Skip to content
Go to file

Latest commit


Git stats


Failed to load latest commit information.
Latest commit message
Commit time

Pandemic Central

An application of machine learning in forecasting U.S. COVID-19 cases

We utilize socioeconomic, mobility, and epidemiological datasets to forecast COVID-19 cases at the US county/county-equivalent level. This repository contains the code we use to generate this information.

See our latest predictions at our website and check us out on Twitter.

Project Status: Active – The project has reached a stable, usable state and is being actively developed. License


We hope to serve as a valuable resource for understanding trends in the ongoing pandemic and raise awareness about COVID-19 at the community level, something which is desperately needed in our attempts to lower the curve. However, we strongly advise against over-interpreting our predictions. Machine learning models are only as good as the data that trains them. We use the best quality data that is available to us, but we acknowledge that error in our predictions is unavoidable.

Getting Started

Follow these instructions to get the project up and running on your local machine.


These are what you must install before using our project.

  1. NumPy, Pandas and Matplotlib

  2. Scikit-learn


  1. TensorFlow (release ≥ 2.0.0) and TensorFlow_docs

  2. Plotly including: plotly, chart_studio, and Plotly Orca

  3. psutil

Your local machine must also have Python 3 (≥ 3.7) installed beforehand.


To run this project, first clone this repository.

git clone

For a basic usage, use this command

python -d


python --default

This command should download the data from sources, preprocess them, train, and export predictions.

For full list of available commands, use

python --help


Make sure you always clone and pull the latest version from Pandemic Central. Our repository can always be found at



Since this is still in its earliest versions, bugs and incompletions are unavoidable. Please feel free to comment or contact our developers! Your contributions are very valuable to us and this project.

For technical support, please email our developers: (Joseph) or (Duy). Thank you for your patience.


Our latest version is v2.0.0. For version details, see Releases tags.


Our project can not be completed without these great sources. We do not own any data; all input data we use are open-source or permission-granted. More details about how we process this data may be found in and

Here is a list of datasets we have used so far:

  1. Apple Maps Mobility Trends Reports

  2. Google Community Mobility Reports

  3. Facebook Movement Range

  4. Johns Hopkins CSSEGISandData

  5. COVID Tracking Project

  6. MIT Projections

  7. IHME Datasets

  8. Reproduction Rate

  9. CCVI Index

  10. US Census Population Data

  11. USDA FIPS Code List

We also thank Plotly, TensorFlow and Python communities for very detailed and helpful documentations.

Please check out these resources for yourself!


An application of machine learning to forecast COVID-19 cases at the US county/county-equivalent level.





No packages published


You can’t perform that action at this time.