Use XgBoost_COVIDandFLUWithoutNan.ipynb to run classification between COVID-19 and influenza paitents.
Raw input file required is UsedCombined.txt
COVID19_PatientTable_WithCitations.txt includes literature references to all source data for COVID-19 patients.
Use sombrero.R to run Self-Organizaing Map (SOM) for clustering COVID-19 patients into subgroups.
Raw input file required is LiteratureSearchDataindividualpatients.tsv
Use covidRF.R and covidRidgeLAsso.R for classification between COVID-19 and influenza patients using random forest, RIDGE, or LASSO regression.
Raw input file required is COVIDandFLUdata.csv
Dependencies for XGBoost include:
xgboost
pandas
sklearn
bayes_opt
numpy
matplotlib
scikitplot
graphviz
Dependencies for SOM include:
SOMbrero
Dependencies for RIDGE, LASSO, and random forest include:
glmnet
pROC
randomForest