✨ Refactored Analyser and added per-Million-Graphs
This commit is contained in:
parent
cadda056fd
commit
f1110d4f07
85
Analyser.py
85
Analyser.py
|
|
@ -35,6 +35,20 @@ class Analyser:
|
|||
self.df = pd.read_csv('statsfile.csv')
|
||||
self.df['dateRep'] = pd.to_datetime(self.df['dateRep'], format='%d/%m/%Y')
|
||||
|
||||
# Calculate total Numbers for each country
|
||||
self.df['totalCases'] = 0
|
||||
self.df['totalDeaths'] = 0
|
||||
self.df['deathRate'] = 0
|
||||
for country in self.df['countriesAndTerritories'].unique():
|
||||
countryData = self.df[self.df['countriesAndTerritories'].isin([country])]
|
||||
countryData = countryData.sort_values('dateRep')
|
||||
countryData['totalCases'] = countryData['cases'].cumsum()
|
||||
countryData['totalDeaths'] = countryData['deaths'].cumsum()
|
||||
countryData['deathRate'] = countryData['totalDeaths'] / countryData['totalCases'] * 100
|
||||
self.df.update(countryData)
|
||||
|
||||
print('DEBUG: Analyser initialized')
|
||||
|
||||
def getAvailableCountries(self):
|
||||
sorted = self.df.sort_values('countriesAndTerritories')
|
||||
return sorted['countriesAndTerritories'].unique()
|
||||
|
|
@ -65,7 +79,6 @@ class Analyser:
|
|||
|
||||
countryData = self.df[self.df['countriesAndTerritories'].isin([country])]
|
||||
countryData = countryData.sort_values('dateRep')
|
||||
countryData['totalCases'] = countryData['cases'].cumsum()
|
||||
countryData['7-Day-Mean'] = countryData['totalCases'].rolling(7).mean()
|
||||
mask = (countryData['dateRep'] >= start_date) & (countryData['dateRep'] <= end_date)
|
||||
countryTimeData = countryData.loc[mask]
|
||||
|
|
@ -150,7 +163,6 @@ class Analyser:
|
|||
|
||||
countryData = self.df[self.df['countriesAndTerritories'].isin([country])]
|
||||
countryData = countryData.sort_values('dateRep')
|
||||
countryData['totalDeaths'] = countryData['deaths'].cumsum()
|
||||
countryData['7-Day-Mean'] = countryData['totalDeaths'].rolling(7).mean()
|
||||
mask = (countryData['dateRep'] >= start_date) & (countryData['dateRep'] <= end_date)
|
||||
countryTimeData = countryData.loc[mask]
|
||||
|
|
@ -235,9 +247,6 @@ class Analyser:
|
|||
|
||||
countryData = self.df[self.df['countriesAndTerritories'].isin([country])]
|
||||
countryData = countryData.sort_values('dateRep')
|
||||
countryData['totalCases'] = countryData['cases'].cumsum()
|
||||
countryData['totalDeaths'] = countryData['deaths'].cumsum()
|
||||
countryData['deathRate'] = countryData['totalDeaths'] / countryData['totalCases'] * 100
|
||||
countryData['7-Day-Mean'] = countryData['deathRate'].rolling(7).mean()
|
||||
mask = (countryData['dateRep'] >= start_date) & (countryData['dateRep'] <= end_date)
|
||||
countryTimeData = countryData.loc[mask]
|
||||
|
|
@ -285,7 +294,6 @@ class Analyser:
|
|||
for index, country in enumerate([country, 'China', 'South_Korea'], start=1):
|
||||
countryTimeData = self.df[self.df['countriesAndTerritories'].isin([country])]
|
||||
countryTimeData = countryTimeData.sort_values('dateRep')
|
||||
countryTimeData['totalCases'] = countryTimeData['cases'].cumsum()
|
||||
countryTimeData[country] = countryTimeData['cases'].rolling(7).mean()
|
||||
|
||||
try:
|
||||
|
|
@ -310,7 +318,6 @@ class Analyser:
|
|||
|
||||
countryData = self.df[self.df['countriesAndTerritories'].isin([country])]
|
||||
countryData = countryData.sort_values('dateRep')
|
||||
countryData['totalCases'] = countryData['cases'].cumsum()
|
||||
countryData['increasePercentage'] = countryData['cases'] / countryData['totalCases'] * 100
|
||||
countryData['7-Day-Mean'] = countryData['increasePercentage'].rolling(7).mean()
|
||||
mask = (countryData['dateRep'] >= start_date) & (countryData['dateRep'] <= end_date)
|
||||
|
|
@ -326,3 +333,67 @@ class Analyser:
|
|||
plt.close()
|
||||
|
||||
return filePath
|
||||
|
||||
def getCasesPerMillionGraph(self, country, showPlot=False) -> str:
|
||||
fig = plt.figure()
|
||||
fig.dpi = 200.0
|
||||
ax = fig.add_subplot(111)
|
||||
plt.title('Cases per Million Citizens in ' + country + ' compared to top 20')
|
||||
|
||||
date = self.getAvailableDates()[len(self.getAvailableDates())-1]
|
||||
timeData = self.df
|
||||
mask = (timeData['dateRep'] == date)
|
||||
timeData = timeData.loc[mask]
|
||||
timeData = timeData.sort_values('countriesAndTerritories')
|
||||
timeData['casesPerMillion'] = ((timeData['totalCases'] / timeData['popData2018']) * 1000000)
|
||||
largestData = timeData.nlargest(20, 'casesPerMillion')
|
||||
|
||||
if country not in largestData['countriesAndTerritories'].unique():
|
||||
largestData = largestData.append(timeData.loc[timeData['countriesAndTerritories'] == country])
|
||||
|
||||
largestData.plot.bar(ax=ax, x="countriesAndTerritories", y="casesPerMillion")
|
||||
|
||||
# Hightlight the selected country
|
||||
for ticks in ax.xaxis.get_major_ticks():
|
||||
if ticks.label1.get_text() == country:
|
||||
ax.patches[largestData.index.get_indexer([ticks.label1.get_text])[0]].set_facecolor('r')
|
||||
|
||||
if showPlot:
|
||||
plt.show(block=True)
|
||||
filePath = ('graphs/casesPerMillionGraph_' + country + '_' + datetime.now().strftime('%Y-%m-%d'))
|
||||
fig.savefig(filePath)
|
||||
plt.close()
|
||||
|
||||
return filePath
|
||||
|
||||
def getDeathsPerMillionGraph(self, country, showPlot=False) -> str:
|
||||
fig = plt.figure()
|
||||
fig.dpi = 200.0
|
||||
ax = fig.add_subplot(111)
|
||||
plt.title('Deaths per Million Citizens in ' + country + ' compared to top 20')
|
||||
|
||||
date = self.getAvailableDates()[len(self.getAvailableDates())-1]
|
||||
timeData = self.df
|
||||
mask = (timeData['dateRep'] == date)
|
||||
timeData = timeData.loc[mask]
|
||||
timeData = timeData.sort_values('countriesAndTerritories')
|
||||
timeData['deathsPerMillion'] = ((timeData['totalDeaths'] / timeData['popData2018']) * 1000000)
|
||||
largestData = timeData.nlargest(20, 'deathsPerMillion')
|
||||
|
||||
if country not in largestData['countriesAndTerritories'].unique():
|
||||
largestData = largestData.append(timeData.loc[timeData['countriesAndTerritories'] == country])
|
||||
|
||||
largestData.plot.bar(ax=ax, x="countriesAndTerritories", y="deathsPerMillion")
|
||||
|
||||
# Hightlight the selected country
|
||||
for ticks in ax.xaxis.get_major_ticks():
|
||||
if ticks.label1.get_text() == country:
|
||||
ax.patches[largestData.index.get_indexer([ticks.label1.get_text])[0]].set_facecolor('r')
|
||||
|
||||
if showPlot:
|
||||
plt.show(block=True)
|
||||
filePath = ('graphs/deathsPerMillionGraph_' + country + '_' + datetime.now().strftime('%Y-%m-%d'))
|
||||
fig.savefig(filePath)
|
||||
plt.close()
|
||||
|
||||
return filePath
|
||||
|
|
|
|||
2
Main.py
2
Main.py
|
|
@ -5,10 +5,8 @@ Project: Analyse worldwide COVID-19 Data and provide graphs etc.
|
|||
@author Patrick Müller
|
||||
"""
|
||||
import DataFetcher as fetcher
|
||||
import Analyser as ana
|
||||
import UserInterface as UI
|
||||
|
||||
if __name__ == '__main__':
|
||||
fetcher.updateStatsFile()
|
||||
#ana.Analyser().getIsItOverGraph('Germany', showPlot=True)
|
||||
UI.main()
|
||||
|
|
|
|||
|
|
@ -78,8 +78,8 @@ class UserInterface(QMainWindow):
|
|||
labelBox.addWidget(graphTypePickerLabel)
|
||||
self.graphTypePicker = QComboBox(parent=self)
|
||||
self.graphTypePicker.addItems(
|
||||
['Total Cases', 'Case Increase', 'Increase Percentage', 'Total Deaths', 'Death Increase', 'Death Rate',
|
||||
'Is it going to end soon?'])
|
||||
['Total Cases', 'Case Increase', 'Increase Percentage', 'Cases per Million', 'Total Deaths',
|
||||
'Death Increase', 'Death Rate', 'Deaths per Million', 'Is it going to end soon?'])
|
||||
picklistBox.addWidget(self.graphTypePicker, 1)
|
||||
|
||||
# Calculate Button
|
||||
|
|
@ -140,7 +140,9 @@ class UserInterface(QMainWindow):
|
|||
deathGraphPath = self.analyser.getDeathGraph(country, startDate, endDate)
|
||||
deathIncreaseGraphPath = self.analyser.getDeathIncreaseGraph(country, startDate, endDate)
|
||||
deathRateGraphPath = self.analyser.getDailyDeathRateGraph(country, startDate, endDate)
|
||||
isItOverGraph = self.analyser.getIsItOverGraph(country)
|
||||
isItOverGraphPath = self.analyser.getIsItOverGraph(country)
|
||||
casesPerMillionGraphPath = self.analyser.getCasesPerMillionGraph(country)
|
||||
deathsPerMillionGraphPath = self.analyser.getDeathsPerMillionGraph(country)
|
||||
self.graphPlaceHolder = QLabel(self)
|
||||
self.clearLayout(self.graphBox)
|
||||
self.graphBox.addWidget(self.graphPlaceHolder)
|
||||
|
|
@ -158,7 +160,11 @@ class UserInterface(QMainWindow):
|
|||
elif self.graphTypePicker.currentText() == 'Death Rate':
|
||||
self.graphPlaceHolder.setPixmap(QPixmap(deathRateGraphPath))
|
||||
elif self.graphTypePicker.currentText() == 'Is it going to end soon?':
|
||||
self.graphPlaceHolder.setPixmap(QPixmap(isItOverGraph))
|
||||
self.graphPlaceHolder.setPixmap(QPixmap(isItOverGraphPath))
|
||||
elif self.graphTypePicker.currentText() == 'Cases per Million':
|
||||
self.graphPlaceHolder.setPixmap(QPixmap(casesPerMillionGraphPath))
|
||||
elif self.graphTypePicker.currentText() == 'Deaths per Million':
|
||||
self.graphPlaceHolder.setPixmap(QPixmap(deathsPerMillionGraphPath))
|
||||
|
||||
def clearLayout(self, layout):
|
||||
for i in reversed(range(layout.count())):
|
||||
|
|
|
|||
1504
statsfile.csv
1504
statsfile.csv
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue