Análise Setores Censitários

setores_censitarios.R

library(sf)
library(tidyverse)

dat <- read_csv2("/Volumes/T7 Touch/github/tidyibge/data-raw/dados_setores_censitarios/Agregados_preliminares_por_setores_censitarios_BR.zip")

file_path <- "/Volumes/T7 Touch/github/tidyibge/data-raw/dados_setores_censitarios/BR_Malha_Preliminar_2022.zip"

setores <- st_read("/Volumes/T7 Touch/github/tidyibge/data-raw/dados_setores_censitarios/BR_Malha_Preliminar_2022.gpkg")

# V0001	numérico		Total de pessoas
# V0002	numérico		Total de Domicílios (DPPO + DPPV + DPPUO + DPIO + DCCM + DCSM)
# V0003	numérico		Total de Domicílios Particulares (DPPO + DPPV + DPPUO + DPIO)
# V0004	numérico		Total de Domicílios Coletivos (DCCM + DCSM)
# V0005	real		Média de moradores em Domicílios Particulares Ocupados (Total pessoas em Domicílios Particulares Ocupados / DPPO + DPIO)
# V0006	real		Percentual de Domicílios Particulares Ocupados Imputados (Total DPO imputados / Total DPO)
# V0007	numérico		Total de Domicílios Particulares Ocupados (DPPO + DPIO)


dict <- tibble(
  name_variable = paste0("v000", 1:7),
  desc_variable = c(
    "Total de Pessoas", "Total de Domicilios", "Total de Domicilios Particulares",
    "Total de Domicilios Coletivos", "Media de moradores em domicilios particulares ocupados",
    "Percentual de domicilios imputados", "Total de domicilios particulares ocupados"),
  short_name = c("pop", "dom", "dom_prt", "dom_col", "pop_dom", "share_dom_imput", "dom_prt_ocup")
)

rename_cols <- dict$name_variable
names(rename_cols) <- dict$short_name

vl_names <- c(
  "code_tract" = "CD_SETOR",
  "area_km2" = "AREA_KM2",
  "code_region" = "CD_REGIAO",
  "name_region" = "NM_REGIAO",
  "code_state" = "CD_UF",
  "name_state" = "NM_UF",
  "code_muni" = "CD_MUN",
  "name_muni" = "NM_MUN",
  "code_district" = "CD_DIST",
  "name_district" = "NM_DIST",
  "code_subdistrict" = "CD_SUBDIST",
  "name_subdistrict" = "NM_SUBDIST",
  "code_microregion" = "CD_MICRO",
  "name_microregion" = "NM_MICRO",
  "code_mesoregion" = "CD_MESO",
  "name_mesoregion" = "NM_MESO",
  "code_immediate" = "CD_RGI",
  "name_immediate" = "NM_RGI",
  "code_intermediate" = "CD_RGINT",
  "name_intermediate" = "NM_RGINT",
  "code_urban_concentration" = "CD_CONCURB",
  "name_urban_concentration" = "NM_CONCURB"
)

rename_cols <- c(rename_cols, vl_names)

dat <- dat %>%
  rename(all_of(rename_cols)) %>%
  select(
    code_tract, code_muni, name_muni, code_region, name_region, code_state,
    name_state, pop:dom_prt_ocup
  )

setores <- setores %>%
  rename(any_of(rename_cols))


# Curitiba ----------------------------------------------------------------


curitiba_setores <- setores %>%
  filter(code_muni == 4106902) %>%
  mutate(across(pop:dom_prt_ocup, as.numeric)) %>%
  mutate(
    area_km2 = as.numeric(area_km2),
    pop_dens_area = pop / area_km2,
    pop_dens_hh = pop / dom_prt_ocup
  )

ggplot(curitiba_setores, aes(pop_dens_area, pop_dens_hh)) +
  geom_jitter()

ggplot(curitiba_setores, aes(log(pop_dens_area))) +
  geom_histogram()

ggplot(curitiba_setores, aes(pop_dens_hh)) +
  geom_histogram()

breaks <- BAMMtools::getJenksBreaks(curitiba_setores$pop, k = 7)

ggplot(curitiba_setores) +
  geom_sf(aes(fill = pop)) +
  scale_fill_fermenter(breaks = breaks, direction = 1, palette = "Spectral")

breaks <- BAMMtools::getJenksBreaks(curitiba_setores$pop_dens_hh, k = 7)

ggplot(curitiba_setores) +
  geom_sf(aes(fill = pop_dens_hh)) +
  scale_fill_fermenter(breaks = breaks, direction = 1, palette = "Spectral")

curitiba_setores %>%
  arrange(desc(pop_dens_hh))

curitiba_subdistritos <- curitiba_setores %>%
  group_by(code_subdistrict, name_subdistrict) %>%
  summarise(across(pop:dom_prt_ocup, sum))

ggplot(curitiba_subdistritos) +
  geom_sf(aes(fill = pop))

curitiba_setores %>%
  mutate(trunc_dens = if_else(pop_dens_hh >= 5, 5, pop_dens_hh)) %>%
  ggplot(aes(fill = trunc_dens)) +
  geom_sf() +
  scale_fill_fermenter(breaks = c(1, 1.5, 2, 2.5, 3, 3.5, 4, 5), direction = 1)

curitiba_setores %>%
  filter(pop > 10, area_km2 < 2.5) %>%
  ggplot(aes(log(area_km2 * 100), log(pop))) +
  geom_point(shape = 21, color = "#219ebc") +
  geom_smooth(method = "lm", se = FALSE, color = "#ffb703") +
  theme_bw()

ggplot(curitiba_setores, aes(x = area_km2, y = pop)) +
  geom_point()

curitiba_setores %>%
  filter(pop > 10, area_km2 < 2.5, pop_dens_hh < 5) %>%
  ggplot(aes(pop_dens_hh, log(pop_dens_area))) +
  geom_point()

curitiba_setores %>%
  filter(pop > 10, area_km2 < 2.5, pop_dens_hh < 5) %>%
  mutate(scaled_pop_dens_area = as.numeric(scale(log(pop_dens_area)))) %>%
  ggplot() +
  geom_sf(aes(fill = scaled_pop_dens_area)) +
  scale_fill_fermenter(
    palette = "RdBu",
    direction = 1,
    breaks = c(-3, -1.5, -1, 0, 1, 1.5, 3)
    )

mapview::mapview(curitiba_setores, zcol = "pop_dens_area")

curitiba_setores %>%
  arrange(desc(pop_dens_area))


santos_setoers <- setores %>%
  filter(code_muni == 3548500)