{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Covid-19 Testing Importance\n",
"\n",
"## Introduction\n",
"\n",
"I believe that testing is one of the most crucial parts of dealing with an epidemic virus. Testing helps us identify and isolate positive cases. The more tests you perform, the faster you isolate the case preventing them from coming into contact with others, **slowing the rate of transmission**. \n",
"\n",
"This will be performed by \"merging\" the information of two data sources:\n",
"* [Our World In Data Covid-19 Tests](https://ourworldindata.org/coronavirus-testing-source-data) for the number of tests of each country\n",
"* [John Hopkins Datasets](https://github.com/CSSEGISandData/COVID-19/tree/master/csse_covid_19_data/csse_covid_19_time_series) for the cases, recovered and deaths of each country \n",
" \n",
"**Date this notebook was written: 23/3/2020** \n",
" \n",
"**Disclaimer**: *In any way I do not want to point my finger on the governments and people of countries. It is not possible to know what were the reasons and the circumstances that lead to a lack of testing. My only target is to see if the data suggests that testing has a major role on this specific epidemic.*"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"ExecuteTime": {
"end_time": "2020-03-24T10:27:21.299557Z",
"start_time": "2020-03-24T10:27:20.334221Z"
}
},
"outputs": [],
"source": [
"import requests\n",
"import re\n",
"\n",
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"from scipy.stats import spearmanr\n",
"\n",
"from bs4 import BeautifulSoup"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Data sources\n",
" \n",
"Link to the created dataset: https://github.com/MikeXydas/Weekend-EDAs/blob/master/datasets/covid_testing_importance.csv \n",
"\n",
"The first thing we want to find is **how many tests** have been performed on each country. The data will be extracted from this page: https://ourworldindata.org/coronavirus-testing-source-data . You may observe that the dates of last report are not the same for each country. This will be taken into account."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"ExecuteTime": {
"end_time": "2020-03-24T10:28:13.689158Z",
"start_time": "2020-03-24T10:28:13.118859Z"
},
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<tr><td>Canada</td><td></td><td></td><td></td><td></td><td>An aggregate figure for Canada is not provided given that the extent to which double-counting between the provincial labs and the national lab (NML) is unclear. See province level data and that for NML above. No figures have yet been found for Nunavut, Manitoba, Yukon and Newfoundland and Labrador provinces (collectively ~5% of population).</td></tr>\n",
"<tr><td>Kuwait</td><td></td><td>17 Mar 2020</td><td><a href=\"https://drive.google.com/file/d/1pVBq-c4HLeUis_BS58xT_jJTJZni2JfR/view?usp=sharing\" rel=\"noreferrer noopener\" target=\"_blank\">Communication from International Press Office at the Ministry of Information in the State of Kuwait, 17 March 2020.</a></td><td>17 Mar 2020</td><td>In an earlier version of this dataset we reported an estimate of 120,000 tests based on an official letter sent to us by the Ministry of Information. After this, they sent a second email correcting their estimate to 27,000, and then a further correction to 20,000. Since no figure is substantiated in a public statement, we have decided to not publish the numbers. We will revise this once the numbers are made public.</td></tr>\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Tests</th>\n",
" <th>Date</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Country</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Armenia</th>\n",
" <td>813</td>\n",
" <td>2020-03-18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Australia</th>\n",
" <td>113615</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Austria</th>\n",
" <td>15613</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Bahrain</th>\n",
" <td>18645</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Belarus</th>\n",
" <td>16000</td>\n",
" <td>2020-03-16</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Belgium</th>\n",
" <td>18360</td>\n",
" <td>2020-03-18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Brazil</th>\n",
" <td>2927</td>\n",
" <td>2020-03-13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>China</th>\n",
" <td>320000</td>\n",
" <td>2020-02-24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Colombia</th>\n",
" <td>4103</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Costa Rica</th>\n",
" <td>1039</td>\n",
" <td>2020-03-19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Croatia</th>\n",
" <td>1264</td>\n",
" <td>2020-03-19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Czechia</th>\n",
" <td>11619</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Denmark</th>\n",
" <td>10730</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Estonia</th>\n",
" <td>2504</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Finland</th>\n",
" <td>3000</td>\n",
" <td>2020-03-19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>France</th>\n",
" <td>36747</td>\n",
" <td>2020-03-15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Germany</th>\n",
" <td>167000</td>\n",
" <td>2020-03-15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Hungary</th>\n",
" <td>3007</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Iceland</th>\n",
" <td>9189</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>India</th>\n",
" <td>14514</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Indonesia</th>\n",
" <td>2028</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Iran</th>\n",
" <td>80000</td>\n",
" <td>2020-03-14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ireland</th>\n",
" <td>6600</td>\n",
" <td>2020-03-17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Israel</th>\n",
" <td>10864</td>\n",
" <td>2020-03-18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Italy</th>\n",
" <td>206886</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Japan</th>\n",
" <td>14901</td>\n",
" <td>2020-03-19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Kyrgyzstan</th>\n",
" <td>1545</td>\n",
" <td>2020-03-13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Latvia</th>\n",
" <td>3205</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Lithuania</th>\n",
" <td>1154</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Malaysia</th>\n",
" <td>13876</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Malta</th>\n",
" <td>889</td>\n",
" <td>2020-03-13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Mexico</th>\n",
" <td>278</td>\n",
" <td>2020-03-10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Netherlands</th>\n",
" <td>6000</td>\n",
" <td>2020-03-07</td>\n",
" </tr>\n",
" <tr>\n",
" <th>New Zealand</th>\n",
" <td>584</td>\n",
" <td>2020-03-17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Norway</th>\n",
" <td>43735</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Pakistan</th>\n",
" <td>1979</td>\n",
" <td>2020-03-19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Panama</th>\n",
" <td>1455</td>\n",
" <td>2020-03-18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Philippines</th>\n",
" <td>1269</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Poland</th>\n",
" <td>13072</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Qatar</th>\n",
" <td>8400</td>\n",
" <td>2020-03-17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Romania</th>\n",
" <td>8284</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Russia</th>\n",
" <td>143519</td>\n",
" <td>2020-03-19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Slovakia</th>\n",
" <td>2707</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Slovenia</th>\n",
" <td>9860</td>\n",
" <td>2020-03-19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>South Africa</th>\n",
" <td>6438</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Korea, South</th>\n",
" <td>316664</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Spain</th>\n",
" <td>30000</td>\n",
" <td>2020-03-18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Sweden</th>\n",
" <td>14300</td>\n",
" <td>2020-03-17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Switzerland</th>\n",
" <td>4000</td>\n",
" <td>2020-03-07</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Taiwan*</th>\n",
" <td>21376</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Thailand</th>\n",
" <td>7084</td>\n",
" <td>2020-03-17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Turkey</th>\n",
" <td>2900</td>\n",
" <td>2020-03-10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ukraine</th>\n",
" <td>316</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>United Arab Emirates</th>\n",
" <td>125000</td>\n",
" <td>2020-03-16</td>\n",
" </tr>\n",
" <tr>\n",
" <th>United Kingdom</th>\n",
" <td>64621</td>\n",
" <td>2020-03-19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>US</th>\n",
" <td>103945</td>\n",
" <td>2020-03-19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Vietnam</th>\n",
" <td>15637</td>\n",
" <td>2020-03-20</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Tests Date\n",
"Country \n",
"Armenia 813 2020-03-18\n",
"Australia 113615 2020-03-20\n",
"Austria 15613 2020-03-20\n",
"Bahrain 18645 2020-03-20\n",
"Belarus 16000 2020-03-16\n",
"Belgium 18360 2020-03-18\n",
"Brazil 2927 2020-03-13\n",
"China 320000 2020-02-24\n",
"Colombia 4103 2020-03-20\n",
"Costa Rica 1039 2020-03-19\n",
"Croatia 1264 2020-03-19\n",
"Czechia 11619 2020-03-20\n",
"Denmark 10730 2020-03-20\n",
"Estonia 2504 2020-03-20\n",
"Finland 3000 2020-03-19\n",
"France 36747 2020-03-15\n",
"Germany 167000 2020-03-15\n",
"Hungary 3007 2020-03-20\n",
"Iceland 9189 2020-03-20\n",
"India 14514 2020-03-20\n",
"Indonesia 2028 2020-03-20\n",
"Iran 80000 2020-03-14\n",
"Ireland 6600 2020-03-17\n",
"Israel 10864 2020-03-18\n",
"Italy 206886 2020-03-20\n",
"Japan 14901 2020-03-19\n",
"Kyrgyzstan 1545 2020-03-13\n",
"Latvia 3205 2020-03-20\n",
"Lithuania 1154 2020-03-20\n",
"Malaysia 13876 2020-03-20\n",
"Malta 889 2020-03-13\n",
"Mexico 278 2020-03-10\n",
"Netherlands 6000 2020-03-07\n",
"New Zealand 584 2020-03-17\n",
"Norway 43735 2020-03-20\n",
"Pakistan 1979 2020-03-19\n",
"Panama 1455 2020-03-18\n",
"Philippines 1269 2020-03-20\n",
"Poland 13072 2020-03-20\n",
"Qatar 8400 2020-03-17\n",
"Romania 8284 2020-03-20\n",
"Russia 143519 2020-03-19\n",
"Slovakia 2707 2020-03-20\n",
"Slovenia 9860 2020-03-19\n",
"South Africa 6438 2020-03-20\n",
"Korea, South 316664 2020-03-20\n",
"Spain 30000 2020-03-18\n",
"Sweden 14300 2020-03-17\n",
"Switzerland 4000 2020-03-07\n",
"Taiwan* 21376 2020-03-20\n",
"Thailand 7084 2020-03-17\n",
"Turkey 2900 2020-03-10\n",
"Ukraine 316 2020-03-20\n",
"United Arab Emirates 125000 2020-03-16\n",
"United Kingdom 64621 2020-03-19\n",
"US 103945 2020-03-19\n",
"Vietnam 15637 2020-03-20"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"response = requests.get('https://ourworldindata.org/coronavirus-testing-source-data')\n",
"soup = BeautifulSoup(response.content)\n",
"\n",
"table_soup = soup.find(\"div\", {\"class\": \"tableContainer\"}).findAll(\"tr\")[1:] # skip the headers\n",
"\n",
"# RegEx to extract the country name, number of test, date\n",
"reg = re.compile(\"<tr><td>(.+)<\\/td><td>([\\d,]+)<\\/td><td>([\\w\\s]+)<\\/td><td>.*<\\/td><td>.*<\\/td><\\/tr>\")\n",
"testing_data = []\n",
"for row in table_soup:\n",
" reg_res = reg.match(str(row))\n",
" if reg_res is not None:\n",
" testing_data.append(reg_res.groups())\n",
" else:\n",
" # Print the rows that failed to be parsed\n",
" print(row)\n",
" \n",
"\n",
"# Create the dataframe\n",
"testing_df = pd.DataFrame(testing_data, columns=[\"Country\", \"Tests\", \"Date\"])\n",
"testing_df['Tests'] = testing_df['Tests'].str.replace(',','').astype(int) # Transform the x,xxx string to integers\n",
"testing_df['Date'] = pd.to_datetime(testing_df['Date']) # Cast Date from string to date type\n",
"\n",
"# Set country name as index of dataframe\n",
"testing_df = testing_df.set_index('Country', drop=False)\n",
"\n",
"# For Canada and Australia we have info about specific regions\n",
"# Since on this notebook we will examine country response we merge them\n",
"\n",
"# Australia, dropping all the province info and keeping the aggregated \"Australia\"\n",
"testing_df = testing_df[~testing_df.Country.str.contains(\"Australia –\")]\n",
"\n",
"# Canada\n",
"testing_df = testing_df[~testing_df.Country.str.contains(\"Canada –\")]\n",
"\n",
"# Usa has two trackers I will keep the most recent one\n",
"testing_df = testing_df.drop('United States – CDC samples tested')\n",
"\n",
"testing_df = testing_df.drop(\"Hong Kong\")\n",
"\n",
"# We rename some countries so as to have the expected country name with the John Hopkins dataset\n",
"testing_df = testing_df.rename({\n",
" \"China – Guangdong\": \"China\",\n",
" \"United States\": \"US\",\n",
" \"Czech Republic\": \"Czechia\",\n",
" \"South Korea\": \"Korea, South\",\n",
" \"Taiwan\": \"Taiwan*\",\n",
" \"Faeroe Islands\":\"Faroe Islands\"\n",
"})\n",
"\n",
"# Drop Palestine since it is not included on the John Hopkins dataset\n",
"testing_df = testing_df.drop(\"Palestine\")\n",
"\n",
"# Drop Faroe Islands since they are merged with Denmark\n",
"testing_df = testing_df.drop(\"Faroe Islands\")\n",
"\n",
"testing_df = testing_df.drop('Country', axis=1)\n",
"\n",
"display(testing_df)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Next we must find info of confirmed cases, recovered cases, deaths for each country above. \n",
"The dataset used will be the [John Hopkins one](https://github.com/CSSEGISandData/COVID19/blob/master/csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Confirmed.csv).\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"ExecuteTime": {
"end_time": "2020-03-24T10:28:23.557039Z",
"start_time": "2020-03-24T10:28:17.137846Z"
},
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Tests</th>\n",
" <th>Date</th>\n",
" <th>Confirmed</th>\n",
" <th>Recovered</th>\n",
" <th>Deaths</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Country</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Armenia</th>\n",
" <td>813</td>\n",
" <td>2020-03-18</td>\n",
" <td>84.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Australia</th>\n",
" <td>113615</td>\n",
" <td>2020-03-20</td>\n",
" <td>791.0</td>\n",
" <td>26.0</td>\n",
" <td>7.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Austria</th>\n",
" <td>15613</td>\n",
" <td>2020-03-20</td>\n",
" <td>2388.0</td>\n",
" <td>9.0</td>\n",
" <td>6.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Bahrain</th>\n",
" <td>18645</td>\n",
" <td>2020-03-20</td>\n",
" <td>285.0</td>\n",
" <td>100.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Belarus</th>\n",
" <td>16000</td>\n",
" <td>2020-03-16</td>\n",
" <td>36.0</td>\n",
" <td>3.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Belgium</th>\n",
" <td>18360</td>\n",
" <td>2020-03-18</td>\n",
" <td>1486.0</td>\n",
" <td>31.0</td>\n",
" <td>14.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Brazil</th>\n",
" <td>2927</td>\n",
" <td>2020-03-13</td>\n",
" <td>151.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>China</th>\n",
" <td>320000</td>\n",
" <td>2020-02-24</td>\n",
" <td>77241.0</td>\n",
" <td>25015.0</td>\n",
" <td>2595.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Colombia</th>\n",
" <td>4103</td>\n",
" <td>2020-03-20</td>\n",
" <td>128.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Costa Rica</th>\n",
" <td>1039</td>\n",
" <td>2020-03-19</td>\n",
" <td>69.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Croatia</th>\n",
" <td>1264</td>\n",
" <td>2020-03-19</td>\n",
" <td>105.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Czechia</th>\n",
" <td>11619</td>\n",
" <td>2020-03-20</td>\n",
" <td>833.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Denmark</th>\n",
" <td>10730</td>\n",
" <td>2020-03-20</td>\n",
" <td>1337.0</td>\n",
" <td>1.0</td>\n",
" <td>9.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Estonia</th>\n",
" <td>2504</td>\n",
" <td>2020-03-20</td>\n",
" <td>283.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Finland</th>\n",
" <td>3000</td>\n",
" <td>2020-03-19</td>\n",
" <td>400.0</td>\n",
" <td>10.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>France</th>\n",
" <td>36747</td>\n",
" <td>2020-03-15</td>\n",
" <td>4523.0</td>\n",
" <td>12.0</td>\n",
" <td>91.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Germany</th>\n",
" <td>167000</td>\n",
" <td>2020-03-15</td>\n",
" <td>5795.0</td>\n",
" <td>46.0</td>\n",
" <td>11.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Hungary</th>\n",
" <td>3007</td>\n",
" <td>2020-03-20</td>\n",
" <td>85.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Iceland</th>\n",
" <td>9189</td>\n",
" <td>2020-03-20</td>\n",
" <td>409.0</td>\n",
" <td>5.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>India</th>\n",
" <td>14514</td>\n",
" <td>2020-03-20</td>\n",
" <td>244.0</td>\n",
" <td>20.0</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Indonesia</th>\n",
" <td>2028</td>\n",
" <td>2020-03-20</td>\n",
" <td>369.0</td>\n",
" <td>15.0</td>\n",
" <td>32.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Iran</th>\n",
" <td>80000</td>\n",
" <td>2020-03-14</td>\n",
" <td>12729.0</td>\n",
" <td>2959.0</td>\n",
" <td>611.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ireland</th>\n",
" <td>6600</td>\n",
" <td>2020-03-17</td>\n",
" <td>223.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Israel</th>\n",
" <td>10864</td>\n",
" <td>2020-03-18</td>\n",
" <td>433.0</td>\n",
" <td>11.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Italy</th>\n",
" <td>206886</td>\n",
" <td>2020-03-20</td>\n",
" <td>47021.0</td>\n",
" <td>4440.0</td>\n",
" <td>4032.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Japan</th>\n",
" <td>14901</td>\n",
" <td>2020-03-19</td>\n",
" <td>924.0</td>\n",
" <td>150.0</td>\n",
" <td>29.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Kyrgyzstan</th>\n",
" <td>1545</td>\n",
" <td>2020-03-13</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Latvia</th>\n",
" <td>3205</td>\n",
" <td>2020-03-20</td>\n",
" <td>111.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Lithuania</th>\n",
" <td>1154</td>\n",
" <td>2020-03-20</td>\n",
" <td>49.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Malaysia</th>\n",
" <td>13876</td>\n",
" <td>2020-03-20</td>\n",
" <td>1030.0</td>\n",
" <td>87.0</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Malta</th>\n",
" <td>889</td>\n",
" <td>2020-03-13</td>\n",
" <td>12.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Mexico</th>\n",
" <td>278</td>\n",
" <td>2020-03-10</td>\n",
" <td>7.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Netherlands</th>\n",
" <td>6000</td>\n",
" <td>2020-03-07</td>\n",
" <td>188.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>New Zealand</th>\n",
" <td>584</td>\n",
" <td>2020-03-17</td>\n",
" <td>12.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Norway</th>\n",
" <td>43735</td>\n",
" <td>2020-03-20</td>\n",
" <td>1914.0</td>\n",
" <td>1.0</td>\n",
" <td>7.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Pakistan</th>\n",
" <td>1979</td>\n",
" <td>2020-03-19</td>\n",
" <td>454.0</td>\n",
" <td>13.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Panama</th>\n",
" <td>1455</td>\n",
" <td>2020-03-18</td>\n",
" <td>86.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Philippines</th>\n",
" <td>1269</td>\n",
" <td>2020-03-20</td>\n",
" <td>230.0</td>\n",
" <td>8.0</td>\n",
" <td>18.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Poland</th>\n",
" <td>13072</td>\n",
" <td>2020-03-20</td>\n",
" <td>425.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Qatar</th>\n",
" <td>8400</td>\n",
" <td>2020-03-17</td>\n",
" <td>439.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Romania</th>\n",
" <td>8284</td>\n",
" <td>2020-03-20</td>\n",
" <td>308.0</td>\n",
" <td>25.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Russia</th>\n",
" <td>143519</td>\n",
" <td>2020-03-19</td>\n",
" <td>199.0</td>\n",
" <td>9.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Slovakia</th>\n",
" <td>2707</td>\n",
" <td>2020-03-20</td>\n",
" <td>137.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Slovenia</th>\n",
" <td>9860</td>\n",
" <td>2020-03-19</td>\n",
" <td>286.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>South Africa</th>\n",
" <td>6438</td>\n",
" <td>2020-03-20</td>\n",
" <td>202.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Korea, South</th>\n",
" <td>316664</td>\n",
" <td>2020-03-20</td>\n",
" <td>8652.0</td>\n",
" <td>1540.0</td>\n",
" <td>94.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Spain</th>\n",
" <td>30000</td>\n",
" <td>2020-03-18</td>\n",
" <td>13910.0</td>\n",
" <td>1081.0</td>\n",
" <td>623.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Sweden</th>\n",
" <td>14300</td>\n",
" <td>2020-03-17</td>\n",
" <td>1190.0</td>\n",
" <td>1.0</td>\n",
" <td>7.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Switzerland</th>\n",
" <td>4000</td>\n",
" <td>2020-03-07</td>\n",
" <td>268.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Taiwan*</th>\n",
" <td>21376</td>\n",
" <td>2020-03-20</td>\n",
" <td>135.0</td>\n",
" <td>26.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Thailand</th>\n",
" <td>7084</td>\n",
" <td>2020-03-17</td>\n",
" <td>177.0</td>\n",
" <td>41.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Turkey</th>\n",
" <td>2900</td>\n",
" <td>2020-03-10</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ukraine</th>\n",
" <td>316</td>\n",
" <td>2020-03-20</td>\n",
" <td>29.0</td>\n",
" <td>0.0</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>United Arab Emirates</th>\n",
" <td>125000</td>\n",
" <td>2020-03-16</td>\n",
" <td>98.0</td>\n",
" <td>23.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>United Kingdom</th>\n",
" <td>64621</td>\n",
" <td>2020-03-19</td>\n",
" <td>2716.0</td>\n",
" <td>67.0</td>\n",
" <td>138.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>US</th>\n",
" <td>103945</td>\n",
" <td>2020-03-19</td>\n",
" <td>13677.0</td>\n",
" <td>0.0</td>\n",
" <td>200.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Vietnam</th>\n",
" <td>15637</td>\n",
" <td>2020-03-20</td>\n",
" <td>91.0</td>\n",
" <td>16.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Tests Date Confirmed Recovered Deaths\n",
"Country \n",
"Armenia 813 2020-03-18 84.0 1.0 0.0\n",
"Australia 113615 2020-03-20 791.0 26.0 7.0\n",
"Austria 15613 2020-03-20 2388.0 9.0 6.0\n",
"Bahrain 18645 2020-03-20 285.0 100.0 1.0\n",
"Belarus 16000 2020-03-16 36.0 3.0 0.0\n",
"Belgium 18360 2020-03-18 1486.0 31.0 14.0\n",
"Brazil 2927 2020-03-13 151.0 0.0 0.0\n",
"China 320000 2020-02-24 77241.0 25015.0 2595.0\n",
"Colombia 4103 2020-03-20 128.0 1.0 0.0\n",
"Costa Rica 1039 2020-03-19 69.0 0.0 1.0\n",
"Croatia 1264 2020-03-19 105.0 5.0 1.0\n",
"Czechia 11619 2020-03-20 833.0 4.0 0.0\n",
"Denmark 10730 2020-03-20 1337.0 1.0 9.0\n",
"Estonia 2504 2020-03-20 283.0 1.0 0.0\n",
"Finland 3000 2020-03-19 400.0 10.0 0.0\n",
"France 36747 2020-03-15 4523.0 12.0 91.0\n",
"Germany 167000 2020-03-15 5795.0 46.0 11.0\n",
"Hungary 3007 2020-03-20 85.0 2.0 3.0\n",
"Iceland 9189 2020-03-20 409.0 5.0 0.0\n",
"India 14514 2020-03-20 244.0 20.0 5.0\n",
"Indonesia 2028 2020-03-20 369.0 15.0 32.0\n",
"Iran 80000 2020-03-14 12729.0 2959.0 611.0\n",
"Ireland 6600 2020-03-17 223.0 5.0 2.0\n",
"Israel 10864 2020-03-18 433.0 11.0 0.0\n",
"Italy 206886 2020-03-20 47021.0 4440.0 4032.0\n",
"Japan 14901 2020-03-19 924.0 150.0 29.0\n",
"Kyrgyzstan 1545 2020-03-13 0.0 0.0 0.0\n",
"Latvia 3205 2020-03-20 111.0 1.0 0.0\n",
"Lithuania 1154 2020-03-20 49.0 1.0 0.0\n",
"Malaysia 13876 2020-03-20 1030.0 87.0 3.0\n",
"Malta 889 2020-03-13 12.0 1.0 0.0\n",
"Mexico 278 2020-03-10 7.0 4.0 0.0\n",
"Netherlands 6000 2020-03-07 188.0 0.0 1.0\n",
"New Zealand 584 2020-03-17 12.0 0.0 0.0\n",
"Norway 43735 2020-03-20 1914.0 1.0 7.0\n",
"Pakistan 1979 2020-03-19 454.0 13.0 2.0\n",
"Panama 1455 2020-03-18 86.0 0.0 1.0\n",
"Philippines 1269 2020-03-20 230.0 8.0 18.0\n",
"Poland 13072 2020-03-20 425.0 1.0 5.0\n",
"Qatar 8400 2020-03-17 439.0 4.0 0.0\n",
"Romania 8284 2020-03-20 308.0 25.0 0.0\n",
"Russia 143519 2020-03-19 199.0 9.0 1.0\n",
"Slovakia 2707 2020-03-20 137.0 0.0 1.0\n",
"Slovenia 9860 2020-03-19 286.0 0.0 1.0\n",
"South Africa 6438 2020-03-20 202.0 0.0 0.0\n",
"Korea, South 316664 2020-03-20 8652.0 1540.0 94.0\n",
"Spain 30000 2020-03-18 13910.0 1081.0 623.0\n",
"Sweden 14300 2020-03-17 1190.0 1.0 7.0\n",
"Switzerland 4000 2020-03-07 268.0 3.0 1.0\n",
"Taiwan* 21376 2020-03-20 135.0 26.0 2.0\n",
"Thailand 7084 2020-03-17 177.0 41.0 1.0\n",
"Turkey 2900 2020-03-10 0.0 0.0 0.0\n",
"Ukraine 316 2020-03-20 29.0 0.0 3.0\n",
"United Arab Emirates 125000 2020-03-16 98.0 23.0 0.0\n",
"United Kingdom 64621 2020-03-19 2716.0 67.0 138.0\n",
"US 103945 2020-03-19 13677.0 0.0 200.0\n",
"Vietnam 15637 2020-03-20 91.0 16.0 0.0"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"def transform_date_to_str(date_str):\n",
" \"\"\"Transforms the date strings to the John Hopkins one: mm/dd/yy \"\"\"\n",
" if date_str[8] != '0':\n",
" return date_str[6:7] + \"/\" + date_str[8:10] + \"/20\"\n",
" else:\n",
" return date_str[6:7] + \"/\" + date_str[9:10] + \"/20\"\n",
"\n",
"def read_john_hopkins_dataset(url, column_name):\n",
" john_hopkins_df = pd.read_csv(url, index_col=['Country/Region'])\n",
" john_hopkins_df = john_hopkins_df.drop('Lat', axis=1)\n",
" john_hopkins_df = john_hopkins_df.drop('Long', axis=1)\n",
"\n",
" # We must sum the cases on countries that are displayed by region eg US and China\n",
" john_hopkins_df_grouped = john_hopkins_df.groupby(['Country/Region']).sum()\n",
"\n",
" testing_df[column_name] = np.nan\n",
" for index, row in testing_df.iterrows():\n",
" try:\n",
" testing_df.at[index, column_name] = john_hopkins_df_grouped.loc[index][transform_date_to_str(str(row['Date']))]\n",
" except KeyError:\n",
" # We are recovering from some missing keys\n",
" print(index)\n",
"\n",
"# Add confirmed cases column \n",
"read_john_hopkins_dataset('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Confirmed.csv',\n",
" \"Confirmed\")\n",
"\n",
"# Add recovered cases column\n",
"read_john_hopkins_dataset('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Recovered.csv',\n",
" \"Recovered\") \n",
"\n",
"# Add deaths column\n",
"read_john_hopkins_dataset('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Deaths.csv',\n",
" \"Deaths\")\n",
"\n",
"display(testing_df)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Having created the dataset we will save it so as we can then import it instead of creating it from scratch having to treat special cases of missing values and future incompatibilities between the two datasets we combine. \n",
"\n",
"Important field that should be added on the dataset to create more useful conclusions:\n",
"* Population\n",
"* Tests per million"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"ExecuteTime": {
"end_time": "2020-03-24T10:28:28.529457Z",
"start_time": "2020-03-24T10:28:28.516219Z"
}
},
"outputs": [],
"source": [
"testing_df.to_csv(path_or_buf='datasets/covid_testing_importance.csv')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Evaluation and Conclusions\n",
"\n",
"Having our dataset created we will try to infer insights by seeing how the number of tests correlates with the number of cases and the ability of the country to successfully deal with the epidemic. \n",
"\n",
"\n",
"### Number Of Cases\n",
"Firstly, I will calculate the correlation between number of tests and number of cases."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"ExecuteTime": {
"end_time": "2020-03-24T10:28:30.721902Z",
"start_time": "2020-03-24T10:28:30.048554Z"
}
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAZ0AAAFsCAYAAAAXEWQeAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8li6FKAAAgAElEQVR4nOydaXhURdaA35OwJBIkKIoQVFAEZA9EUCCIoOAIIiqKigoji4rgOiju4DLgwIi7yIiCjCAj8jGACgoY2WRYIyiCiAQhIrIlEgwQkvP9qNtNp+lOukkn6XTqfZ5+urtu3brnVt++59Y5p06JqmKxWCwWS0kQVdoCWCwWi6X8YJWOxWKxWEoMq3QsFovFUmJYpWOxWCyWEsMqHYvFYrGUGFbpWCwWi6XEsErHUu4RkfYi8pWI7BcRFZFlTvlM53uN0pYxVIjIOOeckkpbFkv5pEJpC1CaiEiwk5T+qqqTi0MWABGJAw4Bn6pqj+I6TmkhIqcDdwM9gMZAPJAFbAa+ACap6i8lLFMNYB6gwL+BA0CJylAWEJHKwF+BXkBL4AzgCPATsBjz2/1QehJaygrlWukAo3yUPQhUA14FMry2pRa7RBGKiFwO/Ac4G9gBzAV2A1WB1sBTwGMi0lJVN5egaB0wyu8BVX3Na9v9jlwHS1CesENEmgH/B1wI7AEWAjuBGKAZMAx4SES6quqiUhPUUiYo10pHVUd6l4lIf4zSeUVV00pYpIhERFoCnwGVgAeAN1U116vORcA/gbgSFq+28/6r9wZV/dVXeXlCRM7FKJmzgb8Dz6nqUa86tYHnMcrbYikYVbUvjxeQhjG11C2k3lnAOGALxsxwEFgAdPJRNxb4G2aklAEcBrYDs4COTp2hznF9vf7m0VZv4GvME+dRIB1j3hgQwLm94LTnsy5Q39me4lFWHXND2YQx/f0BbAU+BJoF2KcrnHafCKBuJa/vjYFpmFHRMWAX8J6v38f5PRRIAvoCa4FsYB8wFTjbo27TAvq7t1NnpvO9ho/93gCaOL/hXiAPSHLqrMGYDWOcPt/uyPE9cIdTRzAKeJNz/ewAngDET790AGY7v/sxp/4bnufkVf8yjLLIcq65+UArzz4K8Leb7tSfGEDdyl6/21hgndP/R51+eAs4x8e+UcAg4H9O/WyMmfMzoJeP+nWBdzD/16POPrOAlj7qFvkatq/Qvcr1SOdUEZEGmBt9AvAV8ClwOtATWCQid6jqNI9dZgDXAuuByZg/SQLQEegMLAFWAaOBxzF/CM/9VzjHfRgzGkjHmDsOADWBROB2YFIhok8BngTu9FP3Tud9snO8aGCR0/5S4HPMzfU84CrgS2BjQQd0TDOXYf7orxQiH6p6zGPfZOeYsZjz3Yq50f8VuE5EOqmqr+M/ivEb/Rfz+7TH9E9TEUlSM8r6HWNebQP8BfgYc1PC470gmmBukKkYhVYV8zDhFt+R+WLMDV+Bm4EPRCQb6Irxj3yK6cfrgReBTOBNzwOJyFDgNYwCmYMZfTUChgA9RKStqu7xqH+l026Uc15pwCXAMucVECISD9zkyP5cYfU1/wjoNuAuIAVzfecCzYF7gO7O77DXo/4rGDPdVoyiy8KMQtti+mm2h1ztMMqoKub6+BjzP7ge+IuI/EVVU5y6Rb6GLSGmtLVeuL0IYKSDeZI9DvT0Kj8T4xT/A4h3ymo57X2N11Ms5sZ0psf3OKfuPD/H3eK0Xd3HthqFnZtTbznmT1fPhyzbMX/2OKfsMkeeqT7aqeA6x0KOd6/Txvwgf4cKHr/FdV7bBjjla73KXU/x+4EGXuf2X2fbNV77uEaYvX3IUNBIx+/Izbk+FHOzjfMob4K5+R5wrhPPkdfZmKfwnV5ttXSute/wGtVgHmTy/T5Ov+1wyq/0qv+kh+yFjnQwyliBzafwPzoXr1GrU97LaXOsR1kUZmTzEx6jJV/XNmb0uMu5Ttt41auLGXVuByqE6hq2r9C+bMh0kIhIe4zje6qqzvHcpqr7McP4qphRjydH1bnSPeqrs08w5DivfKjqvgD3n4K5Cd/pVX455k87S1WzvLZl+zjecVX1DrTwRS3nfVeA8rnoApwPfKmq//U69iTMCKOViLTyse9YVf3Ro74C7zpf2wQphz/SgJcKqTPcsy9V9XuMya868Iyq/u6x7XfMiKiOiJzp0cZ9QDRwn2d9Z5+5GBNabxGp5BR3wTzFf6aqC73kGUtwPqpT/e1Q1Z3qMWr1KJ+NUQrdvDdhzIa5PvbxvLZvxFgJxqrqKq96aZgRU12gnVczRbmGLSHEmteC5zLn/SwRGelje4LzfjGAqu4Wka+Aq0RkLcbuvBRYpapHgjz2hxiT0A8iMgMzeloRpOKagflj3ikiz3kown7O+2SPuuswT+SDHJPiHMxIaZ2qnqT4QoxLmSz2s30xZhSQ6MjpyRof9Xc679WLLhpg+uCkG6QHeRhzqjeum/5aH9vSnfc6mNEanLjerhKRK3zsE495+q+HGQm7+u1r74qqekxEvsHcuIsVEYkC+gN3YCLc4jHK08UBD7nyROQjjNn0OxH5GPMf+UZVD3k17eqPi/z8/5o47xdjRpqleQ1bfGCVTvC4nkK7Oy9/eEZh9cQ4iftgHMsAfzp/tOGqesB7Zz88j3GoDwYeBh4B8kRkESbYYENhDahqpojMBm7FOKeXikgVTIDCLxgfiKvuURHpCDwL3IDxJwFkiMgk4GlVPekJ0ovdzntCgbVOpprX/v7a9RUx5evp9bjzHu1j26nwWyHbs3096XvIkVnAtooeZa7r7clCjue63lz9tsdPvcLk9uRUfzswTv6BmFHSZxhl63rIGozxgXpyN0Y59MOEqQPkiMgc4BFV3eGUufqjbyHHj4OQXcOWEGLNa8HjulkMUFUp4DXMtYOqZqnqE6p6IWbo3w/zNH4XZvQSEI457l+qeglQA6PMpmIcogtEpFqBDZxgivPuGt3cgPmTTvVhAtyrqkNVtTbGeX0PxmfwCPByAMdyOa4vE5HYAOWDE/18jp/ttbzqlTRaeJWQkOkcq2Ih19taj/pgHOu+8NefvvgGY+5qKCJ1At1JROpiFM5qjG/tTlUdoaoj1UxTOKnvVDVHVf+hqk0wv+3NGKf/jcCnTkAAnDi/LoX0xz892i7qNWwJIVbpBM9K5z35VHZW1R2q+gHG9p4OdPW4GbvMNYU+javqAVWdq6r9MZMuzwEuDVCML51j3+Qc26V8pvjfBVR1i6q+g4m6y8E4hQuTcyPm5lUNEyJcIB6+CZdpqpOfqq5yb9NapLES44NrH2B9V39c7r3B6dtArxEcf8fHzvGfKqS6K2sBmNB7gM+9RxHOfKzaFICq/qaqH6vqdZioziYebRb1/xf0NWwJLVbpBM/XmD/27SJyq68KItJKRKo7n2uJyMU+qlUFquDhPHX+oNkYR7Cvdjv7KBPMnCGAPwM5AVXNw4yQTseEqV6B8Q1t9Wr7ImdyoDc1MKbZgI6HcYb/CTwvIkMce7/3eVzgmP2aO0ULMea+q0Xkaq+6/TG+i1RVjXSl8yrm+nhDROp5bxSRGCe4xcUijP/qGid02pPhBG8qexQTXn63iDzn8VDgKUNNEZmICVMHE2QB0NG5Pl31qgETfewfJyInBXg4Ssw1encprxmYB6ZH/P0fRCRZRCo630N1DVtChPXpBImqqojchPlzTxORRzBmhEMYB3AiZgjfDDNh9EKM32Q9Juw1HeOHuNZ5/7uX7X8RZu7FJ5j5A8eBhaq6EvhCRHZhnv52YH6/y51jLsM4SANlCjAC42OKwvcopy0wRUT+h7G3/4Yx2/TCPP0WFr0FgKquF5FrMCOyN4HhIrLYaS/Okb8d5snzMWef4yJyJ8bEMk9EZmFCaptg+u4gxlEd0Th9NwQzqXKziHyOmcsSi3k46YjplySn/nERuQszT+czEZnJiXk67TGj3KuCOP5OR3n9H/A0xiH/JcZXE4P5PS7HXIsfOfv8JCLzMEporfNbn4GJWNuHuZY8FUE88D8R2YwZ4f4CnAZcDVwETFMnJ5+qZovIDRg/0SIRWQJswMx9Ow8TnXg+5qEuhxBdw5YQomEQtx1OLwLPSBCPcU6mYiYF/glsw0TH3AXEOPVqYCLOvsY4U48674vwPTckAWPS2It5wlWcjASYXGBzODHDfT/GN/QQcNopnOtKp/1sfMxXwEREveTUc2VA+MWRocspHO90zJPzEszNJwdjo1+FCZI418c+TTE3M9dM/HRMhN0FPur6nW2PRyYBr/JTnafzRgHnuQbI8rPtpDYDlL8VJiHpTqcf9mMeSt4EOvio3865xg47fXxKGQk82ovB+EIWYG7cxzAPWt9i/CKNvOpXxYRob+NExoVXMCOXfP2DUaCPY5K+7nTq/455iBqAM+fGq/1azrn84Fy/h4AfnWvlFiCqOK5h+yr6S5wfxmKxWCyWYsf6dCwWi8VSYlilY7FYLJYSwyodi8VisZQYVulYLBaLpcSwSsdisVgsJYZVOhaLxWIpMazSsVgsFkuJYZWOxWKxWEoMq3QsFovFUmJYpWOxWCyWEsMqHYvFYrGUGFbpWCwWi6XEsErHYrFYioiInCMiH4nINhFZKyKfichgZ4kHX/XfFZHGJS1nOGDX07FYLJYi4CxU93/AFFW9xSlrgVlO3ieqOrCExAs77EjHYrFYisYVQI6qTnAVqOq3wFIgTkRmishmEfnQtZKqiKSISJLzOUtEXhSRb0VkpYjUdMqvFZH/ich6EVnoKi/rWKVjsVgsRaMpsNbPtkTgQaAxcAFm9VZvqgArVbUFZoHDQU75MuBSVU3ELE73aCiFLi2sec1isViKj1WqugtARFKBuhhl4skxwOX7WcuJ5cTrADNEpBZQCbNicJnHjnQsFoulaHwPtPaz7ajH51x8P+jn6IklnD3rvI5ZFr0ZcDdmyfAyj1U6FovFUjQWA5VFZLCrQESaA8lFbLcakO587lfEtsKGcmNeq1GjhtatW7e0xSgyhw8fpkqVKqUtRrnA9nXJUpb6e2N6pvtzVOzp5GX/kQC8IiKPAUeANGB2EQ8zEvhYRA5iFFu9IrYXFsiJUV1kk5SUpGvWrCltMYpMSkoKnTp1Km0xygW2r0uWstTf7ccsJj0jG4DdUx7k6O6tUsoilRki3rzmhB1OzMzMLLyyxWKxBMDwbg2JrRhd2mKUSSJe6ajqXFUdXK1atdIWxWKxhBlxcXEApKWlMW3atELrp6Wl0bRpU3olJjD6hmYkxMcWt4gRR8QrHYvFYimMQJWOJ70SE1g+ojPHfvvJ3xwdiw8iXulY85rFYimMESNGsHTpUlq2bMn48eNJS0sjOTmZVq1a0apVK1asWHHSPh07diQ1NdX9XUSWOelvLAUQ8dFrqjoXmJuUlDSo0MoWi6VcMmbMGMaNG8e8eWaO5p9//smXX35JTEwMW7du5dZbb8U7EGnAgAFMnjwZABFpAMQ46W8sBRDxSsdisVg8mb0+nbELtvBrRjbZObnMXp9OvFednJwchg4dSmpqKtHR0fz4448ntXPTTTfx/PPPAwhwFzC52IWPAKzSsVgs5YbZ69N5fNZGsnNyAVCFx2dtpO95h/LVGz9+PDVr1uTbb78lLy+PmJiTkwGcdtppXHXVVWzbti0euBn/WQksHlifjsViKTeMXbDFrXBcZOfk8vGG/Rw6dELxZGZmUqtWLaKiopg6dSq5ubneTQEwcOBAgHOB1ap6sPgkjxwiXunYkGmLxeLiV2dCpzeZMbWIjo6mRYsWjB8/niFDhjBlyhRatGjB5s2b/WZKaN26NZh8ae8Xm9ARhjWvWSyWckPt+Fh3JgGA8x6eCUDCmVVZvHhxvrobNmxwf37ppZcAqFu3Lt999527/NdffwXj0/mi2ISOMCJ+pGOxWCwufGUSiK0YzfBuDYNu64MPPqBt27YA6aqaFxoJI5+IVzrWp2OxWFx4ZhIQICE+ltE3NKNXYkLQbd15553s3LkTwPpygiDizWt2no7FYvGkV2LCKSkZS2iI+JGOxWKxWMIHq3QsFovFUmJYpWOxWCyWEsMqHYvFYrGUGBGvdGz0msVisYQPEa90bEYCi8ViCR8iXulYLBaLJXywSsdisVgsJYZVOhaLxWIpMazSsVgsFkuJYZWOxWKxWEoMq3QsFovFUmJEvNKx83QsFoslfIh4pWPn6VjKGy+++CJNmjShefPmtGzZkv/9739BtzFnzhzGjBlTDNIVTlpaGk2bNs1XNnLkSMaNG8fKlStp27YtLVu25OKLL2bkyJGlIqPl1In4pQ0slvLEN998w7x581i3bh2VK1dm3759HDt2LOh2evbsSc+ePUMqW1xcHFlZWUVqo1+/fvznP/+hRYsW5ObmsmXLlhBJZykpIn6kY7GUJ3bv3k2NGjWoXLkyADVq1KB27drUrVuXRx99lGbNmtGmTRt++uknAObOnUvbtm1JTEzkyiuvZM+ePQBMnjyZoUOHAtC/f3/uv/9+2rVrxwUXXMDMmTNDJu/x48eDqv/7779Tq1YtAKKjo2ncuHHIZLGUDFbpWCwRRNeuXdm5cycNGjRgyJAhfP311+5t1apVY+PGjQwdOpQHH3wQgA4dOrBy5UrWr1/PLbfcwj/+8Q+f7e7evZtly5Yxb948RowYUSQZU1JSSE5OpmfPnm6l0atXLwYPHkyTJk2YNm2au25cXBxPPvkkb7/9Nq+//jqDBg2iYcOGXH/99bzzzjscOXKkSLJYSh5rXrNYyjiz16czdsEWfs3IpnZ8LE+/O4czs37mq6++ok+fPm7fzK233up+f+ihhwDYtWsXffr0Yffu3Rw7dox69er5PEavXr2IioqicePG7tFQUVi3bh3fffed+3g3PvgCf/ltO39fncNz4x+gRlwMAIcPH+bSSy+lYsWKfP3115x++umsWbOGL774gmnTpjF9+nRSUlKKLI+l5LBKx2Ipw8xen87jszaSnZMLQHpGNk/9dxOjb2jGqFGdaNasGVOmTAFARNz7uT4PGzaMhx9+mJ49e5KSkuLXMe8y1wGoalDyuRRidk4us9enEw+0adPGrXBmr0/noWfGUHnHcvZmQ07mfn77syKz16dTqVIlevTowZdffsnFF19MWloaF154Iffeey+DBg3irLPOYv/+/Zx55pnBdJulFLHmNYulDDN2wRa3wgHI2b+LP/b8wtgFxsGemprK+eefD8CMGTPc75dddhkAmZmZJCQkALiVU6hwKcT0jGwUUIXHZ21k2da9VKlSxV3vqbdnkPXzeh5+9iVq3/UGlc+5EImpylNvfUTFihU5ePAg8+fPp3HjxqSlpbmV3tatW4mOjiY+Pj6kcluKFzvSsVjKML9mZOf7npdzhINfTmDv0cM0nxZP/fr1mThxIvPmzePgwYM0b96cypUrM336dMCEIt90001Ur16dzp07s3379pDJ5q0QAbJzcvlo9U7qepTt3X+QqJgqVKpcmZz9Ozn66xbO7DaEbV9M4Vh2Np07d+bZZ5+lcuXKbNu2jYYNG3LaaadRoUIFPvzwQ6Kjo0Mms6X4sUrHYinD1I6PJd1D8VQ+pz7n3DGOhPhYlo/onK/u8OHDeemll/KVXXfddVx33XUntdu/f3/69+8PmEg2TwINe/ZWiC72ZR3Np3QuSGxP6vrPefHRofxRpQ6VazekQrWatLr3Fb59oSepqakAzJw5k8svv/wkeSxlC2tes1jKMMO7NSS2Yv4n/diK0Qzv1rCUJDpB7fjYfN/Pe9iEWl/YvC3z5s1zlz/WvRl1+77Ak/94g7NveIpzbhtD9QsTGd6tYT4F17t373BVOImuDyJyjYj8KCLnl4YgInKXiGwUkQ0i8p2InPxEEVg7LUXkGo/vI0Xkb6GQscwqHRGpIiJrRKRHactisZQWvRITGH1DMxLiYxEgIT6W0Tc0o1diQr56aWlp1KhRo0RlC1Qhus6hUnRUgecQ7ohIF+A14C+quiPAfUJmbRKROsCTQAdVbQ5cCmw4xeZaAtcUWusUCBvzmoi8B/QAflfVph7lVwOvAtHAu6rqys3xGPCfEhfUYgkzeiUmhOUN2iWTZzj38G4NfcraKzGBlMytbB/TqYSlDA0i0hH4F3CNqm5zyuoC7wE1gL3AX1X1FxGZDBzBjJCWi8jTwOtAU6AiMFJV/+vsPxVwRV0MVdUVBYhxNnAIyAJQ1SzXZxFpCUwATgO2AXep6kERSQH+pqprRKQGsAZoADwHxIpIB2C0035jp/55wCuq+tqp9FXYKB1gMvAG8IGrQESigTeBq4BdwGoRmQMkAJuAmJIX02KxBEq4KsQQI8BsoJOqbvYofx2YoqpTROQuzCiol7OtDtBOVXNF5O/AYlW9S0TigVUishD4HbhKVY+IyEXAdCCpADm+BfYA20VkETBLVec62z4Ahqnq1yLyHPAs8KCvRlT1mIg8AySp6lAw5jWgEXAFUBXYIiJvq2pO4N1kCBulo6pLHM3uSRvgJ1X9GUBEPgKuA+Iw2r8xkC0in6lqnnebIjIYGAxQs2bNiJhElpWVFRHnURawfV2ylKX+zsjOYU/mEY7l5gEioCuAAcADHtUuA25wPk8FPNM9fKyqrtC+rkBPD59JDGY08SvwhjNKycWMQPziKLCrgUuALsB4EWkNjAfiVdWVnmIK8HHQJw2fqupR4KiI/A7UxAwGgiJslI4fEoCdHt93AW09tG9/YJ8vhQOgqhOBiQBJSUnaqVOnYhW2JEhJSSESzqMsYPu6ZCkr/T17fTqPL9pIdk4UEGXGOcrNwCIReUJV/x5AM4c9Pgtwo6rmy17qjC72AC3MgSg054+aSUyrMKOlL4H3MUrHH8c54dsvzHJ01ONzLqeoP8psIAGAqk5W1XkF1bHr6VgsllDia/6Rqv4JdAf6isgAp3gFcIvzuS+w1E+TC4Bh4qSJEBFXNFw1YLfzUH0Hxq+NU2ezdyMiUltEWnkUtQR2qGomcFBEkp3yOwDXqCcNaO187u2x7yGMGS3khLvSSQfO9fhexykLGLuejsViCSX+5h+p6gHgauApEekJDAP+KiIbMDf6B3zuCM9jAgg2iMj3zneAt4B+IvItxp9yGMBx+IuPdioC40Rks4ikAn08jtkPGOvI0hITKAAwDrhXRNZjAh5cfIUJHEgVkT5+O+MUCHfz2mrgIhGph1E2twC3la5IFoulrLBnzx4eeughVq5cSfXq1alUqRKPPvoo119//Sm36T0ht1LNC92fVXUn4Jk1Nf8MXVOnv9f3bOBuH/W2As09ih5z3i/FBFh519/h63jOtlRnP+/yzV7HeMopP4DxDfnEM8I4WMJmpCMi04FvgIYisktEBqjqcWAoZvj5A/AfVf0+yHatec1iKYeoKr169aJjx478/PPPrF27lo8++ohduwLzfftb68fX/KOSRFXnnWq4cjgQNkpHVW9V1VqqWlFV66jqJKf8M1VtoKoXquqLp9CuNa9ZLOWQxYsXU6lSJe655x532fnnn8+wYcPIzc1l+PDhXHLJJTRv3px33nkHOHmtn7S0NBo1akT//v1p0KABffv2JW7/DzD3afa8ezfHft2C5h4/JiJtROQbEVkvIitEpCGYYCcRmSUi80Vkq4j8wym/S0ReccklIoNEpCCHf8QQNkqnuLAjHYulfPL999/TqlUrn9smTZpEtWrVWL16NatXr+Zf//qXO9npunXrePXVV/nxxx8B+Omnn3jkkUfYvHkzmzdvZtq0aWxav4qPJr1Jmz+WkLM3bSOwGUhW1UTgGcAzgq0lxr/SDOgjIudiJrZfKyIVnTp/xUwkjXjC3adTZJzJUXOTkpIGlbYsFoul+HGt4bN54fdUPrKfy9en0ysxgfvuu49ly5ZRqVIlzj//fDZs2OBeejszM5OtW7dSqVKlfGv9ANSrV49mzZoB0KRJE7p06YKI0KxZM9LS0lzVqgFTnEmcinHqu1jkRJAhIpuA81V1p4gsBnqIyA9ARVXdWKwdEyZEvNKxWCwniI6Odt9AAWbPnk3dunVLT6AQ47moXYUa53FgxQoen2Xu5W+++Sb79u0jKSmJ8847j9dff51u3brl2z8lJSXfWj+QfwG7qKgo9/eoqChPv8/zwFeqer0zyT3Fowl/81veBZ7AjJLeP+WTLmNY85rFUo6IjY0lNTXV/fJWOP6c52UFzzk0Mee3QI8f4/dVc92L2v35558AdOvWjbfffpucHJPF5ccff+Tw4cO+Gw2MapyYztE/kB1U9X+YKSG3YVLclAsiXunYQAKLpWAmT55Mz5496dy5M126dCErK4suXbrQqlUrmjVrxn//+1/AZKq++OKLGTRoEE2aNKFr165kZ5vQ4Z9++okrr7ySFi1a0KpVK7Zt2wbA2LFj3c76Z599ttjPxXMOjYhw1g1PceSXjawacxtt2rShX79+vPTSSwwcOJDGjRvTqlUrmjZtyt13311UhfsPYLQz3yUYC9J/gOWqerAoBy9TqGq5eLVu3Vojga+++qq0RSg3RGJfR0VFaYsWLbRFixbaq1cvVVV9//33NSEhQffv36+qqjk5OZqZmamqqnv37tULL7xQ8/LydPv27RodHa3r169XVdWbbrpJp06dqqqqbdq00VmzZqmqanZ2th4+fFgXLFiggwYN0ry8PM3NzdXu3bvr119/7Ve2UPR3u9GL9PzH5p30ajd6UZHb9gewRk/xvgTMA7qc6v5l8WV9OhZLhONyrP+akQ0VKjHy/U9Pyvx81VVXccYZZwDmQfSJJ55gyZIlREVFkZ6ezp49ewDjVG/ZsiUArVu3Ji0tjUOHDpGenu6ecBkTY1J4ffHFF3zxxRckJpqsLllZWWzdupWOHTsW27kO79bQ7dNxES6L2nniyiYNfKuqi0pbnpIk4pWOiFwLXFu/fv3SFsViKXE8HesAqrgd656Kx9N5/uGHH7J3717Wrl1LxYoVqVu3LkeOmFyTnk716Ohot3nNF6rK448/zt13nzTZvtgIZg2f0kRVMygka3SkYn06FksE4ys5ZXZOrtux7ovMzEzOPvtsKlasyFdffcWOHQUvglm1alXq1KnD7NmzATh69Ch//vkn3bp147333nMvOZ2ennaChwYAACAASURBVM7vv/9exDMqnF6JCSwf0ZntY7qzfETnsFM45Z2IH+lYLOUZf8kp/ZUD9O3bl2uvvZZmzZqRlJREo0aNCj3O1KlTufvuu3nmmWeoWLEiH3/8MV27duWHH37gsssuAyAuLo5///vfnH322ad2MpaIQBxnVsSTlJSka9asKW0xikxZWXMkEoiEvm4/ZnG+5JQuEuJjWT7CZ27IUqOs9reIrFXVglb0tHgQ8eY1i6U84ys5ZTg61i3lh4hXOnZyqKU80ysxgdE3NCMhPhbBjHBG39AspH6OtLQ0mjbNn+l+5MiRjBs3rsD91qxZw/333w+YUc53330X9LHr1q3Lvn37Cixfu3Yt9erVY/369cyZM4cxY8YEfRxfpKSk0KNHj5C0VZ6IeJ+O2txrlnJOr8SEsHSmJyUlkZRkrFIpKSnusOxQsmHDBnr37s2MGTNITEwkMTGRnj17hvw4lsCJ+JGOxWIpXTp16sRjjz1GmzZtaNCgAUuXmlWbXSOFtLQ0JkyYwMyZM2nZsiVLly5l79693HjjjVxyySVccsklLF++HID9+/fTtWtXmjRpwsCBAynIJ/3DDz/Qq1cvpk6dSps2bQCTfWHo0KEA9O/fn/vvv5927dpxwQUXuJN/5uXlMWTIEBo1asRVV13FNddc4942f/58GjVqRKtWrZg1a5b7WCJyhojMFpENIrJSRJo75SNFZIqILBWRHSJyg4j8Q0Q2OssdVKScYZWOxWIpdo4fP86qVat45ZVXGDVqVL5tdevW5Z577qF3796kpqaSnJzMAw88wEMPPcTq1av55JNPGDhwIACjRo2iQ4cOfP/991x//fX88ssvfo953XXX8cYbb9ChQwe/dXbv3s2yZcuYN28eI0aMAGDWrFmkpaWxadMmpk6dyjfffAPAkSNHGDRoEHPnzmXt2rX89ttvnk2NAtaranNMEs8PPLZdiFnRsyfwb0xi0GZANtA9kP6LJCLevGaxWIoHV6aDX3bsYP++w8x2lhBwISLuzzfccANwIotBYSxcuJBNmza5v//xxx9kZWWxZMkS9wije/fuVK9e3W8bV155Je+++y7dunUjOtr3Sp+9evUiKiqKxo0bu817y5Yt46abbiIqKopzzjmHK664AoDNmzdTr149LrroIgBuv/12Jk6c6GqqA3AjgKouFpEzReR0Z9vnqpojIhuBaGC+U74RqFtoZ0QYET/SsYEEFkvocWU6SM/IRmKrcuzwHzw+ayOz15tEywcOHKBGjRru+q5MBtHR0QEl1szLy2PlypXubNjp6enExcUFJeMbb7wBwJAhQ/zW8cywUIzTR4467ecBOXriQHmUwwf/iFc6NiOBxRJ6PDMdRFWKJTruDA78tI6xC7Zw4MAB5s+fX6BZy5uqVau6lx0A6Nq1K6+//rr7e2pqKgAdO3Zk2rRpAHz++eccPOg/OXNUVBTTpk1j8+bNPPPMMwHL0r59ez755BPy8vLYs2cPKSkpADRq1Ii0tDR3Bu3p0/OtRrAU6AsgIp2Afar6R8AHLUdEvNKxWEqL2evTaT9mMfVGfEr7MYvdo4BwRUR45JFH3N/HjRvHyJEjfdb1zmhwZveHyVzxEavHD6Rz5848++yzXHjhhQEf+9prr2XZsmXuQILXXnuNNWvW0Lx5cxo3bsyECRMAePbZZ1myZAlNmjRh1qxZnHfeeQW2GxMTw5w5c5gzZw5vvvlmQLLceOON1KlTh8aNG3P77bfTqlUrqlWrRkxMDBMnTqR79+60atXKO7PCSKC1iGwAxgD9Aj75cobNSFDGKKuztssiRelr70SbYCZlhnqOTCiJiYmhVq1arF69mho1ajBu3DiysrJ8Kh5fmQ40L5c6Z8SdcqaDcLq2s7KyiIuLY//+/bRp04bly5dzzjnn+KxrMxIEhx3pWCzFwKkk2ixtKlSowODBgxk/fvxJ29LS0ujcuTPNmzenS5cu9G8eR2zFaPZ9Op79C95g9wcPc2jJZHZNGkJGRgaqyplnnskHH5ggrjvvvJMvv/yStLQ0kpOTadWqFa1atWLFihXu7cuWLXMfr2/fvu7F40qDHj160LJlS5KTk3n66af9KhxL8FilY7EUA6eSaDMcuO+++/jwww/xDrwZNmwY/fr1Y8OGDfTt25dPJ/6d0Tc047RK0eQe2k/roW/w3tuv85cunVi+fDnff/89F1xwgXtOzjfffEO7du04++yz+fLLL1m3bh0zZsxwZyQYMGAA8+eboK7MzExWrFhB9+6lF02ckpJCamoqmzZton///qUmRyRS7iInLJaSoHZ8rM9Em7XjY0tBGv94LvCWnZPL4m2HuPPOO3nttdeIjT0h6zfffOMOVb7jjjt49NFHmZ2YwOxmtbjiitvo1+8qAA4nJ7NkyRLOP/987r33XiZOnEh6ejrVq1enSpUqZGZmMnToUFJTU4mOjubHH38E4PLLL2fXrl3s3buXTz75hBtvvJEKFeztKRKxIx2LpRgoC4k2PcOelRMLvF3U+WYmTZrE4cOHA2rHcwG4jh07snTpUpYuXUqnTp0466yzmDlzJsnJyQCMHz+emjVr8u2337JmzRqOHTvm3rdbt278+9//5v333+euu+4K6blawoeIVzp2no6lNCiJRJtFxZ/facLK37n5ZqN4XLRr146PPvoIMCuLupSIN+eeey779u1j69atXHDBBXTo0IFx48a5l6jOzMykVq1aREVFMXXqVHJzTxy/W7duvPLKKwA0btw4pOdqCR8iXunYeTqW0iLcV7AsyO/0yCOP5Mve/Prrr/P+++/TvHlzpk6dyquvvuq33bZt29KggVmJOTk5mfT0dPecnSFDhjBlyhRatGjB5s2b842SzjjjDC6++GL++te/huL0LGGKDZkuY4RTWGmkE+l9HW4LvM2fP5/77ruPdevWUZYeEm3IdHBE/EjHYglHwmHiaDj5nRYuXEj//v0ZNmxYmVI4luCx4SEWSwnjPXE0PSObx2dtBChRE5zrWK7otdrxsQzv1rBUzIBXXnklH330UUSPLC0Gq3QslhKmoImjJX3DD9cF3iyRi1U6FksBeM5jCdVIoKxOHLVYQoH16VgsfsjIzsk3j8VlBiuq/8XfBNFwmzhqsRQHVulYLH7Yk3kk6PxpgQQIhJMD32Ipaax5zWLxw7HcPHw9l/kzgwUaIBBODnyLpaSxSsdi8UOlaN+GAH9msGACBKwD31JeKZPmNRG5WEQmiMhMEbm3tOWxRCY1q8UEbAabvT7d50RLsAECFosnYaN0ROQ9EfldRL7zKr9aRLaIyE8iMgJAVX9Q1XuAm4H2pSGvJfKJj60YUP40l1nNHzZAoOjMnj0bEWHz5s2nvP+mTZuC3m/y5MkMHToUgAkTJrjXB7KcOuFkXpsMvAG4f1URiQbeBK4CdgGrRWSOqm4SkZ7AvcDUUpDVUk4IxAzmy6zmQoArGp1VDJKVL6ZPn06HDh2YPn06o0aNCnr/2bNn06NHD5+JRI8fPx7QMgr33HNP0Me1nExY5V4TkbrAPFVt6ny/DBipqt2c748DqOpoj30+VVWfqz2JyGBgMEDNmjVbu7LklmVcy+haip9A+3pjesEZzKNESKgeS3xsxVCJFpH46+/s7GzuvPNOXn75ZZ588kk++OADUlNTmTFjBqNHm1vBq6++SsOGDbn66quZOHEiK1asIDo6mqSkJJKTk3niiSeoUqUKVapUYdSoUYwdO5b69euzceNGunTpQp06dZg6dSrHjx/n9NNP58knn+SMM85g/vz5bNmyhQceeIDJkycTGxtLnz59mDdvHvPmzSMnJ4eff/45A0hQ1T9LuMvKJOE00vFFArDT4/suoK2IdAJuACoDn/nbWVUnAhPBJPyMhBQbkZ6EMpzw7mt/E0Wf9JM405OE+GiWj+hUYJ3yjr9r+8MPP6Rnz57ccccdvP3221StWpWWLVuycOFCd/2ZM2fSqFEjmjVrxtq1a9m+fTsiQkZGBvHx8axZs4YePXrQu3dvAP71r39x9tlns2WLCX8/ePAgjz/+OCLCu+++y/Lly/nnP/9JWloaWVlZdOrUiZSUFOLi4ujUqRPNmjVj3LhxAIhINjAAeL0EuqnME+5KxyeqmgKkBFJXRK4Frq1fv35ximSJcAoKhx7erWG+bb6wwQTB4angM2e/zv0PPADALbfcwvTp0+nRo4fP/apVq0ZMTAwDBgygR48efusB9OnTx/15165d9OnTh927d3Ps2DHq1atXoHzfffcdTz31FBkZGQBnAk2CPcfyStgEEvghHTjX43sdpyxg7Ho6llBQWDi0K+DAHzaYIHA8VzQ9nn2IjG2pvDjiQc6ufS5jx47lP//5D9HR0eTl5bn3OXLkCAAVKlRg1apV9O7dm3nz5nH11Vf7PY7nWj7Dhg1j6NChbNy4kXfeecfdnj/69+/PG2+8wcaNGwF+BWKKcs7liXBXOquBi0SknohUAm4B5pSyTJZySGH50lwLtr3Sp6XNNlBEPBX8n1uWU6XJFSTc+x4X3T+FnTt3Uq9ePfLy8ti0aRNHjx4lIyODRYsWAcYvlJmZyTXXXMP48eP59ttvAahatSqHDh3ye8zMzEwSEkzAyJQpUwqV8dChQ9SqVYucnByAM4p2xuWLgM1rjpP/UqA2EAvsA7YAK1W14MeCwNqfDnQCaojILuBZVZ0kIkOBBUA08J6qfh9ku9a8ZikyteNjffptvEcwNttA0fFU8Id/+JpqbXvnK7/xxhv56KOPuPnmm2natCn16tUjMTERMMrguuuu48iRI6gqL7/8MmDMcoMGDeK1115j5syZJx1z5MiR3HTTTVSvXp3OnTuzffv2AmV8/vnnadu2LWeddRZAke9/5YkCo9dEJB4Y6LwuwkSAenMMM/p4y/G1hCV25VBLsHj2tbdPB8wIxte8Hcup4ervcFvRtDDsyqHB4de8JiJ/A34GHsaMNG4G6gPVgErAOcBlwGNAPLBQRBaKSFjZEUTkWhGZmJlZcFirxVIQnn6bgiaKWoqOTYga2RRkXrsNuAuYo6p5Prb/7rz+B7wqIrWBvwE9gbGhFvRUUdW5wNykpKRBpS2LpWxj86WVDNZEGdn4VTqq2iqYhlT1V8yoyGKxWIqEVfCRS7hHr1ksFoslgggoek1Ezitgcx6Qqar+4xFLERu9ZrFYLOFDoCOdNGC7n9cOIENEtopI2PlN7ORQi8ViCR8CnadzD/AEkAF8AuzBRK/diIlmewvoCEwQkRxVnRx6US0lhb8cYxaLxVJUAlU6DYA1qtrbq/w5EfkEOEdVe4jIVOABzDIFYYE1rwVHoEsuRwKBKlerhC2W0BGoee124F0/294F+jqfPwbCKpjemteCo6AcY5GEZ34vxSjXh2akUnfEp7Qfs5jZ69P91nt81sZ829uPWUw9r/0sFotvAh3pVAVq+Nl2FuBaBOMPwH+qXUvYU1iOsUAJ99GBL+Xqys3hUiyj20UzdmXBSri8jAotllAR6Ejna+DvItLas1BEkoAXga+coouAX0InnqWk8ZcNOf60wBcgK2x0EA4UpkSzc3LZk3mkQCVcXkaFFksoCVTp3AfkAKtEZLuI/E9EtmOyERwFhjn14jDLS1vKKMO7NaRi9Mkp9rKOHA9YaZSFm3EgSw0cy83zW692fGzIRoUWS3kiIKWjqtuBRsC9wGJgv/N+D3Cxsx1VHa+qbxWTrKeEzb0WHL0SE6hS6WSra06eBqw0ysLN2Fd+L28qRUcVmAesIIVksVh8E/DSBqqag1n6eWLxiRN6bO614MnMzvFZHqjSCHQZgNLEM79XekY2wgmfDhjFUrNapULzgPnKPG0TU1os/glquWoRaQpcjlm0aD/wdbDr21jCn6IqDV/LN4fbzdgz0CEhPpYrGp3FV5v35lMs8ZlbAf95wGxiSosleAJNg1MBM/fmVvKvqaMiMg3or6o2ai1CKKrSCPebsa+5SJ+sTXcvVeBSSLece4gnxywuUHabmNJiCY5ARzrPYtbTeQb4N/AbJiPB7c62n513SwQQqNIoKCw6nG/GhQU6uBXSucUXBh3uIeUWS3ERqNK5HXhBVV/0KNsBvCgi0cBfCVOlYzMSnBqFKY1QZi4o6RvwqYZBh0qm8pT1wWLxJtCQ6drACj/bVjjbwxKbkaB4CFVYdGnM6SntMOiyEFJusRQXgSqdX4H2fra1c7ZbyhGhujmXxg24OMOgA0mLUxZCyssa0dHRtGzZkqZNm3LttdeSkZERsrbXrFnD/fffH7L2yjuBmtc+BJ4UkTzn826MT+cW4EngpeIRzxIsJWWqClVYdHHcgAvrg+IKgw7UbFYWQsrLGrGxsaSmpgLQr18/3nzzTZ588smQtJ2UlERSUlJI2rIEPtIZCcwERgFbgSzgJ0wKnJnAc8UhnCU4StJUVdBoIRhCPcEy0D7olZjA8hGd2T6mO8tHdM4XADH6hmYkOMdPiI91R7UVRqCjtlD1ncU3l112Genp5vdOSUmhR48e7m1Dhw5l8uTJAIwYMYLGjRvTvHlz/va3vwHw8ccf07RpU1q0aEHHjh1PamPVqlVcdtllJCYm0q5dO7ZssSbRYAlopKOqx4HbRORFzLo5ZwAHgCV2nk74UBJOcBehCosO9ZyekXO+L3IfuIIoUlJSGNa3U8DHDnTUFu4h5WWZ3NxcFi1axIABAwqst3//fv7v//6PzZs3IyJuc9xzzz3HggULSEhI8Gmia9SoEUuXLqVChQosXLiQJ554oljOI5IJanKoo2DyKRkRaQEMUFVr9CxlStpXEIqw6FDegGevTyejiNkUikIwZrNwDikvK3iaUQ//mU29hk3IOvA7F198MVdddVWB+1arVo2YmBgGDBhAjx493COZ9u3b079/f26++WZuuOGGk/bLzMykX79+bN26FREhJ8f39WbxT6DmtYKoj0kIaillymouMH+mrkBxOe8fnJHqt05J9IE1m5Uc3mZUqVCJmJv/yRv//QZV5c03Td7hChUqkJeX597vyJEj7vJVq1bRu3dv5s2bx9VXXw3AhAkTeOGFF9i5cyetW7dm//79+Y779NNPc8UVV/Ddd98xd+5cd3uWwAmF0rGECeXxpud58ymI9IzsYl9kzdMfJATnD7IEhz9T8mtLfuG1117jn//8J8ePH+f8889n06ZNHD16lIyMDBYtWgRAVlYWmZmZXHPNNYwfP55vv/0WgG3bttG2bVuee+45zjrrLHbu3JnvGJmZmSQkmN/T5RuyBEdQ5rWySHmaHFoefQW+bj7+KIlJmKEwm+3fv58uXboA8NtvvxEdHc1ZZ50FGEd2pUqVTtqnW7duzJw5k6pVqxbp2L5QVbZt28bKlSu5/fbbQ97+qVCQKTkxsTPNmzdn+vTp3HHHHdx88800bdqUevXqkZiYCMChQ4e47rrrOHLkCKrKyy+/DMDw4cPZunUrqkqXLl1o0aIFX3/9tbv9Rx99lH79+vHCCy/QvXv34j/RCERUtfBaBTUgciPwH1UtOE98KZOUlKRr1qwpbTGKTEpKCp06dSptMcKGeiM+JdgrOCE+luUjOhdaLxz6euTIkcTFxbmjq0oaVWXw4MEkJyezc+dOtm3bxt///nfOOeeckB8rmP5uP2axz9FtoL9tKBGRtapqY6oDxJrXLCEnkAmSoeJUfDVleRLmtddeS+vWrWnSpAnvvvuuu7xOnTpkZGQwevRo3nrLLGk1bNgwunbtCsAXX3xBv379ABg8eDBJSUk0adKE5557Ll8bI0eOJDExkebNm/Pjjz8iIkyYMIFp06YxadIk/vGPfxSLwgmW8mhKjhT8Kh0R2SkivxT2AiaUoLyWMKek09r4u/m80qele66NN+EeWFEQU6ZMYe3ataxevZqXX36ZgwcP5tuenJzM0qVLAVi3bh0ZGRnk5uaydOlS97yTMWPGsGbNGr799lu+/PJLNm3a5N6/Zs2arF+/noEDB/Lyyy+jqtx3333cdttt3HXXXYwYMYLffvut5E7YD9Z/VnYpyKezCIK2XFjKKa7wVV8mj+KaKwTFl12gtPDOpnDu7j9IuijOvX38+PHMmTMHgF27drFt27Z8s+UvueQSVq9eTUZGBnFxcdSvX59169axdOlS7rjjDgCmT5/OpEmTOH78OL/++iubNm2icePGAO4w4datW/PZZ58hIrz99tts27aNqKgonnrqqZLqikKxYedlE79KR1X7l6AcljKMd/oXXxSnSStSFlnzlUZnyw+/E3NaFQAWLlzIkiVLWLlyJbGxsXTo0OGkkN3KlSuTkJDABx98QPv27WnQoAGLFi1ix44dNGjQgK1bt/Lqq6+yatUq4uPjuf322/O1UblyZcDkMjt+/DgAIkL9+vUpD8E4luIn4qPXLMVPIBFkhZm0iitnXFl6GvbVj8fz8kjZshcw4bpnnHEGsbGxfP/996xevdpnO8nJyYwbN44PPviAiy66iOHDh3PppZcC8Mcff1C1alVOP/10du/ezYIFC9xzVCyWkqAgn06rYBsTkRgRaVQ0kSxljcJGMYWZtEpjeYNwxF8//uFkWejevTt//vknjRs35qmnnqJt27Y+6ycnJ7Nnzx4uvfRSEhISqFixIsnJyQC0atWKxo0b06hRI+68807at/eXPD78SEtLo2nTpvnKRo4cybhx4wrczzNLdEpKCitW+FulxT9169Zl3759/jbHioiKyClpbxFJE5EahdTpLyJ7RSTV49U4iGPcIyJ3BilXJxFpF8w+gVDQSGeJiCwG3gK+UNU8fxVF5DzMQm/DgH8Cm0MqpSWs8Zf+BSA+tiIi8NCMVMYu2OJzBFOSOePCGV/9GN+hrzsgIiYmhgULFvjcd9euXe7P3bp14+jRo+7vP//8s/uziDB16tRC27j00ktZuHBh8CcRhnhmiU5JSSEuLo527UJ6Lz0DWAbcCsz33igigpme4vceGiAzVHXoqeyoqj4DvkSkgpNb0xedMMmdg9fSBVBQyHRDYB/wX2CPiMwRkedF5H4RuVtERojIRBFJxSxX/VfgEVUt+LHDEnH4iyC7/dLzOHo8j4N/5hQ4grHryxhsGHDR6NSpE4899hht2rShQYMG7ig+V5botLQ0JkyYwPjx42nZsiVLly5l79693HjjjVxyySVccsklLF++HDATdLt27UqTJk0YOHAg/uYzOuVnAP2Bq0QkBkBE6orIFhH5APgOOFdE3haRNSLyvYiM8mrqURHZKCKrRCRg55kzGvlaRP4rIj+LyBgR6eu0s1FELnTqjRSRvzmfU0TkFRFZAzwgIteKyP9EZL2ILBSRmiJSF7gHeMgZVSWLyFki8omIrHZe7Z32LvcYfa0XkQJnKBcUSJAO3CUiIzAKpRvwMOBpnN8OLAFGAAu0qDNNA0REegHdgdOBSar6RUkctyxQ0ks/g3+HfaAjGLu+jKGsBT6EI8ePH2fVqlV89tlnjBo1Kt9orW7dutxzzz35JtvedtttPPTQQ3To0IFffvmFbt268cMPPzBq1Cg6dOjAM888w6effsqkSZN8Hs8x1R1V1W0ikoK5L33ibL4I6KeqKwFE5ElVPSAi0cAiEWmuqhucupmq2swxgb0C9OBk+ohIB4/vlznvLYCLMZn/fwbeVdU2IvIAxvr0oI+2KrkmtIpIdeBSVVURGQg8qqqPiMgEIMs1kBCRacB4VV3mWLcWOMf9G3Cfqi4XkTigwIR0hQYSqOrvmEXaXnIOHA/EAPtVNWQpVkXkPUxH/66qTT3KrwZeBaIxnTlGVWcDs53OGgdYpUPgi4gVB74c9g/5ScDpPYIJ9fIGZZmyFPhQUrgepH7ZsYP9+w4ze316vj4y1iuDZ8h3WlpaoW0vXLgw3zylP/74g6ysLJYsWcKsWbMA40urXr26z/2nT58O5mYP8BFwJyeUzg6XwnG4WUQGY+67tYDGgEvpTPd4H+9H3JPMa865r1bV3c73bZy4H24ErvDXlsfnOsAMEakFVMIMJnxxJdDYo79Pd5TMcuBlEfkQmKWqu/zsD5xC9Jqqhm4d2PxMBt4APnAVOE8EbwJXAbuA1SIyR1VdV8lTznYL4ecbCXQEE6lP+KUx6ow0PB+kJLYqxw7/ke9B6sCBA9SrV89d31fId0Hk5eWxcuVKYmJigpYtNzeXTz75BKC2iKQBApzpYV467KorIvUwI4JLVPWgiEzGPLy7UD+fA+Gox+c8j+95+L/HH/b4/DrwsqrOEZFOmEU7fRGFGRF5j2TGiMinwDXAchHppqp+/fphkwZHVZdw4onBRRvgJ1X9WVWPYZ4krhPDS8DnqrqupGUNV8LNNxKMj6KoyxuEGzYiLzR4PkhFVYolOu4MDvy0jrELtnDgwAHmz59Phw4dCmnlBFWrVuXQoUPu7127duX11193f3cted2xY0emTZsGwOeff35S5geARYsW0bx5c4ANqlpXVc/HjHKu93Ho0zE3+kwRqQn8xWt7H4/3bwI+odBQDXBdmP08yg8Bnv6ZLzDmOgBEpKXzfqGqblTVl4DVQIERzOE+TycB8MwtvgtoiznxK4FqIlK/gMiMwcBgMOk9UlJSilfaIpCRncOezCMcy82jUnQUNavFEB9b8aR6WVlZfs9jRMs8juWeHCATHSW889HcQtsOJa7zGdIoD0FQ1Dl2JeIzt5KSsrVYjx8KCurrwtjz2yGGNPL+LY6zZ8s6UjLD/9xLA1/9fcu5h+DcE993P/QAH09+hx0r/kWbd6Pp06cPO3fuZOfOnWRkZLB27Vr3sgVHjhwhJSWF1NRU9u/fT0pKCmeffTZvvfUWH374Iffffz99+vThlVdeYcKECeTm5tK8eXMefvhhunTpwgsvvMC7775L06ZNqVmzJsuXL6datWpuWcaPH0+TJk344ot81v1PgHsxvm43qvqtiKzHRPbuxJikPKkuIhswo5Rb/XSRt09nSKGdGhgjgY9Fv2cmNAAAFThJREFU5CCwGHANHecCM0XkOsw9937gTUfOCphzvAd4UESuwIysvgc+L+hgRc4yHUqciIl5Lp+OiPQGrlbVgc73O4C2pxI2GM5Zpn3N6I+tGO0zl1RBmXh9tVMxSkAgJ/fE7+yv7VARzPmEM0XJMu0v+7UA28fYlPi+8NXf4ZRN2h9is0wHRdiY1/yQTr7nHOpwYhgYEE444MTMzMyQChZKCvLFBIOvJIhxMRXyKZxTbTsYQnU+ZZmyuopruGHDyCOPcFc6q4GLRKSeiFQCbgHmBNOAqs5V1cGew+JwI5S+GG/fSMafvgMMi9PPE26+pdLA3ixDg80mHXkE5NMRk6LhNFX9xaPsbqApZn7OvKIKIiLTMTNga4jILuBZVZ0kIkMx8eDRwHuq+n2Q7Yb9yqHBzFPJyM6h/ZjFAUdElcYcGDvvJnIj8koDG0YeWQQaSPAexok/BEBEngZGAQeBISJym6rOKGD/QlFVn84zVf0M+KwI7c4F5iYlJQ061TaKm0Dnqcxen076wWzSM8wTdCDzcEpjDoydd2OwN0uL5WQCNa8lYdbXcXEP8HdVPRMzT+bhUAtWngjUhDB2wRbyNDj/TGmYJ6xJxGKx+CPQkc4ZwB4AEWkKnANMcbbNxszCDUvKgnkNAnsq/jUjO39YhWd5EdsONfYp32Kx+CLQkc5+TOQYQGfgV1V1TTaoGEQ7JU5ZCCQIFBsRZbFYyjqBKouFwEjHqf8IZnTjohGwI9SCWU5meLeGRHnkmYLy6SuxWCxll0CVzqOYWbSjgW2YIAIXfTFrSYQlZWGeTqD0SkwgoXqs9ZVYLJYyS0A+HVXdg0m66YsrKSSVdWlSFqLXgiE+tiLLR3Ryf5+9Pj2oEGqLxWIpTYLKvSYiUZh03GcCa1T1sKr+USySWQqlNJcysFgsllMh4AAAEbkP+A2z/sNizMqiiMhsEbm/eMQrOpFkXvPGppuxWCxljYCUjogMwiykNhu4GZO30MVS4MbQixYaIil6zRubbsZisZQ1Ah3pPAz8U1UHA//ntW0zzqjHUrLYEGqLxVLWCFTp1MPkP/PFYSA+NOJYgsEmlbRYLGWNQAMJ9gF1/WxrSJDLDVhCg00qGf7YJastlvwEqnTmAc+ISAonJoKqk336IfJPFg0rykoanFPFppsJX2x0ocVyMoGa157CLKP6HSY7gQKvAT8AucBzxSJdCIjkQAJLeGOjCy2WkwlI6ajqPkym6dGYXGvbMKOkN4DLVDXy4pEtliJiowstlpMJeHKoqv5/e3cfbFdV3nH8+yORF4EmvGY0gEChSIAO1FteCsiFAZKIyEsp745oIA0MLUzRkow6xbYWCliZ8lLMSEipSmAyioBheJFeA5jUIFINpUgIWkIcQhACobyU5Okfax85HO49d997z9l7331/n5kz5+6119n7uSv33id77bXXeg34u+w1qrmf3YrgxezM3i/vczqbSBrfUjZV0iWSDuhOaN3R6Gd//pU3CN7tZ7/jZx4LYZ3l0YVm75f3ns6tpNVDAZA0C7gHuApYKunoLsTWFe5nt6J4MTuz98vbvXYwcGnT9heAb5KWOZgLfJE0wKByWkevuZ/diuTRhWbvlfdKZ0eyZ3Ek7UF6WPS67D7PzcB+3Qlv5FpHr/kpfjOz8uRNOq+SZpYG6AXWRsTPs+0NwOYdjqtr3M9uZlaevN1rPwZmS3oHuBhY1LRvD2BVpwPrFj/Fb2ZWnrxJ569JieZOYCVwWdO+04AlnQ2ru9zPbmZWjrwrhz4N7Clpu4h4qWX3RaR1dszMzNoa0sqh/SQcIuIXnQvHzMzqLHfSkbQpMJ00q3TrwIGIiFE/U4GZmXVXrqQj6cPAw6TlDYJ3Vw6NpmqVTDp1n2XazGw0yTtk+irgRWAXUsI5CNgd+CqwIvu6kjzLtJlZdeTtXjsc+DywOtveGBG/Iq2xM460zMEJnQ/PzMzqJO+VznbA6ojYSFqeepumfQ+SHhg1MzNrK2/SWQVsn339DHBs074DgTc7GZSZmdVT3u61fweOIC1L/Q3gekn7A/8HTM3KzMzM2sqbdL4EbAsQEf+Sra1zGvBB4EoqvFy1mZlVR94ZCdYCa5u2rwWu7VZQo10nVib16qZmVkcDJh1JmwDHAc9GxPIB6uwH7BoRd3UpvlGnsTJpY6G4xsqkQO6k0e4YE7sQs5lZUdoNJDibtGLo623qvAbcKumMjkY1inViZVKvbmpmdTVY0rk5Ip4dqEL2rM5NwGc6HNeo1YmVSb26qZnVVbuk80fAfTmO8QDQ05lw8pG0u6SbJC0s8rx5dGJlUq9uamZ11S7pbA28nOMYL2d1R0TSPElrJC1vKZ8m6SlJKyTNBoiIlRExY6Tn7IZOrEzq1U3NrK7aJZ21wEdyHGMXmka2jcB8YFpzQTbFzvWk2a2nAGdImtKBc3XNiQdM5vKT92PyxC0QMHniFlx+8n5DGnnWiWOYmVWRIqL/HdJtwDYRcWy/Fd6tdx/wckScNuJgpF2BuyNi32z7EOCyiJiabc8BiIjLs+2FEXFKm+PNBGYCTJo06WMLFiwYaYilW79+PVtttVXZYYwJbutijdb2PvLII38aEYXeYhjN2j2ncw3wsKSvA5dGxNvNOyV9gDT79FHAYV2KbzLwXNP2KuAgSduRZrg+QNKcRhJqFRFzgbkAPT090dvb26Uwi9PX10cdvo/RwG1dLLf32DBg0omIJZIuAb4GnJVd0fw62/0R4BjSRKCXRMTSrkf63theAmblqev1dMzMqqPtjAQRcY2kx4BLgZOAxvCpN4A+4IqIeKiL8T0P7Ny0vVNWllv24OpdPT0953UyMDMzG7pBp8GJiMXA4myGgsZM0y9FxIY2H+uUZcCeknYjJZvTgTOHcoDGlc74iR/i0Cse9HQyZmYlyru0ARGxMSLWZK+OJxxJtwJLgL0krZI0IyLeAS4E7gWeBG6PiCeGctzGyqGbbL7l76aTueNnQ7pYMjOzDsk7y3TXRUS/U+lExCJgUafO05hOxlc7ZmbFq0zS6Zbm7rUGTydjZlaO3N1ro1Vz91qDp5MxMytH7ZNOK08nY2ZWnjHVvTbZi6GZmZWq9kmn+TmdR2YfVXY4ZmZj2pjrXjMzs/I46ZiZWWFqn3QkHS9p7rp168oOxcxszKt90mkMmZ4wYULZoZiZjXm1TzpmZlYdTjpmZlaY2icd39MxM6uO2icd39MxM6uO2icdMzOrDicdMzMrjJOOmZkVxknHzMwKU/uk49FrZmbVUfuk49FrZmbVUfukY2Zm1eGkY2ZmhXHSMTOzwjjpmJlZYZx0zMysME46ZmZWmNonHT+nY2ZWHbVPOn5Ox8ysOmqfdMzMrDqcdMzMrDBOOmZmVhgnHTMzK4yTjpmZFcZJx8zMCuOkY2ZmhXHSMTOzwjjpmJlZYcaXHcBwSNoSuAF4G+iLiG+XHJKZmeVQmSsdSfMkrZG0vKV8mqSnJK2QNDsrPhlYGBHnAZ8qPFgzMxuWyiQdYD4wrblA0jjgemA6MAU4Q9IUYCfguazahgJjNDOzEahM91pELJa0a0vxgcCKiFgJIGkBcAKwipR4HqdN4pQ0E5gJMGnSJPr6+joed9HWr19fi+9jNHBbF8vtPTZUJukMYDLvXtFASjYHAf8MXCfpOOCugT4cEXOBuQA9PT3R29vbvUgL0tfXRx2+j9HAbV0st/fYUPWk06+IeB34bJ66ko4Hjt9jjz26G5SZmQ2qSvd0+vM8sHPT9k5ZWW5eT8fMrDqqnnSWAXtK2k3SpsDpwJ1DOYBXDjUzq47KJB1JtwJLgL0krZI0IyLeAS4E7gWeBG6PiCeGclxf6ZiZVUdl7ulExBkDlC8CFhUcjpmZdUFlrnS6xd1rZmbVUfuk4+41M7PqqH3SMTOz6qh90nH3mplZddQ+6bh7zcysOmqfdMzMrDqcdMzMrDC1Tzq+p2NmVh21Tzq+p2NmVh21TzpmZlYdTjpmZlaY2icd39MxM6uO2icd39MxM6uO2icdMzOrDicdMzMrjJOOmZkVxknHzMwKU/uk49FrZmbVUfuk49FrZmbVUfukY2Zm1eGkY2ZmhXHSMTOzwjjpmJlZYZx0zMysME46ZmZWmNonHT+nY2ZWHbVPOn5Ox8ysOmqfdMzMrDqcdMzMrDBOOmZmVhgnHTMzK4yTjpmZFcZJx8zMCuOkY2ZmhXHSMTOzwjjpmJlZYUZl0pG0u6SbJC0sOxYzM8uv8KQjaZ6kNZKWt5RPk/SUpBWSZrc7RkSsjIgZ3Y3UzMw6bXwJ55wPXAfc0iiQNA64HjgGWAUsk3QnMA64vOXzn4uINcWEamZmnVR40omIxZJ2bSk+EFgRESsBJC0AToiIy4FPDvdckmYCM7PN9ZKeyr6eAOSddjpP3XZ1BtqXt7x1e3tg7SDxdNJQ2mqkn3dbj/62HmjfYG0NxbZ3J9v6IyMPZwyJiMJfwK7A8qbtU4BvNm1/Griuzee3A24EngHmDOP8cztZt12dgfblLe9n+9GC/61yt5Xb2m090L7B2rro9i6yrf1676uM7rURi4iXgFkjOMRdHa7brs5A+/KWDyXWbhjp+d3W+dWhrQfaN5bb2pooy9rFnjR1r90dEftm24cAl0XE1Gx7DkCk7jVrIunRiOgpO46xwG1dLLf32FCVIdPLgD0l7SZpU+B04M6SY6qquWUHMIa4rYvl9h4DCr/SkXQr0Eu6afgC8DcRcZOkTwDXkEaszYuIrxYamJmZdV0p3WtmZjY2VaV7zczMxgAnHTMzK4yTjpmZFcZJZ5STtLekGyUtlHR+2fHUnaQtJT0qadgzZdjgJPVKeij72e4tOx7rHCedChrKpKgR8WREzAJOBQ4tI97RbBgT0F4K3F5slPUwxLYOYD2wOWk+RqsJJ51qmg9May5omhR1OjAFOEPSlGzfp4AfAIuKDbMW5pOzrSUdA/wX4Alnh2c++X+uH4qI6aQk/5WC47QuctKpoIhYDPy2pfh3k6JGxNvAAuCErP6d2S/oWcVGOvoNsa17gYOBM4HzJPn3ZwiG0tYRsTHb/zKwWYFhWpeNyrnXxqjJwHNN26uAg7L+7pNJv5i+0umMfts6Ii4EkHQOsLbpD6MN30A/1ycDU4GJpKVQrCacdEa5iOgD+koOY0yJiPllx1B3EfFd4Ltlx2Gd5+6B0eN5YOem7Z2yMus8t3Vx3NZjjJPO6OFJUYvjti6O23qMcdKpoGxS1CXAXpJWSZoREe8AFwL3Ak8Ct0fEE2XGWQdu6+K4rQ084aeZmRXIVzpmZlYYJx0zMyuMk46ZmRXGScfMzArjpGNmZoVx0jEzs8I46ZgNgaQvSForaeuyY2mQdKikjZJ6yo7FbDBOOtYxkmIIr127FMNMSRd06dg7AF8E/jEiXmsqvzr7nj7ajfMOJiIeAR4AvlbG+c2GwhN+Wid9umX7cGAmMBd4qGXfi12KYSZp4a8bunDsi4EPADd24dgjdQ3wA0lHRMSPyg7GbCBOOtYxEfGt5m1J40lJYEnrvtEmmxdsBnBH81VOhdxHWlxuFuCkY5Xl7jUrlaRxki6W9LikNyS9Kul+Se9belvSeZIek7RO0vpseeNbJE3I9q8FPgbs09KV15Pt31/S9yStlvSWpN9IekDS0TlC/TgwiRGuWSSpR9Ldkl6W9KakX0i6SJL6qTtV0rKsXVZLujL7fEj6fHPdbA6z+4ETsgRpVkm+0rHSZH9oFwLHk1aMnAt8EDgH6JM0PSIeyOqeT+oy+yEwD3gb2AX4JGmhr3Wk/+VfSeoCm9N0qpWSPgw8CLxB6h5bBewAHAT0kO6JtHNE9v6TEXy/h5MSw3rSwmQvAieRusamAH/eVPdY0hLkvwH+IfvMmcBRbU6xhLR67IHAw8ON06ybnHSsTGcDJwJnRcR3GoWSrgUeI/0x3jcrPgl4ATi2ZcXOLzW+iIiFkmYDm/fT1XcmsA1wdkQM52plChDAymF8tqGxAuafRMQvs7iuI03lP1PSvIj4j6zO14E3gYMj4vms7g3A0jbHfyZ73wcnHasod69Zmc4m3Ye4T9L2jRewNel/+ftkVyiQrmS2AY7trysqh3XZ+3GSthrG53cAXo2IDcP4LJJ2B/6QNHX/LxvlWQK9PNs8Kav7+6Qkd1sj4WR13wKubXOal7L3HYcTo1kRfKVjZdqb9Aey3Ui2ScBq4CukrrB7gDWSfkS6v3J7RPxvjnPdQ+rKuwA4V9JPSDffF0TE0zk+H8Bwkl3Dbtl7f2vFNMp2b6n7VD91+ytraMTn9Uqsspx0rEwC/oc0KmwgKwAiYrmkPwCOId3X6AVuBi6TdFhErGp3ouyK4s8k7Q9MIw3nngN8WdKsiJg3SKwvAltLGjfcq50CbJu9d2s4utmIOelYmZ4GDgYWR8Tbg1WOiDeBu7IXkk4FbgP+Ari0UW2QYzwOPA5ckXXl/ZTUvTVY0lkO/CmwJ/Dfg8Xaj8a9oH362Telpc6vsve9+qnbX1nDHtn78iFFZlYg39OxMt0CbEHqOnsfSZOavt6+nyqPZe/bNpWtb9lufH671ntBEbEWeA6YmOM+UV/2fvAg9foVEc8CPwdOldRIDkjaBJidbX4vq7uCtHTzqZImN9XdjJRgB3IwaXTesuHEaFYEX+lYmf4VmA7MlnQI6b7Lb4GdSd1f25FuvgM8IunXwCOk4c7bA58DNgDfbjrmUqBX0j+RrmI2APcC5wOflfR90iivDcDRwKHAvBh83faHScOXPwHMH6DOrOxZoVZLIuKHwIWkIdNLspFoa0mDB44E5jaNXAP4K+BuYKmkbwCvk4ZMv5Ptf0+82YO4xwDfz3PVaFaaiPDLr668SM/bBHBOmzoCzgV+DLxG+p/6SuB24MSmeheSnrN5gfSMzmrSUOPDWo73e8C/kf6gb8zO30N6duVbpITzOmk022PAXwLjc34/f5vFN6Gl/OrsPAO9rm6q+8ekkXmvAG+RusIuAtTP+aYDj5KGTq8GriLdywrggpa6x2XlR5T97+6XX+1eivBAF7M8si6+FcAVEXFFSTF8hnSldXxE3N1Ufj+wWUR8vIy4zPJy0jEbgmz6mdnAbtHFOdgkjQPGRVNXWXZPZynwUeBDEfFKVn4YsBg4KCJ8P8cqzUnHrIKyq6r/BL5DGuW3I+mezt7AlyPi70sMz2zYPJDArJpeJ80zdwrpAVlII9rOjYibSovKbIR8pWNmZoXxczpmZlYYJx0zMyuMk46ZmRXGScfMzArjpGNmZoX5f3VkLLkE9LsWAAAAAElFTkSuQmCC\n",
"text/plain": [
"<Figure size 360x360 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"# Plot the cases-axis, tests axis\n",
"fig, ax = plt.subplots()\n",
"fig.set_size_inches(5, 5)\n",
"ax.set_yscale('log')\n",
"ax.set_xscale('log')\n",
"ax.scatter(testing_df.Tests, testing_df.Confirmed)\n",
"\n",
"# We do the +0.1 to avoid having 0 values on a log scale, this +1 will not be used on calculating the correlation value\n",
"ax.set_xlim([min(testing_df.Tests)+ 0.1,max(testing_df.Tests) + 0.1])\n",
"ax.set_ylim([min(testing_df.Confirmed) + 0.1,max(testing_df.Confirmed) + 0.1])\n",
"ax.grid(True)\n",
"\n",
"for i, row in enumerate(testing_df.iterrows()):\n",
" # Add the annotation of the country name if the country has many tests\n",
" # to avoid text cluttering\n",
" if testing_df.Tests[i] > 2e4:\n",
" ax.annotate(row[0], (testing_df.Tests[i], testing_df.Confirmed[i]))\n",
"\n",
"fig.suptitle('Tests vs Confirmed Cases', fontsize=20)\n",
"plt.xlabel('Tests (Log)', fontsize=18)\n",
"plt.ylabel('Cases (Log)', fontsize=16) \n",
"\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Although this is not a straight line it seems like it has a linear relationship. The use of a **log-log** plot suggests a power law in the form of $Cases=kTests^n$. \n",
"When a slope on a log-log plot is between 0 and 1, it signifies that the nonlinear effect of the dependent variable lessens as its value increases [(ref)](https://statisticsbyjim.com/regression/log-log-plots/). In our case this means that **as the number of tests increases the rate of discovered cases slows down**."
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"ExecuteTime": {
"end_time": "2020-03-24T10:28:35.063952Z",
"start_time": "2020-03-24T10:28:35.051360Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Spearmans correlation: 0.718\n"
]
}
],
"source": [
"# Calculate the correlation value\n",
"corr_cases, _ = spearmanr(testing_df.Tests, testing_df.Confirmed)\n",
"print('Spearmans correlation: %.3f' % corr_cases)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"As expected the Spearman's Correlation of **0.718** is big enough to suggest a positive correlation."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Death Ratio\n",
"\n",
"We let a new variable $deathRatio = \\frac{deaths}{cases}$. This variable could be translated as the effectiveness of the health care system of each country, where the smaller the value the more effective."
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"ExecuteTime": {
"end_time": "2020-03-24T10:43:58.055623Z",
"start_time": "2020-03-24T10:43:57.602706Z"
}
},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 720x720 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"testing_df['DeathRatio'] = testing_df.Deaths / testing_df.Confirmed\n",
"\n",
"testing_df_death_ratio = testing_df[['Tests', 'DeathRatio']].dropna() # Remove null values\n",
"\n",
"# Remove countries with no deaths so as to not clutter the plot\n",
"testing_df_death_ratio = testing_df_death_ratio[testing_df_death_ratio['DeathRatio'] != 0]\n",
"\n",
"# Plot the cases-axis, tests axis\n",
"fig, ax = plt.subplots()\n",
"fig.set_size_inches(10, 10)\n",
"ax.scatter(testing_df_death_ratio.Tests, testing_df_death_ratio.DeathRatio)\n",
"\n",
"ax.grid(True)\n",
"\n",
"for i, row in enumerate(testing_df_death_ratio.iterrows()):\n",
" ax.annotate(row[0], (testing_df_death_ratio.Tests[i], testing_df_death_ratio.DeathRatio[i]))\n",
"\n",
"fig.suptitle('Tests vs Death Ratio', fontsize=20)\n",
"plt.xlabel('Tests', fontsize=18)\n",
"plt.ylabel('Death Ratio', fontsize=16) \n",
"\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"On the above plot we can see that countries that are performing a lot of testing like Germany, US and South Korea manage to face this epidemic with a little amount of deaths while countries like Ukraine, Indonesia and Philippines that perform a smaller amount of tests have greater number of deaths. \n",
" \n",
"**Correlation or Causality?** \n",
"This is a hard to answer question. Countries like Germany, and Australia have a better economy than Ukraine and Indonesia which plays a major role on the above results. However, one can say that better economy means more testing which means a smaller death ratio. **In conclusion, it seems like performing as much as possible testing will help contain the the number of deaths.** \n",
" \n",
"**Following** since this was written and ran at the end of March it would be really interesting to check the above numbers again when we have managed to deal with this epidemic. "
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.6.9 64-bit ('thesisEnv': virtualenv)",
"language": "python",
"name": "python36964bitthesisenvvirtualenv849bc23effdd4f5cbcfcfcad50606969"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.9"
},
"toc": {
"base_numbering": 1,
"nav_menu": {},
"number_sections": true,
"sideBar": true,
"skip_h1_title": true,
"title_cell": "Table of Contents",
"title_sidebar": "Contents",
"toc_cell": false,
"toc_position": {},
"toc_section_display": true,
"toc_window_display": true
},
"varInspector": {
"cols": {
"lenName": 16,
"lenType": 16,
"lenVar": 40
},
"kernels_config": {
"python": {
"delete_cmd_postfix": "",
"delete_cmd_prefix": "del ",
"library": "var_list.py",
"varRefreshCmd": "print(var_dic_list())"
},
"r": {
"delete_cmd_postfix": ") ",
"delete_cmd_prefix": "rm(",
"library": "var_list.r",
"varRefreshCmd": "cat(var_dic_list()) "
}
},
"types_to_exclude": [
"module",
"function",
"builtin_function_or_method",
"instance",
"_Feature"
],
"window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 4
}