version 0.3.0

cran · Jan 10, 2024 · 58d3a87 · 58d3a87
1 parent 94c6dd6
commit 58d3a87
Show file tree

Hide file tree

Showing 33 changed files with 764 additions and 249 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: censobr
 Title: Download Data from Brazil's Population Census
-Version: 0.2.0
+Version: 0.3.0
 Authors@R: 
     c(person(given="Rafael H. M.", family="Pereira", 
              email="rafa.pereira.br@gmail.com", 
@@ -29,11 +29,11 @@ VignetteBuilder: knitr
 Encoding: UTF-8
 RoxygenNote: 7.2.3
 NeedsCompilation: no
-Packaged: 2023-09-30 19:52:33 UTC; user
+Packaged: 2024-01-09 14:46:40 UTC; user
 Author: Rafael H. M. Pereira [aut, cre]
     (<https://orcid.org/0000-0003-2125-7465>),
   Rogério J. Barbosa [aut] (<https://orcid.org/0000-0002-6796-4547>),
   Ipea - Institute for Applied Economic Research [cph, fnd]
 Maintainer: Rafael H. M. Pereira <rafa.pereira.br@gmail.com>
 Repository: CRAN
-Date/Publication: 2023-09-30 20:12:39 UTC
+Date/Publication: 2024-01-09 15:20:06 UTC
diff --git a/MD5 b/MD5
@@ -1,69 +1,71 @@
-e501c70a2ca31dab947fa334a44ed91d *DESCRIPTION
+c36b6f37cf2aa526eda17b89208f6840 *DESCRIPTION
 11b2243851ba384d31e621f2a9723256 *LICENSE
 bb00d5b1ea3334728d7f4edd3e4059f8 *NAMESPACE
-771012419c24bab80fa5d09ad47130de *NEWS.md
+b1c779553f60812f2dbc346076b31a97 *NEWS.md
 50ceedf9155831fdb61be13a3ddf635b *R/add_labels_emigration.R
 147ff2b51428da402a1bfcb2dc672a25 *R/add_labels_families.R
 924ee082323f6718913ba9c5b5c6d4df *R/add_labels_households.R
 8f6ecbd7a36a79c209c57d6d540ea50a *R/add_labels_mortality.R
 bfe9f25530e79d908a730036ff54e567 *R/add_labels_population.R
 4f184a43d030cbd1bc69216ab1e3e5d1 *R/censobr.R
 90db4293312fd8312dccba29d36a2e9f *R/censobr_cache.R
-bf599e5ef98e6dc5bd164a5839381f57 *R/data_dictionary.R
-ad7412a40acea813f957ddcf5ecfbe5f *R/docs_interview_manual.R
-f27cb1189cf76346c0baf73056890db2 *R/docs_questionnaire.R
-5335cb518b47c337741a6ebdb3e5ccd7 *R/onLoad.R
-9a41fac7cbcb9e5e65c45b08d87712e9 *R/read_emigration.R
-69d7d750b80d890cae8c98e1accb7f7a *R/read_families.R
-2c310f7bd33266e90370c8a563b8a0cb *R/read_households.R
-98fd5c2e16389a94bbd77e7463f78403 *R/read_mortality.R
-cf5adf8dc0459227d475572550dd41d6 *R/read_population.R
-14cc08f00642a7638f0a82cd067b7276 *R/read_tracts.R
+6250af9c3c6ba62d5362f51065ef2e9a *R/data_dictionary.R
+f6f8697b7bebb6e27454230dd5571f40 *R/docs_interview_manual.R
+b750dc138208e86276ed20d2cdbb7bc8 *R/docs_questionnaire.R
+5db447b39879a0b197003105bb519735 *R/onLoad.R
+013f504ec4e1f9d2fbde6b3e279a9d86 *R/read_emigration.R
+38e43fc88be617910f7aaad0f72fc4cb *R/read_families.R
+1b9b299a16020d597e3e12a72287d530 *R/read_households.R
+1eb8cbdd59de7d1da038c8a2136a656d *R/read_mortality.R
+ef9a8b16c4e8bc538d70da6df4a8e45a *R/read_population.R
+1c885f6aa3fbaa45187ec18c516ef1d2 *R/read_tracts.R
 ae2c72d160b5ba04e7d46189fd245920 *R/set_censobr_cache_dir.R
 8e65410a49a53bf3f71b65093e6e051d *R/utils.R
-ec6e3a7757b40a7a81902edc34c396e2 *README.md
+675361616e266343f825951deddd8190 *README.md
 b83b0d0dfa6ea82d51880813fbebc0e9 *build/vignette.rds
 1add3ea9fc68f2187ff497e0e726608b *inst/CITATION
-9bd3244db54bd152a17e96d6a6d92235 *inst/doc/censobr.R
-23980b4222b3b56f0f634966a35e72cf *inst/doc/censobr.Rmd
-4d397fa70f43504cd8207dde6126ca55 *inst/doc/censobr.html
-c0c3740d72056db3bb46a0a8b158df25 *inst/doc/census_tracts_data.R
-cfaa611a8566c3e52f4b37c6335c0f59 *inst/doc/census_tracts_data.Rmd
-5db2c7d78e73fa4f6cf4abcce85cb3d4 *inst/doc/census_tracts_data.html
+be9f934b89ec11782d77624586c3acf0 *inst/doc/censobr.R
+a7e96fb4b26d55a530e885ac6ac0ddd1 *inst/doc/censobr.Rmd
+54db2f44de485d3de636d7c4db5a43ee *inst/doc/censobr.html
+2a54857875632028158b03215526cd77 *inst/doc/census_tracts_data.R
+1bb98a5280e03697d5d910096f20f0df *inst/doc/census_tracts_data.Rmd
+cfee424034783233ac66d6c2f45bd069 *inst/doc/census_tracts_data.html
 79f025df5dd3d9a4a9b475fcc73bf7b7 *inst/doc/documentation.R
 c27e67ab9a915f2a262b19d60395462b *inst/doc/documentation.Rmd
-15eaa899bd3b740ee74c198b0d71efd8 *inst/doc/documentation.html
+5d281b34ed4d0d7943c9cbd906fb8057 *inst/doc/documentation.html
 1b48e3117c78dc490ca54081b9231ef5 *man/cache_message.Rd
 51d078d209ebdeac09c8f9be853256bd *man/censobr.Rd
 42ebbbe9b8012060917497f933f0c280 *man/censobr_cache.Rd
-fa57305420939827f7b08e7faf771173 *man/data_dictionary.Rd
+787d37d3685ac3fea243259b6a7d7350 *man/data_dictionary.Rd
 248aa9b96723be11c43ad41a71ed05c0 *man/download_file.Rd
 b99bafee7c0cc94c8cf6b0f409bc3499 *man/figures/censobr_hexsticker.R
 48219fca1ec818a8f49f1fd7b04efc68 *man/figures/ipea_logo.png
 58bce978de1ff44ddff45c565fe6e4e2 *man/figures/logo.png
 4b2af118a659294ac2cf09051d69970d *man/figures/person_icon.xcf
 0122f64d230ba374dad15f0cf2f413f7 *man/figures/person_icon_white.png
 b721bd549d8d9e07427113334b9f77f5 *man/interview_manual.Rd
-c15cc92875dc74441d147a5c585d3be6 *man/questionnaire.Rd
+b577b311f7026759738bb931aeeedfff *man/questionnaire.Rd
 a855d8a046ff6692d8b36b41d83e13b0 *man/read_emigration.Rd
-0656dbf86c8e47b216cbc684ec6c618e *man/read_families.Rd
+2d7fba45b09378d3fc720a4beb8befdb *man/read_families.Rd
 77fc7b46b57dfe79a62978bf3d977127 *man/read_households.Rd
 38ecc42fd552db16c005b200e0815b9d *man/read_mortality.Rd
 e5137234284092291506c676f41a4068 *man/read_population.Rd
-e37e4cc4444631ddde66447c8821cb1f *man/read_tracts.Rd
+436103e9586a70b63971f33c4be72619 *man/read_tracts.Rd
 612385be109e4192883eb7f8aa849c87 *man/roxygen/templates/add_labels.R
 d5d889932073de579e60949cd9f841d0 *man/roxygen/templates/as_data_frame.R
 1eee990802cf2b626122a37d1807c6d0 *man/roxygen/templates/cache.R
 ae2ba005e0f39daa9c2dc28b9818ce78 *man/roxygen/templates/columns.R
 d4d9d9cd6cc072a6d02469509b649dd5 *man/roxygen/templates/showProgress.R
 dfe018710e98911d4d0294c8af34f802 *man/roxygen/templates/year.R
 adff8fcc69430033b7d0b72c08688156 *man/set_censobr_cache_dir.Rd
+370770fecac6b547a80cc2c9007c3704 *tests/tests_rafa/merge_household.R
+ad01582e1dcf61fdcc6aced8fb041fe2 *tests/tests_rafa/merge_pdfs.R
 e1470eb4b1e5d8dab99db882f4452300 *tests/tests_rafa/survey.R
-eb8a6410059183ee1810e7c52f9328f1 *tests/tests_rafa/test_rafa.R
-71e5a807df34dd34e4ba852862b18771 *tests/testthat.R
+629b09a768cbe392d888c360c55e2653 *tests/tests_rafa/test_rafa.R
+dcd1fb174c42985502542d1fc24bde5a *tests/testthat.R
 54897480c2acc432e286a384796cfbba *tests/testthat/test_data_dictionary.R
-bd90535c465e9b6d25adc8bc1f81bf94 *tests/testthat/test_docs_interview_manual.R
-cb593d5162a376f8e9b53f91a4a9b6e9 *tests/testthat/test_docs_questionnaire.R
+d6b80f38605260e47f6f5acf993bd9a2 *tests/testthat/test_docs_interview_manual.R
+7b1cb8c07cea20ee50906ddb2788bdc2 *tests/testthat/test_docs_questionnaire.R
 cd6c09779ea978e67ddcd86ced7d4bf6 *tests/testthat/test_labels_emigration.R
 6ec3662a4a95c4f94afe60b7b3b4b8fd *tests/testthat/test_labels_families.R
 72a96831f3ca3cb7965757e876d42978 *tests/testthat/test_labels_households.R
@@ -77,6 +79,6 @@ cc3fd48ca85481d9d50a6371305f761e *tests/testthat/test_read_population.R
 016205ea450e7d2cfa0ae2823fdd9349 *tests/testthat/test_read_tracts.R
 d2035d14be886a18e3d67158ff99d8d1 *tests/testthat/test_set_censobr_cache_dir.R
 f4bfe8d8fc843ece5dfdfc5ac17617cd *tests/testthat/test_z_censobr_cache.R
-23980b4222b3b56f0f634966a35e72cf *vignettes/censobr.Rmd
-cfaa611a8566c3e52f4b37c6335c0f59 *vignettes/census_tracts_data.Rmd
+a7e96fb4b26d55a530e885ac6ac0ddd1 *vignettes/censobr.Rmd
+1bb98a5280e03697d5d910096f20f0df *vignettes/census_tracts_data.Rmd
 c27e67ab9a915f2a262b19d60395462b *vignettes/documentation.Rmd
diff --git a/NEWS.md b/NEWS.md
@@ -1,4 +1,23 @@
-# censobr v0.1.1999 dev
+# censobr v0.3.0
+
+* Major changes
+  * The `questionnaire()` function now accepts questionnaires of `type`: `"long"` or `"short"`.
+  * Updated census tract data following latest update by IBGE on Oct/2023. Closed [#38](https://github.com/ipeaGIT/censobr/issues/38). As a result, the package moved to data release v0.3.0.
+
+* Minor changes
+  * Replaced `.onAttach` by `.onLoad` so that the package works with `censobr::function()`
+  * Fixed documentation of various functions.
+  * Fixed issue to make sure censobr uses suggested packages conditionally on CRAN
+  * Fixed message when user requests a data set / file for a year that is not available
+
+* New data set and files included in this version:
+  * 2022 census [*New*]
+    * Questionnaires and interview manuals 
+  * Short questionnaires for every census between 1960 and 2022.
+  * Long questionnaire for the 1960 and 2022 censuses.
+
+
+# censobr v0.2.0
 
 * Major changes
   * New function `read_tracts()` to read  Census tract-level aggregate data.

diff --git a/R/data_dictionary.R b/R/data_dictionary.R
@@ -20,7 +20,7 @@
 #'
 #' data_dictionary(year = 2010, dataset = 'tracts', showProgress = FALSE)
 
-data_dictionary <- function(year = NULL,
+data_dictionary <- function(year = 2010,
                             dataset = NULL,
                             showProgress = TRUE,
                             cache = TRUE){

diff --git a/R/docs_interview_manual.R b/R/docs_interview_manual.R
@@ -24,10 +24,10 @@ interview_manual <- function(year = NULL,
   checkmate::assert_numeric(year)
 
   # data available for the years:
-  years <- c(1970, 1980, 1991, 2000, 2010)
+  years <- c(1970, 1980, 1991, 2000, 2010, 2022)
   if (isFALSE(year %in% years)) { stop(  paste0("Error: Interview manual currently only available for the years: ",
-                                              paste(years), collapse = " ")
-                                        )}
+                                              paste(years, collapse = " "))
+                                         ) }
 
   ### Get url
   fname <- paste0(year, '_interview_manual.pdf')

diff --git a/R/docs_questionnaire.R b/R/docs_questionnaire.R
@@ -5,9 +5,10 @@
 #' censuses
 #'
 #' @template year
-#' @param type Character. The type of questionnaire, whether the one used in the
-#'        sample component of the census, or on the universe component. Options
-#'        currently include `c("sample")`.
+#' @param type Character. The type of questionnaire used in the survey, whether
+#'        the `"long"` one used in the sample component of the census, or the
+#'        `"short"` one, which is answered by more households. Options include
+#'        `c("long", "short")`.
 #' @template showProgress
 #' @template cache
 #'
@@ -18,30 +19,33 @@
 #' library(censobr)
 #'
 #' # Open questionnaire on browser
-#' questionnaire(year = 2010, type = 'sample', showProgress = FALSE)
+#' questionnaire(year = 2010, type = 'long', showProgress = FALSE)
 #'
-questionnaire <- function(year = NULL,
-                               type = NULL,
-                               showProgress = TRUE,
-                               cache = TRUE){
-  # year = 2010
-  # type = 'sample'
+questionnaire <- function(year = 2010,
+                          type = NULL,
+                          showProgress = TRUE,
+                          cache = TRUE){
+  # year = 2000
+  # type = 'short'
+  # type = 'long'
 
   ### check inputs
   checkmate::assert_numeric(year)
   checkmate::assert_string(type)
 
   # data available for the years:
-  years <- c(1970, 1980, 1991, 2000, 2010)
+  years <- c(1960, 1970, 1980, 1991, 2000, 2010, 2022)
   if (isFALSE(year %in% years)) { stop(  paste0("Error: Questionnaire currently only available for the years: ",
-                                              paste(years), collapse = " ")
+                                              paste(years, collapse = ", "))
                                         )}
 
   # data available for data sets:
-  data_sets <- c('sample')
+  data_sets <- c('long', 'short')
   if (isFALSE(type %in% data_sets)) { stop( paste0("Error: Questionnaire currently only available for the types: ",
                                               paste(data_sets, collapse = ", "))
-                                            )}
+  )}
+
+
 
   ### Get url
   fname <- paste0(year, '_questionnaire_', type, '.pdf')

diff --git a/R/onLoad.R b/R/onLoad.R
@@ -1,10 +1,10 @@
 # package global variables
 censobr_env <- new.env(parent = emptyenv()) # nocov start
 
-.onAttach <- function(libname, pkgname){
+.onLoad <- function(libname, pkgname){
 
   # data release
-  censobr_env$data_release <- 'v0.2.0'
+  censobr_env$data_release <- 'v0.3.0'
 
   # local cache dir
   cache_d <- paste0('censobr/data_release_', censobr_env$data_release)

diff --git a/R/read_emigration.R b/R/read_emigration.R
@@ -27,11 +27,11 @@
 #'
 #'
 read_emigration <- function(year = 2010,
-                             columns = NULL,
-                             add_labels = NULL,
-                             as_data_frame = FALSE,
-                             showProgress = TRUE,
-                             cache = TRUE){
+                            columns = NULL,
+                            add_labels = NULL,
+                            as_data_frame = FALSE,
+                            showProgress = TRUE,
+                            cache = TRUE){
 
   ### check inputs
   checkmate::assert_numeric(year)
@@ -42,7 +42,7 @@ read_emigration <- function(year = 2010,
   # data available for the years:
   years <- c(2010)
   if (isFALSE(year %in% years)) { stop(paste0("Error: Data currently only available for the years ",
-                                              paste(years), collapse = " "))}
+                                              paste(years, collapse = " ")))}
 
   ### Get url
   file_url <- paste0("https://github.com/ipeaGIT/censobr/releases/download/",

diff --git a/R/read_families.R b/R/read_families.R
@@ -4,7 +4,7 @@
 #' Download microdata of family records from Brazil's census. Data collected in
 #' the sample component of the questionnaire.
 #'
-#' @param year Numeric. Year of reference in the format `yyyymm`. Defaults to `2000`.
+#' @param year Numeric. Year of reference in the format `yyyy`. Defaults to `2000`.
 #' @template columns
 #' @template add_labels
 #' @template as_data_frame
@@ -36,7 +36,7 @@ read_families <- function(year = 2000,
   # data available for the years:
   years <- c(2000)
   if (isFALSE(year %in% years)) { stop(paste0("Error: Data currently only available for the years ",
-                                              paste(years), collapse = " "))}
+                                              paste(years, collapse = " ")))}
 
   ### Get url
   file_url <- paste0("https://github.com/ipeaGIT/censobr/releases/download/",

diff --git a/R/read_households.R b/R/read_households.R
@@ -36,7 +36,7 @@ read_households <- function(year = 2010,
   # data available for the years:
   years <- c(1970, 1980, 1991, 2000, 2010)
   if (isFALSE(year %in% years)) { stop(paste0("Error: Data currently only available for the years ",
-                                              paste(years), collapse = " "))}
+                                              paste(years, collapse = " ")))}
 
   ### Get url
   file_url <- paste0("https://github.com/ipeaGIT/censobr/releases/download/",

diff --git a/R/read_mortality.R b/R/read_mortality.R
@@ -31,11 +31,11 @@
 #' # dplyr::glimpse(df)
 #'
 read_mortality <- function(year = 2010,
-                        columns = NULL,
-                        add_labels = NULL,
-                        as_data_frame = FALSE,
-                        showProgress = TRUE,
-                        cache = TRUE){
+                           columns = NULL,
+                           add_labels = NULL,
+                           as_data_frame = FALSE,
+                           showProgress = TRUE,
+                           cache = TRUE){
 
   ### check inputs
   checkmate::assert_numeric(year)
@@ -46,12 +46,12 @@ read_mortality <- function(year = 2010,
   # available for the years:
   years <- c(2010)
   if (isFALSE(year %in% years)) { stop(paste0("Error: Data currently only available for the years ",
-                                              paste(years), collapse = " "))
+                                              paste(years, collapse = " ")))
       }
 
   ### Get url
   file_url <- paste0("https://github.com/ipeaGIT/censobr/releases/download/",
-                     censobr_env$data_release, "/", year, "_deaths_",
+                     censobr_env$data_release, "/", year, "_mortality_",
                      censobr_env$data_release, ".parquet")
 
 

diff --git a/R/read_population.R b/R/read_population.R
@@ -36,7 +36,7 @@ read_population <- function(year = 2010,
   # data available for the years:
   years <- c(1970, 1980, 1991, 2000, 2010)
   if (isFALSE(year %in% years)) { stop(paste0("Error: Data currently only available for the years ",
-                                             paste(years), collapse = " "))}
+                                             paste(years, collapse = " ")))}
 
   ### Get url
   file_url <- paste0("https://github.com/ipeaGIT/censobr/releases/download/",

diff --git a/R/read_tracts.R b/R/read_tracts.R
@@ -5,7 +5,7 @@
 #'
 #' @template year
 #' @param dataset Character. The dataset to be opened. Options currently include
-#'        `c("Basico", "Domicilio", "DomicilioRenda", "Entorno", "ResponsavelRenda", "Responsavel", "PessoaRenda")`.
+#'        `c("Basico", "Domicilio", "DomicilioRenda", "Responsavel", "ResponsavelRenda", "Pessoa", "PessoaRenda",  "Entorno")`.
 #' @template as_data_frame
 #' @template showProgress
 #' @template cache
@@ -41,7 +41,7 @@ read_tracts <- function(year = 2010,
   # data available for the years:
   years <- c(2010)
   if (isFALSE(year %in% years)) { stop(paste0("Error: Data currently only available for the years ",
-                                              paste(years), collapse = " "))}
+                                              paste(years, collapse = " ")))}
 
   # data available for data sets:
   data_sets <- c("Basico", "Domicilio", "DomicilioRenda", "Entorno",

diff --git a/README.md b/README.md
@@ -7,10 +7,7 @@
 coverage](https://codecov.io/gh/ipeaGIT/censobr/branch/main/graph/badge.svg)](https://app.codecov.io/gh/ipeaGIT/censobr?branch=main)
 [![Lifecycle:
      maturing](https://img.shields.io/badge/lifecycle-maturing-yellow.svg)](https://lifecycle.r-lib.org/articles/stages.html)
-
-[![R-CMD-check-main](https://github.com/ipeaGIT/censobr/workflows/R-CMD-check-main/badge.svg)](https://github.com/ipeaGIT/censobr/actions)
-[![R-CMD-check-dev](https://github.com/ipeaGIT/censobr/workflows/R-CMD-check-dev/badge.svg)](https://github.com/ipeaGIT/censobr/actions)
-
+[![R-CMD-check](https://github.com/ipeaGIT/censobr/actions/workflows/R-CMD-check.yaml/badge.svg?branch=main)](https://github.com/ipeaGIT/censobr/actions?query=branch%3Amain)
 
 **censobr** is an R package to download data from Brazil's Population Census. The package is built on top of the [Arrow platform](https://arrow.apache.org/docs/r/), which allows users to work with larger-than-memory census data using [{dplyr} familiar functions](https://arrow.apache.org/docs/r/articles/arrow.html#analyzing-arrow-data-with-dplyr).
 
@@ -118,10 +115,7 @@ bibentry(
 )
 
 ```
-::: {.pkgdown-devel}
-tests only on dev branch
-`2+2`
-:::
+