Holistic Analysis of Corona Virus using Statastical modelling and Machine Learning
Visualize and Predict spread of CoronaVirus Since the pilot out-break in Wuhan,Huebei COVID-19 has infected almost 50,000+ people in 28 countries. This project aims at visualizing changes happening on a global scale by incorporating rapid mapping of live datasets. A pilot model build upon ARIMA and Exponential Curve fitting helps to predict future outbreaks by analysing the current data pool.

Getting Started
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

Prerequisites

1. Python >=3.5
2. Numpy
3. Pandas
4. Statsmodels
5. Dash
6. Amira
7. SCIPY
8. Seaborn
9. Matplotlib

Installing A step by step series of examples that tell you how to get a development env running

Developing a Flask application

1. Fetch the CSV from this GITHUB repository:https://github.com/Perishleaf/data-visualisation-scripts
   Data can also be imported from the repository (mapping wont be live)
2. Create a Flask Server
   How to set up a flash server:https://www.twilio.com/docs/usage/tutorials/how-to-set-up-your-python-and-flask-development-environment
3. Select the plots you want to plot using the dataset
   Guide: https://www.freecodecamp.org/news/how-to-build-a-web-application-using-flask-and-deploy-it-to-the-cloud-3551c985e492/
4. Render the elements and the visualise the changes
5. You can also use hello.py

TimeSeries Forecasting

These models are used to forecast/predict time-series data. As our data highly depends upon timestamps it's highly advisable to use this

1. It's beautifully explained how to implement any timeseries forecasting model in this link:
   https://machinelearningmastery.com/arima-for-time-series-forecasting-with-python/
2. Note: Make sure to use the dataset to generate the predictive model
   If you need our model drop us a mail at vivek.bhanushali16@siesgst.ac.in
3. We achieved an accuracy of 97.8% with the limited dataset.

The model uses diffrential equations to generalise results, the better the diffrential equation the higher accuracy the model yields

Predicting fatality - Curve fitting using Exponential Equations

Fetches data in real time and processes numerical attributes to forecast potential deaths and infections

1. Import the dataset from the affomentioned github repository
2. Visualise the infected and death rates
3. Refinment of the dataset
4. Visualising new infections/deaths per day
5. Use exponential equation: n(t) = c(t-t0)^p+a0 Where
   n = function of no. of days
   p = exponential factor
   t = time
6. We achieved an accuracy of 95%
7. For Queries drop a mail to: avantilaingam@gmail.com

Computing risk factor

To visualise which country is most vulnerable we computed risk factor using epidemiologic analysis

Refer page: https://www.cdc.gov/csels/dsepd/ss1978/lesson3/section5.html

Risk factor =function([age,health facilities,population,standard of living, travel ration],country)

Version (1.0.0) Includes

1. Visualising changes
2. Predictive analysis
3. Risk Factor association

Authors Apurva Mhatre - Time Series Forecasting.
Avantika Mahalingam - Curve fitting and predictions.
Aaditya Gurav - Flask server implementation.

License This project is opensource.