Merge branch 'master' of https://github.com/ipeaGIT/geobr

README.md

@@ -11,7 +11,7 @@ The package is currently available in [**R**](https://CRAN.R-project.org/package
 
 | ***R*** | ***Python*** | ***Repo***|
 |-----|-----|----|
-| [![CRAN/METACRAN Version](https://www.r-pkg.org/badges/version/geobr)](https://CRAN.R-project.org/package=geobr) <br /> [![CRAN/METACRAN Total downloads](http://cranlogs.r-pkg.org/badges/grand-total/geobr?color=blue)](https://CRAN.R-project.org/package=geobr) <br /> [![CRAN/METACRAN downloads per month](http://cranlogs.r-pkg.org/badges/geobr?color=yellow)](https://CRAN.R-project.org/package=geobr) <br /> [![Codecov test coverage](https://codecov.io/gh/ipeaGIT/geobr/branch/master/graph/badge.svg)](https://app.codecov.io/gh/ipeaGIT/geobr?branch=master)  <br /> [![Lifecycle: stable](https://img.shields.io/badge/lifecycle-stable-brightgreen.svg)](https://www.tidyverse.org/lifecycle/#stable) <br /> [![R build status](https://github.com/ipeaGIT/geobr/workflows/R-CMD-check/badge.svg)](https://github.com/ipeaGIT/geobr/actions)  | [![PyPI version](https://badge.fury.io/py/geobr.svg)](https://badge.fury.io/py/geobr) <br />  [![Downloads](https://static.pepy.tech/badge/geobr)](https://pepy.tech/project/geobr) <br />  [![Downloads](https://static.pepy.tech/badge/geobr/month)](https://pepy.tech/project/geobr)  <br /> [![Lifecycle: maturing](https://img.shields.io/badge/lifecycle-maturing-blue.svg)](https://www.tidyverse.org/lifecycle/#maturing) <br /> [![Python build status](https://github.com/ipeaGIT/geobr/workflows/Python-CMD-check/badge.svg)](https://github.com/ipeaGIT/geobr/actions) |<img alt="GitHub stars" src="https://img.shields.io/github/stars/ipeaGIT/geobr.svg?color=orange"> <br /> <br />  [![Project Status: Active – The project has reached a stable, usable state and is being actively developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active) |
+| [![CRAN/METACRAN Version](https://www.r-pkg.org/badges/version/geobr)](https://CRAN.R-project.org/package=geobr) <br /> [![CRAN/METACRAN Total downloads](https://cranlogs.r-pkg.org/badges/grand-total/geobr?color=blue)](https://CRAN.R-project.org/package=geobr) <br /> [![CRAN/METACRAN downloads per month](https://cranlogs.r-pkg.org/badges/geobr?color=yellow)](https://CRAN.R-project.org/package=geobr) <br /> [![Codecov test coverage](https://codecov.io/gh/ipeaGIT/geobr/branch/master/graph/badge.svg)](https://app.codecov.io/gh/ipeaGIT/geobr?branch=master)  <br /> [![Lifecycle: stable](https://img.shields.io/badge/lifecycle-stable-brightgreen.svg)](https://www.tidyverse.org/lifecycle/#stable) <br /> [![R build status](https://github.com/ipeaGIT/geobr/workflows/R-CMD-check/badge.svg)](https://github.com/ipeaGIT/geobr/actions)  | [![PyPI version](https://badge.fury.io/py/geobr.svg)](https://badge.fury.io/py/geobr) <br />  [![Downloads](https://static.pepy.tech/badge/geobr)](https://pepy.tech/project/geobr) <br />  [![Downloads](https://static.pepy.tech/badge/geobr/month)](https://pepy.tech/project/geobr)  <br /> [![Lifecycle: maturing](https://img.shields.io/badge/lifecycle-maturing-blue.svg)](https://www.tidyverse.org/lifecycle/#maturing) <br /> [![Python build status](https://github.com/ipeaGIT/geobr/workflows/Python-CMD-check/badge.svg)](https://github.com/ipeaGIT/geobr/actions) |<img alt="GitHub stars" src="https://img.shields.io/github/stars/ipeaGIT/geobr.svg?color=orange"> <br /> <br />  [![Project Status: Active – The project has reached a stable, usable state and is being actively developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active) |
 
 
 

data_prep/R/census_tract_2022.R

@@ -18,6 +18,7 @@ dir.create(dest_dir, recursive = T)
 
 if(year == 2022){
 
+  ftp <- 'https://ftp.ibge.gov.br/Censos/Censo_Demografico_2022/Agregados_por_Setores_Censitarios_preliminares/malha_com_atributos/setores/gpkg/BR/BR_Malha_Preliminar_2022.zip'
   dest_file <-  download_file(file_url = ftp, dest_dir = raw_dir)
 
 }
@@ -28,21 +29,22 @@ if(year == 2022){
   temp_dir <- tempdir()
 
   unzip(dest_file, exdir = temp_dir)
+  local_file <- list.files(temp_dir, full.names = T, pattern = 'gpkg')
 
-  local_file <- unzip_fun(dest_file)
 
 
+# read and save original raw data
+df <- sf::st_read(local_file)
+saveRDS(df, paste0(raw_dir,'/BR_Malha_Preliminar_2022.rds'))
 
-df <- sf::st_read('./data_raw/census_tracts/2022/BR_Malha_Preliminar_2022.gpkg')
-saveRDS(df, './data_raw/census_tracts/2022/BR_Malha_Preliminar_2022.rds')
 
 
 
-#### 1. clean and save data -----------------
 
-df$AREA_KM2 <- NULL
+#### 1. clean and save data -----------------
+df <- readRDS(paste0(raw_dir,'/BR_Malha_Preliminar_2022.rds'))
 
-temp_sf <- dplyr::rename(df,
+temp_sf <- dplyr::select(df,
                      code_tract = CD_SETOR,
                      code_muni = CD_MUN,
                      name_muni = NM_MUN,
@@ -73,11 +75,15 @@ temp_sf <- mutate(temp_sf, code_tract = gsub("P","", code_tract))
 head(temp_sf)
 
 
-# make all columns as character
-char_cols <- names(temp_sf)
-char_cols <- char_cols[char_cols %like% 'code_|name_']
+# make all name columns as character
+all_cols <- names(temp_sf)
+char_cols <- all_cols[all_cols %like% 'name_']
 temp_sf <- mutate(temp_sf, across(all_of(char_cols), as.character))
 
+# make all columns as character
+num_cols <- all_cols[all_cols %like% 'code_']
+temp_sf <- mutate(temp_sf, across(all_of(char_cols), as.numeric))
+
 
 # Use UTF-8 encoding
 temp_sf <- use_encoding_utf8(temp_sf)
@@ -91,14 +97,19 @@ gc()
 
 save_state <- function(code_uf){ # code_uf <- 33
 
+    message(code_uf)
+
     temp_sf2 <- subset(temp_sf, code_state == code_uf)
-    # temp_sf2 <- subset(temp_sf2, code_muni == '3304557')
+    # temp_sf2 <- subset(temp_sf, code_muni == '3304557')
 
     # convert to MULTIPOLYGON
     temp_sf2 <- to_multipolygon(temp_sf2)
 
+    temp_sf2 <- fix_topoly(temp_sf2)
+
     # simplify
     temp_sf_simplified <- simplify_temp_sf(temp_sf2, tolerance = 10)
+    temp_sf_simplified <- fix_topoly(temp_sf_simplified)
 
     # Save cleaned sf in the cleaned directory
     sf::st_write(temp_sf2, paste0(dest_dir,'/', code_uf,'census_tract_', year, '.gpkg'))

data_prep/R/cnefe.R

@@ -0,0 +1,50 @@
+library(arrow)
+library(dplyr)
+library(sf)
+library(mapview)
+library(sfheaders)
+
+dir_coord <- 'R:/Dropbox/git/import_cnefe/data/2022/coordenadas/parquet/'
+dir_addrs <- 'R:/Dropbox/git/import_cnefe/data/2022/arquivos/parquet/'
+
+
+
+#coord <- arrow::read_parquet(file = paste0(dir_coord,'53_DF.parquet'))
+arqui <- arrow::read_parquet(file = paste0(dir_addrs,'53_DF.parquet'))
+
+
+c <- subset(arqui, cep == 70355030) # 71665015
+c
+
+c <- sfheaders::sf_point(obj = c, x='lon', y='lat', keep = T)
+
+st_crs(c) <- 4674
+plot(c)
+
+mapview(c)
+
+# build polygons with {concaveman}
+temp <- concaveman::concaveman(c)
+plot(temp)
+
+
+n <- unique(arqui$desc_localidade)
+n <- sort(n)
+
+get_neig_poly <- function(name){ # name = 'ASA SUL'
+
+
+  c <- filter(arqui, desc_localidade == name)
+  c <- sfheaders::sf_point(obj = c, x='lon', y='lat', keep = F)
+  st_crs(c) <- 4674
+  # mapview(c)
+
+  temp <- concaveman::concaveman(c)
+  # mapview(temp)
+ # saveRDS(temp, file = paste0('./test_cnefe/', name, '.rds'))
+  sf::st_write(temp, dsn = paste0('./test_cnefe/', name, '.gpkg'),quiet = T)
+
+}
+
+pbapply::pblapply(X = n, FUN = get_neig_poly)
+

data_prep/R/regions.R

@@ -0,0 +1,23 @@
+library(geobr)
+library(collapse)
+library(sf)
+library(s2)
+library(geos)
+
+i = 2020
+
+uf <- read_state(code_state = 'all',
+                 year= i,
+                 simplified = FALSE)
+
+r <- uf |>
+  fmutate(geom = s2::as_s2_geography(geom)) |>
+  fgroup_by(code_region, name_region) |>
+  fsummarise(geom = s2::s2_union_agg(geom)) |>
+  fmutate(geom = st_as_sfc(geom))
+
+r
+
+sf::st_is_valid(r)
+
+plot(r['name_region'])

data_prep/R/topology.R

@@ -15,3 +15,59 @@ df <- sf::st_make_valid(df)
 df <- sf::st_buffer(df, dist = -1)
 
 mapview(df)
+
+
+
+
+
+
+
+
+
+library(sf)
+library(geobr)
+library(dplyr)
+
+biomes <- read_biomes(
+  year = 2019,
+  simplified = FALSE,
+  showProgress = FALSE
+)
+
+fix_topology_brute <- function(poly_sf){ # poly_sf = biomes
+
+  # check which polys are valid
+  is_valid <- sf::st_is_valid(poly_sf)
+
+  # keep hold of valid polys
+  poly_valid <- poly_sf[is_valid, ]
+
+  # let's work on invalid ones
+  poly_invalid <- poly_sf[!is_valid, ]
+
+  # detect problematic edges
+  problem_edges <- st_is_valid(poly_invalid, reason=TRUE)
+  problem_edges <- sub(".*:\\D*(\\d+).*", "\\1", problem_edges) |> as.numeric()
+
+  # convert to point
+  poly_invalid2 <- sf::st_cast(poly_invalid, "POINT") |> suppressWarnings()
+
+  # drop problem edges
+  poly_invalid2 <- poly_invalid2[-c(problem_edges), ]
+
+  poly_invalid2 <- sf::st_combine(poly_invalid2)
+  poly_invalid2 <- sf::st_cast(poly_invalid2, "POLYGON")
+  poly_invalid2 <- sf::st_sf(poly_invalid2)
+
+  poly_invalid2 <- rename(poly_invalid2, geom = poly_invalid2)
+  poly_invalid2$code_biome <- 1
+  poly_invalid2$name_biome <- 'Amazônia'
+  poly_invalid2$year <- 2019
+  poly_invalid2 <- dplyr::select(poly_invalid2, names(poly_valid))
+
+  manchas_consertadas <- rbind(poly_valid, poly_invalid2)
+  manchas_consertadas <- sf::st_union(manchas_consertadas)
+  manchas_consertadas <- sf::st_make_valid(manchas_consertadas)
+
+  return(manchas_consertadas)
+}