Skip to content
Snippets Groups Projects
Commit 70d1b5f1 authored by Dr. Hamed Khalili's avatar Dr. Hamed Khalili
Browse files

Upload New File

parent 9775b30b
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
p_2/code/generating_data___month_encoded.ipynb 0 → 100644
+ 2497
− 0
View file @ 70d1b5f1
%% Cell type:code id:0127991b-fa6f-4dd8-bb75-c12beaffde73 tags:
``` python
###******************************HALLO*******************************
###***************************BAYESIAN GOVERMENT COVID APPLICATION**************************************************WRITEN BY:
###********************************************************************************************************HAMED KHALILI***********
###***************************INPUTS OF THE PROGRAM********************************************************************************************
#import pandas as pd
#import base64
import pandas as pd
incidence_days_number=7
CBook_i=pd.DataFrame({'index':[] ,'countriesAndTerritories':[], 'dateRep':[], 'cases':[] ,'Rescd':[] ,str(incidence_days_number)+'days_before_mean':[], str(incidence_days_number)+'days_after_mean':[] })
countries=['Netherlands','Germany']#
for tage in [7]:
incidence_days_number=tage
print(incidence_days_number)
#X=['MasksMandatoryAllSpaces','MasksMandatoryClosedSpaces']
method="hierarchical"#or#pooled#or#unpooled
###********************************************************************************************************************************************
#['ClosDaycare','ClosDaycarePartial','ClosPrimPartial','ClosSecPartial','ClosPrim','ClosSec','ClosHighPartial','ClosHigh']
#['RestaurantsCafes','RestaurantsCafesPartial']
#['GymsSportsCentres','GymsSportsCentresPartial']
#['Teleworking','TeleworkingPartial','WorkplaceClosuresPartial','AdaptationOfWorkplace','AdaptationOfWorkplacePartial','WorkplaceClosures']
#['MasksMandatoryClosedSpacesPartial','MasksMandatoryAllSpaces','MasksMandatoryClosedSpaces','MasksMandatoryAllSpacesPartial']
#y_pred =this is almost identical to y_est except we do not specify the observed data. PyMC considers this to be a stochastic node
#(as opposed to an observed node) and as the MCMC sampler runs - it also samples data from y_est.
"""
['Netherlands','Czechia','Lithuania','Austria','Poland','Slovenia','Estonia','Italy','Slovakia','Ireland','Denmark',
'Iceland','Cyprus','Greece','Belgium','Bulgaria','France','Germany','Latvia','Spain','Norway','Romania','Liechtenstein',
'Portugal','Luxembourg','Hungary','Malta','Croatia','Finland','Sweden']
['EntertainmentVenuesPartial','RestaurantsCafesPartial','EntertainmentVenues','MassGatherAll','ClosSec','GymsSportsCentresPartial','ClosPrim',
'NonEssentialShopsPartial','ClosPubAnyPartial','RestaurantsCafes','GymsSportsCentres','MassGather50','PrivateGatheringRestrictions',
'MassGatherAllPartial',
'ClosHigh','NonEssentialShops','ClosSecPartial','OutdoorOver500','ClosDaycare','BanOnAllEvents','IndoorOver500','QuarantineForInternationalTravellers',
'ClosHighPartial','IndoorOver100','Teleworking','ClosPubAny','PlaceOfWorshipPartial','MasksMandatoryClosedSpacesPartial','MassGather50Partial',
'StayHomeOrderPartial','OutdoorOver100','IndoorOver50','ClosPrimPartial','PrivateGatheringRestrictionsPartial','MasksMandatoryClosedSpaces',
'OutdoorOver1000','TeleworkingPartial','MasksMandatoryAllSpaces','OutdoorOver50','StayHomeOrder','QuarantineForInternationalTravellersPartial',
'MasksMandatoryAllSpacesPartial','StayHomeGen','PlaceOfWorship','ClosDaycarePartial','IndoorOver1000','BanOnAllEventsPartial',
'HotelsOtherAccommodationPartial',
'StayHomeRiskG','ClosureOfPublicTransportPartial','AdaptationOfWorkplace','HotelsOtherAccommodation','MasksVoluntaryClosedSpacesPartial',
'RegionalStayHomeOrderPartial','AdaptationOfWorkplacePartial','MasksVoluntaryAllSpaces','MasksVoluntaryAllSpacesPartial','MasksVoluntaryClosedSpaces',
'SocialCircle','WorkplaceClosures','RegionalStayHomeOrder','ClosureOfPublicTransport','StayHomeGenPartial','WorkplaceClosuresPartial',
'StayHomeRiskGPartial','SocialCirclePartial']
"""
###************MAIN BODY OF THE PROGRAM****************************************************************************************************
def add_elemant(element,lis,j):
for i in lis:
if element in i:
return i[j]
colors = ['#348ABD', '#A60628', '#7A68A6', '#467821', '#D55E00', '#CC79A7', '#56B4E9', '#009E73', '#F0E442', '#0072B2']
import pandas as pd
import datetime
from datetime import timedelta
import warnings
warnings.filterwarnings("ignore", category=FutureWarning)
import seaborn as sns
#import arviz as az
import itertools
import matplotlib.pyplot as plt
import numpy as np
# import pymc3 as pm
# import scipy
#import scipy.stats as stats
from IPython.display import Image
from sklearn import preprocessing
import pandas as pd
import datetime
from IPython.display import display
cb =pd.read_excel(r"C:\Users\Hamed\AppData\Roaming\Microsoft\Windows\Start Menu\Programs\Anaconda3 (64-bit)\datac.xlsx")
measures =pd.read_excel(r"C:\Users\Hamed\AppData\Roaming\Microsoft\Windows\Start Menu\Programs\Anaconda3 (64-bit)\response_graphs.xlsx")
#if method=="hierarchical":
#liss=[]
responses_plus=[]
responses_minus=[]
liss_plus = pd.DataFrame({'country':[],'mean':[],'std':[],'count+':[],'count-':[],'mean+':[],'mean-':[],'std+':[],'std-':[]})
for index,name in (enumerate(cb['countriesAndTerritories'].value_counts().index.tolist())):
#for name in['Germany']:
land=name
cb_2=cb.loc[(cb['countriesAndTerritories'] == land)]
cb_2=cb_2[['countriesAndTerritories','dateRep','cases']].iloc[::-1]
#cb=cb[(cb['dateRep']>=datetime.date(2020,2,3))] # df[(df['date']>datetime.date(2016,1,1))
cb_2['dateRep'] = pd.to_datetime(cb_2['dateRep'], format='%d/%m/%Y')
#cb_2=cb_2.loc[cb_2['dateRep']>='2020-03-02']
cb_2['cases'].values[cb_2['cases']<0] = cb_2['cases'].values[cb_2['cases']<0]*(-1)
cb_2['cases'].values[cb_2['cases']==0]=1
if cb_2.isnull().values.any():
cb_2['cases']=cb_2['cases'].interpolate()
cb_2=cb_2.reset_index()
measures_2=measures.loc[(measures['Country'] == land)]
if measures_2.isnull().values.any():
#print(measures_2[measures_2['E'].isna()])
measures_2=measures_2.dropna()
measures_2=measures_2.reset_index()
cooBook=cb_2
lst=[]
cooBook["Rescd"] = [list() for x in range(len(cooBook.index))]
measures_2['A'] = pd.to_datetime(measures_2['A'], format='%d/%m/%Y')
measures_2['E'] = pd.to_datetime(measures_2['E'], format='%d/%m/%Y')
for i in range (0,len(measures_2)):
#col="rc"#(measures['Measure'][i])
A=(measures_2['A'][i])
E=(measures_2['E'][i]++ timedelta(days=1))
#if col not in coBook.columns:
#coBook[col] = pd.Series(dtype='int')
for j in range (0,len(cooBook)):
date=cooBook['dateRep'][j]
#date_E=coBook['time_iso8601'][j-1]
#if coBook[col][j] != 1:
if date>=A and date<=E:
cooBook["Rescd"][j].append(measures_2['Measure'][i])
CBook=cooBook
#CBook['daily_cases']=CBook['daily_cases'].diff()
#CBook=CBook[1::]
#CBook=CBook.reset_index()
CBook[str(incidence_days_number)+'days_before_mean'] = pd.Series(dtype='float')
CBook[str(incidence_days_number)+'days_after_mean'] = pd.Series(dtype='float')
CBook = CBook.replace(np.nan, 0)
for i in range (incidence_days_number,len(CBook)-incidence_days_number):
caesdayNplusone=CBook.loc[i+incidence_days_number, ['cases']].to_list()[0]
averagecasesdayonetoNminusone_forward=sum(CBook.iloc[i:i+incidence_days_number]['cases'].values)/incidence_days_number
averagecasesdayonetoNminusone_backward=sum(CBook.iloc[i-incidence_days_number:i]['cases'].values)/incidence_days_number
#if averagecasesdayonetoNminusone ==0:
#print("00000000")
CBook.loc[i, [str(incidence_days_number)+'days_after_mean']]=averagecasesdayonetoNminusone_forward#/averagecasesdayonetoNminusone_backward-1
CBook.loc[i, [str(incidence_days_number)+'days_before_mean']]=averagecasesdayonetoNminusone_backward
CBook=CBook.loc[ (CBook['dateRep']>=min(CBook[incidence_days_number::]['dateRep']))]
#operator="or"
#mass='rpn_minus_one'+str(incidence_days_number)
#CBook[mass]=CBook[mass].pct_change()
#CBook=CBook.iloc[1: , :]
#CBook[[mass]] = CBook[[mass]].apply(lambda x: 100*x)
data_collecting_start_date=min(measures_2['A'])
data_collecting_end_date=max(measures_2['E'])
if land== 'Hungary':#03/03/2020-11/06/2021 for Hungary
data_collecting_start_date='2020-03-11'
data_collecting_end_date='2021-06-11'
if land== 'Iceland':#23/07/2020-03/12/2021 for
data_collecting_start_date='2020-07-23'
data_collecting_end_date='2020-12-04'
if land== 'Liechtenstein':# 01/10/2020-24/10/2022 for Liechtenstein
data_collecting_start_date='2020-12-31'
data_collecting_end_date='2022-03-31'#2020-03-10 14.04.2022
if land== 'Cyprus':# 01/10/2020-24/10/2022 for Liechtenstein
data_collecting_start_date='2020-10-03'
data_collecting_end_date='2022-04-14'#2020-03-10 14.04.2022
if land== 'Germany':# 01/10/2020-24/10/2022 for Liechtenstein
data_collecting_start_date='2020-02-24'
if land== 'Ireland':# 01/10/2020-24/10/2022 for Liechtenstein
data_collecting_start_date='2020-03-02'
CBook=CBook.loc[ (CBook['dateRep']>=data_collecting_start_date) ]
CBook=CBook.loc[ (CBook['dateRep']<=data_collecting_end_date) ]
CBook_i=pd.concat([CBook_i, CBook], axis=0)
#CBook_i
import category_encoders as ce
encoder= ce.BinaryEncoder(cols=['countriesAndTerritories'],return_df=True)
data_encoded=encoder.fit_transform(CBook_i)
data_encoded=pd.concat([data_encoded, data_encoded['dateRep'].dt.month%12], axis=1)
data_encoded=data_encoded.reset_index()
data_encoded.drop(data_encoded.columns[[0,1]], axis = 1, inplace = True)
data_encoded.columns=['countriesAndTerritories_0', 'countriesAndTerritories_1','countriesAndTerritories_2','countriesAndTerritories_3','countriesAndTerritories_4','dateRep','cases' ,'Rescd',str(incidence_days_number)+'days_before_mean',str(incidence_days_number)+'days_after_mean','month']
data_encoded=pd.concat([data_encoded, data_encoded['dateRep'].dt.week], axis=1)#CBook_i['dateRep'].dt.week
data_encoded.columns=['countriesAndTerritories_0', 'countriesAndTerritories_1','countriesAndTerritories_2','countriesAndTerritories_3','countriesAndTerritories_4','dateRep','cases' ,'Rescd',str(incidence_days_number)+'days_before_mean',str(incidence_days_number)+'days_after_mean','month','week']
data_encoded=pd.concat([data_encoded, data_encoded['dateRep'].dt.year], axis=1)#CBook_i['dateRep'].dt.week
data_encoded.columns=['countriesAndTerritories_0', 'countriesAndTerritories_1','countriesAndTerritories_2','countriesAndTerritories_3','countriesAndTerritories_4','dateRep','cases' ,'Rescd',str(incidence_days_number)+'days_before_mean',str(incidence_days_number)+'days_after_mean','month','week','year']
data_encoded=pd.concat([data_encoded, CBook_i[['countriesAndTerritories']].reset_index()], axis=1)
data_encoded['week'].mask((data_encoded['year'] == 2021) & (data_encoded['month'] ==1) & (data_encoded['week'] ==53) ,1, inplace=True)
data_encoded['week'].mask((data_encoded['year'] == 2022) & (data_encoded['month'] ==1) & (data_encoded['week'] ==52) ,1, inplace=True)
v = pd.read_excel(r"C:\Users\Hamed\Downloads\data(7).xlsx")
variant_plus = pd.DataFrame({'measure':[], 'v':[],'vd':[]})
import warnings
warnings.filterwarnings("ignore")
i=0
while i < len(v):
c=v.iloc[i]['country']
w=v.iloc[i]['year_week']
n=1
j=i
measure=c+w
s=[v.iloc[i]['variant']]
sp=[v.iloc[i]['percent_variant']]
while j+1< len (v) and v.iloc[j+1]['country']+v.iloc[j+1]['year_week']==measure:
# .tolist()==list(name) and :
#print(i)
s.append(v.iloc[j+1]['variant'])
sp.append(v.iloc[j+1]['percent_variant'])
n=n+1
j=j+1
#print(j)
if str(sp[0])=='nan':
s=['not_sequenced']
sp=[100]
info ={'measure':measure,'v':s,'vd':sp}
variant_plus = variant_plus.append(info, ignore_index = True)
i=j+1
variant_plus.columns=['country_year_week', 'variants','variants_percentage']
dist=dict()
for i in range (0, len(variant_plus)):
dist[variant_plus.iloc[i]['country_year_week']]=[variant_plus.iloc[i]['variants'],variant_plus.iloc[i]['variants_percentage']]
def valuation_formula(x, y,w):
a=x + str(y)+ '-'+ str(w)
if a in dist:
return dist[a]
else:
return [['not_sequenced'], [100]]
data_encoded['va'] = data_encoded.apply(lambda row: valuation_formula(row['countriesAndTerritories'], row['year'],row['week']), axis=1)
vaccin=pd.read_excel(r"C:\Users\Hamed\AppData\Roaming\Microsoft\Windows\Start Menu\Programs\Anaconda3 (64-bit)\data(6).xlsx")
cou=[]
for idx, name in (enumerate(v['country'].value_counts().index.tolist())):
cou.append( name)
cou_cod=[]
for idx, name in (enumerate(v['country_code'].value_counts().index.tolist())):
cou_cod.append( name)
vaccin_all=vaccin.loc[(vaccin['TargetGroup'] == 'ALL')]
vaccin_all=vaccin_all.sort_values(by = ['ReportingCountry','YearWeekISO'])
dist_vaccin=dict()
for index,name in (enumerate(vaccin_all['ReportingCountry'].value_counts().index.tolist())):
#for name in['Germany']:
land=name
vaccin_all_land=vaccin_all.loc[(vaccin_all['ReportingCountry'] == land)]
vaccin_all_land=vaccin_all_land.reset_index()
for i in range (0, len(vaccin_all_land)):
vaccin_all_land.iloc[i]['FirstDose']=vaccin_all_land.iloc[i]['FirstDose']/7
vaccin_all_land['CUMSUM_FirstDose'] = vaccin_all_land['FirstDose'].cumsum()
vaccin_all_land['CUMSUM_FirstDose'] =vaccin_all_land['CUMSUM_FirstDose'] /vaccin_all_land.iloc[0]['Population']
vaccin_all_land.iloc[i]['SecondDose']=vaccin_all_land.iloc[i]['SecondDose']/7
vaccin_all_land['CUMSUM_SecondDose'] = vaccin_all_land['SecondDose'].cumsum()
vaccin_all_land['CUMSUM_SecondDose'] =vaccin_all_land['CUMSUM_SecondDose'] /vaccin_all_land.iloc[0]['Population']
vaccin_all_land.iloc[i]['DoseAdditional1']=vaccin_all_land.iloc[i]['DoseAdditional1']/7
vaccin_all_land['CUMSUM_DoseAdditional1'] = vaccin_all_land['DoseAdditional1'].cumsum()
vaccin_all_land['CUMSUM_DoseAdditional1'] =vaccin_all_land['CUMSUM_DoseAdditional1'] /vaccin_all_land.iloc[0]['Population']
vaccin_all_land.iloc[i]['DoseAdditional2']=vaccin_all_land.iloc[i]['DoseAdditional2']/7
vaccin_all_land['CUMSUM_DoseAdditional2'] = vaccin_all_land['DoseAdditional2'].cumsum()
vaccin_all_land['CUMSUM_DoseAdditional2'] =vaccin_all_land['CUMSUM_DoseAdditional2'] /vaccin_all_land.iloc[0]['Population']
vaccin_all_land.iloc[i]['DoseAdditional3']=vaccin_all_land.iloc[i]['DoseAdditional3']/7
vaccin_all_land['CUMSUM_DoseAdditional3'] = vaccin_all_land['DoseAdditional3'].cumsum()
vaccin_all_land['CUMSUM_DoseAdditional3'] =vaccin_all_land['CUMSUM_DoseAdditional3'] /vaccin_all_land.iloc[0]['Population']
dist_vaccin[vaccin_all_land.iloc[i]['ReportingCountry']+vaccin_all_land.iloc[i]['YearWeekISO']]=[vaccin_all_land.iloc[i]['CUMSUM_FirstDose'],vaccin_all_land.iloc[i]['CUMSUM_SecondDose'],vaccin_all_land.iloc[i]['CUMSUM_DoseAdditional1'],vaccin_all_land.iloc[i]['CUMSUM_DoseAdditional2'],vaccin_all_land.iloc[i]['CUMSUM_DoseAdditional3']]
for index,name in (enumerate(vaccin_all['ReportingCountry'].value_counts().index.tolist())):
land=name
for y in range(2020,2023):
for w in range(1,57):
#for name in['Germany']:
if (y==2020 and w==1 and name+str(y)+'-W'+str(w) not in dist_vaccin):
dist_vaccin[name+str(y)+'-W'+str(w)]=[0,0,0,0,0]
if (y==2020 and w>1 and name+str(y)+'-W'+str(w) not in dist_vaccin):
dist_vaccin[name+str(y)+'-W'+str(w)]=dist_vaccin[name+str(y)+'-W'+str(w-1)]
if (y==2021 and w==1 and name+str(y)+'-W'+str(w) not in dist_vaccin):
dist_vaccin[name+str(y)+'-W'+str(w)]=dist_vaccin[name+str(y-1)+'-W'+str(56)]
if (y==2021 and w>1 and name+str(y)+'-W'+str(w) not in dist_vaccin):
dist_vaccin[name+str(y)+'-W'+str(w)]=dist_vaccin[name+str(y)+'-W'+str(w-1)]
if (y==2022 and w==1 and name+str(y)+'-W'+str(w) not in dist_vaccin):
dist_vaccin[name+str(y)+'-W'+str(w)]=dist_vaccin[name+str(y-1)+'-W'+str(56)]
if (y==2022 and w>1 and name+str(y)+'-W'+str(w) not in dist_vaccin):
dist_vaccin[name+str(y)+'-W'+str(w)]=dist_vaccin[name+str(y)+'-W'+str(w-1)]
def valuation_formula(x,y,w):
x=cou_cod[cou.index(x)]
a=x + str(y)+ '-W'+ str(w)
if a in dist_vaccin:
return dist_vaccin[a]
else:
return [0,0,0,0,0]
data_encoded['vaccin'] = data_encoded.apply(lambda row: valuation_formula(row['countriesAndTerritories'], row['year'],row['week']), axis=1)
pd.set_option('display.max_columns', 500)
v_list=['not_sequenced']
for idx, name in (enumerate(v['variant'].value_counts().index.tolist())):
v_list.append( name)
measures_list=[]
for idx, name in (enumerate(measures['Measure'].value_counts().index.tolist())):
measures_list.append( name)
def vf(x,y):
if x in y:
return 1
else:
return 0
def vf(x,y):
if x in y:
return 1
else:
return 0
for i in measures_list:
data_encoded[i] = data_encoded.apply(lambda row: vf(i, row['Rescd']), axis=1)
def vaf(x,y):
if x in y[0]:
return y[1][y[0].index(x)]
else:
return 0
for i in v_list:
data_encoded[i] = data_encoded.apply(lambda row: vaf(i, row['va']), axis=1)
def vac(x,i):
return x[i]
for i in range (0,5):
data_encoded['vaccin_'+str(i)] = data_encoded.apply(lambda row: vac(row['vaccin'],i), axis=1)
data_encoded_i= data_encoded
encoder= ce.BinaryEncoder(cols=['month'],return_df=True)
data_encoded=encoder.fit_transform(data_encoded)
data_encoded=pd.concat([data_encoded, data_encoded_i[['month']]], axis=1)
writer = pd.ExcelWriter('data_encoded.xlsx', engine='xlsxwriter')
data_encoded.to_excel('data_encoded.xlsx', sheet_name='1', index=False)
#data_encoded
for i in range(0,len(data_encoded)):
#if data_encoded.iloc[i]['cases']==0:
if data_encoded.iloc[i]['7days_before_mean']==0:#sum(data_encoded.iloc[i-7:i]['cases'].values)/7):
print(i,data_encoded.iloc[i]['countriesAndTerritories'],data_encoded.iloc[i]['dateRep'])
df=data_encoded
for i in range (0, len(df)-1):
if df.iloc[i]['dateRep']+datetime.timedelta(days=1)!=df.iloc[i+1]['dateRep'] and df.iloc[i]['countriesAndTerritories']==df.iloc[i+1]['countriesAndTerritories']:
print(df.iloc[i]['countriesAndTerritories'],df.iloc[i]['dateRep'],df.iloc[i+1]['dateRep'])
```
%% Output
7
%% Cell type:code id:c05338be-25fc-4cd3-b52a-0e3a2b6c8bd1 tags:
``` python
data_encoded =pd.read_excel(r"C:\Users\Hamed\data_encoded.xlsx")
df=data_encoded
nnn_data_encoded=df.head(0)
nnn_data_encoded['rp_zeitraum'] = pd.Series(dtype='float')
nnn_data_encoded = nnn_data_encoded.replace(np.nan, 0)
lll=nnn_data_encoded.columns.values.tolist()
nnn=30
for index, name in (enumerate(df['countriesAndTerritories'].value_counts().index.tolist())):
#for name in['Germany']:
land=name
#print(land)
data_encoded_land=df.loc[(df['countriesAndTerritories'] == land)].reset_index()
for i in range (nnn-1, len(data_encoded_land)):
#data_encoded_zeitraum=data_encoded_land[i-nnn+1:i:]
rp_zeitraum=data_encoded_land.iloc[i]['7days_after_mean']/data_encoded_land.iloc[i-nnn+1]['7days_before_mean']
v=data_encoded_land[i-nnn+1:i:].drop(['dateRep', 'cases' , 'Rescd' , 'week' ,'year' , 'month', 'countriesAndTerritories', 'va' , 'vaccin' , 'index'], axis=1).mean(axis='index')
a=pd.DataFrame([v]).reset_index()
b=data_encoded_land[i:i+1:][['dateRep', 'cases' , 'Rescd' , 'week' ,'year' , 'month', 'countriesAndTerritories', 'va' , 'vaccin' , 'index']].reset_index()
c=pd.concat([a, b.reindex(a.index)], axis=1)
c['rp_zeitraum'] = pd.Series(dtype='float')
c = c.replace(np.nan, 0)
c['rp_zeitraum']=c['rp_zeitraum'].apply(lambda x:rp_zeitraum)
c=c[lll]
c=c.drop(['index'], axis=1)
nnn_data_encoded=pd.concat([nnn_data_encoded, c], axis=0)
month_data_encoded=nnn_data_encoded
```
%% Cell type:code id:5b33cef1-82e3-4f8c-9c59-8a1847bf2520 tags:
``` python
writer = pd.ExcelWriter('month_data_encoded.xlsx', engine='xlsxwriter')
month_data_encoded.to_excel('month_data_encoded.xlsx', sheet_name='1', index=False)
month_data_encoded
```
%% Output
countriesAndTerritories_0 countriesAndTerritories_1 \
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
.. ... ...
0 1.0 1.0
0 1.0 1.0
0 1.0 1.0
0 1.0 1.0
0 1.0 1.0
countriesAndTerritories_2 countriesAndTerritories_3 \
0 0.0 1.0
0 0.0 1.0
0 0.0 1.0
0 0.0 1.0
0 0.0 1.0
.. ... ...
0 1.0 0.0
0 1.0 0.0
0 1.0 0.0
0 1.0 0.0
0 1.0 0.0
countriesAndTerritories_4 dateRep cases \
0 0.0 2020-03-29 2599.0
0 0.0 2020-03-30 4376.0
0 0.0 2020-03-31 7578.0
0 0.0 2020-04-01 4861.0
0 0.0 2020-04-02 2116.0
.. ... ... ...
0 1.0 2020-11-30 21.0
0 1.0 2020-12-01 20.0
0 1.0 2020-12-02 15.0
0 1.0 2020-12-03 14.0
0 1.0 2020-12-04 14.0
Rescd 7days_before_mean \
0 ['ClosDaycare', 'ClosHighPartial', 'ClosPubAny... 790.871921
0 ['ClosDaycare', 'ClosHighPartial', 'ClosPubAny... 904.541872
0 ['ClosDaycare', 'ClosHighPartial', 'ClosPubAny... 1019.802956
0 ['ClosDaycare', 'ClosHighPartial', 'ClosPubAny... 1140.788177
0 ['ClosDaycare', 'ClosHighPartial', 'ClosPubAny... 1286.832512
.. ... ...
0 ['ClosPubAnyPartial', 'EntertainmentVenues', '... 32.187192
0 ['ClosPubAnyPartial', 'EntertainmentVenues', '... 29.433498
0 ['ClosPubAnyPartial', 'EntertainmentVenues', '... 27.137931
0 ['ClosPubAnyPartial', 'EntertainmentVenues', '... 25.426108
0 ['ClosPubAnyPartial', 'EntertainmentVenues', '... 24.054187
7days_after_mean month_0 month_1 month_2 month_3 week year \
0 1741.147783 0.034483 0.034483 0.000000 0.965517 13 2020
0 1891.231527 0.000000 0.000000 0.000000 1.000000 14 2020
0 2036.330049 0.000000 0.000000 0.000000 1.000000 14 2020
0 2178.492611 0.000000 0.000000 0.000000 1.000000 14 2020
0 2300.748768 0.000000 0.000000 0.034483 0.965517 14 2020
.. ... ... ... ... ... ... ...
0 20.995074 1.000000 0.000000 0.000000 1.000000 49 2020
0 20.719212 1.000000 0.000000 0.000000 1.000000 49 2020
0 20.502463 1.000000 0.000000 0.034483 0.965517 49 2020
0 20.315271 1.000000 0.000000 0.068966 0.931034 49 2020
0 20.098522 1.000000 0.000000 0.103448 0.896552 49 2020
index countriesAndTerritories \
0 NaN France
0 NaN France
0 NaN France
0 NaN France
0 NaN France
.. ... ...
0 NaN Iceland
0 NaN Iceland
0 NaN Iceland
0 NaN Iceland
0 NaN Iceland
va vaccin \
0 [['Other', 'XBB.1.5', 'B.1.351', 'B.1.617.2', ... [0, 0, 0, 0, 0]
0 [['Other', 'XBB.1.5', 'B.1.351', 'B.1.617.2', ... [0, 0, 0, 0, 0]
0 [['Other', 'XBB.1.5', 'B.1.351', 'B.1.617.2', ... [0, 0, 0, 0, 0]
0 [['Other', 'XBB.1.5', 'B.1.351', 'B.1.617.2', ... [0, 0, 0, 0, 0]
0 [['Other', 'XBB.1.5', 'B.1.351', 'B.1.617.2', ... [0, 0, 0, 0, 0]
.. ... ...
0 [['Other', 'XBB.1.5', 'B.1.351', 'B.1.617.2', ... [0, 0, 0, 0, 0]
0 [['Other', 'XBB.1.5', 'B.1.351', 'B.1.617.2', ... [0, 0, 0, 0, 0]
0 [['Other', 'XBB.1.5', 'B.1.351', 'B.1.617.2', ... [0, 0, 0, 0, 0]
0 [['Other', 'XBB.1.5', 'B.1.351', 'B.1.617.2', ... [0, 0, 0, 0, 0]
0 [['Other', 'XBB.1.5', 'B.1.351', 'B.1.617.2', ... [0, 0, 0, 0, 0]
EntertainmentVenuesPartial RestaurantsCafesPartial EntertainmentVenues \
0 0.000000 0.0 0.448276
0 0.000000 0.0 0.482759
0 0.000000 0.0 0.517241
0 0.000000 0.0 0.551724
0 0.000000 0.0 0.586207
.. ... ... ...
0 0.034483 1.0 1.000000
0 0.000000 1.0 1.000000
0 0.000000 1.0 1.000000
0 0.000000 1.0 1.000000
0 0.000000 1.0 1.000000
MassGatherAll ClosSec GymsSportsCentresPartial ClosPrim \
0 1.0 0.0 0.0 0.0
0 1.0 0.0 0.0 0.0
0 1.0 0.0 0.0 0.0
0 1.0 0.0 0.0 0.0
0 1.0 0.0 0.0 0.0
.. ... ... ... ...
0 1.0 0.0 1.0 0.0
0 1.0 0.0 1.0 0.0
0 1.0 0.0 1.0 0.0
0 1.0 0.0 1.0 0.0
0 1.0 0.0 1.0 0.0
NonEssentialShopsPartial ClosPubAnyPartial RestaurantsCafes \
0 0.0 0.0 0.448276
0 0.0 0.0 0.482759
0 0.0 0.0 0.517241
0 0.0 0.0 0.551724
0 0.0 0.0 0.586207
.. ... ... ...
0 1.0 1.0 0.000000
0 1.0 1.0 0.000000
0 1.0 1.0 0.000000
0 1.0 1.0 0.000000
0 1.0 1.0 0.000000
GymsSportsCentres MassGather50 PrivateGatheringRestrictions \
0 0.448276 0.0 0.413793
0 0.482759 0.0 0.448276
0 0.517241 0.0 0.482759
0 0.551724 0.0 0.517241
0 0.586207 0.0 0.551724
.. ... ... ...
0 0.000000 1.0 1.000000
0 0.000000 1.0 1.000000
0 0.000000 1.0 1.000000
0 0.000000 1.0 1.000000
0 0.000000 1.0 1.000000
MassGatherAllPartial ClosHigh NonEssentialShops ClosSecPartial \
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
.. ... ... ... ...
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
OutdoorOver500 ClosDaycare BanOnAllEvents IndoorOver500 \
0 0.0 0.448276 0.0 0.0
0 0.0 0.482759 0.0 0.0
0 0.0 0.517241 0.0 0.0
0 0.0 0.551724 0.0 0.0
0 0.0 0.586207 0.0 0.0
.. ... ... ... ...
0 0.0 0.000000 0.0 0.0
0 0.0 0.000000 0.0 0.0
0 0.0 0.000000 0.0 0.0
0 0.0 0.000000 0.0 0.0
0 0.0 0.000000 0.0 0.0
QuarantineForInternationalTravellers ClosHighPartial IndoorOver100 \
0 0.0 0.448276 0.0
0 0.0 0.482759 0.0
0 0.0 0.517241 0.0
0 0.0 0.551724 0.0
0 0.0 0.586207 0.0
.. ... ... ...
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
Teleworking ClosPubAny PlaceOfWorshipPartial \
0 0.413793 0.448276 0.0
0 0.448276 0.482759 0.0
0 0.482759 0.517241 0.0
0 0.517241 0.551724 0.0
0 0.551724 0.586207 0.0
.. ... ... ...
0 0.000000 0.000000 0.0
0 0.000000 0.000000 0.0
0 0.000000 0.000000 0.0
0 0.000000 0.000000 0.0
0 0.000000 0.000000 0.0
MasksMandatoryClosedSpacesPartial MassGather50Partial \
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
.. ... ...
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
StayHomeOrderPartial OutdoorOver100 IndoorOver50 ClosPrimPartial \
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
.. ... ... ... ...
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0
PrivateGatheringRestrictionsPartial MasksMandatoryClosedSpaces \
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
.. ... ...
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
OutdoorOver1000 TeleworkingPartial MasksMandatoryAllSpaces \
0 0.551724 0.0 0.0
0 0.586207 0.0 0.0
0 0.620690 0.0 0.0
0 0.655172 0.0 0.0
0 0.689655 0.0 0.0
.. ... ... ...
0 0.000000 0.0 0.0
0 0.000000 0.0 0.0
0 0.000000 0.0 0.0
0 0.000000 0.0 0.0
0 0.000000 0.0 0.0
OutdoorOver50 StayHomeOrder QuarantineForInternationalTravellersPartial \
0 0.0 0.413793 0.0
0 0.0 0.448276 0.0
0 0.0 0.482759 0.0
0 0.0 0.517241 0.0
0 0.0 0.551724 0.0
.. ... ... ...
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
MasksMandatoryAllSpacesPartial StayHomeGen PlaceOfWorship \
0 0.0 0.137931 0.0
0 0.0 0.137931 0.0
0 0.0 0.137931 0.0
0 0.0 0.137931 0.0
0 0.0 0.137931 0.0
.. ... ... ...
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
0 1.0 0.000000 0.0
ClosDaycarePartial IndoorOver1000 BanOnAllEventsPartial \
0 0.0 1.0 0.0
0 0.0 1.0 0.0
0 0.0 1.0 0.0
0 0.0 1.0 0.0
0 0.0 1.0 0.0
.. ... ... ...
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
HotelsOtherAccommodationPartial StayHomeRiskG \
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
.. ... ...
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
ClosureOfPublicTransportPartial AdaptationOfWorkplace \
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
.. ... ...
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
HotelsOtherAccommodation MasksVoluntaryClosedSpacesPartial \
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
.. ... ...
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
RegionalStayHomeOrderPartial AdaptationOfWorkplacePartial \
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
.. ... ...
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
MasksVoluntaryAllSpaces MasksVoluntaryAllSpacesPartial \
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
.. ... ...
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
0 0.0 0.0
MasksVoluntaryClosedSpaces SocialCircle WorkplaceClosures \
0 0.0 0.0 0.413793
0 0.0 0.0 0.448276
0 0.0 0.0 0.482759
0 0.0 0.0 0.517241
0 0.0 0.0 0.551724
.. ... ... ...
0 0.0 0.0 0.000000
0 0.0 0.0 0.000000
0 0.0 0.0 0.000000
0 0.0 0.0 0.000000
0 0.0 0.0 0.000000
RegionalStayHomeOrder ClosureOfPublicTransport StayHomeGenPartial \
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
.. ... ... ...
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
WorkplaceClosuresPartial StayHomeRiskGPartial SocialCirclePartial \
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
.. ... ... ...
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
0 0.0 0.0 0.0
not_sequenced B.1.617.2 BA.2 BA.5 Other B.1.1.7 BA.1 \
0 6.896552 0.0 0.062069 0.0 93.041379 0.000000 0.0
0 3.448276 0.0 0.072414 0.0 96.479310 0.000000 0.0
0 0.000000 0.0 0.072414 0.0 99.924138 0.003448 0.0
0 0.000000 0.0 0.072414 0.0 99.920690 0.006897 0.0
0 0.000000 0.0 0.072414 0.0 99.917241 0.010345 0.0
.. ... ... ... ... ... ... ...
0 0.000000 0.0 0.000000 0.0 100.000000 0.000000 0.0
0 0.000000 0.0 0.000000 0.0 99.962069 0.037931 0.0
0 0.000000 0.0 0.000000 0.0 99.924138 0.075862 0.0
0 0.000000 0.0 0.000000 0.0 99.886207 0.113793 0.0
0 0.000000 0.0 0.000000 0.0 99.848276 0.151724 0.0
BA.4 BA.2.75 BQ.1 XBB B.1.351 P.1 XBB.1.5 B.1.525 B.1.621 C.37 \
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
.. ... ... ... ... ... ... ... ... ... ...
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
B.1.617.1 B.1.616 B.1.620 B.1.427/B.1.429 P.3 UNK B.1.1.529 \
0 0.0 0.0 0.0 0.0 0.0 1.606897 0.0
0 0.0 0.0 0.0 0.0 0.0 1.641379 0.0
0 0.0 0.0 0.0 0.0 0.0 1.682759 0.0
0 0.0 0.0 0.0 0.0 0.0 1.703448 0.0
0 0.0 0.0 0.0 0.0 0.0 1.724138 0.0
.. ... ... ... ... ... ... ...
0 0.0 0.0 0.0 0.0 0.0 3.003448 0.0
0 0.0 0.0 0.0 0.0 0.0 3.031034 0.0
0 0.0 0.0 0.0 0.0 0.0 3.024138 0.0
0 0.0 0.0 0.0 0.0 0.0 3.017241 0.0
0 0.0 0.0 0.0 0.0 0.0 3.010345 0.0
BA.3 AY.4.2 BA.4/BA.5 SGTF B.1.1.7+E484K BA.2+L452X B.1.617.3 \
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
.. ... ... ... ... ... ... ...
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
vaccin_0 vaccin_1 vaccin_2 vaccin_3 vaccin_4 month rp_zeitraum
0 0.0 0.0 0.0 0.0 0.0 3 756.829268
0 0.0 0.0 0.0 0.0 0.0 3 336.711111
0 0.0 0.0 0.0 0.0 0.0 3 222.686567
0 0.0 0.0 0.0 0.0 0.0 4 145.469274
0 0.0 0.0 0.0 0.0 0.0 4 126.560606
.. ... ... ... ... ... ... ...
0 0.0 0.0 0.0 0.0 0.0 11 0.183333
0 0.0 0.0 0.0 0.0 0.0 0 0.216867
0 0.0 0.0 0.0 0.0 0.0 0 0.254002
0 0.0 0.0 0.0 0.0 0.0 0 0.270136
0 0.0 0.0 0.0 0.0 0.0 0 0.265971
[21549 rows x 124 columns]
%% Cell type:code id:358acefb-05a6-4298-b33a-cffa4ec17134 tags:
``` python
```
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment