data-raw/README.md

In laderast/cvdRiskData: Synthetic Dataset for Cardiovascular Risk Prediction

Raw Data Folder

There are six versions of the datasets in the folder.

dataDictionary.pdf has information for all of the covariates - we use this in an exercise to understand the datasets.

full means the full patient cohort (~500K patients).

• fullPatientData.csv - the entire patient cohort
• fullDataTrainSet.csv - a subset of the patients subsetted for training a model
• fullDataTestSet.csv - a subset of the patients subsetted for testing a model

geno means a smaller cohort (~50K patients) who have additional SNP covariates:

• genoData.csv - the entire genotyped cohort
• genoDataTestSet.csv - subset of genotyped cohort for training a model
• genoDataTrainSet.csv - subset of genotyped cohort for testing a model

laderast/cvdRiskData documentation built on May 28, 2019, 7:37 a.m.