Forecasting Global Covid-19 with Kaggle Dataset

Using FacebookProphet forecasting tooling and python, this is an attempt to forecast global covid 19 spread. Specifically, forecast confirmed cases and fatalities between April 15 - May 14 2020 by region.

Implemented with Python 3.7.4, FacebookProphet, and (external database)[data-sources]. ** Note: Graph only visible when run with Jupyter Notebook. **

Run Locally

1. pip install -r requirements.txt
2. python src/covid_forecaster.py

Run in Docker Locally

1. docker build .
2. docker run -i

Run with Jupyter Notebook

Graph will print out in the notebook.

1. pip install -r requirements.txt
2. jupyter notebook ./src/US_Covid_19_Cases_Forecast.ipynb

Data Sources

Time Series Summary of Covid

Daily time series summary tables, including confirmed, deaths and recovered. All data are from the daily case report (Source).

Forecast Graphs

US Cases 30 Day Forecast

Forecast with data until May 12 2020

Forecast with data until April 2020