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)

# setting MSK ggplot theme, color palette, and gtsummary theme
theme_set(mskRvis::theme_biostat()); mskRvis::set_msk_palette()
{{(ifelse(tolower(Sys.info()[["user"]]) %in% eval(as.list(bstfun::theme_gtsummary_msk)$name), glue::glue("theme_gtsummary_msk('{tolower(Sys.info()[['user']])}')"), "theme_gtsummary_compact()"))}}
here_data() # current path to data

# example code for importing excel file
df_raw_data <-
  readxl::read_excel(
    path = here_data("Raw Data from PI.xlsx")
  ) %>%
  janitor::clean_names(case = "all_caps") %>% # uppercase col names
  mutate(across(where(lubridate::is.POSIXt), lubridate::as_date)) # use lubridates

Create Master Analytic Data Set

Check Variables

Save Analytic Data

# applying variable labels, and dropping raw variables
df_main <- df_main %>%
  set_derived_variables(path = here::here("scripts/derived_variables.xlsx"))

# overview of master analytic dataset
skimr::skim(df_main)

# saving master analytic data set
saveRDS(
  object = df_main,
  file = here_data("df_main.Rds")
)