lambdabaa/CORD-19

Download the CORD-19 dataset from Kaggle.

Clusters

Social Science

• Pandemics
• Public Policy

Treatment

• Case Studies I
• Case Studies II
• Drug Design
• Immunology & Vaccination
• Medical Care

Epidemiology

• Epidemiology
• Respiratory Illness
• Virology

Biology

• Animal Studies
• Biochemical Engineering
• Cell Biology
• Genomics
• Microbiology

Modeling

• Mathematical Modeling

Transmission, Detection, & Surveillance

• Transmission
• Detection & Surveillance

Foreign Language

• French
• German

Usage

python3 -m pip install -r requirements.txt
./preprocessing.py  # extract_text()
./preprocessing.py > titles.csv  # extract_titles()
./bpe.sh
./preprocessing.py  # apply_bpe()
./doc2vec.py
./kmeans.py ./docvec > clusters.csv
./csvmerge.py > docs.csv