In ddsjoberg/bstfun: Functions for the MSK Biostatistics Department

knitr::opts_chunk$set(echo = TRUE)

set.seed({{format(Sys.Date(), format = "%Y%m%d")}})

Raw Data Import

library(biostatR)
library(tidyverse)
library(labelled)
library(lubridate)
library(glue)

# Set custom gtsummary theme if exists in the bstfun::theme_gtsummary_msk
bstfun::theme_gtsummary_msk('leej22')

# Location of data
options(path_data = "")

# example code for importing excel file
raw_dat <-
  readxl::read_excel(
    path = paste(
      bstfun::path_data(data_folder_name = "data"),
      "raw.xlsx",
      sep = "/"
      )
  ) %>%
  janitor::clean_names(case = "all_caps") %>% # uppercase col names
  mutate(across(where(lubridate::is.POSIXt), lubridate::as_date)) %>%# use lubridates 
  # convert all character/string fields to all upper case 
  mutate_if(is.character, toupper) %>%
  mutate_if(is.character, trimws, which = "both", whitespace = "[\\h\\v]") # get rid of whitespace

Create Master Analytic Data Set

Check Variables

Save Analytic Data

# applying variable labels, and dropping raw variables
df_main <- 
  df_main %>%
  labelled::set_variable_labels(
    mrn = "Patient MRN"
  )


# saving master analytic data set
saveRDS(
  object = df_main,
  file = bstfun::path_data("dat.Rds", data_folder_name = "data")
)