ruralitic-qrm/src/municipalities/00-import.R

# 00 - Libraries ---------------------------------------------------------------
library(tidyverse)
library(readxl)

# 01 - Import ------------------------------------------------------------------

# Municipalities_db.xlsx has two title rows before the merged-cell header:
# Row 1: "Municipalities Database" (title)
# Row 2: blank
# Row 3: category names (forward-filled across sub-columns)
# Row 4: sub-category names
# Row 5+: data

# I first extract the categories and subcategories
header_rows <- read_xlsx(
  "data/Municipalities_db.xlsx",
  col_names = FALSE,
  n_max = 2,
  skip = 2
)

# Then, I reshape it as a list using a "category_subcategory" format
col_names <- header_rows |>
  t() |>
  as_tibble(.name_repair = "unique") |>
  set_names(c("category", "subcategory")) |>
  fill(category) |>
  mutate(
    col_name = if_else(
      is.na(subcategory),
      category,
      str_c(category, subcategory, sep = " - ")
    ) |>
      str_to_lower() |>
      str_replace_all("[^a-z0-9]+", "_") |>
      str_remove("_$")
  ) |>
  pull(col_name)

# Finally, I read the table skiping the first for rows and then append col_names
municipalities_raw <- read_xlsx(
  "data/Municipalities_db.xlsx",
  skip = 4,
  col_names = col_names,
  col_types = "text"
) |>
  mutate(across(-c(code, municipality), \(x) suppressWarnings(as.numeric(x))))

# Write out as rds for future reading
write_rds(municipalities_raw, "data/processed/m_raw.rds")