COVID-19 - Pandemic in India!

DISCLAIMER - This is an auto generated README.md created within jupyterlab using the main India_&_World_COVID_19.ipynb file and hence has some cuts and glitches. I highly recommend going through the main notebook file for the perfect version.

To run the project in its whole, extra datasets (given as .zip) are needed. You can clone the repository in your working directory with the command: git clone https://github.com/rawatraghav/INDIA-and-COVID-19.git or download repository as zip file.

COVID-19 - Pandemic in India!

About COVID-19

The coronavirus (COVID-19) pandemic is the greatest global humanitarian challenge the world has faced since World War II. The pandemic virus has spread widely, and the number of cases is rising daily. The government is working to slow down its spread.

Till date it has spread across 215 countries infecting 5,491,194 people and killing 346,331 so far. In India, as many as 138,536 COVID-19 cases have been reported so far. Of these, 57,692 have recovered and 4,024 have died. COVID19

Corona Virus Explained in Simple Terms:

Let's say Raghav got infected yesterday, but he won't know it untill next 14 days
Raghav thinks he is healthy but he is infecting 10 persons per day
Now these 10 persons think they are completely healthy, they travel, go out and infect 100 others
These 100 persons think they are healthy but they have already infected 1000 persons
No one knows who is healthy or who can infect you
All you can do is be responsible, stay in quarentine

Problem Statement:

India has responded quickly, implementing a proactive, nationwide, lockdown, to flatten the curve and use the time to plan and resource responses adequately. As of 23rd May 2020, India has witnessed 3720 deaths from 32 States and Union Territories, with a total of 123202 confirmed cases due to COVID-19. Globally the Data Scientists are using AI and machine learning to analyze, predict, and take safety measures against COVID-19 in India.

We need a explore the COVID situation in India and the world, and strong model that predicts how the virus could spread across India in the next 15 days. ###Steps to be achieved:

Analyze the present condition in India
Collect the COVID-19 data from websites
Figure out the death rate and cure rate per 100 citizens across the affected states
Plotting charts to visualize the following:
Age group distribution of affected patients
Total sample tests done till date
Growth rate of COVID in top 15 states
Top 10 States in each health facility
State wise testing insights
ICMR testing centres in each state
Use Facebook Prophet to predict the confirmed cases in India
Use ARIMA time series model to predict the confirmed cases in India
Compare the Indian COVID-19 cases on global level

Importing the required libraries

# importing the required libraries
# !pip install folium
import pandas as pd

# Visualisation libraries
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
import plotly.express as px
import plotly.graph_objects as go
import folium 
from folium import plugins

# Manipulating the default plot size
plt.rcParams['figure.figsize'] = 10, 12

# Disable warnings 
import warnings
warnings.filterwarnings('ignore')

Part 1: Analysing the present condition in India

How it started in India?:

The first COVID-19 case was reported on 30th January 2020 when a student arrived Kerala from Wuhan. Just in next 2 days, Kerela reported 2 more cases. For almost a month, no new cases were reported in India, however, on 2nd March 2020, five new cases of corona virus were reported in Kerala again and since then the cases have been rising affecting 25 states, till now (Bihar and Manipur being the most recent). Here is a brief timeline of the cases in India. ###COVID-19 in India - Timeline

Recent COVID-19 updates in India

Sikkim on Saturday reported its first +ve COVID-19 case
With over 6,500 fresh cases, the Covid in India rose to 1,25,101 on Saturday morning, with 3,720 fatalities
West Bengal asks Railways not to send migrant trains to State till May 26 in view of Cyclone Amphan
196 new COVID 19 positive cases were reported in Karnataka on Saturday
Complete lockdown in Bengaluru on Sunday.
Bruhat Bengaluru Mahanagara Palike (BBMP) Commissioner B.H. Anil Kumar said the conditions and restrictions on Sunday will be similar to that under coronavirus lockdown 1.0.

How is AI-ML useful in fighting the COVID-19 pandemic?

Medical resource optimization
Ensuring demand planning stability
Contact tracing
Situational awareness and critical response analysis

1.1 Scraping the datasets from the official Govt. website

# for date and time opeations
from datetime import datetime
# for file and folder operations
import os
# for regular expression opeations
import re
# for listing files in a folder
import glob
# for getting web contents
import requests 
import json
import csv
import numpy as np
# for scraping web contents
# from bs4 import BeautifulSoup

raw_1 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data1.csv')
raw_2 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data2.csv')
raw_3 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data3.csv')
raw_4 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data4.csv')
raw_5 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data5.csv')
raw_6 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data6.csv')
raw_7 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data7.csv')
raw_8 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data8.csv')
raw_9 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data9.csv')
raw_10 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data10.csv')
raw_11 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data11.csv')
raw_12 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data12.csv')
raw_13 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data13.csv')
raw_14 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data14.csv')
raw_15 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data15.csv')
raw_16 = pd.read_csv('https://api.covid19india.org/csv/latest/raw_data16.csv')

full_data = pd.concat([raw_1,
raw_2,
raw_3,
raw_4,
raw_5,
raw_6,
raw_7,
raw_8,
raw_9,
raw_10,
raw_11,
raw_12,
raw_13,
raw_14,
raw_15,
raw_16])

print(full_data.shape)
full_data.head()

(352525, 22)

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Patient Number	State Patient Number	Date Announced	Estimated Onset Date	Age Bracket	Gender	Detected City	Detected District	Detected State	State code	...	Contracted from which Patient (Suspected)	Nationality	Type of transmission	Status Change Date	Source_1	Source_2	Source_3	Backup Notes	Num Cases	Entry_ID
0	1.0	KL-TS-P1	30/01/2020	NaN	20	F	Thrissur	Thrissur	Kerala	KL	...	NaN	India	Imported	14/02/2020	https://twitter.com/vijayanpinarayi/status/122...	https://weather.com/en-IN/india/news/news/2020...	NaN	Student from Wuhan	1.0	NaN
1	2.0	KL-AL-P1	02/02/2020	NaN	NaN	NaN	Alappuzha	Alappuzha	Kerala	KL	...	NaN	India	Imported	14/02/2020	https://www.indiatoday.in/india/story/kerala-r...	https://weather.com/en-IN/india/news/news/2020...	NaN	Student from Wuhan	1.0	NaN
2	3.0	KL-KS-P1	03/02/2020	NaN	NaN	NaN	Kasaragod	Kasaragod	Kerala	KL	...	NaN	India	Imported	14/02/2020	https://www.indiatoday.in/india/story/kerala-n...	https://twitter.com/ANI/status/122422148580539...	https://weather.com/en-IN/india/news/news/2020...	Student from Wuhan	1.0	NaN
3	4.0	DL-P1	02/03/2020	NaN	45	M	East Delhi (Mayur Vihar)	East Delhi	Delhi	DL	...	NaN	India	Imported	15/03/2020	https://www.indiatoday.in/india/story/not-a-ja...	https://economictimes.indiatimes.com/news/poli...	NaN	Travel history to Italy and Austria	1.0	NaN
4	5.0	TS-P1	02/03/2020	NaN	24	M	Hyderabad	Hyderabad	Telangana	TG	...	NaN	India	Imported	02/03/2020	https://www.deccanherald.com/national/south/qu...	https://www.indiatoday.in/india/story/coronavi...	https://www.thehindu.com/news/national/coronav...	Travel history to Dubai, Singapore contact	1.0	NaN

5 rows × 22 columns

Daily Cases

day_wise = pd.read_csv('https://api.covid19india.org/csv/latest/case_time_series.csv')

day_wise.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Date	Daily Confirmed	Total Confirmed
0	30 January	1	1
1	31 January	0	1
2	01 February	0	1
3	02 February	1	2
4	03 February	1	3

State Wise

state_wise = pd.read_csv('https://api.covid19india.org/csv/latest/state_wise.csv')

state_wise.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	State	Confirmed	Recovered	Deaths	Active	Last_Updated_Time	Migrated_Other	State_code	Delta_Confirmed	Delta_Recovered	Delta_Deaths	State_Notes
0	Total	6877073	5871898	106037	898090	08/10/2020 21:24:52	1048	TT	44085	47436	483	NaN
1	Maharashtra	1480489	1196441	39072	244527	07/10/2020 22:32:57	449	MH	0	0	0	[Sep 9] :239 cases have been removed from the ...
2	Andhra Pradesh	734427	678828	6086	49513	07/10/2020 17:50:55	0	AP	0	0	0	NaN
3	Karnataka	679356	552519	9675	117143	08/10/2020 21:13:54	19	KA	10704	9613	101	NaN
4	Tamil Nadu	640943	586454	10052	44437	08/10/2020 21:13:56	0	TN	5088	5718	68	[July 22]: 444 backdated deceased entries adde...

from datetime import date

state_wise_daily = pd.read_csv('https://api.covid19india.org/csv/latest/state_wise_daily.csv')

state_wise_daily = state_wise_daily.melt(id_vars=['Date','Status'],
                                        value_vars=state_wise_daily.columns[2:],
                                        var_name='State',value_name='Count')

state_wise_daily = state_wise_daily.pivot_table(index=['Date','State'],
                                        columns=['Status'],values='Count').reset_index()

state_codes = {code:state for code, state in zip(state_wise['State_code'], state_wise['State'])}
state_codes['DD'] = 'Daman and Diu'
state_wise_daily['State_Name'] = state_wise_daily['State'].map(state_codes)

state_wise_daily

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

Status	Date	State	Confirmed	Deceased	Recovered	State_Name
0	01-Apr-20	AN	0	0	0	Andaman and Nicobar Islands
1	01-Apr-20	AP	67	0	1	Andhra Pradesh
2	01-Apr-20	AR	0	0	0	Arunachal Pradesh
3	01-Apr-20	AS	15	0	0	Assam
4	01-Apr-20	BR	3	0	0	Bihar
...	...	...	...	...	...	...
8107	31-May-20	TT	8789	222	4928	Total
8108	31-May-20	UN	448	0	0	State Unassigned
8109	31-May-20	UP	374	4	192	Uttar Pradesh
8110	31-May-20	UT	158	0	0	Uttarakhand
8111	31-May-20	WB	371	8	187	West Bengal

8112 rows × 6 columns

state_wise.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	State	Confirmed	Recovered	Deaths	Active	Last_Updated_Time	Migrated_Other	State_code	Delta_Confirmed	Delta_Recovered	Delta_Deaths	State_Notes
0	Total	6877073	5871898	106037	898090	08/10/2020 21:24:52	1048	TT	44085	47436	483	NaN
1	Maharashtra	1480489	1196441	39072	244527	07/10/2020 22:32:57	449	MH	0	0	0	[Sep 9] :239 cases have been removed from the ...
2	Andhra Pradesh	734427	678828	6086	49513	07/10/2020 17:50:55	0	AP	0	0	0	NaN
3	Karnataka	679356	552519	9675	117143	08/10/2020 21:13:54	19	KA	10704	9613	101	NaN
4	Tamil Nadu	640943	586454	10052	44437	08/10/2020 21:13:56	0	TN	5088	5718	68	[July 22]: 444 backdated deceased entries adde...

Data Cleaning

# date-time information
# =====================
#saving a copy of the dataframe
df_India = state_wise.copy()
# today's date
now  = datetime.now()
# format date to month-day-year
df_India['Date'] = now.strftime("%m/%d/%Y") 

# add 'Date' column to dataframe
df_India['Date'] = pd.to_datetime(df_India['Date'], format='%m/%d/%Y')

df_India.head(36)

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	State	Confirmed	Recovered	Deaths	Active	Last_Updated_Time	Migrated_Other	State_code	Delta_Confirmed	Delta_Recovered	Delta_Deaths	State_Notes	Date
0	Total	6877073	5871898	106037	898090	08/10/2020 21:24:52	1048	TT	44085	47436	483	NaN	2020-10-08
1	Maharashtra	1480489	1196441	39072	244527	07/10/2020 22:32:57	449	MH	0	0	0	[Sep 9] :239 cases have been removed from the ...	2020-10-08
2	Andhra Pradesh	734427	678828	6086	49513	07/10/2020 17:50:55	0	AP	0	0	0	NaN	2020-10-08
3	Karnataka	679356	552519	9675	117143	08/10/2020 21:13:54	19	KA	10704	9613	101	NaN	2020-10-08
4	Tamil Nadu	640943	586454	10052	44437	08/10/2020 21:13:56	0	TN	5088	5718	68	[July 22]: 444 backdated deceased entries adde...	2020-10-08
5	Uttar Pradesh	427459	378662	6245	42552	08/10/2020 21:21:49	0	UP	3133	3690	45	NaN	2020-10-08
6	Delhi	300833	272948	5643	22242	08/10/2020 21:13:59	0	DL	2726	2643	27	[July 14]: Value for the total tests conducted...	2020-10-08
7	West Bengal	284030	249737	5439	28854	08/10/2020 21:21:51	0	WB	3526	2970	63	NaN	2020-10-08
8	Odisha	244142	216984	1027	26131	08/10/2020 21:14:03	0	OR	3144	3312	16	[July 12th] :20 non-covid deaths reported in s...	2020-10-08
9	Kerala	258851	167256	931	90579	08/10/2020 20:37:52	85	KL	5445	7003	24	Mahe native who expired in Kannur included in ...	2020-10-08
10	Telangana	206644	179075	1201	26368	08/10/2020 10:44:51	0	TG	1896	2067	12	[July 27] : Telangana bulletin for the previou...	2020-10-08
11	Bihar	192671	180357	929	11384	08/10/2020 21:21:53	1	BR	1244	1006	2	NaN	2020-10-08
12	Assam	191397	157635	794	32965	08/10/2020 21:14:07	3	AS	1188	0	9	NaN	2020-10-08
13	Gujarat	147950	128023	3541	16386	08/10/2020 21:14:08	0	GJ	1278	1266	10	NaN	2020-10-08
14	Rajasthan	150467	127526	1590	21351	07/10/2020 19:54:02	0	RJ	0	0	0	NaN	2020-10-08
15	Madhya Pradesh	142012	122687	2547	16778	08/10/2020 21:24:54	0	MP	1705	2420	29	NaN	2020-10-08
16	Haryana	138582	126267	1548	10767	08/10/2020 21:21:58	0	HR	1184	1426	20	[Aug 2]: 21 Foreign Evacuees have been merged ...	2020-10-08
17	Chhattisgarh	131739	103828	1134	26777	07/10/2020 23:21:49	0	CT	0	0	0	[Sep 9]:57 backdated deceased cases have been ...	2020-10-08
18	Punjab	120868	107200	3741	9927	08/10/2020 20:37:54	0	PB	0	1615	29	NaN	2020-10-08
19	Jharkhand	89702	79176	767	9759	07/10/2020 22:33:14	0	JH	0	0	0	NaN	2020-10-08
20	Jammu and Kashmir	81793	69020	1291	11482	08/10/2020 21:14:12	0	JK	696	1336	9	NaN	2020-10-08
21	Uttarakhand	52959	43631	688	8367	07/10/2020 21:48:59	273	UT	0	0	0	NaN	2020-10-08
22	Goa	37102	31902	484	4716	08/10/2020 21:14:14	0	GA	432	458	7	NaN	2020-10-08
23	Puducherry	30539	25256	556	4727	08/10/2020 21:14:16	0	PY	378	326	5	NaN	2020-10-08
24	Tripura	27756	23043	301	4389	08/10/2020 11:38:56	23	TR	214	389	3	[Aug 4]: Tripura bulletin for the previous day...	2020-10-08
25	Himachal Pradesh	16565	13316	226	2996	07/10/2020 22:33:17	27	HP	0	0	0	NaN	2020-10-08
26	Chandigarh	12922	11344	186	1392	08/10/2020 21:14:18	0	CH	102	154	4	NaN	2020-10-08
27	Manipur	12489	9604	80	2805	07/10/2020 19:40:19	0	MN	0	0	0	NaN	2020-10-08
28	Arunachal Pradesh	11267	8396	21	2850	08/10/2020 00:47:05	0	AR	0	0	0	[July 25]: All numbers corresponding to Papum ...	2020-10-08
29	Meghalaya	7165	4694	60	2411	07/10/2020 21:49:06	0	ML	0	0	0	NaN	2020-10-08
30	Nagaland	6715	5450	12	1194	07/10/2020 19:40:22	59	NL	0	0	0	NaN	2020-10-08
31	Ladakh	4802	3511	63	1228	08/10/2020 01:48:06	0	LA	0	0	0	[Sep 08] : Testing details are not available i...	2020-10-08
32	Andaman and Nicobar Islands	3935	3696	54	185	07/10/2020 23:21:51	0	AN	0	0	0	NaN	2020-10-08
33	Dadra and Nagar Haveli and Daman and Diu	3118	2979	2	109	07/10/2020 20:13:04	28	DN	0	0	0	NaN	2020-10-08
34	Sikkim	3234	2534	51	568	07/10/2020 23:21:53	81	SK	0	0	0	NaN	2020-10-08
35	Mizoram	2150	1919	0	231	08/10/2020 10:41:00	0	MZ	2	24	0	NaN	2020-10-08

# latitude and longitude information
# ==================================

# latitude of the states
lat = {'Delhi':28.7041, 'Haryana':29.0588, 'Kerala':10.8505, 'Rajasthan':27.0238,
       'Telengana':18.1124, 'Uttar Pradesh':26.8467, 'Ladakh':34.2996, 'Tamil Nadu':11.1271,
       'Jammu and Kashmir':33.7782, 'Punjab':31.1471, 'Karnataka':15.3173, 'Maharashtra':19.7515,
       'Andhra Pradesh':15.9129, 'Odisha':20.9517, 'Uttarakhand':30.0668, 'West Bengal':22.9868, 
       'Puducherry': 11.9416, 'Chandigarh': 30.7333, 'Chhattisgarh':21.2787, 'Gujarat': 22.2587, 
       'Himachal Pradesh': 31.1048, 'Madhya Pradesh': 22.9734, 'Bihar': 25.0961, 'Manipur':24.6637, 
       'Mizoram':23.1645, 'Goa': 15.2993, 'Andaman and Nicobar Islands': 11.7401, 'Assam' : 26.2006, 
       'Jharkhand': 23.6102, 'Arunachal Pradesh': 28.2180, 'Tripura': 23.9408, 'Nagaland': 26.1584, 
       'Meghalaya' : 25.4670, 'Dadar Nagar Haveli' : 20.1809, 'Sikkim': 27.5330}

# longitude of the states
long = {'Delhi':77.1025, 'Haryana':76.0856, 'Kerala':76.2711, 'Rajasthan':74.2179,
        'Telengana':79.0193, 'Uttar Pradesh':80.9462, 'Ladakh':78.2932, 'Tamil Nadu':78.6569,
        'Jammu and Kashmir':76.5762, 'Punjab':75.3412, 'Karnataka':75.7139, 'Maharashtra':75.7139,
        'Andhra Pradesh':79.7400, 'Odisha':85.0985, 'Uttarakhand':79.0193, 'West Bengal':87.8550, 
        'Puducherry': 79.8083, 'Chandigarh': 76.7794, 'Chhattisgarh':81.8661, 'Gujarat': 71.1924, 
        'Himachal Pradesh': 77.1734, 'Madhya Pradesh': 78.6569, 'Bihar': 85.3131, 'Manipur':93.9063, 
        'Mizoram':92.9376, 'Goa': 74.1240, 'Andaman and Nicobar Islands': 92.6586, 'Assam' : 92.9376, 
        'Jharkhand': 85.2799, 'Arunachal Pradesh': 94.7278, 'Tripura': 91.9882, 'Nagaland': 94.5624,
        'Meghalaya' : 91.3662, 'Dadar Nagar Haveli' : 73.0169, 'Sikkim': 88.5122}

# add latitude column based on 'Name of State / UT' column
df_India['Latitude'] = df_India['State'].map(lat)

# add longitude column based on 'Name of State / UT' column
df_India['Longitude'] = df_India['State'].map(long)

df_India.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	State	Confirmed	Recovered	Deaths	Active	Last_Updated_Time	Migrated_Other	State_code	Delta_Confirmed	Delta_Recovered	Delta_Deaths	State_Notes	Date	Latitude	Longitude
0	Total	6877073	5871898	106037	898090	08/10/2020 21:24:52	1048	TT	44085	47436	483	NaN	2020-10-08	NaN	NaN
1	Maharashtra	1480489	1196441	39072	244527	07/10/2020 22:32:57	449	MH	0	0	0	[Sep 9] :239 cases have been removed from the ...	2020-10-08	19.7515	75.7139
2	Andhra Pradesh	734427	678828	6086	49513	07/10/2020 17:50:55	0	AP	0	0	0	NaN	2020-10-08	15.9129	79.7400
3	Karnataka	679356	552519	9675	117143	08/10/2020 21:13:54	19	KA	10704	9613	101	NaN	2020-10-08	15.3173	75.7139
4	Tamil Nadu	640943	586454	10052	44437	08/10/2020 21:13:56	0	TN	5088	5718	68	[July 22]: 444 backdated deceased entries adde...	2020-10-08	11.1271	78.6569

# rename columns
    
df_India = df_India.rename(columns={'Delta_Recovered' :'Cured/Discharged', 
                                      'Total Confirmed cases *': 'Confirmed', 
                                      'Total Confirmed cases ': 'Confirmed', 
                                      'Total Confirmed cases* ': 'Confirmed'})
df_India = df_India.rename(columns={'Cured/Discharged':'Delta_Cured'})
df_India = df_India.rename(columns={'State':'State/UnionTerritory'})
df_India = df_India.rename(columns={'State':'State/UnionTerritory'})

df_India = df_India.rename(columns=lambda x: re.sub('Total Confirmed cases \(Including .* foreign Nationals\) ',
                                                      'Total Confirmed cases',x))
df_India = df_India.rename(columns={'Deaths ( more than 70% cases due to comorbidities )':'Deaths', 
                                      'Deaths**':'Deaths'})

# unique state names
df_India['State/UnionTerritory'].unique()

array(['Total', 'Maharashtra', 'Andhra Pradesh', 'Karnataka',
       'Tamil Nadu', 'Uttar Pradesh', 'Delhi', 'West Bengal', 'Odisha',
       'Kerala', 'Telangana', 'Bihar', 'Assam', 'Gujarat', 'Rajasthan',
       'Madhya Pradesh', 'Haryana', 'Chhattisgarh', 'Punjab', 'Jharkhand',
       'Jammu and Kashmir', 'Uttarakhand', 'Goa', 'Puducherry', 'Tripura',
       'Himachal Pradesh', 'Chandigarh', 'Manipur', 'Arunachal Pradesh',
       'Meghalaya', 'Nagaland', 'Ladakh', 'Andaman and Nicobar Islands',
       'Dadra and Nagar Haveli and Daman and Diu', 'Sikkim', 'Mizoram',
       'State Unassigned', 'Lakshadweep'], dtype=object)

# number of missing values 
df_India.isna().sum()

State/UnionTerritory     0
Confirmed                0
Recovered                0
Deaths                   0
Active                   0
Last_Updated_Time        0
Migrated_Other           0
State_code               0
Delta_Confirmed          0
Delta_Cured              0
Delta_Deaths             0
State_Notes             26
Date                     0
Latitude                 5
Longitude                5
dtype: int64

# number of unique values 
df_India.nunique()

State/UnionTerritory    38
Confirmed               37
Recovered               37
Deaths                  36
Active                  37
Last_Updated_Time       38
Migrated_Other          13
State_code              38
Delta_Confirmed         21
Delta_Cured             21
Delta_Deaths            19
State_Notes             12
Date                     1
Latitude                33
Longitude               30
dtype: int64

# fix datatype
df_India['Date'] = pd.to_datetime(df_India['Date'])

# rename state/UT names
df_India['State/UnionTerritory'].replace('Chattisgarh', 'Chhattisgarh', inplace=True)
df_India['State/UnionTerritory'].replace('Pondicherry', 'Puducherry', inplace=True)

Final dataframe

df_India = df_India.drop(['Migrated_Other','State_Notes'], axis=1)
df_India = df_India.drop([0], axis=0)

df_India.head(36)

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	State/UnionTerritory	Confirmed	Recovered	Deaths	Active	Last_Updated_Time	State_code	Delta_Confirmed	Delta_Cured	Delta_Deaths	Date	Latitude	Longitude
1	Maharashtra	1480489	1196441	39072	244527	07/10/2020 22:32:57	MH	0	0	0	2020-10-08	19.7515	75.7139
2	Andhra Pradesh	734427	678828	6086	49513	07/10/2020 17:50:55	AP	0	0	0	2020-10-08	15.9129	79.7400
3	Karnataka	679356	552519	9675	117143	08/10/2020 21:13:54	KA	10704	9613	101	2020-10-08	15.3173	75.7139
4	Tamil Nadu	640943	586454	10052	44437	08/10/2020 21:13:56	TN	5088	5718	68	2020-10-08	11.1271	78.6569
5	Uttar Pradesh	427459	378662	6245	42552	08/10/2020 21:21:49	UP	3133	3690	45	2020-10-08	26.8467	80.9462
6	Delhi	300833	272948	5643	22242	08/10/2020 21:13:59	DL	2726	2643	27	2020-10-08	28.7041	77.1025
7	West Bengal	284030	249737	5439	28854	08/10/2020 21:21:51	WB	3526	2970	63	2020-10-08	22.9868	87.8550
8	Odisha	244142	216984	1027	26131	08/10/2020 21:14:03	OR	3144	3312	16	2020-10-08	20.9517	85.0985
9	Kerala	258851	167256	931	90579	08/10/2020 20:37:52	KL	5445	7003	24	2020-10-08	10.8505	76.2711
10	Telangana	206644	179075	1201	26368	08/10/2020 10:44:51	TG	1896	2067	12	2020-10-08	NaN	NaN
11	Bihar	192671	180357	929	11384	08/10/2020 21:21:53	BR	1244	1006	2	2020-10-08	25.0961	85.3131
12	Assam	191397	157635	794	32965	08/10/2020 21:14:07	AS	1188	0	9	2020-10-08	26.2006	92.9376
13	Gujarat	147950	128023	3541	16386	08/10/2020 21:14:08	GJ	1278	1266	10	2020-10-08	22.2587	71.1924
14	Rajasthan	150467	127526	1590	21351	07/10/2020 19:54:02	RJ	0	0	0	2020-10-08	27.0238	74.2179
15	Madhya Pradesh	142012	122687	2547	16778	08/10/2020 21:24:54	MP	1705	2420	29	2020-10-08	22.9734	78.6569
16	Haryana	138582	126267	1548	10767	08/10/2020 21:21:58	HR	1184	1426	20	2020-10-08	29.0588	76.0856
17	Chhattisgarh	131739	103828	1134	26777	07/10/2020 23:21:49	CT	0	0	0	2020-10-08	21.2787	81.8661
18	Punjab	120868	107200	3741	9927	08/10/2020 20:37:54	PB	0	1615	29	2020-10-08	31.1471	75.3412
19	Jharkhand	89702	79176	767	9759	07/10/2020 22:33:14	JH	0	0	0	2020-10-08	23.6102	85.2799
20	Jammu and Kashmir	81793	69020	1291	11482	08/10/2020 21:14:12	JK	696	1336	9	2020-10-08	33.7782	76.5762
21	Uttarakhand	52959	43631	688	8367	07/10/2020 21:48:59	UT	0	0	0	2020-10-08	30.0668	79.0193
22	Goa	37102	31902	484	4716	08/10/2020 21:14:14	GA	432	458	7	2020-10-08	15.2993	74.1240
23	Puducherry	30539	25256	556	4727	08/10/2020 21:14:16	PY	378	326	5	2020-10-08	11.9416	79.8083
24	Tripura	27756	23043	301	4389	08/10/2020 11:38:56	TR	214	389	3	2020-10-08	23.9408	91.9882
25	Himachal Pradesh	16565	13316	226	2996	07/10/2020 22:33:17	HP	0	0	0	2020-10-08	31.1048	77.1734
26	Chandigarh	12922	11344	186	1392	08/10/2020 21:14:18	CH	102	154	4	2020-10-08	30.7333	76.7794
27	Manipur	12489	9604	80	2805	07/10/2020 19:40:19	MN	0	0	0	2020-10-08	24.6637	93.9063
28	Arunachal Pradesh	11267	8396	21	2850	08/10/2020 00:47:05	AR	0	0	0	2020-10-08	28.2180	94.7278
29	Meghalaya	7165	4694	60	2411	07/10/2020 21:49:06	ML	0	0	0	2020-10-08	25.4670	91.3662
30	Nagaland	6715	5450	12	1194	07/10/2020 19:40:22	NL	0	0	0	2020-10-08	26.1584	94.5624
31	Ladakh	4802	3511	63	1228	08/10/2020 01:48:06	LA	0	0	0	2020-10-08	34.2996	78.2932
32	Andaman and Nicobar Islands	3935	3696	54	185	07/10/2020 23:21:51	AN	0	0	0	2020-10-08	11.7401	92.6586
33	Dadra and Nagar Haveli and Daman and Diu	3118	2979	2	109	07/10/2020 20:13:04	DN	0	0	0	2020-10-08	NaN	NaN
34	Sikkim	3234	2534	51	568	07/10/2020 23:21:53	SK	0	0	0	2020-10-08	27.5330	88.5122
35	Mizoram	2150	1919	0	231	08/10/2020 10:41:00	MZ	2	24	0	2020-10-08	23.1645	92.9376
36	State Unassigned	0	0	0	0	19/07/2020 09:40:01	UN	0	0	0	2020-10-08	NaN	NaN

# complete data info
df_India.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 37 entries, 1 to 37
Data columns (total 13 columns):
 #   Column                Non-Null Count  Dtype         
---  ------                --------------  -----         
 0   State/UnionTerritory  37 non-null     object        
 1   Confirmed             37 non-null     int64         
 2   Recovered             37 non-null     int64         
 3   Deaths                37 non-null     int64         
 4   Active                37 non-null     int64         
 5   Last_Updated_Time     37 non-null     object        
 6   State_code            37 non-null     object        
 7   Delta_Confirmed       37 non-null     int64         
 8   Delta_Cured           37 non-null     int64         
 9   Delta_Deaths          37 non-null     int64         
 10  Date                  37 non-null     datetime64[ns]
 11  Latitude              33 non-null     float64       
 12  Longitude             33 non-null     float64       
dtypes: datetime64[ns](1), float64(2), int64(7), object(3)
memory usage: 4.0+ KB

Save as .csv file

# saving data
# ===========

# file names as year-month-day.csv format
file_name = now.strftime("%Y_%m_%d")+' - COVID-19_India_preprocessed.csv'

# location for saving the file
file_loc = '/content/'

# save file as a scv file
df_India.to_csv(file_loc + file_name, index=False)

1.2 Analysing COVID19 Cases in India

from datetime import date



total_cases = df_India['Confirmed'].sum()
print('Total number of confirmed COVID 2019 cases across India till date ',date.today(),':', total_cases)

Total number of confirmed COVID 2019 cases across India till date  2020-10-08 : 6877073

#Learn how to highlight your dataframe
df_temp = df_India.drop(['Latitude', 'Longitude', 'Date'], axis = 1) #Removing Date, Latitude and Longitude and other extra columns
df_temp.style.background_gradient(cmap='Reds')

today = now.strftime("%Y_%m_%d")
total_cured = df_India['Delta_Cured'].sum()
recovered = df_India['Recovered'].sum()
print("Total people who were recovered as of "+today+" are: ", recovered)
total_cases = df_India['Confirmed'].sum()
print("Total people who were detected COVID+ve as of "+today+" are: ", total_cases)
total_death = df_India['Deaths'].sum()
print("Total people who died due to COVID19 as of "+today+" are: ",total_death)
total_active = total_cases-recovered-total_death
print("Total active COVID19 cases as of "+today+" are: ",total_active)

Total people who were recovered as of 2020_10_08 are:  5871898
Total people who were detected COVID+ve as of 2020_10_08 are:  6877073
Total people who died due to COVID19 as of 2020_10_08 are:  106037
Total active COVID19 cases as of 2020_10_08 are:  899138

#Total Active  is the Total cases - (Number of death + Cured)
df_India['Total Active'] = df_India['Confirmed'] - (df_India['Deaths'] + df_India['Recovered'])
total_active = df_India['Total Active'].sum()
print('Total number of active COVID 19 cases across India:', total_active)
Tot_Cases = df_India.groupby('State/UnionTerritory')['Total Active'].sum().sort_values(ascending=False).to_frame()
Tot_Cases.style.background_gradient(cmap='Reds')

Total number of active COVID 19 cases across India: 899138

state_cases = df_India.groupby('State/UnionTerritory')['Confirmed','Deaths','Delta_Cured'].max().reset_index()

#state_cases = state_cases.astype({'Deaths': 'int'})
state_cases['Active'] = state_cases['Confirmed'] - (state_cases['Deaths']+state_cases['Delta_Cured'])
state_cases["Death Rate (per 100)"] = np.round(100*state_cases["Deaths"]/state_cases["Confirmed"],2)
state_cases["Cure Rate (per 100)"] = np.round(100*state_cases["Delta_Cured"]/state_cases["Confirmed"],2)
state_cases.sort_values('Confirmed', ascending= False).fillna(0).style.background_gradient(cmap='Blues',subset=["Confirmed"])\
                        .background_gradient(cmap='Blues',subset=["Deaths"])\
                        .background_gradient(cmap='Blues',subset=["Delta_Cured"])\
                        .background_gradient(cmap='Blues',subset=["Active"])\
                        .background_gradient(cmap='Blues',subset=["Death Rate (per 100)"])\
                        .background_gradient(cmap='Blues',subset=["Cure Rate (per 100)"])

Visualization Inference:

Almost +1,611 cases of COVID-19 has been reported today (23rd May) taking total cases to 123202.
The cases have been confirmed across 32 states and union territories.
Out of 123202 cases, 51784 people have been cured, discharged or migrated.
Maharashtra, Tamilnaidu, Gujrat and Delhi are worsely affected states with maximum number of confirmed cases
Till 23rd of May 3720 people have died in India

Finding more detail COVID Insights in India

# age_details = pd.read_csv('/content/AgeGroupDetails.csv')
india_covid_19 = pd.read_csv('./covid_19_india.csv')
hospital_beds = pd.read_csv('./HospitalBedsIndia.csv')
individual_details = pd.read_csv('./IndividualDetails.csv')
ICMR_details = pd.read_csv('./ICMRTestingDetails.csv')
ICMR_labs = pd.read_csv('./ICMRTestingLabs.csv')
state_testing = pd.read_csv('./StatewiseTestingDetails.csv')
population = pd.read_csv('./population_india_census2011.csv')

india_covid_19['Date'] = pd.to_datetime(india_covid_19['Date'],dayfirst = True)
state_testing['Date'] = pd.to_datetime(state_testing['Date'])
ICMR_details['DateTime'] = pd.to_datetime(ICMR_details['DateTime'],dayfirst = True)
ICMR_details = ICMR_details.dropna(subset=['TotalSamplesTested', 'TotalPositiveCases'])

confirmed_df = pd.read_csv('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv')
deaths_df = pd.read_csv('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_deaths_global.csv')
recovered_df = pd.read_csv('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_recovered_global.csv')
latest_data = pd.read_csv('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-29-2020.csv')

We could see that the age group <40 is the most affected which is against the trend which says elderly people are more at risk of being affected. Only 17% of people >60 are affected.

dates = list(confirmed_df.columns[4:])
dates = list(pd.to_datetime(dates))
dates_india = dates[8:]
# print(dates_india)

tes = list(pd.to_datetime(dates))
dates_india = dates[8:]
df1 = confirmed_df.groupby('Country/Region').sum().reset_index()
df2 = deaths_df.groupby('Country/Region').sum().reset_index()
df3 = recovered_df.groupby('Country/Region').sum().reset_index()

k = df1[df1['Country/Region']=='India'].loc[:,'1/30/20':]
india_confirmed = k.values.tolist()[0] 

k = df2[df2['Country/Region']=='India'].loc[:,'1/30/20':]
india_deaths = k.values.tolist()[0] 

k = df3[df3['Country/Region']=='India'].loc[:,'1/30/20':]
india_recovered = k.values.tolist()[0] 

plt.figure(figsize= (15,10))
plt.xticks(rotation = 90 ,fontsize = 11)
plt.yticks(fontsize = 10)
plt.xlabel("Dates",fontsize = 20)
plt.ylabel('Total cases',fontsize = 20)
plt.title("Total Confirmed, Active, Death in India" , fontsize = 20)

ax1 = plt.plot_date(y= india_confirmed,x= dates_india,label = 'Confirmed',linestyle ='-',color = 'b')
ax2 = plt.plot_date(y= india_recovered,x= dates_india,label = 'Recovered',linestyle ='-',color = 'g')
ax3 = plt.plot_date(y= india_deaths,x= dates_india,label = 'Death',linestyle ='-',color = 'r')
plt.legend()

<matplotlib.legend.Legend at 0x25ced931dc0>

Total Samples Tested

import matplotlib.dates as mdates
ICMR_details['Percent_positive'] = round((ICMR_details['TotalPositiveCases']/ICMR_details['TotalSamplesTested'])*100,1)

fig, ax1 = plt.subplots(figsize= (15,5))
ax1.xaxis.set_major_formatter(mdates.DateFormatter('%d-%b'))
ax1.set_ylabel('Positive Cases (% of Total Samples Tested)')
ax1.bar(ICMR_details['DateTime'] , ICMR_details['Percent_positive'], color="red",label = 'Percentage of Positive Cases')
ax1.text(ICMR_details['DateTime'][0],4, 'Total Samples Tested as of Apr 23rd = 541789', style='italic',fontsize= 10,
        bbox={'facecolor': 'white' ,'alpha': 0.5, 'pad': 5})

ax2 = ax1.twinx()  
ax2.xaxis.set_major_formatter(mdates.DateFormatter('%d-%b'))
ax2.set_ylabel('Num Samples Tested')
ax2.fill_between(ICMR_details['DateTime'],ICMR_details['TotalSamplesTested'],color = 'black',alpha = 0.5,label = 'Samples Tested');

plt.legend(loc="upper left")
plt.title('Total Samples Tested')
plt.show()

Testing LIVE Status

import json
# get response from the web page
response = requests.get('https://api.covid19india.org/state_test_data.json')

# get contents from the response
content = response.content

# parse the json file
parsed = json.loads(content)

# keys
parsed.keys()

dict_keys(['states_tested_data'])

# save data in a dataframe
tested = pd.DataFrame(parsed['states_tested_data'])

# first few rows
tested.tail()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	antigentests	numicubeds	numisolationbeds	numventilators	...	totaln95masks	totalpeoplecurrentlyinquarantine	totalpeoplereleasedfromquarantine	totalppe	totaltested	updatedon	_djhdx
6026	1221370	1243	12715	790	...	2383040	2426	107757	2409262	3397988	04/10/2020	NaN
6027	1245401	1243	12715	790	...	2395040	2425	107761	2415262	3438128	05/10/2020	NaN
6028	1267956	1243	12715	790	...	2405040	2413	107779	2420262	3480510	06/10/2020	NaN
6029	1288884	1243	12715	790	...	2417040	2410	107787	2425262	3523161	07/10/2020	NaN
6030		1243	12715	790	...	2428040	2415	107792	2430262	3565602	08/10/2020	NaN

5 rows × 32 columns

# fix datatype
tested['updatedon'] = pd.to_datetime(tested['updatedon'])

# save file as a scv file
tested.to_csv('updated_tests_latest_state_level.csv', index=False)

state_test_cases = tested.groupby(['updatedon','state'])['totaltested','populationncp2019projection','testpositivityrate',	'testsperpositivecase',	'testsperthousand','totalpeoplecurrentlyinquarantine'].max().reset_index()

state_test_cases[:-50]

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	updatedon	state	totaltested	populationncp2019projection	testpositivityrate	testsperpositivecase	testsperthousand	totalpeoplecurrentlyinquarantine
0	2020-01-04	Delhi	2621	19814000	0.00%		0.13
1	2020-01-04	Kerala	7965	35125000	3.33%	30	0.23	622
2	2020-01-04	West Bengal	659	96906000	5.61%	18	0.01
3	2020-01-05	Andaman and Nicobar Islands	3754	397000	0.88%	114	9.46	643
4	2020-01-05	Andhra Pradesh	102460	52221000	1.43%	70	1.96
...	...	...	...	...	...	...	...	...
5975	2020-12-08	Jammu and Kashmir	750847	13203000	3.52%	28	56.87	42494
5976	2020-12-08	Jharkhand	402072	37403000	5.04%	20	10.75
5977	2020-12-08	Karnataka	1826317	65798000	0.00%		27.76	289355
5978	2020-12-08	Kerala	1056360	35125000	3.61%	28	30.07	12426
5979	2020-12-08	Ladakh	23034	293000	7.86%	13	78.61	363

5980 rows × 8 columns

state_test_cases = tested.groupby('state')['totaltested','populationncp2019projection','testpositivityrate',	'testsperpositivecase',	'testsperthousand','totalpeoplecurrentlyinquarantine'].max()
state_test_cases['testpositivityrate'] = state_test_cases['testpositivityrate'].str.replace('%', '')

state_test_cases = state_test_cases.apply(pd.to_numeric)

state_test_cases.nunique()

totaltested                         35
populationncp2019projection         34
testpositivityrate                  34
testsperpositivecase                19
testsperthousand                    25
totalpeoplecurrentlyinquarantine    28
dtype: int64

state_test_cases.sort_values('totaltested', ascending= False).style.background_gradient(cmap='Blues',subset=["totaltested"])\
                        .background_gradient(cmap='Blues',subset=["populationncp2019projection"])\
                        .background_gradient(cmap='Blues',subset=["testpositivityrate"])\
                        .background_gradient(cmap='Blues',subset=["testsperpositivecase"])\
                        .background_gradient(cmap='Blues',subset=["testsperthousand"])\
                        .background_gradient(cmap='Blues',subset=["totalpeoplecurrentlyinquarantine"])

Day-by-Day Confirmed Cases in Top 15 States in India

all_state = list(df_India['State/UnionTerritory'].unique())

latest = india_covid_19[india_covid_19['Date'] > '24-03-20']
state_cases = latest.groupby('State/UnionTerritory')['Confirmed','Deaths','Cured'].max().reset_index()
latest['Active'] = latest['Confirmed'] - (latest['Deaths']- latest['Cured'])
state_cases = state_cases.sort_values('Confirmed', ascending= False).fillna(0)
states =list(state_cases['State/UnionTerritory'][0:15])

states_confirmed = {}
states_deaths = {}
states_recovered = {}
states_dates = {}

for state in states:
    df = latest[latest['State/UnionTerritory'] == state].reset_index()
    k = []
    l = []
    m = []
    n = []
    for i in range(1,len(df)):
        k.append(df['Confirmed'][i]-df['Confirmed'][i-1])
        l.append(df['Deaths'][i]-df['Deaths'][i-1])
        m.append(df['Cured'][i]-df['Cured'][i-1])
        n.append(df['Active'][i]-df['Active'][i-1])
    states_confirmed[state] = k
    states_deaths[state] = l
    states_recovered[state] = m
#     states_active[state] = n
    date = list(df['Date'])
    states_dates[state] = date[1:]
    
fig = plt.figure(figsize= (25,17))
plt.suptitle('Day-by-Day Confirmed Cases in Top 15 States in India',fontsize = 20,y=1.0)
k=0
for i in range(1,15):
    ax = fig.add_subplot(5,3,i)
    ax.xaxis.set_major_formatter(mdates.DateFormatter('%d-%b'))
    ax.bar(states_dates[states[k]],states_confirmed[states[k]],label = 'Day wise Confirmed Cases ') 
    plt.title(states[k],fontsize = 20)
    handles, labels = ax.get_legend_handles_labels()
    fig.legend(handles, labels, loc='upper left')
    k=k+1
plt.tight_layout(pad=5.0)

Growth Rate in top 15 States in India

def calc_growthRate(values):
    k = []
    for i in range(1,len(values)):
        summ = 0
        for j in range(i):
            summ = summ + values[j]
        rate = (values[i]/summ)*100
        k.append(int(rate))
    return k

fig = plt.figure(figsize= (25,17))
plt.suptitle('Growth Rate in Top 15 States',fontsize = 20,y=1.0)
k=0
for i in range(1,15):
    ax = fig.add_subplot(5,3,i)
    ax.xaxis.set_major_formatter(mdates.DateFormatter('%d-%b'))
    #ax.bar(states_dates[states[k]],states_confirmed[states[k]],label = 'Day wise Confirmed Cases ') 
    growth_rate = calc_growthRate(states_confirmed[states[k]])
    ax.plot_date(states_dates[states[k]][21:],growth_rate[20:],color = '#9370db',label = 'Growth Rate',linewidth =3,linestyle='-')  
    plt.title(states[k],fontsize = 20)
    handles, labels = ax.get_legend_handles_labels()
    fig.legend(handles, labels, loc='upper left')
    k=k+1
plt.tight_layout(pad=3.0)

Though being highly populated the relative confimred cases of India is low compared to other countries. This could be because of two reasons:

67 days lockdown imposed by prime minister Narendra Modi in several stages (Source : Health Ministry)
Low testing rate (Source: news18)

Exploring different types of hospital beds available in India during lockdown

cols_object = list(hospital_beds.columns[2:8])

for cols in cols_object:
    hospital_beds[cols] = hospital_beds[cols].astype(int,errors = 'ignore')

hospital_beds = hospital_beds.drop('Sno',axis=1)

hospital_beds.head(36)

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	State/UT	NumPrimaryHealthCenters_HMIS	NumCommunityHealthCenters_HMIS	NumSubDistrictHospitals_HMIS	NumDistrictHospitals_HMIS	TotalPublicHealthFacilities_HMIS	NumPublicBeds_HMIS	NumRuralHospitals_NHP18	NumRuralBeds_NHP18	NumUrbanHospitals_NHP18	NumUrbanBeds_NHP18
0	Andaman & Nicobar Islands	27	4	NaN	3	34	1246	27	575	3	500
1	Andhra Pradesh	1417	198	31.0	20	1666	60799	193	6480	65	16658
2	Arunachal Pradesh	122	62	NaN	15	199	2320	208	2136	10	268
3	Assam	1007	166	14.0	33	1220	19115	1176	10944	50	6198
4	Bihar	2007	63	33.0	43	2146	17796	930	6083	103	5936
5	Chandigarh	40	2	1.0	4	47	3756	0	0	4	778
6	Chhattisgarh	813	166	12.0	32	1023	14354	169	5070	45	4342
7	Dadra & Nagar Haveli	9	2	1.0	1	13	568	10	273	1	316
8	Daman & Diu	4	2	NaN	2	8	298	5	240	0	0
9	Delhi	534	25	9.0	47	615	20572	0	0	109	24383
10	Goa	31	4	2.0	3	40	2666	17	1405	25	1608
11	Gujarat	1770	385	44.0	37	2236	41129	364	11715	122	20565
12	Haryana	500	131	24.0	28	683	13841	609	6690	59	4550
13	Himachal Pradesh	516	79	61.0	15	671	8706	705	5665	96	6734
14	Jammu & Kashmir	702	87	NaN	29	818	11342	56	7234	76	4417
15	Jharkhand	343	179	13.0	23	558	7404	519	5842	36	4942
16	Karnataka	2547	207	147.0	42	2943	56333	2471	21072	374	49093
17	Kerala	933	229	82.0	53	1297	39511	981	16865	299	21139
18	Lakshadweep	4	3	2.0	1	10	250	9	300	0	0
19	Madhya Pradesh	1420	324	72.0	51	1867	38140	334	10020	117	18819
20	Maharashtra	2638	430	101.0	70	3239	68998	273	12398	438	39048
21	Manipur	87	17	1.0	9	114	2562	23	730	7	697
22	Meghalaya	138	29	NaN	13	180	4585	143	1970	14	2487
23	Mizoram	65	10	3.0	9	87	2312	56	604	34	1393
24	Nagaland	134	21	NaN	11	166	1944	21	630	15	1250
25	Odisha	1360	377	27.0	35	1799	16497	1655	6339	149	12180
26	Puducherry	40	4	5.0	4	53	4462	3	96	11	3473
27	Punjab	521	146	47.0	28	742	13527	510	5805	172	12128
28	Rajasthan	2463	579	64.0	33	3139	51844	602	21088	150	10760
29	Sikkim	25	2	1.0	4	32	1145	24	260	9	1300
30	Tamil Nadu	1854	385	310.0	32	2581	72616	692	40179	525	37353
31	Telangana	788	82	47.0	15	932	17358	802	7668	61	13315
32	Tripura	114	22	12.0	9	157	4895	99	1140	56	3277
33	Uttar Pradesh	3277	671	NaN	174	4122	58310	4442	39104	193	37156
34	Uttarakhand	275	69	19.0	20	383	6660	410	3284	50	5228
35	West Bengal	1374	406	70.0	55	1905	51163	1272	19684	294	58882

Exploring top 10 States in each health facilities

# top_10_primary = hospital_beds.nlargest(10,'NumPrimaryHealthCenters_HMIS')
top_10_community = hospital_beds.nlargest(10,'NumCommunityHealthCenters_HMIS')
top_10_district_hospitals = hospital_beds.nlargest(10,'NumDistrictHospitals_HMIS')
top_10_public_facility = hospital_beds.nlargest(10,'TotalPublicHealthFacilities_HMIS')
top_10_public_beds = hospital_beds.nlargest(10,'NumPublicBeds_HMIS')

plt.subplot(222)
plt.title('Community Health Centers')
plt.barh(top_10_community['State/UT'],top_10_community['NumCommunityHealthCenters_HMIS'],color = '#9370db');

plt.subplot(224)
plt.title('Total Public Health Facilities')
plt.barh(top_10_community['State/UT'],top_10_public_facility['TotalPublicHealthFacilities_HMIS'],color='#9370db');

plt.subplot(223)
plt.title('District Hospitals')
plt.barh(top_10_community['State/UT'],top_10_district_hospitals['NumDistrictHospitals_HMIS'],color = '#87479d');

Exploring Urban and Rural Healthcare Facility

top_rural_hos = hospital_beds.nlargest(10,'NumRuralHospitals_NHP18')
top_rural_beds = hospital_beds.nlargest(10,'NumRuralBeds_NHP18')
top_urban_hos = hospital_beds.nlargest(10,'NumUrbanHospitals_NHP18')
top_urban_beds = hospital_beds.nlargest(10,'NumUrbanBeds_NHP18')

plt.figure(figsize=(15,10))
plt.suptitle('Urban and Rural Health Facility',fontsize=20)
plt.subplot(221)
plt.title('Rural Hospitals')
plt.barh(top_rural_hos['State/UT'],top_rural_hos['NumRuralHospitals_NHP18'],color = '#87479d');

plt.subplot(222)
plt.title('Urban Hospitals')
plt.barh(top_urban_hos['State/UT'],top_urban_hos['NumUrbanHospitals_NHP18'],color = '#9370db');

plt.subplot(223)
plt.title('Rural Beds')
plt.barh(top_rural_beds['State/UT'],top_rural_beds['NumRuralBeds_NHP18'],color = '#87479d');

plt.subplot(224)
plt.title('Urban Beds')
plt.barh(top_urban_beds['State/UT'],top_urban_beds['NumUrbanBeds_NHP18'],color = '#9370db');

Exploring Statewise Testing Insights

state_test = pd.pivot_table(state_testing, values=['TotalSamples','Negative','Positive'], index='State', aggfunc='max')
state_names = list(state_test.index)
state_test['State'] = state_names

plt.figure(figsize=(25,20))
sns.set_color_codes("pastel")
sns.barplot(x="TotalSamples", y= state_names, data=state_test,label="Total Samples", color = '#7370db')
sns.barplot(x='Negative', y=state_names, data=state_test,label='Negative', color= '#af8887')
sns.barplot(x='Positive', y=state_names, data=state_test,label='Positive', color='#6ff79d')
plt.title('Testing statewise insight',fontsize = 20)
plt.legend(ncol=2, loc="lower right", frameon=True);

Number of ICMR Testing Centres in each state

values = list(ICMR_labs['state'].value_counts())
names = list(ICMR_labs['state'].value_counts().index)

plt.figure(figsize=(15,10))
sns.set_color_codes("pastel")
plt.title('ICMR Testing Centers in each State', fontsize = 20)
sns.barplot(x= values, y= names,color = '#ff2345');

Let's Start with the predictions

train = pd.read_csv('/content/train.csv')
test = pd.read_csv('/content/test.csv')
train['Date'] = pd.to_datetime(train['Date'])
test['Date'] = pd.to_datetime(test['Date'])

Prophet

Prophet is open source software released by Facebook’s Core Data Science team. It is available for download on CRAN and PyPI.

We use Prophet, a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. It works best with time series that have strong seasonal effects and several seasons of historical data. Prophet is robust to missing data and shifts in the trend, and typically handles outliers well.

Why Prophet?

Accurate and fast: Prophet is used in many applications across Facebook for producing reliable forecasts for planning and goal setting. Facebook finds it to perform better than any other approach in the majority of cases. It fit models in Stan so that you get forecasts in just a few seconds.
Fully automatic: Get a reasonable forecast on messy data with no manual effort. Prophet is robust to outliers, missing data, and dramatic changes in your time series.
Tunable forecasts: The Prophet procedure includes many possibilities for users to tweak and adjust forecasts. You can use human-interpretable parameters to improve your forecast by adding your domain knowledge
Available in R or Python: Facebook has implemented the Prophet procedure in R and Python. Both of them share the same underlying Stan code for fitting. You can use whatever language you’re comfortable with to get forecasts.

References

!pip install Prophet

Collecting Prophet
  Downloading prophet-0.1.1.post1.tar.gz (90 kB)
Requirement already satisfied: pytz>=2014.9 in c:\users\raghav\anaconda3\lib\site-packages (from Prophet) (2020.1)
Requirement already satisfied: pandas>=0.15.1 in c:\users\raghav\anaconda3\lib\site-packages (from Prophet) (1.0.4)
Requirement already satisfied: six>=1.8.0 in c:\users\raghav\anaconda3\lib\site-packages (from Prophet) (1.15.0)
Requirement already satisfied: python-dateutil>=2.6.1 in c:\users\raghav\anaconda3\lib\site-packages (from pandas>=0.15.1->Prophet) (2.8.1)
Requirement already satisfied: numpy>=1.13.3 in c:\users\raghav\anaconda3\lib\site-packages (from pandas>=0.15.1->Prophet) (1.19.1)
Building wheels for collected packages: Prophet
  Building wheel for Prophet (setup.py): started
  Building wheel for Prophet (setup.py): finished with status 'done'
  Created wheel for Prophet: filename=prophet-0.1.1.post1-py3-none-any.whl size=13254 sha256=ba625745471e8c2acffc86c1c928c450f8274af8233d264d6f65a0cd31fff95f
  Stored in directory: c:\users\raghav\appdata\local\pip\cache\wheels\98\36\19\702df5440d2cf01c8221d08fb26bfe66e872100e7bfd75bb8f
Successfully built Prophet
Installing collected packages: Prophet
Successfully installed Prophet-0.1.1.post1

# !pip install pystan
# !pip install fbprophet

!conda install -c conda-forge fbprophet

from fbprophet import Prophet
from fbprophet.plot import plot_plotly, add_changepoints_to_plot

k = df1[df1['Country/Region']=='India'].loc[:,'1/22/20':]
india_confirmed = k.values.tolist()[0] 
data = pd.DataFrame(columns = ['ds','y'])
data['ds'] = dates
data['y'] = india_confirmed

The input to Prophet is always a dataframe with two columns: ds and y. The ds (datestamp) column should be of a format expected by Pandas, ideally YYYY-MM-DD for a date or YYYY-MM-DD HH:MM:SS for a timestamp. The y column must be numeric, and represents the measurement we wish to forecast.

4.1 Forecasting Confirmed NCOVID-19 Cases Worldwide with Prophet (Base model)

Generating a week ahead forecast of confirmed cases of NCOVID-19 using Prophet, with 95% prediction interval by creating a base model with no tweaking of seasonality-related parameters and additional regressors.

prop = Prophet(interval_width=0.95)
prop.fit(data)
future = prop.make_future_dataframe(periods=15)
future.tail(15)

INFO:fbprophet:Disabling yearly seasonality. Run prophet with yearly_seasonality=True to override this.
INFO:fbprophet:Disabling daily seasonality. Run prophet with daily_seasonality=True to override this.

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	ds
253	2020-10-01
254	2020-10-02
255	2020-10-03
256	2020-10-04
257	2020-10-05
258	2020-10-06
259	2020-10-07
260	2020-10-08
261	2020-10-09
262	2020-10-10
263	2020-10-11
264	2020-10-12
265	2020-10-13
266	2020-10-14
267	2020-10-15

The predict method will assign each row in future a predicted value which it names yhat. If you pass in historical dates, it will provide an in-sample fit. The forecast object here is a new dataframe that includes a column yhat with the forecast, as well as columns for components and uncertainty intervals.

#predicting the future with date, and upper and lower limit of y value
forecast = prop.predict(future)
forecast[['ds', 'yhat', 'yhat_lower', 'yhat_upper']].tail()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	ds	yhat	yhat_lower	yhat_upper
263	2020-10-11	7.100590e+06	7.006306e+06	7.195882e+06
264	2020-10-12	7.178642e+06	7.074952e+06	7.289030e+06
265	2020-10-13	7.257725e+06	7.147775e+06	7.366396e+06
266	2020-10-14	7.336894e+06	7.217428e+06	7.455318e+06
267	2020-10-15	7.417946e+06	7.301104e+06	7.551448e+06

You can plot the forecast by calling the Prophet.plot method and passing in your forecast dataframe.

confirmed_forecast_plot = prop.plot(forecast)

confirmed_forecast_plot =prop.plot_components(forecast)

ARIMA Model

from statsmodels.tsa.arima_model import ARIMA

from datetime import timedelta 

arima = ARIMA(data['y'], order=(5, 1, 0))
arima = arima.fit(trend='c', full_output=True, disp=True)
forecast = arima.forecast(steps= 30)
pred = list(forecast[0])

start_date = data['ds'].max()
prediction_dates = []
for i in range(30):
    date = start_date + timedelta(days=1)
    prediction_dates.append(date)
    start_date = date
plt.figure(figsize= (15,10))
plt.xlabel("Dates",fontsize = 20)
plt.ylabel('Total cases',fontsize = 20)
plt.title("Predicted Values for the next 15 Days" , fontsize = 20)

plt.plot_date(y= pred,x= prediction_dates,linestyle ='dashed',color = '#ff9999',label = 'Predicted');
plt.plot_date(y=data['y'],x=data['ds'],linestyle = '-',color = 'blue',label = 'Actual');
plt.legend();

1.4 Visualising the spread geographically

# df_India.head()
df = df_India.dropna(subset = ["Latitude","Longitude"], inplace=True)

# Learn how to use folium to create a zoomable map
map = folium.Map(location=[20, 70], zoom_start=4,tiles='Stamenterrain')

for lat, lon, value, name in zip(df_India['Latitude'], df_India['Longitude'], df_India['Confirmed'], df_India['State/UnionTerritory']):
    folium.CircleMarker([lat, lon], radius=value*0.002, popup = ('<strong>State</strong>: ' + str(name).capitalize() + '<br>''<strong>Total Cases</strong>: ' + str(value) + '<br>'),color='red',fill_color='red',fill_opacity=0.09 ).add_to(map)
map

#Part 3: Exploring World wide data

3.1 Visualizing: Worldwide NCOVID-19 cases

world_confirmed = confirmed_df[confirmed_df.columns[-1:]].sum()
world_recovered = recovered_df[recovered_df.columns[-1:]].sum()
world_deaths = deaths_df[deaths_df.columns[-1:]].sum()
world_active = world_confirmed - (world_recovered - world_deaths)

labels = ['Active','Recovered','Deceased']
sizes = [world_active,world_recovered,world_deaths]
color= ['blue','green','red']
explode = []

for i in labels:
    explode.append(0.05)
    
plt.figure(figsize= (15,10))
plt.pie(sizes, labels=labels, autopct='%1.1f%%', startangle=9, explode = explode,colors = color)
centre_circle = plt.Circle((0,0),0.70,fc='white')

fig = plt.gcf()
fig.gca().add_artist(centre_circle)
plt.title('World COVID-19 Cases',fontsize = 20)
plt.axis('equal')  
plt.tight_layout()

dates

[Timestamp('2020-01-22 00:00:00'),
 Timestamp('2020-01-23 00:00:00'),
 Timestamp('2020-01-24 00:00:00'),
 Timestamp('2020-01-25 00:00:00'),
 Timestamp('2020-01-26 00:00:00'),
 Timestamp('2020-01-27 00:00:00'),
 Timestamp('2020-01-28 00:00:00'),
 Timestamp('2020-01-29 00:00:00'),
 Timestamp('2020-01-30 00:00:00'),
 Timestamp('2020-01-31 00:00:00'),
 Timestamp('2020-02-01 00:00:00'),
 Timestamp('2020-02-02 00:00:00'),
 Timestamp('2020-02-03 00:00:00'),
 Timestamp('2020-02-04 00:00:00'),
 Timestamp('2020-02-05 00:00:00'),
 Timestamp('2020-02-06 00:00:00'),
 Timestamp('2020-02-07 00:00:00'),
 Timestamp('2020-02-08 00:00:00'),
 Timestamp('2020-02-09 00:00:00'),
 Timestamp('2020-02-10 00:00:00'),
 Timestamp('2020-02-11 00:00:00'),
 Timestamp('2020-02-12 00:00:00'),
 Timestamp('2020-02-13 00:00:00'),
 Timestamp('2020-02-14 00:00:00'),
 Timestamp('2020-02-15 00:00:00'),
 Timestamp('2020-02-16 00:00:00'),
 Timestamp('2020-02-17 00:00:00'),
 Timestamp('2020-02-18 00:00:00'),
 Timestamp('2020-02-19 00:00:00'),
 Timestamp('2020-02-20 00:00:00'),
 Timestamp('2020-02-21 00:00:00'),
 Timestamp('2020-02-22 00:00:00'),
 Timestamp('2020-02-23 00:00:00'),
 Timestamp('2020-02-24 00:00:00'),
 Timestamp('2020-02-25 00:00:00'),
 Timestamp('2020-02-26 00:00:00'),
 Timestamp('2020-02-27 00:00:00'),
 Timestamp('2020-02-28 00:00:00'),
 Timestamp('2020-02-29 00:00:00'),
 Timestamp('2020-03-01 00:00:00'),
 Timestamp('2020-03-02 00:00:00'),
 Timestamp('2020-03-03 00:00:00'),
 Timestamp('2020-03-04 00:00:00'),
 Timestamp('2020-03-05 00:00:00'),
 Timestamp('2020-03-06 00:00:00'),
 Timestamp('2020-03-07 00:00:00'),
 Timestamp('2020-03-08 00:00:00'),
 Timestamp('2020-03-09 00:00:00'),
 Timestamp('2020-03-10 00:00:00'),
 Timestamp('2020-03-11 00:00:00'),
 Timestamp('2020-03-12 00:00:00'),
 Timestamp('2020-03-13 00:00:00'),
 Timestamp('2020-03-14 00:00:00'),
 Timestamp('2020-03-15 00:00:00'),
 Timestamp('2020-03-16 00:00:00'),
 Timestamp('2020-03-17 00:00:00'),
 Timestamp('2020-03-18 00:00:00'),
 Timestamp('2020-03-19 00:00:00'),
 Timestamp('2020-03-20 00:00:00'),
 Timestamp('2020-03-21 00:00:00'),
 Timestamp('2020-03-22 00:00:00'),
 Timestamp('2020-03-23 00:00:00'),
 Timestamp('2020-03-24 00:00:00'),
 Timestamp('2020-03-25 00:00:00'),
 Timestamp('2020-03-26 00:00:00'),
 Timestamp('2020-03-27 00:00:00'),
 Timestamp('2020-03-28 00:00:00'),
 Timestamp('2020-03-29 00:00:00'),
 Timestamp('2020-03-30 00:00:00'),
 Timestamp('2020-03-31 00:00:00'),
 Timestamp('2020-04-01 00:00:00'),
 Timestamp('2020-04-02 00:00:00'),
 Timestamp('2020-04-03 00:00:00'),
 Timestamp('2020-04-04 00:00:00'),
 Timestamp('2020-04-05 00:00:00'),
 Timestamp('2020-04-06 00:00:00'),
 Timestamp('2020-04-07 00:00:00'),
 Timestamp('2020-04-08 00:00:00'),
 Timestamp('2020-04-09 00:00:00'),
 Timestamp('2020-04-10 00:00:00'),
 Timestamp('2020-04-11 00:00:00'),
 Timestamp('2020-04-12 00:00:00'),
 Timestamp('2020-04-13 00:00:00'),
 Timestamp('2020-04-14 00:00:00'),
 Timestamp('2020-04-15 00:00:00'),
 Timestamp('2020-04-16 00:00:00'),
 Timestamp('2020-04-17 00:00:00'),
 Timestamp('2020-04-18 00:00:00'),
 Timestamp('2020-04-19 00:00:00'),
 Timestamp('2020-04-20 00:00:00'),
 Timestamp('2020-04-21 00:00:00'),
 Timestamp('2020-04-22 00:00:00'),
 Timestamp('2020-04-23 00:00:00'),
 Timestamp('2020-04-24 00:00:00'),
 Timestamp('2020-04-25 00:00:00'),
 Timestamp('2020-04-26 00:00:00'),
 Timestamp('2020-04-27 00:00:00'),
 Timestamp('2020-04-28 00:00:00'),
 Timestamp('2020-04-29 00:00:00'),
 Timestamp('2020-04-30 00:00:00'),
 Timestamp('2020-05-01 00:00:00'),
 Timestamp('2020-05-02 00:00:00'),
 Timestamp('2020-05-03 00:00:00'),
 Timestamp('2020-05-04 00:00:00'),
 Timestamp('2020-05-05 00:00:00'),
 Timestamp('2020-05-06 00:00:00'),
 Timestamp('2020-05-07 00:00:00'),
 Timestamp('2020-05-08 00:00:00'),
 Timestamp('2020-05-09 00:00:00'),
 Timestamp('2020-05-10 00:00:00'),
 Timestamp('2020-05-11 00:00:00'),
 Timestamp('2020-05-12 00:00:00'),
 Timestamp('2020-05-13 00:00:00'),
 Timestamp('2020-05-14 00:00:00'),
 Timestamp('2020-05-15 00:00:00'),
 Timestamp('2020-05-16 00:00:00'),
 Timestamp('2020-05-17 00:00:00'),
 Timestamp('2020-05-18 00:00:00'),
 Timestamp('2020-05-19 00:00:00'),
 Timestamp('2020-05-20 00:00:00'),
 Timestamp('2020-05-21 00:00:00'),
 Timestamp('2020-05-22 00:00:00'),
 Timestamp('2020-05-23 00:00:00'),
 Timestamp('2020-05-24 00:00:00'),
 Timestamp('2020-05-25 00:00:00'),
 Timestamp('2020-05-26 00:00:00'),
 Timestamp('2020-05-27 00:00:00'),
 Timestamp('2020-05-28 00:00:00'),
 Timestamp('2020-05-29 00:00:00'),
 Timestamp('2020-05-30 00:00:00'),
 Timestamp('2020-05-31 00:00:00'),
 Timestamp('2020-06-01 00:00:00'),
 Timestamp('2020-06-02 00:00:00'),
 Timestamp('2020-06-03 00:00:00'),
 Timestamp('2020-06-04 00:00:00'),
 Timestamp('2020-06-05 00:00:00'),
 Timestamp('2020-06-06 00:00:00'),
 Timestamp('2020-06-07 00:00:00'),
 Timestamp('2020-06-08 00:00:00'),
 Timestamp('2020-06-09 00:00:00'),
 Timestamp('2020-06-10 00:00:00'),
 Timestamp('2020-06-11 00:00:00'),
 Timestamp('2020-06-12 00:00:00'),
 Timestamp('2020-06-13 00:00:00'),
 Timestamp('2020-06-14 00:00:00'),
 Timestamp('2020-06-15 00:00:00'),
 Timestamp('2020-06-16 00:00:00'),
 Timestamp('2020-06-17 00:00:00'),
 Timestamp('2020-06-18 00:00:00'),
 Timestamp('2020-06-19 00:00:00'),
 Timestamp('2020-06-20 00:00:00'),
 Timestamp('2020-06-21 00:00:00'),
 Timestamp('2020-06-22 00:00:00'),
 Timestamp('2020-06-23 00:00:00'),
 Timestamp('2020-06-24 00:00:00'),
 Timestamp('2020-06-25 00:00:00'),
 Timestamp('2020-06-26 00:00:00'),
 Timestamp('2020-06-27 00:00:00'),
 Timestamp('2020-06-28 00:00:00'),
 Timestamp('2020-06-29 00:00:00'),
 Timestamp('2020-06-30 00:00:00'),
 Timestamp('2020-07-01 00:00:00'),
 Timestamp('2020-07-02 00:00:00'),
 Timestamp('2020-07-03 00:00:00'),
 Timestamp('2020-07-04 00:00:00'),
 Timestamp('2020-07-05 00:00:00'),
 Timestamp('2020-07-06 00:00:00'),
 Timestamp('2020-07-07 00:00:00'),
 Timestamp('2020-07-08 00:00:00'),
 Timestamp('2020-07-09 00:00:00'),
 Timestamp('2020-07-10 00:00:00'),
 Timestamp('2020-07-11 00:00:00'),
 Timestamp('2020-07-12 00:00:00'),
 Timestamp('2020-07-13 00:00:00'),
 Timestamp('2020-07-14 00:00:00'),
 Timestamp('2020-07-15 00:00:00'),
 Timestamp('2020-07-16 00:00:00'),
 Timestamp('2020-07-17 00:00:00'),
 Timestamp('2020-07-18 00:00:00'),
 Timestamp('2020-07-19 00:00:00'),
 Timestamp('2020-07-20 00:00:00'),
 Timestamp('2020-07-21 00:00:00'),
 Timestamp('2020-07-22 00:00:00'),
 Timestamp('2020-07-23 00:00:00'),
 Timestamp('2020-07-24 00:00:00'),
 Timestamp('2020-07-25 00:00:00'),
 Timestamp('2020-07-26 00:00:00'),
 Timestamp('2020-07-27 00:00:00'),
 Timestamp('2020-07-28 00:00:00'),
 Timestamp('2020-07-29 00:00:00'),
 Timestamp('2020-07-30 00:00:00'),
 Timestamp('2020-07-31 00:00:00'),
 Timestamp('2020-08-01 00:00:00'),
 Timestamp('2020-08-02 00:00:00'),
 Timestamp('2020-08-03 00:00:00'),
 Timestamp('2020-08-04 00:00:00'),
 Timestamp('2020-08-05 00:00:00'),
 Timestamp('2020-08-06 00:00:00'),
 Timestamp('2020-08-07 00:00:00'),
 Timestamp('2020-08-08 00:00:00'),
 Timestamp('2020-08-09 00:00:00'),
 Timestamp('2020-08-10 00:00:00'),
 Timestamp('2020-08-11 00:00:00'),
 Timestamp('2020-08-12 00:00:00'),
 Timestamp('2020-08-13 00:00:00'),
 Timestamp('2020-08-14 00:00:00'),
 Timestamp('2020-08-15 00:00:00'),
 Timestamp('2020-08-16 00:00:00'),
 Timestamp('2020-08-17 00:00:00'),
 Timestamp('2020-08-18 00:00:00'),
 Timestamp('2020-08-19 00:00:00'),
 Timestamp('2020-08-20 00:00:00'),
 Timestamp('2020-08-21 00:00:00'),
 Timestamp('2020-08-22 00:00:00'),
 Timestamp('2020-08-23 00:00:00'),
 Timestamp('2020-08-24 00:00:00'),
 Timestamp('2020-08-25 00:00:00'),
 Timestamp('2020-08-26 00:00:00'),
 Timestamp('2020-08-27 00:00:00'),
 Timestamp('2020-08-28 00:00:00'),
 Timestamp('2020-08-29 00:00:00'),
 Timestamp('2020-08-30 00:00:00'),
 Timestamp('2020-08-31 00:00:00'),
 Timestamp('2020-09-01 00:00:00'),
 Timestamp('2020-09-02 00:00:00'),
 Timestamp('2020-09-03 00:00:00'),
 Timestamp('2020-09-04 00:00:00'),
 Timestamp('2020-09-05 00:00:00'),
 Timestamp('2020-09-06 00:00:00'),
 Timestamp('2020-09-07 00:00:00'),
 Timestamp('2020-09-08 00:00:00'),
 Timestamp('2020-09-09 00:00:00'),
 Timestamp('2020-09-10 00:00:00'),
 Timestamp('2020-09-11 00:00:00'),
 Timestamp('2020-09-12 00:00:00'),
 Timestamp('2020-09-13 00:00:00'),
 Timestamp('2020-09-14 00:00:00'),
 Timestamp('2020-09-15 00:00:00'),
 Timestamp('2020-09-16 00:00:00'),
 Timestamp('2020-09-17 00:00:00'),
 Timestamp('2020-09-18 00:00:00'),
 Timestamp('2020-09-19 00:00:00'),
 Timestamp('2020-09-20 00:00:00'),
 Timestamp('2020-09-21 00:00:00'),
 Timestamp('2020-09-22 00:00:00'),
 Timestamp('2020-09-23 00:00:00'),
 Timestamp('2020-09-24 00:00:00'),
 Timestamp('2020-09-25 00:00:00'),
 Timestamp('2020-09-26 00:00:00'),
 Timestamp('2020-09-27 00:00:00'),
 Timestamp('2020-09-28 00:00:00'),
 Timestamp('2020-09-29 00:00:00'),
 Timestamp('2020-09-30 00:00:00')]

hotspots = ['China','Germany','Iran','Italy','Spain','US','Korea, South','France','Turkey','United Kingdom','India']
dates = list(confirmed_df.columns[4:])
dates = list(pd.to_datetime(dates))
dates_india = dates[8:]

df1 = confirmed_df.groupby('Country/Region').sum().reset_index()
df2 = deaths_df.groupby('Country/Region').sum().reset_index()
df3 = recovered_df.groupby('Country/Region').sum().reset_index()

global_confirmed = {}
global_deaths = {}
global_recovered = {}
global_active= {}

for country in hotspots:
    k =df1[df1['Country/Region'] == country].loc[:,'1/30/20':]
    global_confirmed[country] = k.values.tolist()[0]

    k =df2[df2['Country/Region'] == country].loc[:,'1/30/20':]
    global_deaths[country] = k.values.tolist()[0]

    k =df3[df3['Country/Region'] == country].loc[:,'1/30/20':]
    global_recovered[country] = k.values.tolist()[0]
    
# for country in hotspots:
#     k = list(map(int.__sub__, global_confirmed[country], global_deaths[country]))
#     global_active[country] = list(map(int.__sub__, k, global_recovered[country]))
    
fig = plt.figure(figsize= (15,25))
plt.suptitle('Active, Recovered, Deaths in Hotspot Countries and India as of '+ today,fontsize = 20,y=1.0)
#plt.legend()
k=0
for i in range(1,12):
    ax = fig.add_subplot(6,2,i)
    ax.xaxis.set_major_formatter(mdates.DateFormatter('%d-%b'))
    # ax.bar(dates_india,global_active[hotspots[k]],color = 'green',alpha = 0.6,label = 'Active');
    ax.bar(dates_india,global_confirmed[hotspots[k]],color='blue',label = 'Confirmed');
    ax.bar(dates_india,global_recovered[hotspots[k]],color='grey',label = 'Recovered');
    ax.bar(dates_india,global_deaths[hotspots[k]],color='red',label = 'Death');   
    plt.title(hotspots[k])
    handles, labels = ax.get_legend_handles_labels()
    fig.legend(handles, labels, loc='upper left')
    k=k+1

plt.tight_layout(pad=3.0)

countries = ['China','Germany','Iran','Italy','Spain','US','Korea, South','France','United Kingdom','India']

global_confirmed = []
global_recovered = []
global_deaths = []

for country in countries:
    k =df1[df1['Country/Region'] == country].loc[:,'1/30/20':]
    global_confirmed.append(k.values.tolist()[0]) 

    k =df2[df2['Country/Region'] == country].loc[:,'1/30/20':]
    global_deaths.append(k.values.tolist()[0]) 

    k =df3[df3['Country/Region'] == country].loc[:,'1/30/20':]
    global_deaths.append(k.values.tolist()[0])

plt.figure(figsize= (15,10))
plt.xticks(rotation = 90 ,fontsize = 11)
plt.yticks(fontsize = 10)
plt.xlabel("Dates",fontsize = 20)
plt.ylabel('Total cases',fontsize = 20)
plt.title("Comparison with other Countries" , fontsize = 20)

for i in range(len(countries)):
    plt.plot_date(y= global_confirmed[i],x= dates_india,label = countries[i])
plt.legend();

COVID-19 Symptoms

SOURCE: www.cdc.gov/coronavirus

Data Source:

The latest data can also be extracted from the available APIs and reading the json. Below are the API list that have been provided by crowd sourced. Extract and use these data to find meaningful insights.

Extracting data from Hirokuapp

api = pd.read_json('https://corona-virus-stats.herokuapp.com/api/v1/cases/countries-search')

json_data = api['data']['rows']

from pandas.io.json import json_normalize

data = json_normalize(json_data)
data

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	country	country_abbreviation	total_cases	new_cases	total_deaths	new_deaths	total_recovered	active_cases	serious_critical	cases_per_mill_pop	flag
0	World		4,525,103	3,077	303,351	269	1,703,742	2,518,010	45,560	581.0	https://upload.wikimedia.org/wikipedia/commons...
1	USA	US	1,457,593	0	86,912	0	318,027	1,052,654	16,240	4,404.0	https://www.worldometers.info/img/flags/us-fla...
2	Spain	ES	272,646	0	27,321	0	186,480	58,845	1,376	5,831.0	https://www.worldometers.info/img/flags/sp-fla...
3	Russia	RU	252,245	0	2,305	0	53,530	196,410	2,300	1,728.0	https://www.worldometers.info/img/flags/rs-fla...
4	UK	GB	233,151	0	33,614	0	N/A	199,193	1,559	3,434.0	https://www.worldometers.info/img/flags/uk-fla...
5	Italy	IT	223,096	0	31,368	0	115,288	76,440	855	3,690.0	https://www.worldometers.info/img/flags/it-fla...
6	Brazil	BR	203,165	247	13,999	6	79,479	109,687	8,318	956.0	https://www.worldometers.info/img/flags/br-fla...
7	France	FR	178,870	0	27,425	0	59,605	91,840	2,299	2,740.0	https://www.worldometers.info/img/flags/fr-fla...
8	Germany	DE	174,975	0	7,928	0	150,300	16,747	1,329	2,088.0	https://www.worldometers.info/img/flags/gm-fla...
9	Turkey	TR	144,749	0	4,007	0	104,030	36,712	963	1,716.0	https://www.worldometers.info/img/flags/tu-fla...

Collecting Data for Statewise Insights

# to parse json contents
import json
# to parse csv files
import csv
import requests

# get response from the web page for LIVE data
response = requests.get('https://api.covid19india.org/raw_data3.json')
# get contents from the response
content = response.content
# parse the json file
parsed = json.loads(content)
# keys
parsed.keys()

dict_keys(['raw_data'])

# save to df
df = pd.DataFrame(parsed['raw_data'])

# shape of the dataframe
print(df.shape)

# # list of columns
print(df.columns)

# # first few rows
df.head()

(10020, 20)
Index(['agebracket', 'contractedfromwhichpatientsuspected', 'currentstatus',
       'dateannounced', 'detectedcity', 'detecteddistrict', 'detectedstate',
       'entryid', 'gender', 'nationality', 'notes', 'numcases',
       'patientnumber', 'source1', 'source2', 'source3', 'statecode',
       'statepatientnumber', 'statuschangedate', 'typeoftransmission'],
      dtype='object')

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	agebracket	currentstatus	dateannounced	detectedcity	detecteddistrict	detectedstate	entryid	gender	notes	numcases	patientnumber	source1	statecode
0		Hospitalized	27/04/2020			West Bengal	1		Details awaited	38	27892	mohfw.gov.in	WB
1		Hospitalized	27/04/2020		Bhilwara	Rajasthan	2		Details awaited	2	27893	https://twitter.com/ANI/status/125461859651442...	RJ
2		Hospitalized	27/04/2020		Jaipur	Rajasthan	3		Details awaited	9	27894	https://twitter.com/ANI/status/125461859651442...	RJ
3	28	Deceased	27/04/2020	Surajpol	Jaipur	Rajasthan	4	M	Details awaited	1	27895	https://twitter.com/ANI/status/125461859651442...	RJ
4		Hospitalized	27/04/2020		Jaisalmer	Rajasthan	5		Details awaited	1	27896	https://twitter.com/ANI/status/125461859651442...	RJ

# creating patient id column from patient number
# ===============================================

df['p_id'] = df['patientnumber'].apply(lambda x : 'P'+str(x))
df.columns

Index(['agebracket', 'contractedfromwhichpatientsuspected', 'currentstatus',
       'dateannounced', 'detectedcity', 'detecteddistrict', 'detectedstate',
       'entryid', 'gender', 'nationality', 'notes', 'numcases',
       'patientnumber', 'source1', 'source2', 'source3', 'statecode',
       'statepatientnumber', 'statuschangedate', 'typeoftransmission', 'p_id'],
      dtype='object')

Rearrange and rename columns

# order of columns
cols = ['patientnumber', 'p_id', 'statepatientnumber', 
        'dateannounced', 'agebracket', 'gender', 
        'detectedcity', 'detecteddistrict', 'detectedstate', 'statecode', 'nationality',
        'typeoftransmission', 'contractedfromwhichpatientsuspected',
        'statuschangedate', 'currentstatus', 'source1', 'source2', 'source3', 'notes']

# rearrange columns
df = df[cols]

# rename columns
df.columns = ['patient_number', 'p_id', 'state_patient_number', 
              'date_announced', 'age_bracket', 'gender', 
              'detected_city', 'detected_district', 'detected_state', 'state_code', 'nationality',
              'type_of_transmission', 'contracted_from_which_patient_suspected',
              'status_change_date', 'current_status', 'source1', 'source2', 'source3', 'notes']

# dataframe shape
df.shape

(10020, 19)

# first 3 rows of the dataframe
df.head(3)

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	patient_number	p_id	date_announced	detected_district	detected_state	state_code	current_status	source1	notes
0	27892	P27892	27/04/2020		West Bengal	WB	Hospitalized	mohfw.gov.in	Details awaited
1	27893	P27893	27/04/2020	Bhilwara	Rajasthan	RJ	Hospitalized	https://twitter.com/ANI/status/125461859651442...	Details awaited
2	27894	P27894	27/04/2020	Jaipur	Rajasthan	RJ	Hospitalized	https://twitter.com/ANI/status/125461859651442...	Details awaited

Missing values

# no. of empty values in each column
# ==================================

print(df.shape, '\n')

for i in df.columns:
    print(i, '\t', df[df[i]==''].shape[0])

(10020, 19) 

patient_number 	 12
p_id 	 0
state_patient_number 	 4882
date_announced 	 0
age_bracket 	 4837
gender 	 5366
detected_city 	 9599
detected_district 	 86
detected_state 	 5
state_code 	 5
nationality 	 10020
type_of_transmission 	 10020
contracted_from_which_patient_suspected 	 9779
status_change_date 	 10020
current_status 	 0
source1 	 65
source2 	 9940
source3 	 9989
notes 	 8089

# no. of non-empty values in each column
# ===================================

print(df.shape, '\n')

for i in df.columns:
    print(i, '\t', df[df[i]!=''].shape[0])

(10020, 19) 

patient_number 	 10008
p_id 	 10020
state_patient_number 	 5138
date_announced 	 10020
age_bracket 	 5183
gender 	 4654
detected_city 	 421
detected_district 	 9934
detected_state 	 10015
state_code 	 10015
nationality 	 0
type_of_transmission 	 0
contracted_from_which_patient_suspected 	 241
status_change_date 	 0
current_status 	 10020
source1 	 9955
source2 	 80
source3 	 31
notes 	 1931

# replacing empty strings with np.nan
# ==================================-

print(df.shape)

df = df.replace(r'', np.nan, regex=True)
df.isna().sum()

(10020, 19)





patient_number                                12
p_id                                           0
state_patient_number                        4882
date_announced                                 0
age_bracket                                 4837
gender                                      5366
detected_city                               9599
detected_district                             86
detected_state                                 5
state_code                                     5
nationality                                10020
type_of_transmission                       10020
contracted_from_which_patient_suspected     9779
status_change_date                         10020
current_status                                 0
source1                                       65
source2                                     9940
source3                                     9989
notes                                       8089
dtype: int64

# droping empty rows (row with just row number but without patient entry
# ======================================================================

print(df.shape)

# df.dropna(subset=['detected_state'], inplace=True)

print(df.shape)
df.isna().sum()

(10020, 19)
(10020, 19)





patient_number                                12
p_id                                           0
state_patient_number                        4882
date_announced                                 0
age_bracket                                 4837
gender                                      5366
detected_city                               9599
detected_district                             86
detected_state                                 5
state_code                                     5
nationality                                10020
type_of_transmission                       10020
contracted_from_which_patient_suspected     9779
status_change_date                         10020
current_status                                 0
source1                                       65
source2                                     9940
source3                                     9989
notes                                       8089
dtype: int64

Save data

# save to csv`
df.to_csv('patients_data.csv', index=False)

Collecting Some more Statewise Data

# get response from the web page
response = requests.get('https://api.covid19india.org/state_test_data.json')

# get contents from the response
content = response.content

# parse the json file
parsed = json.loads(content)

# keys
parsed.keys()

dict_keys(['states_tested_data'])

# get response from the web page
response = requests.get('https://api.covid19india.org/state_test_data.json')

# get contents from the response
content = response.content

# parse the json file
parsed = json.loads(content)

# keys
parsed.keys()

dict_keys(['states_tested_data'])

# save data in a dataframe
th = pd.DataFrame(parsed['states_tested_data'])

# first few rows
th

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	antigentests	coronaenquirycalls	cumulativepeopleinquarantine	negative	numcallsstatehelpline	numicubeds	numisolationbeds	numventilators	othertests	peopleinicu	...	testsperpositivecase	testsperthousand	totaln95masks	totalpeoplecurrentlyinquarantine	totalpeoplereleasedfromquarantine	totalppe	totaltested	unconfirmed	updatedon	_djhdx
0				1210			50				...	117	3.53					1403	181	17/04/2020	NaN
1					280		50				...	99	6.75		614	347		2679	246	24/04/2020	NaN
2					298		50				...	86	7.17		724	420		2848	106	27/04/2020	NaN
3					340		50				...	114	9.46		643	556		3754	199	01/05/2020	NaN
4					471		98				...	202	16.82		16	1196		6677	136	16/05/2020	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
5803	1057947					1243	12675	790			...			2298040	2444	107697	2370262	3098657		27/09/2020	NaN
5804	1082706					1243	12675	790			...			2308040	2447	107712	2375262	3139938		28/09/2020	NaN
5805	1107750					1243	12675	790			...			2323040	2439	107706	2381262	3183697		29/09/2020	NaN
5806	1131535					1243	12715	790			...			2335040	2442	107721	2387262	3227462		30/09/2020	NaN
5807	1155254					1243	12715	790			...			2350040	2439	107726	2393262	3271316		01/10/2020	NaN

5808 rows × 32 columns

th.columns

Index(['antigentests', 'coronaenquirycalls', 'cumulativepeopleinquarantine',
       'negative', 'numcallsstatehelpline', 'numicubeds', 'numisolationbeds',
       'numventilators', 'othertests', 'peopleinicu', 'peopleonventilators',
       'populationncp2019projection', 'positive', 'rtpcrtests', 'source1',
       'source2', 'source3', 'state', 'tagpeopleinquarantine',
       'tagtotaltested', 'testpositivityrate', 'testspermillion',
       'testsperpositivecase', 'testsperthousand', 'totaln95masks',
       'totalpeoplecurrentlyinquarantine', 'totalpeoplereleasedfromquarantine',
       'totalppe', 'totaltested', 'unconfirmed', 'updatedon', '_djhdx'],
      dtype='object')

# save to csv`
th.to_csv('tests_latest_state_level.csv', index=False)

# to get web contents
import requests
# to parse json contents
import json
# to parse csv files
import csv

Zones

# get response from the web page
response = requests.get('https://api.covid19india.org/zones.json')

# get contents from the response
content = response.content

# parse the json file
parsed = json.loads(content)

# keys
parsed.keys()

dict_keys(['zones'])

zo = pd.DataFrame(parsed['zones'])
zo.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	district	districtcode	lastupdated	source	state	statecode	zone
0	Nicobars	AN_Nicobars	01/05/2020	https://www.facebook.com/airnewsalerts/photos/...	Andaman and Nicobar Islands	AN	Green
1	North and Middle Andaman	AN_North and Middle Andaman	01/05/2020	https://www.facebook.com/airnewsalerts/photos/...	Andaman and Nicobar Islands	AN	Green
2	South Andaman	AN_South Andaman	01/05/2020	https://www.facebook.com/airnewsalerts/photos/...	Andaman and Nicobar Islands	AN	Red
3	Anantapur	AP_Anantapur	01/05/2020	https://www.facebook.com/airnewsalerts/photos/...	Andhra Pradesh	AP	Orange
4	Chittoor	AP_Chittoor	01/05/2020	https://www.facebook.com/airnewsalerts/photos/...	Andhra Pradesh	AP	Red

# save to csv`
zo.to_csv('zones.csv', index=False)

National level daily

response = requests.get('https://api.covid19india.org/data.json')
content = response.content
parsed = json.loads(content)
parsed.keys()

dict_keys(['cases_time_series', 'statewise', 'tested'])

national = pd.DataFrame(parsed['cases_time_series'])
national.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	dailyconfirmed	date	totalconfirmed
0	1	30 January	1
1	0	31 January	1
2	0	01 February	1
3	1	02 February	2
4	1	03 February	3

national.columns

Index(['dailyconfirmed', 'dailydeceased', 'dailyrecovered', 'date',
       'totalconfirmed', 'totaldeceased', 'totalrecovered'],
      dtype='object')

national = national[['date', 'totalconfirmed', 'totaldeceased', 'totalrecovered', 
                     'dailyconfirmed', 'dailydeceased', 'dailyrecovered']]
national.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	date	totalconfirmed	dailyconfirmed
0	30 January	1	1
1	31 January	1	0
2	01 February	1	0
3	02 February	2	1
4	03 February	3	1

# save to csv`
national.to_csv('nation_level_daily.csv', index=False)

National level latest

state_level = pd.DataFrame(parsed['statewise'])
state_level.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	active	confirmed	deaths	deltaconfirmed	deltadeaths	deltarecovered	lastupdatedtime	migratedother	recovered	state	statecode	statenotes
0	945551	6397896	99833	5936	29	2941	02/10/2020 12:20:45	918	5351594	Total	TT
1	259006	1400922	37056	0	0	0	01/10/2020 23:39:43	434	1104426	Maharashtra	MH	[Sep 9] :239 cases have been removed from the ...
2	57858	700235	5869	0	0	0	01/10/2020 22:07:48	0	636508	Andhra Pradesh	AP
3	46369	603290	9586	0	0	0	01/10/2020 18:46:44	0	547335	Tamil Nadu	TN	[July 22]: 444 backdated deceased entries adde...
4	110412	611837	8994	0	0	0	01/10/2020 22:07:49	19	492412	Karnataka	KA

state_level.columns

Index(['active', 'confirmed', 'deaths', 'deltaconfirmed', 'deltadeaths',
       'deltarecovered', 'lastupdatedtime', 'migratedother', 'recovered',
       'state', 'statecode', 'statenotes'],
      dtype='object')

state_level = state_level[['state', 'statecode', 'lastupdatedtime',  
                           'confirmed', 'active', 'deaths', 'recovered',
                           'deltaconfirmed', 'deltadeaths', 'deltarecovered', 'statenotes']]
state_level.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	state	statecode	lastupdatedtime	confirmed	active	deaths	recovered	deltaconfirmed	deltadeaths	deltarecovered	statenotes
0	Total	TT	02/10/2020 12:20:45	6397896	945551	99833	5351594	5936	29	2941
1	Maharashtra	MH	01/10/2020 23:39:43	1400922	259006	37056	1104426	0	0	0	[Sep 9] :239 cases have been removed from the ...
2	Andhra Pradesh	AP	01/10/2020 22:07:48	700235	57858	5869	636508	0	0	0
3	Tamil Nadu	TN	01/10/2020 18:46:44	603290	46369	9586	547335	0	0	0	[July 22]: 444 backdated deceased entries adde...
4	Karnataka	KA	01/10/2020 22:07:49	611837	110412	8994	492412	0	0	0

# save to csv`
state_level.to_csv('state_level_latest.csv', index=False)

Name		Name	Last commit message	Last commit date
Latest commit History 9 Commits
media		media
ICMR_data.zip		ICMR_data.zip
India_&_World_COVID_19.ipynb		India_&_World_COVID_19.ipynb
LICENSE		LICENSE
README.md		README.md
earth-coronavirus--covid-19-planet-earth-infected-by-coronavirus-shut.jpg		earth-coronavirus--covid-19-planet-earth-infected-by-coronavirus-shut.jpg

License

rawatraghav/INDIA-and-COVID-19

Folders and files

Latest commit

History

Repository files navigation

COVID-19 - Pandemic in India!

About COVID-19

Problem Statement:

Importing the required libraries

Part 1: Analysing the present condition in India

Recent COVID-19 updates in India

How is AI-ML useful in fighting the COVID-19 pandemic?

1.1 Scraping the datasets from the official Govt. website

Daily Cases

State Wise

Data Cleaning

Final dataframe

Save as .csv file

1.2 Analysing COVID19 Cases in India

Finding more detail COVID Insights in India

Total Samples Tested

Testing LIVE Status

Day-by-Day Confirmed Cases in Top 15 States in India

Growth Rate in top 15 States in India

Exploring different types of hospital beds available in India during lockdown

Exploring top 10 States in each health facilities

Exploring Urban and Rural Healthcare Facility

Exploring Statewise Testing Insights

Number of ICMR Testing Centres in each state

Let's Start with the predictions

Prophet

Why Prophet?

References

4.1 Forecasting Confirmed NCOVID-19 Cases Worldwide with Prophet (Base model)

ARIMA Model

1.4 Visualising the spread geographically

3.1 Visualizing: Worldwide NCOVID-19 cases

COVID-19 Symptoms

Data Source:

Extracting data from Hirokuapp

Collecting Data for Statewise Insights

Rearrange and rename columns

Missing values

Save data

Collecting Some more Statewise Data

Zones

National level daily

National level latest

About

Topics

Resources

License

Stars

Watchers

Forks

Languages