Skip to content

I was unfortunate to contract COVID-19 during the second wave in India. Time-series graphs, denoting the caseload were omnipresent in this period. I found that time series analysis resonated with me since it used mathematical equations to understand and give meaning to perpetual events. Under the guidance of Professor Supratim Biswas, at IIT Bombay

Notifications You must be signed in to change notification settings

absaw/COVID19Analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

COVID19Analysis

COVID 19 Time series analysis and prediction for Rapid Early Warning before next wave

Project Flow

  1. Get data - CSV file - Johns Hopkins University GitHub
  2. Convert it into dataframe
  3. Calculate the number of daily cases column
  4. Apply stationarity tests a. Visual Graph-Rolling Mean, Standard Deviation b. ADF Test
  5. Check for seasonality
  6. Apply transformation to change series into a stationary series
  7. Divide data into train and test
  8. Fit model on train data
  9. Make predictions on test data
  10. Graph the predicted values along with the test values
  11. Calculate Accuracy Parameters a. Mean Absolute Error b. Mean Square Error c. Root Mean Square Error
  12. Plot other graphs a. Error Residual Graphs b. Value Density Plot

About

I was unfortunate to contract COVID-19 during the second wave in India. Time-series graphs, denoting the caseload were omnipresent in this period. I found that time series analysis resonated with me since it used mathematical equations to understand and give meaning to perpetual events. Under the guidance of Professor Supratim Biswas, at IIT Bombay

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published