This repo contains code and notebooks for the COVID-19 Open Research Dataset Challenge (CORD-19) on kaggle
Clone and modify the Kaggle notebook
- Download the data
Login to Kaggle and download the CORD Research Challenge data and extract to a folder called data.
You can also use the kaggle cli
bash
kaggle datasets download allen-institute-for-ai/CORD-19-research-challenge
``
2. Install
Install the library using pip
pip install git+https://github.com/dgunning/cord19.git
dir data\CORD-19-research-challenge
The library is meant for use in Jupyter or Kaggle notebooks
from cord import ResearchPapers
research_papers = ResearchPapers.load()
After loading the research papers you can display in a notebook
research_papers
The search function returns the items that match the search query
research_papers.searchbar('vaccine transmission'
A more convenient way to search is through the search bar. This displays a search widgets in Jupyter notebook
research_papers.searchbar('vaccine transmission')
There are many ways to select subsets of research papers including
- Papers since SARS
research_papers.since_sars() - Papers since SARS-COV-2
research_papers.since_sarscov2() - Papers before SARS
research_papers.before_sars() - Papers before SARS-COV-2
research_papers.before_sarscov2() - Papers before a date
research_papers.before('1989-09-12') - Papers after a date
research_papers.after('1989-09-12') - Papers that contains a string
research_papers.contains("Fauci", column='authors') - Papers that match a string (using regex)
research_papers.match('H[0-9]N[0-9]')
You can select individual papers by using Python indexing []
research_papers[200]
