11/1/22, 12:49 PM assignment.

ipynb - Colaboratory

import numpy as np
import pandas as pd
import matplotlib.pyplot  as plt
from sklearn.impute  import SimpleImputer

#Read the data:

d = pd.read_csv(r"/owid-covid-data.csv")

df =  pd.DataFrame(d)

#View the Data:

df.shape

(231176, 67)

df.head()

iso_code continent location date total_cases new_cases new_cases_smoothed to

2020-
0 AFG Asia Afghanistan 5.0 5.0 NaN
02-24

2020-
1 AFG Asia Afghanistan 5.0 0.0 NaN
02-25

2020-
2 AFG Asia Afghanistan 5.0 0.0 NaN
02-26

2020-
3 AFG Asia Afghanistan 5.0 0.0 NaN
02-27

2020-
4 AFG Asia Afghanistan 5.0 0.0 NaN
02-28

5 rows × 67 columns

df.dtypes

iso_code object

continent object

location object

date object

total_cases float64

...

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 1/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory

population float64

excess_mortality_cumulative_absolute float64

excess_mortality_cumulative float64

excess_mortality float64

excess_mortality_cumulative_per_million float64

Length: 67, dtype: object

df.describe(include = "all")

iso_code continent location date total_cases new_cases new_cases_smo

count 231176 218126 231176 231176 2.180760e+05 2.177610e+05 2.165650

unique 248 6 248 1034 NaN NaN

2021-
top MEX Europe Mexico NaN NaN
09-14

freq 1033 52934 1033 247 NaN NaN

mean NaN NaN NaN NaN 4.479755e+06 1.234293e+04 1.238437

std NaN NaN NaN NaN 2.798278e+07 8.510011e+04 8.31688

min NaN NaN NaN NaN 1.000000e+00 0.000000e+00 0.000000

25% NaN NaN NaN NaN 4.427000e+03 0.000000e+00 6.000000

50% NaN NaN NaN NaN 4.975150e+04 5.300000e+01 9.328600

75% NaN NaN NaN NaN 5.259428e+05 9.510000e+02 1.12157

max NaN NaN NaN NaN 6.299857e+08 4.081968e+06 3.436032

11 rows × 67 columns

df.columns

Index(['iso_code', 'continent', 'location', 'date', 'total_cases', 'new_cases',

'new_cases_smoothed', 'total_deaths', 'new_deaths',

'new_deaths_smoothed', 'total_cases_per_million',

'new_cases_per_million', 'new_cases_smoothed_per_million',

'total_deaths_per_million', 'new_deaths_per_million',

'new_deaths_smoothed_per_million', 'reproduction_rate', 'icu_patients',

'icu_patients_per_million', 'hosp_patients',

'hosp_patients_per_million', 'weekly_icu_admissions',

'weekly_icu_admissions_per_million', 'weekly_hosp_admissions',

'weekly_hosp_admissions_per_million', 'total_tests', 'new_tests',

'total_tests_per_thousand', 'new_tests_per_thousand',

'new_tests_smoothed', 'new_tests_smoothed_per_thousand',

'positive_rate', 'tests_per_case', 'tests_units', 'total_vaccinations',

'people_vaccinated', 'people_fully_vaccinated', 'total_boosters',

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 2/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory

'new_vaccinations', 'new_vaccinations_smoothed',

'total_vaccinations_per_hundred', 'people_vaccinated_per_hundred',

'people_fully_vaccinated_per_hundred', 'total_boosters_per_hundred',

'new_vaccinations_smoothed_per_million',

'new_people_vaccinated_smoothed',

'new_people_vaccinated_smoothed_per_hundred', 'stringency_index',

'population_density', 'median_age', 'aged_65_older', 'aged_70_older',

'gdp_per_capita', 'extreme_poverty', 'cardiovasc_death_rate',

'diabetes_prevalence', 'female_smokers', 'male_smokers',

'handwashing_facilities', 'hospital_beds_per_thousand',

'life_expectancy', 'human_development_index', 'population',

'excess_mortality_cumulative_absolute', 'excess_mortality_cumulative',

'excess_mortality', 'excess_mortality_cumulative_per_million'],

dtype='object')

,'new_cases_per_million','total_cases_per_million'],axis = 1, inplace = True)

# shape of table After dropping  some columns

df.shape

(231176, 63)

ndex. In our dataset we will rename the columns:

ion':'Country','continent':'Continent','iso_code':'ISO_code'},inplace = True )

#List the continent name:

continent =  list(df.Continent.unique())

continent

['Asia', nan, 'Europe', 'Africa', 'North America', 'South America', 'Oceania']

#simple imputer:

#Simple imputer helps with missing values in a dataset. In the below code, a simple imputer w

imputer = SimpleImputer(strategy='constant')

df2 = pd.DataFrame(imputer.fit_transform(df),columns=df.columns)

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 3/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory

df2

ISO_code Continent Country Date total_cases new_cases total_deaths n

2020-
0 AFG Asia Afghanistan 5.0 5.0 missing_value mis
02-24

2020-
1 AFG Asia Afghanistan 5.0 0.0 missing_value mis
02-25

2020-
2 AFG Asia Afghanistan 5.0 0.0 missing_value mis
02-26

2020-
3 AFG Asia Afghanistan 5.0 0.0 missing_value mis
02-27

2020-
4 AFG Asia Afghanistan 5.0 0.0 missing_value mis
02-28

... ... ... ... ... ... ... ...

2022-
231171 ZWE Africa Zimbabwe 257893.0 0.0 5606.0
10-25

2022-
231172 ZWE Africa Zimbabwe 257893.0 0.0 5606.0
10-26

2022-
231173 ZWE Africa Zimbabwe 257893.0 0.0 5606.0
10-27

2022-
231174 ZWE Africa Zimbabwe 257893.0 0.0 5606.0
10-28

2022-
231175 ZWE Africa Zimbabwe 257893.0 0.0 5606.0
10-29

231176 rows × 63 columns

df2.groupby(['Date','Country'])[['Date','Country','total_cases','total_deaths','total_vaccina

df2

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 4/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory

ISO_code Continent Country Date total_cases new_cases total_deaths n

2020-
0 AFG Asia Afghanistan 5.0 5.0 missing_value mis
02-24

2020-
1 AFG Asia Afghanistan 5.0 0.0 missing_value mis
02-25

2020-
2 AFG Asia Afghanistan 5.0 0.0 missing_value mis
02-26

2020-
3 AFG Asia Afghanistan 5.0 0.0 missing_value mis
02-27

2020-
4 AFG Asia Afghanistan 5.0 0.0 missing_value mis
02-28

... ... ... ... ... ... ... ...

2022-
231171 ZWE Africa Zimbabwe 257893.0 0.0 5606.0
10-25

2022-
231172 ZWE Africa Zimbabwe 257893.0 0.0 5606.0
10-26

2022-
231173 ZWE Africa Zimbabwe 257893.0 0.0 5606.0
10-27

2022-
df3 = df2.groupby(['Date','Country'])[['Date','Country','total_cases','total_deaths','total_v
231174 ZWE Africa Zimbabwe 257893.0 0.0 5606.0
10-28
df3.tail(10)

2022-
231175 ZWE Africa Zimbabwe 257893.0 0.0 5606.0
10-29

231176 rows × 63 columns

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 5/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory

Date Country total_cases total_deaths total_vaccinations

#change missing_value to 0

231166 2022-10-29 Wallis and Futuna 761.0 7.0 missing_value

231167 2022-10-29 World 629985701.0 6588602.0

231168 2022-10-29 Yemen 11939.0 2158.0 missing_value

231169 2022-10-29 Zambia 333674.0 4017.0 missing_value

231170 Date
2022-10-29 Country total_cases257893.0
Zimbabwe total_deaths 5606.0
total_vaccinations
missing_value
0
231171 2020-01-01
2022-10-30 Argentina Austria 0.0
missing_value 0.0
missing_value 0.0
missing_value
1
231172 2020-01-01
2022-10-30 MexicoGermany 0.0
missing_value 0.0
missing_value 0.0
missing_value
2
231173 2020-01-02
2022-10-30 Argentina Israel 0.0
missing_value 0.0
missing_value 0.0
missing_value
3
231174 2020-01-02
2022-10-30 MexicoMalaysia 0.0
missing_value 0.0
missing_value 0.0
missing_value
4
231175 2020-01-03
2022-10-30 Argentina Russia 0.0
missing_value 0.0
missing_value 0.0
missing_value
... ... ... ... ... ...

231171 2022-10-30 Austria 0.0 0.0 0.0

231172 2022-10-30 Germany 0.0 0.0 0.0

231173 2022-10-30 Israel 0.0 0.0 0.0

231174 2022-10-30 Malaysia 0.0 0.0 0.0

231175 2022-10-30 Russia 0.0 0.0 0.0

231176 rows × 5 columns

#total countries where total_deaths is greater than 1000000

df4=df3[df3['total_deaths']>1000000]

df4

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 6/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory

Date Country total_cases total_deaths total_vaccinations

45117 2020-09-16 World 29933149.0 1004634.0 0.000000e+00

45345 2020-09-17 World 30248717.0 1010285.0 0.000000e+00

45573 2020-09-18 World 30575342.0 1016140.0 0.000000e+00

45801 2020-09-19 World 30868423.0 1021413.0 0.000000e+00

46029 2020-09-20 World 31123528.0 1025401.0 0.000000e+00

... ... ... ... ... ...

231093 2022-10-29 North America 115473140.0 1525509.0 0.000000e+00

231132 2022-10-29 South America 64273975.0 1332168.0 9.290533e+08

231158 2022-10-29 United States 97447532.0 1070264.0 0.000000e+00

231159 2022-10-29 Upper middle income 138798900.0 2497566.0 5.321340e+09

231167 2022-10-29 World 629985701.0 6588602.0 1.288604e+10

4770 rows × 5 columns

#unique conuntries where total_deaths is greater than 1000000
countries = df4['Country'].unique()
print(len(countries))

print()
print("conuntry_deaths_greater_than_1000000 : ")
print()

conuntry_deaths_greater_than_1000000 = list(df4['Country'].unique())
conuntry_deaths_greater_than_1000000

10

conuntry_deaths_greater_than_1000000 :

['World',

'High income',

'Upper middle income',

'Europe',

'South America',

'Asia',

'Lower middle income',

'North America',

'European Union',

'United States']

New Section

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 7/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory

#plotting the trend
for idx in range(0, len(countries)):
 C = df4[df4['Country']==countries[idx]].reset_index()
 plt.scatter(np.arange(0, len(C)),C['total_cases'],color="blue",label="total_cases"
 plt.scatter(np.arange(0, len(C)),C['total_deaths'],color="red",label="total_deaths
 plt.scatter(np.arange(0, len(C)),C['total_vaccinations'],color="green", label="tot
 plt.title(countries[ idx])
 plt.xlabel("Number of days since first suspect")
 plt.ylabel("Number of cases")
 plt.legend()
 plt.show()

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 8/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 9/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 10/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory

#group the countries

df5 = df4.groupby(['Country']) [['Country', 'total_cases', 'total_deaths']].sum().reset_index
df5

Country total_cases total_deaths

0 Asia 5.521382e+10 5.806319e+08

1 Europe 7.241052e+10 8.742173e+08

2 European Union 3.696045e+10 2.760102e+08

3 High income 1.213026e+11 1.303327e+09

4 Lower middle income 3.455630e+10 5.294324e+08

5 North America 3.665789e+10 5.602120e+08

6 South America 2.429292e+10 6.009055e+08

7 United States 1.583746e+10 1.799059e+08

8 Upper middle income 5.491293e+10 1.225825e+09

9 World 2.286620e+11 3.447812e+09

C = df5

plt.scatter (np.arange(0,len (C)),C['total_cases'], color="blue", label="total_cases")

plt.scatter(np.arange(0,len (C)),C['total_deaths'], color="red", label="total_deaths")

plt.title("World")

plt.xlabel("Number of days since first suspect")

plt.ylabel("Number of cases")

plt.legend()

plt.show()

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 11/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory

#analysis by date where total_deaths is greater than 1000000

date = df4['Date'].unique()
len (date)

774

df6 = df4.groupby(['Date']) [[ 'Date', 'total_cases', 'total_deaths']].sum().reset_index()

df6

Date total_cases total_deaths

0 2020-09-16 2.993315e+07 1004634.0

1 2020-09-17 3.024872e+07 1010285.0

2 2020-09-18 3.057534e+07 1016140.0

3 2020-09-19 3.086842e+07 1021413.0

4 2020-09-20 3.112353e+07 1025401.0

... ... ... ...

769 2022-10-25 2.128946e+09 21647461.0

770 2022-10-26 2.130554e+09 21656263.0

771 2022-10-27 2.132099e+09 21665448.0

772 2022-10-28 2.133303e+09 21670280.0

773 2022-10-29 2.133942e+09 21672141.0

774 rows × 3 columns

#graph plotting by Date
C = df6
plt.scatter (np.arange(0,len (C)),C['total_cases'], color="blue", label="total_case
plt.scatter (np.arange(0,len (C)),C['total_deaths' ], color="red", label="total_dea
plt.title("World")
plt.xlabel("Number of days since first suspect")
plt.ylabel("Number of cases")
https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 12/13
11/1/22, 12:49 PM assignment.ipynb - Colaboratory
plt.ylabel( Number of cases )
plt.legend()
plt.show()

Colab paid products

check 0s completed at 12:36 PM

https://colab.research.google.com/drive/1AJFCKFDfnSSH-YAv3_nCI5B9eA7zmP7v#scrollTo=32WSiJI7AmH2&printMode=true 13/13