Paddy/covid-19-analysis
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

🐛 Reverted the refactor because it fucked the data up

Browse Source
This commit is contained in:
Patrick Müller 2020-03-30 17:49:23 +02:00
parent 4b7c6e6af2
commit 64d2950d59
1 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
Analyser.py
View File

@ -33,13 +33,10 @@ class Analyser:
self.df = pd.read_csv('statsfile.csv') self.df = pd.read_csv('statsfile.csv')
self.df['dateRep'] = pd.to_datetime(self.df['dateRep'], format='%d/%m/%Y') self.df['dateRep'] = pd.to_datetime(self.df['dateRep'], format='%d/%m/%Y')
self.df = self.df.sort_values('dateRep')
self.df['totalCases'] = self.df['cases'].cumsum()
self.df['totalDeaths'] = self.df['deaths'].cumsum()
self.df['deathRate'] = self.df['deaths'] / self.df['cases'] * 100
def getAvailableCountries(self): def getAvailableCountries(self):
return self.df['countriesAndTerritories'].unique() sorted = self.df.sort_values('countriesAndTerritories')
return sorted['countriesAndTerritories'].unique()
def getAvailableDates(self): def getAvailableDates(self):
retList = [] retList = []
@ -65,6 +62,8 @@ class Analyser:
countryData = self.df[self.df['countriesAndTerritories'].isin([country])] countryData = self.df[self.df['countriesAndTerritories'].isin([country])]
mask = (countryData['dateRep'] >= start_date) & (countryData['dateRep'] <= end_date) mask = (countryData['dateRep'] >= start_date) & (countryData['dateRep'] <= end_date)
countryTimeData = countryData.loc[mask] countryTimeData = countryData.loc[mask]
countryTimeData = countryTimeData.sort_values('dateRep')
countryTimeData['totalCases'] = countryTimeData['cases'].cumsum()
countryTimeData.plot(ax=ax, x='dateRep', y='totalCases') countryTimeData.plot(ax=ax, x='dateRep', y='totalCases')
@ -133,6 +132,8 @@ class Analyser:
countryData = self.df[self.df['countriesAndTerritories'].isin([country])] countryData = self.df[self.df['countriesAndTerritories'].isin([country])]
mask = (countryData['dateRep'] >= start_date) & (countryData['dateRep'] <= end_date) mask = (countryData['dateRep'] >= start_date) & (countryData['dateRep'] <= end_date)
countryTimeData = countryData.loc[mask] countryTimeData = countryData.loc[mask]
countryTimeData = countryTimeData.sort_values('dateRep')
countryTimeData['totalDeaths'] = countryTimeData['deaths'].cumsum()
countryTimeData.plot(ax=ax, x='dateRep', y='totalDeaths') countryTimeData.plot(ax=ax, x='dateRep', y='totalDeaths')
@ -189,6 +190,10 @@ class Analyser:
countryData = self.df[self.df['countriesAndTerritories'].isin([country])] countryData = self.df[self.df['countriesAndTerritories'].isin([country])]
mask = (countryData['dateRep'] >= start_date) & (countryData['dateRep'] <= end_date) mask = (countryData['dateRep'] >= start_date) & (countryData['dateRep'] <= end_date)
countryTimeData = countryData.loc[mask] countryTimeData = countryData.loc[mask]
countryTimeData = countryTimeData.sort_values('dateRep')
countryTimeData['totalCases'] = countryTimeData['cases'].cumsum()
countryTimeData['totalDeaths'] = countryTimeData['deaths'].cumsum()
countryTimeData['deathRate'] = countryTimeData['totalDeaths'] / countryTimeData['totalCases'] * 100
countryTimeData.plot(ax=ax, x='dateRep', y='deathRate') countryTimeData.plot(ax=ax, x='dateRep', y='deathRate')