Notes

#Deaths
import pandas as pd
import csv
import itertools
import numpy as np
data2 = pd.read_csv('time_series_covid19_deaths_global.csv')
df3 = data2.groupby("Country/Region")[data2.columns].sum()
#Drop Column after 31 March 2020
df_3=df3.drop(df3.columns[72:],axis=1)
df4 = df_3.sort_values(by=[df_3.columns[71]],ascending=False)
df5=df4.drop(['Lat','Long'], axis=1)
df8=df5.T
def keep_cols(Data, keep_these):
"""Keep only the columns [keep_these] in a DataFrame, delete
all other columns.
"""
drop_these = list(set(list(Data)) - set(keep_these))
return Data.drop(drop_these, axis = 1)

new_data = df8.pipe(keep_cols, ['Pakistan', 'Poland','Philippines','Thailand','Ecuador','Luxembourg'])
new_data.plot(figsize=(20,10))
plt.legend(fontsize=15)
plt.title("Deaths in Top 5 Countries with Similar Spread as Pakistan", loc='center', fontsize=20, fontweight=0, color='Orange')
plt.xlabel("Time Series",fontsize=25)
plt.ylabel("Deaths",fontsize=25)



#Recovered
import pandas as pd
import csv
import itertools
import numpy as np
data2 = pd.read_csv('time_series_covid19_recovered_global.csv')
df3 = data2.groupby("Country/Region")[data2.columns].sum()
#Drop Column after 31 March 2020
df_3=df3.drop(df3.columns[72:],axis=1)
df4 = df_3.sort_values(by=[df_3.columns[71]],ascending=False)
df5=df4.drop(['Lat','Long'], axis=1)
df9=df5.T
def keep_cols(Data, keep_these):
"""Keep only the columns [keep_these] in a DataFrame, delete
all other columns.
"""
drop_these = list(set(list(Data)) - set(keep_these))
return Data.drop(drop_these, axis = 1)

new_data = df9.pipe(keep_cols, ['Pakistan', 'Poland','Philippines','Thailand','Ecuador','Luxembourg'])
new_data.plot(figsize=(20,10))
plt.legend(fontsize=15)
plt.title("Recovered cases in Top 5 Countries with Similar Spread as Pakistan", loc='center', fontsize=20, fontweight=0, color='Orange')
plt.xlabel("Time Series",fontsize=25)
plt.ylabel("Recovered Cases",fontsize=25)





#Confirmed
import pandas as pd
import csv
import itertools
import numpy as np
data2 = pd.read_csv('time_series_covid19_confirmed_global.csv')
df3 = data2.groupby("Country/Region")[data2.columns].sum()
#Drop Column after 31 March 2020
df_3=df3.drop(df3.columns[72:],axis=1)
df4 = df_3.sort_values(by=[df_3.columns[71]],ascending=False)
df5=df4.drop(['Lat','Long'], axis=1)
df7=df5.T
def keep_cols(Data, keep_these):
"""Keep only the columns [keep_these] in a DataFrame, delete
all other columns.
"""
drop_these = list(set(list(Data)) - set(keep_these))
return Data.drop(drop_these, axis = 1)

new_data = df7.pipe(keep_cols, ['Pakistan', 'Poland','Philippines','Thailand','Ecuador','Luxembourg'])
new_data.plot(figsize=(20,10))
plt.legend(fontsize=15)
plt.title("Confirmed cases in Top 5 Countries with Similar Spread as Pakistan", loc='center', fontsize=20, fontweight=0, color='Orange')
plt.xlabel("Time Series",fontsize=25)
plt.ylabel("Confirmed Cases",fontsize=25)