1. 3. COVID-19 statistics from aggregated data from net site
   4. with Python
   5. Input from internet site: cases, recovered, deaths.
   6. Calculates active cases.
   7. version 0000.0015
   8. 12.5.2022

1. 1. parametrit

paiva1="2022-01-01" paiva2="2022-07-07" ymax1=15000 ymax2=50

1. paiva1="2021-04-01"
2. paiva2="2021-06-29"
3. ymax1=400
4. ymax2=10

import math as math import numpy as np import pandas as pd import matplotlib.pyplot as plt import matplotlib.ticker as ticker

1. import locale

from datetime import datetime, timedelta import matplotlib.dates as mdates from dateutil import rrule, parser from scipy import interpolate import scipy.signal

from matplotlib.ticker import (MultipleLocator, FormatStrFormatter,

                              AutoMinorLocator, MaxNLocator)

from scipy.signal import savgol_filter from bs4 import BeautifulSoup import requests import json

1. locale.setlocale(locale.LC_ALL, 'fi_FI')

def format_func(value, tick_number):

   N = int(np.round(value/10))
   if N == 0:
       return "0"
   else:
       return r"${0}\pv$".format(N)
       
   
   

1. 1. very basic exponential r0 calculation

def calculate_r0(time1, time2, val1, val2): k=0 td=time2-time1 ## #optim #td=1 gr0=math.log(val2/val1) gr=gr0/td if(gr!=0): td= math.log(2.0)/gr else: return(1)

tau=5.0

k=math.log(2.0)/td

r0=math.exp(k*tau) if(r0==32): r0=1

if(r0>32): r0=4

return(r0)

def cut_by_dates(dfx, start_date, end_date): mask = (dfx['Date'] >= start_date) & (dfx['Date'] <= end_date) dfx2 = dfx.loc[mask] #print(dfx2) return(dfx2)

def load_country_cases(maa): dfin = pd.read_csv('https://datahub.io/core/covid-19/r/countries-aggregated.csv', parse_dates=['Date']) countries = [maa] dfin = dfin[dfin['Country'].isin(countries)] #print (head(dfin)) #quit(-1) selected_columns = dfin"Date", "Confirmed", "Recovered", "Deaths" df2 = selected_columns.copy()

df=df2 len1=len(df["Date"]) aktiv2= [None] * len1 for n in range(0,len1-1): aktiv2[n]=0

dates=df['Date'] rekov1=df['Recovered'] konf1=df['Confirmed'] death1=df['Deaths'] #print(dates) spanni=6

#print(rekov1)

#quit(-1)

rulla = rekov1.rolling(window=spanni).mean() rulla2 = rulla.rolling(window=spanni).mean()

tulosrulla=rulla2 tulosrulla= tulosrulla.replace(np.nan, 0) tulosrulla=np.array(tulosrulla).astype(int) rulla2=tulosrulla

x=np.linspace(0,len1,len1); #print("kupla") #print(tulosrulla)

#print(konf1) #print(death1) #print(aktiv2) konf1=np.array(konf1).astype(int) death1=np.array(death1).astype(int) #print(konf1) #quit(-1)

for n in range(0,(len1-1)): #print("luzmu") rulla2[n]=tulosrulla[n] #print ("luzmu2") #aktiv2[n]=konf1[n]-death1[n]-rulla2[n] aktiv2[n]=konf1[n] #print(rulla2[n])

#quit(-1)

#aktiv3=np.array(aktiv2).astype(int)

dailycases1= [0] * len1 dailydeaths1= [0] * len1

for n in range(1,(len1-1)): dailycases1[n]=konf1[n]-konf1[n-1] if (dailycases1[n]<0): dailycases1[n]=0

for n in range(1,(len1-1)): dailydeaths1[n]=death1[n]-death1[n-1] if (dailydeaths1[n]<0): dailydeaths1[n]=0

#quit(-1) df.insert (2, "Daily_Cases", dailycases1) df.insert (3, "Daily_Deaths", dailydeaths1) df['ActiveEst']=aktiv2 #print (df) dfout = df'Date', 'Confirmed','Deaths','Recovered', 'ActiveEst','Daily_Cases','Daily_Deaths' #print(df) #print(dfout) #print(".") return(dfout)

def load_fin_wiki_data(): url="https://fi.wikipedia.org/wiki/Suomen_koronaviruspandemian_aikajana" response = requests.get(url) soup = BeautifulSoup(response.text, 'lxml') table = soup.find_all('table')[0] # Grab the first table df = pd.read_html(str(table))[0] #print(df) #Päivä Tapauksia Uusia tapauksia Sairaalassa Teholla Kuolleita Uusia kuolleita Toipuneita

df2 = df'Tapauksia','Uusia tapauksia','Sairaalassa','Teholla','Kuolleita','Uusia kuolleita','Toipuneita'

kaikkiatapauksia=df['Tapauksia'] toipuneita=df['Toipuneita'] uusiatapauksia=df['Uusia tapauksia'] sairaalassa=df['Sairaalassa'] teholla=df['Teholla'] kuolleita=df['Kuolleita'] uusiakuolleita=df['Uusia kuolleita']

len1=len(kaikkiatapauksia)

kaikkiatapauksia2=[] toipuneita2=[] uusiatapauksia2=[] sairaalassa2=[] teholla2=[] kuolleita2=[] uusiakuolleita2=[]

for n in range(0,len1): elem0=kaikkiatapauksia[n] elem1 = .join(c for c in elem0 if c.isdigit()) elem2=int(elem1) kaikkiatapauksia2.append(elem2) elem0=toipuneita[n] elem1 = .join(c for c in elem0 if c.isdigit()) toipuneita2.append(int(elem1)) elem0=uusiatapauksia[n] elem1 = .join(c for c in elem0 if c.isdigit()) uusiatapauksia2.append(int(elem1)) elem0=sairaalassa[n] #elem1 = .join(c for c in elem0 if c.isdigit()) sairaalassa2.append(int(elem0)) elem0=teholla[n] #elem1 = .join(c for c in elem0 if c.isdigit()) teholla2.append(int(elem0)) elem0=kuolleita[n] #elem1 = .join(c for c in elem0 if c.isdigit()) kuolleita2.append(int(elem0)) elem0=uusiakuolleita[n] #elem1 = .join(c for c in elem0 if c.isdigit()) uusiakuolleita2.append(int(elem0))

#kaikkiatapauksia3=np.array(kaikkiatapauksia2).astype(int) #print("---") #print(kaikkiatapauksia2) #print(toipuneita2)

kaikkiatapauksia3=np.array(kaikkiatapauksia2).astype(int) toipuneita3=np.array(toipuneita2).astype(int) uusiatapauksia3=np.array(uusiatapauksia2).astype(int) sairaalassa3=np.array(sairaalassa2).astype(int) teholla3=np.array(teholla2).astype(int) kuolleita3=np.array(kuolleita2) .astype(int) uusiakuolleita3=np.array(uusiakuolleita2).astype(int)

napapaiva1 = np.datetime64("2020-04-01") timedelta1= np.timedelta64(len(kaikkiatapauksia3),'D') napapaiva2 = napapaiva1+timedelta1

#dada1 = np.linspace(napapaiva1.astype('f8'), napapaiva2.astype('f8'), dtype='<M8[D]') dada1 = pd.date_range(napapaiva1, napapaiva2, periods=len(kaikkiatapauksia3)).to_pydatetime()

#print(dada1)

data = {'Date':dada1, 'Kaikkia tapauksia':kaikkiatapauksia3, "Uusia tapauksia":uusiatapauksia3, "Sairaalassa":sairaalassa3, "Teholla":teholla3, "Kuolleita":kuolleita3, "Uusiakuolleita":uusiakuolleita3, "Toipuneita":toipuneita3 }

df2 = pd.DataFrame(data)

#print(kaikkiatapauksia3) #print ("Fin wiki data.") return(df2)

def plottaa_tapaukset_kuolemat(paivat, tapaukset, kuolemat, kuolemat_liuku): #left, right = plt.xlim() fig, ax1 = plt.subplots(constrained_layout=True) ax1.set_ylim(0,ymax2) ax1.set_ylabel('Päivittäiset kuolemat', color='black',size=18) ax1.tick_params(axis='both', which='major', labelsize=15) ax1.bar(paivat,kuolemat, linewidth=2, color='black',label="Päivittäiset kuolemat") ax1.plot(paivat,kuolemat_liuku, linewidth=20, color='grey', label="Kuolemat viikon keskiarvo") ax2 = ax1.twinx() ax2.set_ylim(0,ymax1) ax2.tick_params(axis='both', which='major', labelsize=15) ax2.set_xlabel('Päivämäärä', color='g',size=18) ax2.set_ylabel('Päivittäiset uudet tapaukset', color='#7f0000',size=18) ax2.set_title('Koronavirustapaukset Suomessa', color='b',size=22) ax2.plot(paivat, tapaukset, linewidth=6.5, color='#af0000', label="Päivittäiset tapaukset")

lines1, labels1 = ax1.get_legend_handles_labels() lines2, labels2 = ax2.get_legend_handles_labels() ax2.legend(lines1 + lines2, labels1 + labels2, loc='upper left', fontsize=16) locator1 = mdates.MonthLocator() dateformat1 = mdates.DateFormatter('%d.%m') ax1.xaxis.set_major_formatter(dateformat1) ax1.xaxis.set_major_locator(locator1) ax2.yaxis.set_major_locator(MaxNLocator(integer=True)) plt.show() plt.savefig('kuva.svg') return(0)

def get_solanpaa_fi_data(): url="https://covid19.solanpaa.fi/data/fin_cases.json" response = requests.get(url,allow_redirects=True) open('solanpaa_fi.json', 'w').write(response.text) with open('solanpaa_fi.json') as f: sola1=pd.read_json(f)

#sola1_top = sola1.head() #print (sola1_top) #Rt […] #Rt_lower […] #Rt_upper […] #Rt_lower50 […] #Rt_upper50 […] #Rt_lower90 […] #Rt_upper90 […] #new_cases_uks […] #new_cases_uks_lower50 […] #new_cases_uks_upper50 […] #new_cases_uks_lower90 […] #new_cases_uks_upper90 […] #new_cases_uks_lower […] #new_cases_uks_upper […]

dada1=sola1["date"] casa1=sola1["cases"] death1=sola1["deaths"] newcasa1=sola1["new_cases"] newdeath1=sola1["new_deaths"] hosp1=sola1["hospitalized"] icu1=sola1["in_icu"] rt=sola1["Rt"] newcasauks=sola1["new_cases_uks"] data = {'Date':dada1, 'Tapauksia':casa1, 'Kuolemia':death1, 'Sairaalassa':hosp1, 'Teholla':icu1, 'Uusia_tapauksia':newcasa1, 'Uusia_kuolemia':newdeath1, 'R':rt, 'Uusia_tapauksia_ennuste':newcasauks, }

df = pd.DataFrame(data)

return(df)

def get_ecdc_fi_hospital_data(): url="https://opendata.ecdc.europa.eu/covid19/hospitalicuadmissionrates/json/" response = requests.get(url,allow_redirects=True) open('ecdc_hoic.json', 'w').write(response.text) with open('ecdc_hoic.json') as f: sola1=pd.read_json(f)

#print(sola1.head())

sola2=sola1.loc[sola1["country"]=='Finland']

#sola2.to_csv (r'ecdc_hospital_finland_origo.csv', index = True, header=True, sep=';')

#print(sola2.head())

dada0=sola2["date"] hosp0=sola2["value"] country0=sola2["country"]

len1=len(dada0) len2=int(len1/2) #print (len2)

dada1=dada0[1:len2-1] hosp1=np.array(hosp0[1:len2-1]) icu1=np.array(hosp0[len2:len1])

#print(dada1) print (icu1) quit(-1)

data = {'Date':dada1, 'Sairaalassa':hosp1, 'Teholla':icu1 }

df = pd.DataFrame(data)

df.to_csv (r'ecdc_hospital_finland.csv', index = True, header=True, sep=';')

return df

def get_thl_fi_open_data(): ## thl open data, 1.2.2021

url1="https://sampo.thl.fi/pivot/prod/fi/epirapo/covid19case/fact_epirapo_covid19case.json?row=measure-444833&column=dateweek20200101-508804L"

url2="https://sampo.thl.fi/pivot/prod/fi/epirapo/covid19case/fact_epirapo_covid19case.json?row=measure-492118&column=dateweek20200101-508804L"

headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36'} response1 = requests.get(url1,headers=headers,allow_redirects=True) open('thl_cases1.json', 'w').write(response1.text) with open('thl_cases1.json') as json_file1: data1 = json.load(json_file1) #print(data1)

headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36'} response2 = requests.get(url2,headers=headers,allow_redirects=True) open('thl_deaths1.json', 'w').write(response2.text) with open('thl_deaths1.json') as json_file2: data2 = json.load(json_file2) #print(data1)

k2=data1['dataset'] k3=k2['dimension'] k4=k3['dateweek20200101'] k5=k4['category'] k6=k5['label'] k8a=k6.keys() k8b=k6.values() d1=k2['value']

m2=data2['dataset'] m3=m2['dimension'] m4=m3['dateweek20200101'] m5=m4['category'] m6=m5['label'] m8a=m6.keys() m8b=m6.values() d2=m2['value']

#print (d1)

d1a=d1.keys() d1b=d1.values() d2a=d2.keys() d2b=d2.values()

#print (k8b) #print (d1a) #print (d1b) #print (d2a) #print (d2b)

len1=len(k8b)

#print(len1)

#dates0=np.datetime64(np.array(list(k8b))) dates0=list(k8b)

casekeys=np.array(list(d1a)).astype(int) cases0=np.array(list(d1b)).astype(int) deathkeys=np.array(list(d2a)).astype(int) deaths0=np.array(list(d2b)).astype(int)

#print(dates0) #print(casekeys) #print(cases0)

kasetab1=np.empty(len1).astype(int) kasetab1[casekeys]=cases0 deathtab1=np.empty(len1).astype(int) deathtab1[deathkeys]=deaths0

#print (len(dates0)) #print (len(kasetab1))

datax = {'Date':dates0, 'Uusia_tapauksia':kasetab1, 'Uusia_kuolemia':deathtab1 }

df = pd.DataFrame(datax)

return(df)

def load_thl_hospital_data(): #url1="https://sampo.thl.fi/pivot/prod/fi/epirapo/covid19case/fact_epirapo_covid19case.json?row=measure-444833&column=dateweek20200101-508804L" url_base1="https://sampo.thl.fi/pivot/prod/fi/epirapo/covid19care/fact_epirapo_covid19care.json" #request1="?row=dateweek20200101-508804L&column=measure-547523.547516.547531.456732.&fo=1" requesta=['?row=dateweek20200101-508804L&column=measure-547523','?row=dateweek20200101-508804L&column=measure-547516','?row=dateweek20200101-508804L&column=measure-547531','?row=dateweek20200101-508804L&column=measure-456732'] #request1="?row=dateweek20200101-508804L&column=measure-547523" ## esh

n=0 for x in requesta: request1=requesta[n] outname1='thl_hospital_'+str(n)+'.json' url1=url_base1+request1 headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36'} response1 = requests.get(url1,headers=headers,allow_redirects=True) open(outname1, 'w').write(response1.text) n=n+1

datetabs=[] kasetabs=[]

for n in range(0,4): outname1='thl_hospital_'+str(n)+'.json' with open(outname1) as json_file1: data1 = json.load(json_file1) #print(data1) k2=data1['dataset'] k3=k2['dimension'] k4=k3['dateweek20200101'] k5=k4['category'] k6=k5['label'] k8a=k6.keys() k8b=k6.values() d1=k2['value']

#print(d1) #print (json.dumps(k2)) #quit(-1)

d1a=d1.keys() d1b=d1.values()

len1=len(k8b)

#print(len1)

#dates0=np.datetime64(np.array(list(k8b))) dates0=list(k8b)

casekeys=np.array(list(d1a)).astype(int) cases0=np.array(list(d1b)).astype(int)

kasetab1=np.empty(len1).astype(int) kasetab1[casekeys]=cases0 kasetab1[kasetab1<0] = 0 kasetab1[kasetab1>100000] = 0 datetabs.append(dates0) kasetabs.append(kasetab1)

daates=datetabs[0] teholla=kasetabs[3] sairaalassa=kasetabs[0]+kasetabs[1]+kasetabs[2] sairaalassa=sairaalassa+teholla

datax = {'Date':dates0, 'Sairaalassa':sairaalassa, 'Teholla':teholla }

df = pd.DataFrame(datax)

return(df)

def cut_country_data_by_current(dfx, start_date): mask = (dfx['Date'] >= start_date) dfx2 = dfx.loc[mask] dfx2.drop(df.tail(1).index,inplace=True) #print(dfx2) return(dfx2)

1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 2. main proge

1. df=load_country_cases("Finland")

1. df.to_csv (r'kovadata1.csv', index = True, header=True, sep=';')
2. df=load_fin_wiki_data()
3. print(df)
4. df=load_thl_hospital_data()
5. datel=df['Date']
6. sairal=df['Sairaalassa']
7. tehol=df['Tehol']

1. df=get_thl_fi_open_data()

df=get_solanpaa_fi_data()

df.to_csv (r'kovadata0.csv', index = True, header=True, sep=';', decimal=",") df2=cut_by_dates(df, paiva1,paiva2)

1. df2=cut_country_data_by_current(df, paiva1)

print(df2)

1. quit(-1)

df2.to_csv (r'kovadata2.csv', index = True, header=True, sep=';', decimal=",")

dates0=df2['Date']

1. cases0=df2['Daily_Cases']

dailycases1=df2['Uusia_tapauksia'] dailydeaths1=df2['Uusia_kuolemia']

1. dailycases1=df2['Daily_Cases']
2. dailydeaths1=df2['Daily_Deaths']

df3 = df2"Date","Sairaalassa", "Teholla","Uusia_kuolemia","Uusia_tapauksia"

1. dates1=dates0.dt.strftime('%d.%m.%Y')

dates1=dates0.dt.strftime('%d.%m.')

df3["Date"]=dates1

df3.rename(columns = {'Date' : 'Pvm' }, inplace = True)

num = df3._get_numeric_data()

num[num < 0] = 0

1. print(dates1)

1. quit(-1)

print(df3)

df3.to_csv (r'epidemia.csv', index = False, header=True, sep=';', decimal=",")

date1 = paiva1 date2 = paiva2 datesx = list(rrule.rrule(rrule.DAILY, dtstart=parser.parse(date1), until=parser.parse(date2)))

1. dates_a=dates0

dates_a=datesx

dailycases_savgol_1 = scipy.signal.savgol_filter(dailycases1,7, 1) dailydeaths_savgol_1 = scipy.signal.savgol_filter(dailydeaths1,7, 1)

pos1=len(dailycases_savgol_1)-2 time2=pos1-0 time1=pos1-21 val1=dailycases_savgol_1[time1] val2=dailycases_savgol_1[time2] ro00=calculate_r0(time1, time2, val1, val2) ro=round(ro00,2) print("R0 = ",ro)

plottaa_tapaukset_kuolemat(dates_a, dailycases1, dailydeaths1, dailydeaths_savgol_1)

print(".")