creatingSynData.R

In etesdahl/claimWranglR: Utility Functions for Working with Health Claims Data

#this script was used to create the sample synthetic data file to be included in the package
library(data.table)
mycolClasses <- c("character", "character", "integer",
                "character","character","character",
                "numeric", "numeric", "character",
                "character","character","character",
                "character", "numeric", "numeric",
                "numeric", "numeric","integer", rep("character", 63))

synData <- fread("DE1_0_2008_to_2010_Inpatient_Claims_Sample_1.csv", verbose = TRUE, colClasses = mycolClasses)
synData[, totClmCount := .N, DESYNPUF_ID ]
synData <- synData[DESYNPUF_ID %in% sample(unique(DESYNPUF_ID), 1000) ]
synData