Canada Covid-19 Data Visualization

import pandas as pd
import numpy as np 
import seaborn as sns
import matplotlib.pyplot as plt 
import ipywidgets as widgets
import plotly.express as px
import plotly.graph_objects as go
from ipywidgets import interact, interactive, fixed, interact_manual

df_cases = pd.read_csv('https://raw.githubusercontent.com/ishaberry/Covid19Canada/master/timeseries_prov/cases_timeseries_prov.csv')
df_deaths = pd.read_csv('https://raw.githubusercontent.com/ishaberry/Covid19Canada/master/timeseries_prov/mortality_timeseries_prov.csv')
df_recovered = pd.read_csv('https://raw.githubusercontent.com/ishaberry/Covid19Canada/master/timeseries_prov/recovered_timeseries_prov.csv')
df_testing = pd.read_csv('https://raw.githubusercontent.com/ishaberry/Covid19Canada/master/timeseries_prov/testing_timeseries_prov.csv')

df_cases

	province	date_report	cases	cumulative_cases
0	Alberta	25-01-2020	0	0
1	Alberta	26-01-2020	0	0
2	Alberta	27-01-2020	0	0
3	Alberta	28-01-2020	0	0
4	Alberta	29-01-2020	0	0
...	...	...	...	...
5133	Yukon	21-01-2021	0	70
5134	Yukon	22-01-2021	0	70
5135	Yukon	23-01-2021	0	70
5136	Yukon	24-01-2021	0	70
5137	Yukon	25-01-2021	0	70

5138 rows × 4 columns

df_deaths

	province	date_death_report	deaths	cumulative_deaths
0	Alberta	08-03-2020	0	0
1	Alberta	09-03-2020	0	0
2	Alberta	10-03-2020	0	0
3	Alberta	11-03-2020	0	0
4	Alberta	12-03-2020	0	0
...	...	...	...	...
4531	Yukon	21-01-2021	0	1
4532	Yukon	22-01-2021	0	1
4533	Yukon	23-01-2021	0	1
4534	Yukon	24-01-2021	0	1
4535	Yukon	25-01-2021	0	1

4536 rows × 4 columns

df_recovered

	province	date_recovered	recovered	cumulative_recovered
0	Alberta	12-02-2020	0	0
1	Alberta	13-02-2020	0	0
2	Alberta	14-02-2020	0	0
3	Alberta	15-02-2020	0	0
4	Alberta	16-02-2020	0	0
...	...	...	...	...
4881	Yukon	21-01-2021	0	69
4882	Yukon	22-01-2021	0	69
4883	Yukon	23-01-2021	0	69
4884	Yukon	24-01-2021	0	69
4885	Yukon	25-01-2021	0	69

4886 rows × 4 columns

df_testing

	province	date_testing	testing	cumulative_testing	testing_info
0	Alberta	15-03-2020	7108	7108	NaN
1	Alberta	16-03-2020	3490	10598	NaN
2	Alberta	17-03-2020	1757	12355	NaN
3	Alberta	18-03-2020	2211	14566	NaN
4	Alberta	19-03-2020	2447	17013	NaN
...	...	...	...	...	...
4433	Yukon	21-01-2021	7	6210	NaN
4434	Yukon	22-01-2021	6	6216	NaN
4435	Yukon	23-01-2021	0	6216	NaN
4436	Yukon	24-01-2021	0	6216	NaN
4437	Yukon	25-01-2021	13	6229	NaN

4438 rows × 5 columns

df_cases['date_report']=pd.to_datetime(df_cases['date_report'])
df_deaths['date_death_report'] = pd.to_datetime(df_deaths['date_death_report'])
df_recovered['date_recovered'] = pd.to_datetime(df_recovered['date_recovered'])
df_testing['date_testing'] = pd.to_datetime(df_testing['date_testing'])

df1 = df_testing.merge(df_recovered,how='outer',left_on=['date_testing','province'],right_on=['date_recovered','province'])

df1

	province	date_testing	testing	cumulative_testing	testing_info	date_recovered	recovered	cumulative_recovered
0	Alberta	2020-03-15	7108.0	7108.0	NaN	2020-03-15	0	0
1	Alberta	2020-03-16	3490.0	10598.0	NaN	2020-03-16	0	0
2	Alberta	2020-03-17	1757.0	12355.0	NaN	2020-03-17	0	0
3	Alberta	2020-03-18	2211.0	14566.0	NaN	2020-03-18	0	0
4	Alberta	2020-03-19	2447.0	17013.0	NaN	2020-03-19	2	2
...	...	...	...	...	...	...	...	...
4881	Yukon	NaT	NaN	NaN	NaN	2020-10-03	0	0
4882	Yukon	NaT	NaN	NaN	NaN	2020-11-03	0	0
4883	Yukon	NaT	NaN	NaN	NaN	2020-12-03	0	0
4884	Yukon	NaT	NaN	NaN	NaN	2020-03-13	0	0
4885	Yukon	NaT	NaN	NaN	NaN	2020-03-14	0	0

4886 rows × 8 columns

df2=df1.merge(df_deaths,how='outer',left_on=['date_recovered','province'],right_on=['date_death_report','province'])

df2

	province	date_testing	testing	cumulative_testing	testing_info	date_recovered	recovered	cumulative_recovered	date_death_report	deaths	cumulative_deaths
0	Alberta	2020-03-15	7108.0	7108.0	NaN	2020-03-15	0	0	2020-03-15	0.0	0.0
1	Alberta	2020-03-16	3490.0	10598.0	NaN	2020-03-16	0	0	2020-03-16	0.0	0.0
2	Alberta	2020-03-17	1757.0	12355.0	NaN	2020-03-17	0	0	2020-03-17	0.0	0.0
3	Alberta	2020-03-18	2211.0	14566.0	NaN	2020-03-18	0	0	2020-03-18	0.0	0.0
4	Alberta	2020-03-19	2447.0	17013.0	NaN	2020-03-19	2	2	2020-03-19	1.0	1.0
...	...	...	...	...	...	...	...	...	...	...	...
4881	Yukon	NaT	NaN	NaN	NaN	2020-10-03	0	0	2020-10-03	0.0	0.0
4882	Yukon	NaT	NaN	NaN	NaN	2020-11-03	0	0	2020-11-03	0.0	0.0
4883	Yukon	NaT	NaN	NaN	NaN	2020-12-03	0	0	2020-12-03	0.0	0.0
4884	Yukon	NaT	NaN	NaN	NaN	2020-03-13	0	0	2020-03-13	0.0	0.0
4885	Yukon	NaT	NaN	NaN	NaN	2020-03-14	0	0	2020-03-14	0.0	0.0

4886 rows × 11 columns

df3=df2.merge(df_cases,how='outer',left_on=['date_recovered','province'],right_on=['date_report','province'])

df3

	province	date_testing	testing	cumulative_testing	testing_info	date_recovered	recovered	cumulative_recovered	date_death_report	deaths	cumulative_deaths	date_report	cases	cumulative_cases
0	Alberta	2020-03-15	7108.0	7108.0	NaN	2020-03-15	0.0	0.0	2020-03-15	0.0	0.0	2020-03-15	17	56
1	Alberta	2020-03-16	3490.0	10598.0	NaN	2020-03-16	0.0	0.0	2020-03-16	0.0	0.0	2020-03-16	18	74
2	Alberta	2020-03-17	1757.0	12355.0	NaN	2020-03-17	0.0	0.0	2020-03-17	0.0	0.0	2020-03-17	23	97
3	Alberta	2020-03-18	2211.0	14566.0	NaN	2020-03-18	0.0	0.0	2020-03-18	0.0	0.0	2020-03-18	22	119
4	Alberta	2020-03-19	2447.0	17013.0	NaN	2020-03-19	2.0	2.0	2020-03-19	1.0	1.0	2020-03-19	27	146
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
5133	Yukon	NaT	NaN	NaN	NaN	NaT	NaN	NaN	NaT	NaN	NaN	2020-07-02	0	0
5134	Yukon	NaT	NaN	NaN	NaN	NaT	NaN	NaN	NaT	NaN	NaN	2020-08-02	0	0
5135	Yukon	NaT	NaN	NaN	NaN	NaT	NaN	NaN	NaT	NaN	NaN	2020-09-02	0	0
5136	Yukon	NaT	NaN	NaN	NaN	NaT	NaN	NaN	NaT	NaN	NaN	2020-10-02	0	0
5137	Yukon	NaT	NaN	NaN	NaN	NaT	NaN	NaN	NaT	NaN	NaN	2020-11-02	0	0

5138 rows × 14 columns

df4=df3.sort_values('date_report',ascending=False)

data_set = df4.drop(columns=['date_testing','testing_info','date_recovered','date_death_report'])

data_set

	province	testing	cumulative_testing	recovered	cumulative_recovered	deaths	cumulative_deaths	date_report	cases	cumulative_cases
3156	PEI	1917.0	81756.0	1.0	95.0	0.0	0.0	2021-12-01	1	103
1254	New Brunswick	1329.0	164885.0	0.0	586.0	2.0	11.0	2021-12-01	17	817
2522	NWT	0.0	10231.0	0.0	24.0	0.0	0.0	2021-12-01	0	24
937	Manitoba	1373.0	441905.0	397.0	22692.0	7.0	747.0	2021-12-01	89	26537
4107	Saskatchewan	842.0	315256.0	226.0	14814.0	5.0	203.0	2021-12-01	248	18776
...	...	...	...	...	...	...	...	...	...	...
5019	NWT	NaN	NaN	NaN	NaN	NaN	NaN	2020-01-02	0	0
4947	New Brunswick	NaN	NaN	NaN	NaN	NaN	NaN	2020-01-02	0	0
5037	Ontario	NaN	NaN	NaN	NaN	NaN	NaN	2020-01-02	0	3
5109	Saskatchewan	NaN	NaN	NaN	NaN	NaN	NaN	2020-01-02	0	0
5073	Quebec	NaN	NaN	NaN	NaN	NaN	NaN	2020-01-02	0	0

5138 rows × 10 columns

data_set1=data_set.head(14)

data_set1

	province	testing	cumulative_testing	recovered	cumulative_recovered	deaths	cumulative_deaths	date_report	cases	cumulative_cases
3156	PEI	1917.0	81756.0	1.0	95.0	0.0	0.0	2021-12-01	1	103
1254	New Brunswick	1329.0	164885.0	0.0	586.0	2.0	11.0	2021-12-01	17	817
2522	NWT	0.0	10231.0	0.0	24.0	0.0	0.0	2021-12-01	0	24
937	Manitoba	1373.0	441905.0	397.0	22692.0	7.0	747.0	2021-12-01	89	26537
4107	Saskatchewan	842.0	315256.0	226.0	14814.0	5.0	203.0	2021-12-01	248	18776
1571	NL	289.0	75103.0	1.0	382.0	0.0	4.0	2021-12-01	0	393
3473	Quebec	7815.0	2611556.0	1982.0	199920.0	45.0	8782.0	2021-12-01	1934	232624
4424	Yukon	12.0	6118.0	0.0	63.0	0.0	1.0	2021-12-01	0	70
2839	Ontario	44802.0	8479734.0	3353.0	186829.0	64.0	5139.0	2021-12-01	2691	226657
620	BC	5785.0	1548105.0	603.0	51144.0	9.0	1019.0	2021-12-01	446	58553
303	Alberta	9374.0	2950446.0	1311.0	98178.0	38.0	1345.0	2021-12-01	652	112743
1888	Nova Scotia	2408.0	254759.0	0.0	1442.0	0.0	65.0	2021-12-01	1	1534
2205	Nunavut	-67.0	2490.0	0.0	265.0	0.0	2.0	2021-12-01	0	266
3790	Repatriated	0.0	0.0	0.0	13.0	0.0	0.0	2021-12-01	0	13

data_table = pd.DataFrame()
data_table['province'] = data_set1['province']
data_table['total_cases']= data_set1['cumulative_cases']
data_table['total_deaths']= data_set1['cumulative_deaths']
data_table['total_recovered']= data_set1['cumulative_recovered']
data_table['total_tested']= data_set1['cumulative_testing']

data_table

	province	total_cases	total_deaths	total_recovered	total_tested
3156	PEI	103	0.0	95.0	81756.0
1254	New Brunswick	817	11.0	586.0	164885.0
2522	NWT	24	0.0	24.0	10231.0
937	Manitoba	26537	747.0	22692.0	441905.0
4107	Saskatchewan	18776	203.0	14814.0	315256.0
1571	NL	393	4.0	382.0	75103.0
3473	Quebec	232624	8782.0	199920.0	2611556.0
4424	Yukon	70	1.0	63.0	6118.0
2839	Ontario	226657	5139.0	186829.0	8479734.0
620	BC	58553	1019.0	51144.0	1548105.0
303	Alberta	112743	1345.0	98178.0	2950446.0
1888	Nova Scotia	1534	65.0	1442.0	254759.0
2205	Nunavut	266	2.0	265.0	2490.0
3790	Repatriated	13	0.0	13.0	0.0

(data_table.style.set_properties(**{'text-align': 'right'}).background_gradient(cmap='Reds').hide_index()).set_caption(
    'province most affected by coronavirus')

province most affected by coronavirus

province	total_cases	total_deaths	total_recovered	total_tested
PEI	103	0.000000	95.000000	81756.000000
New Brunswick	817	11.000000	586.000000	164885.000000
NWT	24	0.000000	24.000000	10231.000000
Manitoba	26537	747.000000	22692.000000	441905.000000
Saskatchewan	18776	203.000000	14814.000000	315256.000000
NL	393	4.000000	382.000000	75103.000000
Quebec	232624	8782.000000	199920.000000	2611556.000000
Yukon	70	1.000000	63.000000	6118.000000
Ontario	226657	5139.000000	186829.000000	8479734.000000
BC	58553	1019.000000	51144.000000	1548105.000000
Alberta	112743	1345.000000	98178.000000	2950446.000000
Nova Scotia	1534	65.000000	1442.000000	254759.000000
Nunavut	266	2.000000	265.000000	2490.000000
Repatriated	13	0.000000	13.000000	0.000000

data_table_daily = pd.DataFrame()
data_table_daily['province'] = data_set1['province']
data_table_daily['cases']= data_set1['cases']
data_table_daily['deaths']= data_set1['deaths']
data_table_daily['recovered']= data_set1['recovered']
data_table_daily['tested']= data_set1['testing']

(data_table_daily.style.set_properties(**{'text-align': 'right'}).background_gradient(cmap='Reds').hide_index()).set_caption(
    'province most affected by coronavirus')

province most affected by coronavirus

province	cases	deaths	recovered	tested
PEI	1	0.000000	1.000000	1917.000000
New Brunswick	17	2.000000	0.000000	1329.000000
NWT	0	0.000000	0.000000	0.000000
Manitoba	89	7.000000	397.000000	1373.000000
Saskatchewan	248	5.000000	226.000000	842.000000
NL	0	0.000000	1.000000	289.000000
Quebec	1934	45.000000	1982.000000	7815.000000
Yukon	0	0.000000	0.000000	12.000000
Ontario	2691	64.000000	3353.000000	44802.000000
BC	446	9.000000	603.000000	5785.000000
Alberta	652	38.000000	1311.000000	9374.000000
Nova Scotia	1	0.000000	0.000000	2408.000000
Nunavut	0	0.000000	0.000000	-67.000000
Repatriated	0	0.000000	0.000000	0.000000

def covid_bubble_chart():
    df = data_table_daily
    fig = px.scatter(df, x="province", y="cases", size="cases", color="province",
               hover_name="province", size_max=90)
    fig.update_layout(
    title="Total province cases",
    xaxis_title="Province",
    yaxis_title="Confirmed Cases",
    width = 700
    )
    fig.show();
    

fig = go.FigureWidget( layout=go.Layout() )

interact(covid_bubble_chart)
ipywLayout = widgets.Layout(border='solid 2px green')
ipywLayout.display='none'
widgets.VBox([fig], layout=ipywLayout)

fig = px.treemap(data_table, 
                 path=["province"], 
                 values="total_cases", height=700,
                 title='The top 10 worst affected provinces - Deaths Cases',
                 color_discrete_sequence = px.colors.qualitative.Prism)

fig.data[0].textinfo = 'label+text+value'

fig.show()

data_table_sorted_cases=data_table.sort_values('total_cases',ascending=False)

fig = px.bar(data_table_sorted_cases,
    x = "province",
    y = "total_cases",
    title= "The Top 10 worst affected provinces - Confirmed", 
    color_discrete_sequence=["blue"], 
    height=600,
    width=1000
)

fig.show()

data_set

	province	testing	cumulative_testing	recovered	cumulative_recovered	deaths	cumulative_deaths	date_report	cases	cumulative_cases
3156	PEI	1917.0	81756.0	1.0	95.0	0.0	0.0	2021-12-01	1	103
1254	New Brunswick	1329.0	164885.0	0.0	586.0	2.0	11.0	2021-12-01	17	817
2522	NWT	0.0	10231.0	0.0	24.0	0.0	0.0	2021-12-01	0	24
937	Manitoba	1373.0	441905.0	397.0	22692.0	7.0	747.0	2021-12-01	89	26537
4107	Saskatchewan	842.0	315256.0	226.0	14814.0	5.0	203.0	2021-12-01	248	18776
...	...	...	...	...	...	...	...	...	...	...
5019	NWT	NaN	NaN	NaN	NaN	NaN	NaN	2020-01-02	0	0
4947	New Brunswick	NaN	NaN	NaN	NaN	NaN	NaN	2020-01-02	0	0
5037	Ontario	NaN	NaN	NaN	NaN	NaN	NaN	2020-01-02	0	3
5109	Saskatchewan	NaN	NaN	NaN	NaN	NaN	NaN	2020-01-02	0	0
5073	Quebec	NaN	NaN	NaN	NaN	NaN	NaN	2020-01-02	0	0

5138 rows × 10 columns

figura = px.bar(data_table_sorted_cases, 
             x="total_cases", y="province", 
                title='The Top 10 worst affected provinces - Confirmed', 
                text='total_cases', orientation='h', 
                color_discrete_sequence=["orange"], 
             width=800, height=700, range_x = [0, max(data_table_sorted_cases['total_cases'])])


figura.show()