Giter Club home page Giter Club logo

covid-19-forecasts's Introduction

COVID-19 Prediction for Confirmed Cases

Build Status

COVID-19 prediction on confirmed case (Taiwan)
https://dspim.github.io/COVID-19-Forecasts/

About this project

As the COVID-19 pandemic continues to grow, health authorities need to have a better understanding of future epidemic development in order to execute proper non-medical interventions and optimize the allocation of critical medical resources.

In view of this, we applied statistical methods to predict daily confirmed cases in infected countries.

What are sample use cases

Our project has two main outputs: a country-level prediction model for confirmed cases and a dashboard for demonstrating prediction results.

First, since this statistical model covers all infected countries, health authorities and medical institutions around the world can use these predictions for executing proper non-medical interventions and medical resource planning.

Secondly, epidemic modelers can either replace the included prediction model with their own models or enhance their models with the included one. In both cases, the modellers can use the dashboard for model output and as the user interface.

How did you address this problem

We developed a country-level prediction model for confirmed cases, based on daily epidemic updates from trustworthy data sources.

We also provided a dashboard to display real-time case statistics, model results and prediction performance over time.

We have designed this system for use in all countries.

All source code can be downloaded on Github. (https://dspim.github.io/COVID-19-Forecasts/)

How I bulit it

Implementation

  1. Install required tools
  • Required: R
  • Install R packages in DESCRIPTION
  • Suggested: RStudio IDE
  1. Clone this repo to your system to get the project files
git clone https://github.com/dspim/COVID-19-Forecasts.git
  1. Open the checked out top level folder inside your terminal
cd COVID-19-Forecasts
  1. Run all relevant build scripts at once
Rscript R/01_get_raw_data.R 
Rscript R/02_get_Stage1_data.R 
Rscript R/03_make_pred.R 
Rscript R/04_makeDashboard.R
  1. Open dashboard file (index.html)

Hack the prediction algorithm

  • Create a prediction function like Pred.Chao() in "./R/main.R Line 77-92"
  • Modified calPred() in "./R/main.R Line 55-58"

Who (or what organizations) could potentially benefit from your solution?

We are data scientists, not epidemonist. We have crunched the numbers and produced a data-driven epidemic prediction model.

We hope health authority and medical institutions around the world can use our project for decision support, such as executing proper non-medical interventions and optimizing the allocation of critical medical resources.

What's next for COVID-19 Prediction on Confirmed Case

  • Develop subnational (city) level prediction models.
  • Hopefully, assist local authorities in decision making for epidemic risk management.
  • Encourage data scientists and/or epidemonists around the world to collaborate by using this system to improve their own prediction models.

Credits

License

The MIT License (MIT)

covid-19-forecasts's People

Contributors

readata avatar johnsonhsieh avatar nondayo avatar sophiejiang avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.