNOxmElV3FKERm3eoxLA3b5y1zApBaJDxQZE0bF0S7NxTshamyAn+iWBJZqmYzbxgeRSVm5JX7lL2IX8MDpVawVna3UQojNZVJIpcK1t7XiZBTiIotfCCGEEEIIiRcbpQo+8UPLxfj/vfxc7JgYBADMRnEy1tYdQzl7WkoVGb0yGdXXLFBk7AkoMiaMapXFL4SoqI7ejSbaj3uNpQ3rpj0+mJUhyvOr3iMFIq/RNIHHZ5cdfyacjAMBzdJuci04GVn8QgghhBBCSDy55f4jOLlcwI6JQbz+kh1SANQ9Lu0QGX3GpRutbUi8oMiYMBxORo4hxobljRLe9fn78M2HZ7v9rfQd1T5zMo4NZuRIgd9un9rM9ugxH5ExZB4j0KqTkcUvhBBCCCGExJFHj1mxSq973nbkMikpAEZpmF4t1IpfHE5GK08+nTKwaSTv+fcma2uboGJLEh8yjV9Cegl1NJRjiPHhzqdO4+sPHcOJ5Q387J6Zbn87fYXDyVhKrqAlMhnHBrLyRryw7uNkVJrZxAOEQHxG+ZDN0oDiZGxCZCyz+IUQQgghhJBYIgTB8UFrXSHyEo9FEBlFTNOIw8lovf+W0TzSPlFNwu1IkbE3oJMxYagiY4lOxtggxkiTXDwSV9RikfVSkp2M1k17TB2X9nUy+ouMhbIYl27eydhMo71wmFa4GUIIIYQQQkisEILgcM11qGVcuiicjGq7tOVe9Ct9AZRxabZL9wR0MiYMOhnjiTguzTi9iB5U3auQZJFRcTJODIpx6fobcblSxfKGXfby2OwyTNOEYVg7h4Wak7GVcely1US1aoYqjLGdjDwnCCGEEEIIiRNuQVCOS0cQGddkJqO9znjFszbjpbs34Zcv2+X79yYbREGReEGRMWFUWPwSS4Tg24zTi+ihf5yMdibjZEADmzpCnUunsFIo4/D8OnZNDQFQMxnDG92zaVtULFaqGEg1FijFtarCcWlCCCGEEEJihVsQFCLjqZUCSpUqsunmh2JXCh5OxpE8Pvu2KwL/nnAyzq1SZOwFOC6dMFj8Ek+EkELht/P0SyajcCeODWRldorXSIEQHscHszhvywgA4KfKyLRo4M63MC4NhG+YLsviF54ThBBCCCGExAm3k3FqKIds2oBpAieXCy29pxzBzodfZwB2JqPXlBaJHxQZE4bapMuss/ggxF86GTuPo126L5yMWUwO+d+IhfA4OZTFhdvGADhzGe1x6eaLX4DwkQDVKs8JQgghhBBC4ohbEEylDGwZjTYyLYTL4VxzA7ViXHqlUGb8WA9AkTFhsPglnpQpqHQNp5MxmSJjpWpiuSCcjJnA3BIxZjAxlMOF20YBOEVG8Rnlm8hkNAyj6YbpMselCSGEEEIIiSWrHqPNMpexxYZpr0zGMIwNZCEi35nLGH8oMiaMMotfYkmlJi5y56XzVPpAZFxRilxGB7IYHxLj0h6ZjLWvTQ5l8WzpZFyWf75R+xnNZ5q7PYhcxrA/4zJCgCIjIYQQQgghscJul1ZExrF6kdE0TSyGHGP2apcOQyplsGG6h6DImDCqjkxGE6bJBXwcKDOTsWv0g8gomqUHs2nkMik5Lr24HjQuncMFNZHxmbk1LNfewy5+aW6HUeQyhnXrigiBMt29hBBCCCGExIZq1cSaEAQV16FwMh5XxqX/+Gs/xXP/5Nv4n195GKuFMoJYbdHJCAATASYKEi8oMiYM93q9TJdQLKhwXLprlPsgk3FRaZYG4MhkdG80iBvzxFAOU8M5bB3LAwAen7XcjIWaE3GgieIXwBYZCyGcjKZpynOC1yhCCCGEEELig7pm8nQy1kRG0zTxbw8fAwD8w50H8ZqP/gA/2nfK932FO7JZJyOgrm8oMsYdiowJo+oSFDgyHQ+ka4vu0o6jnhNJbZcWTsaxAWuHT+z0lasmVlw7igur1munhq3XuMtfbCdjs+PStUzGEEJ6xRHrkMxjQgghhBBCSC+yWhMDDcO5JtjqymQ8PL+O40sFZFIGdkwM4vD8Ot78dz/GVx886v2+tZzHkXzrIuPcKsel4w5FxoThFhVZ/hIP1KZvjkx3ln5wMi6t10pfBi3hcCCblg8E7oZp1ckI2CLjT2u5jEKIzbfoZCyFcDJWFOGXxS+EEEIIIYTEh7WC3QJtGIb8utvJuPfgPADgoh3j+NbvvgyvvXgGAPCNnxyre89K1ZRrsaFc8+PSkxyX7hkoMiaMCp2MsUQVujgy3VlUgTfpmYxjA/au4KQMR3beiBeUTEag3slYaNHJmGvRyUjRnRBCCCGEkPiwKseanWKgWvximibuPTgHALjszEmM5DN47cXbAABzq/VCoGMEuxUn4zDHpXsFiowJo1p1i4wUtOJAhSJj16iYfSAyykzGrPzaeO3XbifjnNIuDQDP2zkBAPjJ4QUcWVi3MxmbLH4RbdRh2qVV0b1Mt3VXWS2UceN3n8STx5cbv5gQQgghhCQeUfriFgO31LLcC+UqFtdLuPdpy8l42ZmTAICpmhB4erVQ956i9CVl2OuGZhBmCncUFIkfFBkThrtEocRRxFigCl1hnF5EH8526WR+9ksbtXHpAVtk9HcyOselz5gewpXnTqNqAp+762D0TMYQImPVITLyGtVNbv3pcXzo1ifwl999stvfCiGEEEIIiQFCEHQ7GQeyaSkkPnliBY/XNqkvPcsSGaeHLRHSy8kom6VdI9hhEWUxIteRxBeKjAmjvvglmaJKr8Hx0O7hyGQsJvOmtORqlwbs8hfRPA1YDXByXHrYFiR/48qzAAA33/2MfH2rmYxhRHSHk5HnQ1dZrj3wLW9wV5gQQgghhChORo8W6K21kelvPHQMpgmcMTWELaPW14QAubBeqstd93NHhmU4n669D59Z4w5FxoThPpnpEooHqpASphiD6EN1zW2UEyoyutqlAdupOK80sC0XyvKaIJyOAHDVBVuwY2IQ82sl7H3GGntoOpOxiXFp9TrF4pfuUqmJwhxbJ4QQQgghgC0IDuXrTQcztZHpbzxklbuIUWnAjmMyzfppKumO9HjPMAzSydgzUGRMGHUiI11CsaCiLOCZydhZVPEkuU5GZ7s04N3AtlATHAezaUfmYiadwlteeCYA66EAAPJNZjJmmyh+YRFSfBDHolTmvYIQQgghhNhuQS8n48y45Vo8vmTlLopRacBaU4hpKvfIdJA7MgzDOToZewWKjAnDLTJyAR8PVFGFmYydRT0nCgl1kXo7GevHpeddpS8qv3r5LkcI80CL49JhnLrMZIwP4vPndYkQQgghhAC2W9CdyQjY49KCy86ccvxelr+suJyMPo3VYZGZjAk1jSQJiowJo+LOZOQCPhaoWZnMZOwslb7NZKwvfplzlb6oTA7n8AvP2y5/n29yXDrfopORubHdRZwfHJcmhBBCCCGA4mT0yE/cNm6LjGMDGezeMuL486naOsPtZJTFL1EzGdkuHXsoMiaMat24NBeOccCRychj0lHKfZDJuBzYLm07GUWztFr6ovLrLzpL/rpVJ2O4TEb7NdwI6S7i2sRxaUIIIYQQAoR3Mj7/zEmkUs6maOFknFsteL5nqyIjnYy9Q2tHmMSW+nFpLhzjgKNdOqEju3Glv5yMHuPSipNRlMB4ORkBYM+OcbzpijOw7/gKznPtSjZCZjKGEhntX1Nk7C5C8C3RyUgIIYQQQhDsZJxRnIyXnzVV9+fTI7Vx6bpMRpHz2Nq4NNuleweKjAmjvl2aC8c4wEzG7uHOZKxWzbodt16mUjWxXBBORvuSbhe/eDgZPTIZBdf/4sUtfR/SyRhiY0O9LtFt3V1k8QuPAyGEEEIIge0WHPQogpxRnIyXKs3SAtvJ6M5kFO7IaE7GUsVEsVyVaw8SP3hkEkZdJiOdjLGgwkzGruEW3pNW/rKyYe/mjTqKX6wb/NJGSX4GQnCc9HEyRqG5cWn7mFTN+pgH0jlkJiOvS4QQQgghBHbuoXAPqowPZnHhtjHsmBjE83ZN1P351HAegEe7dMB7hkEd3U7qdFpSoJMxYbBdOp5UmMnYNdzjuBulCgZbtOnHEdEsPZhNO3b0JgazyKYNlComji6sY9fUkNIurV9klOPSlcY3/XrHtYlcgtylvQSdjIQQQgghRMVugq6XiwzDwFfe9WIA8HQTTvs4GVcK0ZyM2XQKuUwKxXIVq8UyxgMms0h3oZMxYXgt3kn3UY8DF/Odpepy966XkrXztejRLA0AmXQKz942BgC4/9ACAGBBOBl9il+ikK89ZIQpEGGsQ3wQ4+phHKiEEEIIIST5rBVFSYu3MSOXSfmOK/uNS4ssxZEWnYyA7WZkLmO8ociYMOhkjCdqmy4X853FPQa6kTCRUTgZ1WZpwSVnWDkp9x2cB2Df7P2KX6KQk07Gxj/f7s0PRgh0D3EsuCFFCCGEEEIAYLXg72RshBAZ3cUvUTMZAWBYNEwXkrWeSxoUGROG27XlFh1Jd1A1FC7mO4v7HEiak3FpvVb6MlgvMj6/FsZ8/zOWyLjQxnHpVjMZvX5POkeF49KE+HJobg3v+/KDeOL4cre/FUIIIaQpvnTvIfzVd5+EaTb/nC2djC0IgqJden616Pi3o2YyAraTcZVOxlhDkTFh1I0h0iEUC1QnIxfzncVdhrRRStbnbzsZ6x8CLqmFMT9ydAkbpYpS/KJ/XFpkMoYp1qm/TiXrmPQSdiaj2dJDKCFJ5l/vP4J/uvcwPnfXwW5/K4QQQkhoTixv4A/+5SF8+NYnsO/EStN/XzoZWxAEhZOxXDWlGQLQ42Qcylt/d41OxlhDkTFh1I0hMussFqhiL8elO4tb0ErcuLTMZKwXDndODmLzaB7lqom9B+eli7Mt49IikzGEYMjs2PigHgseB0KcbJSta+bKBh0ThBBCeodb7jsin/GemVtr6u+aphnJyZjPpDFSEwNPrxbk11c1OBmH6WTsCSgyJgz3uDSdjPGg4ih+4THpJO5SkcSJjLXFr1cmo2EY0s34vcdOAADSKcPT9RiVZsal3WIWr1Pdg6VUhPgjrk1Ji9kghBCSXEzTxD/de0j+/sjCelN/v1ipyufDVpyMQH35S7Vq4tSKJThGMTsIF6QQQUk8ociYMISYlUkZALhojAtcyHcPoTGKDI+kLRaFk3HURzgUuYzfffQ4AGtU2jAM7d9HLm29Z5jil7qCKjquu4Y6qs4NEEKclCgyEkII6THuP7SAp06uyt8fnm9OZFRHkYey0URGUf4yu7SBtWIFmZSBM6aGWnpPwHZBxk1kPDS3ht/4+7vxe//4QLe/lVhAkTFhiLV6vuYq4vhbPFAdphQZO4twMg7XbPvrMbspRWWlNnow6uFkBOxcxqdPW6MS7RiVBqKNS7P4pXtwA4QQf0SectLuG4QQQpLLl+49DMB+Nj8839y4tBhFzmdSyKRbk4umXU7G/TXR88zpIZnj3grSyVhobVz6tidO4sFDCy3/+34sbZRw2xMn8aOnTml/716EImPCEIJKvrbrwEKFeODIZOQx6ShCwBLZIBsJy8QUWWEjPk7G5+yckM5moD2lLwCQS1vXnHDj0s7XUNzqHo5MRjoZCXFQqtLJSAghpHdYL1bw/x48CgB40wvOAAAcadbJKPIY863HK7nHpZ86aZXPnLt5pOX3BNRMxubvy3OrRfznT92Nt//DvZG+By/EM3QmRXkNoMiYOMQacUC6irhojAOOTMYyj0knEZ+9sNdvJMyRIp2MPg8Cg7k0Ltw2Jn/fbidjGJHRnR1LJ2P3oJOREH8qYlw6YfcNQkhyObqwjkNNFn2Q5PCtR2axXChj5+QgfunSnQCaH5eWzdK51gtapkZq49IrLpFxSzSRUXxPay0UvyysFVE1beFTJ+J5OpPWH0nVi7RFZDxy5Aje8pa3YHp6GkNDQ3je856HvXv3yj83TRPXXXcdtm/fjsHBQbziFa/AI4884niPQqGAd7/73di0aROGh4fxute9DocPH27Ht5soqrUfcOlkZNZZLFCPAxfynUVc9EU7WtKKX5ZrDwIjAbuNl5wxIX/dLidjtnZTLYRxMro2P7gZ0j0qyrWJLmtCnIi8WDoZCSG9QLVq4nU3/Qg/91c/RKHM61Y/8qW9VuHLf3z+TuyqZR+eXi02JcpFaZYWTA0JJ6NV9qLLyThUW++sFpr/+RbrjXLVlJqJLsT0aDpFkRFog8g4Pz+PF7/4xchms/i3f/s3/PSnP8WHPvQhTExMyNd88IMfxIc//GHcdNNNuOeeezAzM4NXvepVWF5elq+59tprccstt+Dmm2/G7bffjpWVFVxzzTWoVHjBDEIIKrla1gHH3+KBeh2jyNhZ3OPSSVssrmxYxS9+49IA8PwzJuWvJ2OYychYh+6h3iN4vyDEiTgnkrY5RQhJJsVKFadWCljaKGN5o7XMOtK7HJpbwx1PnQYA/NKlOzE+mJXFkEebaJiWTsYWm6WB+uKXp05YmYznbh5u+T0Be1y6FSejOm2le2NdaDBZjksDaIPI+Gd/9mfYtWsXPvWpT+EFL3gBzjrrLFx11VU499xzAVguxo9+9KP4wAc+gDe84Q3Ys2cPPvOZz2BtbQ1f+MIXAACLi4v45Cc/iQ996EO4+uqrcckll+Bzn/scHnroIXznO9/R/S0nCtvJyHHpOFGmW6hrSJFxQDgZk/X5rzTpZGzXuLQomwrVLh3DcenbnjiJt/zdj/H0qdXGL04QFY5LE+KLOD84Lh0vPvbvT+Fdn78vFvcOQuKEeh/nPb3/+Of7DsM0gSvPnZYuxh0TgwCAQ02MTOtwMk6P2JmMK4UyZpc2AADnRHUy1r6nVjIZi208P4TISCejhXaR8atf/Souu+wy/PIv/zK2bNmCSy65BJ/4xCfknx84cACzs7N49atfLb+Wz+fx8pe/HHfccQcAYO/evSiVSo7XbN++HXv27JGvcVMoFLC0tOT4rx8Ri/eBjKXyVzguHQsqFXUhz4fiTmJnMibVySjapf0fBM6YGpItb1PD7RqXDp/J6F4YlmKwUPyr7z6J2/edwl9+98lufysdpUSRkRBfxDmxVqrANLt/nSIWn7x9P77+0DE8eWK58YsJ6SPUNUaY5zGSHKpVE1/ea0XL/fJlO+XXd05aYmMzuYyiXTpSJuNwHoAlMu6vjUpvHs1jfDDaOkRk7LfSLq2eE7rX42IqK8tMRgBtEBn379+Pj33sY9i9eze+9a1v4b/+1/+K3/md38E//MM/AABmZ2cBAFu3bnX8va1bt8o/m52dRS6Xw+TkpO9r3Nxwww0YHx+X/+3atUv3/7WeoM7JGIPFO3GVK/Cm31HKrnHpQoJExmrVlDt5QQ1whmHg1RdtRTpl4KLt4235XpoZl3aP5XZ7M2R5o4QHDi0AAL7+k2NtCYSOK5Vq+x64COl1xP3DNMPlzZLOII4FHaaEOCnTydi33HXgNA7Pr2M0n8HPXrRNfn3npOVkbKZheq0QvV16WhmX3ndC5DFGG5UGojkZ2+n0pZPRiXaRsVqt4vnPfz6uv/56XHLJJXjHO96Bt7/97fjYxz7meJ1hOA+AaZp1X3MT9Jr3v//9WFxclP8dOnQo2v+RHkX8gIvRRWadxQOOJHYHNdRXWP6T5GRcVfJIgsalAeBPX38x9v7h1dizo00iY9qOaGgUplznZOyyuPXj/XPyeypWqvjy3v65f5QrvDYR4oe6QchcxvggrlsUfglxoppLeH70F1++13IxXvPcbRhUHIhCZDw8H75xXI+T0RIZi+UqfnJ4EUD00hdAcTK2kMmoPufqdvqK+1ImzUxGoA0i47Zt2/DsZz/b8bULL7wQzzzzDABgZmYGAOociSdOnJDuxpmZGRSLRczPz/u+xk0+n8fY2Jjjv36kIp2MtXZpOlNigZpBx0zGzqEuEMVNKUkLRZHHmE0bcmPBj1TKaFseI2A7GYHGP+PuTMZuX6du33cKALBpxBrt+PyPn9HeOhdXuAFCiD/qRm2SNqh6HZFzTRGFECdOJ2N/PMcQayLnGw8fAwD80qXOaU5bZGwhkzGCk3Eol5Zrk3uengOgR2QUTsa1VjIZ21r8wnFpFe0i44tf/GI8/vjjjq898cQTOPPMMwEAZ599NmZmZnDrrbfKPy8Wi7jttttw5ZVXAgAuvfRSZLNZx2uOHTuGhx9+WL6GeFM1nU5GjkvHgwrdQl1BFVCS2C4t8hhH8pmGTvB2k003ITK626W7PC79o5rI+D9eewFG8xkcPL2GHz11qqvfU6dwioy8XxCiom6AcDQ3HpimKa9VSYo/IUQH7XRqkfjy9Z8cw0apinM2D+P5StkjAOyYsDIZj7TSLh3ByWgYhhyZfvSY1ZVx7hYNTkYhMraSydjOcemKGJemkxFog8j4u7/7u7jrrrtw/fXXY9++ffjCF76Aj3/843jXu94FwPqBu/baa3H99dfjlltuwcMPP4y3vvWtGBoawpve9CYAwPj4ON72trfhPe95D7773e/i/vvvx1ve8hZcfPHFuPrqq3V/y4lCOhkzwsnIG0wcUB113XZt9ROqYy6J7dLLolk6oPSlU+QUkbFR7qj7HOjmOXF8aQNPnliBYQA/c8EWvOH5OwAAn7vrYNe+p07ivDYl59wgRAfqBkgrrgmiH3WPaoMiCiEOSjQ19CVfEoUvl+6qMx0IJ+PJ5ULoaS4d7dIAMFVrmBbXbR2ZjGIUfK1UaXrqyFH8Uta79hAaTJaZjAAA7SvTyy+/HLfccgve//7340/+5E9w9tln46Mf/Sje/OY3y9e8733vw/r6Ot75zndifn4eV1xxBb797W9jdHRUvuYjH/kIMpkM3vjGN2J9fR1XXXUVPv3pTyOdbl1R7wcqrkxGOlPiAUcSu4PqIBWW/0SNS0snY3sao5shlTKQTRsoVczmx6W76GQULsaLd4xjYiiHN7/wTHzmzoP4zqMnMLu4gZnxga59b51AFRYZ5UCIE2Yyxg/1GYpORkKclNku3XfsO7GCvQfnkTIgN8pVJoayGM6lsVqs4MjCeqiRZelkzEfTXUTDNAAMZFPYPj4Y6f0AO/7KNIGNckWOT4fB0b6u+Zm3VFvLsPjFoi1+zmuuuQYPPfQQNjY28Oijj+Ltb3+7488Nw8B1112HY8eOYWNjA7fddhv27NnjeM3AwABuvPFGnD59Gmtra/ja177Wt43RzSAW7wMik7HLY4jEwpnJSOG3U6g//2I3LkkLRZHJOBohM0UnYmS60YOtu0263MVYB5HH+OLzNgEAzt86ihecNYVK1cTN9zzTte+rU5Q5Lk2IL45x6QTdO3qZMostCPGlyI3DvuM7jx4HALx092ZsHavfGDcMAzuabJjW5WQU49IAcM6mEaQ0CHADmTSEWXO10Nx9uVi2X9+uceksi18AtElkJN1DOOZysl2ai8ZuY5omnYxdQoi7hmHniiRpoSicjMMRdxp1kZMO6gbj0u5Mxi5dp0zTlE7Gl9RERgB44+XWhtb3Hz9Z93c+/oOn8B8/dgeWNkqd+SbbTIXj0oT4om5UMZMxHqjXKYqMhDgpM5Ox7xCuwzOnh3xfs3PS+rOw5S862qUBu2Ea0JPHCFiTU0PZ1hqmS210+oq1DZ2MFhQZE0b9uDRvMN3GXXLBY9I5xGefSRnS3ZukTMYVmcnY/XFpwM5lbLTwc2eodMvJ+NTJFRxfKiCfSeHSMyfl18WvHz225DhfTdPEx/79Kew9OI+7njrd8e+3HZS5AUKIL3Qyxg91kZikyQRCdKDe0ykyxodK1cSdT52WgqBOxDUxE1A4InIZjyyshXrPtUL0dmnAJTJqyGMUDNW+r6adjG0tfrHeL8N2aQAUGROHW2Ts5hgisXAfg0alGEQfdtOXIYOCk7RQlCJjTMalhZOx0YNtvZOxO+fE7U9aLsbLz5qSIjQAnDk1hNGBDIrlKp48viK/fmhuHfNrloNxdmmjs99sm2C7NCH+MJMxflQ4Lk2IL+0UUUjrfOOhY/i1T9yFD337Ce3vLZ6hswHi1o4JS2TstJNx2iEy6nEyAsBwrjUno6P4RbfIqBhbCEXGxFGty2TkorHbVF0lF8xk7Bzis08bBgYUAazZNrK4IjMZY9AuDdhOxsaZjPFwMt6+z3IjvlgZlQasUYw928cBAA8dWZBfv//QvPz10YVkiIzqOCgXJIQ4UTdA2C4dDxzFL2UeE0JUym0stiCtc3Rh3fG/OpHiVoDI2Oy4tMxk1Opk1CcyirKX1SbvyyVHZqnetYc49zLMZARAkTFx1DkZeYPpOnVORh6TjqHmYwwqu3EbCVmYLG/E08nYyBFXJzJ2SXi/7xlLNHzRudN1f3bxTiEyLsqvPXjI/vXsov4HxW6gfva8NhHipKRcq5Lkgu9lHMUvCYo/IUQHzGSMJ+L5qh3PWeI9g8almy1+ke3SmjIZDQM4e5O+cWmRRb8excmo+fwQpZZZOhkBUGRMFKZpQjx75YWTka65rlOpUGTsFjKTMZ3CQEYRGROyMIntuHQleDFe72Ts/PEoVaqYWy0CAHbVHr5ULt4hRMYl+bUHVCfjYu87GU3TZLs0IQGo16oNOhljQZlORkJ8UTdG6GSMD0LcascxsVuNg5yM1nPu8eWNhtfNcqUqoyiitkufu3kEQ7k0nrdrwmH2iIp0MjaZyeh0Muo9FiVpbKG8BgDxWJkSLagPw7L4pQuLd+KETsbuIc6JlGEglTKQy6RQLFcT40hZqTUcj8RkXDobcly6LpOxC+PS82uWwGgYwMRQru7Phciolr88fNQWHI8lwMno/th5bSLEiXpOJOW+0evQyUiIPyWHU4sbh3GhULuXtCNHVqz1g8Z0p4dzGMimsFGq4tjCBs4KcBWuKfe6oXw0YXByOIcf/f7PaBUYAdth2XQmYxszS8WaM0js7ScotSaIipL9N0AnY2yob5c2YZo8Lp2g4grhFbmMSQnwj52TUYiMIcelxURBN2Id5lctgXZiMIu0x2jDmdN2+csTx5fx+OwyiuWqfO3xxULPZ3u6HaTM8CXESYXj0rFDfa5l8QshTtT7eqOpEtI5xOZ7OzZzZRZgwJiuYRiy/OVIg1xI0SydSRnyuT4Kk8M5R7miDlrNZCwqwrvuOAFxbL3WFP0IRcYEoa4XmckYHyoegiLHEjuDmskIwG6YTsjYW1wzGcMWv4iHjm6cD2JUWg2lVjEMQ7oZHz6yiPsPLQAAXnDWFAzD2g09XXuPXsW9AcL8JkKcqIIWi1/igTqhw3FpQpyUHDnLXGvEBSFAteM5SwjL2QaCoCh/ufF7T+LJ48u+r1ObpQ0jnoKZyGRcKzTnZCw5nIwsfmkn8ViZEi2ou1f2uDRvMN1GZDKmDHs8sVSpSkGGtI+KS2QUolZSFibSydhj49JqQdVasVIndnWCRiIjYI1M3/HUaTx0ZFHmeF521iT2n1rB8aUCZhc3sHk035Hvtx0wyoGQYFRBKykO+F6HTkZC/Cmx+CWWyEzGdoxLS3ErWBB8ywvPxI/2ncJd++fws3/5Q/zq5bswNZzDI0eX8PjsMq44ewof/pXnSSdj1GbpdtK6k7F949LlamNHaT9BlSNBqE5Ge1yaN5huI8Rf1SrOxXxncI9LD2aFkzEZn79ofxuNyYNAXjoZG4RK186JfK2MpxvFL3NrjUXGPaL85fAiHqg5GZ+3awIz49bIydEez2V0l1IxXoMQm2rVhDqIkBQHfK+jPtdS+I0XSdnA7WXU+ziLX+JDe4tfRKtxsKzzqmdvxbd/92V41bO3olI18fkfP4Mbv7cP33vsBI4srONf7j+CowvrDidjXBluMZOxnSK8OA6NxN5+gSJjglDHcnNyXJqLxm4jhK5cJgXhOueNvzMI8Uo4GUXrehIWJqZpxs7JKK47jUYQxI//QLZ716m5lcYi43N2ivKXZTx1cgUA8NxdE9g+PgAAONYg1ybuuIvBuPlBiI37/GAmYzxwFL/QqRUb9p9cwfP++Fbc8I1Hu/2t9DXqdYtOxvgg1n2ltoxLh3MyAsA5m0fwiV+/DF/4L1fgtRfP4Fcv34U/+YWLcP7WEQDAnU+dlsJdrJ2M+dbapTtR/EIno0V8f3pI06gjhyKole3S3UeIv5lUCtm01W7MnJTOIH78ZSZjTdRKwmKxoPwcxSaTURa/NBqXdjsZu9cuPenRLC04Y2oIYwMZLNWyL3dODmLTSB7bak7GY0sbof6tYrmKIwvrODugza8b1JVSMV6DEIl782OdTcaxQHW+s106Pjx8dAnrpQrufnqu299KX1N2ZDLy/IgLonCkHSaTknTQhfeOXXneJlx53ib5+yML63ji+Aru2n8aLzt/M4BkOhlV4V33sShV7fU+oZMxUagKutjNoJOx+6itX1L85e5iR3A7GQcS5GRcUcKOh3PxEBmzGetzbuQuEaJiPiucj50/H06HyGQ0DEOOTAOWixEAtkknYziR8X999RG88i/+HXc8darF77Y9uO8PvC4RYuPe/FhvcjFD2kPJkcnY+/fypCDuH4wV6C7MZIwnQtBqh/taPMtlIzjoXnTONADgzv2KkzEmawsvhJOx2UK29joZRQEPnYwARcZEIRxzqZQhVfRy1YTp0W5MOodaPiIuPN3IoOtH/DIZEyEyKs3SqZhY83Np0RYd/PNdNe3iF6DeUdcJ5kOIjABkwzQAXCJExomayBgyk/H+Z+YBWC3VcaLOyUjXQ6zgArG7uDOtk+CATwLq5sgGnYyxoZ0iCglPiU7GWCKyyttxTKSDLkKr8eVnTSGTMnB4fh2Pz1rxQEMxmZLyQjgZmy1+cbRLl/WuPcS5l6aTEQBFxkRRFWKWYThU9G4s4IlN2SEyimIMHpNOIH72U3VOxt5/8BJOxuF8fMYZcplw7dJikSiORzfiA8I4GQHg4p0BTsbFxk5G0zRxaG4t9Os7SV27NO8VseF/fuVhXPq/b8XRHs/97GXqnYy9f99IAo5xaToZY4O47ydhE7eXUTdHKPjGh3a2SwsHXZTCkeF8RuaQf/ex49bXYjwuLdql1wpNFr+U2yfCV5rIxuwHKDImCFXMUnczupF3RmxUN50QGbm72BncTkYhaiXBkbKsOBnjQq52Y230ECWOi3AydsPZG9bJ+NydEwCsvMk9260HMJHJeHxpQ27u+DG3WpQ7rbMxExnrnIxckMSGuw/MYblQxqPHlrr9rfQt7mcniifxoOwYl+Y1Ky6I51qeJ92l1MZxUNI6YjO9ata75KNij0tHk3VeWBuZPnja2hgfjLXIKDIZWx+XLujOZBTZmDGZLus2FBkThDqWq/6A8ybTXdTjYrfv8ph0AlV4B+w24yQ8BNvN0tkufyc2YZ2MFTkubT0kdNptbZom5tbCiYy7pobwkV95Lv7mzc+XD1xbRvNIGdZD46mVQuDff6bmYgTi52R0X4cY4xAfxLFJwoZIr+I1Ls34me7jdDLymhUXCtLJyGPSTdSJBEZuxIe2Fo5UnPnzrfKic6cdv49zJqOY4lqNUPyie2NddjBEGFtPEvH96SFNI3LO1LFcgOUv3UYVGY3a9b8d7WKkHvWcAOxMxiQs3FcKJQDAaJycjCFF9EqXi19WixX5oNFIZASAX7xkp+P3mXQKW0YHMLu0gWOLG9gyNuD7d1WRMe5OxiLvFbFBuB64YO8eYpMqZVjuk0rVRKliIpehS6GbqPEa1jGpOp55SXeQ49JlS4w3DJ4n3aDscDLynh4Xiu4swMaPnqER96qohSOXnTmFbNqQPzdDMYpjcmOPS8ep+MU5Pdfv8K6cIGT+nGE4BK0S3SldRW04tseleePvBGVXCG+yMhmtG2u8xqWtz7nRCII4Lt1yMopR6YFsSj6oNEvY8pdDish4YnlD+5hMFOoyGel6iA0cPew+4jqlXmPZnNt93NdQuhnjgVi8myY30ruJur6gkzE+qMeiUNF7H9HloBvMpfG8WvY4EHMnY+17K1aqTf2cl9oowgu9hSKjBUXGBOFW0EU2A52M3cUzk5E3/o4gxnIT3S49EJ+HgGzYcWlXJmOnRXdZ+jLU+layKH85uhDsTlSdjFUTONlgvLqTuMVdjkvHB9vJ2PvXql5FLEYGsml5D0mCC77XcW+OFHhMYoH6XLvBkqSuwUzGeKIK77rFX51ZgC86xx6ZHopxJqOaF9nM5l87x9ZZ/OKEImOCqLjy58QPOUXG7uLIZGTxS0dR3b1A0jIZrXHpODoZG45Lm8526U6LW8LJOBliVNoPUf4yuxReZATilcvo/tzpsI4PdDJ2n4ocQUvJBQ1Fxu5TJzJy0zYWqAv2DbZ+dw0WI8UTRxag5metsnKvisoLFZFxOEbrCze5TEquOZrJZSy1VewVxhbKawBFxkQhFu7iZ1vsaHBcurvYTsaUFH45StIZyi53b5LapVfi2C7dopOx0xshp0M2SwdhOxkbjUtbfy7+v8Ypl7GuXZrXpdhQliIjj0m3UKNOZJ4vx6W7jntcmkJ8PFDv+zwm3UPdPOQ9PT44HHTtcjJqcNA9/8xJKd7F2ckI2JmRayFFRtM0HQKv/kxGjkurUGRMEFXhmDOEk5Hj0nFAhsenwEzGDiPPibRTZEzCA/ByIX7j0uLBpNEDlHgIFsUvbmdKu5nXIjJaTsYgZ2KxXMXRWmbjJWdMNHx9pxH3BvE8xAVJfBD3iCRsiPQq0pWQNuhkjBHu5ye6teKBw8nIzZGuoRa40dAQH9o5Li2e5bIaHHQD2TR+/rnbMTqQwYXbxiK/XzsRuYxrITf/3OeD7mdetks7ic/qlESm7B6XFk5G3mS6iupkzHJcuqOUXcK73S7d+59/rJ2MDX6+xUZ7t4pftDgZa8UvQc7EIwvrME3r527P9nHctX8Osw2KYjqJOD8Gs2msFivc/IgJpmnKcygJGyK9ihyXTqUgDB10MnYfd8wDRcZ4QCdjPHC0S/PciAWVqul4zi3qLn6p6nMyAsCH3vhcFMsXy2f6uCKclqshG6bdz7jtGltnJqNFvH96SFNUXSKjELQ6vYAnTlTxN5eh8NtJ3NZ14WRMQlD8Ss3JOBonJ2PIcWnxQCQyMjt9PsxrLH6ZXdrwvcaKPMYzpoawbaKx87HTiPNDuLR4XYoH6s8THUHdQ5wP6ZSRqKiNXofFL/GEImM8KNPJGDvcz1bFsr51uToCrFPcirvACNgiY9hxaffaRL+jlOPSKvH/CSKhkZmMhqv4hZmMXaWq5AJmQ46TEj2I+7oQ3gdz1uefhIWiEBlj5WRMh3My2pmMteKXDjvo5tZqIuNI6yLjltEBpFMGKlUTJ5e9G6OFyLhrasgWJWMkMorFuhBQKDLGA3V3nYv17mEXvyiZjDweXcd9v9jg81QsUO8fPE+6h/r8VaqYME0aTbqN222tU/xVNyV1jEv3EkO1cenVkBMG7mdc7ePSyuQiociYKPzHpXmD6SZ2JqPBTMYOU1GC+wFb1ErCwj2OImO21eKXDrut5zQ4GdMpA1tH8wCAYz4j0IcUJ+NMTWSMl5PRHpcGmN8bF9SytiRcq3qVkpKvJBwTGxyX7jru4hc6GeMBMxnjgdtYQjdj92mng059fu63Md1hUfxSaNHJ2C6Rsc+Ogx8UGROE6pgD7HFpLhy7izqyy0zGzuIW3mV4fwIWijKTMU7j0iF/vt0Ouk67rXUUvwBoKBw+c1qIjIPSyXh8aUNeq7uNuDfYx8GMzffWz6g5Whvl3r9W9Spqu/QAi19iQ8k9Lk0nYyxQF/AFXre6hnvNR1ND92mng059r2yfFY4062SsK35pV8s3x6UBUGRMFBXFMQfYSnqJ49JdxZHJmGYmYydxC++yXToBi5I4OhnzLToZKx1+CNZR/AJA5iweXfB2MspMxukhbB7JI2VY14NTq97j1Z3G7WQEeL+IA+qiMAkbIr2K17h02BZL0j7qnIwJuJ8ngSJjHmJBff4fz49u01Yno3Le9Zu4FdXJqFuAr3Bc2gE/hQRRNZ1NuuKHnE7G7lLxyGTkzmJnKLuEd7FQLJarPV2IVKmacrEbJ5ExbOZo2SUydlLYKleqWFwvAYguMu6oiYwHa45FFdM0HePSmXQKW0bjlcsoPvd81n4U4P2i+5Q4dhgL5Lh0KsVMxhjhjtegoBUPnMUvvG51i/oGXR6LbuN20LVrXDrdZyJjq5mMan68zszSchsKeHoZiowJwi2oZEXxC28wXaUinYwpmVnHm35nqNQ5Ge1LXq+N89yx7xR+enQJgO1iBGI2Lp0JV/xSdY9Ld1DYml+zBEbDAMYHs5He6zk7xwEA9x+ar/uzhbUSlmvHaefkEIDG49WdxtPJyGtT13GKjL11nUoSalOkiNrg8eg+7vsFnYzxoKg8U/E86R7uNR+djN3HfQwKGp+zRKxHNm3AMPpL3Bpusl1aPFsJBySgNxO+rMSjEYqMicItqAgnozu/hnQWe1wazGTsMKrACwADGfvG0ktjiCeXC3jLJ3+Mt3zyxyhXqlJkzKVTsswmDuQytlPXb3fQNE3byZi1i1861YA4X2uWHh/MIhMxv+bSMycBAI8eW8aqa1xDjEpvHctLMTVuDdNisZ7PpiGeTemy7j7qQy8X691DDXGXTsYeum8kFXeGb69tGCYVR8wDr1tdw73mY/FL92lnFmBZcdz3G0O1Sa6wMSZiQ2pYmQDTJcJXqybEqRd1bZEU+CkkCDku7cpkpJOxu6hCFzMZO4sq8AKWy7cXW9ePLKyjalqtyI8eW45l6Qtgi4yA/4Ot+vyrCqSdGl8/vaInjxEAto0PYvv4ACpVEw8eXnD8mRAZz5wall+Lq5MxmzKQTXEDJC44xg7pQuka0smYTtmlYRRPuo49xm7dywsczY0FHJeOB8xkjB/tbDWWZSN9OKLbvJPRuneoMVO6nnn7ueXbD4qMCUKcJymZyShExt4RU5KIVyZjscxj0gncTkagN92kc0pRyN1Pz2GlYI38ximPEbBzTgD/B1tVTFTH13WOLAQhnIxTQ9FFRgC4pOZmvO+gc2RaiIy7pobk12wno1UUY5omPv6Dp/CtR2a1fC/NopZSZbkBEhvUY0DnXPcoK/duZjLGB3EPEW4UNrDHgyJjHmJBfbs07+ndpq3FL64pxn5iUGQyFkK2S5dFDrk9vaNL8FUd9v14LLygyJggKq4sAGHXZVtod6k4FvK9J3D1MhVXGRJgu+16KcfpVM19BwB3HziN5Y34NUsDTpHRzymqioyqk7FTIqOuZmnBpWdYIuNel8iolr4IZsatohjhZPz3J07i+m88hmtvfqArbgN5z0gb9v2Cm1JdxzEuXa50LEqAOLEXbymOS8cImatVc7HQyRgP1BFQjrB3D3F+iI1DOhm7T32rcTucjP0n6bSayZhPp7QXsTqcjH04uu4FP4UEIZ2MruKXXm7RTQIOtxCLXzpKxaPpqxeF3tOKyHjP0/MykzFuIqM6ju73YKvu9uWV8epOxTrM6xYZhZPxmQVZaAPYTsYzpgfl16STcckSGW+++xkAljvqoSOLWr6fZhAPV9wAiRfqYt00manVLdTil4EcRca4IJxawsnYSxuGSabgcDLymHQLcQ8Xzbu8f3Sfdo6wi+thtg/dcyKTsVknYy6TkqYIXfmYqoOYTkYLiowJwu3aksUvdKZ0FdVhykzGzqIKvAIhbPXS7q46Lj23WsSDhxYAxC+TEYASCeCTyah8Wc1w7JSTcU6zyPjs7WMYyKawuF7C/lOr8uvPeDkZx+xMxhNLG/juoyfkn93z9JyW76cZKopTK5dmvEZccAf3bxR751qVJDyLXzgG2nXERpUtMvKYdBvTNF2ZjDwm3UAtnxAur1561k0qbqFX58aIbDSmk7EhRcXlm9Ns+hGbkinDNnv1O/33E5lgKrUfcBa/xIuyx7h0kQv5jlD1GJfuxew51ckIAN99zBKn4uZkBGzhsFjxXmS4c0s6nR2rW2TMplN4zs4JAHYu4/6TKziyYOUunjltF79srYmMxXIVn/jhfpSrpsyFuftA50VG9dqUkdem3jkvkop7Z52Zc91BOkTSKQzVFjMUT7qP2DgfrW2ycVy6+7jNDDxPuoMajyVcXjSadB+3qKi3+KV+YqtfEG7d1ZATBmLdl8uk5FpQl+CrxqsQC34SCULcR4TIKNpCO+UQIt5UlVDejGZ7NgnGy8mY60Eno8gR3Dlpjd7uP2k55uLoZLQ/3+BMxpQBGIYhH4w6JfrK4hdNIiNgj0yLXMYbv7cPpglcfeEWbBrJy9flMin5+8/edRAA8J9eeCYAy8nY6WgLNZOxF8X3pOI+BlywdwexYE+nDAy0yclIF17zyOKXHJ2MccF9zaLjtzuom7VDdDLGhrpMxraMS/efpDOcrzkZCyGdjGXhZExpjwgq97HY60f//UQmmKpLUOn04p14YwtdKY5LdxhVRBFke9Cxdbo2Lv0f9sw4vj4aRydjg89XxDqI3T7xv50S2IQrdFKnyCjKX56Zx74Ty/jKA0cAANdefX7da0Uu40apipF8Bu99zbMwks9geaOMx2aXtH1PYVBbCcV5wXHp7uMel+aCvTuomb5iXHpNYybjVx44gj3/61v4t4eOaXvPfkBmztUWmMxk7D5uEYWZjN1BXVsIkZHrje5Tl8mo08nosc7pF4STca0UriBPdTLmtBe/OKdJCUXGRCEW7ylDFL9w0RgH7Hbp3iwd6WVs11yPOxlrwthVF251BArHelzar/il4r0Zoo5RtxPpZBzSJzI+v+Zk3HdiBf/7/z2Kqgm8+tlbsWfHeN1rZ2oiIwD8/HO3Y2wgK52QnR6ZrigbILw2xYe6cWku2LuCEOGzqRQGxbi0RpFx78F5lCpmXTM9CUYcF3H/47h093GLJnRfdwdVMBEbI730rJtU3MegHcUvfZnJWNtoMs1wz0my+KUdTkbxvNCHx8EPfhIJQhWzALvdqNShxTvxpuyxkGcmY2eoKE4tQVbz7lW7MU3TMS79nJ22cBXLcekGN+6K23EtMhk74GRUP0ud49JTwzmcvcnKXrztiZMAvF2MgO1kBIBfe8EuAMALzp4C0PnyF5nlk+K4dJxwC+5csHeHkpJz3Y7iF/H+qyFD64mFyBkXIiMzS7uPWzShu7Q7iHuHWmzRS1M7SUWcH2IpoldkrB3zPnTQDWTSMtc8zH20qOQsZzNG7Wuax6X78Dj4QZExQaiuFMDe1aCTsbtUPUYSuZDvDIHt0j7FJHFjpVCWDyTTw3m84Oxp+WfDvehkrBMZO3edWitW5PelU2QEgOfXRqYBa6z92dvHPF+3fcLK1Xz2tjFcXHM6CpHx7gNzoUY+dFFRxjsyPSa+Jxn3JhTHpbtDRToTbJGxXDW13b+FELNa4PFtBnGNGqaTMTbQyRgPSmU7jiaXoZMxLojzQ1yz9I5L928WYErZAFwLcR+VTkZlXFrX+SFbvikySigyJgi3kzHLdulYoIoquQzdQp3E7ZoDFCejTzFJ3BBtyEO5NAZzabzgbFvMimMmY6PGtqrp3O3rZHas+CzzGbstVhdi5BkA/tvVu31f90uX7sTrnrsdf/qLe2DUtmCfs3McuUwKp1aK2H9qVev3FYSaydjIgUo6h3tcusAFe1coKWNog8r1QpfoK95/NWRoPbGwi19EJiPPj25Tn8nIY9INSoqTkdMJ8UGIiuKZXafwW5HHvD8lHbthuvF9VJwLbSl+qdrPC8SCn0SCEIv3dG3hmpbj0r0hpiQVVejKsl26o3iJjEJMKfTIg9epFed476VnTsnxgFiOSzcY0RGOxZRrXLoTxS9HF9YBAJtG8lLg08Wrnr0V524exm+97BxcMOPtYhT/9l/92iW4RHE+5jNpXLJrAkBncxnV84NFYfGhflxa7zHZe3Aen//xwY66ZnuRiuJMyKYNeR/RlctYrIljHJduDnF+SCcjn6e6Dtul40FZGQfN92D+eFIRx6AtTsY+H9OVDdNNiIy5TEquVbS3S/fpcfCCImOCKLvGpe3iF95guonaOMVMxs5iO7XsS10201tC7+kVq1l6eiQPABgfzOJF50wjkzJwzuaRbn5rnogRHb/P152T2ckx3TueOg0AeN4ZE9rfe/NoHt99zyvwP157YUt/Xx2Z7hRqUHWvZZUmGfcx0L1gf/+//AQfuOVhPDa7rPV9k0ZJuVYZhv6GadvJSEGmGcTnNjrQHpHx6z85hs/e+bTW90w6QkSROZmlKjcxuoAQTDJpxjPFCbfIqPOY9HPxC6A4GZsZl1bPD01TbWXl3CMW8bPBkJap+hS/MJOxu1Q8Mhk71aTb77jPCcB2MvZKGLYY8d2kZAh+8jcux9JGCVvHBvz+Wtdo9PlWTKe7tJNOxh8+aZWyvGz3prb/W83SDZGxojR953htig3uBYju0cOFtRIA4ORyARdu0/rWiUIsGtK1c2Mgm8ZKoaxN9BULHjoZm6PsyjfTfX6878sPYrVYwWv2zGDLaPzusXFE/CyPDmSwUhv/L5SrGMjqjSUhwajjoL02tZNk1PND/b0O1LKffkTEZoRxMhYVJ6P4vLQVv7iMXoROxkQhFukpl0OoE62txB91JDHHcemO4nXRl7mYPXIMvNqQB3PpWAqMgP35+j1EVVzhyHJMt83i1uJ6CQ8cWgAAvGT35rb+W63w/DMmkU4ZOLKwjuu++ogc7W4naiajOA4creo+9SKj3mMi3n95g+JWELL4pXatGsxZ9xFtImPtOIQJrCc24rrVjnHpatXEas2pKsR40hjxszw2kJVfYyFP53FMJ2T0OrVI64h77nBOv8hoj0v3p6QzlG/eyZhN28VI+jIZ+1vs9aI/fyITihRUalljsviFzpSuoha/ZGXxC2/6ncA9mgv0npPxdC2TUYxLx51GBSL1mYydaZe+86nTqJrAuZuHsaPW8BwnhvMZvPGyXQCAT9/xNF72we/jvV96EIttXOh6RTnw2tR92j0uLR60lzcoogRRco2hiXFpfZmMol2aYm8zSJGxtmCvVE1tsUDqc8EKj0toxM/yUD4N8bi1wUKejiPHpRVTQ7HC49Bt6tqldToZ+3xMtxkno7P4Re/GerninNIiFBkTRV1ra4qLxjjgVfxSrDCvphO43b0AHMegFzi9WstkVJyMcUaEKfu5Syp11ykxLt3e4yFGpV8aQxej4Ppf3IPPvu0FeNE50yhXTXx572HcfM8zbfv3pAivNFEyw7f7uAV63e3S4pmAIkowZZfrerAmaulrl7bHpfk8EA7TNOV1Sy0+0+VmVJ8LKP6GR44hplO2GM/yl46jbozk6GSMDXXj0hrX5dK92q9ORtku3UQmYybV0BDRLP1+HLxo+ydxww03wDAMXHvttfJrpmniuuuuw/bt2zE4OIhXvOIVeOSRRxx/r1Ao4N3vfjc2bdqE4eFhvO51r8Phw4fb/e32NPXj0lw0xgG1fCSrhANyjL39eDoZe6xxz3Yy9obIKEXcBsUvYoTdbjVu7/nwwydPAQBeGsM8RoFhGHjp7s344m+9EL/+ojMBWLl57cLeeU0xJD5GtDOT0TRNKQgscVw6EDtQvyYyZq1zRFfxi7hGVk39I/FJRb1PCAcLoO8cUe9bFBnDo7a2ihxGNkx3nrIUe42em9pJMgVZ/GKdG0WNLl9x7qX71cmYD1/IJu4fOaXsUJfgq04tEou2ioz33HMPPv7xj+M5z3mO4+sf/OAH8eEPfxg33XQT7rnnHszMzOBVr3oVlpftpsNrr70Wt9xyC26++WbcfvvtWFlZwTXXXIMKbd++CCdj/bg0xaxuUvXIZAS4mO8E6jiooNfEFJHJ2DPj0pngB1v7Rmz9vhNlSAdPr+KZuTVk0wZeeM502/4dnYjMzcX19o20qplz8rzg/aLrCHFrKKd/sa6elxyXDkbdIATscWndTkaA5S9hUe8TqhtFm5NReZ8VZmWGxm5ttUVGCuedR3Uy6i62IK0jrvUjeSuzVOcxEc8L2T4VtwbFuHSITSFn8YtmJ2Ofj6170TaRcWVlBW9+85vxiU98ApOTk/Lrpmniox/9KD7wgQ/gDW94A/bs2YPPfOYzWFtbwxe+8AUAwOLiIj75yU/iQx/6EK6++mpccskl+NznPoeHHnoI3/nOd9r1Lfc8fllnvSKmJBW1XEENhOUIQ/sRekm6p52MvTku7VesU3U5GcWxaWcmo3AxXnLGpMzEiTvjg9bD6EIbRUZVhJeO0h45L5KMeBAWo1U6F+uqE2yFTsZAyi4nvFjM0DXXPdRN80wqhXyDeI5m4TFpDXUMMV9z/HJcuvOoEQ+i2KJXnnWTjDgGI3lRNqLveVeUJmbS/TmmO9zCuLRVjKT3mVctXSIWbfsk3vWud+Hnfu7ncPXVVzu+fuDAAczOzuLVr361/Fo+n8fLX/5y3HHHHQCAvXv3olQqOV6zfft27NmzR77GTaFQwNLSkuO/fsOddWZnbFHM6iZqJmM6ZaBmNOXuYgfwcjLmeqjgwjRNzK321rh0vsGIjnvhLotf2uigE3mML4vxqLQbITJ2wsmYUUaruCnVfcQ9e7TW1KrVyag8ULNdOhi3M0GOgeoal1buQWGaMYnzeTaTMqSgVdA0fsjil9YQP8vZdAoDGWYydouSw6llOL5Guoe4rogc2UrVzpaNijvWo98YaqH4JZdJNVyrNAuLX+ppi8h4880347777sMNN9xQ92ezs7MAgK1btzq+vnXrVvlns7OzyOVyDgek+zVubrjhBoyPj8v/du3apeP/Sk9RdeUBSCcjx9+6iprTYBiGDIXljb/9VCpOQQvoLSfj0npZ/vxM9YiTMXQmo+EsfmmXyFiuVHHHvtMA4l364mZiqCYytrFduqRkMvJ+ER9KdU5G/flNAEWURpQrTmeC7vF1NZeL49LhEMJvyrCmdvIZvaO5znFpHpOwqE7GAelkjP8zVtIoKc+8vfSsm3TEMRCuO/VrURHXxH4tHBHTSWE26mwno6F/XLpqvzex0P4TeejQIfy3//bf8LnPfQ4DAwO+rzMM50EwTbPua26CXvP+978fi4uL8r9Dhw41/833OGKDN1X7jNIsfokF1aq3w5QiY/sR7t6Uct3opXbpU7Vm6dF8Ri6m4k74TMbOFFQ9eHgBy4Uyxgez2LNjvC3/RjuYGLRE5Y44GVOG9tER0jq2yGgJzQWNi3Wnk5GZjEG4nfCDmp2MJYeTkYJWGErSfW3dZ6STUZPwW+C4dEuoIqOIFdDlLiXhKavt0pxOiA3iWi+cjIA+kbFUpZMRaNLJmE4hK0V4vY7SdJ+KvV5o/yT27t2LEydO4NJLL0Umk0Emk8Ftt92Gv/qrv0Imk5EORrcj8cSJE/LPZmZmUCwWMT8/7/saN/l8HmNjY47/+o2K64FY7GpwXLq7uBcq4sLGG3/7qXjcfHtpd1eMSk/1yKg00PjzrbqOiSx+adN1SuQxvuS8TT01xmBnMhbb9m+o16Zcuv1j6yQcJTkubS1IdI5LFzguHRo7Y8klMupyMirPALoaq5OO7dqxjonYfGtP8QvPj7AUa6WcOWVcWpcYT8Ij1hXZNJ2McUIcgyHVyai5cKRfswBbyWRsS/FL1XlvIm0QGa+66io89NBDeOCBB+R/l112Gd785jfjgQcewDnnnIOZmRnceuut8u8Ui0XcdtttuPLKKwEAl156KbLZrOM1x44dw8MPPyxfQ+qp+DiESm1sbSWNcR8Xe5yUi/l2487/A3rLSdprpS9A43FpcUyk47rN49JCZHxpD+UxAsB4bVx6o1RtW7ZVRRFRxDnSCw7fpCOuTWNtHpdepogSiNuZMJDTJ564M7koaIXD7YTXXvxSoZOxFcTGiDUuzUzGblFSBKes5uZ10jriGOTSqYbTPs1S9oiF6ieG8s20S9sRKDnNa0H3vYkA2ms2R0dHsWfPHsfXhoeHMT09Lb9+7bXX4vrrr8fu3buxe/duXH/99RgaGsKb3vQmAMD4+Dje9ra34T3veQ+mp6cxNTWF9773vbj44ovrimSIjThP0q6xXF3hsqQ13BcejjB0jopL0ALsRUkv7O6elqUv+S5/J+HJNXDqVpT2Q0AtqNJ/PJY2Snjg0AIA4CU9JjKO5jMwDMA0gaX1kly4uZlfLeLg3Bqet2ui6X/DvjbZoyMcl+4+7uKXDY1jhxyXDk/Zda3S6WR0Xx/DLJBIfU7mgOYmY2e7NEWysBQVEUW2S/Ne0nHsjfVUw2cx0jlE/m4uY42xF8tVfZmMrgiJfkM4GcNMA6jFL7rPDzWqgFhoFxnD8L73vQ/r6+t45zvfifn5eVxxxRX49re/jdHRUfmaj3zkI8hkMnjjG9+I9fV1XHXVVfj0pz+NdLo3csm6gRyXloUKHJeOAxXlpg/0lpOu13F/9gC0W+TbyemVmsjYQ07GfINdWvdmSDudjHc+dRqVqolzNg1j5+SQ9vdvJ6mUgfHBLBbWSlhcL2HLmHfG8Xu/9CC++9gJfPm/vgiXnTXV1L/hyGTsQMs3CYc4d0ZrgebrRX3XKvW6t1GqolSp9u2YVSPcgtagRoeW+/oYZtSL2D+/YlJH97g0i5FaoyALFehk7CYlj2ILTid0H+H0zQtxq8DCEV0M58NnMqqbIbqdvl6Tc/1OR0TGf//3f3f83jAMXHfddbjuuut8/87AwABuvPFG3Hjjje395hKE0BLrxqV5g+kqvuPSPC5tRzq1PDIZe2GERI5L91ImY8N2aeciUW6GtCHW4YdPngTQe6PSAiEyLviUv5QqVfzoKWsc/McH5poWGe12aaX4hdelruNul9ZVagHUn5crG2VM9tAmRicRx0EWv2hsl3YfB47mhqPs2ji0x6Xb4WTkMQmL6hAa0Nz4TcJTqtobI3k5ncCNw25TVB10DZ6Rm8VuFO/PzcLBJjIZ1euU9kxG1wYYaUMmI+keVR8xi86U7uIuH7EvbDwu7UaeEx7t0r0gpohx6anh3hmXbjaT0R6X1n8+2HmMm7W/dyeYqJW/LK55i4yPzy7Lhdxjs8tNv786ui4eUHvhvEg6ZdlEqX9cuuA6vix/8UfNLAVsJ6OOkhb3eUZBKxwVl2snXzsmuhrYKTK2hrNdWu8IOwmPKnTQ0BAP1PzdrJLJqM1B1+fi1nBt869YrgY+v1arplLmltK+FlePMbHgJ5EgZP6ccDKm6EyJA3WiSkaMsfO4tBPTND2DeHWHLkfl6z85hk/efgCmWX+jE+PSm3rJySg/X+8bd8U1UpBu05juM6fXcPD0GjIpAy88d1rre3eKMdkw7S0y3l/LmwSAx44tNf3+6vnBzY/44C5+KVVMbfcLd+bmcoG5jH6UXFlXgxqLX+qcjByXDoXqvgaAgYzI/9Pz+RU4Lt0Sqsg4IEfY+TPdacoeYhZzlruLeq23HHRG3dejUHZthvUbamN30Aaguuaz2tf1aiTuexPpUiYjaQ8Vl2tLOhm5aOwqblFFd6MV8UbVrNSMDFm8E5MRkt//559gpVDGuZuH8YpnbXH82ZwofukhJ6MUGX0WGHZ8gDOjVLfo/sN91qj088+YxEi+N291E0OWuLzoJzI+My9/vf/UKjZKFd+CGC+cu+u8LsWFUlWMS2fl1zbKVYxo2CF3b67QyeiP+97dzuIXuubC4c7JFCUj7XAyrhTKME0ThsFFYyPkGGLakPcgHWI8aQ7x85tJGfLZyu1eJ51Fveda7dLW+aFP3BLHvD99Y0K4LVVMrBXLGB/Mer7OcRyUcWl9Ym/NZU+RUdKfP5EJpWI6VXRhnW5H1hkJj38mYzxErqSitqqnYupkLJQr0i3xt7ftr/vz06tWJuNUD2WmNRrRsd1zqP1ve4pffviEGJXuzTxGABgftMTRxbWi558/oDgZK1UT+06sNPX+qpPRHpfmdanbiA0QVRzXNXroXthQZPTGNM06kVFnoYV7VI5OxnCUXJm+uotf1AVn1WSuYFjUzDm78ZufXaexS0Cc7blekzKkM6jXFMtBp1ncqvS3kxGw3YyrBf/7qOrozaaUbExtBTxOAwWhyJgo3GKWumjkDaZ7+GYycoShragio+pkjNPnv6Is8O/cfxoPKqJRtWpKJ2MvjUs3Chuv1jkZ9Tuuy0ohykvP7808RgCYGLSOu9e49MJaEftPrgIALpgZBdB8LqOjXbqHskqTjjgG2YwhF+y6XEF1xS8cl/ZEFdvFuLRO8cQt5tPJGI6yq+SgncUvAEemwyJE3lw6LXMydWbJknCogpMQUUyT2fzdRArw6RQMw5DTbLrELRnr0cfilshlDGqYLinnRiplyOgyFr+0j/79iUwgVdPpEFKFlQpvMF1D7Cy6x9i5mG8vqoPXK5MxDiMk7l23v/3BU/LXC+slOfLdS+2vjZyiZZc7SGbHanRcP3h4Ecsb1tjExTvGtb1vpxFjH17j0sLFePamYbzwHCtzsplcRtWplVZGq5gV232kyJhOSfdcu0QUOhm98dqkymf0ORnZLt0a7uIX212qyclYcR5bHpdw2NcsQ6vjlzRHUQodtpMR0Lve2HdiBc+cXtP2fklHzStV/5filj6G8o2djOI4iDW47ugs99qGUGRMFGIHSxSMqBcc7mJ1h2rVlEKRELqYfdYZVM0q7XAy2p9/tx2+onRBPHT828OzePqU5U47vWKNSo8PZnuqrSzXIOfE7bgW/6tzI+T2Wqv0i8+b7ukQ5vGhWvGLR7u0EBmft2sCF26znIyPzoYXGcsOEUV/056AC83mEccgl7ZLFPSJKM7jS5HRG3XTQzxLieKXQjn6vcN9/9fRWN0PuMP16WSMB452ac3CLwmPmlmqPjfqGs3dKFXwCzfdjjd87EdyKoUEU6q4RMa07nZpOhnDOBmLruOg2/Ajj0MPrdfaDT+JBCGcjBnXGCJAQatbVEznQh5gJmOncDgZleD2fNq6GZlm9x2+Ylx658QgXvmszTBN4BM/tLIZT4vSlx4alQbs9nS/h1p343c7xqXveXoOAPDi83o3jxEAJgKcjPc/swAAuOSMCVwwMwYAePTYcmjxQ/3ZT6fbMy79o32ncPF138Lf335A23v2A2Uld042GmsSa+lkDId6PcqmxLi0XaoUdYEoRZnaeUfHXDjUzDlAFRn1ZzICPC5hcbRLy1gBCuedpqw4fTMpA+LRV9do7vxaEavFCk6tFLHMcyMU7mu97kxGd05tPyIyGQPbpV1OxqzmsXV3hjOhyJgoxA+42MzguHT3cS/kAY5Ldwrx2RuGs/glm7F/3e3yF+GSGBnI4B0vPxcA8KW9h3HdVx/BJ35giY3TPTQqDcARpuwleNmbIU4no87zYXnDEuVmxga0vWc38BuXNk3T4WQ8f+soDMNqIz9Zc8A2ouwaB822ofX+wcMLKFVM3L7vlLb3TDqmaSrZQSkporSv+IWZjF6Ixbp6/xhQxg+jHg9x75mouZVXAxwYxKZUcd4/RP6ftnZpd1Ymj0soSkruHMelu0dJcbUZhr15qEvQUs+zJY/NT1KP2AARaw/trcYsfsFQqExGb7FXe8t3Hx8HNxQZE4QcQzSci3eAjaHdwiEyykzG2mI+BsUjSaZieu8qORy+mrI4WkWKjPkMrjh7Cs/bNYFiuYpP3/E0vvvYCQDAjonBbn6LTePMAar/fMsVt5NR/7i0GNNSnUe9yMSQJTC7RcYDp1axuF5CPpPCBTNjGMylcfb0MADgsWPhyl8qFbfIqH9cWhyHI/Pr2t4z6ZRcDjrtmXMcBw2FXLgpI2iZdEreT6I6S8VxmKyd4xulKvNQQ+AeSROuufaNS1MoC4PDyag54oGER83GBIC85vu66hj2mrAg9fg5GbVnMvbxuHSoTEafsXVdYq9Yw2T7+Di4yXT7GyD6kKJK7eZi7WIZKFVMx+go6RyqW8g9HkonY3txi1kCMUJimkChUgGQ7cJ3Z6GKjIZh4C9/9Xn45/uOKOH2KfzSpTu79v21Qk7NAapUHaIjYAf3p2XxS+180CgyigVnPtPbN3vVyWiaJozaRoVwMe7ZMS4/3wu2jWL/qVU8NruEl4Vo1HYXI2Xa4GQUx+HoAkXGsKjHJZsxZL6ZtnHp2vEdH8xicb3EcWkf3NmxgoFsGiuFcmQBpeRyMgLAWqmCMeY5BeIufhFlPPqcjByXbgV1AS821Nku3XnUTEagFl9T0OhkVI4pRcZw2JmM1rUqr31c2rn270dCtUuXnfcOcY5Ua9FZUfPbSz7PDP0MRcYEIcellfy5TCqFUqWiNe+MhMeroZKZjJ3B7ewViBGSYrnadYevyGQcGbAuxWdOD+P3XnV+N7+lyDicjOUqkHf+udgMkSKjdDLqFLes9xIL0F5FCBCVqomVQhmjA9bvZR7jrgn52gtnxvCNh2bDOxmVByLDMOymPZ0iY23hv1woY2mjhLGB7gn6vYLqrrbapfWOS4uFzfRwriYycqHohd/o00A2hZWChnHp2nEYyWfkZvBqocxzpAF28Ys7k1HX+eF8nxWK8KFQ887EvYTj0p3Hfd3SfV9XN1coMobD3S6dVSKFdFCu2OdevyIyGVeDMhndxS+u9vV0Ktp6gS3f9fTvT2QCqXqo6O1wp5DweOUC0snYGdxilkpes02+VVQnY1JIpwz5mXs9RLnDkaWTUeuYrvWgIQSaXmUgm5YPRGrDtMxjPGNCfu2CbbXyl9lwIqN719W9q6sDdbSKbsZwOFqNU4Ycly5odjKKQik6Gb0RUwjuhZuuvLmSsjCUCySO5jZEFlukXE5GzcUv4rrLOIFwFJW8s7zcGInewk6ao+Qanc1pLkZSxXz1mYT4Y58bTuFXm8jIwhEM52tOxoDrtV/xC6DnWNjHobfXHTrhJ5Egyh5ORtncyuKXruDVNpWj8NsR5GfvsbuX1ZyJ0ipigZ8kkRFQWts8HmyFqzrlcjLqzCNLipMRqG+Y3ihV8OixJQBW6YvggplRAMC+E8uhfq4rrgIFdfdV13mhLkgoMoZDzdQyDP3j0mJkaGqYImMQfnEbujIyC4qYNSLzpHgsGiGLLWrXK+1O39r5N1XLyuQxCUdR3nNT8poF6BO3Vgpl/Pm3HsNPjy5peb+kItZ6OVkyone9UaCTsWncGxe626XdI/L9SBgno7h3CJFXzU7U0ZFAJ2M9/fsTmUCqrkxGwF5AdltM6VfErruX8Mtj0l6kmGXUX/B1B/62itounSTE5+u1wHAX8oj/1Vn8IkXGHncyAvUN08/MraFcNTGazzhKgXZODmIkn0GpYmL/ydWG71t2ZWM6CpG0iYz2+7D8JRxiXFrshud1F78IEWXYyjGgU8sbt2NOIEWtiOO5aoO4aMZkk3Fj3JuH7XIyTtZEeB6TxpQrVYjbd1Zplwb0ib/ffmQWf/39p/CX331Cy/slFbVdGrBzAHU9624wk7FpVJcv0AaRsUpxSzoZA67XxYr1sys+/1TKsA0RGp55vUxF/U7vr8CIxCuDTjoZmf/XFbwuOll5g+ExaSdVn3ZpwCpUAPSNK7SKcEmMJszJKB5svcQqOwvQOg8yUnTXcz6UKlX5bwwkwck45BQZD5yyBMSzNw/LIhjAyhoVbsbHZhu7PSqucVBVZNR1v1BdD0cWNrS8Z9IpuYothKilrfhFyWQELJGRI431lCreTnjZnBvgmAiD6m4Zrl3/1zgu3RC7SbU2Lp3139BqhaJ0+lrXXbZLN0a9d+cyKWTTKbl5pWtzRNz/Tq0UtbxfUqnPZKSTsdv4ZjJquGaZplknLPcjYSJHxAau+qwrTT8a1uN+zwz9DD+JBCGLXxRRRdzo2S7dHbwaKulk7AzlgKYvOhnbS1B7njwutcOi28moLjaT5GQU+UdCZDxrerjutRdss0TGR0OUv7jPj3TKgDhVOC7dPewmSutnd1BTBqD7/cW4dKVqYi2iYJZE/FwJclw6spPRzukSLgy65hpTcuVeyeIXTeeHuH9Mclw6NOp9Xly3BjJ6x9iFWElhK5hym11z6vPVEo9FKNxZgHmNcU3qc3O2n52MIdqlC65zA9BbwkMnYz29vwIjEi8no138QqdCN/DKBWQmY2fwEngFcRF6RR7acC5ZImPQCILIAkzXjoGMdNC0EaIuNnMJ2FEcH7QWuwvrloPjaSEybqoXGXdMDAEATiw3dg16uqzFeaFL8FVcDxQZw1F2uRJ0ZQAKxCJxfDArr40cma7HL19pQCm1iILadDnM4pfQlJXMUsA+P7Q5GV0iPM+NxhQq9s+tuJ/oEuPlv1F7H4qMwbjdVLqbjAscl24ad6uxFH41lo0A/e2gG5QiY5CTsXbvyHg4GTUcC7GGocho078/kQnEq01XBJtyXLo7BJXxUPhtL0G7SkFOu06SVCejeIjyClOuy2TUHOmwoYympBJws/cblz7HQ2QUrsel9cYLY/FQ5emybkMT5RGKjKEQCw8R6aC72EJ1So7WrjvLG1wsuvFrisxrcpaq7pZhFr+Exl38Iu7l5aqppTxMnB90MoZHFipkUjLCQ/fmiHgfuueCKbuEDt1ORvV4io1PEox4nsq3YVxaFcf6WdySkSOBxS/1Tkadph/bVNS/x8ENRcYEIYxA6qJRNrdyXLorBLqF6GRsK+5iC5W4HIOVDZHJmO3q96Eb8WBb8HIyuhym2sela4v/fCYZtzdZ/FIbl376tL+T0RYZGy/EvK9NmvOblIfo40sbXT/fegG5255qz7i0Km6JVuMlNkzX4RemP6hJPFHdLSx+CU+lblxab5OxnclIkTEssllaWbzr3hwR71MoV7W9ZxIpuZqGdZsa6GRsnrril4BixGZRN+f7u126dg8NuF7b2Zj2PT2ncXTdPYVCKDImCi9RRbdLiDSHVy5gVuNFjfjjJboLpAjWZSfjakKdjEE7tWVXrEOmTcJWPgGlL4DTybhaKOP4UgEAcLZHJqO7iToIr2uT7hIe9fyqmpbQSIIpuwp5dDnnBGLBk8+kMDpQK7egyFiHHabvNy4dMZPRQ+yloNUYP6cWoFdknJTj0hS0GlH0GEMUTkZdhVWquEU3oz8lV5yA7WTUm1kK2BufJBh3JqNOYUuM6BqG91qnXxCRI2GcjF7FLzruHe7SJUKRMTGYpglhBHKM5rL4pat42aeZydgZwjkZuye+V6smVmrOlZGktUsHiIxV1zkhdv10ORnF4n8gAaUvgLP4RbgYJ4eyGB+qd782IzK626UB+7jpa6J0PvAdZcN0Q+rHpfUu1tWGRdFqv0yRsQ63Y04g26UjLtpVsVc2Y7KApyHuzLl0ypCCSkGDkCKdjENCZKSQ0givMUSZlam5+AWggy6IssvJmNP8rKturiwXyvJ5jvhTUCJ81P/VMS4tj3efu+eGlPI00/T+mQwqftFxfvg9M/Qz/CQSgnqdz3iMSzP/rzsEtUsXeUzaSlAmo+6cmlZYK1Ug7oWJExkDdmrd4m/7nIzJuL2pwuHTp9YAAGd7jEq7X9sIT5e15ngNkY+5acRasLP8pTHukRtd47mCokcmI4WUevxcCTJrLqIgqLoqZLs0nYwNcRe/AIrwq+EcEefH5HBWvqeOrMck4xZRAH0FSfa/oTgZmSHri/u6JTd82xCBYprcoAqDmoMM6D0m5Uq9kaUfEU5G0/S/5sgNVrX4JSA/vlnoZKwnGasw4nABpTwELV2LxlKFeSjNIAUVr+KXLo/qJh1xTniVf+h2bLWCGFFMp4zEuO4EQcU6Fde4tCyn0pXJmLBxaYfIGJDHCABjg9aD1nqp0lBAr3g04WWkA1VvPuY5m0YAsPwlDG5XkO5ss2K5XmTkQrGesssxJ9DWLq0cB7v4hc9WjSh5bB7ms2LkLdrnV62ackNeZDICdJg2wh4H9RJ+6WTsFKZp1sVtCEe8rg31guu6x2PRmKKPk7Gk4TmrFDCx1U+IzVjAP9u4WLGuRW0vfunzY6GSrJVtH6OKjI6MrZReJ+Ov/O2deOkHv491PnSFIsjJyHHp9hJ3J6NwD43kM7KRMSlkA3Zq3edEWrrnOC7txURtbG9xvYT9Jy2R0SuPEYDM2AMauz2EiNLOa5MQfIXzkiJjY9y74QNtymTMpg2ZBcvil3r87h/yeEQel7bFALsZk8ehERUP8VdsKLkFkGZR71fD+YxcjNJhGozt1LIX+rqvW+r7UNjyRn2GEpu3ubR1HPQ5GZ3Hkw3TjakrfsnodzL2c+kLYJlJRPnLms9mnRB1Vce1zmMhN8D6/Fio8JNICBUlg8DLmaKj+MU0TTxwaAEnlws4PL8W+f36Aa9MRt0NrsQbr3FQgTgGuh68WkEEyidtVBoIFnHd54TMjWXxiyfCybhSKGPfyRUA/k7GdMqQ7rRGC7GyR36MznHpcqUq/42zN1vfL8elG+NuB9U+Lq3ECbD4xZ+Sh9MX0CeeiCKGXCaF4RDNmMTCXfwC2M75qOH96vNAjmPsoXE7tQBVjNcUvaGKjCwc8URd58nnq5qTUdfklPs+RMG3Me7zI6gYsVnkpiTdc0q2sff12is7VuexoJOxHoqMCcExLm3UC1o6Fo3FSlVmPy7wxhIK27XVnqBZ4k/V9BcZY+FkrC3sRxPWLA0EZ84I4Ulcp8TxqZrQEiJeSJiTcUz5+Xj06BIA/0xGIHwuo3cmo75xafXYn7OJImNY3A2IcjxXUzuo+v72uDTv5278HCIDmkRfcf/PpQ17XJoTIg1xF78A+hrY1eeBnOIwXaHIGIgsMXIUv+iNeVDPNzqvvVHvuUJkzAc8i7WC28lIkbExbnFL/K+ORmP3eHw/IzaF/BqmC8oUh0DXetw0TYqMHvCnMiFUfcalhbilQ9BSb/Lzq7TIh0Eu5JVrTtAoKdGHPQ5af5mLw8i6Oi6dNLJhnIy146IuFnWMTG8kzMmYUVqAxTXDz8kIhBcZZSajcnESD0c6NqXU0UU5Lj2/7tv8RyzcxRbi51hXRIkjk5Eiii9+Tnhd4okjk1E4MHgcGiKuTepCUZuTsWy7glIpQ96bmZUZjNy4yCiZjDXhd12TyKiKWxS2vFGnQcS4dLsiUAQ8Fo3xa5fWkwPIshGBmPrwix0Rbl61+EVXPr+6dmG7tA0/iYRQdjgZ7a/rHM1VH6rpZAyHV6V9LsNx6U4Q90xGUbYwnECRMRcwguDOZFQXi3rELes6lU+IkxEAxofsrMXNo/lAYVqIjEuNnIyV+vND58NvQSkD2Dk5BMByai2tU0gJougel66N0hbK1cgCbbVqFwPk0va4NItf6hEL9rp2aU2FFqqjdIhjuaEpVeqfqWyRUc8xEddBOhnDIUUUDydj1JxMAYtfGqNujIjCw5wmAV4gnq8mh8JtZhK1GMk6FkHFiM1S8niO61caFai5szEBfRqJV1QBociYGNTRULVEQgahanBBqE4KZqKEI2gkke3S7UXklKY8SlVi0S5dW7iMJHBcOh8gVtUVv6RUkVHDuHTtvBpIiJMRsIVDIHhUGgDGBsI6GQOiHDSMSwsRJp9JYzCXlm2tLH8Jxi1uDSitiToz57KZlBSrOS5djxxDc7kSdI1LFxVhZkQZl6bTNxivnGsxLh25+KXsLTJS/A3GM5NRc7s0nYyNUZ24At3xTOIetHVsAACPRRiKrs0LndNsLH6xsfWOBpmMmfpn3qjHQjVIUGS04U9lQpALRpegovMhSR17mF/juHQYqh4PxMxk7AzlICdjDEbWxTk5mkQnY8BOrVt4VxfxOgqqkuhknFCcjH7N0oLQTkaP80P8uqTDUaoUjADAjolBAMxlbIQ7v2lAeSCOOjLtLraQmYwUUeqQcRtuJ6OmjEx14SkWR5Wqqc1xlFSkCK9ct8Q5EvWYuB15IzWHKZ2MwbhzZIF2tEsrmYwUtjxRXeoC+1lMl9hrHYfNo3kANJyEwS1uif+tVE1Hn0JL781xaYmMHfF5Tip6OK7l9E7EjXWHk5Hj0hJ+EglBXKjcP9sjGrN+1jku3TSB5QqV6ONvxJ9K7cbuXiQCamZg9z5/sbBPZCZjgIjrHmNPpQyIvREdDdNucSsJTAzm5K+D8hgBe7S6YfGLx/mRlQ9cOo6DKOCxFpvbJyznw9FFioxBuMelM+mUHOmJKqKox5Xj0sHI7L+2tUsr49I5+x5A11wwwcUvepy+0smY47h0GLzbpUV2qf7CEbrnvPGKeMjpdjLWrntbRulkDIs4P0QJj3qe6BrTpbAFGTuy5nO9dj9bqb8uViI+W9WeFwzDu2y0X+FPZUJo5GTU8ZCkPlRz9yocIpRXPS7qLoqO8VDijXimcp8TQDycjKJdOonj0rkAEdc9Lg3YbkYtxS8lp7iVBMYc49JDga9ttl3aMVoli1/0ja0LsXd7zcl4ZJ4iYxBeC0V79FCPiCKKLdgu7U/ZI04A0NkubZ8f6ZShhNazZCQIL/F3sA1lPADHpcNS9NjYk+eJBgddpWo6RDI6Gb2R13dPJ6OmbEw5Ll1zMvJYNERuKMlxafvaFdW57i6K62caORlLHpshdg55tGdeNkt7Q5ExIVTM+oU7AKUdT6/IuLDOcekweDoZlQa+bhaPJB3ZuuZx0dfp2GqVlQQ7GYNEXK9zQggqWsalk+hkVMelN40EvnYsdLt0/Q64zqwgkY+Wc41LM5MxGPe4NGA7taKOS4uRIHFMhMi4UaqyiMyF3+JNd7u0OOekoOWTJ0Us5OaIcn4MaZrYcY/T6Xx+TjLFgHHpqNcsoP5cW6Lz2hOZz+czOaUD4WRkJmN43NcV9d4edQ1Y8niO61caOxnrr1Pi/h71ONBR6g0/jYRQ9Vi4A43blpphvWifhPOrvLGEwSuTcTCbluOhXFC0Dy8xS5CPk5MxgSJjNiAHSJRUqeJvWjrodI5LJ8fJqBa/nDndRiejpnwawB5vy8tx6fCZjHsPzvXtiGLJY6RnMKcrB7DieG/12rPChbsDeyzXe1y6UK7K+3uU97ddc2yYDoPMylSuW+LnOKoL1O3IE1MGKxqen5OMV2ur7WSMfk93i4wrhbKWaJWkIV2+Hk4tXYYG8Xy1ZZROxrAUXdd6wzC0lU96TT70Kw2djDIOw6sjIWrxC52MXlBkTAh+gsqwxuBqNZORN5ZweI1cGYZhXwz58No2/IR3wHaTsl26PUgR16v4RWQBeuy26x2XTs7tbaImHG4fH2g4Bm6LjMHXfDm2nvYal25n8ctG4N/70b5T+I8fuxO/+el7+jKzthQ0Lh1RRCm4xoUy6ZQc0+1XUdcPr/Z1QE/bt2mada6KIT4ThMLLYTqkSaCty2SkkzEUQZmMBQ3FL0KoVJ8Z6GasR26MOJ6t9D3rlitV+Yy2hU7G0IjNdq8xXV0OOrZL2+3S6z7mHdtRat/D7XFpir3tgD+VCcEr5wxQxj00OOYcxS9slw6FnZXp/DpdC+0nyMkobjLdbPJM9Lh0QM6J17VKthprLX5JjpNRlL1cvHO84WvHaqJ1K+3SOkerhNjrzmQ8vrwReJz3HpwHANx9YA7fffRE5O+j1whsao1a/CIcFcp7i5HpJeYyOvAtflEWiq2OTKvXRXGtHOEzQSi8xgNtB4umcWn3MeHESSDu0X9Ab7u0ECqHsmn5vERxqx6ve4dOJ6P6vCycjMsb5cgNyUnHy+krx3QjPmuVAmKh+o2hkE5GNbIsF2CIaAa/DOd+h59GQhAjiH7FLzoeXNUdydVihXmCIfC78Ogs5CHeBAXx6tzdDUO1auKJ48uOhzFx7EcT6GQMerD1yo8Vx0jHw6o9ppuc29sVZ0/hH3/rhfj/veE5DV8rnIwNRUYPR6nIOdObjWktNqeHc8hlUjBNYHbR382478SK/PWff+vxvlvA2M4EZ8QGoKH4xcNxNCLLX3gvUil7tBiL30dt+1YXljm3k5HFL4F4ORl1xQLV5WSyXToUpUr9dUVXWZX6HvlsOvQmWj/i5WrTNZYLOEXGzTWREeCxaITXfZdORv0I886az6ZQoewl9uopfvF6biMUGRODWIilfJyMWsalXQ+/LH9pjJ/QxUDx9uN3TgD6c2oa8fm7n8GrP/ID/N0P98uviQy04QQ6GcWNu+DxYOtVOJLRdKMHlAVJgpyMhmHginOmMTmca/haITIuF4IdBl7XppxG8b3gGltPpQxsH7dGrILKX546aYuMjx9fxlceOBL5e+klvMLJhWAeufjFw1ExOmD9vDCT0UlQxlJUAUUtHLNdc3wmCINX8ctwLnhxGRa344jHJBxe7dK6cmTV9xjIpkIXm/UjXlEbOp91hSs1mzYwkE3L847Hwp9K1YR4DMt5OUyjOhk5pitpFDni5fTVNb0jJh94HJxQZEwIfuPSQsDYKFUjByWvu8YeFtd4Y2mEV+4ZwB3yThDkZNS5uxuGuw/MAQAeOLQgv7bcD+PSXpmMUvy1v0Ynoz7GlJKYIIeB12JdVwg24D22vmMyuPylWjWlyPjGy3YCAD586xPymPYDXs4EXePS0qmljAsJZ9BygfdzlaDFWz7iKKhY0KQM+5lN5ElxNDeYskfu3JBmJ6M7k5ECfDCeGyMZ/e3SA9l06GKzfkSWhqW8RBT90wk8Fo0pemwoAcpx0TSmy1bjxptNXpshuqbaeBy84aeREPxFRnuBF3UMxy0yzlNkbIgcl/YdY++fxXOnKcfIyfjE7DIA4ODpNfnvin97NJ/1/Xu9Ss5nd7BaNSG6PJxOxlrhiBYHXf2DRD+RTadCOQy8RHidjlK5IFHE3u3jwSLj0cV1bJSqyKYN/NE1z8aW0TwOz6/jiz9+JvL30yuUPMZBdY1Le40LiU0Ojks7qXiI8ALhzm1ZZPQYn2PJSDi8HCPDmgRav+IXbgYHUyw723MBZwt71AIvcU8fyKYobAVgt0t7ORk1ZGOWndMJdJU2Rl1jeI2xRx+XZiajIGizSXWUemWWRhUZSzwOnvTnKiyBVHwyGfOZtFysRH14dS9wWP7SmEq1PvcMYMh7JwjOZNQnpjSiVKli/ynLnXVobg2maTqOu7oRkBRytYdc9wNURVlsODMZa8dDR7t02XY99CthFmJlj2uTzqxS6ShVFp6i/MVvXFrkMZ41PYzRgSz+29W7AQA3ff8p2RafdLxcQVFFLYHXuNAoMxk98WpqFYhri3vjNSxex9gug+PGox+maSrHxUug1eNkzLtH2IuVvmy6D4tXscVgzr7/Rt8cEfeStBS2WFRVj9e5kdO5ceiKoqHg25hCxb4mqRuHeV2txnIzjOJWkJNR/ZyzGf1ir5/Rq9+hyJgQautFzx9wkVMQNa/GvcBZ4I2lIX65Ttwhbz/2Rb/+Mid2rzrRLn3w9Kp8wFsulLGwVpLHfTCb9nTK9DqivbtOZFSEIqeDToxL08mogzAOAy8RXogeWopfPLIxd0iR0bv45amTqwCA87aMAAB++dJdSBnAqZUCTq0UIn9PvYBX4YiuplYvB53IZKTI6KQc0NopRN9Cq5mMlfprlHgmiPqclmTU+4ej+EXTM27R5fQVwm+lanbkWaFXES45dfE+lE1DeB6iRjFs0MkYCq9SJF3Zf4B9/xHXLR6Lxohn/1wmBcOof9Zi8Ys+hvL+5Wnq9dur+CVqnACPgzf8NBKCeCBOGfUPxHb5S8RxaXfxC52MDan6ZDIyULz9+I2qA/qy50zTxA+eOBmYT/rE8RXH7w/OrckFfRJLXwD/EYRy1c/JKBx0+nOD+pEwbg/xUJT2zG/SsCAJcDL6jUsLJ+O5my2RMZdJYWbMKos5HFAWkyTscpb6cWldxS/qMbGfD7hQVBGClteiwS5+iTYu7XAyNgitJ877hyrCD8lW0Uokx3PduHTOvj9zQ9gfKaQoxySVMrRFMchMxoydychG43rskc36e3qlakbOvLYjUOhkDIt0R7vuI9qKXwI2w/oN4WQslqt1aw+Hk1F5tsoG5Mc3Q5lORk8oMiaEqulvmR7WNJorRoPEeNUCMxkb0sjJyJD39lENGCPIa8pkvPOp0/j1v78bv/mZe3zHqZ44vuz4/TNza3LBIs6lpOGXeVnxFRn1Oeg2XK3G/Ui4cWkvJ6POdun6TEa1+MXrfHmqJjIKJ6P77/QDJQ9xS9eIoNeYLselvRHngNeiQYyCtlrEU3KJWQCLX8JQ9nHCq+VpaxHcvm6nbypl2MeFIqMvXoUKADA2oEcQZPFLOGTxizoOqvw66n294DrOE0M8Fo2wy9Z8REZNTsYkTkQ1y5CyKbTm2pBVXepOR6mm4hcPFzGhyJgYxPnh5WTUNZorRMZt45azhOPSjan4uOmGNblLiT9BO0u6nIwH56wil70H53HHU6c9X/NkzckofgSeOb0qFyxJbJYG7BttoRIgMirnhCx+iTgubZomnYxoTmRMt2tcunYcBpTjIO4da8WK5/cmmqUdIqMYsZ7vE5GxLIot7MczcTyjbux5j0tTZPTCHn/y2qSKVsRT8HAycrqhMWoxmCoy5jMpiN+uRfj87GIk+5o1wmibhng5cwF915YNpURsbNB6z6V1Hg83svjFY+MQiO6a8x2XpuHEF3cEg8CvHLFZKG7Z5DIpeV9wT314FeoBamYpnYztgCJjQvArGAH0PbwWpMhoLfo4Lt2Ysk8uIItf2o88JzyEd7HILlfNSONV6vG78XtPer7m8ZqT8flnTAKwnIzLCRcZ1XFp1bEmHoINw9n6ndEkbqkPbHk6GRtkMtY/dOkcl5Zh/cpxGMimsWkkBwA47BIN51eLOL1q3VPO2Twsv95oxDppeD0MC8dI1I09byej9d4rFBkd+N27gehFPF7jpUHNmMRCjdNQn3UNw5CjzVHEQC8RfoTHpSFezlzAdjJGFRntdmk6GYOQxS9qJqNyjYnqmpMbhxyXDo07gkGQ1eRkLMmJlP593lXxmwjwurarv48a1SQFfjpKHfDTSAhiTeglMtpZP3qcjCIji+PSjfEb2WXxS/sR9wxvJ6Oe3V31+N21fw73Pj3n+PNiuYqnT1llFldduAUAcPD0mlzQjyR0XDpfc4KYpnPETRgV3fEB4vdRM4NUZ9EAnYyBY2pemYzSUapFZPR2lPqJhsLFuGNi0DH2Isal/Rqpk0bZY1x6YtASZqM6RoKcjGxrdSKLXzwcInYRT2vnidcIndx45Li0L3ZOpuEYeQPU4pwI49IeAv8wHaYNKfgs4G0nY8RxaSXfl8KWPyWPTSTDMLSNhBZcOcthCuZ6jZVCGR+45SHcfWCu8YtD4CduiYzG6OPS/vepfkTeB1ybQl4brOrvoxZ72c/TPA4qFBkTQsX0L7nQNZorRcZxioxh8bNQ88G1/VQCFonqDT+KyCiOnzi8N31/n+PPD5xaRblqYjSfwRVnTwEADs2tyZKFpDoZsxlFxFVu3mUfx7Usfok4Li0egg2jv8dHxmqLu2bbpe3REZ3t0s7HjB0+IqMofVFdjIAtSvo1UicNr9FD28kYbXrALpXxKn7hvUhFjksHOBnXW3Yy1pcBDLH4pSFBOZlDGqZDih5lVSLTnOeHP17iLKBvA4OZjOHwa7jNaRK07Jzl5DoZ/9+DR/H5Hz+Dt//DvTix5Hzm2HdiGV978Khv/roXfuKWXzliswTFevQjfk7Gks+5oSs6q0xHqSf8NBJCNSAPQNdo7nrROgm3T1giY5JuLO3CL5OR+UvtR9x8vXJK1YVjlFYxIdz/4iU7kU4Z+PfHT+Khw4vyz0Xpy+6tIzhz2hJPji1tyLHQpIqMfiM6fueD7aCL2H6oCFtup0s/MT4knIz+15egTEYtxS8eC3ZAcTIuuh/g6/MYAWCnzGRci/w99QJljzH29mYy6hlpTBpBGUvCJV2I2i6tbMbwmaAx0uXrsZATEztRnIxyjN2zfZ3HxQ+v1nrAdrpFb5e2833tEexSpKibJOLXNJzVJGhtlH0yGRO0Fnz6tPWcsbhewv+45WEpKD5xfBlv+Js78O4v3o9/vOdQ6PfzczJmNQm/HJd2Yjvavcel3dcobZmMzMb0hD+VCUE8fKW8xqU1PSRtSCejteibZyZjQ3ydjDk97lLij2xc9zgnUil7hESHk/HCbaP4heduBwDc9H07m/HJmsh4/tZRTA/nMJRLwzSBx2etryd1XDqTtoP41Zt3xed8kO3SERcNQtgS44z9Srjil3qnb0Zju/SGy/UgsJ2J3uPSbpFRvH5poxx57K4X8NpxF07GQrnacg4g4B1CL1yvK4VyUw6NpBO0aJDt0q2KjB6OUuHAWC9VIsdGJJWg0UAdjkMvQYBTJ40pehTmAPqKXwrSyZiSwmXVBFYYLeCgVPZuGs5pGgm1szFFu3QtxiNBIuOhOXsz8zuPHsdXHzyK2cUNvPXv78ZS7ef4g996PHR0iZdrHbCvMe5yxGahuOVEOhkLfsUv7mxMTe3SLH7xRLvIeMMNN+Dyyy/H6OgotmzZgte//vV4/PHHHa8xTRPXXXcdtm/fjsHBQbziFa/AI4884nhNoVDAu9/9bmzatAnDw8N43eteh8OHD+v+dhND1WP0TaDrIWnD1S69VqzIRT3xxm9kV6drYXG9hD/614ex9+B85PdKEo0u+tK1VY5e/DKcz+CdrzwXhgF865Hj0sH4uHQyjsIwDJwxNQQA+OnRJQDJdTICykOUh5PR/RCsKwtww2dEt98IJTJ6ZMhkdY5L+zgZd9Sc8O626H01kfHczU6RcTifkSLb0T4YmS55jEuP5DPyOEVxMxY9BEyx0VGpmi2P/yaRss+1CtCYyZiuF7OA1sewk45dbBHkZNQgMipiGfOzG+Pn1hIu6ajj0mrhyEA2Le8pbDV2IjYOc671hq77ujtnWTxnrBTKWnKc48AzNZHxsjOtosb/9dVH8NZP3Y2jixs4Z9Mwzt08jLnVIj7ynSdCvV/DwpEI6w8g+JrYj/jdBxo5SksVM9Imq19UQb+j/dO47bbb8K53vQt33XUXbr31VpTLZbz61a/G6uqqfM0HP/hBfPjDH8ZNN92Ee+65BzMzM3jVq16F5eVl+Zprr70Wt9xyC26++WbcfvvtWFlZwTXXXINKhQ9fXohMRq/RUCloRXj4KlWq8qF7y2heupSStIPVDvycW2LXXYdr4dafHsdn7zro227cr/h99gJxsylGuKaIc2o4n8F5W0bxH/bMAAD+upbN+ORxSzg5f6slnAiR8cRyAYC9059EvJqK/YRfsTkS3cnoXTbSb4Rrl64fs8m2pfjFZ1xacTJulCqybdrtZASA7ePC/Zj8kWmvkTfDMDAxGD2X0etBezCblucjR6ZtxKLBa+NW/ExvtLjJ6tXGm8+k5HGga84bWfzimckYPdOy4HFcOMYeTLVqKmVVzuMiRpuDYjvCIAwO7jFdllU58ROcxOcWdTTXfRzGlOfXpYTcO4TI+Me/cBEu2j6GhbUSHptdxqaRPD7zmy/An/zCHgDAZ+86iMdmlxq+n72h5Dw3ZE5mRE2j7DMi36/43Qf8cmN15fPTyeiNdpHxm9/8Jt761rfioosuwnOf+1x86lOfwjPPPIO9e/cCsFyMH/3oR/GBD3wAb3jDG7Bnzx585jOfwdraGr7whS8AABYXF/HJT34SH/rQh3D11Vfjkksuwec+9zk89NBD+M53vqP7W04EtqBS/2c6il/UnfXBXFpbRlTS8SpXAJyuhahtkvO1fL9jfeDyaYZGIqOdiRLFyWidFyL39F2vPA8A8LUHj+Lx2WU8fdraXDl/6ygAW2QUDOeSKzLmPXKA/DMZa+PSkTMZ7bGqfmZMWYT55VaVPa5NtjCsw8lou09URPHLieWCdDvuP7kK07QWj9PDubr3shumk3+N88qFA+yczSj3XC9xyzAMKaT0wzh6WMK1S0fLZFTHpQ3DUEa9krFg140Q4NNe49IaPjvPcWlG2wSiLszb3S4tzrskthrroOQTJ6Ara9l9T8+kU/LekYRjsbhWkv8/zt40jL/45ecil0lhKJfGp956OXZNDeHF523Cf9gzg0rVxP/6yiMN3W9eGxfq76O3S9NBpyLuA2GdjOo9OIrTl2Pr3rT9p3Jx0SpBmJqymlUPHDiA2dlZvPrVr5avyefzePnLX4477rgDALB3716USiXHa7Zv3449e/bI17gpFApYWlpy/NdPBAkqOopfNmph2inDOilFFgdFxmBkVqZLVMlnUnJxH3VBsVz7+8eXk78Ab4ZGbV85D6dds8hx6dpC5KLt4/iZC7agagK//88/QdW0dnu3jOYBAGdOO0XGpGYyAt6Nhv6ZjMLJqOchuN+djMJBYpr29cGNPBbpepFRS/FLyXtcemo4J792fNFy9O5T8hi9Cnt2yPKX9bo/SxLVqmm7tVyLhgkNG3u2uOXdAksno03Q/UMsstdbHJf2EnsB1TVHQcuLoMZvGQsUofhFtEvnHGPsFH6DCCcyaip+ybqcjAkQtnRS9sh6BfQJWl4RKEkqfzlUK5fbNJLHUC6DC7eN4bu/93Lc9t9fiYt3jsvXfeDnLsRANoUfH5jDNx+eDXzPkhS3nM+kuhq//YTlfmVQiowhMxlVkTHCsaCT0Zu2ioymaeL3fu/38JKXvAR79lgW49lZ64TcunWr47Vbt26VfzY7O4tcLofJyUnf17i54YYbMD4+Lv/btWuX7v87scZevAc8fEURGWs3+cFs2hrdkq4Klr8EYWfQOS88hmFoy8oUu8QLa6VIpQBJI8jdCyiZKBEElRUlk1Eg3IwPHFoAYLkYhXCyy+VkHE1wJmPW48G27HM+6Cp+cY/z9CtqbpXfQszbydiGcWmXk9EwDCkaHq6NPz8lmqU3149KA7bIeHQh2SJjSRHZ3eeIHbIfYVzaR9xiw3Q9QePSQuyI6mR0L3ikk5GFFp4EFr/4OFiawev8EEIZRUZv1Pu7W/yV15VCRCejuK9nnVmASRC2dFLymZwS9/XIxS8eEShjg8lZC4pR6TOmBuXXdk0NYXPNJCDYOTmEN73gTADA7ftOBb6nV8kXoK4/oj3zNjJT9Bt2JqO3yOg+DumU4VlS2Sz22DqPg0pbP43f/u3fxk9+8hN88YtfrPszt1vBNE1PB0PY17z//e/H4uKi/O/QofAV80lANOl6bWboCK5eLznHFXS4KvqBIPF3RMMYO+BcGJ5YKkR6ryQR9NkDenYSxcJDLXC59MxJXHnutPz9+TOj8tdnTg87/n7fOhkN74fgqOKW34huP9JoISY+a3XnVY6Blqu+Y9ZhME3TN5MRUHMZN2CaJr7/+AkAznNFxR6XTrjIqCw43A/DOu65frv5oyy3qCNoXHqwdp4UWm6X9h6JZ/5fMKWABfWQhp/hosc1i8UvwZSUMcGUS9waH7Q+u6iZjPK+XnODiSzAqO+bNIQTq65dWpbwRVtrFFzrQMA+xkkQfG2RcajBK4Fzt1jP8seXgifI7DFd7xH2qMKvXx5qvzLk4zxfL9b/7Aq88uObxWvTnrRRZHz3u9+Nr371q/j+97+PnTt3yq/PzFjFCG5H4okTJ6S7cWZmBsViEfPz876vcZPP5zE2Nub4r5+QY7me49LRH1zrREYxLh3BVdEPBF14dI3hqHk3HJm28cvDFGRrN/1WbyzVqilHs4ZdjsTf/pnz5K/PV4osdkwMQv12+qFduuiVyeg6JmltxS90MgoajZR5Fb9MDedgGNafzUVwJqgPzl7HQnUm3rn/NH5yeBH5TAqvf952z/fb3ifj0qrI7r5uyUzGCIu5gk8uka7stCRhOxk70y4NAEO56CO/SaZS9c+9EvfgtQibtkGt33SXeuOVLyoQTsaVQjlSc6vtZHSOSydB2NKJn+A0WVuvifz2VrGnE+xjPTFovXcSRtebERm3jQ8AAI4thhQZ/UbYI26se20W9zN+TkaxSeRVtqnDVVpmy7cn2j8N0zTx27/92/iXf/kXfO9738PZZ5/t+POzzz4bMzMzuPXWW+XXisUibrvtNlx55ZUAgEsvvRTZbNbxmmPHjuHhhx+WryFO/BxCgDouHaH4pXbCirwDFr+EQxwXr9ZvXTvkqpOx0a5aPxEkvAPRnYxriovFLRa+6JxpvPi8aaQM4IpzbFdjLpPCtvFB37+XJLxygHwzGTUVv4hFf77Pi1+AEE5Gj9H1bDoli1eiXEucImP9zrHaMP23t+0HALzxsl2YHsnXvRawRcnjyxta8iLjilhwGEb9OSIWc1qKX9xORmYyOjBN0zfaAVDGpTW2SwN6om2SjFgEei2ohzWMmnuVA8iJE54bnkhh1mMzSVxXKlWzbtHfDDKTMcNx6SD8nOpi3PfUSkSRUTxfZVQnY3KOxaGayOiONfJi65glMjZ6TvK71tvPxxHbpVn84sAvcmTZY+pMoGOqjcUv3mhf4b7rXe/CF77wBXzlK1/B6OiodCyOj49jcHAQhmHg2muvxfXXX4/du3dj9+7duP766zE0NIQ3velN8rVve9vb8J73vAfT09OYmprCe9/7Xlx88cW4+uqrdX/LiaAa8EA8UlP2i5UqiuVq3cUuDGInUYwJyZ0xioyBBDkZdY1GqSLlcY5LS6qNnIwRSy7EcUsZ9W3GhmHg7379cpxaKdQ9sJwxNSTHPpM8Lu01giBGENtX/FJzXPd58QvQ+OHfz+m7eXQAp1aKOLFcwEUt/tviOBiG90PX9gnrAf2HT57CkYV1pAzg7S89x/f9podzyGVSKJarmF3cCLUI6EXUBYM7GkbkIEfKZPQRBEYoMjqoKI5qr5IRsciO3i7tPMYsGQkmyC0y5ONgaQavZne2SwfjlzkHWOuFdMpApWpiaaNUN/ERFntM1/o32C7tjd/5sbm2eXdyOdr6YMOr+GUoOceiGSfjTE1kPLVSDFxX+00P5NLR3XOAnePMMV0LP0e72CTyWnPpKDxk8Ys32qXvj33sY1hcXMQrXvEKbNu2Tf73j//4j/I173vf+3Dttdfine98Jy677DIcOXIE3/72tzE6aucxfeQjH8HrX/96vPGNb8SLX/xiDA0N4Wtf+xrSaS4evaiYQY45+zNr9eHVLTLqWPD0A2K8J+0ZVK6r+EXNZKSTUeAnaAmiNu6ppS9eWbGDubSnGCIeYFKGfT4lkXym/sYtsmPdD0QZmckYcVyaTkZJYyej9/mxday2IImwYVFQnCeBbdE1sf21F2/DGdP+D/aplFH3d5KIdKJ4XLPssrXo7dL5Oicji19U1NgGr3t31HFpP3eLDqEsyZQDxqWjbtqapukpmDEnMxgv96fAMAyZnxjl2iLELXHeCZFxifEODvzuH5tqTsaTK9FERnlfzybPyViuVGUcS9CziGBqOCevE0FuxqKPu1RkNEZtl+aYrhM/J+NKgJMxanQWQEepH9ptNGFyNwzDwHXXXYfrrrvO9zUDAwO48cYbceONN2r87pKL3xgiYF188pkUCuUqVgplTNbG4Zph3ZWJomPB0w+Ia5Z3JqOu4hf7GMxSZJQEnROAupMYzcnY7MizeIAZ8REnk4LXCELZZ9wtq6tdWu60J1e8DUsjt4dXJiMAbKktSHSMS/uJvWJcWvCOl53b8D23TwzgwKnVROcyCleD1+ihjogSuQj1KRxhJqNFKSAbE7AdVestOhkLPgvPEToZAwnKyZSB/y2OS6sLTIeTsfa+66UKKlWTThUXQZmMgLWBMb9WavnaUqma8ro4wHbpQEpVb6FDOBlPRRUZPZyMYwmJzjq2uIFy1UQuncLW0YGGrzcMA1vH8zg0t47jS/7TFX4ifK5mmIouMnJMV0U6Gd2ZjBv+6zUx+bQeYXOPTkZvKLkmhEaCStTw6vU6JyPHpcMgnYweYpKuBcUSMxk9Ee7eTjgZm0E4GYV7KKlkPURGP2FLHKOoeXt0Mto0cnv4PRSJrKETEUarGhXwbJuwH+JffN40Lt453vA91bKYpCJ+/r1EFHHPjbKw9hMEhNuIDboWjnFpD/FEiB3FFlvYSz4LT7v4hcfBiyAnowz8b3HTtujIka0vfgF4XLzwGjFXEbmMSy06GdVG5AEWvwQiBCd3bJbIZIw6Li03DxOYySjyGHdODfrmuLsRI9NB5g6/HOScx6RPK5R8nqn7FelkLPhkMnqMS0/VjFenIxQjlTm27gl/KhOCFFR8nFFRs37cxS8T4sYSoYG0Hwja3dBR/FIoVxwPxyeYySipVLxHcwV2ZmBr7jlRpNSsyHjJGRPIpg1cuG208Yt7GPEQpZaAyFgH151HOKPnI15PvB6C+xX74d/7+lL2OT90OBk3PALiVfKZNM6sOXrDuBgBYMeE9fp+GJd2Z/UB9j13IcI5UvQRBDgu7UTNyfK6fagxF4UWNqn8RuhGNJT0JZmg4hexuGz1eUp9jlIFgXwmJa+RdJjWU6xYP6t+IuNY7drSavuwGkmQdxW/JKHRWCd+xS+bRm0no46W7wFHu3QyRMZm8hgFM7USx9mAhmkZUeI6P8RGSSv3DxU6GZ2IjTq3KzFo8mxTzek7F8HpG9S/0M8kt3Wgz6g2cjJGDK/2y2Rc6PEbS7upBBTy6GiSdDce0sloI9ulfYT3qE5G+6bVnKC1c3IId73/Kuk0Syr2Tq39UOvnZLSb+iIGk3s8BPcrYTMZ610P7XcyAsBfv+n5OLKwjpedvznUe4qymGSLjP7j0uKeu1qstFzgJpos/cStZYooAOzrVDZteEZaqJlkG6WK3HwNixAD3OfHEMelA7GdWvU/++JnuFCuolypNp1RVqzYThTVyWQYBobzGSyul3hcPJBlUr7j0tEyGcU9PZs25PpGuvTXyzBNM9GxM83glwu3acRyapUqJhbXS9IV3yxBTsZeF3xbEhlr+dVhRMb6TMb6YsRWYCajk2Elk1G9NojNp9F2ORkD7k39DEXGhCAFFR+RcUQ2LrV6o3cG/oqb1FqxgkK5QueQD/YYu/9DcZQRHPHglk0bKFVMrBYrWCmUm84JTCKyZMRnhy9qo5gcl841/1lP13bOkoyXiOuXyShFxoCHtTDQyWgTvl3aLfhGH61qlMkIAHt2jGPPjsZj0oIdk+GLX/YenMM9T89j00gem0fz2Dk5iHM3j4T+t7pFqeI/cjM6kIVhAKZpHVMxAtcMRR9xyxYCenuhqIugsXXAun6Je+5GufmNW7+Fp45ngiQjnnO9ipGGlM2+tVIFY82KjAEFJiM1kZEN0/VId3RAJiMQXWQc8BC2ipUqNkrVpkX+pFLy2TjMZ9IYH8xicb2Ek8uF6CKjcl9Pyrh0KyLj1hDj0muuKUCBeEbdaDHXV8B2aSdDtXto1bR+XoVmYWcy1ps7pkeii4wVOhk9oRKREKoNfsCjjuaul5ztbqP5DFKGdSIvrpWwZYw3eS+CLjw6il/Eg9v0cB6rhTKWC2UcX9rASA8sqNtNI/t6XpuTkZdRL2TxS8X++fbLjhXC1nKhjNVCuekRdEEYB12/0Mhh4BflsEVmMm607BIpNBiXbgU1kzHo+6pUTfznT91TlwF22ZmTeOcrz8Urn7Ults6XoIbCdMrA2IC1UFxcL7YkMpZ83p/j0k7CjD4NZNIoVcotNUz7CTMyk5FilifyuHicH7m0NdZcrppYLZTlmG5YGomMQHiHaaVqYv/JFZy3ZSS21xpdBH1uQPQNDFvYsu8lw7k00ikDlarlzKPIaCHvHx6bI5tGcpbIuFLA7q3NR/WUKlX5/OYl+K4WKyhVqj3brisyGf0KXLzYFmJcWoiv467JJVHGs7xRxnqxeTe8gK3GTtQok9VCWWoWQZmM08LJGGFcukRHqSf8NBKCzDrzeaBp9iHJjbv4JZUy7LbLHt/BaidBI7s6il/Eg9voQAZbx/W4wZKCyGT0OydEhknUdulWBbGk4zku7VPGMzqQlWMOUcZ03Y7rfmZs0Pq59HIYVKsmRDSTW0gRD7+litlysZcQe3WOrc+MD8AwrGM8F7DjfGhuDUsbZWTTBl66exMumBlFNm3g3oPz+M1P34v/8Jc/xCNHF7V9Xzrxy9QSyJiSFo5LpWrKRWJ9JmNtw4siIwC7sM3PBQ/YokcrThTpZHQdh6jZ2UmnHOD0FWPNQGsibcGnFAmwj0tYEf7/3vYUXvWRH+BLew83/X30Go3GpRsVkDXCKwLFMOz1R6vvm0RKPsUvQPTyFzU7UHUyqrE/vTwy3VomY21cOsDJKH4+3fFIY4MZmSN7bLG1CBjTNJWNl2RvZoQlnTKkTiFcpGp3gZcpREyWnV6JXvzCbEwnFBkTQuN2aZFT0GImo7R82z8ykzXLfSsLnn6h3ZmMy0rOhHCDHV+myAjYgpbfyJtXMUkzrLRY/NIv5DzapYMcQnL0JIJITiejjepkdIe9i+MAAGnXtSmXScmMmlYzXtsxtp7PpKUA+tTJVd/XPXF8GQCwe8soPvu2K/DNa1+G23//Z/BbLzsHw7k0Hptdxvu+/JNIAfjtotggxN0uf2n+nqtupviJjOulSuS2yyRgF4z4X0eE6LHegsjo1zgqG5JbfE5LOrZbxC97XCwum3+m8ivjAZp/VhPXoCdr/5tk/PJFBWORMxm931+8b6+P6erEz6kO2FnLLYuMynVOvW6lUwZGa+dH3A0nVWWjTWVpoyQ3VJtxMopn1hNLBTlNWPfePk5GwzCwrWYMOdbiM6/6HOflXu1XbL3Duuaom07DHo5R8bwbtHndCL8oqH6HP5UJobHIqGdcWrUij2tqhE0yQcdFR7u0eHAbGchi66ie8oykIMdB25TJKJ2MHNXxRHy+jnbp2mftlR27pSaSn4ggkhd8mvz6EfFQW66adaKF2HUFvAVf0TDdqqu0Xcfhou1jAIC3/8O9+O6jxz1f8+SJFQDA+VvtyIitYwP4H6+9EN9/7yuQy6TwyNElPHg4fm7GRqNP42Jjr4XFnHoeukVMdaOEbkb1OPgvGAY1OBlzGfdxiNaQnHRkWZXPgnoogpOxFHDNajYrUwhf/SCAhR+XblFkLDujmgQyC5AmB0lQ07AofznVoltrQ3H6up/fxFowzj/vc6tFXP6n38Hb/+Heug1GMSo9PZxrKv5oy6g1XVGsVDHnsQ6uVk1pBPGKb9iuRMC0QlmZEqKT0cYdOyKeaQazac9xZvvc0NEuzbWHCj+NhCB0Ej+RMeq4tHiQVnNRJniTb0hQJmPUYwI4x6W3yIZeOhkBReD1HZeOlsm4UuS4dBBexS8VnxFdAJjR4GTkuLTNYDYtFxvuh391B9zroSjqtUS4HnSLjP/nFy/Gc3eOY3G9hLd95l7c8I1H6zYJpJPRI3dqy9gArrl4GwDgc3cd1Pq96aDhuLR0Mja/UFTPQ7eDLptOSdGMApd/87qKuMYUWshktJ2MzuuUuJe04sTrBxqJv1GmQ4ST0Ussa3ZDWDiN+2HKp5H7WuS9tjpKW/C5p48lpHBEJ0G5cJHHpeUasP69e6H85e4Dczi9WsT3HjuBu/bPOf6slTxGwLpWTA/7N0wvF8oylsar1Tiqk7GkbhZTZJQMuRztywXr59IrjxGAPIZLG+WW14Nhcpz7EYqMCUE06foJKu1wMspx6XU6Gf0QixWvXMAo+UECsTs8poxLn6CTEaZpNnT35jN6nIwsfvEm5/H5iqwzr2MiG6Yj/PxyXNpGza1yP/xX1B3wACdj1Pwm3S3fOyYG8U//9UV465VnAQD+9gf78Ykf7ne85onjwsnoHW7/5heeCQD42oNHY7dBVmo0Lh3BMaK+t1cZhVgEMeMsnCtBjEtHy2R0HgfhwChVzJYXO0kmqPgFsKcKWmnn1ln8IgS1uI+P6qDQwMk4FrFUyi/fl5mM9ZQCcuFE1MjJFt1aQff0RiVzceCx2SX567/9wVOOP2slj1Egchm9NmTF55HPpDw3vkVxTKuZjOpzHMelbdxra/G/oz5rtfHBrFyTtDqZWQ7IQ+1n+FOZEGTBSINx6daLX6wTyHtcOr43lm4TlMk4UltQFCvVlhcUtpMxq4g0dDKq8Sh+IqN0MrL4pS14ORnLAe5S+fMbZVxa5DfRyQjA3+0hjoNheN8z7A2LiE5GjcUvgnwmjetedxF+/2cvAAB8/7ET8s/KlSqeqo1LP8tHZHz+GRO4YGYUhXIVX74vXsUMjRoKo2QyFgOKLQB7l5/j0kqBQlC7tBiXLrcgMvpmMjqbMYmToOIXwBZpW8m0DDo/7EKecO8rxMU4iy668HPlCqK2S8vilwydjEFUlDI3z3bp2sbhqTZEoPSCk/HxWTsf9d8fP4lHj9mi4yNHrV+3JDKO1RqmPZ6V/JqlBdsnrGfeowvRnIwpn+e4fsXtZFxp4GRMpQxpmmq1/KXCcWlP+GkkhGoDq+5Ikw9JbuziF3VcmsUvjSgHZjJGX1CsKG46Fr/YqJlzfiKjLYK1VgBhF79Q0PIiVxPWVRG3GiC6S5FRQ/GLzlbjXka4SOqcjA3uF1si5rt2Ihvz1RdtBQA8eHhRHveDc2soVqoYzKaxc3LQ8+8ZhoG31NyMn//xwVgVwPgVggiiZDKWAsZBAXussVXHUZKoNHDMAbajZ6OFcWm/Rt5MOiXPmVbceEmn1GAhNxKhnVvXuLRpmvJ62w/Pxn6uXEHkTEa5cejtZIyzsNVJ1IkRz3bpiE5Gr5ZvQZzyMZ86uYIv7z1cV8TyWE1k3F4bUf7ED6wJiK8+eBRfeeAoAOBF5043/e/JhmmP51a/ZmlBVCdjucGmZL9ii4zWz6zsLggwhEzXyl9Or7Z2fgQ1u/cz/MlMCJVGTsZctHHpDY/Fuz26xXFpL6rKzqLXQ7G6oGj1uCxtqO3StjAQp4VzN1A0Rl8hRZeTkePS3niNSweJ7jpEculk1Dym26v4LcTKAWPrgOJkbPFYtGtcWuWcTcOYGs6hWK7i4SOWE0G0uZ63ZSRwZ//1l+zAcC6N/SdXcef+0237Hpul4bh0hEzGgo+wJRCjRCK/qJ+Ri7dAJ2OtXboF11xQI++IhhiVpNJoJC1K8UvQ2G8z49IrhbJ8Hu+HKCEhMuZ9ritCYFlWPpdm8HMyUmR0oj5neV3jRQTK6ZVCS8chzLh0t+MBvvPT4/j5G2/He7/0IL7901n59fViBU+fXgUA/J9f3APAEhe/9cgs3vflBwEA73j5OXjxeZua/jeDssSX1u04Ky+Ek/FYi07GMPepfmRYOtqFkzGEyDiiy8nIY6FCkTEhVBpkMkYtGREP0mquhBAZ51d5k/eiogh9DQt5WnQtLEuRMSuDnYvlal/soAfRjJOx1OKoOselgxHjU4526QAnig6RnO3STvyykuyHU+/PaXNkJ2P7HaWGYeDSMycBAHsPWkHuIo9xt9Is7cVIPoPXX7IDAPDZO+NTANNwXDpCJmOQUwuwHUccl1az/0K0Szc5Ll2uVGWch5cYMJRvPVcw6Yjj4lv84hqTa4agcemRJpyM6rm5Uaq2lNnZS8gcZJ+IErXwopXNdHlPdxe/yEIZnieAs2nY67oyNZyDYVhRQq3kzgVFoHR7dN00TfzdD/fj7Z+9V7rX7njK3jx88sQyTNNyq73yWVtw5bnTKFdNvOOze7FRquKVz9qM973mgpb+7Zlx/3HpsE7G5UK5pTgBMS5NYcvJkGtyUzzT+I1LA8B0zel7erU1kbHRs1u/wk8jIdglF95/Hj2Tsb74ZSLC6FY/oO4W+gldUY+L2i6dz6QxVbN89/vItOpk9BUZPcZ5m0EsAulk9EYsBIseIqNXEdKWsWgieaVqymPJdmkLX5GxQSmScDKeXG5N8O2Uo/Symsh479PzAOxmab/SFxUxMv1vD8/i71zlMd2iXAl2GwqRsZXzo9Qgk9EufuGiXR6HwOKX1salS4oY4Dmam4v2TJBkGm2ODEWY2AkqfmnmOc19biY9l1Fksotrk5t8Ji0/01aEFL8x3V4oG+kkQnAyDO/7eiadwlRtzdZKodtG7fxwO0qBaJtfOvg/X38U/+frj8I0gYt3jAMA7qk9EwDAY8es54JnzYzCMAy84+Xnyj87Z/Mw/vLXLvF9FmpEsJMxOJNxOJ+RLsdWGqbF9dDveaFfacnJKMalW4wTKFPw9YQ/mQnBFhl9WvcitkuLG70zk1HkcCR/JKQVyorI6HfhsY9La7vdy8q4NGCPRERp6E0CDiejj7vXa5w39PtXqnJxSSejN17FL0FFSKpI7rUr3Aj136GT0cK3XbqBI0i6oivVlhYOG2V/14NOLjtLOBnnYZomnpTN0sFORgC4cNsYfu9V5wOwFimfvfPptn2fYWk0Lj0uc5Cbv+c2cjKO5K2flVafEZJEqYEID9iiR6FJp5p6nfJaHLqbMYmNXMj5nB9iEdlS8UvA+dGMk9EteiV9E36u5vwRApYXYxFyGcVzlnvjkOPSTsTmRdDGiLivn2pBSAlyMnbzWByeX8Mnbz8AwwD+8OcuxCffehkAq01aOAlFHuMFM2MAgJft3oQrz53GltE8/u7XL5Ou2FaQmYwB7dJB7799wnIzHl1oPpeROYDeiM2m1RYyGedadDIGrW36Ga7EEkLVDHYy2mO5laadKeVKVd7AVCejaGNiu7Q3YZyMUYLKAdsGPlpbILJh2kJ89n7tuYCSydjCuPSqsohh8Ys3zWYyAqpI3vzPb0EZW6TIaNFqJmM+k5buhFY2LGwnY3uPw54d48hlUji9WsS+EyvYf0qIjI2djADw7p85D//fKyxXwx995RH80z2H2va9hqHYwJkgjsnSRvP5Zo2LX6K1wCaJSgMxC1CdjE2KjI7stPr3F6H1dDLWU2rkZIxS/BLYLh1e+HWLikkXweaFyDgcJDK27jqUefDMZAyk3GCDCgA2jdgTCs0Spl26G67SHzxxCgDw/DMm8V9eeg62jA7grOkhmKa1+QgAjx+3MpsvmLGeCwzDwOf/yxW44w9+BudsbrwhGYQYl17eKNddd8RUwNigv7i1bdzfCdmIcoMirH5FrMnWCi4nY8C49FQtk/FUi5mMje5N/Qo/jYQgbNNeY4iAfdJVqqYjIy0MG8rr1d3E8dqCZ71USXzuTCs4REbf4xLNYaqOSwNKYUO/i4xm4xDeXITiF/EwkU0bLBnxwevzlY5rn/NBiOQnWhC2hOMhkzKYi1KjkZMx6IFoay2XsZXyl04Uv4j3f05tPOrL9x1GqWJiOJfGjgnvZmk3hmHgfa95Fv7zi88CAPzBv/wEB2sB8WF45Ogi/vr7+1pyQ3vRaFxaHbtqdkHn12gsiNoCmyRKoYpfWhuXlo65dAqGx3XQduPxOLhpVPxij8m1Xsbj7WS0jnWY5zT3uHTS87FPhxAZo1xbNnwcdEK4WeKmCIBwmXDCyRhNZPQvfumG4PuDJ04CAF5+/mb5tcvOmgIA3Pu0ldWsjksLDEPPc+JIPiOv2W4342KDcWnAFimPtjQu3VhY7kfcTkaxXhsNdDJa58Zci+3SLH7xhiuxhCCLX3x+wMVJBzQvaKntieou1mg+A/HPMRelnrKSkeLnpotSyFOpmvIiKh7iZD5In4uMQnQPGnfLRhiXZulLY4LGpf2OS5SfXxlATxejRCzE6p2Mjc8PkZHZkpOxg8fi0trI9JfvPQwAOG/rqKd444dhGPif1zwbz9k5jqoJPHBoIfTf/YN/fgh//q3H8ZUHjjb1PfvRaFw6m07Je0azY5iFkJmMLH5Rsv8CFqHiZ7vZ4pdSQPYfUL9AIjYNi18ibNqGczKWG04Cua+1rUQb9AplJU4jWGQUDdPNrxMKMgvQO5NxrVjRtsnTyzS6dwDRxqX9sjEBpV26w4J6qVLFj/ZZTsaXKSLj5bVngnsOzOPkcgGnV4swjPATDs0izB3HXUJhqHHpcdEw3cq4NMtGvJBORncmY4CTcZNol265+IWj617wJzMhVBuo6OmUIUedmxW0NpTSF3XxlkoZLH8JIMzORhSRUV0Mioe4LWPRWmGTQiPHHKA47VoYlxY3reEcRUY/gsal/c4J+bDWgsgoHEV+LZf9iGg1dJd5hLk2bdHhZGxzJiMAXHam5VoQD4fnb2l+/MkwDDx7m5XX9NTJcE7GUysFPHRkEYDtmPDjs3c+jT/+2iPyPu1HqRo8Lg2oC7rmHoZlZpfvuHRNCKDIKMelgxbswsm43qQYWGwgBkSNUEkyjYpforRLF0IUv5RDTAItrDvPyySP84qoJMMIdmuJza5Wri0FKW457+ujinCT5M84LI3ODcAWUtrlZFwvVVp6nm6VBw4tYLlQxuRQVha+AMDlNSfjA4cX8NCRBQDAWdPDjk4BnWzzaZhu1C4NANtqUxctFb+wbMQTW+twZzL6H4cpWfwSMZOR49IO+GkkBOFk9BuXBlrf5V33KH0RiPKX+RbV/yQTxk0XpfhF7ArnMyn5YGyPm/a3k7GRsxdQRbDm23PFzYvN0v4IEbfgcDJav/Zz9m4dbz1TtCCzm3hbE/iNMQnhN4yTsZXRdZHJ6NVEqZtLaw3TglbdCudsHgYA7D+5Eur1wkEB2NlPXhyaW8P/+uoj+NSPnsZ9z/i/DrBdbkG74bJhusVxaT8no7iWcfzQvif4FekB9kJmo8lFdVCLMQAMsfjFl0aL6iifXVDxi7qZ2Ej8dU/1JFkAm69tdIwPZgPdVCIzvKVMRp/il3TKkO7rJH/GYRHt0tlMYyfjyVaKXwKmE0YHshBLz04ei9set0alX7J7s+NZ5uxNw9g0kkOxXMWXahMOz2qTixGw111uoXBpvZbJGMLJeHSxeScj26W9EetqsQEYql26lle6Uig3Hf9mmqZtoKCT0QF/MhNCozFEQN0hb+4EEieq1+J9vMUFTz9QNRvvbAxHcDK6m6UB1QlGJyMQPEagxcnI0hdfvIp1hKnR18k42roT13bP8ZgIGmYyBpwfW2sLktacjJ1plwasHehzawIhAJw/06LIuMlyQO4P6WT84ZO2yPjkiRUs+oyKffqOpyEMjI8cXQp8z1IlWAgEbJHR799r9N5+I+xyXJoOOrt9PVQmY6tOxmCxl07GehqNB8pn3BacjEHir3MSKPh4i5FRuRmQ4EzGuRB5jICeTEavMd0ohTJJoxymXXrEer46tdy8KaTgI/YCNcE333nB9zaPPEbAmkwQEw7f/ulxAMAF29onMoqGaffmeJhMRulkXNhoupSVI7reyPI0MS7tsVZ2MzaQkdMFzTZMq/0LdJU6ociYEMQPuZ9DCGhd0JI3eQ8no2iYbnbB0w+InY2ga06U0ShbZLRvYGJH7eRKoen20STRqAgJsMcGoxS/MJPRn7zy+YqHp0qDVuMo7egyIJ5ORol4uC2Wqw4xpNHYOmBHL0Qp4elUKZJYUADA+Vtba4s8tzZmvf/USsOxZtM08cMnrQWO+Fm+71C9S3F5o4R/VBqrHzm6GPi+YcalJwZrESVNjkvbxS/ex5zj0jalUO3SNad2kyJj40zG1oWypFNucFxEnuVaK07GBk7fsJNAQlg4c2rI8fskIkXGoUYio3dsRxg2pIMuXoUjcSOM4LRptDYurdnJCNiGk04dCzWu5GW7N9X9+WW1XEaxDrqgxc3HMIjyFndDtD0u3bhder1Uafqzkxm1HNF1MCzL05xOxqD1mmEYcrOkWZGxrIqMdJU64KeREMJkbEUel/bYwZLj0gkOt26VMG6hKEHl7mZpAJgeziFlWP/26RZbspJAtZl26XK16R1EsQDkuLQ/YhFtmva50DCTcdwOJi83Kf4WmMlYx4hSzqU+wFZCRDlsqTkZj0dxMnZI8BXlL6P5jCwPapZdk4PIpg1slKo41kDk3ndiBceXCshnUvgPe2YAAPd5jEz/4z2HsFIoy5/3hk7GEOPSrU4PBI2DAk4nY7PXw6RRDjEuraNd2gsxmksnYz2N3FrisytWqk1PKBTLwU7fsC5J4Vw8Y9pyVyd5yieskzFKE7R9X/cvHKHIqBa/BDkZRYNusemynKDjANjHolOu0ttrkwQXbhuTG6IqLzh7yvH7Z82Mte178SosLFWqUuQKGpceyKbl+XN0oblnLY7oeiM36gplVKtmqHFpwG6YbrYYST2X6GR0QpExIQhRJajootUxnI0AkZHj0v6EyWSUx6QF14LXuHQmnZK5K8cX+1dkDNOeqy7yyk26PsPsjPU76sOuWFhXG2RlTg/nkU4ZqJrAqSYDmAsNFon9iGEYMnRcXYiFcTJuVZyMzYpOQSHx7eDqC7fivC0j+JXLdzXVLK2SSadwZk0YeOpEcC7jD2oLnBecPYUrz7VcFO5cxkrVxKfveBoA8FsvOwcA8MTx5UDxoxzKydjaGKbtZAwWGStVU24s9iuNWowB28nYdLt0A7FXTpywXbqORvf1ISW+pNnyl0Yi/EjI9vU6J2OCN+DDj0u37pIW55fXmO64T7FZPyIELa/PSTA5lJPnTrNuLdny7fP+spBsvTM/736j0oJnbxuTYtNgNo0zaudjOxBuRNXJqIqtQWO66t8/1mQuY1m6V/nMqyI2mwrlquOa0+g4TI+05mTkuLQ//MlMCOVmxqWbfHgNKn4R49JJzp1plTBuOnExbK34pSYyuhqzooycJoVGY7mAczHRrOthNeTOWD/j9fk2cgilU4Z00Lmb+hrBcWlvvBwGYTJ8xWZFoVyVAeZh6WS7NGAtcr/zey/HH17z7Ejvc86m+vKXUysFvP6vf4S//v4++TUxKv2y3Zvx/DMnAFhNl6r79tuPzOLw/Domh7J498/sxvhgFqWKiSdPLPv++6UGzcOAksmo2ck4mE3Ln4d+H5mWi7cAJ6MQ0Jtul24g9g6xXdqXcoPzI5u2S/Cafc5tVMhjP6uFExnPmO6jcenQmYwRil88NqykQzLBn3FYhMAV5ORPpQxMD7fWMN3o+Uq6SjuwFqxW7biSl51fPyoNWMLb88+wJhzO3zoS+KwTFTWmStzDlzbsNUIjEVC0Ux9tsmHadnZT2FJRN5tEpngmZTRcG0y32DCtloe28+esF+FqLCFUQzhTWs3/Wy/6u1LscOvk7ta2Shg3XbTiF+tmPuLandkiyjNaGHNMCo0KRgDnQqXZ0RER/j7kIbwTi0zKkI2DQuAIE+uwpUWRvNFOe7/iNVLWKNsMsD5H8XebKX8pV6ryOPea4CtyGZ9Syl/+34NH8cChBfz5tx7H139yDIVyBT/ePwcAeOn5m7B7yyhG8xmsFSt4bNYWEP/u9gMAgLe88EwM5tJ49jZrXCtoZLqRAAW0nsnYKAvQMAy5adL3ImOIMTSx6dp88Yv13o1avtfoZKyjUfELAAzXjstak89Ujc69MJNApUpVipDCyZjkKZ9uF79wXNpGbMrOjAfHhbTaMN1oOmG8dl9abHJDshXuP7SAUytFDOXSjjxmN1eeNw0AeN6uibZ+P9PDOWTTBkzTFm+F8D3WwD0HANsnak7GheacjGGyg/uRXDol1xiiRHJkINNwymVKjEs3GTWmrmtanaRJKr21AiC+VMwQTsYWs342ApyM4y2ObvUDYdx0UZokvcalATZMA7aIEvTZZ9IpmVfXrJOR49KNMQyjrsE7zHVKtBo3LzLSyeiFp8goFusNAsOFK+JIEw+/BeVc6jXBVzoZT9lOxjv3n5a//v1//gn+ee8RrJcq2Dyax7O2jiKdMvC8MyYAAPc9Y41M//DJk9h7cB7ZtIH/9MIzAQAXbbdExp8GiIxhxqUjZzIGvHcUx1GSsM+PEO3SLWb/ZRsVv9DJWEeYTaqhkI5DNw2zMkPkZ6uOOtXJ2KhIqlcRWeyTDYpforRAB2Utd9I9F3eO1Vxw28KKjE06GRsWvzQh+Jqm2fTmjKBcqeK6rz4CAHjVs7f6bpoBwH95yTn48196Dn73Vee39G+FJZUypLlDiL126Yt/HqNgm09xTCPKITZd+hHDMOR9VKwjwkydyXHppp2MFHv94E9mQpBB/gEqevTil/oflwkxLs2dxDrCZDIO19yl0YpfvMelT/T1uHTjzx6wF/PNNkxzXDocdSJjiEWi2IlvVmTsdKNxr+CVyRjmOADAOZtrGYWKs68RqsgYJGjFkXM21xqma/9/q1UTPz5guRZ3Tg5ipVDGB/71IQDAS8/bJHetLz3TGsvae3AeG6UK/vBfHwYAvPmKM6Uz96Idwsno3zAdZly61XG3Ru25AOhkrGE7fQOKXzL2ta0ZEanUQMyKsvGYdMRxCRLhW3WCNhyXlsfF/33FNXY0n5HuPtO0o22ShnQyjoQTGZu9rlSrpnw2G/A4LnYmI9cfx2sC1dYGxWebRloTGeXYeoNMxjAi40dufQIXX/ct3F27tzbD3/5gPx46soixgQw+8NoLA1+by6Twy5ftkuvUdiKfW2vHQXwOYURG4WQ82mQmo3xe4IhuHeJ6LSb6wqzVNtWuY6dbzGRstGnfj/ATSQiVBoUKQHuKXyY5Lu1LmIW8ekyaLVcQD2xuO77tZKTI2EhkzGWcIlhY6GQMh/x8K+5MxsaFI806cQtl/7GqfsZ7XDrc+XFuTXTb16AIRUXcL3LpVKBjNY6cWxNVjy1uYLVQxmOzy1hYK2Eol8bNv/VCTA/nIC7TL1WyoITIeN8z87jpe/tw8PQaZsYG8J5X2w6Ki7aPA7CcjH6ilBgHDRJRdtXGMI8urDd13RLnoJ+DDrDFAHF9+/pPjuHrPzkW+t9ICqUmnIyAU1hvhC1m+ZSX1Jx4a6VKYh1wrVIKcf9oNdOyYfFLiHZpsdk+PpRFPpOWz8xJddpJkbGBiCMc0uulSlPRNI1c8V4baP3KsSVLoArrZGy2QVeXk9E0TXx572GUKib+7of7m/oenji+jL/8zpMAgOted5Fnq3S3EFMfwlEqcqyDmqUFwsl4rFknY5VORj/E5OWJ2jqiUekLYI9LNysyhokf6lf4k5kQxH07TP5fsyUj6wGtZXY+FG/ybmzhNyA/qHZMqqa9UxiWlQ1vN5248c728bh0WKeWcJOowb1hsJ2MdM0FIRZspbL1+YYRf7e0PC5NJ6MX4iHX6WQM91B0nswoDC8y9nLL98RQTjoFD5xalaPSl581hZ2TQ/jLX70EhmFdV158ni0yPm/XBAwDODS3jv9721MArEWQ6jI/Z9Mw8pkUVosVHJxb8/z3SyEKR7aM5jGQTaFqWkJjWMI4GdVx6UePLeFdX7gPv/3F+5r6d5JAmPNDfR5qZvSvkZNRTDeYJvq+5dtNo+IXwI4FatXJ6HfdCjMJJK6xQnCRmeUdatztJKZpNp3JCDRu51ZRzyuKjP5UqyaOL1rP+40yGYUIeWiuuWt6ozI3W2QM/lk/cGpVFpx877ETocXOcqWK//6lB1GsVHHVBVvwi5fsCPutdwT3BI49Lt1Y3LLbpTeaMpvYBWUUt9yI+4DIEw9jCBHj0qebFODLIdeb/UjvrQKIJ9UQTkbxwHOyyUKQjbK/yCjyodZLlZYzNpKK7Rbyf81QLi3LMZodmbYzGZ07ZTMclw7Vtg607mQUI1N0MgZjj6Nbn1cYx3Xr49K1nXY6GR0EOxmDPyvhZHyqCSejdDz06HGQ/59PruDOpyyR8UXnWgHyL9m9CZ972xX4+7deLjOYAOsa/KytowCsz/bqC7fiNRdtdbxvJp3CBbL8xXtkulwJdrkBVt7QGTU3o59Y6UWpgVMLsEvEljfKsk3bNIFbf3o89L+TBMJkMqZThhS7xDNSGAoNCkYGs/YzQZBrrh8phXDutBpBY4vw3ptUYSaBhGNRPGsnuZhkrViRP8uNRMZMOiUz0poZbRbnVTZteD4zJPnzbYa5tSKKlSoMA477khfnykiQ8Pd0QMnG9C1+CXcsfrTvlPx1uWriX+8/Evj6lUIZ/3TvIbzxb+/Eg4etMenr33Bx7Ao2ZqS5wzkuPR5iXHrr2AAMw7oGNeOis4uw4vVZxAE7k7FW/BJGZKxdx+aadTKGzDjvR/iJJASxOEkFXHgvrC1wHp1dbmpkQbRLexW/jA1k5M2/32/0bmROZsCFxzCMlgt5lmQmo3tc2rrZnV4tNi2eJYUwbetA65mMHJcOhxA0xGIkzI6feFg7utDcrq5sl6aT0YHMrVJaH8OIKABw7hZrfPj0ahHzIR+8Gi1G4o7Iodx3YgU/PlATGc+Zln/+4vM24WXnb677e8+vjUwP5dL441+4yHMRJMpf/Bqmw4xLA8AZU9b3+Mzp8FmZzTgZHzy8iK8/ZI9Jf/uns6H/nSRQDpmxJDb4mlmUNBJ7nc8E3LhVEU74oAwy28mod1x6OITIKGKDxDU3ycWI4mc+n7EFxCBaaZiWOYA+95IohTJJQhSGTA/nAzeRAFtkPDi31tT6YKNBHE1YkfH2msh4dq1k7Uv3HvZ9zvv72w/g8v/zHbzvyz/Bfc8sIJ0y8Ke/ePH/v737Do+izv8A/p7dTTa9N9IpoffeFLFgORGUJgKK4s/e63l3CpwFlbOeh4qnggqIqHCiIqB0kF5DCEkIISGF9F62ze+P3ZnU3Z1NIWHzfj3PPSdhs8yW75TPfIrdvpPtIdS3Ybm0NF3afpDRVaNCsKVX5sUi5Rmmcpkug1uNyD0ZLUFfJeXSgZbPoFJnlCs4lVDafqgz4jfTSUite2x9yWMCPODtpoHOYELSpTLFz22rJ6MgCE59ItUSSlOom3vn3dp0aX8PFznDIs/BtG9noXSn3+xMRh0HvyjRsBxdycT1mEBPuKgFlNcYHDrhqp1CycNaXbVBxsaZjPb2TR6uGkT4mfsFKS2ZvpLLpYHaIOPPJ7NRVm2Al1YjBwdtmTk8CpH+7nhtan/5PWvIXpBRp6BcGgBiLJNrLxQoz2S0F0QBaoNmG09kQRSBARHmPpL7Uwub1Vdu06lsTPloD85kW5+o3RHVDhix17O0NiCtlL0BI0DtOQGHv9QSRbG2DYqNQHltT8a2GfxiK0hWYrmR42tpI+TXzEnwV4K6pdJKssqkfYsjmYz2suKlY1tZjaFT9y/NUThZGjD3bPfSamA0ibjgwE0qezcPpe+6rSCj0SRin6U6YPFt/eCqUeHspTKcymyc2Z9RWInXfz2DKr0R3YI88fyNvbD3xWsxeVC44m2+nLo0Kpe29GRUkMkI1LamceTa3CDflGRwqyHpxkdumfJMRk9XtXzeWlCh/NpZSRuPzurKvAqgRpT0oFOpBAyMNF80nLxofcJlQ1U2gowA4CcHGZ2v70xLKClhB5o/9Vt6fMNyaUEQ5JKJzjr8xdHp0o5k9gK1F3/MZLStYRBXSe9YV40KPULMpafWgjFNke+0X6HBrbbSVIaB0p6MQP3MPiWkC0N7GRUdlZTpcT7ffAE2smuAosbqg6P8sOfFa3HH0Eirj6kd/lLSZPaGknJpoE6Q0ZFyaYP9LMmGJ+KvTu2PXqHeMJpEbDvrWMm0zmDCoo2nceJiCf6+/pTDg83ak15BFQIAeT+VfEl5kNFeT0YAza5ucGZ1+yYr6T3u8OAXO0FGb+l5bQ5+aTqT0Rkz7Qot5/v+Cif3+svtmpRfvFcrLNEVRccnVzuTbMt5vr1+jID5+qB7iGMD3URRtBvwlYJp1XqT/NiGTl4sRlm1AT5uGozrEYSb+oUBMGczNvTJznMwmkSM7xGEP56dgEcn9lD0+tqLXC5t6asoT5dWkEEHAL3DzDcgE7OVBxlry6WvzHOttiQdQ6X9upfWfrBXEAS5ZLqgvDll6/wcGuI74iSkXmf2etANiPAD4GCQUWf74OLMd2tbQmm2kHRh50hDbFEU6wQZGx/EpAnTnbUvo1Fhz7nmZDLWGIzyQcXLlUFGW6QL6dogo/1MRqA24yvBgQyo2kzGK7NMt620ZLo04PjwF7nE7Qr9HLpZgoySuqXSLdU7zBtqlYD8cp18h70uvcLePtKE6XQHMhlrFGQy1r0guiouCIOj/DDJ0ltyy2nHgowbjmfK/ZCOphfj11NXTsl1bcac7fXRM9Tx7BNlmYzNG17izKTsUkDZ4JcKB947URRrM32tDuSxX8Iu7WOlc2I/D2kwovPdgJfaZ0jDEuyR2jWdcuDaQ6qislai66pR1U7w7sTXH5ccyGQEajOwlR7T9UZRrpazFvD11mrkXrLWPgupH+PY7kFQqwTMGG6+Ife/45n1evrnlFTLgcfHr+3R4fovNiXEcs1VYzChuFIv31hQ0pMRAPp0Md+wSsxRfs4rZ9yzTLcRjwZDOb0UBnulkmlHMhmVDhrtjBhkdBJyUMXOzljKZDyVWaz4uaUMIauZjE58ItUSSgMqkf7m0jpHAiqVOqP8mTcdZJQyGTtnubTy6dLmv3ckk7HuRYYnp0vbJAdxLYNflPY6k4OMVgZkNEW+036FZtC1FWm6Yf1MRuWNqqXMPkczGa/UzyHK371eEEMa+tIa3FzU8gVeU8NfpP2Qi533LkYKMhZWKs4Q1CsIbtU9EX9sYg8AwKS+5myTnUl5ioe7mUwilu9KBWCeqg0Ab/52xmqGS0ejV1j+FGfJZHSoXFpB302p1IuDX2rVzWS0td+S3jtHejLW7clsb+q3zenSlfUDC87cSkgql1aayTgo0g8AcDyjWPG/URtktH6eJR3fHCnDdjZSH0ClvQp7OJjJWHe/be24rlIJdntkSv0Yx8UFATAHG8N93VBabcCWOsPFlu9Khc5owsjYAIxqxZt8bUmrUctZcDml1XWmSysNMlpmJmSXKj+mM4POKs8GCSDeCqvOApqTyehAZVBnw2+mk1BaHir1WErMLlN8wSBlMjY1+AWoWy7deQ/yTTEYlX0m43uYhwjsTs5T/NxSaYhaJTQZ/A1tMOmss5GnS9sJurtbDkSZxcp7/0llWFqNigd3O6SAhlSqaZL3U7Z/r28XKcjoeCbjlZpB11akC90qvVHOompOJmOK0p6MV3hGqUatQkygOTDm46aRT/5bi1QyfTqz8XdbaXAr0t8DKsH8mSrtu6tT8Nw9LROyr4oLki/u+kf4oIuvGyp1xnqTQW3ZlpiLlNxyeGs1+PaB0Qj10SKjsApf7bug6Pfbm0FhubSUyZhWUKH4fEpJJqOSScadjdFUN8ho/TvcnPeubgDT2ueiaLq0lMnYIMjojFl2dXsyKjEoyg8AEJ9VovimrpKseGd+j5XKKTWfvyrPZJSqE5T1ZKypU+lj6+ahraB6pc6AoxeKAQDje5iDjGqVgOnDzNmML/1wEhtPZKGgvAarD5qPE49d20PR9nUUda+7pEF7Sga/AObzLJUAFFXqm6xyaIrUXoXBrcaan8loCTI6MMxNyZDXzorviBOo2/BYSdZcgKcrDCYRiTnKSnxsDX4B6mQyduKDfFOknoz2sumustzVO5pejDKFd2PL6kyWbqqUoDaTsXMGGY0K3/vreocAAFYfTFd891DKZODQF/ukgIZUqmlQWMbex5LJmFVSrXyq8RWeQddW6vZsle6uO1LeIV2QXCyqUhRIudIHvwC12Xcjuwa2+sRAa8NfjKbakjQXBW0euviaM+CVlkzrFHwu/cJ98fszE/DZ3cPlnwmCgEl9HSuZ/nTXOQDAnNExCPFxw7OTegEAPtyWjAOpBVh7KB2LfjqNH4827sXVESiZYgwAwd5a+LhpYBJre3jaUxtItjW8hNOlG5IuqFWC7bZAEZbKkIPnCxX3ua7bLsXe4JdKndHqkBHpHNhXLpd23lZCjgYZuwV5wttNg2q9CWcVXnsoOaYzyFibyai0Z2HdFihKBubUPabbKl229VkcSiuCzmhChJ87Yi09hQHg/qu7YVTXAFTojHh8zTHM/PRPVOtNGBjpK18bXSmk9z+npLp2urS7susENxe13KpF6aC02uPUlXuu1VY8GsQrlPbPlwcdOlCdwLJ16/jNdAKGukFGO5lbgiDI2YynLhYrev4qOyUL8okUy6XrUZotFBXgga5BnjCaRPxpmbxmT5mNfoxA3Z6MnbRc2nJBorZzh2/asEh4aTVIzauQSznskcqwOPTFPldL/57anozKgls+bi6ItpSEKm0jUHsifGVm0LUVtUqQ9xPSyb/egTvgQV6u8HV3gSgCqQoyH5wh2HuDJagmZVm0pr5SkDG7frl03ewee+XSgOMTppUEtwDzBWjDY/0kS4P+389cqpdR1pQjFwpxKK0IrmoV7h0XCwCYNjQSfbr4oKzagFnL9+PFH05hxb40PLvuBDIcGF5zuUgDPNysVG9IBEGQsz+V9mVU1JNRKpdmJqNMr2CyNACM6x6EbkGeKK024NuD6YqeW/pM1CrB6vla3ZuK1srYSxr0YfOzTJluzmT2js7RIKNKJcgl0ycUXnsoqU7o7EFGURTrTJd2V/Q70QEe0KgEVOqM8tAYW6Sbi/aO6bYmTEtZ8ON6BNYLVPq4uWDV/aPw2MQeEITa7Erzn6+soI0UZEwrqJArB5T2ZATMPZsBKE4A0ivsHdwZeTS4PlOaFDIk2g8AcORCkeJ/y5HKoM7myr0KIJmpTgaWkhsajk6Ylsql7QcZO+dB3hqlJexAbfmA0kCXVC5tbWJWZ89kNCjsUeql1WDa0AgAwMp9aYqeu9ySXcIgo32uDaZ3Ky1jB+pmfCnbT9lrEt+ZNbwQUzoYCTAHUhwZ/uIMwd7pwyJx9rWbcFP/sFZ/7n5dzMffjMKqehdjdYOMSjJMHZ0wrSS4Zc3IrgHwcdOgoEKHfeesH6P0RhPe/z0ZAHD7kAj5OKRWCfjnlH7QalTw93DBuB6B6BbsCVEEvt7fsUqoy2sMcq+yfgpK5eMsJdNKJ0zXTpdWMCGZg19kUiajvWwRlUrAA1d3AwB8vue8oqFu8tqwEcDUalTyuVxTGaaiKMrBRKm6x5kDYI4GGQFgsKVk+oTCvoxSP3hbx3R7fQCdXVmNQR4QFaawJ6OLWoVYS7a+kowtpS1QfOp8300mERcKKrDpVDbe2XIWG45lAgDG9WicnahRq/Dcjb2w4t6RiPBzx9U9g3F9n1BFr6Ujkd5/6VigEhr3BrRFas2SqPDGem25NM95G2rUk1FhufTQaH8AQGp+BQoUtqIxKOiz3FnxHXEC9XvV2P9IB1ruJioNMlZbTsCs9mSUB790zoO8NUr7OgG1JdO7k5UGGWvLpZsiZTJ21iCj0lJ1ALh7bCwA4I/EXEWlhxVyufSVG0S5XBpO7zY5cOdV6svYsKzUGmcIbrWVhhe7BgfKpYHaaZRKGsXXXpBcuacXgiC02ffI18OldthXne923b5XSk5WowPMn0l6gbIyXXvTc21xUaswZbD5ZsySXxObzGYsqdLj3i8PYXdyPjQqAQ9M6Fbv70fEBiDhnzfh6Ms3YNX9o/G3m/sAANYeypBvZHYEJy8WwySay6ZCFFy0S8NfknMVZjIqmPLNTMbGDAozGQHg9qERCPbWIrukGj+dyLL7eGkwma3PRBAE+XNpqgy7Wm9qlL1UWy7tfFU+hZWOBxmlvoxKh7/INw5t7It9nDiQq4SUxejr7mL1Gq0pPRwY6FajINgrbQMAfLzjHAYu3oIJS3fg4VVH8e9tKcgtq4FWo5ITKpoyoWcw9v71Wqy8d4TNlggdlRRklNoBeLu5OPQ6HM5kNCpr69EZNerJqDApxM/DFXGWm+qHFWYzMpPRuiv3KoBkxmZmMibnltmdwGc0iXKAwGpPRsuBpYjl0vU40vdsTHdz76/z+RWKysekTEYfK0FG6eKotNrQoS7gLhdHdvrdg71wVVwQRBH45oD9rBrpAoOZjPZJ2TrNGTjSL8Kx4S9ySc8VHNxqK9LJv5TtYVQ4lEriyPAXOfuEwV6rmsrSjc80/3eEn7uiz0VqJ+BoJmNz77Y/dX0cfNw0SMguxeoGZagXCipwx7K92JOSDw9XNT6eO0zu5VmXWiXIJXATe4cgKsAdJVV6/O94ZrO2qS0cSy8GAAy2lE3Z42gmo5LPoTaTkUFGSW22iP21odWocd+4rgCA5bvO2e07V6Mwy9fW8BcpkKhR1QYjpd6M1XqT4sFAV4qiZmQyDoqSrj3KFfXLrFaQQefM2aJKZMul0sqyGCXdQyyZjEqO6XplN3DDLduQW1aD8hoDXDUqDIjwxazhUfjnlH745YmrEOiltfvvXWll0hKpXFoaJOlIqTQA9LbcWE/JLVeUgW0wMZPRmoaZjEoHvwDA8FhzNqPSkmmDwoF9nRG/mU7AWGcynr3yUMBcShvirYVJtH8BX/fEyPrgl859kLdGCv4quWD0dnPBUMtFjZKS6fJqqSdj0wcxb61G/rw6Yzajo0GU+ZZsRiVZNRUMMiomZzIa6/dkVLKf6mspKz2XV64oUC5dKDK41ZhUUtb8TEZLuXQnyWRsa9KE6brHX6kf77gegYqeQyqXVnJTShRFeQ02t1dmoJdWHuDyzpazcpBhZ1Iepv5nL87lVaCLrxvWPTRG7mlpi1olYN7oGADAin1pigdvSb7cex7DX9uKJ789ht3JeXZ7RSolZVkNsWRd2SP1ZEwrqJAzfmxRklHqwenSjeSWmc9jlGZr3TUqGl5aDZIulWNHUq7NxyoplwZqj/lNBcjq9mOUgiRerhpIu1hnKuc1mkR5mI2/h/IgY4i3GyL83CGK5oxhe5Rk0Mk30Ko751q55ODQF4l849CBTEZ7x455o2Pxj7/0wbszB2HzU1fj9OIbsfHx8Xhr+kDcPSZW/jedVcPPQOnQF0m4rxt83DQwmERFwV9Hbrx0Nh4NjhOOlK0PiwkAABxOK1T0eD0zGa3iVYATqJvJqPRLPlBuwGy7ZLqqTpDR2gFGam7Ncun6HMlkBIDxPYIBALuT8+w+1l65tCAI8gGvUwYZHQjwAsA1vUIQHeCBkio9NtjJqpGDjA6UpnRWDculHelTGuqjRaCnK0wicFbBUAW5XJrBrUbkbI9KqSdj7aADJaSLg9T8CrvBHGcY/NLWmpowvdfS63Bsd2UTNaMtQcb8cp3drCCjSYR0mtCSvkFzRkWjd5g3iiv1eHtzIpZuTsQ9XxxEUaUeAyN98b9Hx8kBVCVmDo+Cm4sKiTllOHhe2Qm95PsjF5FfrsP/jmdh3ucHcdVb2xQPTrNGFEU5k3GIwkzGEG8tvC0TppUMRpIH8NhYH1IrjspOWIVgzY6z5vOi0V2VBeF93V0wZ1Q0AOCTHak2HyutH3v7LCkbpqn1Jp3/StmLgLk/pLTvdaYJ08WVOnl/4u/hWLaWlM14IsN+uyYlGXSdvVxaniytsB+jRL5xqGiYm/0BPID5u3//Vd1wx9BI9Arz7nQ96kIbfAY+VpJArBEEQc5mTMyxX8EjD/DjdOlG6iaBeLqqHQoAjrBkMsZnlirKQDeyN6ZVfEecgEkepqA8zVwqmbY3YbruVDFrvSX8PM070iq90elKQlpCusuktCfHVT0tw1+S8+1eyJfKg1+s350J8bb0ZSzrfBOmHQlmSY+7e4w5q+azXak2338OflFOOsnUGU0wmkT5pEjJ5yIIQu0kXjvDX3QGk/yZMbjVmHThW2q5OaF38AZIpL8HXDUq6AwmZBZV2Xwse2PaJwXiUvLKUa03orhSJwccx3ZXFkTxcXORL/Dt9ZLV1Rkq05zBLxKNWoVFt/UDAKw5mIH/bD8HAJg7OhrfPThGUQ/Duvw8XHH7EMvgrT/TFP+e0STKGTi3DQqHj5sGWSXVePGHk3LpUnNkFlchv7wGGpWgOFhad8J0sp2sIFEUUVplCWjZymR0ZSZjQ9sSzdmI1/UJUfw7947rCo1KwMG0QpsX7V/sOQ8A6Bdh+zO3WS5dWZvJWJcz9iyXhr74urs4fGHtyPAXJcPcOnu5dE6p+XjsaCajFGTML6+xO/08y1L+y3Mr23zcNPUy6BwNMgJAH6kvY7btG+s6g0muYnB35efSUN0kEEdKpQFzK5ogLy10RhNOZdq/GSJVBrE3ZmP8ZjoBR7O2AGCAwgnT0kHeVomKt1Yj/9ud9UDfFClbSOmF/MAIX/i4aVBabbBbSlJs6X9prVwaqL2rltsJMxmb04j3zpHR8PNwQWp+BX49lW31cbWDXxhktKduJuOu5DwYTCL8PVwQ7G2/Lw8AOchor63Dt4fMPeJ83V34uTTBt8HUR2n/EqTwc1CrBHSzTKNMybN98lsbZOTphTVSlq7RJOJsThn2pxZCFM0Zo44E6qIDLcNfCm1no+gNtTdNWhJkBIDR3QIxeVA4APM+8N+zh+C1qQPsZrlYc4+lVcVv8Tm4+YPduPuLg3jx+5PYl5JvtYQ6s6gKNQYTXDUqvDtzEPa9dB0CPF2RXliJjSfrD/rIK6uRG/HbI2Ux9uni49DrkRrFJ9vJuN6VnI/0wkpoNSr0slxMNsVTDjLypi0ApOaV43x+BVzUAsbHBSv+vTBfN7l0/9uDGU0+ZndyHrafzYNGJeDp6+NsPp+njeCvVA7t1yDI6IyZdlKQMdCBfoySQZYqKiXDX6RMRltrsWG/4dYkiiJe3hCPaR/vs7u2m5JbVo0fjlzEop9OY+2hdGSX2L5B15SkS2WY+cmfeHzNsSbbMeQ0syejp1Yj/46tY3pqXjn+tfksgKYnQ1MtQRDqZZQ62pMRqO3LmGBnwvRXf6Yhq6Qawd5ajFKY3d2ZeNTNZHTwmkAQBAyPMWczHk6z3ZdRFEW5CoOJJ43xKsAJyBlzDjTLHRTpB5VgLn/baGP6XpXO9tAXwLwg5ZIQJ7pb21KOBn81apV8EP/9zCWrj0vJLcev8TkAai9umtKZJ0ybHMzUAswXzPeONTeL/8/2lCabxdcYjNhnKWtszgl2ZyP1uNIbTfj+8EUAwNQhEYrLaKRsIlsTpi+VVuPt38wnwc/d2IslC02oe6H7Z2oBMgqr4O2mwXW97ffOk3S37GtOZ9o++a3hAB676mfplsr7FKVZjJIYafiLnUzGGmPtxakj+0RrltwxAIsm98UvT4yXA47N1TvMBxN7BcMkAmeyS7ErKQ9rD2fgrv8ewNRl+/BbfE6jfbE0yblbkCc0ahW8tBosGC/tu2sHfRSU12Dyv/fgpg92Ya+CXsdyP0aFpdKSOCmT0cbwF1EU8d7WJADA3NExNgcgeFrKpR0Z/KI3mvD5nvN49ecERUM1riRSFuPIrgEO30SaNSIKALD+WGajShujScTrv5wBAMwbE4NuTQwrqqu2J2PjYI80+KVRJqN8buw8gxGlIKN/M86B+kf4QiUAOaXVcoCsKVU6o1zB0LC/Wl1tGWT8bHcqvt5/AUcuFOGOZfuwK8l+KyO90YSV+9Lwlw93Y+Trf+DZdSewYl8aXvzhFMYs2YYb39uFJb+ewb6UfLs9XNcdzsBtH+3BwbRCbDyRhefXnWy0L5TLpX3dHX59UhuUc7lN36Sq1hvxyKqjqNAZMaprAB68upvD/0ZnU7dk2tGejICyCdPFlTr8e1sKAODZG3oyuNWEujEL72a8P9LwF3t9GX85lY0tCZegUQm4y9Keg2rxm+kETM3IZAzwdMVDE7pj2Y5z+OsPJ9Ev3KfJE6wD5809juztxPw8XFBYoeOE6TocHa4AADcP6IJN8Tn47+7zmDY0stFnYjSJeP77E9AZTJjQM9hm6ZB0sLtU2vnKpaX3XmmpumT+2Fh8tjsViTll+CMxt9EAg+U7U3EurwJBXq64fUhkq22vs5Ky2S6VVuPohWIAwIxhUYp/v2+d/jRGk9jkPm7xxtMorzFgcJQf5ozkQb4pdTMZ11gmA08dHKF4iAJgzmD75WQ2lu9OxYzhUU2WZ6UXVMr9M1kubVu/cF/sTs7H6awSHLDcCVfaj1EiDX9pasJ0SZUeP53IQkWNQb4Ad9WoWmVyp5dWg/mW6b2t4bO7hyPpUjnyymuQV1aD4xlFWHf4Ik5kFOOhb45g3ugYvDq1v/x4qVRaCu4BwN1jYvDpznNIyS3H5tM5mNQvDE+tPY4cy022F74/ic1PX20zSHUs3Zy1MFjh0BeJdLMvKdf6heGOs3k4nlEMNxcVHprQ3ebzeVopyy2s0OF/xzOxN6UA/cJ9MH1YJKICPHAmuxTPf38C8ZYbAHtT8vH5/BGI8HMs8GAwmlBUqUeQl2uHmvC6/aw5yHitAzdFJFfFBSPCzx2ZxVX4LT4HUy3l+QDw/ZEMJOaUwcdNgyevs53FCNT2ymwqk1HKVPRrMAjFGQcjFlY6Plla4qnVoGeoNxJzynA8oxg3+YY1eozRJOKJb4/Jn811fax/7lIgp6RKD1EUW+17ezitEG9Zbl5GB3ggvbAS9644hBdv6gV/D1ckZJciJbccsYGemNAzGGO6B2J/agFe//VMvd6sAyN9MSTKDyczS3A8oxhnL5Xh7KUyfLorFR6uavQK85YTRNQqAUFergj20iKvvAa/njInEwyN9sPJiyX46UQWuvi54aWb+8jPL+3fHO3JCJhLpncn5yPFypCRhf87jcScMgR5ueLfs4fwBq4CdTNKm1Mu3TPUG4JgzsDPL69BUBM3oz78IwUlVXr0DvPGjOHKz6c7E7VKgJuLCtV6k8Pl0gAwzJLJeCS9CCaT2OS1ZH55DV7532kAwKMTezjUj7qzYJDRCTjaf07yzA09ceRCEQ6cL8Qjq45iw6Pj6pUl7EvJx5JNiQCA2XYu3v2YydiI0cGejAAweWAXrDucgd3J+Xjh+5NY++CYep/rF3vO41h6Mby1Giy5Y4DNEyqp7C6nk2UyVuuNciZosI1skab4erhg3pgYfLzjHD7alozr+4TI7/H5/Ar8e7v57uHLt/at1+CdmiZlLB44by4H7RfuI2dwKdE1yBPuLmpU6Y245YPduKZXMCb0DMaASF94u7ngjzOX8OupHKhVApbcMcDhoHJn4WM5ycoorJKDvVKGj1KzR0Th+8MZOHGxBH9bfwqf3zNcXhsmk4gV+9KwdPNZVOmNcHdRY1AkT7hskYa/7ErOQ0ZhFQQBGN0twKHniLJkMtbtyag3mrDmYDre25qEogbH4+bc0b8cNGpVvf3C9GGReOr6nli+KxXLd6Xix6MXsei2fvKxUOp9WDeT39vNBfPHxuLDbSn4aHsKzl4qw+7kfLi5qODv4YrM4iq8tSmxXrCyLp3BhHhLxvSQaH+Htl/qyXihoBI1BmOjALsoinjvd3MW491jYu22i5CDjDoj9EYTdp7Nw7ojGdiWmAu95bzi9zOX8MEfyRgc5Yf4zBIYTCJ83V3gojYP0pny0V58PHcoavQm7EzKxaG0IkwZHI57GwSHT14sxpqD6UjIKkViThlqDCaMjA3Ay7f2ldvqtKeyaj0OpJqD8Nf2Vt6PUaJWCZg5PArv/Z6Ebw+ly0HGihoD/rXF/Jk8cV1co+BgU2xNl5bOfX0aZDJ2hJ6BOSXV2HgiC7cM7OJw4Lkp0mT5AAcmS9c1OMoPiTlleGLNMcSFeqFfuA+GxfhjQs8QhPposein09iacAmuGhX+e4/tYLn0/hpMIip1xnoJEUcuFGLp5rPoGuSJ/7uqW72b9qXVeiRklSKvrAa5ZTUoqdShTxcfjIsLgt5gwmOrj8FoEjFlcDjenj4QL/14Cj8ezcQbvybW+/d3J+fj6/0XoFYJ8rVYoKcrHr+2B24dFF4vSFRUocPulHzsPJuHnUl5yC+vkVs0NEUlAE9f3xOPTuyB9ccy8ey6E/h0ZyrCfd1xz9hYSz9f8/fK0Z6MQG11wrkmesl+dygDaw9nQBCAD+8c4nC/3c4qtM7n0JxrBE+tBjEBHkgrqMTZnDIE9ah/rEjLr8DX+9MAAH//Sx9ONLbB01WDar2uWS2U+oX7QqtRobhSj9T8cvQIadzeZOH/TqOwQofeYd54dGKP1thkp9MxzzjrWLZsGZYuXYrs7Gz069cP77//Pq666qr23qwOpblBRo1ahX/PHoJbPtyNxJwy/GNDPF6b2h9uLmqkF1TikdVHYTSJmDo4HPeNi7X5XNIJWkkVMxklzclkFAQBb04biBvf24XDF4qwYl+aXAZ2Lq8c/9pivrP6j1v7INzOyWJYJ+3J+NG2FFwoqESYjxvubEZm24LxXfHl3vM4cbEEe1LycVVcMERRxD82nILOYMJVcUG4rYUlgp2F1P9Naq02Y5hj2Z9qlYA5o6Lx+d7z9TIAAHMWl5Shdf9VXdGni/LgZWcjXYhlWhq4D4jwRX87Qw4a0qhVWDpjEG79cA+2JeZi/bFM3DE0EsczirF442n5Yml0twC8NW0gYiz9AqlpUpAxo7BK/rOSQEddUrl0emElMgorseNsLlbsS5MnhvYI8ZJ7oAHAjf0czwRrL0FeWrx4U2+s2n8BFTojUnLL5T6GUpCxR4N2IfeO64r/7jmP01mlcouF16YOQLivG+767wF8vf8Cbu4fhrFN9BY7k10KncEEPw8XxFoyRJUK9dHCW6tBWY0B5/Mr0Dus/r5oW2IuTl4sgYerWlHJodS0XmcwYcySP5BfXnteNSDCF5P6huJgWiH2pOTLJd439gvFq1P7Q28UsWDFISTmlGHGJ3/We97jGcUwiZDPKf44cwkPrzoKnaH+sJyDaYWY/NEe3DE0AmO7B1kCMdUI8HDFnSOjFffUlZRV67Fsxzn8eiobN/YLw4LxXRtNYrVmd3I+DCYR3YI80TWoefuUGcMj8cEfSdifWojz+RUI9dHiqbXHkVdWg+gAD8yzDH2zRwpgpRdWolpvrHdTvsRKT8aW3oAXRfOQI5VKkId1OOJERjHu/+ow8spq8NH2FLw7c1C9zMBzeeVyP1ilClpQLg0A04ZFYkvCJRRW6OS1+p2lnYqUNSgIwPuzBmNkV9s3Xtxd1HBRC9AbRZRU6eGp1aBSZ8DSzWexYl8aRBHYn1qIbw9l4Ob+YejbxQe7kvJxJL2oyQF/apWAQE9X5JbVoHuwJ964fQC0GjXemTEIvUK98e2hDIT6aNG3iy+6h3giMbsMO5JykVFYBVe1CveOj8WjE3s0mcXm7+mK2waF47ZB4TCZRJzJKZX3/4D5BlFBeQ3yymtQVm3A5EHhGBEbIL9n2SVV+NeWJCzaeBqhPlp5P+PhqpZvJDqih+X7dPhCEVJyy+XvwK6kPPxt/SkA5iBnU/tLalrdjNLmZDIC5hYiaQWV+HRXKvqH+8rBymq9EYs3nobeKOKaXsG4yoH+tJ2Rh1aNggrAS+v45+CqUWFQlB8Oni/E4bSiekHG8hoDvtl/Ab+cyoZaJeBfMwa1uNe1s+rQQca1a9fiqaeewrJlyzBu3Dh8+umnuPnmm5GQkIDoaJbFSc5ZUt3VzSgTCPFxw4d3DsGczw/g+yMX8cvJbIzpHogLBRUortRjYKQv3pw20G4JglQSwkzGWrXBX8d2PhF+7vjbLX3wt/WnsHRzIvzcXXA8oxhbEnJQYwlyzVSQIl/bk7GmVctI2kq13gitlXK+Kp0Rbi72S/2SLpXh013miaeLbuvXrDtYQV5azB4ZjS/3puGx1ccwLMYffu4u2JtSAK1Ghdem9u/w72VHUffA66pWYcrgCBuPbto/bu2LRyb2wO5k893//ecKkFVSLfehi/R3V1Tq1pk17BN258jmldj0DPXGk9fHYenms1j002lsP5sn9/T1dFXjpVv64K6R0cwoVSA20BOermpU6Mx9ucY5WCoNQA7kphdW4qq3t8s/D/B0xdM39MTsEVFXdImbWiVgYKQf/kwtwLH0IvQK8zYHXSwl+Q17Evt7umLu6Bgst9yImDU8CtMtNzbmjIrGqgPpeOGHk1jzf6PlLFCJFKwbHOXn8P5dEATEhXrhaHoxHlt9DEOj/dArzAd6owl5ZTXYkmAue7x7TKzNXoySutlY+eU6S3uOCEwbFlkvgJlZXIVfTmYhJtATk/qGytv9/cNj8dS3x/D7mVwEe2sxoWcwtBoVVh1Ix6s/J8BVo4KvuwueWXscBpOICT2DMXN4FPqG+8BVo8I7m8/ix2OZ+PGo+X91fbQ9BTOHR2H+uFgEedp+LSJE/HoqB+9uPSsHSpfvSsWKvWmYNiwCd46IxoAIX5v7C6kf48RmZDFKwv3cMaFnMLafzcN/tqcgMacU8ZmlcNWo8Prt/RW3dpCCq9sSczHitd9xqyVgNCzGXw4yNtzX+krTpZvIZDSaRGQVV+F0VikSskuRmlcObzcNgr20CPB0RWJOGXYm5cl9927qF4aXbumNmEBP6AwmbEvMxbbES4jw88CEXsEY2OC93HQqG09/dxzVevOQpJIqPRasPIwHr+6GyAAPOTNdJQDPTuqFhyd0V7TvLmrB4BcAGBEbgCP/uB4Xi8yvPT7TfEP3xMVipFtaP7z8l764ZUAXu88lCAJ83FxQUKHDf7anQIR5mI8UvLtjSARKqvT4IzEXv57KkUuQAfO5Q4SfO4K9tfB01eDQhUKk5lUgt6wGbi4qfDx3mLwWBUHAgxO648EmWh2IooiLRVXw1GoUl5CrLBPsHSmxfHRiD2SVVGP1gXQ8+e1xPH6tOXsqzNetWeekQ2P80DPUC0mXyjHr0z+x8r6REATg4W+OwGBJMHmMGVoOqZtR2pyejIC5P+y2xFzsSsrDLR/uxkd3DcGFgkq8/VsiskqqoRKAv93Sx/4TdXLSoC7vZgTgAWB4jD8Oni/Ein1puFBYiWAvLU5nlWJTfDYqLedtj17T3eEb9p1Jhw4yvvvuu1iwYAHuv/9+AMD777+PzZs34+OPP8aSJUvaeevan8kk4uOd5/COJbtNalTqqLE9gvDmHQPw7tYkXCqtkU/qgr21WD5vuKIpi37u5gNrw/KszkhvNOHrPy/gJ8vFt6va8YP/7JFR+PVUNvak5OPZdSfkn4d4axUFfc2PNR/sqvRGlNUYmn1XraVKKvWAUP/kO7+8BhuOZeL3M5eQU1KNvLIaVOiMiPBzx7ShEZg+LAqeWjU2HM/C90cu4ky2+YIg2EuLEB8tegR7oW+4D/qF+6J3F2/4uLnAZBLx9/WnoDeKuL5PaIuydh68ujvWH8tEcaVeXg+AuayKGVrK1R3wcn3fkGZnPgR4umLK4Ag5SFlYocOZ7FKcyyvHVXHB8HDt0Ieydld37bm7qFuUifvg1d3wW3wOTmWWYOOJLAgCMG1oJJ6b1KtZJVudlUoloE8XHxy+YO4DOMbBoS+A+XgQ7K1FXlkNNCoBQ2P8MbFXCO4aFd2syZYd0eBoc5DxeEYx7hwZjeySalTojNCohCb3xfdf1RXrj2Ui0t8di6f0k3/+0i19sONsHi4WVeGqt7ejR4gXrukZjAm9gjEiNqDZ/Rgl1/UJxdH0YqTklss9I+vy0mrwgMLBCS5qFR6/tgfSCioxZVA4JvQKbnJYVoSfOx64unHQw0urwWd3D0d2STW6WAIQoijC280Fn+w8h5c3xEMQzBnmUweHY+mMQfWe/91Zg3HP2Fh8vOMcKvVGBHtpEeTligPnC3E8oxhf77+Ar/dfcODdMQ/puXtMDH45lY1DaUVYczADaw5mIMDTFVfHBWFk10DEBnkgNtATYT5uUKkEmEwidlj6MV7XgiAjANw5Mhrbz+bh+yPmjLlAT1csv3sYhsUob1Fw26Bw5JRUY+2hDGQWV2HNwXSsOZgOL61G7o3u59F0ufTu5DzM/ORPiBBRXmNEXlkNCitq0EQyXSNajQp6owm/nc7BH4mXcF3vUBw4X1DvfPu935MQ4OmK7sGeECDAKIo4Ytm3TOwVjHdmDsa/tyXjy71pcjUAYC7JNYnA0s1nceB8Id6ZMQhZxVXYmZSHo+lFCPV2Q19Lm5M+XXzgpdW0OJMRMAftogI8EBXggZv6h+G5G3vJ5cSuahVu6t+4V6M1AZ6uKKjQYdWBdPlnXXzdsOSOAbiml/l7k5hTii/3pKGkSo9xcUG4pmdwoxsNgLn1xJ+p+egV5iO3QVD6WtqaIAj45239kFtajd/P5Mrl/s3pxwiY+yav+b/RuOfLg4jPLMXsz/bDzcV842ts90C8PX0Qbxg6qDUyGcf1CMKPj4zFI6uOIr2wErcv2yf/XYSfOxbd1k/xd7MzkwZGNSfZBDB/Dst2nENiTlmjQTzdgjxx58go3NeKvamdkSCKooJD3OWn0+ng4eGBdevW4fbbb5d//uSTT+L48ePYuXOnzd8vLS2Fr68vSkpK4OPjfGV0BeU1ePq7E/K0szuGRuC1qf1bdLEtiiLOXirDzrN5OJ1Vigeu7qY4Qv/hH8l4d2sS+oX7YELPzpvCLQLYHJ+D1HxzuVqvUG98dvdwRDtYfgUAF4sqcefy/RAEYELPYEzoGYKx3QMdmiQ2cNFmlFYbMOcyX3QaTSLO5VXgTHapXKIZ4eeOvuE+EEURO87myeXk1mhUgt3HSKIDPBDm64aD5wvh4arG1mcmtLj3UKXOgARLhsHpzFJ4uWnw4k29mRbvgO1nc3Hvl4cAAF/OH9GibBRqPr3RhLi/bwJgLllfOmNQi54v6VIZ7v3yEGICPfC3W/rwTm4zvfK/eHz15wVoVAJOLJzUrCmR5/LKcaGgAsNjA9rtRlJb2nI6Bw98fQS9Qr2x+emrsTMpD/d8cRA9Qrzw+zMTmvwday1k4jNLsHjjaRy5UFQvuCNNoqzSG7HyvpHNPofJKKzE6awSJGSVIulSOTy0agR7axHspcXY7kEO9aNtC6IoYvHGBKzYlwbAnN356pT+igMJoihif2ohlu1IwZ6UfCi5egj0dMWjE3tg7ugY+dh5KK0QK/amYWdSXpP9DV01KsQEeCDER4u9KQXw0mpw9OUbWnTs1RtNGPvmNuSV1SAuxAtfzB/R7MCQySTiwPlC/HD0IrYn5spBNwD46bFxGFinRcHRdPNkYmtc1AJ6hnqjbxcfxIV6oUpnQl55NfLLdOYMzF7BGNU1ABcKKvHaLwnYnVw7JT3EW4u/DOyCnJJq7EnOR1kT7+X8sbH4x1/6yBnNv8Vn4+/r4xHi44bpwyIxZXA4tp3Jxcv/i0eNwSQHn62JDfRAQbkOZTWGDnNM35pwCeuPXYS/hyuCvbUI93XHzQPC4O2E+0PAfG46+7MDOGHJvr5jaATenTm42c9XWq3HghWHcCjNHJTuHeaN7x4a45THk7Z2qbQao974AwCw9emr6w0nc1RptR4vfn8Sm+Jz4OmqxiMTe2DB+K6KEn8ImPf5AexOzsdfb+5td9haU0RRxNaES0jOLUdemXkoXYCnK6YOicDQaMcrHpyFI/G1Dpv+kZ+fD6PRiNDQ+tlIoaGhyMnJafT4mpoa1NTUTtEtLS1t821sT6//cga7kvLg5qLCP6f0V1Q+a48gCOgd5tOon5AS0t2bur2QOrMgL1c8c0MvzBwe2exytUh/D+x58doWbUdUgAdOZ5XWu8PbXjKLq+SAIwAMivLDHUMi0KeLD4K9tfB1d8GelHysO5yBPSnmPkwDI30xY1gkbuwXhhqDCXnlNcgpqUZiThkSskrlIGZ6YaVcZvPMDT1bpbm5h6sGw2MDMDzWsWEMVEtqDB/m44ar4tjXp724qFUI8tIiv7ymWX1KG+oZ6o29f23ZvonMWXNf/XkBw2L8mxVgBMwTQpvTq+1KMTjaD4B5cnN5jaF2srSNHnLW+lP3j/DFuofGoqRSj73n8rHjbC52JuXhUqn53FGjElo0sKg2M8t+mWd7EAQBCyf3RdcgT7ioVZg9MsqhCyVBEDCmeyDGdA+E0SRCSY6CWiU0+jdGxAZgRGwA9EYTjl4ows6kPCRkl+JCgbm3qM5gQnJuudx7c0LP4Bbf3HNRq/DBrMHYk5KPh67p3qIAikpV+z6YTCJOZ5ViZ1IuXDUqDGhww2VIlB9+eHhsvd7Ybq5qOQs5wMNV0TlirzBvfL1gFHaczcWfqQUY3TUQV8UFyb+rN5pwIqMYeWW110Fhvm6Nhhjd1L8LbuwXVu8zmTkiCgOjfPHIqqNIzauAt1aDcT2CMLpbgNw3MSG7FNkl1UirM2Sqi1/HyFy/oW8obuh75fSbbSkPVw2+uGc4pn28D2kFlYgJaFl1jY+bC766bxRe+vEk0gsr8Z85QxlgbKYgLy3cXdSoNhgVtcawxcfNBcvmDMWRC0WIDfJsctI0WSe1LmhuWwdBEDCpXxgm9bP/WGpah81kzMrKQkREBPbt24cxY8bIP3/99dfx9ddfIzGx/oSvRYsWYfHixY2ex1kzGfPLa/DEmmNYOLmf3Ay9PVXqDPhiz3kUVrBcOtRHi7tGRXeIu6gnMoqx8USWopKc1iQI5n43UjmzKJob6ydklaKixoAb+4fZTPfPLa1Gtd6kKAO0yFI6m5BdCpUg4J6xsZy41kGIooi1hzIwINKx3kPU+vanFiCvrAaTObSowzCaRHz9Zxom9App9lCLzmDcm9uQWVyF1fePwsaTWVhzMANPXNsDz0zq1eLnlio49iTno2uQZ72hGHT5GYwmZBZXIa2gEhcKKpBfrsOsEVGtcuOQbNMZTEgvrERMoEeT5fmFFTokZJXidFYJ/DxcMGsEe+O3p+ySKvzveBZmDo9S3AuS2t72s7kordI3qwc5tZ60/ApsScjB3NExbKnUihzJZOywQUZHy6WbymSMiopy2iAjERERkbN7dPVR/HIyG8/f2AvbE3Nx+EIRPrhzMC/iiIiIiC4TR4KMHba5mKurK4YNG4atW7fW+/nWrVsxduzYRo/XarXw8fGp9z8iIiIiunINsQxjOZZeJJfQxoW0fwUHERERETXWofNHn3nmGcybNw/Dhw/HmDFjsHz5cqSnp+Ohhx5q700jIiIiojY2xNKXcd+5AlTqjFAJQLdglpcTERERdUQdOsg4a9YsFBQU4J///Ceys7PRv39//Prrr4iJiWnvTSMiIiKiNtYv3BcuagGVOiMAIDrAgxM2iYiIiDqoDh1kBIBHHnkEjzzySHtvBhERERFdZm4uavTp4oOTF0sAAD1YKk1ERETUYXXYnoxERERERFJfRgDoEeLVfhtCRERERDYxyEhEREREHdZgS19GAIhjkJGIiIiow2KQkYiIiIg6rCFR/vJ/x4UyyEhERETUUXX4noxERERE1HnFBHpgSLQfiip06BnKnoxEREREHRWDjERERETUYQmCgB8eGgtBMP83EREREXVMDDISERERUYemUjG4SERERNTRsScjERERERERERERtQiDjERERERERERERNQiDDISERERERERERFRizDISERERERERERERC3CICMRERERERERERG1CIOMRERERERERERE1CIMMhIREREREREREVGLMMhIRERERERERERELcIgIxEREREREREREbUIg4xERERERERERETUIgwyEhERERERERERUYswyEhEREREREREREQtomnvDWgroigCAEpLS9t5S4iIiIiIiIiIiK48UlxNirPZ4rRBxrKyMgBAVFRUO28JERERERERERHRlausrAy+vr42HyOISkKRVyCTyYSsrCx4e3tDEIT23pxWUVpaiqioKGRkZMDHx6e9N4eo3XFNEFnH9UFkHdcHkTJcK0TWcX1QZyGKIsrKyhAeHg6VynbXRafNZFSpVIiMjGzvzWgTPj4+3IkR1cE1QWQd1weRdVwfRMpwrRBZx/VBnYG9DEYJB78QERERERERERFRizDISERERERERERERC3CIOMVRKvVYuHChdBqte29KUQdAtcEkXVcH0TWcX0QKcO1QmQd1wdRY047+IWIiIiIiIiIiIguD2YyEhERERERERERUYswyEhEREREREREREQtwiAjERERERERERERtQiDjERERERERERERNQiDDISERFdgaqrq9t7E4g6rMOHD3ONEBEREV1mDDJ2AIWFhcjPzwcAmEymdt4aovZ38eJFrF69Gn/++SeKi4vbe3OIOpTz589j0KBBeOONN9p7U4g6nNTUVEyZMgUjR47Ed999196bQ9RhZWRkYOPGjTh16hSMRiMAQBTFdt4qoo6B1+dEzccgYzv7+9//jt69e2P5PtHfqgAAF/pJREFU8uUAAJWKHwl1XqIo4sknn0Tfvn2xfPly3HDDDXjmmWeQnZ3d3ptG1O5EUcRDDz2Enj17omfPnnjiiSfae5OIOgxRFPHII48gLi4OgiDA19cXXl5e7b1ZRB3Sc889h969e+ODDz7A+PHj8fjjjyM1NRWCIDDQSJ0er8+JWoYrpp0UFxdjwYIF+P333xEdHY39+/fj0KFDAHgXkTqntLQ0XHvttThy5Ai2bNmCzZs347333sOhQ4eQkJDQ3ptH1K5SUlIQGBiIPXv24ODBg1i3bh2CgoLae7OIOoQNGzbA09MTR44cwb59+7Bhwwb06dMHmzZtAsDzKqK6vvjiC+zbtw+bN2/Gb7/9hv/+97+Ij4/HfffdBwAQBKGdt5CoffD6nKh1MMh4GdXdObm7uyMmJgYvvfQS3nnnHWRmZmL9+vXQ6/W8i0idRt3vucFgwNSpU/H5559j9OjR0Gq1mDp1KtRqNeLi4tpxK4naR9314eLigvDwcIwfPx5DhgzBvn378Oyzz+KNN97Ab7/9hrKysnbcUqLLr+76yMvLwzfffIMDBw5g1KhRqKqqQvfu3VFYWIjKykoGTahTk9aK9P8//PADunfvjvHjx0Oj0WDGjBkYPHgwdu3ahf/+97/1HkvUmfD6nKh1CCJXy2VRVVUFlUoFrVYLwHzwLi0tha+vLwBz2cL+/fvxt7/9DbfccgtEUeRJMTm1hmuiuroa1dXV8PPzAwBcunQJc+fORVZWFsaMGYPJkydjypQp7bjFRJdPw/VhMpmwYcMGTJ8+HZMmTUJiYiKGDx+OlJQU5Ofn47rrrsPKlSvbeauJLo+m1odUzmY0GqFWq/H0009j27ZtOHHiRL2/J+pMGq6V4uJizJkzB4MHD8arr74qr4sXXngBP/30EwoKCpCdnQ2NRtOem010WUjX29JxAwBKSkp4fU7UQjzjugxeeukljB8/Hrfeeis+/PBDlJaWQhAE+Pj4yI1kn3jiCYiiiA0bNiA/P593S8ipNbUm3Nzc5ABjcnIyYmNjodFo8MILL6CoqAgvvPACB11Qp9DU+lCpVJg4cSLmzZuH8vJy/PTTT1i1ahWOHz+OhQsX4sCBA/j444/be9OJ2lzD9VFWVgaVSiWfT0kXgNdffz3S0tKQnp7OACN1Sg3XSnFxMfz8/NCnTx9s2bIFr732GgoKCvDCCy9gxYoVWLhwIVxcXORsRiJn9u6778rXFVKAEQB8fX15fU7UQjzrakM6nQ4zZszATz/9hBdeeAHh4eH49NNPcddddwEwnwhLJ8bR0dGYOXMmjh49ip9//ln+e+7IyJnYWxOSuLg47N+/H5s2bcI999yD7777DpMnT8bPP/+Mqqqqdtp6orZlbX3Mnj0bAODv74+XXnoJ77//PgYMGAAXFxcAwLRp0xAXF4fjx4/LE0KJnI299SEFEutmNAYGBiIjI6PdtpmoPVhbK3feeScAYNGiRRg3bhy+/vpr9OzZE5s2bcLPP/+M2bNno3v37jzPIqd26NAhTJw4Ec899xx+/PFH/PnnnwDqT5BWqVQQRZHX50TNxCBjGzp37hxOnDiB999/H7NmzcLKlSuxfPlybNu2DUuXLm20g3rooYcQGhqKTZs24dSpU1i1ahUzt8ipOLImBg0aJP+3Wq1GSkoKAgICoNFoeHAnp2RtfWzfvh1Lly4FAPTu3RvDhw+Xb1KJooiAgAAkJiZCrVbXuxtP5EyUHj+kC8Xx48cjMzMTxcXF9X5O5OysrZVdu3bhzTffhJeXF95//31s374dO3bswKlTpzBy5EjU1NTg7Nmzcmk1kTPavHkzgoKC8MUXX8j/D9QGFhvi9TmR4xhkbENVVVVISUnBsGHDAJj7PowbNw6vvPIKlixZgpSUFACQsxm1Wi0eeOABHD58GBMnTsR9990HNze39nwJRK1K6ZpoaP/+/SgqKsKcOXPg4uLCfijklOytj+Tk5Ea/IwgCfvvtN/j7+2Pu3LmXe5OJLhtHzqkA882p0aNHY/v27fV+TuTsbK2Vt99+G0lJSQCAyMhIDBgwQA6sfPfdd+jWrRtuv/32dtt2orYifc/vvvtuPPPMM5g/fz4mTpyIU6dOYd26dfUeA5jPr3h9TtQ8PONqQyqVCn379sXq1avr/fzZZ5+Fn58fPv30UwDmkh6VSoVz587hxx9/xPnz5zFz5kwUFhbi2WefbY9NJ2oTSteEyWRCQkICdu7ciYcffhiTJk3C0KFDMX369PbYbKLLwpH1ER8fj+3bt+Ohhx7CnXfeieuuuw6jRo1qj80muiyUrg+DwQAA8PLyQnZ2NioqKqDX6y/79hK1F3trZfny5QDM1x8FBQXYsGEDHnzwQTz88MP4y1/+grCwMFaMkNOREhSio6MxZswYAMDMmTPRpUsXrF69GkVFRfX6+wLg9TlRMzHI2AL2DsAxMTGIi4vDnj17kJ2dDUEQYDAY4OLigsceewxr1qyByWSSy9s+/fRTeRLismXL4OnpeTleBlGraa01oVKpcPLkSSxduhSpqanYs2cP3nvvPbkHHdGVqDXXx9GjR/Hqq68iKSkJO3fuxJIlS1gqTVe01lofGo1GnhT68ssv4+mnn+axg5xKa15/mEwm7Nu3D6mpqdi7dy9efvllCILAihG6YikNkIuiiG7dumHy5MnIzs7GihUrADTOeuf1OZHjGGRsptzcXJSVlcl/rnvXQ7qL7u/vj8mTJyMxMRHfffcdAECj0QAwT67y9/dHRkaG/LtvvvkmMjIyMGDAgMv1MohaTWutiQsXLgAApkyZgo8++gibN2/GwIEDL9fLIGoTrb0+pk2bhs8++wzbtm2r17+U6ErUmudUQO2k0Hnz5qFnz56X5TUQXQ6ttVbS09MBAMHBwXjllVewdetWHkvoiqdkfUikQXnTp09H37598fPPP8ttaY4ePSo/jtfnRI5jkNFBBoMBCxYswMiRI3H99ddjzpw5KCgoqHfXQ6PRoLq6Gt9++y3uu+8+DB48GGvXrpX7AgHAxYsXERwcjJiYmEYTEYmuJK29Jrp27QoAcHd3R2xs7OV+OUStqq3Wh6enJ7p3737ZXw9Ra2qLcyoiZ9Taa6Xu+ZW3t/flfClErU7p+tDr9Vi5cqX8Z5PJBB8fH8yYMQMmkwmLFy/Gddddh+HDh6OoqAgAr8+JmoOrxgEGgwHz589HQkICVq5cidmzZ+PkyZOYOnUqzpw5Iz/uww8/REREBL799lsAwDPPPINu3brhpptuwiOPPIIHH3wQ77zzDmbNmgVAeVo3UUfDNUFkHdcHkXVcH0TKcK0QWefI+ggLC8PGjRsbBRD79euHjIwMrF69GiEhIcjOzoa/v3+7vB4ipyCSYunp6WJcXJz49ddfyz/Lzs4WIyIixMcff1wsLCwUv/zySzE6OlpctWqVaDQa5ceZTCbxjTfeEP/v//5PvOWWW8S9e/e2x0sgalVcE0TWcX0QWcf1QaQM1wqRdY6uD5PJVO/3//jjD9HLy0scPHiwePjw4cu9+UROiUFGBxw7dkx0d3cXk5OTRVEUxerqalEURfGjjz4S4+LixI0bN4omk0msqKio93sNd2ZEzoJrgsg6rg8i67g+iJThWiGyrrnrQ5Kfny+uXr36sm0vUWfAcmkrli9fjs8++wy7du2SfxYXF4ewsDB88803AGpTrB999FH4+vrihx9+QE1NDTw8POo9Fye0kTPgmiCyjuuDyDquDyJluFaIrGvN9QGYWwYEBgZi9uzZl+cFEHUSDDI2sGbNGoSGhmLFihVYtmwZpk+fjtdffx2AeQrVzJkzsXr1auTm5sLFxQXV1dUAgCeffBLr169vz00nahNcE0TWcX0QWcf1QaQM1wqRdW21PhiIJ2obDDLWsXr1arz11lv45z//iX379uGXX37BK6+8giVLlqC0tBQ+Pj64/vrr4efnh8WLFwMAtFotACAyMhJarRZJSUnt+RKIWhXXBJF1XB9E1nF9ECnDtUJkHdcH0ZWHQUbUTlfT6/UYNWoU7r77bgBAeHg4hgwZgoiICCQkJAAAxo8fj7vuugsrV67E+vXrodfrAQB79+5F3759MWDAgPZ5EUStiGuCyDquDyLruD6IlOFaIbKO64PoyqVp7w1oT0ePHkW3bt3g5+cHAJg6dSrmzp0LtVotP8bLywulpaXo1asXAMDNzQ0LFixAdnY27rnnHgwdOhQhISH4+eef8a9//QuCIEAURaZf0xWJa4LIOq4PIuu4PoiU4Vohso7rg+jK1ymDjD/88AOeeuopaLVa6PV63HPPPXj00UcRGhoKADCZTHLT2G3btqF79+7w9/eHTqeDq6srvL298dZbb2HEiBGIj4/HpUuXcPToUfTu3RsA+zvQlYdrgsg6rg8i67g+iJThWiGyjuuDyHkIopSL3EkcPnwY8+bNw0MPPYSJEydi7969WLhwIaZPn47XXnsNAQEBMJlMMJlM0Gg0uOOOOxAeHo6PPvqovTedqE1wTRBZx/VBZB3XB5EyXCtE1nF9EDmXTtOTUYqlHj58GOXl5bj33nsxcOBAPPzww1i4cCGOHTuGZcuWAQBUKhVUKhVEUcTJkydx8803AwCSkpIwe/ZsZGRktNvrIGotXBNE1nF9EFnH9UGkDNcKkXVcH0TOqdMEGaUU6fPnz6Nnz57QaGorxefPn49hw4Zh06ZNOH36NADzjuzQoUPw8PDA0KFD8dRTT2HgwIEoKChASEhIu7wGotbENUFkHdcHkXVcH0TKcK0QWcf1QeScnDbIuHXrVjzxxBP44IMPcPDgQfnn48aNw759+5CTkwMAMBqN8PT0xJQpUyAIArZs2SI/9tdff0V8fDx69eqFrVu3Yu/evdiyZQu0Wu1lfz1ELcU1QWQd1weRdVwfRMpwrRBZx/VB1Dk4XZAxOzsbkydPxty5c1FYWIjPP/8ckyZNkndkkyZNQmxsLN566y0AtXdQbrjhBqhUKqSkpMjP5eLigqCgIKxYsQKnT5/GsGHDLv8LImohrgki67g+iKzj+iBShmuFyDquD6JORnQiFRUV4j333CPOmjVLTE1NlX8+YsQIcf78+aIoiqLBYBC/+uorUaVSiXv37q33+3PmzBGvueYa+c+5ubmXZ8OJ2gjXBJF1XB9E1nF9ECnDtUJkHdcHUefjVJmMHh4e0Gq1mD9/Prp27QqDwQAAuPXWW3HmzBkAgFqtxsyZMzFlyhTcf//92LlzJ0RRRE5ODpKTkzF37lz5+YKDg9vldRC1Fq4JIuu4Pois4/ogUoZrhcg6rg+izkcQRctYJyeh1+vh4uICwDyxShAEzJs3D+7u7li+fLn8s+rqatx8881ISEjA4MGDER8fj+joaHz33XeIiopq51dB1Hq4Jois4/ogso7rg0gZrhUi67g+iDoXpwsyNuXqq6/Gfffdh/nz50MURZhMJqjValy6dAknT57EoUOHEBsbi7vuuqu9N5XosuCaILKO64PIOq4PImW4Vois4/ogcl5OH2RMTU3F2LFj8csvv8iNYXU6HVxdXdt5y4jaB9cEkXVcH0TWcX0QKcO1QmQd1weRc3Oqnox1SbHTPXv2wMvLS96BLV68GE8++SRyc3Pbc/OILjuuCSLruD6IrOP6IFKGa4XIOq4Pos5B094b0FYEQQAAHDx4ENOmTcPWrVvxwAMPoLKyEl9//TVCQkLaeQuJLi+uCSLruD6IrOP6IFKGa4XIOq4Pos7Bqculq6urMWDAAJw7dw6urq5YvHgxXnzxxfbeLKJ2wzVBZB3XB5F1XB9EynCtEFnH9UHk/Jw6yAgAN9xwA+Li4vDuu+/Czc2tvTeHqN1xTRBZx/VBZB3XB5EyXCtE1nF9EDk3pw8yGo1GqNXq9t4Mog6Da4LIOq4PIuu4PoiU4Vohso7rg8i5OX2QkYiIiIiIiIiIiNqW006XJiIiIiIiIiIiosuDQUYiIiIiIiIiIiJqEQYZiYiIiIiIiIiIqEUYZCQiIiIiIiIiIqIWYZCRiIiIiIiIiIiIWoRBRiIiIiIiIiIiImoRBhmJiIiIyK5rrrkGTz31VHtvBhERERF1UAwyEhEREVGr2rFjBwRBQHFxsUO/l5aWBkEQ5P/5+vpi9OjR2LhxY9tsKBERERG1GgYZiYiIiKhD+f3335GdnY0DBw5g5MiRmDZtGuLj49t7s4iIiIjIBgYZiYiIiKieiooK3H333fDy8kKXLl3wzjvv1Pv7b775BsOHD4e3tzfCwsJw1113ITc3F4A5G3HixIkAAH9/fwiCgPnz5wMARFHE22+/jW7dusHd3R2DBg3C999/3+jfDwwMRFhYGHr37o3XX38der0e27dvl/8+MzMTs2bNgr+/PwIDAzFlyhSkpaXJfz9//nxMnToVixcvRkhICHx8fPDggw9Cp9O18jtFRERERBIGGYmIiIionueffx7bt2/H+vXrsWXLFuzYsQNHjhyR/16n0+HVV1/FiRMnsGHDBpw/f14OJEZFReGHH34AAJw9exbZ2dn44IMPAAD/+Mc/8OWXX+Ljjz/G6dOn8fTTT2Pu3LnYuXNnk9uh1+vx2WefAQBcXFwAAJWVlZg4cSK8vLywa9cu7NmzB15eXrjpppvqBRH/+OMPnDlzBtu3b8eaNWuwfv16LF68uNXfKyIiIiIyE0RRFNt7I4iIiIioYygvL0dgYCC++uorzJo1CwBQWFiIyMhIPPDAA3j//fcb/c6hQ4cwcuRIlJWVwcvLCzt27MDEiRNRVFQEPz8/AObsyKCgIGzbtg1jxoyRf/f+++9HZWUlVq9ejbS0NHTt2hXu7u5QqVSoqqqCyWRCbGwsjhw5goCAAHzxxRd4++23cebMGQiCAMAc9PTz88OGDRswadIkzJ8/Hxs3bkRGRgY8PDwAAJ988gmef/55lJSUQKXifXYiIiKi1qZp7w0gIiIioo7j3Llz0Ol09QKBAQEB6NWrl/znY8eOYdGiRTh+/DgKCwthMpkAAOnp6ejbt2+Tz5uQkIDq6mrccMMN9X6u0+kwZMiQej9bu3YtevfujaSkJDz11FP45JNPEBAQAAA4cuQIUlJS4O3tXe93qqurce7cOfnPgwYNkgOMADBmzBiUl5cjIyMDMTExjrwlRERERKQAg4xEREREJLNX5FJRUYFJkyZh0qRJ+OabbxAcHIz09HTceOONNnseSoHIX375BREREfX+TqvV1vtzVFQU4uLiEBcXBy8vL0ybNg0JCQkICQmByWTCsGHDsGrVqkb/RnBwsN3XJ2U/EhEREVHrYpCRiIiIiGQ9evSAi4sL9u/fj+joaABAUVERkpKSMGHCBCQmJiI/Px9vvvkmoqKiAACHDx+u9xyurq4AAKPRKP+sb9++0Gq1SE9Px4QJExRvz4QJE9C/f3+8/vrr+OCDDzB06FCsXbtWHuhizYkTJ1BVVQV3d3cAwP79++Hl5YXIyEjF/zYRERERKceGNEREREQk8/LywoIFC/D888/jjz/+QHx8PObPny/3MYyOjoarqyv+/e9/IzU1FT/99BNeffXVes8RExMDQRDw888/Iy8vD+Xl5fD29sZzzz2Hp59+GitXrsS5c+dw7Ngx/Oc//8HKlSttbtOzzz6LTz/9FJmZmZgzZw6CgoIwZcoU7N69G+fPn8fOnTvx5JNP4uLFi/Lv6HQ6LFiwAAkJCdi0aRMWLlyIxx57jP0YiYiIiNoIz7KIiIiIqJ6lS5fi6quvxm233Ybrr78e48ePx7BhwwCYS5JXrFiBdevWoW/fvnjzzTfxr3/9q97vR0REYPHixfjrX/+K0NBQPPbYYwCAV199Fa+88gqWLFmCPn364MYbb8TGjRvRtWtXm9tz6623IjY2Fq+//jo8PDywa9cuREdH44477kCfPn1w3333oaqqql5m43XXXYe4uDhcffXVmDlzJiZPnoxFixa17htFRERERDJOlyYiIiIipzJ//nwUFxdjw4YN7b0pRERERJ0GMxmJiIiIiIiIiIioRRhkJCIiIiIiIiIiohZhuTQRERERERERERG1CDMZiYiIiIiIiIiIqEUYZCQiIiIiIiIiIqIWYZCRiIiIiIiIiIiIWoRBRiIiIiIiIiIiImoRBhmJiIiIiIiIiIioRRhkJCIiIiIiIiIiohZhkJGIiIiIiIiIiIhahEFGIiIiIiIiIiIiahEGGYmIiIiIiIiIiKhF/h9DxRPS/CbaEwAAAABJRU5ErkJggg==", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "mycountry = data[data.countriesAndTerritories=='Italy']\n", "mycountry.set_index('dateRep').deaths.plot(figsize=(16,5))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.16" } }, "nbformat": 4, "nbformat_minor": 4 }