variable_names.R

library(tidyverse)

## this r code is taking from here: https://github.com/mkearney/pkguse
read_r_files <- function(...) {
    dirs <- unlist(list(...))
    r <- unlist(lapply(dirs, list.files,
                       pattern = "\\.(R|Rmd|Rmarkdown|rmd|r|Rhistory)$",
                       recursive = TRUE,
                       full.names = TRUE,
                       all.files = TRUE))
    suppressWarnings( x <- unlist(lapply(r, tfse::readlines)))
    x
}

## read in r files
rss <- read_r_files(c("C://Users//favoo//Dropbox", "C://Users//favoo//Documents//git_proj"))


## parse everything that comes before assignment arrow "<-"
df_names <- rss %>% 
    stringr::str_extract("\\w+(?=.*<-)") %>% 
    na.omit() %>% 
    table(df_name = .) %>% 
    as_tibble()

## look at most common occuring variable names
df_names %>% 
    arrange(-n)