In dmontemayor/Rcricvol: Data Processing Tools in R for cricvol project

data <- read.csv("../data/partitioning.csv")
names(data)[1] <- "patientid"
rawdata <- read.csv("../data/RedCap.csv")
combined <- merge(data, rawdata, by = "patientid")

n patients in each group

table(data$group)

female/male ratio

table(combined[combined$sex_v3y0.y == 2,]$group)/table(combined[combined$sex_v3y0.y == 1,]$group)
print(paste("overall:", mean(table(combined[combined$sex_v3y0.y == 2,]$group)/table(combined[combined$sex_v3y0.y == 1,]$group))))

mean age (untransformed)

print(paste("group 0:", mean(combined[combined$group == 0,]$age_integer_v3y0.y)))
print(paste("group 1:", mean(combined[combined$group == 1,]$age_integer_v3y0.y)))
print(paste("group 2:", mean(combined[combined$group == 2,]$age_integer_v3y0.y)))
print(paste("group 3:", mean(combined[combined$group == 3,]$age_integer_v3y0.y)))
print(paste("group 4:", mean(combined[combined$group == 4,]$age_integer_v3y0.y)))

print(paste("overall:", mean(combined$age_integer_v3y0.y)))

library(randomForest)
rf <- randomForest(factor(group) ~ . - patientid, data = data)
print(rf)

dmontemayor/Rcricvol documentation built on Sept. 9, 2021, 9:12 a.m.