The epicenter of the outbreak of COVID-19 moves to Europe in these weeks. The situation is still highly unpredictable. We need to manage to keep away from the threat of the COVID-19. Washing hands properly and staying away from the crowded area is our duty to stop the spread of COVID-19.

Fortunately, many scientific efforts are happening to deal with COVID-19. Various kinds of data set are publicly available. We can create an application based on that to support people or get new insight into the mechanism of COVID-19. In this post, I made a list of useful data sources or projects related to the COVID-19 issue. These data was useful to write the previous blog post for sure.

Cases Data

• Raw data of the cases of COVID-19
  • https://github.com/CSSEGISandData/COVID-19
• Downloadable CSV data of the cases of COVID-19 from HDX
  • https://data.humdata.org/dataset/novel-coronavirus-2019-ncov-cases
• Machine-readable data describing the cases of COVID-19.
  • https://ourworldindata.org/coronavirus-source-data
• Today’s data on the geographic distribution of COVID-19 cases worldwide
  • https://www.ecdc.europa.eu/en/publications-data/download-todays-data-geographic-distribution-covid-19-cases-worldwide
• Cases in Tokyo
  • https://github.com/tokyo-metropolitan-gov/covid19

• Cases in Italy
  • https://github.com/pcm-dpc/COVID-19
• Cases in Wuhan
  • https://github.com/globalcitizen/2019-wuhan-coronavirus-data

Open Source Projects

Open-source software or applications for public usage related to the COVID-19 issues.

• Data Crawler
  • https://github.com/BlankerL/DXY-COVID-19-Crawler
• Collection of notebooks related to COVID-19 outbreak
  • https://github.com/arnoudbuzing/wolfram-coronavirus
• Spread Map in Wuhan
  • https://github.com/ncovis/choropleth

• Spread Map for Poland
  • https://github.com/konradkalemba/korona.ws
• iOS app to track COVID-19
  • https://github.com/MhdHejazi/CoronaTracker
• GraphQL API to get the data
  • https://github.com/rlindskog/covid19-graphql

Scholarly Articles

In response to the COVID-19 pandemic, Allen Institute for AI published the research achievement as free scholarly articles, which is named CORD-19. The dataset is expected to be used to find a new insight by mobilizing the natural language processing technology. The data is structured, and metadata contained a machine-readable format so that we can make use of the technology to explore these data.

• https://pages.semanticscholar.org/coronavirus-research
• https://www.whitehouse.gov/briefings-statements/call-action-tech-community-new-machine-readable-covid-19-dataset/

Competition

A new competition is launched using the CORD-19 dataset. Correctly, it’s not a competition in the usual sense in Kaggle. There is no award, score, and ranking there. It is a real-world challenge to tackle the COVID-19 outbreak. Our responsibility is to find useful insight and contribute it to the community so that we can fight the problem and defeat it hopefully soon.

• https://www.kaggle.com/allen-institute-for-ai/CORD-19-research-challenge

Last but not least…

It is crucial not to spread the wrong information or fake news. We should always check the primary source of information when you have any doubts. Please be aware of the site of WHO and other official announcements from your local government.

I sincerely hope the situation will recover soon.

Image by Markus Spiske from Pixabay