In [1]:

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import folium # for leaflet maps

from IPython.display import HTML

HTML('''<script>
code_show=true; 
function code_toggle() {
 if (code_show){
 $('div.input').hide();
 } else {
 $('div.input').show();
 }
 code_show = !code_show
} 
$( document ).ready(code_toggle);
</script>
<form action="javascript:code_toggle()"><input type="submit" value="Click to show/unshow codes."></form>''')

Out[1]:

1. Map of reported cases¶

Kevin Siswandi. Last updated 29/03/2020.

Note: This analysis was originally made at the end of February 2020, when China (Hubei) was the epicentre of the outbreak. Therefore, I made separate analysis for China and the rest of the world.

Public data are provided by JHU. Latest data are available from https://github.com/CSSEGISandData/COVID-19

In [2]:

# read data
full_table = pd.read_csv('covid_19_clean_complete.csv', parse_dates=['Date'])

# combine china and mainland china
full_table['Country/Region'].replace({'China':'Mainland China'},inplace=True)
countries = full_table['Country/Region'].unique().tolist()

# filling missing values
full_table[['Province/State']] = full_table[['Province/State']].fillna('--')

print("\nTotal countries affected by CoVID-19 thus far: ",len(countries))
print("\nLatest daily case reports included in the notebook: ", str(max(full_table['Date']))[:10])

Total countries affected by CoVID-19 thus far:  188

Latest daily case reports included in the notebook:  2020-05-16

In [3]:

# cases in the Diamond Princess cruise ship
ship = full_table[full_table['Province/State']=='Diamond Princess cruise ship']
full_table = full_table[full_table['Province/State']!='Diamond Princess cruise ship']

# cases in china vs outside china
china = full_table[full_table['Country/Region']=='Mainland China']
row = full_table[full_table['Country/Region']!='Mainland China']

# latest numbers (cumulative)
full_latest = full_table[full_table['Date'] == max(full_table['Date'])].reset_index()
china_latest = full_latest[full_latest['Country/Region']=='Mainland China']
row_latest = full_latest[full_latest['Country/Region']!='Mainland China']

full_latest_grouped = full_latest.groupby('Country/Region')['Confirmed', 'Deaths', 'Recovered'].sum().reset_index()
china_latest_grouped = china_latest.groupby('Province/State')['Confirmed', 'Deaths', 'Recovered'].sum().reset_index()
row_latest_grouped = row_latest.groupby('Country/Region')['Confirmed', 'Deaths', 'Recovered'].sum().reset_index()

1.1. Latest number of cases by countries/provinces¶

For the dashboard by JHU see https://www.arcgis.com/apps/opsdashboard/index.html#/bda7594740fd40299423467b48e9ecf6

In [4]:

rl = row_latest.groupby('Country/Region')['Confirmed', 'Deaths', 'Recovered'].sum()
rl = rl.reset_index().sort_values(by='Confirmed', ascending=False).reset_index(drop=True)

ncl = rl.copy()[:20]
ncl['Affected'] = ncl['Confirmed'] - ncl['Deaths'] - ncl['Recovered']
ncl = ncl.melt(id_vars="Country/Region", value_vars=['Affected', 'Recovered', 'Deaths'])

fig = px.bar(ncl.sort_values(['variable', 'value']), 
             x="value", y="Country/Region", color='variable', orientation='h', height=800,
             # height=600, width=1000,
             title='Number of cases for the 20 most affected countries (excluding China)')
fig.update_layout(uniformtext_minsize=8, uniformtext_mode='hide')
fig.show()

# ------------------------------------------

cl = china_latest.groupby('Province/State')['Confirmed', 'Deaths', 'Recovered'].sum()
cl = cl.reset_index().sort_values(by='Confirmed', ascending=False).reset_index(drop=True)
# cl.head().style.background_gradient(cmap='rainbow')

ncl = cl.copy()
ncl['Affected'] = ncl['Confirmed'] - ncl['Deaths'] - ncl['Recovered']
ncl = ncl.melt(id_vars="Province/State", value_vars=['Affected', 'Recovered', 'Deaths'])

fig = px.bar(ncl.sort_values(['variable', 'value']), 
             y="value", x="Province/State", color='variable', orientation='v', height=800,
             # height=600, width=1000,
             title='Number of cases in China')
fig.update_layout(uniformtext_minsize=8, uniformtext_mode='hide')
fig.show()

1.2 Geographical map of the reported cases¶

In [5]:

full_latest = full_latest[full_latest['Province/State'] != 'Diamond Princess']

In [6]:

# map of reported cases worldwide

m = folium.Map(location=[10, -20], tiles='openstreetmap',
               min_zoom=1, max_zoom=4, zoom_start=2.3)

for i in range(0, len(full_latest)):
    folium.CircleMarker(
        location=[full_latest.iloc[i]['Lat'], full_latest.iloc[i]['Long']],
        color='crimson', 
        tooltip =   '<li><bold>Country : '+str(full_latest.iloc[i]['Country/Region'])+
                    '<li><bold>Province : '+str(full_latest.iloc[i]['Province/State'])+
                    '<li><bold>Confirmed : '+str(full_latest.iloc[i]['Confirmed'])+
                    '<li><bold>Deaths : '+str(full_latest.iloc[i]['Deaths'])+
                    '<li><bold>Recovered : '+str(full_latest.iloc[i]['Recovered']),
        radius=int(full_latest.iloc[i]['Confirmed']**0.2 + 1),
        fill_color='red',
        fill_opacity=0.7).add_to(m)
m

Out[6]:

1.3. Spread of CoVID-19 over time¶

Play with the interactive map below to visualize the progression of number of cases over time (from 22/1/2020). Note that the spread outside China only started to happen much later.

In [7]:

china_map = china.groupby(['Date', 'Province/State'])['Confirmed', 'Deaths', 'Recovered', 
                                                      'Lat', 'Long'].max()
china_map = china_map.reset_index()
china_map['size'] = china_map['Confirmed'].pow(0.5)
china_map['Date'] = pd.to_datetime(china_map['Date'])
china_map['Date'] = china_map['Date'].dt.strftime('%m/%d/%Y')
china_map.head()

fig = px.scatter_geo(china_map, lat='Lat', lon='Long', scope='asia',
                     color="size", size='size', hover_name='Province/State', 
                     hover_data=['Confirmed', 'Deaths', 'Recovered'],
                     projection="natural earth", animation_frame="Date", 
                     title='Spread in China over time')
fig.update(layout_coloraxis_showscale=False)
fig.show()

# -----------------------------------------------------------------------------------

formated_gdf = row.groupby(['Date', 'Country/Region'])['Confirmed', 'Deaths', 'Recovered'].max()
formated_gdf = formated_gdf.reset_index()
formated_gdf = formated_gdf[formated_gdf['Country/Region']!='Mainland China']
formated_gdf['Date'] = pd.to_datetime(formated_gdf['Date'])
formated_gdf['Date'] = formated_gdf['Date'].dt.strftime('%m/%d/%Y')

fig = px.scatter_geo(formated_gdf[formated_gdf['Country/Region']!='China'], 
                     locations="Country/Region", locationmode='country names', 
                     color="Confirmed", size='Confirmed', hover_name="Country/Region", 
                     range_color= [0, max(formated_gdf['Confirmed'])+2], 
                     projection="natural earth", animation_frame="Date", 
                     title='Spread outside China over time')
fig.update(layout_coloraxis_showscale=False)
fig.show()

1.4. Countries with highest number of deaths¶

In [8]:

# countries by highest deaths
temp_flg = full_latest_grouped[['Country/Region', 'Deaths']]
temp_flg = temp_flg.sort_values(by='Deaths', ascending=False)
temp_flg = temp_flg.reset_index(drop=True)
temp_flg = temp_flg[temp_flg['Deaths']>0]
temp_flg.style.background_gradient(cmap='Pastel1_r')

Out[8]:

	Country/Region	Deaths
0	US	88754
1	United Kingdom	34546
2	Italy	31763
3	Spain	27563
4	France	27532
5	Brazil	15662
6	Belgium	9005
7	Germany	7938
8	Iran	6937
9	Canada	5800
10	Netherlands	5689
11	Mexico	5045
12	Mainland China	4638
13	Turkey	4096
14	Sweden	3674
15	India	2871
16	Ecuador	2688
17	Russia	2537
18	Peru	2523
19	Switzerland	1879
20	Ireland	1533
21	Portugal	1203
22	Romania	1094
23	Indonesia	1089
24	Poland	915
25	Pakistan	834
26	Philippines	817
27	Japan	725
28	Austria	629
29	Egypt	612
30	Colombia	562
31	Denmark	543
32	Algeria	542
33	Ukraine	497
34	Hungary	448
35	Dominican Republic	428
36	Chile	421
37	Argentina	363
38	Bangladesh	314
39	Saudi Arabia	302
40	Finland	297
41	Czechia	296
42	Panama	269
43	Israel	268
44	South Korea	262
45	South Africa	261
46	Norway	232
47	Serbia	228
48	United Arab Emirates	214
49	Moldova	207
50	Morocco	192
51	Nigeria	176
52	Afghanistan	168
53	Bolivia	165
54	Greece	162
55	Belarus	160
56	Cameroon	140
57	Honduras	138
58	Bosnia and Herzegovina	129
59	Iraq	121
60	Malaysia	113
61	Kuwait	107
62	Bulgaria	105
63	Luxembourg	104
64	Slovenia	103
65	North Macedonia	98
66	Australia	98
67	Sudan	97
68	Croatia	95
69	Cuba	79
70	Estonia	63
71	Congo (Kinshasa)	61
72	Thailand	56
73	Lithuania	55
74	Armenia	55
75	Somalia	55
76	Burkina Faso	51
77	Niger	51
78	Andorra	51
79	Chad	50
80	Kenya	50
81	Mali	48
82	Tunisia	45
83	San Marino	41
84	Azerbaijan	36
85	Tajikistan	36
86	Kazakhstan	34
87	Guatemala	33
88	Albania	31
89	Sierra Leone	29
90	Kosovo	29
91	Ghana	29
92	Slovakia	28
93	Lebanon	26
94	El Salvador	26
95	Senegal	25
96	Cote d'Ivoire	25
97	Singapore	22
98	New Zealand	21
99	Oman	21
100	Tanzania	21
101	Liberia	20
102	Haiti	20
103	Uruguay	19
104	Latvia	19
105	Yemen	18
106	Cyprus	17
107	Guinea	16
108	Congo (Brazzaville)	15
109	Qatar	15
110	Kyrgyzstan	14
111	Diamond Princess	13
112	Georgia	12
113	Bahrain	12
114	Paraguay	11
115	Togo	11
116	Gabon	11
117	Bahamas	11
118	Uzbekistan	11
119	Venezuela	10
120	Mauritius	10
121	Costa Rica	10
122	Guyana	10
123	Iceland	10
124	Sri Lanka	9
125	Montenegro	9
126	Jordan	9
127	Jamaica	9
128	Trinidad and Tobago	8
129	Nicaragua	8
130	Sao Tome and Principe	7
131	Equatorial Guinea	7
132	Taiwan*	7
133	Barbados	7
134	Zambia	7
135	Burma	6
136	Malta	6
137	Ethiopia	5
138	Guinea-Bissau	4
139	Djibouti	4
140	South Sudan	4
141	Monaco	4
142	Mauritania	4
143	Maldives	4
144	Zimbabwe	4
145	Syria	3
146	Cabo Verde	3
147	Antigua and Barbuda	3
148	Malawi	3
149	Libya	3
150	Angola	2
151	West Bank and Gaza	2
152	Benin	2
153	Belize	2
154	Eswatini	2
155	MS Zaandam	2
156	Gambia	1
157	Brunei	1
158	Liechtenstein	1
159	Nepal	1
160	Suriname	1
161	Burundi	1
162	Comoros	1
163	Botswana	1

1.5. Countries with no recovered cases¶

In [9]:

# Countries with no cases recovered (yet)
temp = row_latest_grouped[row_latest_grouped['Recovered']==0]
temp = temp[['Country/Region', 'Confirmed', 'Deaths', 'Recovered']]
temp = temp.sort_values('Confirmed', ascending=False)
temp = temp.reset_index(drop=True)
temp.style.background_gradient(cmap='Pastel1_r')

Out[9]:

	Country/Region	Confirmed	Deaths
0	Canada	77206	5800
1	Tajikistan	1322	36
2	Mozambique	129	0
3	Syria	51	3
4	Timor-Leste	24	0
5	MS Zaandam	9	2
6	Lesotho	1	0

1.6. Number of new reported cases daily¶

In [10]:

temp = full_table.groupby(['Country/Region', 'Date', ])['Confirmed', 'Deaths', 'Recovered']
temp = temp.sum().diff().reset_index()

mask = temp['Country/Region'] != temp['Country/Region'].shift(1)

temp.loc[mask, 'Confirmed'] = np.nan
temp.loc[mask, 'Deaths'] = np.nan
temp.loc[mask, 'Recovered'] = np.nan

fig = px.bar(temp, x="Date", y="Confirmed", color='Country/Region',
             title='Number of new cases reported globally everyday')
fig.show()

fig = px.bar(temp[temp['Country/Region']!='Mainland China'], x="Date", y="Confirmed", color='Country/Region',
             title='Number of daily new cases (excluding) China')
fig.show()

fig = px.bar(temp[temp['Country/Region']!='Mainland China'], x="Date", y="Deaths", color='Country/Region',
             title='Number of daily new death cases (excluding China)')
fig.show()

1.7 Countries with all affected recovered/died¶

In [11]:

temp = row_latest_grouped[row_latest_grouped['Confirmed']==
                          row_latest_grouped['Deaths']+
                          row_latest_grouped['Recovered']]
temp = temp[['Country/Region', 'Confirmed', 'Deaths', 'Recovered']]
temp = temp.sort_values('Confirmed', ascending=False)
temp = temp.reset_index(drop=True)
temp.style.background_gradient(cmap='Greens')

Out[11]:

	Country/Region	Confirmed	Deaths	Recovered
0	Mauritius	332	10	322
1	Cambodia	122	0	122
2	Eritrea	39	0	39
3	Belize	18	2	16
4	Saint Lucia	18	0	18
5	Suriname	10	1	9
6	Papua New Guinea	8	0	8
7	Western Sahara	6	0	6

1.8. Chinese provinces with all affected recovered/died¶

In [12]:

temp = china_latest_grouped[china_latest_grouped['Confirmed']==
                          china_latest_grouped['Deaths']+
                          china_latest_grouped['Recovered']]
temp = temp[['Province/State', 'Confirmed', 'Deaths', 'Recovered']]
temp = temp.sort_values('Confirmed', ascending=False)
temp = temp.reset_index(drop=True)
temp.style.background_gradient(cmap='Greens')

Out[12]:

	Province/State	Confirmed	Deaths	Recovered
0	Henan	1276	22	1254
1	Zhejiang	1268	1	1267
2	Hunan	1019	4	1015
3	Anhui	991	6	985
4	Heilongjiang	945	13	932
5	Jiangxi	937	1	936
6	Jiangsu	653	0	653
7	Chongqing	579	6	573
8	Sichuan	561	3	558
9	Fujian	356	1	355
10	Guangxi	254	2	252
11	Shanxi	198	0	198
12	Yunnan	185	2	183
13	Guizhou	147	2	145
14	Gansu	139	2	137
15	Xinjiang	76	3	73
16	Ningxia	75	0	75
17	Qinghai	18	0	18
18	Tibet	1	0	1

2. Basic reporting¶

2.1. Summary statistics for the past 5 days¶

In [13]:

# global data
all_cases = full_table.groupby('Date')['Confirmed', 'Deaths', 'Recovered'].sum()
all_cases = all_cases.reset_index()
all_cases = all_cases.sort_values('Date', ascending=False)
all_cases.head(5).style.background_gradient(cmap='Pastel1')

Out[13]:

	Date	Confirmed	Deaths	Recovered
115	2020-05-16 00:00:00	4634062	311781	1655256
114	2020-05-15 00:00:00	4542341	307666	1600051
113	2020-05-14 00:00:00	4442157	302418	1551698
112	2020-05-13 00:00:00	4347012	297197	1513280
111	2020-05-12 00:00:00	4261741	291942	1459275

2.2. Current status: breakdown by countries (alphabetical)¶

In [14]:

# breakdown by countries, alphabetical
temp = full_latest.groupby(['Country/Region', 'Province/State'])['Confirmed', 'Deaths', 'Recovered'].max()
temp.style.background_gradient(cmap='Pastel1_r')

Out[14]:

		Confirmed	Deaths	Recovered
Country/Region	Province/State
Afghanistan	--	6402	168	745
Albania	--	933	31	714
Algeria	--	6821	542	3409
Andorra	--	761	51	615
Angola	--	48	2	17
Antigua and Barbuda	--	25	3	19
Argentina	--	7805	363	2534
Armenia	--	4283	55	1791
Australia	Australian Capital Territory	107	3	104
	New South Wales	3075	45	2611
	Northern Territory	29	0	27
	Queensland	1055	6	1037
	South Australia	439	4	435
	Tasmania	228	13	192
	Victoria	1558	18	1417
	Western Australia	553	9	541
Austria	--	16201	629	14524
Azerbaijan	--	3138	36	1944
Bahamas	--	96	11	42
Bahrain	--	6747	12	2762
Bangladesh	--	20995	314	4117
Barbados	--	86	7	67
Belarus	--	28681	160	9498
Belgium	--	54989	9005	14460
Belize	--	18	2	16
Benin	--	339	2	83
Bhutan	--	21	0	5
Bolivia	--	3826	165	473
Bosnia and Herzegovina	--	2267	129	1355
Botswana	--	24	1	17
Brazil	--	233511	15662	89672
Brunei	--	141	1	136
Bulgaria	--	2175	105	573
Burkina Faso	--	782	51	604
Burma	--	182	6	96
Burundi	--	15	1	7
Cabo Verde	--	328	3	84
Cambodia	--	122	0	122
Cameroon	--	3105	140	1567
Canada	Alberta	6587	126	0
	British Columbia	2428	141	0
	Grand Princess	13	0	0
	Manitoba	289	7	0
	New Brunswick	120	0	0
	Newfoundland and Labrador	260	3	0
	Northwest Territories	5	0	0
	Nova Scotia	1037	55	0
	Ontario	23645	1976	0
	Prince Edward Island	27	0	0
	Quebec	42192	3484	0
	Saskatchewan	591	7	0
	Yukon	11	0	0
Central African Republic	--	327	0	13
Chad	--	474	50	111
Chile	--	41428	421	18014
Colombia	--	14939	562	3587
Comoros	--	11	1	3
Congo (Brazzaville)	--	391	15	87
Congo (Kinshasa)	--	1455	61	270
Costa Rica	--	853	10	551
Cote d'Ivoire	--	2061	25	987
Croatia	--	2224	95	1913
Cuba	--	1862	79	1460
Cyprus	--	914	17	515
Czechia	--	8455	296	5422
Denmark	--	10858	543	9107
	Faroe Islands	187	0	187
	Greenland	11	0	11
Diamond Princess	--	712	13	651
Djibouti	--	1331	4	950
Dominica	--	16	0	15
Dominican Republic	--	12110	428	3726
Ecuador	--	32763	2688	3433
Egypt	--	11719	612	2950
El Salvador	--	1265	26	441
Equatorial Guinea	--	594	7	22
Eritrea	--	39	0	39
Estonia	--	1770	63	934
Eswatini	--	202	2	72
Ethiopia	--	306	5	113
Fiji	--	18	0	15
Finland	--	6286	297	5000
France	--	177207	27483	59142
	French Guiana	197	1	125
	French Polynesia	60	0	59
	Guadeloupe	155	13	109
	Martinique	192	14	91
	Mayotte	1312	18	627
	New Caledonia	18	0	18
	Reunion	443	0	354
	Saint Barthelemy	6	0	6
	Saint Pierre and Miquelon	1	0	1
	St Martin	39	3	30
Gabon	--	1320	11	244
Gambia	--	23	1	12
Georgia	--	683	12	419
Germany	--	175752	7938	152600
Ghana	--	5735	29	1754
Greece	--	2819	162	1374
Grenada	--	22	0	14
Guatemala	--	1763	33	138
Guinea	--	2658	16	1133
Guinea-Bissau	--	969	4	26
Guyana	--	117	10	43
Haiti	--	358	20	29
Holy See	--	12	0	2
Honduras	--	2565	138	278
Hungary	--	3473	448	1371
Iceland	--	1802	10	1786
India	--	90648	2871	34224
Indonesia	--	17025	1089	3911
Iran	--	118392	6937	93147
Iraq	--	3260	121	2126
Ireland	--	24048	1533	19470
Israel	--	16608	268	12855
Italy	--	224760	31763	122810
Jamaica	--	517	9	121
Japan	--	16237	725	10338
Jordan	--	607	9	404
Kazakhstan	--	5850	34	2980
Kenya	--	830	50	301
Kosovo	--	944	29	690
Kuwait	--	13802	107	3843
Kyrgyzstan	--	1117	14	783
Laos	--	19	0	14
Latvia	--	997	19	662
Lebanon	--	902	26	247
Lesotho	--	1	0	0
Liberia	--	223	20	116
Libya	--	65	3	28
Liechtenstein	--	82	1	55
Lithuania	--	1534	55	988
Luxembourg	--	3930	104	3699
MS Zaandam	--	9	2	0
Madagascar	--	283	0	114
Mainland China	Anhui	991	6	985
	Beijing	593	9	577
	Chongqing	579	6	573
	Fujian	356	1	355
	Gansu	139	2	137
	Guangdong	1590	8	1579
	Guangxi	254	2	252
	Guizhou	147	2	145
	Hainan	169	6	162
	Hebei	328	6	321
	Heilongjiang	945	13	932
	Henan	1276	22	1254
	Hong Kong	1052	4	1022
	Hubei	68134	4512	63616
	Hunan	1019	4	1015
	Inner Mongolia	209	1	196
	Jiangsu	653	0	653
	Jiangxi	937	1	936
	Jilin	144	2	113
	Liaoning	149	2	144
	Macau	45	0	44
	Ningxia	75	0	75
	Qinghai	18	0	18
	Shaanxi	308	3	301
	Shandong	788	7	780
	Shanghai	665	7	641
	Shanxi	198	0	198
	Sichuan	561	3	558
	Tianjin	192	3	187
	Tibet	1	0	1
	Xinjiang	76	3	73
	Yunnan	185	2	183
	Zhejiang	1268	1	1267
Malawi	--	65	3	24
Malaysia	--	6872	113	5512
Maldives	--	1078	4	58
Mali	--	835	48	479
Malta	--	546	6	450
Mauritania	--	40	4	7
Mauritius	--	332	10	322
Mexico	--	47144	5045	31848
Moldova	--	5934	207	2344
Monaco	--	96	4	87
Mongolia	--	135	0	20
Montenegro	--	324	9	311
Morocco	--	6741	192	3487
Mozambique	--	129	0	0
Namibia	--	16	0	13
Nepal	--	291	1	36
Netherlands	--	43870	5670	0
	Aruba	101	3	93
	Curacao	16	1	14
	Sint Maarten	77	15	54
New Zealand	--	1499	21	1433
Nicaragua	--	25	8	7
Niger	--	889	51	689
Nigeria	--	5621	176	1472
North Macedonia	--	1762	98	1267
Norway	--	8237	232	32
Oman	--	5029	21	1436
Pakistan	--	38799	834	10880
Panama	--	9449	269	6080
Papua New Guinea	--	8	0	8
Paraguay	--	778	11	198
Peru	--	88541	2523	28272
Philippines	--	12305	817	2561
Poland	--	18257	915	7175
Portugal	--	28810	1203	3822
Qatar	--	30972	15	3788
Romania	--	16704	1094	9574
Russia	--	272043	2537	63166
Rwanda	--	289	0	178
Saint Kitts and Nevis	--	15	0	14
Saint Lucia	--	18	0	18
Saint Vincent and the Grenadines	--	17	0	14
San Marino	--	653	41	198
Sao Tome and Principe	--	235	7	4
Saudi Arabia	--	52016	302	23666
Senegal	--	2429	25	949
Serbia	--	10496	228	4479
Seychelles	--	11	0	10
Sierra Leone	--	462	29	106
Singapore	--	27356	22	8342
Slovakia	--	1493	28	1151
Slovenia	--	1465	103	272
Somalia	--	1357	55	148
South Africa	--	14355	261	6478
South Korea	--	11050	262	9888
South Sudan	--	236	4	4
Spain	--	230698	27563	146446
Sri Lanka	--	960	9	520
Sudan	--	2289	97	222
Suriname	--	10	1	9
Sweden	--	29677	3674	4971
Switzerland	--	30572	1879	27400
Syria	--	51	3	0
Taiwan*	--	440	7	389
Tajikistan	--	1322	36	0
Tanzania	--	509	21	183
Thailand	--	3025	56	2855
Timor-Leste	--	24	0	0
Togo	--	298	11	99
Trinidad and Tobago	--	116	8	107
Tunisia	--	1037	45	807
Turkey	--	148067	4096	108137
US	--	1467820	88754	268376
Uganda	--	227	0	63
Ukraine	--	17858	497	4906
United Arab Emirates	--	22627	214	7931
United Kingdom	--	240161	34466	0
	Anguilla	3	0	3
	Bermuda	123	9	73
	British Virgin Islands	8	1	6
	Cayman Islands	94	1	55
	Channel Islands	554	43	458
	Falkland Islands (Malvinas)	13	0	13
	Gibraltar	147	0	145
	Isle of Man	335	24	285
	Montserrat	11	1	10
	Turks and Caicos Islands	12	1	10
Uruguay	--	733	19	558
Uzbekistan	--	2738	11	2213
Venezuela	--	504	10	241
Vietnam	--	318	0	260
West Bank and Gaza	--	376	2	329
Western Sahara	--	6	0	6
Yemen	--	122	18	1
Zambia	--	679	7	183
Zimbabwe	--	42	4	13

2.3. Current standing (sorted by # cases)¶

In [15]:

# breakdown by countries, sorted by cases

temp_f = full_latest_grouped[['Country/Region', 'Confirmed', 'Deaths', 'Recovered']]
temp_f = temp_f.sort_values(by='Confirmed', ascending=False)
temp_f = temp_f.reset_index(drop=True)
temp_f.style.background_gradient(cmap='Pastel1_r')

Out[15]:

	Country/Region	Confirmed	Deaths	Recovered
0	US	1467820	88754	268376
1	Russia	272043	2537	63166
2	United Kingdom	241461	34546	1058
3	Brazil	233511	15662	89672
4	Spain	230698	27563	146446
5	Italy	224760	31763	122810
6	France	179630	27532	60562
7	Germany	175752	7938	152600
8	Turkey	148067	4096	108137
9	Iran	118392	6937	93147
10	India	90648	2871	34224
11	Peru	88541	2523	28272
12	Mainland China	84044	4638	79293
13	Canada	77206	5800	0
14	Belgium	54989	9005	14460
15	Saudi Arabia	52016	302	23666
16	Mexico	47144	5045	31848
17	Netherlands	44064	5689	161
18	Chile	41428	421	18014
19	Pakistan	38799	834	10880
20	Ecuador	32763	2688	3433
21	Qatar	30972	15	3788
22	Switzerland	30572	1879	27400
23	Sweden	29677	3674	4971
24	Portugal	28810	1203	3822
25	Belarus	28681	160	9498
26	Singapore	27356	22	8342
27	Ireland	24048	1533	19470
28	United Arab Emirates	22627	214	7931
29	Bangladesh	20995	314	4117
30	Poland	18257	915	7175
31	Ukraine	17858	497	4906
32	Indonesia	17025	1089	3911
33	Romania	16704	1094	9574
34	Israel	16608	268	12855
35	Japan	16237	725	10338
36	Austria	16201	629	14524
37	Colombia	14939	562	3587
38	South Africa	14355	261	6478
39	Kuwait	13802	107	3843
40	Philippines	12305	817	2561
41	Dominican Republic	12110	428	3726
42	Egypt	11719	612	2950
43	Denmark	11056	543	9305
44	South Korea	11050	262	9888
45	Serbia	10496	228	4479
46	Panama	9449	269	6080
47	Czechia	8455	296	5422
48	Norway	8237	232	32
49	Argentina	7805	363	2534
50	Australia	7044	98	6364
51	Malaysia	6872	113	5512
52	Algeria	6821	542	3409
53	Bahrain	6747	12	2762
54	Morocco	6741	192	3487
55	Afghanistan	6402	168	745
56	Finland	6286	297	5000
57	Moldova	5934	207	2344
58	Kazakhstan	5850	34	2980
59	Ghana	5735	29	1754
60	Nigeria	5621	176	1472
61	Oman	5029	21	1436
62	Armenia	4283	55	1791
63	Luxembourg	3930	104	3699
64	Bolivia	3826	165	473
65	Hungary	3473	448	1371
66	Iraq	3260	121	2126
67	Azerbaijan	3138	36	1944
68	Cameroon	3105	140	1567
69	Thailand	3025	56	2855
70	Greece	2819	162	1374
71	Uzbekistan	2738	11	2213
72	Guinea	2658	16	1133
73	Honduras	2565	138	278
74	Senegal	2429	25	949
75	Sudan	2289	97	222
76	Bosnia and Herzegovina	2267	129	1355
77	Croatia	2224	95	1913
78	Bulgaria	2175	105	573
79	Cote d'Ivoire	2061	25	987
80	Cuba	1862	79	1460
81	Iceland	1802	10	1786
82	Estonia	1770	63	934
83	Guatemala	1763	33	138
84	North Macedonia	1762	98	1267
85	Lithuania	1534	55	988
86	New Zealand	1499	21	1433
87	Slovakia	1493	28	1151
88	Slovenia	1465	103	272
89	Congo (Kinshasa)	1455	61	270
90	Somalia	1357	55	148
91	Djibouti	1331	4	950
92	Tajikistan	1322	36	0
93	Gabon	1320	11	244
94	El Salvador	1265	26	441
95	Kyrgyzstan	1117	14	783
96	Maldives	1078	4	58
97	Tunisia	1037	45	807
98	Latvia	997	19	662
99	Guinea-Bissau	969	4	26
100	Sri Lanka	960	9	520
101	Kosovo	944	29	690
102	Albania	933	31	714
103	Cyprus	914	17	515
104	Lebanon	902	26	247
105	Niger	889	51	689
106	Costa Rica	853	10	551
107	Mali	835	48	479
108	Kenya	830	50	301
109	Burkina Faso	782	51	604
110	Paraguay	778	11	198
111	Andorra	761	51	615
112	Uruguay	733	19	558
113	Diamond Princess	712	13	651
114	Georgia	683	12	419
115	Zambia	679	7	183
116	San Marino	653	41	198
117	Jordan	607	9	404
118	Equatorial Guinea	594	7	22
119	Malta	546	6	450
120	Jamaica	517	9	121
121	Tanzania	509	21	183
122	Venezuela	504	10	241
123	Chad	474	50	111
124	Sierra Leone	462	29	106
125	Taiwan*	440	7	389
126	Congo (Brazzaville)	391	15	87
127	West Bank and Gaza	376	2	329
128	Haiti	358	20	29
129	Benin	339	2	83
130	Mauritius	332	10	322
131	Cabo Verde	328	3	84
132	Central African Republic	327	0	13
133	Montenegro	324	9	311
134	Vietnam	318	0	260
135	Ethiopia	306	5	113
136	Togo	298	11	99
137	Nepal	291	1	36
138	Rwanda	289	0	178
139	Madagascar	283	0	114
140	South Sudan	236	4	4
141	Sao Tome and Principe	235	7	4
142	Uganda	227	0	63
143	Liberia	223	20	116
144	Eswatini	202	2	72
145	Burma	182	6	96
146	Brunei	141	1	136
147	Mongolia	135	0	20
148	Mozambique	129	0	0
149	Cambodia	122	0	122
150	Yemen	122	18	1
151	Guyana	117	10	43
152	Trinidad and Tobago	116	8	107
153	Bahamas	96	11	42
154	Monaco	96	4	87
155	Barbados	86	7	67
156	Liechtenstein	82	1	55
157	Libya	65	3	28
158	Malawi	65	3	24
159	Syria	51	3	0
160	Angola	48	2	17
161	Zimbabwe	42	4	13
162	Mauritania	40	4	7
163	Eritrea	39	0	39
164	Antigua and Barbuda	25	3	19
165	Nicaragua	25	8	7
166	Botswana	24	1	17
167	Timor-Leste	24	0	0
168	Gambia	23	1	12
169	Grenada	22	0	14
170	Bhutan	21	0	5
171	Laos	19	0	14
172	Saint Lucia	18	0	18
173	Belize	18	2	16
174	Fiji	18	0	15
175	Saint Vincent and the Grenadines	17	0	14
176	Dominica	16	0	15
177	Namibia	16	0	13
178	Burundi	15	1	7
179	Saint Kitts and Nevis	15	0	14
180	Holy See	12	0	2
181	Seychelles	11	0	10
182	Comoros	11	1	3
183	Suriname	10	1	9
184	MS Zaandam	9	2	0
185	Papua New Guinea	8	0	8
186	Western Sahara	6	0	6
187	Lesotho	1	0	0

2.4. Breakdown of cases in Mainland China by province¶

In [16]:

# breakdown of cases in China by provinces

temp_f = china_latest_grouped[['Province/State', 'Confirmed', 'Deaths', 'Recovered']]
temp_f = temp_f.sort_values(by='Confirmed', ascending=False)
temp_f = temp_f.reset_index(drop=True)
temp_f.style.background_gradient(cmap='Pastel1_r')

Out[16]:

	Province/State	Confirmed	Deaths	Recovered
0	Hubei	68134	4512	63616
1	Guangdong	1590	8	1579
2	Henan	1276	22	1254
3	Zhejiang	1268	1	1267
4	Hong Kong	1052	4	1022
5	Hunan	1019	4	1015
6	Anhui	991	6	985
7	Heilongjiang	945	13	932
8	Jiangxi	937	1	936
9	Shandong	788	7	780
10	Shanghai	665	7	641
11	Jiangsu	653	0	653
12	Beijing	593	9	577
13	Chongqing	579	6	573
14	Sichuan	561	3	558
15	Fujian	356	1	355
16	Hebei	328	6	321
17	Shaanxi	308	3	301
18	Guangxi	254	2	252
19	Inner Mongolia	209	1	196
20	Shanxi	198	0	198
21	Tianjin	192	3	187
22	Yunnan	185	2	183
23	Hainan	169	6	162
24	Liaoning	149	2	144
25	Guizhou	147	2	145
26	Jilin	144	2	113
27	Gansu	139	2	137
28	Xinjiang	76	3	73
29	Ningxia	75	0	75
30	Macau	45	0	44
31	Qinghai	18	0	18
32	Tibet	1	0	1

3. Comparing hotspots¶

3.1. Hubei/Rest of China/Rest of the World¶

In [17]:

def location(row):
    if row['Country/Region']=='Mainland China':
        if row['Province/State']=='Hubei':
            return 'Hubei'
        else:
            return 'Other Chinese Provinces'
    else:
        return 'Rest of the World'

temp = full_latest.copy()
temp['Region'] = temp.apply(location, axis=1)
temp = temp.groupby('Region')['Confirmed', 'Deaths', 'Recovered'].sum().reset_index()
temp = temp.melt(id_vars='Region', value_vars=['Confirmed', 'Deaths', 'Recovered'], 
                 var_name='Case', value_name='Count').sort_values('Count')

fig = px.bar(temp, y='Region', x='Count', color='Case', barmode='group', orientation='h',
             text='Count', title='Hubei - Rest of China - Rest of the World', 
             color_discrete_sequence= ['#EF553B', '#00CC96', '#636EFA'])
fig.update_traces(textposition='outside')
fig.update_layout(uniformtext_minsize=8, uniformtext_mode='hide')
fig.show()

3.2. Number of total cases in time¶

In [18]:

gdf = full_table.groupby(['Date', 'Country/Region'])['Confirmed', 'Deaths', 'Recovered'].max()
gdf = gdf.reset_index()

temp = gdf[gdf['Country/Region']=='Mainland China'].reset_index()
temp = temp.melt(id_vars='Date', value_vars=['Confirmed', 'Deaths', 'Recovered'],
                var_name='Case', value_name='Count')
fig = px.bar(temp, x="Date", y="Count", color='Case', facet_col="Case",
            title='Cases in China')
fig.show()

temp = gdf[gdf['Country/Region']!='Mainland China'].groupby('Date').sum().reset_index()
temp = temp.melt(id_vars='Date', value_vars=['Confirmed', 'Deaths', 'Recovered'],
                var_name='Case', value_name='Count')
fig = px.bar(temp, x="Date", y="Count", color='Case', facet_col="Case",
             title='Cases in rest of the World')
fig.show()

3.3 Number of countries affected by CoVID-19 in time¶

Note that China has 31 administrative divisions (省级行政区) under direct jurisdiction (excluding Hong Kong and Macau). https://en.wikipedia.org/wiki/Provinces_of_China

In [19]:

c_spread = china[china['Confirmed']!=0].groupby('Date')['Province/State'].unique().apply(len)
c_spread = pd.DataFrame(c_spread).reset_index()

fig = px.line(c_spread, x='Date', y='Province/State', 
              title='Number of provinces in China affected over time')
fig.show()

# ------------------------------------------------------------------------------------------

spread = full_table[full_table['Confirmed']!=0].groupby('Date')['Country/Region'].unique().apply(len)
spread = pd.DataFrame(spread).reset_index()

fig = px.line(spread, x='Date', y='Country/Region', 
              title='Number of countries affected over time')
fig.show()

3.4. Recovery and mortality rate over time¶

In [20]:

temp = full_table.groupby('Date').sum().reset_index()
temp.head()

# adding two more columns
temp['% death'] = round(temp['Deaths']/
                                                     temp['Confirmed'], 3)*100
temp['% recovered'] = round(temp['Recovered']/
                                                        temp['Confirmed'], 3)*100

temp = temp.melt(id_vars='Date', 
                 value_vars=['% death', 
                             '% recovered'], 
                 var_name='Ratio', 
                 value_name='Value')

fig = px.line(temp, x="Date", y="Value", color='Ratio', 
              title='Recovery and Mortality Rate over Time')
fig.show()

3.5 Treemap of countries with reported cases¶

In [21]:

fig = px.treemap(china_latest.sort_values(by='Confirmed', ascending=False).reset_index(drop=True), 
                 path=["Province/State"], values="Confirmed", 
                 title='Number of Confirmed Cases in Chinese Provinces',
                 color_discrete_sequence = px.colors.qualitative.Prism)
fig.show()

fig = px.treemap(china_latest.sort_values(by='Deaths', ascending=False).reset_index(drop=True), 
                 path=["Province/State"], values="Deaths", 
                 title='Number of Deaths Reported in Chinese Provinces',
                 color_discrete_sequence = px.colors.qualitative.Prism)
fig.show()

fig = px.treemap(china_latest.sort_values(by='Recovered', ascending=False).reset_index(drop=True), 
                 path=["Province/State"], values="Recovered", 
                 title='Number of Recovered Cases in Chinese Provinces',
                 color_discrete_sequence = px.colors.qualitative.Prism)
fig.show()

In [22]:

fig = px.treemap(row_latest, path=["Country/Region"], values="Confirmed", 
                 title='# confirmed (excluding Mainland China)',
                 color_discrete_sequence = px.colors.qualitative.Pastel)
fig.show()

fig = px.treemap(row_latest, path=["Country/Region"], values="Deaths", 
                 title='# deaths (excluding Mainland China)',
                 color_discrete_sequence = px.colors.qualitative.Pastel)
fig.show()

fig = px.treemap(row_latest, path=["Country/Region"], values="Recovered", 
                 title='# recovered (excluding Mainland China)',
                 color_discrete_sequence = px.colors.qualitative.Pastel)
fig.show()

4. Comparison with other epidemics¶

Source: WHO

In [23]:

epidemics = pd.DataFrame({
    'epidemic' : ['COVID-19', 'SARS', 'EBOLA', 'MERS', 'H1N1'],
    'start_year' : [2019, 2003, 2014, 2012, 2009],
    'end_year' : [2020, 2004, 2016, 2017, 2010],
    'confirmed' : [all_cases.iloc[0,1], 8096, 28646, 2494, 6724149],
    'deaths' : [all_cases.iloc[0, 2], 774, 11323, 858, 19654]
})

epidemics['% mortality'] = round((epidemics['deaths']/epidemics['confirmed'])*100, 2)

epidemics

Out[23]:

	epidemic	start_year	end_year	confirmed	deaths	% mortality
0	COVID-19	2019	2020	4634062	311781	6.73
1	SARS	2003	2004	8096	774	9.56
2	EBOLA	2014	2016	28646	11323	39.53
3	MERS	2012	2017	2494	858	34.40
4	H1N1	2009	2010	6724149	19654	0.29

In [24]:

temp = epidemics.melt(id_vars='epidemic', value_vars=['confirmed', 'deaths', '% mortality'],
                      var_name='Case', value_name='Value')

fig = px.bar(temp, x="epidemic", y="Value", color='epidemic', text='Value', facet_col="Case",
             color_discrete_sequence = px.colors.qualitative.Bold)
fig.update_traces(textposition='outside')
fig.update_layout(uniformtext_minsize=8, uniformtext_mode='hide')
fig.update_yaxes(showticklabels=False)
fig.layout.yaxis2.update(matches=None)
fig.layout.yaxis3.update(matches=None)
fig.show()

In [25]:

temp = full_table.groupby('Date')['Confirmed'].sum().reset_index()

covid = temp['Confirmed']
sars = [8096 for i in range(len(temp))]
ebola = [28646 for i in range(len(temp))]
mers = [2494 for i in range(len(temp))]
h1n1 = [6724149 for i in range(len(temp))]

plt.style.use('fivethirtyeight')
plt.figure(figsize=(20, 8))
ax = plt.plot(temp['Date'], covid, label='COVID-19 (2019-2020)', c='#555555', alpha=0.8)
ax = plt.plot(temp['Date'], sars, label='SARS (2003-2004)', c='#E71D36', ls='--', alpha=0.8)
ax = plt.plot(temp['Date'], ebola, label='EBOLA (2014-2016)', c='#FF9F1C', ls='--', alpha=0.8)
ax = plt.plot(temp['Date'], mers, label='MERS (2012-2017)', c='#2EC4B6', ls='--', alpha=0.8)
plt.title('Number of cases (excluding H1N1)')
plt.legend()
plt.show()

/Users/kevinsiswandi/opt/anaconda3/lib/python3.7/site-packages/pandas/plotting/_matplotlib/converter.py:103: FutureWarning:

Using an implicitly registered datetime converter for a matplotlib plotting method. The converter was registered by pandas on import. Future versions of pandas will require you to explicitly register matplotlib converters.

To register the converters:
	>>> from pandas.plotting import register_matplotlib_converters
	>>> register_matplotlib_converters()

In [26]:

temp = full_table.groupby('Date')['Deaths'].sum().reset_index()

covid = temp['Deaths']
sars = [774 for i in range(len(temp))]
ebola = [11323 for i in range(len(temp))]
mers = [858 for i in range(len(temp))]
h1n1 = [19654 for i in range(len(temp))]

plt.figure(figsize=(20, 8))
ax = plt.plot(temp['Date'], covid, label='COVID-19 (2019-2020)', c='#555555', alpha=0.8)
ax = plt.plot(temp['Date'], sars, label='SARS (2003-2004)', c='#E71D36', ls='--', alpha=0.8)
ax = plt.plot(temp['Date'], ebola, label='EBOLA (2014-2016)', c='#FF9F1C', ls='--', alpha=0.8)
ax = plt.plot(temp['Date'], mers, label='MERS (2012-2017)', c='#2EC4B6', ls='--', alpha=0.8)
ax = plt.plot(temp['Date'], h1n1, label='H1N1 (2009-2010)', c='#2345BA', ls='--', alpha=0.8)
plt.title('Number of deaths')
plt.legend()
plt.show()

In [ ]: