Exploring the Novel Coronavirus (COVID-19) Dataset

Code

%%time
import os
f_name = 'novel-corona-virus-2019-dataset.zip'
if not os.path.exists(f_name):
  os.environ['KAGGLE_USERNAME'] = "" # username from the json file
  os.environ['KAGGLE_KEY'] = "" # key from the json file
  !kaggle datasets download -d sudalairajkumar/novel-corona-virus-2019-dataset

CPU times: user 325 µs, sys: 65 µs, total: 390 µs
Wall time: 605 µs

Code

import zipfile
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt
import networkx as nx

Code

df = dict()
with zipfile.ZipFile(f_name) as z:
  for fz in z.namelist():
    with z.open(fz) as f:
        df[fz.split('.')[0]] = pd.read_csv(f)

Code

df.keys()

dict_keys(['COVID19_line_list_data', 'COVID19_open_line_list', 'covid_19_data', 'time_series_covid_19_confirmed', 'time_series_covid_19_deaths', 'time_series_covid_19_recovered'])

First Preview over the data

Code

conf = df.get('time_series_covid_19_confirmed')
dth = df.get('time_series_covid_19_deaths')
recov = df.get('time_series_covid_19_recovered')

Code

conf[:5]

	Province/State	Country/Region	Lat	Long	2/24/20	2/25/20	2/26/20	2/27/20	2/28/20	2/29/20	3/1/20	3/2/20	3/3/20	3/4/20	3/5/20	3/6/20	3/7/20	3/8/20	3/9/20	3/10/20	3/11/20	3/12/20	3/13/20	3/14/20	3/15/20	3/16/20	3/17/20	3/18/20	3/19/20	3/20/20	3/21/20	3/22/20	3/23/20	3/24/20	3/25/20	3/26/20	3/27/20
0	NaN	Afghanistan	33.0000	65.0000	1	1	1	1	1	1	1	1	1	1	1	1	1	4	4	5	7	7	7	11	16	21	22	22	22	24	24	40	40	74	84	94	110
1	NaN	Albania	41.1533	20.1683	0	0	0	0	0	0	0	0	0	0	0	0	0	0	2	10	12	23	33	38	42	51	55	59	64	70	76	89	104	123	146	174	186
2	NaN	Algeria	28.0339	1.6596	0	1	1	1	1	1	1	3	5	12	12	17	17	19	20	20	20	24	26	37	48	54	60	74	87	90	139	201	230	264	302	367	409
3	NaN	Andorra	42.5063	1.5218	0	0	0	0	0	0	0	1	1	1	1	1	1	1	1	1	1	1	1	1	1	2	39	39	53	75	88	113	133	164	188	224	267
4	NaN	Angola	-11.2027	17.8739	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	2	2	3	3	3	4	4

Code

dth[:5]

	Province/State	Country/Region	Lat	Long	3/11/20	3/12/20	3/13/20	3/14/20	3/15/20	3/16/20	3/17/20	3/18/20	3/19/20	3/20/20	3/21/20	3/22/20	3/23/20	3/24/20	3/25/20	3/26/20	3/27/20
0	NaN	Afghanistan	33.0000	65.0000	0	0	0	0	0	0	0	0	0	0	0	1	1	1	2	4	4
1	NaN	Albania	41.1533	20.1683	1	1	1	1	1	1	1	2	2	2	2	2	4	5	5	6	8
2	NaN	Algeria	28.0339	1.6596	0	1	2	3	4	4	4	7	9	11	15	17	17	19	21	25	26
3	NaN	Andorra	42.5063	1.5218	0	0	0	0	0	0	0	0	0	0	0	1	1	1	1	3	3
4	NaN	Angola	-11.2027	17.8739	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0

Code

recov[:5]

	Province/State	Country/Region	Lat	Long	3/12/20	3/13/20	3/14/20	3/15/20	3/16/20	3/17/20	3/18/20	3/19/20	3/20/20	3/21/20	3/22/20	3/23/20	3/24/20	3/25/20	3/26/20	3/27/20
0	NaN	Afghanistan	33.0000	65.0000	0	0	0	0	1	1	1	1	1	1	1	1	1	2	2	2
1	NaN	Albania	41.1533	20.1683	0	0	0	0	0	0	0	0	0	2	2	2	10	17	17	31
2	NaN	Algeria	28.0339	1.6596	8	8	12	12	12	12	12	32	32	32	65	65	24	65	29	29
3	NaN	Andorra	42.5063	1.5218	1	0	1	1	1	1	1	1	1	1	1	1	1	1	1	1
4	NaN	Angola	-11.2027	17.8739	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0

Code

conf_time_cols = conf.columns.tolist()[4:]
dth_time_cols = dth.columns.tolist()[4:]
recov_time_cols = recov.columns.tolist()[4:]

Code

conf_graph = nx.Graph()
dth_graph = nx.Graph()
recov_graph = nx.Graph()

Code

for i in range(conf.__len__()):
    conf_graph.add_edge(conf.iloc[i]['Country/Region'],conf.iloc[i]['Province/State'],relation='state-level')
    conf_graph.add_edge(conf.iloc[i]['Province/State'],conf.iloc[i][conf_time_cols[-1]],relation='number-level')

Confirmed Cases at a Country-State Level

Code

plt.figure(figsize=(50,50))
nx.draw_networkx(conf_graph)

Death Cases at a Country-State Level

Code

for i in range(dth.__len__()):
    dth_graph.add_edge(dth.iloc[i]['Country/Region'],dth.iloc[i]['Province/State'],relation='state-level')
    dth_graph.add_edge(conf.iloc[i]['Province/State'],conf.iloc[i][dth_time_cols[-1]],relation='number-level')

Code

plt.figure(figsize=(50,50))
nx.draw_networkx(dth_graph)

Recovered Cases at a Country-State Level

Code

for i in range(recov.__len__()):
    recov_graph.add_edge(dth.iloc[i]['Country/Region'],dth.iloc[i]['Province/State'],relation='state-level')
    recov_graph.add_edge(conf.iloc[i]['Province/State'],conf.iloc[i][recov_time_cols[-1]],relation='number-level')

Code

plt.figure(figsize=(50,50))
nx.draw_networkx(recov_graph)

Overview over the Confirmed Cases by time

Code

conf[conf_time_cols].describe().boxplot(figsize=(55,20))

Overview over the Death Cases by time

Code

dth[dth_time_cols].describe().boxplot(figsize=(55,20))

Overview over the Recovered Cases by time

Code

recov[recov_time_cols].describe().boxplot(figsize=(55,20))

Latest Confirmed Cases Grouped by Country/Region and Province/State

Code

conf.loc[:,['Country/Region','Province/State',conf_time_cols[-1]]].groupby(['Country/Region','Province/State']).agg({
    conf_time_cols[-1]: 'sum'
})

		3/27/20
Country/Region	Province/State
Australia	Australian Capital Territory	62
	New South Wales	1405
	Northern Territory	12
	Queensland	555
	South Australia	257
...	...	...
United Kingdom	Cayman Islands	8
	Channel Islands	88
	Gibraltar	55
	Isle of Man	29
	Montserrat	5

76 rows × 1 columns

Latest Death Cases Grouped by Country/Region and Province/State

Code

dth.loc[:,['Country/Region','Province/State',dth_time_cols[-1]]].groupby(['Country/Region','Province/State']).agg({
    dth_time_cols[-1]: 'sum'
})

		3/27/20
Country/Region	Province/State
Australia	Australian Capital Territory	0
	New South Wales	7
	Northern Territory	0
	Queensland	1
	South Australia	0
...	...	...
United Kingdom	Cayman Islands	1
	Channel Islands	1
	Gibraltar	0
	Isle of Man	0
	Montserrat	0

76 rows × 1 columns

Latest Recovered Cases Grouped by Country/Region and Province/State

Code

recov.loc[:,['Country/Region','Province/State',recov_time_cols[-1]]].groupby(['Country/Region','Province/State']).agg({
    recov_time_cols[-1]: 'sum'
})

		3/27/20
Country/Region	Province/State
Australia	Australian Capital Territory	1
	New South Wales	4
	Northern Territory	0
	Queensland	8
	South Australia	6
...	...	...
United Kingdom	Cayman Islands	0
	Channel Islands	0
	Gibraltar	14
	Isle of Man	0
	Montserrat	0

61 rows × 1 columns

Code

total_cases = conf[conf_time_cols[-1]].sum()
total_deaths = dth[dth_time_cols[-1]].sum()
total_recovs = recov[recov_time_cols[-1]].sum()

Code

total_cases, total_deaths, total_recovs

(593291, 27198, 130915)

Code

death_rate = (total_deaths / total_cases) * 100.0
recov_rate = (total_recovs / total_cases) * 100.0

Code

plt.figure(figsize=(10,10))
objects = ('Death Ratio', 'Recover Ratio')
y_pos = np.arange(len(objects))
performance = [death_rate,recov_rate]

plt.bar(y_pos, performance, align='center', alpha=0.5)
plt.xticks(y_pos, objects)
plt.ylabel('%')
plt.title('Death vs Recover Ratio')

plt.show()

Code

plt.figure(figsize=(10,10))
objects = ('Total Confirmed','Total Deaths', 'Total Recovered')
y_pos = np.arange(len(objects))
performance = [total_cases, total_deaths, total_recovs]

plt.bar(y_pos, performance, align='center', alpha=0.5)
plt.xticks(y_pos, objects)
plt.title("Numbers of " + " - ".join(objects))

plt.show()

Code

import plotly.express as px

Code

conf['cases'] = conf[conf_time_cols[-1]]
dth['cases'] = dth[dth_time_cols[-1]]
recov['cases'] = recov[recov_time_cols[-1]]

Code

hov_data = ["Province/State", "Country/Region","cases"]

Map of Confirmed cases on the last available day

Code

plt.figure(figsize=(25,25))
fig = px.scatter_mapbox(conf, lat="Lat", lon="Long", hover_name="Province/State", hover_data=hov_data,
                        color_discrete_sequence=["fuchsia"],zoom=3)
fig.update_layout(mapbox_style="carto-darkmatter")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.show()

<Figure size 1800x1800 with 0 Axes>

Map of Death cases on the last available day

Code

plt.figure(figsize=(50,50))
fig = px.scatter_mapbox(dth, lat="Lat", lon="Long", hover_name="Province/State", hover_data=hov_data,
                        color_discrete_sequence=["fuchsia"],zoom=3)
fig.update_layout(mapbox_style="carto-darkmatter")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.show()

<Figure size 3600x3600 with 0 Axes>

Map of Recovered cases on the last available day

Code

plt.figure(figsize=(25,25))
fig = px.scatter_mapbox(recov, lat="Lat", lon="Long", hover_name="Province/State", hover_data=hov_data,
                        color_discrete_sequence=["fuchsia"],zoom=3)
fig.update_layout(mapbox_style="carto-darkmatter")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.show()

<Figure size 1800x1800 with 0 Axes>