inst/script/make-research_funding_rates.R

In rafalab/dslabs: Data Science Labs

library(tidyverse)
library(tidyr)
library(stringr)
library(readr)

## Download the table
library("pdftools")
temp_file <- tempfile()
url <- "http://www.pnas.org/content/suppl/2015/09/16/1510159112.DCSupplemental/pnas.201510159SI.pdf"
download.file(url, temp_file)
txt <- pdf_text(temp_file)
file.remove(temp_file)

raw_data_research_funding_rates <- txt[2]

save(raw_data_research_funding_rates, file="data/raw_data_research_funding_rates.rda", compress="xz")

## Get the names
tab <- str_split(raw_data_research_funding_rates, "\n")[[1]]
the_names_1 <- tab[3]
the_names_2 <- tab[4]

the_names_1 <- the_names_1 %>%
  str_trim() %>%
  str_replace_all(",\\s[n|%]", "") %>%
  str_split("\\s{2,}", simplify = TRUE)

the_names_2 <- the_names_2 %>%
  str_trim() %>%
  str_split("\\s+", simplify = TRUE)

tmp_names <- str_c(rep(the_names_1, each = 3), the_names_2[-1], sep = "_")
the_names <- c(the_names_2[1], tmp_names) %>%
  str_to_lower() %>%
  str_replace_all("\\s", "_")

## Create the table
research_funding_rates <- tab[6:14] %>%
  str_trim %>%
  str_split("\\s{2,}", simplify = TRUE) %>%
  data.frame(stringsAsFactors = FALSE) %>%
  setNames(the_names) %>%
  mutate_at(-1, parse_number)

save(research_funding_rates, file="data/research_funding_rates.rda", compress="xz")