clean up

src/municipalities/02-CA.R

@@ -57,7 +57,9 @@ truly_exclude <- c(
   "land_area_ha",
   all_vars[str_detect(all_vars, "^type_of_land_")],
   all_vars[str_detect(all_vars, "^use_of_land_")],
-  "forest", "open_land", "total_green_space",
+  "forest",
+  "open_land",
+  "total_green_space",
   all_vars[str_detect(all_vars, "^inland_water")],
   all_vars[str_detect(all_vars, "^seawater")],
   all_vars[str_detect(all_vars, "^the_four_large")],
@@ -90,19 +92,30 @@ col_sup_politics <- analysis_vars[
 # rather than resident persons. Projecting them as supplementary shows how
 # they relate to the population-composition space without distorting it.
 col_sup_infra <- analysis_vars[
-  str_detect(analysis_vars,
+  str_detect(
-    "^number_of_(rented|tenant_owned|owner_occupied)_dwellings") |
+    analysis_vars,
+    "^number_of_(rented|tenant_owned|owner_occupied)_dwellings"
+  ) |
     str_detect(analysis_vars, "^number_of_registered_passenger_cars_") |
     str_detect(analysis_vars, "^workplaces_") |
     str_detect(analysis_vars, "^agricultural_enterprises_") |
     str_detect(analysis_vars, "^livestock_") |
-    analysis_vars %in% c(
+    analysis_vars %in%
-      "sex_men", "sex_women",
+      c(
-      "employment_by_gender_men", "employment_by_gender_women",
+        "sex_men",
-      "number_of_inmigrations", "number_of_outmigrations",
+        "sex_women",
-      "births", "deaths", "marriages", "divorces",
+        "employment_by_gender_men",
-      "buildings", "buildings_for_seasonal_use",
+        "employment_by_gender_women",
-      "concentrations_of_holiday_homes", "holiday_home_areas",
+        "number_of_inmigrations",
+        "number_of_outmigrations",
+        "births",
+        "deaths",
+        "marriages",
+        "divorces",
+        "buildings",
+        "buildings_for_seasonal_use",
+        "concentrations_of_holiday_homes",
+        "holiday_home_areas",
         "social_assistance_number_of_receiver_households",
         "urban_residences_proximity_to_public_green_areas_500_meters_or_less",
         "number_of_localities"
@@ -129,14 +142,6 @@ active_vars <- analysis_vars[
 # Everything else → post-hoc correlations with CA dimensions
 outside_ca <- setdiff(analysis_vars, c(active_vars, col_sup_vars))
 
-cat(
-  "Active (person-count population composition): ", length(active_vars), "\n",
-  "col.sup – educational provision:             ", length(col_sup_edu), "\n",
-  "col.sup – political vote counts:             ", length(col_sup_politics), "\n",
-  "col.sup – infrastructure / event counts:     ", length(col_sup_infra), "\n",
-  "Outside CA (rates / continuous / other):     ", length(outside_ca), "\n"
-)
-
 # 03-Build CA matrix -----------------------------------------------------------
 X <- m_sample |>
   select(all_of(c(active_vars, col_sup_vars))) |>
@@ -154,9 +159,6 @@ idx_sup <- seq(length(active_vars) + 1L, ncol(X))
 # 04-Run CA --------------------------------------------------------------------
 ca <- CA(X, ncp = 10, col.sup = idx_sup, graph = FALSE)
 
-cat("\nEigenvalues (first 10 dimensions):\n")
-print(round(ca$eig[1:10, ], 3))
-
 contribs <- ca$col$contrib |>
   as.data.frame() |>
   rownames_to_column("variable")
@@ -177,7 +179,11 @@ outside_data <- m_sample |>
     replace_na(x, if (is.finite(m)) m else 0)
   }))
 
-posthoc_cor <- cor(ca_row_coords, outside_data, use = "pairwise.complete.obs") |>
+posthoc_cor <- cor(
+  ca_row_coords,
+  outside_data,
+  use = "pairwise.complete.obs"
+) |>
   as.data.frame() |>
   rownames_to_column("dimension")
 

src/municipalities/03-attainment-ts.R

@@ -40,16 +40,20 @@ cat("Municipalities to fetch:", length(munis), "\n")
 fetch_batch <- function(muni_batch) {
   query <- list(
     query = list(
-      list(code = "Region",
+      list(
-           selection = list(filter = "item", values = as.list(muni_batch))),
+        code = "Region",
-      list(code = "Alder",
+        selection = list(filter = "item", values = as.list(muni_batch))
-           selection = list(filter = "item", values = AGES)),
+      ),
-      list(code = "UtbildningsNiva",
+      list(code = "Alder", selection = list(filter = "item", values = AGES)),
-           selection = list(filter = "item", values = LEVELS)),
+      list(
-      list(code = "Kon",
+        code = "UtbildningsNiva",
-           selection = list(filter = "item", values = GENDERS)),
+        selection = list(filter = "item", values = LEVELS)
-      list(code = "Tid",
+      ),
-           selection = list(filter = "item", values = as.list(YEARS)))
+      list(code = "Kon", selection = list(filter = "item", values = GENDERS)),
+      list(
+        code = "Tid",
+        selection = list(filter = "item", values = as.list(YEARS))
+      )
     ),
     response = list(format = "json")
   )
@@ -80,8 +84,17 @@ batches  <- split(munis, ceiling(seq_along(munis) / 50))
 raw_list <- vector("list", length(batches))
 
 for (i in seq_along(batches)) {
-  cat("  Fetching batch", i, "/", length(batches),
+  cat(
-      "(munis", batches[[i]][1], "–", tail(batches[[i]], 1), ")\n")
+    "  Fetching batch",
+    i,
+    "/",
+    length(batches),
+    "(munis",
+    batches[[i]][1],
+    "–",
+    tail(batches[[i]], 1),
+    ")\n"
+  )
   raw_list[[i]] <- tryCatch(
     fetch_batch(batches[[i]]),
     error = function(e) {
@@ -93,7 +106,6 @@ for (i in seq_along(batches)) {
 }
 
 raw <- bind_rows(compact(raw_list))
-cat("Total rows fetched:", nrow(raw), "\n")
 
 # Aggregate: sum across ages and genders → n per (code, year, edu_level)
 attainment <- raw |>
@@ -112,6 +124,3 @@ attainment_summary <- attainment |>
 
 write_rds(attainment, "data/processed/attainment_ts.rds")
 write_rds(attainment_summary, "data/processed/attainment_summary.rds")
-cat("Saved attainment_ts.rds and attainment_summary.rds\n")
-cat("Years:", paste(sort(unique(attainment$year)), collapse = ", "), "\n")
-cat("Municipalities:", n_distinct(attainment$code), "\n")