v0.3.2

CRAN-SUBMISSION

@@ -1,3 +1,3 @@
-Version: 0.3.1
-Date: 2024-02-08 15:14:44 UTC
-SHA: 028ef793b00ac8f8551a2c051e2dc46c574fa73c
+Version: 0.3.2
+Date: 2024-03-23 15:56:12 UTC
+SHA: 05af38fa8f5eb7aed083b789d0ef9aa35749a361

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: censobr
 Title: Download Data from Brazil's Population Census
-Version: 0.3.1
+Version: 0.3.2
 Authors@R: 
     c(person(given="Rafael H. M.", family="Pereira", 
              email="[email protected]", 

NEWS.md

@@ -1,3 +1,13 @@
+# censobr v0.3.2
+
+* Minor changes
+  * Moved {arrow} package back to `Imports`
+
+* New data set and files included in this version:
+  * 2022 census
+    * Preliminary aggregate results of census tracts
+
+
 # censobr v0.3.1
 
 * Minor changes

R/read_tracts.R

@@ -6,6 +6,7 @@
 #' @template year
 #' @param dataset Character. The dataset to be opened. Options currently include
 #'        `c("Basico", "Domicilio", "DomicilioRenda", "Responsavel", "ResponsavelRenda", "Pessoa", "PessoaRenda",  "Entorno")`.
+#'        Preliminary results of the 2022 census are available with `"Preliminares"`.
 #' @template as_data_frame
 #' @template showProgress
 #' @template cache
@@ -39,15 +40,21 @@ read_tracts <- function(year = 2010,
 
 
   # data available for the years:
-  years <- c(2010)
+  years <- c(2010, 2022)
   if (isFALSE(year %in% years)) { stop(paste0("Error: Data currently only available for the years ",
                                               paste(years, collapse = " ")))}
 
-  # data available for data sets:
-  data_sets <- c("Basico", "Domicilio", "DomicilioRenda", "Entorno",
+  # data sets available for 2010:
+  data_sets_2010 <- c("Basico", "Domicilio", "DomicilioRenda", "Entorno",
                  "ResponsavelRenda", "Responsavel", "PessoaRenda", "Pessoa")
-  if (isFALSE(dataset %in% data_sets)) { stop( paste0("Error: Data currently only available for the datasets: ",
-                                                    paste(data_sets, collapse = ", "))
+  if (year==2010 & isFALSE(dataset %in% data_sets_2010)) { stop( paste0("Error: Data currently only available for the datasets: ",
+                                                    paste(data_sets_2010, collapse = ", "))
+  )}
+
+  # data sets available for 2022:
+  data_sets_2022 <- c("Preliminares")
+  if (year==2022 & isFALSE(dataset %in% data_sets_2022)) { stop( paste0("Error: Data currently only available for the datasets: ",
+                                                                        paste(data_sets_2022, collapse = ", "))
   )}
 
   ### Get url

cran-comments.md

@@ -1,13 +1,14 @@
 ## R CMD check results
 
-── R CMD check results ──────────────────────────────────────────────────── censobr 0.3.1 ────
-Duration: 1h 38m 26.4s
+── R CMD check results ────────────────────────────── censobr 0.3.9999999 ────
+Duration: 5m 52.9s
 
 0 errors ✔ | 0 warnings ✔ | 0 notes ✔
 
 
 * Minor changes
-  * Moved {arrow} package from `Imports` to `Suggests` while the {arrow} team fixes their conflict with CRAN policies related to downloading binary software. [See here](https://github.com/apache/arrow/issues/39806).
-* New package contributors:
-  * Diego Rabatone Oliveira
-  * Neal Richardson
+  * Moved {arrow} package back to `Imports`
+
+* New data set and files included in this version:
+  * 2022 census
+    * Preliminary aggregate results of census tracts

data_prep/R/add_geography_cols.R

@@ -3,11 +3,12 @@
 add_geography_cols <- function(arrw, year){
 
 
-  # get code_muni from weighting area
+  # get code_muni
   col <- case_when(year == 1970 ~ 'code_muni',
                    year == 1980 ~ 'code_muni',
                    year == 1991 ~ 'code_muni',
                    year == 2010 ~ 'V0011',
+                   year == 2022 ~ 'CD_MUN'
                    year == 2000 ~ 'AREAP')
 
   if(year %in% c(2000, 2010)){

data_prep/R/census_tracts_aggreg_2022_prelim.R

@@ -0,0 +1,54 @@
+library(dplyr)
+library(data.table)
+library(arrow)
+
+df <- data.table::fread('C:/Users/user/Downloads/Agregados_preliminares_por_setores_censitarios_BR/Agregados_preliminares_por_setores_censitarios_BR.csv')
+head(df)
+
+
+# remove P from code tract
+df[, CD_SETOR := gsub("P","", CD_SETOR)]
+head(df)
+
+
+# make all columns as character
+df <- mutate(df, across(everything(), as.character))
+
+names(df) <- toupper(names(df))
+
+df2 <- dplyr::rename(df,
+              code_tract = CD_SETOR,
+              code_muni = CD_MUN,
+              name_muni = NM_MUN,
+              code_subdistrict = CD_SUBDIST,
+              name_subdistrict = NM_SUBDIST,
+              code_district = CD_DIST,
+              name_district = NM_DIST,
+              code_urban_concentration = CD_CONCURB,
+              name_urban_concentration = NM_CONCURB,
+              code_state = CD_UF,
+              name_state = NM_UF,
+              code_micro = CD_MICRO,
+              name_micro = NM_MICRO,
+              code_meso = CD_MESO,
+              name_meso = NM_MESO,
+              code_immediate = CD_RGI,
+              name_immediate = NM_RGI,
+              code_intermediate = CD_RGINT,
+              name_intermediate = NM_RGINT,
+              code_region = CD_REGIAO,
+              name_region = NM_REGIAO,
+              area_km2 = AREA_KM2
+              )
+head(df2)
+
+
+# save
+dir.create('./data/tracts/2022/', recursive = T)
+
+dest_file <- paste0('2022_tracts_Preliminares.parquet')
+arrow::write_parquet(df2, paste0('./data/tracts/2022/', dest_file))
+
+arrow::write_parquet(df2, 'd2.parquet')
+
+

tests/testthat/test_read_tracts.R

@@ -20,7 +20,7 @@ test_that("read_tracts", {
   test2 <- read_tracts(year = 2010, dataset = 'Basico', as_data_frame = TRUE)
   testthat::expect_true(is(test2, "data.frame"))
 
-  # different data sets
+  # 2010 different data sets
   ## check if file have been downloaded
   tbls <- c('Basico', 'Domicilio', 'DomicilioRenda', 'Entorno',
              'ResponsavelRenda', 'Responsavel', 'PessoaRenda', 'Pessoa')
@@ -30,6 +30,14 @@ test_that("read_tracts", {
     testthat::expect_true( nrow(tmp_d) >= 303000)
   } )
 
+  # 2022 different data sets
+  ## check if file have been downloaded
+  tbls <- c('Preliminares')
+  lapply(X=tbls, FUN = function(y){ # y = 'Preliminares'
+    tmp_d <- read_tracts(year = 2022, dataset = y)
+    testthat::expect_true( nrow(tmp_d) == 452340)
+  } )
+
 
   # check whether cache argument is working
   time_first <- system.time(
@@ -54,7 +62,7 @@ test_that("read_tracts", {
   testthat::expect_error(read_tracts(year=999, dataset='Basico'))
   testthat::expect_error(read_tracts(year=999, dataset='Basico'))
   testthat::expect_error(read_tracts(year=2010, dataset='banana'))
-  testthat::expect_error(read_tracts(year=2010, dataset='banana'))
+  testthat::expect_error(read_tracts(year=2022, dataset='banana'))
 
   testthat::expect_error(read_tracts(year=2010, dataset='Basico', showProgress = 'banana' ))
   testthat::expect_error(read_tracts(year=2010, dataset='Basico', cache = 'banana' ))