FWO_SB_2017.R

library(tidyverse)
library(pdftools)

df <- pdf_text("SB-Beurs-2017.pdf") %>%
  str_split(pattern = "\n") %>%
  unlist() %>%
  as_tibble() %>%
  filter(str_detect(value, "18N")) %>% # select lines with project number in them
  mutate(value = str_trim(value), # trim trailing spaces
         value = if_else(str_sub(value, 1, 2) %in% str_c(LETTERS, " "),  # Remove letters
                         str_sub(value, 3, -1),
                         value)) %>%
  separate(value, into = c("Mandaathouder", "Universiteit", "Aanvraagnummer"), fill = "right", sep = "\\s{2,}") %>%
  mutate(Aanvraagnummer = if_else(is.na(Aanvraagnummer), # Not everything is parsed well so neet some tweaking
                                  str_sub(Universiteit, -8,-1),
                                  Aanvraagnummer),
         Universiteit = if_else(str_detect(Universiteit, "18N"), # Split strings with project numbers in their University column
                                str_sub(Universiteit, 1, -9),
                                Universiteit),
         Universiteit = if_else(Universiteit == "", # Split strings with University name in Mandaathouder column
                                str_extract(Mandaathouder, "[A-z]+$"),
                                Universiteit),
         Universiteit = if_else(Universiteit == "Leuven", # Fix if only Leuven was put in the University column
                                "KU Leuven",
                                str_trim(Universiteit)))
  
  
  
df %>% group_by(Universiteit) %>%
  summarise(Total_projects = n()) %>%
  ggplot(aes(x = reorder(Universiteit, Total_projects), y = Total_projects)) +
  geom_col() +
  xlab("") +
  ylab("Amount of FWO-SB projects") +
  coord_flip() +
  theme_minimal() +
  theme(axis.text.y = element_text(size = 16, face = "bold"))

ggsave("FWO_SB_2017.png")

# Update
professors <- tibble(Universiteit = c("UAntwerpen", "KU Leuven", "UGent", "VUB", "UHasselt"), 
                     NumberZAP = c(624, 1561, 1502, 402, 392))

df %>% group_by(Universiteit) %>%
  summarise(Total_projects = n()) %>%
  ungroup() %>%
  left_join(professors) %>%
  mutate(normalized_count = Total_projects/(NumberZAP/100)) %>%
  ggplot(aes(x = reorder(Universiteit, normalized_count), y = normalized_count)) +
  geom_col() +
  xlab("") +
  ylab("Amount of FWO-SB projects per 100 professors") +
  coord_flip() +
  theme_minimal() +
  theme(axis.text.y = element_text(size = 16, face = "bold"))

ggsave("FWO_SB_2017_per100prof.png")