Despite the fact that there're many Covid datasets, there is a lack of publicly available datasets or analysis about hospitalization data. We want to bridge this gap by creating a new well-organized, clean Covid-related hospitalization dataset.
What it does
Process and aggregate multiple datasets from reliable sources and yield one new, well-organized, clean Covid-related hospitalization dataset.
How we built it
Jupyter Notebook and Plotly Dash!
Challenges we ran into
Different datasets are not always consistent.
Accomplishments that we're proud of
A new, well-organized, clean Covid-related hospitalization dataset.
What we learned
Data preprocessing and merging across multiple datasets from different sources.
What's next for Covid Data Gigs
We believe that the dataset can be further enriched and welcome any future contributions.