In ddsjoberg/hotfun: Collection of Functions Used in the Health Outcomes Team at MSKCC

knitr::opts_chunk$set(echo = TRUE)
set.seed({{format(Sys.Date(), format = "%Y%m%d")}})
renv::settings$snapshot.type("all")

Raw Data Import

library(hotverse); library(tidyverse)
# library(tidylog)

# setting MSK ggplot theme, gtsummary theme, and color palette
theme_set(mskRvis::theme_biostat()); theme_gtsummary_msk("hot"); mskRvis::set_msk_palette()

# 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_if(lubridate::is.POSIXt, lubridate::as_date) # use lubridates

Create Master Analytic Data Set

Check Variable Derivations

Save Analytic Data

# applying variable labels, and dropping raw variables
df_main <- df_main %>%
  set_derived_variables(path = here::here("scripts/derived_variables_{{stringr::str_split(folder_name, pattern = ' |-', simplify = T)[, 1] %>% tolower()}}.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")
)

ddsjoberg/hotfun documentation built on Dec. 12, 2021, 3:41 a.m.