1. 2. COVID-19 statistics from aggregated data from net site
   3. with Python
   4. Input from internet site: cases, recovered, deaths.
   5. Calculates active cases.
   7. v. 2000.08
   8. 13.5.2021

apv="2020-07-01" lpv="2021-05-12"

paiva1=apv paiva2=lpv

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

import locale from datetime import datetime, timedelta

import matplotlib.ticker as ticker import matplotlib.dates as mdates from matplotlib.ticker import (MultipleLocator, FormatStrFormatter,

                              AutoMinorLocator)

from matplotlib.ticker import MaxNLocator from matplotlib.ticker import ScalarFormatter

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

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)
       

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)) if (elem1!=): toipuneita2.append(int(elem1)) else: toipuneita2.append(0)

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)

for n in range(1,len1): toipu0=toipuneita3[n] if (toipu0==0): paikka=n toipui=toipu1 break toipu1=toipu0

## oletus: toipuu suureksi osaksi akuutista vaiheesta 3 viikossa ## todellisuudessa yli 60% kärsii ainakin yhdestä pitkäkestoisesta oireesta

for n in range(paikka,len1): toipui=toipui+uusiatapauksia3[n-21]-uusiakuolleita3[n] toipuneita3[n]=toipui #print(toipuneita3[n])

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 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"]

print(dada1) len1=len(dada1) toipuneita=np.zeros(len1) toipuneita=toipuneita*0 aktiivisia=toipuneita

toipui=0 for n in range(0,len1):

if(n>21): toipui=toipui+newcasa1[n-21]-newdeath1[n]

toipuneita[n]=toipui

aktiivisia=casa1-toipuneita-death1 #print(toipuneita)

#print("KKKK") #print (dada1[0+21])

data = {'Date':dada1, 'Tapauksia':casa1, 'Kuolemia':death1, 'Sairaalassa':hosp1, 'Teholla':icu1, 'Uusia_tapauksia':newcasa1, 'Uusia_kuolemia':newdeath1, 'R':rt, 'Uusia_tapauksia_ennuste':newcasauks, 'Toipuneita':toipuneita, 'Aktiivisia':aktiivisia, }

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)

1. 1. set dates

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

1. df=load_fin_wiki_data()

df=get_solanpaa_fi_data()

1. print(df)
2. quit(-1)

df2=cut_by_dates(df, paiva1,paiva2)

1. print(df2)
2. quit(-1)

dates0=df2['Date']

1. cases0=df2['Daily_Cases']

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

konf1=np.array(df2['Tapauksia']) rekov1=np.array(df2['Toipuneita']) death1=np.array(df2['Kuolemia'])

konf_alussa=konf1[0] rekov_alussa=rekov1[0] death_alussa=death1[0]

konf2=np.array(konf1)-konf_alussa

1. print(konf2)

1. quit(-1)

rekov2=np.array(rekov1)-rekov_alussa death2=np.array(death1)-death_alussa

aktiv_b=np.array(konf2)-np.array(rekov2)-np.array(death2) aktiv_c = scipy.signal.savgol_filter(aktiv_b,7, 1)

dates_a=dates0

fig, ax = plt.subplots(constrained_layout=True)

ax.legend(fontsize=14)

ax2=ax.twinx()

1. secax = ax.secondary_xaxis('top')
2. secax.set_xlabel('paivia')

plt.xticks(fontsize=18)

plt.yticks(fontsize=18, rotation=0)

ax.set_xlabel('Kuukausi 2020-2021', color='g',size=16) ax.set_ylabel('Kuolleita', color='k',size=18) ax.set_title('Koronavirusepidemia', color='b',size=22) ax2.set_ylabel('Tapauksia', color='#7f0000', size=18)

ax.tick_params(axis='both', which='major', labelsize=18)

ax2.plot(dates_a, konf2,'y.-',linewidth=4.0, label='tapauksia') ax2.plot(dates_a, aktiv_c,'r-',linewidth=4.0, label='sairaana') ax2.plot(dates_a, rekov2,'g-',linewidth=4.0, label='akuutein vaihe ohi') ax.plot(dates_a, death2,'k-',linewidth=4.0, label='kuolleita')

locator1 = mdates.MonthLocator() # every month

dateformat1 = mdates.DateFormatter('%b')

ax.xaxis.set_major_formatter(dateformat1) ax.xaxis.set_major_locator(locator1)

ax2.yaxis.set_major_locator(MaxNLocator(integer=True))

ax.legend(fontsize=14, loc="upper left") ax2.legend(fontsize=14, loc="center left")

plt.show()

plt.savefig('kuva.svg')