In [243]:
# Importing all the important libraries import numpy as np import pandas as pd import matplotlib.pyplot as plt import matplotlib.colors as mcolors import random import math import time from sklearn.model_selection import RandomizedSearchCV, train_test_split from sklearn.svm import SVR from sklearn.metrics import mean_squared_error, mean_absolute_error import datetime import operator plt.style.use('seaborn') %matplotlib inline
In [244]:
# Loading all the three datasets confirmed_cases = pd.read_csv('D:/Corona_virus analysis/time_series_covid-19_confirmed.csv' )
In [245]:
deaths_reported = pd.read_csv('D:/Corona_virus analysis/time_series_covid-19_deaths.csv' )
In [246]:
recovered_cases = pd.read_csv('D:/Corona_virus analysis/time_series_covid-19_recovered.csv' )
In [247]:
# Display the head of the dataset confirmed_cases.head()
Out[247]:
| Province/State | Country/Region | Lat | Long | 1/22/20 | 1/23/20 | 1/24/20 | 1/25/20 | 1/26/20 | 1/27/20 | ... | 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | NaN | Thailand | 15.0000 | 101.0000 | 2 | 3 | 5 | 7 | 8 | 8 | ... | 48 | 50 | 50 | 50 | 53 | 59 | 70 | 75 | 82 | 114 |
| 1 | NaN | Japan | 36.0000 | 138.0000 | 2 | 1 | 2 | 2 | 4 | 4 | ... | 420 | 461 | 502 | 511 | 581 | 639 | 639 | 701 | 773 | 839 |
| 2 | NaN | Singapore | 1.2833 | 103.8333 | 0 | 1 | 3 | 3 | 4 | 5 | ... | 130 | 138 | 150 | 150 | 160 | 178 | 178 | 200 | 212 | 226 |
| 3 | NaN | Nepal | 28.1667 | 84.2500 | 0 | 0 | 0 | 1 | 1 | 1 | ... | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
| 4 | NaN | Malaysia | 2.5000 | 112.5000 | 0 | 0 | 0 | 3 | 4 | 4 | ... | 83 | 93 | 99 | 117 | 129 | 149 | 149 | 197 | 238 | 428 |
5 rows à 58 columns
In [248]:
deaths_reported.head()
Out[248]:
| Province/State | Country/Region | Lat | Long | 1/22/20 | 1/23/20 | 1/24/20 | 1/25/20 | 1/26/20 | 1/27/20 | ... | 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | NaN | Thailand | 15.0000 | 101.0000 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
| 1 | NaN | Japan | 36.0000 | 138.0000 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 6 | 6 | 6 | 10 | 10 | 15 | 16 | 19 | 22 | 22 |
| 2 | NaN | Singapore | 1.2833 | 103.8333 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| 3 | NaN | Nepal | 28.1667 | 84.2500 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| 4 | NaN | Malaysia | 2.5000 | 112.5000 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
5 rows à 58 columns
In [249]:
recovered_cases.head()
Out[249]:
| Province/State | Country/Region | Lat | Long | 1/22/20 | 1/23/20 | 1/24/20 | 1/25/20 | 1/26/20 | 1/27/20 | ... | 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | NaN | Thailand | 15.0000 | 101.0000 | 0 | 0 | 0 | 0 | 2 | 2 | ... | 31 | 31 | 31 | 31 | 33 | 34 | 34 | 35 | 35 | 35 |
| 1 | NaN | Japan | 36.0000 | 138.0000 | 0 | 0 | 0 | 0 | 1 | 1 | ... | 46 | 76 | 76 | 76 | 101 | 118 | 118 | 118 | 118 | 118 |
| 2 | NaN | Singapore | 1.2833 | 103.8333 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 78 | 78 | 78 | 78 | 78 | 96 | 96 | 97 | 105 | 105 |
| 3 | NaN | Nepal | 28.1667 | 84.2500 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
| 4 | NaN | Malaysia | 2.5000 | 112.5000 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 22 | 23 | 24 | 24 | 24 | 26 | 26 | 26 | 35 | 42 |
5 rows à 58 columns
In [250]:
# Extracting all the columns using the .keys() function cols = confirmed_cases.keys() cols
Out[250]:
Index(['Province/State', 'Country/Region', 'Lat', 'Long', '1/22/20', '1/23/20',
'1/24/20', '1/25/20', '1/26/20', '1/27/20', '1/28/20', '1/29/20',
'1/30/20', '1/31/20', '2/1/20', '2/2/20', '2/3/20', '2/4/20', '2/5/20',
'2/6/20', '2/7/20', '2/8/20', '2/9/20', '2/10/20', '2/11/20', '2/12/20',
'2/13/20', '2/14/20', '2/15/20', '2/16/20', '2/17/20', '2/18/20',
'2/19/20', '2/20/20', '2/21/20', '2/22/20', '2/23/20', '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'],
dtype='object')
In [251]:
# Extracting only the dates columns that have information of confirmed, deaths and recovered cases confirmed = confirmed_cases.loc[:, cols[4]:cols[-1]]
In [252]:
deaths = deaths_reported.loc[:, cols[4]:cols[-1]]
In [253]:
recoveries = recovered_cases.loc[:, cols[4]:cols[-1]]
In [254]:
# Check the head of the outbreak cases confirmed.head()
Out[254]:
| 1/22/20 | 1/23/20 | 1/24/20 | 1/25/20 | 1/26/20 | 1/27/20 | 1/28/20 | 1/29/20 | 1/30/20 | 1/31/20 | ... | 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 2 | 3 | 5 | 7 | 8 | 8 | 14 | 14 | 14 | 19 | ... | 48 | 50 | 50 | 50 | 53 | 59 | 70 | 75 | 82 | 114 |
| 1 | 2 | 1 | 2 | 2 | 4 | 4 | 7 | 7 | 11 | 15 | ... | 420 | 461 | 502 | 511 | 581 | 639 | 639 | 701 | 773 | 839 |
| 2 | 0 | 1 | 3 | 3 | 4 | 5 | 7 | 7 | 10 | 13 | ... | 130 | 138 | 150 | 150 | 160 | 178 | 178 | 200 | 212 | 226 |
| 3 | 0 | 0 | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | ... | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
| 4 | 0 | 0 | 0 | 3 | 4 | 4 | 4 | 7 | 8 | 8 | ... | 83 | 93 | 99 | 117 | 129 | 149 | 149 | 197 | 238 | 428 |
5 rows à 54 columns
In [255]:
# Finding the total confirmed cases, death cases and the recovered cases and append them to an 4 empty lists # Also, calculate the total mortality rate which is the death_sum/confirmed cases dates = confirmed.keys() world_cases = [] total_deaths = [] mortality_rate = [] total_recovered = [] for i in dates: confirmed_sum = confirmed[i].sum() death_sum = deaths[i].sum() recovered_sum = recoveries[i].sum() world_cases.append(confirmed_sum ) total_deaths.append(death_sum) mortality_rate.append(death_sum /confirmed_sum) total_recovered.append(recovered_sum )
In [256]:
# Let's display each of the newly created variables confirmed_sum
Out[256]:
167449
In [257]:
death_sum
Out[257]:
6440
In [258]:
recovered_sum
Out[258]:
76034
In [259]:
world_cases
Out[259]:
[555, 653, 941, 1434, 2118, 2927, 5578, 6166, 8234, 9927, 12038, 16787, 19881, 23892, 27635, 30817, 34391, 37120, 40150, 42762, 44802, 45221, 60368, 66885, 69030, 71224, 73258, 75136, 75639, 76197, 76823, 78579, 78965, 79568, 80413, 81395, 82754, 84120, 86011, 88369, 90306, 92840, 95120, 97882, 101784, 105821, 109795, 113561, 118592, 125865, 128343, 145193, 156097, 167449]
In [260]:
# Convert all the dates and the cases in the form of a numpy array days_since_1_22 = np.array([i for i in range(len(dates))]).reshape(-1, 1) world_cases = np.array(world_cases).reshape(- 1, 1) total_deaths = np.array(total_deaths).reshape( -1, 1) total_recovered = np.array(total_recovered).reshape (-1, 1)
In [261]:
days_since_1_22
Out[261]:
array([[ 0],
[ 1],
[ 2],
[ 3],
[ 4],
[ 5],
[ 6],
[ 7],
[ 8],
[ 9],
[10],
[11],
[12],
[13],
[14],
[15],
[16],
[17],
[18],
[19],
[20],
[21],
[22],
[23],
[24],
[25],
[26],
[27],
[28],
[29],
[30],
[31],
[32],
[33],
[34],
[35],
[36],
[37],
[38],
[39],
[40],
[41],
[42],
[43],
[44],
[45],
[46],
[47],
[48],
[49],
[50],
[51],
[52],
[53]])
In [262]:
world_cases
Out[262]:
array([[ 555],
[ 653],
[ 941],
[ 1434],
[ 2118],
[ 2927],
[ 5578],
[ 6166],
[ 8234],
[ 9927],
[ 12038],
[ 16787],
[ 19881],
[ 23892],
[ 27635],
[ 30817],
[ 34391],
[ 37120],
[ 40150],
[ 42762],
[ 44802],
[ 45221],
[ 60368],
[ 66885],
[ 69030],
[ 71224],
[ 73258],
[ 75136],
[ 75639],
[ 76197],
[ 76823],
[ 78579],
[ 78965],
[ 79568],
[ 80413],
[ 81395],
[ 82754],
[ 84120],
[ 86011],
[ 88369],
[ 90306],
[ 92840],
[ 95120],
[ 97882],
[101784],
[105821],
[109795],
[113561],
[118592],
[125865],
[128343],
[145193],
[156097],
[167449]], dtype=int64)
In [263]:
total_deaths
Out[263]:
array([[ 17],
[ 18],
[ 26],
[ 42],
[ 56],
[ 82],
[ 131],
[ 133],
[ 171],
[ 213],
[ 259],
[ 362],
[ 426],
[ 492],
[ 564],
[ 634],
[ 719],
[ 806],
[ 906],
[1013],
[1113],
[1118],
[1371],
[1523],
[1666],
[1770],
[1868],
[2007],
[2122],
[2247],
[2251],
[2458],
[2469],
[2629],
[2708],
[2770],
[2814],
[2872],
[2941],
[2996],
[3085],
[3160],
[3254],
[3348],
[3460],
[3558],
[3802],
[3988],
[4262],
[4615],
[4720],
[5404],
[5819],
[6440]], dtype=int64)
In [264]:
total_recovered
Out[264]:
array([[ 28],
[ 30],
[ 36],
[ 39],
[ 52],
[ 61],
[ 107],
[ 126],
[ 143],
[ 222],
[ 284],
[ 472],
[ 623],
[ 852],
[ 1124],
[ 1487],
[ 2011],
[ 2616],
[ 3244],
[ 3946],
[ 4683],
[ 5150],
[ 6295],
[ 8058],
[ 9395],
[10865],
[12583],
[14352],
[16121],
[18177],
[18890],
[22886],
[23394],
[25227],
[27905],
[30384],
[33277],
[36711],
[39782],
[42716],
[45602],
[48228],
[51170],
[53796],
[55865],
[58358],
[60694],
[62494],
[64404],
[67003],
[68324],
[70251],
[72624],
[76034]], dtype=int64)
In [265]:
# Future forecasting for the next 10 days days_in_future = 10 future_forecast = np.array([i for i in range(len(dates)+days_in_future )]).reshape(-1, 1) adjusted_dates = future_forecast[:-10]
In [266]:
future_forecast
Out[266]:
array([[ 0],
[ 1],
[ 2],
[ 3],
[ 4],
[ 5],
[ 6],
[ 7],
[ 8],
[ 9],
[10],
[11],
[12],
[13],
[14],
[15],
[16],
[17],
[18],
[19],
[20],
[21],
[22],
[23],
[24],
[25],
[26],
[27],
[28],
[29],
[30],
[31],
[32],
[33],
[34],
[35],
[36],
[37],
[38],
[39],
[40],
[41],
[42],
[43],
[44],
[45],
[46],
[47],
[48],
[49],
[50],
[51],
[52],
[53],
[54],
[55],
[56],
[57],
[58],
[59],
[60],
[61],
[62],
[63]])
In [267]:
# Convert all the integers into datetime for better visualization start = '1/22/2020' start_date = datetime.datetime.strptime(start , '%m/%d/%Y') future_forcast_dates = [] for i in range(len(future_forcast)): future_forcast_dates.append((start_date + datetime.timedelta(days=i)).strftime ('%m/%d/%Y'))
In [268]:
# For visualization with the latest data of 15th of march latest_confirmed = confirmed_cases[dates[-1]] latest_deaths = deaths_reported[dates[-1]] latest_recoveries = recovered_cases[dates[-1]]
In [269]:
latest_confirmed
Out[269]:
0 114
1 839
2 226
3 1
4 428
...
445 1
446 1
447 1
448 1
449 1
Name: 3/15/20, Length: 450, dtype: int64
In [270]:
latest_deaths
Out[270]:
0 1
1 22
2 0
3 0
4 0
..
445 0
446 0
447 0
448 0
449 0
Name: 3/15/20, Length: 450, dtype: int64
In [271]:
latest_recoveries
Out[271]:
0 35
1 118
2 105
3 1
4 42
...
445 0
446 0
447 0
448 0
449 0
Name: 3/15/20, Length: 450, dtype: int64
In [272]:
# Find the list of unique countries unique_countries = list(confirmed_cases['Country/Region' ].unique()) unique_countries
Out[272]:
['Thailand', 'Japan', 'Singapore', 'Nepal', 'Malaysia', 'Canada', 'Australia', 'Cambodia', 'Sri Lanka', 'Germany', 'Finland', 'United Arab Emirates', 'Philippines', 'India', 'Italy', 'Sweden', 'Spain', 'Belgium', 'Egypt', 'Lebanon', 'Iraq', 'Oman', 'Afghanistan', 'Bahrain', 'Kuwait', 'Algeria', 'Croatia', 'Switzerland', 'Austria', 'Israel', 'Pakistan', 'Brazil', 'Georgia', 'Greece', 'North Macedonia', 'Norway', 'Romania', 'Estonia', 'Netherlands', 'San Marino', 'Belarus', 'Iceland', 'Lithuania', 'Mexico', 'New Zealand', 'Nigeria', 'Ireland', 'Luxembourg', 'Monaco', 'Qatar', 'Ecuador', 'Azerbaijan', 'Armenia', 'Dominican Republic', 'Indonesia', 'Portugal', 'Andorra', 'Latvia', 'Morocco', 'Saudi Arabia', 'Senegal', 'Argentina', 'Chile', 'Jordan', 'Ukraine', 'Hungary', 'Liechtenstein', 'Poland', 'Tunisia', 'Bosnia and Herzegovina', 'Slovenia', 'South Africa', 'Bhutan', 'Cameroon', 'Colombia', 'Costa Rica', 'Peru', 'Serbia', 'Slovakia', 'Togo', 'Malta', 'Martinique', 'Bulgaria', 'Maldives', 'Bangladesh', 'Paraguay', 'Albania', 'Cyprus', 'Brunei', 'US', 'Burkina Faso', 'Holy See', 'Mongolia', 'Panama', 'China', 'Iran', 'Korea, South', 'France', 'Cruise Ship', 'Denmark', 'Czechia', 'Taiwan*', 'Vietnam', 'Russia', 'Moldova', 'Bolivia', 'Honduras', 'United Kingdom', 'Congo (Kinshasa)', "Cote d'Ivoire", 'Jamaica', 'Reunion', 'Turkey', 'Cuba', 'Guyana', 'Kazakhstan', 'Cayman Islands', 'Guadeloupe', 'Ethiopia', 'Sudan', 'Guinea', 'Aruba', 'Kenya', 'Antigua and Barbuda', 'Uruguay', 'Ghana', 'Jersey', 'Namibia', 'Seychelles', 'Trinidad and Tobago', 'Venezuela', 'Curacao', 'Eswatini', 'Gabon', 'Guatemala', 'Guernsey', 'Mauritania', 'Rwanda', 'Saint Lucia', 'Saint Vincent and the Grenadines', 'Suriname', 'occupied Palestinian territory', 'Kosovo', 'Central African Republic', 'Congo (Brazzaville)', 'Equatorial Guinea', 'Uzbekistan']
In [273]:
# The next line of code will basically calculate the total number of confirmed cases by each country country_confirmed_cases = [] no_cases = [] for i in unique_countries: cases = latest_confirmed[confirmed_cases ['Country/Region']==i].sum () if cases > 0: country_confirmed_cases.append( cases) else: no_cases.append(i) for i in no_cases: unique_countries.remove(i) unique_countries = [k for k, v in sorted(zip(unique_countries, country_confirmed_cases), key=operator.itemgetter(1), reverse=True)] for i in range(len(unique_countries)): country_confirmed_cases[i] = latest_confirmed[confirmed_cases ['Country/Region']==unique_countries [i]].sum()
In [274]:
# number of cases per country/region print('Confirmed Cases by Countries/Regions:') for i in range(len(unique_countries)): print(f'{unique_countries[i]}: {country_confirmed_cases[i]} cases')
Confirmed Cases by Countries/Regions: China: 81003 cases Italy: 24747 cases Iran: 13938 cases Korea, South: 8162 cases Spain: 7798 cases Germany: 5795 cases France: 4513 cases US: 3499 cases Switzerland: 2200 cases Norway: 1221 cases United Kingdom: 1144 cases Netherlands: 1135 cases Sweden: 1022 cases Belgium: 886 cases Denmark: 875 cases Austria: 860 cases Japan: 839 cases Cruise Ship: 696 cases Malaysia: 428 cases Qatar: 401 cases Greece: 331 cases Australia: 297 cases Czechia: 253 cases Canada: 252 cases Israel: 251 cases Portugal: 245 cases Finland: 244 cases Singapore: 226 cases Slovenia: 219 cases Bahrain: 214 cases Estonia: 171 cases Iceland: 171 cases Brazil: 162 cases Philippines: 140 cases Romania: 131 cases Ireland: 129 cases Poland: 119 cases Indonesia: 117 cases Iraq: 116 cases Thailand: 114 cases India: 113 cases Kuwait: 112 cases Egypt: 110 cases Lebanon: 110 cases Saudi Arabia: 103 cases San Marino: 101 cases United Arab Emirates: 98 cases Chile: 74 cases Russia: 63 cases Luxembourg: 59 cases Taiwan*: 59 cases Vietnam: 56 cases Slovakia: 54 cases Pakistan: 53 cases South Africa: 51 cases Bulgaria: 51 cases Brunei: 50 cases Croatia: 49 cases Algeria: 48 cases Serbia: 48 cases Argentina: 45 cases Peru: 43 cases Panama: 43 cases Albania: 42 cases Mexico: 41 cases Colombia: 34 cases Georgia: 33 cases Hungary: 32 cases Latvia: 30 cases Ecuador: 28 cases Morocco: 28 cases Belarus: 27 cases Costa Rica: 27 cases Armenia: 26 cases Cyprus: 26 cases Senegal: 24 cases Bosnia and Herzegovina: 24 cases Azerbaijan: 23 cases Moldova: 23 cases Oman: 22 cases Malta: 21 cases Sri Lanka: 18 cases Tunisia: 18 cases Afghanistan: 16 cases North Macedonia: 14 cases Maldives: 13 cases Lithuania: 12 cases Dominican Republic: 11 cases Bolivia: 10 cases Jamaica: 10 cases Venezuela: 10 cases Martinique: 9 cases Kazakhstan: 9 cases New Zealand: 8 cases Jordan: 8 cases Cambodia: 7 cases Reunion: 7 cases Paraguay: 6 cases Turkey: 6 cases Ghana: 6 cases Bangladesh: 5 cases Liechtenstein: 4 cases Cuba: 4 cases Guyana: 4 cases Uruguay: 4 cases Ukraine: 3 cases Burkina Faso: 3 cases Honduras: 3 cases Guadeloupe: 3 cases Kenya: 3 cases Nigeria: 2 cases Monaco: 2 cases Cameroon: 2 cases Congo (Kinshasa): 2 cases Aruba: 2 cases Jersey: 2 cases Namibia: 2 cases Seychelles: 2 cases Trinidad and Tobago: 2 cases Saint Lucia: 2 cases Kosovo: 2 cases Nepal: 1 cases Andorra: 1 cases Bhutan: 1 cases Togo: 1 cases Holy See: 1 cases Mongolia: 1 cases Cote d'Ivoire: 1 cases Cayman Islands: 1 cases Ethiopia: 1 cases Sudan: 1 cases Guinea: 1 cases Antigua and Barbuda: 1 cases Curacao: 1 cases Eswatini: 1 cases Gabon: 1 cases Guatemala: 1 cases Guernsey: 1 cases Mauritania: 1 cases Rwanda: 1 cases Saint Vincent and the Grenadines: 1 cases Suriname: 1 cases Central African Republic: 1 cases Congo (Brazzaville): 1 cases Equatorial Guinea: 1 cases Uzbekistan: 1 cases
In [275]:
# Find the list of unique provinces unique_provinces = list(confirmed_cases['Province/State' ].unique()) # those are countries, which are not provinces/states. outliers = ['United Kingdom', 'Denmark', 'France'] for i in outliers: unique_provinces.remove(i)
In [276]:
# Finding the number of confirmed cases per province, state or city province_confirmed_cases = [] no_cases = [] for i in unique_provinces: cases = latest_confirmed[confirmed_cases ['Province/State']==i].sum () if cases > 0: province_confirmed_cases.append (cases) else: no_cases.append(i) for i in no_cases: unique_provinces.remove(i)
In [277]:
# number of cases per province/state/city for i in range(len(unique_provinces)): print(f'{unique_provinces[i]}: {province_confirmed_cases[i]} cases')
British Columbia: 73 cases New South Wales: 134 cases Victoria: 57 cases Queensland: 61 cases South Australia: 20 cases Western Australia: 17 cases Tasmania: 6 cases Northern Territory: 1 cases Ontario: 104 cases Alberta: 39 cases Quebec: 24 cases Washington: 643 cases New York: 732 cases California: 426 cases Massachusetts: 164 cases Diamond Princess: 742 cases Grand Princess: 23 cases Georgia: 99 cases Colorado: 131 cases Florida: 115 cases New Jersey: 98 cases Oregon: 36 cases Texas: 72 cases Illinois: 93 cases Pennsylvania: 66 cases Iowa: 18 cases Maryland: 32 cases North Carolina: 33 cases South Carolina: 28 cases Tennessee: 39 cases Virginia: 45 cases Arizona: 13 cases Indiana: 20 cases Kentucky: 20 cases District of Columbia: 16 cases Nevada: 24 cases New Hampshire: 13 cases Minnesota: 35 cases Nebraska: 17 cases Ohio: 37 cases Rhode Island: 20 cases Wisconsin: 32 cases Connecticut: 24 cases Hawaii: 6 cases Oklahoma: 7 cases Utah: 28 cases Kansas: 8 cases Louisiana: 91 cases Missouri: 5 cases Vermont: 8 cases Alaska: 1 cases Arkansas: 16 cases Delaware: 7 cases Idaho: 5 cases Maine: 12 cases Michigan: 33 cases Mississippi: 10 cases Montana: 7 cases New Mexico: 13 cases North Dakota: 1 cases South Dakota: 9 cases Wyoming: 3 cases Hubei: 67794 cases Guangdong: 1360 cases Henan: 1273 cases Zhejiang: 1231 cases Hunan: 1018 cases Anhui: 990 cases Jiangxi: 935 cases Shandong: 760 cases Jiangsu: 631 cases Chongqing: 576 cases Sichuan: 539 cases Heilongjiang: 482 cases Beijing: 442 cases Shanghai: 353 cases Hebei: 318 cases Fujian: 296 cases Guangxi: 252 cases Shaanxi: 245 cases Yunnan: 174 cases Hainan: 168 cases Guizhou: 146 cases Tianjin: 136 cases Shanxi: 133 cases Gansu: 133 cases Hong Kong: 145 cases Liaoning: 125 cases Jilin: 93 cases Xinjiang: 76 cases Inner Mongolia: 75 cases Ningxia: 75 cases Qinghai: 18 cases Macau: 10 cases Faroe Islands: 11 cases St Martin: 2 cases Channel Islands: 3 cases New Brunswick: 2 cases Tibet: 1 cases Saint Barthelemy: 1 cases Gibraltar: 1 cases Australian Capital Territory: 1 cases French Polynesia: 3 cases Manitoba: 4 cases Saskatchewan: 2 cases Alabama: 12 cases Puerto Rico: 5 cases Virgin Islands, U.S.: 1 cases French Guiana: 7 cases Guam: 3 cases Newfoundland and Labrador: 1 cases Prince Edward Island: 1 cases Mayotte: 1 cases
In [278]:
# handling nan values if there is any nan_indices = [] for i in range(len(unique_provinces)): if type(unique_provinces[i]) == float: nan_indices.append(i) unique_provinces = list(unique_provinces) province_confirmed_cases = list(province_confirmed_cases) for i in nan_indices: unique_provinces.pop(i) province_confirmed_cases.pop(i)
In [279]:
# Plot a bar graph to see the total confirmed cases across different countries plt.figure(figsize=(32, 32)) plt.barh(unique_countries, country_confirmed_cases) plt.title('Number of Covid-19 Confirmed Cases in Countries') plt.xlabel('Number of Covid19 Confirmed Cases') plt.show()
In [280]:
# Plot a bar graph to see the total confirmed cases between mainland china and outside mainland china china_confirmed = latest_confirmed[confirmed_cases ['Country/Region']=='China' ].sum() outside_mainland_china_confirmed = np.sum(country_confirmed_cases) - china_confirmed plt.figure(figsize=(16, 9)) plt.barh('Mainland China', china_confirmed) plt.barh('Outside Mainland China', outside_mainland_china_confirmed ) plt.title('Number of Confirmed Coronavirus Cases') plt.show()
In [281]:
# Print the total cases in mainland china and outside of it print('Outside Mainland China {} cases:'.format(outside_mainland_china_confirmed )) print('Mainland China: {} cases'.format(china_confirmed)) print('Total: {} cases'.format(china_confirmed+outside_mainland_china_ ))confirmed
Outside Mainland China 86446 cases: Mainland China: 81003 cases Total: 167449 cases
In [282]:
# Only show 10 countries with the most confirmed cases, the rest are grouped into the category named others visual_unique_countries = [] visual_confirmed_cases = [] others = np.sum(country_confirmed_cases[ 10:]) for i in range(len(country_confirmed_cases [:10])): visual_unique_countries.append( unique_countries[i]) visual_confirmed_cases.append(country_confirmed_cases [i]) visual_unique_countries.append( 'Others') visual_confirmed_cases.append(others )
In [283]:
# Visualize the 10 countries plt.figure(figsize=(32, 18)) plt.barh(visual_unique_countries , visual_confirmed_cases) plt.title('Number of Covid-19 Confirmed Cases in Countries/Regions', size=20) plt.show()
In [284]:
# Create a pie chart to see the total confirmed cases in 10 different countries c = random.choices(list(mcolors.CSS4_COLORS .values()),k = len(unique_countries)) plt.figure(figsize=(20,20)) plt.title('Covid-19 Confirmed Cases per Country') plt.pie(visual_confirmed_cases, colors=c) plt.legend(visual_unique_countries , loc='best') plt.show()
In [285]:
# Create a pie chart to see the total confirmed cases in 10 different countries outside China c = random.choices(list(mcolors.CSS4_COLORS .values()),k = len(unique_countries)) plt.figure(figsize=(20,20)) plt.title('Covid-19 Confirmed Cases in Countries Outside of Mainland China') plt.pie(visual_confirmed_cases[ 1:], colors=c) plt.legend(visual_unique_countries [1:], loc='best') plt.show()
In [286]:
# Building the SVM model kernel = ['poly', 'sigmoid', 'rbf'] c = [0.01, 0.1, 1, 10] gamma = [0.01, 0.1, 1] epsilon = [0.01, 0.1, 1] shrinking = [True, False] svm_grid = {'kernel': kernel, 'C': c, 'gamma' : gamma, 'epsilon': epsilon, 'shrinking' : shrinking} svm = SVR() svm_search = RandomizedSearchCV(svm, svm_grid, scoring='neg_mean_squared_error' , cv=3, return_train_score=True, n_jobs=-1, n_iter=40, verbose=1) svm_search.fit(X_train_confirmed , y_train_confirmed)
Fitting 3 folds for each of 40 candidates, totalling 120 fits
[Parallel(n_jobs=-1)]: Using backend LokyBackend with 4 concurrent workers. [Parallel(n_jobs=-1)]: Done 44 tasks | elapsed: 8.1s [Parallel(n_jobs=-1)]: Done 120 out of 120 | elapsed: 37.2s finished C:\ProgramData\Anaconda3\lib\site-packages\sklearn\utils\ validation.py:724: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel(). y = column_or_1d(y, warn=True)
Out[286]:
RandomizedSearchCV(cv=3, error_score='raise-deprecating', estimator=SVR(C=1.0, cache_size=200, coef0=0.0, degree=3, epsilon=0.1, gamma='auto_deprecated', kernel='rbf', max_iter=-1, shrinking=True, tol=0.001, verbose=False), iid='warn', n_iter=40, n_jobs=-1, param_distributions={'C': [0.01, 0.1, 1, 10], 'epsilon': [0.01, 0.1, 1], 'gamma': [0.01, 0.1, 1], 'kernel': ['poly', 'sigmoid', 'rbf'], 'shrinking': [True, False]}, pre_dispatch='2*n_jobs', random_state=None, refit=True, return_train_score=True, scoring='neg_mean_squared_ error', verbose=1)
In [287]:
svm_search.best_params_
Out[287]:
{'shrinking': False,
'kernel': 'poly',
'gamma': 0.1,
'epsilon': 0.01,
'C': 0.01}
In [288]:
svm_confirmed = svm_search.best_estimator_ svm_pred = svm_confirmed.predict(future_forecast )
In [289]:
svm_confirmed
Out[289]:
SVR(C=0.01, cache_size=200, coef0=0.0, degree=3, epsilon=0.01, gamma=0.1,
kernel='poly', max_iter=-1, shrinking=False, tol=0.001, verbose=False)
In [290]:
svm_pred
Out[290]:
array([ 30387.35440129, 30388.33185622, 30395.1740407 , 30413.74568429,
30449.91151654, 30509.53626702, 30598.48466527, 30722.62144085,
30887.81132331, 31099.91904222, 31364.80932711, 31688.34690756,
32076.39651311, 32534.82287332, 33069.49071775, 33686.26477594,
34391.00977746, 35189.59045185, 36087.87152868, 37091.7177375 ,
38206.99380786, 39439.56446933, 40795.29445144, 42280.04848376,
43899.69129585, 45660.08761726, 47567.10217753, 49626.59970624,
51844.44493293, 54226.50258716, 56778.63739848, 59506.71409644,
62416.59741062, 65514.15207054, 68805.24280579, 72295.7343459 ,
75991.49142043, 79898.37875894, 84022.26109098, 88369.00314611,
92944.46965388, 97754.52534385, 102805.03494557, 108101.8631886 ,
113650.87480248, 119457.93451679, 125528.90706107, 131869.65716488,
138486.04955776, 145383.94896929, 152569.220129 , 160047.72776646,
167825.33661123, 175907.91139284, 184301.31684088, 193011.41768487,
202044.07865439, 211405.16447898, 221100.53988821, 231136.06961162,
241517.61837877, 252251.05091922, 263342.23196252, 274797.02623822])
In [291]:
# check against testing data svm_test_pred = svm_confirmed.predict(X_test_confirmed ) plt.plot(svm_test_pred) plt.plot(y_test_confirmed) print('MAE:', mean_absolute_error(svm_test_pred , y_test_confirmed)) print('MSE:',mean_squared_error (svm_test_pred, y_test_confirmed))
MAE: 16262.299241035274 MSE: 284685673.1830624
In [292]:
# Total Number of coronavirus cases over time plt.figure(figsize=(20, 12)) plt.plot(adjusted_dates, world_cases) plt.title('Number of Coronavirus Cases Over Time', size=30) plt.xlabel('Days Since 1/22/2020', size=30) plt.ylabel('Number of Cases', size=30) plt.xticks(size=15) plt.yticks(size=15) plt.show()
In [293]:
# Confirmed vs Predicted cases plt.figure(figsize=(20, 12)) plt.plot(adjusted_dates, world_cases) plt.plot(future_forcast, svm_pred, linestyle='dashed', color='purple') plt.title('Number of Coronavirus Cases Over Time', size=30) plt.xlabel('Days Since 1/22/2020', size=30) plt.ylabel('Number of Cases', size=30) plt.legend(['Confirmed Cases', 'SVM predictions']) plt.xticks(size=15) plt.yticks(size=15) plt.show()
In [294]:
# Predictions for the next 10 days using SVM print('SVM future predictions:') set(zip(future_forcast_dates[-10 :], svm_pred[-10:]))
SVM future predictions:
Out[294]:
{('03/16/2020', 184301.31684087563),
('03/17/2020', 193011.4176848725),
('03/18/2020', 202044.07865439056),
('03/19/2020', 211405.1644789848),
('03/20/2020', 221100.53988820987),
('03/21/2020', 231136.06961162097),
('03/22/2020', 241517.618378773),
('03/23/2020', 252251.05091922113),
('03/24/2020', 263342.23196251923),
('03/25/2020', 274797.0262382235)}
In [295]:
# Using Linear regression model to make predictions from sklearn.linear_model import LinearRegression linear_model = LinearRegression(normalize=True , fit_intercept=True) linear_model.fit(X_train_confirmed , y_train_confirmed) test_linear_pred = linear_model.predict(X_test_confirmed ) linear_pred = linear_model.predict(future_forcast ) print('MAE:', mean_absolute_error(test_linear_pred , y_test_confirmed)) print('MSE:',mean_squared_error (test_linear_pred, y_test_confirmed))
MAE: 11965.537037037033 MSE: 307996364.0108404
In [296]:
plt.plot(y_test_confirmed) plt.plot(test_linear_pred)
Out[296]:
[<matplotlib.lines.Line2D at 0x24e0303edc8>]
In [297]:
plt.figure(figsize=(20, 12)) plt.plot(adjusted_dates, world_cases) plt.plot(future_forcast, linear_pred, linestyle='dashed', color='orange') plt.title('Number of Coronavirus Cases Over Time', size=30) plt.xlabel('Days Since 1/22/2020', size=30) plt.ylabel('Number of Cases', size=30) plt.legend(['Confirmed Cases', 'Linear Regression Predictions']) plt.xticks(size=15) plt.yticks(size=15) plt.show()
In [298]:
# Predictions for the next 10 days using Linear Regression print('Linear regression future predictions:') print(linear_pred[-10:])
Linear regression future predictions: [[132336.25252525] [134890.72222222] [137445.19191919] [139999.66161616] [142554.13131313] [145108.6010101 ] [147663.07070707] [150217.54040404] [152772.01010101] [155326.47979798]]
In [299]:
# Total deaths over time plt.figure(figsize=(20, 12)) plt.plot(adjusted_dates, total_deaths, color='red') plt.title('Number of Coronavirus Deaths Over Time', size=30) plt.xlabel('Time', size=30) plt.ylabel('Number of Deaths', size=30) plt.xticks(size=15) plt.yticks(size=15) plt.show()
In [300]:
mean_mortality_rate = np.mean(mortality_rate) plt.figure(figsize=(20, 12)) plt.plot(adjusted_dates, mortality_rate, color='orange') plt.axhline(y = mean_mortality_rate,linestyle='--' , color='black') plt.title('Mortality Rate of Coronavirus Over Time', size=30) plt.legend(['mortality rate', 'y='+str(mean_mortality_rate)]) plt.xlabel('Time', size=30) plt.ylabel('Mortality Rate', size=30) plt.xticks(size=15) plt.yticks(size=15) plt.show()
In [301]:
# Coronavirus Cases Recovered Over Time plt.figure(figsize=(20, 12)) plt.plot(adjusted_dates, total_recovered, color='green') plt.title('Number of Coronavirus Cases Recovered Over Time', size=30) plt.xlabel('Time', size=30) plt.ylabel('Number of Cases', size=30) plt.xticks(size=15) plt.yticks(size=15) plt.show()
In [302]:
# Number of Coronavirus cases recovered vs the number of deaths plt.figure(figsize=(20, 12)) plt.plot(adjusted_dates, total_deaths, color='r') plt.plot(adjusted_dates, total_recovered, color='green') plt.legend(['deaths', 'recoveries'], loc='best', fontsize=20) plt.title('Number of Coronavirus Cases', size=30) plt.xlabel('Time', size=30) plt.ylabel('Number of Cases', size=30) plt.xticks(size=15) plt.yticks(size=15) plt.show()
In [303]:
# Coronavirus Deaths vs Recoveries plt.figure(figsize=(20, 12)) plt.plot(total_recovered, total_deaths) plt.title('Coronavirus Deaths vs Coronavirus Recoveries', size=30) plt.xlabel('Total number of Coronavirus Recoveries', size=30) plt.ylabel('Total number of Coronavirus Deaths', size=30) plt.xticks(size=15) plt.yticks(size=15) plt.show()
In [ ]: