List and plot the top countries with highest number of covid-19 deaths per million people.

covid19_ranking.py

"""
List and plot the top countries with highest number of covid-19 deaths per million people.

"""

import csv
import requests
import matplotlib.pyplot as plt


# Configuration

variable = "deaths" # Change for 'cases' to compare number of cases per million
days = 250 # Days after 1st case or death
rank = 13 # Number of countries of the ranking
chart = True # Show plot

# Source of data
#url = "https://covid.ourworldindata.org/data/owid-covid-data.csv"
url = "https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/owid-covid-data.csv"


# Column numbers
column_country = 2 # Country name
column_date = 3 # Date
column_dpm = 10 if variable == "deaths" else 13 # Cases or deaths per million


def toFloat(value):
    # Helper to convert str to float
    try:
        result = float(value)
    except ValueError:
        result = 0
    return result


with requests.Session() as s:
    # Download data
    download = s.get(url)
    decoded_content = download.content.decode('utf-8')
    myreader = csv.reader(decoded_content.splitlines(), delimiter=',')
    rows = list(myreader)


# Dataframes
cases = {} # Cases or deaths
dates = {} # Dates (duh)

for row in rows[1:]: # For each day
    c = toFloat(row[column_dpm]) # Cases or deaths per million inhabitants
    d = row[column_date]
    if c != 0: # Do not add until first case or death
        if row[column_country] in cases: # If country already added
            cases[row[column_country]].append(c)
            dates[row[column_country]].append(d)
        else: # If not, then create entry
            cases[row[column_country]] = [c]
            dates[row[column_country]] = [d]
    
# Get cases or deaths on day N for each country
dataDN = {} 
datesDN = {}  

for country in cases:
    if len(cases[country]) >= days:
        dataDN[country] = cases[country][days-1]
        datesDN[country] = dates[country][days-1]  
        

# Sort the list and print
sorted_list = sorted(dataDN.items(), key=lambda x: x[1], reverse=True)
print("Country".ljust(20) + "Cases/Hab".ljust(13) + "Date of day {} after 1st case".format(days))
print("-------------------------------------------------------------------")
cnt = 0
for country in sorted_list:
    cnt+=1
    if cnt <= rank:
        print(country[0][:18].ljust(20) + str(country[1]).ljust(13) + datesDN[country[0]])
        if chart:
            plt.plot(cases[country[0]][:days], label=country)
    else:
        break

if chart:
    plt.xlabel('Days after the 1st case')
    plt.ylabel('Deaths per million people')
    plt.title('Deaths per million people after the 1st case')
    plt.legend()
    plt.show()