Covid-19 Analysis

  • Tech Stack: Scikit learn, Numpy, Pandas, Python, Google colab
  • Github URL: Project Link

Abstract:

The coronavirus (COVID-19) that was first reported at the end of 2019 has impacted every aspect of life as we know it. This case study focuses on incorporating field of data science with rising cases of covid or any such pandemics. Using few data pre-processing and cleaning techniques, we modelled the system to predict daily and cumulative incidence of COVID-19 cases throughout the world, death to infected ratio and such useful data which helps us in tackling the challenge we are up against. The coronavirus (COVID-19) has affected 181 countries with approximately 1,87,93,542 confirmed cases. Our model helps in understanding the transmission dynamics of the infection in each country which got affected on a daily basis and evaluating the effectiveness of control policies are critical for our further actions. To date, the statistics of COVID19 reported cases show that more than 80% of infected are mild cases of disease, around 14% of infected have severe complications, and about 5% are categorized as critical disease victims. The data obtained from this model can be used implement effective policies that yielded significant changes in the trend of cases like lockdown policy, shutdown of all nonessential companies.

Motivation and Objective:

We apply our method to predicting the number of new COVID-19 cases in India and for a subset of counties within the state to demonstrate the utility of this method at varying scales of prediction. Our method produces reasonably accurate results when the effective reproduction number is distributed similarly in the future as in the past. Large deviations from the predicted results can imply that a change in policy or some other factors have occurred that have dramatically altered the disease transmission over time.